diff options
889 files changed, 29398 insertions, 12518 deletions
@@ -69,6 +69,7 @@ Jean Tourrilhes <jt@hpl.hp.com> Jeff Garzik <jgarzik@pretzel.yyz.us> Jens Axboe <axboe@suse.de> Jens Osterkamp <Jens.Osterkamp@de.ibm.com> +John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> John Stultz <johnstul@us.ibm.com> <josh@joshtriplett.org> <josh@freedesktop.org> <josh@joshtriplett.org> <josh@kernel.org> diff --git a/Documentation/RCU/Design/Data-Structures/BigTreeClassicRCU.svg b/Documentation/RCU/Design/Data-Structures/BigTreeClassicRCU.svg new file mode 100644 index 0000000..727e270 --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/BigTreeClassicRCU.svg @@ -0,0 +1,474 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:28:20 2015 --> + +<!-- Magnification: 3.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="9.1in" + height="8.9in" + viewBox="-66 -66 10932 10707" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="BigTreeClassicRCU.fig"> + <metadata + id="metadata106"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title></dc:title> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs104"> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow1Mend" + style="overflow:visible;"> + <path + id="path3864" + d="M 0.0,0.0 L 5.0,-5.0 L -12.5,0.0 L 5.0,5.0 L 0.0,0.0 z " + style="fill-rule:evenodd;stroke:#000000;stroke-width:1.0pt;" + transform="scale(0.4) rotate(180) translate(10,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="973" + inkscape:window-height="1137" + id="namedview102" + showgrid="false" + inkscape:zoom="0.9743589" + inkscape:cx="409.50003" + inkscape:cy="400.49997" + inkscape:window-x="915" + inkscape:window-y="24" + inkscape:window-maximized="0" + inkscape:current-layer="g4" /> + <g + style="stroke-width:.025in; fill:none" + id="g4"> + <!-- Line: box --> + <rect + x="0" + y="0" + width="10800" + height="5625" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect6" /> + <!-- Line: box --> + <rect + x="1125" + y="3600" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect8" /> + <!-- Line: box --> + <rect + x="3825" + y="900" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect10" /> + <!-- Line: box --> + <rect + x="6525" + y="3600" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect12" /> + <!-- Line --> + <polyline + points="3375,6525 3375,5046 " + style="stroke:#00d1d1;stroke-width:44.9934641;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline14" /> + <!-- Arrowhead on XXXpoint 3375 6525 - 3375 4860--> + <!-- Circle --> + <circle + cx="7425" + cy="6075" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle18" /> + <!-- Circle --> + <circle + cx="7875" + cy="6075" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle20" /> + <!-- Circle --> + <circle + cx="8325" + cy="6075" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle22" /> + <!-- Circle --> + <circle + cx="2025" + cy="6075" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle24" /> + <!-- Circle --> + <circle + cx="2475" + cy="6075" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle26" /> + <!-- Circle --> + <circle + cx="2925" + cy="6075" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle28" /> + <!-- Circle --> + <circle + cx="4725" + cy="4275" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle30" /> + <!-- Circle --> + <circle + cx="5175" + cy="4275" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle32" /> + <!-- Circle --> + <circle + cx="5625" + cy="4275" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle34" /> + <!-- Line: box --> + <rect + x="2025" + y="6525" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect36" /> + <!-- Line --> + <polyline + points="2475,3600 3975,2310 " + style="stroke:#00d1d1;stroke-width:44.9934641;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline38" /> + <!-- Arrowhead on XXXpoint 2475 3600 - 4116 2190--> + <!-- Line --> + <polyline + points="7875,3600 6372,2310 " + style="stroke:#00d1d1;stroke-width:44.9934641;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline42" /> + <!-- Arrowhead on XXXpoint 7875 3600 - 6231 2190--> + <!-- Line --> + <polyline + points="6975,8775 6975,5046 " + style="stroke:#00d1d1;stroke-width:44.9934641;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline46" /> + <!-- Arrowhead on XXXpoint 6975 8775 - 6975 4860--> + <!-- Line --> + <polyline + points="1575,8775 1575,5046 " + style="stroke:#00d1d1;stroke-width:44.9934641;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline50" /> + <!-- Arrowhead on XXXpoint 1575 8775 - 1575 4860--> + <!-- Line --> + <polyline + points="8775,6525 8775,5046 " + style="stroke:#00d1d1;stroke-width:44.9934641;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline54" /> + <!-- Arrowhead on XXXpoint 8775 6525 - 8775 4860--> + <!-- Text --> + <text + xml:space="preserve" + x="1575" + y="9225" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text58">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1575" + y="9675" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text60">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="1575" + y="10350" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text62">CPU 0</text> + <!-- Text --> + <text + xml:space="preserve" + x="3375" + y="6975" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text64">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="3375" + y="7425" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text66">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="3375" + y="8100" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text68">CPU 15</text> + <!-- Text --> + <text + xml:space="preserve" + x="6975" + y="9225" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text70">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="6975" + y="9675" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text72">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="6975" + y="10350" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text74">CPU 1007</text> + <!-- Text --> + <text + xml:space="preserve" + x="8730" + y="6930" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text76">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="8730" + y="7380" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text78">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="8730" + y="8055" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text80">CPU 1023</text> + <!-- Text --> + <text + xml:space="preserve" + x="225" + y="450" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="start" + id="text82">struct rcu_state</text> + <!-- Text --> + <text + xml:space="preserve" + x="2475" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text84">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2475" + y="4500" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text86">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="7875" + y="4500" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text88">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="7875" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text90">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5175" + y="1350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text92">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5175" + y="1800" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text94">rcu_node</text> + <!-- Line: box --> + <rect + x="225" + y="8775" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect96" /> + <!-- Line: box --> + <rect + x="5625" + y="8775" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect98" /> + <!-- Line: box --> + <rect + x="7380" + y="6480" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect100" /> + </g> +</svg> diff --git a/Documentation/RCU/Design/Data-Structures/BigTreeClassicRCUBH.svg b/Documentation/RCU/Design/Data-Structures/BigTreeClassicRCUBH.svg new file mode 100644 index 0000000..9bbb194 --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/BigTreeClassicRCUBH.svg @@ -0,0 +1,499 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:26:09 2015 --> + +<!-- Magnification: 2.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="5.7in" + height="6.6in" + viewBox="-44 -44 6838 7888" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="BigTreeClassicRCUBH.fig"> + <metadata + id="metadata110"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title></dc:title> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs108"> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow1Mend" + style="overflow:visible;"> + <path + id="path3868" + d="M 0.0,0.0 L 5.0,-5.0 L -12.5,0.0 L 5.0,5.0 L 0.0,0.0 z " + style="fill-rule:evenodd;stroke:#000000;stroke-width:1.0pt;" + transform="scale(0.4) rotate(180) translate(10,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow2Mend" + style="overflow:visible;"> + <path + id="path3886" + style="fill-rule:evenodd;stroke-width:0.62500000;stroke-linejoin:round;" + d="M 8.7185878,4.0337352 L -2.2072895,0.016013256 L 8.7185884,-4.0017078 C 6.9730900,-1.6296469 6.9831476,1.6157441 8.7185878,4.0337352 z " + transform="scale(0.6) rotate(180) translate(0,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="878" + inkscape:window-height="1148" + id="namedview106" + showgrid="false" + inkscape:zoom="1.3547758" + inkscape:cx="256.5" + inkscape:cy="297" + inkscape:window-x="45" + inkscape:window-y="24" + inkscape:window-maximized="0" + inkscape:current-layer="g4" /> + <g + style="stroke-width:.025in; fill:none" + id="g4"> + <!-- Line: box --> + <rect + x="450" + y="0" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect6" /> + <!-- Line: box --> + <rect + x="4950" + y="4950" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect8" /> + <!-- Line: box --> + <rect + x="750" + y="600" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect10" /> + <!-- Line: box --> + <rect + x="0" + y="450" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect12" /> + <!-- Line: box --> + <rect + x="300" + y="1050" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect14" /> + <!-- Circle --> + <circle + cx="2850" + cy="3900" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle16" /> + <!-- Circle --> + <circle + cx="3150" + cy="3900" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle18" /> + <!-- Circle --> + <circle + cx="3450" + cy="3900" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle20" /> + <!-- Circle --> + <circle + cx="1350" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle22" /> + <!-- Circle --> + <circle + cx="1650" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle24" /> + <!-- Circle --> + <circle + cx="1950" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle26" /> + <!-- Circle --> + <circle + cx="4350" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle28" /> + <!-- Circle --> + <circle + cx="4650" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle30" /> + <!-- Circle --> + <circle + cx="4950" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle32" /> + <!-- Line --> + <polyline + points="1350,3450 2350,2590 " + style="stroke:#00d1d1;stroke-width:30.0045575;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline34" /> + <!-- Arrowhead on XXXpoint 1350 3450 - 2444 2510--> + <!-- Line --> + <polyline + points="4950,3450 3948,2590 " + style="stroke:#00d1d1;stroke-width:30.0045575;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline38" /> + <!-- Arrowhead on XXXpoint 4950 3450 - 3854 2510--> + <!-- Line: box --> + <rect + x="750" + y="3450" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect42" /> + <!-- Line --> + <polyline + points="2250,5400 2250,4414 " + style="stroke:#00d1d1;stroke-width:30.0045575;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline44" /> + <!-- Arrowhead on XXXpoint 2250 5400 - 2250 4290--> + <!-- Line: box --> + <rect + x="1500" + y="5400" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect48" /> + <!-- Line: box --> + <rect + x="300" + y="6600" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect50" /> + <!-- Line: box --> + <rect + x="3750" + y="3450" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect52" /> + <!-- Line: box --> + <rect + x="4500" + y="5400" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect54" /> + <!-- Line: box --> + <rect + x="3300" + y="6600" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect56" /> + <!-- Line: box --> + <rect + x="2250" + y="1650" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect58" /> + <!-- Text --> + <text + xml:space="preserve" + x="6450" + y="300" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text60">rcu_bh</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="1950" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text62">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="2250" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text64">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="1650" + y="3750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text66">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1650" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text68">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="4650" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text70">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="4650" + y="3750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text72">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="5700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text74">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="6000" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text76">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="6900" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text78">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text80">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="5250" + y="5700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text82">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5250" + y="6000" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text84">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="6900" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text86">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text88">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="450" + y="1350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="start" + id="text90">struct rcu_state</text> + <!-- Text --> + <text + xml:space="preserve" + x="6000" + y="750" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text92">rcu_sched</text> + <!-- Line --> + <polyline + points="5250,5400 5250,4414 " + style="stroke:#00d1d1;stroke-width:30.0045575;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline94" /> + <!-- Arrowhead on XXXpoint 5250 5400 - 5250 4290--> + <!-- Line --> + <polyline + points="4050,6600 4050,4414 " + style="stroke:#00d1d1;stroke-width:30.0045575;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline98" /> + <!-- Arrowhead on XXXpoint 4050 6600 - 4050 4290--> + <!-- Line --> + <polyline + points="1050,6600 1050,4414 " + style="stroke:#00d1d1;stroke-width:30.0045575;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline102" /> + <!-- Arrowhead on XXXpoint 1050 6600 - 1050 4290--> + </g> +</svg> diff --git a/Documentation/RCU/Design/Data-Structures/BigTreeClassicRCUBHdyntick.svg b/Documentation/RCU/Design/Data-Structures/BigTreeClassicRCUBHdyntick.svg new file mode 100644 index 0000000..21ba782 --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/BigTreeClassicRCUBHdyntick.svg @@ -0,0 +1,695 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:20:02 2015 --> + +<!-- Magnification: 2.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="5.7in" + height="8.6in" + viewBox="-44 -44 6838 10288" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="BigTreeClassicRCUBHdyntick.fig"> + <metadata + id="metadata166"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title></dc:title> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs164"> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow1Mend" + style="overflow:visible;"> + <path + id="path3924" + d="M 0.0,0.0 L 5.0,-5.0 L -12.5,0.0 L 5.0,5.0 L 0.0,0.0 z " + style="fill-rule:evenodd;stroke:#000000;stroke-width:1.0pt;" + transform="scale(0.4) rotate(180) translate(10,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow2Lend" + style="overflow:visible;"> + <path + id="path3936" + style="fill-rule:evenodd;stroke-width:0.62500000;stroke-linejoin:round;" + d="M 8.7185878,4.0337352 L -2.2072895,0.016013256 L 8.7185884,-4.0017078 C 6.9730900,-1.6296469 6.9831476,1.6157441 8.7185878,4.0337352 z " + transform="scale(1.1) rotate(180) translate(1,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="845" + inkscape:window-height="988" + id="namedview162" + showgrid="false" + inkscape:zoom="1.0452196" + inkscape:cx="256.5" + inkscape:cy="387.00003" + inkscape:window-x="356" + inkscape:window-y="61" + inkscape:window-maximized="0" + inkscape:current-layer="g4" /> + <g + style="stroke-width:.025in; fill:none" + id="g4"> + <!-- Line: box --> + <rect + x="450" + y="0" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect6" /> + <!-- Line: box --> + <rect + x="4950" + y="4950" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect8" /> + <!-- Line: box --> + <rect + x="750" + y="600" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect10" /> + <!-- Line --> + <polyline + points="5250,8100 5688,5912 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline12" /> + <!-- Arrowhead on XXXpoint 5250 8100 - 5710 5790--> + <polyline + points="5714 6068 5704 5822 5598 6044 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline14" /> + <!-- Line --> + <polyline + points="4050,9300 4486,7262 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline16" /> + <!-- Arrowhead on XXXpoint 4050 9300 - 4512 7140--> + <polyline + points="4514 7418 4506 7172 4396 7394 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline18" /> + <!-- Line --> + <polyline + points="1040,9300 1476,7262 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline20" /> + <!-- Arrowhead on XXXpoint 1040 9300 - 1502 7140--> + <polyline + points="1504 7418 1496 7172 1386 7394 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline22" /> + <!-- Line --> + <polyline + points="2240,8100 2676,6062 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline24" /> + <!-- Arrowhead on XXXpoint 2240 8100 - 2702 5940--> + <polyline + points="2704 6218 2696 5972 2586 6194 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline26" /> + <!-- Line: box --> + <rect + x="0" + y="450" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect28" /> + <!-- Line: box --> + <rect + x="300" + y="1050" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect30" /> + <!-- Line --> + <polyline + points="1350,3450 2350,2590 " + style="stroke:#00d1d1;stroke-width:30.0045575;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline32" /> + <!-- Arrowhead on XXXpoint 1350 3450 - 2444 2510--> + <!-- Line --> + <polyline + points="4950,3450 3948,2590 " + style="stroke:#00d1d1;stroke-width:30.0045575;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline36" /> + <!-- Arrowhead on XXXpoint 4950 3450 - 3854 2510--> + <!-- Line --> + <polyline + points="4050,6600 4050,4414 " + style="stroke:#00d1d1;stroke-width:30.00455750000000066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline40" /> + <!-- Arrowhead on XXXpoint 4050 6600 - 4050 4290--> + <!-- Line --> + <polyline + points="1050,6600 1050,4414 " + style="stroke:#00d1d1;stroke-width:30.00455750000000066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline44" /> + <!-- Arrowhead on XXXpoint 1050 6600 - 1050 4290--> + <!-- Line --> + <polyline + points="2250,5400 2250,4414 " + style="stroke:#00d1d1;stroke-width:30.00455750000000066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline48" /> + <!-- Arrowhead on XXXpoint 2250 5400 - 2250 4290--> + <!-- Line --> + <polyline + points="2250,8100 2250,6364 " + style="stroke:#00ff00;stroke-width:30;stroke-linejoin:miter;stroke-linecap:butt;marker-end:url(#Arrow1Mend)" + id="polyline52" /> + <!-- Arrowhead on XXXpoint 2250 8100 - 2250 6240--> + <!-- Line --> + <polyline + points="1050,9300 1050,7564 " + style="stroke:#00ff00;stroke-width:30;stroke-linejoin:miter;stroke-linecap:butt;marker-end:url(#Arrow1Mend)" + id="polyline56" /> + <!-- Arrowhead on XXXpoint 1050 9300 - 1050 7440--> + <!-- Line --> + <polyline + points="4050,9300 4050,7564 " + style="stroke:#00ff00;stroke-width:30;stroke-linejoin:miter;stroke-linecap:butt;marker-end:url(#Arrow1Mend)" + id="polyline60" /> + <!-- Arrowhead on XXXpoint 4050 9300 - 4050 7440--> + <!-- Line --> + <polyline + points="5250,8100 5250,6364 " + style="stroke:#00ff00;stroke-width:30;stroke-linejoin:miter;stroke-linecap:butt;marker-end:url(#Arrow1Mend)" + id="polyline64" /> + <!-- Arrowhead on XXXpoint 5250 8100 - 5250 6240--> + <!-- Circle --> + <circle + cx="2850" + cy="3900" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle68" /> + <!-- Circle --> + <circle + cx="3150" + cy="3900" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle70" /> + <!-- Circle --> + <circle + cx="3450" + cy="3900" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle72" /> + <!-- Circle --> + <circle + cx="1350" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle74" /> + <!-- Circle --> + <circle + cx="1650" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle76" /> + <!-- Circle --> + <circle + cx="1950" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle78" /> + <!-- Circle --> + <circle + cx="4350" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle80" /> + <!-- Circle --> + <circle + cx="4650" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle82" /> + <!-- Circle --> + <circle + cx="4950" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle84" /> + <!-- Line: box --> + <rect + x="750" + y="3450" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect86" /> + <!-- Line: box --> + <rect + x="300" + y="6600" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect88" /> + <!-- Line: box --> + <rect + x="3750" + y="3450" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect90" /> + <!-- Line: box --> + <rect + x="4500" + y="5400" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect92" /> + <!-- Line: box --> + <rect + x="3300" + y="6600" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect94" /> + <!-- Line: box --> + <rect + x="2250" + y="1650" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect96" /> + <!-- Line: box --> + <rect + x="0" + y="9300" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect98" /> + <!-- Line: box --> + <rect + x="1350" + y="8100" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect100" /> + <!-- Line: box --> + <rect + x="3000" + y="9300" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect102" /> + <!-- Line: box --> + <rect + x="4350" + y="8100" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect104" /> + <!-- Line: box --> + <rect + x="1500" + y="5400" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect106" /> + <!-- Text --> + <text + xml:space="preserve" + x="6450" + y="300" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text108">rcu_bh</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="1950" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text110">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="2250" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text112">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="1650" + y="3750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text114">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1650" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text116">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="4650" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text118">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="4650" + y="3750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text120">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="5700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text122">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="6000" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text124">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="6900" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text126">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text128">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="5250" + y="5700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text130">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5250" + y="6000" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text132">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="6900" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text134">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text136">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="450" + y="1350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="start" + id="text138">struct rcu_state</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="9600" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text140">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="9900" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text142">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="9600" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text144">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="9900" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text146">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="2400" + y="8400" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text148">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2400" + y="8700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text150">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="5400" + y="8400" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text152">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5400" + y="8700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text154">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="6000" + y="750" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text156">rcu_sched</text> + <!-- Line --> + <polyline + points="5250,5400 5250,4414 " + style="stroke:#00d1d1;stroke-width:30.00455750000000066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline158" /> + <!-- Arrowhead on XXXpoint 5250 5400 - 5250 4290--> + </g> +</svg> diff --git a/Documentation/RCU/Design/Data-Structures/BigTreePreemptRCUBHdyntick.svg b/Documentation/RCU/Design/Data-Structures/BigTreePreemptRCUBHdyntick.svg new file mode 100644 index 0000000..15adcac --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/BigTreePreemptRCUBHdyntick.svg @@ -0,0 +1,741 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:32:59 2015 --> + +<!-- Magnification: 2.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="6.1in" + height="8.9in" + viewBox="-44 -44 7288 10738" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="BigTreePreemptRCUBHdyntick.fig"> + <metadata + id="metadata182"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title></dc:title> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs180"> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow1Mend" + style="overflow:visible;"> + <path + id="path3940" + d="M 0.0,0.0 L 5.0,-5.0 L -12.5,0.0 L 5.0,5.0 L 0.0,0.0 z " + style="fill-rule:evenodd;stroke:#000000;stroke-width:1.0pt;" + transform="scale(0.4) rotate(180) translate(10,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="874" + inkscape:window-height="1148" + id="namedview178" + showgrid="false" + inkscape:zoom="1.2097379" + inkscape:cx="274.5" + inkscape:cy="400.49997" + inkscape:window-x="946" + inkscape:window-y="24" + inkscape:window-maximized="0" + inkscape:current-layer="g4" /> + <g + style="stroke-width:.025in; fill:none" + id="g4"> + <!-- Line: box --> + <rect + x="900" + y="0" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect6" /> + <!-- Line: box --> + <rect + x="1200" + y="600" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect8" /> + <!-- Line: box --> + <rect + x="5400" + y="4950" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect10" /> + <!-- Line: box --> + <rect + x="450" + y="450" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect12" /> + <!-- Line: box --> + <rect + x="750" + y="1050" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect14" /> + <!-- Line: box --> + <rect + x="4950" + y="5400" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect16" /> + <!-- Line --> + <polyline + points="5250,8550 5688,6362 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline18" /> + <!-- Arrowhead on XXXpoint 5250 8550 - 5710 6240--> + <polyline + points="5714 6518 5704 6272 5598 6494 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline20" /> + <!-- Line --> + <polyline + points="4050,9750 4486,7712 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline22" /> + <!-- Arrowhead on XXXpoint 4050 9750 - 4512 7590--> + <polyline + points="4514 7868 4506 7622 4396 7844 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline24" /> + <!-- Line --> + <polyline + points="1040,9750 1476,7712 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline26" /> + <!-- Arrowhead on XXXpoint 1040 9750 - 1502 7590--> + <polyline + points="1504 7868 1496 7622 1386 7844 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline28" /> + <!-- Line --> + <polyline + points="2240,8550 2676,6512 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline30" /> + <!-- Arrowhead on XXXpoint 2240 8550 - 2702 6390--> + <polyline + points="2704 6668 2696 6422 2586 6644 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline32" /> + <!-- Line --> + <polyline + points="4050,9750 5682,6360 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline34" /> + <!-- Arrowhead on XXXpoint 4050 9750 - 5736 6246--> + <polyline + points="5672 6518 5722 6276 5562 6466 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline36" /> + <!-- Line --> + <polyline + points="1010,9750 2642,6360 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline38" /> + <!-- Arrowhead on XXXpoint 1010 9750 - 2696 6246--> + <polyline + points="2632 6518 2682 6276 2522 6466 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline40" /> + <!-- Line: box --> + <rect + x="0" + y="900" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect42" /> + <!-- Line: box --> + <rect + x="300" + y="1500" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect44" /> + <!-- Line --> + <polyline + points="1350,3900 2350,3040 " + style="stroke:#00d1d1;stroke-width:30.00205472;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline46" /> + <!-- Arrowhead on XXXpoint 1350 3900 - 2444 2960--> + <!-- Line --> + <polyline + points="4950,3900 3948,3040 " + style="stroke:#00d1d1;stroke-width:30.00205472;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline50" /> + <!-- Arrowhead on XXXpoint 4950 3900 - 3854 2960--> + <!-- Line --> + <polyline + points="4050,7050 4050,4864 " + style="stroke:#00d1d1;stroke-width:30.00205472;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline54" /> + <!-- Arrowhead on XXXpoint 4050 7050 - 4050 4740--> + <!-- Line --> + <polyline + points="1050,7050 1050,4864 " + style="stroke:#00d1d1;stroke-width:30.00205472;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline58" /> + <!-- Arrowhead on XXXpoint 1050 7050 - 1050 4740--> + <!-- Line --> + <polyline + points="2250,5850 2250,4864 " + style="stroke:#00d1d1;stroke-width:30.00205472;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline62" /> + <!-- Arrowhead on XXXpoint 2250 5850 - 2250 4740--> + <!-- Line --> + <polyline + points="2250,8550 2250,6814 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline66" /> + <!-- Arrowhead on XXXpoint 2250 8550 - 2250 6690--> + <!-- Line --> + <polyline + points="1050,9750 1050,8014 " + style="stroke:#00ff00;stroke-width:30.00205472;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline70" /> + <!-- Arrowhead on XXXpoint 1050 9750 - 1050 7890--> + <!-- Line --> + <polyline + points="4050,9750 4050,8014 " + style="stroke:#00ff00;stroke-width:30.00205472;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline74" /> + <!-- Arrowhead on XXXpoint 4050 9750 - 4050 7890--> + <!-- Line --> + <polyline + points="5250,8550 5250,6814 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline78" /> + <!-- Arrowhead on XXXpoint 5250 8550 - 5250 6690--> + <!-- Circle --> + <circle + cx="2850" + cy="4350" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle82" /> + <!-- Circle --> + <circle + cx="3150" + cy="4350" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle84" /> + <!-- Circle --> + <circle + cx="3450" + cy="4350" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle86" /> + <!-- Circle --> + <circle + cx="1350" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle88" /> + <!-- Circle --> + <circle + cx="1650" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle90" /> + <!-- Circle --> + <circle + cx="1950" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle92" /> + <!-- Circle --> + <circle + cx="4350" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle94" /> + <!-- Circle --> + <circle + cx="4650" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle96" /> + <!-- Circle --> + <circle + cx="4950" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle98" /> + <!-- Line: box --> + <rect + x="750" + y="3900" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect100" /> + <!-- Line: box --> + <rect + x="300" + y="7050" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect102" /> + <!-- Line: box --> + <rect + x="3750" + y="3900" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect104" /> + <!-- Line: box --> + <rect + x="4500" + y="5850" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect106" /> + <!-- Line: box --> + <rect + x="3300" + y="7050" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect108" /> + <!-- Line: box --> + <rect + x="2250" + y="2100" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect110" /> + <!-- Line: box --> + <rect + x="0" + y="9750" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect112" /> + <!-- Line: box --> + <rect + x="1350" + y="8550" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect114" /> + <!-- Line: box --> + <rect + x="3000" + y="9750" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect116" /> + <!-- Line: box --> + <rect + x="4350" + y="8550" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect118" /> + <!-- Line: box --> + <rect + x="1500" + y="5850" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect120" /> + <!-- Text --> + <text + xml:space="preserve" + x="6450" + y="750" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text122">rcu_bh</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="2400" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text124">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="2700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text126">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="1650" + y="4200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text128">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1650" + y="4500" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text130">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="4650" + y="4500" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text132">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="4650" + y="4200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text134">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="6150" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text136">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="6450" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text138">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="7350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text140">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="7650" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text142">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="5250" + y="6150" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text144">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5250" + y="6450" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text146">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="7350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text148">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="7650" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text150">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="450" + y="1800" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="start" + id="text152">struct rcu_state</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="10050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text154">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="10350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text156">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="10050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text158">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="10350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text160">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="2400" + y="8850" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text162">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2400" + y="9150" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text164">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="5400" + y="8850" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text166">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5400" + y="9150" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text168">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="6900" + y="300" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text170">rcu_preempt</text> + <!-- Text --> + <text + xml:space="preserve" + x="6000" + y="1200" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text172">rcu_sched</text> + <!-- Line --> + <polyline + points="5250,5850 5250,4864 " + style="stroke:#00d1d1;stroke-width:30.00205472;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline174" /> + <!-- Arrowhead on XXXpoint 5250 5850 - 5250 4740--> + </g> +</svg> diff --git a/Documentation/RCU/Design/Data-Structures/BigTreePreemptRCUBHdyntickCB.svg b/Documentation/RCU/Design/Data-Structures/BigTreePreemptRCUBHdyntickCB.svg new file mode 100644 index 0000000..bbc3801 --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/BigTreePreemptRCUBHdyntickCB.svg @@ -0,0 +1,858 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:29:48 2015 --> + +<!-- Magnification: 2.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="7.4in" + height="9.9in" + viewBox="-44 -44 8938 11938" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="BigTreePreemptRCUBHdyntickCB.svg"> + <metadata + id="metadata212"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title></dc:title> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs210"> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow1Mend" + style="overflow:visible;"> + <path + id="path3970" + d="M 0.0,0.0 L 5.0,-5.0 L -12.5,0.0 L 5.0,5.0 L 0.0,0.0 z " + style="fill-rule:evenodd;stroke:#000000;stroke-width:1.0pt;" + transform="scale(0.4) rotate(180) translate(10,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="881" + inkscape:window-height="1128" + id="namedview208" + showgrid="false" + inkscape:zoom="1.0195195" + inkscape:cx="333" + inkscape:cy="445.49997" + inkscape:window-x="936" + inkscape:window-y="24" + inkscape:window-maximized="0" + inkscape:current-layer="g4" /> + <g + style="stroke-width:.025in; fill:none" + id="g4"> + <!-- Line: box --> + <rect + x="900" + y="0" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect6" /> + <!-- Line: box --> + <rect + x="1200" + y="600" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect8" /> + <!-- Line: box --> + <rect + x="5400" + y="4950" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect10" /> + <!-- Line: box --> + <rect + x="450" + y="450" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect12" /> + <!-- Line: box --> + <rect + x="750" + y="1050" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect14" /> + <!-- Line: box --> + <rect + x="4950" + y="5400" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect16" /> + <!-- Line --> + <polyline + points="5250,8550 5688,6362 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline18" /> + <!-- Arrowhead on XXXpoint 5250 8550 - 5710 6240--> + <polyline + points="5714 6518 5704 6272 5598 6494 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline20" /> + <!-- Line --> + <polyline + points="4050,9750 4486,7712 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline22" /> + <!-- Arrowhead on XXXpoint 4050 9750 - 4512 7590--> + <polyline + points="4514 7868 4506 7622 4396 7844 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline24" /> + <!-- Line --> + <polyline + points="1040,9750 1476,7712 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline26" /> + <!-- Arrowhead on XXXpoint 1040 9750 - 1502 7590--> + <polyline + points="1504 7868 1496 7622 1386 7844 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline28" /> + <!-- Line --> + <polyline + points="2240,8550 2676,6512 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline30" /> + <!-- Arrowhead on XXXpoint 2240 8550 - 2702 6390--> + <polyline + points="2704 6668 2696 6422 2586 6644 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline32" /> + <!-- Line --> + <polyline + points="4050,9600 5692,6062 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline34" /> + <!-- Arrowhead on XXXpoint 4050 9600 - 5744 5948--> + <polyline + points="5682 6220 5730 5978 5574 6170 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline36" /> + <!-- Line --> + <polyline + points="1086,9600 2728,6062 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline38" /> + <!-- Arrowhead on XXXpoint 1086 9600 - 2780 5948--> + <polyline + points="2718 6220 2766 5978 2610 6170 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline40" /> + <!-- Line: box --> + <rect + x="0" + y="900" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect42" /> + <!-- Line: box --> + <rect + x="300" + y="1500" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect44" /> + <!-- Line --> + <polyline + points="1350,3900 2350,3040 " + style="stroke:#00d1d1;stroke-width:29.99463964;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline46" /> + <!-- Arrowhead on XXXpoint 1350 3900 - 2444 2960--> + <!-- Line --> + <polyline + points="4950,3900 3948,3040 " + style="stroke:#00d1d1;stroke-width:29.99463964;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline50" /> + <!-- Arrowhead on XXXpoint 4950 3900 - 3854 2960--> + <!-- Line --> + <polyline + points="4050,7050 4050,4864 " + style="stroke:#00d1d1;stroke-width:29.99463964;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline54" /> + <!-- Arrowhead on XXXpoint 4050 7050 - 4050 4740--> + <!-- Line --> + <polyline + points="1050,7050 1050,4864 " + style="stroke:#00d1d1;stroke-width:29.99463964;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline58" /> + <!-- Arrowhead on XXXpoint 1050 7050 - 1050 4740--> + <!-- Line --> + <polyline + points="2250,5850 2250,4864 " + style="stroke:#00d1d1;stroke-width:29.99463964;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline62" /> + <!-- Arrowhead on XXXpoint 2250 5850 - 2250 4740--> + <!-- Line --> + <polyline + points="2250,8550 2250,6814 " + style="stroke:#00ff00;stroke-width:29.99463964;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline66" /> + <!-- Arrowhead on XXXpoint 2250 8550 - 2250 6690--> + <!-- Line --> + <polyline + points="1050,9750 1050,8014 " + style="stroke:#00ff00;stroke-width:29.99463964;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline70" /> + <!-- Arrowhead on XXXpoint 1050 9750 - 1050 7890--> + <!-- Line --> + <polyline + points="4050,9750 4050,8014 " + style="stroke:#00ff00;stroke-width:29.99463964;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline74" /> + <!-- Arrowhead on XXXpoint 4050 9750 - 4050 7890--> + <!-- Line --> + <polyline + points="5250,8550 5250,6814 " + style="stroke:#00ff00;stroke-width:29.99463964;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline78" /> + <!-- Arrowhead on XXXpoint 5250 8550 - 5250 6690--> + <!-- Line --> + <polyline + points="6000,6300 8048,7910 " + style="stroke:#87cfff;stroke-width:30;stroke-linejoin:miter;stroke-linecap:butt;marker-end:url(#Arrow1Mend)" + id="polyline82" /> + <!-- Arrowhead on XXXpoint 6000 6300 - 8146 7986--> + <!-- Circle --> + <circle + cx="2850" + cy="4350" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle86" /> + <!-- Circle --> + <circle + cx="3150" + cy="4350" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle88" /> + <!-- Circle --> + <circle + cx="3450" + cy="4350" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle90" /> + <!-- Circle --> + <circle + cx="1350" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle92" /> + <!-- Circle --> + <circle + cx="1650" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle94" /> + <!-- Circle --> + <circle + cx="1950" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle96" /> + <!-- Circle --> + <circle + cx="4350" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle98" /> + <!-- Circle --> + <circle + cx="4650" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle100" /> + <!-- Circle --> + <circle + cx="4950" + cy="5550" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle102" /> + <!-- Line: box --> + <rect + x="7350" + y="7950" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect104" /> + <!-- Line: box --> + <rect + x="7350" + y="9450" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect106" /> + <!-- Line --> + <polyline + points="8100,8850 8100,9384 " + style="stroke:#000000;stroke-width:30;stroke-linejoin:miter;stroke-linecap:butt;marker-end:url(#Arrow1Mend)" + id="polyline108" /> + <!-- Arrowhead on XXXpoint 8100 8850 - 8100 9510--> + <!-- Line: box --> + <rect + x="7350" + y="10950" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect112" /> + <!-- Line --> + <polyline + points="8100,10350 8100,10884 " + style="stroke:#000000;stroke-width:30;stroke-linejoin:miter;stroke-linecap:butt;marker-end:url(#Arrow1Mend)" + id="polyline114" /> + <!-- Arrowhead on XXXpoint 8100 10350 - 8100 11010--> + <!-- Line: box --> + <rect + x="750" + y="3900" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect118" /> + <!-- Line: box --> + <rect + x="300" + y="7050" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect120" /> + <!-- Line: box --> + <rect + x="3750" + y="3900" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect122" /> + <!-- Line: box --> + <rect + x="4500" + y="5850" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect124" /> + <!-- Line: box --> + <rect + x="3300" + y="7050" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect126" /> + <!-- Line: box --> + <rect + x="2250" + y="2100" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect128" /> + <!-- Line: box --> + <rect + x="0" + y="9750" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect130" /> + <!-- Line: box --> + <rect + x="1350" + y="8550" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect132" /> + <!-- Line: box --> + <rect + x="3000" + y="9750" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect134" /> + <!-- Line: box --> + <rect + x="4350" + y="8550" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect136" /> + <!-- Line: box --> + <rect + x="1500" + y="5850" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect138" /> + <!-- Text --> + <text + xml:space="preserve" + x="8100" + y="8250" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text140">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="8100" + y="8550" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text142">rcu_head</text> + <!-- Text --> + <text + xml:space="preserve" + x="8100" + y="9750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text144">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="8100" + y="10050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text146">rcu_head</text> + <!-- Text --> + <text + xml:space="preserve" + x="8100" + y="11250" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text148">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="8100" + y="11550" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text150">rcu_head</text> + <!-- Text --> + <text + xml:space="preserve" + x="6000" + y="1200" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text152">rcu_sched</text> + <!-- Text --> + <text + xml:space="preserve" + x="6450" + y="750" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text154">rcu_bh</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="2400" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text156">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="2700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text158">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="1650" + y="4200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text160">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1650" + y="4500" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text162">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="4650" + y="4500" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text164">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="4650" + y="4200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text166">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="6150" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text168">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="6450" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text170">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="7350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text172">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="7650" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text174">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="5250" + y="6150" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text176">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5250" + y="6450" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text178">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="7350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text180">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="7650" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text182">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="450" + y="1800" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="start" + id="text184">struct rcu_state</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="10050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text186">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="10350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text188">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="10050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text190">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="10350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text192">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="2400" + y="8850" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text194">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2400" + y="9150" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text196">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="5400" + y="8850" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text198">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5400" + y="9150" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text200">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="6900" + y="300" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text202">rcu_preempt</text> + <!-- Line --> + <polyline + points="5250,5850 5250,4864 " + style="stroke:#00d1d1;stroke-width:29.99463964;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline204" /> + <!-- Arrowhead on XXXpoint 5250 5850 - 5250 4740--> + </g> +</svg> diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html new file mode 100644 index 0000000..7eb47ac --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html @@ -0,0 +1,1333 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" + "http://www.w3.org/TR/html4/loose.dtd"> + <html> + <head><title>A Tour Through TREE_RCU's Data Structures [LWN.net]</title> + <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1"> + + <p>January 27, 2016</p> + <p>This article was contributed by Paul E. McKenney</p> + +<h3>Introduction</h3> + +This document describes RCU's major data structures and their relationship +to each other. + +<ol> +<li> <a href="#Data-Structure Relationships"> + Data-Structure Relationships</a> +<li> <a href="#The rcu_state Structure"> + The <tt>rcu_state</tt> Structure</a> +<li> <a href="#The rcu_node Structure"> + The <tt>rcu_node</tt> Structure</a> +<li> <a href="#The rcu_data Structure"> + The <tt>rcu_data</tt> Structure</a> +<li> <a href="#The rcu_dynticks Structure"> + The <tt>rcu_dynticks</tt> Structure</a> +<li> <a href="#The rcu_head Structure"> + The <tt>rcu_head</tt> Structure</a> +<li> <a href="#RCU-Specific Fields in the task_struct Structure"> + RCU-Specific Fields in the <tt>task_struct</tt> Structure</a> +<li> <a href="#Accessor Functions"> + Accessor Functions</a> +</ol> + +At the end we have the +<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>. + +<h3><a name="Data-Structure Relationships">Data-Structure Relationships</a></h3> + +<p>RCU is for all intents and purposes a large state machine, and its +data structures maintain the state in such a way as to allow RCU readers +to execute extremely quickly, while also processing the RCU grace periods +requested by updaters in an efficient and extremely scalable fashion. +The efficiency and scalability of RCU updaters is provided primarily +by a combining tree, as shown below: + +</p><p><img src="BigTreeClassicRCU.svg" alt="BigTreeClassicRCU.svg" width="30%"> + +</p><p>This diagram shows an enclosing <tt>rcu_state</tt> structure +containing a tree of <tt>rcu_node</tt> structures. +Each leaf node of the <tt>rcu_node</tt> tree has up to 16 +<tt>rcu_data</tt> structures associated with it, so that there +are <tt>NR_CPUS</tt> number of <tt>rcu_data</tt> structures, +one for each possible CPU. +This structure is adjusted at boot time, if needed, to handle the +common case where <tt>nr_cpu_ids</tt> is much less than +<tt>NR_CPUs</tt>. +For example, a number of Linux distributions set <tt>NR_CPUs=4096</tt>, +which results in a three-level <tt>rcu_node</tt> tree. +If the actual hardware has only 16 CPUs, RCU will adjust itself +at boot time, resulting in an <tt>rcu_node</tt> tree with only a single node. + +</p><p>The purpose of this combining tree is to allow per-CPU events +such as quiescent states, dyntick-idle transitions, +and CPU hotplug operations to be processed efficiently +and scalably. +Quiescent states are recorded by the per-CPU <tt>rcu_data</tt> structures, +and other events are recorded by the leaf-level <tt>rcu_node</tt> +structures. +All of these events are combined at each level of the tree until finally +grace periods are completed at the tree's root <tt>rcu_node</tt> +structure. +A grace period can be completed at the root once every CPU +(or, in the case of <tt>CONFIG_PREEMPT_RCU</tt>, task) +has passed through a quiescent state. +Once a grace period has completed, record of that fact is propagated +back down the tree. + +</p><p>As can be seen from the diagram, on a 64-bit system +a two-level tree with 64 leaves can accommodate 1,024 CPUs, with a fanout +of 64 at the root and a fanout of 16 at the leaves. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Why isn't the fanout at the leaves also 64? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Because there are more types of events that affect the leaf-level + <tt>rcu_node</tt> structures than further up the tree. + Therefore, if the leaf <tt>rcu_node</tt> structures have fanout of + 64, the contention on these structures' <tt>->structures</tt> + becomes excessive. + Experimentation on a wide variety of systems has shown that a fanout + of 16 works well for the leaves of the <tt>rcu_node</tt> tree. + </font> + + <p><font color="ffffff">Of course, further experience with + systems having hundreds or thousands of CPUs may demonstrate + that the fanout for the non-leaf <tt>rcu_node</tt> structures + must also be reduced. + Such reduction can be easily carried out when and if it proves + necessary. + In the meantime, if you are using such a system and running into + contention problems on the non-leaf <tt>rcu_node</tt> structures, + you may use the <tt>CONFIG_RCU_FANOUT</tt> kernel configuration + parameter to reduce the non-leaf fanout as needed. + </font> + + <p><font color="ffffff">Kernels built for systems with + strong NUMA characteristics might also need to adjust + <tt>CONFIG_RCU_FANOUT</tt> so that the domains of the + <tt>rcu_node</tt> structures align with hardware boundaries. + However, there has thus far been no need for this. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<p>If your system has more than 1,024 CPUs (or more than 512 CPUs on +a 32-bit system), then RCU will automatically add more levels to the +tree. +For example, if you are crazy enough to build a 64-bit system with 65,536 +CPUs, RCU would configure the <tt>rcu_node</tt> tree as follows: + +</p><p><img src="HugeTreeClassicRCU.svg" alt="HugeTreeClassicRCU.svg" width="50%"> + +</p><p>RCU currently permits up to a four-level tree, which on a 64-bit system +accommodates up to 4,194,304 CPUs, though only a mere 524,288 CPUs for +32-bit systems. +On the other hand, you can set <tt>CONFIG_RCU_FANOUT</tt> to be +as small as 2 if you wish, which would permit only 16 CPUs, which +is useful for testing. + +</p><p>This multi-level combining tree allows us to get most of the +performance and scalability +benefits of partitioning, even though RCU grace-period detection is +inherently a global operation. +The trick here is that only the last CPU to report a quiescent state +into a given <tt>rcu_node</tt> structure need advance to the <tt>rcu_node</tt> +structure at the next level up the tree. +This means that at the leaf-level <tt>rcu_node</tt> structure, only +one access out of sixteen will progress up the tree. +For the internal <tt>rcu_node</tt> structures, the situation is even +more extreme: Only one access out of sixty-four will progress up +the tree. +Because the vast majority of the CPUs do not progress up the tree, +the lock contention remains roughly constant up the tree. +No matter how many CPUs there are in the system, at most 64 quiescent-state +reports per grace period will progress all the way to the root +<tt>rcu_node</tt> structure, thus ensuring that the lock contention +on that root <tt>rcu_node</tt> structure remains acceptably low. + +</p><p>In effect, the combining tree acts like a big shock absorber, +keeping lock contention under control at all tree levels regardless +of the level of loading on the system. + +</p><p>The Linux kernel actually supports multiple flavors of RCU +running concurrently, so RCU builds separate data structures for each +flavor. +For example, for <tt>CONFIG_TREE_RCU=y</tt> kernels, RCU provides +rcu_sched and rcu_bh, as shown below: + +</p><p><img src="BigTreeClassicRCUBH.svg" alt="BigTreeClassicRCUBH.svg" width="33%"> + +</p><p>Energy efficiency is increasingly important, and for that +reason the Linux kernel provides <tt>CONFIG_NO_HZ_IDLE</tt>, which +turns off the scheduling-clock interrupts on idle CPUs, which in +turn allows those CPUs to attain deeper sleep states and to consume +less energy. +CPUs whose scheduling-clock interrupts have been turned off are +said to be in <i>dyntick-idle mode</i>. +RCU must handle dyntick-idle CPUs specially +because RCU would otherwise wake up each CPU on every grace period, +which would defeat the whole purpose of <tt>CONFIG_NO_HZ_IDLE</tt>. +RCU uses the <tt>rcu_dynticks</tt> structure to track +which CPUs are in dyntick idle mode, as shown below: + +</p><p><img src="BigTreeClassicRCUBHdyntick.svg" alt="BigTreeClassicRCUBHdyntick.svg" width="33%"> + +</p><p>However, if a CPU is in dyntick-idle mode, it is in that mode +for all flavors of RCU. +Therefore, a single <tt>rcu_dynticks</tt> structure is allocated per +CPU, and all of a given CPU's <tt>rcu_data</tt> structures share +that <tt>rcu_dynticks</tt>, as shown in the figure. + +</p><p>Kernels built with <tt>CONFIG_PREEMPT_RCU</tt> support +rcu_preempt in addition to rcu_sched and rcu_bh, as shown below: + +</p><p><img src="BigTreePreemptRCUBHdyntick.svg" alt="BigTreePreemptRCUBHdyntick.svg" width="35%"> + +</p><p>RCU updaters wait for normal grace periods by registering +RCU callbacks, either directly via <tt>call_rcu()</tt> and +friends (namely <tt>call_rcu_bh()</tt> and <tt>call_rcu_sched()</tt>), +there being a separate interface per flavor of RCU) +or indirectly via <tt>synchronize_rcu()</tt> and friends. +RCU callbacks are represented by <tt>rcu_head</tt> structures, +which are queued on <tt>rcu_data</tt> structures while they are +waiting for a grace period to elapse, as shown in the following figure: + +</p><p><img src="BigTreePreemptRCUBHdyntickCB.svg" alt="BigTreePreemptRCUBHdyntickCB.svg" width="40%"> + +</p><p>This figure shows how <tt>TREE_RCU</tt>'s and +<tt>PREEMPT_RCU</tt>'s major data structures are related. +Lesser data structures will be introduced with the algorithms that +make use of them. + +</p><p>Note that each of the data structures in the above figure has +its own synchronization: + +<p><ol> +<li> Each <tt>rcu_state</tt> structures has a lock and a mutex, + and some fields are protected by the corresponding root + <tt>rcu_node</tt> structure's lock. +<li> Each <tt>rcu_node</tt> structure has a spinlock. +<li> The fields in <tt>rcu_data</tt> are private to the corresponding + CPU, although a few can be read and written by other CPUs. +<li> Similarly, the fields in <tt>rcu_dynticks</tt> are private + to the corresponding CPU, although a few can be read by + other CPUs. +</ol> + +<p>It is important to note that different data structures can have +very different ideas about the state of RCU at any given time. +For but one example, awareness of the start or end of a given RCU +grace period propagates slowly through the data structures. +This slow propagation is absolutely necessary for RCU to have good +read-side performance. +If this balkanized implementation seems foreign to you, one useful +trick is to consider each instance of these data structures to be +a different person, each having the usual slightly different +view of reality. + +</p><p>The general role of each of these data structures is as +follows: + +</p><ol> +<li> <tt>rcu_state</tt>: + This structure forms the interconnection between the + <tt>rcu_node</tt> and <tt>rcu_data</tt> structures, + tracks grace periods, serves as short-term repository + for callbacks orphaned by CPU-hotplug events, + maintains <tt>rcu_barrier()</tt> state, + tracks expedited grace-period state, + and maintains state used to force quiescent states when + grace periods extend too long, +<li> <tt>rcu_node</tt>: This structure forms the combining + tree that propagates quiescent-state + information from the leaves to the root, and also propagates + grace-period information from the root to the leaves. + It provides local copies of the grace-period state in order + to allow this information to be accessed in a synchronized + manner without suffering the scalability limitations that + would otherwise be imposed by global locking. + In <tt>CONFIG_PREEMPT_RCU</tt> kernels, it manages the lists + of tasks that have blocked while in their current + RCU read-side critical section. + In <tt>CONFIG_PREEMPT_RCU</tt> with + <tt>CONFIG_RCU_BOOST</tt>, it manages the + per-<tt>rcu_node</tt> priority-boosting + kernel threads (kthreads) and state. + Finally, it records CPU-hotplug state in order to determine + which CPUs should be ignored during a given grace period. +<li> <tt>rcu_data</tt>: This per-CPU structure is the + focus of quiescent-state detection and RCU callback queuing. + It also tracks its relationship to the corresponding leaf + <tt>rcu_node</tt> structure to allow more-efficient + propagation of quiescent states up the <tt>rcu_node</tt> + combining tree. + Like the <tt>rcu_node</tt> structure, it provides a local + copy of the grace-period information to allow for-free + synchronized + access to this information from the corresponding CPU. + Finally, this structure records past dyntick-idle state + for the corresponding CPU and also tracks statistics. +<li> <tt>rcu_dynticks</tt>: + This per-CPU structure tracks the current dyntick-idle + state for the corresponding CPU. + Unlike the other three structures, the <tt>rcu_dynticks</tt> + structure is not replicated per RCU flavor. +<li> <tt>rcu_head</tt>: + This structure represents RCU callbacks, and is the + only structure allocated and managed by RCU users. + The <tt>rcu_head</tt> structure is normally embedded + within the RCU-protected data structure. +</ol> + +<p>If all you wanted from this article was a general notion of how +RCU's data structures are related, you are done. +Otherwise, each of the following sections give more details on +the <tt>rcu_state</tt>, <tt>rcu_node</tt>, <tt>rcu_data</tt>, +and <tt>rcu_dynticks</tt> data structures. + +<h3><a name="The rcu_state Structure"> +The <tt>rcu_state</tt> Structure</a></h3> + +<p>The <tt>rcu_state</tt> structure is the base structure that +represents a flavor of RCU. +This structure forms the interconnection between the +<tt>rcu_node</tt> and <tt>rcu_data</tt> structures, +tracks grace periods, contains the lock used to +synchronize with CPU-hotplug events, +and maintains state used to force quiescent states when +grace periods extend too long, + +</p><p>A few of the <tt>rcu_state</tt> structure's fields are discussed, +singly and in groups, in the following sections. +The more specialized fields are covered in the discussion of their +use. + +<h5>Relationship to rcu_node and rcu_data Structures</h5> + +This portion of the <tt>rcu_state</tt> structure is declared +as follows: + +<pre> + 1 struct rcu_node node[NUM_RCU_NODES]; + 2 struct rcu_node *level[NUM_RCU_LVLS + 1]; + 3 struct rcu_data __percpu *rda; +</pre> + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Wait a minute! + You said that the <tt>rcu_node</tt> structures formed a tree, + but they are declared as a flat array! + What gives? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + The tree is laid out in the array. + The first node In the array is the head, the next set of nodes in the + array are children of the head node, and so on until the last set of + nodes in the array are the leaves. + </font> + + <p><font color="ffffff">See the following diagrams to see how + this works. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<p>The <tt>rcu_node</tt> tree is embedded into the +<tt>->node[]</tt> array as shown in the following figure: + +</p><p><img src="TreeMapping.svg" alt="TreeMapping.svg" width="40%"> + +</p><p>One interesting consequence of this mapping is that a +breadth-first traversal of the tree is implemented as a simple +linear scan of the array, which is in fact what the +<tt>rcu_for_each_node_breadth_first()</tt> macro does. +This macro is used at the beginning and ends of grace periods. + +</p><p>Each entry of the <tt>->level</tt> array references +the first <tt>rcu_node</tt> structure on the corresponding level +of the tree, for example, as shown below: + +</p><p><img src="TreeMappingLevel.svg" alt="TreeMappingLevel.svg" width="40%"> + +</p><p>The zero<sup>th</sup> element of the array references the root +<tt>rcu_node</tt> structure, the first element references the +first child of the root <tt>rcu_node</tt>, and finally the second +element references the first leaf <tt>rcu_node</tt> structure. + +</p><p>For whatever it is worth, if you draw the tree to be tree-shaped +rather than array-shaped, it is easy to draw a planar representation: + +</p><p><img src="TreeLevel.svg" alt="TreeLevel.svg" width="60%"> + +</p><p>Finally, the <tt>->rda</tt> field references a per-CPU +pointer to the corresponding CPU's <tt>rcu_data</tt> structure. + +</p><p>All of these fields are constant once initialization is complete, +and therefore need no protection. + +<h5>Grace-Period Tracking</h5> + +<p>This portion of the <tt>rcu_state</tt> structure is declared +as follows: + +<pre> + 1 unsigned long gpnum; + 2 unsigned long completed; +</pre> + +<p>RCU grace periods are numbered, and +the <tt>->gpnum</tt> field contains the number of the grace +period that started most recently. +The <tt>->completed</tt> field contains the number of the +grace period that completed most recently. +If the two fields are equal, the RCU grace period that most recently +started has already completed, and therefore the corresponding +flavor of RCU is idle. +If <tt>->gpnum</tt> is one greater than <tt>->completed</tt>, +then <tt>->gpnum</tt> gives the number of the current RCU +grace period, which has not yet completed. +Any other combination of values indicates that something is broken. +These two fields are protected by the root <tt>rcu_node</tt>'s +<tt>->lock</tt> field. + +</p><p>There are <tt>->gpnum</tt> and <tt>->completed</tt> fields +in the <tt>rcu_node</tt> and <tt>rcu_data</tt> structures +as well. +The fields in the <tt>rcu_state</tt> structure represent the +most current values, and those of the other structures are compared +in order to detect the start of a new grace period in a distributed +fashion. +The values flow from <tt>rcu_state</tt> to <tt>rcu_node</tt> +(down the tree from the root to the leaves) to <tt>rcu_data</tt>. + +<h5>Miscellaneous</h5> + +<p>This portion of the <tt>rcu_state</tt> structure is declared +as follows: + +<pre> + 1 unsigned long gp_max; + 2 char abbr; + 3 char *name; +</pre> + +<p>The <tt>->gp_max</tt> field tracks the duration of the longest +grace period in jiffies. +It is protected by the root <tt>rcu_node</tt>'s <tt>->lock</tt>. + +<p>The <tt>->name</tt> field points to the name of the RCU flavor +(for example, “rcu_sched”), and is constant. +The <tt>->abbr</tt> field contains a one-character abbreviation, +for example, “s” for RCU-sched. + +<h3><a name="The rcu_node Structure"> +The <tt>rcu_node</tt> Structure</a></h3> + +<p>The <tt>rcu_node</tt> structures form the combining +tree that propagates quiescent-state +information from the leaves to the root and also that propagates +grace-period information from the root down to the leaves. +They provides local copies of the grace-period state in order +to allow this information to be accessed in a synchronized +manner without suffering the scalability limitations that +would otherwise be imposed by global locking. +In <tt>CONFIG_PREEMPT_RCU</tt> kernels, they manage the lists +of tasks that have blocked while in their current +RCU read-side critical section. +In <tt>CONFIG_PREEMPT_RCU</tt> with +<tt>CONFIG_RCU_BOOST</tt>, they manage the +per-<tt>rcu_node</tt> priority-boosting +kernel threads (kthreads) and state. +Finally, they record CPU-hotplug state in order to determine +which CPUs should be ignored during a given grace period. + +</p><p>The <tt>rcu_node</tt> structure's fields are discussed, +singly and in groups, in the following sections. + +<h5>Connection to Combining Tree</h5> + +<p>This portion of the <tt>rcu_node</tt> structure is declared +as follows: + +<pre> + 1 struct rcu_node *parent; + 2 u8 level; + 3 u8 grpnum; + 4 unsigned long grpmask; + 5 int grplo; + 6 int grphi; +</pre> + +<p>The <tt>->parent</tt> pointer references the <tt>rcu_node</tt> +one level up in the tree, and is <tt>NULL</tt> for the root +<tt>rcu_node</tt>. +The RCU implementation makes heavy use of this field to push quiescent +states up the tree. +The <tt>->level</tt> field gives the level in the tree, with +the root being at level zero, its children at level one, and so on. +The <tt>->grpnum</tt> field gives this node's position within +the children of its parent, so this number can range between 0 and 31 +on 32-bit systems and between 0 and 63 on 64-bit systems. +The <tt>->level</tt> and <tt>->grpnum</tt> fields are +used only during initialization and for tracing. +The <tt>->grpmask</tt> field is the bitmask counterpart of +<tt>->grpnum</tt>, and therefore always has exactly one bit set. +This mask is used to clear the bit corresponding to this <tt>rcu_node</tt> +structure in its parent's bitmasks, which are described later. +Finally, the <tt>->grplo</tt> and <tt>->grphi</tt> fields +contain the lowest and highest numbered CPU served by this +<tt>rcu_node</tt> structure, respectively. + +</p><p>All of these fields are constant, and thus do not require any +synchronization. + +<h5>Synchronization</h5> + +<p>This field of the <tt>rcu_node</tt> structure is declared +as follows: + +<pre> + 1 raw_spinlock_t lock; +</pre> + +<p>This field is used to protect the remaining fields in this structure, +unless otherwise stated. +That said, all of the fields in this structure can be accessed without +locking for tracing purposes. +Yes, this can result in confusing traces, but better some tracing confusion +than to be heisenbugged out of existence. + +<h5>Grace-Period Tracking</h5> + +<p>This portion of the <tt>rcu_node</tt> structure is declared +as follows: + +<pre> + 1 unsigned long gpnum; + 2 unsigned long completed; +</pre> + +<p>These fields are the counterparts of the fields of the same name in +the <tt>rcu_state</tt> structure. +They each may lag up to one behind their <tt>rcu_state</tt> +counterparts. +If a given <tt>rcu_node</tt> structure's <tt>->gpnum</tt> and +<tt>->complete</tt> fields are equal, then this <tt>rcu_node</tt> +structure believes that RCU is idle. +Otherwise, as with the <tt>rcu_state</tt> structure, +the <tt>->gpnum</tt> field will be one greater than the +<tt>->complete</tt> fields, with <tt>->gpnum</tt> +indicating which grace period this <tt>rcu_node</tt> believes +is still being waited for. + +</p><p>The <tt>>gpnum</tt> field of each <tt>rcu_node</tt> +structure is updated at the beginning +of each grace period, and the <tt>->completed</tt> fields are +updated at the end of each grace period. + +<h5>Quiescent-State Tracking</h5> + +<p>These fields manage the propagation of quiescent states up the +combining tree. + +</p><p>This portion of the <tt>rcu_node</tt> structure has fields +as follows: + +<pre> + 1 unsigned long qsmask; + 2 unsigned long expmask; + 3 unsigned long qsmaskinit; + 4 unsigned long expmaskinit; +</pre> + +<p>The <tt>->qsmask</tt> field tracks which of this +<tt>rcu_node</tt> structure's children still need to report +quiescent states for the current normal grace period. +Such children will have a value of 1 in their corresponding bit. +Note that the leaf <tt>rcu_node</tt> structures should be +thought of as having <tt>rcu_data</tt> structures as their +children. +Similarly, the <tt>->expmask</tt> field tracks which +of this <tt>rcu_node</tt> structure's children still need to report +quiescent states for the current expedited grace period. +An expedited grace period has +the same conceptual properties as a normal grace period, but the +expedited implementation accepts extreme CPU overhead to obtain +much lower grace-period latency, for example, consuming a few +tens of microseconds worth of CPU time to reduce grace-period +duration from milliseconds to tens of microseconds. +The <tt>->qsmaskinit</tt> field tracks which of this +<tt>rcu_node</tt> structure's children cover for at least +one online CPU. +This mask is used to initialize <tt>->qsmask</tt>, +and <tt>->expmaskinit</tt> is used to initialize +<tt>->expmask</tt> and the beginning of the +normal and expedited grace periods, respectively. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Why are these bitmasks protected by locking? + Come on, haven't you heard of atomic instructions??? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Lockless grace-period computation! Such a tantalizing possibility! + </font> + + <p><font color="ffffff">But consider the following sequence of events: + </font> + + <ol> + <li> <font color="ffffff">CPU 0 has been in dyntick-idle + mode for quite some time. + When it wakes up, it notices that the current RCU + grace period needs it to report in, so it sets a + flag where the scheduling clock interrupt will find it. + </font><p> + <li> <font color="ffffff">Meanwhile, CPU 1 is running + <tt>force_quiescent_state()</tt>, + and notices that CPU 0 has been in dyntick idle mode, + which qualifies as an extended quiescent state. + </font><p> + <li> <font color="ffffff">CPU 0's scheduling clock + interrupt fires in the + middle of an RCU read-side critical section, and notices + that the RCU core needs something, so commences RCU softirq + processing. + </font> + <p> + <li> <font color="ffffff">CPU 0's softirq handler + executes and is just about ready + to report its quiescent state up the <tt>rcu_node</tt> + tree. + </font><p> + <li> <font color="ffffff">But CPU 1 beats it to the punch, + completing the current + grace period and starting a new one. + </font><p> + <li> <font color="ffffff">CPU 0 now reports its quiescent + state for the wrong + grace period. + That grace period might now end before the RCU read-side + critical section. + If that happens, disaster will ensue. + </font> + </ol> + + <p><font color="ffffff">So the locking is absolutely required in + order to coordinate + clearing of the bits with the grace-period numbers in + <tt>->gpnum</tt> and <tt>->completed</tt>. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<h5>Blocked-Task Management</h5> + +<p><tt>PREEMPT_RCU</tt> allows tasks to be preempted in the +midst of their RCU read-side critical sections, and these tasks +must be tracked explicitly. +The details of exactly why and how they are tracked will be covered +in a separate article on RCU read-side processing. +For now, it is enough to know that the <tt>rcu_node</tt> +structure tracks them. + +<pre> + 1 struct list_head blkd_tasks; + 2 struct list_head *gp_tasks; + 3 struct list_head *exp_tasks; + 4 bool wait_blkd_tasks; +</pre> + +<p>The <tt>->blkd_tasks</tt> field is a list header for +the list of blocked and preempted tasks. +As tasks undergo context switches within RCU read-side critical +sections, their <tt>task_struct</tt> structures are enqueued +(via the <tt>task_struct</tt>'s <tt>->rcu_node_entry</tt> +field) onto the head of the <tt>->blkd_tasks</tt> list for the +leaf <tt>rcu_node</tt> structure corresponding to the CPU +on which the outgoing context switch executed. +As these tasks later exit their RCU read-side critical sections, +they remove themselves from the list. +This list is therefore in reverse time order, so that if one of the tasks +is blocking the current grace period, all subsequent tasks must +also be blocking that same grace period. +Therefore, a single pointer into this list suffices to track +all tasks blocking a given grace period. +That pointer is stored in <tt>->gp_tasks</tt> for normal +grace periods and in <tt>->exp_tasks</tt> for expedited +grace periods. +These last two fields are <tt>NULL</tt> if either there is +no grace period in flight or if there are no blocked tasks +preventing that grace period from completing. +If either of these two pointers is referencing a task that +removes itself from the <tt>->blkd_tasks</tt> list, +then that task must advance the pointer to the next task on +the list, or set the pointer to <tt>NULL</tt> if there +are no subsequent tasks on the list. + +</p><p>For example, suppose that tasks T1, T2, and T3 are +all hard-affinitied to the largest-numbered CPU in the system. +Then if task T1 blocked in an RCU read-side +critical section, then an expedited grace period started, +then task T2 blocked in an RCU read-side critical section, +then a normal grace period started, and finally task 3 blocked +in an RCU read-side critical section, then the state of the +last leaf <tt>rcu_node</tt> structure's blocked-task list +would be as shown below: + +</p><p><img src="blkd_task.svg" alt="blkd_task.svg" width="60%"> + +</p><p>Task T1 is blocking both grace periods, task T2 is +blocking only the normal grace period, and task T3 is blocking +neither grace period. +Note that these tasks will not remove themselves from this list +immediately upon resuming execution. +They will instead remain on the list until they execute the outermost +<tt>rcu_read_unlock()</tt> that ends their RCU read-side critical +section. + +<p> +The <tt>->wait_blkd_tasks</tt> field indicates whether or not +the current grace period is waiting on a blocked task. + +<h5>Sizing the <tt>rcu_node</tt> Array</h5> + +<p>The <tt>rcu_node</tt> array is sized via a series of +C-preprocessor expressions as follows: + +<pre> + 1 #ifdef CONFIG_RCU_FANOUT + 2 #define RCU_FANOUT CONFIG_RCU_FANOUT + 3 #else + 4 # ifdef CONFIG_64BIT + 5 # define RCU_FANOUT 64 + 6 # else + 7 # define RCU_FANOUT 32 + 8 # endif + 9 #endif +10 +11 #ifdef CONFIG_RCU_FANOUT_LEAF +12 #define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF +13 #else +14 # ifdef CONFIG_64BIT +15 # define RCU_FANOUT_LEAF 64 +16 # else +17 # define RCU_FANOUT_LEAF 32 +18 # endif +19 #endif +20 +21 #define RCU_FANOUT_1 (RCU_FANOUT_LEAF) +22 #define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT) +23 #define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT) +24 #define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT) +25 +26 #if NR_CPUS <= RCU_FANOUT_1 +27 # define RCU_NUM_LVLS 1 +28 # define NUM_RCU_LVL_0 1 +29 # define NUM_RCU_NODES NUM_RCU_LVL_0 +30 # define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 } +31 # define RCU_NODE_NAME_INIT { "rcu_node_0" } +32 # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" } +33 # define RCU_EXP_NAME_INIT { "rcu_node_exp_0" } +34 #elif NR_CPUS <= RCU_FANOUT_2 +35 # define RCU_NUM_LVLS 2 +36 # define NUM_RCU_LVL_0 1 +37 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) +38 # define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1) +39 # define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 } +40 # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" } +41 # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" } +42 # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1" } +43 #elif NR_CPUS <= RCU_FANOUT_3 +44 # define RCU_NUM_LVLS 3 +45 # define NUM_RCU_LVL_0 1 +46 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) +47 # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) +48 # define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2) +49 # define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 } +50 # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" } +51 # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" } +52 # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" } +53 #elif NR_CPUS <= RCU_FANOUT_4 +54 # define RCU_NUM_LVLS 4 +55 # define NUM_RCU_LVL_0 1 +56 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3) +57 # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) +58 # define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) +59 # define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3) +60 # define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 } +61 # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" } +62 # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" } +63 # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" } +64 #else +65 # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" +66 #endif +</pre> + +<p>The maximum number of levels in the <tt>rcu_node</tt> structure +is currently limited to four, as specified by lines 21-24 +and the structure of the subsequent “if” statement. +For 32-bit systems, this allows 16*32*32*32=524,288 CPUs, which +should be sufficient for the next few years at least. +For 64-bit systems, 16*64*64*64=4,194,304 CPUs is allowed, which +should see us through the next decade or so. +This four-level tree also allows kernels built with +<tt>CONFIG_RCU_FANOUT=8</tt> to support up to 4096 CPUs, +which might be useful in very large systems having eight CPUs per +socket (but please note that no one has yet shown any measurable +performance degradation due to misaligned socket and <tt>rcu_node</tt> +boundaries). +In addition, building kernels with a full four levels of <tt>rcu_node</tt> +tree permits better testing of RCU's combining-tree code. + +</p><p>The <tt>RCU_FANOUT</tt> symbol controls how many children +are permitted at each non-leaf level of the <tt>rcu_node</tt> tree. +If the <tt>CONFIG_RCU_FANOUT</tt> Kconfig option is not specified, +it is set based on the word size of the system, which is also +the Kconfig default. + +</p><p>The <tt>RCU_FANOUT_LEAF</tt> symbol controls how many CPUs are +handled by each leaf <tt>rcu_node</tt> structure. +Experience has shown that allowing a given leaf <tt>rcu_node</tt> +structure to handle 64 CPUs, as permitted by the number of bits in +the <tt>->qsmask</tt> field on a 64-bit system, results in +excessive contention for the leaf <tt>rcu_node</tt> structures' +<tt>->lock</tt> fields. +The number of CPUs per leaf <tt>rcu_node</tt> structure is therefore +limited to 16 given the default value of <tt>CONFIG_RCU_FANOUT_LEAF</tt>. +If <tt>CONFIG_RCU_FANOUT_LEAF</tt> is unspecified, the value +selected is based on the word size of the system, just as for +<tt>CONFIG_RCU_FANOUT</tt>. +Lines 11-19 perform this computation. + +</p><p>Lines 21-24 compute the maximum number of CPUs supported by +a single-level (which contains a single <tt>rcu_node</tt> structure), +two-level, three-level, and four-level <tt>rcu_node</tt> tree, +respectively, given the fanout specified by <tt>RCU_FANOUT</tt> +and <tt>RCU_FANOUT_LEAF</tt>. +These numbers of CPUs are retained in the +<tt>RCU_FANOUT_1</tt>, +<tt>RCU_FANOUT_2</tt>, +<tt>RCU_FANOUT_3</tt>, and +<tt>RCU_FANOUT_4</tt> +C-preprocessor variables, respectively. + +</p><p>These variables are used to control the C-preprocessor <tt>#if</tt> +statement spanning lines 26-66 that computes the number of +<tt>rcu_node</tt> structures required for each level of the tree, +as well as the number of levels required. +The number of levels is placed in the <tt>NUM_RCU_LVLS</tt> +C-preprocessor variable by lines 27, 35, 44, and 54. +The number of <tt>rcu_node</tt> structures for the topmost level +of the tree is always exactly one, and this value is unconditionally +placed into <tt>NUM_RCU_LVL_0</tt> by lines 28, 36, 45, and 55. +The rest of the levels (if any) of the <tt>rcu_node</tt> tree +are computed by dividing the maximum number of CPUs by the +fanout supported by the number of levels from the current level down, +rounding up. This computation is performed by lines 37, +46-47, and 56-58. +Lines 31-33, 40-42, 50-52, and 62-63 create initializers +for lockdep lock-class names. +Finally, lines 64-66 produce an error if the maximum number of +CPUs is too large for the specified fanout. + +<h3><a name="The rcu_data Structure"> +The <tt>rcu_data</tt> Structure</a></h3> + +<p>The <tt>rcu_data</tt> maintains the per-CPU state for the +corresponding flavor of RCU. +The fields in this structure may be accessed only from the corresponding +CPU (and from tracing) unless otherwise stated. +This structure is the +focus of quiescent-state detection and RCU callback queuing. +It also tracks its relationship to the corresponding leaf +<tt>rcu_node</tt> structure to allow more-efficient +propagation of quiescent states up the <tt>rcu_node</tt> +combining tree. +Like the <tt>rcu_node</tt> structure, it provides a local +copy of the grace-period information to allow for-free +synchronized +access to this information from the corresponding CPU. +Finally, this structure records past dyntick-idle state +for the corresponding CPU and also tracks statistics. + +</p><p>The <tt>rcu_data</tt> structure's fields are discussed, +singly and in groups, in the following sections. + +<h5>Connection to Other Data Structures</h5> + +<p>This portion of the <tt>rcu_data</tt> structure is declared +as follows: + +<pre> + 1 int cpu; + 2 struct rcu_state *rsp; + 3 struct rcu_node *mynode; + 4 struct rcu_dynticks *dynticks; + 5 unsigned long grpmask; + 6 bool beenonline; +</pre> + +<p>The <tt>->cpu</tt> field contains the number of the +corresponding CPU, the <tt>->rsp</tt> pointer references +the corresponding <tt>rcu_state</tt> structure (and is most frequently +used to locate the name of the corresponding flavor of RCU for tracing), +and the <tt>->mynode</tt> field references the corresponding +<tt>rcu_node</tt> structure. +The <tt>->mynode</tt> is used to propagate quiescent states +up the combining tree. +<p>The <tt>->dynticks</tt> pointer references the +<tt>rcu_dynticks</tt> structure corresponding to this +CPU. +Recall that a single per-CPU instance of the <tt>rcu_dynticks</tt> +structure is shared among all flavors of RCU. +These first four fields are constant and therefore require not +synchronization. + +</p><p>The <tt>->grpmask</tt> field indicates the bit in +the <tt>->mynode->qsmask</tt> corresponding to this +<tt>rcu_data</tt> structure, and is also used when propagating +quiescent states. +The <tt>->beenonline</tt> flag is set whenever the corresponding +CPU comes online, which means that the debugfs tracing need not dump +out any <tt>rcu_data</tt> structure for which this flag is not set. + +<h5>Quiescent-State and Grace-Period Tracking</h5> + +<p>This portion of the <tt>rcu_data</tt> structure is declared +as follows: + +<pre> + 1 unsigned long completed; + 2 unsigned long gpnum; + 3 bool cpu_no_qs; + 4 bool core_needs_qs; + 5 bool gpwrap; + 6 unsigned long rcu_qs_ctr_snap; +</pre> + +<p>The <tt>completed</tt> and <tt>gpnum</tt> +fields are the counterparts of the fields of the same name +in the <tt>rcu_state</tt> and <tt>rcu_node</tt> structures. +They may each lag up to one behind their <tt>rcu_node</tt> +counterparts, but in <tt>CONFIG_NO_HZ_IDLE</tt> and +<tt>CONFIG_NO_HZ_FULL</tt> kernels can lag +arbitrarily far behind for CPUs in dyntick-idle mode (but these counters +will catch up upon exit from dyntick-idle mode). +If a given <tt>rcu_data</tt> structure's <tt>->gpnum</tt> and +<tt>->complete</tt> fields are equal, then this <tt>rcu_data</tt> +structure believes that RCU is idle. +Otherwise, as with the <tt>rcu_state</tt> and <tt>rcu_node</tt> +structure, +the <tt>->gpnum</tt> field will be one greater than the +<tt>->complete</tt> fields, with <tt>->gpnum</tt> +indicating which grace period this <tt>rcu_data</tt> believes +is still being waited for. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + All this replication of the grace period numbers can only cause + massive confusion. + Why not just keep a global pair of counters and be done with it??? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Because if there was only a single global pair of grace-period + numbers, there would need to be a single global lock to allow + safely accessing and updating them. + And if we are not going to have a single global lock, we need + to carefully manage the numbers on a per-node basis. + Recall from the answer to a previous Quick Quiz that the consequences + of applying a previously sampled quiescent state to the wrong + grace period are quite severe. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<p>The <tt>->cpu_no_qs</tt> flag indicates that the +CPU has not yet passed through a quiescent state, +while the <tt>->core_needs_qs</tt> flag indicates that the +RCU core needs a quiescent state from the corresponding CPU. +The <tt>->gpwrap</tt> field indicates that the corresponding +CPU has remained idle for so long that the <tt>completed</tt> +and <tt>gpnum</tt> counters are in danger of overflow, which +will cause the CPU to disregard the values of its counters on +its next exit from idle. +Finally, the <tt>rcu_qs_ctr_snap</tt> field is used to detect +cases where a given operation has resulted in a quiescent state +for all flavors of RCU, for example, <tt>cond_resched_rcu_qs()</tt>. + +<h5>RCU Callback Handling</h5> + +<p>In the absence of CPU-hotplug events, RCU callbacks are invoked by +the same CPU that registered them. +This is strictly a cache-locality optimization: callbacks can and +do get invoked on CPUs other than the one that registered them. +After all, if the CPU that registered a given callback has gone +offline before the callback can be invoked, there really is no other +choice. + +</p><p>This portion of the <tt>rcu_data</tt> structure is declared +as follows: + +<pre> + 1 struct rcu_head *nxtlist; + 2 struct rcu_head **nxttail[RCU_NEXT_SIZE]; + 3 unsigned long nxtcompleted[RCU_NEXT_SIZE]; + 4 long qlen_lazy; + 5 long qlen; + 6 long qlen_last_fqs_check; + 7 unsigned long n_force_qs_snap; + 8 unsigned long n_cbs_invoked; + 9 unsigned long n_cbs_orphaned; +10 unsigned long n_cbs_adopted; +11 long blimit; +</pre> + +<p>The <tt>->nxtlist</tt> pointer and the +<tt>->nxttail[]</tt> array form a four-segment list with +older callbacks near the head and newer ones near the tail. +Each segment contains callbacks with the corresponding relationship +to the current grace period. +The pointer out of the end of each of the four segments is referenced +by the element of the <tt>->nxttail[]</tt> array indexed by +<tt>RCU_DONE_TAIL</tt> (for callbacks handled by a prior grace period), +<tt>RCU_WAIT_TAIL</tt> (for callbacks waiting on the current grace period), +<tt>RCU_NEXT_READY_TAIL</tt> (for callbacks that will wait on the next +grace period), and +<tt>RCU_NEXT_TAIL</tt> (for callbacks that are not yet associated +with a specific grace period) +respectively, as shown in the following figure. + +</p><p><img src="nxtlist.svg" alt="nxtlist.svg" width="40%"> + +</p><p>In this figure, the <tt>->nxtlist</tt> pointer references the +first +RCU callback in the list. +The <tt>->nxttail[RCU_DONE_TAIL]</tt> array element references +the <tt>->nxtlist</tt> pointer itself, indicating that none +of the callbacks is ready to invoke. +The <tt>->nxttail[RCU_WAIT_TAIL]</tt> array element references callback +CB 2's <tt>->next</tt> pointer, which indicates that +CB 1 and CB 2 are both waiting on the current grace period. +The <tt>->nxttail[RCU_NEXT_READY_TAIL]</tt> array element +references the same RCU callback that <tt>->nxttail[RCU_WAIT_TAIL]</tt> +does, which indicates that there are no callbacks waiting on the next +RCU grace period. +The <tt>->nxttail[RCU_NEXT_TAIL]</tt> array element references +CB 4's <tt>->next</tt> pointer, indicating that all the +remaining RCU callbacks have not yet been assigned to an RCU grace +period. +Note that the <tt>->nxttail[RCU_NEXT_TAIL]</tt> array element +always references the last RCU callback's <tt>->next</tt> pointer +unless the callback list is empty, in which case it references +the <tt>->nxtlist</tt> pointer. + +</p><p>CPUs advance their callbacks from the +<tt>RCU_NEXT_TAIL</tt> to the <tt>RCU_NEXT_READY_TAIL</tt> to the +<tt>RCU_WAIT_TAIL</tt> to the <tt>RCU_DONE_TAIL</tt> list segments +as grace periods advance. +The CPU advances the callbacks in its <tt>rcu_data</tt> structure +whenever it notices that another RCU grace period has completed. +The CPU detects the completion of an RCU grace period by noticing +that the value of its <tt>rcu_data</tt> structure's +<tt>->completed</tt> field differs from that of its leaf +<tt>rcu_node</tt> structure. +Recall that each <tt>rcu_node</tt> structure's +<tt>->completed</tt> field is updated at the end of each +grace period. + +</p><p>The <tt>->nxtcompleted[]</tt> array records grace-period +numbers corresponding to the list segments. +This allows CPUs that go idle for extended periods to determine +which of their callbacks are ready to be invoked after reawakening. + +</p><p>The <tt>->qlen</tt> counter contains the number of +callbacks in <tt>->nxtlist</tt>, and the +<tt>->qlen_lazy</tt> contains the number of those callbacks that +are known to only free memory, and whose invocation can therefore +be safely deferred. +The <tt>->qlen_last_fqs_check</tt> and +<tt>->n_force_qs_snap</tt> coordinate the forcing of quiescent +states from <tt>call_rcu()</tt> and friends when callback +lists grow excessively long. + +</p><p>The <tt>->n_cbs_invoked</tt>, +<tt>->n_cbs_orphaned</tt>, and <tt>->n_cbs_adopted</tt> +fields count the number of callbacks invoked, +sent to other CPUs when this CPU goes offline, +and received from other CPUs when those other CPUs go offline. +Finally, the <tt>->blimit</tt> counter is the maximum number of +RCU callbacks that may be invoked at a given time. + +<h5>Dyntick-Idle Handling</h5> + +<p>This portion of the <tt>rcu_data</tt> structure is declared +as follows: + +<pre> + 1 int dynticks_snap; + 2 unsigned long dynticks_fqs; +</pre> + +The <tt>->dynticks_snap</tt> field is used to take a snapshot +of the corresponding CPU's dyntick-idle state when forcing +quiescent states, and is therefore accessed from other CPUs. +Finally, the <tt>->dynticks_fqs</tt> field is used to +count the number of times this CPU is determined to be in +dyntick-idle state, and is used for tracing and debugging purposes. + +<h3><a name="The rcu_dynticks Structure"> +The <tt>rcu_dynticks</tt> Structure</a></h3> + +<p>The <tt>rcu_dynticks</tt> maintains the per-CPU dyntick-idle state +for the corresponding CPU. +Unlike the other structures, <tt>rcu_dynticks</tt> is not +replicated over the different flavors of RCU. +The fields in this structure may be accessed only from the corresponding +CPU (and from tracing) unless otherwise stated. +Its fields are as follows: + +<pre> + 1 int dynticks_nesting; + 2 int dynticks_nmi_nesting; + 3 atomic_t dynticks; +</pre> + +<p>The <tt>->dynticks_nesting</tt> field counts the +nesting depth of normal interrupts. +In addition, this counter is incremented when exiting dyntick-idle +mode and decremented when entering it. +This counter can therefore be thought of as counting the number +of reasons why this CPU cannot be permitted to enter dyntick-idle +mode, aside from non-maskable interrupts (NMIs). +NMIs are counted by the <tt>->dynticks_nmi_nesting</tt> +field, except that NMIs that interrupt non-dyntick-idle execution +are not counted. + +</p><p>Finally, the <tt>->dynticks</tt> field counts the corresponding +CPU's transitions to and from dyntick-idle mode, so that this counter +has an even value when the CPU is in dyntick-idle mode and an odd +value otherwise. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Why not just count all NMIs? + Wouldn't that be simpler and less error prone? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + It seems simpler only until you think hard about how to go about + updating the <tt>rcu_dynticks</tt> structure's + <tt>->dynticks</tt> field. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<p>Additional fields are present for some special-purpose +builds, and are discussed separately. + +<h3><a name="The rcu_head Structure"> +The <tt>rcu_head</tt> Structure</a></h3> + +<p>Each <tt>rcu_head</tt> structure represents an RCU callback. +These structures are normally embedded within RCU-protected data +structures whose algorithms use asynchronous grace periods. +In contrast, when using algorithms that block waiting for RCU grace periods, +RCU users need not provide <tt>rcu_head</tt> structures. + +</p><p>The <tt>rcu_head</tt> structure has fields as follows: + +<pre> + 1 struct rcu_head *next; + 2 void (*func)(struct rcu_head *head); +</pre> + +<p>The <tt>->next</tt> field is used +to link the <tt>rcu_head</tt> structures together in the +lists within the <tt>rcu_data</tt> structures. +The <tt>->func</tt> field is a pointer to the function +to be called when the callback is ready to be invoked, and +this function is passed a pointer to the <tt>rcu_head</tt> +structure. +However, <tt>kfree_rcu()</tt> uses the <tt>->func</tt> +field to record the offset of the <tt>rcu_head</tt> +structure within the enclosing RCU-protected data structure. + +</p><p>Both of these fields are used internally by RCU. +From the viewpoint of RCU users, this structure is an +opaque “cookie”. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Given that the callback function <tt>->func</tt> + is passed a pointer to the <tt>rcu_head</tt> structure, + how is that function supposed to find the beginning of the + enclosing RCU-protected data structure? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + In actual practice, there is a separate callback function per + type of RCU-protected data structure. + The callback function can therefore use the <tt>container_of()</tt> + macro in the Linux kernel (or other pointer-manipulation facilities + in other software environments) to find the beginning of the + enclosing structure. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<h3><a name="RCU-Specific Fields in the task_struct Structure"> +RCU-Specific Fields in the <tt>task_struct</tt> Structure</a></h3> + +<p>The <tt>CONFIG_PREEMPT_RCU</tt> implementation uses some +additional fields in the <tt>task_struct</tt> structure: + +<pre> + 1 #ifdef CONFIG_PREEMPT_RCU + 2 int rcu_read_lock_nesting; + 3 union rcu_special rcu_read_unlock_special; + 4 struct list_head rcu_node_entry; + 5 struct rcu_node *rcu_blocked_node; + 6 #endif /* #ifdef CONFIG_PREEMPT_RCU */ + 7 #ifdef CONFIG_TASKS_RCU + 8 unsigned long rcu_tasks_nvcsw; + 9 bool rcu_tasks_holdout; +10 struct list_head rcu_tasks_holdout_list; +11 int rcu_tasks_idle_cpu; +12 #endif /* #ifdef CONFIG_TASKS_RCU */ +</pre> + +<p>The <tt>->rcu_read_lock_nesting</tt> field records the +nesting level for RCU read-side critical sections, and +the <tt>->rcu_read_unlock_special</tt> field is a bitmask +that records special conditions that require <tt>rcu_read_unlock()</tt> +to do additional work. +The <tt>->rcu_node_entry</tt> field is used to form lists of +tasks that have blocked within preemptible-RCU read-side critical +sections and the <tt>->rcu_blocked_node</tt> field references +the <tt>rcu_node</tt> structure whose list this task is a member of, +or <tt>NULL</tt> if it is not blocked within a preemptible-RCU +read-side critical section. + +<p>The <tt>->rcu_tasks_nvcsw</tt> field tracks the number of +voluntary context switches that this task had undergone at the +beginning of the current tasks-RCU grace period, +<tt>->rcu_tasks_holdout</tt> is set if the current tasks-RCU +grace period is waiting on this task, <tt>->rcu_tasks_holdout_list</tt> +is a list element enqueuing this task on the holdout list, +and <tt>->rcu_tasks_idle_cpu</tt> tracks which CPU this +idle task is running, but only if the task is currently running, +that is, if the CPU is currently idle. + +<h3><a name="Accessor Functions"> +Accessor Functions</a></h3> + +<p>The following listing shows the +<tt>rcu_get_root()</tt>, <tt>rcu_for_each_node_breadth_first</tt>, +<tt>rcu_for_each_nonleaf_node_breadth_first()</tt>, and +<tt>rcu_for_each_leaf_node()</tt> function and macros: + +<pre> + 1 static struct rcu_node *rcu_get_root(struct rcu_state *rsp) + 2 { + 3 return &rsp->node[0]; + 4 } + 5 + 6 #define rcu_for_each_node_breadth_first(rsp, rnp) \ + 7 for ((rnp) = &(rsp)->node[0]; \ + 8 (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) + 9 + 10 #define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \ + 11 for ((rnp) = &(rsp)->node[0]; \ + 12 (rnp) < (rsp)->level[NUM_RCU_LVLS - 1]; (rnp)++) + 13 + 14 #define rcu_for_each_leaf_node(rsp, rnp) \ + 15 for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \ + 16 (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) +</pre> + +<p>The <tt>rcu_get_root()</tt> simply returns a pointer to the +first element of the specified <tt>rcu_state</tt> structure's +<tt>->node[]</tt> array, which is the root <tt>rcu_node</tt> +structure. + +</p><p>As noted earlier, the <tt>rcu_for_each_node_breadth_first()</tt> +macro takes advantage of the layout of the <tt>rcu_node</tt> +structures in the <tt>rcu_state</tt> structure's +<tt>->node[]</tt> array, performing a breadth-first traversal by +simply traversing the array in order. +The <tt>rcu_for_each_nonleaf_node_breadth_first()</tt> macro operates +similarly, but traverses only the first part of the array, thus excluding +the leaf <tt>rcu_node</tt> structures. +Finally, the <tt>rcu_for_each_leaf_node()</tt> macro traverses only +the last part of the array, thus traversing only the leaf +<tt>rcu_node</tt> structures. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + What do <tt>rcu_for_each_nonleaf_node_breadth_first()</tt> and + <tt>rcu_for_each_leaf_node()</tt> do if the <tt>rcu_node</tt> tree + contains only a single node? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + In the single-node case, + <tt>rcu_for_each_nonleaf_node_breadth_first()</tt> is a no-op + and <tt>rcu_for_each_leaf_node()</tt> traverses the single node. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<h3><a name="Summary"> +Summary</a></h3> + +So each flavor of RCU is represented by an <tt>rcu_state</tt> structure, +which contains a combining tree of <tt>rcu_node</tt> and +<tt>rcu_data</tt> structures. +Finally, in <tt>CONFIG_NO_HZ_IDLE</tt> kernels, each CPU's dyntick-idle +state is tracked by an <tt>rcu_dynticks</tt> structure. + +If you made it this far, you are well prepared to read the code +walkthroughs in the other articles in this series. + +<h3><a name="Acknowledgments"> +Acknowledgments</a></h3> + +I owe thanks to Cyrill Gorcunov, Mathieu Desnoyers, Dhaval Giani, Paul +Turner, Abhishek Srivastava, Matt Kowalczyk, and Serge Hallyn +for helping me get this document into a more human-readable state. + +<h3><a name="Legal Statement"> +Legal Statement</a></h3> + +<p>This work represents the view of the author and does not necessarily +represent the view of IBM. + +</p><p>Linux is a registered trademark of Linus Torvalds. + +</p><p>Other company, product, and service names may be trademarks or +service marks of others. + +</body></html> diff --git a/Documentation/RCU/Design/Data-Structures/HugeTreeClassicRCU.svg b/Documentation/RCU/Design/Data-Structures/HugeTreeClassicRCU.svg new file mode 100644 index 0000000..2bf12b4 --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/HugeTreeClassicRCU.svg @@ -0,0 +1,939 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:37:22 2015 --> + +<!-- Magnification: 3.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="15.1in" + height="11.2in" + viewBox="-66 -66 18087 13407" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="HugeTreeClassicRCU.fig"> + <metadata + id="metadata224"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title></dc:title> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs222"> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow1Mend" + style="overflow:visible;"> + <path + id="path3982" + d="M 0.0,0.0 L 5.0,-5.0 L -12.5,0.0 L 5.0,5.0 L 0.0,0.0 z " + style="fill-rule:evenodd;stroke:#000000;stroke-width:1.0pt;" + transform="scale(0.4) rotate(180) translate(10,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="1134" + inkscape:window-height="789" + id="namedview220" + showgrid="false" + inkscape:zoom="0.60515873" + inkscape:cx="679.5" + inkscape:cy="504" + inkscape:window-x="786" + inkscape:window-y="24" + inkscape:window-maximized="0" + inkscape:current-layer="g4" /> + <g + style="stroke-width:.025in; fill:none" + id="g4"> + <!-- Line: box --> + <rect + x="450" + y="0" + width="17100" + height="8325" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect6" /> + <!-- Line: box --> + <rect + x="11025" + y="3600" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect8" /> + <!-- Line: box --> + <rect + x="4275" + y="3600" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect10" /> + <!-- Line: box --> + <rect + x="5400" + y="6300" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect12" /> + <!-- Line: box --> + <rect + x="9900" + y="6300" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect14" /> + <!-- Line: box --> + <rect + x="14400" + y="6300" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect16" /> + <!-- Line: box --> + <rect + x="900" + y="6300" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect18" /> + <!-- Line: box --> + <rect + x="7650" + y="900" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect20" /> + <!-- Line --> + <polyline + points="3150,9225 3150,7746 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline22" /> + <!-- Arrowhead on XXXpoint 3150 9225 - 3150 7560--> + <!-- Circle --> + <circle + cx="8550" + cy="4275" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle26" /> + <!-- Circle --> + <circle + cx="9000" + cy="4275" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle28" /> + <!-- Circle --> + <circle + cx="9450" + cy="4275" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle30" /> + <!-- Line --> + <polyline + points="6750,6300 8250,5010 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline32" /> + <!-- Arrowhead on XXXpoint 6750 6300 - 8391 4890--> + <!-- Line --> + <polyline + points="11250,6300 9747,5010 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline36" /> + <!-- Arrowhead on XXXpoint 11250 6300 - 9606 4890--> + <!-- Circle --> + <circle + cx="13950" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle40" /> + <!-- Circle --> + <circle + cx="13500" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle42" /> + <!-- Circle --> + <circle + cx="13050" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle44" /> + <!-- Circle --> + <circle + cx="9450" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle46" /> + <!-- Circle --> + <circle + cx="9000" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle48" /> + <!-- Circle --> + <circle + cx="8550" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle50" /> + <!-- Circle --> + <circle + cx="4950" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle52" /> + <!-- Circle --> + <circle + cx="4500" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle54" /> + <!-- Circle --> + <circle + cx="4050" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle56" /> + <!-- Circle --> + <circle + cx="1800" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle58" /> + <!-- Circle --> + <circle + cx="2250" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle60" /> + <!-- Circle --> + <circle + cx="2700" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle62" /> + <!-- Circle --> + <circle + cx="15300" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle64" /> + <!-- Circle --> + <circle + cx="15750" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle66" /> + <!-- Circle --> + <circle + cx="16200" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle68" /> + <!-- Circle --> + <circle + cx="10800" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle70" /> + <!-- Circle --> + <circle + cx="11250" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle72" /> + <!-- Circle --> + <circle + cx="11700" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle74" /> + <!-- Circle --> + <circle + cx="6300" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle76" /> + <!-- Circle --> + <circle + cx="6750" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle78" /> + <!-- Circle --> + <circle + cx="7200" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle80" /> + <!-- Line: box --> + <rect + x="0" + y="11475" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect82" /> + <!-- Line: box --> + <rect + x="1800" + y="9225" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect84" /> + <!-- Line: box --> + <rect + x="4500" + y="11475" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect86" /> + <!-- Line: box --> + <rect + x="6300" + y="9270" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect88" /> + <!-- Line: box --> + <rect + x="8955" + y="11475" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect90" /> + <!-- Line: box --> + <rect + x="10755" + y="9270" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect92" /> + <!-- Line: box --> + <rect + x="13455" + y="11475" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect94" /> + <!-- Line: box --> + <rect + x="15255" + y="9270" + width="2700" + height="1800" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect96" /> + <!-- Line --> + <polyline + points="11700,3600 10197,2310 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline98" /> + <!-- Arrowhead on XXXpoint 11700 3600 - 10056 2190--> + <!-- Line --> + <polyline + points="6300,3600 7800,2310 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline102" /> + <!-- Arrowhead on XXXpoint 6300 3600 - 7941 2190--> + <!-- Line --> + <polyline + points="3150,6300 4650,5010 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline106" /> + <!-- Arrowhead on XXXpoint 3150 6300 - 4791 4890--> + <!-- Line --> + <polyline + points="14850,6300 13347,5010 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline110" /> + <!-- Arrowhead on XXXpoint 14850 6300 - 13206 4890--> + <!-- Line --> + <polyline + points="1350,11475 1350,7746 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline114" /> + <!-- Arrowhead on XXXpoint 1350 11475 - 1350 7560--> + <!-- Line --> + <polyline + points="16650,9225 16650,7746 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline118" /> + <!-- Arrowhead on XXXpoint 16650 9225 - 16650 7560--> + <!-- Line --> + <polyline + points="14850,11475 14850,7746 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline122" /> + <!-- Arrowhead on XXXpoint 14850 11475 - 14850 7560--> + <!-- Line --> + <polyline + points="12150,9225 12150,7746 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline126" /> + <!-- Arrowhead on XXXpoint 12150 9225 - 12150 7560--> + <!-- Line --> + <polyline + points="10350,11475 10350,7746 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline130" /> + <!-- Arrowhead on XXXpoint 10350 11475 - 10350 7560--> + <!-- Line --> + <polyline + points="7650,9225 7650,7746 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline134" /> + <!-- Arrowhead on XXXpoint 7650 9225 - 7650 7560--> + <!-- Line --> + <polyline + points="5850,11475 5850,7746 " + style="stroke:#00d1d1;stroke-width:44.99790066;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline138" /> + <!-- Arrowhead on XXXpoint 5850 11475 - 5850 7560--> + <!-- Text --> + <text + xml:space="preserve" + x="12375" + y="4500" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text142">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="12375" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text144">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5625" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text146">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5625" + y="4500" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text148">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="6750" + y="6750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text150">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="6750" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text152">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="11250" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text154">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="11250" + y="6750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text156">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="15750" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text158">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="15750" + y="6750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text160">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="6750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text162">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text164">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="1350" + y="13050" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text166">CPU 0</text> + <!-- Text --> + <text + xml:space="preserve" + x="1350" + y="11925" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text168">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1350" + y="12375" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text170">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="10800" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text172">CPU 15</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="9675" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text174">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="10125" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text176">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="5850" + y="11925" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text178">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5850" + y="12375" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text180">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="5850" + y="13050" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text182">CPU 21823</text> + <!-- Text --> + <text + xml:space="preserve" + x="7650" + y="10845" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text184">CPU 21839</text> + <!-- Text --> + <text + xml:space="preserve" + x="7650" + y="10170" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text186">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="7650" + y="9720" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text188">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="10305" + y="11925" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text190">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="10305" + y="12375" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text192">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="10305" + y="13050" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text194">CPU 43679</text> + <!-- Text --> + <text + xml:space="preserve" + x="12105" + y="10845" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text196">CPU 43695</text> + <!-- Text --> + <text + xml:space="preserve" + x="12105" + y="10170" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text198">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="12105" + y="9720" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text200">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="14805" + y="11925" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text202">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="14805" + y="12375" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text204">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="14805" + y="13050" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text206">CPU 65519</text> + <!-- Text --> + <text + xml:space="preserve" + x="16605" + y="10845" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text208">CPU 65535</text> + <!-- Text --> + <text + xml:space="preserve" + x="16605" + y="10170" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text210">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="16605" + y="9720" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text212">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="675" + y="450" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="start" + id="text214">struct rcu_state</text> + <!-- Text --> + <text + xml:space="preserve" + x="9000" + y="1350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text216">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="9000" + y="1800" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text218">rcu_node</text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Data-Structures/TreeLevel.svg b/Documentation/RCU/Design/Data-Structures/TreeLevel.svg new file mode 100644 index 0000000..7a7eb3b --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/TreeLevel.svg @@ -0,0 +1,828 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:41:29 2015 --> + +<!-- Magnification: 3.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="17.7in" + height="10.4in" + viewBox="-66 -66 21237 12507" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="TreeLevel.fig"> + <metadata + id="metadata216"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title></dc:title> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs214"> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow1Mend" + style="overflow:visible;"> + <path + id="path3974" + d="M 0.0,0.0 L 5.0,-5.0 L -12.5,0.0 L 5.0,5.0 L 0.0,0.0 z " + style="fill-rule:evenodd;stroke:#000000;stroke-width:1.0pt;" + transform="scale(0.4) rotate(180) translate(10,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="1023" + inkscape:window-height="1148" + id="namedview212" + showgrid="false" + inkscape:zoom="0.55869424" + inkscape:cx="796.50006" + inkscape:cy="467.99997" + inkscape:window-x="897" + inkscape:window-y="24" + inkscape:window-maximized="0" + inkscape:current-layer="g4" /> + <g + style="stroke-width:.025in; fill:none" + id="g4"> + <!-- Line: box --> + <rect + x="0" + y="0" + width="20655" + height="8325" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect6" /> + <!-- Line: box --> + <rect + x="14130" + y="3600" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect8" /> + <!-- Line: box --> + <rect + x="7380" + y="3600" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect10" /> + <!-- Line: box --> + <rect + x="8505" + y="6300" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect12" /> + <!-- Line: box --> + <rect + x="13005" + y="6300" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect14" /> + <!-- Line: box --> + <rect + x="17505" + y="6300" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect16" /> + <!-- Line: box --> + <rect + x="4005" + y="6300" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect18" /> + <!-- Line: box --> + <rect + x="10755" + y="900" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect20" /> + <!-- Line --> + <polyline + points="6255,9225 6255,7746 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline22" /> + <!-- Arrowhead on XXXpoint 6255 9225 - 6255 7560--> + <!-- Circle --> + <circle + cx="11655" + cy="4275" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle26" /> + <!-- Circle --> + <circle + cx="12105" + cy="4275" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle28" /> + <!-- Circle --> + <circle + cx="12555" + cy="4275" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle30" /> + <!-- Line --> + <polyline + points="9855,6300 11355,5010 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline32" /> + <!-- Arrowhead on XXXpoint 9855 6300 - 11496 4890--> + <!-- Line --> + <polyline + points="14355,6300 12852,5010 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline36" /> + <!-- Arrowhead on XXXpoint 14355 6300 - 12711 4890--> + <!-- Circle --> + <circle + cx="17055" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle40" /> + <!-- Circle --> + <circle + cx="16605" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle42" /> + <!-- Circle --> + <circle + cx="16155" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle44" /> + <!-- Circle --> + <circle + cx="12555" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle46" /> + <!-- Circle --> + <circle + cx="12105" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle48" /> + <!-- Circle --> + <circle + cx="11655" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle50" /> + <!-- Circle --> + <circle + cx="8055" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle52" /> + <!-- Circle --> + <circle + cx="7605" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle54" /> + <!-- Circle --> + <circle + cx="7155" + cy="6975" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle56" /> + <!-- Circle --> + <circle + cx="4905" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle58" /> + <!-- Circle --> + <circle + cx="5355" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle60" /> + <!-- Circle --> + <circle + cx="5805" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle62" /> + <!-- Circle --> + <circle + cx="18405" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle64" /> + <!-- Circle --> + <circle + cx="18855" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle66" /> + <!-- Circle --> + <circle + cx="19305" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle68" /> + <!-- Circle --> + <circle + cx="13905" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle70" /> + <!-- Circle --> + <circle + cx="14355" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle72" /> + <!-- Circle --> + <circle + cx="14805" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle74" /> + <!-- Circle --> + <circle + cx="9405" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle76" /> + <!-- Circle --> + <circle + cx="9855" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle78" /> + <!-- Circle --> + <circle + cx="10305" + cy="8775" + r="114" + style="fill:#000000;stroke:#000000;stroke-width:21;" + id="circle80" /> + <!-- Line: box --> + <rect + x="225" + y="1125" + width="3150" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:21; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect82" /> + <!-- Line: box --> + <rect + x="225" + y="2250" + width="3150" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:21; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect84" /> + <!-- Line: box --> + <rect + x="225" + y="3375" + width="3150" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:21; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect86" /> + <!-- Line --> + <polyline + points="14805,3600 13302,2310 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline88" /> + <!-- Arrowhead on XXXpoint 14805 3600 - 13161 2190--> + <!-- Line --> + <polyline + points="9405,3600 10905,2310 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline92" /> + <!-- Arrowhead on XXXpoint 9405 3600 - 11046 2190--> + <!-- Line --> + <polyline + points="6255,6300 7755,5010 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline96" /> + <!-- Arrowhead on XXXpoint 6255 6300 - 7896 4890--> + <!-- Line --> + <polyline + points="17955,6300 16452,5010 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline100" /> + <!-- Arrowhead on XXXpoint 17955 6300 - 16311 4890--> + <!-- Line --> + <polyline + points="4455,11025 4455,7746 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline104" /> + <!-- Arrowhead on XXXpoint 4455 11025 - 4455 7560--> + <!-- Line --> + <polyline + points="19755,9225 19755,7746 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline108" /> + <!-- Arrowhead on XXXpoint 19755 9225 - 19755 7560--> + <!-- Line --> + <polyline + points="17955,11025 17955,7746 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline112" /> + <!-- Arrowhead on XXXpoint 17955 11025 - 17955 7560--> + <!-- Line --> + <polyline + points="15255,9225 15255,7746 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline116" /> + <!-- Arrowhead on XXXpoint 15255 9225 - 15255 7560--> + <!-- Line --> + <polyline + points="13455,11025 13455,7746 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline120" /> + <!-- Arrowhead on XXXpoint 13455 11025 - 13455 7560--> + <!-- Line --> + <polyline + points="10755,9225 10755,7746 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline124" /> + <!-- Arrowhead on XXXpoint 10755 9225 - 10755 7560--> + <!-- Line --> + <polyline + points="8955,11025 8955,7746 " + style="stroke:#00d1d1;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline128" /> + <!-- Arrowhead on XXXpoint 8955 11025 - 8955 7560--> + <!-- Line: box --> + <rect + x="12105" + y="11025" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect132" /> + <!-- Line: box --> + <rect + x="13905" + y="9225" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect134" /> + <!-- Line: box --> + <rect + x="16605" + y="11025" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect136" /> + <!-- Line: box --> + <rect + x="18405" + y="9225" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect138" /> + <!-- Line: box --> + <rect + x="9405" + y="9225" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect140" /> + <!-- Line: box --> + <rect + x="7605" + y="11025" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect142" /> + <!-- Line: box --> + <rect + x="4905" + y="9225" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect144" /> + <!-- Line: box --> + <rect + x="3105" + y="11025" + width="2700" + height="1350" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect146" /> + <!-- Line --> + <polyline + points="3375,1575 10701,1575 " + style="stroke:#000000;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline148" /> + <!-- Arrowhead on XXXpoint 3375 1575 - 10890 1575--> + <!-- Line --> + <polyline + points="3375,3825 4050,3825 4050,5400 2700,5400 2700,6975 3951,6975 " + style="stroke:#000000;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline152" /> + <!-- Arrowhead on XXXpoint 2700 6975 - 4140 6975--> + <!-- Line --> + <polyline + points="3375,2700 5175,2700 5175,4275 7326,4275 " + style="stroke:#000000;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline156" /> + <!-- Arrowhead on XXXpoint 5175 4275 - 7515 4275--> + <!-- Text --> + <text + xml:space="preserve" + x="15480" + y="4500" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text160">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="15480" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text162">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="8730" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text164">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="8730" + y="4500" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text166">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="9855" + y="6750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text168">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="9855" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text170">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="14355" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text172">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="14355" + y="6750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text174">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="18855" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text176">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="18855" + y="6750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text178">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5355" + y="6750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text180">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5355" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text182">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="450" + y="1800" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="324" + text-anchor="start" + id="text184">->level[0]</text> + <!-- Text --> + <text + xml:space="preserve" + x="450" + y="2925" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="324" + text-anchor="start" + id="text186">->level[1]</text> + <!-- Text --> + <text + xml:space="preserve" + x="450" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="324" + text-anchor="start" + id="text188">->level[2]</text> + <!-- Text --> + <text + xml:space="preserve" + x="12105" + y="1350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text190">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="12105" + y="1800" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="middle" + id="text192">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="6255" + y="10125" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text194">CPU 15</text> + <!-- Text --> + <text + xml:space="preserve" + x="4455" + y="11925" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text196">CPU 0</text> + <!-- Text --> + <text + xml:space="preserve" + x="19755" + y="10125" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text198">CPU 65535</text> + <!-- Text --> + <text + xml:space="preserve" + x="17955" + y="11925" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text200">CPU 65519</text> + <!-- Text --> + <text + xml:space="preserve" + x="15255" + y="10125" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text202">CPU 43695</text> + <!-- Text --> + <text + xml:space="preserve" + x="13455" + y="11925" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text204">CPU 43679</text> + <!-- Text --> + <text + xml:space="preserve" + x="10755" + y="10125" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text206">CPU 21839</text> + <!-- Text --> + <text + xml:space="preserve" + x="8955" + y="11925" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text208">CPU 21823</text> + <!-- Text --> + <text + xml:space="preserve" + x="225" + y="450" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="288" + text-anchor="start" + id="text210">struct rcu_state</text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Data-Structures/TreeMapping.svg b/Documentation/RCU/Design/Data-Structures/TreeMapping.svg new file mode 100644 index 0000000..729cfa9 --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/TreeMapping.svg @@ -0,0 +1,305 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:43:22 2015 --> + +<!-- Magnification: 1.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="3.1in" + height="0.9in" + viewBox="-12 -12 3699 1074" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="TreeMapping.fig"> + <metadata + id="metadata66"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title></dc:title> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs64"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow2Lend" + style="overflow:visible;"> + <path + id="path3836" + style="fill-rule:evenodd;stroke-width:0.62500000;stroke-linejoin:round;" + d="M 8.7185878,4.0337352 L -2.2072895,0.016013256 L 8.7185884,-4.0017078 C 6.9730900,-1.6296469 6.9831476,1.6157441 8.7185878,4.0337352 z " + transform="scale(1.1) rotate(180) translate(1,0)" /> + </marker> + <marker + inkscape:stockid="Arrow2Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow2Mend" + style="overflow:visible;"> + <path + id="path3842" + style="fill-rule:evenodd;stroke-width:0.62500000;stroke-linejoin:round;" + d="M 8.7185878,4.0337352 L -2.2072895,0.016013256 L 8.7185884,-4.0017078 C 6.9730900,-1.6296469 6.9831476,1.6157441 8.7185878,4.0337352 z " + transform="scale(0.6) rotate(180) translate(0,0)" /> + </marker> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow1Mend" + style="overflow:visible;"> + <path + id="path3824" + d="M 0.0,0.0 L 5.0,-5.0 L -12.5,0.0 L 5.0,5.0 L 0.0,0.0 z " + style="fill-rule:evenodd;stroke:#000000;stroke-width:1.0pt;" + transform="scale(0.4) rotate(180) translate(10,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="991" + inkscape:window-height="606" + id="namedview62" + showgrid="false" + inkscape:zoom="3.0752688" + inkscape:cx="139.5" + inkscape:cy="40.5" + inkscape:window-x="891" + inkscape:window-y="177" + inkscape:window-maximized="0" + inkscape:current-layer="g4" /> + <g + style="stroke-width:.025in; fill:none" + id="g4"> + <!-- Line: box --> + <rect + x="0" + y="0" + width="3675" + height="1050" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect6" /> + <!-- Line: box --> + <rect + x="75" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect8" /> + <!-- Line: box --> + <rect + x="600" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect10" /> + <!-- Line: box --> + <rect + x="1125" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect12" /> + <!-- Line: box --> + <rect + x="1650" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect14" /> + <!-- Line: box --> + <rect + x="2175" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect16" /> + <!-- Line: box --> + <rect + x="3225" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect18" /> + <!-- Line --> + <polyline + points="675,375 675,150 300,150 300,358 " + style="stroke:#000000;stroke-width:7.00088889;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline20" /> + <!-- Arrowhead on XXXpoint 300 150 - 300 390--> + <!-- Line --> + <polyline + points="1200,675 1200,900 300,900 300,691 " + style="stroke:#000000;stroke-width:7.00088889;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline24" /> + <!-- Arrowhead on XXXpoint 300 900 - 300 660--> + <!-- Line --> + <polyline + points="1725,375 1725,150 900,150 900,358 " + style="stroke:#000000;stroke-width:7.00088889;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline28" /> + <!-- Arrowhead on XXXpoint 900 150 - 900 390--> + <!-- Line --> + <polyline + points="2250,375 2250,75 825,75 825,358 " + style="stroke:#000000;stroke-width:7.00088889;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline32" /> + <!-- Arrowhead on XXXpoint 825 75 - 825 390--> + <!-- Line --> + <polyline + points="2775,675 2775,900 1425,900 1425,691 " + style="stroke:#000000;stroke-width:7.00088889;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline36" /> + <!-- Arrowhead on XXXpoint 1425 900 - 1425 660--> + <!-- Line --> + <polyline + points="3300,675 3300,975 1350,975 1350,691 " + style="stroke:#000000;stroke-width:7.00088889;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline40" /> + <!-- Arrowhead on XXXpoint 1350 975 - 1350 660--> + <!-- Line: box --> + <rect + x="2700" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect44" /> + <!-- Text --> + <text + xml:space="preserve" + x="300" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text46">0:7 </text> + <!-- Text --> + <text + xml:space="preserve" + x="1350" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text48">4:7 </text> + <!-- Text --> + <text + xml:space="preserve" + x="1875" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text50">0:1 </text> + <!-- Text --> + <text + xml:space="preserve" + x="2400" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text52">2:3 </text> + <!-- Text --> + <text + xml:space="preserve" + x="2925" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text54">4:5 </text> + <!-- Text --> + <text + xml:space="preserve" + x="3450" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text56">6:7 </text> + <!-- Text --> + <text + xml:space="preserve" + x="825" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text58">0:3 </text> + <!-- Text --> + <text + xml:space="preserve" + x="3600" + y="150" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="end" + id="text60">struct rcu_state</text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Data-Structures/TreeMappingLevel.svg b/Documentation/RCU/Design/Data-Structures/TreeMappingLevel.svg new file mode 100644 index 0000000..5b416a4 --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/TreeMappingLevel.svg @@ -0,0 +1,380 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:45:19 2015 --> + +<!-- Magnification: 1.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="3.1in" + height="1.8in" + viewBox="-12 -12 3699 2124" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="TreeMappingLevel.svg"> + <metadata + id="metadata98"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs96"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow2Lend" + style="overflow:visible;"> + <path + id="path3868" + style="fill-rule:evenodd;stroke-width:0.62500000;stroke-linejoin:round;" + d="M 8.7185878,4.0337352 L -2.2072895,0.016013256 L 8.7185884,-4.0017078 C 6.9730900,-1.6296469 6.9831476,1.6157441 8.7185878,4.0337352 z " + transform="scale(1.1) rotate(180) translate(1,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="1598" + inkscape:window-height="1211" + id="namedview94" + showgrid="false" + inkscape:zoom="5.2508961" + inkscape:cx="139.5" + inkscape:cy="81" + inkscape:window-x="840" + inkscape:window-y="122" + inkscape:window-maximized="0" + inkscape:current-layer="g4" /> + <g + style="stroke-width:.025in; fill:none" + id="g4"> + <!-- Line: box --> + <rect + x="0" + y="0" + width="3675" + height="2100" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect6" /> + <!-- Line: box --> + <rect + x="75" + y="1350" + width="750" + height="225" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect8" /> + <!-- Line: box --> + <rect + x="75" + y="1575" + width="750" + height="225" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect10" /> + <!-- Line: box --> + <rect + x="75" + y="1800" + width="750" + height="225" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect12" /> + <!-- Arc --> + <path + style="stroke:#000000;stroke-width:7;stroke-linecap:butt;" + d="M 1800,900 A 118 118 0 0 0 1800 1125 " + id="path14" /> + <!-- Arc --> + <path + style="stroke:#000000;stroke-width:7;stroke-linecap:butt;" + d="M 750,900 A 75 75 0 0 0 750 1050 " + id="path16" /> + <!-- Line --> + <polyline + points="750,900 750,691 " + style="stroke:#000000;stroke-width:7.00025806;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline18" /> + <!-- Arrowhead on XXXpoint 750 900 - 750 660--> + <!-- Line: box --> + <rect + x="75" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect22" /> + <!-- Line: box --> + <rect + x="600" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect24" /> + <!-- Line: box --> + <rect + x="1650" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect26" /> + <!-- Line: box --> + <rect + x="2175" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect28" /> + <!-- Line: box --> + <rect + x="3225" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect30" /> + <!-- Line --> + <polyline + points="675,375 675,150 300,150 300,358 " + style="stroke:#000000;stroke-width:7.00025806;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline32" /> + <!-- Arrowhead on XXXpoint 300 150 - 300 390--> + <!-- Line --> + <polyline + points="1725,375 1725,150 900,150 900,358 " + style="stroke:#000000;stroke-width:7.00025806;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline36" /> + <!-- Arrowhead on XXXpoint 900 150 - 900 390--> + <!-- Line --> + <polyline + points="2250,375 2250,75 825,75 825,358 " + style="stroke:#000000;stroke-width:7.00025806;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline40" /> + <!-- Arrowhead on XXXpoint 825 75 - 825 390--> + <!-- Line --> + <polyline + points="2775,675 2775,975 1425,975 1425,691 " + style="stroke:#000000;stroke-width:7.00025806;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline44" /> + <!-- Arrowhead on XXXpoint 1425 975 - 1425 660--> + <!-- Line: box --> + <rect + x="2700" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect48" /> + <!-- Line: box --> + <rect + x="1125" + y="375" + width="375" + height="300" + rx="0" + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect50" /> + <!-- Line --> + <polyline + points="3300,675 3300,1050 1350,1050 1350,691 " + style="stroke:#000000;stroke-width:7.00025806;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline52" /> + <!-- Arrowhead on XXXpoint 1350 1050 - 1350 660--> + <!-- Line --> + <polyline + points="825,1425 975,1425 975,1200 225,1200 225,691 " + style="stroke:#000000;stroke-width:7.00025806;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline56" /> + <!-- Arrowhead on XXXpoint 225 1200 - 225 660--> + <!-- Line --> + <polyline + points="1200,675 1200,975 300,975 300,691 " + style="stroke:#000000;stroke-width:7.00025806;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline60" /> + <!-- Arrowhead on XXXpoint 300 975 - 300 660--> + <!-- Text --> + <text + xml:space="preserve" + x="150" + y="1500" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="108" + text-anchor="start" + id="text64">->level[0]</text> + <!-- Text --> + <text + xml:space="preserve" + x="150" + y="1725" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="108" + text-anchor="start" + id="text66">->level[1]</text> + <!-- Text --> + <text + xml:space="preserve" + x="150" + y="1950" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="108" + text-anchor="start" + id="text68">->level[2]</text> + <!-- Text --> + <text + xml:space="preserve" + x="300" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text70">0:7 </text> + <!-- Text --> + <text + xml:space="preserve" + x="1350" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text72">4:7 </text> + <!-- Text --> + <text + xml:space="preserve" + x="1875" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text74">0:1 </text> + <!-- Text --> + <text + xml:space="preserve" + x="2400" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text76">2:3 </text> + <!-- Text --> + <text + xml:space="preserve" + x="2925" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text78">4:5 </text> + <!-- Text --> + <text + xml:space="preserve" + x="3450" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text80">6:7 </text> + <!-- Text --> + <text + xml:space="preserve" + x="825" + y="525" + fill="#000000" + font-family="Times" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="middle" + id="text82">0:3 </text> + <!-- Text --> + <text + xml:space="preserve" + x="3600" + y="150" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="normal" + font-size="96" + text-anchor="end" + id="text84">struct rcu_state</text> + <!-- Line --> + <polyline + points="825,1875 1800,1875 1800,1125 " + style="stroke:#000000;stroke-width:7.00025806;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:none" + id="polyline86" /> + <!-- Line --> + <polyline + points="1800,900 1800,691 " + style="stroke:#000000;stroke-width:7.00025806;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Lend)" + id="polyline88" /> + <!-- Arrowhead on XXXpoint 1800 900 - 1800 660--> + <!-- Line --> + <polyline + points="825,1650 1200,1650 1200,1125 750,1125 750,1050 " + style="stroke:#000000;stroke-width:7; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline92" /> + </g> +</svg> diff --git a/Documentation/RCU/Design/Data-Structures/blkd_task.svg b/Documentation/RCU/Design/Data-Structures/blkd_task.svg new file mode 100644 index 0000000..00e810b --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/blkd_task.svg @@ -0,0 +1,843 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:35:03 2015 --> + +<!-- Magnification: 2.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="10.1in" + height="8.6in" + viewBox="-44 -44 12088 10288" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="blkd_task.fig"> + <metadata + id="metadata212"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title></dc:title> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs210"> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow1Mend" + style="overflow:visible;"> + <path + id="path3970" + d="M 0.0,0.0 L 5.0,-5.0 L -12.5,0.0 L 5.0,5.0 L 0.0,0.0 z " + style="fill-rule:evenodd;stroke:#000000;stroke-width:1.0pt;" + transform="scale(0.4) rotate(180) translate(10,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="1087" + inkscape:window-height="1144" + id="namedview208" + showgrid="false" + inkscape:zoom="1.0495049" + inkscape:cx="454.50003" + inkscape:cy="387.00003" + inkscape:window-x="833" + inkscape:window-y="28" + inkscape:window-maximized="0" + inkscape:current-layer="g4" /> + <g + style="stroke-width:.025in; fill:none" + id="g4"> + <!-- Line: box --> + <rect + x="450" + y="0" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect6" /> + <!-- Line: box --> + <rect + x="4950" + y="4950" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect8" /> + <!-- Line: box --> + <rect + x="750" + y="600" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect10" /> + <!-- Line --> + <polyline + points="5250,8100 5688,5912 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline12" /> + <!-- Arrowhead on XXXpoint 5250 8100 - 5710 5790--> + <polyline + points="5714 6068 5704 5822 5598 6044 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline14" /> + <!-- Line --> + <polyline + points="4050,9300 4486,7262 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline16" /> + <!-- Arrowhead on XXXpoint 4050 9300 - 4512 7140--> + <polyline + points="4514 7418 4506 7172 4396 7394 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline18" /> + <!-- Line --> + <polyline + points="1040,9300 1476,7262 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline20" /> + <!-- Arrowhead on XXXpoint 1040 9300 - 1502 7140--> + <polyline + points="1504 7418 1496 7172 1386 7394 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline22" /> + <!-- Line --> + <polyline + points="2240,8100 2676,6062 " + style="stroke:#00ff00;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="polyline24" /> + <!-- Arrowhead on XXXpoint 2240 8100 - 2702 5940--> + <polyline + points="2704 6218 2696 5972 2586 6194 " + style="stroke:#00ff00;stroke-width:14;stroke-miterlimit:8; " + id="polyline26" /> + <!-- Line: box --> + <rect + x="0" + y="450" + width="6300" + height="7350" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffffff; " + id="rect28" /> + <!-- Line: box --> + <rect + x="300" + y="1050" + width="5700" + height="3750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffff00; " + id="rect30" /> + <!-- Line --> + <polyline + points="1350,3450 2350,2590 " + style="stroke:#00d1d1;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline32" /> + <!-- Arrowhead on XXXpoint 1350 3450 - 2444 2510--> + <!-- Line --> + <polyline + points="4950,3450 3948,2590 " + style="stroke:#00d1d1;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline36" /> + <!-- Arrowhead on XXXpoint 4950 3450 - 3854 2510--> + <!-- Line --> + <polyline + points="4050,6600 4050,4414 " + style="stroke:#00d1d1;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline40" /> + <!-- Arrowhead on XXXpoint 4050 6600 - 4050 4290--> + <!-- Line --> + <polyline + points="1050,6600 1050,4414 " + style="stroke:#00d1d1;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline44" /> + <!-- Arrowhead on XXXpoint 1050 6600 - 1050 4290--> + <!-- Line --> + <polyline + points="2250,5400 2250,4414 " + style="stroke:#00d1d1;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline48" /> + <!-- Arrowhead on XXXpoint 2250 5400 - 2250 4290--> + <!-- Line --> + <polyline + points="2250,8100 2250,6364 " + style="stroke:#00ff00;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline52" /> + <!-- Arrowhead on XXXpoint 2250 8100 - 2250 6240--> + <!-- Line --> + <polyline + points="1050,9300 1050,7564 " + style="stroke:#00ff00;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline56" /> + <!-- Arrowhead on XXXpoint 1050 9300 - 1050 7440--> + <!-- Line --> + <polyline + points="4050,9300 4050,7564 " + style="stroke:#00ff00;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline60" /> + <!-- Arrowhead on XXXpoint 4050 9300 - 4050 7440--> + <!-- Line --> + <polyline + points="5250,8100 5250,6364 " + style="stroke:#00ff00;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline64" /> + <!-- Arrowhead on XXXpoint 5250 8100 - 5250 6240--> + <!-- Circle --> + <circle + cx="2850" + cy="3900" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle68" /> + <!-- Circle --> + <circle + cx="3150" + cy="3900" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle70" /> + <!-- Circle --> + <circle + cx="3450" + cy="3900" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle72" /> + <!-- Circle --> + <circle + cx="1350" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle74" /> + <!-- Circle --> + <circle + cx="1650" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle76" /> + <!-- Circle --> + <circle + cx="1950" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle78" /> + <!-- Circle --> + <circle + cx="4350" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle80" /> + <!-- Circle --> + <circle + cx="4650" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle82" /> + <!-- Circle --> + <circle + cx="4950" + cy="5100" + r="76" + style="fill:#000000;stroke:#000000;stroke-width:14;" + id="circle84" /> + <!-- Line: box --> + <rect + x="750" + y="3450" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect86" /> + <!-- Line: box --> + <rect + x="300" + y="6600" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect88" /> + <!-- Line: box --> + <rect + x="4500" + y="5400" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect90" /> + <!-- Line: box --> + <rect + x="3300" + y="6600" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect92" /> + <!-- Line: box --> + <rect + x="2250" + y="1650" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect94" /> + <!-- Line: box --> + <rect + x="0" + y="9300" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect96" /> + <!-- Line: box --> + <rect + x="1350" + y="8100" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect98" /> + <!-- Line: box --> + <rect + x="3000" + y="9300" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect100" /> + <!-- Line: box --> + <rect + x="4350" + y="8100" + width="2100" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#00ff00; " + id="rect102" /> + <!-- Line: box --> + <rect + x="1500" + y="5400" + width="1500" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect104" /> + <!-- Line --> + <polygon + points="5550,3450 7350,2850 7350,5100 5550,4350 5550,3450 " + style="stroke:#000000;stroke-width:14; stroke-linejoin:miter; stroke-linecap:butt; stroke-dasharray:120 120;fill:#ffbfbf; " + id="polygon106" /> + <!-- Line --> + <polyline + points="9300,3150 10734,3150 " + style="stroke:#000000;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline108" /> + <!-- Arrowhead on XXXpoint 9300 3150 - 10860 3150--> + <!-- Line: box --> + <rect + x="10800" + y="2850" + width="1200" + height="750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect112" /> + <!-- Line --> + <polyline + points="11400,3600 11400,4284 " + style="stroke:#000000;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline114" /> + <!-- Arrowhead on XXXpoint 11400 3600 - 11400 4410--> + <!-- Line: box --> + <rect + x="10800" + y="4350" + width="1200" + height="750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect118" /> + <!-- Line --> + <polyline + points="11400,5100 11400,5784 " + style="stroke:#000000;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline120" /> + <!-- Arrowhead on XXXpoint 11400 5100 - 11400 5910--> + <!-- Line: box --> + <rect + x="10800" + y="5850" + width="1200" + height="750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect124" /> + <!-- Line --> + <polyline + points="9300,3900 9900,3900 9900,4650 10734,4650 " + style="stroke:#000000;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline126" /> + <!-- Arrowhead on XXXpoint 9900 4650 - 10860 4650--> + <!-- Line --> + <polyline + points="9300,4650 9600,4650 9600,6150 10734,6150 " + style="stroke:#000000;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline130" /> + <!-- Arrowhead on XXXpoint 9600 6150 - 10860 6150--> + <!-- Text --> + <text + xml:space="preserve" + x="6450" + y="300" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text134">rcu_bh</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="1950" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text136">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="3150" + y="2250" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text138">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="1650" + y="3750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text140">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1650" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text142">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="5700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text144">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2250" + y="6000" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text146">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="6900" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text148">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text150">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="5250" + y="5700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text152">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5250" + y="6000" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text154">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="6900" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text156">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="7200" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text158">rcu_data</text> + <!-- Text --> + <text + xml:space="preserve" + x="450" + y="1350" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="start" + id="text160">struct rcu_state</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="9600" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text162">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="1050" + y="9900" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text164">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="9600" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text166">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="4050" + y="9900" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text168">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="2400" + y="8400" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text170">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="2400" + y="8700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text172">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="5400" + y="8400" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text174">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="5400" + y="8700" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text176">rcu_dynticks</text> + <!-- Text --> + <text + xml:space="preserve" + x="6000" + y="750" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="192" + text-anchor="end" + id="text178">rcu_sched</text> + <!-- Text --> + <text + xml:space="preserve" + x="11400" + y="3300" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="216" + text-anchor="middle" + id="text180">T3</text> + <!-- Text --> + <text + xml:space="preserve" + x="11400" + y="4800" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="216" + text-anchor="middle" + id="text182">T2</text> + <!-- Text --> + <text + xml:space="preserve" + x="11400" + y="6300" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="216" + text-anchor="middle" + id="text184">T1</text> + <!-- Line --> + <polyline + points="5250,5400 5250,4414 " + style="stroke:#00d1d1;stroke-width:30.00057884;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline186" /> + <!-- Arrowhead on XXXpoint 5250 5400 - 5250 4290--> + <!-- Line: box --> + <rect + x="3750" + y="3450" + width="1800" + height="900" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect190" /> + <!-- Line: box --> + <rect + x="7350" + y="2850" + width="1950" + height="750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect192" /> + <!-- Line: box --> + <rect + x="7350" + y="3600" + width="1950" + height="750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect194" /> + <!-- Line: box --> + <rect + x="7350" + y="4350" + width="1950" + height="750" + rx="0" + style="stroke:#000000;stroke-width:30; stroke-linejoin:miter; stroke-linecap:butt; fill:#ffbfbf; " + id="rect196" /> + <!-- Text --> + <text + xml:space="preserve" + x="4650" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text198">rcu_node</text> + <!-- Text --> + <text + xml:space="preserve" + x="4650" + y="3750" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="middle" + id="text200">struct</text> + <!-- Text --> + <text + xml:space="preserve" + x="7500" + y="3300" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="start" + id="text202">blkd_tasks</text> + <!-- Text --> + <text + xml:space="preserve" + x="7500" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="start" + id="text204">gp_tasks</text> + <!-- Text --> + <text + xml:space="preserve" + x="7500" + y="4800" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="192" + text-anchor="start" + id="text206">exp_tasks</text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Data-Structures/nxtlist.svg b/Documentation/RCU/Design/Data-Structures/nxtlist.svg new file mode 100644 index 0000000..abc4cc7 --- /dev/null +++ b/Documentation/RCU/Design/Data-Structures/nxtlist.svg @@ -0,0 +1,396 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5e --> + +<!-- CreationDate: Wed Dec 9 17:39:46 2015 --> + +<!-- Magnification: 3.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="10.4in" + height="10.4in" + viewBox="-66 -66 12507 12507" + id="svg2" + version="1.1" + inkscape:version="0.48.4 r9939" + sodipodi:docname="nxtlist.fig"> + <metadata + id="metadata94"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title></dc:title> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs92"> + <marker + inkscape:stockid="Arrow1Mend" + orient="auto" + refY="0.0" + refX="0.0" + id="Arrow1Mend" + style="overflow:visible;"> + <path + id="path3852" + d="M 0.0,0.0 L 5.0,-5.0 L -12.5,0.0 L 5.0,5.0 L 0.0,0.0 z " + style="fill-rule:evenodd;stroke:#000000;stroke-width:1.0pt;" + transform="scale(0.4) rotate(180) translate(10,0)" /> + </marker> + </defs> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="925" + inkscape:window-height="928" + id="namedview90" + showgrid="false" + inkscape:zoom="0.80021373" + inkscape:cx="467.99997" + inkscape:cy="467.99997" + inkscape:window-x="948" + inkscape:window-y="73" + inkscape:window-maximized="0" + inkscape:current-layer="g4" /> + <g + style="stroke-width:.025in; fill:none" + id="g4"> + <!-- Line: box --> + <rect + x="0" + y="0" + width="7875" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect6" /> + <!-- Line: box --> + <rect + x="0" + y="1125" + width="7875" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect8" /> + <!-- Line: box --> + <rect + x="0" + y="2250" + width="7875" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect10" /> + <!-- Line: box --> + <rect + x="0" + y="3375" + width="7875" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect12" /> + <!-- Line: box --> + <rect + x="0" + y="4500" + width="7875" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; fill:#87cfff; " + id="rect14" /> + <!-- Line: box --> + <rect + x="10575" + y="0" + width="1800" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect16" /> + <!-- Line: box --> + <rect + x="10575" + y="1125" + width="1800" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect18" /> + <!-- Line --> + <polyline + points="11475,2250 11475,3276 " + style="stroke:#000000;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline20" /> + <!-- Arrowhead on XXXpoint 11475 2250 - 11475 3465--> + <!-- Line: box --> + <rect + x="10575" + y="6750" + width="1800" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect24" /> + <!-- Line: box --> + <rect + x="10575" + y="7875" + width="1800" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect26" /> + <!-- Line: box --> + <rect + x="10575" + y="10125" + width="1800" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect28" /> + <!-- Line: box --> + <rect + x="10575" + y="11250" + width="1800" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect30" /> + <!-- Line: box --> + <rect + x="10575" + y="3375" + width="1800" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect32" /> + <!-- Line --> + <polyline + points="11475,5625 11475,6651 " + style="stroke:#000000;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline34" /> + <!-- Arrowhead on XXXpoint 11475 5625 - 11475 6840--> + <!-- Line --> + <polyline + points="7875,225 10476,225 " + style="stroke:#000000;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline38" /> + <!-- Arrowhead on XXXpoint 7875 225 - 10665 225--> + <!-- Line --> + <polyline + points="7875,1350 9675,1350 9675,675 7971,675 " + style="stroke:#000000;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline42" /> + <!-- Arrowhead on XXXpoint 9675 675 - 7785 675--> + <!-- Line --> + <polyline + points="7875,2475 9675,2475 9675,4725 10476,4725 " + style="stroke:#000000;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline46" /> + <!-- Arrowhead on XXXpoint 9675 4725 - 10665 4725--> + <!-- Line --> + <polyline + points="7875,3600 9225,3600 9225,5175 10476,5175 " + style="stroke:#000000;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline50" /> + <!-- Arrowhead on XXXpoint 9225 5175 - 10665 5175--> + <!-- Line --> + <polyline + points="7875,4725 8775,4725 8775,11475 10476,11475 " + style="stroke:#000000;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline54" /> + <!-- Arrowhead on XXXpoint 8775 11475 - 10665 11475--> + <!-- Line: box --> + <rect + x="10575" + y="4500" + width="1800" + height="1125" + rx="0" + style="stroke:#000000;stroke-width:45; stroke-linejoin:miter; stroke-linecap:butt; " + id="rect58" /> + <!-- Line --> + <polyline + points="11475,9000 11475,10026 " + style="stroke:#000000;stroke-width:45.00382345;stroke-linejoin:miter;stroke-linecap:butt;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow1Mend)" + id="polyline60" /> + <!-- Arrowhead on XXXpoint 11475 9000 - 11475 10215--> + <!-- Text --> + <text + xml:space="preserve" + x="225" + y="675" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="324" + text-anchor="start" + id="text64">nxtlist</text> + <!-- Text --> + <text + xml:space="preserve" + x="225" + y="1800" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="324" + text-anchor="start" + id="text66">nxttail[RCU_DONE_TAIL]</text> + <!-- Text --> + <text + xml:space="preserve" + x="225" + y="2925" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="324" + text-anchor="start" + id="text68">nxttail[RCU_WAIT_TAIL]</text> + <!-- Text --> + <text + xml:space="preserve" + x="225" + y="4050" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="324" + text-anchor="start" + id="text70">nxttail[RCU_NEXT_READY_TAIL]</text> + <!-- Text --> + <text + xml:space="preserve" + x="225" + y="5175" + fill="#000000" + font-family="Courier" + font-style="normal" + font-weight="bold" + font-size="324" + text-anchor="start" + id="text72">nxttail[RCU_NEXT_TAIL]</text> + <!-- Text --> + <text + xml:space="preserve" + x="11475" + y="675" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text74">CB 1</text> + <!-- Text --> + <text + xml:space="preserve" + x="11475" + y="1800" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text76">next</text> + <!-- Text --> + <text + xml:space="preserve" + x="11475" + y="7425" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text78">CB 3</text> + <!-- Text --> + <text + xml:space="preserve" + x="11475" + y="8550" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text80">next</text> + <!-- Text --> + <text + xml:space="preserve" + x="11475" + y="10800" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text82">CB 4</text> + <!-- Text --> + <text + xml:space="preserve" + x="11475" + y="11925" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text84">next</text> + <!-- Text --> + <text + xml:space="preserve" + x="11475" + y="4050" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text86">CB 2</text> + <!-- Text --> + <text + xml:space="preserve" + x="11475" + y="5175" + fill="#000000" + font-family="Helvetica" + font-style="normal" + font-weight="normal" + font-size="324" + text-anchor="middle" + id="text88">next</text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png b/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png Binary files differdeleted file mode 100644 index 7496a55..0000000 --- a/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png +++ /dev/null diff --git a/Documentation/RCU/Design/Requirements/RCUApplicability.svg b/Documentation/RCU/Design/Requirements/RCUApplicability.svg deleted file mode 100644 index ebcbeee..0000000 --- a/Documentation/RCU/Design/Requirements/RCUApplicability.svg +++ /dev/null @@ -1,237 +0,0 @@ -<?xml version="1.0" encoding="UTF-8" standalone="no"?> -<!-- Creator: fig2dev Version 3.2 Patchlevel 5d --> - -<!-- CreationDate: Tue Mar 4 18:34:25 2014 --> - -<!-- Magnification: 3.000 --> - -<svg - xmlns:dc="http://purl.org/dc/elements/1.1/" - xmlns:cc="http://creativecommons.org/ns#" - xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" - xmlns:svg="http://www.w3.org/2000/svg" - xmlns="http://www.w3.org/2000/svg" - xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" - xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" - width="1089.1382" - height="668.21368" - viewBox="-2121 -36 14554.634 8876.4061" - id="svg2" - version="1.1" - inkscape:version="0.48.3.1 r9886" - sodipodi:docname="RCUApplicability.svg"> - <metadata - id="metadata40"> - <rdf:RDF> - <cc:Work - rdf:about=""> - <dc:format>image/svg+xml</dc:format> - <dc:type - rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> - <dc:title /> - </cc:Work> - </rdf:RDF> - </metadata> - <defs - id="defs38" /> - <sodipodi:namedview - pagecolor="#ffffff" - bordercolor="#666666" - borderopacity="1" - objecttolerance="10" - gridtolerance="10" - guidetolerance="10" - inkscape:pageopacity="0" - inkscape:pageshadow="2" - inkscape:window-width="849" - inkscape:window-height="639" - id="namedview36" - showgrid="false" - inkscape:zoom="0.51326165" - inkscape:cx="544.56912" - inkscape:cy="334.10686" - inkscape:window-x="149" - inkscape:window-y="448" - inkscape:window-maximized="0" - inkscape:current-layer="g4" - fit-margin-top="5" - fit-margin-left="5" - fit-margin-right="5" - fit-margin-bottom="5" /> - <g - style="fill:none;stroke-width:0.025in" - id="g4" - transform="translate(-2043.6828,14.791398)"> - <!-- Line: box --> - <rect - x="0" - y="0" - width="14400" - height="8775" - rx="0" - style="fill:#ffa1a1;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter" - id="rect6" /> - <!-- Line: box --> - <rect - x="1350" - y="0" - width="11700" - height="6075" - rx="0" - style="fill:#ffff00;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter" - id="rect8" /> - <!-- Line: box --> - <rect - x="2700" - y="0" - width="9000" - height="4275" - rx="0" - style="fill:#00ff00;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter" - id="rect10" /> - <!-- Line: box --> - <rect - x="4050" - y="0" - width="6300" - height="2475" - rx="0" - style="fill:#87cfff;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter" - id="rect12" /> - <!-- Text --> - <text - xml:space="preserve" - x="7200" - y="900" - font-style="normal" - font-weight="normal" - font-size="324" - id="text14" - sodipodi:linespacing="125%" - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" - id="tspan3017">Read-Mostly, Stale &</tspan></text> - <!-- Text --> - <text - xml:space="preserve" - x="7200" - y="1350" - font-style="normal" - font-weight="normal" - font-size="324" - id="text16" - sodipodi:linespacing="125%" - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" - id="tspan3019">Inconsistent Data OK</tspan></text> - <!-- Text --> - <text - xml:space="preserve" - x="7200" - y="1800" - font-style="normal" - font-weight="normal" - font-size="324" - id="text18" - sodipodi:linespacing="125%" - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" - id="tspan3021">(RCU Works Great!!!)</tspan></text> - <!-- Text --> - <text - xml:space="preserve" - x="7200" - y="3825" - font-style="normal" - font-weight="normal" - font-size="324" - id="text20" - sodipodi:linespacing="125%" - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" - id="tspan3023">(RCU Works Well)</tspan></text> - <!-- Text --> - <text - xml:space="preserve" - x="7200" - y="3375" - font-style="normal" - font-weight="normal" - font-size="324" - id="text22" - sodipodi:linespacing="125%" - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" - id="tspan3025">Read-Mostly, Need Consistent Data</tspan></text> - <!-- Text --> - <text - xml:space="preserve" - x="7200" - y="5175" - font-style="normal" - font-weight="normal" - font-size="324" - id="text24" - sodipodi:linespacing="125%" - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" - id="tspan3027">Read-Write, Need Consistent Data</tspan></text> - <!-- Text --> - <text - xml:space="preserve" - x="7200" - y="6975" - font-style="normal" - font-weight="normal" - font-size="324" - id="text26" - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" - sodipodi:linespacing="125%">Update-Mostly, Need Consistent Data</text> - <!-- Text --> - <text - xml:space="preserve" - x="7200" - y="5625" - font-style="normal" - font-weight="normal" - font-size="324" - id="text28" - sodipodi:linespacing="125%" - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" - id="tspan3029">(RCU Might Be OK...)</tspan></text> - <!-- Text --> - <text - xml:space="preserve" - x="7200" - y="7875" - font-style="normal" - font-weight="normal" - font-size="324" - id="text30" - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" - sodipodi:linespacing="125%">(1) Provide Existence Guarantees For Update-Friendly Mechanisms</text> - <!-- Text --> - <text - xml:space="preserve" - x="7200" - y="8325" - font-style="normal" - font-weight="normal" - font-size="324" - id="text32" - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" - sodipodi:linespacing="125%">(2) Provide Wait-Free Read-Side Primitives for Real-Time Use)</text> - <!-- Text --> - <text - xml:space="preserve" - x="7200" - y="7425" - font-style="normal" - font-weight="normal" - font-size="324" - id="text34" - style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" - sodipodi:linespacing="125%">(RCU is Very Unlikely to be the Right Tool For The Job, But it Can:</text> - </g> -</svg> diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html index a725f99..e7e24b3 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.html +++ b/Documentation/RCU/Design/Requirements/Requirements.html @@ -1,5 +1,3 @@ -<!-- DO NOT HAND EDIT. --> -<!-- Instead, edit Documentation/RCU/Design/Requirements/Requirements.htmlx and run 'sh htmlqqz.sh Documentation/RCU/Design/Requirements/Requirements' --> <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> <html> @@ -65,8 +63,8 @@ All that aside, here are the categories of currently known RCU requirements: <p> This is followed by a <a href="#Summary">summary</a>, -which is in turn followed by the inevitable -<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>. +however, the answers to each quick quiz immediately follows the quiz. +Select the big white space with your mouse to see the answer. <h2><a name="Fundamental Requirements">Fundamental Requirements</a></h2> @@ -153,13 +151,27 @@ Therefore, the outcome: </blockquote> cannot happen. -<p><a name="Quick Quiz 1"><b>Quick Quiz 1</b>:</a> -Wait a minute! -You said that updaters can make useful forward progress concurrently -with readers, but pre-existing readers will block -<tt>synchronize_rcu()</tt>!!! -Just who are you trying to fool??? -<br><a href="#qq1answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Wait a minute! + You said that updaters can make useful forward progress concurrently + with readers, but pre-existing readers will block + <tt>synchronize_rcu()</tt>!!! + Just who are you trying to fool??? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + First, if updaters do not wish to be blocked by readers, they can use + <tt>call_rcu()</tt> or <tt>kfree_rcu()</tt>, which will + be discussed later. + Second, even when using <tt>synchronize_rcu()</tt>, the other + update-side code does run concurrently with readers, whether + pre-existing or not. +</font></td></tr> +<tr><td> </td></tr> +</table> <p> This scenario resembles one of the first uses of RCU in @@ -210,9 +222,20 @@ to guarantee that <tt>do_something()</tt> never runs concurrently with <tt>recovery()</tt>, but with little or no synchronization overhead in <tt>do_something_dlm()</tt>. -<p><a name="Quick Quiz 2"><b>Quick Quiz 2</b>:</a> -Why is the <tt>synchronize_rcu()</tt> on line 28 needed? -<br><a href="#qq2answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Why is the <tt>synchronize_rcu()</tt> on line 28 needed? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Without that extra grace period, memory reordering could result in + <tt>do_something_dlm()</tt> executing <tt>do_something()</tt> + concurrently with the last bits of <tt>recovery()</tt>. +</font></td></tr> +<tr><td> </td></tr> +</table> <p> In order to avoid fatal problems such as deadlocks, @@ -332,12 +355,27 @@ It also prevents any number of “interesting” compiler optimizations, for example, the use of <tt>gp</tt> as a scratch location immediately preceding the assignment. -<p><a name="Quick Quiz 3"><b>Quick Quiz 3</b>:</a> -But <tt>rcu_assign_pointer()</tt> does nothing to prevent the -two assignments to <tt>p->a</tt> and <tt>p->b</tt> -from being reordered. -Can't that also cause problems? -<br><a href="#qq3answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + But <tt>rcu_assign_pointer()</tt> does nothing to prevent the + two assignments to <tt>p->a</tt> and <tt>p->b</tt> + from being reordered. + Can't that also cause problems? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + No, it cannot. + The readers cannot see either of these two fields until + the assignment to <tt>gp</tt>, by which time both fields are + fully initialized. + So reordering the assignments + to <tt>p->a</tt> and <tt>p->b</tt> cannot possibly + cause any problems. +</font></td></tr> +<tr><td> </td></tr> +</table> <p> It is tempting to assume that the reader need not do anything special @@ -494,11 +532,42 @@ The <tt>rcu_access_pointer()</tt> on line 6 is similar to code protected by the corresponding update-side lock. </ol> -<p><a name="Quick Quiz 4"><b>Quick Quiz 4</b>:</a> -Without the <tt>rcu_dereference()</tt> or the -<tt>rcu_access_pointer()</tt>, what destructive optimizations -might the compiler make use of? -<br><a href="#qq4answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Without the <tt>rcu_dereference()</tt> or the + <tt>rcu_access_pointer()</tt>, what destructive optimizations + might the compiler make use of? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Let's start with what happens to <tt>do_something_gp()</tt> + if it fails to use <tt>rcu_dereference()</tt>. + It could reuse a value formerly fetched from this same pointer. + It could also fetch the pointer from <tt>gp</tt> in a byte-at-a-time + manner, resulting in <i>load tearing</i>, in turn resulting a bytewise + mash-up of two distince pointer values. + It might even use value-speculation optimizations, where it makes + a wrong guess, but by the time it gets around to checking the + value, an update has changed the pointer to match the wrong guess. + Too bad about any dereferences that returned pre-initialization garbage + in the meantime! + </font> + + <p><font color="ffffff"> + For <tt>remove_gp_synchronous()</tt>, as long as all modifications + to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>, + the above optimizations are harmless. + However, + with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt>, + <tt>sparse</tt> will complain if you + define <tt>gp</tt> with <tt>__rcu</tt> and then + access it without using + either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>. +</font></td></tr> +<tr><td> </td></tr> +</table> <p> In short, RCU's publish-subscribe guarantee is provided by the combination @@ -571,17 +640,156 @@ systems with more than one CPU: <tt>synchronize_rcu()</tt> migrates in the meantime. </ol> -<p><a name="Quick Quiz 5"><b>Quick Quiz 5</b>:</a> -Given that multiple CPUs can start RCU read-side critical sections -at any time without any ordering whatsoever, how can RCU possibly tell whether -or not a given RCU read-side critical section starts before a -given instance of <tt>synchronize_rcu()</tt>? -<br><a href="#qq5answer">Answer</a> - -<p><a name="Quick Quiz 6"><b>Quick Quiz 6</b>:</a> -The first and second guarantees require unbelievably strict ordering! -Are all these memory barriers <i> really</i> required? -<br><a href="#qq6answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Given that multiple CPUs can start RCU read-side critical sections + at any time without any ordering whatsoever, how can RCU possibly + tell whether or not a given RCU read-side critical section starts + before a given instance of <tt>synchronize_rcu()</tt>? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + If RCU cannot tell whether or not a given + RCU read-side critical section starts before a + given instance of <tt>synchronize_rcu()</tt>, + then it must assume that the RCU read-side critical section + started first. + In other words, a given instance of <tt>synchronize_rcu()</tt> + can avoid waiting on a given RCU read-side critical section only + if it can prove that <tt>synchronize_rcu()</tt> started first. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + The first and second guarantees require unbelievably strict ordering! + Are all these memory barriers <i> really</i> required? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Yes, they really are required. + To see why the first guarantee is required, consider the following + sequence of events: + </font> + + <ol> + <li> <font color="ffffff"> + CPU 1: <tt>rcu_read_lock()</tt> + </font> + <li> <font color="ffffff"> + CPU 1: <tt>q = rcu_dereference(gp); + /* Very likely to return p. */</tt> + </font> + <li> <font color="ffffff"> + CPU 0: <tt>list_del_rcu(p);</tt> + </font> + <li> <font color="ffffff"> + CPU 0: <tt>synchronize_rcu()</tt> starts. + </font> + <li> <font color="ffffff"> + CPU 1: <tt>do_something_with(q->a); + /* No smp_mb(), so might happen after kfree(). */</tt> + </font> + <li> <font color="ffffff"> + CPU 1: <tt>rcu_read_unlock()</tt> + </font> + <li> <font color="ffffff"> + CPU 0: <tt>synchronize_rcu()</tt> returns. + </font> + <li> <font color="ffffff"> + CPU 0: <tt>kfree(p);</tt> + </font> + </ol> + + <p><font color="ffffff"> + Therefore, there absolutely must be a full memory barrier between the + end of the RCU read-side critical section and the end of the + grace period. + </font> + + <p><font color="ffffff"> + The sequence of events demonstrating the necessity of the second rule + is roughly similar: + </font> + + <ol> + <li> <font color="ffffff">CPU 0: <tt>list_del_rcu(p);</tt> + </font> + <li> <font color="ffffff">CPU 0: <tt>synchronize_rcu()</tt> starts. + </font> + <li> <font color="ffffff">CPU 1: <tt>rcu_read_lock()</tt> + </font> + <li> <font color="ffffff">CPU 1: <tt>q = rcu_dereference(gp); + /* Might return p if no memory barrier. */</tt> + </font> + <li> <font color="ffffff">CPU 0: <tt>synchronize_rcu()</tt> returns. + </font> + <li> <font color="ffffff">CPU 0: <tt>kfree(p);</tt> + </font> + <li> <font color="ffffff"> + CPU 1: <tt>do_something_with(q->a); /* Boom!!! */</tt> + </font> + <li> <font color="ffffff">CPU 1: <tt>rcu_read_unlock()</tt> + </font> + </ol> + + <p><font color="ffffff"> + And similarly, without a memory barrier between the beginning of the + grace period and the beginning of the RCU read-side critical section, + CPU 1 might end up accessing the freelist. + </font> + + <p><font color="ffffff"> + The “as if” rule of course applies, so that any + implementation that acts as if the appropriate memory barriers + were in place is a correct implementation. + That said, it is much easier to fool yourself into believing + that you have adhered to the as-if rule than it is to actually + adhere to it! +</font></td></tr> +<tr><td> </td></tr> +</table> + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + You claim that <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt> + generate absolutely no code in some kernel builds. + This means that the compiler might arbitrarily rearrange consecutive + RCU read-side critical sections. + Given such rearrangement, if a given RCU read-side critical section + is done, how can you be sure that all prior RCU read-side critical + sections are done? + Won't the compiler rearrangements make that impossible to determine? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + In cases where <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt> + generate absolutely no code, RCU infers quiescent states only at + special locations, for example, within the scheduler. + Because calls to <tt>schedule()</tt> had better prevent calling-code + accesses to shared variables from being rearranged across the call to + <tt>schedule()</tt>, if RCU detects the end of a given RCU read-side + critical section, it will necessarily detect the end of all prior + RCU read-side critical sections, no matter how aggressively the + compiler scrambles the code. + </font> + + <p><font color="ffffff"> + Again, this all assumes that the compiler cannot scramble code across + calls to the scheduler, out of interrupt handlers, into the idle loop, + into user-mode code, and so on. + But if your kernel build allows that sort of scrambling, you have broken + far more than just RCU! +</font></td></tr> +<tr><td> </td></tr> +</table> <p> Note that these memory-barrier requirements do not replace the fundamental @@ -626,9 +834,19 @@ inconvenience can be avoided through use of the <tt>call_rcu()</tt> and <tt>kfree_rcu()</tt> API members described later in this document. -<p><a name="Quick Quiz 7"><b>Quick Quiz 7</b>:</a> -But how does the upgrade-to-write operation exclude other readers? -<br><a href="#qq7answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + But how does the upgrade-to-write operation exclude other readers? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + It doesn't, just like normal RCU updates, which also do not exclude + RCU readers. +</font></td></tr> +<tr><td> </td></tr> +</table> <p> This guarantee allows lookup code to be shared between read-side @@ -714,9 +932,20 @@ to do significant reordering. This is by design: Any significant ordering constraints would slow down these fast-path APIs. -<p><a name="Quick Quiz 8"><b>Quick Quiz 8</b>:</a> -Can't the compiler also reorder this code? -<br><a href="#qq8answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Can't the compiler also reorder this code? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + No, the volatile casts in <tt>READ_ONCE()</tt> and + <tt>WRITE_ONCE()</tt> prevent the compiler from reordering in + this particular case. +</font></td></tr> +<tr><td> </td></tr> +</table> <h3><a name="Readers Do Not Exclude Updaters">Readers Do Not Exclude Updaters</a></h3> @@ -769,10 +998,28 @@ new readers can start immediately after <tt>synchronize_rcu()</tt> starts, and <tt>synchronize_rcu()</tt> is under no obligation to wait for these new readers. -<p><a name="Quick Quiz 9"><b>Quick Quiz 9</b>:</a> -Suppose that synchronize_rcu() did wait until all readers had completed. -Would the updater be able to rely on this? -<br><a href="#qq9answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Suppose that synchronize_rcu() did wait until <i>all</i> + readers had completed instead of waiting only on + pre-existing readers. + For how long would the updater be able to rely on there + being no readers? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + For no time at all. + Even if <tt>synchronize_rcu()</tt> were to wait until + all readers had completed, a new reader might start immediately after + <tt>synchronize_rcu()</tt> completed. + Therefore, the code following + <tt>synchronize_rcu()</tt> can <i>never</i> rely on there being + no readers. +</font></td></tr> +<tr><td> </td></tr> +</table> <h3><a name="Grace Periods Don't Partition Read-Side Critical Sections"> Grace Periods Don't Partition Read-Side Critical Sections</a></h3> @@ -969,11 +1216,24 @@ grace period. As a result, an RCU read-side critical section cannot partition a pair of RCU grace periods. -<p><a name="Quick Quiz 10"><b>Quick Quiz 10</b>:</a> -How long a sequence of grace periods, each separated by an RCU read-side -critical section, would be required to partition the RCU read-side -critical sections at the beginning and end of the chain? -<br><a href="#qq10answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + How long a sequence of grace periods, each separated by an RCU + read-side critical section, would be required to partition the RCU + read-side critical sections at the beginning and end of the chain? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + In theory, an infinite number. + In practice, an unknown number that is sensitive to both implementation + details and timing considerations. + Therefore, even in practice, RCU users must abide by the + theoretical rather than the practical answer. +</font></td></tr> +<tr><td> </td></tr> +</table> <h3><a name="Disabling Preemption Does Not Block Grace Periods"> Disabling Preemption Does Not Block Grace Periods</a></h3> @@ -1109,12 +1369,27 @@ These classes is covered in the following sections. <h3><a name="Specialization">Specialization</a></h3> <p> -RCU is and always has been intended primarily for read-mostly situations, as -illustrated by the following figure. -This means that RCU's read-side primitives are optimized, often at the +RCU is and always has been intended primarily for read-mostly situations, +which means that RCU's read-side primitives are optimized, often at the expense of its update-side primitives. +Experience thus far is captured by the following list of situations: -<p><img src="RCUApplicability.svg" alt="RCUApplicability.svg" width="70%"></p> +<ol> +<li> Read-mostly data, where stale and inconsistent data is not + a problem: RCU works great! +<li> Read-mostly data, where data must be consistent: + RCU works well. +<li> Read-write data, where data must be consistent: + RCU <i>might</i> work OK. + Or not. +<li> Write-mostly data, where data must be consistent: + RCU is very unlikely to be the right tool for the job, + with the following exceptions, where RCU can provide: + <ol type=a> + <li> Existence guarantees for update-friendly mechanisms. + <li> Wait-free read-side primitives for real-time use. + </ol> +</ol> <p> This focus on read-mostly situations means that RCU must interoperate @@ -1127,9 +1402,43 @@ synchronization primitives be legal within RCU read-side critical sections, including spinlocks, sequence locks, atomic operations, reference counters, and memory barriers. -<p><a name="Quick Quiz 11"><b>Quick Quiz 11</b>:</a> -What about sleeping locks? -<br><a href="#qq11answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + What about sleeping locks? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + These are forbidden within Linux-kernel RCU read-side critical + sections because it is not legal to place a quiescent state + (in this case, voluntary context switch) within an RCU read-side + critical section. + However, sleeping locks may be used within userspace RCU read-side + critical sections, and also within Linux-kernel sleepable RCU + <a href="#Sleepable RCU"><font color="ffffff">(SRCU)</font></a> + read-side critical sections. + In addition, the -rt patchset turns spinlocks into a + sleeping locks so that the corresponding critical sections + can be preempted, which also means that these sleeplockified + spinlocks (but not other sleeping locks!) may be acquire within + -rt-Linux-kernel RCU read-side critical sections. + </font> + + <p><font color="ffffff"> + Note that it <i>is</i> legal for a normal RCU read-side + critical section to conditionally acquire a sleeping locks + (as in <tt>mutex_trylock()</tt>), but only as long as it does + not loop indefinitely attempting to conditionally acquire that + sleeping locks. + The key point is that things like <tt>mutex_trylock()</tt> + either return with the mutex held, or return an error indication if + the mutex was not immediately available. + Either way, <tt>mutex_trylock()</tt> returns immediately without + sleeping. +</font></td></tr> +<tr><td> </td></tr> +</table> <p> It often comes as a surprise that many algorithms do not require a @@ -1160,10 +1469,7 @@ some period of time, so the exact wait period is a judgment call. One of our pair of veternarians might wait 30 seconds before pronouncing the cat dead, while the other might insist on waiting a full minute. The two veternarians would then disagree on the state of the cat during -the final 30 seconds of the minute following the last heartbeat, as -fancifully illustrated below: - -<p><img src="2013-08-is-it-dead.png" alt="2013-08-is-it-dead.png" width="431"></p> +the final 30 seconds of the minute following the last heartbeat. <p> Interestingly enough, this same situation applies to hardware. @@ -1343,7 +1649,8 @@ situations where neither <tt>synchronize_rcu()</tt> nor <tt>synchronize_rcu_expedited()</tt> would be legal, including within preempt-disable code, <tt>local_bh_disable()</tt> code, interrupt-disable code, and interrupt handlers. -However, even <tt>call_rcu()</tt> is illegal within NMI handlers. +However, even <tt>call_rcu()</tt> is illegal within NMI handlers +and from idle and offline CPUs. The callback function (<tt>remove_gp_cb()</tt> in this case) will be executed within softirq (software interrupt) environment within the Linux kernel, @@ -1354,12 +1661,27 @@ write an RCU callback function that takes too long. Long-running operations should be relegated to separate threads or (in the Linux kernel) workqueues. -<p><a name="Quick Quiz 12"><b>Quick Quiz 12</b>:</a> -Why does line 19 use <tt>rcu_access_pointer()</tt>? -After all, <tt>call_rcu()</tt> on line 25 stores into the -structure, which would interact badly with concurrent insertions. -Doesn't this mean that <tt>rcu_dereference()</tt> is required? -<br><a href="#qq12answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Why does line 19 use <tt>rcu_access_pointer()</tt>? + After all, <tt>call_rcu()</tt> on line 25 stores into the + structure, which would interact badly with concurrent insertions. + Doesn't this mean that <tt>rcu_dereference()</tt> is required? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Presumably the <tt>->gp_lock</tt> acquired on line 18 excludes + any changes, including any insertions that <tt>rcu_dereference()</tt> + would protect against. + Therefore, any insertions will be delayed until after + <tt>->gp_lock</tt> + is released on line 25, which in turn means that + <tt>rcu_access_pointer()</tt> suffices. +</font></td></tr> +<tr><td> </td></tr> +</table> <p> However, all that <tt>remove_gp_cb()</tt> is doing is @@ -1406,14 +1728,31 @@ This was due to the fact that RCU was not heavily used within DYNIX/ptx, so the very few places that needed something like <tt>synchronize_rcu()</tt> simply open-coded it. -<p><a name="Quick Quiz 13"><b>Quick Quiz 13</b>:</a> -Earlier it was claimed that <tt>call_rcu()</tt> and -<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked -by readers. -But how can that be correct, given that the invocation of the callback -and the freeing of the memory (respectively) must still wait for -a grace period to elapse? -<br><a href="#qq13answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Earlier it was claimed that <tt>call_rcu()</tt> and + <tt>kfree_rcu()</tt> allowed updaters to avoid being blocked + by readers. + But how can that be correct, given that the invocation of the callback + and the freeing of the memory (respectively) must still wait for + a grace period to elapse? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + We could define things this way, but keep in mind that this sort of + definition would say that updates in garbage-collected languages + cannot complete until the next time the garbage collector runs, + which does not seem at all reasonable. + The key point is that in most cases, an updater using either + <tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> can proceed to the + next update as soon as it has invoked <tt>call_rcu()</tt> or + <tt>kfree_rcu()</tt>, without having to wait for a subsequent + grace period. +</font></td></tr> +<tr><td> </td></tr> +</table> <p> But what if the updater must wait for the completion of code to be @@ -1838,11 +2177,26 @@ kthreads to be spawned. Therefore, invoking <tt>synchronize_rcu()</tt> during scheduler initialization can result in deadlock. -<p><a name="Quick Quiz 14"><b>Quick Quiz 14</b>:</a> -So what happens with <tt>synchronize_rcu()</tt> during -scheduler initialization for <tt>CONFIG_PREEMPT=n</tt> -kernels? -<br><a href="#qq14answer">Answer</a> +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + So what happens with <tt>synchronize_rcu()</tt> during + scheduler initialization for <tt>CONFIG_PREEMPT=n</tt> + kernels? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + In <tt>CONFIG_PREEMPT=n</tt> kernel, <tt>synchronize_rcu()</tt> + maps directly to <tt>synchronize_sched()</tt>. + Therefore, <tt>synchronize_rcu()</tt> works normally throughout + boot in <tt>CONFIG_PREEMPT=n</tt> kernels. + However, your code must also work in <tt>CONFIG_PREEMPT=y</tt> kernels, + so it is still necessary to avoid invoking <tt>synchronize_rcu()</tt> + during scheduler initialization. +</font></td></tr> +<tr><td> </td></tr> +</table> <p> I learned of these boot-time requirements as a result of a series of @@ -2171,6 +2525,14 @@ This real-time requirement motivated the grace-period kthread, which also simplified handling of a number of race conditions. <p> +RCU must avoid degrading real-time response for CPU-bound threads, whether +executing in usermode (which is one use case for +<tt>CONFIG_NO_HZ_FULL=y</tt>) or in the kernel. +That said, CPU-bound loops in the kernel must execute +<tt>cond_resched_rcu_qs()</tt> at least once per few tens of milliseconds +in order to avoid receiving an IPI from RCU. + +<p> Finally, RCU's status as a synchronization primitive means that any RCU failure can result in arbitrary memory corruption that can be extremely difficult to debug. @@ -2223,6 +2585,8 @@ described in a separate section. <li> <a href="#Sched Flavor">Sched Flavor</a> <li> <a href="#Sleepable RCU">Sleepable RCU</a> <li> <a href="#Tasks RCU">Tasks RCU</a> +<li> <a href="#Waiting for Multiple Grace Periods"> + Waiting for Multiple Grace Periods</a> </ol> <h3><a name="Bottom-Half Flavor">Bottom-Half Flavor</a></h3> @@ -2472,6 +2836,94 @@ The tasks-RCU API is quite compact, consisting only of <tt>synchronize_rcu_tasks()</tt>, and <tt>rcu_barrier_tasks()</tt>. +<h3><a name="Waiting for Multiple Grace Periods"> +Waiting for Multiple Grace Periods</a></h3> + +<p> +Perhaps you have an RCU protected data structure that is accessed from +RCU read-side critical sections, from softirq handlers, and from +hardware interrupt handlers. +That is three flavors of RCU, the normal flavor, the bottom-half flavor, +and the sched flavor. +How to wait for a compound grace period? + +<p> +The best approach is usually to “just say no!” and +insert <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt> +around each RCU read-side critical section, regardless of what +environment it happens to be in. +But suppose that some of the RCU read-side critical sections are +on extremely hot code paths, and that use of <tt>CONFIG_PREEMPT=n</tt> +is not a viable option, so that <tt>rcu_read_lock()</tt> and +<tt>rcu_read_unlock()</tt> are not free. +What then? + +<p> +You <i>could</i> wait on all three grace periods in succession, as follows: + +<blockquote> +<pre> + 1 synchronize_rcu(); + 2 synchronize_rcu_bh(); + 3 synchronize_sched(); +</pre> +</blockquote> + +<p> +This works, but triples the update-side latency penalty. +In cases where this is not acceptable, <tt>synchronize_rcu_mult()</tt> +may be used to wait on all three flavors of grace period concurrently: + +<blockquote> +<pre> + 1 synchronize_rcu_mult(call_rcu, call_rcu_bh, call_rcu_sched); +</pre> +</blockquote> + +<p> +But what if it is necessary to also wait on SRCU? +This can be done as follows: + +<blockquote> +<pre> + 1 static void call_my_srcu(struct rcu_head *head, + 2 void (*func)(struct rcu_head *head)) + 3 { + 4 call_srcu(&my_srcu, head, func); + 5 } + 6 + 7 synchronize_rcu_mult(call_rcu, call_rcu_bh, call_rcu_sched, call_my_srcu); +</pre> +</blockquote> + +<p> +If you needed to wait on multiple different flavors of SRCU +(but why???), you would need to create a wrapper function resembling +<tt>call_my_srcu()</tt> for each SRCU flavor. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + But what if I need to wait for multiple RCU flavors, but I also need + the grace periods to be expedited? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + If you are using expedited grace periods, there should be less penalty + for waiting on them in succession. + But if that is nevertheless a problem, you can use workqueues + or multiple kthreads to wait on the various expedited grace + periods concurrently. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<p> +Again, it is usually better to adjust the RCU read-side critical sections +to use a single flavor of RCU, but when this is not feasible, you can use +<tt>synchronize_rcu_mult()</tt>. + <h2><a name="Possible Future Changes">Possible Future Changes</a></h2> <p> @@ -2569,329 +3021,4 @@ and is provided under the terms of the Creative Commons Attribution-Share Alike 3.0 United States license. -<h3><a name="Answers to Quick Quizzes"> -Answers to Quick Quizzes</a></h3> - -<a name="qq1answer"></a> -<p><b>Quick Quiz 1</b>: -Wait a minute! -You said that updaters can make useful forward progress concurrently -with readers, but pre-existing readers will block -<tt>synchronize_rcu()</tt>!!! -Just who are you trying to fool??? - - -</p><p><b>Answer</b>: -First, if updaters do not wish to be blocked by readers, they can use -<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt>, which will -be discussed later. -Second, even when using <tt>synchronize_rcu()</tt>, the other -update-side code does run concurrently with readers, whether pre-existing -or not. - - -</p><p><a href="#Quick%20Quiz%201"><b>Back to Quick Quiz 1</b>.</a> - -<a name="qq2answer"></a> -<p><b>Quick Quiz 2</b>: -Why is the <tt>synchronize_rcu()</tt> on line 28 needed? - - -</p><p><b>Answer</b>: -Without that extra grace period, memory reordering could result in -<tt>do_something_dlm()</tt> executing <tt>do_something()</tt> -concurrently with the last bits of <tt>recovery()</tt>. - - -</p><p><a href="#Quick%20Quiz%202"><b>Back to Quick Quiz 2</b>.</a> - -<a name="qq3answer"></a> -<p><b>Quick Quiz 3</b>: -But <tt>rcu_assign_pointer()</tt> does nothing to prevent the -two assignments to <tt>p->a</tt> and <tt>p->b</tt> -from being reordered. -Can't that also cause problems? - - -</p><p><b>Answer</b>: -No, it cannot. -The readers cannot see either of these two fields until -the assignment to <tt>gp</tt>, by which time both fields are -fully initialized. -So reordering the assignments -to <tt>p->a</tt> and <tt>p->b</tt> cannot possibly -cause any problems. - - -</p><p><a href="#Quick%20Quiz%203"><b>Back to Quick Quiz 3</b>.</a> - -<a name="qq4answer"></a> -<p><b>Quick Quiz 4</b>: -Without the <tt>rcu_dereference()</tt> or the -<tt>rcu_access_pointer()</tt>, what destructive optimizations -might the compiler make use of? - - -</p><p><b>Answer</b>: -Let's start with what happens to <tt>do_something_gp()</tt> -if it fails to use <tt>rcu_dereference()</tt>. -It could reuse a value formerly fetched from this same pointer. -It could also fetch the pointer from <tt>gp</tt> in a byte-at-a-time -manner, resulting in <i>load tearing</i>, in turn resulting a bytewise -mash-up of two distince pointer values. -It might even use value-speculation optimizations, where it makes a wrong -guess, but by the time it gets around to checking the value, an update -has changed the pointer to match the wrong guess. -Too bad about any dereferences that returned pre-initialization garbage -in the meantime! - -<p> -For <tt>remove_gp_synchronous()</tt>, as long as all modifications -to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>, -the above optimizations are harmless. -However, -with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt>, -<tt>sparse</tt> will complain if you -define <tt>gp</tt> with <tt>__rcu</tt> and then -access it without using -either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>. - - -</p><p><a href="#Quick%20Quiz%204"><b>Back to Quick Quiz 4</b>.</a> - -<a name="qq5answer"></a> -<p><b>Quick Quiz 5</b>: -Given that multiple CPUs can start RCU read-side critical sections -at any time without any ordering whatsoever, how can RCU possibly tell whether -or not a given RCU read-side critical section starts before a -given instance of <tt>synchronize_rcu()</tt>? - - -</p><p><b>Answer</b>: -If RCU cannot tell whether or not a given -RCU read-side critical section starts before a -given instance of <tt>synchronize_rcu()</tt>, -then it must assume that the RCU read-side critical section -started first. -In other words, a given instance of <tt>synchronize_rcu()</tt> -can avoid waiting on a given RCU read-side critical section only -if it can prove that <tt>synchronize_rcu()</tt> started first. - - -</p><p><a href="#Quick%20Quiz%205"><b>Back to Quick Quiz 5</b>.</a> - -<a name="qq6answer"></a> -<p><b>Quick Quiz 6</b>: -The first and second guarantees require unbelievably strict ordering! -Are all these memory barriers <i> really</i> required? - - -</p><p><b>Answer</b>: -Yes, they really are required. -To see why the first guarantee is required, consider the following -sequence of events: - -<ol> -<li> CPU 1: <tt>rcu_read_lock()</tt> -<li> CPU 1: <tt>q = rcu_dereference(gp); - /* Very likely to return p. */</tt> -<li> CPU 0: <tt>list_del_rcu(p);</tt> -<li> CPU 0: <tt>synchronize_rcu()</tt> starts. -<li> CPU 1: <tt>do_something_with(q->a); - /* No smp_mb(), so might happen after kfree(). */</tt> -<li> CPU 1: <tt>rcu_read_unlock()</tt> -<li> CPU 0: <tt>synchronize_rcu()</tt> returns. -<li> CPU 0: <tt>kfree(p);</tt> -</ol> - -<p> -Therefore, there absolutely must be a full memory barrier between the -end of the RCU read-side critical section and the end of the -grace period. - -<p> -The sequence of events demonstrating the necessity of the second rule -is roughly similar: - -<ol> -<li> CPU 0: <tt>list_del_rcu(p);</tt> -<li> CPU 0: <tt>synchronize_rcu()</tt> starts. -<li> CPU 1: <tt>rcu_read_lock()</tt> -<li> CPU 1: <tt>q = rcu_dereference(gp); - /* Might return p if no memory barrier. */</tt> -<li> CPU 0: <tt>synchronize_rcu()</tt> returns. -<li> CPU 0: <tt>kfree(p);</tt> -<li> CPU 1: <tt>do_something_with(q->a); /* Boom!!! */</tt> -<li> CPU 1: <tt>rcu_read_unlock()</tt> -</ol> - -<p> -And similarly, without a memory barrier between the beginning of the -grace period and the beginning of the RCU read-side critical section, -CPU 1 might end up accessing the freelist. - -<p> -The “as if” rule of course applies, so that any implementation -that acts as if the appropriate memory barriers were in place is a -correct implementation. -That said, it is much easier to fool yourself into believing that you have -adhered to the as-if rule than it is to actually adhere to it! - - -</p><p><a href="#Quick%20Quiz%206"><b>Back to Quick Quiz 6</b>.</a> - -<a name="qq7answer"></a> -<p><b>Quick Quiz 7</b>: -But how does the upgrade-to-write operation exclude other readers? - - -</p><p><b>Answer</b>: -It doesn't, just like normal RCU updates, which also do not exclude -RCU readers. - - -</p><p><a href="#Quick%20Quiz%207"><b>Back to Quick Quiz 7</b>.</a> - -<a name="qq8answer"></a> -<p><b>Quick Quiz 8</b>: -Can't the compiler also reorder this code? - - -</p><p><b>Answer</b>: -No, the volatile casts in <tt>READ_ONCE()</tt> and -<tt>WRITE_ONCE()</tt> prevent the compiler from reordering in -this particular case. - - -</p><p><a href="#Quick%20Quiz%208"><b>Back to Quick Quiz 8</b>.</a> - -<a name="qq9answer"></a> -<p><b>Quick Quiz 9</b>: -Suppose that synchronize_rcu() did wait until all readers had completed. -Would the updater be able to rely on this? - - -</p><p><b>Answer</b>: -No. -Even if <tt>synchronize_rcu()</tt> were to wait until -all readers had completed, a new reader might start immediately after -<tt>synchronize_rcu()</tt> completed. -Therefore, the code following -<tt>synchronize_rcu()</tt> cannot rely on there being no readers -in any case. - - -</p><p><a href="#Quick%20Quiz%209"><b>Back to Quick Quiz 9</b>.</a> - -<a name="qq10answer"></a> -<p><b>Quick Quiz 10</b>: -How long a sequence of grace periods, each separated by an RCU read-side -critical section, would be required to partition the RCU read-side -critical sections at the beginning and end of the chain? - - -</p><p><b>Answer</b>: -In theory, an infinite number. -In practice, an unknown number that is sensitive to both implementation -details and timing considerations. -Therefore, even in practice, RCU users must abide by the theoretical rather -than the practical answer. - - -</p><p><a href="#Quick%20Quiz%2010"><b>Back to Quick Quiz 10</b>.</a> - -<a name="qq11answer"></a> -<p><b>Quick Quiz 11</b>: -What about sleeping locks? - - -</p><p><b>Answer</b>: -These are forbidden within Linux-kernel RCU read-side critical sections -because it is not legal to place a quiescent state (in this case, -voluntary context switch) within an RCU read-side critical section. -However, sleeping locks may be used within userspace RCU read-side critical -sections, and also within Linux-kernel sleepable RCU -<a href="#Sleepable RCU">(SRCU)</a> -read-side critical sections. -In addition, the -rt patchset turns spinlocks into a sleeping locks so -that the corresponding critical sections can be preempted, which -also means that these sleeplockified spinlocks (but not other sleeping locks!) -may be acquire within -rt-Linux-kernel RCU read-side critical sections. - -<p> -Note that it <i>is</i> legal for a normal RCU read-side critical section -to conditionally acquire a sleeping locks (as in <tt>mutex_trylock()</tt>), -but only as long as it does not loop indefinitely attempting to -conditionally acquire that sleeping locks. -The key point is that things like <tt>mutex_trylock()</tt> -either return with the mutex held, or return an error indication if -the mutex was not immediately available. -Either way, <tt>mutex_trylock()</tt> returns immediately without sleeping. - - -</p><p><a href="#Quick%20Quiz%2011"><b>Back to Quick Quiz 11</b>.</a> - -<a name="qq12answer"></a> -<p><b>Quick Quiz 12</b>: -Why does line 19 use <tt>rcu_access_pointer()</tt>? -After all, <tt>call_rcu()</tt> on line 25 stores into the -structure, which would interact badly with concurrent insertions. -Doesn't this mean that <tt>rcu_dereference()</tt> is required? - - -</p><p><b>Answer</b>: -Presumably the <tt>->gp_lock</tt> acquired on line 18 excludes -any changes, including any insertions that <tt>rcu_dereference()</tt> -would protect against. -Therefore, any insertions will be delayed until after <tt>->gp_lock</tt> -is released on line 25, which in turn means that -<tt>rcu_access_pointer()</tt> suffices. - - -</p><p><a href="#Quick%20Quiz%2012"><b>Back to Quick Quiz 12</b>.</a> - -<a name="qq13answer"></a> -<p><b>Quick Quiz 13</b>: -Earlier it was claimed that <tt>call_rcu()</tt> and -<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked -by readers. -But how can that be correct, given that the invocation of the callback -and the freeing of the memory (respectively) must still wait for -a grace period to elapse? - - -</p><p><b>Answer</b>: -We could define things this way, but keep in mind that this sort of -definition would say that updates in garbage-collected languages -cannot complete until the next time the garbage collector runs, -which does not seem at all reasonable. -The key point is that in most cases, an updater using either -<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> can proceed to the -next update as soon as it has invoked <tt>call_rcu()</tt> or -<tt>kfree_rcu()</tt>, without having to wait for a subsequent -grace period. - - -</p><p><a href="#Quick%20Quiz%2013"><b>Back to Quick Quiz 13</b>.</a> - -<a name="qq14answer"></a> -<p><b>Quick Quiz 14</b>: -So what happens with <tt>synchronize_rcu()</tt> during -scheduler initialization for <tt>CONFIG_PREEMPT=n</tt> -kernels? - - -</p><p><b>Answer</b>: -In <tt>CONFIG_PREEMPT=n</tt> kernel, <tt>synchronize_rcu()</tt> -maps directly to <tt>synchronize_sched()</tt>. -Therefore, <tt>synchronize_rcu()</tt> works normally throughout -boot in <tt>CONFIG_PREEMPT=n</tt> kernels. -However, your code must also work in <tt>CONFIG_PREEMPT=y</tt> kernels, -so it is still necessary to avoid invoking <tt>synchronize_rcu()</tt> -during scheduler initialization. - - -</p><p><a href="#Quick%20Quiz%2014"><b>Back to Quick Quiz 14</b>.</a> - - </body></html> diff --git a/Documentation/RCU/Design/Requirements/Requirements.htmlx b/Documentation/RCU/Design/Requirements/Requirements.htmlx deleted file mode 100644 index 3a97ba4..0000000 --- a/Documentation/RCU/Design/Requirements/Requirements.htmlx +++ /dev/null @@ -1,2741 +0,0 @@ -<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" - "http://www.w3.org/TR/html4/loose.dtd"> - <html> - <head><title>A Tour Through RCU's Requirements [LWN.net]</title> - <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=utf-8"> - -<h1>A Tour Through RCU's Requirements</h1> - -<p>Copyright IBM Corporation, 2015</p> -<p>Author: Paul E. McKenney</p> -<p><i>The initial version of this document appeared in the -<a href="https://lwn.net/">LWN</a> articles -<a href="https://lwn.net/Articles/652156/">here</a>, -<a href="https://lwn.net/Articles/652677/">here</a>, and -<a href="https://lwn.net/Articles/653326/">here</a>.</i></p> - -<h2>Introduction</h2> - -<p> -Read-copy update (RCU) is a synchronization mechanism that is often -used as a replacement for reader-writer locking. -RCU is unusual in that updaters do not block readers, -which means that RCU's read-side primitives can be exceedingly fast -and scalable. -In addition, updaters can make useful forward progress concurrently -with readers. -However, all this concurrency between RCU readers and updaters does raise -the question of exactly what RCU readers are doing, which in turn -raises the question of exactly what RCU's requirements are. - -<p> -This document therefore summarizes RCU's requirements, and can be thought -of as an informal, high-level specification for RCU. -It is important to understand that RCU's specification is primarily -empirical in nature; -in fact, I learned about many of these requirements the hard way. -This situation might cause some consternation, however, not only -has this learning process been a lot of fun, but it has also been -a great privilege to work with so many people willing to apply -technologies in interesting new ways. - -<p> -All that aside, here are the categories of currently known RCU requirements: -</p> - -<ol> -<li> <a href="#Fundamental Requirements"> - Fundamental Requirements</a> -<li> <a href="#Fundamental Non-Requirements">Fundamental Non-Requirements</a> -<li> <a href="#Parallelism Facts of Life"> - Parallelism Facts of Life</a> -<li> <a href="#Quality-of-Implementation Requirements"> - Quality-of-Implementation Requirements</a> -<li> <a href="#Linux Kernel Complications"> - Linux Kernel Complications</a> -<li> <a href="#Software-Engineering Requirements"> - Software-Engineering Requirements</a> -<li> <a href="#Other RCU Flavors"> - Other RCU Flavors</a> -<li> <a href="#Possible Future Changes"> - Possible Future Changes</a> -</ol> - -<p> -This is followed by a <a href="#Summary">summary</a>, -which is in turn followed by the inevitable -<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>. - -<h2><a name="Fundamental Requirements">Fundamental Requirements</a></h2> - -<p> -RCU's fundamental requirements are the closest thing RCU has to hard -mathematical requirements. -These are: - -<ol> -<li> <a href="#Grace-Period Guarantee"> - Grace-Period Guarantee</a> -<li> <a href="#Publish-Subscribe Guarantee"> - Publish-Subscribe Guarantee</a> -<li> <a href="#Memory-Barrier Guarantees"> - Memory-Barrier Guarantees</a> -<li> <a href="#RCU Primitives Guaranteed to Execute Unconditionally"> - RCU Primitives Guaranteed to Execute Unconditionally</a> -<li> <a href="#Guaranteed Read-to-Write Upgrade"> - Guaranteed Read-to-Write Upgrade</a> -</ol> - -<h3><a name="Grace-Period Guarantee">Grace-Period Guarantee</a></h3> - -<p> -RCU's grace-period guarantee is unusual in being premeditated: -Jack Slingwine and I had this guarantee firmly in mind when we started -work on RCU (then called “rclock”) in the early 1990s. -That said, the past two decades of experience with RCU have produced -a much more detailed understanding of this guarantee. - -<p> -RCU's grace-period guarantee allows updaters to wait for the completion -of all pre-existing RCU read-side critical sections. -An RCU read-side critical section -begins with the marker <tt>rcu_read_lock()</tt> and ends with -the marker <tt>rcu_read_unlock()</tt>. -These markers may be nested, and RCU treats a nested set as one -big RCU read-side critical section. -Production-quality implementations of <tt>rcu_read_lock()</tt> and -<tt>rcu_read_unlock()</tt> are extremely lightweight, and in -fact have exactly zero overhead in Linux kernels built for production -use with <tt>CONFIG_PREEMPT=n</tt>. - -<p> -This guarantee allows ordering to be enforced with extremely low -overhead to readers, for example: - -<blockquote> -<pre> - 1 int x, y; - 2 - 3 void thread0(void) - 4 { - 5 rcu_read_lock(); - 6 r1 = READ_ONCE(x); - 7 r2 = READ_ONCE(y); - 8 rcu_read_unlock(); - 9 } -10 -11 void thread1(void) -12 { -13 WRITE_ONCE(x, 1); -14 synchronize_rcu(); -15 WRITE_ONCE(y, 1); -16 } -</pre> -</blockquote> - -<p> -Because the <tt>synchronize_rcu()</tt> on line 14 waits for -all pre-existing readers, any instance of <tt>thread0()</tt> that -loads a value of zero from <tt>x</tt> must complete before -<tt>thread1()</tt> stores to <tt>y</tt>, so that instance must -also load a value of zero from <tt>y</tt>. -Similarly, any instance of <tt>thread0()</tt> that loads a value of -one from <tt>y</tt> must have started after the -<tt>synchronize_rcu()</tt> started, and must therefore also load -a value of one from <tt>x</tt>. -Therefore, the outcome: -<blockquote> -<pre> -(r1 == 0 && r2 == 1) -</pre> -</blockquote> -cannot happen. - -<p>@@QQ@@ -Wait a minute! -You said that updaters can make useful forward progress concurrently -with readers, but pre-existing readers will block -<tt>synchronize_rcu()</tt>!!! -Just who are you trying to fool??? -<p>@@QQA@@ -First, if updaters do not wish to be blocked by readers, they can use -<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt>, which will -be discussed later. -Second, even when using <tt>synchronize_rcu()</tt>, the other -update-side code does run concurrently with readers, whether pre-existing -or not. -<p>@@QQE@@ - -<p> -This scenario resembles one of the first uses of RCU in -<a href="https://en.wikipedia.org/wiki/DYNIX">DYNIX/ptx</a>, -which managed a distributed lock manager's transition into -a state suitable for handling recovery from node failure, -more or less as follows: - -<blockquote> -<pre> - 1 #define STATE_NORMAL 0 - 2 #define STATE_WANT_RECOVERY 1 - 3 #define STATE_RECOVERING 2 - 4 #define STATE_WANT_NORMAL 3 - 5 - 6 int state = STATE_NORMAL; - 7 - 8 void do_something_dlm(void) - 9 { -10 int state_snap; -11 -12 rcu_read_lock(); -13 state_snap = READ_ONCE(state); -14 if (state_snap == STATE_NORMAL) -15 do_something(); -16 else -17 do_something_carefully(); -18 rcu_read_unlock(); -19 } -20 -21 void start_recovery(void) -22 { -23 WRITE_ONCE(state, STATE_WANT_RECOVERY); -24 synchronize_rcu(); -25 WRITE_ONCE(state, STATE_RECOVERING); -26 recovery(); -27 WRITE_ONCE(state, STATE_WANT_NORMAL); -28 synchronize_rcu(); -29 WRITE_ONCE(state, STATE_NORMAL); -30 } -</pre> -</blockquote> - -<p> -The RCU read-side critical section in <tt>do_something_dlm()</tt> -works with the <tt>synchronize_rcu()</tt> in <tt>start_recovery()</tt> -to guarantee that <tt>do_something()</tt> never runs concurrently -with <tt>recovery()</tt>, but with little or no synchronization -overhead in <tt>do_something_dlm()</tt>. - -<p>@@QQ@@ -Why is the <tt>synchronize_rcu()</tt> on line 28 needed? -<p>@@QQA@@ -Without that extra grace period, memory reordering could result in -<tt>do_something_dlm()</tt> executing <tt>do_something()</tt> -concurrently with the last bits of <tt>recovery()</tt>. -<p>@@QQE@@ - -<p> -In order to avoid fatal problems such as deadlocks, -an RCU read-side critical section must not contain calls to -<tt>synchronize_rcu()</tt>. -Similarly, an RCU read-side critical section must not -contain anything that waits, directly or indirectly, on completion of -an invocation of <tt>synchronize_rcu()</tt>. - -<p> -Although RCU's grace-period guarantee is useful in and of itself, with -<a href="https://lwn.net/Articles/573497/">quite a few use cases</a>, -it would be good to be able to use RCU to coordinate read-side -access to linked data structures. -For this, the grace-period guarantee is not sufficient, as can -be seen in function <tt>add_gp_buggy()</tt> below. -We will look at the reader's code later, but in the meantime, just think of -the reader as locklessly picking up the <tt>gp</tt> pointer, -and, if the value loaded is non-<tt>NULL</tt>, locklessly accessing the -<tt>->a</tt> and <tt>->b</tt> fields. - -<blockquote> -<pre> - 1 bool add_gp_buggy(int a, int b) - 2 { - 3 p = kmalloc(sizeof(*p), GFP_KERNEL); - 4 if (!p) - 5 return -ENOMEM; - 6 spin_lock(&gp_lock); - 7 if (rcu_access_pointer(gp)) { - 8 spin_unlock(&gp_lock); - 9 return false; -10 } -11 p->a = a; -12 p->b = a; -13 gp = p; /* ORDERING BUG */ -14 spin_unlock(&gp_lock); -15 return true; -16 } -</pre> -</blockquote> - -<p> -The problem is that both the compiler and weakly ordered CPUs are within -their rights to reorder this code as follows: - -<blockquote> -<pre> - 1 bool add_gp_buggy_optimized(int a, int b) - 2 { - 3 p = kmalloc(sizeof(*p), GFP_KERNEL); - 4 if (!p) - 5 return -ENOMEM; - 6 spin_lock(&gp_lock); - 7 if (rcu_access_pointer(gp)) { - 8 spin_unlock(&gp_lock); - 9 return false; -10 } -<b>11 gp = p; /* ORDERING BUG */ -12 p->a = a; -13 p->b = a;</b> -14 spin_unlock(&gp_lock); -15 return true; -16 } -</pre> -</blockquote> - -<p> -If an RCU reader fetches <tt>gp</tt> just after -<tt>add_gp_buggy_optimized</tt> executes line 11, -it will see garbage in the <tt>->a</tt> and <tt>->b</tt> -fields. -And this is but one of many ways in which compiler and hardware optimizations -could cause trouble. -Therefore, we clearly need some way to prevent the compiler and the CPU from -reordering in this manner, which brings us to the publish-subscribe -guarantee discussed in the next section. - -<h3><a name="Publish-Subscribe Guarantee">Publish/Subscribe Guarantee</a></h3> - -<p> -RCU's publish-subscribe guarantee allows data to be inserted -into a linked data structure without disrupting RCU readers. -The updater uses <tt>rcu_assign_pointer()</tt> to insert the -new data, and readers use <tt>rcu_dereference()</tt> to -access data, whether new or old. -The following shows an example of insertion: - -<blockquote> -<pre> - 1 bool add_gp(int a, int b) - 2 { - 3 p = kmalloc(sizeof(*p), GFP_KERNEL); - 4 if (!p) - 5 return -ENOMEM; - 6 spin_lock(&gp_lock); - 7 if (rcu_access_pointer(gp)) { - 8 spin_unlock(&gp_lock); - 9 return false; -10 } -11 p->a = a; -12 p->b = a; -13 rcu_assign_pointer(gp, p); -14 spin_unlock(&gp_lock); -15 return true; -16 } -</pre> -</blockquote> - -<p> -The <tt>rcu_assign_pointer()</tt> on line 13 is conceptually -equivalent to a simple assignment statement, but also guarantees -that its assignment will -happen after the two assignments in lines 11 and 12, -similar to the C11 <tt>memory_order_release</tt> store operation. -It also prevents any number of “interesting” compiler -optimizations, for example, the use of <tt>gp</tt> as a scratch -location immediately preceding the assignment. - -<p>@@QQ@@ -But <tt>rcu_assign_pointer()</tt> does nothing to prevent the -two assignments to <tt>p->a</tt> and <tt>p->b</tt> -from being reordered. -Can't that also cause problems? -<p>@@QQA@@ -No, it cannot. -The readers cannot see either of these two fields until -the assignment to <tt>gp</tt>, by which time both fields are -fully initialized. -So reordering the assignments -to <tt>p->a</tt> and <tt>p->b</tt> cannot possibly -cause any problems. -<p>@@QQE@@ - -<p> -It is tempting to assume that the reader need not do anything special -to control its accesses to the RCU-protected data, -as shown in <tt>do_something_gp_buggy()</tt> below: - -<blockquote> -<pre> - 1 bool do_something_gp_buggy(void) - 2 { - 3 rcu_read_lock(); - 4 p = gp; /* OPTIMIZATIONS GALORE!!! */ - 5 if (p) { - 6 do_something(p->a, p->b); - 7 rcu_read_unlock(); - 8 return true; - 9 } -10 rcu_read_unlock(); -11 return false; -12 } -</pre> -</blockquote> - -<p> -However, this temptation must be resisted because there are a -surprisingly large number of ways that the compiler -(to say nothing of -<a href="https://h71000.www7.hp.com/wizard/wiz_2637.html">DEC Alpha CPUs</a>) -can trip this code up. -For but one example, if the compiler were short of registers, it -might choose to refetch from <tt>gp</tt> rather than keeping -a separate copy in <tt>p</tt> as follows: - -<blockquote> -<pre> - 1 bool do_something_gp_buggy_optimized(void) - 2 { - 3 rcu_read_lock(); - 4 if (gp) { /* OPTIMIZATIONS GALORE!!! */ -<b> 5 do_something(gp->a, gp->b);</b> - 6 rcu_read_unlock(); - 7 return true; - 8 } - 9 rcu_read_unlock(); -10 return false; -11 } -</pre> -</blockquote> - -<p> -If this function ran concurrently with a series of updates that -replaced the current structure with a new one, -the fetches of <tt>gp->a</tt> -and <tt>gp->b</tt> might well come from two different structures, -which could cause serious confusion. -To prevent this (and much else besides), <tt>do_something_gp()</tt> uses -<tt>rcu_dereference()</tt> to fetch from <tt>gp</tt>: - -<blockquote> -<pre> - 1 bool do_something_gp(void) - 2 { - 3 rcu_read_lock(); - 4 p = rcu_dereference(gp); - 5 if (p) { - 6 do_something(p->a, p->b); - 7 rcu_read_unlock(); - 8 return true; - 9 } -10 rcu_read_unlock(); -11 return false; -12 } -</pre> -</blockquote> - -<p> -The <tt>rcu_dereference()</tt> uses volatile casts and (for DEC Alpha) -memory barriers in the Linux kernel. -Should a -<a href="http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf">high-quality implementation of C11 <tt>memory_order_consume</tt> [PDF]</a> -ever appear, then <tt>rcu_dereference()</tt> could be implemented -as a <tt>memory_order_consume</tt> load. -Regardless of the exact implementation, a pointer fetched by -<tt>rcu_dereference()</tt> may not be used outside of the -outermost RCU read-side critical section containing that -<tt>rcu_dereference()</tt>, unless protection of -the corresponding data element has been passed from RCU to some -other synchronization mechanism, most commonly locking or -<a href="https://www.kernel.org/doc/Documentation/RCU/rcuref.txt">reference counting</a>. - -<p> -In short, updaters use <tt>rcu_assign_pointer()</tt> and readers -use <tt>rcu_dereference()</tt>, and these two RCU API elements -work together to ensure that readers have a consistent view of -newly added data elements. - -<p> -Of course, it is also necessary to remove elements from RCU-protected -data structures, for example, using the following process: - -<ol> -<li> Remove the data element from the enclosing structure. -<li> Wait for all pre-existing RCU read-side critical sections - to complete (because only pre-existing readers can possibly have - a reference to the newly removed data element). -<li> At this point, only the updater has a reference to the - newly removed data element, so it can safely reclaim - the data element, for example, by passing it to <tt>kfree()</tt>. -</ol> - -This process is implemented by <tt>remove_gp_synchronous()</tt>: - -<blockquote> -<pre> - 1 bool remove_gp_synchronous(void) - 2 { - 3 struct foo *p; - 4 - 5 spin_lock(&gp_lock); - 6 p = rcu_access_pointer(gp); - 7 if (!p) { - 8 spin_unlock(&gp_lock); - 9 return false; -10 } -11 rcu_assign_pointer(gp, NULL); -12 spin_unlock(&gp_lock); -13 synchronize_rcu(); -14 kfree(p); -15 return true; -16 } -</pre> -</blockquote> - -<p> -This function is straightforward, with line 13 waiting for a grace -period before line 14 frees the old data element. -This waiting ensures that readers will reach line 7 of -<tt>do_something_gp()</tt> before the data element referenced by -<tt>p</tt> is freed. -The <tt>rcu_access_pointer()</tt> on line 6 is similar to -<tt>rcu_dereference()</tt>, except that: - -<ol> -<li> The value returned by <tt>rcu_access_pointer()</tt> - cannot be dereferenced. - If you want to access the value pointed to as well as - the pointer itself, use <tt>rcu_dereference()</tt> - instead of <tt>rcu_access_pointer()</tt>. -<li> The call to <tt>rcu_access_pointer()</tt> need not be - protected. - In contrast, <tt>rcu_dereference()</tt> must either be - within an RCU read-side critical section or in a code - segment where the pointer cannot change, for example, in - code protected by the corresponding update-side lock. -</ol> - -<p>@@QQ@@ -Without the <tt>rcu_dereference()</tt> or the -<tt>rcu_access_pointer()</tt>, what destructive optimizations -might the compiler make use of? -<p>@@QQA@@ -Let's start with what happens to <tt>do_something_gp()</tt> -if it fails to use <tt>rcu_dereference()</tt>. -It could reuse a value formerly fetched from this same pointer. -It could also fetch the pointer from <tt>gp</tt> in a byte-at-a-time -manner, resulting in <i>load tearing</i>, in turn resulting a bytewise -mash-up of two distince pointer values. -It might even use value-speculation optimizations, where it makes a wrong -guess, but by the time it gets around to checking the value, an update -has changed the pointer to match the wrong guess. -Too bad about any dereferences that returned pre-initialization garbage -in the meantime! - -<p> -For <tt>remove_gp_synchronous()</tt>, as long as all modifications -to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>, -the above optimizations are harmless. -However, -with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt>, -<tt>sparse</tt> will complain if you -define <tt>gp</tt> with <tt>__rcu</tt> and then -access it without using -either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>. -<p>@@QQE@@ - -<p> -In short, RCU's publish-subscribe guarantee is provided by the combination -of <tt>rcu_assign_pointer()</tt> and <tt>rcu_dereference()</tt>. -This guarantee allows data elements to be safely added to RCU-protected -linked data structures without disrupting RCU readers. -This guarantee can be used in combination with the grace-period -guarantee to also allow data elements to be removed from RCU-protected -linked data structures, again without disrupting RCU readers. - -<p> -This guarantee was only partially premeditated. -DYNIX/ptx used an explicit memory barrier for publication, but had nothing -resembling <tt>rcu_dereference()</tt> for subscription, nor did it -have anything resembling the <tt>smp_read_barrier_depends()</tt> -that was later subsumed into <tt>rcu_dereference()</tt>. -The need for these operations made itself known quite suddenly at a -late-1990s meeting with the DEC Alpha architects, back in the days when -DEC was still a free-standing company. -It took the Alpha architects a good hour to convince me that any sort -of barrier would ever be needed, and it then took me a good <i>two</i> hours -to convince them that their documentation did not make this point clear. -More recent work with the C and C++ standards committees have provided -much education on tricks and traps from the compiler. -In short, compilers were much less tricky in the early 1990s, but in -2015, don't even think about omitting <tt>rcu_dereference()</tt>! - -<h3><a name="Memory-Barrier Guarantees">Memory-Barrier Guarantees</a></h3> - -<p> -The previous section's simple linked-data-structure scenario clearly -demonstrates the need for RCU's stringent memory-ordering guarantees on -systems with more than one CPU: - -<ol> -<li> Each CPU that has an RCU read-side critical section that - begins before <tt>synchronize_rcu()</tt> starts is - guaranteed to execute a full memory barrier between the time - that the RCU read-side critical section ends and the time that - <tt>synchronize_rcu()</tt> returns. - Without this guarantee, a pre-existing RCU read-side critical section - might hold a reference to the newly removed <tt>struct foo</tt> - after the <tt>kfree()</tt> on line 14 of - <tt>remove_gp_synchronous()</tt>. -<li> Each CPU that has an RCU read-side critical section that ends - after <tt>synchronize_rcu()</tt> returns is guaranteed - to execute a full memory barrier between the time that - <tt>synchronize_rcu()</tt> begins and the time that the RCU - read-side critical section begins. - Without this guarantee, a later RCU read-side critical section - running after the <tt>kfree()</tt> on line 14 of - <tt>remove_gp_synchronous()</tt> might - later run <tt>do_something_gp()</tt> and find the - newly deleted <tt>struct foo</tt>. -<li> If the task invoking <tt>synchronize_rcu()</tt> remains - on a given CPU, then that CPU is guaranteed to execute a full - memory barrier sometime during the execution of - <tt>synchronize_rcu()</tt>. - This guarantee ensures that the <tt>kfree()</tt> on - line 14 of <tt>remove_gp_synchronous()</tt> really does - execute after the removal on line 11. -<li> If the task invoking <tt>synchronize_rcu()</tt> migrates - among a group of CPUs during that invocation, then each of the - CPUs in that group is guaranteed to execute a full memory barrier - sometime during the execution of <tt>synchronize_rcu()</tt>. - This guarantee also ensures that the <tt>kfree()</tt> on - line 14 of <tt>remove_gp_synchronous()</tt> really does - execute after the removal on - line 11, but also in the case where the thread executing the - <tt>synchronize_rcu()</tt> migrates in the meantime. -</ol> - -<p>@@QQ@@ -Given that multiple CPUs can start RCU read-side critical sections -at any time without any ordering whatsoever, how can RCU possibly tell whether -or not a given RCU read-side critical section starts before a -given instance of <tt>synchronize_rcu()</tt>? -<p>@@QQA@@ -If RCU cannot tell whether or not a given -RCU read-side critical section starts before a -given instance of <tt>synchronize_rcu()</tt>, -then it must assume that the RCU read-side critical section -started first. -In other words, a given instance of <tt>synchronize_rcu()</tt> -can avoid waiting on a given RCU read-side critical section only -if it can prove that <tt>synchronize_rcu()</tt> started first. -<p>@@QQE@@ - -<p>@@QQ@@ -The first and second guarantees require unbelievably strict ordering! -Are all these memory barriers <i> really</i> required? -<p>@@QQA@@ -Yes, they really are required. -To see why the first guarantee is required, consider the following -sequence of events: - -<ol> -<li> CPU 1: <tt>rcu_read_lock()</tt> -<li> CPU 1: <tt>q = rcu_dereference(gp); - /* Very likely to return p. */</tt> -<li> CPU 0: <tt>list_del_rcu(p);</tt> -<li> CPU 0: <tt>synchronize_rcu()</tt> starts. -<li> CPU 1: <tt>do_something_with(q->a); - /* No smp_mb(), so might happen after kfree(). */</tt> -<li> CPU 1: <tt>rcu_read_unlock()</tt> -<li> CPU 0: <tt>synchronize_rcu()</tt> returns. -<li> CPU 0: <tt>kfree(p);</tt> -</ol> - -<p> -Therefore, there absolutely must be a full memory barrier between the -end of the RCU read-side critical section and the end of the -grace period. - -<p> -The sequence of events demonstrating the necessity of the second rule -is roughly similar: - -<ol> -<li> CPU 0: <tt>list_del_rcu(p);</tt> -<li> CPU 0: <tt>synchronize_rcu()</tt> starts. -<li> CPU 1: <tt>rcu_read_lock()</tt> -<li> CPU 1: <tt>q = rcu_dereference(gp); - /* Might return p if no memory barrier. */</tt> -<li> CPU 0: <tt>synchronize_rcu()</tt> returns. -<li> CPU 0: <tt>kfree(p);</tt> -<li> CPU 1: <tt>do_something_with(q->a); /* Boom!!! */</tt> -<li> CPU 1: <tt>rcu_read_unlock()</tt> -</ol> - -<p> -And similarly, without a memory barrier between the beginning of the -grace period and the beginning of the RCU read-side critical section, -CPU 1 might end up accessing the freelist. - -<p> -The “as if” rule of course applies, so that any implementation -that acts as if the appropriate memory barriers were in place is a -correct implementation. -That said, it is much easier to fool yourself into believing that you have -adhered to the as-if rule than it is to actually adhere to it! -<p>@@QQE@@ - -<p> -Note that these memory-barrier requirements do not replace the fundamental -RCU requirement that a grace period wait for all pre-existing readers. -On the contrary, the memory barriers called out in this section must operate in -such a way as to <i>enforce</i> this fundamental requirement. -Of course, different implementations enforce this requirement in different -ways, but enforce it they must. - -<h3><a name="RCU Primitives Guaranteed to Execute Unconditionally">RCU Primitives Guaranteed to Execute Unconditionally</a></h3> - -<p> -The common-case RCU primitives are unconditional. -They are invoked, they do their job, and they return, with no possibility -of error, and no need to retry. -This is a key RCU design philosophy. - -<p> -However, this philosophy is pragmatic rather than pigheaded. -If someone comes up with a good justification for a particular conditional -RCU primitive, it might well be implemented and added. -After all, this guarantee was reverse-engineered, not premeditated. -The unconditional nature of the RCU primitives was initially an -accident of implementation, and later experience with synchronization -primitives with conditional primitives caused me to elevate this -accident to a guarantee. -Therefore, the justification for adding a conditional primitive to -RCU would need to be based on detailed and compelling use cases. - -<h3><a name="Guaranteed Read-to-Write Upgrade">Guaranteed Read-to-Write Upgrade</a></h3> - -<p> -As far as RCU is concerned, it is always possible to carry out an -update within an RCU read-side critical section. -For example, that RCU read-side critical section might search for -a given data element, and then might acquire the update-side -spinlock in order to update that element, all while remaining -in that RCU read-side critical section. -Of course, it is necessary to exit the RCU read-side critical section -before invoking <tt>synchronize_rcu()</tt>, however, this -inconvenience can be avoided through use of the -<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt> API members -described later in this document. - -<p>@@QQ@@ -But how does the upgrade-to-write operation exclude other readers? -<p>@@QQA@@ -It doesn't, just like normal RCU updates, which also do not exclude -RCU readers. -<p>@@QQE@@ - -<p> -This guarantee allows lookup code to be shared between read-side -and update-side code, and was premeditated, appearing in the earliest -DYNIX/ptx RCU documentation. - -<h2><a name="Fundamental Non-Requirements">Fundamental Non-Requirements</a></h2> - -<p> -RCU provides extremely lightweight readers, and its read-side guarantees, -though quite useful, are correspondingly lightweight. -It is therefore all too easy to assume that RCU is guaranteeing more -than it really is. -Of course, the list of things that RCU does not guarantee is infinitely -long, however, the following sections list a few non-guarantees that -have caused confusion. -Except where otherwise noted, these non-guarantees were premeditated. - -<ol> -<li> <a href="#Readers Impose Minimal Ordering"> - Readers Impose Minimal Ordering</a> -<li> <a href="#Readers Do Not Exclude Updaters"> - Readers Do Not Exclude Updaters</a> -<li> <a href="#Updaters Only Wait For Old Readers"> - Updaters Only Wait For Old Readers</a> -<li> <a href="#Grace Periods Don't Partition Read-Side Critical Sections"> - Grace Periods Don't Partition Read-Side Critical Sections</a> -<li> <a href="#Read-Side Critical Sections Don't Partition Grace Periods"> - Read-Side Critical Sections Don't Partition Grace Periods</a> -<li> <a href="#Disabling Preemption Does Not Block Grace Periods"> - Disabling Preemption Does Not Block Grace Periods</a> -</ol> - -<h3><a name="Readers Impose Minimal Ordering">Readers Impose Minimal Ordering</a></h3> - -<p> -Reader-side markers such as <tt>rcu_read_lock()</tt> and -<tt>rcu_read_unlock()</tt> provide absolutely no ordering guarantees -except through their interaction with the grace-period APIs such as -<tt>synchronize_rcu()</tt>. -To see this, consider the following pair of threads: - -<blockquote> -<pre> - 1 void thread0(void) - 2 { - 3 rcu_read_lock(); - 4 WRITE_ONCE(x, 1); - 5 rcu_read_unlock(); - 6 rcu_read_lock(); - 7 WRITE_ONCE(y, 1); - 8 rcu_read_unlock(); - 9 } -10 -11 void thread1(void) -12 { -13 rcu_read_lock(); -14 r1 = READ_ONCE(y); -15 rcu_read_unlock(); -16 rcu_read_lock(); -17 r2 = READ_ONCE(x); -18 rcu_read_unlock(); -19 } -</pre> -</blockquote> - -<p> -After <tt>thread0()</tt> and <tt>thread1()</tt> execute -concurrently, it is quite possible to have - -<blockquote> -<pre> -(r1 == 1 && r2 == 0) -</pre> -</blockquote> - -(that is, <tt>y</tt> appears to have been assigned before <tt>x</tt>), -which would not be possible if <tt>rcu_read_lock()</tt> and -<tt>rcu_read_unlock()</tt> had much in the way of ordering -properties. -But they do not, so the CPU is within its rights -to do significant reordering. -This is by design: Any significant ordering constraints would slow down -these fast-path APIs. - -<p>@@QQ@@ -Can't the compiler also reorder this code? -<p>@@QQA@@ -No, the volatile casts in <tt>READ_ONCE()</tt> and -<tt>WRITE_ONCE()</tt> prevent the compiler from reordering in -this particular case. -<p>@@QQE@@ - -<h3><a name="Readers Do Not Exclude Updaters">Readers Do Not Exclude Updaters</a></h3> - -<p> -Neither <tt>rcu_read_lock()</tt> nor <tt>rcu_read_unlock()</tt> -exclude updates. -All they do is to prevent grace periods from ending. -The following example illustrates this: - -<blockquote> -<pre> - 1 void thread0(void) - 2 { - 3 rcu_read_lock(); - 4 r1 = READ_ONCE(y); - 5 if (r1) { - 6 do_something_with_nonzero_x(); - 7 r2 = READ_ONCE(x); - 8 WARN_ON(!r2); /* BUG!!! */ - 9 } -10 rcu_read_unlock(); -11 } -12 -13 void thread1(void) -14 { -15 spin_lock(&my_lock); -16 WRITE_ONCE(x, 1); -17 WRITE_ONCE(y, 1); -18 spin_unlock(&my_lock); -19 } -</pre> -</blockquote> - -<p> -If the <tt>thread0()</tt> function's <tt>rcu_read_lock()</tt> -excluded the <tt>thread1()</tt> function's update, -the <tt>WARN_ON()</tt> could never fire. -But the fact is that <tt>rcu_read_lock()</tt> does not exclude -much of anything aside from subsequent grace periods, of which -<tt>thread1()</tt> has none, so the -<tt>WARN_ON()</tt> can and does fire. - -<h3><a name="Updaters Only Wait For Old Readers">Updaters Only Wait For Old Readers</a></h3> - -<p> -It might be tempting to assume that after <tt>synchronize_rcu()</tt> -completes, there are no readers executing. -This temptation must be avoided because -new readers can start immediately after <tt>synchronize_rcu()</tt> -starts, and <tt>synchronize_rcu()</tt> is under no -obligation to wait for these new readers. - -<p>@@QQ@@ -Suppose that synchronize_rcu() did wait until all readers had completed. -Would the updater be able to rely on this? -<p>@@QQA@@ -No. -Even if <tt>synchronize_rcu()</tt> were to wait until -all readers had completed, a new reader might start immediately after -<tt>synchronize_rcu()</tt> completed. -Therefore, the code following -<tt>synchronize_rcu()</tt> cannot rely on there being no readers -in any case. -<p>@@QQE@@ - -<h3><a name="Grace Periods Don't Partition Read-Side Critical Sections"> -Grace Periods Don't Partition Read-Side Critical Sections</a></h3> - -<p> -It is tempting to assume that if any part of one RCU read-side critical -section precedes a given grace period, and if any part of another RCU -read-side critical section follows that same grace period, then all of -the first RCU read-side critical section must precede all of the second. -However, this just isn't the case: A single grace period does not -partition the set of RCU read-side critical sections. -An example of this situation can be illustrated as follows, where -<tt>x</tt>, <tt>y</tt>, and <tt>z</tt> are initially all zero: - -<blockquote> -<pre> - 1 void thread0(void) - 2 { - 3 rcu_read_lock(); - 4 WRITE_ONCE(a, 1); - 5 WRITE_ONCE(b, 1); - 6 rcu_read_unlock(); - 7 } - 8 - 9 void thread1(void) -10 { -11 r1 = READ_ONCE(a); -12 synchronize_rcu(); -13 WRITE_ONCE(c, 1); -14 } -15 -16 void thread2(void) -17 { -18 rcu_read_lock(); -19 r2 = READ_ONCE(b); -20 r3 = READ_ONCE(c); -21 rcu_read_unlock(); -22 } -</pre> -</blockquote> - -<p> -It turns out that the outcome: - -<blockquote> -<pre> -(r1 == 1 && r2 == 0 && r3 == 1) -</pre> -</blockquote> - -is entirely possible. -The following figure show how this can happen, with each circled -<tt>QS</tt> indicating the point at which RCU recorded a -<i>quiescent state</i> for each thread, that is, a state in which -RCU knows that the thread cannot be in the midst of an RCU read-side -critical section that started before the current grace period: - -<p><img src="GPpartitionReaders1.svg" alt="GPpartitionReaders1.svg" width="60%"></p> - -<p> -If it is necessary to partition RCU read-side critical sections in this -manner, it is necessary to use two grace periods, where the first -grace period is known to end before the second grace period starts: - -<blockquote> -<pre> - 1 void thread0(void) - 2 { - 3 rcu_read_lock(); - 4 WRITE_ONCE(a, 1); - 5 WRITE_ONCE(b, 1); - 6 rcu_read_unlock(); - 7 } - 8 - 9 void thread1(void) -10 { -11 r1 = READ_ONCE(a); -12 synchronize_rcu(); -13 WRITE_ONCE(c, 1); -14 } -15 -16 void thread2(void) -17 { -18 r2 = READ_ONCE(c); -19 synchronize_rcu(); -20 WRITE_ONCE(d, 1); -21 } -22 -23 void thread3(void) -24 { -25 rcu_read_lock(); -26 r3 = READ_ONCE(b); -27 r4 = READ_ONCE(d); -28 rcu_read_unlock(); -29 } -</pre> -</blockquote> - -<p> -Here, if <tt>(r1 == 1)</tt>, then -<tt>thread0()</tt>'s write to <tt>b</tt> must happen -before the end of <tt>thread1()</tt>'s grace period. -If in addition <tt>(r4 == 1)</tt>, then -<tt>thread3()</tt>'s read from <tt>b</tt> must happen -after the beginning of <tt>thread2()</tt>'s grace period. -If it is also the case that <tt>(r2 == 1)</tt>, then the -end of <tt>thread1()</tt>'s grace period must precede the -beginning of <tt>thread2()</tt>'s grace period. -This mean that the two RCU read-side critical sections cannot overlap, -guaranteeing that <tt>(r3 == 1)</tt>. -As a result, the outcome: - -<blockquote> -<pre> -(r1 == 1 && r2 == 1 && r3 == 0 && r4 == 1) -</pre> -</blockquote> - -cannot happen. - -<p> -This non-requirement was also non-premeditated, but became apparent -when studying RCU's interaction with memory ordering. - -<h3><a name="Read-Side Critical Sections Don't Partition Grace Periods"> -Read-Side Critical Sections Don't Partition Grace Periods</a></h3> - -<p> -It is also tempting to assume that if an RCU read-side critical section -happens between a pair of grace periods, then those grace periods cannot -overlap. -However, this temptation leads nowhere good, as can be illustrated by -the following, with all variables initially zero: - -<blockquote> -<pre> - 1 void thread0(void) - 2 { - 3 rcu_read_lock(); - 4 WRITE_ONCE(a, 1); - 5 WRITE_ONCE(b, 1); - 6 rcu_read_unlock(); - 7 } - 8 - 9 void thread1(void) -10 { -11 r1 = READ_ONCE(a); -12 synchronize_rcu(); -13 WRITE_ONCE(c, 1); -14 } -15 -16 void thread2(void) -17 { -18 rcu_read_lock(); -19 WRITE_ONCE(d, 1); -20 r2 = READ_ONCE(c); -21 rcu_read_unlock(); -22 } -23 -24 void thread3(void) -25 { -26 r3 = READ_ONCE(d); -27 synchronize_rcu(); -28 WRITE_ONCE(e, 1); -29 } -30 -31 void thread4(void) -32 { -33 rcu_read_lock(); -34 r4 = READ_ONCE(b); -35 r5 = READ_ONCE(e); -36 rcu_read_unlock(); -37 } -</pre> -</blockquote> - -<p> -In this case, the outcome: - -<blockquote> -<pre> -(r1 == 1 && r2 == 1 && r3 == 1 && r4 == 0 && r5 == 1) -</pre> -</blockquote> - -is entirely possible, as illustrated below: - -<p><img src="ReadersPartitionGP1.svg" alt="ReadersPartitionGP1.svg" width="100%"></p> - -<p> -Again, an RCU read-side critical section can overlap almost all of a -given grace period, just so long as it does not overlap the entire -grace period. -As a result, an RCU read-side critical section cannot partition a pair -of RCU grace periods. - -<p>@@QQ@@ -How long a sequence of grace periods, each separated by an RCU read-side -critical section, would be required to partition the RCU read-side -critical sections at the beginning and end of the chain? -<p>@@QQA@@ -In theory, an infinite number. -In practice, an unknown number that is sensitive to both implementation -details and timing considerations. -Therefore, even in practice, RCU users must abide by the theoretical rather -than the practical answer. -<p>@@QQE@@ - -<h3><a name="Disabling Preemption Does Not Block Grace Periods"> -Disabling Preemption Does Not Block Grace Periods</a></h3> - -<p> -There was a time when disabling preemption on any given CPU would block -subsequent grace periods. -However, this was an accident of implementation and is not a requirement. -And in the current Linux-kernel implementation, disabling preemption -on a given CPU in fact does not block grace periods, as Oleg Nesterov -<a href="https://lkml.kernel.org/g/20150614193825.GA19582@redhat.com">demonstrated</a>. - -<p> -If you need a preempt-disable region to block grace periods, you need to add -<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>, for example -as follows: - -<blockquote> -<pre> - 1 preempt_disable(); - 2 rcu_read_lock(); - 3 do_something(); - 4 rcu_read_unlock(); - 5 preempt_enable(); - 6 - 7 /* Spinlocks implicitly disable preemption. */ - 8 spin_lock(&mylock); - 9 rcu_read_lock(); -10 do_something(); -11 rcu_read_unlock(); -12 spin_unlock(&mylock); -</pre> -</blockquote> - -<p> -In theory, you could enter the RCU read-side critical section first, -but it is more efficient to keep the entire RCU read-side critical -section contained in the preempt-disable region as shown above. -Of course, RCU read-side critical sections that extend outside of -preempt-disable regions will work correctly, but such critical sections -can be preempted, which forces <tt>rcu_read_unlock()</tt> to do -more work. -And no, this is <i>not</i> an invitation to enclose all of your RCU -read-side critical sections within preempt-disable regions, because -doing so would degrade real-time response. - -<p> -This non-requirement appeared with preemptible RCU. -If you need a grace period that waits on non-preemptible code regions, use -<a href="#Sched Flavor">RCU-sched</a>. - -<h2><a name="Parallelism Facts of Life">Parallelism Facts of Life</a></h2> - -<p> -These parallelism facts of life are by no means specific to RCU, but -the RCU implementation must abide by them. -They therefore bear repeating: - -<ol> -<li> Any CPU or task may be delayed at any time, - and any attempts to avoid these delays by disabling - preemption, interrupts, or whatever are completely futile. - This is most obvious in preemptible user-level - environments and in virtualized environments (where - a given guest OS's VCPUs can be preempted at any time by - the underlying hypervisor), but can also happen in bare-metal - environments due to ECC errors, NMIs, and other hardware - events. - Although a delay of more than about 20 seconds can result - in splats, the RCU implementation is obligated to use - algorithms that can tolerate extremely long delays, but where - “extremely long” is not long enough to allow - wrap-around when incrementing a 64-bit counter. -<li> Both the compiler and the CPU can reorder memory accesses. - Where it matters, RCU must use compiler directives and - memory-barrier instructions to preserve ordering. -<li> Conflicting writes to memory locations in any given cache line - will result in expensive cache misses. - Greater numbers of concurrent writes and more-frequent - concurrent writes will result in more dramatic slowdowns. - RCU is therefore obligated to use algorithms that have - sufficient locality to avoid significant performance and - scalability problems. -<li> As a rough rule of thumb, only one CPU's worth of processing - may be carried out under the protection of any given exclusive - lock. - RCU must therefore use scalable locking designs. -<li> Counters are finite, especially on 32-bit systems. - RCU's use of counters must therefore tolerate counter wrap, - or be designed such that counter wrap would take way more - time than a single system is likely to run. - An uptime of ten years is quite possible, a runtime - of a century much less so. - As an example of the latter, RCU's dyntick-idle nesting counter - allows 54 bits for interrupt nesting level (this counter - is 64 bits even on a 32-bit system). - Overflowing this counter requires 2<sup>54</sup> - half-interrupts on a given CPU without that CPU ever going idle. - If a half-interrupt happened every microsecond, it would take - 570 years of runtime to overflow this counter, which is currently - believed to be an acceptably long time. -<li> Linux systems can have thousands of CPUs running a single - Linux kernel in a single shared-memory environment. - RCU must therefore pay close attention to high-end scalability. -</ol> - -<p> -This last parallelism fact of life means that RCU must pay special -attention to the preceding facts of life. -The idea that Linux might scale to systems with thousands of CPUs would -have been met with some skepticism in the 1990s, but these requirements -would have otherwise have been unsurprising, even in the early 1990s. - -<h2><a name="Quality-of-Implementation Requirements">Quality-of-Implementation Requirements</a></h2> - -<p> -These sections list quality-of-implementation requirements. -Although an RCU implementation that ignores these requirements could -still be used, it would likely be subject to limitations that would -make it inappropriate for industrial-strength production use. -Classes of quality-of-implementation requirements are as follows: - -<ol> -<li> <a href="#Specialization">Specialization</a> -<li> <a href="#Performance and Scalability">Performance and Scalability</a> -<li> <a href="#Composability">Composability</a> -<li> <a href="#Corner Cases">Corner Cases</a> -</ol> - -<p> -These classes is covered in the following sections. - -<h3><a name="Specialization">Specialization</a></h3> - -<p> -RCU is and always has been intended primarily for read-mostly situations, as -illustrated by the following figure. -This means that RCU's read-side primitives are optimized, often at the -expense of its update-side primitives. - -<p><img src="RCUApplicability.svg" alt="RCUApplicability.svg" width="70%"></p> - -<p> -This focus on read-mostly situations means that RCU must interoperate -with other synchronization primitives. -For example, the <tt>add_gp()</tt> and <tt>remove_gp_synchronous()</tt> -examples discussed earlier use RCU to protect readers and locking to -coordinate updaters. -However, the need extends much farther, requiring that a variety of -synchronization primitives be legal within RCU read-side critical sections, -including spinlocks, sequence locks, atomic operations, reference -counters, and memory barriers. - -<p>@@QQ@@ -What about sleeping locks? -<p>@@QQA@@ -These are forbidden within Linux-kernel RCU read-side critical sections -because it is not legal to place a quiescent state (in this case, -voluntary context switch) within an RCU read-side critical section. -However, sleeping locks may be used within userspace RCU read-side critical -sections, and also within Linux-kernel sleepable RCU -<a href="#Sleepable RCU">(SRCU)</a> -read-side critical sections. -In addition, the -rt patchset turns spinlocks into a sleeping locks so -that the corresponding critical sections can be preempted, which -also means that these sleeplockified spinlocks (but not other sleeping locks!) -may be acquire within -rt-Linux-kernel RCU read-side critical sections. - -<p> -Note that it <i>is</i> legal for a normal RCU read-side critical section -to conditionally acquire a sleeping locks (as in <tt>mutex_trylock()</tt>), -but only as long as it does not loop indefinitely attempting to -conditionally acquire that sleeping locks. -The key point is that things like <tt>mutex_trylock()</tt> -either return with the mutex held, or return an error indication if -the mutex was not immediately available. -Either way, <tt>mutex_trylock()</tt> returns immediately without sleeping. -<p>@@QQE@@ - -<p> -It often comes as a surprise that many algorithms do not require a -consistent view of data, but many can function in that mode, -with network routing being the poster child. -Internet routing algorithms take significant time to propagate -updates, so that by the time an update arrives at a given system, -that system has been sending network traffic the wrong way for -a considerable length of time. -Having a few threads continue to send traffic the wrong way for a -few more milliseconds is clearly not a problem: In the worst case, -TCP retransmissions will eventually get the data where it needs to go. -In general, when tracking the state of the universe outside of the -computer, some level of inconsistency must be tolerated due to -speed-of-light delays if nothing else. - -<p> -Furthermore, uncertainty about external state is inherent in many cases. -For example, a pair of veternarians might use heartbeat to determine -whether or not a given cat was alive. -But how long should they wait after the last heartbeat to decide that -the cat is in fact dead? -Waiting less than 400 milliseconds makes no sense because this would -mean that a relaxed cat would be considered to cycle between death -and life more than 100 times per minute. -Moreover, just as with human beings, a cat's heart might stop for -some period of time, so the exact wait period is a judgment call. -One of our pair of veternarians might wait 30 seconds before pronouncing -the cat dead, while the other might insist on waiting a full minute. -The two veternarians would then disagree on the state of the cat during -the final 30 seconds of the minute following the last heartbeat, as -fancifully illustrated below: - -<p><img src="2013-08-is-it-dead.png" alt="2013-08-is-it-dead.png" width="431"></p> - -<p> -Interestingly enough, this same situation applies to hardware. -When push comes to shove, how do we tell whether or not some -external server has failed? -We send messages to it periodically, and declare it failed if we -don't receive a response within a given period of time. -Policy decisions can usually tolerate short -periods of inconsistency. -The policy was decided some time ago, and is only now being put into -effect, so a few milliseconds of delay is normally inconsequential. - -<p> -However, there are algorithms that absolutely must see consistent data. -For example, the translation between a user-level SystemV semaphore -ID to the corresponding in-kernel data structure is protected by RCU, -but it is absolutely forbidden to update a semaphore that has just been -removed. -In the Linux kernel, this need for consistency is accommodated by acquiring -spinlocks located in the in-kernel data structure from within -the RCU read-side critical section, and this is indicated by the -green box in the figure above. -Many other techniques may be used, and are in fact used within the -Linux kernel. - -<p> -In short, RCU is not required to maintain consistency, and other -mechanisms may be used in concert with RCU when consistency is required. -RCU's specialization allows it to do its job extremely well, and its -ability to interoperate with other synchronization mechanisms allows -the right mix of synchronization tools to be used for a given job. - -<h3><a name="Performance and Scalability">Performance and Scalability</a></h3> - -<p> -Energy efficiency is a critical component of performance today, -and Linux-kernel RCU implementations must therefore avoid unnecessarily -awakening idle CPUs. -I cannot claim that this requirement was premeditated. -In fact, I learned of it during a telephone conversation in which I -was given “frank and open” feedback on the importance -of energy efficiency in battery-powered systems and on specific -energy-efficiency shortcomings of the Linux-kernel RCU implementation. -In my experience, the battery-powered embedded community will consider -any unnecessary wakeups to be extremely unfriendly acts. -So much so that mere Linux-kernel-mailing-list posts are -insufficient to vent their ire. - -<p> -Memory consumption is not particularly important for in most -situations, and has become decreasingly -so as memory sizes have expanded and memory -costs have plummeted. -However, as I learned from Matt Mackall's -<a href="http://elinux.org/Linux_Tiny-FAQ">bloatwatch</a> -efforts, memory footprint is critically important on single-CPU systems with -non-preemptible (<tt>CONFIG_PREEMPT=n</tt>) kernels, and thus -<a href="https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com">tiny RCU</a> -was born. -Josh Triplett has since taken over the small-memory banner with his -<a href="https://tiny.wiki.kernel.org/">Linux kernel tinification</a> -project, which resulted in -<a href="#Sleepable RCU">SRCU</a> -becoming optional for those kernels not needing it. - -<p> -The remaining performance requirements are, for the most part, -unsurprising. -For example, in keeping with RCU's read-side specialization, -<tt>rcu_dereference()</tt> should have negligible overhead (for -example, suppression of a few minor compiler optimizations). -Similarly, in non-preemptible environments, <tt>rcu_read_lock()</tt> and -<tt>rcu_read_unlock()</tt> should have exactly zero overhead. - -<p> -In preemptible environments, in the case where the RCU read-side -critical section was not preempted (as will be the case for the -highest-priority real-time process), <tt>rcu_read_lock()</tt> and -<tt>rcu_read_unlock()</tt> should have minimal overhead. -In particular, they should not contain atomic read-modify-write -operations, memory-barrier instructions, preemption disabling, -interrupt disabling, or backwards branches. -However, in the case where the RCU read-side critical section was preempted, -<tt>rcu_read_unlock()</tt> may acquire spinlocks and disable interrupts. -This is why it is better to nest an RCU read-side critical section -within a preempt-disable region than vice versa, at least in cases -where that critical section is short enough to avoid unduly degrading -real-time latencies. - -<p> -The <tt>synchronize_rcu()</tt> grace-period-wait primitive is -optimized for throughput. -It may therefore incur several milliseconds of latency in addition to -the duration of the longest RCU read-side critical section. -On the other hand, multiple concurrent invocations of -<tt>synchronize_rcu()</tt> are required to use batching optimizations -so that they can be satisfied by a single underlying grace-period-wait -operation. -For example, in the Linux kernel, it is not unusual for a single -grace-period-wait operation to serve more than -<a href="https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response">1,000 separate invocations</a> -of <tt>synchronize_rcu()</tt>, thus amortizing the per-invocation -overhead down to nearly zero. -However, the grace-period optimization is also required to avoid -measurable degradation of real-time scheduling and interrupt latencies. - -<p> -In some cases, the multi-millisecond <tt>synchronize_rcu()</tt> -latencies are unacceptable. -In these cases, <tt>synchronize_rcu_expedited()</tt> may be used -instead, reducing the grace-period latency down to a few tens of -microseconds on small systems, at least in cases where the RCU read-side -critical sections are short. -There are currently no special latency requirements for -<tt>synchronize_rcu_expedited()</tt> on large systems, but, -consistent with the empirical nature of the RCU specification, -that is subject to change. -However, there most definitely are scalability requirements: -A storm of <tt>synchronize_rcu_expedited()</tt> invocations on 4096 -CPUs should at least make reasonable forward progress. -In return for its shorter latencies, <tt>synchronize_rcu_expedited()</tt> -is permitted to impose modest degradation of real-time latency -on non-idle online CPUs. -That said, it will likely be necessary to take further steps to reduce this -degradation, hopefully to roughly that of a scheduling-clock interrupt. - -<p> -There are a number of situations where even -<tt>synchronize_rcu_expedited()</tt>'s reduced grace-period -latency is unacceptable. -In these situations, the asynchronous <tt>call_rcu()</tt> can be -used in place of <tt>synchronize_rcu()</tt> as follows: - -<blockquote> -<pre> - 1 struct foo { - 2 int a; - 3 int b; - 4 struct rcu_head rh; - 5 }; - 6 - 7 static void remove_gp_cb(struct rcu_head *rhp) - 8 { - 9 struct foo *p = container_of(rhp, struct foo, rh); -10 -11 kfree(p); -12 } -13 -14 bool remove_gp_asynchronous(void) -15 { -16 struct foo *p; -17 -18 spin_lock(&gp_lock); -19 p = rcu_dereference(gp); -20 if (!p) { -21 spin_unlock(&gp_lock); -22 return false; -23 } -24 rcu_assign_pointer(gp, NULL); -25 call_rcu(&p->rh, remove_gp_cb); -26 spin_unlock(&gp_lock); -27 return true; -28 } -</pre> -</blockquote> - -<p> -A definition of <tt>struct foo</tt> is finally needed, and appears -on lines 1-5. -The function <tt>remove_gp_cb()</tt> is passed to <tt>call_rcu()</tt> -on line 25, and will be invoked after the end of a subsequent -grace period. -This gets the same effect as <tt>remove_gp_synchronous()</tt>, -but without forcing the updater to wait for a grace period to elapse. -The <tt>call_rcu()</tt> function may be used in a number of -situations where neither <tt>synchronize_rcu()</tt> nor -<tt>synchronize_rcu_expedited()</tt> would be legal, -including within preempt-disable code, <tt>local_bh_disable()</tt> code, -interrupt-disable code, and interrupt handlers. -However, even <tt>call_rcu()</tt> is illegal within NMI handlers. -The callback function (<tt>remove_gp_cb()</tt> in this case) will be -executed within softirq (software interrupt) environment within the -Linux kernel, -either within a real softirq handler or under the protection -of <tt>local_bh_disable()</tt>. -In both the Linux kernel and in userspace, it is bad practice to -write an RCU callback function that takes too long. -Long-running operations should be relegated to separate threads or -(in the Linux kernel) workqueues. - -<p>@@QQ@@ -Why does line 19 use <tt>rcu_access_pointer()</tt>? -After all, <tt>call_rcu()</tt> on line 25 stores into the -structure, which would interact badly with concurrent insertions. -Doesn't this mean that <tt>rcu_dereference()</tt> is required? -<p>@@QQA@@ -Presumably the <tt>->gp_lock</tt> acquired on line 18 excludes -any changes, including any insertions that <tt>rcu_dereference()</tt> -would protect against. -Therefore, any insertions will be delayed until after <tt>->gp_lock</tt> -is released on line 25, which in turn means that -<tt>rcu_access_pointer()</tt> suffices. -<p>@@QQE@@ - -<p> -However, all that <tt>remove_gp_cb()</tt> is doing is -invoking <tt>kfree()</tt> on the data element. -This is a common idiom, and is supported by <tt>kfree_rcu()</tt>, -which allows “fire and forget” operation as shown below: - -<blockquote> -<pre> - 1 struct foo { - 2 int a; - 3 int b; - 4 struct rcu_head rh; - 5 }; - 6 - 7 bool remove_gp_faf(void) - 8 { - 9 struct foo *p; -10 -11 spin_lock(&gp_lock); -12 p = rcu_dereference(gp); -13 if (!p) { -14 spin_unlock(&gp_lock); -15 return false; -16 } -17 rcu_assign_pointer(gp, NULL); -18 kfree_rcu(p, rh); -19 spin_unlock(&gp_lock); -20 return true; -21 } -</pre> -</blockquote> - -<p> -Note that <tt>remove_gp_faf()</tt> simply invokes -<tt>kfree_rcu()</tt> and proceeds, without any need to pay any -further attention to the subsequent grace period and <tt>kfree()</tt>. -It is permissible to invoke <tt>kfree_rcu()</tt> from the same -environments as for <tt>call_rcu()</tt>. -Interestingly enough, DYNIX/ptx had the equivalents of -<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>, but not -<tt>synchronize_rcu()</tt>. -This was due to the fact that RCU was not heavily used within DYNIX/ptx, -so the very few places that needed something like -<tt>synchronize_rcu()</tt> simply open-coded it. - -<p>@@QQ@@ -Earlier it was claimed that <tt>call_rcu()</tt> and -<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked -by readers. -But how can that be correct, given that the invocation of the callback -and the freeing of the memory (respectively) must still wait for -a grace period to elapse? -<p>@@QQA@@ -We could define things this way, but keep in mind that this sort of -definition would say that updates in garbage-collected languages -cannot complete until the next time the garbage collector runs, -which does not seem at all reasonable. -The key point is that in most cases, an updater using either -<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> can proceed to the -next update as soon as it has invoked <tt>call_rcu()</tt> or -<tt>kfree_rcu()</tt>, without having to wait for a subsequent -grace period. -<p>@@QQE@@ - -<p> -But what if the updater must wait for the completion of code to be -executed after the end of the grace period, but has other tasks -that can be carried out in the meantime? -The polling-style <tt>get_state_synchronize_rcu()</tt> and -<tt>cond_synchronize_rcu()</tt> functions may be used for this -purpose, as shown below: - -<blockquote> -<pre> - 1 bool remove_gp_poll(void) - 2 { - 3 struct foo *p; - 4 unsigned long s; - 5 - 6 spin_lock(&gp_lock); - 7 p = rcu_access_pointer(gp); - 8 if (!p) { - 9 spin_unlock(&gp_lock); -10 return false; -11 } -12 rcu_assign_pointer(gp, NULL); -13 spin_unlock(&gp_lock); -14 s = get_state_synchronize_rcu(); -15 do_something_while_waiting(); -16 cond_synchronize_rcu(s); -17 kfree(p); -18 return true; -19 } -</pre> -</blockquote> - -<p> -On line 14, <tt>get_state_synchronize_rcu()</tt> obtains a -“cookie” from RCU, -then line 15 carries out other tasks, -and finally, line 16 returns immediately if a grace period has -elapsed in the meantime, but otherwise waits as required. -The need for <tt>get_state_synchronize_rcu</tt> and -<tt>cond_synchronize_rcu()</tt> has appeared quite recently, -so it is too early to tell whether they will stand the test of time. - -<p> -RCU thus provides a range of tools to allow updaters to strike the -required tradeoff between latency, flexibility and CPU overhead. - -<h3><a name="Composability">Composability</a></h3> - -<p> -Composability has received much attention in recent years, perhaps in part -due to the collision of multicore hardware with object-oriented techniques -designed in single-threaded environments for single-threaded use. -And in theory, RCU read-side critical sections may be composed, and in -fact may be nested arbitrarily deeply. -In practice, as with all real-world implementations of composable -constructs, there are limitations. - -<p> -Implementations of RCU for which <tt>rcu_read_lock()</tt> -and <tt>rcu_read_unlock()</tt> generate no code, such as -Linux-kernel RCU when <tt>CONFIG_PREEMPT=n</tt>, can be -nested arbitrarily deeply. -After all, there is no overhead. -Except that if all these instances of <tt>rcu_read_lock()</tt> -and <tt>rcu_read_unlock()</tt> are visible to the compiler, -compilation will eventually fail due to exhausting memory, -mass storage, or user patience, whichever comes first. -If the nesting is not visible to the compiler, as is the case with -mutually recursive functions each in its own translation unit, -stack overflow will result. -If the nesting takes the form of loops, either the control variable -will overflow or (in the Linux kernel) you will get an RCU CPU stall warning. -Nevertheless, this class of RCU implementations is one -of the most composable constructs in existence. - -<p> -RCU implementations that explicitly track nesting depth -are limited by the nesting-depth counter. -For example, the Linux kernel's preemptible RCU limits nesting to -<tt>INT_MAX</tt>. -This should suffice for almost all practical purposes. -That said, a consecutive pair of RCU read-side critical sections -between which there is an operation that waits for a grace period -cannot be enclosed in another RCU read-side critical section. -This is because it is not legal to wait for a grace period within -an RCU read-side critical section: To do so would result either -in deadlock or -in RCU implicitly splitting the enclosing RCU read-side critical -section, neither of which is conducive to a long-lived and prosperous -kernel. - -<p> -It is worth noting that RCU is not alone in limiting composability. -For example, many transactional-memory implementations prohibit -composing a pair of transactions separated by an irrevocable -operation (for example, a network receive operation). -For another example, lock-based critical sections can be composed -surprisingly freely, but only if deadlock is avoided. - -<p> -In short, although RCU read-side critical sections are highly composable, -care is required in some situations, just as is the case for any other -composable synchronization mechanism. - -<h3><a name="Corner Cases">Corner Cases</a></h3> - -<p> -A given RCU workload might have an endless and intense stream of -RCU read-side critical sections, perhaps even so intense that there -was never a point in time during which there was not at least one -RCU read-side critical section in flight. -RCU cannot allow this situation to block grace periods: As long as -all the RCU read-side critical sections are finite, grace periods -must also be finite. - -<p> -That said, preemptible RCU implementations could potentially result -in RCU read-side critical sections being preempted for long durations, -which has the effect of creating a long-duration RCU read-side -critical section. -This situation can arise only in heavily loaded systems, but systems using -real-time priorities are of course more vulnerable. -Therefore, RCU priority boosting is provided to help deal with this -case. -That said, the exact requirements on RCU priority boosting will likely -evolve as more experience accumulates. - -<p> -Other workloads might have very high update rates. -Although one can argue that such workloads should instead use -something other than RCU, the fact remains that RCU must -handle such workloads gracefully. -This requirement is another factor driving batching of grace periods, -but it is also the driving force behind the checks for large numbers -of queued RCU callbacks in the <tt>call_rcu()</tt> code path. -Finally, high update rates should not delay RCU read-side critical -sections, although some read-side delays can occur when using -<tt>synchronize_rcu_expedited()</tt>, courtesy of this function's use -of <tt>try_stop_cpus()</tt>. -(In the future, <tt>synchronize_rcu_expedited()</tt> will be -converted to use lighter-weight inter-processor interrupts (IPIs), -but this will still disturb readers, though to a much smaller degree.) - -<p> -Although all three of these corner cases were understood in the early -1990s, a simple user-level test consisting of <tt>close(open(path))</tt> -in a tight loop -in the early 2000s suddenly provided a much deeper appreciation of the -high-update-rate corner case. -This test also motivated addition of some RCU code to react to high update -rates, for example, if a given CPU finds itself with more than 10,000 -RCU callbacks queued, it will cause RCU to take evasive action by -more aggressively starting grace periods and more aggressively forcing -completion of grace-period processing. -This evasive action causes the grace period to complete more quickly, -but at the cost of restricting RCU's batching optimizations, thus -increasing the CPU overhead incurred by that grace period. - -<h2><a name="Software-Engineering Requirements"> -Software-Engineering Requirements</a></h2> - -<p> -Between Murphy's Law and “To err is human”, it is necessary to -guard against mishaps and misuse: - -<ol> -<li> It is all too easy to forget to use <tt>rcu_read_lock()</tt> - everywhere that it is needed, so kernels built with - <tt>CONFIG_PROVE_RCU=y</tt> will spat if - <tt>rcu_dereference()</tt> is used outside of an - RCU read-side critical section. - Update-side code can use <tt>rcu_dereference_protected()</tt>, - which takes a - <a href="https://lwn.net/Articles/371986/">lockdep expression</a> - to indicate what is providing the protection. - If the indicated protection is not provided, a lockdep splat - is emitted. - - <p> - Code shared between readers and updaters can use - <tt>rcu_dereference_check()</tt>, which also takes a - lockdep expression, and emits a lockdep splat if neither - <tt>rcu_read_lock()</tt> nor the indicated protection - is in place. - In addition, <tt>rcu_dereference_raw()</tt> is used in those - (hopefully rare) cases where the required protection cannot - be easily described. - Finally, <tt>rcu_read_lock_held()</tt> is provided to - allow a function to verify that it has been invoked within - an RCU read-side critical section. - I was made aware of this set of requirements shortly after Thomas - Gleixner audited a number of RCU uses. -<li> A given function might wish to check for RCU-related preconditions - upon entry, before using any other RCU API. - The <tt>rcu_lockdep_assert()</tt> does this job, - asserting the expression in kernels having lockdep enabled - and doing nothing otherwise. -<li> It is also easy to forget to use <tt>rcu_assign_pointer()</tt> - and <tt>rcu_dereference()</tt>, perhaps (incorrectly) - substituting a simple assignment. - To catch this sort of error, a given RCU-protected pointer may be - tagged with <tt>__rcu</tt>, after which running sparse - with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt> will complain - about simple-assignment accesses to that pointer. - Arnd Bergmann made me aware of this requirement, and also - supplied the needed - <a href="https://lwn.net/Articles/376011/">patch series</a>. -<li> Kernels built with <tt>CONFIG_DEBUG_OBJECTS_RCU_HEAD=y</tt> - will splat if a data element is passed to <tt>call_rcu()</tt> - twice in a row, without a grace period in between. - (This error is similar to a double free.) - The corresponding <tt>rcu_head</tt> structures that are - dynamically allocated are automatically tracked, but - <tt>rcu_head</tt> structures allocated on the stack - must be initialized with <tt>init_rcu_head_on_stack()</tt> - and cleaned up with <tt>destroy_rcu_head_on_stack()</tt>. - Similarly, statically allocated non-stack <tt>rcu_head</tt> - structures must be initialized with <tt>init_rcu_head()</tt> - and cleaned up with <tt>destroy_rcu_head()</tt>. - Mathieu Desnoyers made me aware of this requirement, and also - supplied the needed - <a href="https://lkml.kernel.org/g/20100319013024.GA28456@Krystal">patch</a>. -<li> An infinite loop in an RCU read-side critical section will - eventually trigger an RCU CPU stall warning splat, with - the duration of “eventually” being controlled by the - <tt>RCU_CPU_STALL_TIMEOUT</tt> <tt>Kconfig</tt> option, or, - alternatively, by the - <tt>rcupdate.rcu_cpu_stall_timeout</tt> boot/sysfs - parameter. - However, RCU is not obligated to produce this splat - unless there is a grace period waiting on that particular - RCU read-side critical section. - <p> - Some extreme workloads might intentionally delay - RCU grace periods, and systems running those workloads can - be booted with <tt>rcupdate.rcu_cpu_stall_suppress</tt> - to suppress the splats. - This kernel parameter may also be set via <tt>sysfs</tt>. - Furthermore, RCU CPU stall warnings are counter-productive - during sysrq dumps and during panics. - RCU therefore supplies the <tt>rcu_sysrq_start()</tt> and - <tt>rcu_sysrq_end()</tt> API members to be called before - and after long sysrq dumps. - RCU also supplies the <tt>rcu_panic()</tt> notifier that is - automatically invoked at the beginning of a panic to suppress - further RCU CPU stall warnings. - - <p> - This requirement made itself known in the early 1990s, pretty - much the first time that it was necessary to debug a CPU stall. - That said, the initial implementation in DYNIX/ptx was quite - generic in comparison with that of Linux. -<li> Although it would be very good to detect pointers leaking out - of RCU read-side critical sections, there is currently no - good way of doing this. - One complication is the need to distinguish between pointers - leaking and pointers that have been handed off from RCU to - some other synchronization mechanism, for example, reference - counting. -<li> In kernels built with <tt>CONFIG_RCU_TRACE=y</tt>, RCU-related - information is provided via both debugfs and event tracing. -<li> Open-coded use of <tt>rcu_assign_pointer()</tt> and - <tt>rcu_dereference()</tt> to create typical linked - data structures can be surprisingly error-prone. - Therefore, RCU-protected - <a href="https://lwn.net/Articles/609973/#RCU List APIs">linked lists</a> - and, more recently, RCU-protected - <a href="https://lwn.net/Articles/612100/">hash tables</a> - are available. - Many other special-purpose RCU-protected data structures are - available in the Linux kernel and the userspace RCU library. -<li> Some linked structures are created at compile time, but still - require <tt>__rcu</tt> checking. - The <tt>RCU_POINTER_INITIALIZER()</tt> macro serves this - purpose. -<li> It is not necessary to use <tt>rcu_assign_pointer()</tt> - when creating linked structures that are to be published via - a single external pointer. - The <tt>RCU_INIT_POINTER()</tt> macro is provided for - this task and also for assigning <tt>NULL</tt> pointers - at runtime. -</ol> - -<p> -This not a hard-and-fast list: RCU's diagnostic capabilities will -continue to be guided by the number and type of usage bugs found -in real-world RCU usage. - -<h2><a name="Linux Kernel Complications">Linux Kernel Complications</a></h2> - -<p> -The Linux kernel provides an interesting environment for all kinds of -software, including RCU. -Some of the relevant points of interest are as follows: - -<ol> -<li> <a href="#Configuration">Configuration</a>. -<li> <a href="#Firmware Interface">Firmware Interface</a>. -<li> <a href="#Early Boot">Early Boot</a>. -<li> <a href="#Interrupts and NMIs"> - Interrupts and non-maskable interrupts (NMIs)</a>. -<li> <a href="#Loadable Modules">Loadable Modules</a>. -<li> <a href="#Hotplug CPU">Hotplug CPU</a>. -<li> <a href="#Scheduler and RCU">Scheduler and RCU</a>. -<li> <a href="#Tracing and RCU">Tracing and RCU</a>. -<li> <a href="#Energy Efficiency">Energy Efficiency</a>. -<li> <a href="#Memory Efficiency">Memory Efficiency</a>. -<li> <a href="#Performance, Scalability, Response Time, and Reliability"> - Performance, Scalability, Response Time, and Reliability</a>. -</ol> - -<p> -This list is probably incomplete, but it does give a feel for the -most notable Linux-kernel complications. -Each of the following sections covers one of the above topics. - -<h3><a name="Configuration">Configuration</a></h3> - -<p> -RCU's goal is automatic configuration, so that almost nobody -needs to worry about RCU's <tt>Kconfig</tt> options. -And for almost all users, RCU does in fact work well -“out of the box.” - -<p> -However, there are specialized use cases that are handled by -kernel boot parameters and <tt>Kconfig</tt> options. -Unfortunately, the <tt>Kconfig</tt> system will explicitly ask users -about new <tt>Kconfig</tt> options, which requires almost all of them -be hidden behind a <tt>CONFIG_RCU_EXPERT</tt> <tt>Kconfig</tt> option. - -<p> -This all should be quite obvious, but the fact remains that -Linus Torvalds recently had to -<a href="https://lkml.kernel.org/g/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com">remind</a> -me of this requirement. - -<h3><a name="Firmware Interface">Firmware Interface</a></h3> - -<p> -In many cases, kernel obtains information about the system from the -firmware, and sometimes things are lost in translation. -Or the translation is accurate, but the original message is bogus. - -<p> -For example, some systems' firmware overreports the number of CPUs, -sometimes by a large factor. -If RCU naively believed the firmware, as it used to do, -it would create too many per-CPU kthreads. -Although the resulting system will still run correctly, the extra -kthreads needlessly consume memory and can cause confusion -when they show up in <tt>ps</tt> listings. - -<p> -RCU must therefore wait for a given CPU to actually come online before -it can allow itself to believe that the CPU actually exists. -The resulting “ghost CPUs” (which are never going to -come online) cause a number of -<a href="https://paulmck.livejournal.com/37494.html">interesting complications</a>. - -<h3><a name="Early Boot">Early Boot</a></h3> - -<p> -The Linux kernel's boot sequence is an interesting process, -and RCU is used early, even before <tt>rcu_init()</tt> -is invoked. -In fact, a number of RCU's primitives can be used as soon as the -initial task's <tt>task_struct</tt> is available and the -boot CPU's per-CPU variables are set up. -The read-side primitives (<tt>rcu_read_lock()</tt>, -<tt>rcu_read_unlock()</tt>, <tt>rcu_dereference()</tt>, -and <tt>rcu_access_pointer()</tt>) will operate normally very early on, -as will <tt>rcu_assign_pointer()</tt>. - -<p> -Although <tt>call_rcu()</tt> may be invoked at any -time during boot, callbacks are not guaranteed to be invoked until after -the scheduler is fully up and running. -This delay in callback invocation is due to the fact that RCU does not -invoke callbacks until it is fully initialized, and this full initialization -cannot occur until after the scheduler has initialized itself to the -point where RCU can spawn and run its kthreads. -In theory, it would be possible to invoke callbacks earlier, -however, this is not a panacea because there would be severe restrictions -on what operations those callbacks could invoke. - -<p> -Perhaps surprisingly, <tt>synchronize_rcu()</tt>, -<a href="#Bottom-Half Flavor"><tt>synchronize_rcu_bh()</tt></a> -(<a href="#Bottom-Half Flavor">discussed below</a>), -and -<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a> -will all operate normally -during very early boot, the reason being that there is only one CPU -and preemption is disabled. -This means that the call <tt>synchronize_rcu()</tt> (or friends) -itself is a quiescent -state and thus a grace period, so the early-boot implementation can -be a no-op. - -<p> -Both <tt>synchronize_rcu_bh()</tt> and <tt>synchronize_sched()</tt> -continue to operate normally through the remainder of boot, courtesy -of the fact that preemption is disabled across their RCU read-side -critical sections and also courtesy of the fact that there is still -only one CPU. -However, once the scheduler starts initializing, preemption is enabled. -There is still only a single CPU, but the fact that preemption is enabled -means that the no-op implementation of <tt>synchronize_rcu()</tt> no -longer works in <tt>CONFIG_PREEMPT=y</tt> kernels. -Therefore, as soon as the scheduler starts initializing, the early-boot -fastpath is disabled. -This means that <tt>synchronize_rcu()</tt> switches to its runtime -mode of operation where it posts callbacks, which in turn means that -any call to <tt>synchronize_rcu()</tt> will block until the corresponding -callback is invoked. -Unfortunately, the callback cannot be invoked until RCU's runtime -grace-period machinery is up and running, which cannot happen until -the scheduler has initialized itself sufficiently to allow RCU's -kthreads to be spawned. -Therefore, invoking <tt>synchronize_rcu()</tt> during scheduler -initialization can result in deadlock. - -<p>@@QQ@@ -So what happens with <tt>synchronize_rcu()</tt> during -scheduler initialization for <tt>CONFIG_PREEMPT=n</tt> -kernels? -<p>@@QQA@@ -In <tt>CONFIG_PREEMPT=n</tt> kernel, <tt>synchronize_rcu()</tt> -maps directly to <tt>synchronize_sched()</tt>. -Therefore, <tt>synchronize_rcu()</tt> works normally throughout -boot in <tt>CONFIG_PREEMPT=n</tt> kernels. -However, your code must also work in <tt>CONFIG_PREEMPT=y</tt> kernels, -so it is still necessary to avoid invoking <tt>synchronize_rcu()</tt> -during scheduler initialization. -<p>@@QQE@@ - -<p> -I learned of these boot-time requirements as a result of a series of -system hangs. - -<h3><a name="Interrupts and NMIs">Interrupts and NMIs</a></h3> - -<p> -The Linux kernel has interrupts, and RCU read-side critical sections are -legal within interrupt handlers and within interrupt-disabled regions -of code, as are invocations of <tt>call_rcu()</tt>. - -<p> -Some Linux-kernel architectures can enter an interrupt handler from -non-idle process context, and then just never leave it, instead stealthily -transitioning back to process context. -This trick is sometimes used to invoke system calls from inside the kernel. -These “half-interrupts” mean that RCU has to be very careful -about how it counts interrupt nesting levels. -I learned of this requirement the hard way during a rewrite -of RCU's dyntick-idle code. - -<p> -The Linux kernel has non-maskable interrupts (NMIs), and -RCU read-side critical sections are legal within NMI handlers. -Thankfully, RCU update-side primitives, including -<tt>call_rcu()</tt>, are prohibited within NMI handlers. - -<p> -The name notwithstanding, some Linux-kernel architectures -can have nested NMIs, which RCU must handle correctly. -Andy Lutomirski -<a href="https://lkml.kernel.org/g/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com">surprised me</a> -with this requirement; -he also kindly surprised me with -<a href="https://lkml.kernel.org/g/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com">an algorithm</a> -that meets this requirement. - -<h3><a name="Loadable Modules">Loadable Modules</a></h3> - -<p> -The Linux kernel has loadable modules, and these modules can -also be unloaded. -After a given module has been unloaded, any attempt to call -one of its functions results in a segmentation fault. -The module-unload functions must therefore cancel any -delayed calls to loadable-module functions, for example, -any outstanding <tt>mod_timer()</tt> must be dealt with -via <tt>del_timer_sync()</tt> or similar. - -<p> -Unfortunately, there is no way to cancel an RCU callback; -once you invoke <tt>call_rcu()</tt>, the callback function is -going to eventually be invoked, unless the system goes down first. -Because it is normally considered socially irresponsible to crash the system -in response to a module unload request, we need some other way -to deal with in-flight RCU callbacks. - -<p> -RCU therefore provides -<tt><a href="https://lwn.net/Articles/217484/">rcu_barrier()</a></tt>, -which waits until all in-flight RCU callbacks have been invoked. -If a module uses <tt>call_rcu()</tt>, its exit function should therefore -prevent any future invocation of <tt>call_rcu()</tt>, then invoke -<tt>rcu_barrier()</tt>. -In theory, the underlying module-unload code could invoke -<tt>rcu_barrier()</tt> unconditionally, but in practice this would -incur unacceptable latencies. - -<p> -Nikita Danilov noted this requirement for an analogous filesystem-unmount -situation, and Dipankar Sarma incorporated <tt>rcu_barrier()</tt> into RCU. -The need for <tt>rcu_barrier()</tt> for module unloading became -apparent later. - -<h3><a name="Hotplug CPU">Hotplug CPU</a></h3> - -<p> -The Linux kernel supports CPU hotplug, which means that CPUs -can come and go. -It is of course illegal to use any RCU API member from an offline CPU. -This requirement was present from day one in DYNIX/ptx, but -on the other hand, the Linux kernel's CPU-hotplug implementation -is “interesting.” - -<p> -The Linux-kernel CPU-hotplug implementation has notifiers that -are used to allow the various kernel subsystems (including RCU) -to respond appropriately to a given CPU-hotplug operation. -Most RCU operations may be invoked from CPU-hotplug notifiers, -including even normal synchronous grace-period operations -such as <tt>synchronize_rcu()</tt>. -However, expedited grace-period operations such as -<tt>synchronize_rcu_expedited()</tt> are not supported, -due to the fact that current implementations block CPU-hotplug -operations, which could result in deadlock. - -<p> -In addition, all-callback-wait operations such as -<tt>rcu_barrier()</tt> are also not supported, due to the -fact that there are phases of CPU-hotplug operations where -the outgoing CPU's callbacks will not be invoked until after -the CPU-hotplug operation ends, which could also result in deadlock. - -<h3><a name="Scheduler and RCU">Scheduler and RCU</a></h3> - -<p> -RCU depends on the scheduler, and the scheduler uses RCU to -protect some of its data structures. -This means the scheduler is forbidden from acquiring -the runqueue locks and the priority-inheritance locks -in the middle of an outermost RCU read-side critical section unless either -(1) it releases them before exiting that same -RCU read-side critical section, or -(2) interrupts are disabled across -that entire RCU read-side critical section. -This same prohibition also applies (recursively!) to any lock that is acquired -while holding any lock to which this prohibition applies. -Adhering to this rule prevents preemptible RCU from invoking -<tt>rcu_read_unlock_special()</tt> while either runqueue or -priority-inheritance locks are held, thus avoiding deadlock. - -<p> -Prior to v4.4, it was only necessary to disable preemption across -RCU read-side critical sections that acquired scheduler locks. -In v4.4, expedited grace periods started using IPIs, and these -IPIs could force a <tt>rcu_read_unlock()</tt> to take the slowpath. -Therefore, this expedited-grace-period change required disabling of -interrupts, not just preemption. - -<p> -For RCU's part, the preemptible-RCU <tt>rcu_read_unlock()</tt> -implementation must be written carefully to avoid similar deadlocks. -In particular, <tt>rcu_read_unlock()</tt> must tolerate an -interrupt where the interrupt handler invokes both -<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>. -This possibility requires <tt>rcu_read_unlock()</tt> to use -negative nesting levels to avoid destructive recursion via -interrupt handler's use of RCU. - -<p> -This pair of mutual scheduler-RCU requirements came as a -<a href="https://lwn.net/Articles/453002/">complete surprise</a>. - -<p> -As noted above, RCU makes use of kthreads, and it is necessary to -avoid excessive CPU-time accumulation by these kthreads. -This requirement was no surprise, but RCU's violation of it -when running context-switch-heavy workloads when built with -<tt>CONFIG_NO_HZ_FULL=y</tt> -<a href="http://www.rdrop.com/users/paulmck/scalability/paper/BareMetal.2015.01.15b.pdf">did come as a surprise [PDF]</a>. -RCU has made good progress towards meeting this requirement, even -for context-switch-have <tt>CONFIG_NO_HZ_FULL=y</tt> workloads, -but there is room for further improvement. - -<h3><a name="Tracing and RCU">Tracing and RCU</a></h3> - -<p> -It is possible to use tracing on RCU code, but tracing itself -uses RCU. -For this reason, <tt>rcu_dereference_raw_notrace()</tt> -is provided for use by tracing, which avoids the destructive -recursion that could otherwise ensue. -This API is also used by virtualization in some architectures, -where RCU readers execute in environments in which tracing -cannot be used. -The tracing folks both located the requirement and provided the -needed fix, so this surprise requirement was relatively painless. - -<h3><a name="Energy Efficiency">Energy Efficiency</a></h3> - -<p> -Interrupting idle CPUs is considered socially unacceptable, -especially by people with battery-powered embedded systems. -RCU therefore conserves energy by detecting which CPUs are -idle, including tracking CPUs that have been interrupted from idle. -This is a large part of the energy-efficiency requirement, -so I learned of this via an irate phone call. - -<p> -Because RCU avoids interrupting idle CPUs, it is illegal to -execute an RCU read-side critical section on an idle CPU. -(Kernels built with <tt>CONFIG_PROVE_RCU=y</tt> will splat -if you try it.) -The <tt>RCU_NONIDLE()</tt> macro and <tt>_rcuidle</tt> -event tracing is provided to work around this restriction. -In addition, <tt>rcu_is_watching()</tt> may be used to -test whether or not it is currently legal to run RCU read-side -critical sections on this CPU. -I learned of the need for diagnostics on the one hand -and <tt>RCU_NONIDLE()</tt> on the other while inspecting -idle-loop code. -Steven Rostedt supplied <tt>_rcuidle</tt> event tracing, -which is used quite heavily in the idle loop. - -<p> -It is similarly socially unacceptable to interrupt an -<tt>nohz_full</tt> CPU running in userspace. -RCU must therefore track <tt>nohz_full</tt> userspace -execution. -And in -<a href="https://lwn.net/Articles/558284/"><tt>CONFIG_NO_HZ_FULL_SYSIDLE=y</tt></a> -kernels, RCU must separately track idle CPUs on the one hand and -CPUs that are either idle or executing in userspace on the other. -In both cases, RCU must be able to sample state at two points in -time, and be able to determine whether or not some other CPU spent -any time idle and/or executing in userspace. - -<p> -These energy-efficiency requirements have proven quite difficult to -understand and to meet, for example, there have been more than five -clean-sheet rewrites of RCU's energy-efficiency code, the last of -which was finally able to demonstrate -<a href="http://www.rdrop.com/users/paulmck/realtime/paper/AMPenergy.2013.04.19a.pdf">real energy savings running on real hardware [PDF]</a>. -As noted earlier, -I learned of many of these requirements via angry phone calls: -Flaming me on the Linux-kernel mailing list was apparently not -sufficient to fully vent their ire at RCU's energy-efficiency bugs! - -<h3><a name="Memory Efficiency">Memory Efficiency</a></h3> - -<p> -Although small-memory non-realtime systems can simply use Tiny RCU, -code size is only one aspect of memory efficiency. -Another aspect is the size of the <tt>rcu_head</tt> structure -used by <tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>. -Although this structure contains nothing more than a pair of pointers, -it does appear in many RCU-protected data structures, including -some that are size critical. -The <tt>page</tt> structure is a case in point, as evidenced by -the many occurrences of the <tt>union</tt> keyword within that structure. - -<p> -This need for memory efficiency is one reason that RCU uses hand-crafted -singly linked lists to track the <tt>rcu_head</tt> structures that -are waiting for a grace period to elapse. -It is also the reason why <tt>rcu_head</tt> structures do not contain -debug information, such as fields tracking the file and line of the -<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> that posted them. -Although this information might appear in debug-only kernel builds at some -point, in the meantime, the <tt>->func</tt> field will often provide -the needed debug information. - -<p> -However, in some cases, the need for memory efficiency leads to even -more extreme measures. -Returning to the <tt>page</tt> structure, the <tt>rcu_head</tt> field -shares storage with a great many other structures that are used at -various points in the corresponding page's lifetime. -In order to correctly resolve certain -<a href="https://lkml.kernel.org/g/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com">race conditions</a>, -the Linux kernel's memory-management subsystem needs a particular bit -to remain zero during all phases of grace-period processing, -and that bit happens to map to the bottom bit of the -<tt>rcu_head</tt> structure's <tt>->next</tt> field. -RCU makes this guarantee as long as <tt>call_rcu()</tt> -is used to post the callback, as opposed to <tt>kfree_rcu()</tt> -or some future “lazy” -variant of <tt>call_rcu()</tt> that might one day be created for -energy-efficiency purposes. - -<h3><a name="Performance, Scalability, Response Time, and Reliability"> -Performance, Scalability, Response Time, and Reliability</a></h3> - -<p> -Expanding on the -<a href="#Performance and Scalability">earlier discussion</a>, -RCU is used heavily by hot code paths in performance-critical -portions of the Linux kernel's networking, security, virtualization, -and scheduling code paths. -RCU must therefore use efficient implementations, especially in its -read-side primitives. -To that end, it would be good if preemptible RCU's implementation -of <tt>rcu_read_lock()</tt> could be inlined, however, doing -this requires resolving <tt>#include</tt> issues with the -<tt>task_struct</tt> structure. - -<p> -The Linux kernel supports hardware configurations with up to -4096 CPUs, which means that RCU must be extremely scalable. -Algorithms that involve frequent acquisitions of global locks or -frequent atomic operations on global variables simply cannot be -tolerated within the RCU implementation. -RCU therefore makes heavy use of a combining tree based on the -<tt>rcu_node</tt> structure. -RCU is required to tolerate all CPUs continuously invoking any -combination of RCU's runtime primitives with minimal per-operation -overhead. -In fact, in many cases, increasing load must <i>decrease</i> the -per-operation overhead, witness the batching optimizations for -<tt>synchronize_rcu()</tt>, <tt>call_rcu()</tt>, -<tt>synchronize_rcu_expedited()</tt>, and <tt>rcu_barrier()</tt>. -As a general rule, RCU must cheerfully accept whatever the -rest of the Linux kernel decides to throw at it. - -<p> -The Linux kernel is used for real-time workloads, especially -in conjunction with the -<a href="https://rt.wiki.kernel.org/index.php/Main_Page">-rt patchset</a>. -The real-time-latency response requirements are such that the -traditional approach of disabling preemption across RCU -read-side critical sections is inappropriate. -Kernels built with <tt>CONFIG_PREEMPT=y</tt> therefore -use an RCU implementation that allows RCU read-side critical -sections to be preempted. -This requirement made its presence known after users made it -clear that an earlier -<a href="https://lwn.net/Articles/107930/">real-time patch</a> -did not meet their needs, in conjunction with some -<a href="https://lkml.kernel.org/g/20050318002026.GA2693@us.ibm.com">RCU issues</a> -encountered by a very early version of the -rt patchset. - -<p> -In addition, RCU must make do with a sub-100-microsecond real-time latency -budget. -In fact, on smaller systems with the -rt patchset, the Linux kernel -provides sub-20-microsecond real-time latencies for the whole kernel, -including RCU. -RCU's scalability and latency must therefore be sufficient for -these sorts of configurations. -To my surprise, the sub-100-microsecond real-time latency budget -<a href="http://www.rdrop.com/users/paulmck/realtime/paper/bigrt.2013.01.31a.LCA.pdf"> -applies to even the largest systems [PDF]</a>, -up to and including systems with 4096 CPUs. -This real-time requirement motivated the grace-period kthread, which -also simplified handling of a number of race conditions. - -<p> -Finally, RCU's status as a synchronization primitive means that -any RCU failure can result in arbitrary memory corruption that can be -extremely difficult to debug. -This means that RCU must be extremely reliable, which in -practice also means that RCU must have an aggressive stress-test -suite. -This stress-test suite is called <tt>rcutorture</tt>. - -<p> -Although the need for <tt>rcutorture</tt> was no surprise, -the current immense popularity of the Linux kernel is posing -interesting—and perhaps unprecedented—validation -challenges. -To see this, keep in mind that there are well over one billion -instances of the Linux kernel running today, given Android -smartphones, Linux-powered televisions, and servers. -This number can be expected to increase sharply with the advent of -the celebrated Internet of Things. - -<p> -Suppose that RCU contains a race condition that manifests on average -once per million years of runtime. -This bug will be occurring about three times per <i>day</i> across -the installed base. -RCU could simply hide behind hardware error rates, given that no one -should really expect their smartphone to last for a million years. -However, anyone taking too much comfort from this thought should -consider the fact that in most jurisdictions, a successful multi-year -test of a given mechanism, which might include a Linux kernel, -suffices for a number of types of safety-critical certifications. -In fact, rumor has it that the Linux kernel is already being used -in production for safety-critical applications. -I don't know about you, but I would feel quite bad if a bug in RCU -killed someone. -Which might explain my recent focus on validation and verification. - -<h2><a name="Other RCU Flavors">Other RCU Flavors</a></h2> - -<p> -One of the more surprising things about RCU is that there are now -no fewer than five <i>flavors</i>, or API families. -In addition, the primary flavor that has been the sole focus up to -this point has two different implementations, non-preemptible and -preemptible. -The other four flavors are listed below, with requirements for each -described in a separate section. - -<ol> -<li> <a href="#Bottom-Half Flavor">Bottom-Half Flavor</a> -<li> <a href="#Sched Flavor">Sched Flavor</a> -<li> <a href="#Sleepable RCU">Sleepable RCU</a> -<li> <a href="#Tasks RCU">Tasks RCU</a> -</ol> - -<h3><a name="Bottom-Half Flavor">Bottom-Half Flavor</a></h3> - -<p> -The softirq-disable (AKA “bottom-half”, -hence the “_bh” abbreviations) -flavor of RCU, or <i>RCU-bh</i>, was developed by -Dipankar Sarma to provide a flavor of RCU that could withstand the -network-based denial-of-service attacks researched by Robert -Olsson. -These attacks placed so much networking load on the system -that some of the CPUs never exited softirq execution, -which in turn prevented those CPUs from ever executing a context switch, -which, in the RCU implementation of that time, prevented grace periods -from ever ending. -The result was an out-of-memory condition and a system hang. - -<p> -The solution was the creation of RCU-bh, which does -<tt>local_bh_disable()</tt> -across its read-side critical sections, and which uses the transition -from one type of softirq processing to another as a quiescent state -in addition to context switch, idle, user mode, and offline. -This means that RCU-bh grace periods can complete even when some of -the CPUs execute in softirq indefinitely, thus allowing algorithms -based on RCU-bh to withstand network-based denial-of-service attacks. - -<p> -Because -<tt>rcu_read_lock_bh()</tt> and <tt>rcu_read_unlock_bh()</tt> -disable and re-enable softirq handlers, any attempt to start a softirq -handlers during the -RCU-bh read-side critical section will be deferred. -In this case, <tt>rcu_read_unlock_bh()</tt> -will invoke softirq processing, which can take considerable time. -One can of course argue that this softirq overhead should be associated -with the code following the RCU-bh read-side critical section rather -than <tt>rcu_read_unlock_bh()</tt>, but the fact -is that most profiling tools cannot be expected to make this sort -of fine distinction. -For example, suppose that a three-millisecond-long RCU-bh read-side -critical section executes during a time of heavy networking load. -There will very likely be an attempt to invoke at least one softirq -handler during that three milliseconds, but any such invocation will -be delayed until the time of the <tt>rcu_read_unlock_bh()</tt>. -This can of course make it appear at first glance as if -<tt>rcu_read_unlock_bh()</tt> was executing very slowly. - -<p> -The -<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-bh API</a> -includes -<tt>rcu_read_lock_bh()</tt>, -<tt>rcu_read_unlock_bh()</tt>, -<tt>rcu_dereference_bh()</tt>, -<tt>rcu_dereference_bh_check()</tt>, -<tt>synchronize_rcu_bh()</tt>, -<tt>synchronize_rcu_bh_expedited()</tt>, -<tt>call_rcu_bh()</tt>, -<tt>rcu_barrier_bh()</tt>, and -<tt>rcu_read_lock_bh_held()</tt>. - -<h3><a name="Sched Flavor">Sched Flavor</a></h3> - -<p> -Before preemptible RCU, waiting for an RCU grace period had the -side effect of also waiting for all pre-existing interrupt -and NMI handlers. -However, there are legitimate preemptible-RCU implementations that -do not have this property, given that any point in the code outside -of an RCU read-side critical section can be a quiescent state. -Therefore, <i>RCU-sched</i> was created, which follows “classic” -RCU in that an RCU-sched grace period waits for for pre-existing -interrupt and NMI handlers. -In kernels built with <tt>CONFIG_PREEMPT=n</tt>, the RCU and RCU-sched -APIs have identical implementations, while kernels built with -<tt>CONFIG_PREEMPT=y</tt> provide a separate implementation for each. - -<p> -Note well that in <tt>CONFIG_PREEMPT=y</tt> kernels, -<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt> -disable and re-enable preemption, respectively. -This means that if there was a preemption attempt during the -RCU-sched read-side critical section, <tt>rcu_read_unlock_sched()</tt> -will enter the scheduler, with all the latency and overhead entailed. -Just as with <tt>rcu_read_unlock_bh()</tt>, this can make it look -as if <tt>rcu_read_unlock_sched()</tt> was executing very slowly. -However, the highest-priority task won't be preempted, so that task -will enjoy low-overhead <tt>rcu_read_unlock_sched()</tt> invocations. - -<p> -The -<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-sched API</a> -includes -<tt>rcu_read_lock_sched()</tt>, -<tt>rcu_read_unlock_sched()</tt>, -<tt>rcu_read_lock_sched_notrace()</tt>, -<tt>rcu_read_unlock_sched_notrace()</tt>, -<tt>rcu_dereference_sched()</tt>, -<tt>rcu_dereference_sched_check()</tt>, -<tt>synchronize_sched()</tt>, -<tt>synchronize_rcu_sched_expedited()</tt>, -<tt>call_rcu_sched()</tt>, -<tt>rcu_barrier_sched()</tt>, and -<tt>rcu_read_lock_sched_held()</tt>. -However, anything that disables preemption also marks an RCU-sched -read-side critical section, including -<tt>preempt_disable()</tt> and <tt>preempt_enable()</tt>, -<tt>local_irq_save()</tt> and <tt>local_irq_restore()</tt>, -and so on. - -<h3><a name="Sleepable RCU">Sleepable RCU</a></h3> - -<p> -For well over a decade, someone saying “I need to block within -an RCU read-side critical section” was a reliable indication -that this someone did not understand RCU. -After all, if you are always blocking in an RCU read-side critical -section, you can probably afford to use a higher-overhead synchronization -mechanism. -However, that changed with the advent of the Linux kernel's notifiers, -whose RCU read-side critical -sections almost never sleep, but sometimes need to. -This resulted in the introduction of -<a href="https://lwn.net/Articles/202847/">sleepable RCU</a>, -or <i>SRCU</i>. - -<p> -SRCU allows different domains to be defined, with each such domain -defined by an instance of an <tt>srcu_struct</tt> structure. -A pointer to this structure must be passed in to each SRCU function, -for example, <tt>synchronize_srcu(&ss)</tt>, where -<tt>ss</tt> is the <tt>srcu_struct</tt> structure. -The key benefit of these domains is that a slow SRCU reader in one -domain does not delay an SRCU grace period in some other domain. -That said, one consequence of these domains is that read-side code -must pass a “cookie” from <tt>srcu_read_lock()</tt> -to <tt>srcu_read_unlock()</tt>, for example, as follows: - -<blockquote> -<pre> - 1 int idx; - 2 - 3 idx = srcu_read_lock(&ss); - 4 do_something(); - 5 srcu_read_unlock(&ss, idx); -</pre> -</blockquote> - -<p> -As noted above, it is legal to block within SRCU read-side critical sections, -however, with great power comes great responsibility. -If you block forever in one of a given domain's SRCU read-side critical -sections, then that domain's grace periods will also be blocked forever. -Of course, one good way to block forever is to deadlock, which can -happen if any operation in a given domain's SRCU read-side critical -section can block waiting, either directly or indirectly, for that domain's -grace period to elapse. -For example, this results in a self-deadlock: - -<blockquote> -<pre> - 1 int idx; - 2 - 3 idx = srcu_read_lock(&ss); - 4 do_something(); - 5 synchronize_srcu(&ss); - 6 srcu_read_unlock(&ss, idx); -</pre> -</blockquote> - -<p> -However, if line 5 acquired a mutex that was held across -a <tt>synchronize_srcu()</tt> for domain <tt>ss</tt>, -deadlock would still be possible. -Furthermore, if line 5 acquired a mutex that was held across -a <tt>synchronize_srcu()</tt> for some other domain <tt>ss1</tt>, -and if an <tt>ss1</tt>-domain SRCU read-side critical section -acquired another mutex that was held across as <tt>ss</tt>-domain -<tt>synchronize_srcu()</tt>, -deadlock would again be possible. -Such a deadlock cycle could extend across an arbitrarily large number -of different SRCU domains. -Again, with great power comes great responsibility. - -<p> -Unlike the other RCU flavors, SRCU read-side critical sections can -run on idle and even offline CPUs. -This ability requires that <tt>srcu_read_lock()</tt> and -<tt>srcu_read_unlock()</tt> contain memory barriers, which means -that SRCU readers will run a bit slower than would RCU readers. -It also motivates the <tt>smp_mb__after_srcu_read_unlock()</tt> -API, which, in combination with <tt>srcu_read_unlock()</tt>, -guarantees a full memory barrier. - -<p> -The -<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">SRCU API</a> -includes -<tt>srcu_read_lock()</tt>, -<tt>srcu_read_unlock()</tt>, -<tt>srcu_dereference()</tt>, -<tt>srcu_dereference_check()</tt>, -<tt>synchronize_srcu()</tt>, -<tt>synchronize_srcu_expedited()</tt>, -<tt>call_srcu()</tt>, -<tt>srcu_barrier()</tt>, and -<tt>srcu_read_lock_held()</tt>. -It also includes -<tt>DEFINE_SRCU()</tt>, -<tt>DEFINE_STATIC_SRCU()</tt>, and -<tt>init_srcu_struct()</tt> -APIs for defining and initializing <tt>srcu_struct</tt> structures. - -<h3><a name="Tasks RCU">Tasks RCU</a></h3> - -<p> -Some forms of tracing use “tramopolines” to handle the -binary rewriting required to install different types of probes. -It would be good to be able to free old trampolines, which sounds -like a job for some form of RCU. -However, because it is necessary to be able to install a trace -anywhere in the code, it is not possible to use read-side markers -such as <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>. -In addition, it does not work to have these markers in the trampoline -itself, because there would need to be instructions following -<tt>rcu_read_unlock()</tt>. -Although <tt>synchronize_rcu()</tt> would guarantee that execution -reached the <tt>rcu_read_unlock()</tt>, it would not be able to -guarantee that execution had completely left the trampoline. - -<p> -The solution, in the form of -<a href="https://lwn.net/Articles/607117/"><i>Tasks RCU</i></a>, -is to have implicit -read-side critical sections that are delimited by voluntary context -switches, that is, calls to <tt>schedule()</tt>, -<tt>cond_resched_rcu_qs()</tt>, and -<tt>synchronize_rcu_tasks()</tt>. -In addition, transitions to and from userspace execution also delimit -tasks-RCU read-side critical sections. - -<p> -The tasks-RCU API is quite compact, consisting only of -<tt>call_rcu_tasks()</tt>, -<tt>synchronize_rcu_tasks()</tt>, and -<tt>rcu_barrier_tasks()</tt>. - -<h2><a name="Possible Future Changes">Possible Future Changes</a></h2> - -<p> -One of the tricks that RCU uses to attain update-side scalability is -to increase grace-period latency with increasing numbers of CPUs. -If this becomes a serious problem, it will be necessary to rework the -grace-period state machine so as to avoid the need for the additional -latency. - -<p> -Expedited grace periods scan the CPUs, so their latency and overhead -increases with increasing numbers of CPUs. -If this becomes a serious problem on large systems, it will be necessary -to do some redesign to avoid this scalability problem. - -<p> -RCU disables CPU hotplug in a few places, perhaps most notably in the -expedited grace-period and <tt>rcu_barrier()</tt> operations. -If there is a strong reason to use expedited grace periods in CPU-hotplug -notifiers, it will be necessary to avoid disabling CPU hotplug. -This would introduce some complexity, so there had better be a <i>very</i> -good reason. - -<p> -The tradeoff between grace-period latency on the one hand and interruptions -of other CPUs on the other hand may need to be re-examined. -The desire is of course for zero grace-period latency as well as zero -interprocessor interrupts undertaken during an expedited grace period -operation. -While this ideal is unlikely to be achievable, it is quite possible that -further improvements can be made. - -<p> -The multiprocessor implementations of RCU use a combining tree that -groups CPUs so as to reduce lock contention and increase cache locality. -However, this combining tree does not spread its memory across NUMA -nodes nor does it align the CPU groups with hardware features such -as sockets or cores. -Such spreading and alignment is currently believed to be unnecessary -because the hotpath read-side primitives do not access the combining -tree, nor does <tt>call_rcu()</tt> in the common case. -If you believe that your architecture needs such spreading and alignment, -then your architecture should also benefit from the -<tt>rcutree.rcu_fanout_leaf</tt> boot parameter, which can be set -to the number of CPUs in a socket, NUMA node, or whatever. -If the number of CPUs is too large, use a fraction of the number of -CPUs. -If the number of CPUs is a large prime number, well, that certainly -is an “interesting” architectural choice! -More flexible arrangements might be considered, but only if -<tt>rcutree.rcu_fanout_leaf</tt> has proven inadequate, and only -if the inadequacy has been demonstrated by a carefully run and -realistic system-level workload. - -<p> -Please note that arrangements that require RCU to remap CPU numbers will -require extremely good demonstration of need and full exploration of -alternatives. - -<p> -There is an embarrassingly large number of flavors of RCU, and this -number has been increasing over time. -Perhaps it will be possible to combine some at some future date. - -<p> -RCU's various kthreads are reasonably recent additions. -It is quite likely that adjustments will be required to more gracefully -handle extreme loads. -It might also be necessary to be able to relate CPU utilization by -RCU's kthreads and softirq handlers to the code that instigated this -CPU utilization. -For example, RCU callback overhead might be charged back to the -originating <tt>call_rcu()</tt> instance, though probably not -in production kernels. - -<h2><a name="Summary">Summary</a></h2> - -<p> -This document has presented more than two decade's worth of RCU -requirements. -Given that the requirements keep changing, this will not be the last -word on this subject, but at least it serves to get an important -subset of the requirements set forth. - -<h2><a name="Acknowledgments">Acknowledgments</a></h2> - -I am grateful to Steven Rostedt, Lai Jiangshan, Ingo Molnar, -Oleg Nesterov, Borislav Petkov, Peter Zijlstra, Boqun Feng, and -Andy Lutomirski for their help in rendering -this article human readable, and to Michelle Rankin for her support -of this effort. -Other contributions are acknowledged in the Linux kernel's git archive. -The cartoon is copyright (c) 2013 by Melissa Broussard, -and is provided -under the terms of the Creative Commons Attribution-Share Alike 3.0 -United States license. - -<p>@@QQAL@@ - -</body></html> diff --git a/Documentation/RCU/Design/htmlqqz.sh b/Documentation/RCU/Design/htmlqqz.sh deleted file mode 100755 index d354f06..0000000 --- a/Documentation/RCU/Design/htmlqqz.sh +++ /dev/null @@ -1,108 +0,0 @@ -#!/bin/sh -# -# Usage: sh htmlqqz.sh file -# -# Extracts and converts quick quizzes in a proto-HTML document file.htmlx. -# Commands, all of which must be on a line by themselves: -# -# "<p>@@QQ@@": Start of a quick quiz. -# "<p>@@QQA@@": Start of a quick-quiz answer. -# "<p>@@QQE@@": End of a quick-quiz answer, and thus of the quick quiz. -# "<p>@@QQAL@@": Place to put quick-quiz answer list. -# -# Places the result in file.html. -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, you can access it online at -# http://www.gnu.org/licenses/gpl-2.0.html. -# -# Copyright (c) 2013 Paul E. McKenney, IBM Corporation. - -fn=$1 -if test ! -r $fn.htmlx -then - echo "Error: $fn.htmlx unreadable." - exit 1 -fi - -echo "<!-- DO NOT HAND EDIT. -->" > $fn.html -echo "<!-- Instead, edit $fn.htmlx and run 'sh htmlqqz.sh $fn' -->" >> $fn.html -awk < $fn.htmlx >> $fn.html ' - -state == "" && $1 != "<p>@@QQ@@" && $1 != "<p>@@QQAL@@" { - print $0; - if ($0 ~ /^<p>@@QQ/) - print "Bad Quick Quiz command: " NR " (expected <p>@@QQ@@ or <p>@@QQAL@@)." > "/dev/stderr" - next; -} - -state == "" && $1 == "<p>@@QQ@@" { - qqn++; - qqlineno = NR; - haveqq = 1; - state = "qq"; - print "<p><a name=\"Quick Quiz " qqn "\"><b>Quick Quiz " qqn "</b>:</a>" - next; -} - -state == "qq" && $1 != "<p>@@QQA@@" { - qq[qqn] = qq[qqn] $0 "\n"; - print $0 - if ($0 ~ /^<p>@@QQ/) - print "Bad Quick Quiz command: " NR ". (expected <p>@@QQA@@)" > "/dev/stderr" - next; -} - -state == "qq" && $1 == "<p>@@QQA@@" { - state = "qqa"; - print "<br><a href=\"#qq" qqn "answer\">Answer</a>" - next; -} - -state == "qqa" && $1 != "<p>@@QQE@@" { - qqa[qqn] = qqa[qqn] $0 "\n"; - if ($0 ~ /^<p>@@QQ/) - print "Bad Quick Quiz command: " NR " (expected <p>@@QQE@@)." > "/dev/stderr" - next; -} - -state == "qqa" && $1 == "<p>@@QQE@@" { - state = ""; - next; -} - -state == "" && $1 == "<p>@@QQAL@@" { - haveqq = ""; - print "<h3><a name=\"Answers to Quick Quizzes\">" - print "Answers to Quick Quizzes</a></h3>" - print ""; - for (i = 1; i <= qqn; i++) { - print "<a name=\"qq" i "answer\"></a>" - print "<p><b>Quick Quiz " i "</b>:" - print qq[i]; - print ""; - print "</p><p><b>Answer</b>:" - print qqa[i]; - print ""; - print "</p><p><a href=\"#Quick%20Quiz%20" i "\"><b>Back to Quick Quiz " i "</b>.</a>" - print ""; - } - next; -} - -END { - if (state != "") - print "Unterminated Quick Quiz: " qqlineno "." > "/dev/stderr" - else if (haveqq) - print "Missing \"<p>@@QQAL@@\", no Quick Quiz." > "/dev/stderr" -}' diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index ec6998b..00a3a38 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -237,17 +237,17 @@ o "ktl" is the low-order 16 bits (in hexadecimal) of the count of The output of "cat rcu/rcu_preempt/rcuexp" looks as follows: -s=21872 wd0=0 wd1=0 wd2=0 wd3=5 n=0 enq=0 sc=21872 +s=21872 wd1=0 wd2=0 wd3=5 n=0 enq=0 sc=21872 These fields are as follows: o "s" is the sequence number, with an odd number indicating that an expedited grace period is in progress. -o "wd0", "wd1", "wd2", and "wd3" are the number of times that an - attempt to start an expedited grace period found that someone - else had completed an expedited grace period that satisfies the - attempted request. "Our work is done." +o "wd1", "wd2", and "wd3" are the number of times that an attempt + to start an expedited grace period found that someone else had + completed an expedited grace period that satisfies the attempted + request. "Our work is done." o "n" is number of times that a concurrent CPU-hotplug operation forced a fallback to a normal grace period. diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index dc49c67..111770f 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -681,22 +681,30 @@ Although RCU can be used in many different ways, a very common use of RCU is analogous to reader-writer locking. The following unified diff shows how closely related RCU and reader-writer locking can be. + @@ -5,5 +5,5 @@ struct el { + int data; + /* Other data fields */ + }; + -rwlock_t listmutex; + +spinlock_t listmutex; + struct el head; + @@ -13,15 +14,15 @@ struct list_head *lp; struct el *p; - - read_lock(); + - read_lock(&listmutex); - list_for_each_entry(p, head, lp) { + rcu_read_lock(); + list_for_each_entry_rcu(p, head, lp) { if (p->key == key) { *result = p->data; - - read_unlock(); + - read_unlock(&listmutex); + rcu_read_unlock(); return 1; } } - - read_unlock(); + - read_unlock(&listmutex); + rcu_read_unlock(); return 0; } @@ -732,7 +740,7 @@ Or, for those who prefer a side-by-side listing: 5 int data; 5 int data; 6 /* Other data fields */ 6 /* Other data fields */ 7 }; 7 }; - 8 spinlock_t listmutex; 8 spinlock_t listmutex; + 8 rwlock_t listmutex; 8 spinlock_t listmutex; 9 struct el head; 9 struct el head; 1 int search(long key, int *result) 1 int search(long key, int *result) @@ -740,15 +748,15 @@ Or, for those who prefer a side-by-side listing: 3 struct list_head *lp; 3 struct list_head *lp; 4 struct el *p; 4 struct el *p; 5 5 - 6 read_lock(); 6 rcu_read_lock(); + 6 read_lock(&listmutex); 6 rcu_read_lock(); 7 list_for_each_entry(p, head, lp) { 7 list_for_each_entry_rcu(p, head, lp) { 8 if (p->key == key) { 8 if (p->key == key) { 9 *result = p->data; 9 *result = p->data; -10 read_unlock(); 10 rcu_read_unlock(); +10 read_unlock(&listmutex); 10 rcu_read_unlock(); 11 return 1; 11 return 1; 12 } 12 } 13 } 13 } -14 read_unlock(); 14 rcu_read_unlock(); +14 read_unlock(&listmutex); 14 rcu_read_unlock(); 15 return 0; 15 return 0; 16 } 16 } diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt index 30df832..87adfb2 100644 --- a/Documentation/devicetree/bindings/ata/ahci-platform.txt +++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt @@ -32,6 +32,10 @@ Optional properties: - target-supply : regulator for SATA target power - phys : reference to the SATA PHY node - phy-names : must be "sata-phy" +- ports-implemented : Mask that indicates which ports that the HBA supports + are available for software to use. Useful if PORTS_IMPL + is not programmed by the BIOS, which is true with + some embedded SOC's. Required properties when using sub-nodes: - #address-cells : number of cells to encode an address diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index 28a4781..0ae0649 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -45,13 +45,13 @@ Required properties: Optional properties: - dual_emac_res_vlan : Specifies VID to be used to segregate the ports - mac-address : See ethernet.txt file in the same directory -- phy_id : Specifies slave phy id +- phy_id : Specifies slave phy id (deprecated, use phy-handle) - phy-handle : See ethernet.txt file in the same directory Slave sub-nodes: - fixed-link : See fixed-link.txt file in the same directory - Either the property phy_id, or the sub-node - fixed-link can be specified + +Note: Exactly one of phy_id, phy-handle, or fixed-link must be specified. Note: "ti,hwmods" field is used to fetch the base address and irq resources from TI, omap hwmod data base during device registration. diff --git a/Documentation/devicetree/bindings/regmap/regmap.txt b/Documentation/devicetree/bindings/regmap/regmap.txt index e98a9652..0127be3 100644 --- a/Documentation/devicetree/bindings/regmap/regmap.txt +++ b/Documentation/devicetree/bindings/regmap/regmap.txt @@ -1,50 +1,29 @@ -Device-Tree binding for regmap - -The endianness mode of CPU & Device scenarios: -Index Device Endianness properties ---------------------------------------------------- -1 BE 'big-endian' -2 LE 'little-endian' -3 Native 'native-endian' - -For one device driver, which will run in different scenarios above -on different SoCs using the devicetree, we need one way to simplify -this. +Devicetree binding for regmap Optional properties: -- {big,little,native}-endian: these are boolean properties, if absent - then the implementation will choose a default based on the device - being controlled. These properties are for register values and all - the buffers only. Native endian means that the CPU and device have - the same endianness. -Examples: -Scenario 1 : CPU in LE mode & device in LE mode. -dev: dev@40031000 { - compatible = "name"; - reg = <0x40031000 0x1000>; - ... -}; + little-endian, + big-endian, + native-endian: See common-properties.txt for a definition -Scenario 2 : CPU in LE mode & device in BE mode. -dev: dev@40031000 { - compatible = "name"; - reg = <0x40031000 0x1000>; - ... - big-endian; -}; +Note: +Regmap defaults to little-endian register access on MMIO based +devices, this is by far the most common setting. On CPU +architectures that typically run big-endian operating systems +(e.g. PowerPC), registers can be defined as big-endian and must +be marked that way in the devicetree. -Scenario 3 : CPU in BE mode & device in BE mode. -dev: dev@40031000 { - compatible = "name"; - reg = <0x40031000 0x1000>; - ... -}; +On SoCs that can be operated in both big-endian and little-endian +modes, with a single hardware switch controlling both the endianess +of the CPU and a byteswap for MMIO registers (e.g. many Broadcom MIPS +chips), "native-endian" is used to allow using the same device tree +blob in both cases. -Scenario 4 : CPU in BE mode & device in LE mode. +Examples: +Scenario 1 : a register set in big-endian mode. dev: dev@40031000 { - compatible = "name"; + compatible = "syscon"; reg = <0x40031000 0x1000>; + big-endian; ... - little-endian; }; diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 8ba7f82..13f89d1 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3292,6 +3292,44 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Lazy RCU callbacks are those which RCU can prove do nothing more than free memory. + rcuperf.gp_exp= [KNL] + Measure performance of expedited synchronous + grace-period primitives. + + rcuperf.holdoff= [KNL] + Set test-start holdoff period. The purpose of + this parameter is to delay the start of the + test until boot completes in order to avoid + interference. + + rcuperf.nreaders= [KNL] + Set number of RCU readers. The value -1 selects + N, where N is the number of CPUs. A value + "n" less than -1 selects N-n+1, where N is again + the number of CPUs. For example, -2 selects N + (the number of CPUs), -3 selects N+1, and so on. + A value of "n" less than or equal to -N selects + a single reader. + + rcuperf.nwriters= [KNL] + Set number of RCU writers. The values operate + the same as for rcuperf.nreaders. + N, where N is the number of CPUs + + rcuperf.perf_runnable= [BOOT] + Start rcuperf running at boot time. + + rcuperf.shutdown= [KNL] + Shut the system down after performance tests + complete. This is useful for hands-off automated + testing. + + rcuperf.perf_type= [KNL] + Specify the RCU implementation to test. + + rcuperf.verbose= [KNL] + Enable additional printk() statements. + rcutorture.cbflood_inter_holdoff= [KNL] Set holdoff time (jiffies) between successive callback-flood tests. diff --git a/Documentation/locking/lockdep-design.txt b/Documentation/locking/lockdep-design.txt index 5001280..9de1c15 100644 --- a/Documentation/locking/lockdep-design.txt +++ b/Documentation/locking/lockdep-design.txt @@ -97,7 +97,7 @@ between any two lock-classes: <hardirq-safe> -> <hardirq-unsafe> <softirq-safe> -> <softirq-unsafe> -The first rule comes from the fact the a hardirq-safe lock could be +The first rule comes from the fact that a hardirq-safe lock could be taken by a hardirq context, interrupting a hardirq-unsafe lock - and thus could result in a lock inversion deadlock. Likewise, a softirq-safe lock could be taken by an softirq context, interrupting a softirq-unsafe @@ -220,7 +220,7 @@ calculated, which hash is unique for every lock chain. The hash value, when the chain is validated for the first time, is then put into a hash table, which hash-table can be checked in a lockfree manner. If the locking chain occurs again later on, the hash table tells us that we -dont have to validate the chain again. +don't have to validate the chain again. Troubleshooting: ---------------- diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 3729cbe..147ae8e 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -4,8 +4,40 @@ By: David Howells <dhowells@redhat.com> Paul E. McKenney <paulmck@linux.vnet.ibm.com> + Will Deacon <will.deacon@arm.com> + Peter Zijlstra <peterz@infradead.org> -Contents: +========== +DISCLAIMER +========== + +This document is not a specification; it is intentionally (for the sake of +brevity) and unintentionally (due to being human) incomplete. This document is +meant as a guide to using the various memory barriers provided by Linux, but +in case of any doubt (and there are many) please ask. + +To repeat, this document is not a specification of what Linux expects from +hardware. + +The purpose of this document is twofold: + + (1) to specify the minimum functionality that one can rely on for any + particular barrier, and + + (2) to provide a guide as to how to use the barriers that are available. + +Note that an architecture can provide more than the minimum requirement +for any particular barrier, but if the architecure provides less than +that, that architecture is incorrect. + +Note also that it is possible that a barrier may be a no-op for an +architecture because the way that arch works renders an explicit barrier +unnecessary in that case. + + +======== +CONTENTS +======== (*) Abstract memory access model. @@ -31,15 +63,15 @@ Contents: (*) Implicit kernel memory barriers. - - Locking functions. + - Lock acquisition functions. - Interrupt disabling functions. - Sleep and wake-up functions. - Miscellaneous functions. - (*) Inter-CPU locking barrier effects. + (*) Inter-CPU acquiring barrier effects. - - Locks vs memory accesses. - - Locks vs I/O accesses. + - Acquires vs memory accesses. + - Acquires vs I/O accesses. (*) Where are memory barriers needed? @@ -61,6 +93,7 @@ Contents: (*) The things CPUs get up to. - And then there's the Alpha. + - Virtual Machine Guests. (*) Example uses. @@ -148,7 +181,7 @@ As a further example, consider this sequence of events: CPU 1 CPU 2 =============== =============== - { A == 1, B == 2, C = 3, P == &A, Q == &C } + { A == 1, B == 2, C == 3, P == &A, Q == &C } B = 4; Q = P; P = &B D = *Q; @@ -430,8 +463,9 @@ And a couple of implicit varieties: This acts as a one-way permeable barrier. It guarantees that all memory operations after the ACQUIRE operation will appear to happen after the ACQUIRE operation with respect to the other components of the system. - ACQUIRE operations include LOCK operations and smp_load_acquire() - operations. + ACQUIRE operations include LOCK operations and both smp_load_acquire() + and smp_cond_acquire() operations. The later builds the necessary ACQUIRE + semantics from relying on a control dependency and smp_rmb(). Memory operations that occur before an ACQUIRE operation may appear to happen after it completes. @@ -464,6 +498,11 @@ And a couple of implicit varieties: This means that ACQUIRE acts as a minimal "acquire" operation and RELEASE acts as a minimal "release" operation. +A subset of the atomic operations described in atomic_ops.txt have ACQUIRE +and RELEASE variants in addition to fully-ordered and relaxed (no barrier +semantics) definitions. For compound atomics performing both a load and a +store, ACQUIRE semantics apply only to the load and RELEASE semantics apply +only to the store portion of the operation. Memory barriers are only required where there's a possibility of interaction between two CPUs or between a CPU and a device. If it can be guaranteed that @@ -517,7 +556,7 @@ following sequence of events: CPU 1 CPU 2 =============== =============== - { A == 1, B == 2, C = 3, P == &A, Q == &C } + { A == 1, B == 2, C == 3, P == &A, Q == &C } B = 4; <write barrier> WRITE_ONCE(P, &B) @@ -544,7 +583,7 @@ between the address load and the data load: CPU 1 CPU 2 =============== =============== - { A == 1, B == 2, C = 3, P == &A, Q == &C } + { A == 1, B == 2, C == 3, P == &A, Q == &C } B = 4; <write barrier> WRITE_ONCE(P, &B); @@ -813,9 +852,10 @@ In summary: the same variable, then those stores must be ordered, either by preceding both of them with smp_mb() or by using smp_store_release() to carry out the stores. Please note that it is -not- sufficient - to use barrier() at beginning of each leg of the "if" statement, - as optimizing compilers do not necessarily respect barrier() - in this case. + to use barrier() at beginning of each leg of the "if" statement + because, as shown by the example above, optimizing compilers can + destroy the control dependency while respecting the letter of the + barrier() law. (*) Control dependencies require at least one run-time conditional between the prior load and the subsequent store, and this @@ -1731,15 +1771,15 @@ The Linux kernel has eight basic CPU memory barriers: All memory barriers except the data dependency barriers imply a compiler -barrier. Data dependencies do not impose any additional compiler ordering. +barrier. Data dependencies do not impose any additional compiler ordering. Aside: In the case of data dependencies, the compiler would be expected to issue the loads in the correct order (eg. `a[b]` would have to load the value of b before loading a[b]), however there is no guarantee in the C specification that the compiler may not speculate the value of b (eg. is equal to 1) and load a before b (eg. tmp = a[1]; if (b != 1) -tmp = a[b]; ). There is also the problem of a compiler reloading b after -having loaded a[b], thus having a newer copy of b than a[b]. A consensus +tmp = a[b]; ). There is also the problem of a compiler reloading b after +having loaded a[b], thus having a newer copy of b than a[b]. A consensus has not yet been reached about these problems, however the READ_ONCE() macro is a good place to start looking. @@ -1794,6 +1834,7 @@ There are some more advanced barrier functions: (*) lockless_dereference(); + This can be thought of as a pointer-fetch wrapper around the smp_read_barrier_depends() data-dependency barrier. @@ -1858,7 +1899,7 @@ This is a variation on the mandatory write barrier that causes writes to weakly ordered I/O regions to be partially ordered. Its effects may go beyond the CPU->Hardware interface and actually affect the hardware at some level. -See the subsection "Locks vs I/O accesses" for more information. +See the subsection "Acquires vs I/O accesses" for more information. =============================== @@ -1873,8 +1914,8 @@ provide more substantial guarantees, but these may not be relied upon outside of arch specific code. -ACQUIRING FUNCTIONS -------------------- +LOCK ACQUISITION FUNCTIONS +-------------------------- The Linux kernel has a number of locking constructs: @@ -1895,7 +1936,7 @@ for each construct. These operations all imply certain barriers: Memory operations issued before the ACQUIRE may be completed after the ACQUIRE operation has completed. An smp_mb__before_spinlock(), combined with a following ACQUIRE, orders prior stores against - subsequent loads and stores. Note that this is weaker than smp_mb()! + subsequent loads and stores. Note that this is weaker than smp_mb()! The smp_mb__before_spinlock() primitive is free on many architectures. (2) RELEASE operation implication: @@ -2090,9 +2131,9 @@ or: event_indicated = 1; wake_up_process(event_daemon); -A write memory barrier is implied by wake_up() and co. if and only if they wake -something up. The barrier occurs before the task state is cleared, and so sits -between the STORE to indicate the event and the STORE to set TASK_RUNNING: +A write memory barrier is implied by wake_up() and co. if and only if they +wake something up. The barrier occurs before the task state is cleared, and so +sits between the STORE to indicate the event and the STORE to set TASK_RUNNING: CPU 1 CPU 2 =============================== =============================== @@ -2206,7 +2247,7 @@ three CPUs; then should the following sequence of events occur: Then there is no guarantee as to what order CPU 3 will see the accesses to *A through *H occur in, other than the constraints imposed by the separate locks -on the separate CPUs. It might, for example, see: +on the separate CPUs. It might, for example, see: *E, ACQUIRE M, ACQUIRE Q, *G, *C, *F, *A, *B, RELEASE Q, *D, *H, RELEASE M @@ -2486,9 +2527,9 @@ The following operations are special locking primitives: clear_bit_unlock(); __clear_bit_unlock(); -These implement ACQUIRE-class and RELEASE-class operations. These should be used in -preference to other operations when implementing locking primitives, because -their implementations can be optimised on many architectures. +These implement ACQUIRE-class and RELEASE-class operations. These should be +used in preference to other operations when implementing locking primitives, +because their implementations can be optimised on many architectures. [!] Note that special memory barrier primitives are available for these situations because on some CPUs the atomic instructions used imply full memory @@ -2568,12 +2609,12 @@ explicit barriers are used. Normally this won't be a problem because the I/O accesses done inside such sections will include synchronous load operations on strictly ordered I/O -registers that form implicit I/O barriers. If this isn't sufficient then an +registers that form implicit I/O barriers. If this isn't sufficient then an mmiowb() may need to be used explicitly. A similar situation may occur between an interrupt routine and two routines -running on separate CPUs that communicate with each other. If such a case is +running on separate CPUs that communicate with each other. If such a case is likely, then interrupt-disabling locks should be used to guarantee ordering. @@ -2587,8 +2628,8 @@ functions: (*) inX(), outX(): These are intended to talk to I/O space rather than memory space, but - that's primarily a CPU-specific concept. The i386 and x86_64 processors do - indeed have special I/O space access cycles and instructions, but many + that's primarily a CPU-specific concept. The i386 and x86_64 processors + do indeed have special I/O space access cycles and instructions, but many CPUs don't have such a concept. The PCI bus, amongst others, defines an I/O space concept which - on such @@ -2610,7 +2651,7 @@ functions: Whether these are guaranteed to be fully ordered and uncombined with respect to each other on the issuing CPU depends on the characteristics - defined for the memory window through which they're accessing. On later + defined for the memory window through which they're accessing. On later i386 architecture machines, for example, this is controlled by way of the MTRR registers. @@ -2635,10 +2676,10 @@ functions: (*) readX_relaxed(), writeX_relaxed() These are similar to readX() and writeX(), but provide weaker memory - ordering guarantees. Specifically, they do not guarantee ordering with + ordering guarantees. Specifically, they do not guarantee ordering with respect to normal memory accesses (e.g. DMA buffers) nor do they guarantee - ordering with respect to LOCK or UNLOCK operations. If the latter is - required, an mmiowb() barrier can be used. Note that relaxed accesses to + ordering with respect to LOCK or UNLOCK operations. If the latter is + required, an mmiowb() barrier can be used. Note that relaxed accesses to the same peripheral are guaranteed to be ordered with respect to each other. @@ -3040,8 +3081,9 @@ The Alpha defines the Linux kernel's memory barrier model. See the subsection on "Cache Coherency" above. + VIRTUAL MACHINE GUESTS -------------------- +---------------------- Guests running within virtual machines might be affected by SMP effects even if the guest itself is compiled without SMP support. This is an artifact of @@ -3050,7 +3092,7 @@ barriers for this use-case would be possible but is often suboptimal. To handle this case optimally, low-level virt_mb() etc macros are available. These have the same effect as smp_mb() etc when SMP is enabled, but generate -identical code for SMP and non-SMP systems. For example, virtual machine guests +identical code for SMP and non-SMP systems. For example, virtual machine guests should use virt_mb() rather than smp_mb() when synchronizing against a (possibly SMP) host. @@ -3058,6 +3100,7 @@ These are equivalent to smp_mb() etc counterparts in all other respects, in particular, they do not control MMIO effects: to control MMIO effects, use mandatory barriers. + ============ EXAMPLE USES ============ diff --git a/Documentation/networking/altera_tse.txt b/Documentation/networking/altera_tse.txt index 3f24df8..50b8589 100644 --- a/Documentation/networking/altera_tse.txt +++ b/Documentation/networking/altera_tse.txt @@ -6,7 +6,7 @@ This is the driver for the Altera Triple-Speed Ethernet (TSE) controllers using the SGDMA and MSGDMA soft DMA IP components. The driver uses the platform bus to obtain component resources. The designs used to test this driver were built for a Cyclone(R) V SOC FPGA board, a Cyclone(R) V FPGA board, -and tested with ARM and NIOS processor hosts seperately. The anticipated use +and tested with ARM and NIOS processor hosts separately. The anticipated use cases are simple communications between an embedded system and an external peer for status and simple configuration of the embedded system. @@ -65,14 +65,14 @@ Driver parameters can be also passed in command line by using: 4.1) Transmit process When the driver's transmit routine is called by the kernel, it sets up a transmit descriptor by calling the underlying DMA transmit routine (SGDMA or -MSGDMA), and initites a transmit operation. Once the transmit is complete, an +MSGDMA), and initiates a transmit operation. Once the transmit is complete, an interrupt is driven by the transmit DMA logic. The driver handles the transmit completion in the context of the interrupt handling chain by recycling resource required to send and track the requested transmit operation. 4.2) Receive process The driver will post receive buffers to the receive DMA logic during driver -intialization. Receive buffers may or may not be queued depending upon the +initialization. Receive buffers may or may not be queued depending upon the underlying DMA logic (MSGDMA is able queue receive buffers, SGDMA is not able to queue receive buffers to the SGDMA receive logic). When a packet is received, the DMA logic generates an interrupt. The driver handles a receive diff --git a/Documentation/networking/checksum-offloads.txt b/Documentation/networking/checksum-offloads.txt index de2a327..56e3686 100644 --- a/Documentation/networking/checksum-offloads.txt +++ b/Documentation/networking/checksum-offloads.txt @@ -69,18 +69,18 @@ LCO: Local Checksum Offload LCO is a technique for efficiently computing the outer checksum of an encapsulated datagram when the inner checksum is due to be offloaded. The ones-complement sum of a correctly checksummed TCP or UDP packet is - equal to the sum of the pseudo header, because everything else gets - 'cancelled out' by the checksum field. This is because the sum was + equal to the complement of the sum of the pseudo header, because everything + else gets 'cancelled out' by the checksum field. This is because the sum was complemented before being written to the checksum field. More generally, this holds in any case where the 'IP-style' ones complement checksum is used, and thus any checksum that TX Checksum Offload supports. That is, if we have set up TX Checksum Offload with a start/offset pair, we - know that _after the device has filled in that checksum_, the ones + know that after the device has filled in that checksum, the ones complement sum from csum_start to the end of the packet will be equal to - _whatever value we put in the checksum field beforehand_. This allows us - to compute the outer checksum without looking at the payload: we simply - stop summing when we get to csum_start, then add the 16-bit word at - (csum_start + csum_offset). + the complement of whatever value we put in the checksum field beforehand. + This allows us to compute the outer checksum without looking at the payload: + we simply stop summing when we get to csum_start, then add the complement of + the 16-bit word at (csum_start + csum_offset). Then, when the true inner checksum is filled in (either by hardware or by skb_checksum_help()), the outer checksum will become correct by virtue of the arithmetic. diff --git a/Documentation/networking/ipvlan.txt b/Documentation/networking/ipvlan.txt index cf99639..14422f8 100644 --- a/Documentation/networking/ipvlan.txt +++ b/Documentation/networking/ipvlan.txt @@ -8,7 +8,7 @@ Initial Release: This is conceptually very similar to the macvlan driver with one major exception of using L3 for mux-ing /demux-ing among slaves. This property makes the master device share the L2 with it's slave devices. I have developed this -driver in conjuntion with network namespaces and not sure if there is use case +driver in conjunction with network namespaces and not sure if there is use case outside of it. @@ -42,7 +42,7 @@ out. In this mode the slaves will RX/TX multicast and broadcast (if applicable) as well. 4.2 L3 mode: - In this mode TX processing upto L3 happens on the stack instance attached + In this mode TX processing up to L3 happens on the stack instance attached to the slave device and packets are switched to the stack instance of the master device for the L2 processing and routing from that instance will be used before packets are queued on the outbound device. In this mode the slaves @@ -56,7 +56,7 @@ situations defines your use case then you can choose to use ipvlan - (a) The Linux host that is connected to the external switch / router has policy configured that allows only one mac per port. (b) No of virtual devices created on a master exceed the mac capacity and -puts the NIC in promiscous mode and degraded performance is a concern. +puts the NIC in promiscuous mode and degraded performance is a concern. (c) If the slave device is to be put into the hostile / untrusted network namespace where L2 on the slave could be changed / misused. diff --git a/Documentation/networking/pktgen.txt b/Documentation/networking/pktgen.txt index f4be85e..2c4e335 100644 --- a/Documentation/networking/pktgen.txt +++ b/Documentation/networking/pktgen.txt @@ -67,12 +67,12 @@ The two basic thread commands are: * add_device DEVICE@NAME -- adds a single device * rem_device_all -- remove all associated devices -When adding a device to a thread, a corrosponding procfile is created +When adding a device to a thread, a corresponding procfile is created which is used for configuring this device. Thus, device names need to be unique. To support adding the same device to multiple threads, which is useful -with multi queue NICs, a the device naming scheme is extended with "@": +with multi queue NICs, the device naming scheme is extended with "@": device@something The part after "@" can be anything, but it is custom to use the thread @@ -221,7 +221,7 @@ Sample scripts A collection of tutorial scripts and helpers for pktgen is in the samples/pktgen directory. The helper parameters.sh file support easy -and consistant parameter parsing across the sample scripts. +and consistent parameter parsing across the sample scripts. Usage example and help: ./pktgen_sample01_simple.sh -i eth4 -m 00:1B:21:3C:9D:F8 -d 192.168.8.2 diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt index d52aa10..5da679c 100644 --- a/Documentation/networking/vrf.txt +++ b/Documentation/networking/vrf.txt @@ -41,7 +41,7 @@ using an rx_handler which gives the impression that packets flow through the VRF device. Similarly on egress routing rules are used to send packets to the VRF device driver before getting sent out the actual interface. This allows tcpdump on a VRF device to capture all packets into and out of the -VRF as a whole.[1] Similiarly, netfilter [2] and tc rules can be applied +VRF as a whole.[1] Similarly, netfilter [2] and tc rules can be applied using the VRF device to specify rules that apply to the VRF domain as a whole. [1] Packets in the forwarded state do not flow through the device, so those diff --git a/Documentation/networking/xfrm_sync.txt b/Documentation/networking/xfrm_sync.txt index d7aac9d..8d88e0f 100644 --- a/Documentation/networking/xfrm_sync.txt +++ b/Documentation/networking/xfrm_sync.txt @@ -4,7 +4,7 @@ Krisztian <hidden@balabit.hu> and others and additional patches from Jamal <hadi@cyberus.ca>. The end goal for syncing is to be able to insert attributes + generate -events so that the an SA can be safely moved from one machine to another +events so that the SA can be safely moved from one machine to another for HA purposes. The idea is to synchronize the SA so that the takeover machine can do the processing of the SA as accurate as possible if it has access to it. @@ -13,7 +13,7 @@ We already have the ability to generate SA add/del/upd events. These patches add ability to sync and have accurate lifetime byte (to ensure proper decay of SAs) and replay counters to avoid replay attacks with as minimal loss at failover time. -This way a backup stays as closely uptodate as an active member. +This way a backup stays as closely up-to-date as an active member. Because the above items change for every packet the SA receives, it is possible for a lot of the events to be generated. @@ -163,7 +163,7 @@ If you have an SA that is getting hit by traffic in bursts such that there is a period where the timer threshold expires with no packets seen, then an odd behavior is seen as follows: The first packet arrival after a timer expiry will trigger a timeout -aevent; i.e we dont wait for a timeout period or a packet threshold +event; i.e we don't wait for a timeout period or a packet threshold to be reached. This is done for simplicity and efficiency reasons. -JHS diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 57653a4..daabdd7 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -60,6 +60,7 @@ show up in /proc/sys/kernel: - panic_on_warn - perf_cpu_time_max_percent - perf_event_paranoid +- perf_event_max_stack - pid_max - powersave-nap [ PPC only ] - printk @@ -645,7 +646,7 @@ allowed to execute. perf_event_paranoid: Controls use of the performance events system by unprivileged -users (without CAP_SYS_ADMIN). The default value is 1. +users (without CAP_SYS_ADMIN). The default value is 2. -1: Allow use of (almost) all events by all users >=0: Disallow raw tracepoint access by users without CAP_IOC_LOCK @@ -654,6 +655,19 @@ users (without CAP_SYS_ADMIN). The default value is 1. ============================================================== +perf_event_max_stack: + +Controls maximum number of stack frames to copy for (attr.sample_type & +PERF_SAMPLE_CALLCHAIN) configured events, for instance, when using +'perf record -g' or 'perf trace --call-graph fp'. + +This can only be done when no events are in use that have callchains +enabled, otherwise writing to this file will return -EBUSY. + +The default value is 127. + +============================================================== + pid_max: PID allocation wrap value. When the kernel's next PID value diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index f52f297..9857606 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -1562,12 +1562,12 @@ Doing the same with chrt -r 5 and function-trace set. <idle>-0 3dN.1 12us : menu_hrtimer_cancel <-tick_nohz_idle_exit <idle>-0 3dN.1 12us : ktime_get <-tick_nohz_idle_exit <idle>-0 3dN.1 12us : tick_do_update_jiffies64 <-tick_nohz_idle_exit - <idle>-0 3dN.1 13us : update_cpu_load_nohz <-tick_nohz_idle_exit - <idle>-0 3dN.1 13us : _raw_spin_lock <-update_cpu_load_nohz + <idle>-0 3dN.1 13us : cpu_load_update_nohz <-tick_nohz_idle_exit + <idle>-0 3dN.1 13us : _raw_spin_lock <-cpu_load_update_nohz <idle>-0 3dN.1 13us : add_preempt_count <-_raw_spin_lock - <idle>-0 3dN.2 13us : __update_cpu_load <-update_cpu_load_nohz - <idle>-0 3dN.2 14us : sched_avg_update <-__update_cpu_load - <idle>-0 3dN.2 14us : _raw_spin_unlock <-update_cpu_load_nohz + <idle>-0 3dN.2 13us : __cpu_load_update <-cpu_load_update_nohz + <idle>-0 3dN.2 14us : sched_avg_update <-__cpu_load_update + <idle>-0 3dN.2 14us : _raw_spin_unlock <-cpu_load_update_nohz <idle>-0 3dN.2 14us : sub_preempt_count <-_raw_spin_unlock <idle>-0 3dN.1 15us : calc_load_exit_idle <-tick_nohz_idle_exit <idle>-0 3dN.1 15us : touch_softlockup_watchdog <-tick_nohz_idle_exit diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt index 54944c7..2a4ee63 100644 --- a/Documentation/x86/pat.txt +++ b/Documentation/x86/pat.txt @@ -196,3 +196,35 @@ Another, more verbose way of getting PAT related debug messages is with "debugpat" boot parameter. With this parameter, various debug messages are printed to dmesg log. +PAT Initialization +------------------ + +The following table describes how PAT is initialized under various +configurations. The PAT MSR must be updated by Linux in order to support WC +and WT attributes. Otherwise, the PAT MSR has the value programmed in it +by the firmware. Note, Xen enables WC attribute in the PAT MSR for guests. + + MTRR PAT Call Sequence PAT State PAT MSR + ========================================================= + E E MTRR -> PAT init Enabled OS + E D MTRR -> PAT init Disabled - + D E MTRR -> PAT disable Disabled BIOS + D D MTRR -> PAT disable Disabled - + - np/E PAT -> PAT disable Disabled BIOS + - np/D PAT -> PAT disable Disabled - + E !P/E MTRR -> PAT init Disabled BIOS + D !P/E MTRR -> PAT disable Disabled BIOS + !M !P/E MTRR stub -> PAT disable Disabled BIOS + + Legend + ------------------------------------------------ + E Feature enabled in CPU + D Feature disabled/unsupported in CPU + np "nopat" boot option specified + !P CONFIG_X86_PAT option unset + !M CONFIG_MTRR option unset + Enabled PAT state set to enabled + Disabled PAT state set to disabled + OS PAT initializes PAT MSR with OS setting + BIOS PAT keeps PAT MSR with BIOS setting + diff --git a/MAINTAINERS b/MAINTAINERS index 42e65d1..9c567a4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -872,9 +872,9 @@ F: drivers/perf/arm_pmu.c F: include/linux/perf/arm_pmu.h ARM PORT -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: arch/arm/ @@ -886,35 +886,35 @@ F: arch/arm/plat-*/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc.git ARM PRIMECELL AACI PL041 DRIVER -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: sound/arm/aaci.* ARM PRIMECELL CLCD PL110 DRIVER -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: drivers/video/fbdev/amba-clcd.* ARM PRIMECELL KMI PL050 DRIVER -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: drivers/input/serio/ambakmi.* F: include/linux/amba/kmi.h ARM PRIMECELL MMCI PL180/1 DRIVER -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: drivers/mmc/host/mmci.* F: include/linux/amba/mmci.h ARM PRIMECELL UART PL010 AND PL011 DRIVERS -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: drivers/tty/serial/amba-pl01*.c F: include/linux/amba/serial.h ARM PRIMECELL BUS SUPPORT -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: drivers/amba/ F: include/linux/amba/bus.h @@ -1036,7 +1036,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained ARM/CLKDEV SUPPORT -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/include/asm/clkdev.h @@ -1093,9 +1093,9 @@ F: arch/arm/boot/dts/cx92755* N: digicolor ARM/EBSA110 MACHINE SUPPORT -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: arch/arm/mach-ebsa110/ F: drivers/net/ethernet/amd/am79c961a.* @@ -1124,9 +1124,9 @@ T: git git://git.berlios.de/gemini-board F: arch/arm/mm/*-fa* ARM/FOOTBRIDGE ARCHITECTURE -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: arch/arm/include/asm/hardware/dec21285.h F: arch/arm/mach-footbridge/ @@ -1457,7 +1457,7 @@ S: Maintained ARM/PT DIGITAL BOARD PORT M: Stefan Eletzhofer <stefan.eletzhofer@eletztrick.de> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained ARM/QUALCOMM SUPPORT @@ -1493,9 +1493,9 @@ S: Supported F: arch/arm64/boot/dts/renesas/ ARM/RISCPC ARCHITECTURE -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: arch/arm/include/asm/hardware/entry-macro-iomd.S F: arch/arm/include/asm/hardware/ioc.h @@ -1773,9 +1773,9 @@ F: drivers/clk/versatile/clk-vexpress-osc.c F: drivers/clocksource/versatile.c ARM/VFP SUPPORT -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: arch/arm/vfp/ @@ -2921,7 +2921,7 @@ F: mm/cleancache.c F: include/linux/cleancache.h CLK API -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-clk@vger.kernel.org S: Maintained F: include/linux/clk.h @@ -3354,9 +3354,9 @@ S: Supported F: drivers/net/ethernet/stmicro/stmmac/ CYBERPRO FB DRIVER -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: drivers/video/fbdev/cyber2000fb.* @@ -3881,7 +3881,7 @@ F: Documentation/devicetree/bindings/display/st,stih4xx.txt DRM DRIVERS FOR VIVANTE GPU IP M: Lucas Stach <l.stach@pengutronix.de> -R: Russell King <linux+etnaviv@arm.linux.org.uk> +R: Russell King <linux+etnaviv@armlinux.org.uk> R: Christian Gmeiner <christian.gmeiner@gmail.com> L: dri-devel@lists.freedesktop.org S: Maintained @@ -4223,8 +4223,8 @@ F: Documentation/efi-stub.txt F: arch/ia64/kernel/efi.c F: arch/x86/boot/compressed/eboot.[ch] F: arch/x86/include/asm/efi.h -F: arch/x86/platform/efi/* -F: drivers/firmware/efi/* +F: arch/x86/platform/efi/ +F: drivers/firmware/efi/ F: include/linux/efi*.h EFI VARIABLE FILESYSTEM @@ -4744,7 +4744,7 @@ F: drivers/platform/x86/fujitsu-tablet.c FUSE: FILESYSTEM IN USERSPACE M: Miklos Szeredi <miklos@szeredi.hu> -L: fuse-devel@lists.sourceforge.net +L: linux-fsdevel@vger.kernel.org W: http://fuse.sourceforge.net/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse.git S: Maintained @@ -4903,7 +4903,7 @@ F: net/ipv4/gre_offload.c F: include/net/gre.h GRETH 10/100/1G Ethernet MAC device driver -M: Kristoffer Glembo <kristoffer@gaisler.com> +M: Andreas Larsson <andreas@gaisler.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/aeroflex/ @@ -6905,7 +6905,7 @@ L: linux-man@vger.kernel.org S: Maintained MARVELL ARMADA DRM SUPPORT -M: Russell King <rmk+kernel@arm.linux.org.uk> +M: Russell King <rmk+kernel@armlinux.org.uk> S: Maintained F: drivers/gpu/drm/armada/ @@ -7905,7 +7905,7 @@ S: Supported F: drivers/nfc/nxp-nci NXP TDA998X DRM DRIVER -M: Russell King <rmk+kernel@arm.linux.org.uk> +M: Russell King <rmk+kernel@armlinux.org.uk> S: Supported F: drivers/gpu/drm/i2c/tda998x_drv.c F: include/drm/i2c/tda998x.h @@ -7978,7 +7978,7 @@ F: arch/arm/*omap*/*pm* F: drivers/cpufreq/omap-cpufreq.c OMAP POWERDOMAIN SOC ADAPTATION LAYER SUPPORT -M: Rajendra Nayak <rnayak@ti.com> +M: Rajendra Nayak <rnayak@codeaurora.org> M: Paul Walmsley <paul@pwsan.com> L: linux-omap@vger.kernel.org S: Maintained @@ -10014,7 +10014,8 @@ F: drivers/infiniband/hw/ocrdma/ SFC NETWORK DRIVER M: Solarflare linux maintainers <linux-net-drivers@solarflare.com> -M: Shradha Shah <sshah@solarflare.com> +M: Edward Cree <ecree@solarflare.com> +M: Bert Kenward <bkenward@solarflare.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/sfc/ @@ -11317,6 +11318,20 @@ F: include/trace/ F: kernel/trace/ F: tools/testing/selftests/ftrace/ +TRACING MMIO ACCESSES (MMIOTRACE) +M: Steven Rostedt <rostedt@goodmis.org> +M: Ingo Molnar <mingo@kernel.org> +R: Karol Herbst <karolherbst@gmail.com> +R: Pekka Paalanen <ppaalanen@gmail.com> +S: Maintained +L: linux-kernel@vger.kernel.org +L: nouveau@lists.freedesktop.org +F: kernel/trace/trace_mmiotrace.c +F: include/linux/mmiotrace.h +F: arch/x86/mm/kmmio.c +F: arch/x86/mm/mmio-mod.c +F: arch/x86/mm/testmmiotrace.c + TRIVIAL PATCHES M: Jiri Kosina <trivial@kernel.org> T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial.git @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = NAME = Charred Weasel # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h index a83bbea6..0131a70 100644 --- a/arch/alpha/include/asm/rwsem.h +++ b/arch/alpha/include/asm/rwsem.h @@ -63,7 +63,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) return res >= 0 ? 1 : 0; } -static inline void __down_write(struct rw_semaphore *sem) +static inline long ___down_write(struct rw_semaphore *sem) { long oldcount; #ifndef CONFIG_SMP @@ -83,10 +83,24 @@ static inline void __down_write(struct rw_semaphore *sem) :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) :"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory"); #endif - if (unlikely(oldcount)) + return oldcount; +} + +static inline void __down_write(struct rw_semaphore *sem) +{ + if (unlikely(___down_write(sem))) rwsem_down_write_failed(sem); } +static inline int __down_write_killable(struct rw_semaphore *sem) +{ + if (unlikely(___down_write(sem))) + if (IS_ERR(rwsem_down_write_failed_killable(sem))) + return -EINTR; + + return 0; +} + /* * trylock for writing -- returns 1 if successful, 0 if contention */ diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index ec4791e..a876743 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -58,6 +58,9 @@ config GENERIC_CSUM config RWSEM_GENERIC_SPINLOCK def_bool y +config ARCH_DISCONTIGMEM_ENABLE + def_bool y + config ARCH_FLATMEM_ENABLE def_bool y @@ -347,6 +350,15 @@ config ARC_HUGEPAGE_16M endchoice +config NODES_SHIFT + int "Maximum NUMA Nodes (as a power of 2)" + default "1" if !DISCONTIGMEM + default "2" if DISCONTIGMEM + depends on NEED_MULTIPLE_NODES + ---help--- + Accessing memory beyond 1GB (with or w/o PAE) requires 2 memory + zones. + if ISA_ARCOMPACT config ARC_COMPACT_IRQ_LEVELS @@ -455,6 +467,7 @@ config LINUX_LINK_BASE config HIGHMEM bool "High Memory Support" + select DISCONTIGMEM help With ARC 2G:2G address split, only upper 2G is directly addressable by kernel. Enable this to potentially allow access to rest of 2G and PAE diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 17f85c9..c22b181 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -13,6 +13,15 @@ #include <asm/byteorder.h> #include <asm/page.h> +#ifdef CONFIG_ISA_ARCV2 +#include <asm/barrier.h> +#define __iormb() rmb() +#define __iowmb() wmb() +#else +#define __iormb() do { } while (0) +#define __iowmb() do { } while (0) +#endif + extern void __iomem *ioremap(phys_addr_t paddr, unsigned long size); extern void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size, unsigned long flags); @@ -31,6 +40,15 @@ extern void iounmap(const void __iomem *addr); #define ioremap_wc(phy, sz) ioremap(phy, sz) #define ioremap_wt(phy, sz) ioremap(phy, sz) +/* + * io{read,write}{16,32}be() macros + */ +#define ioread16be(p) ({ u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; }) +#define ioread32be(p) ({ u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; }) + +#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force u16)cpu_to_be16(v), p); }) +#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force u32)cpu_to_be32(v), p); }) + /* Change struct page to physical address */ #define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) @@ -108,15 +126,6 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr) } -#ifdef CONFIG_ISA_ARCV2 -#include <asm/barrier.h> -#define __iormb() rmb() -#define __iowmb() wmb() -#else -#define __iormb() do { } while (0) -#define __iowmb() do { } while (0) -#endif - /* * MMIO can also get buffered/optimized in micro-arch, so barriers needed * Based on ARM model for the typical use case diff --git a/arch/arc/include/asm/mmzone.h b/arch/arc/include/asm/mmzone.h new file mode 100644 index 0000000..8e97136 --- /dev/null +++ b/arch/arc/include/asm/mmzone.h @@ -0,0 +1,43 @@ +/* + * Copyright (C) 2016 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ASM_ARC_MMZONE_H +#define _ASM_ARC_MMZONE_H + +#ifdef CONFIG_DISCONTIGMEM + +extern struct pglist_data node_data[]; +#define NODE_DATA(nid) (&node_data[nid]) + +static inline int pfn_to_nid(unsigned long pfn) +{ + int is_end_low = 1; + + if (IS_ENABLED(CONFIG_ARC_HAS_PAE40)) + is_end_low = pfn <= virt_to_pfn(0xFFFFFFFFUL); + + /* + * node 0: lowmem: 0x8000_0000 to 0xFFFF_FFFF + * node 1: HIGHMEM w/o PAE40: 0x0 to 0x7FFF_FFFF + * HIGHMEM with PAE40: 0x1_0000_0000 to ... + */ + if (pfn >= ARCH_PFN_OFFSET && is_end_low) + return 0; + + return 1; +} + +static inline int pfn_valid(unsigned long pfn) +{ + int nid = pfn_to_nid(pfn); + + return (pfn <= node_end_pfn(nid)); +} +#endif /* CONFIG_DISCONTIGMEM */ + +#endif diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index 36da89e..0d53854 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -72,11 +72,20 @@ typedef unsigned long pgprot_t; typedef pte_t * pgtable_t; +/* + * Use virt_to_pfn with caution: + * If used in pte or paddr related macros, it could cause truncation + * in PAE40 builds + * As a rule of thumb, only use it in helpers starting with virt_ + * You have been warned ! + */ #define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) #define ARCH_PFN_OFFSET virt_to_pfn(CONFIG_LINUX_LINK_BASE) +#ifdef CONFIG_FLATMEM #define pfn_valid(pfn) (((pfn) - ARCH_PFN_OFFSET) < max_mapnr) +#endif /* * __pa, __va, virt_to_page (ALERT: deprecated, don't use them) @@ -85,12 +94,10 @@ typedef pte_t * pgtable_t; * virt here means link-address/program-address as embedded in object code. * And for ARC, link-addr = physical address */ -#define __pa(vaddr) ((unsigned long)vaddr) +#define __pa(vaddr) ((unsigned long)(vaddr)) #define __va(paddr) ((void *)((unsigned long)(paddr))) -#define virt_to_page(kaddr) \ - (mem_map + virt_to_pfn((kaddr) - CONFIG_LINUX_LINK_BASE)) - +#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) #define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) /* Default Permissions for stack/heaps pages (Non Executable) */ diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 7d6c93e..10d4b8b 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -278,14 +278,13 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) #define pmd_present(x) (pmd_val(x)) #define pmd_clear(xp) do { pmd_val(*(xp)) = 0; } while (0) -#define pte_page(pte) \ - (mem_map + virt_to_pfn(pte_val(pte) - CONFIG_LINUX_LINK_BASE)) - +#define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) -#define pte_pfn(pte) virt_to_pfn(pte_val(pte)) -#define pfn_pte(pfn, prot) (__pte(((pte_t)(pfn) << PAGE_SHIFT) | \ - pgprot_val(prot))) -#define __pte_index(addr) (virt_to_pfn(addr) & (PTRS_PER_PTE - 1)) +#define pfn_pte(pfn, prot) (__pte(((pte_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) + +/* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/ +#define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) +#define __pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) /* * pte_offset gets a @ptr to PMD entry (PGD in our 2-tier paging system) diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 5487d0b..8be9303 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -30,11 +30,16 @@ static const unsigned long low_mem_start = CONFIG_LINUX_LINK_BASE; static unsigned long low_mem_sz; #ifdef CONFIG_HIGHMEM -static unsigned long min_high_pfn; +static unsigned long min_high_pfn, max_high_pfn; static u64 high_mem_start; static u64 high_mem_sz; #endif +#ifdef CONFIG_DISCONTIGMEM +struct pglist_data node_data[MAX_NUMNODES] __read_mostly; +EXPORT_SYMBOL(node_data); +#endif + /* User can over-ride above with "mem=nnn[KkMm]" in cmdline */ static int __init setup_mem_sz(char *str) { @@ -109,13 +114,11 @@ void __init setup_arch_memory(void) /* Last usable page of low mem */ max_low_pfn = max_pfn = PFN_DOWN(low_mem_start + low_mem_sz); -#ifdef CONFIG_HIGHMEM - min_high_pfn = PFN_DOWN(high_mem_start); - max_pfn = PFN_DOWN(high_mem_start + high_mem_sz); +#ifdef CONFIG_FLATMEM + /* pfn_valid() uses this */ + max_mapnr = max_low_pfn - min_low_pfn; #endif - max_mapnr = max_pfn - min_low_pfn; - /*------------- bootmem allocator setup -----------------------*/ /* @@ -129,7 +132,7 @@ void __init setup_arch_memory(void) * the crash */ - memblock_add(low_mem_start, low_mem_sz); + memblock_add_node(low_mem_start, low_mem_sz, 0); memblock_reserve(low_mem_start, __pa(_end) - low_mem_start); #ifdef CONFIG_BLK_DEV_INITRD @@ -149,13 +152,6 @@ void __init setup_arch_memory(void) zones_size[ZONE_NORMAL] = max_low_pfn - min_low_pfn; zones_holes[ZONE_NORMAL] = 0; -#ifdef CONFIG_HIGHMEM - zones_size[ZONE_HIGHMEM] = max_pfn - max_low_pfn; - - /* This handles the peripheral address space hole */ - zones_holes[ZONE_HIGHMEM] = min_high_pfn - max_low_pfn; -#endif - /* * We can't use the helper free_area_init(zones[]) because it uses * PAGE_OFFSET to compute the @min_low_pfn which would be wrong @@ -168,6 +164,34 @@ void __init setup_arch_memory(void) zones_holes); /* holes */ #ifdef CONFIG_HIGHMEM + /* + * Populate a new node with highmem + * + * On ARC (w/o PAE) HIGHMEM addresses are actually smaller (0 based) + * than addresses in normal ala low memory (0x8000_0000 based). + * Even with PAE, the huge peripheral space hole would waste a lot of + * mem with single mem_map[]. This warrants a mem_map per region design. + * Thus HIGHMEM on ARC is imlemented with DISCONTIGMEM. + * + * DISCONTIGMEM in turns requires multiple nodes. node 0 above is + * populated with normal memory zone while node 1 only has highmem + */ + node_set_online(1); + + min_high_pfn = PFN_DOWN(high_mem_start); + max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz); + + zones_size[ZONE_NORMAL] = 0; + zones_holes[ZONE_NORMAL] = 0; + + zones_size[ZONE_HIGHMEM] = max_high_pfn - min_high_pfn; + zones_holes[ZONE_HIGHMEM] = 0; + + free_area_init_node(1, /* node-id */ + zones_size, /* num pages per zone */ + min_high_pfn, /* first pfn of node */ + zones_holes); /* holes */ + high_memory = (void *)(min_high_pfn << PAGE_SHIFT); kmap_init(); #endif @@ -185,7 +209,7 @@ void __init mem_init(void) unsigned long tmp; reset_all_zones_managed_pages(); - for (tmp = min_high_pfn; tmp < max_pfn; tmp++) + for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++) free_highmem_page(pfn_to_page(tmp)); #endif diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi index 0827d59..cd0cd5f 100644 --- a/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/arch/arm/boot/dts/at91sam9x5.dtsi @@ -106,7 +106,7 @@ pmc: pmc@fffffc00 { compatible = "atmel,at91sam9x5-pmc", "syscon"; - reg = <0xfffffc00 0x100>; + reg = <0xfffffc00 0x200>; interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>; interrupt-controller; #address-cells = <1>; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index b3c26a9..d9e2d9c 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -329,6 +329,7 @@ regulator-name = "V28"; regulator-min-microvolt = <2800000>; regulator-max-microvolt = <2800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ regulator-always-on; /* due to battery cover sensor */ }; @@ -336,30 +337,35 @@ regulator-name = "VCSI"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ }; &vaux3 { regulator-name = "VMMC2_30"; regulator-min-microvolt = <2800000>; regulator-max-microvolt = <3000000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ }; &vaux4 { regulator-name = "VCAM_ANA_28"; regulator-min-microvolt = <2800000>; regulator-max-microvolt = <2800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ }; &vmmc1 { regulator-name = "VMMC1"; regulator-min-microvolt = <1850000>; regulator-max-microvolt = <3150000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ }; &vmmc2 { regulator-name = "V28_A"; regulator-min-microvolt = <2800000>; regulator-max-microvolt = <3000000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ regulator-always-on; /* due VIO leak to AIC34 VDDs */ }; @@ -367,6 +373,7 @@ regulator-name = "VPLL"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ regulator-always-on; }; @@ -374,6 +381,7 @@ regulator-name = "VSDI_CSI"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ regulator-always-on; }; @@ -381,6 +389,7 @@ regulator-name = "VMMC2_IO_18"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ }; &vio { diff --git a/arch/arm/boot/dts/omap34xx.dtsi b/arch/arm/boot/dts/omap34xx.dtsi index 387dc31..96f8ce7 100644 --- a/arch/arm/boot/dts/omap34xx.dtsi +++ b/arch/arm/boot/dts/omap34xx.dtsi @@ -46,7 +46,7 @@ 0x480bd800 0x017c>; interrupts = <24>; iommus = <&mmu_isp>; - syscon = <&scm_conf 0xdc>; + syscon = <&scm_conf 0x6c>; ti,phy-type = <OMAP3ISP_PHY_TYPE_COMPLEX_IO>; #clock-cells = <1>; ports { diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 902657d..914bf4c 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -472,7 +472,7 @@ ldo1_reg: ldo1 { /* VDDAPHY_CAM: vdda_csiport */ regulator-name = "ldo1"; - regulator-min-microvolt = <1500000>; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; @@ -498,7 +498,7 @@ ldo4_reg: ldo4 { /* VDDAPHY_DISP: vdda_dsiport/hdmi */ regulator-name = "ldo4"; - regulator-min-microvolt = <1500000>; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts index ecc591d..4d87d9c 100644 --- a/arch/arm/boot/dts/omap5-cm-t54.dts +++ b/arch/arm/boot/dts/omap5-cm-t54.dts @@ -513,7 +513,7 @@ ldo1_reg: ldo1 { /* VDDAPHY_CAM: vdda_csiport */ regulator-name = "ldo1"; - regulator-min-microvolt = <1500000>; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; @@ -537,7 +537,7 @@ ldo4_reg: ldo4 { /* VDDAPHY_DISP: vdda_dsiport/hdmi */ regulator-name = "ldo4"; - regulator-min-microvolt = <1500000>; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index 38805eb..120b6b8 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -269,7 +269,7 @@ omap5_pmx_wkup: pinmux@c840 { compatible = "ti,omap5-padconf", "pinctrl-single"; - reg = <0xc840 0x0038>; + reg = <0xc840 0x003c>; #address-cells = <1>; #size-cells = <0>; #interrupt-cells = <1>; diff --git a/arch/arm/boot/dts/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom-apq8064.dtsi index 65d0e8d..04f541b 100644 --- a/arch/arm/boot/dts/qcom-apq8064.dtsi +++ b/arch/arm/boot/dts/qcom-apq8064.dtsi @@ -666,7 +666,7 @@ }; sata0: sata@29000000 { - compatible = "generic-ahci"; + compatible = "qcom,apq8064-ahci", "generic-ahci"; status = "disabled"; reg = <0x29000000 0x180>; interrupts = <GIC_SPI 209 IRQ_TYPE_NONE>; @@ -688,6 +688,7 @@ phys = <&sata_phy0>; phy-names = "sata-phy"; + ports-implemented = <0x1>; }; /* Temporary fixed regulator */ diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi index 78996bd..9817090 100644 --- a/arch/arm/boot/dts/sama5d2.dtsi +++ b/arch/arm/boot/dts/sama5d2.dtsi @@ -280,7 +280,7 @@ status = "disabled"; nfc@c0000000 { - compatible = "atmel,sama5d4-nfc"; + compatible = "atmel,sama5d3-nfc"; #address-cells = <1>; #size-cells = <1>; reg = < /* NFC Command Registers */ diff --git a/arch/arm/boot/dts/sun8i-q8-common.dtsi b/arch/arm/boot/dts/sun8i-q8-common.dtsi index 9d2b7e2..346a49d 100644 --- a/arch/arm/boot/dts/sun8i-q8-common.dtsi +++ b/arch/arm/boot/dts/sun8i-q8-common.dtsi @@ -125,8 +125,6 @@ }; ®_dc1sw { - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; regulator-name = "vcc-lcd"; }; diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h index fc8ba16..99d9f63 100644 --- a/arch/arm/include/asm/domain.h +++ b/arch/arm/include/asm/domain.h @@ -84,6 +84,7 @@ #ifndef __ASSEMBLY__ +#ifdef CONFIG_CPU_CP15_MMU static inline unsigned int get_domain(void) { unsigned int domain; @@ -103,6 +104,16 @@ static inline void set_domain(unsigned val) : : "r" (val) : "memory"); isb(); } +#else +static inline unsigned int get_domain(void) +{ + return 0; +} + +static inline void set_domain(unsigned val) +{ +} +#endif #ifdef CONFIG_CPU_USE_DOMAINS #define modify_domain(dom,type) \ diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index e0eea72..a708fa1 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -17,34 +17,28 @@ #include <asm/mach/map.h> #include <asm/mmu_context.h> #include <asm/pgtable.h> +#include <asm/ptrace.h> #ifdef CONFIG_EFI void efi_init(void); int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); +int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); -#define efi_call_virt(f, ...) \ -({ \ - efi_##f##_t *__f; \ - efi_status_t __s; \ - \ - efi_virtmap_load(); \ - __f = efi.systab->runtime->f; \ - __s = __f(__VA_ARGS__); \ - efi_virtmap_unload(); \ - __s; \ -}) +#define arch_efi_call_virt_setup() efi_virtmap_load() +#define arch_efi_call_virt_teardown() efi_virtmap_unload() -#define __efi_call_virt(f, ...) \ +#define arch_efi_call_virt(f, args...) \ ({ \ efi_##f##_t *__f; \ - \ - efi_virtmap_load(); \ __f = efi.systab->runtime->f; \ - __f(__VA_ARGS__); \ - efi_virtmap_unload(); \ + __f(args); \ }) +#define ARCH_EFI_IRQ_FLAGS_MASK \ + (PSR_J_BIT | PSR_E_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | \ + PSR_T_BIT | MODE_MASK) + static inline void efi_set_pgd(struct mm_struct *mm) { check_and_switch_context(mm, NULL); @@ -59,7 +53,16 @@ void efi_virtmap_unload(void); /* arch specific definitions used by the stub code */ -#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) +#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) +#define __efi_call_early(f, ...) f(__VA_ARGS__) +#define efi_is_64bit() (false) + +struct screen_info *alloc_screen_info(efi_system_table_t *sys_table_arg); +void free_screen_info(efi_system_table_t *sys_table, struct screen_info *si); + +static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) +{ +} /* * A reasonable upper bound for the uncompressed kernel size is 32 MBytes, diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h index fa5b42d..3cc14dd 100644 --- a/arch/arm/include/asm/mmu_context.h +++ b/arch/arm/include/asm/mmu_context.h @@ -15,6 +15,7 @@ #include <linux/compiler.h> #include <linux/sched.h> +#include <linux/preempt.h> #include <asm/cacheflush.h> #include <asm/cachetype.h> #include <asm/proc-fns.h> @@ -66,6 +67,7 @@ static inline void check_and_switch_context(struct mm_struct *mm, cpu_switch_mm(mm->pgd, mm); } +#ifndef MODULE #define finish_arch_post_lock_switch \ finish_arch_post_lock_switch static inline void finish_arch_post_lock_switch(void) @@ -87,6 +89,7 @@ static inline void finish_arch_post_lock_switch(void) preempt_enable_no_resched(); } } +#endif /* !MODULE */ #endif /* CONFIG_MMU */ diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c index ff8a9d8..9f43ba0 100644 --- a/arch/arm/kernel/efi.c +++ b/arch/arm/kernel/efi.c @@ -11,6 +11,41 @@ #include <asm/mach/map.h> #include <asm/mmu_context.h> +static int __init set_permissions(pte_t *ptep, pgtable_t token, + unsigned long addr, void *data) +{ + efi_memory_desc_t *md = data; + pte_t pte = *ptep; + + if (md->attribute & EFI_MEMORY_RO) + pte = set_pte_bit(pte, __pgprot(L_PTE_RDONLY)); + if (md->attribute & EFI_MEMORY_XP) + pte = set_pte_bit(pte, __pgprot(L_PTE_XN)); + set_pte_ext(ptep, pte, PTE_EXT_NG); + return 0; +} + +int __init efi_set_mapping_permissions(struct mm_struct *mm, + efi_memory_desc_t *md) +{ + unsigned long base, size; + + base = md->virt_addr; + size = md->num_pages << EFI_PAGE_SHIFT; + + /* + * We can only use apply_to_page_range() if we can guarantee that the + * entire region was mapped using pages. This should be the case if the + * region does not cover any naturally aligned SECTION_SIZE sized + * blocks. + */ + if (round_down(base + size, SECTION_SIZE) < + round_up(base, SECTION_SIZE) + SECTION_SIZE) + return apply_to_page_range(mm, base, size, set_permissions, md); + + return 0; +} + int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) { struct map_desc desc = { @@ -34,5 +69,11 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) desc.type = MT_DEVICE; create_mapping_late(mm, &desc, true); + + /* + * If stricter permissions were specified, apply them now. + */ + if (md->attribute & (EFI_MEMORY_RO | EFI_MEMORY_XP)) + return efi_set_mapping_permissions(mm, md); return 0; } diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index 9b8c5a1..fb1a69e 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -236,7 +236,7 @@ ENTRY(__setup_mpu) mov r0, #CONFIG_VECTORS_BASE @ Cover from VECTORS_BASE ldr r5,=(MPU_AP_PL1RW_PL0NA | MPU_RGN_NORMAL) /* Writing N to bits 5:1 (RSR_SZ) --> region size 2^N+1 */ - mov r6, #(((PAGE_SHIFT - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN) + mov r6, #(((2 * PAGE_SHIFT - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN) setup_region r0, r5, r6, MPU_DATA_SIDE @ VECTORS_BASE, PL0 NA, enabled beq 3f @ Memory-map not unified diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 6284779..b8df458 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -631,7 +631,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) info->address &= ~alignment_mask; info->ctrl.len <<= offset; - if (!bp->overflow_handler) { + if (is_default_overflow_handler(bp)) { /* * Mismatch breakpoints are required for single-stepping * breakpoints. @@ -754,7 +754,7 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, * mismatch breakpoint so we can single-step over the * watchpoint trigger. */ - if (!wp->overflow_handler) + if (is_default_overflow_handler(wp)) enable_single_step(wp, instruction_pointer(regs)); unlock: diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c index 4e02ae5..27563be 100644 --- a/arch/arm/kernel/perf_callchain.c +++ b/arch/arm/kernel/perf_callchain.c @@ -75,7 +75,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) tail = (struct frame_tail __user *)regs->ARM_fp - 1; - while ((entry->nr < PERF_MAX_STACK_DEPTH) && + while ((entry->nr < sysctl_perf_event_max_stack) && tail && !((unsigned long)tail & 0x3)) tail = user_backtrace(tail, entry); } diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 2c4bea3..7d4e285 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -883,7 +883,8 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) request_resource(&ioport_resource, &lp2); } -#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE) +#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE) || \ + defined(CONFIG_EFI) struct screen_info screen_info = { .orig_video_lines = 30, .orig_video_cols = 80, diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 58dbd5c..d6d4191 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1004,7 +1004,7 @@ static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap) kvm_pfn_t pfn = *pfnp; gfn_t gfn = *ipap >> PAGE_SHIFT; - if (PageTransCompound(pfn_to_page(pfn))) { + if (PageTransCompoundMap(pfn_to_page(pfn))) { unsigned long mask; /* * The address we faulted on is backed by a transparent huge diff --git a/arch/arm/mach-davinci/board-mityomapl138.c b/arch/arm/mach-davinci/board-mityomapl138.c index d97c588..bc4e63f 100644 --- a/arch/arm/mach-davinci/board-mityomapl138.c +++ b/arch/arm/mach-davinci/board-mityomapl138.c @@ -121,6 +121,11 @@ static void read_factory_config(struct nvmem_device *nvmem, void *context) const char *partnum = NULL; struct davinci_soc_info *soc_info = &davinci_soc_info; + if (!IS_BUILTIN(CONFIG_NVMEM)) { + pr_warn("Factory Config not available without CONFIG_NVMEM\n"); + goto bad_config; + } + ret = nvmem_device_read(nvmem, 0, sizeof(factory_config), &factory_config); if (ret != sizeof(struct factory_config)) { diff --git a/arch/arm/mach-davinci/common.c b/arch/arm/mach-davinci/common.c index f55ef2e..742133b 100644 --- a/arch/arm/mach-davinci/common.c +++ b/arch/arm/mach-davinci/common.c @@ -33,6 +33,11 @@ void davinci_get_mac_addr(struct nvmem_device *nvmem, void *context) char *mac_addr = davinci_soc_info.emac_pdata->mac_addr; off_t offset = (off_t)context; + if (!IS_BUILTIN(CONFIG_NVMEM)) { + pr_warn("Cannot read MAC addr from EEPROM without CONFIG_NVMEM\n"); + return; + } + /* Read MAC addr from EEPROM */ if (nvmem_device_read(nvmem, offset, ETH_ALEN, mac_addr) == ETH_ALEN) pr_info("Read MAC addr from EEPROM: %pM\n", mac_addr); diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c index 7c21760..875a2ba 100644 --- a/arch/arm/mach-exynos/pm_domains.c +++ b/arch/arm/mach-exynos/pm_domains.c @@ -92,7 +92,7 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on) if (IS_ERR(pd->clk[i])) break; - if (IS_ERR(pd->clk[i])) + if (IS_ERR(pd->pclk[i])) continue; /* Skip on first power up */ if (clk_set_parent(pd->clk[i], pd->pclk[i])) pr_err("%s: error setting parent to clock%d\n", diff --git a/arch/arm/mach-socfpga/headsmp.S b/arch/arm/mach-socfpga/headsmp.S index 5d94b7a..c160fa3 100644 --- a/arch/arm/mach-socfpga/headsmp.S +++ b/arch/arm/mach-socfpga/headsmp.S @@ -13,6 +13,7 @@ #include <asm/assembler.h> .arch armv7-a + .arm ENTRY(secondary_trampoline) /* CPU1 will always fetch from 0x0 when it is brought out of reset. diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 1dd1093..d5805e4 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -87,7 +87,6 @@ static unsigned long irbar_read(void) /* MPU initialisation functions */ void __init sanity_check_meminfo_mpu(void) { - int i; phys_addr_t phys_offset = PHYS_OFFSET; phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size; struct memblock_region *reg; @@ -110,11 +109,13 @@ void __init sanity_check_meminfo_mpu(void) } else { /* * memblock auto merges contiguous blocks, remove - * all blocks afterwards + * all blocks afterwards in one go (we can't remove + * blocks separately while iterating) */ pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n", - &mem_start, ®->base); - memblock_remove(reg->base, reg->size); + &mem_end, ®->base); + memblock_remove(reg->base, 0 - reg->base); + break; } } @@ -144,7 +145,7 @@ void __init sanity_check_meminfo_mpu(void) pr_warn("Truncating memory from %pa to %pa (MPU region constraints)", &specified_mem_size, &aligned_region_size); memblock_remove(mem_start + aligned_region_size, - specified_mem_size - aligned_round_size); + specified_mem_size - aligned_region_size); mem_end = mem_start + aligned_region_size; } @@ -261,7 +262,7 @@ void __init mpu_setup(void) return; region_err = mpu_setup_region(MPU_RAM_REGION, PHYS_OFFSET, - ilog2(meminfo.bank[0].size), + ilog2(memblock.memory.regions[0].size), MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL); if (region_err) { panic("MPU region initialization failure! %d", region_err); @@ -285,7 +286,7 @@ void __init arm_mm_memblock_reserve(void) * some architectures which the DRAM is the exception vector to trap, * alloc_page breaks with error, although it is not NULL, but "0." */ - memblock_reserve(CONFIG_VECTORS_BASE, PAGE_SIZE); + memblock_reserve(CONFIG_VECTORS_BASE, 2 * PAGE_SIZE); #else /* ifndef CONFIG_CPU_V7M */ /* * There is no dedicated vector page on V7-M. So nothing needs to be diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index efa77c1..521b1ec 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -2,6 +2,7 @@ menu "Platform selection" config ARCH_SUNXI bool "Allwinner sunxi 64-bit SoC Family" + select GENERIC_IRQ_CHIP help This enables support for Allwinner sunxi based SoCs like the A64. diff --git a/arch/arm64/boot/dts/renesas/r8a7795.dtsi b/arch/arm64/boot/dts/renesas/r8a7795.dtsi index a7315eb..706d242 100644 --- a/arch/arm64/boot/dts/renesas/r8a7795.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7795.dtsi @@ -120,7 +120,6 @@ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <0>; - status = "disabled"; }; soc { diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 8e88a69..622db3c 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -4,6 +4,7 @@ #include <asm/io.h> #include <asm/mmu_context.h> #include <asm/neon.h> +#include <asm/ptrace.h> #include <asm/tlbflush.h> #ifdef CONFIG_EFI @@ -14,32 +15,29 @@ extern void efi_init(void); int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); -#define efi_call_virt(f, ...) \ +#define efi_set_mapping_permissions efi_create_mapping + +#define arch_efi_call_virt_setup() \ ({ \ - efi_##f##_t *__f; \ - efi_status_t __s; \ - \ kernel_neon_begin(); \ efi_virtmap_load(); \ - __f = efi.systab->runtime->f; \ - __s = __f(__VA_ARGS__); \ - efi_virtmap_unload(); \ - kernel_neon_end(); \ - __s; \ }) -#define __efi_call_virt(f, ...) \ +#define arch_efi_call_virt(f, args...) \ ({ \ efi_##f##_t *__f; \ - \ - kernel_neon_begin(); \ - efi_virtmap_load(); \ __f = efi.systab->runtime->f; \ - __f(__VA_ARGS__); \ + __f(args); \ +}) + +#define arch_efi_call_virt_teardown() \ +({ \ efi_virtmap_unload(); \ kernel_neon_end(); \ }) +#define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) + /* arch specific definitions used by the stub code */ /* @@ -50,7 +48,16 @@ int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); #define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */ #define MAX_FDT_OFFSET SZ_512M -#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) +#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) +#define __efi_call_early(f, ...) f(__VA_ARGS__) +#define efi_is_64bit() (true) + +#define alloc_screen_info(x...) &screen_info +#define free_screen_info(x...) + +static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) +{ +} #define EFI_ALLOC_ALIGN SZ_64K diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index b6abc85..78f5248 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -17,22 +17,51 @@ #include <asm/efi.h> -int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) +/* + * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be + * executable, everything else can be mapped with the XN bits + * set. Also take the new (optional) RO/XP bits into account. + */ +static __init pteval_t create_mapping_protection(efi_memory_desc_t *md) { - pteval_t prot_val; + u64 attr = md->attribute; + u32 type = md->type; - /* - * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be - * executable, everything else can be mapped with the XN bits - * set. - */ - if ((md->attribute & EFI_MEMORY_WB) == 0) - prot_val = PROT_DEVICE_nGnRE; - else if (md->type == EFI_RUNTIME_SERVICES_CODE || - !PAGE_ALIGNED(md->phys_addr)) - prot_val = pgprot_val(PAGE_KERNEL_EXEC); - else - prot_val = pgprot_val(PAGE_KERNEL); + if (type == EFI_MEMORY_MAPPED_IO) + return PROT_DEVICE_nGnRE; + + if (WARN_ONCE(!PAGE_ALIGNED(md->phys_addr), + "UEFI Runtime regions are not aligned to 64 KB -- buggy firmware?")) + /* + * If the region is not aligned to the page size of the OS, we + * can not use strict permissions, since that would also affect + * the mapping attributes of the adjacent regions. + */ + return pgprot_val(PAGE_KERNEL_EXEC); + + /* R-- */ + if ((attr & (EFI_MEMORY_XP | EFI_MEMORY_RO)) == + (EFI_MEMORY_XP | EFI_MEMORY_RO)) + return pgprot_val(PAGE_KERNEL_RO); + + /* R-X */ + if (attr & EFI_MEMORY_RO) + return pgprot_val(PAGE_KERNEL_ROX); + + /* RW- */ + if (attr & EFI_MEMORY_XP || type != EFI_RUNTIME_SERVICES_CODE) + return pgprot_val(PAGE_KERNEL); + + /* RWX */ + return pgprot_val(PAGE_KERNEL_EXEC); +} + +/* we will fill this structure from the stub, so don't put it in .bss */ +struct screen_info screen_info __section(.data); + +int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) +{ + pteval_t prot_val = create_mapping_protection(md); create_pgd_mapping(mm, md->phys_addr, md->virt_addr, md->num_pages << EFI_PAGE_SHIFT, diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index b45c95d..4ef5373 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -616,7 +616,7 @@ static int breakpoint_handler(unsigned long unused, unsigned int esr, perf_bp_event(bp, regs); /* Do we need to handle the stepping? */ - if (!bp->overflow_handler) + if (is_default_overflow_handler(bp)) step = 1; unlock: rcu_read_unlock(); @@ -712,7 +712,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, perf_bp_event(wp, regs); /* Do we need to handle the stepping? */ - if (!wp->overflow_handler) + if (is_default_overflow_handler(wp)) step = 1; unlock: diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index 5e360ce..1428849a 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -112,6 +112,7 @@ __efistub___memset = KALLSYMS_HIDE(__pi_memset); __efistub__text = KALLSYMS_HIDE(_text); __efistub__end = KALLSYMS_HIDE(_end); __efistub__edata = KALLSYMS_HIDE(_edata); +__efistub_screen_info = KALLSYMS_HIDE(screen_info); #endif diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index ff46654..32c3c6e 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -122,7 +122,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry, tail = (struct frame_tail __user *)regs->regs[29]; - while (entry->nr < PERF_MAX_STACK_DEPTH && + while (entry->nr < sysctl_perf_event_max_stack && tail && !((unsigned long)tail & 0xf)) tail = user_backtrace(tail, entry); } else { @@ -132,7 +132,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry, tail = (struct compat_frame_tail __user *)regs->compat_fp - 1; - while ((entry->nr < PERF_MAX_STACK_DEPTH) && + while ((entry->nr < sysctl_perf_event_max_stack) && tail && !((unsigned long)tail & 0x3)) tail = compat_user_backtrace(tail, entry); #endif diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index a34420a..b405bbb 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -476,6 +476,7 @@ emit_cond_jmp: case BPF_JGE: jmp_cond = A64_COND_CS; break; + case BPF_JSET: case BPF_JNE: jmp_cond = A64_COND_NE; break; diff --git a/arch/ia64/include/asm/iommu.h b/arch/ia64/include/asm/iommu.h index 105c93b..1d12129 100644 --- a/arch/ia64/include/asm/iommu.h +++ b/arch/ia64/include/asm/iommu.h @@ -1,7 +1,6 @@ #ifndef _ASM_IA64_IOMMU_H #define _ASM_IA64_IOMMU_H 1 -#define cpu_has_x2apic 0 /* 10 seconds */ #define DMAR_OPERATION_TIMEOUT (((cycles_t) local_cpu_data->itc_freq)*10) diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h index ce11247..8b23e07 100644 --- a/arch/ia64/include/asm/rwsem.h +++ b/arch/ia64/include/asm/rwsem.h @@ -49,8 +49,8 @@ __down_read (struct rw_semaphore *sem) /* * lock for writing */ -static inline void -__down_write (struct rw_semaphore *sem) +static inline long +___down_write (struct rw_semaphore *sem) { long old, new; @@ -59,10 +59,26 @@ __down_write (struct rw_semaphore *sem) new = old + RWSEM_ACTIVE_WRITE_BIAS; } while (cmpxchg_acq(&sem->count, old, new) != old); - if (old != 0) + return old; +} + +static inline void +__down_write (struct rw_semaphore *sem) +{ + if (___down_write(sem)) rwsem_down_write_failed(sem); } +static inline int +__down_write_killable (struct rw_semaphore *sem) +{ + if (___down_write(sem)) + if (IS_ERR(rwsem_down_write_failed_killable(sem))) + return -EINTR; + + return 0; +} + /* * unlock after reading */ diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index 300dac3..bf0865c 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -531,8 +531,6 @@ efi_init (void) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, vendor); - set_bit(EFI_SYSTEM_TABLES, &efi.flags); - palo_phys = EFI_INVALID_TABLE_ADDR; if (efi_config_init(arch_tables) != 0) diff --git a/arch/metag/kernel/perf_callchain.c b/arch/metag/kernel/perf_callchain.c index 3156334..252abc1 100644 --- a/arch/metag/kernel/perf_callchain.c +++ b/arch/metag/kernel/perf_callchain.c @@ -65,7 +65,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) --frame; - while ((entry->nr < PERF_MAX_STACK_DEPTH) && frame) + while ((entry->nr < sysctl_perf_event_max_stack) && frame) frame = user_backtrace(frame, entry); } diff --git a/arch/mips/kernel/perf_event.c b/arch/mips/kernel/perf_event.c index c1cf9c6..5021c54 100644 --- a/arch/mips/kernel/perf_event.c +++ b/arch/mips/kernel/perf_event.c @@ -35,7 +35,7 @@ static void save_raw_perf_callchain(struct perf_callchain_entry *entry, addr = *sp++; if (__kernel_text_address(addr)) { perf_callchain_store(entry, addr); - if (entry->nr >= PERF_MAX_STACK_DEPTH) + if (entry->nr >= sysctl_perf_event_max_stack) break; } } @@ -59,7 +59,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry, } do { perf_callchain_store(entry, pc); - if (entry->nr >= PERF_MAX_STACK_DEPTH) + if (entry->nr >= sysctl_perf_event_max_stack) break; pc = unwind_stack(current, &sp, pc, &ra); } while (pc); diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index c976ebf..57b4836 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -344,7 +344,7 @@ tracesys_next: #endif cmpib,COND(=),n -1,%r20,tracesys_exit /* seccomp may have returned -1 */ - comiclr,>>= __NR_Linux_syscalls, %r20, %r0 + comiclr,>> __NR_Linux_syscalls, %r20, %r0 b,n .Ltracesys_nosys LDREGX %r20(%r19), %r19 diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index e4396a7..4afe66a 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -82,7 +82,7 @@ static inline unsigned long create_zero_mask(unsigned long bits) "andc %1,%1,%2\n\t" "popcntd %0,%1" : "=r" (leading_zero_bits), "=&r" (trailing_zero_bit_mask) - : "r" (bits)); + : "b" (bits)); return leading_zero_bits; } diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 8cac1eb..55c924b 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -565,7 +565,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) smp_ops->give_timebase(); /* Wait until cpu puts itself in the online & active maps */ - while (!cpu_online(cpu) || !cpu_active(cpu)) + while (!cpu_online(cpu)) cpu_relax(); return 0; diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index e04a675..22d9015 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -247,7 +247,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry, sp = regs->gpr[1]; perf_callchain_store(entry, next_ip); - while (entry->nr < PERF_MAX_STACK_DEPTH) { + while (entry->nr < sysctl_perf_event_max_stack) { fp = (unsigned long __user *) sp; if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp)) return; @@ -453,7 +453,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry, sp = regs->gpr[1]; perf_callchain_store(entry, next_ip); - while (entry->nr < PERF_MAX_STACK_DEPTH) { + while (entry->nr < sysctl_perf_event_max_stack) { fp = (unsigned int __user *) (unsigned long) sp; if (!valid_user_sp(sp, 0) || read_user_stack_32(fp, &next_sp)) return; diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h index fead491..c75e447 100644 --- a/arch/s390/include/asm/rwsem.h +++ b/arch/s390/include/asm/rwsem.h @@ -90,7 +90,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) /* * lock for writing */ -static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) +static inline long ___down_write(struct rw_semaphore *sem) { signed long old, new, tmp; @@ -104,13 +104,23 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) : "=&d" (old), "=&d" (new), "=Q" (sem->count) : "Q" (sem->count), "m" (tmp) : "cc", "memory"); - if (old != 0) - rwsem_down_write_failed(sem); + + return old; } static inline void __down_write(struct rw_semaphore *sem) { - __down_write_nested(sem, 0); + if (___down_write(sem)) + rwsem_down_write_failed(sem); +} + +static inline int __down_write_killable(struct rw_semaphore *sem) +{ + if (___down_write(sem)) + if (IS_ERR(rwsem_down_write_failed_killable(sem))) + return -EINTR; + + return 0; } /* diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 40a6b4f..7b89a75 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -832,7 +832,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) pcpu_attach_task(pcpu, tidle); pcpu_start_fn(pcpu, smp_start_secondary, NULL); /* Wait until cpu puts itself in the online & active maps */ - while (!cpu_online(cpu) || !cpu_active(cpu)) + while (!cpu_online(cpu)) cpu_relax(); return 0; } diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index a319745..751c337 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -26,6 +26,7 @@ generic-y += percpu.h generic-y += poll.h generic-y += preempt.h generic-y += resource.h +generic-y += rwsem.h generic-y += sembuf.h generic-y += serial.h generic-y += shmbuf.h diff --git a/arch/sh/include/asm/rwsem.h b/arch/sh/include/asm/rwsem.h deleted file mode 100644 index edab572..0000000 --- a/arch/sh/include/asm/rwsem.h +++ /dev/null @@ -1,132 +0,0 @@ -/* - * include/asm-sh/rwsem.h: R/W semaphores for SH using the stuff - * in lib/rwsem.c. - */ - -#ifndef _ASM_SH_RWSEM_H -#define _ASM_SH_RWSEM_H - -#ifndef _LINUX_RWSEM_H -#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead" -#endif - -#ifdef __KERNEL__ - -#define RWSEM_UNLOCKED_VALUE 0x00000000 -#define RWSEM_ACTIVE_BIAS 0x00000001 -#define RWSEM_ACTIVE_MASK 0x0000ffff -#define RWSEM_WAITING_BIAS (-0x00010000) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -/* - * lock for reading - */ -static inline void __down_read(struct rw_semaphore *sem) -{ - if (atomic_inc_return((atomic_t *)(&sem->count)) > 0) - smp_wmb(); - else - rwsem_down_read_failed(sem); -} - -static inline int __down_read_trylock(struct rw_semaphore *sem) -{ - int tmp; - - while ((tmp = sem->count) >= 0) { - if (tmp == cmpxchg(&sem->count, tmp, - tmp + RWSEM_ACTIVE_READ_BIAS)) { - smp_wmb(); - return 1; - } - } - return 0; -} - -/* - * lock for writing - */ -static inline void __down_write(struct rw_semaphore *sem) -{ - int tmp; - - tmp = atomic_add_return(RWSEM_ACTIVE_WRITE_BIAS, - (atomic_t *)(&sem->count)); - if (tmp == RWSEM_ACTIVE_WRITE_BIAS) - smp_wmb(); - else - rwsem_down_write_failed(sem); -} - -static inline int __down_write_trylock(struct rw_semaphore *sem) -{ - int tmp; - - tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, - RWSEM_ACTIVE_WRITE_BIAS); - smp_wmb(); - return tmp == RWSEM_UNLOCKED_VALUE; -} - -/* - * unlock after reading - */ -static inline void __up_read(struct rw_semaphore *sem) -{ - int tmp; - - smp_wmb(); - tmp = atomic_dec_return((atomic_t *)(&sem->count)); - if (tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0) - rwsem_wake(sem); -} - -/* - * unlock after writing - */ -static inline void __up_write(struct rw_semaphore *sem) -{ - smp_wmb(); - if (atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS, - (atomic_t *)(&sem->count)) < 0) - rwsem_wake(sem); -} - -/* - * implement atomic add functionality - */ -static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem) -{ - atomic_add(delta, (atomic_t *)(&sem->count)); -} - -/* - * downgrade write lock to read lock - */ -static inline void __downgrade_write(struct rw_semaphore *sem) -{ - int tmp; - - smp_wmb(); - tmp = atomic_add_return(-RWSEM_WAITING_BIAS, (atomic_t *)(&sem->count)); - if (tmp < 0) - rwsem_downgrade_wake(sem); -} - -static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) -{ - __down_write(sem); -} - -/* - * implement exchange and add functionality - */ -static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem) -{ - smp_mb(); - return atomic_add_return(delta, (atomic_t *)(&sem->count)); -} - -#endif /* __KERNEL__ */ -#endif /* _ASM_SH_RWSEM_H */ diff --git a/arch/sparc/configs/sparc32_defconfig b/arch/sparc/configs/sparc32_defconfig index fb23fd6..c74d370 100644 --- a/arch/sparc/configs/sparc32_defconfig +++ b/arch/sparc/configs/sparc32_defconfig @@ -24,7 +24,6 @@ CONFIG_INET_AH=y CONFIG_INET_ESP=y CONFIG_INET_IPCOMP=y # CONFIG_INET_LRO is not set -CONFIG_IPV6_PRIVACY=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig index 04920ab..3583d67 100644 --- a/arch/sparc/configs/sparc64_defconfig +++ b/arch/sparc/configs/sparc64_defconfig @@ -48,7 +48,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=y CONFIG_INET_ESP=y CONFIG_INET_IPCOMP=y -CONFIG_IPV6_PRIVACY=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y CONFIG_IPV6_OPTIMISTIC_DAD=y diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index e9286188..6024c26 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -16,6 +16,7 @@ generic-y += mm-arch-hooks.h generic-y += module.h generic-y += mutex.h generic-y += preempt.h +generic-y += rwsem.h generic-y += serial.h generic-y += trace_clock.h generic-y += types.h diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h deleted file mode 100644 index 069bf4d..0000000 --- a/arch/sparc/include/asm/rwsem.h +++ /dev/null @@ -1,124 +0,0 @@ -/* - * rwsem.h: R/W semaphores implemented using CAS - * - * Written by David S. Miller (davem@redhat.com), 2001. - * Derived from asm-i386/rwsem.h - */ -#ifndef _SPARC64_RWSEM_H -#define _SPARC64_RWSEM_H - -#ifndef _LINUX_RWSEM_H -#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead" -#endif - -#ifdef __KERNEL__ - -#define RWSEM_UNLOCKED_VALUE 0x00000000L -#define RWSEM_ACTIVE_BIAS 0x00000001L -#define RWSEM_ACTIVE_MASK 0xffffffffL -#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -/* - * lock for reading - */ -static inline void __down_read(struct rw_semaphore *sem) -{ - if (unlikely(atomic64_inc_return((atomic64_t *)(&sem->count)) <= 0L)) - rwsem_down_read_failed(sem); -} - -static inline int __down_read_trylock(struct rw_semaphore *sem) -{ - long tmp; - - while ((tmp = sem->count) >= 0L) { - if (tmp == cmpxchg(&sem->count, tmp, - tmp + RWSEM_ACTIVE_READ_BIAS)) { - return 1; - } - } - return 0; -} - -/* - * lock for writing - */ -static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) -{ - long tmp; - - tmp = atomic64_add_return(RWSEM_ACTIVE_WRITE_BIAS, - (atomic64_t *)(&sem->count)); - if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) - rwsem_down_write_failed(sem); -} - -static inline void __down_write(struct rw_semaphore *sem) -{ - __down_write_nested(sem, 0); -} - -static inline int __down_write_trylock(struct rw_semaphore *sem) -{ - long tmp; - - tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, - RWSEM_ACTIVE_WRITE_BIAS); - return tmp == RWSEM_UNLOCKED_VALUE; -} - -/* - * unlock after reading - */ -static inline void __up_read(struct rw_semaphore *sem) -{ - long tmp; - - tmp = atomic64_dec_return((atomic64_t *)(&sem->count)); - if (unlikely(tmp < -1L && (tmp & RWSEM_ACTIVE_MASK) == 0L)) - rwsem_wake(sem); -} - -/* - * unlock after writing - */ -static inline void __up_write(struct rw_semaphore *sem) -{ - if (unlikely(atomic64_sub_return(RWSEM_ACTIVE_WRITE_BIAS, - (atomic64_t *)(&sem->count)) < 0L)) - rwsem_wake(sem); -} - -/* - * implement atomic add functionality - */ -static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem) -{ - atomic64_add(delta, (atomic64_t *)(&sem->count)); -} - -/* - * downgrade write lock to read lock - */ -static inline void __downgrade_write(struct rw_semaphore *sem) -{ - long tmp; - - tmp = atomic64_add_return(-RWSEM_WAITING_BIAS, (atomic64_t *)(&sem->count)); - if (tmp < 0L) - rwsem_downgrade_wake(sem); -} - -/* - * implement exchange and add functionality - */ -static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) -{ - return atomic64_add_return(delta, (atomic64_t *)(&sem->count)); -} - -#endif /* __KERNEL__ */ - -#endif /* _SPARC64_RWSEM_H */ diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h index 56f9338..1d8321c 100644 --- a/arch/sparc/include/asm/spitfire.h +++ b/arch/sparc/include/asm/spitfire.h @@ -48,6 +48,7 @@ #define SUN4V_CHIP_SPARC_M6 0x06 #define SUN4V_CHIP_SPARC_M7 0x07 #define SUN4V_CHIP_SPARC64X 0x8a +#define SUN4V_CHIP_SPARC_SN 0x8b #define SUN4V_CHIP_UNKNOWN 0xff #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index b6de8b1..36eee81 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -423,8 +423,10 @@ #define __NR_setsockopt 355 #define __NR_mlock2 356 #define __NR_copy_file_range 357 +#define __NR_preadv2 358 +#define __NR_pwritev2 359 -#define NR_syscalls 358 +#define NR_syscalls 360 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 diff --git a/arch/sparc/kernel/cherrs.S b/arch/sparc/kernel/cherrs.S index 4ee1ad4..655628de 100644 --- a/arch/sparc/kernel/cherrs.S +++ b/arch/sparc/kernel/cherrs.S @@ -214,8 +214,7 @@ do_dcpe_tl1_nonfatal: /* Ok we may use interrupt globals safely. */ subcc %g1, %g2, %g1 ! Next cacheline bge,pt %icc, 1b nop - ba,pt %xcc, dcpe_icpe_tl1_common - nop + ba,a,pt %xcc, dcpe_icpe_tl1_common do_dcpe_tl1_fatal: sethi %hi(1f), %g7 @@ -224,8 +223,7 @@ do_dcpe_tl1_fatal: mov 0x2, %o0 call cheetah_plus_parity_error add %sp, PTREGS_OFF, %o1 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_dcpe_tl1,.-do_dcpe_tl1 .globl do_icpe_tl1 @@ -259,8 +257,7 @@ do_icpe_tl1_nonfatal: /* Ok we may use interrupt globals safely. */ subcc %g1, %g2, %g1 bge,pt %icc, 1b nop - ba,pt %xcc, dcpe_icpe_tl1_common - nop + ba,a,pt %xcc, dcpe_icpe_tl1_common do_icpe_tl1_fatal: sethi %hi(1f), %g7 @@ -269,8 +266,7 @@ do_icpe_tl1_fatal: mov 0x3, %o0 call cheetah_plus_parity_error add %sp, PTREGS_OFF, %o1 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_icpe_tl1,.-do_icpe_tl1 .type dcpe_icpe_tl1_common,#function @@ -456,7 +452,7 @@ __cheetah_log_error: cmp %g2, 0x63 be c_cee nop - ba,pt %xcc, c_deferred + ba,a,pt %xcc, c_deferred .size __cheetah_log_error,.-__cheetah_log_error /* Cheetah FECC trap handling, we get here from tl{0,1}_fecc diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c index dfad8b1..493e023 100644 --- a/arch/sparc/kernel/cpu.c +++ b/arch/sparc/kernel/cpu.c @@ -506,6 +506,12 @@ static void __init sun4v_cpu_probe(void) sparc_pmu_type = "sparc-m7"; break; + case SUN4V_CHIP_SPARC_SN: + sparc_cpu_type = "SPARC-SN"; + sparc_fpu_type = "SPARC-SN integrated FPU"; + sparc_pmu_type = "sparc-sn"; + break; + case SUN4V_CHIP_SPARC64X: sparc_cpu_type = "SPARC64-X"; sparc_fpu_type = "SPARC64-X integrated FPU"; diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c index e69ec0e..45c820e 100644 --- a/arch/sparc/kernel/cpumap.c +++ b/arch/sparc/kernel/cpumap.c @@ -328,6 +328,7 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index) case SUN4V_CHIP_NIAGARA5: case SUN4V_CHIP_SPARC_M6: case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_SN: case SUN4V_CHIP_SPARC64X: rover_inc_table = niagara_iterate_method; break; diff --git a/arch/sparc/kernel/fpu_traps.S b/arch/sparc/kernel/fpu_traps.S index a686482..336d275 100644 --- a/arch/sparc/kernel/fpu_traps.S +++ b/arch/sparc/kernel/fpu_traps.S @@ -100,8 +100,8 @@ do_fpdis: fmuld %f0, %f2, %f26 faddd %f0, %f2, %f28 fmuld %f0, %f2, %f30 - b,pt %xcc, fpdis_exit - nop + ba,a,pt %xcc, fpdis_exit + 2: andcc %g5, FPRS_DU, %g0 bne,pt %icc, 3f fzero %f32 @@ -144,8 +144,8 @@ do_fpdis: fmuld %f32, %f34, %f58 faddd %f32, %f34, %f60 fmuld %f32, %f34, %f62 - ba,pt %xcc, fpdis_exit - nop + ba,a,pt %xcc, fpdis_exit + 3: mov SECONDARY_CONTEXT, %g3 add %g6, TI_FPREGS, %g1 @@ -197,8 +197,7 @@ fpdis_exit2: fp_other_bounce: call do_fpother add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size fp_other_bounce,.-fp_other_bounce .align 32 diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index cd1f592..a076b42 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -414,6 +414,8 @@ sun4v_chip_type: cmp %g2, 'T' be,pt %xcc, 70f cmp %g2, 'M' + be,pt %xcc, 70f + cmp %g2, 'S' bne,pn %xcc, 49f nop @@ -433,6 +435,9 @@ sun4v_chip_type: cmp %g2, '7' be,pt %xcc, 5f mov SUN4V_CHIP_SPARC_M7, %g4 + cmp %g2, 'N' + be,pt %xcc, 5f + mov SUN4V_CHIP_SPARC_SN, %g4 ba,pt %xcc, 49f nop @@ -461,9 +466,8 @@ sun4v_chip_type: subcc %g3, 1, %g3 bne,pt %xcc, 41b add %g1, 1, %g1 - mov SUN4V_CHIP_SPARC64X, %g4 ba,pt %xcc, 5f - nop + mov SUN4V_CHIP_SPARC64X, %g4 49: mov SUN4V_CHIP_UNKNOWN, %g4 @@ -548,8 +552,7 @@ sun4u_init: stxa %g0, [%g7] ASI_DMMU membar #Sync - ba,pt %xcc, sun4u_continue - nop + ba,a,pt %xcc, sun4u_continue sun4v_init: /* Set ctx 0 */ @@ -560,14 +563,12 @@ sun4v_init: mov SECONDARY_CONTEXT, %g7 stxa %g0, [%g7] ASI_MMU membar #Sync - ba,pt %xcc, niagara_tlb_fixup - nop + ba,a,pt %xcc, niagara_tlb_fixup sun4u_continue: BRANCH_IF_ANY_CHEETAH(g1, g7, cheetah_tlb_fixup) - ba,pt %xcc, spitfire_tlb_fixup - nop + ba,a,pt %xcc, spitfire_tlb_fixup niagara_tlb_fixup: mov 3, %g2 /* Set TLB type to hypervisor. */ @@ -597,6 +598,9 @@ niagara_tlb_fixup: cmp %g1, SUN4V_CHIP_SPARC_M7 be,pt %xcc, niagara4_patch nop + cmp %g1, SUN4V_CHIP_SPARC_SN + be,pt %xcc, niagara4_patch + nop call generic_patch_copyops nop @@ -639,8 +643,7 @@ niagara_patch: call hypervisor_patch_cachetlbops nop - ba,pt %xcc, tlb_fixup_done - nop + ba,a,pt %xcc, tlb_fixup_done cheetah_tlb_fixup: mov 2, %g2 /* Set TLB type to cheetah+. */ @@ -659,8 +662,7 @@ cheetah_tlb_fixup: call cheetah_patch_cachetlbops nop - ba,pt %xcc, tlb_fixup_done - nop + ba,a,pt %xcc, tlb_fixup_done spitfire_tlb_fixup: /* Set TLB type to spitfire. */ @@ -774,8 +776,7 @@ setup_trap_table: call %o1 add %sp, (2047 + 128), %o0 - ba,pt %xcc, 2f - nop + ba,a,pt %xcc, 2f 1: sethi %hi(sparc64_ttable_tl0), %o0 set prom_set_trap_table_name, %g2 @@ -814,8 +815,7 @@ setup_trap_table: BRANCH_IF_ANY_CHEETAH(o2, o3, 1f) - ba,pt %xcc, 2f - nop + ba,a,pt %xcc, 2f /* Disable STICK_INT interrupts. */ 1: diff --git a/arch/sparc/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S index 753b4f0..34b4933 100644 --- a/arch/sparc/kernel/misctrap.S +++ b/arch/sparc/kernel/misctrap.S @@ -18,8 +18,7 @@ __do_privact: 109: or %g7, %lo(109b), %g7 call do_privact add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __do_privact,.-__do_privact .type do_mna,#function @@ -46,8 +45,7 @@ do_mna: mov %l5, %o2 call mem_address_unaligned add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_mna,.-do_mna .type do_lddfmna,#function @@ -65,8 +63,7 @@ do_lddfmna: mov %l5, %o2 call handle_lddfmna add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_lddfmna,.-do_lddfmna .type do_stdfmna,#function @@ -84,8 +81,7 @@ do_stdfmna: mov %l5, %o2 call handle_stdfmna add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_stdfmna,.-do_stdfmna .type breakpoint_trap,#function diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index badf095..c2b202d 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -245,6 +245,18 @@ static void pci_parse_of_addrs(struct platform_device *op, } } +static void pci_init_dev_archdata(struct dev_archdata *sd, void *iommu, + void *stc, void *host_controller, + struct platform_device *op, + int numa_node) +{ + sd->iommu = iommu; + sd->stc = stc; + sd->host_controller = host_controller; + sd->op = op; + sd->numa_node = numa_node; +} + static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, struct device_node *node, struct pci_bus *bus, int devfn) @@ -259,13 +271,10 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, if (!dev) return NULL; + op = of_find_device_by_node(node); sd = &dev->dev.archdata; - sd->iommu = pbm->iommu; - sd->stc = &pbm->stc; - sd->host_controller = pbm; - sd->op = op = of_find_device_by_node(node); - sd->numa_node = pbm->numa_node; - + pci_init_dev_archdata(sd, pbm->iommu, &pbm->stc, pbm, op, + pbm->numa_node); sd = &op->dev.archdata; sd->iommu = pbm->iommu; sd->stc = &pbm->stc; @@ -994,6 +1003,27 @@ void pcibios_set_master(struct pci_dev *dev) /* No special bus mastering setup handling */ } +#ifdef CONFIG_PCI_IOV +int pcibios_add_device(struct pci_dev *dev) +{ + struct pci_dev *pdev; + + /* Add sriov arch specific initialization here. + * Copy dev_archdata from PF to VF + */ + if (dev->is_virtfn) { + struct dev_archdata *psd; + + pdev = dev->physfn; + psd = &pdev->dev.archdata; + pci_init_dev_archdata(&dev->dev.archdata, psd->iommu, + psd->stc, psd->host_controller, NULL, + psd->numa_node); + } + return 0; +} +#endif /* CONFIG_PCI_IOV */ + static int __init pcibios_init(void) { pci_dfl_cache_line_size = 64 >> 2; diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 6596f66..a4b8b5a 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1756,7 +1756,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry, } } #endif - } while (entry->nr < PERF_MAX_STACK_DEPTH); + } while (entry->nr < sysctl_perf_event_max_stack); } static inline int @@ -1790,7 +1790,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry, pc = sf.callers_pc; ufp = (unsigned long)sf.fp + STACK_BIAS; perf_callchain_store(entry, pc); - } while (entry->nr < PERF_MAX_STACK_DEPTH); + } while (entry->nr < sysctl_perf_event_max_stack); } static void perf_callchain_user_32(struct perf_callchain_entry *entry, @@ -1822,7 +1822,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry, ufp = (unsigned long)sf.fp; } perf_callchain_store(entry, pc); - } while (entry->nr < PERF_MAX_STACK_DEPTH); + } while (entry->nr < sysctl_perf_event_max_stack); } void diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 26db95b..599f120 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -285,7 +285,8 @@ static void __init sun4v_patch(void) sun4v_patch_2insn_range(&__sun4v_2insn_patch, &__sun4v_2insn_patch_end); - if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7) + if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_SN) sun_m7_patch_2insn_range(&__sun_m7_2insn_patch, &__sun_m7_2insn_patch_end); @@ -524,6 +525,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_BLKINIT; if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || @@ -532,6 +534,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_N2; } @@ -561,6 +564,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 | AV_SPARC_ASI_BLK_INIT | @@ -570,6 +574,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC | AV_SPARC_FMAF); diff --git a/arch/sparc/kernel/spiterrs.S b/arch/sparc/kernel/spiterrs.S index c357e40..4a73009 100644 --- a/arch/sparc/kernel/spiterrs.S +++ b/arch/sparc/kernel/spiterrs.S @@ -85,8 +85,7 @@ __spitfire_cee_trap_continue: ba,pt %xcc, etraptl1 rd %pc, %g7 - ba,pt %xcc, 2f - nop + ba,a,pt %xcc, 2f 1: ba,pt %xcc, etrap_irq rd %pc, %g7 @@ -100,8 +99,7 @@ __spitfire_cee_trap_continue: mov %l5, %o2 call spitfire_access_error add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_access_error,.-__spitfire_access_error /* This is the trap handler entry point for ECC correctable @@ -179,8 +177,7 @@ __spitfire_data_access_exception_tl1: mov %l5, %o2 call spitfire_data_access_exception_tl1 add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_data_access_exception_tl1,.-__spitfire_data_access_exception_tl1 .type __spitfire_data_access_exception,#function @@ -200,8 +197,7 @@ __spitfire_data_access_exception: mov %l5, %o2 call spitfire_data_access_exception add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_data_access_exception,.-__spitfire_data_access_exception .type __spitfire_insn_access_exception_tl1,#function @@ -220,8 +216,7 @@ __spitfire_insn_access_exception_tl1: mov %l5, %o2 call spitfire_insn_access_exception_tl1 add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_insn_access_exception_tl1,.-__spitfire_insn_access_exception_tl1 .type __spitfire_insn_access_exception,#function @@ -240,6 +235,5 @@ __spitfire_insn_access_exception: mov %l5, %o2 call spitfire_insn_access_exception add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_insn_access_exception,.-__spitfire_insn_access_exception diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index 6c3dd6c..eac7f0d 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -88,4 +88,4 @@ sys_call_table: /*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr /*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen -/*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range +/*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2 diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 12b524c..b0f17ff 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -89,7 +89,7 @@ sys_call_table32: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range + .word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range, compat_sys_preadv2, compat_sys_pwritev2 #endif /* CONFIG_COMPAT */ @@ -170,4 +170,4 @@ sys_call_table: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word sys_setsockopt, sys_mlock2, sys_copy_file_range + .word sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2 diff --git a/arch/sparc/kernel/utrap.S b/arch/sparc/kernel/utrap.S index b7f0f3f..c731e80 100644 --- a/arch/sparc/kernel/utrap.S +++ b/arch/sparc/kernel/utrap.S @@ -11,8 +11,7 @@ utrap_trap: /* %g3=handler,%g4=level */ mov %l4, %o1 call bad_trap add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap invoke_utrap: sllx %g3, 3, %g3 diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c index cb5789c..f6bb857 100644 --- a/arch/sparc/kernel/vio.c +++ b/arch/sparc/kernel/vio.c @@ -45,6 +45,14 @@ static const struct vio_device_id *vio_match_device( return NULL; } +static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env) +{ + const struct vio_dev *vio_dev = to_vio_dev(dev); + + add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, vio_dev->compat); + return 0; +} + static int vio_bus_match(struct device *dev, struct device_driver *drv) { struct vio_dev *vio_dev = to_vio_dev(dev); @@ -105,15 +113,25 @@ static ssize_t type_show(struct device *dev, return sprintf(buf, "%s\n", vdev->type); } +static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + const struct vio_dev *vdev = to_vio_dev(dev); + + return sprintf(buf, "vio:T%sS%s\n", vdev->type, vdev->compat); +} + static struct device_attribute vio_dev_attrs[] = { __ATTR_RO(devspec), __ATTR_RO(type), + __ATTR_RO(modalias), __ATTR_NULL }; static struct bus_type vio_bus_type = { .name = "vio", .dev_attrs = vio_dev_attrs, + .uevent = vio_hotplug, .match = vio_bus_match, .probe = vio_device_probe, .remove = vio_device_remove, diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index aadd321..7d02b1f 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -33,6 +33,10 @@ ENTRY(_start) jiffies = jiffies_64; #endif +#ifdef CONFIG_SPARC64 +ASSERT((swapper_tsb == 0x0000000000408000), "Error: sparc64 early assembler too large") +#endif + SECTIONS { #ifdef CONFIG_SPARC64 diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S index 1e67ce9..855019a 100644 --- a/arch/sparc/kernel/winfixup.S +++ b/arch/sparc/kernel/winfixup.S @@ -32,8 +32,7 @@ fill_fixup: rd %pc, %g7 call do_sparc64_fault add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap /* Be very careful about usage of the trap globals here. * You cannot touch %g5 as that has the fault information. diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 1cfe6aa..09e8388 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1769,6 +1769,7 @@ static void __init setup_page_offset(void) max_phys_bits = 47; break; case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_SN: default: /* M7 and later support 52-bit virtual addresses. */ sparc64_va_hole_top = 0xfff8000000000000UL; @@ -1986,6 +1987,7 @@ static void __init sun4v_linear_pte_xor_finalize(void) */ switch (sun4v_chip_type) { case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_SN: pagecv_flag = 0x00; break; default: @@ -2138,6 +2140,7 @@ void __init paging_init(void) */ switch (sun4v_chip_type) { case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_SN: page_cache4v_flag = _PAGE_CP_4V; break; default: diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 2dc18605..7bb1574 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -164,10 +164,6 @@ config INSTRUCTION_DECODER def_bool y depends on KPROBES || PERF_EVENTS || UPROBES -config PERF_EVENTS_INTEL_UNCORE - def_bool y - depends on PERF_EVENTS && CPU_SUP_INTEL && PCI - config OUTPUT_FORMAT string default "elf32-i386" if X86_32 @@ -1046,6 +1042,8 @@ config X86_THERMAL_VECTOR def_bool y depends on X86_MCE_INTEL +source "arch/x86/events/Kconfig" + config X86_LEGACY_VM86 bool "Legacy VM86 support" default n @@ -1210,15 +1208,6 @@ config MICROCODE_OLD_INTERFACE def_bool y depends on MICROCODE -config PERF_EVENTS_AMD_POWER - depends on PERF_EVENTS && CPU_SUP_AMD - tristate "AMD Processor Power Reporting Mechanism" - ---help--- - Provide power reporting mechanism support for AMD processors. - Currently, it leverages X86_FEATURE_ACC_POWER - (CPUID Fn8000_0007_EDX[12]) interface to calculate the - average power consumption on Family 15h processors. - config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" ---help--- @@ -1932,54 +1921,38 @@ config RELOCATABLE (CONFIG_PHYSICAL_START) is used as the minimum location. config RANDOMIZE_BASE - bool "Randomize the address of the kernel image" + bool "Randomize the address of the kernel image (KASLR)" depends on RELOCATABLE default n ---help--- - Randomizes the physical and virtual address at which the - kernel image is decompressed, as a security feature that - deters exploit attempts relying on knowledge of the location - of kernel internals. + In support of Kernel Address Space Layout Randomization (KASLR), + this randomizes the physical address at which the kernel image + is decompressed and the virtual address where the kernel + image is mapped, as a security feature that deters exploit + attempts relying on knowledge of the location of kernel + code internals. + + The kernel physical and virtual address can be randomized + from 16MB up to 1GB on 64-bit and 512MB on 32-bit. (Note that + using RANDOMIZE_BASE reduces the memory space available to + kernel modules from 1.5GB to 1GB.) + + Entropy is generated using the RDRAND instruction if it is + supported. If RDTSC is supported, its value is mixed into + the entropy pool as well. If neither RDRAND nor RDTSC are + supported, then entropy is read from the i8254 timer. + + Since the kernel is built using 2GB addressing, and + PHYSICAL_ALIGN must be at a minimum of 2MB, only 10 bits of + entropy is theoretically possible. Currently, with the + default value for PHYSICAL_ALIGN and due to page table + layouts, 64-bit uses 9 bits of entropy and 32-bit uses 8 bits. + + If CONFIG_HIBERNATE is also enabled, KASLR is disabled at boot + time. To enable it, boot with "kaslr" on the kernel command + line (which will also disable hibernation). - Entropy is generated using the RDRAND instruction if it is - supported. If RDTSC is supported, it is used as well. If - neither RDRAND nor RDTSC are supported, then randomness is - read from the i8254 timer. - - The kernel will be offset by up to RANDOMIZE_BASE_MAX_OFFSET, - and aligned according to PHYSICAL_ALIGN. Since the kernel is - built using 2GiB addressing, and PHYSICAL_ALGIN must be at a - minimum of 2MiB, only 10 bits of entropy is theoretically - possible. At best, due to page table layouts, 64-bit can use - 9 bits of entropy and 32-bit uses 8 bits. - - If unsure, say N. - -config RANDOMIZE_BASE_MAX_OFFSET - hex "Maximum kASLR offset allowed" if EXPERT - depends on RANDOMIZE_BASE - range 0x0 0x20000000 if X86_32 - default "0x20000000" if X86_32 - range 0x0 0x40000000 if X86_64 - default "0x40000000" if X86_64 - ---help--- - The lesser of RANDOMIZE_BASE_MAX_OFFSET and available physical - memory is used to determine the maximal offset in bytes that will - be applied to the kernel when kernel Address Space Layout - Randomization (kASLR) is active. This must be a multiple of - PHYSICAL_ALIGN. - - On 32-bit this is limited to 512MiB by page table layouts. The - default is 512MiB. - - On 64-bit this is limited by how the kernel fixmap page table is - positioned, so this cannot be larger than 1GiB currently. Without - RANDOMIZE_BASE, there is a 512MiB to 1.5GiB split between kernel - and modules. When RANDOMIZE_BASE_MAX_OFFSET is above 512MiB, the - modules area will shrink to compensate, up to the current maximum - 1GiB to 1GiB split. The default is 1GiB. - - If unsure, leave at the default value. + If unsure, say N. # Relocation on x86 needs some additional build support config X86_NEED_RELOCS diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 4086abc..6fce7f0 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -208,7 +208,8 @@ endif head-y := arch/x86/kernel/head_$(BITS).o head-y += arch/x86/kernel/head$(BITS).o -head-y += arch/x86/kernel/head.o +head-y += arch/x86/kernel/ebda.o +head-y += arch/x86/kernel/platform-quirks.o libs-y += arch/x86/lib/ diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index b1ef9e4..700a9c6 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -86,16 +86,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|_end\)$$/\#define VO_\2 0x\1/p' - -quiet_cmd_voffset = VOFFSET $@ - cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@ - -targets += voffset.h -$(obj)/voffset.h: vmlinux FORCE - $(call if_changed,voffset) - -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ @@ -106,7 +97,7 @@ $(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE AFLAGS_header.o += -I$(obj) -$(obj)/header.o: $(obj)/voffset.h $(obj)/zoffset.h +$(obj)/header.o: $(obj)/zoffset.h LDFLAGS_setup.elf := -T $(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 8774cb2..cfdd8c3 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -57,12 +57,27 @@ LDFLAGS_vmlinux := -T hostprogs-y := mkpiggy HOST_EXTRACFLAGS += -I$(srctree)/tools/include +sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' + +quiet_cmd_voffset = VOFFSET $@ + cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@ + +targets += ../voffset.h + +$(obj)/../voffset.h: vmlinux FORCE + $(call if_changed,voffset) + +$(obj)/misc.o: $(obj)/../voffset.h + vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \ - $(obj)/string.o $(obj)/cmdline.o \ + $(obj)/string.o $(obj)/cmdline.o $(obj)/error.o \ $(obj)/piggy.o $(obj)/cpuflags.o vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o -vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/aslr.o +vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o +ifdef CONFIG_X86_64 + vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o +endif $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone @@ -109,10 +124,8 @@ suffix-$(CONFIG_KERNEL_XZ) := xz suffix-$(CONFIG_KERNEL_LZO) := lzo suffix-$(CONFIG_KERNEL_LZ4) := lz4 -RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \ - $(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh) quiet_cmd_mkpiggy = MKPIGGY $@ - cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false ) + cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false ) targets += piggy.S $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c deleted file mode 100644 index 6a9b96b..0000000 --- a/arch/x86/boot/compressed/aslr.c +++ /dev/null @@ -1,339 +0,0 @@ -#include "misc.h" - -#include <asm/msr.h> -#include <asm/archrandom.h> -#include <asm/e820.h> - -#include <generated/compile.h> -#include <linux/module.h> -#include <linux/uts.h> -#include <linux/utsname.h> -#include <generated/utsrelease.h> - -/* Simplified build-specific string for starting entropy. */ -static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" - LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; - -#define I8254_PORT_CONTROL 0x43 -#define I8254_PORT_COUNTER0 0x40 -#define I8254_CMD_READBACK 0xC0 -#define I8254_SELECT_COUNTER0 0x02 -#define I8254_STATUS_NOTREADY 0x40 -static inline u16 i8254(void) -{ - u16 status, timer; - - do { - outb(I8254_PORT_CONTROL, - I8254_CMD_READBACK | I8254_SELECT_COUNTER0); - status = inb(I8254_PORT_COUNTER0); - timer = inb(I8254_PORT_COUNTER0); - timer |= inb(I8254_PORT_COUNTER0) << 8; - } while (status & I8254_STATUS_NOTREADY); - - return timer; -} - -static unsigned long rotate_xor(unsigned long hash, const void *area, - size_t size) -{ - size_t i; - unsigned long *ptr = (unsigned long *)area; - - for (i = 0; i < size / sizeof(hash); i++) { - /* Rotate by odd number of bits and XOR. */ - hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7); - hash ^= ptr[i]; - } - - return hash; -} - -/* Attempt to create a simple but unpredictable starting entropy. */ -static unsigned long get_random_boot(void) -{ - unsigned long hash = 0; - - hash = rotate_xor(hash, build_str, sizeof(build_str)); - hash = rotate_xor(hash, real_mode, sizeof(*real_mode)); - - return hash; -} - -static unsigned long get_random_long(void) -{ -#ifdef CONFIG_X86_64 - const unsigned long mix_const = 0x5d6008cbf3848dd3UL; -#else - const unsigned long mix_const = 0x3f39e593UL; -#endif - unsigned long raw, random = get_random_boot(); - bool use_i8254 = true; - - debug_putstr("KASLR using"); - - if (has_cpuflag(X86_FEATURE_RDRAND)) { - debug_putstr(" RDRAND"); - if (rdrand_long(&raw)) { - random ^= raw; - use_i8254 = false; - } - } - - if (has_cpuflag(X86_FEATURE_TSC)) { - debug_putstr(" RDTSC"); - raw = rdtsc(); - - random ^= raw; - use_i8254 = false; - } - - if (use_i8254) { - debug_putstr(" i8254"); - random ^= i8254(); - } - - /* Circular multiply for better bit diffusion */ - asm("mul %3" - : "=a" (random), "=d" (raw) - : "a" (random), "rm" (mix_const)); - random += raw; - - debug_putstr("...\n"); - - return random; -} - -struct mem_vector { - unsigned long start; - unsigned long size; -}; - -#define MEM_AVOID_MAX 5 -static struct mem_vector mem_avoid[MEM_AVOID_MAX]; - -static bool mem_contains(struct mem_vector *region, struct mem_vector *item) -{ - /* Item at least partially before region. */ - if (item->start < region->start) - return false; - /* Item at least partially after region. */ - if (item->start + item->size > region->start + region->size) - return false; - return true; -} - -static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two) -{ - /* Item one is entirely before item two. */ - if (one->start + one->size <= two->start) - return false; - /* Item one is entirely after item two. */ - if (one->start >= two->start + two->size) - return false; - return true; -} - -static void mem_avoid_init(unsigned long input, unsigned long input_size, - unsigned long output, unsigned long output_size) -{ - u64 initrd_start, initrd_size; - u64 cmd_line, cmd_line_size; - unsigned long unsafe, unsafe_len; - char *ptr; - - /* - * Avoid the region that is unsafe to overlap during - * decompression (see calculations at top of misc.c). - */ - unsafe_len = (output_size >> 12) + 32768 + 18; - unsafe = (unsigned long)input + input_size - unsafe_len; - mem_avoid[0].start = unsafe; - mem_avoid[0].size = unsafe_len; - - /* Avoid initrd. */ - initrd_start = (u64)real_mode->ext_ramdisk_image << 32; - initrd_start |= real_mode->hdr.ramdisk_image; - initrd_size = (u64)real_mode->ext_ramdisk_size << 32; - initrd_size |= real_mode->hdr.ramdisk_size; - mem_avoid[1].start = initrd_start; - mem_avoid[1].size = initrd_size; - - /* Avoid kernel command line. */ - cmd_line = (u64)real_mode->ext_cmd_line_ptr << 32; - cmd_line |= real_mode->hdr.cmd_line_ptr; - /* Calculate size of cmd_line. */ - ptr = (char *)(unsigned long)cmd_line; - for (cmd_line_size = 0; ptr[cmd_line_size++]; ) - ; - mem_avoid[2].start = cmd_line; - mem_avoid[2].size = cmd_line_size; - - /* Avoid heap memory. */ - mem_avoid[3].start = (unsigned long)free_mem_ptr; - mem_avoid[3].size = BOOT_HEAP_SIZE; - - /* Avoid stack memory. */ - mem_avoid[4].start = (unsigned long)free_mem_end_ptr; - mem_avoid[4].size = BOOT_STACK_SIZE; -} - -/* Does this memory vector overlap a known avoided area? */ -static bool mem_avoid_overlap(struct mem_vector *img) -{ - int i; - struct setup_data *ptr; - - for (i = 0; i < MEM_AVOID_MAX; i++) { - if (mem_overlaps(img, &mem_avoid[i])) - return true; - } - - /* Avoid all entries in the setup_data linked list. */ - ptr = (struct setup_data *)(unsigned long)real_mode->hdr.setup_data; - while (ptr) { - struct mem_vector avoid; - - avoid.start = (unsigned long)ptr; - avoid.size = sizeof(*ptr) + ptr->len; - - if (mem_overlaps(img, &avoid)) - return true; - - ptr = (struct setup_data *)(unsigned long)ptr->next; - } - - return false; -} - -static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / - CONFIG_PHYSICAL_ALIGN]; -static unsigned long slot_max; - -static void slots_append(unsigned long addr) -{ - /* Overflowing the slots list should be impossible. */ - if (slot_max >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET / - CONFIG_PHYSICAL_ALIGN) - return; - - slots[slot_max++] = addr; -} - -static unsigned long slots_fetch_random(void) -{ - /* Handle case of no slots stored. */ - if (slot_max == 0) - return 0; - - return slots[get_random_long() % slot_max]; -} - -static void process_e820_entry(struct e820entry *entry, - unsigned long minimum, - unsigned long image_size) -{ - struct mem_vector region, img; - - /* Skip non-RAM entries. */ - if (entry->type != E820_RAM) - return; - - /* Ignore entries entirely above our maximum. */ - if (entry->addr >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET) - return; - - /* Ignore entries entirely below our minimum. */ - if (entry->addr + entry->size < minimum) - return; - - region.start = entry->addr; - region.size = entry->size; - - /* Potentially raise address to minimum location. */ - if (region.start < minimum) - region.start = minimum; - - /* Potentially raise address to meet alignment requirements. */ - region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN); - - /* Did we raise the address above the bounds of this e820 region? */ - if (region.start > entry->addr + entry->size) - return; - - /* Reduce size by any delta from the original address. */ - region.size -= region.start - entry->addr; - - /* Reduce maximum size to fit end of image within maximum limit. */ - if (region.start + region.size > CONFIG_RANDOMIZE_BASE_MAX_OFFSET) - region.size = CONFIG_RANDOMIZE_BASE_MAX_OFFSET - region.start; - - /* Walk each aligned slot and check for avoided areas. */ - for (img.start = region.start, img.size = image_size ; - mem_contains(®ion, &img) ; - img.start += CONFIG_PHYSICAL_ALIGN) { - if (mem_avoid_overlap(&img)) - continue; - slots_append(img.start); - } -} - -static unsigned long find_random_addr(unsigned long minimum, - unsigned long size) -{ - int i; - unsigned long addr; - - /* Make sure minimum is aligned. */ - minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); - - /* Verify potential e820 positions, appending to slots list. */ - for (i = 0; i < real_mode->e820_entries; i++) { - process_e820_entry(&real_mode->e820_map[i], minimum, size); - } - - return slots_fetch_random(); -} - -unsigned char *choose_kernel_location(struct boot_params *boot_params, - unsigned char *input, - unsigned long input_size, - unsigned char *output, - unsigned long output_size) -{ - unsigned long choice = (unsigned long)output; - unsigned long random; - -#ifdef CONFIG_HIBERNATION - if (!cmdline_find_option_bool("kaslr")) { - debug_putstr("KASLR disabled by default...\n"); - goto out; - } -#else - if (cmdline_find_option_bool("nokaslr")) { - debug_putstr("KASLR disabled by cmdline...\n"); - goto out; - } -#endif - - boot_params->hdr.loadflags |= KASLR_FLAG; - - /* Record the various known unsafe memory ranges. */ - mem_avoid_init((unsigned long)input, input_size, - (unsigned long)output, output_size); - - /* Walk e820 and find a random address. */ - random = find_random_addr(choice, output_size); - if (!random) { - debug_putstr("KASLR could not find suitable E820 region...\n"); - goto out; - } - - /* Always enforce the minimum. */ - if (random < choice) - goto out; - - choice = random; -out: - return (unsigned char *)choice; -} diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index b68e303..73ccf63 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -15,9 +15,9 @@ static inline char rdfs8(addr_t addr) #include "../cmdline.c" static unsigned long get_cmd_line_ptr(void) { - unsigned long cmd_line_ptr = real_mode->hdr.cmd_line_ptr; + unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr; - cmd_line_ptr |= (u64)real_mode->ext_cmd_line_ptr << 32; + cmd_line_ptr |= (u64)boot_params->ext_cmd_line_ptr << 32; return cmd_line_ptr; } diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 583d539..52fef60 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -571,312 +571,6 @@ free_handle: efi_call_early(free_pool, pci_handle); } -static void -setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line, - struct efi_pixel_bitmask pixel_info, int pixel_format) -{ - if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) { - si->lfb_depth = 32; - si->lfb_linelength = pixels_per_scan_line * 4; - si->red_size = 8; - si->red_pos = 0; - si->green_size = 8; - si->green_pos = 8; - si->blue_size = 8; - si->blue_pos = 16; - si->rsvd_size = 8; - si->rsvd_pos = 24; - } else if (pixel_format == PIXEL_BGR_RESERVED_8BIT_PER_COLOR) { - si->lfb_depth = 32; - si->lfb_linelength = pixels_per_scan_line * 4; - si->red_size = 8; - si->red_pos = 16; - si->green_size = 8; - si->green_pos = 8; - si->blue_size = 8; - si->blue_pos = 0; - si->rsvd_size = 8; - si->rsvd_pos = 24; - } else if (pixel_format == PIXEL_BIT_MASK) { - find_bits(pixel_info.red_mask, &si->red_pos, &si->red_size); - find_bits(pixel_info.green_mask, &si->green_pos, - &si->green_size); - find_bits(pixel_info.blue_mask, &si->blue_pos, &si->blue_size); - find_bits(pixel_info.reserved_mask, &si->rsvd_pos, - &si->rsvd_size); - si->lfb_depth = si->red_size + si->green_size + - si->blue_size + si->rsvd_size; - si->lfb_linelength = (pixels_per_scan_line * si->lfb_depth) / 8; - } else { - si->lfb_depth = 4; - si->lfb_linelength = si->lfb_width / 2; - si->red_size = 0; - si->red_pos = 0; - si->green_size = 0; - si->green_pos = 0; - si->blue_size = 0; - si->blue_pos = 0; - si->rsvd_size = 0; - si->rsvd_pos = 0; - } -} - -static efi_status_t -__gop_query32(struct efi_graphics_output_protocol_32 *gop32, - struct efi_graphics_output_mode_info **info, - unsigned long *size, u64 *fb_base) -{ - struct efi_graphics_output_protocol_mode_32 *mode; - efi_status_t status; - unsigned long m; - - m = gop32->mode; - mode = (struct efi_graphics_output_protocol_mode_32 *)m; - - status = efi_early->call(gop32->query_mode, gop32, - mode->mode, size, info); - if (status != EFI_SUCCESS) - return status; - - *fb_base = mode->frame_buffer_base; - return status; -} - -static efi_status_t -setup_gop32(struct screen_info *si, efi_guid_t *proto, - unsigned long size, void **gop_handle) -{ - struct efi_graphics_output_protocol_32 *gop32, *first_gop; - unsigned long nr_gops; - u16 width, height; - u32 pixels_per_scan_line; - u32 ext_lfb_base; - u64 fb_base; - struct efi_pixel_bitmask pixel_info; - int pixel_format; - efi_status_t status; - u32 *handles = (u32 *)(unsigned long)gop_handle; - int i; - - first_gop = NULL; - gop32 = NULL; - - nr_gops = size / sizeof(u32); - for (i = 0; i < nr_gops; i++) { - struct efi_graphics_output_mode_info *info = NULL; - efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; - bool conout_found = false; - void *dummy = NULL; - u32 h = handles[i]; - u64 current_fb_base; - - status = efi_call_early(handle_protocol, h, - proto, (void **)&gop32); - if (status != EFI_SUCCESS) - continue; - - status = efi_call_early(handle_protocol, h, - &conout_proto, &dummy); - if (status == EFI_SUCCESS) - conout_found = true; - - status = __gop_query32(gop32, &info, &size, ¤t_fb_base); - if (status == EFI_SUCCESS && (!first_gop || conout_found)) { - /* - * Systems that use the UEFI Console Splitter may - * provide multiple GOP devices, not all of which are - * backed by real hardware. The workaround is to search - * for a GOP implementing the ConOut protocol, and if - * one isn't found, to just fall back to the first GOP. - */ - width = info->horizontal_resolution; - height = info->vertical_resolution; - pixel_format = info->pixel_format; - pixel_info = info->pixel_information; - pixels_per_scan_line = info->pixels_per_scan_line; - fb_base = current_fb_base; - - /* - * Once we've found a GOP supporting ConOut, - * don't bother looking any further. - */ - first_gop = gop32; - if (conout_found) - break; - } - } - - /* Did we find any GOPs? */ - if (!first_gop) - goto out; - - /* EFI framebuffer */ - si->orig_video_isVGA = VIDEO_TYPE_EFI; - - si->lfb_width = width; - si->lfb_height = height; - si->lfb_base = fb_base; - - ext_lfb_base = (u64)(unsigned long)fb_base >> 32; - if (ext_lfb_base) { - si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; - si->ext_lfb_base = ext_lfb_base; - } - - si->pages = 1; - - setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); - - si->lfb_size = si->lfb_linelength * si->lfb_height; - - si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; -out: - return status; -} - -static efi_status_t -__gop_query64(struct efi_graphics_output_protocol_64 *gop64, - struct efi_graphics_output_mode_info **info, - unsigned long *size, u64 *fb_base) -{ - struct efi_graphics_output_protocol_mode_64 *mode; - efi_status_t status; - unsigned long m; - - m = gop64->mode; - mode = (struct efi_graphics_output_protocol_mode_64 *)m; - - status = efi_early->call(gop64->query_mode, gop64, - mode->mode, size, info); - if (status != EFI_SUCCESS) - return status; - - *fb_base = mode->frame_buffer_base; - return status; -} - -static efi_status_t -setup_gop64(struct screen_info *si, efi_guid_t *proto, - unsigned long size, void **gop_handle) -{ - struct efi_graphics_output_protocol_64 *gop64, *first_gop; - unsigned long nr_gops; - u16 width, height; - u32 pixels_per_scan_line; - u32 ext_lfb_base; - u64 fb_base; - struct efi_pixel_bitmask pixel_info; - int pixel_format; - efi_status_t status; - u64 *handles = (u64 *)(unsigned long)gop_handle; - int i; - - first_gop = NULL; - gop64 = NULL; - - nr_gops = size / sizeof(u64); - for (i = 0; i < nr_gops; i++) { - struct efi_graphics_output_mode_info *info = NULL; - efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; - bool conout_found = false; - void *dummy = NULL; - u64 h = handles[i]; - u64 current_fb_base; - - status = efi_call_early(handle_protocol, h, - proto, (void **)&gop64); - if (status != EFI_SUCCESS) - continue; - - status = efi_call_early(handle_protocol, h, - &conout_proto, &dummy); - if (status == EFI_SUCCESS) - conout_found = true; - - status = __gop_query64(gop64, &info, &size, ¤t_fb_base); - if (status == EFI_SUCCESS && (!first_gop || conout_found)) { - /* - * Systems that use the UEFI Console Splitter may - * provide multiple GOP devices, not all of which are - * backed by real hardware. The workaround is to search - * for a GOP implementing the ConOut protocol, and if - * one isn't found, to just fall back to the first GOP. - */ - width = info->horizontal_resolution; - height = info->vertical_resolution; - pixel_format = info->pixel_format; - pixel_info = info->pixel_information; - pixels_per_scan_line = info->pixels_per_scan_line; - fb_base = current_fb_base; - - /* - * Once we've found a GOP supporting ConOut, - * don't bother looking any further. - */ - first_gop = gop64; - if (conout_found) - break; - } - } - - /* Did we find any GOPs? */ - if (!first_gop) - goto out; - - /* EFI framebuffer */ - si->orig_video_isVGA = VIDEO_TYPE_EFI; - - si->lfb_width = width; - si->lfb_height = height; - si->lfb_base = fb_base; - - ext_lfb_base = (u64)(unsigned long)fb_base >> 32; - if (ext_lfb_base) { - si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; - si->ext_lfb_base = ext_lfb_base; - } - - si->pages = 1; - - setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); - - si->lfb_size = si->lfb_linelength * si->lfb_height; - - si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; -out: - return status; -} - -/* - * See if we have Graphics Output Protocol - */ -static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, - unsigned long size) -{ - efi_status_t status; - void **gop_handle = NULL; - - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - size, (void **)&gop_handle); - if (status != EFI_SUCCESS) - return status; - - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - proto, NULL, &size, gop_handle); - if (status != EFI_SUCCESS) - goto free_handle; - - if (efi_early->is64) - status = setup_gop64(si, proto, size, gop_handle); - else - status = setup_gop32(si, proto, size, gop_handle); - -free_handle: - efi_call_early(free_pool, gop_handle); - return status; -} - static efi_status_t setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height) { @@ -1038,7 +732,7 @@ void setup_graphics(struct boot_params *boot_params) EFI_LOCATE_BY_PROTOCOL, &graphics_proto, NULL, &size, gop_handle); if (status == EFI_BUFFER_TOO_SMALL) - status = setup_gop(si, &graphics_proto, size); + status = efi_setup_gop(NULL, si, &graphics_proto, size); if (status != EFI_SUCCESS) { size = 0; diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index d487e72..c0223f1 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -11,80 +11,6 @@ #define DESC_TYPE_CODE_DATA (1 << 0) -#define EFI_CONSOLE_OUT_DEVICE_GUID \ - EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x0, 0x90, 0x27, \ - 0x3f, 0xc1, 0x4d) - -#define PIXEL_RGB_RESERVED_8BIT_PER_COLOR 0 -#define PIXEL_BGR_RESERVED_8BIT_PER_COLOR 1 -#define PIXEL_BIT_MASK 2 -#define PIXEL_BLT_ONLY 3 -#define PIXEL_FORMAT_MAX 4 - -struct efi_pixel_bitmask { - u32 red_mask; - u32 green_mask; - u32 blue_mask; - u32 reserved_mask; -}; - -struct efi_graphics_output_mode_info { - u32 version; - u32 horizontal_resolution; - u32 vertical_resolution; - int pixel_format; - struct efi_pixel_bitmask pixel_information; - u32 pixels_per_scan_line; -} __packed; - -struct efi_graphics_output_protocol_mode_32 { - u32 max_mode; - u32 mode; - u32 info; - u32 size_of_info; - u64 frame_buffer_base; - u32 frame_buffer_size; -} __packed; - -struct efi_graphics_output_protocol_mode_64 { - u32 max_mode; - u32 mode; - u64 info; - u64 size_of_info; - u64 frame_buffer_base; - u64 frame_buffer_size; -} __packed; - -struct efi_graphics_output_protocol_mode { - u32 max_mode; - u32 mode; - unsigned long info; - unsigned long size_of_info; - u64 frame_buffer_base; - unsigned long frame_buffer_size; -} __packed; - -struct efi_graphics_output_protocol_32 { - u32 query_mode; - u32 set_mode; - u32 blt; - u32 mode; -}; - -struct efi_graphics_output_protocol_64 { - u64 query_mode; - u64 set_mode; - u64 blt; - u64 mode; -}; - -struct efi_graphics_output_protocol { - void *query_mode; - unsigned long set_mode; - unsigned long blt; - struct efi_graphics_output_protocol_mode *mode; -}; - struct efi_uga_draw_protocol_32 { u32 get_mode; u32 set_mode; diff --git a/arch/x86/boot/compressed/error.c b/arch/x86/boot/compressed/error.c new file mode 100644 index 0000000..6248740 --- /dev/null +++ b/arch/x86/boot/compressed/error.c @@ -0,0 +1,22 @@ +/* + * Callers outside of misc.c need access to the error reporting routines, + * but the *_putstr() functions need to stay in misc.c because of how + * memcpy() and memmove() are defined for the compressed boot environment. + */ +#include "misc.h" + +void warn(char *m) +{ + error_putstr("\n\n"); + error_putstr(m); + error_putstr("\n\n"); +} + +void error(char *m) +{ + warn(m); + error_putstr(" -- System halted"); + + while (1) + asm("hlt"); +} diff --git a/arch/x86/boot/compressed/error.h b/arch/x86/boot/compressed/error.h new file mode 100644 index 0000000..2e59dac --- /dev/null +++ b/arch/x86/boot/compressed/error.h @@ -0,0 +1,7 @@ +#ifndef BOOT_COMPRESSED_ERROR_H +#define BOOT_COMPRESSED_ERROR_H + +void warn(char *m); +void error(char *m); + +#endif /* BOOT_COMPRESSED_ERROR_H */ diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 0256064..1038524 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -176,7 +176,9 @@ preferred_addr: 1: /* Target address to relocate to for decompression */ - addl $z_extract_offset, %ebx + movl BP_init_size(%esi), %eax + subl $_end, %eax + addl %eax, %ebx /* Set up the stack */ leal boot_stack_end(%ebx), %esp @@ -233,24 +235,28 @@ relocated: 2: /* - * Do the decompression, and jump to the new kernel.. + * Do the extraction, and jump to the new kernel.. */ - /* push arguments for decompress_kernel: */ - pushl $z_run_size /* size of kernel with .bss and .brk */ + /* push arguments for extract_kernel: */ pushl $z_output_len /* decompressed length, end of relocs */ - leal z_extract_offset_negative(%ebx), %ebp + + movl BP_init_size(%esi), %eax + subl $_end, %eax + movl %ebx, %ebp + subl %eax, %ebp pushl %ebp /* output address */ + pushl $z_input_len /* input_len */ leal input_data(%ebx), %eax pushl %eax /* input_data */ leal boot_heap(%ebx), %eax pushl %eax /* heap area */ pushl %esi /* real mode pointer */ - call decompress_kernel /* returns kernel location in %eax */ - addl $28, %esp + call extract_kernel /* returns kernel location in %eax */ + addl $24, %esp /* - * Jump to the decompressed kernel. + * Jump to the extracted kernel. */ xorl %ebx, %ebx jmp *%eax diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 86558a1..0d80a7a 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -110,7 +110,9 @@ ENTRY(startup_32) 1: /* Target address to relocate to for decompression */ - addl $z_extract_offset, %ebx + movl BP_init_size(%esi), %eax + subl $_end, %eax + addl %eax, %ebx /* * Prepare for entering 64 bit mode @@ -132,7 +134,7 @@ ENTRY(startup_32) /* Initialize Page tables to 0 */ leal pgtable(%ebx), %edi xorl %eax, %eax - movl $((4096*6)/4), %ecx + movl $(BOOT_INIT_PGT_SIZE/4), %ecx rep stosl /* Build Level 4 */ @@ -338,7 +340,9 @@ preferred_addr: 1: /* Target address to relocate to for decompression */ - leaq z_extract_offset(%rbp), %rbx + movl BP_init_size(%rsi), %ebx + subl $_end, %ebx + addq %rbp, %rbx /* Set up the stack */ leaq boot_stack_end(%rbx), %rsp @@ -408,19 +412,16 @@ relocated: 2: /* - * Do the decompression, and jump to the new kernel.. + * Do the extraction, and jump to the new kernel.. */ pushq %rsi /* Save the real mode argument */ - movq $z_run_size, %r9 /* size of kernel with .bss and .brk */ - pushq %r9 movq %rsi, %rdi /* real mode address */ leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ leaq input_data(%rip), %rdx /* input_data */ movl $z_input_len, %ecx /* input_len */ movq %rbp, %r8 /* output target address */ movq $z_output_len, %r9 /* decompressed length, end of relocs */ - call decompress_kernel /* returns kernel location in %rax */ - popq %r9 + call extract_kernel /* returns kernel location in %rax */ popq %rsi /* @@ -485,4 +486,4 @@ boot_stack_end: .section ".pgtable","a",@nobits .balign 4096 pgtable: - .fill 6*4096, 1, 0 + .fill BOOT_PGT_SIZE, 1, 0 diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c new file mode 100644 index 0000000..cfeb025 --- /dev/null +++ b/arch/x86/boot/compressed/kaslr.c @@ -0,0 +1,510 @@ +/* + * kaslr.c + * + * This contains the routines needed to generate a reasonable level of + * entropy to choose a randomized kernel base address offset in support + * of Kernel Address Space Layout Randomization (KASLR). Additionally + * handles walking the physical memory maps (and tracking memory regions + * to avoid) in order to select a physical memory location that can + * contain the entire properly aligned running kernel image. + * + */ +#include "misc.h" +#include "error.h" + +#include <asm/msr.h> +#include <asm/archrandom.h> +#include <asm/e820.h> + +#include <generated/compile.h> +#include <linux/module.h> +#include <linux/uts.h> +#include <linux/utsname.h> +#include <generated/utsrelease.h> + +/* Simplified build-specific string for starting entropy. */ +static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" + LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; + +#define I8254_PORT_CONTROL 0x43 +#define I8254_PORT_COUNTER0 0x40 +#define I8254_CMD_READBACK 0xC0 +#define I8254_SELECT_COUNTER0 0x02 +#define I8254_STATUS_NOTREADY 0x40 +static inline u16 i8254(void) +{ + u16 status, timer; + + do { + outb(I8254_PORT_CONTROL, + I8254_CMD_READBACK | I8254_SELECT_COUNTER0); + status = inb(I8254_PORT_COUNTER0); + timer = inb(I8254_PORT_COUNTER0); + timer |= inb(I8254_PORT_COUNTER0) << 8; + } while (status & I8254_STATUS_NOTREADY); + + return timer; +} + +static unsigned long rotate_xor(unsigned long hash, const void *area, + size_t size) +{ + size_t i; + unsigned long *ptr = (unsigned long *)area; + + for (i = 0; i < size / sizeof(hash); i++) { + /* Rotate by odd number of bits and XOR. */ + hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7); + hash ^= ptr[i]; + } + + return hash; +} + +/* Attempt to create a simple but unpredictable starting entropy. */ +static unsigned long get_random_boot(void) +{ + unsigned long hash = 0; + + hash = rotate_xor(hash, build_str, sizeof(build_str)); + hash = rotate_xor(hash, boot_params, sizeof(*boot_params)); + + return hash; +} + +static unsigned long get_random_long(const char *purpose) +{ +#ifdef CONFIG_X86_64 + const unsigned long mix_const = 0x5d6008cbf3848dd3UL; +#else + const unsigned long mix_const = 0x3f39e593UL; +#endif + unsigned long raw, random = get_random_boot(); + bool use_i8254 = true; + + debug_putstr(purpose); + debug_putstr(" KASLR using"); + + if (has_cpuflag(X86_FEATURE_RDRAND)) { + debug_putstr(" RDRAND"); + if (rdrand_long(&raw)) { + random ^= raw; + use_i8254 = false; + } + } + + if (has_cpuflag(X86_FEATURE_TSC)) { + debug_putstr(" RDTSC"); + raw = rdtsc(); + + random ^= raw; + use_i8254 = false; + } + + if (use_i8254) { + debug_putstr(" i8254"); + random ^= i8254(); + } + + /* Circular multiply for better bit diffusion */ + asm("mul %3" + : "=a" (random), "=d" (raw) + : "a" (random), "rm" (mix_const)); + random += raw; + + debug_putstr("...\n"); + + return random; +} + +struct mem_vector { + unsigned long start; + unsigned long size; +}; + +enum mem_avoid_index { + MEM_AVOID_ZO_RANGE = 0, + MEM_AVOID_INITRD, + MEM_AVOID_CMDLINE, + MEM_AVOID_BOOTPARAMS, + MEM_AVOID_MAX, +}; + +static struct mem_vector mem_avoid[MEM_AVOID_MAX]; + +static bool mem_contains(struct mem_vector *region, struct mem_vector *item) +{ + /* Item at least partially before region. */ + if (item->start < region->start) + return false; + /* Item at least partially after region. */ + if (item->start + item->size > region->start + region->size) + return false; + return true; +} + +static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two) +{ + /* Item one is entirely before item two. */ + if (one->start + one->size <= two->start) + return false; + /* Item one is entirely after item two. */ + if (one->start >= two->start + two->size) + return false; + return true; +} + +/* + * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T). + * The mem_avoid array is used to store the ranges that need to be avoided + * when KASLR searches for an appropriate random address. We must avoid any + * regions that are unsafe to overlap with during decompression, and other + * things like the initrd, cmdline and boot_params. This comment seeks to + * explain mem_avoid as clearly as possible since incorrect mem_avoid + * memory ranges lead to really hard to debug boot failures. + * + * The initrd, cmdline, and boot_params are trivial to identify for + * avoiding. They are MEM_AVOID_INITRD, MEM_AVOID_CMDLINE, and + * MEM_AVOID_BOOTPARAMS respectively below. + * + * What is not obvious how to avoid is the range of memory that is used + * during decompression (MEM_AVOID_ZO_RANGE below). This range must cover + * the compressed kernel (ZO) and its run space, which is used to extract + * the uncompressed kernel (VO) and relocs. + * + * ZO's full run size sits against the end of the decompression buffer, so + * we can calculate where text, data, bss, etc of ZO are positioned more + * easily. + * + * For additional background, the decompression calculations can be found + * in header.S, and the memory diagram is based on the one found in misc.c. + * + * The following conditions are already enforced by the image layouts and + * associated code: + * - input + input_size >= output + output_size + * - kernel_total_size <= init_size + * - kernel_total_size <= output_size (see Note below) + * - output + init_size >= output + output_size + * + * (Note that kernel_total_size and output_size have no fundamental + * relationship, but output_size is passed to choose_random_location + * as a maximum of the two. The diagram is showing a case where + * kernel_total_size is larger than output_size, but this case is + * handled by bumping output_size.) + * + * The above conditions can be illustrated by a diagram: + * + * 0 output input input+input_size output+init_size + * | | | | | + * | | | | | + * |-----|--------|--------|--------------|-----------|--|-------------| + * | | | + * | | | + * output+init_size-ZO_INIT_SIZE output+output_size output+kernel_total_size + * + * [output, output+init_size) is the entire memory range used for + * extracting the compressed image. + * + * [output, output+kernel_total_size) is the range needed for the + * uncompressed kernel (VO) and its run size (bss, brk, etc). + * + * [output, output+output_size) is VO plus relocs (i.e. the entire + * uncompressed payload contained by ZO). This is the area of the buffer + * written to during decompression. + * + * [output+init_size-ZO_INIT_SIZE, output+init_size) is the worst-case + * range of the copied ZO and decompression code. (i.e. the range + * covered backwards of size ZO_INIT_SIZE, starting from output+init_size.) + * + * [input, input+input_size) is the original copied compressed image (ZO) + * (i.e. it does not include its run size). This range must be avoided + * because it contains the data used for decompression. + * + * [input+input_size, output+init_size) is [_text, _end) for ZO. This + * range includes ZO's heap and stack, and must be avoided since it + * performs the decompression. + * + * Since the above two ranges need to be avoided and they are adjacent, + * they can be merged, resulting in: [input, output+init_size) which + * becomes the MEM_AVOID_ZO_RANGE below. + */ +static void mem_avoid_init(unsigned long input, unsigned long input_size, + unsigned long output) +{ + unsigned long init_size = boot_params->hdr.init_size; + u64 initrd_start, initrd_size; + u64 cmd_line, cmd_line_size; + char *ptr; + + /* + * Avoid the region that is unsafe to overlap during + * decompression. + */ + mem_avoid[MEM_AVOID_ZO_RANGE].start = input; + mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input; + add_identity_map(mem_avoid[MEM_AVOID_ZO_RANGE].start, + mem_avoid[MEM_AVOID_ZO_RANGE].size); + + /* Avoid initrd. */ + initrd_start = (u64)boot_params->ext_ramdisk_image << 32; + initrd_start |= boot_params->hdr.ramdisk_image; + initrd_size = (u64)boot_params->ext_ramdisk_size << 32; + initrd_size |= boot_params->hdr.ramdisk_size; + mem_avoid[MEM_AVOID_INITRD].start = initrd_start; + mem_avoid[MEM_AVOID_INITRD].size = initrd_size; + /* No need to set mapping for initrd, it will be handled in VO. */ + + /* Avoid kernel command line. */ + cmd_line = (u64)boot_params->ext_cmd_line_ptr << 32; + cmd_line |= boot_params->hdr.cmd_line_ptr; + /* Calculate size of cmd_line. */ + ptr = (char *)(unsigned long)cmd_line; + for (cmd_line_size = 0; ptr[cmd_line_size++]; ) + ; + mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line; + mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size; + add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start, + mem_avoid[MEM_AVOID_CMDLINE].size); + + /* Avoid boot parameters. */ + mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params; + mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params); + add_identity_map(mem_avoid[MEM_AVOID_BOOTPARAMS].start, + mem_avoid[MEM_AVOID_BOOTPARAMS].size); + + /* We don't need to set a mapping for setup_data. */ + +#ifdef CONFIG_X86_VERBOSE_BOOTUP + /* Make sure video RAM can be used. */ + add_identity_map(0, PMD_SIZE); +#endif +} + +/* + * Does this memory vector overlap a known avoided area? If so, record the + * overlap region with the lowest address. + */ +static bool mem_avoid_overlap(struct mem_vector *img, + struct mem_vector *overlap) +{ + int i; + struct setup_data *ptr; + unsigned long earliest = img->start + img->size; + bool is_overlapping = false; + + for (i = 0; i < MEM_AVOID_MAX; i++) { + if (mem_overlaps(img, &mem_avoid[i]) && + mem_avoid[i].start < earliest) { + *overlap = mem_avoid[i]; + is_overlapping = true; + } + } + + /* Avoid all entries in the setup_data linked list. */ + ptr = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data; + while (ptr) { + struct mem_vector avoid; + + avoid.start = (unsigned long)ptr; + avoid.size = sizeof(*ptr) + ptr->len; + + if (mem_overlaps(img, &avoid) && (avoid.start < earliest)) { + *overlap = avoid; + is_overlapping = true; + } + + ptr = (struct setup_data *)(unsigned long)ptr->next; + } + + return is_overlapping; +} + +static unsigned long slots[KERNEL_IMAGE_SIZE / CONFIG_PHYSICAL_ALIGN]; + +struct slot_area { + unsigned long addr; + int num; +}; + +#define MAX_SLOT_AREA 100 + +static struct slot_area slot_areas[MAX_SLOT_AREA]; + +static unsigned long slot_max; + +static unsigned long slot_area_index; + +static void store_slot_info(struct mem_vector *region, unsigned long image_size) +{ + struct slot_area slot_area; + + if (slot_area_index == MAX_SLOT_AREA) + return; + + slot_area.addr = region->start; + slot_area.num = (region->size - image_size) / + CONFIG_PHYSICAL_ALIGN + 1; + + if (slot_area.num > 0) { + slot_areas[slot_area_index++] = slot_area; + slot_max += slot_area.num; + } +} + +static void slots_append(unsigned long addr) +{ + /* Overflowing the slots list should be impossible. */ + if (slot_max >= KERNEL_IMAGE_SIZE / CONFIG_PHYSICAL_ALIGN) + return; + + slots[slot_max++] = addr; +} + +static unsigned long slots_fetch_random(void) +{ + /* Handle case of no slots stored. */ + if (slot_max == 0) + return 0; + + return slots[get_random_long("Physical") % slot_max]; +} + +static void process_e820_entry(struct e820entry *entry, + unsigned long minimum, + unsigned long image_size) +{ + struct mem_vector region, img, overlap; + + /* Skip non-RAM entries. */ + if (entry->type != E820_RAM) + return; + + /* Ignore entries entirely above our maximum. */ + if (entry->addr >= KERNEL_IMAGE_SIZE) + return; + + /* Ignore entries entirely below our minimum. */ + if (entry->addr + entry->size < minimum) + return; + + region.start = entry->addr; + region.size = entry->size; + + /* Potentially raise address to minimum location. */ + if (region.start < minimum) + region.start = minimum; + + /* Potentially raise address to meet alignment requirements. */ + region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN); + + /* Did we raise the address above the bounds of this e820 region? */ + if (region.start > entry->addr + entry->size) + return; + + /* Reduce size by any delta from the original address. */ + region.size -= region.start - entry->addr; + + /* Reduce maximum size to fit end of image within maximum limit. */ + if (region.start + region.size > KERNEL_IMAGE_SIZE) + region.size = KERNEL_IMAGE_SIZE - region.start; + + /* Walk each aligned slot and check for avoided areas. */ + for (img.start = region.start, img.size = image_size ; + mem_contains(®ion, &img) ; + img.start += CONFIG_PHYSICAL_ALIGN) { + if (mem_avoid_overlap(&img, &overlap)) + continue; + slots_append(img.start); + } +} + +static unsigned long find_random_phys_addr(unsigned long minimum, + unsigned long image_size) +{ + int i; + unsigned long addr; + + /* Make sure minimum is aligned. */ + minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); + + /* Verify potential e820 positions, appending to slots list. */ + for (i = 0; i < boot_params->e820_entries; i++) { + process_e820_entry(&boot_params->e820_map[i], minimum, + image_size); + } + + return slots_fetch_random(); +} + +static unsigned long find_random_virt_addr(unsigned long minimum, + unsigned long image_size) +{ + unsigned long slots, random_addr; + + /* Make sure minimum is aligned. */ + minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); + /* Align image_size for easy slot calculations. */ + image_size = ALIGN(image_size, CONFIG_PHYSICAL_ALIGN); + + /* + * There are how many CONFIG_PHYSICAL_ALIGN-sized slots + * that can hold image_size within the range of minimum to + * KERNEL_IMAGE_SIZE? + */ + slots = (KERNEL_IMAGE_SIZE - minimum - image_size) / + CONFIG_PHYSICAL_ALIGN + 1; + + random_addr = get_random_long("Virtual") % slots; + + return random_addr * CONFIG_PHYSICAL_ALIGN + minimum; +} + +/* + * Since this function examines addresses much more numerically, + * it takes the input and output pointers as 'unsigned long'. + */ +unsigned char *choose_random_location(unsigned long input, + unsigned long input_size, + unsigned long output, + unsigned long output_size) +{ + unsigned long choice = output; + unsigned long random_addr; + +#ifdef CONFIG_HIBERNATION + if (!cmdline_find_option_bool("kaslr")) { + warn("KASLR disabled: 'kaslr' not on cmdline (hibernation selected)."); + goto out; + } +#else + if (cmdline_find_option_bool("nokaslr")) { + warn("KASLR disabled: 'nokaslr' on cmdline."); + goto out; + } +#endif + + boot_params->hdr.loadflags |= KASLR_FLAG; + + /* Record the various known unsafe memory ranges. */ + mem_avoid_init(input, input_size, output); + + /* Walk e820 and find a random address. */ + random_addr = find_random_phys_addr(output, output_size); + if (!random_addr) { + warn("KASLR disabled: could not find suitable E820 region!"); + goto out; + } + + /* Always enforce the minimum. */ + if (random_addr < choice) + goto out; + + choice = random_addr; + + add_identity_map(choice, output_size); + + /* This actually loads the identity pagetable on x86_64. */ + finalize_identity_maps(); +out: + return (unsigned char *)choice; +} diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 79dac17..f14db4e 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -1,8 +1,10 @@ /* * misc.c * - * This is a collection of several routines from gzip-1.0.3 - * adapted for Linux. + * This is a collection of several routines used to extract the kernel + * which includes KASLR relocation, decompression, ELF parsing, and + * relocation processing. Additionally included are the screen and serial + * output functions and related debugging support functions. * * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994 * puts by Nick Holloway 1993, better puts by Martin Mares 1995 @@ -10,111 +12,37 @@ */ #include "misc.h" +#include "error.h" #include "../string.h" - -/* WARNING!! - * This code is compiled with -fPIC and it is relocated dynamically - * at run time, but no relocation processing is performed. - * This means that it is not safe to place pointers in static structures. - */ +#include "../voffset.h" /* - * Getting to provable safe in place decompression is hard. - * Worst case behaviours need to be analyzed. - * Background information: - * - * The file layout is: - * magic[2] - * method[1] - * flags[1] - * timestamp[4] - * extraflags[1] - * os[1] - * compressed data blocks[N] - * crc[4] orig_len[4] - * - * resulting in 18 bytes of non compressed data overhead. - * - * Files divided into blocks - * 1 bit (last block flag) - * 2 bits (block type) - * - * 1 block occurs every 32K -1 bytes or when there 50% compression - * has been achieved. The smallest block type encoding is always used. - * - * stored: - * 32 bits length in bytes. - * - * fixed: - * magic fixed tree. - * symbols. - * - * dynamic: - * dynamic tree encoding. - * symbols. - * - * - * The buffer for decompression in place is the length of the - * uncompressed data, plus a small amount extra to keep the algorithm safe. - * The compressed data is placed at the end of the buffer. The output - * pointer is placed at the start of the buffer and the input pointer - * is placed where the compressed data starts. Problems will occur - * when the output pointer overruns the input pointer. - * - * The output pointer can only overrun the input pointer if the input - * pointer is moving faster than the output pointer. A condition only - * triggered by data whose compressed form is larger than the uncompressed - * form. - * - * The worst case at the block level is a growth of the compressed data - * of 5 bytes per 32767 bytes. - * - * The worst case internal to a compressed block is very hard to figure. - * The worst case can at least be boundined by having one bit that represents - * 32764 bytes and then all of the rest of the bytes representing the very - * very last byte. - * - * All of which is enough to compute an amount of extra data that is required - * to be safe. To avoid problems at the block level allocating 5 extra bytes - * per 32767 bytes of data is sufficient. To avoind problems internal to a - * block adding an extra 32767 bytes (the worst case uncompressed block size) - * is sufficient, to ensure that in the worst case the decompressed data for - * block will stop the byte before the compressed data for a block begins. - * To avoid problems with the compressed data's meta information an extra 18 - * bytes are needed. Leading to the formula: - * - * extra_bytes = (uncompressed_size >> 12) + 32768 + 18 + decompressor_size. - * - * Adding 8 bytes per 32K is a bit excessive but much easier to calculate. - * Adding 32768 instead of 32767 just makes for round numbers. - * Adding the decompressor_size is necessary as it musht live after all - * of the data as well. Last I measured the decompressor is about 14K. - * 10K of actual data and 4K of bss. - * + * WARNING!! + * This code is compiled with -fPIC and it is relocated dynamically at + * run time, but no relocation processing is performed. This means that + * it is not safe to place pointers in static structures. */ -/* - * gzip declarations - */ +/* Macros used by the included decompressor code below. */ #define STATIC static -#undef memcpy - /* - * Use a normal definition of memset() from string.c. There are already + * Use normal definitions of mem*() from string.c. There are already * included header files which expect a definition of memset() and by * the time we define memset macro, it is too late. */ +#undef memcpy #undef memset #define memzero(s, n) memset((s), 0, (n)) +#define memmove memmove - -static void error(char *m); +/* Functions used by the included decompressor code below. */ +void *memmove(void *dest, const void *src, size_t n); /* * This is set up by the setup-routine at boot-time */ -struct boot_params *real_mode; /* Pointer to real-mode data */ +struct boot_params *boot_params; memptr free_mem_ptr; memptr free_mem_end_ptr; @@ -146,12 +74,16 @@ static int lines, cols; #ifdef CONFIG_KERNEL_LZ4 #include "../../../../lib/decompress_unlz4.c" #endif +/* + * NOTE: When adding a new decompressor, please update the analysis in + * ../header.S. + */ static void scroll(void) { int i; - memcpy(vidmem, vidmem + cols * 2, (lines - 1) * cols * 2); + memmove(vidmem, vidmem + cols * 2, (lines - 1) * cols * 2); for (i = (lines - 1) * cols * 2; i < lines * cols * 2; i += 2) vidmem[i] = ' '; } @@ -184,12 +116,12 @@ void __putstr(const char *s) } } - if (real_mode->screen_info.orig_video_mode == 0 && + if (boot_params->screen_info.orig_video_mode == 0 && lines == 0 && cols == 0) return; - x = real_mode->screen_info.orig_x; - y = real_mode->screen_info.orig_y; + x = boot_params->screen_info.orig_x; + y = boot_params->screen_info.orig_y; while ((c = *s++) != '\0') { if (c == '\n') { @@ -210,8 +142,8 @@ void __putstr(const char *s) } } - real_mode->screen_info.orig_x = x; - real_mode->screen_info.orig_y = y; + boot_params->screen_info.orig_x = x; + boot_params->screen_info.orig_y = y; pos = (x + cols * y) * 2; /* Update cursor position */ outb(14, vidport); @@ -237,23 +169,13 @@ void __puthex(unsigned long value) } } -static void error(char *x) -{ - error_putstr("\n\n"); - error_putstr(x); - error_putstr("\n\n -- System halted"); - - while (1) - asm("hlt"); -} - #if CONFIG_X86_NEED_RELOCS static void handle_relocations(void *output, unsigned long output_len) { int *reloc; unsigned long delta, map, ptr; unsigned long min_addr = (unsigned long)output; - unsigned long max_addr = min_addr + output_len; + unsigned long max_addr = min_addr + (VO___bss_start - VO__text); /* * Calculate the delta between where vmlinux was linked to load @@ -295,7 +217,7 @@ static void handle_relocations(void *output, unsigned long output_len) * So we work backwards from the end of the decompressed image. */ for (reloc = output + output_len - sizeof(*reloc); *reloc; reloc--) { - int extended = *reloc; + long extended = *reloc; extended += map; ptr = (unsigned long)extended; @@ -372,9 +294,7 @@ static void parse_elf(void *output) #else dest = (void *)(phdr->p_paddr); #endif - memcpy(dest, - output + phdr->p_offset, - phdr->p_filesz); + memmove(dest, output + phdr->p_offset, phdr->p_filesz); break; default: /* Ignore other PT_* */ break; } @@ -383,23 +303,41 @@ static void parse_elf(void *output) free(phdrs); } -asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, +/* + * The compressed kernel image (ZO), has been moved so that its position + * is against the end of the buffer used to hold the uncompressed kernel + * image (VO) and the execution environment (.bss, .brk), which makes sure + * there is room to do the in-place decompression. (See header.S for the + * calculations.) + * + * |-----compressed kernel image------| + * V V + * 0 extract_offset +INIT_SIZE + * |-----------|---------------|-------------------------|--------| + * | | | | + * VO__text startup_32 of ZO VO__end ZO__end + * ^ ^ + * |-------uncompressed kernel image---------| + * + */ +asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, unsigned char *input_data, unsigned long input_len, unsigned char *output, - unsigned long output_len, - unsigned long run_size) + unsigned long output_len) { + const unsigned long kernel_total_size = VO__end - VO__text; unsigned char *output_orig = output; - real_mode = rmode; + /* Retain x86 boot parameters pointer passed from startup_32/64. */ + boot_params = rmode; - /* Clear it for solely in-kernel use */ - real_mode->hdr.loadflags &= ~KASLR_FLAG; + /* Clear flags intended for solely in-kernel use. */ + boot_params->hdr.loadflags &= ~KASLR_FLAG; - sanitize_boot_params(real_mode); + sanitize_boot_params(boot_params); - if (real_mode->screen_info.orig_video_mode == 7) { + if (boot_params->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; vidport = 0x3b4; } else { @@ -407,11 +345,11 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, vidport = 0x3d4; } - lines = real_mode->screen_info.orig_video_lines; - cols = real_mode->screen_info.orig_video_cols; + lines = boot_params->screen_info.orig_video_lines; + cols = boot_params->screen_info.orig_video_cols; console_init(); - debug_putstr("early console in decompress_kernel\n"); + debug_putstr("early console in extract_kernel\n"); free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; @@ -421,16 +359,16 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, debug_putaddr(input_len); debug_putaddr(output); debug_putaddr(output_len); - debug_putaddr(run_size); + debug_putaddr(kernel_total_size); /* * The memory hole needed for the kernel is the larger of either * the entire decompressed kernel plus relocation table, or the * entire decompressed kernel plus .bss and .brk sections. */ - output = choose_kernel_location(real_mode, input_data, input_len, output, - output_len > run_size ? output_len - : run_size); + output = choose_random_location((unsigned long)input_data, input_len, + (unsigned long)output, + max(output_len, kernel_total_size)); /* Validate memory location choices. */ if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1)) diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 3783dc3..b6fec1f 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -32,7 +32,7 @@ /* misc.c */ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; -extern struct boot_params *real_mode; /* Pointer to real-mode data */ +extern struct boot_params *boot_params; void __putstr(const char *s); void __puthex(unsigned long value); #define error_putstr(__x) __putstr(__x) @@ -66,26 +66,35 @@ int cmdline_find_option_bool(const char *option); #if CONFIG_RANDOMIZE_BASE -/* aslr.c */ -unsigned char *choose_kernel_location(struct boot_params *boot_params, - unsigned char *input, +/* kaslr.c */ +unsigned char *choose_random_location(unsigned long input_ptr, unsigned long input_size, - unsigned char *output, + unsigned long output_ptr, unsigned long output_size); /* cpuflags.c */ bool has_cpuflag(int flag); #else static inline -unsigned char *choose_kernel_location(struct boot_params *boot_params, - unsigned char *input, +unsigned char *choose_random_location(unsigned long input_ptr, unsigned long input_size, - unsigned char *output, + unsigned long output_ptr, unsigned long output_size) { - return output; + return (unsigned char *)output_ptr; } #endif +#ifdef CONFIG_X86_64 +void add_identity_map(unsigned long start, unsigned long size); +void finalize_identity_maps(void); +extern unsigned char _pgtable[]; +#else +static inline void add_identity_map(unsigned long start, unsigned long size) +{ } +static inline void finalize_identity_maps(void) +{ } +#endif + #ifdef CONFIG_EARLY_PRINTK /* early_serial_console.c */ extern int early_serial_base; diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index d8222f2..72bad2c 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -18,11 +18,10 @@ * * H. Peter Anvin <hpa@linux.intel.com> * - * ----------------------------------------------------------------------- */ - -/* - * Compute the desired load offset from a compressed program; outputs - * a small assembly wrapper with the appropriate symbols defined. + * ----------------------------------------------------------------------- + * + * Outputs a small assembly wrapper with the appropriate symbols defined. + * */ #include <stdlib.h> @@ -35,14 +34,11 @@ int main(int argc, char *argv[]) { uint32_t olen; long ilen; - unsigned long offs; - unsigned long run_size; FILE *f = NULL; int retval = 1; - if (argc < 3) { - fprintf(stderr, "Usage: %s compressed_file run_size\n", - argv[0]); + if (argc < 2) { + fprintf(stderr, "Usage: %s compressed_file\n", argv[0]); goto bail; } @@ -67,29 +63,11 @@ int main(int argc, char *argv[]) ilen = ftell(f); olen = get_unaligned_le32(&olen); - /* - * Now we have the input (compressed) and output (uncompressed) - * sizes, compute the necessary decompression offset... - */ - - offs = (olen > ilen) ? olen - ilen : 0; - offs += olen >> 12; /* Add 8 bytes for each 32K block */ - offs += 64*1024 + 128; /* Add 64K + 128 bytes slack */ - offs = (offs+4095) & ~4095; /* Round to a 4K boundary */ - run_size = atoi(argv[2]); - printf(".section \".rodata..compressed\",\"a\",@progbits\n"); printf(".globl z_input_len\n"); printf("z_input_len = %lu\n", ilen); printf(".globl z_output_len\n"); printf("z_output_len = %lu\n", (unsigned long)olen); - printf(".globl z_extract_offset\n"); - printf("z_extract_offset = 0x%lx\n", offs); - /* z_extract_offset_negative allows simplification of head_32.S */ - printf(".globl z_extract_offset_negative\n"); - printf("z_extract_offset_negative = -0x%lx\n", offs); - printf(".globl z_run_size\n"); - printf("z_run_size = %lu\n", run_size); printf(".globl input_data, input_data_end\n"); printf("input_data:\n"); diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c new file mode 100644 index 0000000..34b95df --- /dev/null +++ b/arch/x86/boot/compressed/pagetable.c @@ -0,0 +1,129 @@ +/* + * This code is used on x86_64 to create page table identity mappings on + * demand by building up a new set of page tables (or appending to the + * existing ones), and then switching over to them when ready. + */ + +/* + * Since we're dealing with identity mappings, physical and virtual + * addresses are the same, so override these defines which are ultimately + * used by the headers in misc.h. + */ +#define __pa(x) ((unsigned long)(x)) +#define __va(x) ((void *)((unsigned long)(x))) + +#include "misc.h" + +/* These actually do the work of building the kernel identity maps. */ +#include <asm/init.h> +#include <asm/pgtable.h> +#include "../../mm/ident_map.c" + +/* Used by pgtable.h asm code to force instruction serialization. */ +unsigned long __force_order; + +/* Used to track our page table allocation area. */ +struct alloc_pgt_data { + unsigned char *pgt_buf; + unsigned long pgt_buf_size; + unsigned long pgt_buf_offset; +}; + +/* + * Allocates space for a page table entry, using struct alloc_pgt_data + * above. Besides the local callers, this is used as the allocation + * callback in mapping_info below. + */ +static void *alloc_pgt_page(void *context) +{ + struct alloc_pgt_data *pages = (struct alloc_pgt_data *)context; + unsigned char *entry; + + /* Validate there is space available for a new page. */ + if (pages->pgt_buf_offset >= pages->pgt_buf_size) { + debug_putstr("out of pgt_buf in " __FILE__ "!?\n"); + debug_putaddr(pages->pgt_buf_offset); + debug_putaddr(pages->pgt_buf_size); + return NULL; + } + + entry = pages->pgt_buf + pages->pgt_buf_offset; + pages->pgt_buf_offset += PAGE_SIZE; + + return entry; +} + +/* Used to track our allocated page tables. */ +static struct alloc_pgt_data pgt_data; + +/* The top level page table entry pointer. */ +static unsigned long level4p; + +/* Locates and clears a region for a new top level page table. */ +static void prepare_level4(void) +{ + /* + * It should be impossible for this not to already be true, + * but since calling this a second time would rewind the other + * counters, let's just make sure this is reset too. + */ + pgt_data.pgt_buf_offset = 0; + + /* + * If we came here via startup_32(), cr3 will be _pgtable already + * and we must append to the existing area instead of entirely + * overwriting it. + */ + level4p = read_cr3(); + if (level4p == (unsigned long)_pgtable) { + debug_putstr("booted via startup_32()\n"); + pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE; + pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE; + memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); + } else { + debug_putstr("booted via startup_64()\n"); + pgt_data.pgt_buf = _pgtable; + pgt_data.pgt_buf_size = BOOT_PGT_SIZE; + memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); + level4p = (unsigned long)alloc_pgt_page(&pgt_data); + } +} + +/* + * Adds the specified range to what will become the new identity mappings. + * Once all ranges have been added, the new mapping is activated by calling + * finalize_identity_maps() below. + */ +void add_identity_map(unsigned long start, unsigned long size) +{ + struct x86_mapping_info mapping_info = { + .alloc_pgt_page = alloc_pgt_page, + .context = &pgt_data, + .pmd_flag = __PAGE_KERNEL_LARGE_EXEC, + }; + unsigned long end = start + size; + + /* Make sure we have a top level page table ready to use. */ + if (!level4p) + prepare_level4(); + + /* Align boundary to 2M. */ + start = round_down(start, PMD_SIZE); + end = round_up(end, PMD_SIZE); + if (start >= end) + return; + + /* Build the mapping. */ + kernel_ident_mapping_init(&mapping_info, (pgd_t *)level4p, + start, end); +} + +/* + * This switches the page tables to the new level4 that has been built + * via calls to add_identity_map() above. If booted via startup_32(), + * this is effectively a no-op. + */ +void finalize_identity_maps(void) +{ + write_cr3(level4p); +} diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c index 00e788b..cea140c 100644 --- a/arch/x86/boot/compressed/string.c +++ b/arch/x86/boot/compressed/string.c @@ -1,7 +1,16 @@ +/* + * This provides an optimized implementation of memcpy, and a simplified + * implementation of memset and memmove. These are used here because the + * standard kernel runtime versions are not yet available and we don't + * trust the gcc built-in implementations as they may do unexpected things + * (e.g. FPU ops) in the minimal decompression stub execution environment. + */ +#include "error.h" + #include "../string.c" #ifdef CONFIG_X86_32 -void *memcpy(void *dest, const void *src, size_t n) +static void *__memcpy(void *dest, const void *src, size_t n) { int d0, d1, d2; asm volatile( @@ -15,7 +24,7 @@ void *memcpy(void *dest, const void *src, size_t n) return dest; } #else -void *memcpy(void *dest, const void *src, size_t n) +static void *__memcpy(void *dest, const void *src, size_t n) { long d0, d1, d2; asm volatile( @@ -39,3 +48,27 @@ void *memset(void *s, int c, size_t n) ss[i] = c; return s; } + +void *memmove(void *dest, const void *src, size_t n) +{ + unsigned char *d = dest; + const unsigned char *s = src; + + if (d <= s || d - s >= n) + return __memcpy(dest, src, n); + + while (n-- > 0) + d[n] = s[n]; + + return dest; +} + +/* Detect and warn about potential overlaps, but handle them with memmove. */ +void *memcpy(void *dest, const void *src, size_t n) +{ + if (dest > src && dest - src < n) { + warn("Avoiding potentially unsafe overlapping memcpy()!"); + return memmove(dest, src, n); + } + return __memcpy(dest, src, n); +} diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 34d047c..e24e0a0 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -70,5 +70,6 @@ SECTIONS _epgtable = . ; } #endif + . = ALIGN(PAGE_SIZE); /* keep ZO size page aligned */ _end = .; } diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c index 45a0768..f0b8d6d 100644 --- a/arch/x86/boot/early_serial_console.c +++ b/arch/x86/boot/early_serial_console.c @@ -1,3 +1,7 @@ +/* + * Serial port routines for use during early boot reporting. This code is + * included from both the compressed kernel and the regular kernel. + */ #include "boot.h" #define DEFAULT_SERIAL_PORT 0x3f8 /* ttyS0 */ diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 6236b9e..3dd5be3 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -440,13 +440,116 @@ setup_data: .quad 0 # 64-bit physical pointer to pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr -#define ZO_INIT_SIZE (ZO__end - ZO_startup_32 + ZO_z_extract_offset) +# +# Getting to provably safe in-place decompression is hard. Worst case +# behaviours need to be analyzed. Here let's take the decompression of +# a gzip-compressed kernel as example, to illustrate it: +# +# The file layout of gzip compressed kernel is: +# +# magic[2] +# method[1] +# flags[1] +# timestamp[4] +# extraflags[1] +# os[1] +# compressed data blocks[N] +# crc[4] orig_len[4] +# +# ... resulting in +18 bytes overhead of uncompressed data. +# +# (For more information, please refer to RFC 1951 and RFC 1952.) +# +# Files divided into blocks +# 1 bit (last block flag) +# 2 bits (block type) +# +# 1 block occurs every 32K -1 bytes or when there 50% compression +# has been achieved. The smallest block type encoding is always used. +# +# stored: +# 32 bits length in bytes. +# +# fixed: +# magic fixed tree. +# symbols. +# +# dynamic: +# dynamic tree encoding. +# symbols. +# +# +# The buffer for decompression in place is the length of the uncompressed +# data, plus a small amount extra to keep the algorithm safe. The +# compressed data is placed at the end of the buffer. The output pointer +# is placed at the start of the buffer and the input pointer is placed +# where the compressed data starts. Problems will occur when the output +# pointer overruns the input pointer. +# +# The output pointer can only overrun the input pointer if the input +# pointer is moving faster than the output pointer. A condition only +# triggered by data whose compressed form is larger than the uncompressed +# form. +# +# The worst case at the block level is a growth of the compressed data +# of 5 bytes per 32767 bytes. +# +# The worst case internal to a compressed block is very hard to figure. +# The worst case can at least be bounded by having one bit that represents +# 32764 bytes and then all of the rest of the bytes representing the very +# very last byte. +# +# All of which is enough to compute an amount of extra data that is required +# to be safe. To avoid problems at the block level allocating 5 extra bytes +# per 32767 bytes of data is sufficient. To avoid problems internal to a +# block adding an extra 32767 bytes (the worst case uncompressed block size) +# is sufficient, to ensure that in the worst case the decompressed data for +# block will stop the byte before the compressed data for a block begins. +# To avoid problems with the compressed data's meta information an extra 18 +# bytes are needed. Leading to the formula: +# +# extra_bytes = (uncompressed_size >> 12) + 32768 + 18 +# +# Adding 8 bytes per 32K is a bit excessive but much easier to calculate. +# Adding 32768 instead of 32767 just makes for round numbers. +# +# Above analysis is for decompressing gzip compressed kernel only. Up to +# now 6 different decompressor are supported all together. And among them +# xz stores data in chunks and has maximum chunk of 64K. Hence safety +# margin should be updated to cover all decompressors so that we don't +# need to deal with each of them separately. Please check +# the description in lib/decompressor_xxx.c for specific information. +# +# extra_bytes = (uncompressed_size >> 12) + 65536 + 128 + +#define ZO_z_extra_bytes ((ZO_z_output_len >> 12) + 65536 + 128) +#if ZO_z_output_len > ZO_z_input_len +# define ZO_z_extract_offset (ZO_z_output_len + ZO_z_extra_bytes - \ + ZO_z_input_len) +#else +# define ZO_z_extract_offset ZO_z_extra_bytes +#endif + +/* + * The extract_offset has to be bigger than ZO head section. Otherwise when + * the head code is running to move ZO to the end of the buffer, it will + * overwrite the head code itself. + */ +#if (ZO__ehead - ZO_startup_32) > ZO_z_extract_offset +# define ZO_z_min_extract_offset ((ZO__ehead - ZO_startup_32 + 4095) & ~4095) +#else +# define ZO_z_min_extract_offset ((ZO_z_extract_offset + 4095) & ~4095) +#endif + +#define ZO_INIT_SIZE (ZO__end - ZO_startup_32 + ZO_z_min_extract_offset) + #define VO_INIT_SIZE (VO__end - VO__text) #if ZO_INIT_SIZE > VO_INIT_SIZE -#define INIT_SIZE ZO_INIT_SIZE +# define INIT_SIZE ZO_INIT_SIZE #else -#define INIT_SIZE VO_INIT_SIZE +# define INIT_SIZE VO_INIT_SIZE #endif + init_size: .long INIT_SIZE # kernel initialization size handover_offset: .long 0 # Filled in by build.c diff --git a/arch/x86/configs/kvm_guest.config b/arch/x86/configs/kvm_guest.config index f9affcc..9906505 100644 --- a/arch/x86/configs/kvm_guest.config +++ b/arch/x86/configs/kvm_guest.config @@ -26,3 +26,6 @@ CONFIG_VIRTIO_NET=y CONFIG_9P_FS=y CONFIG_NET_9P=y CONFIG_NET_9P_VIRTIO=y +CONFIG_SCSI_LOWLEVEL=y +CONFIG_SCSI_VIRTIO=y +CONFIG_VIRTIO_INPUT=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 4f404a6..0c8d796 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -173,6 +173,7 @@ CONFIG_TIGON3=y CONFIG_NET_TULIP=y CONFIG_E100=y CONFIG_E1000=y +CONFIG_E1000E=y CONFIG_SKY2=y CONFIG_FORCEDETH=y CONFIG_8139TOO=y diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 064c7e2..5b7fa14 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1477,7 +1477,7 @@ static int __init aesni_init(void) } aesni_ctr_enc_tfm = aesni_ctr_enc; #ifdef CONFIG_AS_AVX - if (cpu_has_avx) { + if (boot_cpu_has(X86_FEATURE_AVX)) { /* optimize performance of ctr mode encryption transform */ aesni_ctr_enc_tfm = aesni_ctr_enc_avx_tfm; pr_info("AES CTR mode by8 optimization enabled\n"); diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index d844569..60907c1 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -562,7 +562,10 @@ static int __init camellia_aesni_init(void) { const char *feature_name; - if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { + if (!boot_cpu_has(X86_FEATURE_AVX) || + !boot_cpu_has(X86_FEATURE_AVX2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE)) { pr_info("AVX2 or AES-NI instructions are not detected.\n"); return -ENODEV; } diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 93d8f29..d96429d 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -554,7 +554,9 @@ static int __init camellia_aesni_init(void) { const char *feature_name; - if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { + if (!boot_cpu_has(X86_FEATURE_AVX) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE)) { pr_info("AVX or AES-NI instructions are not detected.\n"); return -ENODEV; } diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c index 8baaff5..2d5c2e0b 100644 --- a/arch/x86/crypto/chacha20_glue.c +++ b/arch/x86/crypto/chacha20_glue.c @@ -129,7 +129,8 @@ static int __init chacha20_simd_mod_init(void) return -ENODEV; #ifdef CONFIG_AS_AVX2 - chacha20_use_avx2 = cpu_has_avx && cpu_has_avx2 && + chacha20_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) && + boot_cpu_has(X86_FEATURE_AVX2) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); #endif return crypto_register_alg(&alg); diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 4264a3d..e32142b 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -179,11 +179,12 @@ static struct shash_alg alg = { static int __init poly1305_simd_mod_init(void) { - if (!cpu_has_xmm2) + if (!boot_cpu_has(X86_FEATURE_XMM2)) return -ENODEV; #ifdef CONFIG_AS_AVX2 - poly1305_use_avx2 = cpu_has_avx && cpu_has_avx2 && + poly1305_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) && + boot_cpu_has(X86_FEATURE_AVX2) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); alg.descsize = sizeof(struct poly1305_simd_desc_ctx); if (poly1305_use_avx2) diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index 6d19834..870f6d8 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -538,7 +538,7 @@ static int __init init(void) { const char *feature_name; - if (!cpu_has_avx2 || !cpu_has_osxsave) { + if (!boot_cpu_has(X86_FEATURE_AVX2) || !boot_cpu_has(X86_FEATURE_OSXSAVE)) { pr_info("AVX2 instructions are not detected.\n"); return -ENODEV; } diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c index 8943407..644f97a 100644 --- a/arch/x86/crypto/serpent_sse2_glue.c +++ b/arch/x86/crypto/serpent_sse2_glue.c @@ -600,7 +600,7 @@ static struct crypto_alg serpent_algs[10] = { { static int __init serpent_sse2_init(void) { - if (!cpu_has_xmm2) { + if (!boot_cpu_has(X86_FEATURE_XMM2)) { printk(KERN_INFO "SSE2 instructions are not detected.\n"); return -ENODEV; } diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c index 081255c..9c5af33 100644 --- a/arch/x86/crypto/sha-mb/sha1_mb.c +++ b/arch/x86/crypto/sha-mb/sha1_mb.c @@ -102,14 +102,14 @@ static asmlinkage struct job_sha1* (*sha1_job_mgr_submit)(struct sha1_mb_mgr *st static asmlinkage struct job_sha1* (*sha1_job_mgr_flush)(struct sha1_mb_mgr *state); static asmlinkage struct job_sha1* (*sha1_job_mgr_get_comp_job)(struct sha1_mb_mgr *state); -inline void sha1_init_digest(uint32_t *digest) +static inline void sha1_init_digest(uint32_t *digest) { static const uint32_t initial_digest[SHA1_DIGEST_LENGTH] = {SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 }; memcpy(digest, initial_digest, sizeof(initial_digest)); } -inline uint32_t sha1_pad(uint8_t padblock[SHA1_BLOCK_SIZE * 2], +static inline uint32_t sha1_pad(uint8_t padblock[SHA1_BLOCK_SIZE * 2], uint32_t total_len) { uint32_t i = total_len & (SHA1_BLOCK_SIZE - 1); diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index dd14616..1024e37 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -166,7 +166,7 @@ static struct shash_alg sha1_avx_alg = { static bool avx_usable(void) { if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { - if (cpu_has_avx) + if (boot_cpu_has(X86_FEATURE_AVX)) pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index 5f4d608..3ae0f43 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -201,7 +201,7 @@ static struct shash_alg sha256_avx_algs[] = { { static bool avx_usable(void) { if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { - if (cpu_has_avx) + if (boot_cpu_has(X86_FEATURE_AVX)) pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 34e5083..0b17c83 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -151,7 +151,7 @@ asmlinkage void sha512_transform_avx(u64 *digest, const char *data, static bool avx_usable(void) { if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { - if (cpu_has_avx) + if (boot_cpu_has(X86_FEATURE_AVX)) pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index e79d93d..ec138e5 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -191,7 +191,7 @@ long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, long syscall_trace_enter(struct pt_regs *regs) { - u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; + u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch); if (phase1_result == 0) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 10868aa..983e5d3 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -207,10 +207,7 @@ ENTRY(ret_from_fork) pushl %eax call schedule_tail - GET_THREAD_INFO(%ebp) popl %eax - pushl $0x0202 # Reset kernel eflags - popfl /* When we fork, we trace the syscall return in the child, too. */ movl %esp, %eax @@ -221,10 +218,7 @@ END(ret_from_fork) ENTRY(ret_from_kernel_thread) pushl %eax call schedule_tail - GET_THREAD_INFO(%ebp) popl %eax - pushl $0x0202 # Reset kernel eflags - popfl movl PT_EBP(%esp), %eax call *PT_EBX(%esp) movl $0, PT_EAX(%esp) @@ -251,7 +245,6 @@ ENDPROC(ret_from_kernel_thread) ret_from_exception: preempt_stop(CLBR_ANY) ret_from_intr: - GET_THREAD_INFO(%ebp) #ifdef CONFIG_VM86 movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS movb PT_CS(%esp), %al diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 858b555..9ee0da1 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -372,9 +372,6 @@ END(ptregs_\func) ENTRY(ret_from_fork) LOCK ; btr $TIF_FORK, TI_flags(%r8) - pushq $0x0002 - popfq /* reset kernel eflags */ - call schedule_tail /* rdi: 'prev' task parameter */ testb $3, CS(%rsp) /* from kernel_thread? */ @@ -781,19 +778,25 @@ ENTRY(native_load_gs_index) pushfq DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) SWAPGS -gs_change: +.Lgs_change: movl %edi, %gs -2: mfence /* workaround */ +2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE SWAPGS popfq ret END(native_load_gs_index) - _ASM_EXTABLE(gs_change, bad_gs) + _ASM_EXTABLE(.Lgs_change, bad_gs) .section .fixup, "ax" /* running with kernelgs */ bad_gs: SWAPGS /* switch back to user gs */ +.macro ZAP_GS + /* This can't be a string because the preprocessor needs to see it. */ + movl $__USER_DS, %eax + movl %eax, %gs +.endm + ALTERNATIVE "", "ZAP_GS", X86_BUG_NULL_SEG xorl %eax, %eax movl %eax, %gs jmp 2b @@ -1019,13 +1022,13 @@ ENTRY(error_entry) movl %ecx, %eax /* zero extend */ cmpq %rax, RIP+8(%rsp) je .Lbstep_iret - cmpq $gs_change, RIP+8(%rsp) + cmpq $.Lgs_change, RIP+8(%rsp) jne .Lerror_entry_done /* - * hack: gs_change can fail with user gsbase. If this happens, fix up + * hack: .Lgs_change can fail with user gsbase. If this happens, fix up * gsbase and proceed. We'll fix up the exception and land in - * gs_change's error handler with kernel gsbase. + * .Lgs_change's error handler with kernel gsbase. */ jmp .Lerror_entry_from_usermode_swapgs diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 847f2f0..e1721da 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -72,24 +72,23 @@ ENTRY(entry_SYSENTER_compat) pushfq /* pt_regs->flags (except IF = 0) */ orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */ pushq $__USER32_CS /* pt_regs->cs */ - xorq %r8,%r8 - pushq %r8 /* pt_regs->ip = 0 (placeholder) */ + pushq $0 /* pt_regs->ip = 0 (placeholder) */ pushq %rax /* pt_regs->orig_ax */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 = 0 */ - pushq %r8 /* pt_regs->r9 = 0 */ - pushq %r8 /* pt_regs->r10 = 0 */ - pushq %r8 /* pt_regs->r11 = 0 */ + pushq $0 /* pt_regs->r8 = 0 */ + pushq $0 /* pt_regs->r9 = 0 */ + pushq $0 /* pt_regs->r10 = 0 */ + pushq $0 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ - pushq %r8 /* pt_regs->r12 = 0 */ - pushq %r8 /* pt_regs->r13 = 0 */ - pushq %r8 /* pt_regs->r14 = 0 */ - pushq %r8 /* pt_regs->r15 = 0 */ + pushq $0 /* pt_regs->r12 = 0 */ + pushq $0 /* pt_regs->r13 = 0 */ + pushq $0 /* pt_regs->r14 = 0 */ + pushq $0 /* pt_regs->r15 = 0 */ cld /* @@ -205,17 +204,16 @@ ENTRY(entry_SYSCALL_compat) pushq %rdx /* pt_regs->dx */ pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ - xorq %r8,%r8 - pushq %r8 /* pt_regs->r8 = 0 */ - pushq %r8 /* pt_regs->r9 = 0 */ - pushq %r8 /* pt_regs->r10 = 0 */ - pushq %r8 /* pt_regs->r11 = 0 */ + pushq $0 /* pt_regs->r8 = 0 */ + pushq $0 /* pt_regs->r9 = 0 */ + pushq $0 /* pt_regs->r10 = 0 */ + pushq $0 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ - pushq %r8 /* pt_regs->r12 = 0 */ - pushq %r8 /* pt_regs->r13 = 0 */ - pushq %r8 /* pt_regs->r14 = 0 */ - pushq %r8 /* pt_regs->r15 = 0 */ + pushq $0 /* pt_regs->r12 = 0 */ + pushq $0 /* pt_regs->r13 = 0 */ + pushq $0 /* pt_regs->r14 = 0 */ + pushq $0 /* pt_regs->r15 = 0 */ /* * User mode is traced as though IRQs are on, and SYSENTER @@ -316,11 +314,10 @@ ENTRY(entry_INT80_compat) pushq %rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ - xorq %r8,%r8 - pushq %r8 /* pt_regs->r8 = 0 */ - pushq %r8 /* pt_regs->r9 = 0 */ - pushq %r8 /* pt_regs->r10 = 0 */ - pushq %r8 /* pt_regs->r11 = 0 */ + pushq $0 /* pt_regs->r8 = 0 */ + pushq $0 /* pt_regs->r9 = 0 */ + pushq $0 /* pt_regs->r10 = 0 */ + pushq $0 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ pushq %rbp /* pt_regs->rbp */ pushq %r12 /* pt_regs->r12 */ diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index b30dd81..4cddd17 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -384,5 +384,5 @@ 375 i386 membarrier sys_membarrier 376 i386 mlock2 sys_mlock2 377 i386 copy_file_range sys_copy_file_range -378 i386 preadv2 sys_preadv2 -379 i386 pwritev2 sys_pwritev2 +378 i386 preadv2 sys_preadv2 compat_sys_preadv2 +379 i386 pwritev2 sys_pwritev2 compat_sys_pwritev2 diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index cac6d17..555263e 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -374,3 +374,5 @@ 543 x32 io_setup compat_sys_io_setup 544 x32 io_submit compat_sys_io_submit 545 x32 execveat compat_sys_execveat/ptregs +534 x32 preadv2 compat_sys_preadv2 +535 x32 pwritev2 compat_sys_pwritev2 diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 03c3eb7..2f02d23 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -13,7 +13,6 @@ #include <uapi/linux/time.h> #include <asm/vgtod.h> -#include <asm/hpet.h> #include <asm/vvar.h> #include <asm/unistd.h> #include <asm/msr.h> @@ -28,16 +27,6 @@ extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts); extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); extern time_t __vdso_time(time_t *t); -#ifdef CONFIG_HPET_TIMER -extern u8 hpet_page - __attribute__((visibility("hidden"))); - -static notrace cycle_t vread_hpet(void) -{ - return *(const volatile u32 *)(&hpet_page + HPET_COUNTER); -} -#endif - #ifdef CONFIG_PARAVIRT_CLOCK extern u8 pvclock_page __attribute__((visibility("hidden"))); @@ -195,10 +184,6 @@ notrace static inline u64 vgetsns(int *mode) if (gtod->vclock_mode == VCLOCK_TSC) cycles = vread_tsc(); -#ifdef CONFIG_HPET_TIMER - else if (gtod->vclock_mode == VCLOCK_HPET) - cycles = vread_hpet(); -#endif #ifdef CONFIG_PARAVIRT_CLOCK else if (gtod->vclock_mode == VCLOCK_PVCLOCK) cycles = vread_pvclock(mode); diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index 4158acc..a708aa9 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -25,7 +25,7 @@ SECTIONS * segment. */ - vvar_start = . - 3 * PAGE_SIZE; + vvar_start = . - 2 * PAGE_SIZE; vvar_page = vvar_start; /* Place all vvars at the offsets in asm/vvar.h. */ @@ -35,8 +35,7 @@ SECTIONS #undef __VVAR_KERNEL_LDS #undef EMIT_VVAR - hpet_page = vvar_start + PAGE_SIZE; - pvclock_page = vvar_start + 2 * PAGE_SIZE; + pvclock_page = vvar_start + PAGE_SIZE; . = SIZEOF_HEADERS; diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 10f7045..b3cf813 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -18,7 +18,6 @@ #include <asm/vdso.h> #include <asm/vvar.h> #include <asm/page.h> -#include <asm/hpet.h> #include <asm/desc.h> #include <asm/cpufeature.h> @@ -129,16 +128,6 @@ static int vvar_fault(const struct vm_special_mapping *sm, if (sym_offset == image->sym_vvar_page) { ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, __pa_symbol(&__vvar_page) >> PAGE_SHIFT); - } else if (sym_offset == image->sym_hpet_page) { -#ifdef CONFIG_HPET_TIMER - if (hpet_address && vclock_was_used(VCLOCK_HPET)) { - ret = vm_insert_pfn_prot( - vma, - (unsigned long)vmf->virtual_address, - hpet_address >> PAGE_SHIFT, - pgprot_noncached(PAGE_READONLY)); - } -#endif } else if (sym_offset == image->sym_pvclock_page) { struct pvclock_vsyscall_time_info *pvti = pvclock_pvti_cpu0_va(); diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig new file mode 100644 index 0000000..98397db --- /dev/null +++ b/arch/x86/events/Kconfig @@ -0,0 +1,36 @@ +menu "Performance monitoring" + +config PERF_EVENTS_INTEL_UNCORE + tristate "Intel uncore performance events" + depends on PERF_EVENTS && CPU_SUP_INTEL && PCI + default y + ---help--- + Include support for Intel uncore performance events. These are + available on NehalemEX and more modern processors. + +config PERF_EVENTS_INTEL_RAPL + tristate "Intel rapl performance events" + depends on PERF_EVENTS && CPU_SUP_INTEL && PCI + default y + ---help--- + Include support for Intel rapl performance events for power + monitoring on modern processors. + +config PERF_EVENTS_INTEL_CSTATE + tristate "Intel cstate performance events" + depends on PERF_EVENTS && CPU_SUP_INTEL && PCI + default y + ---help--- + Include support for Intel cstate performance events for power + monitoring on modern processors. + +config PERF_EVENTS_AMD_POWER + depends on PERF_EVENTS && CPU_SUP_AMD + tristate "AMD Processor Power Reporting Mechanism" + ---help--- + Provide power reporting mechanism support for AMD processors. + Currently, it leverages X86_FEATURE_ACC_POWER + (CPUID Fn8000_0007_EDX[12]) interface to calculate the + average power consumption on Family 15h processors. + +endmenu diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile index f59618a..1d392c3 100644 --- a/arch/x86/events/Makefile +++ b/arch/x86/events/Makefile @@ -6,9 +6,6 @@ obj-$(CONFIG_X86_LOCAL_APIC) += amd/ibs.o msr.o ifdef CONFIG_AMD_IOMMU obj-$(CONFIG_CPU_SUP_AMD) += amd/iommu.o endif -obj-$(CONFIG_CPU_SUP_INTEL) += intel/core.o intel/bts.o intel/cqm.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel/cstate.o intel/ds.o intel/knc.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel/lbr.o intel/p4.o intel/p6.o intel/pt.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel/rapl.o msr.o -obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel/uncore.o intel/uncore_nhmex.o -obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel/uncore_snb.o intel/uncore_snbep.o + +obj-$(CONFIG_CPU_SUP_INTEL) += msr.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel/ diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c index 40625ca..6011a57 100644 --- a/arch/x86/events/amd/iommu.c +++ b/arch/x86/events/amd/iommu.c @@ -474,6 +474,7 @@ static __init int _init_perf_amd_iommu( static struct perf_amd_iommu __perf_iommu = { .pmu = { + .task_ctx_nr = perf_invalid_context, .event_init = perf_iommu_event_init, .add = perf_iommu_add, .del = perf_iommu_del, diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 3db9569..98ac573 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -263,6 +263,7 @@ static const struct attribute_group *amd_uncore_attr_groups[] = { }; static struct pmu amd_nb_pmu = { + .task_ctx_nr = perf_invalid_context, .attr_groups = amd_uncore_attr_groups, .name = "amd_nb", .event_init = amd_uncore_event_init, @@ -274,6 +275,7 @@ static struct pmu amd_nb_pmu = { }; static struct pmu amd_l2_pmu = { + .task_ctx_nr = perf_invalid_context, .attr_groups = amd_uncore_attr_groups, .name = "amd_l2", .event_init = amd_uncore_event_init, diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 041e442..73a75aa 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -360,6 +360,9 @@ int x86_add_exclusive(unsigned int what) { int i; + if (x86_pmu.lbr_pt_coexist) + return 0; + if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { mutex_lock(&pmc_reserve_mutex); for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { @@ -380,6 +383,9 @@ fail_unlock: void x86_del_exclusive(unsigned int what) { + if (x86_pmu.lbr_pt_coexist) + return; + atomic_dec(&x86_pmu.lbr_exclusive[what]); atomic_dec(&active_events); } @@ -1518,7 +1524,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) static void __init pmu_check_apic(void) { - if (cpu_has_apic) + if (boot_cpu_has(X86_FEATURE_APIC)) return; x86_pmu.apic = 0; @@ -2177,7 +2183,7 @@ void arch_perf_update_userpage(struct perf_event *event, * cap_user_time_zero doesn't make sense when we're using a different * time base for the records. */ - if (event->clock == &local_clock) { + if (!event->attr.use_clockid) { userpg->cap_user_time_zero = 1; userpg->time_zero = data->cyc2ns_offset; } @@ -2277,7 +2283,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); - while (entry->nr < PERF_MAX_STACK_DEPTH) { + while (entry->nr < sysctl_perf_event_max_stack) { unsigned long bytes; frame.next_frame = 0; frame.return_address = 0; @@ -2337,7 +2343,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) return; pagefault_disable(); - while (entry->nr < PERF_MAX_STACK_DEPTH) { + while (entry->nr < sysctl_perf_event_max_stack) { unsigned long bytes; frame.next_frame = NULL; frame.return_address = 0; diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile new file mode 100644 index 0000000..3660b2c --- /dev/null +++ b/arch/x86/events/intel/Makefile @@ -0,0 +1,9 @@ +obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o cqm.o +obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o +obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl.o +intel-rapl-objs := rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel-uncore.o +intel-uncore-objs := uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o +obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE) += intel-cstate.o +intel-cstate-objs := cstate.o diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index b99dc92..0a6e393 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -171,18 +171,6 @@ static void bts_buffer_pad_out(struct bts_phys *phys, unsigned long head) memset(page_address(phys->page) + index, 0, phys->size - index); } -static bool bts_buffer_is_full(struct bts_buffer *buf, struct bts_ctx *bts) -{ - if (buf->snapshot) - return false; - - if (local_read(&buf->data_size) >= bts->handle.size || - bts->handle.size - local_read(&buf->data_size) < BTS_RECORD_SIZE) - return true; - - return false; -} - static void bts_update(struct bts_ctx *bts) { int cpu = raw_smp_processor_id(); @@ -213,18 +201,15 @@ static void bts_update(struct bts_ctx *bts) } } +static int +bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle); + static void __bts_event_start(struct perf_event *event) { struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); struct bts_buffer *buf = perf_get_aux(&bts->handle); u64 config = 0; - if (!buf || bts_buffer_is_full(buf, bts)) - return; - - event->hw.itrace_started = 1; - event->hw.state = 0; - if (!buf->snapshot) config |= ARCH_PERFMON_EVENTSEL_INT; if (!event->attr.exclude_kernel) @@ -241,16 +226,41 @@ static void __bts_event_start(struct perf_event *event) wmb(); intel_pmu_enable_bts(config); + } static void bts_event_start(struct perf_event *event, int flags) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct bts_buffer *buf; + + buf = perf_aux_output_begin(&bts->handle, event); + if (!buf) + goto fail_stop; + + if (bts_buffer_reset(buf, &bts->handle)) + goto fail_end_stop; + + bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base; + bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum; + bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold; + + event->hw.itrace_started = 1; + event->hw.state = 0; __bts_event_start(event); /* PMI handler: this counter is running and likely generating PMIs */ ACCESS_ONCE(bts->started) = 1; + + return; + +fail_end_stop: + perf_aux_output_end(&bts->handle, 0, false); + +fail_stop: + event->hw.state = PERF_HES_STOPPED; } static void __bts_event_stop(struct perf_event *event) @@ -269,15 +279,32 @@ static void __bts_event_stop(struct perf_event *event) static void bts_event_stop(struct perf_event *event, int flags) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct bts_buffer *buf = perf_get_aux(&bts->handle); /* PMI handler: don't restart this counter */ ACCESS_ONCE(bts->started) = 0; __bts_event_stop(event); - if (flags & PERF_EF_UPDATE) + if (flags & PERF_EF_UPDATE) { bts_update(bts); + + if (buf) { + if (buf->snapshot) + bts->handle.head = + local_xchg(&buf->data_size, + buf->nr_pages << PAGE_SHIFT); + perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), + !!local_xchg(&buf->lost, 0)); + } + + cpuc->ds->bts_index = bts->ds_back.bts_buffer_base; + cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base; + cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum; + cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold; + } } void intel_bts_enable_local(void) @@ -417,34 +444,14 @@ int intel_bts_interrupt(void) static void bts_event_del(struct perf_event *event, int mode) { - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); - struct bts_buffer *buf = perf_get_aux(&bts->handle); - bts_event_stop(event, PERF_EF_UPDATE); - - if (buf) { - if (buf->snapshot) - bts->handle.head = - local_xchg(&buf->data_size, - buf->nr_pages << PAGE_SHIFT); - perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), - !!local_xchg(&buf->lost, 0)); - } - - cpuc->ds->bts_index = bts->ds_back.bts_buffer_base; - cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base; - cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum; - cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold; } static int bts_event_add(struct perf_event *event, int mode) { - struct bts_buffer *buf; struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - int ret = -EBUSY; event->hw.state = PERF_HES_STOPPED; @@ -454,26 +461,10 @@ static int bts_event_add(struct perf_event *event, int mode) if (bts->handle.event) return -EBUSY; - buf = perf_aux_output_begin(&bts->handle, event); - if (!buf) - return -EINVAL; - - ret = bts_buffer_reset(buf, &bts->handle); - if (ret) { - perf_aux_output_end(&bts->handle, 0, false); - return ret; - } - - bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base; - bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum; - bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold; - if (mode & PERF_EF_START) { bts_event_start(event, 0); - if (hwc->state & PERF_HES_STOPPED) { - bts_event_del(event, 0); - return -EBUSY; - } + if (hwc->state & PERF_HES_STOPPED) + return -EINVAL; } return 0; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index aff7988..7c66695 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -1465,6 +1465,140 @@ static __initconst const u64 slm_hw_cache_event_ids }, }; +static struct extra_reg intel_glm_extra_regs[] __read_mostly = { + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x760005ffbfull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x360005ffbfull, RSP_1), + EVENT_EXTRA_END +}; + +#define GLM_DEMAND_DATA_RD BIT_ULL(0) +#define GLM_DEMAND_RFO BIT_ULL(1) +#define GLM_ANY_RESPONSE BIT_ULL(16) +#define GLM_SNP_NONE_OR_MISS BIT_ULL(33) +#define GLM_DEMAND_READ GLM_DEMAND_DATA_RD +#define GLM_DEMAND_WRITE GLM_DEMAND_RFO +#define GLM_DEMAND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO) +#define GLM_LLC_ACCESS GLM_ANY_RESPONSE +#define GLM_SNP_ANY (GLM_SNP_NONE_OR_MISS|SNB_NO_FWD|SNB_HITM) +#define GLM_LLC_MISS (GLM_SNP_ANY|SNB_NON_DRAM) + +static __initconst const u64 glm_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [C(RESULT_MISS)] = 0x0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [C(RESULT_MISS)] = 0x0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0380, /* ICACHE.ACCESSES */ + [C(RESULT_MISS)] = 0x0280, /* ICACHE.MISSES */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */ + [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */ + [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */ + [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [C(RESULT_MISS)] = 0x0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [C(RESULT_MISS)] = 0x0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x00c0, /* INST_RETIRED.ANY_P */ + [C(RESULT_MISS)] = 0x0481, /* ITLB.MISS */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [C(RESULT_MISS)] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + }, +}; + +static __initconst const u64 glm_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = GLM_DEMAND_READ| + GLM_LLC_ACCESS, + [C(RESULT_MISS)] = GLM_DEMAND_READ| + GLM_LLC_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = GLM_DEMAND_WRITE| + GLM_LLC_ACCESS, + [C(RESULT_MISS)] = GLM_DEMAND_WRITE| + GLM_LLC_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = GLM_DEMAND_PREFETCH| + GLM_LLC_ACCESS, + [C(RESULT_MISS)] = GLM_DEMAND_PREFETCH| + GLM_LLC_MISS, + }, + }, +}; + #define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ #define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ #define KNL_MCDRAM_LOCAL BIT_ULL(21) @@ -3447,7 +3581,7 @@ __init int intel_pmu_init(void) memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); - intel_pmu_lbr_init_atom(); + intel_pmu_lbr_init_slm(); x86_pmu.event_constraints = intel_slm_event_constraints; x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; @@ -3456,6 +3590,30 @@ __init int intel_pmu_init(void) pr_cont("Silvermont events, "); break; + case 92: /* 14nm Atom "Goldmont" */ + case 95: /* 14nm Atom "Goldmont Denverton" */ + memcpy(hw_cache_event_ids, glm_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_glm_pebs_event_constraints; + x86_pmu.extra_regs = intel_glm_extra_regs; + /* + * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS + * for precise cycles. + * :pp is identical to :ppp + */ + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + pr_cont("Goldmont events, "); + break; + case 37: /* 32nm Westmere */ case 44: /* 32nm Westmere-EP */ case 47: /* 32nm Westmere-EX */ @@ -3637,6 +3795,8 @@ __init int intel_pmu_init(void) pr_cont("Knights Landing events, "); break; + case 142: /* 14nm Kabylake Mobile */ + case 158: /* 14nm Kabylake Desktop */ case 78: /* 14nm Skylake Mobile */ case 94: /* 14nm Skylake Desktop */ case 85: /* 14nm Skylake Server */ @@ -3706,7 +3866,7 @@ __init int intel_pmu_init(void) c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; } c->idxmsk64 &= - ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); + ~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); c->weight = hweight64(c->idxmsk64); } } diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 7946c42..9ba4e41 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -91,6 +91,8 @@ #include <asm/cpu_device_id.h> #include "../perf_event.h" +MODULE_LICENSE("GPL"); + #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ struct kobj_attribute *attr, \ @@ -106,22 +108,27 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf); +/* Model -> events mapping */ +struct cstate_model { + unsigned long core_events; + unsigned long pkg_events; + unsigned long quirks; +}; + +/* Quirk flags */ +#define SLM_PKG_C6_USE_C7_MSR (1UL << 0) + struct perf_cstate_msr { u64 msr; struct perf_pmu_events_attr *attr; - bool (*test)(int idx); }; /* cstate_core PMU */ - static struct pmu cstate_core_pmu; static bool has_cstate_core; -enum perf_cstate_core_id { - /* - * cstate_core events - */ +enum perf_cstate_core_events { PERF_CSTATE_CORE_C1_RES = 0, PERF_CSTATE_CORE_C3_RES, PERF_CSTATE_CORE_C6_RES, @@ -130,69 +137,16 @@ enum perf_cstate_core_id { PERF_CSTATE_CORE_EVENT_MAX, }; -bool test_core(int idx) -{ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || - boot_cpu_data.x86 != 6) - return false; - - switch (boot_cpu_data.x86_model) { - case 30: /* 45nm Nehalem */ - case 26: /* 45nm Nehalem-EP */ - case 46: /* 45nm Nehalem-EX */ - - case 37: /* 32nm Westmere */ - case 44: /* 32nm Westmere-EP */ - case 47: /* 32nm Westmere-EX */ - if (idx == PERF_CSTATE_CORE_C3_RES || - idx == PERF_CSTATE_CORE_C6_RES) - return true; - break; - case 42: /* 32nm SandyBridge */ - case 45: /* 32nm SandyBridge-E/EN/EP */ - - case 58: /* 22nm IvyBridge */ - case 62: /* 22nm IvyBridge-EP/EX */ - - case 60: /* 22nm Haswell Core */ - case 63: /* 22nm Haswell Server */ - case 69: /* 22nm Haswell ULT */ - case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ - - case 61: /* 14nm Broadwell Core-M */ - case 86: /* 14nm Broadwell Xeon D */ - case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ - case 79: /* 14nm Broadwell Server */ - - case 78: /* 14nm Skylake Mobile */ - case 94: /* 14nm Skylake Desktop */ - if (idx == PERF_CSTATE_CORE_C3_RES || - idx == PERF_CSTATE_CORE_C6_RES || - idx == PERF_CSTATE_CORE_C7_RES) - return true; - break; - case 55: /* 22nm Atom "Silvermont" */ - case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ - case 76: /* 14nm Atom "Airmont" */ - if (idx == PERF_CSTATE_CORE_C1_RES || - idx == PERF_CSTATE_CORE_C6_RES) - return true; - break; - } - - return false; -} - PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00"); PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01"); PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02"); PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03"); static struct perf_cstate_msr core_msr[] = { - [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1, test_core, }, - [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3, test_core, }, - [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6, test_core, }, - [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7, test_core, }, + [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1 }, + [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3 }, + [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6 }, + [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7 }, }; static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = { @@ -234,18 +188,11 @@ static const struct attribute_group *core_attr_groups[] = { NULL, }; -/* cstate_core PMU end */ - - /* cstate_pkg PMU */ - static struct pmu cstate_pkg_pmu; static bool has_cstate_pkg; -enum perf_cstate_pkg_id { - /* - * cstate_pkg events - */ +enum perf_cstate_pkg_events { PERF_CSTATE_PKG_C2_RES = 0, PERF_CSTATE_PKG_C3_RES, PERF_CSTATE_PKG_C6_RES, @@ -257,69 +204,6 @@ enum perf_cstate_pkg_id { PERF_CSTATE_PKG_EVENT_MAX, }; -bool test_pkg(int idx) -{ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || - boot_cpu_data.x86 != 6) - return false; - - switch (boot_cpu_data.x86_model) { - case 30: /* 45nm Nehalem */ - case 26: /* 45nm Nehalem-EP */ - case 46: /* 45nm Nehalem-EX */ - - case 37: /* 32nm Westmere */ - case 44: /* 32nm Westmere-EP */ - case 47: /* 32nm Westmere-EX */ - if (idx == PERF_CSTATE_CORE_C3_RES || - idx == PERF_CSTATE_CORE_C6_RES || - idx == PERF_CSTATE_CORE_C7_RES) - return true; - break; - case 42: /* 32nm SandyBridge */ - case 45: /* 32nm SandyBridge-E/EN/EP */ - - case 58: /* 22nm IvyBridge */ - case 62: /* 22nm IvyBridge-EP/EX */ - - case 60: /* 22nm Haswell Core */ - case 63: /* 22nm Haswell Server */ - case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ - - case 61: /* 14nm Broadwell Core-M */ - case 86: /* 14nm Broadwell Xeon D */ - case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ - case 79: /* 14nm Broadwell Server */ - - case 78: /* 14nm Skylake Mobile */ - case 94: /* 14nm Skylake Desktop */ - if (idx == PERF_CSTATE_PKG_C2_RES || - idx == PERF_CSTATE_PKG_C3_RES || - idx == PERF_CSTATE_PKG_C6_RES || - idx == PERF_CSTATE_PKG_C7_RES) - return true; - break; - case 55: /* 22nm Atom "Silvermont" */ - case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ - case 76: /* 14nm Atom "Airmont" */ - if (idx == PERF_CSTATE_CORE_C6_RES) - return true; - break; - case 69: /* 22nm Haswell ULT */ - if (idx == PERF_CSTATE_PKG_C2_RES || - idx == PERF_CSTATE_PKG_C3_RES || - idx == PERF_CSTATE_PKG_C6_RES || - idx == PERF_CSTATE_PKG_C7_RES || - idx == PERF_CSTATE_PKG_C8_RES || - idx == PERF_CSTATE_PKG_C9_RES || - idx == PERF_CSTATE_PKG_C10_RES) - return true; - break; - } - - return false; -} - PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00"); PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01"); PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02"); @@ -329,13 +213,13 @@ PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05"); PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06"); static struct perf_cstate_msr pkg_msr[] = { - [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2, test_pkg, }, - [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3, test_pkg, }, - [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6, test_pkg, }, - [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7, test_pkg, }, - [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8, test_pkg, }, - [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9, test_pkg, }, - [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10, test_pkg, }, + [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2 }, + [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3 }, + [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6 }, + [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7 }, + [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8 }, + [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9 }, + [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10 }, }; static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = { @@ -366,8 +250,6 @@ static const struct attribute_group *pkg_attr_groups[] = { NULL, }; -/* cstate_pkg PMU end*/ - static ssize_t cstate_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) @@ -385,7 +267,7 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev, static int cstate_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config; - int ret = 0; + int cpu; if (event->attr.type != event->pmu->type) return -ENOENT; @@ -400,26 +282,36 @@ static int cstate_pmu_event_init(struct perf_event *event) event->attr.sample_period) /* no sampling */ return -EINVAL; + if (event->cpu < 0) + return -EINVAL; + if (event->pmu == &cstate_core_pmu) { if (cfg >= PERF_CSTATE_CORE_EVENT_MAX) return -EINVAL; if (!core_msr[cfg].attr) return -EINVAL; event->hw.event_base = core_msr[cfg].msr; + cpu = cpumask_any_and(&cstate_core_cpu_mask, + topology_sibling_cpumask(event->cpu)); } else if (event->pmu == &cstate_pkg_pmu) { if (cfg >= PERF_CSTATE_PKG_EVENT_MAX) return -EINVAL; if (!pkg_msr[cfg].attr) return -EINVAL; event->hw.event_base = pkg_msr[cfg].msr; - } else + cpu = cpumask_any_and(&cstate_pkg_cpu_mask, + topology_core_cpumask(event->cpu)); + } else { return -ENOENT; + } + + if (cpu >= nr_cpu_ids) + return -ENODEV; - /* must be done before validate_group */ + event->cpu = cpu; event->hw.config = cfg; event->hw.idx = -1; - - return ret; + return 0; } static inline u64 cstate_pmu_read_counter(struct perf_event *event) @@ -469,172 +361,91 @@ static int cstate_pmu_event_add(struct perf_event *event, int mode) return 0; } +/* + * Check if exiting cpu is the designated reader. If so migrate the + * events when there is a valid target available + */ static void cstate_cpu_exit(int cpu) { - int i, id, target; + unsigned int target; - /* cpu exit for cstate core */ - if (has_cstate_core) { - id = topology_core_id(cpu); - target = -1; - - for_each_online_cpu(i) { - if (i == cpu) - continue; - if (id == topology_core_id(i)) { - target = i; - break; - } - } - if (cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask) && target >= 0) + if (has_cstate_core && + cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask)) { + + target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu); + /* Migrate events if there is a valid target */ + if (target < nr_cpu_ids) { cpumask_set_cpu(target, &cstate_core_cpu_mask); - WARN_ON(cpumask_empty(&cstate_core_cpu_mask)); - if (target >= 0) perf_pmu_migrate_context(&cstate_core_pmu, cpu, target); + } } - /* cpu exit for cstate pkg */ - if (has_cstate_pkg) { - id = topology_physical_package_id(cpu); - target = -1; - - for_each_online_cpu(i) { - if (i == cpu) - continue; - if (id == topology_physical_package_id(i)) { - target = i; - break; - } - } - if (cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask) && target >= 0) + if (has_cstate_pkg && + cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) { + + target = cpumask_any_but(topology_core_cpumask(cpu), cpu); + /* Migrate events if there is a valid target */ + if (target < nr_cpu_ids) { cpumask_set_cpu(target, &cstate_pkg_cpu_mask); - WARN_ON(cpumask_empty(&cstate_pkg_cpu_mask)); - if (target >= 0) perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target); + } } } static void cstate_cpu_init(int cpu) { - int i, id; + unsigned int target; - /* cpu init for cstate core */ - if (has_cstate_core) { - id = topology_core_id(cpu); - for_each_cpu(i, &cstate_core_cpu_mask) { - if (id == topology_core_id(i)) - break; - } - if (i >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_core_cpu_mask); - } + /* + * If this is the first online thread of that core, set it in + * the core cpu mask as the designated reader. + */ + target = cpumask_any_and(&cstate_core_cpu_mask, + topology_sibling_cpumask(cpu)); - /* cpu init for cstate pkg */ - if (has_cstate_pkg) { - id = topology_physical_package_id(cpu); - for_each_cpu(i, &cstate_pkg_cpu_mask) { - if (id == topology_physical_package_id(i)) - break; - } - if (i >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask); - } + if (has_cstate_core && target >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cstate_core_cpu_mask); + + /* + * If this is the first online thread of that package, set it + * in the package cpu mask as the designated reader. + */ + target = cpumask_any_and(&cstate_pkg_cpu_mask, + topology_core_cpumask(cpu)); + if (has_cstate_pkg && target >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask); } static int cstate_cpu_notifier(struct notifier_block *self, - unsigned long action, void *hcpu) + unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - break; case CPU_STARTING: cstate_cpu_init(cpu); break; - case CPU_UP_CANCELED: - case CPU_DYING: - break; - case CPU_ONLINE: - case CPU_DEAD: - break; case CPU_DOWN_PREPARE: cstate_cpu_exit(cpu); break; default: break; } - return NOTIFY_OK; } -/* - * Probe the cstate events and insert the available one into sysfs attrs - * Return false if there is no available events. - */ -static bool cstate_probe_msr(struct perf_cstate_msr *msr, - struct attribute **events_attrs, - int max_event_nr) -{ - int i, j = 0; - u64 val; - - /* Probe the cstate events. */ - for (i = 0; i < max_event_nr; i++) { - if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val)) - msr[i].attr = NULL; - } - - /* List remaining events in the sysfs attrs. */ - for (i = 0; i < max_event_nr; i++) { - if (msr[i].attr) - events_attrs[j++] = &msr[i].attr->attr.attr; - } - events_attrs[j] = NULL; - - return (j > 0) ? true : false; -} - -static int __init cstate_init(void) -{ - /* SLM has different MSR for PKG C6 */ - switch (boot_cpu_data.x86_model) { - case 55: - case 76: - case 77: - pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY; - } - - if (cstate_probe_msr(core_msr, core_events_attrs, PERF_CSTATE_CORE_EVENT_MAX)) - has_cstate_core = true; - - if (cstate_probe_msr(pkg_msr, pkg_events_attrs, PERF_CSTATE_PKG_EVENT_MAX)) - has_cstate_pkg = true; - - return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV; -} - -static void __init cstate_cpumask_init(void) -{ - int cpu; - - cpu_notifier_register_begin(); - - for_each_online_cpu(cpu) - cstate_cpu_init(cpu); - - __perf_cpu_notifier(cstate_cpu_notifier); - - cpu_notifier_register_done(); -} +static struct notifier_block cstate_cpu_nb = { + .notifier_call = cstate_cpu_notifier, + .priority = CPU_PRI_PERF + 1, +}; static struct pmu cstate_core_pmu = { .attr_groups = core_attr_groups, .name = "cstate_core", .task_ctx_nr = perf_invalid_context, .event_init = cstate_pmu_event_init, - .add = cstate_pmu_event_add, /* must have */ - .del = cstate_pmu_event_del, /* must have */ + .add = cstate_pmu_event_add, + .del = cstate_pmu_event_del, .start = cstate_pmu_event_start, .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, @@ -646,49 +457,203 @@ static struct pmu cstate_pkg_pmu = { .name = "cstate_pkg", .task_ctx_nr = perf_invalid_context, .event_init = cstate_pmu_event_init, - .add = cstate_pmu_event_add, /* must have */ - .del = cstate_pmu_event_del, /* must have */ + .add = cstate_pmu_event_add, + .del = cstate_pmu_event_del, .start = cstate_pmu_event_start, .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT, }; -static void __init cstate_pmus_register(void) +static const struct cstate_model nhm_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES), +}; + +static const struct cstate_model snb_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES) | + BIT(PERF_CSTATE_CORE_C7_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES), +}; + +static const struct cstate_model hswult_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES) | + BIT(PERF_CSTATE_CORE_C7_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES) | + BIT(PERF_CSTATE_PKG_C8_RES) | + BIT(PERF_CSTATE_PKG_C9_RES) | + BIT(PERF_CSTATE_PKG_C10_RES), +}; + +static const struct cstate_model slm_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C1_RES) | + BIT(PERF_CSTATE_CORE_C6_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C6_RES), + .quirks = SLM_PKG_C6_USE_C7_MSR, +}; + +#define X86_CSTATES_MODEL(model, states) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) } + +static const struct x86_cpu_id intel_cstates_match[] __initconst = { + X86_CSTATES_MODEL(30, nhm_cstates), /* 45nm Nehalem */ + X86_CSTATES_MODEL(26, nhm_cstates), /* 45nm Nehalem-EP */ + X86_CSTATES_MODEL(46, nhm_cstates), /* 45nm Nehalem-EX */ + + X86_CSTATES_MODEL(37, nhm_cstates), /* 32nm Westmere */ + X86_CSTATES_MODEL(44, nhm_cstates), /* 32nm Westmere-EP */ + X86_CSTATES_MODEL(47, nhm_cstates), /* 32nm Westmere-EX */ + + X86_CSTATES_MODEL(42, snb_cstates), /* 32nm SandyBridge */ + X86_CSTATES_MODEL(45, snb_cstates), /* 32nm SandyBridge-E/EN/EP */ + + X86_CSTATES_MODEL(58, snb_cstates), /* 22nm IvyBridge */ + X86_CSTATES_MODEL(62, snb_cstates), /* 22nm IvyBridge-EP/EX */ + + X86_CSTATES_MODEL(60, snb_cstates), /* 22nm Haswell Core */ + X86_CSTATES_MODEL(63, snb_cstates), /* 22nm Haswell Server */ + X86_CSTATES_MODEL(70, snb_cstates), /* 22nm Haswell + GT3e */ + + X86_CSTATES_MODEL(69, hswult_cstates), /* 22nm Haswell ULT */ + + X86_CSTATES_MODEL(55, slm_cstates), /* 22nm Atom Silvermont */ + X86_CSTATES_MODEL(77, slm_cstates), /* 22nm Atom Avoton/Rangely */ + X86_CSTATES_MODEL(76, slm_cstates), /* 22nm Atom Airmont */ + + X86_CSTATES_MODEL(61, snb_cstates), /* 14nm Broadwell Core-M */ + X86_CSTATES_MODEL(86, snb_cstates), /* 14nm Broadwell Xeon D */ + X86_CSTATES_MODEL(71, snb_cstates), /* 14nm Broadwell + GT3e */ + X86_CSTATES_MODEL(79, snb_cstates), /* 14nm Broadwell Server */ + + X86_CSTATES_MODEL(78, snb_cstates), /* 14nm Skylake Mobile */ + X86_CSTATES_MODEL(94, snb_cstates), /* 14nm Skylake Desktop */ + { }, +}; +MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); + +/* + * Probe the cstate events and insert the available one into sysfs attrs + * Return false if there are no available events. + */ +static bool __init cstate_probe_msr(const unsigned long evmsk, int max, + struct perf_cstate_msr *msr, + struct attribute **attrs) { - int err; + bool found = false; + unsigned int bit; + u64 val; + + for (bit = 0; bit < max; bit++) { + if (test_bit(bit, &evmsk) && !rdmsrl_safe(msr[bit].msr, &val)) { + *attrs++ = &msr[bit].attr->attr.attr; + found = true; + } else { + msr[bit].attr = NULL; + } + } + *attrs = NULL; + + return found; +} + +static int __init cstate_probe(const struct cstate_model *cm) +{ + /* SLM has different MSR for PKG C6 */ + if (cm->quirks & SLM_PKG_C6_USE_C7_MSR) + pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY; + + has_cstate_core = cstate_probe_msr(cm->core_events, + PERF_CSTATE_CORE_EVENT_MAX, + core_msr, core_events_attrs); + + has_cstate_pkg = cstate_probe_msr(cm->pkg_events, + PERF_CSTATE_PKG_EVENT_MAX, + pkg_msr, pkg_events_attrs); + + return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV; +} + +static inline void cstate_cleanup(void) +{ + if (has_cstate_core) + perf_pmu_unregister(&cstate_core_pmu); + + if (has_cstate_pkg) + perf_pmu_unregister(&cstate_pkg_pmu); +} + +static int __init cstate_init(void) +{ + int cpu, err; + + cpu_notifier_register_begin(); + for_each_online_cpu(cpu) + cstate_cpu_init(cpu); if (has_cstate_core) { err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1); - if (WARN_ON(err)) - pr_info("Failed to register PMU %s error %d\n", - cstate_core_pmu.name, err); + if (err) { + has_cstate_core = false; + pr_info("Failed to register cstate core pmu\n"); + goto out; + } } if (has_cstate_pkg) { err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1); - if (WARN_ON(err)) - pr_info("Failed to register PMU %s error %d\n", - cstate_pkg_pmu.name, err); + if (err) { + has_cstate_pkg = false; + pr_info("Failed to register cstate pkg pmu\n"); + cstate_cleanup(); + goto out; + } } + __register_cpu_notifier(&cstate_cpu_nb); +out: + cpu_notifier_register_done(); + return err; } static int __init cstate_pmu_init(void) { + const struct x86_cpu_id *id; int err; - if (cpu_has_hypervisor) + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + + id = x86_match_cpu(intel_cstates_match); + if (!id) return -ENODEV; - err = cstate_init(); + err = cstate_probe((const struct cstate_model *) id->driver_data); if (err) return err; - cstate_cpumask_init(); - - cstate_pmus_register(); - - return 0; + return cstate_init(); } +module_init(cstate_pmu_init); -device_initcall(cstate_pmu_init); +static void __exit cstate_pmu_exit(void) +{ + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&cstate_cpu_nb); + cstate_cleanup(); + cpu_notifier_register_done(); +} +module_exit(cstate_pmu_exit); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8584b90..7ce9f3f 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -645,6 +645,12 @@ struct event_constraint intel_slm_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_glm_pebs_event_constraints[] = { + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), + EVENT_CONSTRAINT_END +}; + struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 1ca5d1e..9e2b40c 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -14,7 +14,8 @@ enum { LBR_FORMAT_EIP_FLAGS = 0x03, LBR_FORMAT_EIP_FLAGS2 = 0x04, LBR_FORMAT_INFO = 0x05, - LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_INFO, + LBR_FORMAT_TIME = 0x06, + LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_TIME, }; static enum { @@ -464,6 +465,16 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) abort = !!(info & LBR_INFO_ABORT); cycles = (info & LBR_INFO_CYCLES); } + + if (lbr_format == LBR_FORMAT_TIME) { + mis = !!(from & LBR_FROM_FLAG_MISPRED); + pred = !mis; + skip = 1; + cycles = ((to >> 48) & LBR_INFO_CYCLES); + + to = (u64)((((s64)to) << 16) >> 16); + } + if (lbr_flags & LBR_EIP_FLAGS) { mis = !!(from & LBR_FROM_FLAG_MISPRED); pred = !mis; @@ -1049,6 +1060,24 @@ void __init intel_pmu_lbr_init_atom(void) pr_cont("8-deep LBR, "); } +/* slm */ +void __init intel_pmu_lbr_init_slm(void) +{ + x86_pmu.lbr_nr = 8; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_CORE_FROM; + x86_pmu.lbr_to = MSR_LBR_CORE_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = nhm_lbr_sel_map; + + /* + * SW branch filter usage: + * - compensate for lack of HW filter + */ + pr_cont("8-deep LBR, "); +} + /* Knights Landing */ void intel_pmu_lbr_init_knl(void) { diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 09a77db..04bb5fb 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -67,11 +67,13 @@ static struct pt_cap_desc { PT_CAP(max_subleaf, 0, CR_EAX, 0xffffffff), PT_CAP(cr3_filtering, 0, CR_EBX, BIT(0)), PT_CAP(psb_cyc, 0, CR_EBX, BIT(1)), + PT_CAP(ip_filtering, 0, CR_EBX, BIT(2)), PT_CAP(mtc, 0, CR_EBX, BIT(3)), PT_CAP(topa_output, 0, CR_ECX, BIT(0)), PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)), PT_CAP(single_range_output, 0, CR_ECX, BIT(2)), PT_CAP(payloads_lip, 0, CR_ECX, BIT(31)), + PT_CAP(num_address_ranges, 1, CR_EAX, 0x3), PT_CAP(mtc_periods, 1, CR_EAX, 0xffff0000), PT_CAP(cycle_thresholds, 1, CR_EBX, 0xffff), PT_CAP(psb_periods, 1, CR_EBX, 0xffff0000), @@ -125,9 +127,46 @@ static struct attribute_group pt_format_group = { .attrs = pt_formats_attr, }; +static ssize_t +pt_timing_attr_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_attr *pmu_attr = + container_of(attr, struct perf_pmu_events_attr, attr); + + switch (pmu_attr->id) { + case 0: + return sprintf(page, "%lu\n", pt_pmu.max_nonturbo_ratio); + case 1: + return sprintf(page, "%u:%u\n", + pt_pmu.tsc_art_num, + pt_pmu.tsc_art_den); + default: + break; + } + + return -EINVAL; +} + +PMU_EVENT_ATTR(max_nonturbo_ratio, timing_attr_max_nonturbo_ratio, 0, + pt_timing_attr_show); +PMU_EVENT_ATTR(tsc_art_ratio, timing_attr_tsc_art_ratio, 1, + pt_timing_attr_show); + +static struct attribute *pt_timing_attr[] = { + &timing_attr_max_nonturbo_ratio.attr.attr, + &timing_attr_tsc_art_ratio.attr.attr, + NULL, +}; + +static struct attribute_group pt_timing_group = { + .attrs = pt_timing_attr, +}; + static const struct attribute_group *pt_attr_groups[] = { &pt_cap_group, &pt_format_group, + &pt_timing_group, NULL, }; @@ -140,6 +179,23 @@ static int __init pt_pmu_hw_init(void) int ret; long i; + rdmsrl(MSR_PLATFORM_INFO, reg); + pt_pmu.max_nonturbo_ratio = (reg & 0xff00) >> 8; + + /* + * if available, read in TSC to core crystal clock ratio, + * otherwise, zero for numerator stands for "not enumerated" + * as per SDM + */ + if (boot_cpu_data.cpuid_level >= CPUID_TSC_LEAF) { + u32 eax, ebx, ecx, edx; + + cpuid(CPUID_TSC_LEAF, &eax, &ebx, &ecx, &edx); + + pt_pmu.tsc_art_num = ebx; + pt_pmu.tsc_art_den = eax; + } + if (boot_cpu_has(X86_FEATURE_VMX)) { /* * Intel SDM, 36.5 "Tracing post-VMXON" says that @@ -263,6 +319,75 @@ static bool pt_event_valid(struct perf_event *event) * These all are cpu affine and operate on a local PT */ +/* Address ranges and their corresponding msr configuration registers */ +static const struct pt_address_range { + unsigned long msr_a; + unsigned long msr_b; + unsigned int reg_off; +} pt_address_ranges[] = { + { + .msr_a = MSR_IA32_RTIT_ADDR0_A, + .msr_b = MSR_IA32_RTIT_ADDR0_B, + .reg_off = RTIT_CTL_ADDR0_OFFSET, + }, + { + .msr_a = MSR_IA32_RTIT_ADDR1_A, + .msr_b = MSR_IA32_RTIT_ADDR1_B, + .reg_off = RTIT_CTL_ADDR1_OFFSET, + }, + { + .msr_a = MSR_IA32_RTIT_ADDR2_A, + .msr_b = MSR_IA32_RTIT_ADDR2_B, + .reg_off = RTIT_CTL_ADDR2_OFFSET, + }, + { + .msr_a = MSR_IA32_RTIT_ADDR3_A, + .msr_b = MSR_IA32_RTIT_ADDR3_B, + .reg_off = RTIT_CTL_ADDR3_OFFSET, + } +}; + +static u64 pt_config_filters(struct perf_event *event) +{ + struct pt_filters *filters = event->hw.addr_filters; + struct pt *pt = this_cpu_ptr(&pt_ctx); + unsigned int range = 0; + u64 rtit_ctl = 0; + + if (!filters) + return 0; + + perf_event_addr_filters_sync(event); + + for (range = 0; range < filters->nr_filters; range++) { + struct pt_filter *filter = &filters->filter[range]; + + /* + * Note, if the range has zero start/end addresses due + * to its dynamic object not being loaded yet, we just + * go ahead and program zeroed range, which will simply + * produce no data. Note^2: if executable code at 0x0 + * is a concern, we can set up an "invalid" configuration + * such as msr_b < msr_a. + */ + + /* avoid redundant msr writes */ + if (pt->filters.filter[range].msr_a != filter->msr_a) { + wrmsrl(pt_address_ranges[range].msr_a, filter->msr_a); + pt->filters.filter[range].msr_a = filter->msr_a; + } + + if (pt->filters.filter[range].msr_b != filter->msr_b) { + wrmsrl(pt_address_ranges[range].msr_b, filter->msr_b); + pt->filters.filter[range].msr_b = filter->msr_b; + } + + rtit_ctl |= filter->config << pt_address_ranges[range].reg_off; + } + + return rtit_ctl; +} + static void pt_config(struct perf_event *event) { u64 reg; @@ -272,7 +397,8 @@ static void pt_config(struct perf_event *event) wrmsrl(MSR_IA32_RTIT_STATUS, 0); } - reg = RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN; + reg = pt_config_filters(event); + reg |= RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN; if (!event->attr.exclude_kernel) reg |= RTIT_CTL_OS; @@ -709,6 +835,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, /* clear STOP and INT from current entry */ buf->topa_index[buf->stop_pos]->stop = 0; + buf->topa_index[buf->stop_pos]->intr = 0; buf->topa_index[buf->intr_pos]->intr = 0; /* how many pages till the STOP marker */ @@ -733,6 +860,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, buf->intr_pos = idx; buf->topa_index[buf->stop_pos]->stop = 1; + buf->topa_index[buf->stop_pos]->intr = 1; buf->topa_index[buf->intr_pos]->intr = 1; return 0; @@ -919,24 +1047,80 @@ static void pt_buffer_free_aux(void *data) kfree(buf); } -/** - * pt_buffer_is_full() - check if the buffer is full - * @buf: PT buffer. - * @pt: Per-cpu pt handle. - * - * If the user hasn't read data from the output region that aux_head - * points to, the buffer is considered full: the user needs to read at - * least this region and update aux_tail to point past it. - */ -static bool pt_buffer_is_full(struct pt_buffer *buf, struct pt *pt) +static int pt_addr_filters_init(struct perf_event *event) { - if (buf->snapshot) - return false; + struct pt_filters *filters; + int node = event->cpu == -1 ? -1 : cpu_to_node(event->cpu); + + if (!pt_cap_get(PT_CAP_num_address_ranges)) + return 0; + + filters = kzalloc_node(sizeof(struct pt_filters), GFP_KERNEL, node); + if (!filters) + return -ENOMEM; + + if (event->parent) + memcpy(filters, event->parent->hw.addr_filters, + sizeof(*filters)); + + event->hw.addr_filters = filters; + + return 0; +} + +static void pt_addr_filters_fini(struct perf_event *event) +{ + kfree(event->hw.addr_filters); + event->hw.addr_filters = NULL; +} + +static int pt_event_addr_filters_validate(struct list_head *filters) +{ + struct perf_addr_filter *filter; + int range = 0; + + list_for_each_entry(filter, filters, entry) { + /* PT doesn't support single address triggers */ + if (!filter->range) + return -EOPNOTSUPP; + + if (!filter->inode && !kernel_ip(filter->offset)) + return -EINVAL; + + if (++range > pt_cap_get(PT_CAP_num_address_ranges)) + return -EOPNOTSUPP; + } + + return 0; +} + +static void pt_event_addr_filters_sync(struct perf_event *event) +{ + struct perf_addr_filters_head *head = perf_event_addr_filters(event); + unsigned long msr_a, msr_b, *offs = event->addr_filters_offs; + struct pt_filters *filters = event->hw.addr_filters; + struct perf_addr_filter *filter; + int range = 0; + + if (!filters) + return; - if (local_read(&buf->data_size) >= pt->handle.size) - return true; + list_for_each_entry(filter, &head->list, entry) { + if (filter->inode && !offs[range]) { + msr_a = msr_b = 0; + } else { + /* apply the offset */ + msr_a = filter->offset + offs[range]; + msr_b = filter->size + msr_a; + } + + filters->filter[range].msr_a = msr_a; + filters->filter[range].msr_b = msr_b; + filters->filter[range].config = filter->filter ? 1 : 2; + range++; + } - return false; + filters->nr_filters = range; } /** @@ -953,7 +1137,7 @@ void intel_pt_interrupt(void) * after PT has been disabled by pt_event_stop(). Make sure we don't * do anything (particularly, re-enable) for this event here. */ - if (!ACCESS_ONCE(pt->handle_nmi)) + if (!READ_ONCE(pt->handle_nmi)) return; /* @@ -1038,23 +1222,36 @@ EXPORT_SYMBOL_GPL(intel_pt_handle_vmx); static void pt_event_start(struct perf_event *event, int mode) { + struct hw_perf_event *hwc = &event->hw; struct pt *pt = this_cpu_ptr(&pt_ctx); - struct pt_buffer *buf = perf_get_aux(&pt->handle); + struct pt_buffer *buf; if (READ_ONCE(pt->vmx_on)) return; - if (!buf || pt_buffer_is_full(buf, pt)) { - event->hw.state = PERF_HES_STOPPED; - return; + buf = perf_aux_output_begin(&pt->handle, event); + if (!buf) + goto fail_stop; + + pt_buffer_reset_offsets(buf, pt->handle.head); + if (!buf->snapshot) { + if (pt_buffer_reset_markers(buf, &pt->handle)) + goto fail_end_stop; } - ACCESS_ONCE(pt->handle_nmi) = 1; - event->hw.state = 0; + WRITE_ONCE(pt->handle_nmi, 1); + hwc->state = 0; pt_config_buffer(buf->cur->table, buf->cur_idx, buf->output_off); pt_config(event); + + return; + +fail_end_stop: + perf_aux_output_end(&pt->handle, 0, true); +fail_stop: + hwc->state = PERF_HES_STOPPED; } static void pt_event_stop(struct perf_event *event, int mode) @@ -1065,7 +1262,7 @@ static void pt_event_stop(struct perf_event *event, int mode) * Protect against the PMI racing with disabling wrmsr, * see comment in intel_pt_interrupt(). */ - ACCESS_ONCE(pt->handle_nmi) = 0; + WRITE_ONCE(pt->handle_nmi, 0); pt_config_stop(event); @@ -1088,19 +1285,7 @@ static void pt_event_stop(struct perf_event *event, int mode) pt_handle_status(pt); pt_update_head(pt); - } -} - -static void pt_event_del(struct perf_event *event, int mode) -{ - struct pt *pt = this_cpu_ptr(&pt_ctx); - struct pt_buffer *buf; - pt_event_stop(event, PERF_EF_UPDATE); - - buf = perf_get_aux(&pt->handle); - - if (buf) { if (buf->snapshot) pt->handle.head = local_xchg(&buf->data_size, @@ -1110,9 +1295,13 @@ static void pt_event_del(struct perf_event *event, int mode) } } +static void pt_event_del(struct perf_event *event, int mode) +{ + pt_event_stop(event, PERF_EF_UPDATE); +} + static int pt_event_add(struct perf_event *event, int mode) { - struct pt_buffer *buf; struct pt *pt = this_cpu_ptr(&pt_ctx); struct hw_perf_event *hwc = &event->hw; int ret = -EBUSY; @@ -1120,34 +1309,18 @@ static int pt_event_add(struct perf_event *event, int mode) if (pt->handle.event) goto fail; - buf = perf_aux_output_begin(&pt->handle, event); - ret = -EINVAL; - if (!buf) - goto fail_stop; - - pt_buffer_reset_offsets(buf, pt->handle.head); - if (!buf->snapshot) { - ret = pt_buffer_reset_markers(buf, &pt->handle); - if (ret) - goto fail_end_stop; - } - if (mode & PERF_EF_START) { pt_event_start(event, 0); - ret = -EBUSY; + ret = -EINVAL; if (hwc->state == PERF_HES_STOPPED) - goto fail_end_stop; + goto fail; } else { hwc->state = PERF_HES_STOPPED; } - return 0; - -fail_end_stop: - perf_aux_output_end(&pt->handle, 0, true); -fail_stop: - hwc->state = PERF_HES_STOPPED; + ret = 0; fail: + return ret; } @@ -1157,6 +1330,7 @@ static void pt_event_read(struct perf_event *event) static void pt_event_destroy(struct perf_event *event) { + pt_addr_filters_fini(event); x86_del_exclusive(x86_lbr_exclusive_pt); } @@ -1171,6 +1345,11 @@ static int pt_event_init(struct perf_event *event) if (x86_add_exclusive(x86_lbr_exclusive_pt)) return -EBUSY; + if (pt_addr_filters_init(event)) { + x86_del_exclusive(x86_lbr_exclusive_pt); + return -ENOMEM; + } + event->destroy = pt_event_destroy; return 0; @@ -1190,7 +1369,7 @@ static __init int pt_init(void) BUILD_BUG_ON(sizeof(struct topa) > PAGE_SIZE); - if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT)) + if (!boot_cpu_has(X86_FEATURE_INTEL_PT)) return -ENODEV; get_online_cpus(); @@ -1224,16 +1403,21 @@ static __init int pt_init(void) PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF; pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE; - pt_pmu.pmu.attr_groups = pt_attr_groups; - pt_pmu.pmu.task_ctx_nr = perf_sw_context; - pt_pmu.pmu.event_init = pt_event_init; - pt_pmu.pmu.add = pt_event_add; - pt_pmu.pmu.del = pt_event_del; - pt_pmu.pmu.start = pt_event_start; - pt_pmu.pmu.stop = pt_event_stop; - pt_pmu.pmu.read = pt_event_read; - pt_pmu.pmu.setup_aux = pt_buffer_setup_aux; - pt_pmu.pmu.free_aux = pt_buffer_free_aux; + pt_pmu.pmu.attr_groups = pt_attr_groups; + pt_pmu.pmu.task_ctx_nr = perf_sw_context; + pt_pmu.pmu.event_init = pt_event_init; + pt_pmu.pmu.add = pt_event_add; + pt_pmu.pmu.del = pt_event_del; + pt_pmu.pmu.start = pt_event_start; + pt_pmu.pmu.stop = pt_event_stop; + pt_pmu.pmu.read = pt_event_read; + pt_pmu.pmu.setup_aux = pt_buffer_setup_aux; + pt_pmu.pmu.free_aux = pt_buffer_free_aux; + pt_pmu.pmu.addr_filters_sync = pt_event_addr_filters_sync; + pt_pmu.pmu.addr_filters_validate = pt_event_addr_filters_validate; + pt_pmu.pmu.nr_addr_filters = + pt_cap_get(PT_CAP_num_address_ranges); + ret = perf_pmu_register(&pt_pmu.pmu, "intel_pt", -1); return ret; diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 3abb5f5..efffa4a 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -20,6 +20,40 @@ #define __INTEL_PT_H__ /* + * PT MSR bit definitions + */ +#define RTIT_CTL_TRACEEN BIT(0) +#define RTIT_CTL_CYCLEACC BIT(1) +#define RTIT_CTL_OS BIT(2) +#define RTIT_CTL_USR BIT(3) +#define RTIT_CTL_CR3EN BIT(7) +#define RTIT_CTL_TOPA BIT(8) +#define RTIT_CTL_MTC_EN BIT(9) +#define RTIT_CTL_TSC_EN BIT(10) +#define RTIT_CTL_DISRETC BIT(11) +#define RTIT_CTL_BRANCH_EN BIT(13) +#define RTIT_CTL_MTC_RANGE_OFFSET 14 +#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) +#define RTIT_CTL_CYC_THRESH_OFFSET 19 +#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET) +#define RTIT_CTL_PSB_FREQ_OFFSET 24 +#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET) +#define RTIT_CTL_ADDR0_OFFSET 32 +#define RTIT_CTL_ADDR0 (0x0full << RTIT_CTL_ADDR0_OFFSET) +#define RTIT_CTL_ADDR1_OFFSET 36 +#define RTIT_CTL_ADDR1 (0x0full << RTIT_CTL_ADDR1_OFFSET) +#define RTIT_CTL_ADDR2_OFFSET 40 +#define RTIT_CTL_ADDR2 (0x0full << RTIT_CTL_ADDR2_OFFSET) +#define RTIT_CTL_ADDR3_OFFSET 44 +#define RTIT_CTL_ADDR3 (0x0full << RTIT_CTL_ADDR3_OFFSET) +#define RTIT_STATUS_FILTEREN BIT(0) +#define RTIT_STATUS_CONTEXTEN BIT(1) +#define RTIT_STATUS_TRIGGEREN BIT(2) +#define RTIT_STATUS_BUFFOVF BIT(3) +#define RTIT_STATUS_ERROR BIT(4) +#define RTIT_STATUS_STOPPED BIT(5) + +/* * Single-entry ToPA: when this close to region boundary, switch * buffers to avoid losing data. */ @@ -48,15 +82,20 @@ struct topa_entry { #define PT_CPUID_LEAVES 2 #define PT_CPUID_REGS_NUM 4 /* number of regsters (eax, ebx, ecx, edx) */ +/* TSC to Core Crystal Clock Ratio */ +#define CPUID_TSC_LEAF 0x15 + enum pt_capabilities { PT_CAP_max_subleaf = 0, PT_CAP_cr3_filtering, PT_CAP_psb_cyc, + PT_CAP_ip_filtering, PT_CAP_mtc, PT_CAP_topa_output, PT_CAP_topa_multiple_entries, PT_CAP_single_range_output, PT_CAP_payloads_lip, + PT_CAP_num_address_ranges, PT_CAP_mtc_periods, PT_CAP_cycle_thresholds, PT_CAP_psb_periods, @@ -66,6 +105,9 @@ struct pt_pmu { struct pmu pmu; u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES]; bool vmx; + unsigned long max_nonturbo_ratio; + unsigned int tsc_art_num; + unsigned int tsc_art_den; }; /** @@ -104,14 +146,40 @@ struct pt_buffer { struct topa_entry *topa_index[0]; }; +#define PT_FILTERS_NUM 4 + +/** + * struct pt_filter - IP range filter configuration + * @msr_a: range start, goes to RTIT_ADDRn_A + * @msr_b: range end, goes to RTIT_ADDRn_B + * @config: 4-bit field in RTIT_CTL + */ +struct pt_filter { + unsigned long msr_a; + unsigned long msr_b; + unsigned long config; +}; + +/** + * struct pt_filters - IP range filtering context + * @filter: filters defined for this context + * @nr_filters: number of defined filters in the @filter array + */ +struct pt_filters { + struct pt_filter filter[PT_FILTERS_NUM]; + unsigned int nr_filters; +}; + /** * struct pt - per-cpu pt context * @handle: perf output handle + * @filters: last configured filters * @handle_nmi: do handle PT PMI on this cpu, there's an active event * @vmx_on: 1 if VMX is ON on this cpu */ struct pt { struct perf_output_handle handle; + struct pt_filters filters; int handle_nmi; int vmx_on; }; diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 1705c9d..99c4bab 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -27,10 +27,14 @@ * event: rapl_energy_dram * perf code: 0x3 * - * dram counter: consumption of the builtin-gpu domain (client only) + * gpu counter: consumption of the builtin-gpu domain (client only) * event: rapl_energy_gpu * perf code: 0x4 * + * psys counter: consumption of the builtin-psys domain (client only) + * event: rapl_energy_psys + * perf code: 0x5 + * * We manage those counters as free running (read-only). They may be * use simultaneously by other tools, such as turbostat. * @@ -53,6 +57,8 @@ #include <asm/cpu_device_id.h> #include "../perf_event.h" +MODULE_LICENSE("GPL"); + /* * RAPL energy status counters */ @@ -64,13 +70,16 @@ #define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */ #define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */ #define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ +#define RAPL_IDX_PSYS_NRG_STAT 4 /* psys */ +#define INTEL_RAPL_PSYS 0x5 /* pseudo-encoding */ -#define NR_RAPL_DOMAINS 0x4 +#define NR_RAPL_DOMAINS 0x5 static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { "pp0-core", "package", "dram", "pp1-gpu", + "psys", }; /* Clients have PP0, PKG */ @@ -89,6 +98,13 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { 1<<RAPL_IDX_RAM_NRG_STAT|\ 1<<RAPL_IDX_PP1_NRG_STAT) +/* SKL clients have PP0, PKG, RAM, PP1, PSYS */ +#define RAPL_IDX_SKL_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\ + 1<<RAPL_IDX_PKG_NRG_STAT|\ + 1<<RAPL_IDX_RAM_NRG_STAT|\ + 1<<RAPL_IDX_PP1_NRG_STAT|\ + 1<<RAPL_IDX_PSYS_NRG_STAT) + /* Knights Landing has PKG, RAM */ #define RAPL_IDX_KNL (1<<RAPL_IDX_PKG_NRG_STAT|\ 1<<RAPL_IDX_RAM_NRG_STAT) @@ -360,6 +376,10 @@ static int rapl_pmu_event_init(struct perf_event *event) bit = RAPL_IDX_PP1_NRG_STAT; msr = MSR_PP1_ENERGY_STATUS; break; + case INTEL_RAPL_PSYS: + bit = RAPL_IDX_PSYS_NRG_STAT; + msr = MSR_PLATFORM_ENERGY_STATUS; + break; default: return -EINVAL; } @@ -414,11 +434,13 @@ RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04"); +RAPL_EVENT_ATTR_STR(energy-psys, rapl_psys, "event=0x05"); RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules"); +RAPL_EVENT_ATTR_STR(energy-psys.unit, rapl_psys_unit, "Joules"); /* * we compute in 0.23 nJ increments regardless of MSR @@ -427,6 +449,7 @@ RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890 RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10"); +RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10"); static struct attribute *rapl_events_srv_attr[] = { EVENT_PTR(rapl_cores), @@ -476,6 +499,27 @@ static struct attribute *rapl_events_hsw_attr[] = { NULL, }; +static struct attribute *rapl_events_skl_attr[] = { + EVENT_PTR(rapl_cores), + EVENT_PTR(rapl_pkg), + EVENT_PTR(rapl_gpu), + EVENT_PTR(rapl_ram), + EVENT_PTR(rapl_psys), + + EVENT_PTR(rapl_cores_unit), + EVENT_PTR(rapl_pkg_unit), + EVENT_PTR(rapl_gpu_unit), + EVENT_PTR(rapl_ram_unit), + EVENT_PTR(rapl_psys_unit), + + EVENT_PTR(rapl_cores_scale), + EVENT_PTR(rapl_pkg_scale), + EVENT_PTR(rapl_gpu_scale), + EVENT_PTR(rapl_ram_scale), + EVENT_PTR(rapl_psys_scale), + NULL, +}; + static struct attribute *rapl_events_knl_attr[] = { EVENT_PTR(rapl_pkg), EVENT_PTR(rapl_ram), @@ -592,6 +636,11 @@ static int rapl_cpu_notifier(struct notifier_block *self, return NOTIFY_OK; } +static struct notifier_block rapl_cpu_nb = { + .notifier_call = rapl_cpu_notifier, + .priority = CPU_PRI_PERF + 1, +}; + static int rapl_check_hw_unit(bool apply_quirk) { u64 msr_rapl_power_unit_bits; @@ -660,7 +709,7 @@ static int __init rapl_prepare_cpus(void) return 0; } -static void __init cleanup_rapl_pmus(void) +static void cleanup_rapl_pmus(void) { int i; @@ -691,52 +740,92 @@ static int __init init_rapl_pmus(void) return 0; } +#define X86_RAPL_MODEL_MATCH(model, init) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init } + +struct intel_rapl_init_fun { + bool apply_quirk; + int cntr_mask; + struct attribute **attrs; +}; + +static const struct intel_rapl_init_fun snb_rapl_init __initconst = { + .apply_quirk = false, + .cntr_mask = RAPL_IDX_CLN, + .attrs = rapl_events_cln_attr, +}; + +static const struct intel_rapl_init_fun hsx_rapl_init __initconst = { + .apply_quirk = true, + .cntr_mask = RAPL_IDX_SRV, + .attrs = rapl_events_srv_attr, +}; + +static const struct intel_rapl_init_fun hsw_rapl_init __initconst = { + .apply_quirk = false, + .cntr_mask = RAPL_IDX_HSW, + .attrs = rapl_events_hsw_attr, +}; + +static const struct intel_rapl_init_fun snbep_rapl_init __initconst = { + .apply_quirk = false, + .cntr_mask = RAPL_IDX_SRV, + .attrs = rapl_events_srv_attr, +}; + +static const struct intel_rapl_init_fun knl_rapl_init __initconst = { + .apply_quirk = true, + .cntr_mask = RAPL_IDX_KNL, + .attrs = rapl_events_knl_attr, +}; + +static const struct intel_rapl_init_fun skl_rapl_init __initconst = { + .apply_quirk = false, + .cntr_mask = RAPL_IDX_SKL_CLN, + .attrs = rapl_events_skl_attr, +}; + static const struct x86_cpu_id rapl_cpu_match[] __initconst = { - [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 }, - [1] = {}, + X86_RAPL_MODEL_MATCH(42, snb_rapl_init), /* Sandy Bridge */ + X86_RAPL_MODEL_MATCH(45, snbep_rapl_init), /* Sandy Bridge-EP */ + + X86_RAPL_MODEL_MATCH(58, snb_rapl_init), /* Ivy Bridge */ + X86_RAPL_MODEL_MATCH(62, snbep_rapl_init), /* IvyTown */ + + X86_RAPL_MODEL_MATCH(60, hsw_rapl_init), /* Haswell */ + X86_RAPL_MODEL_MATCH(63, hsx_rapl_init), /* Haswell-Server */ + X86_RAPL_MODEL_MATCH(69, hsw_rapl_init), /* Haswell-Celeron */ + X86_RAPL_MODEL_MATCH(70, hsw_rapl_init), /* Haswell GT3e */ + + X86_RAPL_MODEL_MATCH(61, hsw_rapl_init), /* Broadwell */ + X86_RAPL_MODEL_MATCH(71, hsw_rapl_init), /* Broadwell-H */ + X86_RAPL_MODEL_MATCH(79, hsx_rapl_init), /* Broadwell-Server */ + X86_RAPL_MODEL_MATCH(86, hsx_rapl_init), /* Broadwell Xeon D */ + + X86_RAPL_MODEL_MATCH(87, knl_rapl_init), /* Knights Landing */ + + X86_RAPL_MODEL_MATCH(78, skl_rapl_init), /* Skylake */ + X86_RAPL_MODEL_MATCH(94, skl_rapl_init), /* Skylake H/S */ + {}, }; +MODULE_DEVICE_TABLE(x86cpu, rapl_cpu_match); + static int __init rapl_pmu_init(void) { - bool apply_quirk = false; + const struct x86_cpu_id *id; + struct intel_rapl_init_fun *rapl_init; + bool apply_quirk; int ret; - if (!x86_match_cpu(rapl_cpu_match)) + id = x86_match_cpu(rapl_cpu_match); + if (!id) return -ENODEV; - switch (boot_cpu_data.x86_model) { - case 42: /* Sandy Bridge */ - case 58: /* Ivy Bridge */ - rapl_cntr_mask = RAPL_IDX_CLN; - rapl_pmu_events_group.attrs = rapl_events_cln_attr; - break; - case 63: /* Haswell-Server */ - case 79: /* Broadwell-Server */ - apply_quirk = true; - rapl_cntr_mask = RAPL_IDX_SRV; - rapl_pmu_events_group.attrs = rapl_events_srv_attr; - break; - case 60: /* Haswell */ - case 69: /* Haswell-Celeron */ - case 70: /* Haswell GT3e */ - case 61: /* Broadwell */ - case 71: /* Broadwell-H */ - rapl_cntr_mask = RAPL_IDX_HSW; - rapl_pmu_events_group.attrs = rapl_events_hsw_attr; - break; - case 45: /* Sandy Bridge-EP */ - case 62: /* IvyTown */ - rapl_cntr_mask = RAPL_IDX_SRV; - rapl_pmu_events_group.attrs = rapl_events_srv_attr; - break; - case 87: /* Knights Landing */ - apply_quirk = true; - rapl_cntr_mask = RAPL_IDX_KNL; - rapl_pmu_events_group.attrs = rapl_events_knl_attr; - break; - default: - return -ENODEV; - } + rapl_init = (struct intel_rapl_init_fun *)id->driver_data; + apply_quirk = rapl_init->apply_quirk; + rapl_cntr_mask = rapl_init->cntr_mask; + rapl_pmu_events_group.attrs = rapl_init->attrs; ret = rapl_check_hw_unit(apply_quirk); if (ret) @@ -756,7 +845,7 @@ static int __init rapl_pmu_init(void) if (ret) goto out; - __perf_cpu_notifier(rapl_cpu_notifier); + __register_cpu_notifier(&rapl_cpu_nb); cpu_notifier_register_done(); rapl_advertise(); return 0; @@ -767,4 +856,14 @@ out: cpu_notifier_register_done(); return ret; } -device_initcall(rapl_pmu_init); +module_init(rapl_pmu_init); + +static void __exit intel_rapl_exit(void) +{ + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&rapl_cpu_nb); + perf_pmu_unregister(&rapl_pmus->pmu); + cleanup_rapl_pmus(); + cpu_notifier_register_done(); +} +module_exit(intel_rapl_exit); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 7012d18..16c1789 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1,3 +1,4 @@ +#include <asm/cpu_device_id.h> #include "uncore.h" static struct intel_uncore_type *empty_uncore[] = { NULL, }; @@ -21,6 +22,8 @@ static struct event_constraint uncore_constraint_fixed = struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); +MODULE_LICENSE("GPL"); + static int uncore_pcibus_to_physid(struct pci_bus *bus) { struct pci2phy_map *map; @@ -754,7 +757,7 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu) pmu->registered = false; } -static void __init __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) +static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) { struct intel_uncore_pmu *pmu = type->pmus; struct intel_uncore_box *box; @@ -770,7 +773,7 @@ static void __init __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) } } -static void __init uncore_exit_boxes(void *dummy) +static void uncore_exit_boxes(void *dummy) { struct intel_uncore_type **types; @@ -787,7 +790,7 @@ static void uncore_free_boxes(struct intel_uncore_pmu *pmu) kfree(pmu->boxes); } -static void __init uncore_type_exit(struct intel_uncore_type *type) +static void uncore_type_exit(struct intel_uncore_type *type) { struct intel_uncore_pmu *pmu = type->pmus; int i; @@ -804,7 +807,7 @@ static void __init uncore_type_exit(struct intel_uncore_type *type) type->events_group = NULL; } -static void __init uncore_types_exit(struct intel_uncore_type **types) +static void uncore_types_exit(struct intel_uncore_type **types) { for (; *types; types++) uncore_type_exit(*types); @@ -989,46 +992,6 @@ static int __init uncore_pci_init(void) size_t size; int ret; - switch (boot_cpu_data.x86_model) { - case 45: /* Sandy Bridge-EP */ - ret = snbep_uncore_pci_init(); - break; - case 62: /* Ivy Bridge-EP */ - ret = ivbep_uncore_pci_init(); - break; - case 63: /* Haswell-EP */ - ret = hswep_uncore_pci_init(); - break; - case 79: /* BDX-EP */ - case 86: /* BDX-DE */ - ret = bdx_uncore_pci_init(); - break; - case 42: /* Sandy Bridge */ - ret = snb_uncore_pci_init(); - break; - case 58: /* Ivy Bridge */ - ret = ivb_uncore_pci_init(); - break; - case 60: /* Haswell */ - case 69: /* Haswell Celeron */ - ret = hsw_uncore_pci_init(); - break; - case 61: /* Broadwell */ - ret = bdw_uncore_pci_init(); - break; - case 87: /* Knights Landing */ - ret = knl_uncore_pci_init(); - break; - case 94: /* SkyLake */ - ret = skl_uncore_pci_init(); - break; - default: - return -ENODEV; - } - - if (ret) - return ret; - size = max_packages * sizeof(struct pci_extra_dev); uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL); if (!uncore_extra_pci_dev) { @@ -1060,7 +1023,7 @@ err: return ret; } -static void __init uncore_pci_exit(void) +static void uncore_pci_exit(void) { if (pcidrv_registered) { pcidrv_registered = false; @@ -1287,46 +1250,6 @@ static int __init uncore_cpu_init(void) { int ret; - switch (boot_cpu_data.x86_model) { - case 26: /* Nehalem */ - case 30: - case 37: /* Westmere */ - case 44: - nhm_uncore_cpu_init(); - break; - case 42: /* Sandy Bridge */ - case 58: /* Ivy Bridge */ - case 60: /* Haswell */ - case 69: /* Haswell */ - case 70: /* Haswell */ - case 61: /* Broadwell */ - case 71: /* Broadwell */ - snb_uncore_cpu_init(); - break; - case 45: /* Sandy Bridge-EP */ - snbep_uncore_cpu_init(); - break; - case 46: /* Nehalem-EX */ - case 47: /* Westmere-EX aka. Xeon E7 */ - nhmex_uncore_cpu_init(); - break; - case 62: /* Ivy Bridge-EP */ - ivbep_uncore_cpu_init(); - break; - case 63: /* Haswell-EP */ - hswep_uncore_cpu_init(); - break; - case 79: /* BDX-EP */ - case 86: /* BDX-DE */ - bdx_uncore_cpu_init(); - break; - case 87: /* Knights Landing */ - knl_uncore_cpu_init(); - break; - default: - return -ENODEV; - } - ret = uncore_types_init(uncore_msr_uncores, true); if (ret) goto err; @@ -1376,20 +1299,123 @@ static int __init uncore_cpumask_init(bool msr) return 0; } +#define X86_UNCORE_MODEL_MATCH(model, init) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init } + +struct intel_uncore_init_fun { + void (*cpu_init)(void); + int (*pci_init)(void); +}; + +static const struct intel_uncore_init_fun nhm_uncore_init __initconst = { + .cpu_init = nhm_uncore_cpu_init, +}; + +static const struct intel_uncore_init_fun snb_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = snb_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun ivb_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = ivb_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun hsw_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = hsw_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun bdw_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = bdw_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun snbep_uncore_init __initconst = { + .cpu_init = snbep_uncore_cpu_init, + .pci_init = snbep_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun nhmex_uncore_init __initconst = { + .cpu_init = nhmex_uncore_cpu_init, +}; + +static const struct intel_uncore_init_fun ivbep_uncore_init __initconst = { + .cpu_init = ivbep_uncore_cpu_init, + .pci_init = ivbep_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun hswep_uncore_init __initconst = { + .cpu_init = hswep_uncore_cpu_init, + .pci_init = hswep_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun bdx_uncore_init __initconst = { + .cpu_init = bdx_uncore_cpu_init, + .pci_init = bdx_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun knl_uncore_init __initconst = { + .cpu_init = knl_uncore_cpu_init, + .pci_init = knl_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun skl_uncore_init __initconst = { + .pci_init = skl_uncore_pci_init, +}; + +static const struct x86_cpu_id intel_uncore_match[] __initconst = { + X86_UNCORE_MODEL_MATCH(26, nhm_uncore_init), /* Nehalem */ + X86_UNCORE_MODEL_MATCH(30, nhm_uncore_init), + X86_UNCORE_MODEL_MATCH(37, nhm_uncore_init), /* Westmere */ + X86_UNCORE_MODEL_MATCH(44, nhm_uncore_init), + X86_UNCORE_MODEL_MATCH(42, snb_uncore_init), /* Sandy Bridge */ + X86_UNCORE_MODEL_MATCH(58, ivb_uncore_init), /* Ivy Bridge */ + X86_UNCORE_MODEL_MATCH(60, hsw_uncore_init), /* Haswell */ + X86_UNCORE_MODEL_MATCH(69, hsw_uncore_init), /* Haswell Celeron */ + X86_UNCORE_MODEL_MATCH(70, hsw_uncore_init), /* Haswell */ + X86_UNCORE_MODEL_MATCH(61, bdw_uncore_init), /* Broadwell */ + X86_UNCORE_MODEL_MATCH(71, bdw_uncore_init), /* Broadwell */ + X86_UNCORE_MODEL_MATCH(45, snbep_uncore_init), /* Sandy Bridge-EP */ + X86_UNCORE_MODEL_MATCH(46, nhmex_uncore_init), /* Nehalem-EX */ + X86_UNCORE_MODEL_MATCH(47, nhmex_uncore_init), /* Westmere-EX aka. Xeon E7 */ + X86_UNCORE_MODEL_MATCH(62, ivbep_uncore_init), /* Ivy Bridge-EP */ + X86_UNCORE_MODEL_MATCH(63, hswep_uncore_init), /* Haswell-EP */ + X86_UNCORE_MODEL_MATCH(79, bdx_uncore_init), /* BDX-EP */ + X86_UNCORE_MODEL_MATCH(86, bdx_uncore_init), /* BDX-DE */ + X86_UNCORE_MODEL_MATCH(87, knl_uncore_init), /* Knights Landing */ + X86_UNCORE_MODEL_MATCH(94, skl_uncore_init), /* SkyLake */ + {}, +}; + +MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); + static int __init intel_uncore_init(void) { - int pret, cret, ret; + const struct x86_cpu_id *id; + struct intel_uncore_init_fun *uncore_init; + int pret = 0, cret = 0, ret; - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + id = x86_match_cpu(intel_uncore_match); + if (!id) return -ENODEV; - if (cpu_has_hypervisor) + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) return -ENODEV; max_packages = topology_max_packages(); - pret = uncore_pci_init(); - cret = uncore_cpu_init(); + uncore_init = (struct intel_uncore_init_fun *)id->driver_data; + if (uncore_init->pci_init) { + pret = uncore_init->pci_init(); + if (!pret) + pret = uncore_pci_init(); + } + + if (uncore_init->cpu_init) { + uncore_init->cpu_init(); + cret = uncore_cpu_init(); + } if (cret && pret) return -ENODEV; @@ -1409,4 +1435,14 @@ err: cpu_notifier_register_done(); return ret; } -device_initcall(intel_uncore_init); +module_init(intel_uncore_init); + +static void __exit intel_uncore_exit(void) +{ + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&uncore_cpu_nb); + uncore_types_exit(uncore_msr_uncores); + uncore_pci_exit(); + cpu_notifier_register_done(); +} +module_exit(intel_uncore_exit); diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index ab2bcaa..b262586 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -219,6 +219,9 @@ #define KNL_CHA_MSR_PMON_BOX_FILTER_TID 0x1ff #define KNL_CHA_MSR_PMON_BOX_FILTER_STATE (7 << 18) #define KNL_CHA_MSR_PMON_BOX_FILTER_OP (0xfffffe2aULL << 32) +#define KNL_CHA_MSR_PMON_BOX_FILTER_REMOTE_NODE (0x1ULL << 32) +#define KNL_CHA_MSR_PMON_BOX_FILTER_LOCAL_NODE (0x1ULL << 33) +#define KNL_CHA_MSR_PMON_BOX_FILTER_NNC (0x1ULL << 37) /* KNL EDC/MC UCLK */ #define KNL_UCLK_MSR_PMON_CTR0_LOW 0x400 @@ -1902,6 +1905,10 @@ static int knl_cha_hw_config(struct intel_uncore_box *box, reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 + KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx; reg1->config = event->attr.config1 & knl_cha_filter_mask(idx); + + reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_REMOTE_NODE; + reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_LOCAL_NODE; + reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_NNC; reg1->idx = idx; } return 0; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index ec863b9..85ef3c2 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -6,6 +6,8 @@ enum perf_msr_id { PERF_MSR_MPERF = 2, PERF_MSR_PPERF = 3, PERF_MSR_SMI = 4, + PERF_MSR_PTSC = 5, + PERF_MSR_IRPERF = 6, PERF_MSR_EVENT_MAX, }; @@ -15,6 +17,16 @@ static bool test_aperfmperf(int idx) return boot_cpu_has(X86_FEATURE_APERFMPERF); } +static bool test_ptsc(int idx) +{ + return boot_cpu_has(X86_FEATURE_PTSC); +} + +static bool test_irperf(int idx) +{ + return boot_cpu_has(X86_FEATURE_IRPERF); +} + static bool test_intel(int idx) { if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || @@ -69,18 +81,22 @@ struct perf_msr { bool (*test)(int idx); }; -PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00"); -PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01"); -PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02"); -PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03"); -PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04"); +PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00"); +PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01"); +PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02"); +PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03"); +PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04"); +PMU_EVENT_ATTR_STRING(ptsc, evattr_ptsc, "event=0x05"); +PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06"); static struct perf_msr msr[] = { - [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, }, - [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, }, - [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, }, - [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, }, - [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, }, + [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, }, + [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, }, + [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, }, + [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, }, + [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, }, + [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &evattr_ptsc, test_ptsc, }, + [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &evattr_irperf, test_irperf, }, }; static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = { @@ -166,7 +182,7 @@ again: if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) delta = sign_extend64(delta, 31); - local64_add(now - prev, &event->count); + local64_add(delta, &event->count); } static void msr_event_start(struct perf_event *event, int flags) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ad4dc7f..8bd764d 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -601,6 +601,7 @@ struct x86_pmu { u64 lbr_sel_mask; /* LBR_SELECT valid bits */ const int *lbr_sel_map; /* lbr_select mappings */ bool lbr_double_abort; /* duplicated lbr aborts */ + bool lbr_pt_coexist; /* LBR may coexist with PT */ /* * Intel PT/LBR/BTS are exclusive @@ -859,6 +860,8 @@ extern struct event_constraint intel_atom_pebs_event_constraints[]; extern struct event_constraint intel_slm_pebs_event_constraints[]; +extern struct event_constraint intel_glm_pebs_event_constraints[]; + extern struct event_constraint intel_nehalem_pebs_event_constraints[]; extern struct event_constraint intel_westmere_pebs_event_constraints[]; @@ -907,6 +910,8 @@ void intel_pmu_lbr_init_nhm(void); void intel_pmu_lbr_init_atom(void); +void intel_pmu_lbr_init_slm(void); + void intel_pmu_lbr_init_snb(void); void intel_pmu_lbr_init_hsw(void); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 0552884..2f29f4e 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -357,7 +357,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, put_user_ex(ptr_to_compat(&frame->uc), &frame->puc); /* Create the ucontext. */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); else put_user_ex(0, &frame->uc.uc_flags); diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 99afb66..e77a644 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -1,11 +1,12 @@ #ifndef _ASM_X86_ALTERNATIVE_H #define _ASM_X86_ALTERNATIVE_H +#ifndef __ASSEMBLY__ + #include <linux/types.h> #include <linux/stddef.h> #include <linux/stringify.h> #include <asm/asm.h> -#include <asm/ptrace.h> /* * Alternative inline assembly for SMP. @@ -233,36 +234,6 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr -struct paravirt_patch_site; -#ifdef CONFIG_PARAVIRT -void apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end); -#else -static inline void apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end) -{} -#define __parainstructions NULL -#define __parainstructions_end NULL -#endif - -extern void *text_poke_early(void *addr, const void *opcode, size_t len); - -/* - * Clear and restore the kernel write-protection flag on the local CPU. - * Allows the kernel to edit read-only pages. - * Side-effect: any interrupt handler running between save and restore will have - * the ability to write to read-only pages. - * - * Warning: - * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and - * no thread can be preempted in the instructions being modified (no iret to an - * invalid instruction possible) or if the instructions are changed from a - * consistent state to another consistent state atomically. - * On the local CPU you need to be protected again NMI or MCE handlers seeing an - * inconsistent instruction while you patch. - */ -extern void *text_poke(void *addr, const void *opcode, size_t len); -extern int poke_int3_handler(struct pt_regs *regs); -extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); +#endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 98f25bb..bc27611 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -239,10 +239,10 @@ extern void __init check_x2apic(void); extern void x2apic_setup(void); static inline int x2apic_enabled(void) { - return cpu_has_x2apic && apic_is_x2apic_enabled(); + return boot_cpu_has(X86_FEATURE_X2APIC) && apic_is_x2apic_enabled(); } -#define x2apic_supported() (cpu_has_x2apic) +#define x2apic_supported() (boot_cpu_has(X86_FEATURE_X2APIC)) #else /* !CONFIG_X86_X2APIC */ static inline void check_x2apic(void) { } static inline void x2apic_setup(void) { } diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 6b8d6e8..abd06b1 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -12,29 +12,46 @@ /* Minimum kernel alignment, as a power of two */ #ifdef CONFIG_X86_64 -#define MIN_KERNEL_ALIGN_LG2 PMD_SHIFT +# define MIN_KERNEL_ALIGN_LG2 PMD_SHIFT #else -#define MIN_KERNEL_ALIGN_LG2 (PAGE_SHIFT + THREAD_SIZE_ORDER) +# define MIN_KERNEL_ALIGN_LG2 (PAGE_SHIFT + THREAD_SIZE_ORDER) #endif #define MIN_KERNEL_ALIGN (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2) #if (CONFIG_PHYSICAL_ALIGN & (CONFIG_PHYSICAL_ALIGN-1)) || \ (CONFIG_PHYSICAL_ALIGN < MIN_KERNEL_ALIGN) -#error "Invalid value for CONFIG_PHYSICAL_ALIGN" +# error "Invalid value for CONFIG_PHYSICAL_ALIGN" #endif #ifdef CONFIG_KERNEL_BZIP2 -#define BOOT_HEAP_SIZE 0x400000 +# define BOOT_HEAP_SIZE 0x400000 #else /* !CONFIG_KERNEL_BZIP2 */ - -#define BOOT_HEAP_SIZE 0x10000 - -#endif /* !CONFIG_KERNEL_BZIP2 */ +# define BOOT_HEAP_SIZE 0x10000 +#endif #ifdef CONFIG_X86_64 -#define BOOT_STACK_SIZE 0x4000 -#else -#define BOOT_STACK_SIZE 0x1000 +# define BOOT_STACK_SIZE 0x4000 + +# define BOOT_INIT_PGT_SIZE (6*4096) +# ifdef CONFIG_RANDOMIZE_BASE +/* + * Assuming all cross the 512GB boundary: + * 1 page for level4 + * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel + * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP). + * Total is 19 pages. + */ +# ifdef CONFIG_X86_VERBOSE_BOOTUP +# define BOOT_PGT_SIZE (19*4096) +# else /* !CONFIG_X86_VERBOSE_BOOTUP */ +# define BOOT_PGT_SIZE (17*4096) +# endif +# else /* !CONFIG_RANDOMIZE_BASE */ +# define BOOT_PGT_SIZE BOOT_INIT_PGT_SIZE +# endif + +#else /* !CONFIG_X86_64 */ +# define BOOT_STACK_SIZE 0x1000 #endif #endif /* _ASM_X86_BOOT_H */ diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h index d194266..eae33c7 100644 --- a/arch/x86/include/asm/clocksource.h +++ b/arch/x86/include/asm/clocksource.h @@ -3,11 +3,10 @@ #ifndef _ASM_X86_CLOCKSOURCE_H #define _ASM_X86_CLOCKSOURCE_H -#define VCLOCK_NONE 0 /* No vDSO clock available. */ -#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */ -#define VCLOCK_HPET 2 /* vDSO should use vread_hpet. */ -#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */ -#define VCLOCK_MAX 3 +#define VCLOCK_NONE 0 /* No vDSO clock available. */ +#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */ +#define VCLOCK_PVCLOCK 2 /* vDSO should use vread_pvclock. */ +#define VCLOCK_MAX 2 struct arch_clocksource_data { int vclock_mode; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index ebb102e..5a3b2c1 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -307,7 +307,7 @@ static inline void __user *arch_compat_alloc_user_space(long len) return (void __user *)round_down(sp - len, 16); } -static inline bool is_x32_task(void) +static inline bool in_x32_syscall(void) { #ifdef CONFIG_X86_X32_ABI if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT) @@ -318,7 +318,7 @@ static inline bool is_x32_task(void) static inline bool in_compat_syscall(void) { - return is_ia32_task() || is_x32_task(); + return in_ia32_syscall() || in_x32_syscall(); } #define in_compat_syscall in_compat_syscall /* override the generic impl */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 3636ec0..25ebb54 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -27,6 +27,7 @@ enum cpuid_leafs CPUID_6_EAX, CPUID_8000_000A_EDX, CPUID_7_ECX, + CPUID_8000_0007_EBX, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -118,31 +119,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) -#define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU) -#define cpu_has_pse boot_cpu_has(X86_FEATURE_PSE) -#define cpu_has_tsc boot_cpu_has(X86_FEATURE_TSC) -#define cpu_has_pge boot_cpu_has(X86_FEATURE_PGE) -#define cpu_has_apic boot_cpu_has(X86_FEATURE_APIC) -#define cpu_has_fxsr boot_cpu_has(X86_FEATURE_FXSR) -#define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM) -#define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2) -#define cpu_has_aes boot_cpu_has(X86_FEATURE_AES) -#define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX) -#define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2) -#define cpu_has_clflush boot_cpu_has(X86_FEATURE_CLFLUSH) -#define cpu_has_gbpages boot_cpu_has(X86_FEATURE_GBPAGES) -#define cpu_has_arch_perfmon boot_cpu_has(X86_FEATURE_ARCH_PERFMON) -#define cpu_has_pat boot_cpu_has(X86_FEATURE_PAT) -#define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC) -#define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) -#define cpu_has_xsaves boot_cpu_has(X86_FEATURE_XSAVES) -#define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE) -#define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) -/* - * Do not add any more of those clumsy macros - use static_cpu_has() for - * fast paths and boot_cpu_has() otherwise! - */ - #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS) /* * Static testing of CPU features. Used the same as boot_cpu_has(). diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 8f9afef..4a41348 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -12,7 +12,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 17 /* N 32-bit words worth of info */ +#define NCAPINTS 18 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -177,6 +177,7 @@ #define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */ #define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ #define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* performance time-stamp counter */ #define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ #define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ @@ -250,6 +251,7 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ #define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+1) /* Instructions Retired Count */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -280,6 +282,11 @@ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */ + /* * BUG word(s) */ @@ -294,6 +301,9 @@ #define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ +#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ + #ifdef CONFIG_X86_32 /* diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 53748c4..78d1e74 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -3,6 +3,7 @@ #include <asm/fpu/api.h> #include <asm/pgtable.h> +#include <asm/processor-flags.h> #include <asm/tlb.h> /* @@ -28,33 +29,22 @@ #define MAX_CMDLINE_ADDRESS UINT_MAX -#ifdef CONFIG_X86_32 +#define ARCH_EFI_IRQ_FLAGS_MASK X86_EFLAGS_IF +#ifdef CONFIG_X86_32 extern unsigned long asmlinkage efi_call_phys(void *, ...); +#define arch_efi_call_virt_setup() kernel_fpu_begin() +#define arch_efi_call_virt_teardown() kernel_fpu_end() + /* * Wrap all the virtual calls in a way that forces the parameters on the stack. */ - -/* Use this macro if your virtual returns a non-void value */ -#define efi_call_virt(f, args...) \ +#define arch_efi_call_virt(f, args...) \ ({ \ - efi_status_t __s; \ - kernel_fpu_begin(); \ - __s = ((efi_##f##_t __attribute__((regparm(0)))*) \ - efi.systab->runtime->f)(args); \ - kernel_fpu_end(); \ - __s; \ -}) - -/* Use this macro if your virtual call does not return any value */ -#define __efi_call_virt(f, args...) \ -({ \ - kernel_fpu_begin(); \ ((efi_##f##_t __attribute__((regparm(0)))*) \ efi.systab->runtime->f)(args); \ - kernel_fpu_end(); \ }) #define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) @@ -78,10 +68,8 @@ struct efi_scratch { u64 phys_stack; } __packed; -#define efi_call_virt(f, ...) \ +#define arch_efi_call_virt_setup() \ ({ \ - efi_status_t __s; \ - \ efi_sync_low_kernel_mappings(); \ preempt_disable(); \ __kernel_fpu_begin(); \ @@ -91,9 +79,13 @@ struct efi_scratch { write_cr3((unsigned long)efi_scratch.efi_pgt); \ __flush_tlb_all(); \ } \ - \ - __s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__); \ - \ +}) + +#define arch_efi_call_virt(f, args...) \ + efi_call((void *)efi.systab->runtime->f, args) \ + +#define arch_efi_call_virt_teardown() \ +({ \ if (efi_scratch.use_pgd) { \ write_cr3(efi_scratch.prev_cr3); \ __flush_tlb_all(); \ @@ -101,15 +93,8 @@ struct efi_scratch { \ __kernel_fpu_end(); \ preempt_enable(); \ - __s; \ }) -/* - * All X86_64 virt calls return non-void values. Thus, use non-void call for - * virt calls that would be void on X86_32. - */ -#define __efi_call_virt(f, args...) efi_call_virt(f, args) - extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, u32 type, u64 attribute); @@ -180,6 +165,8 @@ static inline bool efi_runtime_supported(void) extern struct console early_efi_console; extern void parse_efi_setup(u64 phys_addr, u32 data_len); +extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); + #ifdef CONFIG_EFI_MIXED extern void efi_thunk_runtime_setup(void); extern efi_status_t efi_thunk_set_virtual_address_map( @@ -225,6 +212,11 @@ __pure const struct efi_config *__efi_early(void); #define efi_call_early(f, ...) \ __efi_early()->call(__efi_early()->f, __VA_ARGS__); +#define __efi_call_early(f, ...) \ + __efi_early()->call((unsigned long)f, __VA_ARGS__); + +#define efi_is_64bit() __efi_early()->is64 + extern bool efi_reboot_required(void); #else diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 15340e3..fea7724 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -176,7 +176,7 @@ static inline void elf_common_init(struct thread_struct *t, regs->si = regs->di = regs->bp = 0; regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0; regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; - t->fs = t->gs = 0; + t->fsbase = t->gsbase = 0; t->fsindex = t->gsindex = 0; t->ds = t->es = ds; } @@ -226,8 +226,8 @@ do { \ (pr_reg)[18] = (regs)->flags; \ (pr_reg)[19] = (regs)->sp; \ (pr_reg)[20] = (regs)->ss; \ - (pr_reg)[21] = current->thread.fs; \ - (pr_reg)[22] = current->thread.gs; \ + (pr_reg)[21] = current->thread.fsbase; \ + (pr_reg)[22] = current->thread.gsbase; \ asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v; \ asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v; \ asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v; \ diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index e6a8613..3a10616 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -4,7 +4,7 @@ #include <asm/page.h> #include <asm-generic/hugetlb.h> -#define hugepages_supported() cpu_has_pse +#define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE) static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h index d0afb05..f706041 100644 --- a/arch/x86/include/asm/irq_work.h +++ b/arch/x86/include/asm/irq_work.h @@ -5,7 +5,7 @@ static inline bool arch_irq_work_has_interrupt(void) { - return cpu_has_apic; + return boot_cpu_has(X86_FEATURE_APIC); } #endif /* _ASM_IRQ_WORK_H */ diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h index 332f98c..22a8537 100644 --- a/arch/x86/include/asm/kgdb.h +++ b/arch/x86/include/asm/kgdb.h @@ -6,6 +6,8 @@ * Copyright (C) 2008 Wind River Systems, Inc. */ +#include <asm/ptrace.h> + /* * BUFMAX defines the maximum number of characters in inbound/outbound * buffers at least NUMREGBYTES*2 are needed for register packets diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 79327e9..0ccb26d 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -8,40 +8,6 @@ #ifdef CONFIG_X86_32 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0))) - -/* - * Make sure the compiler doesn't do anything stupid with the - * arguments on the stack - they are owned by the *caller*, not - * the callee. This just fools gcc into not spilling into them, - * and keeps it from doing tailcall recursion and/or using the - * stack slots for temporaries, since they are live and "used" - * all the way to the end of the function. - * - * NOTE! On x86-64, all the arguments are in registers, so this - * only matters on a 32-bit kernel. - */ -#define asmlinkage_protect(n, ret, args...) \ - __asmlinkage_protect##n(ret, ##args) -#define __asmlinkage_protect_n(ret, args...) \ - __asm__ __volatile__ ("" : "=r" (ret) : "0" (ret), ##args) -#define __asmlinkage_protect0(ret) \ - __asmlinkage_protect_n(ret) -#define __asmlinkage_protect1(ret, arg1) \ - __asmlinkage_protect_n(ret, "m" (arg1)) -#define __asmlinkage_protect2(ret, arg1, arg2) \ - __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2)) -#define __asmlinkage_protect3(ret, arg1, arg2, arg3) \ - __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3)) -#define __asmlinkage_protect4(ret, arg1, arg2, arg3, arg4) \ - __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ - "m" (arg4)) -#define __asmlinkage_protect5(ret, arg1, arg2, arg3, arg4, arg5) \ - __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ - "m" (arg4), "m" (arg5)) -#define __asmlinkage_protect6(ret, arg1, arg2, arg3, arg4, arg5, arg6) \ - __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ - "m" (arg4), "m" (arg5), "m" (arg6)) - #endif /* CONFIG_X86_32 */ #ifdef __ASSEMBLY__ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 92b6f65..8bf766e 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -104,13 +104,23 @@ #define MCE_LOG_SIGNATURE "MACHINECHECK" /* AMD Scalable MCA */ +#define MSR_AMD64_SMCA_MC0_CTL 0xc0002000 +#define MSR_AMD64_SMCA_MC0_STATUS 0xc0002001 +#define MSR_AMD64_SMCA_MC0_ADDR 0xc0002002 #define MSR_AMD64_SMCA_MC0_MISC0 0xc0002003 #define MSR_AMD64_SMCA_MC0_CONFIG 0xc0002004 #define MSR_AMD64_SMCA_MC0_IPID 0xc0002005 +#define MSR_AMD64_SMCA_MC0_DESTAT 0xc0002008 +#define MSR_AMD64_SMCA_MC0_DEADDR 0xc0002009 #define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a +#define MSR_AMD64_SMCA_MCx_CTL(x) (MSR_AMD64_SMCA_MC0_CTL + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_STATUS(x) (MSR_AMD64_SMCA_MC0_STATUS + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_ADDR(x) (MSR_AMD64_SMCA_MC0_ADDR + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_MISC(x) (MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_CONFIG(x) (MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_IPID(x) (MSR_AMD64_SMCA_MC0_IPID + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_DESTAT(x) (MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_DEADDR(x) (MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x))) /* @@ -168,9 +178,18 @@ struct mce_vendor_flags { __reserved_0 : 61; }; + +struct mca_msr_regs { + u32 (*ctl) (int bank); + u32 (*status) (int bank); + u32 (*addr) (int bank); + u32 (*misc) (int bank); +}; + extern struct mce_vendor_flags mce_flags; extern struct mca_config mca_cfg; +extern struct mca_msr_regs msr_ops; extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 8428002..39634819 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -115,103 +115,12 @@ static inline void destroy_context(struct mm_struct *mm) destroy_context_ldt(mm); } -static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, - struct task_struct *tsk) -{ - unsigned cpu = smp_processor_id(); +extern void switch_mm(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk); - if (likely(prev != next)) { -#ifdef CONFIG_SMP - this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); - this_cpu_write(cpu_tlbstate.active_mm, next); -#endif - cpumask_set_cpu(cpu, mm_cpumask(next)); - - /* - * Re-load page tables. - * - * This logic has an ordering constraint: - * - * CPU 0: Write to a PTE for 'next' - * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. - * CPU 1: set bit 1 in next's mm_cpumask - * CPU 1: load from the PTE that CPU 0 writes (implicit) - * - * We need to prevent an outcome in which CPU 1 observes - * the new PTE value and CPU 0 observes bit 1 clear in - * mm_cpumask. (If that occurs, then the IPI will never - * be sent, and CPU 0's TLB will contain a stale entry.) - * - * The bad outcome can occur if either CPU's load is - * reordered before that CPU's store, so both CPUs must - * execute full barriers to prevent this from happening. - * - * Thus, switch_mm needs a full barrier between the - * store to mm_cpumask and any operation that could load - * from next->pgd. TLB fills are special and can happen - * due to instruction fetches or for no reason at all, - * and neither LOCK nor MFENCE orders them. - * Fortunately, load_cr3() is serializing and gives the - * ordering guarantee we need. - * - */ - load_cr3(next->pgd); - - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); - - /* Stop flush ipis for the previous mm */ - cpumask_clear_cpu(cpu, mm_cpumask(prev)); - - /* Load per-mm CR4 state */ - load_mm_cr4(next); - -#ifdef CONFIG_MODIFY_LDT_SYSCALL - /* - * Load the LDT, if the LDT is different. - * - * It's possible that prev->context.ldt doesn't match - * the LDT register. This can happen if leave_mm(prev) - * was called and then modify_ldt changed - * prev->context.ldt but suppressed an IPI to this CPU. - * In this case, prev->context.ldt != NULL, because we - * never set context.ldt to NULL while the mm still - * exists. That means that next->context.ldt != - * prev->context.ldt, because mms never share an LDT. - */ - if (unlikely(prev->context.ldt != next->context.ldt)) - load_mm_ldt(next); -#endif - } -#ifdef CONFIG_SMP - else { - this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); - BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next); - - if (!cpumask_test_cpu(cpu, mm_cpumask(next))) { - /* - * On established mms, the mm_cpumask is only changed - * from irq context, from ptep_clear_flush() while in - * lazy tlb mode, and here. Irqs are blocked during - * schedule, protecting us from simultaneous changes. - */ - cpumask_set_cpu(cpu, mm_cpumask(next)); - - /* - * We were in lazy tlb mode and leave_mm disabled - * tlb flush IPI delivery. We must reload CR3 - * to make sure to use no freed page tables. - * - * As above, load_cr3() is serializing and orders TLB - * fills with respect to the mm_cpumask write. - */ - load_cr3(next->pgd); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); - load_mm_cr4(next); - load_mm_ldt(next); - } - } -#endif -} +extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk); +#define switch_mm_irqs_off switch_mm_irqs_off #define activate_mm(prev, next) \ do { \ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 5b3c9a5..5a73a9c 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -89,27 +89,16 @@ #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 #define MSR_IA32_RTIT_CTL 0x00000570 -#define RTIT_CTL_TRACEEN BIT(0) -#define RTIT_CTL_CYCLEACC BIT(1) -#define RTIT_CTL_OS BIT(2) -#define RTIT_CTL_USR BIT(3) -#define RTIT_CTL_CR3EN BIT(7) -#define RTIT_CTL_TOPA BIT(8) -#define RTIT_CTL_MTC_EN BIT(9) -#define RTIT_CTL_TSC_EN BIT(10) -#define RTIT_CTL_DISRETC BIT(11) -#define RTIT_CTL_BRANCH_EN BIT(13) -#define RTIT_CTL_MTC_RANGE_OFFSET 14 -#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) -#define RTIT_CTL_CYC_THRESH_OFFSET 19 -#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET) -#define RTIT_CTL_PSB_FREQ_OFFSET 24 -#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET) #define MSR_IA32_RTIT_STATUS 0x00000571 -#define RTIT_STATUS_CONTEXTEN BIT(1) -#define RTIT_STATUS_TRIGGEREN BIT(2) -#define RTIT_STATUS_ERROR BIT(4) -#define RTIT_STATUS_STOPPED BIT(5) +#define MSR_IA32_RTIT_STATUS 0x00000571 +#define MSR_IA32_RTIT_ADDR0_A 0x00000580 +#define MSR_IA32_RTIT_ADDR0_B 0x00000581 +#define MSR_IA32_RTIT_ADDR1_A 0x00000582 +#define MSR_IA32_RTIT_ADDR1_B 0x00000583 +#define MSR_IA32_RTIT_ADDR2_A 0x00000584 +#define MSR_IA32_RTIT_ADDR2_B 0x00000585 +#define MSR_IA32_RTIT_ADDR3_A 0x00000586 +#define MSR_IA32_RTIT_ADDR3_B 0x00000587 #define MSR_IA32_RTIT_CR3_MATCH 0x00000572 #define MSR_IA32_RTIT_OUTPUT_BASE 0x00000560 #define MSR_IA32_RTIT_OUTPUT_MASK 0x00000561 @@ -205,6 +194,8 @@ #define MSR_CONFIG_TDP_CONTROL 0x0000064B #define MSR_TURBO_ACTIVATION_RATIO 0x0000064C +#define MSR_PLATFORM_ENERGY_STATUS 0x0000064D + #define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658 #define MSR_PKG_ANY_CORE_C0_RES 0x00000659 #define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A @@ -315,6 +306,9 @@ #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +/* Fam 17h MSRs */ +#define MSR_F17H_IRPERF 0xc00000e9 + /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 @@ -328,6 +322,7 @@ #define MSR_F15H_PERF_CTR 0xc0010201 #define MSR_F15H_NB_PERF_CTL 0xc0010240 #define MSR_F15H_NB_PERF_CTR 0xc0010241 +#define MSR_F15H_PTSC 0xc0010280 #define MSR_F15H_IC_CFG 0xc0011021 /* Fam 10h MSRs */ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 7a79ee2..7dc1d8f 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -84,7 +84,10 @@ static inline unsigned long long native_read_msr(unsigned int msr) { DECLARE_ARGS(val, low, high); - asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr)); + asm volatile("1: rdmsr\n" + "2:\n" + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe) + : EAX_EDX_RET(val, low, high) : "c" (msr)); if (msr_tracepoint_active(__tracepoint_read_msr)) do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); @@ -98,7 +101,10 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, asm volatile("2: rdmsr ; xor %[err],%[err]\n" "1:\n\t" ".section .fixup,\"ax\"\n\t" - "3: mov %[fault],%[err] ; jmp 1b\n\t" + "3: mov %[fault],%[err]\n\t" + "xorl %%eax, %%eax\n\t" + "xorl %%edx, %%edx\n\t" + "jmp 1b\n\t" ".previous\n\t" _ASM_EXTABLE(2b, 3b) : [err] "=r" (*err), EAX_EDX_RET(val, low, high) @@ -108,10 +114,14 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, return EAX_EDX_VAL(val, low, high); } -static inline void native_write_msr(unsigned int msr, - unsigned low, unsigned high) +/* Can be uninlined because referenced by paravirt */ +notrace static inline void native_write_msr(unsigned int msr, + unsigned low, unsigned high) { - asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory"); + asm volatile("1: wrmsr\n" + "2:\n" + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe) + : : "c" (msr), "a"(low), "d" (high) : "memory"); if (msr_tracepoint_active(__tracepoint_read_msr)) do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index b94f6f6..dbff145 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -24,6 +24,7 @@ #define _ASM_X86_MTRR_H #include <uapi/asm/mtrr.h> +#include <asm/pat.h> /* @@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn) static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) { } +static inline void mtrr_bp_init(void) +{ + pat_disable("MTRRs disabled, skipping PAT initialization too."); +} #define mtrr_ap_init() do {} while (0) -#define mtrr_bp_init() do {} while (0) #define set_mtrr_aps_delayed_init() do {} while (0) #define mtrr_aps_init() do {} while (0) #define mtrr_bp_restore() do {} while (0) diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index 802dde3..cf8f619 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -37,7 +37,10 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE +#ifndef __pa #define __pa(x) __phys_addr((unsigned long)(x)) +#endif + #define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x)) /* __pa_symbol should be used for C visible symbols. This seems to be the official gcc blessed way to do such arithmetic. */ @@ -51,7 +54,9 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, #define __pa_symbol(x) \ __phys_addr_symbol(__phys_reloc_hide((unsigned long)(x))) +#ifndef __va #define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) +#endif #define __boot_va(x) __va(x) #define __boot_pa(x) __pa(x) diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 4928cf0..d5c2f8b 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -47,12 +47,10 @@ * are fully set up. If kernel ASLR is configured, it can extend the * kernel page table mapping, reducing the size of the modules area. */ -#define KERNEL_IMAGE_SIZE_DEFAULT (512 * 1024 * 1024) -#if defined(CONFIG_RANDOMIZE_BASE) && \ - CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE_DEFAULT -#define KERNEL_IMAGE_SIZE CONFIG_RANDOMIZE_BASE_MAX_OFFSET +#if defined(CONFIG_RANDOMIZE_BASE) +#define KERNEL_IMAGE_SIZE (1024 * 1024 * 1024) #else -#define KERNEL_IMAGE_SIZE KERNEL_IMAGE_SIZE_DEFAULT +#define KERNEL_IMAGE_SIZE (512 * 1024 * 1024) #endif #endif /* _ASM_X86_PAGE_64_DEFS_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 601f1b8..2970d22 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -15,17 +15,6 @@ #include <linux/cpumask.h> #include <asm/frame.h> -static inline int paravirt_enabled(void) -{ - return pv_info.paravirt_enabled; -} - -static inline int paravirt_has_feature(unsigned int feature) -{ - WARN_ON_ONCE(!pv_info.paravirt_enabled); - return (pv_info.features & feature); -} - static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) { @@ -130,21 +119,31 @@ static inline void wbinvd(void) #define get_kernel_rpl() (pv_info.kernel_rpl) -static inline u64 paravirt_read_msr(unsigned msr, int *err) +static inline u64 paravirt_read_msr(unsigned msr) +{ + return PVOP_CALL1(u64, pv_cpu_ops.read_msr, msr); +} + +static inline void paravirt_write_msr(unsigned msr, + unsigned low, unsigned high) +{ + return PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high); +} + +static inline u64 paravirt_read_msr_safe(unsigned msr, int *err) { - return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err); + return PVOP_CALL2(u64, pv_cpu_ops.read_msr_safe, msr, err); } -static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high) +static inline int paravirt_write_msr_safe(unsigned msr, + unsigned low, unsigned high) { - return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high); + return PVOP_CALL3(int, pv_cpu_ops.write_msr_safe, msr, low, high); } -/* These should all do BUG_ON(_err), but our headers are too tangled. */ #define rdmsr(msr, val1, val2) \ do { \ - int _err; \ - u64 _l = paravirt_read_msr(msr, &_err); \ + u64 _l = paravirt_read_msr(msr); \ val1 = (u32)_l; \ val2 = _l >> 32; \ } while (0) @@ -156,8 +155,7 @@ do { \ #define rdmsrl(msr, val) \ do { \ - int _err; \ - val = paravirt_read_msr(msr, &_err); \ + val = paravirt_read_msr(msr); \ } while (0) static inline void wrmsrl(unsigned msr, u64 val) @@ -165,23 +163,23 @@ static inline void wrmsrl(unsigned msr, u64 val) wrmsr(msr, (u32)val, (u32)(val>>32)); } -#define wrmsr_safe(msr, a, b) paravirt_write_msr(msr, a, b) +#define wrmsr_safe(msr, a, b) paravirt_write_msr_safe(msr, a, b) /* rdmsr with exception handling */ -#define rdmsr_safe(msr, a, b) \ -({ \ - int _err; \ - u64 _l = paravirt_read_msr(msr, &_err); \ - (*a) = (u32)_l; \ - (*b) = _l >> 32; \ - _err; \ +#define rdmsr_safe(msr, a, b) \ +({ \ + int _err; \ + u64 _l = paravirt_read_msr_safe(msr, &_err); \ + (*a) = (u32)_l; \ + (*b) = _l >> 32; \ + _err; \ }) static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) { int err; - *p = paravirt_read_msr(msr, &err); + *p = paravirt_read_msr_safe(msr, &err); return err; } diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index e8c2326..7fa9e77 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -69,15 +69,9 @@ struct pv_info { u16 extra_user_64bit_cs; /* __USER_CS if none */ #endif - int paravirt_enabled; - unsigned int features; /* valid only if paravirt_enabled is set */ const char *name; }; -#define paravirt_has(x) paravirt_has_feature(PV_SUPPORTED_##x) -/* Supported features */ -#define PV_SUPPORTED_RTC (1<<0) - struct pv_init_ops { /* * Patch may replace one of the defined code sequences with @@ -155,10 +149,16 @@ struct pv_cpu_ops { void (*cpuid)(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx); - /* MSR, PMC and TSR operations. - err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */ - u64 (*read_msr)(unsigned int msr, int *err); - int (*write_msr)(unsigned int msr, unsigned low, unsigned high); + /* Unsafe MSR operations. These will warn or panic on failure. */ + u64 (*read_msr)(unsigned int msr); + void (*write_msr)(unsigned int msr, unsigned low, unsigned high); + + /* + * Safe MSR operations. + * read sets err to 0 or -EIO. write returns 0 or -EIO. + */ + u64 (*read_msr_safe)(unsigned int msr, int *err); + int (*write_msr_safe)(unsigned int msr, unsigned low, unsigned high); u64 (*read_pmc)(int counter); diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index ca6c228..0b1ff4c 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -5,8 +5,8 @@ #include <asm/pgtable_types.h> bool pat_enabled(void); +void pat_disable(const char *reason); extern void pat_init(void); -void pat_init_cache_modes(u64); extern int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 97f3242..f86491a 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -183,7 +183,7 @@ static inline int pmd_trans_huge(pmd_t pmd) static inline int has_transparent_hugepage(void) { - return cpu_has_pse; + return boot_cpu_has(X86_FEATURE_PSE); } #ifdef __HAVE_ARCH_PTE_DEVMAP diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 9264476..62c6cc3 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -388,9 +388,16 @@ struct thread_struct { unsigned long ip; #endif #ifdef CONFIG_X86_64 - unsigned long fs; + unsigned long fsbase; + unsigned long gsbase; +#else + /* + * XXX: this could presumably be unsigned short. Alternatively, + * 32-bit kernels could be taught to use fsindex instead. + */ + unsigned long fs; + unsigned long gs; #endif - unsigned long gs; /* Save middle states of ptrace breakpoints */ struct perf_event *ptrace_bps[HBP_NUM]; @@ -473,8 +480,6 @@ static inline unsigned long current_top_of_stack(void) #include <asm/paravirt.h> #else #define __cpuid native_cpuid -#define paravirt_enabled() 0 -#define paravirt_has(x) 0 static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index ceec86eb..453744c 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -99,26 +99,36 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) /* * lock for writing */ -static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) +#define ____down_write(sem, slow_path) \ +({ \ + long tmp; \ + struct rw_semaphore* ret; \ + asm volatile("# beginning down_write\n\t" \ + LOCK_PREFIX " xadd %1,(%3)\n\t" \ + /* adds 0xffff0001, returns the old value */ \ + " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \ + /* was the active mask 0 before? */\ + " jz 1f\n" \ + " call " slow_path "\n" \ + "1:\n" \ + "# ending down_write" \ + : "+m" (sem->count), "=d" (tmp), "=a" (ret) \ + : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \ + : "memory", "cc"); \ + ret; \ +}) + +static inline void __down_write(struct rw_semaphore *sem) { - long tmp; - asm volatile("# beginning down_write\n\t" - LOCK_PREFIX " xadd %1,(%2)\n\t" - /* adds 0xffff0001, returns the old value */ - " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" - /* was the active mask 0 before? */ - " jz 1f\n" - " call call_rwsem_down_write_failed\n" - "1:\n" - "# ending down_write" - : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) - : "memory", "cc"); + ____down_write(sem, "call_rwsem_down_write_failed"); } -static inline void __down_write(struct rw_semaphore *sem) +static inline int __down_write_killable(struct rw_semaphore *sem) { - __down_write_nested(sem, 0); + if (IS_ERR(____down_write(sem, "call_rwsem_down_write_failed_killable"))) + return -EINTR; + + return 0; } /* diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 7d5a192..1549caa0 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -2,6 +2,7 @@ #define _ASM_X86_SEGMENT_H #include <linux/const.h> +#include <asm/alternative.h> /* * Constructor for a conventional segment GDT (or LDT) entry. @@ -207,13 +208,6 @@ #define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) #define __PER_CPU_SEG (GDT_ENTRY_PER_CPU*8 + 3) -/* TLS indexes for 64-bit - hardcoded in arch_prctl(): */ -#define FS_TLS 0 -#define GS_TLS 1 - -#define GS_TLS_SEL ((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3) -#define FS_TLS_SEL ((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3) - #endif #ifndef CONFIG_PARAVIRT @@ -249,10 +243,13 @@ extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDL #endif /* - * Load a segment. Fall back on loading the zero - * segment if something goes wrong.. + * Load a segment. Fall back on loading the zero segment if something goes + * wrong. This variant assumes that loading zero fully clears the segment. + * This is always the case on Intel CPUs and, even on 64-bit AMD CPUs, any + * failure to fully clear the cached descriptor is only observable for + * FS and GS. */ -#define loadsegment(seg, value) \ +#define __loadsegment_simple(seg, value) \ do { \ unsigned short __val = (value); \ \ @@ -269,6 +266,38 @@ do { \ : "+r" (__val) : : "memory"); \ } while (0) +#define __loadsegment_ss(value) __loadsegment_simple(ss, (value)) +#define __loadsegment_ds(value) __loadsegment_simple(ds, (value)) +#define __loadsegment_es(value) __loadsegment_simple(es, (value)) + +#ifdef CONFIG_X86_32 + +/* + * On 32-bit systems, the hidden parts of FS and GS are unobservable if + * the selector is NULL, so there's no funny business here. + */ +#define __loadsegment_fs(value) __loadsegment_simple(fs, (value)) +#define __loadsegment_gs(value) __loadsegment_simple(gs, (value)) + +#else + +static inline void __loadsegment_fs(unsigned short value) +{ + asm volatile(" \n" + "1: movw %0, %%fs \n" + "2: \n" + + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_clear_fs) + + : : "rm" (value) : "memory"); +} + +/* __loadsegment_gs is intentionally undefined. Use load_gs_index instead. */ + +#endif + +#define loadsegment(seg, value) __loadsegment_ ## seg (value) + /* * Save a segment register away: */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 11af24e..ac1d5da 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -6,6 +6,7 @@ #define COMMAND_LINE_SIZE 2048 #include <linux/linkage.h> +#include <asm/page_types.h> #ifdef __i386__ diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 751bf4b..8f321a1 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -39,8 +39,7 @@ do { \ */ \ unsigned long ebx, ecx, edx, esi, edi; \ \ - asm volatile("pushfl\n\t" /* save flags */ \ - "pushl %%ebp\n\t" /* save EBP */ \ + asm volatile("pushl %%ebp\n\t" /* save EBP */ \ "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ @@ -49,7 +48,6 @@ do { \ "jmp __switch_to\n" /* regparm call */ \ "1:\t" \ "popl %%ebp\n\t" /* restore EBP */ \ - "popfl\n" /* restore flags */ \ \ /* output parameters */ \ : [prev_sp] "=m" (prev->thread.sp), \ diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h new file mode 100644 index 0000000..9039506 --- /dev/null +++ b/arch/x86/include/asm/text-patching.h @@ -0,0 +1,40 @@ +#ifndef _ASM_X86_TEXT_PATCHING_H +#define _ASM_X86_TEXT_PATCHING_H + +#include <linux/types.h> +#include <linux/stddef.h> +#include <asm/ptrace.h> + +struct paravirt_patch_site; +#ifdef CONFIG_PARAVIRT +void apply_paravirt(struct paravirt_patch_site *start, + struct paravirt_patch_site *end); +#else +static inline void apply_paravirt(struct paravirt_patch_site *start, + struct paravirt_patch_site *end) +{} +#define __parainstructions NULL +#define __parainstructions_end NULL +#endif + +extern void *text_poke_early(void *addr, const void *opcode, size_t len); + +/* + * Clear and restore the kernel write-protection flag on the local CPU. + * Allows the kernel to edit read-only pages. + * Side-effect: any interrupt handler running between save and restore will have + * the ability to write to read-only pages. + * + * Warning: + * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and + * no thread can be preempted in the instructions being modified (no iret to an + * invalid instruction possible) or if the instructions are changed from a + * consistent state to another consistent state atomically. + * On the local CPU you need to be protected again NMI or MCE handlers seeing an + * inconsistent instruction while you patch. + */ +extern void *text_poke(void *addr, const void *opcode, size_t len); +extern int poke_int3_handler(struct pt_regs *regs); +extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); + +#endif /* _ASM_X86_TEXT_PATCHING_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index ffae84d..30c133a 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -255,7 +255,7 @@ static inline bool test_and_clear_restore_sigmask(void) return true; } -static inline bool is_ia32_task(void) +static inline bool in_ia32_syscall(void) { #ifdef CONFIG_X86_32 return true; diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 1fde8d5..4e5be94 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -181,7 +181,7 @@ static inline void __native_flush_tlb_single(unsigned long addr) static inline void __flush_tlb_all(void) { - if (cpu_has_pge) + if (static_cpu_has(X86_FEATURE_PGE)) __flush_tlb_global(); else __flush_tlb(); diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 174c421..7428697 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -22,7 +22,7 @@ extern void disable_TSC(void); static inline cycles_t get_cycles(void) { #ifndef CONFIG_X86_TSC - if (!cpu_has_tsc) + if (!boot_cpu_has(X86_FEATURE_TSC)) return 0; #endif diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index a969ae6..12f9653 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -108,9 +108,17 @@ struct exception_table_entry { #define ARCH_HAS_RELATIVE_EXTABLE +#define swap_ex_entry_fixup(a, b, tmp, delta) \ + do { \ + (a)->fixup = (b)->fixup + (delta); \ + (b)->fixup = (tmp).fixup - (delta); \ + (a)->handler = (b)->handler + (delta); \ + (b)->handler = (tmp).handler - (delta); \ + } while (0) + extern int fixup_exception(struct pt_regs *regs, int trapnr); extern bool ex_has_fault_handler(unsigned long ip); -extern int early_fixup_exception(unsigned long *ip); +extern void early_fixup_exception(struct pt_regs *regs, int trapnr); /* * These are the main single-value transfer routines. They automatically diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 1ae89a2..4dcdf74 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -142,6 +142,44 @@ struct x86_cpuinit_ops { struct timespec; /** + * struct x86_legacy_devices - legacy x86 devices + * + * @pnpbios: this platform can have a PNPBIOS. If this is disabled the platform + * is known to never have a PNPBIOS. + * + * These are devices known to require LPC or ISA bus. The definition of legacy + * devices adheres to the ACPI 5.2.9.3 IA-PC Boot Architecture flag + * ACPI_FADT_LEGACY_DEVICES. These devices consist of user visible devices on + * the LPC or ISA bus. User visible devices are devices that have end-user + * accessible connectors (for example, LPT parallel port). Legacy devices on + * the LPC bus consist for example of serial and parallel ports, PS/2 keyboard + * / mouse, and the floppy disk controller. A system that lacks all known + * legacy devices can assume all devices can be detected exclusively via + * standard device enumeration mechanisms including the ACPI namespace. + * + * A system which has does not have ACPI_FADT_LEGACY_DEVICES enabled must not + * have any of the legacy devices enumerated below present. + */ +struct x86_legacy_devices { + int pnpbios; +}; + +/** + * struct x86_legacy_features - legacy x86 features + * + * @rtc: this device has a CMOS real-time clock present + * @ebda_search: it's safe to search for the EBDA signature in the hardware's + * low RAM + * @devices: legacy x86 devices, refer to struct x86_legacy_devices + * documentation for further details. + */ +struct x86_legacy_features { + int rtc; + int ebda_search; + struct x86_legacy_devices devices; +}; + +/** * struct x86_platform_ops - platform specific runtime functions * @calibrate_tsc: calibrate TSC * @get_wallclock: get time from HW clock like RTC etc. @@ -152,6 +190,14 @@ struct timespec; * @save_sched_clock_state: save state for sched_clock() on suspend * @restore_sched_clock_state: restore state for sched_clock() on resume * @apic_post_init: adjust apic if neeeded + * @legacy: legacy features + * @set_legacy_features: override legacy features. Use of this callback + * is highly discouraged. You should only need + * this if your hardware platform requires further + * custom fine tuning far beyong what may be + * possible in x86_early_init_platform_quirks() by + * only using the current x86_hardware_subarch + * semantics. */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); @@ -165,6 +211,8 @@ struct x86_platform_ops { void (*save_sched_clock_state)(void); void (*restore_sched_clock_state)(void); void (*apic_post_init)(void); + struct x86_legacy_features legacy; + void (*set_legacy_features)(void); }; struct pci_dev; @@ -186,6 +234,8 @@ extern struct x86_cpuinit_ops x86_cpuinit; extern struct x86_platform_ops x86_platform; extern struct x86_msi_ops x86_msi; extern struct x86_io_apic_ops x86_io_apic_ops; + +extern void x86_early_init_platform_quirks(void); extern void x86_init_noop(void); extern void x86_init_uint_noop(unsigned int unused); diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index c54beb4..635eac5 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -550,7 +550,7 @@ static struct xor_block_template xor_block_pIII_sse = { #define XOR_TRY_TEMPLATES \ do { \ AVX_XOR_SPEED; \ - if (cpu_has_xmm) { \ + if (boot_cpu_has(X86_FEATURE_XMM)) { \ xor_speed(&xor_block_pIII_sse); \ xor_speed(&xor_block_sse_pf64); \ } else if (boot_cpu_has(X86_FEATURE_MMX)) { \ diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h index 7c0a517..22a7b18 100644 --- a/arch/x86/include/asm/xor_avx.h +++ b/arch/x86/include/asm/xor_avx.h @@ -167,12 +167,12 @@ static struct xor_block_template xor_block_avx = { #define AVX_XOR_SPEED \ do { \ - if (cpu_has_avx && cpu_has_osxsave) \ + if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE)) \ xor_speed(&xor_block_avx); \ } while (0) #define AVX_SELECT(FASTEST) \ - (cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST) + (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE) ? &xor_block_avx : FASTEST) #else diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 3292543..c18ce67 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -157,7 +157,46 @@ struct boot_params { __u8 _pad9[276]; /* 0xeec */ } __attribute__((packed)); -enum { +/** + * enum x86_hardware_subarch - x86 hardware subarchitecture + * + * The x86 hardware_subarch and hardware_subarch_data were added as of the x86 + * boot protocol 2.07 to help distinguish and support custom x86 boot + * sequences. This enum represents accepted values for the x86 + * hardware_subarch. Custom x86 boot sequences (not X86_SUBARCH_PC) do not + * have or simply *cannot* make use of natural stubs like BIOS or EFI, the + * hardware_subarch can be used on the Linux entry path to revector to a + * subarchitecture stub when needed. This subarchitecture stub can be used to + * set up Linux boot parameters or for special care to account for nonstandard + * handling of page tables. + * + * These enums should only ever be used by x86 code, and the code that uses + * it should be well contained and compartamentalized. + * + * KVM and Xen HVM do not have a subarch as these are expected to follow + * standard x86 boot entries. If there is a genuine need for "hypervisor" type + * that should be considered separately in the future. Future guest types + * should seriously consider working with standard x86 boot stubs such as + * the BIOS or EFI boot stubs. + * + * WARNING: this enum is only used for legacy hacks, for platform features that + * are not easily enumerated or discoverable. You should not ever use + * this for new features. + * + * @X86_SUBARCH_PC: Should be used if the hardware is enumerable using standard + * PC mechanisms (PCI, ACPI) and doesn't need a special boot flow. + * @X86_SUBARCH_LGUEST: Used for x86 hypervisor demo, lguest + * @X86_SUBARCH_XEN: Used for Xen guest types which follow the PV boot path, + * which start at asm startup_xen() entry point and later jump to the C + * xen_start_kernel() entry point. Both domU and dom0 type of guests are + * currently supportd through this PV boot path. + * @X86_SUBARCH_INTEL_MID: Used for Intel MID (Mobile Internet Device) platform + * systems which do not have the PCI legacy interfaces. + * @X86_SUBARCH_CE4100: Used for Intel CE media processor (CE4100) SoC for + * for settop boxes and media devices, the use of a subarch for CE4100 + * is more of a hack... + */ +enum x86_hardware_subarch { X86_SUBARCH_PC = 0, X86_SUBARCH_LGUEST, X86_SUBARCH_XEN, diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 616ebd2..9abf855 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -2,7 +2,11 @@ # Makefile for the linux kernel. # -extra-y := head_$(BITS).o head$(BITS).o head.o vmlinux.lds +extra-y := head_$(BITS).o +extra-y += head$(BITS).o +extra-y += ebda.o +extra-y += platform-quirks.o +extra-y += vmlinux.lds CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 8c2f1ef..f115a58 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -136,7 +136,7 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) { struct acpi_table_madt *madt = NULL; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -EINVAL; madt = (struct acpi_table_madt *)table; @@ -913,6 +913,15 @@ late_initcall(hpet_insert_resource); static int __init acpi_parse_fadt(struct acpi_table_header *table) { + if (!(acpi_gbl_FADT.boot_flags & ACPI_FADT_LEGACY_DEVICES)) { + pr_debug("ACPI: no legacy devices present\n"); + x86_platform.legacy.devices.pnpbios = 0; + } + + if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) { + pr_debug("ACPI: not registering RTC platform device\n"); + x86_platform.legacy.rtc = 0; + } #ifdef CONFIG_X86_PM_TIMER /* detect the location of the ACPI PM Timer */ @@ -951,7 +960,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) { int count; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; /* @@ -979,7 +988,7 @@ static int __init acpi_parse_madt_lapic_entries(void) int ret; struct acpi_subtable_proc madt_proc[2]; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; /* @@ -1125,7 +1134,7 @@ static int __init acpi_parse_madt_ioapic_entries(void) if (acpi_disabled || acpi_noirq) return -ENODEV; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; /* diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 25f9093..5cb272a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -11,6 +11,7 @@ #include <linux/stop_machine.h> #include <linux/slab.h> #include <linux/kdebug.h> +#include <asm/text-patching.h> #include <asm/alternative.h> #include <asm/sections.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d356987..60078a6 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -607,7 +607,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev) long tapic = apic_read(APIC_TMCCT); unsigned long pm = acpi_pm_read_early(); - if (cpu_has_tsc) + if (boot_cpu_has(X86_FEATURE_TSC)) tsc = rdtsc(); switch (lapic_cal_loops++) { @@ -668,7 +668,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) *delta = (long)res; /* Correct the tsc counter value */ - if (cpu_has_tsc) { + if (boot_cpu_has(X86_FEATURE_TSC)) { res = (((u64)(*deltatsc)) * pm_100ms); do_div(res, deltapm); apic_printk(APIC_VERBOSE, "TSC delta adjusted to " @@ -760,7 +760,7 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "..... calibration result: %u\n", lapic_timer_frequency); - if (cpu_has_tsc) { + if (boot_cpu_has(X86_FEATURE_TSC)) { apic_printk(APIC_VERBOSE, "..... CPU clock speed is " "%ld.%04ld MHz.\n", (deltatsc / LAPIC_CAL_LOOPS) / (1000000 / HZ), @@ -1085,7 +1085,7 @@ void lapic_shutdown(void) { unsigned long flags; - if (!cpu_has_apic && !apic_from_smp_config()) + if (!boot_cpu_has(X86_FEATURE_APIC) && !apic_from_smp_config()) return; local_irq_save(flags); @@ -1134,7 +1134,7 @@ void __init init_bsp_APIC(void) * Don't do the setup now if we have a SMP BIOS as the * through-I/O-APIC virtual wire mode might be active. */ - if (smp_found_config || !cpu_has_apic) + if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC)) return; /* @@ -1227,7 +1227,7 @@ void setup_local_APIC(void) unsigned long long tsc = 0, ntsc; long long max_loops = cpu_khz ? cpu_khz : 1000000; - if (cpu_has_tsc) + if (boot_cpu_has(X86_FEATURE_TSC)) tsc = rdtsc(); if (disable_apic) { @@ -1311,7 +1311,7 @@ void setup_local_APIC(void) break; } if (queued) { - if (cpu_has_tsc && cpu_khz) { + if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { ntsc = rdtsc(); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else @@ -1445,7 +1445,7 @@ static void __x2apic_disable(void) { u64 msr; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return; rdmsrl(MSR_IA32_APICBASE, msr); @@ -1561,7 +1561,7 @@ void __init check_x2apic(void) pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n"); x2apic_mode = 1; x2apic_state = X2APIC_ON; - } else if (!cpu_has_x2apic) { + } else if (!boot_cpu_has(X86_FEATURE_X2APIC)) { x2apic_state = X2APIC_DISABLED; } } @@ -1632,7 +1632,7 @@ void __init enable_IR_x2apic(void) */ static int __init detect_init_APIC(void) { - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { pr_info("No local APIC present\n"); return -1; } @@ -1711,14 +1711,14 @@ static int __init detect_init_APIC(void) goto no_apic; case X86_VENDOR_INTEL: if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 || - (boot_cpu_data.x86 == 5 && cpu_has_apic)) + (boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC))) break; goto no_apic; default: goto no_apic; } - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { /* * Over-ride BIOS and try to enable the local APIC only if * "lapic" specified. @@ -2233,19 +2233,19 @@ int __init APIC_init_uniprocessor(void) return -1; } #ifdef CONFIG_X86_64 - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { disable_apic = 1; pr_info("Apic disabled by BIOS\n"); return -1; } #else - if (!smp_found_config && !cpu_has_apic) + if (!smp_found_config && !boot_cpu_has(X86_FEATURE_APIC)) return -1; /* * Complain if the BIOS pretends there is one. */ - if (!cpu_has_apic && + if (!boot_cpu_has(X86_FEATURE_APIC) && APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) { pr_err("BIOS bug, local APIC 0x%x not detected!...\n", boot_cpu_physical_apicid); @@ -2426,7 +2426,7 @@ static void apic_pm_activate(void) static int __init init_lapic_sysfs(void) { /* XXX: remove suspend/resume procs if !apic_pm_state.active? */ - if (cpu_has_apic) + if (boot_cpu_has(X86_FEATURE_APIC)) register_syscore_ops(&lapic_syscore_ops); return 0; diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 331a7a0..13d19ed 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -100,13 +100,13 @@ static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask, static u32 noop_apic_read(u32 reg) { - WARN_ON_ONCE((cpu_has_apic && !disable_apic)); + WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); return 0; } static void noop_apic_write(u32 reg, u32 v) { - WARN_ON_ONCE(cpu_has_apic && !disable_apic); + WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); } struct apic apic_noop = { diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index fdb0fbf..84e33ff 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1454,7 +1454,7 @@ void native_disable_io_apic(void) ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry); } - if (cpu_has_apic || apic_from_smp_config()) + if (boot_cpu_has(X86_FEATURE_APIC) || apic_from_smp_config()) disconnect_bsp_APIC(ioapic_i8259.pin != -1); } diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 28bde88..2a0f225 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -230,7 +230,7 @@ int safe_smp_processor_id(void) { int apicid, cpuid; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return 0; apicid = hard_smp_processor_id(); diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index ef49551..a5e400a 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -944,7 +944,7 @@ static int __init print_ICs(void) print_PIC(); /* don't print out if apic is not there */ - if (!cpu_has_apic && !apic_from_smp_config()) + if (!boot_cpu_has(X86_FEATURE_APIC) && !apic_from_smp_config()) return 0; print_local_APICs(show_lapic); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 9307f18..c7364bd 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -2267,7 +2267,7 @@ static int __init apm_init(void) dmi_check_system(apm_dmi_table); - if (apm_info.bios.version == 0 || paravirt_enabled() || machine_is_olpc()) { + if (apm_info.bios.version == 0 || machine_is_olpc()) { printk(KERN_INFO "apm: BIOS not found.\n"); return -ENODEV; } diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 5c04246..674134e 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -80,6 +80,7 @@ void common(void) { OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); OFFSET(BP_version, boot_params, hdr.version); OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment); + OFFSET(BP_init_size, boot_params, hdr.init_size); OFFSET(BP_pref_address, boot_params, hdr.pref_address); OFFSET(BP_code32_start, boot_params, hdr.code32_start); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7b76eb6..c343a54 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -565,14 +565,17 @@ static void early_init_amd(struct cpuinfo_x86 *c) * can safely set X86_FEATURE_EXTD_APICID unconditionally for families * after 16h. */ - if (cpu_has_apic && c->x86 > 0x16) { - set_cpu_cap(c, X86_FEATURE_EXTD_APICID); - } else if (cpu_has_apic && c->x86 >= 0xf) { - /* check CPU config space for extended APIC ID */ - unsigned int val; - val = read_pci_config(0, 24, 0, 0x68); - if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18))) + if (boot_cpu_has(X86_FEATURE_APIC)) { + if (c->x86 > 0x16) set_cpu_cap(c, X86_FEATURE_EXTD_APICID); + else if (c->x86 >= 0xf) { + /* check CPU config space for extended APIC ID */ + unsigned int val; + + val = read_pci_config(0, 24, 0, 0x68); + if ((val >> 17 & 0x3) == 0x3) + set_cpu_cap(c, X86_FEATURE_EXTD_APICID); + } } #endif @@ -628,6 +631,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c) */ msr_set_bit(MSR_K7_HWCR, 6); #endif + set_cpu_bug(c, X86_BUG_SWAPGS_FENCE); } static void init_amd_gh(struct cpuinfo_x86 *c) @@ -746,7 +750,7 @@ static void init_amd(struct cpuinfo_x86 *c) if (c->x86 >= 0xf) set_cpu_cap(c, X86_FEATURE_K8); - if (cpu_has_xmm2) { + if (cpu_has(c, X86_FEATURE_XMM2)) { /* MFENCE stops RDTSC speculation */ set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8394b3d..6ef6ed9 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -430,7 +430,7 @@ void load_percpu_segment(int cpu) #ifdef CONFIG_X86_32 loadsegment(fs, __KERNEL_PERCPU); #else - loadsegment(gs, 0); + __loadsegment_simple(gs, 0); wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu)); #endif load_stack_canary_segment(); @@ -717,6 +717,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c) } } + if (c->extended_cpuid_level >= 0x80000007) { + cpuid(0x80000007, &eax, &ebx, &ecx, &edx); + + c->x86_capability[CPUID_8000_0007_EBX] = ebx; + c->x86_power = edx; + } + if (c->extended_cpuid_level >= 0x80000008) { cpuid(0x80000008, &eax, &ebx, &ecx, &edx); @@ -729,9 +736,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_phys_bits = 36; #endif - if (c->extended_cpuid_level >= 0x80000007) - c->x86_power = cpuid_edx(0x80000007); - if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); @@ -862,30 +866,34 @@ static void detect_nopl(struct cpuinfo_x86 *c) #else set_cpu_cap(c, X86_FEATURE_NOPL); #endif +} +static void detect_null_seg_behavior(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_X86_64 /* - * ESPFIX is a strange bug. All real CPUs have it. Paravirt - * systems that run Linux at CPL > 0 may or may not have the - * issue, but, even if they have the issue, there's absolutely - * nothing we can do about it because we can't use the real IRET - * instruction. + * Empirically, writing zero to a segment selector on AMD does + * not clear the base, whereas writing zero to a segment + * selector on Intel does clear the base. Intel's behavior + * allows slightly faster context switches in the common case + * where GS is unused by the prev and next threads. * - * NB: For the time being, only 32-bit kernels support - * X86_BUG_ESPFIX as such. 64-bit kernels directly choose - * whether to apply espfix using paravirt hooks. If any - * non-paravirt system ever shows up that does *not* have the - * ESPFIX issue, we can change this. + * Since neither vendor documents this anywhere that I can see, + * detect it directly instead of hardcoding the choice by + * vendor. + * + * I've designated AMD's behavior as the "bug" because it's + * counterintuitive and less friendly. */ -#ifdef CONFIG_X86_32 -#ifdef CONFIG_PARAVIRT - do { - extern void native_iret(void); - if (pv_cpu_ops.iret == native_iret) - set_cpu_bug(c, X86_BUG_ESPFIX); - } while (0); -#else - set_cpu_bug(c, X86_BUG_ESPFIX); -#endif + + unsigned long old_base, tmp; + rdmsrl(MSR_FS_BASE, old_base); + wrmsrl(MSR_FS_BASE, 1); + loadsegment(fs, 0); + rdmsrl(MSR_FS_BASE, tmp); + if (tmp != 0) + set_cpu_bug(c, X86_BUG_NULL_SEG); + wrmsrl(MSR_FS_BASE, old_base); #endif } @@ -921,6 +929,33 @@ static void generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ detect_nopl(c); + + detect_null_seg_behavior(c); + + /* + * ESPFIX is a strange bug. All real CPUs have it. Paravirt + * systems that run Linux at CPL > 0 may or may not have the + * issue, but, even if they have the issue, there's absolutely + * nothing we can do about it because we can't use the real IRET + * instruction. + * + * NB: For the time being, only 32-bit kernels support + * X86_BUG_ESPFIX as such. 64-bit kernels directly choose + * whether to apply espfix using paravirt hooks. If any + * non-paravirt system ever shows up that does *not* have the + * ESPFIX issue, we can change this. + */ +#ifdef CONFIG_X86_32 +# ifdef CONFIG_PARAVIRT + do { + extern void native_iret(void); + if (pv_cpu_ops.iret == native_iret) + set_cpu_bug(c, X86_BUG_ESPFIX); + } while (0); +# else + set_cpu_bug(c, X86_BUG_ESPFIX); +# endif +#endif } static void x86_init_cache_qos(struct cpuinfo_x86 *c) @@ -1076,12 +1111,12 @@ void enable_sep_cpu(void) struct tss_struct *tss; int cpu; + if (!boot_cpu_has(X86_FEATURE_SEP)) + return; + cpu = get_cpu(); tss = &per_cpu(cpu_tss, cpu); - if (!boot_cpu_has(X86_FEATURE_SEP)) - goto out; - /* * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field -- * see the big comment in struct x86_hw_tss's definition. @@ -1096,7 +1131,6 @@ void enable_sep_cpu(void) wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); -out: put_cpu(); } #endif @@ -1528,7 +1562,7 @@ void cpu_init(void) pr_info("Initializing CPU#%d\n", cpu); if (cpu_feature_enabled(X86_FEATURE_VME) || - cpu_has_tsc || + boot_cpu_has(X86_FEATURE_TSC) || boot_cpu_has(X86_FEATURE_DE)) cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 6adef9c..bd9dcd6 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -333,7 +333,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) switch (dir0_lsn) { case 0xd: /* either a 486SLC or DLC w/o DEVID */ dir0_msn = 0; - p = Cx486_name[(cpu_has_fpu ? 1 : 0)]; + p = Cx486_name[!!boot_cpu_has(X86_FEATURE_FPU)]; break; case 0xe: /* a 486S A step */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 1f7fdb9..8dae51f 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -152,9 +152,9 @@ static void early_init_intel(struct cpuinfo_x86 *c) * the TLB when any changes are made to any of the page table entries. * The operating system must reload CR3 to cause the TLB to be flushed" * - * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should - * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE - * to be modified + * As a result, boot_cpu_has(X86_FEATURE_PGE) in arch/x86/include/asm/tlbflush.h + * should be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * to be modified. */ if (c->x86 == 5 && c->x86_model == 9) { pr_info("Disabling PGE capability bit\n"); @@ -233,7 +233,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * The Quark is also family 5, but does not have the same bug. */ clear_cpu_bug(c, X86_BUG_F00F); - if (!paravirt_enabled() && c->x86 == 5 && c->x86_model < 9) { + if (c->x86 == 5 && c->x86_model < 9) { static int f00f_workaround_enabled; set_cpu_bug(c, X86_BUG_F00F); @@ -281,7 +281,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * integrated APIC (see 11AP erratum in "Pentium Processor * Specification Update"). */ - if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 && + if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 && (c->x86_mask < 0x6 || c->x86_mask == 0xb)) set_cpu_bug(c, X86_BUG_11AP); @@ -336,7 +336,7 @@ static int intel_num_cpu_cores(struct cpuinfo_x86 *c) { unsigned int eax, ebx, ecx, edx; - if (c->cpuid_level < 4) + if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4) return 1; /* Intel has a non-standard dependency on %ecx for this CPUID level. */ @@ -456,7 +456,7 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON); } - if (cpu_has_xmm2) + if (cpu_has(c, X86_FEATURE_XMM2)) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); if (boot_cpu_has(X86_FEATURE_DS)) { @@ -468,7 +468,7 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_PEBS); } - if (c->x86 == 6 && cpu_has_clflush && + if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_CLFLUSH) && (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47)) set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 2658e2a..93d824e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -26,6 +26,52 @@ static struct gen_pool *mce_evt_pool; static LLIST_HEAD(mce_event_llist); static char gen_pool_buf[MCE_POOLSZ]; +/* + * Compare the record "t" with each of the records on list "l" to see if + * an equivalent one is present in the list. + */ +static bool is_duplicate_mce_record(struct mce_evt_llist *t, struct mce_evt_llist *l) +{ + struct mce_evt_llist *node; + struct mce *m1, *m2; + + m1 = &t->mce; + + llist_for_each_entry(node, &l->llnode, llnode) { + m2 = &node->mce; + + if (!mce_cmp(m1, m2)) + return true; + } + return false; +} + +/* + * The system has panicked - we'd like to peruse the list of MCE records + * that have been queued, but not seen by anyone yet. The list is in + * reverse time order, so we need to reverse it. While doing that we can + * also drop duplicate records (these were logged because some banks are + * shared between cores or by all threads on a socket). + */ +struct llist_node *mce_gen_pool_prepare_records(void) +{ + struct llist_node *head; + LLIST_HEAD(new_head); + struct mce_evt_llist *node, *t; + + head = llist_del_all(&mce_event_llist); + if (!head) + return NULL; + + /* squeeze out duplicates while reversing order */ + llist_for_each_entry_safe(node, t, head, llnode) { + if (!is_duplicate_mce_record(node, t)) + llist_add(&node->llnode, &new_head); + } + + return new_head.first; +} + void mce_gen_pool_process(void) { struct llist_node *head; diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 547720e..cd74a3f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -35,6 +35,7 @@ void mce_gen_pool_process(void); bool mce_gen_pool_empty(void); int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); +struct llist_node *mce_gen_pool_prepare_records(void); extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); @@ -81,3 +82,17 @@ static inline int apei_clear_mce(u64 record_id) #endif void mce_inject_log(struct mce *m); + +/* + * We consider records to be equivalent if bank+status+addr+misc all match. + * This is only used when the system is going down because of a fatal error + * to avoid cluttering the console log with essentially repeated information. + * In normal processing all errors seen are logged. + */ +static inline bool mce_cmp(struct mce *m1, struct mce *m2) +{ + return m1->bank != m2->bank || + m1->status != m2->status || + m1->addr != m2->addr || + m1->misc != m2->misc; +} diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 5119766..631356c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -204,6 +204,33 @@ static int error_context(struct mce *m) return IN_KERNEL; } +static int mce_severity_amd_smca(struct mce *m, int err_ctx) +{ + u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank); + u32 low, high; + + /* + * We need to look at the following bits: + * - "succor" bit (data poisoning support), and + * - TCC bit (Task Context Corrupt) + * in MCi_STATUS to determine error severity. + */ + if (!mce_flags.succor) + return MCE_PANIC_SEVERITY; + + if (rdmsr_safe(addr, &low, &high)) + return MCE_PANIC_SEVERITY; + + /* TCC (Task context corrupt). If set and if IN_KERNEL, panic. */ + if ((low & MCI_CONFIG_MCAX) && + (m->status & MCI_STATUS_TCC) && + (err_ctx == IN_KERNEL)) + return MCE_PANIC_SEVERITY; + + /* ...otherwise invoke hwpoison handler. */ + return MCE_AR_SEVERITY; +} + /* * See AMD Error Scope Hierarchy table in a newer BKDG. For example * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" @@ -225,6 +252,9 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc * to at least kill process to prolong system operation. */ if (mce_flags.overflow_recov) { + if (mce_flags.smca) + return mce_severity_amd_smca(m, ctx); + /* software can try to contain */ if (!(m->mcgstatus & MCG_STATUS_RIPV) && (ctx == IN_KERNEL)) return MCE_PANIC_SEVERITY; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index f0c921b..92e5e37 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -161,7 +161,6 @@ void mce_log(struct mce *mce) if (!mce_gen_pool_add(mce)) irq_work_queue(&mce_irq_work); - mce->finished = 0; wmb(); for (;;) { entry = mce_log_get_idx_check(mcelog.next); @@ -194,7 +193,6 @@ void mce_log(struct mce *mce) mcelog.entry[entry].finished = 1; wmb(); - mce->finished = 1; set_bit(0, &mce_need_notify); } @@ -224,6 +222,53 @@ void mce_unregister_decode_chain(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); +static inline u32 ctl_reg(int bank) +{ + return MSR_IA32_MCx_CTL(bank); +} + +static inline u32 status_reg(int bank) +{ + return MSR_IA32_MCx_STATUS(bank); +} + +static inline u32 addr_reg(int bank) +{ + return MSR_IA32_MCx_ADDR(bank); +} + +static inline u32 misc_reg(int bank) +{ + return MSR_IA32_MCx_MISC(bank); +} + +static inline u32 smca_ctl_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_CTL(bank); +} + +static inline u32 smca_status_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_STATUS(bank); +} + +static inline u32 smca_addr_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_ADDR(bank); +} + +static inline u32 smca_misc_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_MISC(bank); +} + +struct mca_msr_regs msr_ops = { + .ctl = ctl_reg, + .status = status_reg, + .addr = addr_reg, + .misc = misc_reg +}; + static void print_mce(struct mce *m) { int ret = 0; @@ -290,7 +335,9 @@ static void wait_for_panic(void) static void mce_panic(const char *msg, struct mce *final, char *exp) { - int i, apei_err = 0; + int apei_err = 0; + struct llist_node *pending; + struct mce_evt_llist *l; if (!fake_panic) { /* @@ -307,11 +354,10 @@ static void mce_panic(const char *msg, struct mce *final, char *exp) if (atomic_inc_return(&mce_fake_panicked) > 1) return; } + pending = mce_gen_pool_prepare_records(); /* First print corrected ones that are still unlogged */ - for (i = 0; i < MCE_LOG_LEN; i++) { - struct mce *m = &mcelog.entry[i]; - if (!(m->status & MCI_STATUS_VAL)) - continue; + llist_for_each_entry(l, pending, llnode) { + struct mce *m = &l->mce; if (!(m->status & MCI_STATUS_UC)) { print_mce(m); if (!apei_err) @@ -319,13 +365,11 @@ static void mce_panic(const char *msg, struct mce *final, char *exp) } } /* Now print uncorrected but with the final one last */ - for (i = 0; i < MCE_LOG_LEN; i++) { - struct mce *m = &mcelog.entry[i]; - if (!(m->status & MCI_STATUS_VAL)) - continue; + llist_for_each_entry(l, pending, llnode) { + struct mce *m = &l->mce; if (!(m->status & MCI_STATUS_UC)) continue; - if (!final || memcmp(m, final, sizeof(struct mce))) { + if (!final || mce_cmp(m, final)) { print_mce(m); if (!apei_err) apei_err = apei_write_mce(m); @@ -356,11 +400,11 @@ static int msr_to_offset(u32 msr) if (msr == mca_cfg.rip_msr) return offsetof(struct mce, ip); - if (msr == MSR_IA32_MCx_STATUS(bank)) + if (msr == msr_ops.status(bank)) return offsetof(struct mce, status); - if (msr == MSR_IA32_MCx_ADDR(bank)) + if (msr == msr_ops.addr(bank)) return offsetof(struct mce, addr); - if (msr == MSR_IA32_MCx_MISC(bank)) + if (msr == msr_ops.misc(bank)) return offsetof(struct mce, misc); if (msr == MSR_IA32_MCG_STATUS) return offsetof(struct mce, mcgstatus); @@ -523,9 +567,9 @@ static struct notifier_block mce_srao_nb = { static void mce_read_aux(struct mce *m, int i) { if (m->status & MCI_STATUS_MISCV) - m->misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i)); + m->misc = mce_rdmsrl(msr_ops.misc(i)); if (m->status & MCI_STATUS_ADDRV) { - m->addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i)); + m->addr = mce_rdmsrl(msr_ops.addr(i)); /* * Mask the reported address by the reported granularity. @@ -607,7 +651,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) m.tsc = 0; barrier(); - m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); + m.status = mce_rdmsrl(msr_ops.status(i)); if (!(m.status & MCI_STATUS_VAL)) continue; @@ -654,7 +698,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) /* * Clear state for this bank. */ - mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0); + mce_wrmsrl(msr_ops.status(i), 0); } /* @@ -679,7 +723,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, char *tmp; for (i = 0; i < mca_cfg.banks; i++) { - m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); + m->status = mce_rdmsrl(msr_ops.status(i)); if (m->status & MCI_STATUS_VAL) { __set_bit(i, validp); if (quirk_no_way_out) @@ -830,9 +874,9 @@ static int mce_start(int *no_way_out) atomic_add(*no_way_out, &global_nwo); /* - * global_nwo should be updated before mce_callin + * Rely on the implied barrier below, such that global_nwo + * is updated before mce_callin. */ - smp_wmb(); order = atomic_inc_return(&mce_callin); /* @@ -957,7 +1001,7 @@ static void mce_clear_state(unsigned long *toclear) for (i = 0; i < mca_cfg.banks; i++) { if (test_bit(i, toclear)) - mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0); + mce_wrmsrl(msr_ops.status(i), 0); } } @@ -994,11 +1038,12 @@ void do_machine_check(struct pt_regs *regs, long error_code) int i; int worst = 0; int severity; + /* * Establish sequential order between the CPUs entering the machine * check handler. */ - int order; + int order = -1; /* * If no_way_out gets set, there is no safe way to recover from this * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. @@ -1012,7 +1057,12 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(toclear, MAX_NR_BANKS); DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); char *msg = "Unknown"; - int lmce = 0; + + /* + * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES + * on Intel. + */ + int lmce = 1; /* If this CPU is offline, just bail out. */ if (cpu_is_offline(smp_processor_id())) { @@ -1051,19 +1101,20 @@ void do_machine_check(struct pt_regs *regs, long error_code) kill_it = 1; /* - * Check if this MCE is signaled to only this logical processor + * Check if this MCE is signaled to only this logical processor, + * on Intel only. */ - if (m.mcgstatus & MCG_STATUS_LMCES) - lmce = 1; - else { - /* - * Go through all the banks in exclusion of the other CPUs. - * This way we don't report duplicated events on shared banks - * because the first one to see it will clear it. - * If this is a Local MCE, then no need to perform rendezvous. - */ + if (m.cpuvendor == X86_VENDOR_INTEL) + lmce = m.mcgstatus & MCG_STATUS_LMCES; + + /* + * Go through all banks in exclusion of the other CPUs. This way we + * don't report duplicated events on shared banks because the first one + * to see it will clear it. If this is a Local MCE, then no need to + * perform rendezvous. + */ + if (!lmce) order = mce_start(&no_way_out); - } for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); @@ -1076,7 +1127,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) m.addr = 0; m.bank = i; - m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); + m.status = mce_rdmsrl(msr_ops.status(i)); if ((m.status & MCI_STATUS_VAL) == 0) continue; @@ -1420,7 +1471,6 @@ static void __mcheck_cpu_init_generic(void) enum mcp_flags m_fl = 0; mce_banks_t all_banks; u64 cap; - int i; if (!mca_cfg.bootlog) m_fl = MCP_DONTLOG; @@ -1436,14 +1486,19 @@ static void __mcheck_cpu_init_generic(void) rdmsrl(MSR_IA32_MCG_CAP, cap); if (cap & MCG_CTL_P) wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); +} + +static void __mcheck_cpu_init_clear_banks(void) +{ + int i; for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (!b->init) continue; - wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); - wrmsrl(MSR_IA32_MCx_STATUS(i), 0); + wrmsrl(msr_ops.ctl(i), b->ctl); + wrmsrl(msr_ops.status(i), 0); } } @@ -1495,7 +1550,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ clear_bit(10, (unsigned long *)&mce_banks[4].ctl); } - if (c->x86 <= 17 && cfg->bootlog < 0) { + if (c->x86 < 17 && cfg->bootlog < 0) { /* * Lots of broken BIOS around that don't clear them * by default and leave crap in there. Don't log: @@ -1628,11 +1683,19 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) break; case X86_VENDOR_AMD: { - u32 ebx = cpuid_ebx(0x80000007); + mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); + mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); + mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); - mce_flags.overflow_recov = !!(ebx & BIT(0)); - mce_flags.succor = !!(ebx & BIT(1)); - mce_flags.smca = !!(ebx & BIT(3)); + /* + * Install proper ops for Scalable MCA enabled processors + */ + if (mce_flags.smca) { + msr_ops.ctl = smca_ctl_reg; + msr_ops.status = smca_status_reg; + msr_ops.addr = smca_addr_reg; + msr_ops.misc = smca_misc_reg; + } mce_amd_feature_init(c); break; @@ -1717,6 +1780,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); + __mcheck_cpu_init_clear_banks(); __mcheck_cpu_init_timer(); } @@ -2082,7 +2146,7 @@ static void mce_disable_error_reporting(void) struct mce_bank *b = &mce_banks[i]; if (b->init) - wrmsrl(MSR_IA32_MCx_CTL(i), 0); + wrmsrl(msr_ops.ctl(i), 0); } return; } @@ -2121,6 +2185,7 @@ static void mce_syscore_resume(void) { __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info)); + __mcheck_cpu_init_clear_banks(); } static struct syscore_ops mce_syscore_ops = { @@ -2138,6 +2203,7 @@ static void mce_cpu_restart(void *data) if (!mce_available(raw_cpu_ptr(&cpu_info))) return; __mcheck_cpu_init_generic(); + __mcheck_cpu_init_clear_banks(); __mcheck_cpu_init_timer(); } @@ -2413,7 +2479,7 @@ static void mce_reenable_cpu(void *h) struct mce_bank *b = &mce_banks[i]; if (b->init) - wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); + wrmsrl(msr_ops.ctl(i), b->ctl); } } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 9d656fd..10b0661 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -54,14 +54,6 @@ /* Threshold LVT offset is at MSR0xC0000410[15:12] */ #define SMCA_THR_LVT_OFF 0xF000 -/* - * OS is required to set the MCAX bit to acknowledge that it is now using the - * new MSR ranges and new registers under each bank. It also means that the OS - * will configure deferred errors in the new MCx_CONFIG register. If the bit is - * not set, uncorrectable errors will cause a system panic. - */ -#define SMCA_MCAX_EN_OFF 0x1 - static const char * const th_names[] = { "load_store", "insn_fetch", @@ -333,7 +325,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high, /* Fall back to method we used for older processors: */ switch (block) { case 0: - addr = MSR_IA32_MCx_MISC(bank); + addr = msr_ops.misc(bank); break; case 1: offset = ((low & MASK_BLKPTR_LO) >> 21); @@ -351,6 +343,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, int offset, u32 misc_high) { unsigned int cpu = smp_processor_id(); + u32 smca_low, smca_high, smca_addr; struct threshold_block b; int new; @@ -369,24 +362,49 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, b.interrupt_enable = 1; - if (mce_flags.smca) { - u32 smca_low, smca_high; - u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); + if (!mce_flags.smca) { + new = (misc_high & MASK_LVTOFF_HI) >> 20; + goto set_offset; + } - if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { - smca_high |= SMCA_MCAX_EN_OFF; - wrmsr(smca_addr, smca_low, smca_high); - } + smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); - /* Gather LVT offset for thresholding: */ - if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) - goto out; + if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { + /* + * OS is required to set the MCAX bit to acknowledge that it is + * now using the new MSR ranges and new registers under each + * bank. It also means that the OS will configure deferred + * errors in the new MCx_CONFIG register. If the bit is not set, + * uncorrectable errors will cause a system panic. + * + * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) + */ + smca_high |= BIT(0); - new = (smca_low & SMCA_THR_LVT_OFF) >> 12; - } else { - new = (misc_high & MASK_LVTOFF_HI) >> 20; + /* + * SMCA logs Deferred Error information in MCA_DE{STAT,ADDR} + * registers with the option of additionally logging to + * MCA_{STATUS,ADDR} if MCA_CONFIG[LogDeferredInMcaStat] is set. + * + * This bit is usually set by BIOS to retain the old behavior + * for OSes that don't use the new registers. Linux supports the + * new registers so let's disable that additional logging here. + * + * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in the high + * portion of the MSR). + */ + smca_high &= ~BIT(2); + + wrmsr(smca_addr, smca_low, smca_high); } + /* Gather LVT offset for thresholding: */ + if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) + goto out; + + new = (smca_low & SMCA_THR_LVT_OFF) >> 12; + +set_offset: offset = setup_APIC_mce_threshold(offset, new); if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt)) @@ -430,12 +448,23 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) deferred_error_interrupt_enable(c); } -static void __log_error(unsigned int bank, bool threshold_err, u64 misc) +static void +__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) { + u32 msr_status = msr_ops.status(bank); + u32 msr_addr = msr_ops.addr(bank); struct mce m; u64 status; - rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + WARN_ON_ONCE(deferred_err && threshold_err); + + if (deferred_err && mce_flags.smca) { + msr_status = MSR_AMD64_SMCA_MCx_DESTAT(bank); + msr_addr = MSR_AMD64_SMCA_MCx_DEADDR(bank); + } + + rdmsrl(msr_status, status); + if (!(status & MCI_STATUS_VAL)) return; @@ -448,10 +477,11 @@ static void __log_error(unsigned int bank, bool threshold_err, u64 misc) m.misc = misc; if (m.status & MCI_STATUS_ADDRV) - rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr); + rdmsrl(msr_addr, m.addr); mce_log(&m); - wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); + + wrmsrl(msr_status, 0); } static inline void __smp_deferred_error_interrupt(void) @@ -479,17 +509,21 @@ asmlinkage __visible void smp_trace_deferred_error_interrupt(void) /* APIC interrupt handler for deferred errors */ static void amd_deferred_error_interrupt(void) { - u64 status; unsigned int bank; + u32 msr_status; + u64 status; for (bank = 0; bank < mca_cfg.banks; ++bank) { - rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + msr_status = (mce_flags.smca) ? MSR_AMD64_SMCA_MCx_DESTAT(bank) + : msr_ops.status(bank); + + rdmsrl(msr_status, status); if (!(status & MCI_STATUS_VAL) || !(status & MCI_STATUS_DEFERRED)) continue; - __log_error(bank, false, 0); + __log_error(bank, true, false, 0); break; } } @@ -544,7 +578,7 @@ static void amd_threshold_interrupt(void) return; log: - __log_error(bank, true, ((u64)high << 32) | low); + __log_error(bank, false, true, ((u64)high << 32) | low); } /* diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 1e8bb6c..1defb8e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -84,7 +84,7 @@ static int cmci_supported(int *banks) */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; - if (!cpu_has_apic || lapic_get_maxlvt() < 6) + if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) return 0; rdmsrl(MSR_IA32_MCG_CAP, cap); *banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff); diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index ac780ca..6b9dc4d 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -450,7 +450,7 @@ asmlinkage __visible void smp_trace_thermal_interrupt(struct pt_regs *regs) /* Thermal monitoring depends on APIC, ACPI and clock modulation */ static int intel_thermal_supported(struct cpuinfo_x86 *c) { - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return 0; if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC)) return 0; diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index f8c81ba..b1086f7 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -137,7 +137,7 @@ static void prepare_set(void) u32 cr0; /* Save value of CR4 and clear Page Global Enable (bit 7) */ - if (cpu_has_pge) { + if (boot_cpu_has(X86_FEATURE_PGE)) { cr4 = __read_cr4(); __write_cr4(cr4 & ~X86_CR4_PGE); } @@ -170,7 +170,7 @@ static void post_set(void) write_cr0(read_cr0() & ~X86_CR0_CD); /* Restore value of CR4 */ - if (cpu_has_pge) + if (boot_cpu_has(X86_FEATURE_PGE)) __write_cr4(cr4); } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 19f5736..16e37a2 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -444,11 +444,24 @@ static void __init print_mtrr_state(void) pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); } +/* PAT setup for BP. We need to go through sync steps here */ +void __init mtrr_bp_pat_init(void) +{ + unsigned long flags; + + local_irq_save(flags); + prepare_set(); + + pat_init(); + + post_set(); + local_irq_restore(flags); +} + /* Grab all of the MTRR state for this CPU into *state */ bool __init get_mtrr_state(void) { struct mtrr_var_range *vrs; - unsigned long flags; unsigned lo, dummy; unsigned int i; @@ -481,15 +494,6 @@ bool __init get_mtrr_state(void) mtrr_state_set = 1; - /* PAT setup for BP. We need to go through sync steps here */ - local_irq_save(flags); - prepare_set(); - - pat_init(); - - post_set(); - local_irq_restore(flags); - return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED); } @@ -741,7 +745,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) wbinvd(); /* Save value of CR4 and clear Page Global Enable (bit 7) */ - if (cpu_has_pge) { + if (boot_cpu_has(X86_FEATURE_PGE)) { cr4 = __read_cr4(); __write_cr4(cr4 & ~X86_CR4_PGE); } @@ -771,7 +775,7 @@ static void post_set(void) __releases(set_atomicity_lock) write_cr0(read_cr0() & ~X86_CR0_CD); /* Restore value of CR4 */ - if (cpu_has_pge) + if (boot_cpu_has(X86_FEATURE_PGE)) __write_cr4(cr4); raw_spin_unlock(&set_atomicity_lock); } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 10f8d47..7d393ec 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -752,6 +752,9 @@ void __init mtrr_bp_init(void) /* BIOS may override */ __mtrr_enabled = get_mtrr_state(); + if (mtrr_enabled()) + mtrr_bp_pat_init(); + if (mtrr_cleanup(phys_addr)) { changed_by_mtrr_cleanup = 1; mtrr_if->set_all(); @@ -759,8 +762,16 @@ void __init mtrr_bp_init(void) } } - if (!mtrr_enabled()) + if (!mtrr_enabled()) { pr_info("MTRR: Disabled\n"); + + /* + * PAT initialization relies on MTRR's rendezvous handler. + * Skip PAT init until the handler can initialize both + * features independently. + */ + pat_disable("MTRRs disabled, skipping PAT initialization too."); + } } void mtrr_ap_init(void) diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 951884d..6c7ced0 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt); void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); bool get_mtrr_state(void); +void mtrr_bp_pat_init(void); extern void set_mtrr_ops(const struct mtrr_ops *ops); diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 364e583..8cac429 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -94,7 +94,7 @@ static void __init vmware_platform_setup(void) */ static uint32_t __init vmware_platform(void) { - if (cpu_has_hypervisor) { + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { unsigned int eax; unsigned int hyper_vendor_id[3]; diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 1f4acd6..3fe45f8 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -151,7 +151,7 @@ static void __init dtb_lapic_setup(void) return; /* Did the boot loader setup the local APIC ? */ - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { if (apic_force_enable(r.start)) return; } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 8efa57a..2bb25c3 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -260,19 +260,12 @@ int __die(const char *str, struct pt_regs *regs, long err) unsigned long sp; #endif printk(KERN_DEFAULT - "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); -#endif -#ifdef CONFIG_SMP - printk("SMP "); -#endif - if (debug_pagealloc_enabled()) - printk("DEBUG_PAGEALLOC "); -#ifdef CONFIG_KASAN - printk("KASAN"); -#endif - printk("\n"); + "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter, + IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", + IS_ENABLED(CONFIG_SMP) ? " SMP" : "", + debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", + IS_ENABLED(CONFIG_KASAN) ? " KASAN" : ""); + if (notify_die(DIE_OOPS, str, regs, err, current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP) return 1; diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/ebda.c index 992f442..afe65df 100644 --- a/arch/x86/kernel/head.c +++ b/arch/x86/kernel/ebda.c @@ -38,7 +38,7 @@ void __init reserve_ebda_region(void) * that the paravirt case can handle memory setup * correctly, without our help. */ - if (paravirt_enabled()) + if (!x86_platform.legacy.ebda_search) return; /* end of low (conventional) memory */ diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index dd9ca9b6..aad34aa 100644 --- a/arch/x86/kernel/fpu/bugs.c +++ b/arch/x86/kernel/fpu/bugs.c @@ -21,11 +21,15 @@ static double __initdata y = 3145727.0; * We should really only care about bugs here * anyway. Not features. */ -static void __init check_fpu(void) +void __init fpu__init_check_bugs(void) { u32 cr0_saved; s32 fdiv_bug; + /* kernel_fpu_begin/end() relies on patched alternative instructions. */ + if (!boot_cpu_has(X86_FEATURE_FPU)) + return; + /* We might have CR0::TS set already, clear it: */ cr0_saved = read_cr0(); write_cr0(cr0_saved & ~X86_CR0_TS); @@ -59,13 +63,3 @@ static void __init check_fpu(void) pr_warn("Hmm, FPU with FDIV bug\n"); } } - -void __init fpu__init_check_bugs(void) -{ - /* - * kernel_fpu_begin/end() in check_fpu() relies on the patched - * alternative instructions. - */ - if (cpu_has_fpu) - check_fpu(); -} diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 8e37cc8..9702754 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -217,14 +217,14 @@ static inline void fpstate_init_fstate(struct fregs_state *fp) void fpstate_init(union fpregs_state *state) { - if (!cpu_has_fpu) { + if (!static_cpu_has(X86_FEATURE_FPU)) { fpstate_init_soft(&state->soft); return; } memset(state, 0, xstate_size); - if (cpu_has_fxsr) + if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); else fpstate_init_fstate(&state->fsave); @@ -237,7 +237,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) dst_fpu->fpregs_active = 0; dst_fpu->last_cpu = -1; - if (!src_fpu->fpstate_active || !cpu_has_fpu) + if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); @@ -506,33 +506,6 @@ void fpu__clear(struct fpu *fpu) * x87 math exception handling: */ -static inline unsigned short get_fpu_cwd(struct fpu *fpu) -{ - if (cpu_has_fxsr) { - return fpu->state.fxsave.cwd; - } else { - return (unsigned short)fpu->state.fsave.cwd; - } -} - -static inline unsigned short get_fpu_swd(struct fpu *fpu) -{ - if (cpu_has_fxsr) { - return fpu->state.fxsave.swd; - } else { - return (unsigned short)fpu->state.fsave.swd; - } -} - -static inline unsigned short get_fpu_mxcsr(struct fpu *fpu) -{ - if (cpu_has_xmm) { - return fpu->state.fxsave.mxcsr; - } else { - return MXCSR_DEFAULT; - } -} - int fpu__exception_code(struct fpu *fpu, int trap_nr) { int err; @@ -547,10 +520,15 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr) * so if this combination doesn't produce any single exception, * then we have a bad program that isn't synchronizing its FPU usage * and it will suffer the consequences since we won't be able to - * fully reproduce the context of the exception + * fully reproduce the context of the exception. */ - cwd = get_fpu_cwd(fpu); - swd = get_fpu_swd(fpu); + if (boot_cpu_has(X86_FEATURE_FXSR)) { + cwd = fpu->state.fxsave.cwd; + swd = fpu->state.fxsave.swd; + } else { + cwd = (unsigned short)fpu->state.fsave.cwd; + swd = (unsigned short)fpu->state.fsave.swd; + } err = swd & ~cwd; } else { @@ -560,7 +538,11 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr) * unmasked exception was caught we must mask the exception mask bits * at 0x1f80, and then use these to mask the exception bits at 0x3f. */ - unsigned short mxcsr = get_fpu_mxcsr(fpu); + unsigned short mxcsr = MXCSR_DEFAULT; + + if (boot_cpu_has(X86_FEATURE_XMM)) + mxcsr = fpu->state.fxsave.mxcsr; + err = ~(mxcsr >> 7) & mxcsr; } diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 54c86ff..aacfd7a 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -29,22 +29,22 @@ static void fpu__init_cpu_generic(void) unsigned long cr0; unsigned long cr4_mask = 0; - if (cpu_has_fxsr) + if (boot_cpu_has(X86_FEATURE_FXSR)) cr4_mask |= X86_CR4_OSFXSR; - if (cpu_has_xmm) + if (boot_cpu_has(X86_FEATURE_XMM)) cr4_mask |= X86_CR4_OSXMMEXCPT; if (cr4_mask) cr4_set_bits(cr4_mask); cr0 = read_cr0(); cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ - if (!cpu_has_fpu) + if (!boot_cpu_has(X86_FEATURE_FPU)) cr0 |= X86_CR0_EM; write_cr0(cr0); /* Flush out any pending x87 state: */ #ifdef CONFIG_MATH_EMULATION - if (!cpu_has_fpu) + if (!boot_cpu_has(X86_FEATURE_FPU)) fpstate_init_soft(¤t->thread.fpu.state.soft); else #endif @@ -89,7 +89,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) } #ifndef CONFIG_MATH_EMULATION - if (!cpu_has_fpu) { + if (!boot_cpu_has(X86_FEATURE_FPU)) { pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n"); for (;;) asm volatile("hlt"); @@ -106,7 +106,7 @@ static void __init fpu__init_system_mxcsr(void) { unsigned int mask = 0; - if (cpu_has_fxsr) { + if (boot_cpu_has(X86_FEATURE_FXSR)) { /* Static because GCC does not get 16-byte stack alignment right: */ static struct fxregs_state fxregs __initdata; @@ -212,7 +212,7 @@ static void __init fpu__init_system_xstate_size_legacy(void) * fpu__init_system_xstate(). */ - if (!cpu_has_fpu) { + if (!boot_cpu_has(X86_FEATURE_FPU)) { /* * Disable xsave as we do not support it if i387 * emulation is enabled. @@ -221,7 +221,7 @@ static void __init fpu__init_system_xstate_size_legacy(void) setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); xstate_size = sizeof(struct swregs_state); } else { - if (cpu_has_fxsr) + if (boot_cpu_has(X86_FEATURE_FXSR)) xstate_size = sizeof(struct fxregs_state); else xstate_size = sizeof(struct fregs_state); diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 8bd1c00..81422df 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -21,7 +21,10 @@ int regset_xregset_fpregs_active(struct task_struct *target, const struct user_r { struct fpu *target_fpu = &target->thread.fpu; - return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0; + if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active) + return regset->n; + else + return 0; } int xfpregs_get(struct task_struct *target, const struct user_regset *regset, @@ -30,7 +33,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, { struct fpu *fpu = &target->thread.fpu; - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; fpu__activate_fpstate_read(fpu); @@ -47,7 +50,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; int ret; - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; fpu__activate_fpstate_write(fpu); @@ -65,7 +68,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, * update the header bits in the xsave header, indicating the * presence of FP and SSE state. */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; return ret; @@ -79,7 +82,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, struct xregs_state *xsave; int ret; - if (!cpu_has_xsave) + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -ENODEV; fpu__activate_fpstate_read(fpu); @@ -108,7 +111,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, struct xregs_state *xsave; int ret; - if (!cpu_has_xsave) + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -ENODEV; fpu__activate_fpstate_write(fpu); @@ -275,10 +278,10 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, fpu__activate_fpstate_read(fpu); - if (!static_cpu_has(X86_FEATURE_FPU)) + if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &fpu->state.fsave, 0, -1); @@ -306,10 +309,10 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, fpu__activate_fpstate_write(fpu); fpstate_sanitize_xstate(fpu); - if (!static_cpu_has(X86_FEATURE_FPU)) + if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpu->state.fsave, 0, -1); @@ -325,7 +328,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, * update the header bit in the xsave header, indicating the * presence of FP. */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FP; return ret; } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index b48ef35..4ea2a59 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -190,7 +190,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu) */ void fpu__init_cpu_xstate(void) { - if (!cpu_has_xsave || !xfeatures_mask) + if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask) return; cr4_set_bits(X86_CR4_OSXSAVE); @@ -280,7 +280,7 @@ static void __init setup_xstate_comp(void) xstate_comp_offsets[0] = 0; xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space); - if (!cpu_has_xsaves) { + if (!boot_cpu_has(X86_FEATURE_XSAVES)) { for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { if (xfeature_enabled(i)) { xstate_comp_offsets[i] = xstate_offsets[i]; @@ -316,13 +316,13 @@ static void __init setup_init_fpu_buf(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - if (!cpu_has_xsave) + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return; setup_xstate_features(); print_xstate_features(); - if (cpu_has_xsaves) { + if (boot_cpu_has(X86_FEATURE_XSAVES)) { init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask; init_fpstate.xsave.header.xfeatures = xfeatures_mask; } @@ -417,7 +417,7 @@ static int xfeature_size(int xfeature_nr) */ static int using_compacted_format(void) { - return cpu_has_xsaves; + return boot_cpu_has(X86_FEATURE_XSAVES); } static void __xstate_dump_leaves(void) @@ -549,7 +549,7 @@ static unsigned int __init calculate_xstate_size(void) unsigned int eax, ebx, ecx, edx; unsigned int calculated_xstate_size; - if (!cpu_has_xsaves) { + if (!boot_cpu_has(X86_FEATURE_XSAVES)) { /* * - CPUID function 0DH, sub-function 0: * EBX enumerates the size (in bytes) required by @@ -630,7 +630,7 @@ void __init fpu__init_system_xstate(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - if (!cpu_has_xsave) { + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { pr_info("x86/fpu: Legacy x87 FPU detected.\n"); return; } @@ -667,7 +667,7 @@ void __init fpu__init_system_xstate(void) pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", xfeatures_mask, xstate_size, - cpu_has_xsaves ? "compacted" : "standard"); + boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard"); } /* @@ -678,7 +678,7 @@ void fpu__resume_cpu(void) /* * Restore XCR0 on xsave capable CPUs: */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 2911ef3..d784bb5 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -34,6 +34,8 @@ asmlinkage __visible void __init i386_start_kernel(void) cr4_init_shadow(); sanitize_boot_params(&boot_params); + x86_early_init_platform_quirks(); + /* Call the subarch specific early setup function */ switch (boot_params.hdr.hardware_subarch) { case X86_SUBARCH_INTEL_MID: diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 1f4422d..b72fb0b 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -182,6 +182,7 @@ void __init x86_64_start_reservations(char *real_mode_data) if (!boot_params.hdr.version) copy_bootdata(__va(real_mode_data)); + x86_early_init_platform_quirks(); reserve_ebda_region(); switch (boot_params.hdr.hardware_subarch) { diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index af11129..6f8902b 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -555,62 +555,53 @@ early_idt_handler_common: */ cld - cmpl $2,(%esp) # X86_TRAP_NMI - je .Lis_nmi # Ignore NMI - - cmpl $2,%ss:early_recursion_flag - je hlt_loop incl %ss:early_recursion_flag - push %eax # 16(%esp) - push %ecx # 12(%esp) - push %edx # 8(%esp) - push %ds # 4(%esp) - push %es # 0(%esp) - movl $(__KERNEL_DS),%eax - movl %eax,%ds - movl %eax,%es - - cmpl $(__KERNEL_CS),32(%esp) - jne 10f + /* The vector number is in pt_regs->gs */ - leal 28(%esp),%eax # Pointer to %eip - call early_fixup_exception - andl %eax,%eax - jnz ex_entry /* found an exception entry */ - -10: -#ifdef CONFIG_PRINTK - xorl %eax,%eax - movw %ax,2(%esp) /* clean up the segment values on some cpus */ - movw %ax,6(%esp) - movw %ax,34(%esp) - leal 40(%esp),%eax - pushl %eax /* %esp before the exception */ - pushl %ebx - pushl %ebp - pushl %esi - pushl %edi - movl %cr2,%eax - pushl %eax - pushl (20+6*4)(%esp) /* trapno */ - pushl $fault_msg - call printk -#endif - call dump_stack -hlt_loop: - hlt - jmp hlt_loop - -ex_entry: - pop %es - pop %ds - pop %edx - pop %ecx - pop %eax - decl %ss:early_recursion_flag -.Lis_nmi: - addl $8,%esp /* drop vector number and error code */ + cld + pushl %fs /* pt_regs->fs */ + movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ + pushl %es /* pt_regs->es */ + movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ + pushl %ds /* pt_regs->ds */ + movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ + pushl %eax /* pt_regs->ax */ + pushl %ebp /* pt_regs->bp */ + pushl %edi /* pt_regs->di */ + pushl %esi /* pt_regs->si */ + pushl %edx /* pt_regs->dx */ + pushl %ecx /* pt_regs->cx */ + pushl %ebx /* pt_regs->bx */ + + /* Fix up DS and ES */ + movl $(__KERNEL_DS), %ecx + movl %ecx, %ds + movl %ecx, %es + + /* Load the vector number into EDX */ + movl PT_GS(%esp), %edx + + /* Load GS into pt_regs->gs and clear high bits */ + movw %gs, PT_GS(%esp) + movw $0, PT_GS+2(%esp) + + movl %esp, %eax /* args are pt_regs (EAX), trapnr (EDX) */ + call early_fixup_exception + + popl %ebx /* pt_regs->bx */ + popl %ecx /* pt_regs->cx */ + popl %edx /* pt_regs->dx */ + popl %esi /* pt_regs->si */ + popl %edi /* pt_regs->di */ + popl %ebp /* pt_regs->bp */ + popl %eax /* pt_regs->ax */ + popl %ds /* pt_regs->ds */ + popl %es /* pt_regs->es */ + popl %fs /* pt_regs->fs */ + popl %gs /* pt_regs->gs */ + decl %ss:early_recursion_flag + addl $4, %esp /* pop pt_regs->orig_ax */ iret ENDPROC(early_idt_handler_common) @@ -647,10 +638,14 @@ ignore_int: popl %eax #endif iret + +hlt_loop: + hlt + jmp hlt_loop ENDPROC(ignore_int) __INITDATA .align 4 -early_recursion_flag: +GLOBAL(early_recursion_flag) .long 0 __REFDATA @@ -715,19 +710,6 @@ __INITRODATA int_msg: .asciz "Unknown interrupt or fault at: %p %p %p\n" -fault_msg: -/* fault info: */ - .ascii "BUG: Int %d: CR2 %p\n" -/* regs pushed in early_idt_handler: */ - .ascii " EDI %p ESI %p EBP %p EBX %p\n" - .ascii " ESP %p ES %p DS %p\n" - .ascii " EDX %p ECX %p EAX %p\n" -/* fault frame: */ - .ascii " vec %p err %p EIP %p CS %p flg %p\n" - .ascii "Stack: %p %p %p %p %p %p %p %p\n" - .ascii " %p %p %p %p %p %p %p %p\n" - .asciz " %p %p %p %p %p %p %p %p\n" - #include "../../x86/xen/xen-head.S" /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 22fbf9d..5df831e 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -20,6 +20,7 @@ #include <asm/processor-flags.h> #include <asm/percpu.h> #include <asm/nops.h> +#include "../entry/calling.h" #ifdef CONFIG_PARAVIRT #include <asm/asm-offsets.h> @@ -64,6 +65,14 @@ startup_64: * tables and then reload them. */ + /* + * Setup stack for verify_cpu(). "-8" because stack_start is defined + * this way, see below. Our best guess is a NULL ptr for stack + * termination heuristics and we don't want to break anything which + * might depend on it (kgdb, ...). + */ + leaq (__end_init_task - 8)(%rip), %rsp + /* Sanitize CPU configuration */ call verify_cpu @@ -350,90 +359,48 @@ early_idt_handler_common: */ cld - cmpl $2,(%rsp) # X86_TRAP_NMI - je .Lis_nmi # Ignore NMI - - cmpl $2,early_recursion_flag(%rip) - jz 1f incl early_recursion_flag(%rip) - pushq %rax # 64(%rsp) - pushq %rcx # 56(%rsp) - pushq %rdx # 48(%rsp) - pushq %rsi # 40(%rsp) - pushq %rdi # 32(%rsp) - pushq %r8 # 24(%rsp) - pushq %r9 # 16(%rsp) - pushq %r10 # 8(%rsp) - pushq %r11 # 0(%rsp) - - cmpl $__KERNEL_CS,96(%rsp) - jne 11f - - cmpl $14,72(%rsp) # Page fault? + /* The vector number is currently in the pt_regs->di slot. */ + pushq %rsi /* pt_regs->si */ + movq 8(%rsp), %rsi /* RSI = vector number */ + movq %rdi, 8(%rsp) /* pt_regs->di = RDI */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq %rax /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + pushq %r9 /* pt_regs->r9 */ + pushq %r10 /* pt_regs->r10 */ + pushq %r11 /* pt_regs->r11 */ + pushq %rbx /* pt_regs->bx */ + pushq %rbp /* pt_regs->bp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ + + cmpq $14,%rsi /* Page fault? */ jnz 10f - GET_CR2_INTO(%rdi) # can clobber any volatile register if pv + GET_CR2_INTO(%rdi) /* Can clobber any volatile register if pv */ call early_make_pgtable andl %eax,%eax - jz 20f # All good + jz 20f /* All good */ 10: - leaq 88(%rsp),%rdi # Pointer to %rip + movq %rsp,%rdi /* RDI = pt_regs; RSI is already trapnr */ call early_fixup_exception - andl %eax,%eax - jnz 20f # Found an exception entry - -11: -#ifdef CONFIG_EARLY_PRINTK - GET_CR2_INTO(%r9) # can clobber any volatile register if pv - movl 80(%rsp),%r8d # error code - movl 72(%rsp),%esi # vector number - movl 96(%rsp),%edx # %cs - movq 88(%rsp),%rcx # %rip - xorl %eax,%eax - leaq early_idt_msg(%rip),%rdi - call early_printk - cmpl $2,early_recursion_flag(%rip) - jz 1f - call dump_stack -#ifdef CONFIG_KALLSYMS - leaq early_idt_ripmsg(%rip),%rdi - movq 40(%rsp),%rsi # %rip again - call __print_symbol -#endif -#endif /* EARLY_PRINTK */ -1: hlt - jmp 1b - -20: # Exception table entry found or page table generated - popq %r11 - popq %r10 - popq %r9 - popq %r8 - popq %rdi - popq %rsi - popq %rdx - popq %rcx - popq %rax + +20: decl early_recursion_flag(%rip) -.Lis_nmi: - addq $16,%rsp # drop vector number and error code - INTERRUPT_RETURN + jmp restore_regs_and_iret ENDPROC(early_idt_handler_common) __INITDATA .balign 4 -early_recursion_flag: +GLOBAL(early_recursion_flag) .long 0 -#ifdef CONFIG_EARLY_PRINTK -early_idt_msg: - .asciz "PANIC: early exception %02lx rip %lx:%lx error %lx cr2 %lx\n" -early_idt_ripmsg: - .asciz "RIP %s\n" -#endif /* CONFIG_EARLY_PRINTK */ - #define NEXT_PAGE(name) \ .balign PAGE_SIZE; \ GLOBAL(name) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index a1f0e4a..f112af7 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -54,7 +54,7 @@ struct hpet_dev { char name[10]; }; -inline struct hpet_dev *EVT_TO_HPET_DEV(struct clock_event_device *evtdev) +static inline struct hpet_dev *EVT_TO_HPET_DEV(struct clock_event_device *evtdev) { return container_of(evtdev, struct hpet_dev, evt); } @@ -773,7 +773,6 @@ static struct clocksource clocksource_hpet = { .mask = HPET_MASK, .flags = CLOCK_SOURCE_IS_CONTINUOUS, .resume = hpet_resume_counter, - .archdata = { .vclock_mode = VCLOCK_HPET }, }; static int hpet_clocksource_register(void) diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index e565e0e..fc25f69 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -13,6 +13,7 @@ #include <linux/cpu.h> #include <asm/kprobes.h> #include <asm/alternative.h> +#include <asm/text-patching.h> #ifdef HAVE_JUMP_LABEL diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 2da6ee9..04cde52 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -45,6 +45,7 @@ #include <linux/uaccess.h> #include <linux/memory.h> +#include <asm/text-patching.h> #include <asm/debugreg.h> #include <asm/apicdef.h> #include <asm/apic.h> diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index ae703ac..38cf7a7 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -51,6 +51,7 @@ #include <linux/ftrace.h> #include <linux/frame.h> +#include <asm/text-patching.h> #include <asm/cacheflush.h> #include <asm/desc.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 7b3b9d1..4425f59 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -29,6 +29,7 @@ #include <linux/kallsyms.h> #include <linux/ftrace.h> +#include <asm/text-patching.h> #include <asm/cacheflush.h> #include <asm/desc.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 8079508..eea2a6f 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -285,14 +285,6 @@ static void __init paravirt_ops_setup(void) { pv_info.name = "KVM"; - /* - * KVM isn't paravirt in the sense of paravirt_enabled. A KVM - * guest kernel works like a bare metal kernel with additional - * features, and paravirt_enabled is about features that are - * missing. - */ - pv_info.paravirt_enabled = 0; - if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) pv_cpu_ops.io_delay = kvm_io_delay; @@ -522,7 +514,7 @@ static noinline uint32_t __kvm_cpuid_base(void) if (boot_cpu_data.cpuid_level < 0) return 0; /* So we don't blow up on old processors */ - if (cpu_has_hypervisor) + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0); return 0; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 005c03e..477ae80 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -31,6 +31,7 @@ #include <linux/jump_label.h> #include <linux/random.h> +#include <asm/text-patching.h> #include <asm/page.h> #include <asm/pgtable.h> #include <asm/setup.h> diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index f08ac28..7b3b3f2 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -294,7 +294,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void) struct pv_info pv_info = { .name = "bare hardware", - .paravirt_enabled = 0, .kernel_rpl = 0, .shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */ @@ -339,8 +338,10 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .write_cr8 = native_write_cr8, #endif .wbinvd = native_wbinvd, - .read_msr = native_read_msr_safe, - .write_msr = native_write_msr_safe, + .read_msr = native_read_msr, + .write_msr = native_write_msr, + .read_msr_safe = native_read_msr_safe, + .write_msr_safe = native_write_msr_safe, .read_pmc = native_read_pmc, .load_tr_desc = native_load_tr_desc, .set_ldt = native_set_ldt, diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c index 35ccf75..f712dfd 100644 --- a/arch/x86/kernel/pci-iommu_table.c +++ b/arch/x86/kernel/pci-iommu_table.c @@ -72,7 +72,7 @@ void __init check_iommu_entries(struct iommu_table_entry *start, } } #else -inline void check_iommu_entries(struct iommu_table_entry *start, +void __init check_iommu_entries(struct iommu_table_entry *start, struct iommu_table_entry *finish) { } diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c new file mode 100644 index 0000000..b2f8a33 --- /dev/null +++ b/arch/x86/kernel/platform-quirks.c @@ -0,0 +1,35 @@ +#include <linux/kernel.h> +#include <linux/init.h> + +#include <asm/setup.h> +#include <asm/bios_ebda.h> + +void __init x86_early_init_platform_quirks(void) +{ + x86_platform.legacy.rtc = 1; + x86_platform.legacy.ebda_search = 0; + x86_platform.legacy.devices.pnpbios = 1; + + switch (boot_params.hdr.hardware_subarch) { + case X86_SUBARCH_PC: + x86_platform.legacy.ebda_search = 1; + break; + case X86_SUBARCH_XEN: + case X86_SUBARCH_LGUEST: + case X86_SUBARCH_INTEL_MID: + case X86_SUBARCH_CE4100: + x86_platform.legacy.devices.pnpbios = 0; + x86_platform.legacy.rtc = 0; + break; + } + + if (x86_platform.set_legacy_features) + x86_platform.set_legacy_features(); +} + +#if defined(CONFIG_PNPBIOS) +bool __init arch_pnpbios_disabled(void) +{ + return x86_platform.legacy.devices.pnpbios == 0; +} +#endif diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6cbab31..6b16c36 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -136,25 +136,6 @@ void release_thread(struct task_struct *dead_task) } } -static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr) -{ - struct user_desc ud = { - .base_addr = addr, - .limit = 0xfffff, - .seg_32bit = 1, - .limit_in_pages = 1, - .useable = 1, - }; - struct desc_struct *desc = t->thread.tls_array; - desc += tls; - fill_ldt(desc, &ud); -} - -static inline u32 read_32bit_tls(struct task_struct *t, int tls) -{ - return get_desc_base(&t->thread.tls_array[tls]); -} - int copy_thread_tls(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct *p, unsigned long tls) { @@ -169,9 +150,9 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); - p->thread.gs = p->thread.gsindex ? 0 : me->thread.gs; + p->thread.gsbase = p->thread.gsindex ? 0 : me->thread.gsbase; savesegment(fs, p->thread.fsindex); - p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs; + p->thread.fsbase = p->thread.fsindex ? 0 : me->thread.fsbase; savesegment(es, p->thread.es); savesegment(ds, p->thread.ds); memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); @@ -210,7 +191,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, */ if (clone_flags & CLONE_SETTLS) { #ifdef CONFIG_IA32_EMULATION - if (is_ia32_task()) + if (in_ia32_syscall()) err = do_set_thread_area(p, -1, (struct user_desc __user *)tls, 0); else @@ -282,7 +263,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); - unsigned fsindex, gsindex; + unsigned prev_fsindex, prev_gsindex; fpu_switch_t fpu_switch; fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); @@ -292,8 +273,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * * (e.g. xen_load_tls()) */ - savesegment(fs, fsindex); - savesegment(gs, gsindex); + savesegment(fs, prev_fsindex); + savesegment(gs, prev_gsindex); /* * Load TLS before restoring any segments so that segment loads @@ -336,66 +317,104 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Switch FS and GS. * * These are even more complicated than DS and ES: they have - * 64-bit bases are that controlled by arch_prctl. Those bases - * only differ from the values in the GDT or LDT if the selector - * is 0. - * - * Loading the segment register resets the hidden base part of - * the register to 0 or the value from the GDT / LDT. If the - * next base address zero, writing 0 to the segment register is - * much faster than using wrmsr to explicitly zero the base. - * - * The thread_struct.fs and thread_struct.gs values are 0 - * if the fs and gs bases respectively are not overridden - * from the values implied by fsindex and gsindex. They - * are nonzero, and store the nonzero base addresses, if - * the bases are overridden. - * - * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should - * be impossible. - * - * Therefore we need to reload the segment registers if either - * the old or new selector is nonzero, and we need to override - * the base address if next thread expects it to be overridden. + * 64-bit bases are that controlled by arch_prctl. The bases + * don't necessarily match the selectors, as user code can do + * any number of things to cause them to be inconsistent. * - * This code is unnecessarily slow in the case where the old and - * new indexes are zero and the new base is nonzero -- it will - * unnecessarily write 0 to the selector before writing the new - * base address. + * We don't promise to preserve the bases if the selectors are + * nonzero. We also don't promise to preserve the base if the + * selector is zero and the base doesn't match whatever was + * most recently passed to ARCH_SET_FS/GS. (If/when the + * FSGSBASE instructions are enabled, we'll need to offer + * stronger guarantees.) * - * Note: This all depends on arch_prctl being the only way that - * user code can override the segment base. Once wrfsbase and - * wrgsbase are enabled, most of this code will need to change. + * As an invariant, + * (fsbase != 0 && fsindex != 0) || (gsbase != 0 && gsindex != 0) is + * impossible. */ - if (unlikely(fsindex | next->fsindex | prev->fs)) { + if (next->fsindex) { + /* Loading a nonzero value into FS sets the index and base. */ loadsegment(fs, next->fsindex); - - /* - * If user code wrote a nonzero value to FS, then it also - * cleared the overridden base address. - * - * XXX: if user code wrote 0 to FS and cleared the base - * address itself, we won't notice and we'll incorrectly - * restore the prior base address next time we reschdule - * the process. - */ - if (fsindex) - prev->fs = 0; + } else { + if (next->fsbase) { + /* Next index is zero but next base is nonzero. */ + if (prev_fsindex) + loadsegment(fs, 0); + wrmsrl(MSR_FS_BASE, next->fsbase); + } else { + /* Next base and index are both zero. */ + if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { + /* + * We don't know the previous base and can't + * find out without RDMSR. Forcibly clear it. + */ + loadsegment(fs, __USER_DS); + loadsegment(fs, 0); + } else { + /* + * If the previous index is zero and ARCH_SET_FS + * didn't change the base, then the base is + * also zero and we don't need to do anything. + */ + if (prev->fsbase || prev_fsindex) + loadsegment(fs, 0); + } + } } - if (next->fs) - wrmsrl(MSR_FS_BASE, next->fs); - prev->fsindex = fsindex; + /* + * Save the old state and preserve the invariant. + * NB: if prev_fsindex == 0, then we can't reliably learn the base + * without RDMSR because Intel user code can zero it without telling + * us and AMD user code can program any 32-bit value without telling + * us. + */ + if (prev_fsindex) + prev->fsbase = 0; + prev->fsindex = prev_fsindex; - if (unlikely(gsindex | next->gsindex | prev->gs)) { + if (next->gsindex) { + /* Loading a nonzero value into GS sets the index and base. */ load_gs_index(next->gsindex); - - /* This works (and fails) the same way as fsindex above. */ - if (gsindex) - prev->gs = 0; + } else { + if (next->gsbase) { + /* Next index is zero but next base is nonzero. */ + if (prev_gsindex) + load_gs_index(0); + wrmsrl(MSR_KERNEL_GS_BASE, next->gsbase); + } else { + /* Next base and index are both zero. */ + if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { + /* + * We don't know the previous base and can't + * find out without RDMSR. Forcibly clear it. + * + * This contains a pointless SWAPGS pair. + * Fixing it would involve an explicit check + * for Xen or a new pvop. + */ + load_gs_index(__USER_DS); + load_gs_index(0); + } else { + /* + * If the previous index is zero and ARCH_SET_GS + * didn't change the base, then the base is + * also zero and we don't need to do anything. + */ + if (prev->gsbase || prev_gsindex) + load_gs_index(0); + } + } } - if (next->gs) - wrmsrl(MSR_KERNEL_GS_BASE, next->gs); - prev->gsindex = gsindex; + /* + * Save the old state and preserve the invariant. + * NB: if prev_gsindex == 0, then we can't reliably learn the base + * without RDMSR because Intel user code can zero it without telling + * us and AMD user code can program any 32-bit value without telling + * us. + */ + if (prev_gsindex) + prev->gsbase = 0; + prev->gsindex = prev_gsindex; switch_fpu_finish(next_fpu, fpu_switch); @@ -516,23 +535,11 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) if (addr >= TASK_SIZE_OF(task)) return -EPERM; cpu = get_cpu(); - /* handle small bases via the GDT because that's faster to - switch. */ - if (addr <= 0xffffffff) { - set_32bit_tls(task, GS_TLS, addr); - if (doit) { - load_TLS(&task->thread, cpu); - load_gs_index(GS_TLS_SEL); - } - task->thread.gsindex = GS_TLS_SEL; - task->thread.gs = 0; - } else { - task->thread.gsindex = 0; - task->thread.gs = addr; - if (doit) { - load_gs_index(0); - ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); - } + task->thread.gsindex = 0; + task->thread.gsbase = addr; + if (doit) { + load_gs_index(0); + ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); } put_cpu(); break; @@ -542,52 +549,30 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) if (addr >= TASK_SIZE_OF(task)) return -EPERM; cpu = get_cpu(); - /* handle small bases via the GDT because that's faster to - switch. */ - if (addr <= 0xffffffff) { - set_32bit_tls(task, FS_TLS, addr); - if (doit) { - load_TLS(&task->thread, cpu); - loadsegment(fs, FS_TLS_SEL); - } - task->thread.fsindex = FS_TLS_SEL; - task->thread.fs = 0; - } else { - task->thread.fsindex = 0; - task->thread.fs = addr; - if (doit) { - /* set the selector to 0 to not confuse - __switch_to */ - loadsegment(fs, 0); - ret = wrmsrl_safe(MSR_FS_BASE, addr); - } + task->thread.fsindex = 0; + task->thread.fsbase = addr; + if (doit) { + /* set the selector to 0 to not confuse __switch_to */ + loadsegment(fs, 0); + ret = wrmsrl_safe(MSR_FS_BASE, addr); } put_cpu(); break; case ARCH_GET_FS: { unsigned long base; - if (task->thread.fsindex == FS_TLS_SEL) - base = read_32bit_tls(task, FS_TLS); - else if (doit) + if (doit) rdmsrl(MSR_FS_BASE, base); else - base = task->thread.fs; + base = task->thread.fsbase; ret = put_user(base, (unsigned long __user *)addr); break; } case ARCH_GET_GS: { unsigned long base; - unsigned gsindex; - if (task->thread.gsindex == GS_TLS_SEL) - base = read_32bit_tls(task, GS_TLS); - else if (doit) { - savesegment(gs, gsindex); - if (gsindex) - rdmsrl(MSR_KERNEL_GS_BASE, base); - else - base = task->thread.gs; - } else - base = task->thread.gs; + if (doit) + rdmsrl(MSR_KERNEL_GS_BASE, base); + else + base = task->thread.gsbase; ret = put_user(base, (unsigned long __user *)addr); break; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 32e9d9c..e60ef91 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -303,29 +303,11 @@ static int set_segment_reg(struct task_struct *task, switch (offset) { case offsetof(struct user_regs_struct,fs): - /* - * If this is setting fs as for normal 64-bit use but - * setting fs_base has implicitly changed it, leave it. - */ - if ((value == FS_TLS_SEL && task->thread.fsindex == 0 && - task->thread.fs != 0) || - (value == 0 && task->thread.fsindex == FS_TLS_SEL && - task->thread.fs == 0)) - break; task->thread.fsindex = value; if (task == current) loadsegment(fs, task->thread.fsindex); break; case offsetof(struct user_regs_struct,gs): - /* - * If this is setting gs as for normal 64-bit use but - * setting gs_base has implicitly changed it, leave it. - */ - if ((value == GS_TLS_SEL && task->thread.gsindex == 0 && - task->thread.gs != 0) || - (value == 0 && task->thread.gsindex == GS_TLS_SEL && - task->thread.gs == 0)) - break; task->thread.gsindex = value; if (task == current) load_gs_index(task->thread.gsindex); @@ -417,7 +399,7 @@ static int putreg(struct task_struct *child, * to set either thread.fs or thread.fsindex and the * corresponding GDT slot. */ - if (child->thread.fs != value) + if (child->thread.fsbase != value) return do_arch_prctl(child, ARCH_SET_FS, value); return 0; case offsetof(struct user_regs_struct,gs_base): @@ -426,7 +408,7 @@ static int putreg(struct task_struct *child, */ if (value >= TASK_SIZE_OF(child)) return -EIO; - if (child->thread.gs != value) + if (child->thread.gsbase != value) return do_arch_prctl(child, ARCH_SET_GS, value); return 0; #endif @@ -453,31 +435,17 @@ static unsigned long getreg(struct task_struct *task, unsigned long offset) #ifdef CONFIG_X86_64 case offsetof(struct user_regs_struct, fs_base): { /* - * do_arch_prctl may have used a GDT slot instead of - * the MSR. To userland, it appears the same either - * way, except the %fs segment selector might not be 0. + * XXX: This will not behave as expected if called on + * current or if fsindex != 0. */ - unsigned int seg = task->thread.fsindex; - if (task->thread.fs != 0) - return task->thread.fs; - if (task == current) - asm("movl %%fs,%0" : "=r" (seg)); - if (seg != FS_TLS_SEL) - return 0; - return get_desc_base(&task->thread.tls_array[FS_TLS]); + return task->thread.fsbase; } case offsetof(struct user_regs_struct, gs_base): { /* - * Exactly the same here as the %fs handling above. + * XXX: This will not behave as expected if called on + * current or if fsindex != 0. */ - unsigned int seg = task->thread.gsindex; - if (task->thread.gs != 0) - return task->thread.gs; - if (task == current) - asm("movl %%gs,%0" : "=r" (seg)); - if (seg != GS_TLS_SEL) - return 0; - return get_desc_base(&task->thread.tls_array[GS_TLS]); + return task->thread.gsbase; } #endif } @@ -1266,7 +1234,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { #ifdef CONFIG_X86_X32_ABI - if (!is_ia32_task()) + if (!in_ia32_syscall()) return x32_arch_ptrace(child, request, caddr, cdata); #endif #ifdef CONFIG_IA32_EMULATION diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index ab0adc0..a9b31eb 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -535,6 +535,15 @@ static void native_machine_emergency_restart(void) mode = reboot_mode == REBOOT_WARM ? 0x1234 : 0; *((unsigned short *)__va(0x472)) = mode; + /* + * If an EFI capsule has been registered with the firmware then + * override the reboot= parameter. + */ + if (efi_capsule_pending(NULL)) { + pr_info("EFI capsule is pending, forcing EFI reboot.\n"); + reboot_type = BOOT_EFI; + } + for (;;) { /* Could also try the reset bit in the Hammer NB */ switch (reboot_type) { diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 4af8d06..eceaa08 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -14,6 +14,7 @@ #include <asm/time.h> #include <asm/intel-mid.h> #include <asm/rtc.h> +#include <asm/setup.h> #ifdef CONFIG_X86_32 /* @@ -185,22 +186,7 @@ static __init int add_rtc_cmos(void) } } #endif - if (of_have_populated_dt()) - return 0; - - /* Intel MID platforms don't have ioport rtc */ - if (intel_mid_identify_cpu()) - return -ENODEV; - -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) { - /* This warning can likely go away again in a year or two. */ - pr_info("ACPI: not registering RTC platform device\n"); - return -ENODEV; - } -#endif - - if (paravirt_enabled() && !paravirt_has(RTC)) + if (!x86_platform.legacy.rtc) return -ENODEV; platform_device_register(&rtc_device); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 548ddf7..22cc2f9 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -248,18 +248,17 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, if (config_enabled(CONFIG_X86_64)) sp -= 128; - if (!onsigstack) { - /* This is the X/Open sanctioned signal stack switching. */ - if (ka->sa.sa_flags & SA_ONSTACK) { - if (current->sas_ss_size) - sp = current->sas_ss_sp + current->sas_ss_size; - } else if (config_enabled(CONFIG_X86_32) && - (regs->ss & 0xffff) != __USER_DS && - !(ka->sa.sa_flags & SA_RESTORER) && - ka->sa.sa_restorer) { - /* This is the legacy signal stack switching. */ - sp = (unsigned long) ka->sa.sa_restorer; - } + /* This is the X/Open sanctioned signal stack switching. */ + if (ka->sa.sa_flags & SA_ONSTACK) { + if (sas_ss_flags(sp) == 0) + sp = current->sas_ss_sp + current->sas_ss_size; + } else if (config_enabled(CONFIG_X86_32) && + !onsigstack && + (regs->ss & 0xffff) != __USER_DS && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) { + /* This is the legacy signal stack switching. */ + sp = (unsigned long) ka->sa.sa_restorer; } if (fpu->fpstate_active) { @@ -391,7 +390,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, put_user_ex(&frame->uc, &frame->puc); /* Create the ucontext. */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); else put_user_ex(0, &frame->uc.uc_flags); @@ -442,7 +441,7 @@ static unsigned long frame_uc_flags(struct pt_regs *regs) { unsigned long flags; - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS; else flags = UC_SIGCONTEXT_SS; @@ -762,7 +761,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { #ifdef CONFIG_X86_64 - if (is_ia32_task()) + if (in_ia32_syscall()) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index a2065d3..fafe8b9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -332,6 +332,11 @@ static void __init smp_init_package_map(void) * primary cores. */ ncpus = boot_cpu_data.x86_max_cores; + if (!ncpus) { + pr_warn("x86_max_cores == zero !?!?"); + ncpus = 1; + } + __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus); /* @@ -1231,7 +1236,7 @@ static int __init smp_sanity_check(unsigned max_cpus) * If we couldn't find a local APIC, then get out of here now! */ if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) && - !cpu_has_apic) { + !boot_cpu_has(X86_FEATURE_APIC)) { if (!disable_apic) { pr_err("BIOS bug, local APIC #%d not detected!...\n", boot_cpu_physical_apicid); diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index b285d4e..623965e 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -68,6 +68,21 @@ struct efifb_dmi_info efifb_dmi_list[] = { [M_UNKNOWN] = { NULL, 0, 0, 0, 0, OVERRIDE_NONE } }; +void efifb_setup_from_dmi(struct screen_info *si, const char *opt) +{ + int i; + + for (i = 0; i < M_UNKNOWN; i++) { + if (efifb_dmi_list[i].base != 0 && + !strcmp(opt, efifb_dmi_list[i].optname)) { + si->lfb_base = efifb_dmi_list[i].base; + si->lfb_linelength = efifb_dmi_list[i].stride; + si->lfb_width = efifb_dmi_list[i].width; + si->lfb_height = efifb_dmi_list[i].height; + } + } +} + #define choose_value(dmivalue, fwvalue, field, flags) ({ \ typeof(fwvalue) _ret_ = fwvalue; \ if ((flags) & (field)) \ @@ -106,14 +121,24 @@ static int __init efifb_set_system(const struct dmi_system_id *id) continue; for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { resource_size_t start, end; + unsigned long flags; + + flags = pci_resource_flags(dev, i); + if (!(flags & IORESOURCE_MEM)) + continue; + + if (flags & IORESOURCE_UNSET) + continue; + + if (pci_resource_len(dev, i) == 0) + continue; start = pci_resource_start(dev, i); - if (start == 0) - break; end = pci_resource_end(dev, i); if (screen_info.lfb_base >= start && screen_info.lfb_base < end) { found_bar = 1; + break; } } } diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index e72a07f..9b0185f 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -74,12 +74,6 @@ void __init tboot_probe(void) return; } - /* only a natively booted kernel should be using TXT */ - if (paravirt_enabled()) { - pr_warning("non-0 tboot_addr but pv_ops is enabled\n"); - return; - } - /* Map and check for tboot UUID. */ set_fixmap(FIX_TBOOT_BASE, boot_params.tboot_addr); tboot = (struct tboot *)fix_to_virt(FIX_TBOOT_BASE); diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c index ab40954..f386bad 100644 --- a/arch/x86/kernel/tce_64.c +++ b/arch/x86/kernel/tce_64.c @@ -40,7 +40,7 @@ static inline void flush_tce(void* tceaddr) { /* a single tce can't cross a cache line */ - if (cpu_has_clflush) + if (boot_cpu_has(X86_FEATURE_CLFLUSH)) clflush(tceaddr); else wbinvd(); diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 7fc5e84..9692a5e 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -114,6 +114,7 @@ int do_set_thread_area(struct task_struct *p, int idx, int can_allocate) { struct user_desc info; + unsigned short __maybe_unused sel, modified_sel; if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; @@ -141,6 +142,47 @@ int do_set_thread_area(struct task_struct *p, int idx, set_tls_desc(p, idx, &info, 1); + /* + * If DS, ES, FS, or GS points to the modified segment, forcibly + * refresh it. Only needed on x86_64 because x86_32 reloads them + * on return to user mode. + */ + modified_sel = (idx << 3) | 3; + + if (p == current) { +#ifdef CONFIG_X86_64 + savesegment(ds, sel); + if (sel == modified_sel) + loadsegment(ds, sel); + + savesegment(es, sel); + if (sel == modified_sel) + loadsegment(es, sel); + + savesegment(fs, sel); + if (sel == modified_sel) + loadsegment(fs, sel); + + savesegment(gs, sel); + if (sel == modified_sel) + load_gs_index(sel); +#endif + +#ifdef CONFIG_X86_32_LAZY_GS + savesegment(gs, sel); + if (sel == modified_sel) + loadsegment(gs, sel); +#endif + } else { +#ifdef CONFIG_X86_64 + if (p->thread.fsindex == modified_sel) + p->thread.fsbase = info.base_addr; + + if (p->thread.gsindex == modified_sel) + p->thread.gsbase = info.base_addr; +#endif + } + return 0; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 06cbe25..d159048 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -51,6 +51,7 @@ #include <asm/processor.h> #include <asm/debugreg.h> #include <linux/atomic.h> +#include <asm/text-patching.h> #include <asm/ftrace.h> #include <asm/traps.h> #include <asm/desc.h> diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c9c4c7c..38ba6de 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -36,7 +36,7 @@ static int __read_mostly tsc_unstable; /* native_sched_clock() is called before tsc_init(), so we must start with the TSC soft disabled to prevent - erroneous rdtsc usage on !cpu_has_tsc processors */ + erroneous rdtsc usage on !boot_cpu_has(X86_FEATURE_TSC) processors */ static int __read_mostly tsc_disabled = -1; static DEFINE_STATIC_KEY_FALSE(__use_tsc); @@ -834,15 +834,15 @@ int recalibrate_cpu_khz(void) #ifndef CONFIG_SMP unsigned long cpu_khz_old = cpu_khz; - if (cpu_has_tsc) { - tsc_khz = x86_platform.calibrate_tsc(); - cpu_khz = tsc_khz; - cpu_data(0).loops_per_jiffy = - cpufreq_scale(cpu_data(0).loops_per_jiffy, - cpu_khz_old, cpu_khz); - return 0; - } else + if (!boot_cpu_has(X86_FEATURE_TSC)) return -ENODEV; + + tsc_khz = x86_platform.calibrate_tsc(); + cpu_khz = tsc_khz; + cpu_data(0).loops_per_jiffy = cpufreq_scale(cpu_data(0).loops_per_jiffy, + cpu_khz_old, cpu_khz); + + return 0; #else return -ENODEV; #endif @@ -922,9 +922,6 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, struct cpufreq_freqs *freq = data; unsigned long *lpj; - if (cpu_has(&cpu_data(freq->cpu), X86_FEATURE_CONSTANT_TSC)) - return 0; - lpj = &boot_cpu_data.loops_per_jiffy; #ifdef CONFIG_SMP if (!(freq->flags & CPUFREQ_CONST_LOOPS)) @@ -954,9 +951,9 @@ static struct notifier_block time_cpufreq_notifier_block = { .notifier_call = time_cpufreq_notifier }; -static int __init cpufreq_tsc(void) +static int __init cpufreq_register_tsc_scaling(void) { - if (!cpu_has_tsc) + if (!boot_cpu_has(X86_FEATURE_TSC)) return 0; if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) return 0; @@ -965,7 +962,7 @@ static int __init cpufreq_tsc(void) return 0; } -core_initcall(cpufreq_tsc); +core_initcall(cpufreq_register_tsc_scaling); #endif /* CONFIG_CPU_FREQ */ @@ -1081,7 +1078,7 @@ static void __init check_system_tsc_reliable(void) */ int unsynchronized_tsc(void) { - if (!cpu_has_tsc || tsc_unstable) + if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_unstable) return 1; #ifdef CONFIG_SMP @@ -1205,7 +1202,7 @@ out: static int __init init_tsc_clocksource(void) { - if (!cpu_has_tsc || tsc_disabled > 0 || !tsc_khz) + if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz) return 0; if (tsc_clocksource_reliable) @@ -1242,7 +1239,7 @@ void __init tsc_init(void) u64 lpj; int cpu; - if (!cpu_has_tsc) { + if (!boot_cpu_has(X86_FEATURE_TSC)) { setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 92ae6ac..6aa0f4d 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -92,7 +92,7 @@ unsigned long try_msr_calibrate_tsc(void) if (freq_desc_tables[cpu_index].msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); - ratio = (lo >> 8) & 0x1f; + ratio = (lo >> 8) & 0xff; } else { rdmsr(MSR_IA32_PERF_STATUS, lo, hi); ratio = (hi >> 8) & 0x1f; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index bf4db6e..6c1ff31 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -516,7 +516,7 @@ struct uprobe_xol_ops { static inline int sizeof_long(void) { - return is_ia32_task() ? 4 : 8; + return in_ia32_syscall() ? 4 : 8; } static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) @@ -578,7 +578,7 @@ static void default_abort_op(struct arch_uprobe *auprobe, struct pt_regs *regs) riprel_post_xol(auprobe, regs); } -static struct uprobe_xol_ops default_xol_ops = { +static const struct uprobe_xol_ops default_xol_ops = { .pre_xol = default_pre_xol_op, .post_xol = default_post_xol_op, .abort = default_abort_op, @@ -695,7 +695,7 @@ static void branch_clear_offset(struct arch_uprobe *auprobe, struct insn *insn) 0, insn->immediate.nbytes); } -static struct uprobe_xol_ops branch_xol_ops = { +static const struct uprobe_xol_ops branch_xol_ops = { .emulate = branch_emulate_op, .post_xol = branch_post_xol_op, }; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 4c941f8..9297a00 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -334,7 +334,7 @@ SECTIONS __brk_limit = .; } - . = ALIGN(PAGE_SIZE); + . = ALIGN(PAGE_SIZE); /* keep VO_INIT_SIZE page aligned */ _end = .; STABS_DEBUG diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index bbbaa80..769af90 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -75,7 +75,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) return 0; /* Update OSXSAVE bit */ - if (cpu_has_xsave && best->function == 0x1) { + if (boot_cpu_has(X86_FEATURE_XSAVE) && best->function == 0x1) { best->ecx &= ~F(OSXSAVE); if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) best->ecx |= F(OSXSAVE); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 0f62943..a2f24af 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5110,13 +5110,17 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) { + register void *__sp asm(_ASM_SP); ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; + if (!(ctxt->d & ByteOp)) fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; + asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [fastop]"+S"(fop) + [fastop]"+S"(fop), "+r"(__sp) : "c"(ctxt->src2.val)); + ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); if (!fop) /* exception is returned in fop variable */ return emulate_de(ctxt); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 1ff4dbb..38c0c32 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2823,7 +2823,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, */ if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && - PageTransCompound(pfn_to_page(pfn)) && + PageTransCompoundMap(pfn_to_page(pfn)) && !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; /* @@ -3844,7 +3844,8 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, boot_cpu_data.x86_phys_bits, context->shadow_root_level, false, - cpu_has_gbpages, true, true); + boot_cpu_has(X86_FEATURE_GBPAGES), + true, true); else __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, boot_cpu_data.x86_phys_bits, @@ -4785,7 +4786,7 @@ restart: */ if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && - PageTransCompound(pfn_to_page(pfn))) { + PageTransCompoundMap(pfn_to_page(pfn))) { drop_spte(kvm, sptep); need_tlb_flush = 1; goto restart; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 31346a3..fafd720 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1254,7 +1254,7 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) kvm_load_ldt(svm->host.ldt); #ifdef CONFIG_X86_64 loadsegment(fs, svm->host.fs); - wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs); + wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gsbase); load_gs_index(svm->host.gs); #else #ifdef CONFIG_X86_32_LAZY_GS diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 2f1ea2f..b72743c 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -809,8 +809,7 @@ TRACE_EVENT(kvm_write_tsc_offset, #define host_clocks \ {VCLOCK_NONE, "none"}, \ - {VCLOCK_TSC, "tsc"}, \ - {VCLOCK_HPET, "hpet"} \ + {VCLOCK_TSC, "tsc"} \ TRACE_EVENT(kvm_update_master_clock, TP_PROTO(bool use_master_clock, unsigned int host_clock, bool offset_matched), diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 133679d..cb47fe3 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3390,7 +3390,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) } } - if (cpu_has_xsaves) + if (boot_cpu_has(X86_FEATURE_XSAVES)) rdmsrl(MSR_IA32_XSS, host_xss); return 0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9b7798c..12f33e6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2611,7 +2611,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_MAX_MCE_BANKS; break; case KVM_CAP_XCRS: - r = cpu_has_xsave; + r = boot_cpu_has(X86_FEATURE_XSAVE); break; case KVM_CAP_TSC_CONTROL: r = kvm_has_tsc_control; @@ -3094,7 +3094,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) /* Set XSTATE_BV and possibly XCOMP_BV. */ xsave->header.xfeatures = xstate_bv; - if (cpu_has_xsaves) + if (boot_cpu_has(X86_FEATURE_XSAVES)) xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; /* @@ -3121,7 +3121,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { - if (cpu_has_xsave) { + if (boot_cpu_has(X86_FEATURE_XSAVE)) { memset(guest_xsave, 0, sizeof(struct kvm_xsave)); fill_xsave((u8 *) guest_xsave->region, vcpu); } else { @@ -3139,7 +3139,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, u64 xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; - if (cpu_has_xsave) { + if (boot_cpu_has(X86_FEATURE_XSAVE)) { /* * Here we allow setting states that are not present in * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility @@ -3160,7 +3160,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, struct kvm_xcrs *guest_xcrs) { - if (!cpu_has_xsave) { + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { guest_xcrs->nr_xcrs = 0; return; } @@ -3176,7 +3176,7 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, { int i, r = 0; - if (!cpu_has_xsave) + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -EINVAL; if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags) @@ -5865,7 +5865,7 @@ int kvm_arch_init(void *opaque) perf_register_guest_info_callbacks(&kvm_guest_cbs); - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); kvm_lapic_init(); @@ -7293,7 +7293,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) static void fx_init(struct kvm_vcpu *vcpu) { fpstate_init(&vcpu->arch.guest_fpu.state); - if (cpu_has_xsaves) + if (boot_cpu_has(X86_FEATURE_XSAVES)) vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index fd57d3a..3847e73 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1408,13 +1408,10 @@ __init void lguest_init(void) { /* We're under lguest. */ pv_info.name = "lguest"; - /* Paravirt is enabled. */ - pv_info.paravirt_enabled = 1; /* We're running at privilege level 1, not 0 as normal. */ pv_info.kernel_rpl = 1; /* Everyone except Xen runs with this set. */ pv_info.shared_kernel_pmd = 1; - pv_info.features = 0; /* * We set up all the lguest overrides for sensitive operations. These diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S index be110ef..bf2c607 100644 --- a/arch/x86/lib/rwsem.S +++ b/arch/x86/lib/rwsem.S @@ -29,8 +29,10 @@ * there is contention on the semaphore. * * %eax contains the semaphore pointer on entry. Save the C-clobbered - * registers (%eax, %edx and %ecx) except %eax whish is either a return - * value or just clobbered.. + * registers (%eax, %edx and %ecx) except %eax which is either a return + * value or just gets clobbered. Same is true for %edx so make sure GCC + * reloads it after the slow path, by making it hold a temporary, for + * example see ____down_write(). */ #define save_common_regs \ @@ -106,6 +108,16 @@ ENTRY(call_rwsem_down_write_failed) ret ENDPROC(call_rwsem_down_write_failed) +ENTRY(call_rwsem_down_write_failed_killable) + FRAME_BEGIN + save_common_regs + movq %rax,%rdi + call rwsem_down_write_failed_killable + restore_common_regs + FRAME_END + ret +ENDPROC(call_rwsem_down_write_failed_killable) + ENTRY(call_rwsem_wake) FRAME_BEGIN /* do nothing if still outstanding active readers */ diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 91d93b9..b559d92 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -612,7 +612,7 @@ unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from, { stac(); #ifdef CONFIG_X86_INTEL_USERCOPY - if (n > 64 && cpu_has_xmm2) + if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_zeroing_intel_nocache(to, from, n); else __copy_user_zeroing(to, from, n); @@ -629,7 +629,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr { stac(); #ifdef CONFIG_X86_INTEL_USERCOPY - if (n > 64 && cpu_has_xmm2) + if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_intel_nocache(to, from, n); else __copy_user(to, from, n); diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index f989132..62c0043 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -2,7 +2,7 @@ KCOV_INSTRUMENT_tlb.o := n obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o gup.o setup_nx.o + pat.o pgtable.o physaddr.o gup.o setup_nx.o tlb.o # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) @@ -12,7 +12,6 @@ CFLAGS_setup_nx.o := $(nostackp) CFLAGS_fault.o := -I$(src)/../include/asm/trace obj-$(CONFIG_X86_PAT) += pat_rbtree.o -obj-$(CONFIG_SMP) += tlb.o obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 82447b3..4bb53b8 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -1,5 +1,6 @@ #include <linux/module.h> #include <asm/uaccess.h> +#include <asm/traps.h> typedef bool (*ex_handler_t)(const struct exception_table_entry *, struct pt_regs *, int); @@ -42,6 +43,43 @@ bool ex_handler_ext(const struct exception_table_entry *fixup, } EXPORT_SYMBOL(ex_handler_ext); +bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + WARN_ONCE(1, "unchecked MSR access error: RDMSR from 0x%x\n", + (unsigned int)regs->cx); + + /* Pretend that the read succeeded and returned 0. */ + regs->ip = ex_fixup_addr(fixup); + regs->ax = 0; + regs->dx = 0; + return true; +} +EXPORT_SYMBOL(ex_handler_rdmsr_unsafe); + +bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + WARN_ONCE(1, "unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x)\n", + (unsigned int)regs->cx, + (unsigned int)regs->dx, (unsigned int)regs->ax); + + /* Pretend that the write succeeded. */ + regs->ip = ex_fixup_addr(fixup); + return true; +} +EXPORT_SYMBOL(ex_handler_wrmsr_unsafe); + +bool ex_handler_clear_fs(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + if (static_cpu_has(X86_BUG_NULL_SEG)) + asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS)); + asm volatile ("mov %0, %%fs" : : "rm" (0)); + return ex_handler_default(fixup, regs, trapnr); +} +EXPORT_SYMBOL(ex_handler_clear_fs); + bool ex_has_fault_handler(unsigned long ip) { const struct exception_table_entry *e; @@ -82,24 +120,46 @@ int fixup_exception(struct pt_regs *regs, int trapnr) return handler(e, regs, trapnr); } +extern unsigned int early_recursion_flag; + /* Restricted version used during very early boot */ -int __init early_fixup_exception(unsigned long *ip) +void __init early_fixup_exception(struct pt_regs *regs, int trapnr) { - const struct exception_table_entry *e; - unsigned long new_ip; - ex_handler_t handler; - - e = search_exception_tables(*ip); - if (!e) - return 0; - - new_ip = ex_fixup_addr(e); - handler = ex_fixup_handler(e); - - /* special handling not supported during early boot */ - if (handler != ex_handler_default) - return 0; - - *ip = new_ip; - return 1; + /* Ignore early NMIs. */ + if (trapnr == X86_TRAP_NMI) + return; + + if (early_recursion_flag > 2) + goto halt_loop; + + if (regs->cs != __KERNEL_CS) + goto fail; + + /* + * The full exception fixup machinery is available as soon as + * the early IDT is loaded. This means that it is the + * responsibility of extable users to either function correctly + * when handlers are invoked early or to simply avoid causing + * exceptions before they're ready to handle them. + * + * This is better than filtering which handlers can be used, + * because refusing to call a handler here is guaranteed to + * result in a hard-to-debug panic. + * + * Keep in mind that not all vectors actually get here. Early + * fage faults, for example, are special. + */ + if (fixup_exception(regs, trapnr)) + return; + +fail: + early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n", + (unsigned)trapnr, (unsigned long)regs->cs, regs->ip, + regs->orig_ax, read_cr2()); + + show_regs(regs); + +halt_loop: + while (true) + halt(); } diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 740d7ac..14a9505 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -162,7 +162,7 @@ static __init int setup_hugepagesz(char *opt) unsigned long ps = memparse(opt, &opt); if (ps == PMD_SIZE) { hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); - } else if (ps == PUD_SIZE && cpu_has_gbpages) { + } else if (ps == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES)) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); } else { printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n", @@ -177,7 +177,7 @@ __setup("hugepagesz=", setup_hugepagesz); static __init int gigantic_pages_init(void) { /* With compaction or CMA we can allocate gigantic pages at runtime */ - if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT)) + if (boot_cpu_has(X86_FEATURE_GBPAGES) && !size_to_hstate(1UL << PUD_SHIFT)) hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); return 0; } diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c new file mode 100644 index 0000000..ec21796 --- /dev/null +++ b/arch/x86/mm/ident_map.c @@ -0,0 +1,79 @@ +/* + * Helper routines for building identity mapping page tables. This is + * included by both the compressed kernel and the regular kernel. + */ + +static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page, + unsigned long addr, unsigned long end) +{ + addr &= PMD_MASK; + for (; addr < end; addr += PMD_SIZE) { + pmd_t *pmd = pmd_page + pmd_index(addr); + + if (!pmd_present(*pmd)) + set_pmd(pmd, __pmd(addr | pmd_flag)); + } +} + +static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, + unsigned long addr, unsigned long end) +{ + unsigned long next; + + for (; addr < end; addr = next) { + pud_t *pud = pud_page + pud_index(addr); + pmd_t *pmd; + + next = (addr & PUD_MASK) + PUD_SIZE; + if (next > end) + next = end; + + if (pud_present(*pud)) { + pmd = pmd_offset(pud, 0); + ident_pmd_init(info->pmd_flag, pmd, addr, next); + continue; + } + pmd = (pmd_t *)info->alloc_pgt_page(info->context); + if (!pmd) + return -ENOMEM; + ident_pmd_init(info->pmd_flag, pmd, addr, next); + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); + } + + return 0; +} + +int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, + unsigned long addr, unsigned long end) +{ + unsigned long next; + int result; + int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0; + + for (; addr < end; addr = next) { + pgd_t *pgd = pgd_page + pgd_index(addr) + off; + pud_t *pud; + + next = (addr & PGDIR_MASK) + PGDIR_SIZE; + if (next > end) + next = end; + + if (pgd_present(*pgd)) { + pud = pud_offset(pgd, 0); + result = ident_pud_init(info, pud, addr, next); + if (result) + return result; + continue; + } + + pud = (pud_t *)info->alloc_pgt_page(info->context); + if (!pud) + return -ENOMEM; + result = ident_pud_init(info, pud, addr, next); + if (result) + return result; + set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); + } + + return 0; +} diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 9d56f27..372aad2 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -157,23 +157,23 @@ static void __init probe_page_size_mask(void) * This will simplify cpa(), which otherwise needs to support splitting * large pages into small in interrupt context, etc. */ - if (cpu_has_pse && !debug_pagealloc_enabled()) + if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled()) page_size_mask |= 1 << PG_LEVEL_2M; #endif /* Enable PSE if available */ - if (cpu_has_pse) + if (boot_cpu_has(X86_FEATURE_PSE)) cr4_set_bits_and_update_boot(X86_CR4_PSE); /* Enable PGE if available */ - if (cpu_has_pge) { + if (boot_cpu_has(X86_FEATURE_PGE)) { cr4_set_bits_and_update_boot(X86_CR4_PGE); __supported_pte_mask |= _PAGE_GLOBAL; } else __supported_pte_mask &= ~_PAGE_GLOBAL; /* Enable 1 GB linear kernel mappings if available: */ - if (direct_gbpages && cpu_has_gbpages) { + if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) { printk(KERN_INFO "Using GB pages for direct mapping\n"); page_size_mask |= 1 << PG_LEVEL_1G; } else { diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index bd7a9b9..84df150 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -284,7 +284,7 @@ kernel_physical_mapping_init(unsigned long start, */ mapping_iter = 1; - if (!cpu_has_pse) + if (!boot_cpu_has(X86_FEATURE_PSE)) use_pse = 0; repeat: @@ -804,9 +804,6 @@ void __init mem_init(void) BUILD_BUG_ON(VMALLOC_START >= VMALLOC_END); #undef high_memory #undef __FIXADDR_TOP -#ifdef CONFIG_RANDOMIZE_BASE - BUILD_BUG_ON(CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE); -#endif #ifdef CONFIG_HIGHMEM BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE > FIXADDR_START); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 214afda..bce2e5d 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -58,79 +58,7 @@ #include "mm_internal.h" -static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page, - unsigned long addr, unsigned long end) -{ - addr &= PMD_MASK; - for (; addr < end; addr += PMD_SIZE) { - pmd_t *pmd = pmd_page + pmd_index(addr); - - if (!pmd_present(*pmd)) - set_pmd(pmd, __pmd(addr | pmd_flag)); - } -} -static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, - unsigned long addr, unsigned long end) -{ - unsigned long next; - - for (; addr < end; addr = next) { - pud_t *pud = pud_page + pud_index(addr); - pmd_t *pmd; - - next = (addr & PUD_MASK) + PUD_SIZE; - if (next > end) - next = end; - - if (pud_present(*pud)) { - pmd = pmd_offset(pud, 0); - ident_pmd_init(info->pmd_flag, pmd, addr, next); - continue; - } - pmd = (pmd_t *)info->alloc_pgt_page(info->context); - if (!pmd) - return -ENOMEM; - ident_pmd_init(info->pmd_flag, pmd, addr, next); - set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); - } - - return 0; -} - -int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, - unsigned long addr, unsigned long end) -{ - unsigned long next; - int result; - int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0; - - for (; addr < end; addr = next) { - pgd_t *pgd = pgd_page + pgd_index(addr) + off; - pud_t *pud; - - next = (addr & PGDIR_MASK) + PGDIR_SIZE; - if (next > end) - next = end; - - if (pgd_present(*pgd)) { - pud = pud_offset(pgd, 0); - result = ident_pud_init(info, pud, addr, next); - if (result) - return result; - continue; - } - - pud = (pud_t *)info->alloc_pgt_page(info->context); - if (!pud) - return -ENOMEM; - result = ident_pud_init(info, pud, addr, next); - if (result) - return result; - set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); - } - - return 0; -} +#include "ident_map.c" /* * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the @@ -1295,7 +1223,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) struct vmem_altmap *altmap = to_vmem_altmap(start); int err; - if (cpu_has_pse) + if (boot_cpu_has(X86_FEATURE_PSE)) err = vmemmap_populate_hugepages(start, end, node, altmap); else if (altmap) { pr_err_once("%s: no cpu support for altmap allocations\n", @@ -1338,7 +1266,7 @@ void register_page_bootmem_memmap(unsigned long section_nr, } get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO); - if (!cpu_has_pse) { + if (!boot_cpu_has(X86_FEATURE_PSE)) { next = (addr + PAGE_SIZE) & PAGE_MASK; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 0d8d53d..f089491 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -378,7 +378,7 @@ EXPORT_SYMBOL(iounmap); int __init arch_ioremap_pud_supported(void) { #ifdef CONFIG_X86_64 - return cpu_has_gbpages; + return boot_cpu_has(X86_FEATURE_GBPAGES); #else return 0; #endif @@ -386,7 +386,7 @@ int __init arch_ioremap_pud_supported(void) int __init arch_ioremap_pmd_supported(void) { - return cpu_has_pse; + return boot_cpu_has(X86_FEATURE_PSE); } /* diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 01be9ec..7a1f7bb 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -1055,7 +1055,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, /* * Map everything starting from the Gb boundary, possibly with 1G pages */ - while (cpu_has_gbpages && end - start >= PUD_SIZE) { + while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) { set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE | massage_pgprot(pud_pgprot))); @@ -1125,8 +1125,14 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr, int primary) { - if (cpa->pgd) + if (cpa->pgd) { + /* + * Right now, we only execute this code path when mapping + * the EFI virtual memory map regions, no other users + * provide a ->pgd value. This may change in the future. + */ return populate_pgd(cpa, vaddr); + } /* * Ignore all non primary paths. @@ -1460,7 +1466,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, * error case we fall back to cpa_flush_all (which uses * WBINVD): */ - if (!ret && cpu_has_clflush) { + if (!ret && boot_cpu_has(X86_FEATURE_CLFLUSH)) { if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { cpa_flush_array(addr, numpages, cache, cpa.flags, pages); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index faec01e..fb0604f 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -40,11 +40,22 @@ static bool boot_cpu_done; static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT); +static void init_cache_modes(void); -static inline void pat_disable(const char *reason) +void pat_disable(const char *reason) { + if (!__pat_enabled) + return; + + if (boot_cpu_done) { + WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n"); + return; + } + __pat_enabled = 0; pr_info("x86/PAT: %s\n", reason); + + init_cache_modes(); } static int __init nopat(char *str) @@ -181,7 +192,7 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) * configuration. * Using lower indices is preferred, so we start with highest index. */ -void pat_init_cache_modes(u64 pat) +static void __init_cache_modes(u64 pat) { enum page_cache_mode cache; char pat_msg[33]; @@ -202,14 +213,11 @@ static void pat_bsp_init(u64 pat) { u64 tmp_pat; - if (!cpu_has_pat) { + if (!boot_cpu_has(X86_FEATURE_PAT)) { pat_disable("PAT not supported by CPU."); return; } - if (!pat_enabled()) - goto done; - rdmsrl(MSR_IA32_CR_PAT, tmp_pat); if (!tmp_pat) { pat_disable("PAT MSR is 0, disabled."); @@ -218,16 +226,12 @@ static void pat_bsp_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); -done: - pat_init_cache_modes(pat); + __init_cache_modes(pat); } static void pat_ap_init(u64 pat) { - if (!pat_enabled()) - return; - - if (!cpu_has_pat) { + if (!boot_cpu_has(X86_FEATURE_PAT)) { /* * If this happens we are on a secondary CPU, but switched to * PAT on the boot CPU. We have no way to undo PAT. @@ -238,18 +242,32 @@ static void pat_ap_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); } -void pat_init(void) +static void init_cache_modes(void) { - u64 pat; - struct cpuinfo_x86 *c = &boot_cpu_data; + u64 pat = 0; + static int init_cm_done; - if (!pat_enabled()) { + if (init_cm_done) + return; + + if (boot_cpu_has(X86_FEATURE_PAT)) { + /* + * CPU supports PAT. Set PAT table to be consistent with + * PAT MSR. This case supports "nopat" boot option, and + * virtual machine environments which support PAT without + * MTRRs. In specific, Xen has unique setup to PAT MSR. + * + * If PAT MSR returns 0, it is considered invalid and emulates + * as No PAT. + */ + rdmsrl(MSR_IA32_CR_PAT, pat); + } + + if (!pat) { /* * No PAT. Emulate the PAT table that corresponds to the two - * cache bits, PWT (Write Through) and PCD (Cache Disable). This - * setup is the same as the BIOS default setup when the system - * has PAT but the "nopat" boot option has been specified. This - * emulated PAT table is used when MSR_IA32_CR_PAT returns 0. + * cache bits, PWT (Write Through) and PCD (Cache Disable). + * This setup is also the same as the BIOS default setup. * * PTE encoding: * @@ -266,10 +284,36 @@ void pat_init(void) */ pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); + } + + __init_cache_modes(pat); + + init_cm_done = 1; +} + +/** + * pat_init - Initialize PAT MSR and PAT table + * + * This function initializes PAT MSR and PAT table with an OS-defined value + * to enable additional cache attributes, WC and WT. + * + * This function must be called on all CPUs using the specific sequence of + * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this + * procedure for PAT. + */ +void pat_init(void) +{ + u64 pat; + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (!pat_enabled()) { + init_cache_modes(); + return; + } - } else if ((c->x86_vendor == X86_VENDOR_INTEL) && - (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || - ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { + if ((c->x86_vendor == X86_VENDOR_INTEL) && + (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || + ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { /* * PAT support with the lower four entries. Intel Pentium 2, * 3, M, and 4 are affected by PAT errata, which makes the @@ -734,25 +778,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, if (file->f_flags & O_DSYNC) pcm = _PAGE_CACHE_MODE_UC_MINUS; -#ifdef CONFIG_X86_32 - /* - * On the PPro and successors, the MTRRs are used to set - * memory types for physical addresses outside main memory, - * so blindly setting UC or PWT on those pages is wrong. - * For Pentiums and earlier, the surround logic should disable - * caching for the high addresses through the KEN pin, but - * we maintain the tradition of paranoia in this code. - */ - if (!pat_enabled() && - !(boot_cpu_has(X86_FEATURE_MTRR) || - boot_cpu_has(X86_FEATURE_K6_MTRR) || - boot_cpu_has(X86_FEATURE_CYRIX_ARR) || - boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) && - (pfn << PAGE_SHIFT) >= __pa(high_memory)) { - pcm = _PAGE_CACHE_MODE_UC; - } -#endif - *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | cachemode2protval(pcm)); return 1; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index fe9b9f7..5643fd0 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -28,6 +28,8 @@ * Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi */ +#ifdef CONFIG_SMP + struct flush_tlb_info { struct mm_struct *flush_mm; unsigned long flush_start; @@ -57,6 +59,118 @@ void leave_mm(int cpu) } EXPORT_SYMBOL_GPL(leave_mm); +#endif /* CONFIG_SMP */ + +void switch_mm(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk) +{ + unsigned long flags; + + local_irq_save(flags); + switch_mm_irqs_off(prev, next, tsk); + local_irq_restore(flags); +} + +void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk) +{ + unsigned cpu = smp_processor_id(); + + if (likely(prev != next)) { +#ifdef CONFIG_SMP + this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); + this_cpu_write(cpu_tlbstate.active_mm, next); +#endif + cpumask_set_cpu(cpu, mm_cpumask(next)); + + /* + * Re-load page tables. + * + * This logic has an ordering constraint: + * + * CPU 0: Write to a PTE for 'next' + * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. + * CPU 1: set bit 1 in next's mm_cpumask + * CPU 1: load from the PTE that CPU 0 writes (implicit) + * + * We need to prevent an outcome in which CPU 1 observes + * the new PTE value and CPU 0 observes bit 1 clear in + * mm_cpumask. (If that occurs, then the IPI will never + * be sent, and CPU 0's TLB will contain a stale entry.) + * + * The bad outcome can occur if either CPU's load is + * reordered before that CPU's store, so both CPUs must + * execute full barriers to prevent this from happening. + * + * Thus, switch_mm needs a full barrier between the + * store to mm_cpumask and any operation that could load + * from next->pgd. TLB fills are special and can happen + * due to instruction fetches or for no reason at all, + * and neither LOCK nor MFENCE orders them. + * Fortunately, load_cr3() is serializing and gives the + * ordering guarantee we need. + * + */ + load_cr3(next->pgd); + + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + + /* Stop flush ipis for the previous mm */ + cpumask_clear_cpu(cpu, mm_cpumask(prev)); + + /* Load per-mm CR4 state */ + load_mm_cr4(next); + +#ifdef CONFIG_MODIFY_LDT_SYSCALL + /* + * Load the LDT, if the LDT is different. + * + * It's possible that prev->context.ldt doesn't match + * the LDT register. This can happen if leave_mm(prev) + * was called and then modify_ldt changed + * prev->context.ldt but suppressed an IPI to this CPU. + * In this case, prev->context.ldt != NULL, because we + * never set context.ldt to NULL while the mm still + * exists. That means that next->context.ldt != + * prev->context.ldt, because mms never share an LDT. + */ + if (unlikely(prev->context.ldt != next->context.ldt)) + load_mm_ldt(next); +#endif + } +#ifdef CONFIG_SMP + else { + this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); + BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next); + + if (!cpumask_test_cpu(cpu, mm_cpumask(next))) { + /* + * On established mms, the mm_cpumask is only changed + * from irq context, from ptep_clear_flush() while in + * lazy tlb mode, and here. Irqs are blocked during + * schedule, protecting us from simultaneous changes. + */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + + /* + * We were in lazy tlb mode and leave_mm disabled + * tlb flush IPI delivery. We must reload CR3 + * to make sure to use no freed page tables. + * + * As above, load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask write. + */ + load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + load_mm_cr4(next); + load_mm_ldt(next); + } + } +#endif +} + +#ifdef CONFIG_SMP + /* * The flush IPI assumes that a thread switch happens in this order: * [cpu0: the cpu that switches] @@ -353,3 +467,5 @@ static int __init create_tlb_single_page_flush_ceiling(void) return 0; } late_initcall(create_tlb_single_page_flush_ceiling); + +#endif /* CONFIG_SMP */ diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 0e07e09..28c0412 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -636,7 +636,7 @@ static int __init ppro_init(char **cpu_type) __u8 cpu_model = boot_cpu_data.x86_model; struct op_x86_model_spec *spec = &op_ppro_spec; /* default */ - if (force_cpu_type == arch_perfmon && cpu_has_arch_perfmon) + if (force_cpu_type == arch_perfmon && boot_cpu_has(X86_FEATURE_ARCH_PERFMON)) return 0; /* @@ -700,7 +700,7 @@ int __init op_nmi_init(struct oprofile_operations *ops) char *cpu_type = NULL; int ret = 0; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; if (force_cpu_type == timer) @@ -761,7 +761,7 @@ int __init op_nmi_init(struct oprofile_operations *ops) if (cpu_type) break; - if (!cpu_has_arch_perfmon) + if (!boot_cpu_has(X86_FEATURE_ARCH_PERFMON)) return -ENODEV; /* use arch perfmon as fallback */ diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index d90528e..350f709 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -75,7 +75,7 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model, u64 val; int i; - if (cpu_has_arch_perfmon) { + if (boot_cpu_has(X86_FEATURE_ARCH_PERFMON)) { union cpuid10_eax eax; eax.full = cpuid_eax(0xa); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index beac4df..4bd08b0 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -445,7 +445,7 @@ void __init xen_msi_init(void) uint32_t eax = cpuid_eax(xen_cpuid_base() + 4); if (((eax & XEN_HVM_CPUID_X2APIC_VIRT) && x2apic_mode) || - ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && cpu_has_apic)) + ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && boot_cpu_has(X86_FEATURE_APIC))) return; } diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index a243381..6a2f569 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -43,40 +43,40 @@ void __init efi_bgrt_init(void) return; if (bgrt_tab->header.length < sizeof(*bgrt_tab)) { - pr_err("Ignoring BGRT: invalid length %u (expected %zu)\n", + pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n", bgrt_tab->header.length, sizeof(*bgrt_tab)); return; } if (bgrt_tab->version != 1) { - pr_err("Ignoring BGRT: invalid version %u (expected 1)\n", + pr_notice("Ignoring BGRT: invalid version %u (expected 1)\n", bgrt_tab->version); return; } if (bgrt_tab->status & 0xfe) { - pr_err("Ignoring BGRT: reserved status bits are non-zero %u\n", + pr_notice("Ignoring BGRT: reserved status bits are non-zero %u\n", bgrt_tab->status); return; } if (bgrt_tab->image_type != 0) { - pr_err("Ignoring BGRT: invalid image type %u (expected 0)\n", + pr_notice("Ignoring BGRT: invalid image type %u (expected 0)\n", bgrt_tab->image_type); return; } if (!bgrt_tab->image_address) { - pr_err("Ignoring BGRT: null image address\n"); + pr_notice("Ignoring BGRT: null image address\n"); return; } image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB); if (!image) { - pr_err("Ignoring BGRT: failed to map image header memory\n"); + pr_notice("Ignoring BGRT: failed to map image header memory\n"); return; } memcpy(&bmp_header, image, sizeof(bmp_header)); memunmap(image); if (bmp_header.id != 0x4d42) { - pr_err("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n", + pr_notice("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n", bmp_header.id); return; } @@ -84,14 +84,14 @@ void __init efi_bgrt_init(void) bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN); if (!bgrt_image) { - pr_err("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n", + pr_notice("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n", bgrt_image_size); return; } image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB); if (!image) { - pr_err("Ignoring BGRT: failed to map image memory\n"); + pr_notice("Ignoring BGRT: failed to map image memory\n"); kfree(bgrt_image); bgrt_image = NULL; return; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 994a7df8..f93545e 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -54,10 +54,6 @@ #include <asm/rtc.h> #include <asm/uv/uv.h> -#define EFI_DEBUG - -struct efi_memory_map memmap; - static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; @@ -119,11 +115,10 @@ void efi_get_time(struct timespec *now) void __init efi_find_mirror(void) { - void *p; + efi_memory_desc_t *md; u64 mirror_size = 0, total_size = 0; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - efi_memory_desc_t *md = p; + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; @@ -146,10 +141,9 @@ void __init efi_find_mirror(void) static void __init do_add_efi_memmap(void) { - void *p; + efi_memory_desc_t *md; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - efi_memory_desc_t *md = p; + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; int e820_type; @@ -209,47 +203,47 @@ int __init efi_memblock_x86_reserve_range(void) #else pmap = (e->efi_memmap | ((__u64)e->efi_memmap_hi << 32)); #endif - memmap.phys_map = pmap; - memmap.nr_map = e->efi_memmap_size / + efi.memmap.phys_map = pmap; + efi.memmap.nr_map = e->efi_memmap_size / e->efi_memdesc_size; - memmap.desc_size = e->efi_memdesc_size; - memmap.desc_version = e->efi_memdesc_version; + efi.memmap.desc_size = e->efi_memdesc_size; + efi.memmap.desc_version = e->efi_memdesc_version; - memblock_reserve(pmap, memmap.nr_map * memmap.desc_size); + WARN(efi.memmap.desc_version != 1, + "Unexpected EFI_MEMORY_DESCRIPTOR version %ld", + efi.memmap.desc_version); - efi.memmap = &memmap; + memblock_reserve(pmap, efi.memmap.nr_map * efi.memmap.desc_size); return 0; } void __init efi_print_memmap(void) { -#ifdef EFI_DEBUG efi_memory_desc_t *md; - void *p; - int i; + int i = 0; - for (p = memmap.map, i = 0; - p < memmap.map_end; - p += memmap.desc_size, i++) { + for_each_efi_memory_desc(md) { char buf[64]; - md = p; pr_info("mem%02u: %s range=[0x%016llx-0x%016llx] (%lluMB)\n", - i, efi_md_typeattr_format(buf, sizeof(buf), md), + i++, efi_md_typeattr_format(buf, sizeof(buf), md), md->phys_addr, md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1, (md->num_pages >> (20 - EFI_PAGE_SHIFT))); } -#endif /* EFI_DEBUG */ } void __init efi_unmap_memmap(void) { + unsigned long size; + clear_bit(EFI_MEMMAP, &efi.flags); - if (memmap.map) { - early_memunmap(memmap.map, memmap.nr_map * memmap.desc_size); - memmap.map = NULL; + + size = efi.memmap.nr_map * efi.memmap.desc_size; + if (efi.memmap.map) { + early_memunmap(efi.memmap.map, size); + efi.memmap.map = NULL; } } @@ -352,8 +346,6 @@ static int __init efi_systab_init(void *phys) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff); - set_bit(EFI_SYSTEM_TABLES, &efi.flags); - return 0; } @@ -440,17 +432,22 @@ static int __init efi_runtime_init(void) static int __init efi_memmap_init(void) { + unsigned long addr, size; + if (efi_enabled(EFI_PARAVIRT)) return 0; /* Map the EFI memory map */ - memmap.map = early_memremap((unsigned long)memmap.phys_map, - memmap.nr_map * memmap.desc_size); - if (memmap.map == NULL) { + size = efi.memmap.nr_map * efi.memmap.desc_size; + addr = (unsigned long)efi.memmap.phys_map; + + efi.memmap.map = early_memremap(addr, size); + if (efi.memmap.map == NULL) { pr_err("Could not map the memory map!\n"); return -ENOMEM; } - memmap.map_end = memmap.map + (memmap.nr_map * memmap.desc_size); + + efi.memmap.map_end = efi.memmap.map + size; if (add_efi_memmap) do_add_efi_memmap(); @@ -552,12 +549,9 @@ void __init efi_set_executable(efi_memory_desc_t *md, bool executable) void __init runtime_code_page_mkexec(void) { efi_memory_desc_t *md; - void *p; /* Make EFI runtime service code area executable */ - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; - + for_each_efi_memory_desc(md) { if (md->type != EFI_RUNTIME_SERVICES_CODE) continue; @@ -604,12 +598,10 @@ void __init old_map_region(efi_memory_desc_t *md) /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { - void *p; efi_memory_desc_t *md, *prev_md = NULL; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + for_each_efi_memory_desc(md) { u64 prev_size; - md = p; if (!prev_md) { prev_md = md; @@ -651,30 +643,31 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md) static void __init save_runtime_map(void) { #ifdef CONFIG_KEXEC_CORE + unsigned long desc_size; efi_memory_desc_t *md; - void *tmp, *p, *q = NULL; + void *tmp, *q = NULL; int count = 0; if (efi_enabled(EFI_OLD_MEMMAP)) return; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; + desc_size = efi.memmap.desc_size; + for_each_efi_memory_desc(md) { if (!(md->attribute & EFI_MEMORY_RUNTIME) || (md->type == EFI_BOOT_SERVICES_CODE) || (md->type == EFI_BOOT_SERVICES_DATA)) continue; - tmp = krealloc(q, (count + 1) * memmap.desc_size, GFP_KERNEL); + tmp = krealloc(q, (count + 1) * desc_size, GFP_KERNEL); if (!tmp) goto out; q = tmp; - memcpy(q + count * memmap.desc_size, md, memmap.desc_size); + memcpy(q + count * desc_size, md, desc_size); count++; } - efi_runtime_map_setup(q, count, memmap.desc_size); + efi_runtime_map_setup(q, count, desc_size); return; out: @@ -714,10 +707,10 @@ static inline void *efi_map_next_entry_reverse(void *entry) { /* Initial call */ if (!entry) - return memmap.map_end - memmap.desc_size; + return efi.memmap.map_end - efi.memmap.desc_size; - entry -= memmap.desc_size; - if (entry < memmap.map) + entry -= efi.memmap.desc_size; + if (entry < efi.memmap.map) return NULL; return entry; @@ -759,10 +752,10 @@ static void *efi_map_next_entry(void *entry) /* Initial call */ if (!entry) - return memmap.map; + return efi.memmap.map; - entry += memmap.desc_size; - if (entry >= memmap.map_end) + entry += efi.memmap.desc_size; + if (entry >= efi.memmap.map_end) return NULL; return entry; @@ -776,8 +769,11 @@ static void * __init efi_map_regions(int *count, int *pg_shift) { void *p, *new_memmap = NULL; unsigned long left = 0; + unsigned long desc_size; efi_memory_desc_t *md; + desc_size = efi.memmap.desc_size; + p = NULL; while ((p = efi_map_next_entry(p))) { md = p; @@ -792,7 +788,7 @@ static void * __init efi_map_regions(int *count, int *pg_shift) efi_map_region(md); get_systab_virt_addr(md); - if (left < memmap.desc_size) { + if (left < desc_size) { new_memmap = realloc_pages(new_memmap, *pg_shift); if (!new_memmap) return NULL; @@ -801,10 +797,9 @@ static void * __init efi_map_regions(int *count, int *pg_shift) (*pg_shift)++; } - memcpy(new_memmap + (*count * memmap.desc_size), md, - memmap.desc_size); + memcpy(new_memmap + (*count * desc_size), md, desc_size); - left -= memmap.desc_size; + left -= desc_size; (*count)++; } @@ -816,7 +811,6 @@ static void __init kexec_enter_virtual_mode(void) #ifdef CONFIG_KEXEC_CORE efi_memory_desc_t *md; unsigned int num_pages; - void *p; efi.systab = NULL; @@ -840,8 +834,7 @@ static void __init kexec_enter_virtual_mode(void) * Map efi regions which were passed via setup_data. The virt_addr is a * fixed addr which was used in first kernel of a kexec boot. */ - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; + for_each_efi_memory_desc(md) { efi_map_region_fixed(md); /* FIXME: add error handling */ get_systab_virt_addr(md); } @@ -850,10 +843,10 @@ static void __init kexec_enter_virtual_mode(void) BUG_ON(!efi.systab); - num_pages = ALIGN(memmap.nr_map * memmap.desc_size, PAGE_SIZE); + num_pages = ALIGN(efi.memmap.nr_map * efi.memmap.desc_size, PAGE_SIZE); num_pages >>= PAGE_SHIFT; - if (efi_setup_page_tables(memmap.phys_map, num_pages)) { + if (efi_setup_page_tables(efi.memmap.phys_map, num_pages)) { clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); return; } @@ -937,16 +930,16 @@ static void __init __efi_enter_virtual_mode(void) if (efi_is_native()) { status = phys_efi_set_virtual_address_map( - memmap.desc_size * count, - memmap.desc_size, - memmap.desc_version, + efi.memmap.desc_size * count, + efi.memmap.desc_size, + efi.memmap.desc_version, (efi_memory_desc_t *)__pa(new_memmap)); } else { status = efi_thunk_set_virtual_address_map( efi_phys.set_virtual_address_map, - memmap.desc_size * count, - memmap.desc_size, - memmap.desc_version, + efi.memmap.desc_size * count, + efi.memmap.desc_size, + efi.memmap.desc_version, (efi_memory_desc_t *)__pa(new_memmap)); } @@ -1011,13 +1004,11 @@ void __init efi_enter_virtual_mode(void) u32 efi_mem_type(unsigned long phys_addr) { efi_memory_desc_t *md; - void *p; if (!efi_enabled(EFI_MEMMAP)) return 0; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; + for_each_efi_memory_desc(md) { if ((md->phys_addr <= phys_addr) && (phys_addr < (md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT)))) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 49e4dd4..6e7242b 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -55,14 +55,12 @@ struct efi_scratch efi_scratch; static void __init early_code_mapping_set_exec(int executable) { efi_memory_desc_t *md; - void *p; if (!(__supported_pte_mask & _PAGE_NX)) return; /* Make EFI service code area executable */ - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; + for_each_efi_memory_desc(md) { if (md->type == EFI_RUNTIME_SERVICES_CODE || md->type == EFI_BOOT_SERVICES_CODE) efi_set_executable(md, executable); @@ -253,7 +251,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) * Map all of RAM so that we can access arguments in the 1:1 * mapping when making EFI runtime calls. */ - for_each_efi_memory_desc(&memmap, md) { + for_each_efi_memory_desc(md) { if (md->type != EFI_CONVENTIONAL_MEMORY && md->type != EFI_LOADER_DATA && md->type != EFI_LOADER_CODE) @@ -398,7 +396,6 @@ void __init efi_runtime_update_mappings(void) unsigned long pfn; pgd_t *pgd = efi_pgd; efi_memory_desc_t *md; - void *p; if (efi_enabled(EFI_OLD_MEMMAP)) { if (__supported_pte_mask & _PAGE_NX) @@ -409,9 +406,8 @@ void __init efi_runtime_update_mappings(void) if (!efi_enabled(EFI_NX_PE_DATA)) return; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + for_each_efi_memory_desc(md) { unsigned long pf = 0; - md = p; if (!(md->attribute & EFI_MEMORY_RUNTIME)) continue; diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index ab50ada..097cb09 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -195,10 +195,9 @@ static bool can_free_region(u64 start, u64 size) */ void __init efi_reserve_boot_services(void) { - void *p; + efi_memory_desc_t *md; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - efi_memory_desc_t *md = p; + for_each_efi_memory_desc(md) { u64 start = md->phys_addr; u64 size = md->num_pages << EFI_PAGE_SHIFT; bool already_reserved; @@ -250,10 +249,9 @@ void __init efi_reserve_boot_services(void) void __init efi_free_boot_services(void) { - void *p; + efi_memory_desc_t *md; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - efi_memory_desc_t *md = p; + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 291226b..9f14bd3 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -106,7 +106,7 @@ static int resume_physical_mapping_init(pgd_t *pgd_base) * normal page tables. * NOTE: We can mark everything as executable here */ - if (cpu_has_pse) { + if (boot_cpu_has(X86_FEATURE_PSE)) { set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE_EXEC)); pfn += PTRS_PER_PTE; } else { diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig index df280da..d957d5f 100644 --- a/arch/x86/ras/Kconfig +++ b/arch/x86/ras/Kconfig @@ -1,4 +1,4 @@ -config AMD_MCE_INJ +config MCE_AMD_INJ tristate "Simple MCE injection interface for AMD processors" depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB default n diff --git a/arch/x86/ras/Makefile b/arch/x86/ras/Makefile index dd2c98b..5f94546 100644 --- a/arch/x86/ras/Makefile +++ b/arch/x86/ras/Makefile @@ -1,2 +1,2 @@ -obj-$(CONFIG_AMD_MCE_INJ) += mce_amd_inj.o +obj-$(CONFIG_MCE_AMD_INJ) += mce_amd_inj.o diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c index 9e02dca..e69f470 100644 --- a/arch/x86/ras/mce_amd_inj.c +++ b/arch/x86/ras/mce_amd_inj.c @@ -290,14 +290,33 @@ static void do_inject(void) wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS, (u32)mcg_status, (u32)(mcg_status >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), - (u32)i_mce.status, (u32)(i_mce.status >> 32)); + if (boot_cpu_has(X86_FEATURE_SMCA)) { + if (inj_type == DFR_INT_INJ) { + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DESTAT(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DEADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + } else { + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_STATUS(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_ADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + } + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(b), + (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + } else { + wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), - (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), - (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), + (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + } toggle_hw_mce_inject(cpu, false); diff --git a/arch/x86/tools/calc_run_size.sh b/arch/x86/tools/calc_run_size.sh deleted file mode 100644 index 1a4c17b..0000000 --- a/arch/x86/tools/calc_run_size.sh +++ /dev/null @@ -1,42 +0,0 @@ -#!/bin/sh -# -# Calculate the amount of space needed to run the kernel, including room for -# the .bss and .brk sections. -# -# Usage: -# objdump -h a.out | sh calc_run_size.sh - -NUM='\([0-9a-fA-F]*[ \t]*\)' -OUT=$(sed -n 's/^[ \t0-9]*.b[sr][sk][ \t]*'"$NUM$NUM$NUM$NUM"'.*/\1\4/p') -if [ -z "$OUT" ] ; then - echo "Never found .bss or .brk file offset" >&2 - exit 1 -fi - -OUT=$(echo ${OUT# }) -sizeA=$(printf "%d" 0x${OUT%% *}) -OUT=${OUT#* } -offsetA=$(printf "%d" 0x${OUT%% *}) -OUT=${OUT#* } -sizeB=$(printf "%d" 0x${OUT%% *}) -OUT=${OUT#* } -offsetB=$(printf "%d" 0x${OUT%% *}) - -run_size=$(( $offsetA + $sizeA + $sizeB )) - -# BFD linker shows the same file offset in ELF. -if [ "$offsetA" -ne "$offsetB" ] ; then - # Gold linker shows them as consecutive. - endB=$(( $offsetB + $sizeB )) - if [ "$endB" != "$run_size" ] ; then - printf "sizeA: 0x%x\n" $sizeA >&2 - printf "offsetA: 0x%x\n" $offsetA >&2 - printf "sizeB: 0x%x\n" $sizeB >&2 - printf "offsetB: 0x%x\n" $offsetB >&2 - echo ".bss and .brk are non-contiguous" >&2 - exit 1 - fi -fi - -printf "%d\n" $run_size -exit 0 diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 880862c..760789a 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -75,7 +75,6 @@ #include <asm/mach_traps.h> #include <asm/mwait.h> #include <asm/pci_x86.h> -#include <asm/pat.h> #include <asm/cpu.h> #ifdef CONFIG_ACPI @@ -1093,6 +1092,26 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) return ret; } +static u64 xen_read_msr(unsigned int msr) +{ + /* + * This will silently swallow a #GP from RDMSR. It may be worth + * changing that. + */ + int err; + + return xen_read_msr_safe(msr, &err); +} + +static void xen_write_msr(unsigned int msr, unsigned low, unsigned high) +{ + /* + * This will silently swallow a #GP from WRMSR. It may be worth + * changing that. + */ + xen_write_msr_safe(msr, low, high); +} + void xen_setup_shared_info(void) { if (!xen_feature(XENFEAT_auto_translated_physmap)) { @@ -1187,13 +1206,11 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf, } static const struct pv_info xen_info __initconst = { - .paravirt_enabled = 1, .shared_kernel_pmd = 0, #ifdef CONFIG_X86_64 .extra_user_64bit_cs = FLAT_USER_CS64, #endif - .features = 0, .name = "Xen", }; @@ -1223,8 +1240,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .wbinvd = native_wbinvd, - .read_msr = xen_read_msr_safe, - .write_msr = xen_write_msr_safe, + .read_msr = xen_read_msr, + .write_msr = xen_write_msr, + + .read_msr_safe = xen_read_msr_safe, + .write_msr_safe = xen_write_msr_safe, .read_pmc = xen_read_pmc, @@ -1469,10 +1489,10 @@ static void xen_pvh_set_cr_flags(int cpu) * For BSP, PSE PGE are set in probe_page_size_mask(), for APs * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu(). */ - if (cpu_has_pse) + if (boot_cpu_has(X86_FEATURE_PSE)) cr4_set_bits_and_update_boot(X86_CR4_PSE); - if (cpu_has_pge) + if (boot_cpu_has(X86_FEATURE_PGE)) cr4_set_bits_and_update_boot(X86_CR4_PGE); } @@ -1506,12 +1526,16 @@ static void __init xen_pvh_early_guest_init(void) } #endif /* CONFIG_XEN_PVH */ +static void __init xen_dom0_set_legacy_features(void) +{ + x86_platform.legacy.rtc = 1; +} + /* First C function to be called on Xen boot */ asmlinkage __visible void __init xen_start_kernel(void) { struct physdev_set_iopl set_iopl; unsigned long initrd_start = 0; - u64 pat; int rc; if (!xen_start_info) @@ -1527,8 +1551,6 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; - if (xen_initial_domain()) - pv_info.features |= PV_SUPPORTED_RTC; pv_init_ops = xen_init_ops; if (!xen_pvh_domain()) { pv_cpu_ops = xen_cpu_ops; @@ -1618,13 +1640,6 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_start_info->nr_pages); xen_reserve_special_pages(); - /* - * Modify the cache mode translation tables to match Xen's PAT - * configuration. - */ - rdmsrl(MSR_IA32_CR_PAT, pat); - pat_init_cache_modes(pat); - /* keep using Xen gdt for now; no urgent need to change it */ #ifdef CONFIG_X86_32 @@ -1670,6 +1685,7 @@ asmlinkage __visible void __init xen_start_kernel(void) boot_params.hdr.ramdisk_image = initrd_start; boot_params.hdr.ramdisk_size = xen_start_info->mod_len; boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line); + boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN; if (!xen_initial_domain()) { add_preferred_console("xenboot", 0, NULL); @@ -1687,6 +1703,8 @@ asmlinkage __visible void __init xen_start_kernel(void) .u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS, }; + x86_platform.set_legacy_features = + xen_dom0_set_legacy_features; xen_init_vga(info, xen_start_info->console.dom0.info_size); xen_start_info->console.domU.mfn = 0; xen_start_info->console.domU.evtchn = 0; diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index b56855a..28cf4c5 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -22,6 +22,7 @@ generic-y += mm-arch-hooks.h generic-y += percpu.h generic-y += preempt.h generic-y += resource.h +generic-y += rwsem.h generic-y += sections.h generic-y += siginfo.h generic-y += statfs.h diff --git a/arch/xtensa/include/asm/rwsem.h b/arch/xtensa/include/asm/rwsem.h deleted file mode 100644 index 249619e..0000000 --- a/arch/xtensa/include/asm/rwsem.h +++ /dev/null @@ -1,131 +0,0 @@ -/* - * include/asm-xtensa/rwsem.h - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Largely copied from include/asm-ppc/rwsem.h - * - * Copyright (C) 2001 - 2005 Tensilica Inc. - */ - -#ifndef _XTENSA_RWSEM_H -#define _XTENSA_RWSEM_H - -#ifndef _LINUX_RWSEM_H -#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead." -#endif - -#define RWSEM_UNLOCKED_VALUE 0x00000000 -#define RWSEM_ACTIVE_BIAS 0x00000001 -#define RWSEM_ACTIVE_MASK 0x0000ffff -#define RWSEM_WAITING_BIAS (-0x00010000) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -/* - * lock for reading - */ -static inline void __down_read(struct rw_semaphore *sem) -{ - if (atomic_add_return(1,(atomic_t *)(&sem->count)) > 0) - smp_wmb(); - else - rwsem_down_read_failed(sem); -} - -static inline int __down_read_trylock(struct rw_semaphore *sem) -{ - int tmp; - - while ((tmp = sem->count) >= 0) { - if (tmp == cmpxchg(&sem->count, tmp, - tmp + RWSEM_ACTIVE_READ_BIAS)) { - smp_wmb(); - return 1; - } - } - return 0; -} - -/* - * lock for writing - */ -static inline void __down_write(struct rw_semaphore *sem) -{ - int tmp; - - tmp = atomic_add_return(RWSEM_ACTIVE_WRITE_BIAS, - (atomic_t *)(&sem->count)); - if (tmp == RWSEM_ACTIVE_WRITE_BIAS) - smp_wmb(); - else - rwsem_down_write_failed(sem); -} - -static inline int __down_write_trylock(struct rw_semaphore *sem) -{ - int tmp; - - tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, - RWSEM_ACTIVE_WRITE_BIAS); - smp_wmb(); - return tmp == RWSEM_UNLOCKED_VALUE; -} - -/* - * unlock after reading - */ -static inline void __up_read(struct rw_semaphore *sem) -{ - int tmp; - - smp_wmb(); - tmp = atomic_sub_return(1,(atomic_t *)(&sem->count)); - if (tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0) - rwsem_wake(sem); -} - -/* - * unlock after writing - */ -static inline void __up_write(struct rw_semaphore *sem) -{ - smp_wmb(); - if (atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS, - (atomic_t *)(&sem->count)) < 0) - rwsem_wake(sem); -} - -/* - * implement atomic add functionality - */ -static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem) -{ - atomic_add(delta, (atomic_t *)(&sem->count)); -} - -/* - * downgrade write lock to read lock - */ -static inline void __downgrade_write(struct rw_semaphore *sem) -{ - int tmp; - - smp_wmb(); - tmp = atomic_add_return(-RWSEM_WAITING_BIAS, (atomic_t *)(&sem->count)); - if (tmp < 0) - rwsem_downgrade_wake(sem); -} - -/* - * implement exchange and add functionality - */ -static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem) -{ - smp_mb(); - return atomic_add_return(delta, (atomic_t *)(&sem->count)); -} - -#endif /* _XTENSA_RWSEM_H */ diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c index 54f0118..a6b00b3 100644 --- a/arch/xtensa/kernel/perf_event.c +++ b/arch/xtensa/kernel/perf_event.c @@ -332,14 +332,14 @@ static int callchain_trace(struct stackframe *frame, void *data) void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) { - xtensa_backtrace_kernel(regs, PERF_MAX_STACK_DEPTH, + xtensa_backtrace_kernel(regs, sysctl_perf_event_max_stack, callchain_trace, NULL, entry); } void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { - xtensa_backtrace_user(regs, PERF_MAX_STACK_DEPTH, + xtensa_backtrace_user(regs, sysctl_perf_event_max_stack, callchain_trace, entry); } diff --git a/block/blk-map.c b/block/blk-map.c index a54f054..b9f88b7 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -9,24 +9,6 @@ #include "blk.h" -static bool iovec_gap_to_prv(struct request_queue *q, - struct iovec *prv, struct iovec *cur) -{ - unsigned long prev_end; - - if (!queue_virt_boundary(q)) - return false; - - if (prv->iov_base == NULL && prv->iov_len == 0) - /* prv is not set - don't check */ - return false; - - prev_end = (unsigned long)(prv->iov_base + prv->iov_len); - - return (((unsigned long)cur->iov_base & queue_virt_boundary(q)) || - prev_end & queue_virt_boundary(q)); -} - int blk_rq_append_bio(struct request_queue *q, struct request *rq, struct bio *bio) { @@ -125,31 +107,18 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, const struct iov_iter *iter, gfp_t gfp_mask) { - struct iovec iov, prv = {.iov_base = NULL, .iov_len = 0}; - bool copy = (q->dma_pad_mask & iter->count) || map_data; + bool copy = false; + unsigned long align = q->dma_pad_mask | queue_dma_alignment(q); struct bio *bio = NULL; struct iov_iter i; int ret; - if (!iter || !iter->count) - return -EINVAL; - - iov_for_each(iov, i, *iter) { - unsigned long uaddr = (unsigned long) iov.iov_base; - - if (!iov.iov_len) - return -EINVAL; - - /* - * Keep going so we check length of all segments - */ - if ((uaddr & queue_dma_alignment(q)) || - iovec_gap_to_prv(q, &prv, &iov)) - copy = true; - - prv.iov_base = iov.iov_base; - prv.iov_len = iov.iov_len; - } + if (map_data) + copy = true; + else if (iov_iter_alignment(iter) & align) + copy = true; + else if (queue_virt_boundary(q)) + copy = queue_virt_boundary(q) & iov_iter_gap_alignment(iter); i = *iter; do { diff --git a/crypto/Kconfig b/crypto/Kconfig index 93a1fdc..1d33beb 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -96,6 +96,7 @@ config CRYPTO_AKCIPHER config CRYPTO_RSA tristate "RSA algorithm" select CRYPTO_AKCIPHER + select CRYPTO_MANAGER select MPILIB select ASN1 help diff --git a/crypto/ahash.c b/crypto/ahash.c index 5fc1f17..3887a98 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -69,8 +69,9 @@ static int hash_walk_new_entry(struct crypto_hash_walk *walk) struct scatterlist *sg; sg = walk->sg; - walk->pg = sg_page(sg); walk->offset = sg->offset; + walk->pg = sg_page(walk->sg) + (walk->offset >> PAGE_SHIFT); + walk->offset = offset_in_page(walk->offset); walk->entrylen = sg->length; if (walk->entrylen > walk->total) diff --git a/crypto/testmgr.c b/crypto/testmgr.c index b86883a..7d4acc4 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -1776,6 +1776,7 @@ static int alg_test_drbg(const struct alg_test_desc *desc, const char *driver, static int do_test_rsa(struct crypto_akcipher *tfm, struct akcipher_testvec *vecs) { + char *xbuf[XBUFSIZE]; struct akcipher_request *req; void *outbuf_enc = NULL; void *outbuf_dec = NULL; @@ -1784,9 +1785,12 @@ static int do_test_rsa(struct crypto_akcipher *tfm, int err = -ENOMEM; struct scatterlist src, dst, src_tab[2]; + if (testmgr_alloc_buf(xbuf)) + return err; + req = akcipher_request_alloc(tfm, GFP_KERNEL); if (!req) - return err; + goto free_xbuf; init_completion(&result.completion); @@ -1804,9 +1808,14 @@ static int do_test_rsa(struct crypto_akcipher *tfm, if (!outbuf_enc) goto free_req; + if (WARN_ON(vecs->m_size > PAGE_SIZE)) + goto free_all; + + memcpy(xbuf[0], vecs->m, vecs->m_size); + sg_init_table(src_tab, 2); - sg_set_buf(&src_tab[0], vecs->m, 8); - sg_set_buf(&src_tab[1], vecs->m + 8, vecs->m_size - 8); + sg_set_buf(&src_tab[0], xbuf[0], 8); + sg_set_buf(&src_tab[1], xbuf[0] + 8, vecs->m_size - 8); sg_init_one(&dst, outbuf_enc, out_len_max); akcipher_request_set_crypt(req, src_tab, &dst, vecs->m_size, out_len_max); @@ -1825,7 +1834,7 @@ static int do_test_rsa(struct crypto_akcipher *tfm, goto free_all; } /* verify that encrypted message is equal to expected */ - if (memcmp(vecs->c, sg_virt(req->dst), vecs->c_size)) { + if (memcmp(vecs->c, outbuf_enc, vecs->c_size)) { pr_err("alg: rsa: encrypt test failed. Invalid output\n"); err = -EINVAL; goto free_all; @@ -1840,7 +1849,13 @@ static int do_test_rsa(struct crypto_akcipher *tfm, err = -ENOMEM; goto free_all; } - sg_init_one(&src, vecs->c, vecs->c_size); + + if (WARN_ON(vecs->c_size > PAGE_SIZE)) + goto free_all; + + memcpy(xbuf[0], vecs->c, vecs->c_size); + + sg_init_one(&src, xbuf[0], vecs->c_size); sg_init_one(&dst, outbuf_dec, out_len_max); init_completion(&result.completion); akcipher_request_set_crypt(req, &src, &dst, vecs->c_size, out_len_max); @@ -1867,6 +1882,8 @@ free_all: kfree(outbuf_enc); free_req: akcipher_request_free(req); +free_xbuf: + testmgr_free_buf(xbuf); return err; } diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c index 1982310..da198b8 100644 --- a/drivers/acpi/acpica/dsmethod.c +++ b/drivers/acpi/acpica/dsmethod.c @@ -428,6 +428,9 @@ acpi_ds_begin_method_execution(struct acpi_namespace_node *method_node, obj_desc->method.mutex->mutex. original_sync_level = obj_desc->method.mutex->mutex.sync_level; + + obj_desc->method.mutex->mutex.thread_id = + acpi_os_get_thread_id(); } } diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index d0f35e6..63cc9db 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -287,8 +287,11 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, offset); rc = -ENXIO; } - } else + } else { rc = 0; + if (cmd_rc) + *cmd_rc = xlat_status(buf, cmd); + } out: ACPI_FREE(out_obj); diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index 5083f85..cfa936a 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -202,6 +202,14 @@ config SATA_FSL If unsure, say N. +config SATA_AHCI_SEATTLE + tristate "AMD Seattle 6.0Gbps AHCI SATA host controller support" + depends on ARCH_SEATTLE + help + This option enables support for AMD Seattle SATA host controller. + + If unsure, say N + config SATA_INIC162X tristate "Initio 162x SATA support (Very Experimental)" depends on PCI diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile index 1857952..0b2afb7 100644 --- a/drivers/ata/Makefile +++ b/drivers/ata/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_ATA) += libata.o # non-SFF interface obj-$(CONFIG_SATA_AHCI) += ahci.o libahci.o obj-$(CONFIG_SATA_ACARD_AHCI) += acard-ahci.o libahci.o +obj-$(CONFIG_SATA_AHCI_SEATTLE) += ahci_seattle.o libahci.o libahci_platform.o obj-$(CONFIG_SATA_AHCI_PLATFORM) += ahci_platform.o libahci.o libahci_platform.o obj-$(CONFIG_SATA_FSL) += sata_fsl.o obj-$(CONFIG_SATA_INIC162X) += sata_inic162x.o diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c index 4044233..62a04c8 100644 --- a/drivers/ata/ahci_platform.c +++ b/drivers/ata/ahci_platform.c @@ -51,6 +51,9 @@ static int ahci_probe(struct platform_device *pdev) if (rc) return rc; + of_property_read_u32(dev->of_node, + "ports-implemented", &hpriv->force_port_map); + if (of_device_is_compatible(dev->of_node, "hisilicon,hisi-ahci")) hpriv->flags |= AHCI_HFLAG_NO_FBS | AHCI_HFLAG_NO_NCQ; diff --git a/drivers/ata/ahci_seattle.c b/drivers/ata/ahci_seattle.c new file mode 100644 index 0000000..6e702ab --- /dev/null +++ b/drivers/ata/ahci_seattle.c @@ -0,0 +1,210 @@ +/* + * AMD Seattle AHCI SATA driver + * + * Copyright (c) 2015, Advanced Micro Devices + * Author: Brijesh Singh <brijesh.singh@amd.com> + * + * based on the AHCI SATA platform driver by Jeff Garzik and Anton Vorontsov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pm.h> +#include <linux/device.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/libata.h> +#include <linux/ahci_platform.h> +#include <linux/acpi.h> +#include <linux/pci_ids.h> +#include "ahci.h" + +/* SGPIO Control Register definition + * + * Bit Type Description + * 31 RW OD7.2 (activity) + * 30 RW OD7.1 (locate) + * 29 RW OD7.0 (fault) + * 28...8 RW OD6.2...OD0.0 (3bits per port, 1 bit per LED) + * 7 RO SGPIO feature flag + * 6:4 RO Reserved + * 3:0 RO Number of ports (0 means no port supported) + */ +#define ACTIVITY_BIT_POS(x) (8 + (3 * x)) +#define LOCATE_BIT_POS(x) (ACTIVITY_BIT_POS(x) + 1) +#define FAULT_BIT_POS(x) (LOCATE_BIT_POS(x) + 1) + +#define ACTIVITY_MASK 0x00010000 +#define LOCATE_MASK 0x00080000 +#define FAULT_MASK 0x00400000 + +#define DRV_NAME "ahci-seattle" + +static ssize_t seattle_transmit_led_message(struct ata_port *ap, u32 state, + ssize_t size); + +struct seattle_plat_data { + void __iomem *sgpio_ctrl; +}; + +static struct ata_port_operations ahci_port_ops = { + .inherits = &ahci_ops, +}; + +static const struct ata_port_info ahci_port_info = { + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_port_ops, +}; + +static struct ata_port_operations ahci_seattle_ops = { + .inherits = &ahci_ops, + .transmit_led_message = seattle_transmit_led_message, +}; + +static const struct ata_port_info ahci_port_seattle_info = { + .flags = AHCI_FLAG_COMMON | ATA_FLAG_EM | ATA_FLAG_SW_ACTIVITY, + .link_flags = ATA_LFLAG_SW_ACTIVITY, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_seattle_ops, +}; + +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + +static ssize_t seattle_transmit_led_message(struct ata_port *ap, u32 state, + ssize_t size) +{ + struct ahci_host_priv *hpriv = ap->host->private_data; + struct ahci_port_priv *pp = ap->private_data; + struct seattle_plat_data *plat_data = hpriv->plat_data; + unsigned long flags; + int pmp; + struct ahci_em_priv *emp; + u32 val; + + /* get the slot number from the message */ + pmp = (state & EM_MSG_LED_PMP_SLOT) >> 8; + if (pmp >= EM_MAX_SLOTS) + return -EINVAL; + emp = &pp->em_priv[pmp]; + + val = ioread32(plat_data->sgpio_ctrl); + if (state & ACTIVITY_MASK) + val |= 1 << ACTIVITY_BIT_POS((ap->port_no)); + else + val &= ~(1 << ACTIVITY_BIT_POS((ap->port_no))); + + if (state & LOCATE_MASK) + val |= 1 << LOCATE_BIT_POS((ap->port_no)); + else + val &= ~(1 << LOCATE_BIT_POS((ap->port_no))); + + if (state & FAULT_MASK) + val |= 1 << FAULT_BIT_POS((ap->port_no)); + else + val &= ~(1 << FAULT_BIT_POS((ap->port_no))); + + iowrite32(val, plat_data->sgpio_ctrl); + + spin_lock_irqsave(ap->lock, flags); + + /* save off new led state for port/slot */ + emp->led_state = state; + + spin_unlock_irqrestore(ap->lock, flags); + + return size; +} + +static const struct ata_port_info *ahci_seattle_get_port_info( + struct platform_device *pdev, struct ahci_host_priv *hpriv) +{ + struct device *dev = &pdev->dev; + struct seattle_plat_data *plat_data; + u32 val; + + plat_data = devm_kzalloc(dev, sizeof(*plat_data), GFP_KERNEL); + if (IS_ERR(plat_data)) + return &ahci_port_info; + + plat_data->sgpio_ctrl = devm_ioremap_resource(dev, + platform_get_resource(pdev, IORESOURCE_MEM, 1)); + if (IS_ERR(plat_data->sgpio_ctrl)) + return &ahci_port_info; + + val = ioread32(plat_data->sgpio_ctrl); + + if (!(val & 0xf)) + return &ahci_port_info; + + hpriv->em_loc = 0; + hpriv->em_buf_sz = 4; + hpriv->em_msg_type = EM_MSG_TYPE_LED; + hpriv->plat_data = plat_data; + + dev_info(dev, "SGPIO LED control is enabled.\n"); + return &ahci_port_seattle_info; +} + +static int ahci_seattle_probe(struct platform_device *pdev) +{ + int rc; + struct ahci_host_priv *hpriv; + + hpriv = ahci_platform_get_resources(pdev); + if (IS_ERR(hpriv)) + return PTR_ERR(hpriv); + + rc = ahci_platform_enable_resources(hpriv); + if (rc) + return rc; + + rc = ahci_platform_init_host(pdev, hpriv, + ahci_seattle_get_port_info(pdev, hpriv), + &ahci_platform_sht); + if (rc) + goto disable_resources; + + return 0; +disable_resources: + ahci_platform_disable_resources(hpriv); + return rc; +} + +static SIMPLE_DEV_PM_OPS(ahci_pm_ops, ahci_platform_suspend, + ahci_platform_resume); + +static const struct acpi_device_id ahci_acpi_match[] = { + { "AMDI0600", 0 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, ahci_acpi_match); + +static struct platform_driver ahci_seattle_driver = { + .probe = ahci_seattle_probe, + .remove = ata_platform_remove_one, + .driver = { + .name = DRV_NAME, + .acpi_match_table = ahci_acpi_match, + .pm = &ahci_pm_ops, + }, +}; +module_platform_driver(ahci_seattle_driver); + +MODULE_DESCRIPTION("Seattle AHCI SATA platform driver"); +MODULE_AUTHOR("Brijesh Singh <brijesh.singh@amd.com>"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 3982054..a5d7c1c 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -507,6 +507,7 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) dev_info(dev, "forcing port_map 0x%x -> 0x%x\n", port_map, hpriv->force_port_map); port_map = hpriv->force_port_map; + hpriv->saved_port_map = port_map; } if (hpriv->mask_port_map) { diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index 433b600..d8f4cc2 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -259,9 +259,6 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) reg = opp_table->regulator; if (IS_ERR(reg)) { /* Regulator may not be required for device */ - if (reg) - dev_err(dev, "%s: Invalid regulator (%ld)\n", __func__, - PTR_ERR(reg)); rcu_read_unlock(); return 0; } diff --git a/drivers/base/property.c b/drivers/base/property.c index 9b1a65d..7f692ac 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -21,7 +21,7 @@ static inline bool is_pset_node(struct fwnode_handle *fwnode) { - return fwnode && fwnode->type == FWNODE_PDATA; + return !IS_ERR_OR_NULL(fwnode) && fwnode->type == FWNODE_PDATA; } static inline struct property_set *to_pset_node(struct fwnode_handle *fwnode) diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 5c79526..a038033 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -13,6 +13,7 @@ #ifndef _REGMAP_INTERNAL_H #define _REGMAP_INTERNAL_H +#include <linux/device.h> #include <linux/regmap.h> #include <linux/fs.h> #include <linux/list.h> diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c index 7526906..5189fd6 100644 --- a/drivers/base/regmap/regmap-mmio.c +++ b/drivers/base/regmap/regmap-mmio.c @@ -23,6 +23,8 @@ #include <linux/regmap.h> #include <linux/slab.h> +#include "internal.h" + struct regmap_mmio_context { void __iomem *regs; unsigned val_bytes; @@ -212,6 +214,7 @@ static const struct regmap_bus regmap_mmio = { .reg_write = regmap_mmio_write, .reg_read = regmap_mmio_read, .free_context = regmap_mmio_free_context, + .val_format_endian_default = REGMAP_ENDIAN_LITTLE, }; static struct regmap_mmio_context *regmap_mmio_gen_context(struct device *dev, @@ -245,7 +248,7 @@ static struct regmap_mmio_context *regmap_mmio_gen_context(struct device *dev, ctx->val_bytes = config->val_bits / 8; ctx->clk = ERR_PTR(-ENODEV); - switch (config->reg_format_endian) { + switch (regmap_get_val_endian(dev, ®map_mmio, config)) { case REGMAP_ENDIAN_DEFAULT: case REGMAP_ENDIAN_LITTLE: #ifdef __LITTLE_ENDIAN diff --git a/drivers/base/regmap/regmap-spmi.c b/drivers/base/regmap/regmap-spmi.c index 7e58f65..4a36e41 100644 --- a/drivers/base/regmap/regmap-spmi.c +++ b/drivers/base/regmap/regmap-spmi.c @@ -142,7 +142,7 @@ static int regmap_spmi_ext_read(void *context, while (val_size) { len = min_t(size_t, val_size, 8); - err = spmi_ext_register_readl(context, addr, val, val_size); + err = spmi_ext_register_readl(context, addr, val, len); if (err) goto err_out; diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c index 02e1818..2beb396f 100644 --- a/drivers/clk/imx/clk-imx6q.c +++ b/drivers/clk/imx/clk-imx6q.c @@ -394,7 +394,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) clk[IMX6QDL_CLK_LDB_DI1_DIV_3_5] = imx_clk_fixed_factor("ldb_di1_div_3_5", "ldb_di1", 2, 7); } else { clk[IMX6QDL_CLK_ECSPI_ROOT] = imx_clk_divider("ecspi_root", "pll3_60m", base + 0x38, 19, 6); - clk[IMX6QDL_CLK_CAN_ROOT] = imx_clk_divider("can_root", "pll3_60", base + 0x20, 2, 6); + clk[IMX6QDL_CLK_CAN_ROOT] = imx_clk_divider("can_root", "pll3_60m", base + 0x20, 2, 6); clk[IMX6QDL_CLK_IPG_PER] = imx_clk_fixup_divider("ipg_per", "ipg", base + 0x1c, 0, 6, imx_cscmr1_fixup); clk[IMX6QDL_CLK_UART_SERIAL_PODF] = imx_clk_divider("uart_serial_podf", "pll3_80m", base + 0x24, 0, 6); clk[IMX6QDL_CLK_LDB_DI0_DIV_3_5] = imx_clk_fixed_factor("ldb_di0_div_3_5", "ldb_di0_sel", 2, 7); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e93405f..c4acfc5 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1557,21 +1557,25 @@ void cpufreq_suspend(void) if (!cpufreq_driver) return; - if (!has_target()) + if (!has_target() && !cpufreq_driver->suspend) goto suspend; pr_debug("%s: Suspending Governors\n", __func__); for_each_active_policy(policy) { - down_write(&policy->rwsem); - ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP); - up_write(&policy->rwsem); + if (has_target()) { + down_write(&policy->rwsem); + ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP); + up_write(&policy->rwsem); - if (ret) - pr_err("%s: Failed to stop governor for policy: %p\n", - __func__, policy); - else if (cpufreq_driver->suspend - && cpufreq_driver->suspend(policy)) + if (ret) { + pr_err("%s: Failed to stop governor for policy: %p\n", + __func__, policy); + continue; + } + } + + if (cpufreq_driver->suspend && cpufreq_driver->suspend(policy)) pr_err("%s: Failed to suspend driver: %p\n", __func__, policy); } @@ -1596,7 +1600,7 @@ void cpufreq_resume(void) cpufreq_suspended = false; - if (!has_target()) + if (!has_target() && !cpufreq_driver->resume) return; pr_debug("%s: Resuming Governors\n", __func__); @@ -1605,7 +1609,7 @@ void cpufreq_resume(void) if (cpufreq_driver->resume && cpufreq_driver->resume(policy)) { pr_err("%s: Failed to resume driver: %p\n", __func__, policy); - } else { + } else if (has_target()) { down_write(&policy->rwsem); ret = cpufreq_start_governor(policy); up_write(&policy->rwsem); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index f502d5b..b230eba 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -453,6 +453,14 @@ static void intel_pstate_hwp_set(const struct cpumask *cpumask) } } +static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy) +{ + if (hwp_active) + intel_pstate_hwp_set(policy->cpus); + + return 0; +} + static void intel_pstate_hwp_set_online_cpus(void) { get_online_cpus(); @@ -1062,8 +1070,9 @@ static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time) static inline int32_t get_avg_frequency(struct cpudata *cpu) { - return div64_u64(cpu->pstate.max_pstate_physical * cpu->sample.aperf * - cpu->pstate.scaling, cpu->sample.mperf); + return fp_toint(mul_fp(cpu->sample.core_pct_busy, + int_tofp(cpu->pstate.max_pstate_physical * + cpu->pstate.scaling / 100))); } static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu) @@ -1106,8 +1115,6 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) int32_t core_busy, max_pstate, current_pstate, sample_ratio; u64 duration_ns; - intel_pstate_calc_busy(cpu); - /* * core_busy is the ratio of actual performance to max * max_pstate is the max non turbo pstate available @@ -1191,8 +1198,11 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time, if ((s64)delta_ns >= pid_params.sample_rate_ns) { bool sample_taken = intel_pstate_sample(cpu, time); - if (sample_taken && !hwp_active) - intel_pstate_adjust_busy_pstate(cpu); + if (sample_taken) { + intel_pstate_calc_busy(cpu); + if (!hwp_active) + intel_pstate_adjust_busy_pstate(cpu); + } } } @@ -1346,8 +1356,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) out: intel_pstate_set_update_util_hook(policy->cpu); - if (hwp_active) - intel_pstate_hwp_set(policy->cpus); + intel_pstate_hwp_set_policy(policy); return 0; } @@ -1411,6 +1420,7 @@ static struct cpufreq_driver intel_pstate_driver = { .flags = CPUFREQ_CONST_LOOPS, .verify = intel_pstate_verify_policy, .setpolicy = intel_pstate_set_policy, + .resume = intel_pstate_hwp_set_policy, .get = intel_pstate_get, .init = intel_pstate_cpu_init, .stop_cpu = intel_pstate_stop_cpu, diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index 0f6b229..247bfa8 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -945,7 +945,7 @@ static int __init longhaul_init(void) } #endif #ifdef CONFIG_X86_IO_APIC - if (cpu_has_apic) { + if (boot_cpu_has(X86_FEATURE_APIC)) { printk(KERN_ERR PFX "APIC detected. Longhaul is currently " "broken in this configuration.\n"); return -ENODEV; diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c index a9c659f..0404203 100644 --- a/drivers/cpufreq/sti-cpufreq.c +++ b/drivers/cpufreq/sti-cpufreq.c @@ -259,6 +259,10 @@ static int sti_cpufreq_init(void) { int ret; + if ((!of_machine_is_compatible("st,stih407")) && + (!of_machine_is_compatible("st,stih410"))) + return -ENODEV; + ddata.cpu = get_cpu_device(0); if (!ddata.cpu) { dev_err(ddata.cpu, "Failed to get device for CPU0\n"); diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c index 545069d..e342565e 100644 --- a/drivers/cpuidle/cpuidle-arm.c +++ b/drivers/cpuidle/cpuidle-arm.c @@ -50,7 +50,7 @@ static int arm_enter_idle_state(struct cpuidle_device *dev, * call the CPU ops suspend protocol with idle index as a * parameter. */ - arm_cpuidle_suspend(idx); + ret = arm_cpuidle_suspend(idx); cpu_pm_exit(); } diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h index 0e82ce3..976b01e 100644 --- a/drivers/crypto/qat/qat_common/adf_common_drv.h +++ b/drivers/crypto/qat/qat_common/adf_common_drv.h @@ -236,6 +236,8 @@ void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, uint32_t vf_mask); void adf_enable_pf2vf_interrupts(struct adf_accel_dev *accel_dev); void adf_disable_pf2vf_interrupts(struct adf_accel_dev *accel_dev); +int adf_init_pf_wq(void); +void adf_exit_pf_wq(void); #else static inline int adf_sriov_configure(struct pci_dev *pdev, int numvfs) { @@ -253,5 +255,14 @@ static inline void adf_enable_pf2vf_interrupts(struct adf_accel_dev *accel_dev) static inline void adf_disable_pf2vf_interrupts(struct adf_accel_dev *accel_dev) { } + +static inline int adf_init_pf_wq(void) +{ + return 0; +} + +static inline void adf_exit_pf_wq(void) +{ +} #endif #endif diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c index 5c897e6..3c3f948 100644 --- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c +++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c @@ -462,12 +462,17 @@ static int __init adf_register_ctl_device_driver(void) if (adf_init_aer()) goto err_aer; + if (adf_init_pf_wq()) + goto err_pf_wq; + if (qat_crypto_register()) goto err_crypto_register; return 0; err_crypto_register: + adf_exit_pf_wq(); +err_pf_wq: adf_exit_aer(); err_aer: adf_chr_drv_destroy(); @@ -480,6 +485,7 @@ static void __exit adf_unregister_ctl_device_driver(void) { adf_chr_drv_destroy(); adf_exit_aer(); + adf_exit_pf_wq(); qat_crypto_unregister(); adf_clean_vf_map(false); mutex_destroy(&adf_ctl_lock); diff --git a/drivers/crypto/qat/qat_common/adf_sriov.c b/drivers/crypto/qat/qat_common/adf_sriov.c index 1117a8b..38a0415 100644 --- a/drivers/crypto/qat/qat_common/adf_sriov.c +++ b/drivers/crypto/qat/qat_common/adf_sriov.c @@ -119,11 +119,6 @@ static int adf_enable_sriov(struct adf_accel_dev *accel_dev) int i; u32 reg; - /* Workqueue for PF2VF responses */ - pf2vf_resp_wq = create_workqueue("qat_pf2vf_resp_wq"); - if (!pf2vf_resp_wq) - return -ENOMEM; - for (i = 0, vf_info = accel_dev->pf.vf_info; i < totalvfs; i++, vf_info++) { /* This ptr will be populated when VFs will be created */ @@ -216,11 +211,6 @@ void adf_disable_sriov(struct adf_accel_dev *accel_dev) kfree(accel_dev->pf.vf_info); accel_dev->pf.vf_info = NULL; - - if (pf2vf_resp_wq) { - destroy_workqueue(pf2vf_resp_wq); - pf2vf_resp_wq = NULL; - } } EXPORT_SYMBOL_GPL(adf_disable_sriov); @@ -304,3 +294,19 @@ int adf_sriov_configure(struct pci_dev *pdev, int numvfs) return numvfs; } EXPORT_SYMBOL_GPL(adf_sriov_configure); + +int __init adf_init_pf_wq(void) +{ + /* Workqueue for PF2VF responses */ + pf2vf_resp_wq = create_workqueue("qat_pf2vf_resp_wq"); + + return !pf2vf_resp_wq ? -ENOMEM : 0; +} + +void adf_exit_pf_wq(void) +{ + if (pf2vf_resp_wq) { + destroy_workqueue(pf2vf_resp_wq); + pf2vf_resp_wq = NULL; + } +} diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index 49768c0..9b6800a 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -1052,7 +1052,6 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) struct mce *m = (struct mce *)data; struct cpuinfo_x86 *c = &cpu_data(m->extcpu); int ecc; - u32 ebx = cpuid_ebx(0x80000007); if (amd_filter_mce(m)) return NOTIFY_STOP; @@ -1075,7 +1074,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) ((m->status & MCI_STATUS_DEFERRED) ? "Deferred" : "-"), ((m->status & MCI_STATUS_POISON) ? "Poison" : "-")); - if (!!(ebx & BIT(3))) { + if (boot_cpu_has(X86_FEATURE_SMCA)) { u32 low, high; u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank); @@ -1094,7 +1093,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) if (m->status & MCI_STATUS_ADDRV) pr_emerg(HW_ERR "MC%d Error Address: 0x%016llx\n", m->bank, m->addr); - if (!!(ebx & BIT(3))) { + if (boot_cpu_has(X86_FEATURE_SMCA)) { decode_smca_errors(m); goto err_code; } @@ -1149,7 +1148,6 @@ static struct notifier_block amd_mce_dec_nb = { static int __init mce_amd_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; - u32 ebx; if (c->x86_vendor != X86_VENDOR_AMD) return -ENODEV; @@ -1205,9 +1203,8 @@ static int __init mce_amd_init(void) break; case 0x17: - ebx = cpuid_ebx(0x80000007); xec_mask = 0x3f; - if (!(ebx & BIT(3))) { + if (!boot_cpu_has(X86_FEATURE_SMCA)) { printk(KERN_WARNING "Decoding supported only on Scalable MCA processors.\n"); goto err_out; } diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index e1670d5..6394152 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -87,6 +87,31 @@ config EFI_RUNTIME_WRAPPERS config EFI_ARMSTUB bool +config EFI_BOOTLOADER_CONTROL + tristate "EFI Bootloader Control" + depends on EFI_VARS + default n + ---help--- + This module installs a reboot hook, such that if reboot() is + invoked with a string argument NNN, "NNN" is copied to the + "LoaderEntryOneShot" EFI variable, to be read by the + bootloader. If the string matches one of the boot labels + defined in its configuration, the bootloader will boot once + to that label. The "LoaderEntryRebootReason" EFI variable is + set with the reboot reason: "reboot" or "shutdown". The + bootloader reads this reboot reason and takes particular + action according to its policy. + +config EFI_CAPSULE_LOADER + tristate "EFI capsule loader" + depends on EFI + help + This option exposes a loader interface "/dev/efi_capsule_loader" for + users to load EFI capsules. This driver requires working runtime + capsule support in the firmware, which many OEMs do not provide. + + Most users should say N. + endmenu config UEFI_CPER diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile index 62e654f..a219640 100644 --- a/drivers/firmware/efi/Makefile +++ b/drivers/firmware/efi/Makefile @@ -9,7 +9,8 @@ # KASAN_SANITIZE_runtime-wrappers.o := n -obj-$(CONFIG_EFI) += efi.o vars.o reboot.o +obj-$(CONFIG_EFI) += efi.o vars.o reboot.o memattr.o +obj-$(CONFIG_EFI) += capsule.o obj-$(CONFIG_EFI_VARS) += efivars.o obj-$(CONFIG_EFI_ESRT) += esrt.o obj-$(CONFIG_EFI_VARS_PSTORE) += efi-pstore.o @@ -18,7 +19,9 @@ obj-$(CONFIG_EFI_RUNTIME_MAP) += runtime-map.o obj-$(CONFIG_EFI_RUNTIME_WRAPPERS) += runtime-wrappers.o obj-$(CONFIG_EFI_STUB) += libstub/ obj-$(CONFIG_EFI_FAKE_MEMMAP) += fake_mem.o +obj-$(CONFIG_EFI_BOOTLOADER_CONTROL) += efibc.o arm-obj-$(CONFIG_EFI) := arm-init.o arm-runtime.o obj-$(CONFIG_ARM) += $(arm-obj-y) obj-$(CONFIG_ARM64) += $(arm-obj-y) +obj-$(CONFIG_EFI_CAPSULE_LOADER) += capsule-loader.o diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c index 8714f8c..ef90f0c 100644 --- a/drivers/firmware/efi/arm-init.c +++ b/drivers/firmware/efi/arm-init.c @@ -11,17 +11,19 @@ * */ +#define pr_fmt(fmt) "efi: " fmt + #include <linux/efi.h> #include <linux/init.h> #include <linux/memblock.h> #include <linux/mm_types.h> #include <linux/of.h> #include <linux/of_fdt.h> +#include <linux/platform_device.h> +#include <linux/screen_info.h> #include <asm/efi.h> -struct efi_memory_map memmap; - u64 efi_system_table; static int __init is_normal_ram(efi_memory_desc_t *md) @@ -40,7 +42,7 @@ static phys_addr_t efi_to_phys(unsigned long addr) { efi_memory_desc_t *md; - for_each_efi_memory_desc(&memmap, md) { + for_each_efi_memory_desc(md) { if (!(md->attribute & EFI_MEMORY_RUNTIME)) continue; if (md->virt_addr == 0) @@ -53,6 +55,36 @@ static phys_addr_t efi_to_phys(unsigned long addr) return addr; } +static __initdata unsigned long screen_info_table = EFI_INVALID_TABLE_ADDR; + +static __initdata efi_config_table_type_t arch_tables[] = { + {LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID, NULL, &screen_info_table}, + {NULL_GUID, NULL, NULL} +}; + +static void __init init_screen_info(void) +{ + struct screen_info *si; + + if (screen_info_table != EFI_INVALID_TABLE_ADDR) { + si = early_memremap_ro(screen_info_table, sizeof(*si)); + if (!si) { + pr_err("Could not map screen_info config table\n"); + return; + } + screen_info = *si; + early_memunmap(si, sizeof(*si)); + + /* dummycon on ARM needs non-zero values for columns/lines */ + screen_info.orig_video_cols = 80; + screen_info.orig_video_lines = 25; + } + + if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && + memblock_is_map_memory(screen_info.lfb_base)) + memblock_mark_nomap(screen_info.lfb_base, screen_info.lfb_size); +} + static int __init uefi_init(void) { efi_char16_t *c16; @@ -85,6 +117,8 @@ static int __init uefi_init(void) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff); + efi.runtime_version = efi.systab->hdr.revision; + /* Show what we know for posterity */ c16 = early_memremap_ro(efi_to_phys(efi.systab->fw_vendor), sizeof(vendor) * sizeof(efi_char16_t)); @@ -108,7 +142,8 @@ static int __init uefi_init(void) goto out; } retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables, - sizeof(efi_config_table_t), NULL); + sizeof(efi_config_table_t), + arch_tables); early_memunmap(config_tables, table_size); out: @@ -143,7 +178,7 @@ static __init void reserve_regions(void) if (efi_enabled(EFI_DBG)) pr_info("Processing EFI memory map:\n"); - for_each_efi_memory_desc(&memmap, md) { + for_each_efi_memory_desc(md) { paddr = md->phys_addr; npages = md->num_pages; @@ -184,9 +219,9 @@ void __init efi_init(void) efi_system_table = params.system_table; - memmap.phys_map = params.mmap; - memmap.map = early_memremap_ro(params.mmap, params.mmap_size); - if (memmap.map == NULL) { + efi.memmap.phys_map = params.mmap; + efi.memmap.map = early_memremap_ro(params.mmap, params.mmap_size); + if (efi.memmap.map == NULL) { /* * If we are booting via UEFI, the UEFI memory map is the only * description of memory we have, so there is little point in @@ -194,28 +229,37 @@ void __init efi_init(void) */ panic("Unable to map EFI memory map.\n"); } - memmap.map_end = memmap.map + params.mmap_size; - memmap.desc_size = params.desc_size; - memmap.desc_version = params.desc_ver; + efi.memmap.map_end = efi.memmap.map + params.mmap_size; + efi.memmap.desc_size = params.desc_size; + efi.memmap.desc_version = params.desc_ver; + + WARN(efi.memmap.desc_version != 1, + "Unexpected EFI_MEMORY_DESCRIPTOR version %ld", + efi.memmap.desc_version); if (uefi_init() < 0) return; reserve_regions(); - early_memunmap(memmap.map, params.mmap_size); + efi_memattr_init(); + early_memunmap(efi.memmap.map, params.mmap_size); - if (IS_ENABLED(CONFIG_ARM)) { - /* - * ARM currently does not allow ioremap_cache() to be called on - * memory regions that are covered by struct page. So remove the - * UEFI memory map from the linear mapping. - */ - memblock_mark_nomap(params.mmap & PAGE_MASK, - PAGE_ALIGN(params.mmap_size + - (params.mmap & ~PAGE_MASK))); - } else { - memblock_reserve(params.mmap & PAGE_MASK, - PAGE_ALIGN(params.mmap_size + - (params.mmap & ~PAGE_MASK))); - } + memblock_reserve(params.mmap & PAGE_MASK, + PAGE_ALIGN(params.mmap_size + + (params.mmap & ~PAGE_MASK))); + + init_screen_info(); +} + +static int __init register_gop_device(void) +{ + void *pd; + + if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI) + return 0; + + pd = platform_device_register_data(NULL, "efi-framebuffer", 0, + &screen_info, sizeof(screen_info)); + return PTR_ERR_OR_ZERO(pd); } +subsys_initcall(register_gop_device); diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 6ae21e4..17ccf0a 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -42,11 +42,13 @@ static struct mm_struct efi_mm = { static bool __init efi_virtmap_init(void) { efi_memory_desc_t *md; + bool systab_found; efi_mm.pgd = pgd_alloc(&efi_mm); init_new_context(NULL, &efi_mm); - for_each_efi_memory_desc(&memmap, md) { + systab_found = false; + for_each_efi_memory_desc(md) { phys_addr_t phys = md->phys_addr; int ret; @@ -64,7 +66,25 @@ static bool __init efi_virtmap_init(void) &phys, ret); return false; } + /* + * If this entry covers the address of the UEFI system table, + * calculate and record its virtual address. + */ + if (efi_system_table >= phys && + efi_system_table < phys + (md->num_pages * EFI_PAGE_SIZE)) { + efi.systab = (void *)(unsigned long)(efi_system_table - + phys + md->virt_addr); + systab_found = true; + } + } + if (!systab_found) { + pr_err("No virtual mapping found for the UEFI System Table\n"); + return false; } + + if (efi_memattr_apply_permissions(&efi_mm, efi_set_mapping_permissions)) + return false; + return true; } @@ -89,26 +109,17 @@ static int __init arm_enable_runtime_services(void) pr_info("Remapping and enabling EFI services.\n"); - mapsize = memmap.map_end - memmap.map; - memmap.map = (__force void *)ioremap_cache(memmap.phys_map, - mapsize); - if (!memmap.map) { - pr_err("Failed to remap EFI memory map\n"); - return -ENOMEM; - } - memmap.map_end = memmap.map + mapsize; - efi.memmap = &memmap; + mapsize = efi.memmap.map_end - efi.memmap.map; - efi.systab = (__force void *)ioremap_cache(efi_system_table, - sizeof(efi_system_table_t)); - if (!efi.systab) { - pr_err("Failed to remap EFI System Table\n"); + efi.memmap.map = memremap(efi.memmap.phys_map, mapsize, MEMREMAP_WB); + if (!efi.memmap.map) { + pr_err("Failed to remap EFI memory map\n"); return -ENOMEM; } - set_bit(EFI_SYSTEM_TABLES, &efi.flags); + efi.memmap.map_end = efi.memmap.map + mapsize; if (!efi_virtmap_init()) { - pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n"); + pr_err("UEFI virtual mapping missing or invalid -- runtime services will not be available\n"); return -ENOMEM; } @@ -116,8 +127,6 @@ static int __init arm_enable_runtime_services(void) efi_native_runtime_setup(); set_bit(EFI_RUNTIME_SERVICES, &efi.flags); - efi.runtime_version = efi.systab->hdr.revision; - return 0; } early_initcall(arm_enable_runtime_services); diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c new file mode 100644 index 0000000..c99c24b --- /dev/null +++ b/drivers/firmware/efi/capsule-loader.c @@ -0,0 +1,343 @@ +/* + * EFI capsule loader driver. + * + * Copyright 2015 Intel Corporation + * + * This file is part of the Linux kernel, and is made available under + * the terms of the GNU General Public License version 2. + */ + +#define pr_fmt(fmt) "efi: " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/miscdevice.h> +#include <linux/highmem.h> +#include <linux/slab.h> +#include <linux/mutex.h> +#include <linux/efi.h> + +#define NO_FURTHER_WRITE_ACTION -1 + +struct capsule_info { + bool header_obtained; + int reset_type; + long index; + size_t count; + size_t total_size; + struct page **pages; + size_t page_bytes_remain; +}; + +/** + * efi_free_all_buff_pages - free all previous allocated buffer pages + * @cap_info: pointer to current instance of capsule_info structure + * + * In addition to freeing buffer pages, it flags NO_FURTHER_WRITE_ACTION + * to cease processing data in subsequent write(2) calls until close(2) + * is called. + **/ +static void efi_free_all_buff_pages(struct capsule_info *cap_info) +{ + while (cap_info->index > 0) + __free_page(cap_info->pages[--cap_info->index]); + + cap_info->index = NO_FURTHER_WRITE_ACTION; +} + +/** + * efi_capsule_setup_info - obtain the efi capsule header in the binary and + * setup capsule_info structure + * @cap_info: pointer to current instance of capsule_info structure + * @kbuff: a mapped first page buffer pointer + * @hdr_bytes: the total received number of bytes for efi header + **/ +static ssize_t efi_capsule_setup_info(struct capsule_info *cap_info, + void *kbuff, size_t hdr_bytes) +{ + efi_capsule_header_t *cap_hdr; + size_t pages_needed; + int ret; + void *temp_page; + + /* Only process data block that is larger than efi header size */ + if (hdr_bytes < sizeof(efi_capsule_header_t)) + return 0; + + /* Reset back to the correct offset of header */ + cap_hdr = kbuff - cap_info->count; + pages_needed = ALIGN(cap_hdr->imagesize, PAGE_SIZE) >> PAGE_SHIFT; + + if (pages_needed == 0) { + pr_err("%s: pages count invalid\n", __func__); + return -EINVAL; + } + + /* Check if the capsule binary supported */ + ret = efi_capsule_supported(cap_hdr->guid, cap_hdr->flags, + cap_hdr->imagesize, + &cap_info->reset_type); + if (ret) { + pr_err("%s: efi_capsule_supported() failed\n", + __func__); + return ret; + } + + cap_info->total_size = cap_hdr->imagesize; + temp_page = krealloc(cap_info->pages, + pages_needed * sizeof(void *), + GFP_KERNEL | __GFP_ZERO); + if (!temp_page) { + pr_debug("%s: krealloc() failed\n", __func__); + return -ENOMEM; + } + + cap_info->pages = temp_page; + cap_info->header_obtained = true; + + return 0; +} + +/** + * efi_capsule_submit_update - invoke the efi_capsule_update API once binary + * upload done + * @cap_info: pointer to current instance of capsule_info structure + **/ +static ssize_t efi_capsule_submit_update(struct capsule_info *cap_info) +{ + int ret; + void *cap_hdr_temp; + + cap_hdr_temp = kmap(cap_info->pages[0]); + if (!cap_hdr_temp) { + pr_debug("%s: kmap() failed\n", __func__); + return -EFAULT; + } + + ret = efi_capsule_update(cap_hdr_temp, cap_info->pages); + kunmap(cap_info->pages[0]); + if (ret) { + pr_err("%s: efi_capsule_update() failed\n", __func__); + return ret; + } + + /* Indicate capsule binary uploading is done */ + cap_info->index = NO_FURTHER_WRITE_ACTION; + pr_info("%s: Successfully upload capsule file with reboot type '%s'\n", + __func__, !cap_info->reset_type ? "RESET_COLD" : + cap_info->reset_type == 1 ? "RESET_WARM" : + "RESET_SHUTDOWN"); + return 0; +} + +/** + * efi_capsule_write - store the capsule binary and pass it to + * efi_capsule_update() API + * @file: file pointer + * @buff: buffer pointer + * @count: number of bytes in @buff + * @offp: not used + * + * Expectation: + * - A user space tool should start at the beginning of capsule binary and + * pass data in sequentially. + * - Users should close and re-open this file note in order to upload more + * capsules. + * - After an error returned, user should close the file and restart the + * operation for the next try otherwise -EIO will be returned until the + * file is closed. + * - An EFI capsule header must be located at the beginning of capsule + * binary file and passed in as first block data of write operation. + **/ +static ssize_t efi_capsule_write(struct file *file, const char __user *buff, + size_t count, loff_t *offp) +{ + int ret = 0; + struct capsule_info *cap_info = file->private_data; + struct page *page; + void *kbuff = NULL; + size_t write_byte; + + if (count == 0) + return 0; + + /* Return error while NO_FURTHER_WRITE_ACTION is flagged */ + if (cap_info->index < 0) + return -EIO; + + /* Only alloc a new page when previous page is full */ + if (!cap_info->page_bytes_remain) { + page = alloc_page(GFP_KERNEL); + if (!page) { + pr_debug("%s: alloc_page() failed\n", __func__); + ret = -ENOMEM; + goto failed; + } + + cap_info->pages[cap_info->index++] = page; + cap_info->page_bytes_remain = PAGE_SIZE; + } + + page = cap_info->pages[cap_info->index - 1]; + + kbuff = kmap(page); + if (!kbuff) { + pr_debug("%s: kmap() failed\n", __func__); + ret = -EFAULT; + goto failed; + } + kbuff += PAGE_SIZE - cap_info->page_bytes_remain; + + /* Copy capsule binary data from user space to kernel space buffer */ + write_byte = min_t(size_t, count, cap_info->page_bytes_remain); + if (copy_from_user(kbuff, buff, write_byte)) { + pr_debug("%s: copy_from_user() failed\n", __func__); + ret = -EFAULT; + goto fail_unmap; + } + cap_info->page_bytes_remain -= write_byte; + + /* Setup capsule binary info structure */ + if (!cap_info->header_obtained) { + ret = efi_capsule_setup_info(cap_info, kbuff, + cap_info->count + write_byte); + if (ret) + goto fail_unmap; + } + + cap_info->count += write_byte; + kunmap(page); + + /* Submit the full binary to efi_capsule_update() API */ + if (cap_info->header_obtained && + cap_info->count >= cap_info->total_size) { + if (cap_info->count > cap_info->total_size) { + pr_err("%s: upload size exceeded header defined size\n", + __func__); + ret = -EINVAL; + goto failed; + } + + ret = efi_capsule_submit_update(cap_info); + if (ret) + goto failed; + } + + return write_byte; + +fail_unmap: + kunmap(page); +failed: + efi_free_all_buff_pages(cap_info); + return ret; +} + +/** + * efi_capsule_flush - called by file close or file flush + * @file: file pointer + * @id: not used + * + * If a capsule is being partially uploaded then calling this function + * will be treated as upload termination and will free those completed + * buffer pages and -ECANCELED will be returned. + **/ +static int efi_capsule_flush(struct file *file, fl_owner_t id) +{ + int ret = 0; + struct capsule_info *cap_info = file->private_data; + + if (cap_info->index > 0) { + pr_err("%s: capsule upload not complete\n", __func__); + efi_free_all_buff_pages(cap_info); + ret = -ECANCELED; + } + + return ret; +} + +/** + * efi_capsule_release - called by file close + * @inode: not used + * @file: file pointer + * + * We will not free successfully submitted pages since efi update + * requires data to be maintained across system reboot. + **/ +static int efi_capsule_release(struct inode *inode, struct file *file) +{ + struct capsule_info *cap_info = file->private_data; + + kfree(cap_info->pages); + kfree(file->private_data); + file->private_data = NULL; + return 0; +} + +/** + * efi_capsule_open - called by file open + * @inode: not used + * @file: file pointer + * + * Will allocate each capsule_info memory for each file open call. + * This provided the capability to support multiple file open feature + * where user is not needed to wait for others to finish in order to + * upload their capsule binary. + **/ +static int efi_capsule_open(struct inode *inode, struct file *file) +{ + struct capsule_info *cap_info; + + cap_info = kzalloc(sizeof(*cap_info), GFP_KERNEL); + if (!cap_info) + return -ENOMEM; + + cap_info->pages = kzalloc(sizeof(void *), GFP_KERNEL); + if (!cap_info->pages) { + kfree(cap_info); + return -ENOMEM; + } + + file->private_data = cap_info; + + return 0; +} + +static const struct file_operations efi_capsule_fops = { + .owner = THIS_MODULE, + .open = efi_capsule_open, + .write = efi_capsule_write, + .flush = efi_capsule_flush, + .release = efi_capsule_release, + .llseek = no_llseek, +}; + +static struct miscdevice efi_capsule_misc = { + .minor = MISC_DYNAMIC_MINOR, + .name = "efi_capsule_loader", + .fops = &efi_capsule_fops, +}; + +static int __init efi_capsule_loader_init(void) +{ + int ret; + + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return -ENODEV; + + ret = misc_register(&efi_capsule_misc); + if (ret) + pr_err("%s: Failed to register misc char file note\n", + __func__); + + return ret; +} +module_init(efi_capsule_loader_init); + +static void __exit efi_capsule_loader_exit(void) +{ + misc_deregister(&efi_capsule_misc); +} +module_exit(efi_capsule_loader_exit); + +MODULE_DESCRIPTION("EFI capsule firmware binary loader"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/firmware/efi/capsule.c b/drivers/firmware/efi/capsule.c new file mode 100644 index 0000000..53b9fd2 --- /dev/null +++ b/drivers/firmware/efi/capsule.c @@ -0,0 +1,308 @@ +/* + * EFI capsule support. + * + * Copyright 2013 Intel Corporation; author Matt Fleming + * + * This file is part of the Linux kernel, and is made available under + * the terms of the GNU General Public License version 2. + */ + +#define pr_fmt(fmt) "efi: " fmt + +#include <linux/slab.h> +#include <linux/mutex.h> +#include <linux/highmem.h> +#include <linux/efi.h> +#include <linux/vmalloc.h> +#include <asm/io.h> + +typedef struct { + u64 length; + u64 data; +} efi_capsule_block_desc_t; + +static bool capsule_pending; +static bool stop_capsules; +static int efi_reset_type = -1; + +/* + * capsule_mutex serialises access to both capsule_pending and + * efi_reset_type and stop_capsules. + */ +static DEFINE_MUTEX(capsule_mutex); + +/** + * efi_capsule_pending - has a capsule been passed to the firmware? + * @reset_type: store the type of EFI reset if capsule is pending + * + * To ensure that the registered capsule is processed correctly by the + * firmware we need to perform a specific type of reset. If a capsule is + * pending return the reset type in @reset_type. + * + * This function will race with callers of efi_capsule_update(), for + * example, calling this function while somebody else is in + * efi_capsule_update() but hasn't reached efi_capsue_update_locked() + * will miss the updates to capsule_pending and efi_reset_type after + * efi_capsule_update_locked() completes. + * + * A non-racy use is from platform reboot code because we use + * system_state to ensure no capsules can be sent to the firmware once + * we're at SYSTEM_RESTART. See efi_capsule_update_locked(). + */ +bool efi_capsule_pending(int *reset_type) +{ + if (!capsule_pending) + return false; + + if (reset_type) + *reset_type = efi_reset_type; + + return true; +} + +/* + * Whitelist of EFI capsule flags that we support. + * + * We do not handle EFI_CAPSULE_INITIATE_RESET because that would + * require us to prepare the kernel for reboot. Refuse to load any + * capsules with that flag and any other flags that we do not know how + * to handle. + */ +#define EFI_CAPSULE_SUPPORTED_FLAG_MASK \ + (EFI_CAPSULE_PERSIST_ACROSS_RESET | EFI_CAPSULE_POPULATE_SYSTEM_TABLE) + +/** + * efi_capsule_supported - does the firmware support the capsule? + * @guid: vendor guid of capsule + * @flags: capsule flags + * @size: size of capsule data + * @reset: the reset type required for this capsule + * + * Check whether a capsule with @flags is supported by the firmware + * and that @size doesn't exceed the maximum size for a capsule. + * + * No attempt is made to check @reset against the reset type required + * by any pending capsules because of the races involved. + */ +int efi_capsule_supported(efi_guid_t guid, u32 flags, size_t size, int *reset) +{ + efi_capsule_header_t capsule; + efi_capsule_header_t *cap_list[] = { &capsule }; + efi_status_t status; + u64 max_size; + + if (flags & ~EFI_CAPSULE_SUPPORTED_FLAG_MASK) + return -EINVAL; + + capsule.headersize = capsule.imagesize = sizeof(capsule); + memcpy(&capsule.guid, &guid, sizeof(efi_guid_t)); + capsule.flags = flags; + + status = efi.query_capsule_caps(cap_list, 1, &max_size, reset); + if (status != EFI_SUCCESS) + return efi_status_to_err(status); + + if (size > max_size) + return -ENOSPC; + + return 0; +} +EXPORT_SYMBOL_GPL(efi_capsule_supported); + +/* + * Every scatter gather list (block descriptor) page must end with a + * continuation pointer. The last continuation pointer of the last + * page must be zero to mark the end of the chain. + */ +#define SGLIST_PER_PAGE ((PAGE_SIZE / sizeof(efi_capsule_block_desc_t)) - 1) + +/* + * How many scatter gather list (block descriptor) pages do we need + * to map @count pages? + */ +static inline unsigned int sg_pages_num(unsigned int count) +{ + return DIV_ROUND_UP(count, SGLIST_PER_PAGE); +} + +/** + * efi_capsule_update_locked - pass a single capsule to the firmware + * @capsule: capsule to send to the firmware + * @sg_pages: array of scatter gather (block descriptor) pages + * @reset: the reset type required for @capsule + * + * Since this function must be called under capsule_mutex check + * whether efi_reset_type will conflict with @reset, and atomically + * set it and capsule_pending if a capsule was successfully sent to + * the firmware. + * + * We also check to see if the system is about to restart, and if so, + * abort. This avoids races between efi_capsule_update() and + * efi_capsule_pending(). + */ +static int +efi_capsule_update_locked(efi_capsule_header_t *capsule, + struct page **sg_pages, int reset) +{ + efi_physical_addr_t sglist_phys; + efi_status_t status; + + lockdep_assert_held(&capsule_mutex); + + /* + * If someone has already registered a capsule that requires a + * different reset type, we're out of luck and must abort. + */ + if (efi_reset_type >= 0 && efi_reset_type != reset) { + pr_err("Conflicting capsule reset type %d (%d).\n", + reset, efi_reset_type); + return -EINVAL; + } + + /* + * If the system is getting ready to restart it may have + * called efi_capsule_pending() to make decisions (such as + * whether to force an EFI reboot), and we're racing against + * that call. Abort in that case. + */ + if (unlikely(stop_capsules)) { + pr_warn("Capsule update raced with reboot, aborting.\n"); + return -EINVAL; + } + + sglist_phys = page_to_phys(sg_pages[0]); + + status = efi.update_capsule(&capsule, 1, sglist_phys); + if (status == EFI_SUCCESS) { + capsule_pending = true; + efi_reset_type = reset; + } + + return efi_status_to_err(status); +} + +/** + * efi_capsule_update - send a capsule to the firmware + * @capsule: capsule to send to firmware + * @pages: an array of capsule data pages + * + * Build a scatter gather list with EFI capsule block descriptors to + * map the capsule described by @capsule with its data in @pages and + * send it to the firmware via the UpdateCapsule() runtime service. + * + * @capsule must be a virtual mapping of the first page in @pages + * (@pages[0]) in the kernel address space. That is, a + * capsule_header_t that describes the entire contents of the capsule + * must be at the start of the first data page. + * + * Even though this function will validate that the firmware supports + * the capsule guid, users will likely want to check that + * efi_capsule_supported() returns true before calling this function + * because it makes it easier to print helpful error messages. + * + * If the capsule is successfully submitted to the firmware, any + * subsequent calls to efi_capsule_pending() will return true. @pages + * must not be released or modified if this function returns + * successfully. + * + * Callers must be prepared for this function to fail, which can + * happen if we raced with system reboot or if there is already a + * pending capsule that has a reset type that conflicts with the one + * required by @capsule. Do NOT use efi_capsule_pending() to detect + * this conflict since that would be racy. Instead, submit the capsule + * to efi_capsule_update() and check the return value. + * + * Return 0 on success, a converted EFI status code on failure. + */ +int efi_capsule_update(efi_capsule_header_t *capsule, struct page **pages) +{ + u32 imagesize = capsule->imagesize; + efi_guid_t guid = capsule->guid; + unsigned int count, sg_count; + u32 flags = capsule->flags; + struct page **sg_pages; + int rv, reset_type; + int i, j; + + rv = efi_capsule_supported(guid, flags, imagesize, &reset_type); + if (rv) + return rv; + + count = DIV_ROUND_UP(imagesize, PAGE_SIZE); + sg_count = sg_pages_num(count); + + sg_pages = kzalloc(sg_count * sizeof(*sg_pages), GFP_KERNEL); + if (!sg_pages) + return -ENOMEM; + + for (i = 0; i < sg_count; i++) { + sg_pages[i] = alloc_page(GFP_KERNEL); + if (!sg_pages[i]) { + rv = -ENOMEM; + goto out; + } + } + + for (i = 0; i < sg_count; i++) { + efi_capsule_block_desc_t *sglist; + + sglist = kmap(sg_pages[i]); + if (!sglist) { + rv = -ENOMEM; + goto out; + } + + for (j = 0; j < SGLIST_PER_PAGE && count > 0; j++) { + u64 sz = min_t(u64, imagesize, PAGE_SIZE); + + sglist[j].length = sz; + sglist[j].data = page_to_phys(*pages++); + + imagesize -= sz; + count--; + } + + /* Continuation pointer */ + sglist[j].length = 0; + + if (i + 1 == sg_count) + sglist[j].data = 0; + else + sglist[j].data = page_to_phys(sg_pages[i + 1]); + + kunmap(sg_pages[i]); + } + + mutex_lock(&capsule_mutex); + rv = efi_capsule_update_locked(capsule, sg_pages, reset_type); + mutex_unlock(&capsule_mutex); + +out: + for (i = 0; rv && i < sg_count; i++) { + if (sg_pages[i]) + __free_page(sg_pages[i]); + } + + kfree(sg_pages); + return rv; +} +EXPORT_SYMBOL_GPL(efi_capsule_update); + +static int capsule_reboot_notify(struct notifier_block *nb, unsigned long event, void *cmd) +{ + mutex_lock(&capsule_mutex); + stop_capsules = true; + mutex_unlock(&capsule_mutex); + + return NOTIFY_DONE; +} + +static struct notifier_block capsule_reboot_nb = { + .notifier_call = capsule_reboot_notify, +}; + +static int __init capsule_reboot_register(void) +{ + return register_reboot_notifier(&capsule_reboot_nb); +} +core_initcall(capsule_reboot_register); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 3a69ed5..05509f3 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -43,6 +43,7 @@ struct efi __read_mostly efi = { .config_table = EFI_INVALID_TABLE_ADDR, .esrt = EFI_INVALID_TABLE_ADDR, .properties_table = EFI_INVALID_TABLE_ADDR, + .mem_attr_table = EFI_INVALID_TABLE_ADDR, }; EXPORT_SYMBOL(efi); @@ -256,7 +257,7 @@ subsys_initcall(efisubsys_init); */ int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) { - struct efi_memory_map *map = efi.memmap; + struct efi_memory_map *map = &efi.memmap; phys_addr_t p, e; if (!efi_enabled(EFI_MEMMAP)) { @@ -338,6 +339,7 @@ static __initdata efi_config_table_type_t common_tables[] = { {UGA_IO_PROTOCOL_GUID, "UGA", &efi.uga}, {EFI_SYSTEM_RESOURCE_TABLE_GUID, "ESRT", &efi.esrt}, {EFI_PROPERTIES_TABLE_GUID, "PROP", &efi.properties_table}, + {EFI_MEMORY_ATTRIBUTES_TABLE_GUID, "MEMATTR", &efi.mem_attr_table}, {NULL_GUID, NULL, NULL}, }; @@ -351,8 +353,9 @@ static __init int match_config_table(efi_guid_t *guid, for (i = 0; efi_guidcmp(table_types[i].guid, NULL_GUID); i++) { if (!efi_guidcmp(*guid, table_types[i].guid)) { *(table_types[i].ptr) = table; - pr_cont(" %s=0x%lx ", - table_types[i].name, table); + if (table_types[i].name) + pr_cont(" %s=0x%lx ", + table_types[i].name, table); return 1; } } @@ -620,16 +623,12 @@ char * __init efi_md_typeattr_format(char *buf, size_t size, */ u64 __weak efi_mem_attributes(unsigned long phys_addr) { - struct efi_memory_map *map; efi_memory_desc_t *md; - void *p; if (!efi_enabled(EFI_MEMMAP)) return 0; - map = efi.memmap; - for (p = map->map; p < map->map_end; p += map->desc_size) { - md = p; + for_each_efi_memory_desc(md) { if ((md->phys_addr <= phys_addr) && (phys_addr < (md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT)))) @@ -637,3 +636,36 @@ u64 __weak efi_mem_attributes(unsigned long phys_addr) } return 0; } + +int efi_status_to_err(efi_status_t status) +{ + int err; + + switch (status) { + case EFI_SUCCESS: + err = 0; + break; + case EFI_INVALID_PARAMETER: + err = -EINVAL; + break; + case EFI_OUT_OF_RESOURCES: + err = -ENOSPC; + break; + case EFI_DEVICE_ERROR: + err = -EIO; + break; + case EFI_WRITE_PROTECTED: + err = -EROFS; + break; + case EFI_SECURITY_VIOLATION: + err = -EACCES; + break; + case EFI_NOT_FOUND: + err = -ENOENT; + break; + default: + err = -EINVAL; + } + + return err; +} diff --git a/drivers/firmware/efi/efibc.c b/drivers/firmware/efi/efibc.c new file mode 100644 index 0000000..8dd0c70 --- /dev/null +++ b/drivers/firmware/efi/efibc.c @@ -0,0 +1,113 @@ +/* + * efibc: control EFI bootloaders which obey LoaderEntryOneShot var + * Copyright (c) 2013-2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#define pr_fmt(fmt) "efibc: " fmt + +#include <linux/efi.h> +#include <linux/module.h> +#include <linux/reboot.h> +#include <linux/slab.h> + +static void efibc_str_to_str16(const char *str, efi_char16_t *str16) +{ + size_t i; + + for (i = 0; i < strlen(str); i++) + str16[i] = str[i]; + + str16[i] = '\0'; +} + +static int efibc_set_variable(const char *name, const char *value) +{ + int ret; + efi_guid_t guid = LINUX_EFI_LOADER_ENTRY_GUID; + struct efivar_entry *entry; + size_t size = (strlen(value) + 1) * sizeof(efi_char16_t); + + if (size > sizeof(entry->var.Data)) { + pr_err("value is too large"); + return -EINVAL; + } + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + pr_err("failed to allocate efivar entry"); + return -ENOMEM; + } + + efibc_str_to_str16(name, entry->var.VariableName); + efibc_str_to_str16(value, (efi_char16_t *)entry->var.Data); + memcpy(&entry->var.VendorGuid, &guid, sizeof(guid)); + + ret = efivar_entry_set(entry, + EFI_VARIABLE_NON_VOLATILE + | EFI_VARIABLE_BOOTSERVICE_ACCESS + | EFI_VARIABLE_RUNTIME_ACCESS, + size, entry->var.Data, NULL); + if (ret) + pr_err("failed to set %s EFI variable: 0x%x\n", + name, ret); + + kfree(entry); + return ret; +} + +static int efibc_reboot_notifier_call(struct notifier_block *notifier, + unsigned long event, void *data) +{ + const char *reason = "shutdown"; + int ret; + + if (event == SYS_RESTART) + reason = "reboot"; + + ret = efibc_set_variable("LoaderEntryRebootReason", reason); + if (ret || !data) + return NOTIFY_DONE; + + efibc_set_variable("LoaderEntryOneShot", (char *)data); + + return NOTIFY_DONE; +} + +static struct notifier_block efibc_reboot_notifier = { + .notifier_call = efibc_reboot_notifier_call, +}; + +static int __init efibc_init(void) +{ + int ret; + + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return -ENODEV; + + ret = register_reboot_notifier(&efibc_reboot_notifier); + if (ret) + pr_err("unable to register reboot notifier\n"); + + return ret; +} +module_init(efibc_init); + +static void __exit efibc_exit(void) +{ + unregister_reboot_notifier(&efibc_reboot_notifier); +} +module_exit(efibc_exit); + +MODULE_AUTHOR("Jeremy Compostella <jeremy.compostella@intel.com>"); +MODULE_AUTHOR("Matt Gumbel <matthew.k.gumbel@intel.com"); +MODULE_DESCRIPTION("EFI Bootloader Control"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 096adcb..116b244 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -661,7 +661,7 @@ static void efivar_update_sysfs_entries(struct work_struct *work) return; err = efivar_init(efivar_update_sysfs_entry, entry, - true, false, &efivar_sysfs_list); + false, &efivar_sysfs_list); if (!err) break; @@ -730,8 +730,7 @@ int efivars_sysfs_init(void) return -ENOMEM; } - efivar_init(efivars_sysfs_callback, NULL, false, - true, &efivar_sysfs_list); + efivar_init(efivars_sysfs_callback, NULL, true, &efivar_sysfs_list); error = create_efivars_bin_attributes(); if (error) { diff --git a/drivers/firmware/efi/fake_mem.c b/drivers/firmware/efi/fake_mem.c index ed3a854..48430ab 100644 --- a/drivers/firmware/efi/fake_mem.c +++ b/drivers/firmware/efi/fake_mem.c @@ -57,7 +57,7 @@ static int __init cmp_fake_mem(const void *x1, const void *x2) void __init efi_fake_memmap(void) { u64 start, end, m_start, m_end, m_attr; - int new_nr_map = memmap.nr_map; + int new_nr_map = efi.memmap.nr_map; efi_memory_desc_t *md; phys_addr_t new_memmap_phy; void *new_memmap; @@ -68,8 +68,7 @@ void __init efi_fake_memmap(void) return; /* count up the number of EFI memory descriptor */ - for (old = memmap.map; old < memmap.map_end; old += memmap.desc_size) { - md = old; + for_each_efi_memory_desc(md) { start = md->phys_addr; end = start + (md->num_pages << EFI_PAGE_SHIFT) - 1; @@ -95,25 +94,25 @@ void __init efi_fake_memmap(void) } /* allocate memory for new EFI memmap */ - new_memmap_phy = memblock_alloc(memmap.desc_size * new_nr_map, + new_memmap_phy = memblock_alloc(efi.memmap.desc_size * new_nr_map, PAGE_SIZE); if (!new_memmap_phy) return; /* create new EFI memmap */ new_memmap = early_memremap(new_memmap_phy, - memmap.desc_size * new_nr_map); + efi.memmap.desc_size * new_nr_map); if (!new_memmap) { - memblock_free(new_memmap_phy, memmap.desc_size * new_nr_map); + memblock_free(new_memmap_phy, efi.memmap.desc_size * new_nr_map); return; } - for (old = memmap.map, new = new_memmap; - old < memmap.map_end; - old += memmap.desc_size, new += memmap.desc_size) { + for (old = efi.memmap.map, new = new_memmap; + old < efi.memmap.map_end; + old += efi.memmap.desc_size, new += efi.memmap.desc_size) { /* copy original EFI memory descriptor */ - memcpy(new, old, memmap.desc_size); + memcpy(new, old, efi.memmap.desc_size); md = new; start = md->phys_addr; end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1; @@ -134,8 +133,8 @@ void __init efi_fake_memmap(void) md->num_pages = (m_end - md->phys_addr + 1) >> EFI_PAGE_SHIFT; /* latter part */ - new += memmap.desc_size; - memcpy(new, old, memmap.desc_size); + new += efi.memmap.desc_size; + memcpy(new, old, efi.memmap.desc_size); md = new; md->phys_addr = m_end + 1; md->num_pages = (end - md->phys_addr + 1) >> @@ -147,16 +146,16 @@ void __init efi_fake_memmap(void) md->num_pages = (m_start - md->phys_addr) >> EFI_PAGE_SHIFT; /* middle part */ - new += memmap.desc_size; - memcpy(new, old, memmap.desc_size); + new += efi.memmap.desc_size; + memcpy(new, old, efi.memmap.desc_size); md = new; md->attribute |= m_attr; md->phys_addr = m_start; md->num_pages = (m_end - m_start + 1) >> EFI_PAGE_SHIFT; /* last part */ - new += memmap.desc_size; - memcpy(new, old, memmap.desc_size); + new += efi.memmap.desc_size; + memcpy(new, old, efi.memmap.desc_size); md = new; md->phys_addr = m_end + 1; md->num_pages = (end - m_end) >> @@ -169,8 +168,8 @@ void __init efi_fake_memmap(void) md->num_pages = (m_start - md->phys_addr) >> EFI_PAGE_SHIFT; /* latter part */ - new += memmap.desc_size; - memcpy(new, old, memmap.desc_size); + new += efi.memmap.desc_size; + memcpy(new, old, efi.memmap.desc_size); md = new; md->phys_addr = m_start; md->num_pages = (end - md->phys_addr + 1) >> @@ -182,10 +181,10 @@ void __init efi_fake_memmap(void) /* swap into new EFI memmap */ efi_unmap_memmap(); - memmap.map = new_memmap; - memmap.phys_map = new_memmap_phy; - memmap.nr_map = new_nr_map; - memmap.map_end = memmap.map + memmap.nr_map * memmap.desc_size; + efi.memmap.map = new_memmap; + efi.memmap.phys_map = new_memmap_phy; + efi.memmap.nr_map = new_nr_map; + efi.memmap.map_end = efi.memmap.map + efi.memmap.nr_map * efi.memmap.desc_size; set_bit(EFI_MEMMAP, &efi.flags); /* print new EFI memmap */ diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index da99bbb..c069451 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -28,7 +28,7 @@ OBJECT_FILES_NON_STANDARD := y # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. KCOV_INSTRUMENT := n -lib-y := efi-stub-helper.o +lib-y := efi-stub-helper.o gop.o # include the stub's generic dependencies from lib/ when building for ARM/arm64 arm-deps := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c fdt_empty_tree.c fdt_sw.c sort.c diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index 414deb8..993aa56 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -20,27 +20,49 @@ bool __nokaslr; -static int efi_secureboot_enabled(efi_system_table_t *sys_table_arg) +static int efi_get_secureboot(efi_system_table_t *sys_table_arg) { - static efi_guid_t const var_guid = EFI_GLOBAL_VARIABLE_GUID; - static efi_char16_t const var_name[] = { + static efi_char16_t const sb_var_name[] = { 'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0 }; + static efi_char16_t const sm_var_name[] = { + 'S', 'e', 't', 'u', 'p', 'M', 'o', 'd', 'e', 0 }; + efi_guid_t var_guid = EFI_GLOBAL_VARIABLE_GUID; efi_get_variable_t *f_getvar = sys_table_arg->runtime->get_variable; - unsigned long size = sizeof(u8); - efi_status_t status; u8 val; + unsigned long size = sizeof(val); + efi_status_t status; - status = f_getvar((efi_char16_t *)var_name, (efi_guid_t *)&var_guid, + status = f_getvar((efi_char16_t *)sb_var_name, (efi_guid_t *)&var_guid, NULL, &size, &val); + if (status != EFI_SUCCESS) + goto out_efi_err; + + if (val == 0) + return 0; + + status = f_getvar((efi_char16_t *)sm_var_name, (efi_guid_t *)&var_guid, + NULL, &size, &val); + + if (status != EFI_SUCCESS) + goto out_efi_err; + + if (val == 1) + return 0; + + return 1; + +out_efi_err: switch (status) { - case EFI_SUCCESS: - return val; case EFI_NOT_FOUND: return 0; + case EFI_DEVICE_ERROR: + return -EIO; + case EFI_SECURITY_VIOLATION: + return -EACCES; default: - return 1; + return -EINVAL; } } @@ -147,6 +169,25 @@ void efi_char16_printk(efi_system_table_t *sys_table_arg, out->output_string(out, str); } +static struct screen_info *setup_graphics(efi_system_table_t *sys_table_arg) +{ + efi_guid_t gop_proto = EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID; + efi_status_t status; + unsigned long size; + void **gop_handle = NULL; + struct screen_info *si = NULL; + + size = 0; + status = efi_call_early(locate_handle, EFI_LOCATE_BY_PROTOCOL, + &gop_proto, NULL, &size, gop_handle); + if (status == EFI_BUFFER_TOO_SMALL) { + si = alloc_screen_info(sys_table_arg); + if (!si) + return NULL; + efi_setup_gop(sys_table_arg, si, &gop_proto, size); + } + return si; +} /* * This function handles the architcture specific differences between arm and @@ -185,6 +226,8 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, efi_guid_t loaded_image_proto = LOADED_IMAGE_PROTOCOL_GUID; unsigned long reserve_addr = 0; unsigned long reserve_size = 0; + int secure_boot = 0; + struct screen_info *si; /* Check if we were booted by the EFI firmware */ if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) @@ -237,6 +280,8 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, __nokaslr = true; } + si = setup_graphics(sys_table); + status = handle_kernel_image(sys_table, image_addr, &image_size, &reserve_addr, &reserve_size, @@ -250,12 +295,21 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, if (status != EFI_SUCCESS) pr_efi_err(sys_table, "Failed to parse EFI cmdline options\n"); + secure_boot = efi_get_secureboot(sys_table); + if (secure_boot > 0) + pr_efi(sys_table, "UEFI Secure Boot is enabled.\n"); + + if (secure_boot < 0) { + pr_efi_err(sys_table, + "could not determine UEFI Secure Boot status.\n"); + } + /* * Unauthenticated device tree data is a security hazard, so * ignore 'dtb=' unless UEFI Secure Boot is disabled. */ - if (efi_secureboot_enabled(sys_table)) { - pr_efi(sys_table, "UEFI Secure Boot is enabled.\n"); + if (secure_boot != 0 && strstr(cmdline_ptr, "dtb=")) { + pr_efi(sys_table, "Ignoring DTB from command line.\n"); } else { status = handle_cmdline_files(sys_table, image, cmdline_ptr, "dtb=", @@ -309,6 +363,7 @@ fail_free_image: efi_free(sys_table, image_size, *image_addr); efi_free(sys_table, reserve_size, reserve_addr); fail_free_cmdline: + free_screen_info(sys_table, si); efi_free(sys_table, cmdline_size, (unsigned long)cmdline_ptr); fail: return EFI_ERROR; diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c index 6f42be4..e1f0b28 100644 --- a/drivers/firmware/efi/libstub/arm32-stub.c +++ b/drivers/firmware/efi/libstub/arm32-stub.c @@ -26,6 +26,43 @@ efi_status_t check_platform_features(efi_system_table_t *sys_table_arg) return EFI_SUCCESS; } +static efi_guid_t screen_info_guid = LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID; + +struct screen_info *alloc_screen_info(efi_system_table_t *sys_table_arg) +{ + struct screen_info *si; + efi_status_t status; + + /* + * Unlike on arm64, where we can directly fill out the screen_info + * structure from the stub, we need to allocate a buffer to hold + * its contents while we hand over to the kernel proper from the + * decompressor. + */ + status = efi_call_early(allocate_pool, EFI_RUNTIME_SERVICES_DATA, + sizeof(*si), (void **)&si); + + if (status != EFI_SUCCESS) + return NULL; + + status = efi_call_early(install_configuration_table, + &screen_info_guid, si); + if (status == EFI_SUCCESS) + return si; + + efi_call_early(free_pool, si); + return NULL; +} + +void free_screen_info(efi_system_table_t *sys_table_arg, struct screen_info *si) +{ + if (!si) + return; + + efi_call_early(install_configuration_table, &screen_info_guid, NULL); + efi_call_early(free_pool, si); +} + efi_status_t handle_kernel_image(efi_system_table_t *sys_table, unsigned long *image_addr, unsigned long *image_size, diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 29ed2f9..3bd127f9 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -125,10 +125,12 @@ unsigned long get_dram_base(efi_system_table_t *sys_table_arg) map.map_end = map.map + map_size; - for_each_efi_memory_desc(&map, md) - if (md->attribute & EFI_MEMORY_WB) + for_each_efi_memory_desc_in_map(&map, md) { + if (md->attribute & EFI_MEMORY_WB) { if (membase > md->phys_addr) membase = md->phys_addr; + } + } efi_call_early(free_pool, map.map); diff --git a/drivers/firmware/efi/libstub/gop.c b/drivers/firmware/efi/libstub/gop.c new file mode 100644 index 0000000..932742e --- /dev/null +++ b/drivers/firmware/efi/libstub/gop.c @@ -0,0 +1,354 @@ +/* ----------------------------------------------------------------------- + * + * Copyright 2011 Intel Corporation; author Matt Fleming + * + * This file is part of the Linux kernel, and is made available under + * the terms of the GNU General Public License version 2. + * + * ----------------------------------------------------------------------- */ + +#include <linux/efi.h> +#include <linux/screen_info.h> +#include <asm/efi.h> +#include <asm/setup.h> + +static void find_bits(unsigned long mask, u8 *pos, u8 *size) +{ + u8 first, len; + + first = 0; + len = 0; + + if (mask) { + while (!(mask & 0x1)) { + mask = mask >> 1; + first++; + } + + while (mask & 0x1) { + mask = mask >> 1; + len++; + } + } + + *pos = first; + *size = len; +} + +static void +setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line, + struct efi_pixel_bitmask pixel_info, int pixel_format) +{ + if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) { + si->lfb_depth = 32; + si->lfb_linelength = pixels_per_scan_line * 4; + si->red_size = 8; + si->red_pos = 0; + si->green_size = 8; + si->green_pos = 8; + si->blue_size = 8; + si->blue_pos = 16; + si->rsvd_size = 8; + si->rsvd_pos = 24; + } else if (pixel_format == PIXEL_BGR_RESERVED_8BIT_PER_COLOR) { + si->lfb_depth = 32; + si->lfb_linelength = pixels_per_scan_line * 4; + si->red_size = 8; + si->red_pos = 16; + si->green_size = 8; + si->green_pos = 8; + si->blue_size = 8; + si->blue_pos = 0; + si->rsvd_size = 8; + si->rsvd_pos = 24; + } else if (pixel_format == PIXEL_BIT_MASK) { + find_bits(pixel_info.red_mask, &si->red_pos, &si->red_size); + find_bits(pixel_info.green_mask, &si->green_pos, + &si->green_size); + find_bits(pixel_info.blue_mask, &si->blue_pos, &si->blue_size); + find_bits(pixel_info.reserved_mask, &si->rsvd_pos, + &si->rsvd_size); + si->lfb_depth = si->red_size + si->green_size + + si->blue_size + si->rsvd_size; + si->lfb_linelength = (pixels_per_scan_line * si->lfb_depth) / 8; + } else { + si->lfb_depth = 4; + si->lfb_linelength = si->lfb_width / 2; + si->red_size = 0; + si->red_pos = 0; + si->green_size = 0; + si->green_pos = 0; + si->blue_size = 0; + si->blue_pos = 0; + si->rsvd_size = 0; + si->rsvd_pos = 0; + } +} + +static efi_status_t +__gop_query32(efi_system_table_t *sys_table_arg, + struct efi_graphics_output_protocol_32 *gop32, + struct efi_graphics_output_mode_info **info, + unsigned long *size, u64 *fb_base) +{ + struct efi_graphics_output_protocol_mode_32 *mode; + efi_graphics_output_protocol_query_mode query_mode; + efi_status_t status; + unsigned long m; + + m = gop32->mode; + mode = (struct efi_graphics_output_protocol_mode_32 *)m; + query_mode = (void *)(unsigned long)gop32->query_mode; + + status = __efi_call_early(query_mode, (void *)gop32, mode->mode, size, + info); + if (status != EFI_SUCCESS) + return status; + + *fb_base = mode->frame_buffer_base; + return status; +} + +static efi_status_t +setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, + efi_guid_t *proto, unsigned long size, void **gop_handle) +{ + struct efi_graphics_output_protocol_32 *gop32, *first_gop; + unsigned long nr_gops; + u16 width, height; + u32 pixels_per_scan_line; + u32 ext_lfb_base; + u64 fb_base; + struct efi_pixel_bitmask pixel_info; + int pixel_format; + efi_status_t status = EFI_NOT_FOUND; + u32 *handles = (u32 *)(unsigned long)gop_handle; + int i; + + first_gop = NULL; + gop32 = NULL; + + nr_gops = size / sizeof(u32); + for (i = 0; i < nr_gops; i++) { + struct efi_graphics_output_mode_info *info = NULL; + efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; + bool conout_found = false; + void *dummy = NULL; + efi_handle_t h = (efi_handle_t)(unsigned long)handles[i]; + u64 current_fb_base; + + status = efi_call_early(handle_protocol, h, + proto, (void **)&gop32); + if (status != EFI_SUCCESS) + continue; + + status = efi_call_early(handle_protocol, h, + &conout_proto, &dummy); + if (status == EFI_SUCCESS) + conout_found = true; + + status = __gop_query32(sys_table_arg, gop32, &info, &size, + ¤t_fb_base); + if (status == EFI_SUCCESS && (!first_gop || conout_found)) { + /* + * Systems that use the UEFI Console Splitter may + * provide multiple GOP devices, not all of which are + * backed by real hardware. The workaround is to search + * for a GOP implementing the ConOut protocol, and if + * one isn't found, to just fall back to the first GOP. + */ + width = info->horizontal_resolution; + height = info->vertical_resolution; + pixel_format = info->pixel_format; + pixel_info = info->pixel_information; + pixels_per_scan_line = info->pixels_per_scan_line; + fb_base = current_fb_base; + + /* + * Once we've found a GOP supporting ConOut, + * don't bother looking any further. + */ + first_gop = gop32; + if (conout_found) + break; + } + } + + /* Did we find any GOPs? */ + if (!first_gop) + goto out; + + /* EFI framebuffer */ + si->orig_video_isVGA = VIDEO_TYPE_EFI; + + si->lfb_width = width; + si->lfb_height = height; + si->lfb_base = fb_base; + + ext_lfb_base = (u64)(unsigned long)fb_base >> 32; + if (ext_lfb_base) { + si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; + si->ext_lfb_base = ext_lfb_base; + } + + si->pages = 1; + + setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); + + si->lfb_size = si->lfb_linelength * si->lfb_height; + + si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; +out: + return status; +} + +static efi_status_t +__gop_query64(efi_system_table_t *sys_table_arg, + struct efi_graphics_output_protocol_64 *gop64, + struct efi_graphics_output_mode_info **info, + unsigned long *size, u64 *fb_base) +{ + struct efi_graphics_output_protocol_mode_64 *mode; + efi_graphics_output_protocol_query_mode query_mode; + efi_status_t status; + unsigned long m; + + m = gop64->mode; + mode = (struct efi_graphics_output_protocol_mode_64 *)m; + query_mode = (void *)(unsigned long)gop64->query_mode; + + status = __efi_call_early(query_mode, (void *)gop64, mode->mode, size, + info); + if (status != EFI_SUCCESS) + return status; + + *fb_base = mode->frame_buffer_base; + return status; +} + +static efi_status_t +setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, + efi_guid_t *proto, unsigned long size, void **gop_handle) +{ + struct efi_graphics_output_protocol_64 *gop64, *first_gop; + unsigned long nr_gops; + u16 width, height; + u32 pixels_per_scan_line; + u32 ext_lfb_base; + u64 fb_base; + struct efi_pixel_bitmask pixel_info; + int pixel_format; + efi_status_t status = EFI_NOT_FOUND; + u64 *handles = (u64 *)(unsigned long)gop_handle; + int i; + + first_gop = NULL; + gop64 = NULL; + + nr_gops = size / sizeof(u64); + for (i = 0; i < nr_gops; i++) { + struct efi_graphics_output_mode_info *info = NULL; + efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; + bool conout_found = false; + void *dummy = NULL; + efi_handle_t h = (efi_handle_t)(unsigned long)handles[i]; + u64 current_fb_base; + + status = efi_call_early(handle_protocol, h, + proto, (void **)&gop64); + if (status != EFI_SUCCESS) + continue; + + status = efi_call_early(handle_protocol, h, + &conout_proto, &dummy); + if (status == EFI_SUCCESS) + conout_found = true; + + status = __gop_query64(sys_table_arg, gop64, &info, &size, + ¤t_fb_base); + if (status == EFI_SUCCESS && (!first_gop || conout_found)) { + /* + * Systems that use the UEFI Console Splitter may + * provide multiple GOP devices, not all of which are + * backed by real hardware. The workaround is to search + * for a GOP implementing the ConOut protocol, and if + * one isn't found, to just fall back to the first GOP. + */ + width = info->horizontal_resolution; + height = info->vertical_resolution; + pixel_format = info->pixel_format; + pixel_info = info->pixel_information; + pixels_per_scan_line = info->pixels_per_scan_line; + fb_base = current_fb_base; + + /* + * Once we've found a GOP supporting ConOut, + * don't bother looking any further. + */ + first_gop = gop64; + if (conout_found) + break; + } + } + + /* Did we find any GOPs? */ + if (!first_gop) + goto out; + + /* EFI framebuffer */ + si->orig_video_isVGA = VIDEO_TYPE_EFI; + + si->lfb_width = width; + si->lfb_height = height; + si->lfb_base = fb_base; + + ext_lfb_base = (u64)(unsigned long)fb_base >> 32; + if (ext_lfb_base) { + si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; + si->ext_lfb_base = ext_lfb_base; + } + + si->pages = 1; + + setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); + + si->lfb_size = si->lfb_linelength * si->lfb_height; + + si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; +out: + return status; +} + +/* + * See if we have Graphics Output Protocol + */ +efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, + struct screen_info *si, efi_guid_t *proto, + unsigned long size) +{ + efi_status_t status; + void **gop_handle = NULL; + + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + size, (void **)&gop_handle); + if (status != EFI_SUCCESS) + return status; + + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + proto, NULL, &size, gop_handle); + if (status != EFI_SUCCESS) + goto free_handle; + + if (efi_is_64bit()) { + status = setup_gop64(sys_table_arg, si, proto, size, + gop_handle); + } else { + status = setup_gop32(sys_table_arg, si, proto, size, + gop_handle); + } + +free_handle: + efi_call_early(free_pool, gop_handle); + return status; +} diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c new file mode 100644 index 0000000..236004b --- /dev/null +++ b/drivers/firmware/efi/memattr.c @@ -0,0 +1,182 @@ +/* + * Copyright (C) 2016 Linaro Ltd. <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define pr_fmt(fmt) "efi: memattr: " fmt + +#include <linux/efi.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/memblock.h> + +#include <asm/early_ioremap.h> + +static int __initdata tbl_size; + +/* + * Reserve the memory associated with the Memory Attributes configuration + * table, if it exists. + */ +int __init efi_memattr_init(void) +{ + efi_memory_attributes_table_t *tbl; + + if (efi.mem_attr_table == EFI_INVALID_TABLE_ADDR) + return 0; + + tbl = early_memremap(efi.mem_attr_table, sizeof(*tbl)); + if (!tbl) { + pr_err("Failed to map EFI Memory Attributes table @ 0x%lx\n", + efi.mem_attr_table); + return -ENOMEM; + } + + if (tbl->version > 1) { + pr_warn("Unexpected EFI Memory Attributes table version %d\n", + tbl->version); + goto unmap; + } + + tbl_size = sizeof(*tbl) + tbl->num_entries * tbl->desc_size; + memblock_reserve(efi.mem_attr_table, tbl_size); + +unmap: + early_memunmap(tbl, sizeof(*tbl)); + return 0; +} + +/* + * Returns a copy @out of the UEFI memory descriptor @in if it is covered + * entirely by a UEFI memory map entry with matching attributes. The virtual + * address of @out is set according to the matching entry that was found. + */ +static bool entry_is_valid(const efi_memory_desc_t *in, efi_memory_desc_t *out) +{ + u64 in_paddr = in->phys_addr; + u64 in_size = in->num_pages << EFI_PAGE_SHIFT; + efi_memory_desc_t *md; + + *out = *in; + + if (in->type != EFI_RUNTIME_SERVICES_CODE && + in->type != EFI_RUNTIME_SERVICES_DATA) { + pr_warn("Entry type should be RuntimeServiceCode/Data\n"); + return false; + } + + if (!(in->attribute & (EFI_MEMORY_RO | EFI_MEMORY_XP))) { + pr_warn("Entry attributes invalid: RO and XP bits both cleared\n"); + return false; + } + + if (PAGE_SIZE > EFI_PAGE_SIZE && + (!PAGE_ALIGNED(in->phys_addr) || + !PAGE_ALIGNED(in->num_pages << EFI_PAGE_SHIFT))) { + /* + * Since arm64 may execute with page sizes of up to 64 KB, the + * UEFI spec mandates that RuntimeServices memory regions must + * be 64 KB aligned. We need to validate this here since we will + * not be able to tighten permissions on such regions without + * affecting adjacent regions. + */ + pr_warn("Entry address region misaligned\n"); + return false; + } + + for_each_efi_memory_desc(md) { + u64 md_paddr = md->phys_addr; + u64 md_size = md->num_pages << EFI_PAGE_SHIFT; + + if (!(md->attribute & EFI_MEMORY_RUNTIME)) + continue; + if (md->virt_addr == 0) { + /* no virtual mapping has been installed by the stub */ + break; + } + + if (md_paddr > in_paddr || (in_paddr - md_paddr) >= md_size) + continue; + + /* + * This entry covers the start of @in, check whether + * it covers the end as well. + */ + if (md_paddr + md_size < in_paddr + in_size) { + pr_warn("Entry covers multiple EFI memory map regions\n"); + return false; + } + + if (md->type != in->type) { + pr_warn("Entry type deviates from EFI memory map region type\n"); + return false; + } + + out->virt_addr = in_paddr + (md->virt_addr - md_paddr); + + return true; + } + + pr_warn("No matching entry found in the EFI memory map\n"); + return false; +} + +/* + * To be called after the EFI page tables have been populated. If a memory + * attributes table is available, its contents will be used to update the + * mappings with tightened permissions as described by the table. + * This requires the UEFI memory map to have already been populated with + * virtual addresses. + */ +int __init efi_memattr_apply_permissions(struct mm_struct *mm, + efi_memattr_perm_setter fn) +{ + efi_memory_attributes_table_t *tbl; + int i, ret; + + if (tbl_size <= sizeof(*tbl)) + return 0; + + /* + * We need the EFI memory map to be setup so we can use it to + * lookup the virtual addresses of all entries in the of EFI + * Memory Attributes table. If it isn't available, this + * function should not be called. + */ + if (WARN_ON(!efi_enabled(EFI_MEMMAP))) + return 0; + + tbl = memremap(efi.mem_attr_table, tbl_size, MEMREMAP_WB); + if (!tbl) { + pr_err("Failed to map EFI Memory Attributes table @ 0x%lx\n", + efi.mem_attr_table); + return -ENOMEM; + } + + if (efi_enabled(EFI_DBG)) + pr_info("Processing EFI Memory Attributes table:\n"); + + for (i = ret = 0; ret == 0 && i < tbl->num_entries; i++) { + efi_memory_desc_t md; + unsigned long size; + bool valid; + char buf[64]; + + valid = entry_is_valid((void *)tbl->entry + i * tbl->desc_size, + &md); + size = md.num_pages << EFI_PAGE_SHIFT; + if (efi_enabled(EFI_DBG) || !valid) + pr_info("%s 0x%012llx-0x%012llx %s\n", + valid ? "" : "!", md.phys_addr, + md.phys_addr + size - 1, + efi_md_typeattr_format(buf, sizeof(buf), &md)); + + if (valid) + ret = fn(mm, &md); + } + memunmap(tbl); + return ret; +} diff --git a/drivers/firmware/efi/reboot.c b/drivers/firmware/efi/reboot.c index 9c59d1c..62ead9b 100644 --- a/drivers/firmware/efi/reboot.c +++ b/drivers/firmware/efi/reboot.c @@ -9,7 +9,8 @@ int efi_reboot_quirk_mode = -1; void efi_reboot(enum reboot_mode reboot_mode, const char *__unused) { - int efi_mode; + const char *str[] = { "cold", "warm", "shutdown", "platform" }; + int efi_mode, cap_reset_mode; if (!efi_enabled(EFI_RUNTIME_SERVICES)) return; @@ -30,6 +31,15 @@ void efi_reboot(enum reboot_mode reboot_mode, const char *__unused) if (efi_reboot_quirk_mode != -1) efi_mode = efi_reboot_quirk_mode; + if (efi_capsule_pending(&cap_reset_mode)) { + if (efi_mode != cap_reset_mode) + printk(KERN_CRIT "efi: %s reset requested but pending " + "capsule update requires %s reset... Performing " + "%s reset.\n", str[efi_mode], str[cap_reset_mode], + str[cap_reset_mode]); + efi_mode = cap_reset_mode; + } + efi.reset_system(efi_mode, EFI_SUCCESS, 0, NULL); } diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index de69530..23bef6b 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -16,10 +16,70 @@ #include <linux/bug.h> #include <linux/efi.h> +#include <linux/irqflags.h> #include <linux/mutex.h> #include <linux/spinlock.h> +#include <linux/stringify.h> #include <asm/efi.h> +static void efi_call_virt_check_flags(unsigned long flags, const char *call) +{ + unsigned long cur_flags, mismatch; + + local_save_flags(cur_flags); + + mismatch = flags ^ cur_flags; + if (!WARN_ON_ONCE(mismatch & ARCH_EFI_IRQ_FLAGS_MASK)) + return; + + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_NOW_UNRELIABLE); + pr_err_ratelimited(FW_BUG "IRQ flags corrupted (0x%08lx=>0x%08lx) by EFI %s\n", + flags, cur_flags, call); + local_irq_restore(flags); +} + +/* + * Arch code can implement the following three template macros, avoiding + * reptition for the void/non-void return cases of {__,}efi_call_virt: + * + * * arch_efi_call_virt_setup + * + * Sets up the environment for the call (e.g. switching page tables, + * allowing kernel-mode use of floating point, if required). + * + * * arch_efi_call_virt + * + * Performs the call. The last expression in the macro must be the call + * itself, allowing the logic to be shared by the void and non-void + * cases. + * + * * arch_efi_call_virt_teardown + * + * Restores the usual kernel environment once the call has returned. + */ + +#define efi_call_virt(f, args...) \ +({ \ + efi_status_t __s; \ + unsigned long flags; \ + arch_efi_call_virt_setup(); \ + local_save_flags(flags); \ + __s = arch_efi_call_virt(f, args); \ + efi_call_virt_check_flags(flags, __stringify(f)); \ + arch_efi_call_virt_teardown(); \ + __s; \ +}) + +#define __efi_call_virt(f, args...) \ +({ \ + unsigned long flags; \ + arch_efi_call_virt_setup(); \ + local_save_flags(flags); \ + arch_efi_call_virt(f, args); \ + efi_call_virt_check_flags(flags, __stringify(f)); \ + arch_efi_call_virt_teardown(); \ +}) + /* * According to section 7.1 of the UEFI spec, Runtime Services are not fully * reentrant, and there are particular combinations of calls that need to be diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 34b7419..d3b7513 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -329,39 +329,6 @@ check_var_size_nonblocking(u32 attributes, unsigned long size) return fops->query_variable_store(attributes, size, true); } -static int efi_status_to_err(efi_status_t status) -{ - int err; - - switch (status) { - case EFI_SUCCESS: - err = 0; - break; - case EFI_INVALID_PARAMETER: - err = -EINVAL; - break; - case EFI_OUT_OF_RESOURCES: - err = -ENOSPC; - break; - case EFI_DEVICE_ERROR: - err = -EIO; - break; - case EFI_WRITE_PROTECTED: - err = -EROFS; - break; - case EFI_SECURITY_VIOLATION: - err = -EACCES; - break; - case EFI_NOT_FOUND: - err = -ENOENT; - break; - default: - err = -EINVAL; - } - - return err; -} - static bool variable_is_present(efi_char16_t *variable_name, efi_guid_t *vendor, struct list_head *head) { @@ -452,8 +419,7 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid, * Returns 0 on success, or a kernel error code on failure. */ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), - void *data, bool atomic, bool duplicates, - struct list_head *head) + void *data, bool duplicates, struct list_head *head) { const struct efivar_operations *ops = __efivars->ops; unsigned long variable_name_size = 1024; @@ -483,7 +449,7 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), &vendor_guid); switch (status) { case EFI_SUCCESS: - if (!atomic) + if (duplicates) spin_unlock_irq(&__efivars->lock); variable_name_size = var_name_strnsize(variable_name, @@ -498,21 +464,19 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), * and may end up looping here forever. */ if (duplicates && - variable_is_present(variable_name, &vendor_guid, head)) { + variable_is_present(variable_name, &vendor_guid, + head)) { dup_variable_bug(variable_name, &vendor_guid, variable_name_size); - if (!atomic) - spin_lock_irq(&__efivars->lock); - status = EFI_NOT_FOUND; - break; + } else { + err = func(variable_name, vendor_guid, + variable_name_size, data); + if (err) + status = EFI_NOT_FOUND; } - err = func(variable_name, vendor_guid, variable_name_size, data); - if (err) - status = EFI_NOT_FOUND; - - if (!atomic) + if (duplicates) spin_lock_irq(&__efivars->lock); break; diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c index 815c4a5..1b95475 100644 --- a/drivers/firmware/qemu_fw_cfg.c +++ b/drivers/firmware/qemu_fw_cfg.c @@ -77,7 +77,7 @@ static inline u16 fw_cfg_sel_endianness(u16 key) static inline void fw_cfg_read_blob(u16 key, void *buf, loff_t pos, size_t count) { - u32 glk; + u32 glk = -1U; acpi_status status; /* If we have ACPI, ensure mutual exclusion against any potential diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c index d9ab0cd..4d9a315 100644 --- a/drivers/gpio/gpio-rcar.c +++ b/drivers/gpio/gpio-rcar.c @@ -196,44 +196,6 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on) return 0; } -static void gpio_rcar_irq_bus_lock(struct irq_data *d) -{ - struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - struct gpio_rcar_priv *p = gpiochip_get_data(gc); - - pm_runtime_get_sync(&p->pdev->dev); -} - -static void gpio_rcar_irq_bus_sync_unlock(struct irq_data *d) -{ - struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - struct gpio_rcar_priv *p = gpiochip_get_data(gc); - - pm_runtime_put(&p->pdev->dev); -} - - -static int gpio_rcar_irq_request_resources(struct irq_data *d) -{ - struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - struct gpio_rcar_priv *p = gpiochip_get_data(gc); - int error; - - error = pm_runtime_get_sync(&p->pdev->dev); - if (error < 0) - return error; - - return 0; -} - -static void gpio_rcar_irq_release_resources(struct irq_data *d) -{ - struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - struct gpio_rcar_priv *p = gpiochip_get_data(gc); - - pm_runtime_put(&p->pdev->dev); -} - static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id) { struct gpio_rcar_priv *p = dev_id; @@ -280,32 +242,18 @@ static void gpio_rcar_config_general_input_output_mode(struct gpio_chip *chip, static int gpio_rcar_request(struct gpio_chip *chip, unsigned offset) { - struct gpio_rcar_priv *p = gpiochip_get_data(chip); - int error; - - error = pm_runtime_get_sync(&p->pdev->dev); - if (error < 0) - return error; - - error = pinctrl_request_gpio(chip->base + offset); - if (error) - pm_runtime_put(&p->pdev->dev); - - return error; + return pinctrl_request_gpio(chip->base + offset); } static void gpio_rcar_free(struct gpio_chip *chip, unsigned offset) { - struct gpio_rcar_priv *p = gpiochip_get_data(chip); - pinctrl_free_gpio(chip->base + offset); - /* Set the GPIO as an input to ensure that the next GPIO request won't + /* + * Set the GPIO as an input to ensure that the next GPIO request won't * drive the GPIO pin as an output. */ gpio_rcar_config_general_input_output_mode(chip, offset, false); - - pm_runtime_put(&p->pdev->dev); } static int gpio_rcar_direction_input(struct gpio_chip *chip, unsigned offset) @@ -452,6 +400,7 @@ static int gpio_rcar_probe(struct platform_device *pdev) } pm_runtime_enable(dev); + pm_runtime_get_sync(dev); io = platform_get_resource(pdev, IORESOURCE_MEM, 0); irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); @@ -488,10 +437,6 @@ static int gpio_rcar_probe(struct platform_device *pdev) irq_chip->irq_unmask = gpio_rcar_irq_enable; irq_chip->irq_set_type = gpio_rcar_irq_set_type; irq_chip->irq_set_wake = gpio_rcar_irq_set_wake; - irq_chip->irq_bus_lock = gpio_rcar_irq_bus_lock; - irq_chip->irq_bus_sync_unlock = gpio_rcar_irq_bus_sync_unlock; - irq_chip->irq_request_resources = gpio_rcar_irq_request_resources; - irq_chip->irq_release_resources = gpio_rcar_irq_release_resources; irq_chip->flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_MASK_ON_SUSPEND; ret = gpiochip_add_data(gpio_chip, p); @@ -522,6 +467,7 @@ static int gpio_rcar_probe(struct platform_device *pdev) err1: gpiochip_remove(gpio_chip); err0: + pm_runtime_put(dev); pm_runtime_disable(dev); return ret; } @@ -532,6 +478,7 @@ static int gpio_rcar_remove(struct platform_device *pdev) gpiochip_remove(&p->gpio_chip); + pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); return 0; } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 682070d..2dc5258 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -977,7 +977,7 @@ bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id) lookup = kmalloc(sizeof(*lookup), GFP_KERNEL); if (lookup) { lookup->adev = adev; - lookup->con_id = con_id; + lookup->con_id = kstrdup(con_id, GFP_KERNEL); list_add_tail(&lookup->node, &acpi_crs_lookup_list); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index e557fc1..7ecea83 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -541,6 +541,7 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, if (!metadata_size) { if (bo->metadata_size) { kfree(bo->metadata); + bo->metadata = NULL; bo->metadata_size = 0; } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c index bf731e9..7f85c2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c @@ -276,8 +276,8 @@ static int amdgpu_atombios_dp_get_dp_link_config(struct drm_connector *connector } } } else { - for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { - for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { + for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; if (max_pix_clock >= pix_clock) { *dp_lanes = lane_num; diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index 1e0bba2..1cd6de5 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -298,6 +298,10 @@ bool amdgpu_atombios_encoder_mode_fixup(struct drm_encoder *encoder, && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2))) adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2; + /* vertical FP must be at least 1 */ + if (mode->crtc_vsync_start == mode->crtc_vdisplay) + adjusted_mode->crtc_vsync_start++; + /* get the native mode for scaling */ if (amdgpu_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) amdgpu_panel_mode_fixup(encoder, adjusted_mode); diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index 6743ff7..059f7c3 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -72,7 +72,7 @@ drm_clflush_pages(struct page *pages[], unsigned long num_pages) { #if defined(CONFIG_X86) - if (cpu_has_clflush) { + if (static_cpu_has(X86_FEATURE_CLFLUSH)) { drm_cache_flush_clflush(pages, num_pages); return; } @@ -105,7 +105,7 @@ void drm_clflush_sg(struct sg_table *st) { #if defined(CONFIG_X86) - if (cpu_has_clflush) { + if (static_cpu_has(X86_FEATURE_CLFLUSH)) { struct sg_page_iter sg_iter; mb(); @@ -129,7 +129,7 @@ void drm_clflush_virt_range(void *addr, unsigned long length) { #if defined(CONFIG_X86) - if (cpu_has_clflush) { + if (static_cpu_has(X86_FEATURE_CLFLUSH)) { const int size = boot_cpu_data.x86_clflush_size; void *end = addr + length; addr = (void *)(((unsigned long)addr) & -size); diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index a0f1bd7..e3f4c72 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -2872,20 +2872,6 @@ static void intel_dp_info(struct seq_file *m, intel_panel_info(m, &intel_connector->panel); } -static void intel_dp_mst_info(struct seq_file *m, - struct intel_connector *intel_connector) -{ - struct intel_encoder *intel_encoder = intel_connector->encoder; - struct intel_dp_mst_encoder *intel_mst = - enc_to_mst(&intel_encoder->base); - struct intel_digital_port *intel_dig_port = intel_mst->primary; - struct intel_dp *intel_dp = &intel_dig_port->dp; - bool has_audio = drm_dp_mst_port_has_audio(&intel_dp->mst_mgr, - intel_connector->port); - - seq_printf(m, "\taudio support: %s\n", yesno(has_audio)); -} - static void intel_hdmi_info(struct seq_file *m, struct intel_connector *intel_connector) { @@ -2929,8 +2915,6 @@ static void intel_connector_info(struct seq_file *m, intel_hdmi_info(m, intel_connector); else if (intel_encoder->type == INTEL_OUTPUT_LVDS) intel_lvds_info(m, intel_connector); - else if (intel_encoder->type == INTEL_OUTPUT_DP_MST) - intel_dp_mst_info(m, intel_connector); } seq_printf(m, "\tmodes:\n"); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 30798cb..6d2fb3f 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -792,7 +792,7 @@ static int i915_drm_resume(struct drm_device *dev) static int i915_drm_resume_early(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - int ret = 0; + int ret; /* * We have a resume ordering issue with the snd-hda driver also @@ -803,6 +803,36 @@ static int i915_drm_resume_early(struct drm_device *dev) * FIXME: This should be solved with a special hdmi sink device or * similar so that power domains can be employed. */ + + /* + * Note that we need to set the power state explicitly, since we + * powered off the device during freeze and the PCI core won't power + * it back up for us during thaw. Powering off the device during + * freeze is not a hard requirement though, and during the + * suspend/resume phases the PCI core makes sure we get here with the + * device powered on. So in case we change our freeze logic and keep + * the device powered we can also remove the following set power state + * call. + */ + ret = pci_set_power_state(dev->pdev, PCI_D0); + if (ret) { + DRM_ERROR("failed to set PCI D0 power state (%d)\n", ret); + goto out; + } + + /* + * Note that pci_enable_device() first enables any parent bridge + * device and only then sets the power state for this device. The + * bridge enabling is a nop though, since bridge devices are resumed + * first. The order of enabling power and enabling the device is + * imposed by the PCI core as described above, so here we preserve the + * same order for the freeze/thaw phases. + * + * TODO: eventually we should remove pci_disable_device() / + * pci_enable_enable_device() from suspend/resume. Due to how they + * depend on the device enable refcount we can't anyway depend on them + * disabling/enabling the device. + */ if (pci_enable_device(dev->pdev)) { ret = -EIO; goto out; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index dabc089..f2cb9a9 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1732,7 +1732,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, if (args->flags & ~(I915_MMAP_WC)) return -EINVAL; - if (args->flags & I915_MMAP_WC && !cpu_has_pat) + if (args->flags & I915_MMAP_WC && !boot_cpu_has(X86_FEATURE_PAT)) return -ENODEV; obj = drm_gem_object_lookup(dev, file, args->handle); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 1328bc5..b845f46 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -488,7 +488,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, ret = relocate_entry_cpu(obj, reloc, target_offset); else if (obj->map_and_fenceable) ret = relocate_entry_gtt(obj, reloc, target_offset); - else if (cpu_has_clflush) + else if (static_cpu_has(X86_FEATURE_CLFLUSH)) ret = relocate_entry_clflush(obj, reloc, target_offset); else { WARN_ONCE(1, "Impossible case in relocation handling\n"); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index f76cbf3..363bd79 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2907,7 +2907,14 @@ enum skl_disp_power_wells { #define GEN6_RP_STATE_CAP _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998) #define BXT_RP_STATE_CAP _MMIO(0x138170) -#define INTERVAL_1_28_US(us) (((us) * 100) >> 7) +/* + * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS + * 8300) freezing up around GPU hangs. Looks as if even + * scheduling/timer interrupts start misbehaving if the RPS + * EI/thresholds are "bad", leading to a very sluggish or even + * frozen machine. + */ +#define INTERVAL_1_28_US(us) roundup(((us) * 100) >> 7, 25) #define INTERVAL_1_33_US(us) (((us) * 3) >> 2) #define INTERVAL_0_833_US(us) (((us) * 6) / 5) #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \ @@ -7437,6 +7444,8 @@ enum skl_disp_power_wells { #define TRANS_CLK_SEL_DISABLED (0x0<<29) #define TRANS_CLK_SEL_PORT(x) (((x)+1)<<29) +#define CDCLK_FREQ _MMIO(0x46200) + #define _TRANSA_MSA_MISC 0x60410 #define _TRANSB_MSA_MISC 0x61410 #define _TRANSC_MSA_MISC 0x62410 diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 30f9214..7d281b4 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -262,8 +262,7 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder) tmp |= AUD_CONFIG_N_PROG_ENABLE; tmp &= ~AUD_CONFIG_UPPER_N_MASK; tmp &= ~AUD_CONFIG_LOWER_N_MASK; - if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT) || - intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DP_MST)) + if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT)) tmp |= AUD_CONFIG_N_VALUE_INDEX; I915_WRITE(HSW_AUD_CFG(pipe), tmp); @@ -476,8 +475,7 @@ static void ilk_audio_codec_enable(struct drm_connector *connector, tmp &= ~AUD_CONFIG_N_VALUE_INDEX; tmp &= ~AUD_CONFIG_N_PROG_ENABLE; tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK; - if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT) || - intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DP_MST)) + if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT)) tmp |= AUD_CONFIG_N_VALUE_INDEX; else tmp |= audio_config_hdmi_pixel_clock(adjusted_mode); @@ -515,8 +513,7 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder) /* ELD Conn_Type */ connector->eld[5] &= ~(3 << 2); - if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT) || - intel_pipe_has_type(crtc, INTEL_OUTPUT_DP_MST)) + if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) connector->eld[5] |= (1 << 2); connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2; diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 505fc5c..0364292 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -257,8 +257,14 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder, pipe_config->has_pch_encoder = true; /* LPT FDI RX only supports 8bpc. */ - if (HAS_PCH_LPT(dev)) + if (HAS_PCH_LPT(dev)) { + if (pipe_config->bw_constrained && pipe_config->pipe_bpp < 24) { + DRM_DEBUG_KMS("LPT only supports 24bpp\n"); + return false; + } + pipe_config->pipe_bpp = 24; + } /* FDI must always be 2.7 GHz */ if (HAS_DDI(dev)) { diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 62de9f4..96ffcc5 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -443,9 +443,17 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) } else if (IS_BROADWELL(dev_priv)) { ddi_translations_fdi = bdw_ddi_translations_fdi; ddi_translations_dp = bdw_ddi_translations_dp; - ddi_translations_edp = bdw_ddi_translations_edp; + + if (dev_priv->edp_low_vswing) { + ddi_translations_edp = bdw_ddi_translations_edp; + n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); + } else { + ddi_translations_edp = bdw_ddi_translations_dp; + n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); + } + ddi_translations_hdmi = bdw_ddi_translations_hdmi; - n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); + n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); hdmi_default_entry = 7; @@ -3098,23 +3106,6 @@ void intel_ddi_fdi_disable(struct drm_crtc *crtc) I915_WRITE(FDI_RX_CTL(PIPE_A), val); } -bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv, - struct intel_crtc *intel_crtc) -{ - u32 temp; - - if (intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_AUDIO)) { - temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); - - intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO); - - if (temp & AUDIO_OUTPUT_ENABLE(intel_crtc->pipe)) - return true; - } - - return false; -} - void intel_ddi_get_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { @@ -3175,8 +3166,11 @@ void intel_ddi_get_config(struct intel_encoder *encoder, break; } - pipe_config->has_audio = - intel_ddi_is_audio_enabled(dev_priv, intel_crtc); + if (intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_AUDIO)) { + temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); + if (temp & AUDIO_OUTPUT_ENABLE(intel_crtc->pipe)) + pipe_config->has_audio = true; + } if (encoder->type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp_bpp && pipe_config->pipe_bpp > dev_priv->vbt.edp_bpp) { @@ -3201,12 +3195,6 @@ void intel_ddi_get_config(struct intel_encoder *encoder, intel_ddi_clock_get(encoder, pipe_config); } -static void intel_ddi_destroy(struct drm_encoder *encoder) -{ - /* HDMI has nothing special to destroy, so we can go with this. */ - intel_dp_encoder_destroy(encoder); -} - static bool intel_ddi_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { @@ -3225,7 +3213,8 @@ static bool intel_ddi_compute_config(struct intel_encoder *encoder, } static const struct drm_encoder_funcs intel_ddi_funcs = { - .destroy = intel_ddi_destroy, + .reset = intel_dp_encoder_reset, + .destroy = intel_dp_encoder_destroy, }; static struct intel_connector * @@ -3324,6 +3313,7 @@ void intel_ddi_init(struct drm_device *dev, enum port port) intel_encoder->post_disable = intel_ddi_post_disable; intel_encoder->get_hw_state = intel_ddi_get_hw_state; intel_encoder->get_config = intel_ddi_get_config; + intel_encoder->suspend = intel_dp_encoder_suspend; intel_dig_port->port = port; intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) & diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 6e0d828..0104a06 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -7988,9 +7988,6 @@ static void i9xx_get_pfit_config(struct intel_crtc *crtc, pipe_config->gmch_pfit.control = tmp; pipe_config->gmch_pfit.pgm_ratios = I915_READ(PFIT_PGM_RATIOS); - if (INTEL_INFO(dev)->gen < 5) - pipe_config->gmch_pfit.lvds_border_bits = - I915_READ(LVDS) & LVDS_BORDER_ENABLE; } static void vlv_crtc_clock_get(struct intel_crtc *crtc, @@ -9752,6 +9749,8 @@ static void broadwell_set_cdclk(struct drm_device *dev, int cdclk) sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ, data); mutex_unlock(&dev_priv->rps.hw_lock); + I915_WRITE(CDCLK_FREQ, DIV_ROUND_CLOSEST(cdclk, 1000) - 1); + intel_update_cdclk(dev); WARN(cdclk != dev_priv->cdclk_freq, @@ -13351,6 +13350,9 @@ static int intel_atomic_prepare_commit(struct drm_device *dev, } for_each_crtc_in_state(state, crtc, crtc_state, i) { + if (state->legacy_cursor_update) + continue; + ret = intel_crtc_wait_for_pending_flips(crtc); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index f069a82..412a34c 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -4898,7 +4898,7 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder) kfree(intel_dig_port); } -static void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) +void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base); @@ -4940,7 +4940,7 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp) edp_panel_vdd_schedule_off(intel_dp); } -static void intel_dp_encoder_reset(struct drm_encoder *encoder) +void intel_dp_encoder_reset(struct drm_encoder *encoder) { struct intel_dp *intel_dp; diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 937e772..2c99972 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -78,8 +78,6 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder, return false; } - if (drm_dp_mst_port_has_audio(&intel_dp->mst_mgr, found->port)) - pipe_config->has_audio = true; mst_pbn = drm_dp_calc_pbn_mode(adjusted_mode->crtc_clock, bpp); pipe_config->pbn = mst_pbn; @@ -104,11 +102,6 @@ static void intel_mst_disable_dp(struct intel_encoder *encoder) struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base); struct intel_digital_port *intel_dig_port = intel_mst->primary; struct intel_dp *intel_dp = &intel_dig_port->dp; - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_crtc *crtc = encoder->base.crtc; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int ret; DRM_DEBUG_KMS("%d\n", intel_dp->active_mst_links); @@ -119,10 +112,6 @@ static void intel_mst_disable_dp(struct intel_encoder *encoder) if (ret) { DRM_ERROR("failed to update payload %d\n", ret); } - if (intel_crtc->config->has_audio) { - intel_audio_codec_disable(encoder); - intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO); - } } static void intel_mst_post_disable_dp(struct intel_encoder *encoder) @@ -221,7 +210,6 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder) struct intel_dp *intel_dp = &intel_dig_port->dp; struct drm_device *dev = intel_dig_port->base.base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); enum port port = intel_dig_port->port; int ret; @@ -234,13 +222,6 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder) ret = drm_dp_check_act_status(&intel_dp->mst_mgr); ret = drm_dp_update_payload_part2(&intel_dp->mst_mgr); - - if (crtc->config->has_audio) { - DRM_DEBUG_DRIVER("Enabling DP audio on pipe %c\n", - pipe_name(crtc->pipe)); - intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO); - intel_audio_codec_enable(encoder); - } } static bool intel_dp_mst_enc_get_hw_state(struct intel_encoder *encoder, @@ -266,9 +247,6 @@ static void intel_dp_mst_enc_get_config(struct intel_encoder *encoder, pipe_config->has_dp_encoder = true; - pipe_config->has_audio = - intel_ddi_is_audio_enabled(dev_priv, crtc); - temp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder)); if (temp & TRANS_DDI_PHSYNC) flags |= DRM_MODE_FLAG_PHSYNC; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 4c027d6..9d0770c 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1019,8 +1019,6 @@ void intel_ddi_set_pipe_settings(struct drm_crtc *crtc); void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp); bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector); void intel_ddi_fdi_disable(struct drm_crtc *crtc); -bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv, - struct intel_crtc *intel_crtc); void intel_ddi_get_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config); struct intel_encoder * @@ -1238,6 +1236,8 @@ void intel_dp_set_link_params(struct intel_dp *intel_dp, void intel_dp_start_link_train(struct intel_dp *intel_dp); void intel_dp_stop_link_train(struct intel_dp *intel_dp); void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode); +void intel_dp_encoder_reset(struct drm_encoder *encoder); +void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder); void intel_dp_encoder_destroy(struct drm_encoder *encoder); int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc); bool intel_dp_compute_config(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index a0d8dae..1ab6f68 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1415,8 +1415,16 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) hdmi_to_dig_port(intel_hdmi)); } - if (!live_status) - DRM_DEBUG_KMS("Live status not up!"); + if (!live_status) { + DRM_DEBUG_KMS("HDMI live status down\n"); + /* + * Live status register is not reliable on all intel platforms. + * So consider live_status only for certain platforms, for + * others, read EDID to determine presence of sink. + */ + if (INTEL_INFO(dev_priv)->gen < 7 || IS_IVYBRIDGE(dev_priv)) + live_status = true; + } intel_hdmi_unset_edid(connector); diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index cd9fe60..10dc351 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -123,6 +123,10 @@ static void intel_lvds_get_config(struct intel_encoder *encoder, pipe_config->base.adjusted_mode.flags |= flags; + if (INTEL_INFO(dev)->gen < 5) + pipe_config->gmch_pfit.lvds_border_bits = + tmp & LVDS_BORDER_ENABLE; + /* gen2/3 store dither state in pfit control, needs to match */ if (INTEL_INFO(dev)->gen < 4) { tmp = I915_READ(PFIT_CONTROL); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 8ed3cf3..3425d8e 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -6646,6 +6646,12 @@ static void broadwell_init_clock_gating(struct drm_device *dev) misccpctl = I915_READ(GEN7_MISCCPCTL); I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE); I915_WRITE(GEN8_L3SQCREG1, BDW_WA_L3SQCREG1_DEFAULT); + /* + * Wait at least 100 clocks before re-enabling clock gating. See + * the definition of L3SQCREG1 in BSpec. + */ + POSTING_READ(GEN8_L3SQCREG1); + udelay(1); I915_WRITE(GEN7_MISCCPCTL, misccpctl); /* diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index b80b08f..532127c 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1742,6 +1742,7 @@ static u32 radeon_get_pll_use_mask(struct drm_crtc *crtc) static int radeon_get_shared_dp_ppll(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; + struct radeon_device *rdev = dev->dev_private; struct drm_crtc *test_crtc; struct radeon_crtc *test_radeon_crtc; @@ -1751,6 +1752,10 @@ static int radeon_get_shared_dp_ppll(struct drm_crtc *crtc) test_radeon_crtc = to_radeon_crtc(test_crtc); if (test_radeon_crtc->encoder && ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_radeon_crtc->encoder))) { + /* PPLL2 is exclusive to UNIPHYA on DCE61 */ + if (ASIC_IS_DCE61(rdev) && !ASIC_IS_DCE8(rdev) && + test_radeon_crtc->pll_id == ATOM_PPLL2) + continue; /* for DP use the same PLL for all */ if (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID) return test_radeon_crtc->pll_id; @@ -1772,6 +1777,7 @@ static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc) { struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); struct drm_device *dev = crtc->dev; + struct radeon_device *rdev = dev->dev_private; struct drm_crtc *test_crtc; struct radeon_crtc *test_radeon_crtc; u32 adjusted_clock, test_adjusted_clock; @@ -1787,6 +1793,10 @@ static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc) test_radeon_crtc = to_radeon_crtc(test_crtc); if (test_radeon_crtc->encoder && !ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_radeon_crtc->encoder))) { + /* PPLL2 is exclusive to UNIPHYA on DCE61 */ + if (ASIC_IS_DCE61(rdev) && !ASIC_IS_DCE8(rdev) && + test_radeon_crtc->pll_id == ATOM_PPLL2) + continue; /* check if we are already driving this connector with another crtc */ if (test_radeon_crtc->connector == radeon_crtc->connector) { /* if we are, return that pll */ diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index afa9db1..cead089a 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -326,8 +326,8 @@ int radeon_dp_get_dp_link_config(struct drm_connector *connector, } } } else { - for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { - for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { + for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; if (max_pix_clock >= pix_clock) { *dp_lanes = lane_num; diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index edd05cd..587cae4 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -310,6 +310,10 @@ static bool radeon_atom_mode_fixup(struct drm_encoder *encoder, && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2))) adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2; + /* vertical FP must be at least 1 */ + if (mode->crtc_vsync_start == mode->crtc_vdisplay) + adjusted_mode->crtc_vsync_start++; + /* get the native mode for scaling */ if (radeon_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) { radeon_panel_mode_fixup(encoder, adjusted_mode); diff --git a/drivers/gpu/drm/radeon/radeon_dp_auxch.c b/drivers/gpu/drm/radeon/radeon_dp_auxch.c index 3b0c229..db64e00 100644 --- a/drivers/gpu/drm/radeon/radeon_dp_auxch.c +++ b/drivers/gpu/drm/radeon/radeon_dp_auxch.c @@ -105,7 +105,7 @@ radeon_dp_aux_transfer_native(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg tmp &= AUX_HPD_SEL(0x7); tmp |= AUX_HPD_SEL(chan->rec.hpd); - tmp |= AUX_EN | AUX_LS_READ_EN; + tmp |= AUX_EN | AUX_LS_READ_EN | AUX_HPD_DISCON(0x1); WREG32(AUX_CONTROL + aux_offset[instance], tmp); diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index e00db3f..abb98c7 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -1068,7 +1068,6 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) goto err_register; } - pdev->dev.of_node = of_node; pdev->dev.parent = dev; ret = platform_device_add_data(pdev, ®->pdata, @@ -1079,6 +1078,12 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) platform_device_put(pdev); goto err_register; } + + /* + * Set of_node only after calling platform_device_add. Otherwise + * the platform:imx-ipuv3-crtc modalias won't be used. + */ + pdev->dev.of_node = of_node; } return 0; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index c6eaff5..0238f01 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -259,6 +259,7 @@ #define USB_DEVICE_ID_CORSAIR_K90 0x1b02 #define USB_VENDOR_ID_CREATIVELABS 0x041e +#define USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51 0x322c #define USB_DEVICE_ID_PRODIKEYS_PCMIDI 0x2801 #define USB_VENDOR_ID_CVTOUCH 0x1ff7 diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index ed2f68e..53fc856 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -71,6 +71,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_3AXIS_5BUTTON_STICK, HID_QUIRK_NOGET }, { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET }, { USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_ELAN, HID_ANY_ID, HID_QUIRK_ALWAYS_POLL }, diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 02c4efe..cf2ba43 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -684,6 +684,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) wacom->tool[idx] = wacom_intuos_get_tool_type(wacom->id[idx]); + wacom->shared->stylus_in_proximity = true; return 1; } @@ -3395,6 +3396,10 @@ static const struct wacom_features wacom_features_0x33E = { "Wacom Intuos PT M 2", 21600, 13500, 2047, 63, INTUOSHT2, WACOM_INTUOS_RES, WACOM_INTUOS_RES, .touch_max = 16, .check_for_hid_type = true, .hid_type = HID_TYPE_USBNONE }; +static const struct wacom_features wacom_features_0x343 = + { "Wacom DTK1651", 34616, 19559, 1023, 0, + DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4, + WACOM_DTU_OFFSET, WACOM_DTU_OFFSET }; static const struct wacom_features wacom_features_HID_ANY_ID = { "Wacom HID", .type = HID_GENERIC }; @@ -3560,6 +3565,7 @@ const struct hid_device_id wacom_ids[] = { { USB_DEVICE_WACOM(0x33C) }, { USB_DEVICE_WACOM(0x33D) }, { USB_DEVICE_WACOM(0x33E) }, + { USB_DEVICE_WACOM(0x343) }, { USB_DEVICE_WACOM(0x4001) }, { USB_DEVICE_WACOM(0x4004) }, { USB_DEVICE_WACOM(0x5000) }, diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 5613e2b..a40a73a 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -103,15 +103,29 @@ static bool hv_need_to_signal(u32 old_write, struct hv_ring_buffer_info *rbi) * there is room for the producer to send the pending packet. */ -static bool hv_need_to_signal_on_read(u32 prev_write_sz, - struct hv_ring_buffer_info *rbi) +static bool hv_need_to_signal_on_read(struct hv_ring_buffer_info *rbi) { u32 cur_write_sz; u32 r_size; - u32 write_loc = rbi->ring_buffer->write_index; + u32 write_loc; u32 read_loc = rbi->ring_buffer->read_index; - u32 pending_sz = rbi->ring_buffer->pending_send_sz; + u32 pending_sz; + /* + * Issue a full memory barrier before making the signaling decision. + * Here is the reason for having this barrier: + * If the reading of the pend_sz (in this function) + * were to be reordered and read before we commit the new read + * index (in the calling function) we could + * have a problem. If the host were to set the pending_sz after we + * have sampled pending_sz and go to sleep before we commit the + * read index, we could miss sending the interrupt. Issue a full + * memory barrier to address this. + */ + mb(); + + pending_sz = rbi->ring_buffer->pending_send_sz; + write_loc = rbi->ring_buffer->write_index; /* If the other end is not blocked on write don't bother. */ if (pending_sz == 0) return false; @@ -120,7 +134,7 @@ static bool hv_need_to_signal_on_read(u32 prev_write_sz, cur_write_sz = write_loc >= read_loc ? r_size - (write_loc - read_loc) : read_loc - write_loc; - if ((prev_write_sz < pending_sz) && (cur_write_sz >= pending_sz)) + if (cur_write_sz >= pending_sz) return true; return false; @@ -455,7 +469,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, /* Update the read index */ hv_set_next_read_location(inring_info, next_read_location); - *signal = hv_need_to_signal_on_read(bytes_avail_towrite, inring_info); + *signal = hv_need_to_signal_on_read(inring_info); return ret; } diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index dbee13a..2e154cb 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -451,6 +451,8 @@ static int at91_adc_probe(struct platform_device *pdev) if (ret) goto vref_disable; + platform_set_drvdata(pdev, indio_dev); + ret = iio_device_register(indio_dev); if (ret < 0) goto per_clk_disable_unprepare; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c index f581256..5ee4e0d 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c @@ -104,6 +104,19 @@ static int inv_mpu6050_deselect_bypass(struct i2c_adapter *adap, return 0; } +static const char *inv_mpu_match_acpi_device(struct device *dev, int *chip_id) +{ + const struct acpi_device_id *id; + + id = acpi_match_device(dev->driver->acpi_match_table, dev); + if (!id) + return NULL; + + *chip_id = (int)id->driver_data; + + return dev_name(dev); +} + /** * inv_mpu_probe() - probe function. * @client: i2c client. @@ -115,14 +128,25 @@ static int inv_mpu_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct inv_mpu6050_state *st; - int result; - const char *name = id ? id->name : NULL; + int result, chip_type; struct regmap *regmap; + const char *name; if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_I2C_BLOCK)) return -EOPNOTSUPP; + if (id) { + chip_type = (int)id->driver_data; + name = id->name; + } else if (ACPI_HANDLE(&client->dev)) { + name = inv_mpu_match_acpi_device(&client->dev, &chip_type); + if (!name) + return -ENODEV; + } else { + return -ENOSYS; + } + regmap = devm_regmap_init_i2c(client, &inv_mpu_regmap_config); if (IS_ERR(regmap)) { dev_err(&client->dev, "Failed to register i2c regmap %d\n", @@ -131,7 +155,7 @@ static int inv_mpu_probe(struct i2c_client *client, } result = inv_mpu_core_probe(regmap, client->irq, name, - NULL, id->driver_data); + NULL, chip_type); if (result < 0) return result; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c index dea6c43..7bcb8d8 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c @@ -46,6 +46,7 @@ static int inv_mpu_probe(struct spi_device *spi) struct regmap *regmap; const struct spi_device_id *id = spi_get_device_id(spi); const char *name = id ? id->name : NULL; + const int chip_type = id ? id->driver_data : 0; regmap = devm_regmap_init_spi(spi, &inv_mpu_regmap_config); if (IS_ERR(regmap)) { @@ -55,7 +56,7 @@ static int inv_mpu_probe(struct spi_device *spi) } return inv_mpu_core_probe(regmap, spi->irq, name, - inv_mpu_i2c_disable, id->driver_data); + inv_mpu_i2c_disable, chip_type); } static int inv_mpu_remove(struct spi_device *spi) diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index 9c5c9ef..0e931a9 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -462,6 +462,8 @@ static int ak8975_setup_irq(struct ak8975_data *data) int rc; int irq; + init_waitqueue_head(&data->data_ready_queue); + clear_bit(0, &data->flags); if (client->irq) irq = client->irq; else @@ -477,8 +479,6 @@ static int ak8975_setup_irq(struct ak8975_data *data) return rc; } - init_waitqueue_head(&data->data_ready_queue); - clear_bit(0, &data->flags); data->eoc_irq = irq; return rc; @@ -732,7 +732,7 @@ static int ak8975_probe(struct i2c_client *client, int eoc_gpio; int err; const char *name = NULL; - enum asahi_compass_chipset chipset; + enum asahi_compass_chipset chipset = AK_MAX_TYPE; /* Grab and set up the supplied GPIO. */ if (client->dev.platform_data) diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c index 80b6bed..64b3d11 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.c +++ b/drivers/infiniband/ulp/iser/iscsi_iser.c @@ -612,6 +612,7 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep, struct Scsi_Host *shost; struct iser_conn *iser_conn = NULL; struct ib_conn *ib_conn; + u32 max_fr_sectors; u16 max_cmds; shost = iscsi_host_alloc(&iscsi_iser_sht, 0, 0); @@ -632,7 +633,6 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep, iser_conn = ep->dd_data; max_cmds = iser_conn->max_cmds; shost->sg_tablesize = iser_conn->scsi_sg_tablesize; - shost->max_sectors = iser_conn->scsi_max_sectors; mutex_lock(&iser_conn->state_mutex); if (iser_conn->state != ISER_CONN_UP) { @@ -657,8 +657,6 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep, */ shost->sg_tablesize = min_t(unsigned short, shost->sg_tablesize, ib_conn->device->ib_device->attrs.max_fast_reg_page_list_len); - shost->max_sectors = min_t(unsigned int, - 1024, (shost->sg_tablesize * PAGE_SIZE) >> 9); if (iscsi_host_add(shost, ib_conn->device->ib_device->dma_device)) { @@ -672,6 +670,15 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep, goto free_host; } + /* + * FRs or FMRs can only map up to a (device) page per entry, but if the + * first entry is misaligned we'll end up using using two entries + * (head and tail) for a single page worth data, so we have to drop + * one segment from the calculation. + */ + max_fr_sectors = ((shost->sg_tablesize - 1) * PAGE_SIZE) >> 9; + shost->max_sectors = min(iser_max_sectors, max_fr_sectors); + if (cmds_max > max_cmds) { iser_info("cmds_max changed from %u to %u\n", cmds_max, max_cmds); @@ -989,7 +996,6 @@ static struct scsi_host_template iscsi_iser_sht = { .queuecommand = iscsi_queuecommand, .change_queue_depth = scsi_change_queue_depth, .sg_tablesize = ISCSI_ISER_DEF_SG_TABLESIZE, - .max_sectors = ISER_DEF_MAX_SECTORS, .cmd_per_lun = ISER_DEF_CMD_PER_LUN, .eh_abort_handler = iscsi_eh_abort, .eh_device_reset_handler= iscsi_eh_device_reset, diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c index 6f8b084..3d8ff09 100644 --- a/drivers/input/joystick/analog.c +++ b/drivers/input/joystick/analog.c @@ -143,9 +143,9 @@ struct analog_port { #include <linux/i8253.h> -#define GET_TIME(x) do { if (cpu_has_tsc) x = (unsigned int)rdtsc(); else x = get_time_pit(); } while (0) -#define DELTA(x,y) (cpu_has_tsc ? ((y) - (x)) : ((x) - (y) + ((x) < (y) ? PIT_TICK_RATE / HZ : 0))) -#define TIME_NAME (cpu_has_tsc?"TSC":"PIT") +#define GET_TIME(x) do { if (boot_cpu_has(X86_FEATURE_TSC)) x = (unsigned int)rdtsc(); else x = get_time_pit(); } while (0) +#define DELTA(x,y) (boot_cpu_has(X86_FEATURE_TSC) ? ((y) - (x)) : ((x) - (y) + ((x) < (y) ? PIT_TICK_RATE / HZ : 0))) +#define TIME_NAME (boot_cpu_has(X86_FEATURE_TSC)?"TSC":"PIT") static unsigned int get_time_pit(void) { unsigned long flags; diff --git a/drivers/input/misc/max8997_haptic.c b/drivers/input/misc/max8997_haptic.c index a806ba3..8d6326d 100644 --- a/drivers/input/misc/max8997_haptic.c +++ b/drivers/input/misc/max8997_haptic.c @@ -255,12 +255,14 @@ static int max8997_haptic_probe(struct platform_device *pdev) struct max8997_dev *iodev = dev_get_drvdata(pdev->dev.parent); const struct max8997_platform_data *pdata = dev_get_platdata(iodev->dev); - const struct max8997_haptic_platform_data *haptic_pdata = - pdata->haptic_pdata; + const struct max8997_haptic_platform_data *haptic_pdata = NULL; struct max8997_haptic *chip; struct input_dev *input_dev; int error; + if (pdata) + haptic_pdata = pdata->haptic_pdata; + if (!haptic_pdata) { dev_err(&pdev->dev, "no haptic platform data\n"); return -EINVAL; diff --git a/drivers/input/misc/twl6040-vibra.c b/drivers/input/misc/twl6040-vibra.c index 53e33fa..42de34b 100644 --- a/drivers/input/misc/twl6040-vibra.c +++ b/drivers/input/misc/twl6040-vibra.c @@ -181,6 +181,14 @@ static void vibra_play_work(struct work_struct *work) { struct vibra_info *info = container_of(work, struct vibra_info, play_work); + int ret; + + /* Do not allow effect, while the routing is set to use audio */ + ret = twl6040_get_vibralr_status(info->twl6040); + if (ret & TWL6040_VIBSEL) { + dev_info(info->dev, "Vibra is configured for audio\n"); + return; + } mutex_lock(&info->mutex); @@ -199,14 +207,6 @@ static int vibra_play(struct input_dev *input, void *data, struct ff_effect *effect) { struct vibra_info *info = input_get_drvdata(input); - int ret; - - /* Do not allow effect, while the routing is set to use audio */ - ret = twl6040_get_vibralr_status(info->twl6040); - if (ret & TWL6040_VIBSEL) { - dev_info(&input->dev, "Vibra is configured for audio\n"); - return -EBUSY; - } info->weak_speed = effect->u.rumble.weak_magnitude; info->strong_speed = effect->u.rumble.strong_magnitude; @@ -257,6 +257,7 @@ static int twl6040_vibra_probe(struct platform_device *pdev) int vddvibr_uV = 0; int error; + of_node_get(twl6040_core_dev->of_node); twl6040_core_node = of_find_node_by_name(twl6040_core_dev->of_node, "vibra"); if (!twl6040_core_node) { diff --git a/drivers/input/mouse/byd.c b/drivers/input/mouse/byd.c index fdc243c..e583f8b 100644 --- a/drivers/input/mouse/byd.c +++ b/drivers/input/mouse/byd.c @@ -2,6 +2,10 @@ * BYD TouchPad PS/2 mouse driver * * Copyright (C) 2015 Chris Diamand <chris@diamand.org> + * Copyright (C) 2015 Richard Pospesel + * Copyright (C) 2015 Tai Chi Minh Ralph Eastwood + * Copyright (C) 2015 Martin Wimpress + * Copyright (C) 2015 Jay Kuri * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published by diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index 2160512..5af7907 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -1093,6 +1093,19 @@ static int mxt_t6_command(struct mxt_data *data, u16 cmd_offset, return 0; } +static int mxt_acquire_irq(struct mxt_data *data) +{ + int error; + + enable_irq(data->irq); + + error = mxt_process_messages_until_invalid(data); + if (error) + return error; + + return 0; +} + static int mxt_soft_reset(struct mxt_data *data) { struct device *dev = &data->client->dev; @@ -1111,7 +1124,7 @@ static int mxt_soft_reset(struct mxt_data *data) /* Ignore CHG line for 100ms after reset */ msleep(100); - enable_irq(data->irq); + mxt_acquire_irq(data); ret = mxt_wait_for_completion(data, &data->reset_completion, MXT_RESET_TIMEOUT); @@ -1466,19 +1479,6 @@ release_mem: return ret; } -static int mxt_acquire_irq(struct mxt_data *data) -{ - int error; - - enable_irq(data->irq); - - error = mxt_process_messages_until_invalid(data); - if (error) - return error; - - return 0; -} - static int mxt_get_info(struct mxt_data *data) { struct i2c_client *client = data->client; diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c index 9bbadaa..7b3845a 100644 --- a/drivers/input/touchscreen/zforce_ts.c +++ b/drivers/input/touchscreen/zforce_ts.c @@ -370,8 +370,8 @@ static int zforce_touch_event(struct zforce_ts *ts, u8 *payload) point.coord_x = point.coord_y = 0; } - point.state = payload[9 * i + 5] & 0x03; - point.id = (payload[9 * i + 5] & 0xfc) >> 2; + point.state = payload[9 * i + 5] & 0x0f; + point.id = (payload[9 * i + 5] & 0xf0) >> 4; /* determine touch major, minor and orientation */ point.area_major = max(payload[9 * i + 6], diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 8adaaea..49721b4 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -36,7 +36,7 @@ static void irq_remapping_disable_io_apic(void) * As this gets called during crash dump, keep this simple for * now. */ - if (cpu_has_apic || apic_from_smp_config()) + if (boot_cpu_has(X86_FEATURE_APIC) || apic_from_smp_config()) disconnect_bsp_APIC(0); } diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c index adc162c..6e9042e 100644 --- a/drivers/lguest/x86/core.c +++ b/drivers/lguest/x86/core.c @@ -603,7 +603,7 @@ void __init lguest_arch_host_init(void) * doing this. */ get_online_cpus(); - if (cpu_has_pge) { /* We have a broader idea of "global". */ + if (boot_cpu_has(X86_FEATURE_PGE)) { /* We have a broader idea of "global". */ /* Remember that this was originally set (for cleanup). */ cpu_had_pge = 1; /* diff --git a/drivers/md/md.c b/drivers/md/md.c index 194580f..14d3b37 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -284,6 +284,8 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) * go away inside make_request */ sectors = bio_sectors(bio); + /* bio could be mergeable after passing to underlayer */ + bio->bi_rw &= ~REQ_NOMERGE; mddev->pers->make_request(mddev, bio); cpu = part_stat_lock(); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 2ea12c6..34783a3 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -70,7 +70,6 @@ static void dump_zones(struct mddev *mddev) (unsigned long long)zone_size>>1); zone_start = conf->strip_zone[j].zone_end; } - printk(KERN_INFO "\n"); } static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) @@ -85,6 +84,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL); unsigned short blksize = 512; + *private_conf = ERR_PTR(-ENOMEM); if (!conf) return -ENOMEM; rdev_for_each(rdev1, mddev) { diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 8ab8b65..e48c262 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3502,8 +3502,6 @@ returnbi: dev = &sh->dev[i]; } else if (test_bit(R5_Discard, &dev->flags)) discard_pending = 1; - WARN_ON(test_bit(R5_SkipCopy, &dev->flags)); - WARN_ON(dev->page != dev->orig_page); } r5l_stripe_write_finished(sh); diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index 6e43c95..3cfd7af 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -846,11 +846,11 @@ struct media_device *media_device_find_devres(struct device *dev) } EXPORT_SYMBOL_GPL(media_device_find_devres); +#if IS_ENABLED(CONFIG_PCI) void media_device_pci_init(struct media_device *mdev, struct pci_dev *pci_dev, const char *name) { -#ifdef CONFIG_PCI mdev->dev = &pci_dev->dev; if (name) @@ -866,16 +866,16 @@ void media_device_pci_init(struct media_device *mdev, mdev->driver_version = LINUX_VERSION_CODE; media_device_init(mdev); -#endif } EXPORT_SYMBOL_GPL(media_device_pci_init); +#endif +#if IS_ENABLED(CONFIG_USB) void __media_device_usb_init(struct media_device *mdev, struct usb_device *udev, const char *board_name, const char *driver_name) { -#ifdef CONFIG_USB mdev->dev = &udev->dev; if (driver_name) @@ -895,9 +895,9 @@ void __media_device_usb_init(struct media_device *mdev, mdev->driver_version = LINUX_VERSION_CODE; media_device_init(mdev); -#endif } EXPORT_SYMBOL_GPL(__media_device_usb_init); +#endif #endif /* CONFIG_MEDIA_CONTROLLER */ diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c index feb521f..4f494ac 100644 --- a/drivers/media/platform/exynos4-is/media-dev.c +++ b/drivers/media/platform/exynos4-is/media-dev.c @@ -1446,22 +1446,13 @@ static int fimc_md_probe(struct platform_device *pdev) platform_set_drvdata(pdev, fmd); - /* Protect the media graph while we're registering entities */ - mutex_lock(&fmd->media_dev.graph_mutex); - ret = fimc_md_register_platform_entities(fmd, dev->of_node); - if (ret) { - mutex_unlock(&fmd->media_dev.graph_mutex); + if (ret) goto err_clk; - } ret = fimc_md_register_sensor_entities(fmd); - if (ret) { - mutex_unlock(&fmd->media_dev.graph_mutex); + if (ret) goto err_m_ent; - } - - mutex_unlock(&fmd->media_dev.graph_mutex); ret = device_create_file(&pdev->dev, &dev_attr_subdev_conf_mode); if (ret) diff --git a/drivers/media/platform/s3c-camif/camif-core.c b/drivers/media/platform/s3c-camif/camif-core.c index 0b44b9a..af237af 100644 --- a/drivers/media/platform/s3c-camif/camif-core.c +++ b/drivers/media/platform/s3c-camif/camif-core.c @@ -493,21 +493,17 @@ static int s3c_camif_probe(struct platform_device *pdev) if (ret < 0) goto err_sens; - mutex_lock(&camif->media_dev.graph_mutex); - ret = v4l2_device_register_subdev_nodes(&camif->v4l2_dev); if (ret < 0) - goto err_unlock; + goto err_sens; ret = camif_register_video_nodes(camif); if (ret < 0) - goto err_unlock; + goto err_sens; ret = camif_create_media_links(camif); if (ret < 0) - goto err_unlock; - - mutex_unlock(&camif->media_dev.graph_mutex); + goto err_sens; ret = media_device_register(&camif->media_dev); if (ret < 0) @@ -516,8 +512,6 @@ static int s3c_camif_probe(struct platform_device *pdev) pm_runtime_put(dev); return 0; -err_unlock: - mutex_unlock(&camif->media_dev.graph_mutex); err_sens: v4l2_device_unregister(&camif->v4l2_dev); media_device_unregister(&camif->media_dev); diff --git a/drivers/media/v4l2-core/videobuf2-v4l2.c b/drivers/media/v4l2-core/videobuf2-v4l2.c index 7f366f1..0b1b8c7 100644 --- a/drivers/media/v4l2-core/videobuf2-v4l2.c +++ b/drivers/media/v4l2-core/videobuf2-v4l2.c @@ -74,11 +74,6 @@ static int __verify_planes_array(struct vb2_buffer *vb, const struct v4l2_buffer return 0; } -static int __verify_planes_array_core(struct vb2_buffer *vb, const void *pb) -{ - return __verify_planes_array(vb, pb); -} - /** * __verify_length() - Verify that the bytesused value for each plane fits in * the plane length and that the data offset doesn't exceed the bytesused value. @@ -442,7 +437,6 @@ static int __fill_vb2_buffer(struct vb2_buffer *vb, } static const struct vb2_buf_ops v4l2_buf_ops = { - .verify_planes_array = __verify_planes_array_core, .fill_user_buffer = __fill_v4l2_buffer, .fill_vb2_buffer = __fill_vb2_buffer, .copy_timestamp = __copy_timestamp, diff --git a/drivers/misc/mic/vop/vop_vringh.c b/drivers/misc/mic/vop/vop_vringh.c index e94c7fb..88e4523 100644 --- a/drivers/misc/mic/vop/vop_vringh.c +++ b/drivers/misc/mic/vop/vop_vringh.c @@ -945,6 +945,11 @@ static long vop_ioctl(struct file *f, unsigned int cmd, unsigned long arg) ret = -EFAULT; goto free_ret; } + /* Ensure desc has not changed between the two reads */ + if (memcmp(&dd, dd_config, sizeof(dd))) { + ret = -EINVAL; + goto free_ret; + } mutex_lock(&vdev->vdev_mutex); mutex_lock(&vi->vop_mutex); ret = vop_virtio_add_device(vdev, dd_config); diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index a290402..5e572b3 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -2181,7 +2181,7 @@ int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *bridge) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - int i, err; + int i, err = 0; mutex_lock(&ps->smi_mutex); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_cle.c b/drivers/net/ethernet/apm/xgene/xgene_enet_cle.c index b2124886..11be804 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_cle.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_cle.c @@ -43,6 +43,7 @@ static void xgene_cle_idt_to_hw(u32 dstqid, u32 fpsel, static void xgene_cle_dbptr_to_hw(struct xgene_enet_pdata *pdata, struct xgene_cle_dbptr *dbptr, u32 *buf) { + buf[0] = SET_VAL(CLE_DROP, dbptr->drop); buf[4] = SET_VAL(CLE_FPSEL, dbptr->fpsel) | SET_VAL(CLE_DSTQIDL, dbptr->dstqid); @@ -412,7 +413,7 @@ static int xgene_enet_cle_init(struct xgene_enet_pdata *pdata) .branch = { { /* IPV4 */ - .valid = 0, + .valid = 1, .next_packet_pointer = 22, .jump_bw = JMP_FW, .jump_rel = JMP_ABS, @@ -420,7 +421,7 @@ static int xgene_enet_cle_init(struct xgene_enet_pdata *pdata) .next_node = PKT_PROT_NODE, .next_branch = 0, .data = 0x8, - .mask = 0xffff + .mask = 0x0 }, { .valid = 0, @@ -456,7 +457,7 @@ static int xgene_enet_cle_init(struct xgene_enet_pdata *pdata) .next_node = RSS_IPV4_TCP_NODE, .next_branch = 0, .data = 0x0600, - .mask = 0xffff + .mask = 0x00ff }, { /* UDP */ @@ -468,7 +469,7 @@ static int xgene_enet_cle_init(struct xgene_enet_pdata *pdata) .next_node = RSS_IPV4_UDP_NODE, .next_branch = 0, .data = 0x1100, - .mask = 0xffff + .mask = 0x00ff }, { .valid = 0, @@ -642,7 +643,7 @@ static int xgene_enet_cle_init(struct xgene_enet_pdata *pdata) { /* TCP DST Port */ .valid = 0, - .next_packet_pointer = 256, + .next_packet_pointer = 258, .jump_bw = JMP_FW, .jump_rel = JMP_ABS, .operation = EQT, diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_cle.h b/drivers/net/ethernet/apm/xgene/xgene_enet_cle.h index 29a17ab..3bf9068 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_cle.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_cle.h @@ -83,6 +83,8 @@ #define CLE_TYPE_POS 0 #define CLE_TYPE_LEN 2 +#define CLE_DROP_POS 28 +#define CLE_DROP_LEN 1 #define CLE_DSTQIDL_POS 25 #define CLE_DSTQIDL_LEN 7 #define CLE_DSTQIDH_POS 0 diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 39e081a..513d2a6 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -219,27 +219,30 @@ void xgene_enet_parse_error(struct xgene_enet_desc_ring *ring, struct xgene_enet_pdata *pdata, enum xgene_enet_err_code status) { - struct rtnl_link_stats64 *stats = &pdata->stats; - switch (status) { case INGRESS_CRC: - stats->rx_crc_errors++; + ring->rx_crc_errors++; + ring->rx_dropped++; break; case INGRESS_CHECKSUM: case INGRESS_CHECKSUM_COMPUTE: - stats->rx_errors++; + ring->rx_errors++; + ring->rx_dropped++; break; case INGRESS_TRUNC_FRAME: - stats->rx_frame_errors++; + ring->rx_frame_errors++; + ring->rx_dropped++; break; case INGRESS_PKT_LEN: - stats->rx_length_errors++; + ring->rx_length_errors++; + ring->rx_dropped++; break; case INGRESS_PKT_UNDER: - stats->rx_frame_errors++; + ring->rx_frame_errors++; + ring->rx_dropped++; break; case INGRESS_FIFO_OVERRUN: - stats->rx_fifo_errors++; + ring->rx_fifo_errors++; break; default: break; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h index ba7da98..45220be 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h @@ -86,7 +86,7 @@ enum xgene_enet_rm { #define RINGADDRL_POS 5 #define RINGADDRL_LEN 27 #define RINGADDRH_POS 0 -#define RINGADDRH_LEN 6 +#define RINGADDRH_LEN 7 #define RINGSIZE_POS 23 #define RINGSIZE_LEN 3 #define RINGTYPE_POS 19 @@ -94,9 +94,9 @@ enum xgene_enet_rm { #define RINGMODE_POS 20 #define RINGMODE_LEN 3 #define RECOMTIMEOUTL_POS 28 -#define RECOMTIMEOUTL_LEN 3 +#define RECOMTIMEOUTL_LEN 4 #define RECOMTIMEOUTH_POS 0 -#define RECOMTIMEOUTH_LEN 2 +#define RECOMTIMEOUTH_LEN 3 #define NUMMSGSINQ_POS 1 #define NUMMSGSINQ_LEN 16 #define ACCEPTLERR BIT(19) @@ -201,6 +201,8 @@ enum xgene_enet_rm { #define USERINFO_LEN 32 #define FPQNUM_POS 32 #define FPQNUM_LEN 12 +#define ELERR_POS 46 +#define ELERR_LEN 2 #define NV_POS 50 #define NV_LEN 1 #define LL_POS 51 diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 8d4c1ad..fd20088 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -443,8 +443,8 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb, skb_tx_timestamp(skb); - pdata->stats.tx_packets++; - pdata->stats.tx_bytes += skb->len; + tx_ring->tx_packets++; + tx_ring->tx_bytes += skb->len; pdata->ring_ops->wr_cmd(tx_ring, count); return NETDEV_TX_OK; @@ -483,12 +483,12 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, skb = buf_pool->rx_skb[skb_index]; /* checking for error */ - status = GET_VAL(LERR, le64_to_cpu(raw_desc->m0)); + status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) || + GET_VAL(LERR, le64_to_cpu(raw_desc->m0)); if (unlikely(status > 2)) { dev_kfree_skb_any(skb); xgene_enet_parse_error(rx_ring, netdev_priv(rx_ring->ndev), status); - pdata->stats.rx_dropped++; ret = -EIO; goto out; } @@ -506,8 +506,8 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring, xgene_enet_skip_csum(skb); } - pdata->stats.rx_packets++; - pdata->stats.rx_bytes += datalen; + rx_ring->rx_packets++; + rx_ring->rx_bytes += datalen; napi_gro_receive(&rx_ring->napi, skb); out: if (--rx_ring->nbufpool == 0) { @@ -630,7 +630,7 @@ static int xgene_enet_register_irq(struct net_device *ndev) ring = pdata->rx_ring[i]; irq_set_status_flags(ring->irq, IRQ_DISABLE_UNLAZY); ret = devm_request_irq(dev, ring->irq, xgene_enet_rx_irq, - IRQF_SHARED, ring->irq_name, ring); + 0, ring->irq_name, ring); if (ret) { netdev_err(ndev, "Failed to request irq %s\n", ring->irq_name); @@ -641,7 +641,7 @@ static int xgene_enet_register_irq(struct net_device *ndev) ring = pdata->tx_ring[i]->cp_ring; irq_set_status_flags(ring->irq, IRQ_DISABLE_UNLAZY); ret = devm_request_irq(dev, ring->irq, xgene_enet_rx_irq, - IRQF_SHARED, ring->irq_name, ring); + 0, ring->irq_name, ring); if (ret) { netdev_err(ndev, "Failed to request irq %s\n", ring->irq_name); @@ -1114,12 +1114,31 @@ static struct rtnl_link_stats64 *xgene_enet_get_stats64( { struct xgene_enet_pdata *pdata = netdev_priv(ndev); struct rtnl_link_stats64 *stats = &pdata->stats; + struct xgene_enet_desc_ring *ring; + int i; - stats->rx_errors += stats->rx_length_errors + - stats->rx_crc_errors + - stats->rx_frame_errors + - stats->rx_fifo_errors; - memcpy(storage, &pdata->stats, sizeof(struct rtnl_link_stats64)); + memset(stats, 0, sizeof(struct rtnl_link_stats64)); + for (i = 0; i < pdata->txq_cnt; i++) { + ring = pdata->tx_ring[i]; + if (ring) { + stats->tx_packets += ring->tx_packets; + stats->tx_bytes += ring->tx_bytes; + } + } + + for (i = 0; i < pdata->rxq_cnt; i++) { + ring = pdata->rx_ring[i]; + if (ring) { + stats->rx_packets += ring->rx_packets; + stats->rx_bytes += ring->rx_bytes; + stats->rx_errors += ring->rx_length_errors + + ring->rx_crc_errors + + ring->rx_frame_errors + + ring->rx_fifo_errors; + stats->rx_dropped += ring->rx_dropped; + } + } + memcpy(storage, stats, sizeof(struct rtnl_link_stats64)); return storage; } @@ -1234,6 +1253,13 @@ static int xgene_enet_get_irqs(struct xgene_enet_pdata *pdata) for (i = 0; i < max_irqs; i++) { ret = platform_get_irq(pdev, i); if (ret <= 0) { + if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) { + max_irqs = i; + pdata->rxq_cnt = max_irqs / 2; + pdata->txq_cnt = max_irqs / 2; + pdata->cq_cnt = max_irqs / 2; + break; + } dev_err(dev, "Unable to get ENET IRQ\n"); ret = ret ? : -ENXIO; return ret; @@ -1437,19 +1463,28 @@ static void xgene_enet_setup_ops(struct xgene_enet_pdata *pdata) pdata->port_ops = &xgene_xgport_ops; pdata->cle_ops = &xgene_cle3in_ops; pdata->rm = RM0; - pdata->rxq_cnt = XGENE_NUM_RX_RING; - pdata->txq_cnt = XGENE_NUM_TX_RING; - pdata->cq_cnt = XGENE_NUM_TXC_RING; + if (!pdata->rxq_cnt) { + pdata->rxq_cnt = XGENE_NUM_RX_RING; + pdata->txq_cnt = XGENE_NUM_TX_RING; + pdata->cq_cnt = XGENE_NUM_TXC_RING; + } break; } if (pdata->enet_id == XGENE_ENET1) { switch (pdata->port_id) { case 0: - pdata->cpu_bufnum = START_CPU_BUFNUM_0; - pdata->eth_bufnum = START_ETH_BUFNUM_0; - pdata->bp_bufnum = START_BP_BUFNUM_0; - pdata->ring_num = START_RING_NUM_0; + if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) { + pdata->cpu_bufnum = X2_START_CPU_BUFNUM_0; + pdata->eth_bufnum = X2_START_ETH_BUFNUM_0; + pdata->bp_bufnum = X2_START_BP_BUFNUM_0; + pdata->ring_num = START_RING_NUM_0; + } else { + pdata->cpu_bufnum = START_CPU_BUFNUM_0; + pdata->eth_bufnum = START_ETH_BUFNUM_0; + pdata->bp_bufnum = START_BP_BUFNUM_0; + pdata->ring_num = START_RING_NUM_0; + } break; case 1: if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) { @@ -1595,21 +1630,22 @@ static int xgene_enet_probe(struct platform_device *pdev) ret = xgene_enet_init_hw(pdata); if (ret) - goto err; + goto err_netdev; mac_ops = pdata->mac_ops; if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII) { ret = xgene_enet_mdio_config(pdata); if (ret) - goto err; + goto err_netdev; } else { INIT_DELAYED_WORK(&pdata->link_work, mac_ops->link_state); } xgene_enet_napi_add(pdata); return 0; -err: +err_netdev: unregister_netdev(ndev); +err: free_netdev(ndev); return ret; } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index 175d188..9d9cf44 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -49,10 +49,10 @@ #define XGENE_ENET_MSS 1448 #define XGENE_MIN_ENET_FRAME_SIZE 60 -#define XGENE_MAX_ENET_IRQ 8 -#define XGENE_NUM_RX_RING 4 -#define XGENE_NUM_TX_RING 4 -#define XGENE_NUM_TXC_RING 4 +#define XGENE_MAX_ENET_IRQ 16 +#define XGENE_NUM_RX_RING 8 +#define XGENE_NUM_TX_RING 8 +#define XGENE_NUM_TXC_RING 8 #define START_CPU_BUFNUM_0 0 #define START_ETH_BUFNUM_0 2 @@ -121,6 +121,16 @@ struct xgene_enet_desc_ring { struct xgene_enet_raw_desc16 *raw_desc16; }; __le64 *exp_bufs; + u64 tx_packets; + u64 tx_bytes; + u64 rx_packets; + u64 rx_bytes; + u64 rx_dropped; + u64 rx_errors; + u64 rx_length_errors; + u64 rx_crc_errors; + u64 rx_frame_errors; + u64 rx_fifo_errors; }; struct xgene_mac_ops { diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.h b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.h index 29a71b4..002df5a 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.h @@ -33,7 +33,7 @@ #define LINK_STATUS BIT(2) #define LINK_UP BIT(15) #define MPA_IDLE_WITH_QMI_EMPTY BIT(12) -#define SG_RX_DV_GATE_REG_0_ADDR 0x0dfc +#define SG_RX_DV_GATE_REG_0_ADDR 0x05fc extern const struct xgene_mac_ops xgene_sgmac_ops; extern const struct xgene_port_ops xgene_sgport_ops; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 12a009d..c39a7f5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -581,12 +581,30 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp, struct page *page; dma_addr_t mapping; u16 sw_prod = rxr->rx_sw_agg_prod; + unsigned int offset = 0; - page = alloc_page(gfp); - if (!page) - return -ENOMEM; + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) { + page = rxr->rx_page; + if (!page) { + page = alloc_page(gfp); + if (!page) + return -ENOMEM; + rxr->rx_page = page; + rxr->rx_page_offset = 0; + } + offset = rxr->rx_page_offset; + rxr->rx_page_offset += BNXT_RX_PAGE_SIZE; + if (rxr->rx_page_offset == PAGE_SIZE) + rxr->rx_page = NULL; + else + get_page(page); + } else { + page = alloc_page(gfp); + if (!page) + return -ENOMEM; + } - mapping = dma_map_page(&pdev->dev, page, 0, PAGE_SIZE, + mapping = dma_map_page(&pdev->dev, page, offset, BNXT_RX_PAGE_SIZE, PCI_DMA_FROMDEVICE); if (dma_mapping_error(&pdev->dev, mapping)) { __free_page(page); @@ -601,6 +619,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp, rxr->rx_sw_agg_prod = NEXT_RX_AGG(sw_prod); rx_agg_buf->page = page; + rx_agg_buf->offset = offset; rx_agg_buf->mapping = mapping; rxbd->rx_bd_haddr = cpu_to_le64(mapping); rxbd->rx_bd_opaque = sw_prod; @@ -642,6 +661,7 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_napi *bnapi, u16 cp_cons, page = cons_rx_buf->page; cons_rx_buf->page = NULL; prod_rx_buf->page = page; + prod_rx_buf->offset = cons_rx_buf->offset; prod_rx_buf->mapping = cons_rx_buf->mapping; @@ -709,7 +729,8 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, struct bnxt_napi *bnapi, RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT; cons_rx_buf = &rxr->rx_agg_ring[cons]; - skb_fill_page_desc(skb, i, cons_rx_buf->page, 0, frag_len); + skb_fill_page_desc(skb, i, cons_rx_buf->page, + cons_rx_buf->offset, frag_len); __clear_bit(cons, rxr->rx_agg_bmap); /* It is possible for bnxt_alloc_rx_page() to allocate @@ -740,7 +761,7 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, struct bnxt_napi *bnapi, return NULL; } - dma_unmap_page(&pdev->dev, mapping, PAGE_SIZE, + dma_unmap_page(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE, PCI_DMA_FROMDEVICE); skb->data_len += frag_len; @@ -792,6 +813,46 @@ static inline struct sk_buff *bnxt_copy_skb(struct bnxt_napi *bnapi, u8 *data, return skb; } +static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_napi *bnapi, + u32 *raw_cons, void *cmp) +{ + struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; + struct rx_cmp *rxcmp = cmp; + u32 tmp_raw_cons = *raw_cons; + u8 cmp_type, agg_bufs = 0; + + cmp_type = RX_CMP_TYPE(rxcmp); + + if (cmp_type == CMP_TYPE_RX_L2_CMP) { + agg_bufs = (le32_to_cpu(rxcmp->rx_cmp_misc_v1) & + RX_CMP_AGG_BUFS) >> + RX_CMP_AGG_BUFS_SHIFT; + } else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) { + struct rx_tpa_end_cmp *tpa_end = cmp; + + agg_bufs = (le32_to_cpu(tpa_end->rx_tpa_end_cmp_misc_v1) & + RX_TPA_END_CMP_AGG_BUFS) >> + RX_TPA_END_CMP_AGG_BUFS_SHIFT; + } + + if (agg_bufs) { + if (!bnxt_agg_bufs_valid(bp, cpr, agg_bufs, &tmp_raw_cons)) + return -EBUSY; + } + *raw_cons = tmp_raw_cons; + return 0; +} + +static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) +{ + if (!rxr->bnapi->in_reset) { + rxr->bnapi->in_reset = true; + set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event); + schedule_work(&bp->sp_task); + } + rxr->rx_next_cons = 0xffff; +} + static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, struct rx_tpa_start_cmp *tpa_start, struct rx_tpa_start_cmp_ext *tpa_start1) @@ -809,6 +870,11 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, prod_rx_buf = &rxr->rx_buf_ring[prod]; tpa_info = &rxr->rx_tpa[agg_id]; + if (unlikely(cons != rxr->rx_next_cons)) { + bnxt_sched_reset(bp, rxr); + return; + } + prod_rx_buf->data = tpa_info->data; mapping = tpa_info->mapping; @@ -846,6 +912,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, rxr->rx_prod = NEXT_RX(prod); cons = NEXT_RX(cons); + rxr->rx_next_cons = NEXT_RX(cons); cons_rx_buf = &rxr->rx_buf_ring[cons]; bnxt_reuse_rx_data(rxr, cons, cons_rx_buf->data); @@ -959,6 +1026,14 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, dma_addr_t mapping; struct sk_buff *skb; + if (unlikely(bnapi->in_reset)) { + int rc = bnxt_discard_rx(bp, bnapi, raw_cons, tpa_end); + + if (rc < 0) + return ERR_PTR(-EBUSY); + return NULL; + } + tpa_info = &rxr->rx_tpa[agg_id]; data = tpa_info->data; prefetch(data); @@ -1125,6 +1200,12 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, cons = rxcmp->rx_cmp_opaque; rx_buf = &rxr->rx_buf_ring[cons]; data = rx_buf->data; + if (unlikely(cons != rxr->rx_next_cons)) { + int rc1 = bnxt_discard_rx(bp, bnapi, raw_cons, rxcmp); + + bnxt_sched_reset(bp, rxr); + return rc1; + } prefetch(data); agg_bufs = (le32_to_cpu(rxcmp->rx_cmp_misc_v1) & RX_CMP_AGG_BUFS) >> @@ -1224,6 +1305,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, next_rx: rxr->rx_prod = NEXT_RX(prod); + rxr->rx_next_cons = NEXT_RX(cons); next_rx_no_prod: *raw_cons = tmp_raw_cons; @@ -1367,6 +1449,10 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) if (!TX_CMP_VALID(txcmp, raw_cons)) break; + /* The valid test of the entry must be done first before + * reading any further. + */ + rmb(); if (TX_CMP_TYPE(txcmp) == CMP_TYPE_TX_L2_CMP) { tx_pkts++; /* return full budget so NAPI will complete. */ @@ -1584,13 +1670,17 @@ static void bnxt_free_rx_skbs(struct bnxt *bp) dma_unmap_page(&pdev->dev, dma_unmap_addr(rx_agg_buf, mapping), - PAGE_SIZE, PCI_DMA_FROMDEVICE); + BNXT_RX_PAGE_SIZE, PCI_DMA_FROMDEVICE); rx_agg_buf->page = NULL; __clear_bit(j, rxr->rx_agg_bmap); __free_page(page); } + if (rxr->rx_page) { + __free_page(rxr->rx_page); + rxr->rx_page = NULL; + } } } @@ -1973,7 +2063,7 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) if (!(bp->flags & BNXT_FLAG_AGG_RINGS)) return 0; - type = ((u32)PAGE_SIZE << RX_BD_LEN_SHIFT) | + type = ((u32)BNXT_RX_PAGE_SIZE << RX_BD_LEN_SHIFT) | RX_BD_TYPE_RX_AGG_BD | RX_BD_FLAGS_SOP; bnxt_init_rxbd_pages(ring, type); @@ -2164,7 +2254,7 @@ void bnxt_set_ring_params(struct bnxt *bp) bp->rx_agg_nr_pages = 0; if (bp->flags & BNXT_FLAG_TPA) - agg_factor = 4; + agg_factor = min_t(u32, 4, 65536 / BNXT_RX_PAGE_SIZE); bp->flags &= ~BNXT_FLAG_JUMBO; if (rx_space > PAGE_SIZE) { @@ -2457,6 +2547,7 @@ static void bnxt_clear_ring_indices(struct bnxt *bp) rxr->rx_prod = 0; rxr->rx_agg_prod = 0; rxr->rx_sw_agg_prod = 0; + rxr->rx_next_cons = 0; } } } @@ -3020,12 +3111,12 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags) /* Number of segs are log2 units, and first packet is not * included as part of this units. */ - if (mss <= PAGE_SIZE) { - n = PAGE_SIZE / mss; + if (mss <= BNXT_RX_PAGE_SIZE) { + n = BNXT_RX_PAGE_SIZE / mss; nsegs = (MAX_SKB_FRAGS - 1) * n; } else { - n = mss / PAGE_SIZE; - if (mss & (PAGE_SIZE - 1)) + n = mss / BNXT_RX_PAGE_SIZE; + if (mss & (BNXT_RX_PAGE_SIZE - 1)) n++; nsegs = (MAX_SKB_FRAGS - n) / n; } @@ -4013,9 +4104,11 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp) } static int bnxt_cfg_rx_mode(struct bnxt *); +static bool bnxt_mc_list_updated(struct bnxt *, u32 *); static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) { + struct bnxt_vnic_info *vnic = &bp->vnic_info[0]; int rc = 0; if (irq_re_init) { @@ -4071,13 +4164,22 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) netdev_err(bp->dev, "HWRM vnic filter failure rc: %x\n", rc); goto err_out; } - bp->vnic_info[0].uc_filter_count = 1; + vnic->uc_filter_count = 1; - bp->vnic_info[0].rx_mask = CFA_L2_SET_RX_MASK_REQ_MASK_BCAST; + vnic->rx_mask = CFA_L2_SET_RX_MASK_REQ_MASK_BCAST; if ((bp->dev->flags & IFF_PROMISC) && BNXT_PF(bp)) - bp->vnic_info[0].rx_mask |= - CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS; + vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS; + + if (bp->dev->flags & IFF_ALLMULTI) { + vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST; + vnic->mc_list_count = 0; + } else { + u32 mask = 0; + + bnxt_mc_list_updated(bp, &mask); + vnic->rx_mask |= mask; + } rc = bnxt_cfg_rx_mode(bp); if (rc) @@ -4309,7 +4411,7 @@ static int bnxt_setup_int_mode(struct bnxt *bp) if (bp->flags & BNXT_FLAG_MSIX_CAP) rc = bnxt_setup_msix(bp); - if (!(bp->flags & BNXT_FLAG_USING_MSIX)) { + if (!(bp->flags & BNXT_FLAG_USING_MSIX) && BNXT_PF(bp)) { /* fallback to INTA */ rc = bnxt_setup_inta(bp); } @@ -4422,6 +4524,7 @@ static void bnxt_enable_napi(struct bnxt *bp) int i; for (i = 0; i < bp->cp_nr_rings; i++) { + bp->bnapi[i]->in_reset = false; bnxt_enable_poll(bp->bnapi[i]); napi_enable(&bp->bnapi[i]->napi); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 709b95b..de9d53e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -407,6 +407,15 @@ struct rx_tpa_end_cmp_ext { #define BNXT_PAGE_SIZE (1 << BNXT_PAGE_SHIFT) +/* The RXBD length is 16-bit so we can only support page sizes < 64K */ +#if (PAGE_SHIFT > 15) +#define BNXT_RX_PAGE_SHIFT 15 +#else +#define BNXT_RX_PAGE_SHIFT PAGE_SHIFT +#endif + +#define BNXT_RX_PAGE_SIZE (1 << BNXT_RX_PAGE_SHIFT) + #define BNXT_MIN_PKT_SIZE 45 #define BNXT_NUM_TESTS(bp) 0 @@ -506,6 +515,7 @@ struct bnxt_sw_rx_bd { struct bnxt_sw_rx_agg_bd { struct page *page; + unsigned int offset; dma_addr_t mapping; }; @@ -574,6 +584,7 @@ struct bnxt_rx_ring_info { u16 rx_prod; u16 rx_agg_prod; u16 rx_sw_agg_prod; + u16 rx_next_cons; void __iomem *rx_doorbell; void __iomem *rx_agg_doorbell; @@ -586,6 +597,9 @@ struct bnxt_rx_ring_info { unsigned long *rx_agg_bmap; u16 rx_agg_bmap_size; + struct page *rx_page; + unsigned int rx_page_offset; + dma_addr_t rx_desc_mapping[MAX_RX_PAGES]; dma_addr_t rx_agg_desc_mapping[MAX_RX_AGG_PAGES]; @@ -623,6 +637,7 @@ struct bnxt_napi { #ifdef CONFIG_NET_RX_BUSY_POLL atomic_t poll_state; #endif + bool in_reset; }; #ifdef CONFIG_NET_RX_BUSY_POLL diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 48a7d7d..a63551d 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -441,7 +441,7 @@ static int macb_mii_init(struct macb *bp) snprintf(bp->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", bp->pdev->name, bp->pdev->id); bp->mii_bus->priv = bp; - bp->mii_bus->parent = &bp->dev->dev; + bp->mii_bus->parent = &bp->pdev->dev; pdata = dev_get_platdata(&bp->pdev->dev); dev_set_drvdata(&bp->dev->dev, bp->mii_bus); @@ -458,7 +458,8 @@ static int macb_mii_init(struct macb *bp) struct phy_device *phydev; phydev = mdiobus_scan(bp->mii_bus, i); - if (IS_ERR(phydev)) { + if (IS_ERR(phydev) && + PTR_ERR(phydev) != -ENODEV) { err = PTR_ERR(phydev); break; } @@ -3019,29 +3020,36 @@ static int macb_probe(struct platform_device *pdev) if (err) goto err_out_free_netdev; + err = macb_mii_init(bp); + if (err) + goto err_out_free_netdev; + + phydev = bp->phy_dev; + + netif_carrier_off(dev); + err = register_netdev(dev); if (err) { dev_err(&pdev->dev, "Cannot register net device, aborting.\n"); - goto err_out_unregister_netdev; + goto err_out_unregister_mdio; } - err = macb_mii_init(bp); - if (err) - goto err_out_unregister_netdev; - - netif_carrier_off(dev); + phy_attached_info(phydev); netdev_info(dev, "Cadence %s rev 0x%08x at 0x%08lx irq %d (%pM)\n", macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID), dev->base_addr, dev->irq, dev->dev_addr); - phydev = bp->phy_dev; - phy_attached_info(phydev); - return 0; -err_out_unregister_netdev: - unregister_netdev(dev); +err_out_unregister_mdio: + phy_disconnect(bp->phy_dev); + mdiobus_unregister(bp->mii_bus); + mdiobus_free(bp->mii_bus); + + /* Shutdown the PHY if there is a GPIO reset */ + if (bp->reset_gpio) + gpiod_set_value(bp->reset_gpio, 0); err_out_free_netdev: free_netdev(dev); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index fa05e34..06b819d 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -533,6 +533,7 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs, nicvf_config_vlan_stripping(nic, nic->netdev->features); /* Enable Receive queue */ + memset(&rq_cfg, 0, sizeof(struct rq_cfg)); rq_cfg.ena = 1; rq_cfg.tcp_ena = 0; nicvf_queue_reg_write(nic, NIC_QSET_RQ_0_7_CFG, qidx, *(u64 *)&rq_cfg); @@ -565,6 +566,7 @@ void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs, qidx, (u64)(cq->dmem.phys_base)); /* Enable Completion queue */ + memset(&cq_cfg, 0, sizeof(struct cq_cfg)); cq_cfg.ena = 1; cq_cfg.reset = 0; cq_cfg.caching = 0; @@ -613,6 +615,7 @@ static void nicvf_snd_queue_config(struct nicvf *nic, struct queue_set *qs, qidx, (u64)(sq->dmem.phys_base)); /* Enable send queue & set queue size */ + memset(&sq_cfg, 0, sizeof(struct sq_cfg)); sq_cfg.ena = 1; sq_cfg.reset = 0; sq_cfg.ldwb = 0; @@ -649,6 +652,7 @@ static void nicvf_rbdr_config(struct nicvf *nic, struct queue_set *qs, /* Enable RBDR & set queue size */ /* Buffer size should be in multiples of 128 bytes */ + memset(&rbdr_cfg, 0, sizeof(struct rbdr_cfg)); rbdr_cfg.ena = 1; rbdr_cfg.reset = 0; rbdr_cfg.ldwb = 0; diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 60908ea..43da891 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -576,7 +576,7 @@ static void setup_rss(struct adapter *adap) unsigned int nq0 = adap2pinfo(adap, 0)->nqsets; unsigned int nq1 = adap->port[1] ? adap2pinfo(adap, 1)->nqsets : 1; u8 cpus[SGE_QSETS + 1]; - u16 rspq_map[RSS_TABLE_SIZE]; + u16 rspq_map[RSS_TABLE_SIZE + 1]; for (i = 0; i < SGE_QSETS; ++i) cpus[i] = i; @@ -586,6 +586,7 @@ static void setup_rss(struct adapter *adap) rspq_map[i] = i % nq0; rspq_map[i + RSS_TABLE_SIZE / 2] = (i % nq1) + nq0; } + rspq_map[RSS_TABLE_SIZE] = 0xffff; /* terminator */ t3_config_rss(adap, F_RQFEEDBACKENABLE | F_TNLLKPEN | F_TNLMAPEN | F_TNLPRTEN | F_TNL2TUPEN | F_TNL4TUPEN | diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index 1f23845a..085f912 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -145,7 +145,7 @@ static void nps_enet_tx_handler(struct net_device *ndev) u32 tx_ctrl_nt = (tx_ctrl_value & TX_CTL_NT_MASK) >> TX_CTL_NT_SHIFT; /* Check if we got TX */ - if (!priv->tx_packet_sent || tx_ctrl_ct) + if (!priv->tx_skb || tx_ctrl_ct) return; /* Ack Tx ctrl register */ @@ -160,7 +160,7 @@ static void nps_enet_tx_handler(struct net_device *ndev) } dev_kfree_skb(priv->tx_skb); - priv->tx_packet_sent = false; + priv->tx_skb = NULL; if (netif_queue_stopped(ndev)) netif_wake_queue(ndev); @@ -183,6 +183,9 @@ static int nps_enet_poll(struct napi_struct *napi, int budget) work_done = nps_enet_rx_handler(ndev); if (work_done < budget) { u32 buf_int_enable_value = 0; + u32 tx_ctrl_value = nps_enet_reg_get(priv, NPS_ENET_REG_TX_CTL); + u32 tx_ctrl_ct = + (tx_ctrl_value & TX_CTL_CT_MASK) >> TX_CTL_CT_SHIFT; napi_complete(napi); @@ -192,6 +195,18 @@ static int nps_enet_poll(struct napi_struct *napi, int budget) nps_enet_reg_set(priv, NPS_ENET_REG_BUF_INT_ENABLE, buf_int_enable_value); + + /* in case we will get a tx interrupt while interrupts + * are masked, we will lose it since the tx is edge interrupt. + * specifically, while executing the code section above, + * between nps_enet_tx_handler and the interrupts enable, all + * tx requests will be stuck until we will get an rx interrupt. + * the two code lines below will solve this situation by + * re-adding ourselves to the poll list. + */ + + if (priv->tx_skb && !tx_ctrl_ct) + napi_reschedule(napi); } return work_done; @@ -217,7 +232,7 @@ static irqreturn_t nps_enet_irq_handler(s32 irq, void *dev_instance) u32 tx_ctrl_ct = (tx_ctrl_value & TX_CTL_CT_MASK) >> TX_CTL_CT_SHIFT; u32 rx_ctrl_cr = (rx_ctrl_value & RX_CTL_CR_MASK) >> RX_CTL_CR_SHIFT; - if ((!tx_ctrl_ct && priv->tx_packet_sent) || rx_ctrl_cr) + if ((!tx_ctrl_ct && priv->tx_skb) || rx_ctrl_cr) if (likely(napi_schedule_prep(&priv->napi))) { nps_enet_reg_set(priv, NPS_ENET_REG_BUF_INT_ENABLE, 0); __napi_schedule(&priv->napi); @@ -387,8 +402,6 @@ static void nps_enet_send_frame(struct net_device *ndev, /* Write the length of the Frame */ tx_ctrl_value |= length << TX_CTL_NT_SHIFT; - /* Indicate SW is done */ - priv->tx_packet_sent = true; tx_ctrl_value |= NPS_ENET_ENABLE << TX_CTL_CT_SHIFT; /* Send Frame */ nps_enet_reg_set(priv, NPS_ENET_REG_TX_CTL, tx_ctrl_value); @@ -465,7 +478,7 @@ static s32 nps_enet_open(struct net_device *ndev) s32 err; /* Reset private variables */ - priv->tx_packet_sent = false; + priv->tx_skb = NULL; priv->ge_mac_cfg_2_value = 0; priv->ge_mac_cfg_3_value = 0; @@ -534,6 +547,11 @@ static netdev_tx_t nps_enet_start_xmit(struct sk_buff *skb, priv->tx_skb = skb; + /* make sure tx_skb is actually written to the memory + * before the HW is informed and the IRQ is fired. + */ + wmb(); + nps_enet_send_frame(ndev, skb); return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/ezchip/nps_enet.h b/drivers/net/ethernet/ezchip/nps_enet.h index d0cab60..3939ca2 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.h +++ b/drivers/net/ethernet/ezchip/nps_enet.h @@ -165,14 +165,12 @@ * struct nps_enet_priv - Storage of ENET's private information. * @regs_base: Base address of ENET memory-mapped control registers. * @irq: For RX/TX IRQ number. - * @tx_packet_sent: SW indication if frame is being sent. * @tx_skb: socket buffer of sent frame. * @napi: Structure for NAPI. */ struct nps_enet_priv { void __iomem *regs_base; s32 irq; - bool tx_packet_sent; struct sk_buff *tx_skb; struct napi_struct napi; u32 ge_mac_cfg_2_value; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 08243c2..2a03857 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1521,9 +1521,15 @@ fec_enet_rx(struct net_device *ndev, int budget) struct fec_enet_private *fep = netdev_priv(ndev); for_each_set_bit(queue_id, &fep->work_rx, FEC_ENET_MAX_RX_QS) { - clear_bit(queue_id, &fep->work_rx); - pkt_received += fec_enet_rx_queue(ndev, + int ret; + + ret = fec_enet_rx_queue(ndev, budget - pkt_received, queue_id); + + if (ret < budget - pkt_received) + clear_bit(queue_id, &fep->work_rx); + + pkt_received += ret; } return pkt_received; } diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig index b5c6d42..2664827 100644 --- a/drivers/net/ethernet/marvell/Kconfig +++ b/drivers/net/ethernet/marvell/Kconfig @@ -68,7 +68,7 @@ config MVNETA config MVNETA_BM tristate - default y if MVNETA=y && MVNETA_BM_ENABLE + default y if MVNETA=y && MVNETA_BM_ENABLE!=n default MVNETA_BM_ENABLE select HWBM help diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 7fc4902..a6d26d3 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3354,8 +3354,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, /* Enable per-CPU interrupts on the CPU that is * brought up. */ - smp_call_function_single(cpu, mvneta_percpu_enable, - pp, true); + mvneta_percpu_enable(pp); /* Enable per-CPU interrupt on the one CPU we care * about. @@ -3387,8 +3386,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, /* Disable per-CPU interrupts on the CPU that is * brought down. */ - smp_call_function_single(cpu, mvneta_percpu_disable, - pp, true); + mvneta_percpu_disable(pp); break; case CPU_DEAD: diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index 7ace07d..c442f6a 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -979,6 +979,8 @@ static int pxa168_init_phy(struct net_device *dev) return 0; pep->phy = mdiobus_scan(pep->smi_bus, pep->phy_addr); + if (IS_ERR(pep->phy)) + return PTR_ERR(pep->phy); if (!pep->phy) return -ENODEV; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b723e3b..ca3a384 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -707,7 +707,7 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb, if (ipv6h->nexthdr == IPPROTO_FRAGMENT || ipv6h->nexthdr == IPPROTO_HOPOPTS) return -1; - hw_checksum = csum_add(hw_checksum, (__force __wsum)(ipv6h->nexthdr << 8)); + hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr)); csum_pseudo_hdr = csum_partial(&ipv6h->saddr, sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 1cf722e..f5c3b94 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -31,3 +31,10 @@ config MLX5_CORE_EN_DCB This flag is depended on the kernel's DCB support. If unsure, set to Y + +config MLX5_CORE_EN_VXLAN + bool "VXLAN offloads Support" + default y + depends on MLX5_CORE_EN && VXLAN && !(MLX5_CORE=y && VXLAN=m) + ---help--- + Say Y here if you want to use VXLAN offloads in the driver. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 4fc45ee..bf65b71 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -6,6 +6,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o \ en_main.o en_fs.o en_ethtool.o en_tx.o en_rx.o \ - en_txrx.o en_clock.o vxlan.o en_tc.o + en_txrx.o en_clock.o en_tc.o +mlx5_core-$(CONFIG_MLX5_CORE_EN_VXLAN) += vxlan.o mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index e80ce94..24344aaf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -564,9 +564,12 @@ struct mlx5e_priv { struct mlx5e_flow_tables fts; struct mlx5e_eth_addr_db eth_addr; struct mlx5e_vlan_db vlan; +#ifdef CONFIG_MLX5_CORE_EN_VXLAN struct mlx5e_vxlan_db vxlan; +#endif struct mlx5e_params params; + struct workqueue_struct *wq; struct work_struct update_carrier_work; struct work_struct set_rx_mode_work; struct delayed_work update_stats_work; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 67d548b..94fef70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -262,9 +262,8 @@ static void mlx5e_update_stats_work(struct work_struct *work) mutex_lock(&priv->state_lock); if (test_bit(MLX5E_STATE_OPENED, &priv->state)) { mlx5e_update_stats(priv); - schedule_delayed_work(dwork, - msecs_to_jiffies( - MLX5E_UPDATE_STATS_INTERVAL)); + queue_delayed_work(priv->wq, dwork, + msecs_to_jiffies(MLX5E_UPDATE_STATS_INTERVAL)); } mutex_unlock(&priv->state_lock); } @@ -280,7 +279,7 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, switch (event) { case MLX5_DEV_EVENT_PORT_UP: case MLX5_DEV_EVENT_PORT_DOWN: - schedule_work(&priv->update_carrier_work); + queue_work(priv->wq, &priv->update_carrier_work); break; default: @@ -1505,7 +1504,7 @@ int mlx5e_open_locked(struct net_device *netdev) mlx5e_update_carrier(priv); mlx5e_timestamp_init(priv); - schedule_delayed_work(&priv->update_stats_work, 0); + queue_delayed_work(priv->wq, &priv->update_stats_work, 0); return 0; @@ -1961,7 +1960,7 @@ static void mlx5e_set_rx_mode(struct net_device *dev) { struct mlx5e_priv *priv = netdev_priv(dev); - schedule_work(&priv->set_rx_mode_work); + queue_work(priv->wq, &priv->set_rx_mode_work); } static int mlx5e_set_mac(struct net_device *netdev, void *addr) @@ -1976,7 +1975,7 @@ static int mlx5e_set_mac(struct net_device *netdev, void *addr) ether_addr_copy(netdev->dev_addr, saddr->sa_data); netif_addr_unlock_bh(netdev); - schedule_work(&priv->set_rx_mode_work); + queue_work(priv->wq, &priv->set_rx_mode_work); return 0; } @@ -2150,6 +2149,7 @@ static int mlx5e_get_vf_stats(struct net_device *dev, vf_stats); } +#if IS_ENABLED(CONFIG_MLX5_CORE_EN_VXLAN) static void mlx5e_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family, __be16 port) { @@ -2158,7 +2158,7 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev, if (!mlx5e_vxlan_allowed(priv->mdev)) return; - mlx5e_vxlan_add_port(priv, be16_to_cpu(port)); + mlx5e_vxlan_queue_work(priv, sa_family, be16_to_cpu(port), 1); } static void mlx5e_del_vxlan_port(struct net_device *netdev, @@ -2169,7 +2169,7 @@ static void mlx5e_del_vxlan_port(struct net_device *netdev, if (!mlx5e_vxlan_allowed(priv->mdev)) return; - mlx5e_vxlan_del_port(priv, be16_to_cpu(port)); + mlx5e_vxlan_queue_work(priv, sa_family, be16_to_cpu(port), 0); } static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv, @@ -2221,6 +2221,7 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb, return features; } +#endif static const struct net_device_ops mlx5e_netdev_ops_basic = { .ndo_open = mlx5e_open, @@ -2252,9 +2253,11 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = { .ndo_set_features = mlx5e_set_features, .ndo_change_mtu = mlx5e_change_mtu, .ndo_do_ioctl = mlx5e_ioctl, +#ifdef CONFIG_MLX5_CORE_EN_VXLAN .ndo_add_vxlan_port = mlx5e_add_vxlan_port, .ndo_del_vxlan_port = mlx5e_del_vxlan_port, .ndo_features_check = mlx5e_features_check, +#endif .ndo_set_vf_mac = mlx5e_set_vf_mac, .ndo_set_vf_vlan = mlx5e_set_vf_vlan, .ndo_get_vf_config = mlx5e_get_vf_config, @@ -2498,10 +2501,14 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) priv = netdev_priv(netdev); + priv->wq = create_singlethread_workqueue("mlx5e"); + if (!priv->wq) + goto err_free_netdev; + err = mlx5_alloc_map_uar(mdev, &priv->cq_uar, false); if (err) { mlx5_core_err(mdev, "alloc_map uar failed, %d\n", err); - goto err_free_netdev; + goto err_destroy_wq; } err = mlx5_core_alloc_pd(mdev, &priv->pdn); @@ -2580,7 +2587,7 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) vxlan_get_rx_port(netdev); mlx5e_enable_async_events(priv); - schedule_work(&priv->set_rx_mode_work); + queue_work(priv->wq, &priv->set_rx_mode_work); return priv; @@ -2617,6 +2624,9 @@ err_dealloc_pd: err_unmap_free_uar: mlx5_unmap_free_uar(mdev, &priv->cq_uar); +err_destroy_wq: + destroy_workqueue(priv->wq); + err_free_netdev: free_netdev(netdev); @@ -2630,9 +2640,9 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) set_bit(MLX5E_STATE_DESTROYING, &priv->state); - schedule_work(&priv->set_rx_mode_work); + queue_work(priv->wq, &priv->set_rx_mode_work); mlx5e_disable_async_events(priv); - flush_scheduled_work(); + flush_workqueue(priv->wq); if (test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state)) { netif_device_detach(netdev); mutex_lock(&priv->state_lock); @@ -2655,6 +2665,8 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) mlx5_core_dealloc_transport_domain(priv->mdev, priv->tdn); mlx5_core_dealloc_pd(priv->mdev, priv->pdn); mlx5_unmap_free_uar(priv->mdev, &priv->cq_uar); + cancel_delayed_work_sync(&priv->update_stats_work); + destroy_workqueue(priv->wq); if (!test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state)) free_netdev(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index 8ba080e..5ff8af4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -269,8 +269,10 @@ EXPORT_SYMBOL(mlx5_alloc_map_uar); void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) { - iounmap(uar->map); - iounmap(uar->bf_map); + if (uar->map) + iounmap(uar->map); + else + iounmap(uar->bf_map); mlx5_cmd_free_uar(mdev, uar->index); } EXPORT_SYMBOL(mlx5_unmap_free_uar); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c index 9f10df2..f2fd1ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c @@ -95,21 +95,22 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port) return vxlan; } -int mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port) +static void mlx5e_vxlan_add_port(struct work_struct *work) { + struct mlx5e_vxlan_work *vxlan_work = + container_of(work, struct mlx5e_vxlan_work, work); + struct mlx5e_priv *priv = vxlan_work->priv; struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; + u16 port = vxlan_work->port; struct mlx5e_vxlan *vxlan; int err; - err = mlx5e_vxlan_core_add_port_cmd(priv->mdev, port); - if (err) - return err; + if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port)) + goto free_work; vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL); - if (!vxlan) { - err = -ENOMEM; + if (!vxlan) goto err_delete_port; - } vxlan->udp_port = port; @@ -119,13 +120,14 @@ int mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port) if (err) goto err_free; - return 0; + goto free_work; err_free: kfree(vxlan); err_delete_port: mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); - return err; +free_work: + kfree(vxlan_work); } static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port) @@ -145,12 +147,36 @@ static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port) kfree(vxlan); } -void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port) +static void mlx5e_vxlan_del_port(struct work_struct *work) { - if (!mlx5e_vxlan_lookup_port(priv, port)) - return; + struct mlx5e_vxlan_work *vxlan_work = + container_of(work, struct mlx5e_vxlan_work, work); + struct mlx5e_priv *priv = vxlan_work->priv; + u16 port = vxlan_work->port; __mlx5e_vxlan_core_del_port(priv, port); + + kfree(vxlan_work); +} + +void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family, + u16 port, int add) +{ + struct mlx5e_vxlan_work *vxlan_work; + + vxlan_work = kmalloc(sizeof(*vxlan_work), GFP_ATOMIC); + if (!vxlan_work) + return; + + if (add) + INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_port); + else + INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_port); + + vxlan_work->priv = priv; + vxlan_work->port = port; + vxlan_work->sa_family = sa_family; + queue_work(priv->wq, &vxlan_work->work); } void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h index a016850..217ac53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h @@ -39,16 +39,30 @@ struct mlx5e_vxlan { u16 udp_port; }; +struct mlx5e_vxlan_work { + struct work_struct work; + struct mlx5e_priv *priv; + sa_family_t sa_family; + u16 port; +}; + static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev) { - return (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) && + return IS_ENABLED(CONFIG_MLX5_CORE_EN_VXLAN) && + (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) && mlx5_core_is_pf(mdev)); } +#ifdef CONFIG_MLX5_CORE_EN_VXLAN void mlx5e_vxlan_init(struct mlx5e_priv *priv); -int mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port); -void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port); -struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port); void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv); +#else +static inline void mlx5e_vxlan_init(struct mlx5e_priv *priv) {} +static inline void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv) {} +#endif + +void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family, + u16 port, int add); +struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port); #endif /* __MLX5_VXLAN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 4afbc3e..668b2f4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2541,11 +2541,11 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, lag->ref_count++; return 0; +err_col_port_enable: + mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id); err_col_port_add: if (!lag->ref_count) mlxsw_sp_lag_destroy(mlxsw_sp, lag_id); -err_col_port_enable: - mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id); return err; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index e1c74ef..9cd6f47 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -214,7 +214,15 @@ static int __mlxsw_sp_port_flood_set(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BM, idx_begin, table_type, range, local_port, set); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); + if (err) + goto err_flood_bm_set; + else + goto buffer_out; +err_flood_bm_set: + mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_UC, idx_begin, + table_type, range, local_port, !set); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); buffer_out: kfree(sftr_pl); return err; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 270c9ee..6d1a956 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -2668,9 +2668,9 @@ static int myri10ge_close(struct net_device *dev) del_timer_sync(&mgp->watchdog_timer); mgp->running = MYRI10GE_ETH_STOPPING; - local_bh_disable(); /* myri10ge_ss_lock_napi needs bh disabled */ for (i = 0; i < mgp->num_slices; i++) { napi_disable(&mgp->ss[i].napi); + local_bh_disable(); /* myri10ge_ss_lock_napi needs this */ /* Lock the slice to prevent the busy_poll handler from * accessing it. Later when we bring the NIC up, myri10ge_open * resets the slice including this lock. @@ -2679,8 +2679,8 @@ static int myri10ge_close(struct net_device *dev) pr_info("Slice %d locked\n", i); mdelay(1); } + local_bh_enable(); } - local_bh_enable(); netif_carrier_off(dev); netif_tx_stop_all_queues(dev); diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c index db80eb1..2b10f1b 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c @@ -1015,20 +1015,24 @@ static int netxen_get_flash_block(struct netxen_adapter *adapter, int base, { int i, v, addr; __le32 *ptr32; + int ret; addr = base; ptr32 = buf; for (i = 0; i < size / sizeof(u32); i++) { - if (netxen_rom_fast_read(adapter, addr, &v) == -1) - return -1; + ret = netxen_rom_fast_read(adapter, addr, &v); + if (ret) + return ret; + *ptr32 = cpu_to_le32(v); ptr32++; addr += sizeof(u32); } if ((char *)buf + size > (char *)ptr32) { __le32 local; - if (netxen_rom_fast_read(adapter, addr, &v) == -1) - return -1; + ret = netxen_rom_fast_read(adapter, addr, &v); + if (ret) + return ret; local = cpu_to_le32(v); memcpy(ptr32, &local, (char *)buf + size - (char *)ptr32); } @@ -1940,7 +1944,7 @@ void netxen_nic_set_link_parameters(struct netxen_adapter *adapter) if (adapter->phy_read && adapter->phy_read(adapter, NETXEN_NIU_GB_MII_MGMT_ADDR_AUTONEG, - &autoneg) != 0) + &autoneg) == 0) adapter->link_autoneg = autoneg; } else goto link_down; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index fd362b6..9c6eed9 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -852,7 +852,8 @@ netxen_check_options(struct netxen_adapter *adapter) ptr32 = (__le32 *)&serial_num; offset = NX_FW_SERIAL_NUM_OFFSET; for (i = 0; i < 8; i++) { - if (netxen_rom_fast_read(adapter, offset, &val) == -1) { + err = netxen_rom_fast_read(adapter, offset, &val); + if (err) { dev_err(&pdev->dev, "error reading board info\n"); adapter->driver_mismatch = 1; return; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 7869465..12f6615 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -421,7 +421,7 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, u8 xmit_type; u16 idx; u16 hlen; - bool data_split; + bool data_split = false; /* Get tx-queue context and netdev index */ txq_index = skb_get_queue_mapping(skb); @@ -1938,8 +1938,6 @@ static struct qede_dev *qede_alloc_etherdev(struct qed_dev *cdev, edev->q_num_rx_buffers = NUM_RX_BDS_DEF; edev->q_num_tx_buffers = NUM_TX_BDS_DEF; - DP_INFO(edev, "Allocated netdev with 64 tx queues and 64 rx queues\n"); - SET_NETDEV_DEV(ndev, &pdev->dev); memset(&edev->stats, 0, sizeof(edev->stats)); @@ -2090,9 +2088,9 @@ static void qede_update_pf_params(struct qed_dev *cdev) { struct qed_pf_params pf_params; - /* 16 rx + 16 tx */ + /* 64 rx + 64 tx */ memset(&pf_params, 0, sizeof(struct qed_pf_params)); - pf_params.eth_pf_params.num_cons = 32; + pf_params.eth_pf_params.num_cons = 128; qed_ops->common->update_pf_params(cdev, &pf_params); } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c index cda9e60..0844b7c 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c @@ -1417,6 +1417,7 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter) struct qlcnic_fw_dump *fw_dump = &ahw->fw_dump; struct pci_dev *pdev = adapter->pdev; bool extended = false; + int ret; prev_version = adapter->fw_version; current_version = qlcnic_83xx_get_fw_version(adapter); @@ -1427,8 +1428,11 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter) if (qlcnic_83xx_md_check_extended_dump_capability(adapter)) extended = !qlcnic_83xx_extend_md_capab(adapter); - if (!qlcnic_fw_cmd_get_minidump_temp(adapter)) - dev_info(&pdev->dev, "Supports FW dump capability\n"); + ret = qlcnic_fw_cmd_get_minidump_temp(adapter); + if (ret) + return; + + dev_info(&pdev->dev, "Supports FW dump capability\n"); /* Once we have minidump template with extended iSCSI dump * capability, update the minidump capture mask to 0x1f as diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 9e2a0bd..4277d0c 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1506,6 +1506,8 @@ static int ravb_close(struct net_device *ndev) priv->phydev = NULL; } + if (priv->chip_id == RCAR_GEN3) + free_irq(priv->emac_irq, ndev); free_irq(ndev->irq, ndev); napi_disable(&priv->napi[RAVB_NC]); diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 98d33d4..1681084 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1920,6 +1920,10 @@ static int efx_ef10_alloc_rss_context(struct efx_nic *efx, u32 *context, return 0; } + if (nic_data->datapath_caps & + 1 << MC_CMD_GET_CAPABILITIES_OUT_RX_RSS_LIMITED_LBN) + return -EOPNOTSUPP; + MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_UPSTREAM_PORT_ID, nic_data->vport_id); MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_TYPE, alloc_type); @@ -2923,9 +2927,16 @@ static void efx_ef10_filter_push_prep(struct efx_nic *efx, bool replacing) { struct efx_ef10_nic_data *nic_data = efx->nic_data; + u32 flags = spec->flags; memset(inbuf, 0, MC_CMD_FILTER_OP_IN_LEN); + /* Remove RSS flag if we don't have an RSS context. */ + if (flags & EFX_FILTER_FLAG_RX_RSS && + spec->rss_context == EFX_FILTER_RSS_CONTEXT_DEFAULT && + nic_data->rx_rss_context == EFX_EF10_RSS_CONTEXT_INVALID) + flags &= ~EFX_FILTER_FLAG_RX_RSS; + if (replacing) { MCDI_SET_DWORD(inbuf, FILTER_OP_IN_OP, MC_CMD_FILTER_OP_IN_OP_REPLACE); @@ -2985,10 +2996,10 @@ static void efx_ef10_filter_push_prep(struct efx_nic *efx, spec->dmaq_id == EFX_FILTER_RX_DMAQ_ID_DROP ? 0 : spec->dmaq_id); MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_MODE, - (spec->flags & EFX_FILTER_FLAG_RX_RSS) ? + (flags & EFX_FILTER_FLAG_RX_RSS) ? MC_CMD_FILTER_OP_IN_RX_MODE_RSS : MC_CMD_FILTER_OP_IN_RX_MODE_SIMPLE); - if (spec->flags & EFX_FILTER_FLAG_RX_RSS) + if (flags & EFX_FILTER_FLAG_RX_RSS) MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_CONTEXT, spec->rss_context != EFX_FILTER_RSS_CONTEXT_DEFAULT ? diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index bbb77cd..e2fcdf1 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -367,7 +367,6 @@ struct cpsw_priv { spinlock_t lock; struct platform_device *pdev; struct net_device *ndev; - struct device_node *phy_node; struct napi_struct napi_rx; struct napi_struct napi_tx; struct device *dev; @@ -1148,25 +1147,34 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) cpsw_ale_add_mcast(priv->ale, priv->ndev->broadcast, 1 << slave_port, 0, 0, ALE_MCAST_FWD_2); - if (priv->phy_node) - slave->phy = of_phy_connect(priv->ndev, priv->phy_node, + if (slave->data->phy_node) { + slave->phy = of_phy_connect(priv->ndev, slave->data->phy_node, &cpsw_adjust_link, 0, slave->data->phy_if); - else + if (!slave->phy) { + dev_err(priv->dev, "phy \"%s\" not found on slave %d\n", + slave->data->phy_node->full_name, + slave->slave_num); + return; + } + } else { slave->phy = phy_connect(priv->ndev, slave->data->phy_id, &cpsw_adjust_link, slave->data->phy_if); - if (IS_ERR(slave->phy)) { - dev_err(priv->dev, "phy %s not found on slave %d\n", - slave->data->phy_id, slave->slave_num); - slave->phy = NULL; - } else { - phy_attached_info(slave->phy); + if (IS_ERR(slave->phy)) { + dev_err(priv->dev, + "phy \"%s\" not found on slave %d, err %ld\n", + slave->data->phy_id, slave->slave_num, + PTR_ERR(slave->phy)); + slave->phy = NULL; + return; + } + } - phy_start(slave->phy); + phy_attached_info(slave->phy); - /* Configure GMII_SEL register */ - cpsw_phy_sel(&priv->pdev->dev, slave->phy->interface, - slave->slave_num); - } + phy_start(slave->phy); + + /* Configure GMII_SEL register */ + cpsw_phy_sel(&priv->pdev->dev, slave->phy->interface, slave->slave_num); } static inline void cpsw_add_default_vlan(struct cpsw_priv *priv) @@ -1940,12 +1948,11 @@ static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv, slave->port_vlan = data->dual_emac_res_vlan; } -static int cpsw_probe_dt(struct cpsw_priv *priv, +static int cpsw_probe_dt(struct cpsw_platform_data *data, struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; struct device_node *slave_node; - struct cpsw_platform_data *data = &priv->data; int i = 0, ret; u32 prop; @@ -2033,25 +2040,21 @@ static int cpsw_probe_dt(struct cpsw_priv *priv, if (strcmp(slave_node->name, "slave")) continue; - priv->phy_node = of_parse_phandle(slave_node, "phy-handle", 0); + slave_data->phy_node = of_parse_phandle(slave_node, + "phy-handle", 0); parp = of_get_property(slave_node, "phy_id", &lenp); - if (of_phy_is_fixed_link(slave_node)) { - struct device_node *phy_node; - struct phy_device *phy_dev; - + if (slave_data->phy_node) { + dev_dbg(&pdev->dev, + "slave[%d] using phy-handle=\"%s\"\n", + i, slave_data->phy_node->full_name); + } else if (of_phy_is_fixed_link(slave_node)) { /* In the case of a fixed PHY, the DT node associated * to the PHY is the Ethernet MAC DT node. */ ret = of_phy_register_fixed_link(slave_node); if (ret) return ret; - phy_node = of_node_get(slave_node); - phy_dev = of_phy_find_device(phy_node); - if (!phy_dev) - return -ENODEV; - snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), - PHY_ID_FMT, phy_dev->mdio.bus->id, - phy_dev->mdio.addr); + slave_data->phy_node = of_node_get(slave_node); } else if (parp) { u32 phyid; struct device_node *mdio_node; @@ -2072,7 +2075,9 @@ static int cpsw_probe_dt(struct cpsw_priv *priv, snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), PHY_ID_FMT, mdio->name, phyid); } else { - dev_err(&pdev->dev, "No slave[%d] phy_id or fixed-link property\n", i); + dev_err(&pdev->dev, + "No slave[%d] phy_id, phy-handle, or fixed-link property\n", + i); goto no_phy_slave; } slave_data->phy_if = of_get_phy_mode(slave_node); @@ -2275,7 +2280,7 @@ static int cpsw_probe(struct platform_device *pdev) /* Select default pin state */ pinctrl_pm_select_default_state(&pdev->dev); - if (cpsw_probe_dt(priv, pdev)) { + if (cpsw_probe_dt(&priv->data, pdev)) { dev_err(&pdev->dev, "cpsw: platform data missing\n"); ret = -ENODEV; goto clean_runtime_disable_ret; diff --git a/drivers/net/ethernet/ti/cpsw.h b/drivers/net/ethernet/ti/cpsw.h index 442a703..e50afd1 100644 --- a/drivers/net/ethernet/ti/cpsw.h +++ b/drivers/net/ethernet/ti/cpsw.h @@ -18,6 +18,7 @@ #include <linux/phy.h> struct cpsw_slave_data { + struct device_node *phy_node; char phy_id[MII_BUS_ID_SIZE]; int phy_if; u8 mac_addr[ETH_ALEN]; diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 58d58f0..f56d66e 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1512,7 +1512,10 @@ static int emac_devioctl(struct net_device *ndev, struct ifreq *ifrq, int cmd) /* TODO: Add phy read and write and private statistics get feature */ - return phy_mii_ioctl(priv->phydev, ifrq, cmd); + if (priv->phydev) + return phy_mii_ioctl(priv->phydev, ifrq, cmd); + else + return -EOPNOTSUPP; } static int match_first_device(struct device *dev, void *data) diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c index 13214a6..743b182 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c @@ -1622,7 +1622,7 @@ static void gelic_wl_scan_complete_event(struct gelic_wl_info *wl) continue; /* copy hw scan info */ - memcpy(target->hwinfo, scan_info, scan_info->size); + memcpy(target->hwinfo, scan_info, be16_to_cpu(scan_info->size)); target->essid_len = strnlen(scan_info->essid, sizeof(scan_info->essid)); target->rate_len = 0; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index bc16889..7b0a644 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -504,8 +504,6 @@ static int geneve_gro_complete(struct sk_buff *skb, int nhoff, int gh_len; int err = -ENOSYS; - udp_tunnel_gro_complete(skb, nhoff); - gh = (struct genevehdr *)(skb->data + nhoff); gh_len = geneve_hlen(gh); type = gh->proto_type; @@ -516,6 +514,9 @@ static int geneve_gro_complete(struct sk_buff *skb, int nhoff, err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); rcu_read_unlock(); + + skb_set_inner_mac_header(skb, nhoff + gh_len); + return err; } diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index 72c9f1f..7c78307 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -635,10 +635,10 @@ static int receive(struct net_device *dev, int cnt) #ifdef __i386__ #include <asm/msr.h> -#define GETTICK(x) \ -({ \ - if (cpu_has_tsc) \ - x = (unsigned int)rdtsc(); \ +#define GETTICK(x) \ +({ \ + if (boot_cpu_has(X86_FEATURE_TSC)) \ + x = (unsigned int)rdtsc(); \ }) #else /* __i386__ */ #define GETTICK(x) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index c638561..92eaab95 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -85,7 +85,7 @@ struct gcm_iv { * @tfm: crypto struct, key storage */ struct macsec_key { - u64 id; + u8 id[MACSEC_KEYID_LEN]; struct crypto_aead *tfm; }; @@ -1529,7 +1529,8 @@ static const struct nla_policy macsec_genl_sa_policy[NUM_MACSEC_SA_ATTR] = { [MACSEC_SA_ATTR_AN] = { .type = NLA_U8 }, [MACSEC_SA_ATTR_ACTIVE] = { .type = NLA_U8 }, [MACSEC_SA_ATTR_PN] = { .type = NLA_U32 }, - [MACSEC_SA_ATTR_KEYID] = { .type = NLA_U64 }, + [MACSEC_SA_ATTR_KEYID] = { .type = NLA_BINARY, + .len = MACSEC_KEYID_LEN, }, [MACSEC_SA_ATTR_KEY] = { .type = NLA_BINARY, .len = MACSEC_MAX_KEY_LEN, }, }; @@ -1576,6 +1577,9 @@ static bool validate_add_rxsa(struct nlattr **attrs) return false; } + if (nla_len(attrs[MACSEC_SA_ATTR_KEYID]) != MACSEC_KEYID_LEN) + return false; + return true; } @@ -1641,7 +1645,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) rx_sa->active = !!nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); - rx_sa->key.id = nla_get_u64(tb_sa[MACSEC_SA_ATTR_KEYID]); + nla_memcpy(rx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEY], MACSEC_KEYID_LEN); rx_sa->sc = rx_sc; rcu_assign_pointer(rx_sc->sa[assoc_num], rx_sa); @@ -1722,6 +1726,9 @@ static bool validate_add_txsa(struct nlattr **attrs) return false; } + if (nla_len(attrs[MACSEC_SA_ATTR_KEYID]) != MACSEC_KEYID_LEN) + return false; + return true; } @@ -1777,7 +1784,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; } - tx_sa->key.id = nla_get_u64(tb_sa[MACSEC_SA_ATTR_KEYID]); + nla_memcpy(tx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEY], MACSEC_KEYID_LEN); spin_lock_bh(&tx_sa->lock); tx_sa->next_pn = nla_get_u32(tb_sa[MACSEC_SA_ATTR_PN]); @@ -2318,7 +2325,7 @@ static int dump_secy(struct macsec_secy *secy, struct net_device *dev, if (nla_put_u8(skb, MACSEC_SA_ATTR_AN, i) || nla_put_u32(skb, MACSEC_SA_ATTR_PN, tx_sa->next_pn) || - nla_put_u64(skb, MACSEC_SA_ATTR_KEYID, tx_sa->key.id) || + nla_put(skb, MACSEC_SA_ATTR_KEYID, MACSEC_KEYID_LEN, tx_sa->key.id) || nla_put_u8(skb, MACSEC_SA_ATTR_ACTIVE, tx_sa->active)) { nla_nest_cancel(skb, txsa_nest); nla_nest_cancel(skb, txsa_list); @@ -2419,7 +2426,7 @@ static int dump_secy(struct macsec_secy *secy, struct net_device *dev, if (nla_put_u8(skb, MACSEC_SA_ATTR_AN, i) || nla_put_u32(skb, MACSEC_SA_ATTR_PN, rx_sa->next_pn) || - nla_put_u64(skb, MACSEC_SA_ATTR_KEYID, rx_sa->key.id) || + nla_put(skb, MACSEC_SA_ATTR_KEYID, MACSEC_KEYID_LEN, rx_sa->key.id) || nla_put_u8(skb, MACSEC_SA_ATTR_ACTIVE, rx_sa->active)) { nla_nest_cancel(skb, rxsa_nest); nla_nest_cancel(skb, rxsc_nest); diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 95394ed..9a35aa4 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -373,7 +373,7 @@ static rx_handler_result_t macvtap_handle_frame(struct sk_buff **pskb) goto wake_up; } - kfree_skb(skb); + consume_skb(skb); while (segs) { struct sk_buff *nskb = segs->next; diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index b3ffaee..f279a89 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -359,27 +359,25 @@ static void at803x_link_change_notify(struct phy_device *phydev) * in the FIFO. In such cases, the FIFO enters an error mode it * cannot recover from by software. */ - if (phydev->drv->phy_id == ATH8030_PHY_ID) { - if (phydev->state == PHY_NOLINK) { - if (priv->gpiod_reset && !priv->phy_reset) { - struct at803x_context context; - - at803x_context_save(phydev, &context); - - gpiod_set_value(priv->gpiod_reset, 1); - msleep(1); - gpiod_set_value(priv->gpiod_reset, 0); - msleep(1); - - at803x_context_restore(phydev, &context); - - phydev_dbg(phydev, "%s(): phy was reset\n", - __func__); - priv->phy_reset = true; - } - } else { - priv->phy_reset = false; + if (phydev->state == PHY_NOLINK) { + if (priv->gpiod_reset && !priv->phy_reset) { + struct at803x_context context; + + at803x_context_save(phydev, &context); + + gpiod_set_value(priv->gpiod_reset, 1); + msleep(1); + gpiod_set_value(priv->gpiod_reset, 0); + msleep(1); + + at803x_context_restore(phydev, &context); + + phydev_dbg(phydev, "%s(): phy was reset\n", + __func__); + priv->phy_reset = true; } + } else { + priv->phy_reset = false; } } @@ -391,7 +389,6 @@ static struct phy_driver at803x_driver[] = { .phy_id_mask = 0xffffffef, .probe = at803x_probe, .config_init = at803x_config_init, - .link_change_notify = at803x_link_change_notify, .set_wol = at803x_set_wol, .get_wol = at803x_get_wol, .suspend = at803x_suspend, @@ -427,7 +424,6 @@ static struct phy_driver at803x_driver[] = { .phy_id_mask = 0xffffffef, .probe = at803x_probe, .config_init = at803x_config_init, - .link_change_notify = at803x_link_change_notify, .set_wol = at803x_set_wol, .get_wol = at803x_get_wol, .suspend = at803x_suspend, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 5590b9c..445fc5a 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -790,9 +790,11 @@ void phy_start(struct phy_device *phydev) break; case PHY_HALTED: /* make sure interrupts are re-enabled for the PHY */ - err = phy_enable_interrupts(phydev); - if (err < 0) - break; + if (phydev->irq != PHY_POLL) { + err = phy_enable_interrupts(phydev); + if (err < 0) + break; + } phydev->state = PHY_RESUMING; do_resume = true; diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index f20890e..f64778a 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -269,6 +269,7 @@ struct skb_data { /* skb->cb is one of these */ struct lan78xx_net *dev; enum skb_state state; size_t length; + int num_of_packet; }; struct usb_context { @@ -1803,7 +1804,34 @@ static void lan78xx_remove_mdio(struct lan78xx_net *dev) static void lan78xx_link_status_change(struct net_device *net) { - /* nothing to do */ + struct phy_device *phydev = net->phydev; + int ret, temp; + + /* At forced 100 F/H mode, chip may fail to set mode correctly + * when cable is switched between long(~50+m) and short one. + * As workaround, set to 10 before setting to 100 + * at forced 100 F/H mode. + */ + if (!phydev->autoneg && (phydev->speed == 100)) { + /* disable phy interrupt */ + temp = phy_read(phydev, LAN88XX_INT_MASK); + temp &= ~LAN88XX_INT_MASK_MDINTPIN_EN_; + ret = phy_write(phydev, LAN88XX_INT_MASK, temp); + + temp = phy_read(phydev, MII_BMCR); + temp &= ~(BMCR_SPEED100 | BMCR_SPEED1000); + phy_write(phydev, MII_BMCR, temp); /* set to 10 first */ + temp |= BMCR_SPEED100; + phy_write(phydev, MII_BMCR, temp); /* set to 100 later */ + + /* clear pending interrupt generated while workaround */ + temp = phy_read(phydev, LAN88XX_INT_STS); + + /* enable phy interrupt back */ + temp = phy_read(phydev, LAN88XX_INT_MASK); + temp |= LAN88XX_INT_MASK_MDINTPIN_EN_; + ret = phy_write(phydev, LAN88XX_INT_MASK, temp); + } } static int lan78xx_phy_init(struct lan78xx_net *dev) @@ -2464,7 +2492,7 @@ static void tx_complete(struct urb *urb) struct lan78xx_net *dev = entry->dev; if (urb->status == 0) { - dev->net->stats.tx_packets++; + dev->net->stats.tx_packets += entry->num_of_packet; dev->net->stats.tx_bytes += entry->length; } else { dev->net->stats.tx_errors++; @@ -2681,10 +2709,11 @@ void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb) return; } - skb->protocol = eth_type_trans(skb, dev->net); dev->net->stats.rx_packets++; dev->net->stats.rx_bytes += skb->len; + skb->protocol = eth_type_trans(skb, dev->net); + netif_dbg(dev, rx_status, dev->net, "< rx, len %zu, type 0x%x\n", skb->len + sizeof(struct ethhdr), skb->protocol); memset(skb->cb, 0, sizeof(struct skb_data)); @@ -2934,13 +2963,16 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) skb_totallen = 0; pkt_cnt = 0; + count = 0; + length = 0; for (skb = tqp->next; pkt_cnt < tqp->qlen; skb = skb->next) { if (skb_is_gso(skb)) { if (pkt_cnt) { /* handle previous packets first */ break; } - length = skb->len; + count = 1; + length = skb->len - TX_OVERHEAD; skb2 = skb_dequeue(tqp); goto gso_skb; } @@ -2961,14 +2993,13 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) for (count = pos = 0; count < pkt_cnt; count++) { skb2 = skb_dequeue(tqp); if (skb2) { + length += (skb2->len - TX_OVERHEAD); memcpy(skb->data + pos, skb2->data, skb2->len); pos += roundup(skb2->len, sizeof(u32)); dev_kfree_skb(skb2); } } - length = skb_totallen; - gso_skb: urb = usb_alloc_urb(0, GFP_ATOMIC); if (!urb) { @@ -2980,6 +3011,7 @@ gso_skb: entry->urb = urb; entry->dev = dev; entry->length = length; + entry->num_of_packet = count; spin_lock_irqsave(&dev->txq.lock, flags); ret = usb_autopm_get_interface_async(dev->intf); diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index f840802..82129ee 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -411,7 +411,7 @@ static int enable_net_traffic(struct net_device *dev, struct usb_device *usb) int ret; read_mii_word(pegasus, pegasus->phy, MII_LPA, &linkpart); - data[0] = 0xc9; + data[0] = 0xc8; /* TX & RX enable, append status, no CRC */ data[1] = 0; if (linkpart & (ADVERTISE_100FULL | ADVERTISE_10FULL)) data[1] |= 0x20; /* set full duplex */ @@ -497,7 +497,7 @@ static void read_bulk_callback(struct urb *urb) pkt_len = buf[count - 3] << 8; pkt_len += buf[count - 4]; pkt_len &= 0xfff; - pkt_len -= 8; + pkt_len -= 4; } /* @@ -528,7 +528,7 @@ static void read_bulk_callback(struct urb *urb) goon: usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb, usb_rcvbulkpipe(pegasus->usb, 1), - pegasus->rx_skb->data, PEGASUS_MTU + 8, + pegasus->rx_skb->data, PEGASUS_MTU, read_bulk_callback, pegasus); rx_status = usb_submit_urb(pegasus->rx_urb, GFP_ATOMIC); if (rx_status == -ENODEV) @@ -569,7 +569,7 @@ static void rx_fixup(unsigned long data) } usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb, usb_rcvbulkpipe(pegasus->usb, 1), - pegasus->rx_skb->data, PEGASUS_MTU + 8, + pegasus->rx_skb->data, PEGASUS_MTU, read_bulk_callback, pegasus); try_again: status = usb_submit_urb(pegasus->rx_urb, GFP_ATOMIC); @@ -823,7 +823,7 @@ static int pegasus_open(struct net_device *net) usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb, usb_rcvbulkpipe(pegasus->usb, 1), - pegasus->rx_skb->data, PEGASUS_MTU + 8, + pegasus->rx_skb->data, PEGASUS_MTU, read_bulk_callback, pegasus); if ((res = usb_submit_urb(pegasus->rx_urb, GFP_KERNEL))) { if (res == -ENODEV) diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 30033db..c369db9 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -29,6 +29,7 @@ #include <linux/crc32.h> #include <linux/usb/usbnet.h> #include <linux/slab.h> +#include <linux/of_net.h> #include "smsc75xx.h" #define SMSC_CHIPNAME "smsc75xx" @@ -761,6 +762,15 @@ static int smsc75xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) static void smsc75xx_init_mac_address(struct usbnet *dev) { + const u8 *mac_addr; + + /* maybe the boot loader passed the MAC address in devicetree */ + mac_addr = of_get_mac_address(dev->udev->dev.of_node); + if (mac_addr) { + memcpy(dev->net->dev_addr, mac_addr, ETH_ALEN); + return; + } + /* try reading mac address from EEPROM */ if (smsc75xx_read_eeprom(dev, EEPROM_MAC_OFFSET, ETH_ALEN, dev->net->dev_addr) == 0) { @@ -772,7 +782,7 @@ static void smsc75xx_init_mac_address(struct usbnet *dev) } } - /* no eeprom, or eeprom values are invalid. generate random MAC */ + /* no useful static MAC address found. generate a random one */ eth_hw_addr_random(dev->net); netif_dbg(dev, ifup, dev->net, "MAC address set to eth_random_addr\n"); } diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 66b3ab9..2edc2bc 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -29,6 +29,7 @@ #include <linux/crc32.h> #include <linux/usb/usbnet.h> #include <linux/slab.h> +#include <linux/of_net.h> #include "smsc95xx.h" #define SMSC_CHIPNAME "smsc95xx" @@ -765,6 +766,15 @@ static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) static void smsc95xx_init_mac_address(struct usbnet *dev) { + const u8 *mac_addr; + + /* maybe the boot loader passed the MAC address in devicetree */ + mac_addr = of_get_mac_address(dev->udev->dev.of_node); + if (mac_addr) { + memcpy(dev->net->dev_addr, mac_addr, ETH_ALEN); + return; + } + /* try reading mac address from EEPROM */ if (smsc95xx_read_eeprom(dev, EEPROM_MAC_OFFSET, ETH_ALEN, dev->net->dev_addr) == 0) { @@ -775,7 +785,7 @@ static void smsc95xx_init_mac_address(struct usbnet *dev) } } - /* no eeprom, or eeprom values are invalid. generate random MAC */ + /* no useful static MAC address found. generate a random one */ eth_hw_addr_random(dev->net); netif_dbg(dev, ifup, dev->net, "MAC address set to eth_random_addr\n"); } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 1c0fa36..8ac261a 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -616,8 +616,9 @@ out: static int vxlan_gro_complete(struct sk_buff *skb, int nhoff, struct udp_offload *uoff) { - udp_tunnel_gro_complete(skb, nhoff); - + /* Sets 'skb->inner_mac_header' since we are always called with + * 'skb->encapsulation' set. + */ return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); } diff --git a/drivers/net/wireless/ath/ath9k/ar5008_phy.c b/drivers/net/wireless/ath/ath9k/ar5008_phy.c index 8f87930..1b271b9 100644 --- a/drivers/net/wireless/ath/ath9k/ar5008_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar5008_phy.c @@ -274,6 +274,9 @@ void ar5008_hw_cmn_spur_mitigate(struct ath_hw *ah, }; static const int inc[4] = { 0, 100, 0, 0 }; + memset(&mask_m, 0, sizeof(int8_t) * 123); + memset(&mask_p, 0, sizeof(int8_t) * 123); + cur_bin = -6000; upper = bin + 100; lower = bin - 100; @@ -424,14 +427,9 @@ static void ar5008_hw_spur_mitigate(struct ath_hw *ah, int tmp, new; int i; - int8_t mask_m[123]; - int8_t mask_p[123]; int cur_bb_spur; bool is2GHz = IS_CHAN_2GHZ(chan); - memset(&mask_m, 0, sizeof(int8_t) * 123); - memset(&mask_p, 0, sizeof(int8_t) * 123); - for (i = 0; i < AR_EEPROM_MODAL_SPURS; i++) { cur_bb_spur = ah->eep_ops->get_spur_channel(ah, i, is2GHz); if (AR_NO_SPUR == cur_bb_spur) diff --git a/drivers/net/wireless/ath/ath9k/ar9002_phy.c b/drivers/net/wireless/ath/ath9k/ar9002_phy.c index db66245..53d7445 100644 --- a/drivers/net/wireless/ath/ath9k/ar9002_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar9002_phy.c @@ -178,14 +178,9 @@ static void ar9002_hw_spur_mitigate(struct ath_hw *ah, int i; struct chan_centers centers; - int8_t mask_m[123]; - int8_t mask_p[123]; int cur_bb_spur; bool is2GHz = IS_CHAN_2GHZ(chan); - memset(&mask_m, 0, sizeof(int8_t) * 123); - memset(&mask_p, 0, sizeof(int8_t) * 123); - ath9k_hw_get_channel_centers(ah, chan, ¢ers); freq = centers.synth_center; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c index 97be104..b5c57ee 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c @@ -93,7 +93,7 @@ #define IWL8260_SMEM_OFFSET 0x400000 #define IWL8260_SMEM_LEN 0x68000 -#define IWL8000_FW_PRE "iwlwifi-8000" +#define IWL8000_FW_PRE "iwlwifi-8000C-" #define IWL8000_MODULE_FIRMWARE(api) \ IWL8000_FW_PRE "-" __stringify(api) ".ucode" diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index f899666..9e45bf9 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -238,19 +238,6 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first) snprintf(drv->firmware_name, sizeof(drv->firmware_name), "%s%s.ucode", name_pre, tag); - /* - * Starting 8000B - FW name format has changed. This overwrites the - * previous name and uses the new format. - */ - if (drv->trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) { - char rev_step = 'A' + CSR_HW_REV_STEP(drv->trans->hw_rev); - - if (rev_step != 'A') - snprintf(drv->firmware_name, - sizeof(drv->firmware_name), "%s%c-%s.ucode", - name_pre, rev_step, tag); - } - IWL_DEBUG_INFO(drv, "attempting to load firmware %s'%s'\n", (drv->fw_index == UCODE_EXPERIMENTAL_INDEX) ? "EXPERIMENTAL " : "", @@ -1060,11 +1047,18 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, return -EINVAL; } - if (WARN(fw_has_capa(capa, IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT) && - !gscan_capa, - "GSCAN is supported but capabilities TLV is unavailable\n")) + /* + * If ucode advertises that it supports GSCAN but GSCAN + * capabilities TLV is not present, or if it has an old format, + * warn and continue without GSCAN. + */ + if (fw_has_capa(capa, IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT) && + !gscan_capa) { + IWL_DEBUG_INFO(drv, + "GSCAN is supported but capabilities TLV is unavailable\n"); __clear_bit((__force long)IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT, capa->_capa); + } return 0; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c index 4856eac..6938cd3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c @@ -526,7 +526,8 @@ void iwl_mvm_fw_error_dump(struct iwl_mvm *mvm) file_len += sizeof(*dump_data) + sizeof(*dump_mem) + sram2_len; /* Make room for fw's virtual image pages, if it exists */ - if (mvm->fw->img[mvm->cur_ucode].paging_mem_size) + if (mvm->fw->img[mvm->cur_ucode].paging_mem_size && + mvm->fw_paging_db[0].fw_paging_block) file_len += mvm->num_of_paging_blk * (sizeof(*dump_data) + sizeof(struct iwl_fw_error_dump_paging) + @@ -643,7 +644,8 @@ void iwl_mvm_fw_error_dump(struct iwl_mvm *mvm) } /* Dump fw's virtual image */ - if (mvm->fw->img[mvm->cur_ucode].paging_mem_size) { + if (mvm->fw->img[mvm->cur_ucode].paging_mem_size && + mvm->fw_paging_db[0].fw_paging_block) { for (i = 1; i < mvm->num_of_paging_blk + 1; i++) { struct iwl_fw_error_dump_paging *paging; struct page *pages = diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 594cd0d..09d895f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -144,9 +144,11 @@ void iwl_free_fw_paging(struct iwl_mvm *mvm) __free_pages(mvm->fw_paging_db[i].fw_paging_block, get_order(mvm->fw_paging_db[i].fw_paging_size)); + mvm->fw_paging_db[i].fw_paging_block = NULL; } kfree(mvm->trans->paging_download_buf); mvm->trans->paging_download_buf = NULL; + mvm->trans->paging_db = NULL; memset(mvm->fw_paging_db, 0, sizeof(mvm->fw_paging_db)); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 75870e6..34731e2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -105,6 +105,7 @@ void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb, struct iwl_tx_cmd *tx_cmd, struct ieee80211_tx_info *info, u8 sta_id) { + struct ieee80211_tx_info *skb_info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (void *)skb->data; __le16 fc = hdr->frame_control; u32 tx_flags = le32_to_cpu(tx_cmd->tx_flags); @@ -185,7 +186,7 @@ void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb, tx_cmd->tx_flags = cpu_to_le32(tx_flags); /* Total # bytes to be transmitted */ tx_cmd->len = cpu_to_le16((u16)skb->len + - (uintptr_t)info->driver_data[0]); + (uintptr_t)skb_info->driver_data[0]); tx_cmd->next_frame_len = 0; tx_cmd->life_time = cpu_to_le32(TX_CMD_LIFE_TIME_INFINITE); tx_cmd->sta_id = sta_id; @@ -327,10 +328,11 @@ static void iwl_mvm_set_tx_cmd_crypto(struct iwl_mvm *mvm, */ static struct iwl_device_cmd * iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb, - int hdrlen, struct ieee80211_sta *sta, u8 sta_id) + struct ieee80211_tx_info *info, int hdrlen, + struct ieee80211_sta *sta, u8 sta_id) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_tx_info *skb_info = IEEE80211_SKB_CB(skb); struct iwl_device_cmd *dev_cmd; struct iwl_tx_cmd *tx_cmd; @@ -350,10 +352,10 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb, iwl_mvm_set_tx_cmd_rate(mvm, tx_cmd, info, sta, hdr->frame_control); - memset(&info->status, 0, sizeof(info->status)); - memset(info->driver_data, 0, sizeof(info->driver_data)); + memset(&skb_info->status, 0, sizeof(skb_info->status)); + memset(skb_info->driver_data, 0, sizeof(skb_info->driver_data)); - info->driver_data[1] = dev_cmd; + skb_info->driver_data[1] = dev_cmd; return dev_cmd; } @@ -361,22 +363,25 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb, int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_tx_info *skb_info = IEEE80211_SKB_CB(skb); + struct ieee80211_tx_info info; struct iwl_device_cmd *dev_cmd; struct iwl_tx_cmd *tx_cmd; u8 sta_id; int hdrlen = ieee80211_hdrlen(hdr->frame_control); - if (WARN_ON_ONCE(info->flags & IEEE80211_TX_CTL_AMPDU)) + memcpy(&info, skb->cb, sizeof(info)); + + if (WARN_ON_ONCE(info.flags & IEEE80211_TX_CTL_AMPDU)) return -1; - if (WARN_ON_ONCE(info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM && - (!info->control.vif || - info->hw_queue != info->control.vif->cab_queue))) + if (WARN_ON_ONCE(info.flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM && + (!info.control.vif || + info.hw_queue != info.control.vif->cab_queue))) return -1; /* This holds the amsdu headers length */ - info->driver_data[0] = (void *)(uintptr_t)0; + skb_info->driver_data[0] = (void *)(uintptr_t)0; /* * IWL_MVM_OFFCHANNEL_QUEUE is used for ROC packets that can be used @@ -385,7 +390,7 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) * and hence needs to be sent on the aux queue */ if (IEEE80211_SKB_CB(skb)->hw_queue == IWL_MVM_OFFCHANNEL_QUEUE && - info->control.vif->type == NL80211_IFTYPE_STATION) + info.control.vif->type == NL80211_IFTYPE_STATION) IEEE80211_SKB_CB(skb)->hw_queue = mvm->aux_queue; /* @@ -398,14 +403,14 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) * AUX station. */ sta_id = mvm->aux_sta.sta_id; - if (info->control.vif) { + if (info.control.vif) { struct iwl_mvm_vif *mvmvif = - iwl_mvm_vif_from_mac80211(info->control.vif); + iwl_mvm_vif_from_mac80211(info.control.vif); - if (info->control.vif->type == NL80211_IFTYPE_P2P_DEVICE || - info->control.vif->type == NL80211_IFTYPE_AP) + if (info.control.vif->type == NL80211_IFTYPE_P2P_DEVICE || + info.control.vif->type == NL80211_IFTYPE_AP) sta_id = mvmvif->bcast_sta.sta_id; - else if (info->control.vif->type == NL80211_IFTYPE_STATION && + else if (info.control.vif->type == NL80211_IFTYPE_STATION && is_multicast_ether_addr(hdr->addr1)) { u8 ap_sta_id = ACCESS_ONCE(mvmvif->ap_sta_id); @@ -414,19 +419,18 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) } } - IWL_DEBUG_TX(mvm, "station Id %d, queue=%d\n", sta_id, info->hw_queue); + IWL_DEBUG_TX(mvm, "station Id %d, queue=%d\n", sta_id, info.hw_queue); - dev_cmd = iwl_mvm_set_tx_params(mvm, skb, hdrlen, NULL, sta_id); + dev_cmd = iwl_mvm_set_tx_params(mvm, skb, &info, hdrlen, NULL, sta_id); if (!dev_cmd) return -1; - /* From now on, we cannot access info->control */ tx_cmd = (struct iwl_tx_cmd *)dev_cmd->payload; /* Copy MAC header from skb into command buffer */ memcpy(tx_cmd->hdr, hdr, hdrlen); - if (iwl_trans_tx(mvm->trans, skb, dev_cmd, info->hw_queue)) { + if (iwl_trans_tx(mvm->trans, skb, dev_cmd, info.hw_queue)) { iwl_trans_free_tx_cmd(mvm->trans, dev_cmd); return -1; } @@ -445,11 +449,11 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) #ifdef CONFIG_INET static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, + struct ieee80211_tx_info *info, struct ieee80211_sta *sta, struct sk_buff_head *mpdus_skb) { struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (void *)skb->data; unsigned int mss = skb_shinfo(skb)->gso_size; struct sk_buff *tmp, *next; @@ -544,6 +548,8 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, /* This skb fits in one single A-MSDU */ if (num_subframes * mss >= tcp_payload_len) { + struct ieee80211_tx_info *skb_info = IEEE80211_SKB_CB(skb); + /* * Compute the length of all the data added for the A-MSDU. * This will be used to compute the length to write in the TX @@ -552,11 +558,10 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, * already had one set of SNAP / IP / TCP headers. */ num_subframes = DIV_ROUND_UP(tcp_payload_len, mss); - info = IEEE80211_SKB_CB(skb); amsdu_add = num_subframes * sizeof(struct ethhdr) + (num_subframes - 1) * (snap_ip_tcp + pad); /* This holds the amsdu headers length */ - info->driver_data[0] = (void *)(uintptr_t)amsdu_add; + skb_info->driver_data[0] = (void *)(uintptr_t)amsdu_add; __skb_queue_tail(mpdus_skb, skb); return 0; @@ -596,11 +601,14 @@ segment: ip_hdr(tmp)->id = htons(ip_base_id + i * num_subframes); if (tcp_payload_len > mss) { + struct ieee80211_tx_info *skb_info = + IEEE80211_SKB_CB(tmp); + num_subframes = DIV_ROUND_UP(tcp_payload_len, mss); - info = IEEE80211_SKB_CB(tmp); amsdu_add = num_subframes * sizeof(struct ethhdr) + (num_subframes - 1) * (snap_ip_tcp + pad); - info->driver_data[0] = (void *)(uintptr_t)amsdu_add; + skb_info->driver_data[0] = + (void *)(uintptr_t)amsdu_add; skb_shinfo(tmp)->gso_size = mss; } else { qc = ieee80211_get_qos_ctl((void *)tmp->data); @@ -622,6 +630,7 @@ segment: } #else /* CONFIG_INET */ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, + struct ieee80211_tx_info *info, struct ieee80211_sta *sta, struct sk_buff_head *mpdus_skb) { @@ -636,10 +645,10 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, * Sets the fields in the Tx cmd that are crypto related */ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, + struct ieee80211_tx_info *info, struct ieee80211_sta *sta) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct iwl_mvm_sta *mvmsta; struct iwl_device_cmd *dev_cmd; struct iwl_tx_cmd *tx_cmd; @@ -660,7 +669,8 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, if (WARN_ON_ONCE(mvmsta->sta_id == IWL_MVM_STATION_COUNT)) return -1; - dev_cmd = iwl_mvm_set_tx_params(mvm, skb, hdrlen, sta, mvmsta->sta_id); + dev_cmd = iwl_mvm_set_tx_params(mvm, skb, info, hdrlen, + sta, mvmsta->sta_id); if (!dev_cmd) goto drop; @@ -736,7 +746,8 @@ int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb, struct ieee80211_sta *sta) { struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_tx_info *skb_info = IEEE80211_SKB_CB(skb); + struct ieee80211_tx_info info; struct sk_buff_head mpdus_skbs; unsigned int payload_len; int ret; @@ -747,21 +758,23 @@ int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb, if (WARN_ON_ONCE(mvmsta->sta_id == IWL_MVM_STATION_COUNT)) return -1; + memcpy(&info, skb->cb, sizeof(info)); + /* This holds the amsdu headers length */ - info->driver_data[0] = (void *)(uintptr_t)0; + skb_info->driver_data[0] = (void *)(uintptr_t)0; if (!skb_is_gso(skb)) - return iwl_mvm_tx_mpdu(mvm, skb, sta); + return iwl_mvm_tx_mpdu(mvm, skb, &info, sta); payload_len = skb_tail_pointer(skb) - skb_transport_header(skb) - tcp_hdrlen(skb) + skb->data_len; if (payload_len <= skb_shinfo(skb)->gso_size) - return iwl_mvm_tx_mpdu(mvm, skb, sta); + return iwl_mvm_tx_mpdu(mvm, skb, &info, sta); __skb_queue_head_init(&mpdus_skbs); - ret = iwl_mvm_tx_tso(mvm, skb, sta, &mpdus_skbs); + ret = iwl_mvm_tx_tso(mvm, skb, &info, sta, &mpdus_skbs); if (ret) return ret; @@ -771,7 +784,7 @@ int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb, while (!skb_queue_empty(&mpdus_skbs)) { skb = __skb_dequeue(&mpdus_skbs); - ret = iwl_mvm_tx_mpdu(mvm, skb, sta); + ret = iwl_mvm_tx_mpdu(mvm, skb, &info, sta); if (ret) { __skb_queue_purge(&mpdus_skbs); return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 05b9685..79d7cd7 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -479,8 +479,18 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x24F3, 0x0930, iwl8260_2ac_cfg)}, {IWL_PCI_DEVICE(0x24F3, 0x0000, iwl8265_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FD, 0x0010, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x0110, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x1110, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x1010, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x0050, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x0150, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x9010, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x8110, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x8050, iwl8265_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FD, 0x8010, iwl8265_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FD, 0x0810, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x9110, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x8130, iwl8265_2ac_cfg)}, /* 9000 Series */ {IWL_PCI_DEVICE(0x9DF0, 0x2A10, iwl5165_2ac_cfg)}, diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index b42f260..4412a57 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -711,6 +711,7 @@ static void xenvif_tx_err(struct xenvif_queue *queue, if (cons == end) break; RING_COPY_REQUEST(&queue->tx, cons++, txp); + extra_count = 0; /* only the first frag can have extras */ } while (1); queue->tx.req_cons = cons; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index f798899..92f5365 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -397,10 +397,17 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) */ start += start_pad; npfns = (pmem->size - start_pad - end_trunc - SZ_8K) / SZ_4K; - if (nd_pfn->mode == PFN_MODE_PMEM) - offset = ALIGN(start + SZ_8K + 64 * npfns, nd_pfn->align) + if (nd_pfn->mode == PFN_MODE_PMEM) { + unsigned long memmap_size; + + /* + * vmemmap_populate_hugepages() allocates the memmap array in + * PMD_SIZE chunks. + */ + memmap_size = ALIGN(64 * npfns, PMD_SIZE); + offset = ALIGN(start + SZ_8K + memmap_size, nd_pfn->align) - start; - else if (nd_pfn->mode == PFN_MODE_RAM) + } else if (nd_pfn->mode == PFN_MODE_RAM) offset = ALIGN(start + SZ_8K, nd_pfn->align) - start; else goto err; diff --git a/drivers/nvmem/mxs-ocotp.c b/drivers/nvmem/mxs-ocotp.c index 8ba19bb..2bb3c57 100644 --- a/drivers/nvmem/mxs-ocotp.c +++ b/drivers/nvmem/mxs-ocotp.c @@ -94,7 +94,7 @@ static int mxs_ocotp_read(void *context, const void *reg, size_t reg_size, if (ret) goto close_banks; - while (val_size) { + while (val_size >= reg_size) { if ((offset < OCOTP_DATA_OFFSET) || (offset % 16)) { /* fill up non-data register */ *buf = 0; @@ -103,7 +103,7 @@ static int mxs_ocotp_read(void *context, const void *reg, size_t reg_size, } buf++; - val_size--; + val_size -= reg_size; offset += reg_size; } diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 6c9f546..dd7cdbe 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -294,7 +294,7 @@ void pci_bus_add_device(struct pci_dev *dev) dev->match_driver = true; retval = device_attach(&dev->dev); - if (retval < 0) { + if (retval < 0 && retval != -EPROBE_DEFER) { dev_warn(&dev->dev, "device attach failed (%d)\n", retval); pci_proc_detach_device(dev); pci_remove_sysfs_dev_files(dev); @@ -324,7 +324,9 @@ void pci_bus_add_devices(const struct pci_bus *bus) } list_for_each_entry(dev, &bus->devices, bus_list) { - BUG_ON(!dev->is_added); + /* Skip if device attach failed */ + if (!dev->is_added) + continue; child = dev->subordinate; if (child) pci_bus_add_devices(child); diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index f700908..f2d01d4 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -847,6 +847,14 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu) if (!platform_get_irq(cpu_pmu->plat_device, 0)) cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + /* + * This is a CPU PMU potentially in a heterogeneous configuration (e.g. + * big.LITTLE). This is not an uncore PMU, and we have taken ctx + * sharing into account (e.g. with our pmu::filter_match callback and + * pmu::event_init group validation). + */ + cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_HETEROGENEOUS_CPUS; + return 0; out_unregister: diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index 4429312..2c447130 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -722,9 +722,11 @@ static int atmel_conf_pin_config_group_set(struct pinctrl_dev *pctldev, break; case PIN_CONFIG_BIAS_PULL_UP: conf |= ATMEL_PIO_PUEN_MASK; + conf &= (~ATMEL_PIO_PDEN_MASK); break; case PIN_CONFIG_BIAS_PULL_DOWN: conf |= ATMEL_PIO_PDEN_MASK; + conf &= (~ATMEL_PIO_PUEN_MASK); break; case PIN_CONFIG_DRIVE_OPEN_DRAIN: if (arg == 0) diff --git a/drivers/pnp/pnpbios/core.c b/drivers/pnp/pnpbios/core.c index facd43b..81603d9 100644 --- a/drivers/pnp/pnpbios/core.c +++ b/drivers/pnp/pnpbios/core.c @@ -521,10 +521,11 @@ static int __init pnpbios_init(void) int ret; if (pnpbios_disabled || dmi_check_system(pnpbios_dmi_table) || - paravirt_enabled()) { + arch_pnpbios_disabled()) { printk(KERN_INFO "PnPBIOS: Disabled\n"); return -ENODEV; } + #ifdef CONFIG_PNPACPI if (!acpi_disabled && !pnpacpi_disabled) { pnpbios_disabled = 1; diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c index 8fad0a7..f2201d4 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl.c @@ -34,6 +34,9 @@ #include <asm/processor.h> #include <asm/cpu_device_id.h> +/* Local defines */ +#define MSR_PLATFORM_POWER_LIMIT 0x0000065C + /* bitmasks for RAPL MSRs, used by primitive access functions */ #define ENERGY_STATUS_MASK 0xffffffff @@ -86,6 +89,7 @@ enum rapl_domain_type { RAPL_DOMAIN_PP0, /* core power plane */ RAPL_DOMAIN_PP1, /* graphics uncore */ RAPL_DOMAIN_DRAM,/* DRAM control_type */ + RAPL_DOMAIN_PLATFORM, /* PSys control_type */ RAPL_DOMAIN_MAX, }; @@ -251,9 +255,11 @@ static const char * const rapl_domain_names[] = { "core", "uncore", "dram", + "psys", }; static struct powercap_control_type *control_type; /* PowerCap Controller */ +static struct rapl_domain *platform_rapl_domain; /* Platform (PSys) domain */ /* caller to ensure CPU hotplug lock is held */ static struct rapl_package *find_package_by_id(int id) @@ -409,6 +415,14 @@ static const struct powercap_zone_ops zone_ops[] = { .set_enable = set_domain_enable, .get_enable = get_domain_enable, }, + /* RAPL_DOMAIN_PLATFORM */ + { + .get_energy_uj = get_energy_counter, + .get_max_energy_range_uj = get_max_energy_counter, + .release = release_zone, + .set_enable = set_domain_enable, + .get_enable = get_domain_enable, + }, }; static int set_power_limit(struct powercap_zone *power_zone, int id, @@ -1160,6 +1174,13 @@ static int rapl_unregister_powercap(void) powercap_unregister_zone(control_type, &rd_package->power_zone); } + + if (platform_rapl_domain) { + powercap_unregister_zone(control_type, + &platform_rapl_domain->power_zone); + kfree(platform_rapl_domain); + } + powercap_unregister_control_type(control_type); return 0; @@ -1239,6 +1260,47 @@ err_cleanup: return ret; } +static int rapl_register_psys(void) +{ + struct rapl_domain *rd; + struct powercap_zone *power_zone; + u64 val; + + if (rdmsrl_safe_on_cpu(0, MSR_PLATFORM_ENERGY_STATUS, &val) || !val) + return -ENODEV; + + if (rdmsrl_safe_on_cpu(0, MSR_PLATFORM_POWER_LIMIT, &val) || !val) + return -ENODEV; + + rd = kzalloc(sizeof(*rd), GFP_KERNEL); + if (!rd) + return -ENOMEM; + + rd->name = rapl_domain_names[RAPL_DOMAIN_PLATFORM]; + rd->id = RAPL_DOMAIN_PLATFORM; + rd->msrs[0] = MSR_PLATFORM_POWER_LIMIT; + rd->msrs[1] = MSR_PLATFORM_ENERGY_STATUS; + rd->rpl[0].prim_id = PL1_ENABLE; + rd->rpl[0].name = pl1_name; + rd->rpl[1].prim_id = PL2_ENABLE; + rd->rpl[1].name = pl2_name; + rd->rp = find_package_by_id(0); + + power_zone = powercap_register_zone(&rd->power_zone, control_type, + "psys", NULL, + &zone_ops[RAPL_DOMAIN_PLATFORM], + 2, &constraint_ops); + + if (IS_ERR(power_zone)) { + kfree(rd); + return PTR_ERR(power_zone); + } + + platform_rapl_domain = rd; + + return 0; +} + static int rapl_register_powercap(void) { struct rapl_domain *rd; @@ -1255,6 +1317,10 @@ static int rapl_register_powercap(void) list_for_each_entry(rp, &rapl_packages, plist) if (rapl_package_register_powercap(rp)) goto err_cleanup_package; + + /* Don't bail out if PSys is not supported */ + rapl_register_psys(); + return ret; err_cleanup_package: @@ -1289,6 +1355,9 @@ static int rapl_check_domain(int cpu, int domain) case RAPL_DOMAIN_DRAM: msr = MSR_DRAM_ENERGY_STATUS; break; + case RAPL_DOMAIN_PLATFORM: + /* PSYS(PLATFORM) is not a CPU domain, so avoid printng error */ + return -EINVAL; default: pr_err("invalid domain id %d\n", domain); return -EINVAL; diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 96168b8..e165b7c 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -126,7 +126,7 @@ struct rio_mport_mapping { struct list_head node; struct mport_dev *md; enum rio_mport_map_dir dir; - u32 rioid; + u16 rioid; u64 rio_addr; dma_addr_t phys_addr; /* for mmap */ void *virt_addr; /* kernel address, for dma_free_coherent */ @@ -137,7 +137,7 @@ struct rio_mport_mapping { struct rio_mport_dma_map { int valid; - uint64_t length; + u64 length; void *vaddr; dma_addr_t paddr; }; @@ -208,7 +208,7 @@ struct mport_cdev_priv { struct kfifo event_fifo; wait_queue_head_t event_rx_wait; spinlock_t fifo_lock; - unsigned int event_mask; /* RIO_DOORBELL, RIO_PORTWRITE */ + u32 event_mask; /* RIO_DOORBELL, RIO_PORTWRITE */ #ifdef CONFIG_RAPIDIO_DMA_ENGINE struct dma_chan *dmach; struct list_head async_list; @@ -276,7 +276,8 @@ static int rio_mport_maint_rd(struct mport_cdev_priv *priv, void __user *arg, return -EFAULT; if ((maint_io.offset % 4) || - (maint_io.length == 0) || (maint_io.length % 4)) + (maint_io.length == 0) || (maint_io.length % 4) || + (maint_io.length + maint_io.offset) > RIO_MAINT_SPACE_SZ) return -EINVAL; buffer = vmalloc(maint_io.length); @@ -298,7 +299,8 @@ static int rio_mport_maint_rd(struct mport_cdev_priv *priv, void __user *arg, offset += 4; } - if (unlikely(copy_to_user(maint_io.buffer, buffer, maint_io.length))) + if (unlikely(copy_to_user((void __user *)(uintptr_t)maint_io.buffer, + buffer, maint_io.length))) ret = -EFAULT; out: vfree(buffer); @@ -319,7 +321,8 @@ static int rio_mport_maint_wr(struct mport_cdev_priv *priv, void __user *arg, return -EFAULT; if ((maint_io.offset % 4) || - (maint_io.length == 0) || (maint_io.length % 4)) + (maint_io.length == 0) || (maint_io.length % 4) || + (maint_io.length + maint_io.offset) > RIO_MAINT_SPACE_SZ) return -EINVAL; buffer = vmalloc(maint_io.length); @@ -327,7 +330,8 @@ static int rio_mport_maint_wr(struct mport_cdev_priv *priv, void __user *arg, return -ENOMEM; length = maint_io.length; - if (unlikely(copy_from_user(buffer, maint_io.buffer, length))) { + if (unlikely(copy_from_user(buffer, + (void __user *)(uintptr_t)maint_io.buffer, length))) { ret = -EFAULT; goto out; } @@ -360,7 +364,7 @@ out: */ static int rio_mport_create_outbound_mapping(struct mport_dev *md, struct file *filp, - u32 rioid, u64 raddr, u32 size, + u16 rioid, u64 raddr, u32 size, dma_addr_t *paddr) { struct rio_mport *mport = md->mport; @@ -369,7 +373,7 @@ rio_mport_create_outbound_mapping(struct mport_dev *md, struct file *filp, rmcd_debug(OBW, "did=%d ra=0x%llx sz=0x%x", rioid, raddr, size); - map = kzalloc(sizeof(struct rio_mport_mapping), GFP_KERNEL); + map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) return -ENOMEM; @@ -394,7 +398,7 @@ err_map_outb: static int rio_mport_get_outbound_mapping(struct mport_dev *md, struct file *filp, - u32 rioid, u64 raddr, u32 size, + u16 rioid, u64 raddr, u32 size, dma_addr_t *paddr) { struct rio_mport_mapping *map; @@ -433,7 +437,7 @@ static int rio_mport_obw_map(struct file *filp, void __user *arg) dma_addr_t paddr; int ret; - if (unlikely(copy_from_user(&map, arg, sizeof(struct rio_mmap)))) + if (unlikely(copy_from_user(&map, arg, sizeof(map)))) return -EFAULT; rmcd_debug(OBW, "did=%d ra=0x%llx sz=0x%llx", @@ -448,7 +452,7 @@ static int rio_mport_obw_map(struct file *filp, void __user *arg) map.handle = paddr; - if (unlikely(copy_to_user(arg, &map, sizeof(struct rio_mmap)))) + if (unlikely(copy_to_user(arg, &map, sizeof(map)))) return -EFAULT; return 0; } @@ -469,7 +473,7 @@ static int rio_mport_obw_free(struct file *filp, void __user *arg) if (!md->mport->ops->unmap_outb) return -EPROTONOSUPPORT; - if (copy_from_user(&handle, arg, sizeof(u64))) + if (copy_from_user(&handle, arg, sizeof(handle))) return -EFAULT; rmcd_debug(OBW, "h=0x%llx", handle); @@ -498,9 +502,9 @@ static int rio_mport_obw_free(struct file *filp, void __user *arg) static int maint_hdid_set(struct mport_cdev_priv *priv, void __user *arg) { struct mport_dev *md = priv->md; - uint16_t hdid; + u16 hdid; - if (copy_from_user(&hdid, arg, sizeof(uint16_t))) + if (copy_from_user(&hdid, arg, sizeof(hdid))) return -EFAULT; md->mport->host_deviceid = hdid; @@ -520,9 +524,9 @@ static int maint_hdid_set(struct mport_cdev_priv *priv, void __user *arg) static int maint_comptag_set(struct mport_cdev_priv *priv, void __user *arg) { struct mport_dev *md = priv->md; - uint32_t comptag; + u32 comptag; - if (copy_from_user(&comptag, arg, sizeof(uint32_t))) + if (copy_from_user(&comptag, arg, sizeof(comptag))) return -EFAULT; rio_local_write_config_32(md->mport, RIO_COMPONENT_TAG_CSR, comptag); @@ -837,7 +841,7 @@ err_out: * @xfer: data transfer descriptor structure */ static int -rio_dma_transfer(struct file *filp, uint32_t transfer_mode, +rio_dma_transfer(struct file *filp, u32 transfer_mode, enum rio_transfer_sync sync, enum dma_data_direction dir, struct rio_transfer_io *xfer) { @@ -875,7 +879,7 @@ rio_dma_transfer(struct file *filp, uint32_t transfer_mode, unsigned long offset; long pinned; - offset = (unsigned long)xfer->loc_addr & ~PAGE_MASK; + offset = (unsigned long)(uintptr_t)xfer->loc_addr & ~PAGE_MASK; nr_pages = PAGE_ALIGN(xfer->length + offset) >> PAGE_SHIFT; page_list = kmalloc_array(nr_pages, @@ -1015,19 +1019,20 @@ static int rio_mport_transfer_ioctl(struct file *filp, void __user *arg) if (unlikely(copy_from_user(&transaction, arg, sizeof(transaction)))) return -EFAULT; - if (transaction.count != 1) + if (transaction.count != 1) /* only single transfer for now */ return -EINVAL; if ((transaction.transfer_mode & priv->md->properties.transfer_mode) == 0) return -ENODEV; - transfer = vmalloc(transaction.count * sizeof(struct rio_transfer_io)); + transfer = vmalloc(transaction.count * sizeof(*transfer)); if (!transfer) return -ENOMEM; - if (unlikely(copy_from_user(transfer, transaction.block, - transaction.count * sizeof(struct rio_transfer_io)))) { + if (unlikely(copy_from_user(transfer, + (void __user *)(uintptr_t)transaction.block, + transaction.count * sizeof(*transfer)))) { ret = -EFAULT; goto out_free; } @@ -1038,8 +1043,9 @@ static int rio_mport_transfer_ioctl(struct file *filp, void __user *arg) ret = rio_dma_transfer(filp, transaction.transfer_mode, transaction.sync, dir, &transfer[i]); - if (unlikely(copy_to_user(transaction.block, transfer, - transaction.count * sizeof(struct rio_transfer_io)))) + if (unlikely(copy_to_user((void __user *)(uintptr_t)transaction.block, + transfer, + transaction.count * sizeof(*transfer)))) ret = -EFAULT; out_free: @@ -1129,11 +1135,11 @@ err_tmo: } static int rio_mport_create_dma_mapping(struct mport_dev *md, struct file *filp, - uint64_t size, struct rio_mport_mapping **mapping) + u64 size, struct rio_mport_mapping **mapping) { struct rio_mport_mapping *map; - map = kzalloc(sizeof(struct rio_mport_mapping), GFP_KERNEL); + map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) return -ENOMEM; @@ -1165,7 +1171,7 @@ static int rio_mport_alloc_dma(struct file *filp, void __user *arg) struct rio_mport_mapping *mapping = NULL; int ret; - if (unlikely(copy_from_user(&map, arg, sizeof(struct rio_dma_mem)))) + if (unlikely(copy_from_user(&map, arg, sizeof(map)))) return -EFAULT; ret = rio_mport_create_dma_mapping(md, filp, map.length, &mapping); @@ -1174,7 +1180,7 @@ static int rio_mport_alloc_dma(struct file *filp, void __user *arg) map.dma_handle = mapping->phys_addr; - if (unlikely(copy_to_user(arg, &map, sizeof(struct rio_dma_mem)))) { + if (unlikely(copy_to_user(arg, &map, sizeof(map)))) { mutex_lock(&md->buf_mutex); kref_put(&mapping->ref, mport_release_mapping); mutex_unlock(&md->buf_mutex); @@ -1192,7 +1198,7 @@ static int rio_mport_free_dma(struct file *filp, void __user *arg) int ret = -EFAULT; struct rio_mport_mapping *map, *_map; - if (copy_from_user(&handle, arg, sizeof(u64))) + if (copy_from_user(&handle, arg, sizeof(handle))) return -EFAULT; rmcd_debug(EXIT, "filp=%p", filp); @@ -1242,14 +1248,18 @@ static int rio_mport_free_dma(struct file *filp, void __user *arg) static int rio_mport_create_inbound_mapping(struct mport_dev *md, struct file *filp, - u64 raddr, u32 size, + u64 raddr, u64 size, struct rio_mport_mapping **mapping) { struct rio_mport *mport = md->mport; struct rio_mport_mapping *map; int ret; - map = kzalloc(sizeof(struct rio_mport_mapping), GFP_KERNEL); + /* rio_map_inb_region() accepts u32 size */ + if (size > 0xffffffff) + return -EINVAL; + + map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) return -ENOMEM; @@ -1262,7 +1272,7 @@ rio_mport_create_inbound_mapping(struct mport_dev *md, struct file *filp, if (raddr == RIO_MAP_ANY_ADDR) raddr = map->phys_addr; - ret = rio_map_inb_region(mport, map->phys_addr, raddr, size, 0); + ret = rio_map_inb_region(mport, map->phys_addr, raddr, (u32)size, 0); if (ret < 0) goto err_map_inb; @@ -1288,7 +1298,7 @@ err_dma_alloc: static int rio_mport_get_inbound_mapping(struct mport_dev *md, struct file *filp, - u64 raddr, u32 size, + u64 raddr, u64 size, struct rio_mport_mapping **mapping) { struct rio_mport_mapping *map; @@ -1331,7 +1341,7 @@ static int rio_mport_map_inbound(struct file *filp, void __user *arg) if (!md->mport->ops->map_inb) return -EPROTONOSUPPORT; - if (unlikely(copy_from_user(&map, arg, sizeof(struct rio_mmap)))) + if (unlikely(copy_from_user(&map, arg, sizeof(map)))) return -EFAULT; rmcd_debug(IBW, "%s filp=%p", dev_name(&priv->md->dev), filp); @@ -1344,7 +1354,7 @@ static int rio_mport_map_inbound(struct file *filp, void __user *arg) map.handle = mapping->phys_addr; map.rio_addr = mapping->rio_addr; - if (unlikely(copy_to_user(arg, &map, sizeof(struct rio_mmap)))) { + if (unlikely(copy_to_user(arg, &map, sizeof(map)))) { /* Delete mapping if it was created by this request */ if (ret == 0 && mapping->filp == filp) { mutex_lock(&md->buf_mutex); @@ -1375,7 +1385,7 @@ static int rio_mport_inbound_free(struct file *filp, void __user *arg) if (!md->mport->ops->unmap_inb) return -EPROTONOSUPPORT; - if (copy_from_user(&handle, arg, sizeof(u64))) + if (copy_from_user(&handle, arg, sizeof(handle))) return -EFAULT; mutex_lock(&md->buf_mutex); @@ -1401,7 +1411,7 @@ static int rio_mport_inbound_free(struct file *filp, void __user *arg) static int maint_port_idx_get(struct mport_cdev_priv *priv, void __user *arg) { struct mport_dev *md = priv->md; - uint32_t port_idx = md->mport->index; + u32 port_idx = md->mport->index; rmcd_debug(MPORT, "port_index=%d", port_idx); @@ -1451,7 +1461,7 @@ static void rio_mport_doorbell_handler(struct rio_mport *mport, void *dev_id, handled = 0; spin_lock(&data->db_lock); list_for_each_entry(db_filter, &data->doorbells, data_node) { - if (((db_filter->filter.rioid == 0xffffffff || + if (((db_filter->filter.rioid == RIO_INVALID_DESTID || db_filter->filter.rioid == src)) && info >= db_filter->filter.low && info <= db_filter->filter.high) { @@ -1525,6 +1535,9 @@ static int rio_mport_remove_db_filter(struct mport_cdev_priv *priv, if (copy_from_user(&filter, arg, sizeof(filter))) return -EFAULT; + if (filter.low > filter.high) + return -EINVAL; + spin_lock_irqsave(&priv->md->db_lock, flags); list_for_each_entry(db_filter, &priv->db_filters, priv_node) { if (db_filter->filter.rioid == filter.rioid && @@ -1737,10 +1750,10 @@ static int rio_mport_add_riodev(struct mport_cdev_priv *priv, return -EEXIST; } - size = sizeof(struct rio_dev); + size = sizeof(*rdev); mport = md->mport; - destid = (u16)dev_info.destid; - hopcount = (u8)dev_info.hopcount; + destid = dev_info.destid; + hopcount = dev_info.hopcount; if (rio_mport_read_config_32(mport, destid, hopcount, RIO_PEF_CAR, &rval)) @@ -1872,8 +1885,8 @@ static int rio_mport_del_riodev(struct mport_cdev_priv *priv, void __user *arg) do { rdev = rio_get_comptag(dev_info.comptag, rdev); if (rdev && rdev->dev.parent == &mport->net->dev && - rdev->destid == (u16)dev_info.destid && - rdev->hopcount == (u8)dev_info.hopcount) + rdev->destid == dev_info.destid && + rdev->hopcount == dev_info.hopcount) break; } while (rdev); } @@ -2146,8 +2159,8 @@ static long mport_cdev_ioctl(struct file *filp, return maint_port_idx_get(data, (void __user *)arg); case RIO_MPORT_GET_PROPERTIES: md->properties.hdid = md->mport->host_deviceid; - if (copy_to_user((void __user *)arg, &(data->md->properties), - sizeof(data->md->properties))) + if (copy_to_user((void __user *)arg, &(md->properties), + sizeof(md->properties))) return -EFAULT; return 0; case RIO_ENABLE_DOORBELL_RANGE: @@ -2159,11 +2172,11 @@ static long mport_cdev_ioctl(struct file *filp, case RIO_DISABLE_PORTWRITE_RANGE: return rio_mport_remove_pw_filter(data, (void __user *)arg); case RIO_SET_EVENT_MASK: - data->event_mask = arg; + data->event_mask = (u32)arg; return 0; case RIO_GET_EVENT_MASK: if (copy_to_user((void __user *)arg, &data->event_mask, - sizeof(data->event_mask))) + sizeof(u32))) return -EFAULT; return 0; case RIO_MAP_OUTBOUND: @@ -2374,7 +2387,7 @@ static ssize_t mport_write(struct file *filp, const char __user *buf, return -EINVAL; ret = rio_mport_send_doorbell(mport, - (u16)event.u.doorbell.rioid, + event.u.doorbell.rioid, event.u.doorbell.payload); if (ret < 0) return ret; @@ -2421,7 +2434,7 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport) struct mport_dev *md; struct rio_mport_attr attr; - md = kzalloc(sizeof(struct mport_dev), GFP_KERNEL); + md = kzalloc(sizeof(*md), GFP_KERNEL); if (!md) { rmcd_error("Unable allocate a device object"); return NULL; @@ -2470,7 +2483,7 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport) /* The transfer_mode property will be returned through mport query * interface */ -#ifdef CONFIG_PPC /* for now: only on Freescale's SoCs */ +#ifdef CONFIG_FSL_RIO /* for now: only on Freescale's SoCs */ md->properties.transfer_mode |= RIO_TRANSFER_MODE_MAPPED; #else md->properties.transfer_mode |= RIO_TRANSFER_MODE_TRANSFER; diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 40cd894..514a5e8 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -157,7 +157,9 @@ static struct regulator_ops axp20x_ops_sw = { static const struct regulator_linear_range axp20x_ldo4_ranges[] = { REGULATOR_LINEAR_RANGE(1250000, 0x0, 0x0, 0), REGULATOR_LINEAR_RANGE(1300000, 0x1, 0x8, 100000), - REGULATOR_LINEAR_RANGE(2500000, 0x9, 0xf, 100000), + REGULATOR_LINEAR_RANGE(2500000, 0x9, 0x9, 0), + REGULATOR_LINEAR_RANGE(2700000, 0xa, 0xb, 100000), + REGULATOR_LINEAR_RANGE(3000000, 0xc, 0xf, 100000), }; static const struct regulator_desc axp20x_regulators[] = { @@ -215,10 +217,14 @@ static const struct regulator_desc axp22x_regulators[] = { AXP22X_ELDO2_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(1)), AXP_DESC(AXP22X, ELDO3, "eldo3", "eldoin", 700, 3300, 100, AXP22X_ELDO3_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(2)), - AXP_DESC_IO(AXP22X, LDO_IO0, "ldo_io0", "ips", 1800, 3300, 100, + /* Note the datasheet only guarantees reliable operation up to + * 3.3V, this needs to be enforced via dts provided constraints */ + AXP_DESC_IO(AXP22X, LDO_IO0, "ldo_io0", "ips", 700, 3800, 100, AXP22X_LDO_IO0_V_OUT, 0x1f, AXP20X_GPIO0_CTRL, 0x07, AXP22X_IO_ENABLED, AXP22X_IO_DISABLED), - AXP_DESC_IO(AXP22X, LDO_IO1, "ldo_io1", "ips", 1800, 3300, 100, + /* Note the datasheet only guarantees reliable operation up to + * 3.3V, this needs to be enforced via dts provided constraints */ + AXP_DESC_IO(AXP22X, LDO_IO1, "ldo_io1", "ips", 700, 3800, 100, AXP22X_LDO_IO1_V_OUT, 0x1f, AXP20X_GPIO1_CTRL, 0x07, AXP22X_IO_ENABLED, AXP22X_IO_DISABLED), AXP_DESC_FIXED(AXP22X, RTC_LDO, "rtc_ldo", "ips", 3000), diff --git a/drivers/regulator/da9063-regulator.c b/drivers/regulator/da9063-regulator.c index ed9e7e9..c6af343 100644 --- a/drivers/regulator/da9063-regulator.c +++ b/drivers/regulator/da9063-regulator.c @@ -900,4 +900,4 @@ module_exit(da9063_regulator_cleanup); MODULE_AUTHOR("Krystian Garbaciak <krystian.garbaciak@diasemi.com>"); MODULE_DESCRIPTION("DA9063 regulators driver"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("paltform:" DA9063_DRVNAME_REGULATORS); +MODULE_ALIAS("platform:" DA9063_DRVNAME_REGULATORS); diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c index a8718e9..83e89e5 100644 --- a/drivers/regulator/gpio-regulator.c +++ b/drivers/regulator/gpio-regulator.c @@ -162,6 +162,8 @@ of_get_gpio_regulator_config(struct device *dev, struct device_node *np, of_property_read_u32(np, "startup-delay-us", &config->startup_delay); config->enable_gpio = of_get_named_gpio(np, "enable-gpio", 0); + if (config->enable_gpio == -EPROBE_DEFER) + return ERR_PTR(-EPROBE_DEFER); /* Fetch GPIOs. - optional property*/ ret = of_gpio_count(np); diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c index d24e2c7..6dfa350 100644 --- a/drivers/regulator/s2mps11.c +++ b/drivers/regulator/s2mps11.c @@ -308,7 +308,7 @@ static struct regulator_ops s2mps11_buck_ops = { .enable_mask = S2MPS11_ENABLE_MASK \ } -#define regulator_desc_s2mps11_buck6_10(num, min, step) { \ +#define regulator_desc_s2mps11_buck67810(num, min, step) { \ .name = "BUCK"#num, \ .id = S2MPS11_BUCK##num, \ .ops = &s2mps11_buck_ops, \ @@ -324,6 +324,22 @@ static struct regulator_ops s2mps11_buck_ops = { .enable_mask = S2MPS11_ENABLE_MASK \ } +#define regulator_desc_s2mps11_buck9 { \ + .name = "BUCK9", \ + .id = S2MPS11_BUCK9, \ + .ops = &s2mps11_buck_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = MIN_3000_MV, \ + .uV_step = STEP_25_MV, \ + .n_voltages = S2MPS11_BUCK9_N_VOLTAGES, \ + .ramp_delay = S2MPS11_RAMP_DELAY, \ + .vsel_reg = S2MPS11_REG_B9CTRL2, \ + .vsel_mask = S2MPS11_BUCK9_VSEL_MASK, \ + .enable_reg = S2MPS11_REG_B9CTRL1, \ + .enable_mask = S2MPS11_ENABLE_MASK \ +} + static const struct regulator_desc s2mps11_regulators[] = { regulator_desc_s2mps11_ldo(1, STEP_25_MV), regulator_desc_s2mps11_ldo(2, STEP_50_MV), @@ -368,11 +384,11 @@ static const struct regulator_desc s2mps11_regulators[] = { regulator_desc_s2mps11_buck1_4(3), regulator_desc_s2mps11_buck1_4(4), regulator_desc_s2mps11_buck5, - regulator_desc_s2mps11_buck6_10(6, MIN_600_MV, STEP_6_25_MV), - regulator_desc_s2mps11_buck6_10(7, MIN_600_MV, STEP_6_25_MV), - regulator_desc_s2mps11_buck6_10(8, MIN_600_MV, STEP_6_25_MV), - regulator_desc_s2mps11_buck6_10(9, MIN_3000_MV, STEP_25_MV), - regulator_desc_s2mps11_buck6_10(10, MIN_750_MV, STEP_12_5_MV), + regulator_desc_s2mps11_buck67810(6, MIN_600_MV, STEP_6_25_MV), + regulator_desc_s2mps11_buck67810(7, MIN_600_MV, STEP_6_25_MV), + regulator_desc_s2mps11_buck67810(8, MIN_600_MV, STEP_6_25_MV), + regulator_desc_s2mps11_buck9, + regulator_desc_s2mps11_buck67810(10, MIN_750_MV, STEP_12_5_MV), }; static struct regulator_ops s2mps14_reg_ops; diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 8eaed05..a655cf2 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -532,6 +532,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) return SCSI_DH_DEV_TEMP_BUSY; retry: + err = 0; retval = submit_rtpg(sdev, buff, bufflen, &sense_hdr, pg->flags); if (retval) { diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c index 5d0ec42..634254a 100644 --- a/drivers/scsi/qla1280.c +++ b/drivers/scsi/qla1280.c @@ -4214,7 +4214,7 @@ static struct scsi_host_template qla1280_driver_template = { .eh_bus_reset_handler = qla1280_eh_bus_reset, .eh_host_reset_handler = qla1280_eh_adapter_reset, .bios_param = qla1280_biosparam, - .can_queue = 0xfffff, + .can_queue = MAX_OUTSTANDING_COMMANDS, .this_id = -1, .sg_tablesize = SG_ALL, .use_clustering = ENABLE_CLUSTERING, diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 39412c9..c1a2d74 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -385,8 +385,8 @@ static int dspi_transfer_one_message(struct spi_master *master, dspi->cur_chip = spi_get_ctldata(spi); dspi->cs = spi->chip_select; dspi->cs_change = 0; - if (dspi->cur_transfer->transfer_list.next - == &dspi->cur_msg->transfers) + if (list_is_last(&dspi->cur_transfer->transfer_list, + &dspi->cur_msg->transfers) || transfer->cs_change) dspi->cs_change = 1; dspi->void_write_data = dspi->cur_chip->void_write_data; diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index 43a02e3..0caa3c8 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -423,12 +423,16 @@ static void omap2_mcspi_tx_dma(struct spi_device *spi, if (mcspi_dma->dma_tx) { struct dma_async_tx_descriptor *tx; + struct scatterlist sg; dmaengine_slave_config(mcspi_dma->dma_tx, &cfg); - tx = dmaengine_prep_slave_sg(mcspi_dma->dma_tx, xfer->tx_sg.sgl, - xfer->tx_sg.nents, DMA_MEM_TO_DEV, - DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + sg_init_table(&sg, 1); + sg_dma_address(&sg) = xfer->tx_dma; + sg_dma_len(&sg) = xfer->len; + + tx = dmaengine_prep_slave_sg(mcspi_dma->dma_tx, &sg, 1, + DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK); if (tx) { tx->callback = omap2_mcspi_tx_callback; tx->callback_param = spi; @@ -474,15 +478,20 @@ omap2_mcspi_rx_dma(struct spi_device *spi, struct spi_transfer *xfer, if (mcspi_dma->dma_rx) { struct dma_async_tx_descriptor *tx; + struct scatterlist sg; dmaengine_slave_config(mcspi_dma->dma_rx, &cfg); if ((l & OMAP2_MCSPI_CHCONF_TURBO) && mcspi->fifo_depth == 0) dma_count -= es; - tx = dmaengine_prep_slave_sg(mcspi_dma->dma_rx, xfer->rx_sg.sgl, - xfer->rx_sg.nents, DMA_DEV_TO_MEM, - DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + sg_init_table(&sg, 1); + sg_dma_address(&sg) = xfer->rx_dma; + sg_dma_len(&sg) = dma_count; + + tx = dmaengine_prep_slave_sg(mcspi_dma->dma_rx, &sg, 1, + DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT | + DMA_CTRL_ACK); if (tx) { tx->callback = omap2_mcspi_rx_callback; tx->callback_param = spi; @@ -496,6 +505,8 @@ omap2_mcspi_rx_dma(struct spi_device *spi, struct spi_transfer *xfer, omap2_mcspi_set_dma_req(spi, 1, 1); wait_for_completion(&mcspi_dma->dma_rx_completion); + dma_unmap_single(mcspi->dev, xfer->rx_dma, count, + DMA_FROM_DEVICE); if (mcspi->fifo_depth > 0) return count; @@ -608,6 +619,8 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer) if (tx != NULL) { wait_for_completion(&mcspi_dma->dma_tx_completion); + dma_unmap_single(mcspi->dev, xfer->tx_dma, xfer->len, + DMA_TO_DEVICE); if (mcspi->fifo_depth > 0) { irqstat_reg = mcspi->base + OMAP2_MCSPI_IRQSTATUS; @@ -1074,16 +1087,6 @@ static void omap2_mcspi_cleanup(struct spi_device *spi) gpio_free(spi->cs_gpio); } -static bool omap2_mcspi_can_dma(struct spi_master *master, - struct spi_device *spi, - struct spi_transfer *xfer) -{ - if (xfer->len < DMA_MIN_BYTES) - return false; - - return true; -} - static int omap2_mcspi_work_one(struct omap2_mcspi *mcspi, struct spi_device *spi, struct spi_transfer *t) { @@ -1265,6 +1268,32 @@ static int omap2_mcspi_transfer_one(struct spi_master *master, return -EINVAL; } + if (len < DMA_MIN_BYTES) + goto skip_dma_map; + + if (mcspi_dma->dma_tx && tx_buf != NULL) { + t->tx_dma = dma_map_single(mcspi->dev, (void *) tx_buf, + len, DMA_TO_DEVICE); + if (dma_mapping_error(mcspi->dev, t->tx_dma)) { + dev_dbg(mcspi->dev, "dma %cX %d bytes error\n", + 'T', len); + return -EINVAL; + } + } + if (mcspi_dma->dma_rx && rx_buf != NULL) { + t->rx_dma = dma_map_single(mcspi->dev, rx_buf, t->len, + DMA_FROM_DEVICE); + if (dma_mapping_error(mcspi->dev, t->rx_dma)) { + dev_dbg(mcspi->dev, "dma %cX %d bytes error\n", + 'R', len); + if (tx_buf != NULL) + dma_unmap_single(mcspi->dev, t->tx_dma, + len, DMA_TO_DEVICE); + return -EINVAL; + } + } + +skip_dma_map: return omap2_mcspi_work_one(mcspi, spi, t); } @@ -1348,7 +1377,6 @@ static int omap2_mcspi_probe(struct platform_device *pdev) master->transfer_one = omap2_mcspi_transfer_one; master->set_cs = omap2_mcspi_set_cs; master->cleanup = omap2_mcspi_cleanup; - master->can_dma = omap2_mcspi_can_dma; master->dev.of_node = node; master->max_speed_hz = OMAP2_MCSPI_MAX_FREQ; master->min_speed_hz = OMAP2_MCSPI_MAX_FREQ >> 15; diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 85e59a4..86138e4 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -126,7 +126,7 @@ static const struct lpss_config lpss_platforms[] = { .reg_general = -1, .reg_ssp = 0x20, .reg_cs_ctrl = 0x24, - .reg_capabilities = 0xfc, + .reg_capabilities = -1, .rx_threshold = 1, .tx_threshold_lo = 32, .tx_threshold_hi = 56, diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c index eac3c96..443f664 100644 --- a/drivers/spi/spi-ti-qspi.c +++ b/drivers/spi/spi-ti-qspi.c @@ -94,6 +94,7 @@ struct ti_qspi { #define QSPI_FLEN(n) ((n - 1) << 0) #define QSPI_WLEN_MAX_BITS 128 #define QSPI_WLEN_MAX_BYTES 16 +#define QSPI_WLEN_MASK QSPI_WLEN(QSPI_WLEN_MAX_BITS) /* STATUS REGISTER */ #define BUSY 0x01 @@ -235,16 +236,16 @@ static inline int ti_qspi_poll_wc(struct ti_qspi *qspi) return -ETIMEDOUT; } -static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t) +static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t, + int count) { - int wlen, count, xfer_len; + int wlen, xfer_len; unsigned int cmd; const u8 *txbuf; u32 data; txbuf = t->tx_buf; cmd = qspi->cmd | QSPI_WR_SNGL; - count = t->len; wlen = t->bits_per_word >> 3; /* in bytes */ xfer_len = wlen; @@ -304,9 +305,10 @@ static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t) return 0; } -static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t) +static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t, + int count) { - int wlen, count; + int wlen; unsigned int cmd; u8 *rxbuf; @@ -323,7 +325,6 @@ static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t) cmd |= QSPI_RD_SNGL; break; } - count = t->len; wlen = t->bits_per_word >> 3; /* in bytes */ while (count) { @@ -354,12 +355,13 @@ static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t) return 0; } -static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t) +static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t, + int count) { int ret; if (t->tx_buf) { - ret = qspi_write_msg(qspi, t); + ret = qspi_write_msg(qspi, t, count); if (ret) { dev_dbg(qspi->dev, "Error while writing\n"); return ret; @@ -367,7 +369,7 @@ static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t) } if (t->rx_buf) { - ret = qspi_read_msg(qspi, t); + ret = qspi_read_msg(qspi, t, count); if (ret) { dev_dbg(qspi->dev, "Error while reading\n"); return ret; @@ -450,7 +452,8 @@ static int ti_qspi_start_transfer_one(struct spi_master *master, struct spi_device *spi = m->spi; struct spi_transfer *t; int status = 0, ret; - int frame_length; + unsigned int frame_len_words, transfer_len_words; + int wlen; /* setup device control reg */ qspi->dc = 0; @@ -462,14 +465,15 @@ static int ti_qspi_start_transfer_one(struct spi_master *master, if (spi->mode & SPI_CS_HIGH) qspi->dc |= QSPI_CSPOL(spi->chip_select); - frame_length = (m->frame_length << 3) / spi->bits_per_word; - - frame_length = clamp(frame_length, 0, QSPI_FRAME); + frame_len_words = 0; + list_for_each_entry(t, &m->transfers, transfer_list) + frame_len_words += t->len / (t->bits_per_word >> 3); + frame_len_words = min_t(unsigned int, frame_len_words, QSPI_FRAME); /* setup command reg */ qspi->cmd = 0; qspi->cmd |= QSPI_EN_CS(spi->chip_select); - qspi->cmd |= QSPI_FLEN(frame_length); + qspi->cmd |= QSPI_FLEN(frame_len_words); ti_qspi_write(qspi, qspi->dc, QSPI_SPI_DC_REG); @@ -479,16 +483,23 @@ static int ti_qspi_start_transfer_one(struct spi_master *master, ti_qspi_disable_memory_map(spi); list_for_each_entry(t, &m->transfers, transfer_list) { - qspi->cmd |= QSPI_WLEN(t->bits_per_word); + qspi->cmd = ((qspi->cmd & ~QSPI_WLEN_MASK) | + QSPI_WLEN(t->bits_per_word)); + + wlen = t->bits_per_word >> 3; + transfer_len_words = min(t->len / wlen, frame_len_words); - ret = qspi_transfer_msg(qspi, t); + ret = qspi_transfer_msg(qspi, t, transfer_len_words * wlen); if (ret) { dev_dbg(qspi->dev, "transfer message failed\n"); mutex_unlock(&qspi->list_lock); return -EINVAL; } - m->actual_length += t->len; + m->actual_length += transfer_len_words * wlen; + frame_len_words -= transfer_len_words; + if (frame_len_words == 0) + break; } mutex_unlock(&qspi->list_lock); diff --git a/drivers/staging/unisys/visorbus/visorchipset.c b/drivers/staging/unisys/visorbus/visorchipset.c index 5fbda7b..9cf4f84 100644 --- a/drivers/staging/unisys/visorbus/visorchipset.c +++ b/drivers/staging/unisys/visorbus/visorchipset.c @@ -2425,7 +2425,7 @@ static __init uint32_t visorutil_spar_detect(void) { unsigned int eax, ebx, ecx, edx; - if (cpu_has_hypervisor) { + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { /* check the ID */ cpuid(UNISYS_SPAR_LEAF_ID, &eax, &ebx, &ecx, &edx); return (ebx == UNISYS_SPAR_ID_EBX) && diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 14718a9..460c855 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -249,18 +249,12 @@ static int usb_port_runtime_suspend(struct device *dev) return retval; } - -static int usb_port_prepare(struct device *dev) -{ - return 1; -} #endif static const struct dev_pm_ops usb_port_pm_ops = { #ifdef CONFIG_PM .runtime_suspend = usb_port_runtime_suspend, .runtime_resume = usb_port_runtime_resume, - .prepare = usb_port_prepare, #endif }; diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index dcb85e3..479187c3 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -312,13 +312,7 @@ static int usb_dev_uevent(struct device *dev, struct kobj_uevent_env *env) static int usb_dev_prepare(struct device *dev) { - struct usb_device *udev = to_usb_device(dev); - - /* Return 0 if the current wakeup setting is wrong, otherwise 1 */ - if (udev->do_remote_wakeup != device_may_wakeup(dev)) - return 0; - - return 1; + return 0; /* Implement eventually? */ } static void usb_dev_complete(struct device *dev) diff --git a/drivers/usb/musb/jz4740.c b/drivers/usb/musb/jz4740.c index 5e5a8fa..bc88899 100644 --- a/drivers/usb/musb/jz4740.c +++ b/drivers/usb/musb/jz4740.c @@ -83,9 +83,9 @@ static int jz4740_musb_init(struct musb *musb) { usb_phy_generic_register(); musb->xceiv = usb_get_phy(USB_PHY_TYPE_USB2); - if (!musb->xceiv) { + if (IS_ERR(musb->xceiv)) { pr_err("HS UDC: no transceiver configured\n"); - return -ENODEV; + return PTR_ERR(musb->xceiv); } /* Silicon does not implement ConfigData register. diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index 87bd578..152865b 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -1164,12 +1164,12 @@ static int musb_gadget_disable(struct usb_ep *ep) musb_writew(epio, MUSB_RXMAXP, 0); } - musb_ep->desc = NULL; - musb_ep->end_point.desc = NULL; - /* abort all pending DMA and requests */ nuke(musb_ep, -ESHUTDOWN); + musb_ep->desc = NULL; + musb_ep->end_point.desc = NULL; + schedule_work(&musb->irq_work); spin_unlock_irqrestore(&(musb->lock), flags); diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 58487a4..2f8ad7f 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -2735,7 +2735,7 @@ static const struct hc_driver musb_hc_driver = { .description = "musb-hcd", .product_desc = "MUSB HDRC host driver", .hcd_priv_size = sizeof(struct musb *), - .flags = HCD_USB2 | HCD_MEMORY | HCD_BH, + .flags = HCD_USB2 | HCD_MEMORY, /* not using irq handler or reset hooks from usbcore, since * those must be shared with peripheral code for OTG configs diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index dd47823..7c9f25e 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -109,6 +109,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */ { USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */ { USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */ + { USB_DEVICE(0x10C4, 0x82F4) }, /* Starizona MicroTouch */ { USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */ { USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */ { USB_DEVICE(0x10C4, 0x8382) }, /* Cygnal Integrated Products, Inc. */ @@ -118,6 +119,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8418) }, /* IRZ Automation Teleport SG-10 GSM/GPRS Modem */ { USB_DEVICE(0x10C4, 0x846E) }, /* BEI USB Sensor Interface (VCP) */ { USB_DEVICE(0x10C4, 0x8477) }, /* Balluff RFID */ + { USB_DEVICE(0x10C4, 0x84B6) }, /* Starizona Hyperion */ { USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */ { USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */ { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ @@ -141,6 +143,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0xF004) }, /* Elan Digital Systems USBcount50 */ { USB_DEVICE(0x10C5, 0xEA61) }, /* Silicon Labs MobiData GPRS USB Modem */ { USB_DEVICE(0x10CE, 0xEA6A) }, /* Silicon Labs MobiData GPRS USB Modem 100EU */ + { USB_DEVICE(0x12B8, 0xEC60) }, /* Link G4 ECU */ + { USB_DEVICE(0x12B8, 0xEC62) }, /* Link G4+ ECU */ { USB_DEVICE(0x13AD, 0x9999) }, /* Baltech card reader */ { USB_DEVICE(0x1555, 0x0004) }, /* Owen AC4 USB-RS485 Converter */ { USB_DEVICE(0x166A, 0x0201) }, /* Clipsal 5500PACA C-Bus Pascal Automation Controller */ diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index 983280e..e5a391a 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -761,7 +761,7 @@ config FB_VESA config FB_EFI bool "EFI-based Framebuffer Support" - depends on (FB = y) && X86 && EFI + depends on (FB = y) && !IA64 && EFI select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 95d293b..f4c045c 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -6,16 +6,14 @@ * */ -#include <linux/module.h> #include <linux/kernel.h> +#include <linux/efi.h> #include <linux/errno.h> #include <linux/fb.h> #include <linux/platform_device.h> #include <linux/screen_info.h> -#include <linux/dmi.h> -#include <linux/pci.h> #include <video/vga.h> -#include <asm/sysfb.h> +#include <asm/efi.h> static bool request_mem_succeeded = false; @@ -85,21 +83,13 @@ static struct fb_ops efifb_ops = { static int efifb_setup(char *options) { char *this_opt; - int i; if (options && *options) { while ((this_opt = strsep(&options, ",")) != NULL) { if (!*this_opt) continue; - for (i = 0; i < M_UNKNOWN; i++) { - if (efifb_dmi_list[i].base != 0 && - !strcmp(this_opt, efifb_dmi_list[i].optname)) { - screen_info.lfb_base = efifb_dmi_list[i].base; - screen_info.lfb_linelength = efifb_dmi_list[i].stride; - screen_info.lfb_width = efifb_dmi_list[i].width; - screen_info.lfb_height = efifb_dmi_list[i].height; - } - } + efifb_setup_from_dmi(&screen_info, this_opt); + if (!strncmp(this_opt, "base:", 5)) screen_info.lfb_base = simple_strtoul(this_opt+5, NULL, 0); else if (!strncmp(this_opt, "stride:", 7)) @@ -338,5 +328,4 @@ static struct platform_driver efifb_driver = { .remove = efifb_remove, }; -module_platform_driver(efifb_driver); -MODULE_LICENSE("GPL"); +builtin_platform_driver(efifb_driver); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 5c802d4..ca6bfdd 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1006,7 +1006,7 @@ struct virtqueue *vring_create_virtqueue( const char *name) { struct virtqueue *vq; - void *queue; + void *queue = NULL; dma_addr_t dma_addr; size_t queue_size_in_bytes; struct vring vring; diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 9781e0d..d46839f 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -151,6 +151,8 @@ static DECLARE_WAIT_QUEUE_HEAD(balloon_wq); static void balloon_process(struct work_struct *work); static DECLARE_DELAYED_WORK(balloon_worker, balloon_process); +static void release_memory_resource(struct resource *resource); + /* When ballooning out (allocating memory to return to Xen) we don't really want the kernel to try too hard since that can trigger the oom killer. */ #define GFP_BALLOON \ @@ -267,6 +269,20 @@ static struct resource *additional_memory_resource(phys_addr_t size) return NULL; } +#ifdef CONFIG_SPARSEMEM + { + unsigned long limit = 1UL << (MAX_PHYSMEM_BITS - PAGE_SHIFT); + unsigned long pfn = res->start >> PAGE_SHIFT; + + if (pfn > limit) { + pr_err("New System RAM resource outside addressable RAM (%lu > %lu)\n", + pfn, limit); + release_memory_resource(res); + return NULL; + } + } +#endif + return res; } diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c index be7e56a..e9d2135 100644 --- a/drivers/xen/efi.c +++ b/drivers/xen/efi.c @@ -316,7 +316,6 @@ static const struct efi efi_xen __initconst = { .get_next_high_mono_count = xen_efi_get_next_high_mono_count, .reset_system = NULL, /* Functionality provided by Xen. */ .set_virtual_address_map = NULL, /* Not used under Xen. */ - .memmap = NULL, /* Not used under Xen. */ .flags = 0 /* Initialized later. */ }; diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index 38272ad..f4edd6d 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -316,7 +316,6 @@ static int evtchn_resize_ring(struct per_user_data *u) { unsigned int new_size; evtchn_port_t *new_ring, *old_ring; - unsigned int p, c; /* * Ensure the ring is large enough to capture all possible @@ -346,20 +345,17 @@ static int evtchn_resize_ring(struct per_user_data *u) /* * Copy the old ring contents to the new ring. * - * If the ring contents crosses the end of the current ring, - * it needs to be copied in two chunks. + * To take care of wrapping, a full ring, and the new index + * pointing into the second half, simply copy the old contents + * twice. * * +---------+ +------------------+ - * |34567 12| -> | 1234567 | - * +-----p-c-+ +------------------+ + * |34567 12| -> |34567 1234567 12| + * +-----p-c-+ +-------c------p---+ */ - p = evtchn_ring_offset(u, u->ring_prod); - c = evtchn_ring_offset(u, u->ring_cons); - if (p < c) { - memcpy(new_ring + c, u->ring + c, (u->ring_size - c) * sizeof(*u->ring)); - memcpy(new_ring + u->ring_size, u->ring, p * sizeof(*u->ring)); - } else - memcpy(new_ring + c, u->ring + c, (p - c) * sizeof(*u->ring)); + memcpy(new_ring, old_ring, u->ring_size * sizeof(*u->ring)); + memcpy(new_ring + u->ring_size, old_ring, + u->ring_size * sizeof(*u->ring)); u->ring = new_ring; u->ring_size = new_size; diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index feef8a9..f024040 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -112,7 +112,6 @@ static int ecryptfs_readdir(struct file *file, struct dir_context *ctx) .sb = inode->i_sb, }; lower_file = ecryptfs_file_to_lower(file); - lower_file->f_pos = ctx->pos; rc = iterate_dir(lower_file, &buf.ctx); ctx->pos = buf.ctx.pos; if (rc < 0) @@ -223,14 +222,6 @@ static int ecryptfs_open(struct inode *inode, struct file *file) } ecryptfs_set_file_lower( file, ecryptfs_inode_to_private(inode)->lower_file); - if (d_is_dir(ecryptfs_dentry)) { - ecryptfs_printk(KERN_DEBUG, "This is a directory\n"); - mutex_lock(&crypt_stat->cs_mutex); - crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED); - mutex_unlock(&crypt_stat->cs_mutex); - rc = 0; - goto out; - } rc = read_or_initialize_metadata(ecryptfs_dentry); if (rc) goto out_put; @@ -247,6 +238,45 @@ out: return rc; } +/** + * ecryptfs_dir_open + * @inode: inode speciying file to open + * @file: Structure to return filled in + * + * Opens the file specified by inode. + * + * Returns zero on success; non-zero otherwise + */ +static int ecryptfs_dir_open(struct inode *inode, struct file *file) +{ + struct dentry *ecryptfs_dentry = file->f_path.dentry; + /* Private value of ecryptfs_dentry allocated in + * ecryptfs_lookup() */ + struct ecryptfs_file_info *file_info; + struct file *lower_file; + + /* Released in ecryptfs_release or end of function if failure */ + file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL); + ecryptfs_set_file_private(file, file_info); + if (unlikely(!file_info)) { + ecryptfs_printk(KERN_ERR, + "Error attempting to allocate memory\n"); + return -ENOMEM; + } + lower_file = dentry_open(ecryptfs_dentry_to_lower_path(ecryptfs_dentry), + file->f_flags, current_cred()); + if (IS_ERR(lower_file)) { + printk(KERN_ERR "%s: Error attempting to initialize " + "the lower file for the dentry with name " + "[%pd]; rc = [%ld]\n", __func__, + ecryptfs_dentry, PTR_ERR(lower_file)); + kmem_cache_free(ecryptfs_file_info_cache, file_info); + return PTR_ERR(lower_file); + } + ecryptfs_set_file_lower(file, lower_file); + return 0; +} + static int ecryptfs_flush(struct file *file, fl_owner_t td) { struct file *lower_file = ecryptfs_file_to_lower(file); @@ -267,6 +297,19 @@ static int ecryptfs_release(struct inode *inode, struct file *file) return 0; } +static int ecryptfs_dir_release(struct inode *inode, struct file *file) +{ + fput(ecryptfs_file_to_lower(file)); + kmem_cache_free(ecryptfs_file_info_cache, + ecryptfs_file_to_private(file)); + return 0; +} + +static loff_t ecryptfs_dir_llseek(struct file *file, loff_t offset, int whence) +{ + return vfs_llseek(ecryptfs_file_to_lower(file), offset, whence); +} + static int ecryptfs_fsync(struct file *file, loff_t start, loff_t end, int datasync) { @@ -346,20 +389,16 @@ const struct file_operations ecryptfs_dir_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = ecryptfs_compat_ioctl, #endif - .open = ecryptfs_open, - .flush = ecryptfs_flush, - .release = ecryptfs_release, + .open = ecryptfs_dir_open, + .release = ecryptfs_dir_release, .fsync = ecryptfs_fsync, - .fasync = ecryptfs_fasync, - .splice_read = generic_file_splice_read, - .llseek = default_llseek, + .llseek = ecryptfs_dir_llseek, }; const struct file_operations ecryptfs_main_fops = { .llseek = generic_file_llseek, .read_iter = ecryptfs_read_update_atime, .write_iter = generic_file_write_iter, - .iterate = ecryptfs_readdir, .unlocked_ioctl = ecryptfs_unlocked_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ecryptfs_compat_ioctl, diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index d48e0d2..5f22e74 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -157,7 +157,7 @@ efivarfs_ioc_setxflags(struct file *file, void __user *arg) return 0; } -long +static long efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p) { void __user *arg = (void __user *)p; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 553c5d2..9cb54a3 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -216,8 +216,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) INIT_LIST_HEAD(&efivarfs_list); - err = efivar_init(efivarfs_callback, (void *)sb, false, - true, &efivarfs_list); + err = efivar_init(efivarfs_callback, (void *)sb, true, &efivarfs_list); if (err) __efivar_entry_iter(efivarfs_destroy, &efivarfs_list, NULL, NULL); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 719924d..dcad5e2 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1295,7 +1295,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii, *nbytesp = nbytes; - return ret; + return ret < 0 ? ret : 0; } static inline int fuse_iter_npages(const struct iov_iter *ii_p) diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 5384ceb..98b3eb7 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -203,6 +203,8 @@ int get_rock_ridge_filename(struct iso_directory_record *de, int retnamlen = 0; int truncate = 0; int ret = 0; + char *p; + int len; if (!ISOFS_SB(inode->i_sb)->s_rock) return 0; @@ -267,12 +269,17 @@ repeat: rr->u.NM.flags); break; } - if ((strlen(retname) + rr->len - 5) >= 254) { + len = rr->len - 5; + if (retnamlen + len >= 254) { truncate = 1; break; } - strncat(retname, rr->u.NM.name, rr->len - 5); - retnamlen += rr->len - 5; + p = memchr(rr->u.NM.name, '\0', len); + if (unlikely(p)) + len = p - rr->u.NM.name; + memcpy(retname + retnamlen, rr->u.NM.name, len); + retnamlen += len; + retname[retnamlen] = '\0'; break; case SIG('R', 'E'): kfree(rs.buffer); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 03b688d..37f9678 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -153,9 +153,9 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, p = buf + len + nlen; *p = '\0'; for (kn = kn_to; kn != common; kn = kn->parent) { - nlen = strlen(kn->name); - p -= nlen; - memcpy(p, kn->name, nlen); + size_t tmp = strlen(kn->name); + p -= tmp; + memcpy(p, kn->name, tmp); *(--p) = '/'; } diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index f73541f..3d670a3 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -15,6 +15,7 @@ #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/namei.h> +#include <linux/seq_file.h> #include "kernfs-internal.h" @@ -40,6 +41,19 @@ static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry) return 0; } +static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry) +{ + struct kernfs_node *node = dentry->d_fsdata; + struct kernfs_root *root = kernfs_root(node); + struct kernfs_syscall_ops *scops = root->syscall_ops; + + if (scops && scops->show_path) + return scops->show_path(sf, node, root); + + seq_dentry(sf, dentry, " \t\n\\"); + return 0; +} + const struct super_operations kernfs_sops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, @@ -47,6 +61,7 @@ const struct super_operations kernfs_sops = { .remount_fs = kernfs_sop_remount_fs, .show_options = kernfs_sop_show_options, + .show_path = kernfs_sop_show_path, }; /** @@ -1794,30 +1794,49 @@ static inline unsigned int fold_hash(unsigned long hash) return hash_64(hash, 32); } +/* + * This is George Marsaglia's XORSHIFT generator. + * It implements a maximum-period LFSR in only a few + * instructions. It also has the property (required + * by hash_name()) that mix_hash(0) = 0. + */ +static inline unsigned long mix_hash(unsigned long hash) +{ + hash ^= hash << 13; + hash ^= hash >> 7; + hash ^= hash << 17; + return hash; +} + #else /* 32-bit case */ #define fold_hash(x) (x) +static inline unsigned long mix_hash(unsigned long hash) +{ + hash ^= hash << 13; + hash ^= hash >> 17; + hash ^= hash << 5; + return hash; +} + #endif unsigned int full_name_hash(const unsigned char *name, unsigned int len) { - unsigned long a, mask; - unsigned long hash = 0; + unsigned long a, hash = 0; for (;;) { a = load_unaligned_zeropad(name); if (len < sizeof(unsigned long)) break; - hash += a; - hash *= 9; + hash = mix_hash(hash + a); name += sizeof(unsigned long); len -= sizeof(unsigned long); if (!len) goto done; } - mask = bytemask_from_count(len); - hash += mask & a; + hash += a & bytemask_from_count(len); done: return fold_hash(hash); } @@ -1835,7 +1854,7 @@ static inline u64 hash_name(const char *name) hash = a = 0; len = -sizeof(unsigned long); do { - hash = (hash + a) * 9; + hash = mix_hash(hash + a); len += sizeof(unsigned long); a = load_unaligned_zeropad(name+len); b = a ^ REPEAT_BYTE('/'); @@ -2267,6 +2286,33 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, EXPORT_SYMBOL(vfs_path_lookup); /** + * lookup_hash - lookup single pathname component on already hashed name + * @name: name and hash to lookup + * @base: base directory to lookup from + * + * The name must have been verified and hashed (see lookup_one_len()). Using + * this after just full_name_hash() is unsafe. + * + * This function also doesn't check for search permission on base directory. + * + * Use lookup_one_len_unlocked() instead, unless you really know what you are + * doing. + * + * Do not hold i_mutex; this helper takes i_mutex if necessary. + */ +struct dentry *lookup_hash(const struct qstr *name, struct dentry *base) +{ + struct dentry *ret; + + ret = lookup_dcache(name, base, 0); + if (!ret) + ret = lookup_slow(name, base, 0); + + return ret; +} +EXPORT_SYMBOL(lookup_hash); + +/** * lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from @@ -2337,7 +2383,6 @@ struct dentry *lookup_one_len_unlocked(const char *name, struct qstr this; unsigned int c; int err; - struct dentry *ret; this.name = name; this.len = len; @@ -2369,10 +2414,7 @@ struct dentry *lookup_one_len_unlocked(const char *name, if (err) return ERR_PTR(err); - ret = lookup_dcache(&this, base, 0); - if (!ret) - ret = lookup_slow(&this, base, 0); - return ret; + return lookup_hash(&this, base); } EXPORT_SYMBOL(lookup_one_len_unlocked); @@ -2942,22 +2984,10 @@ no_open: dentry = lookup_real(dir, dentry, nd->flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); - - if (create_error) { - int open_flag = op->open_flag; - - error = create_error; - if ((open_flag & O_EXCL)) { - if (!dentry->d_inode) - goto out; - } else if (!dentry->d_inode) { - goto out; - } else if ((open_flag & O_TRUNC) && - d_is_reg(dentry)) { - goto out; - } - /* will fail later, go on to get the right error */ - } + } + if (create_error && !dentry->d_inode) { + error = create_error; + goto out; } looked_up: path->dentry = dentry; @@ -4213,7 +4243,11 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; - if (source == target) + /* + * Check source == target. + * On overlayfs need to look at underlying inodes. + */ + if (vfs_select_inode(old_dentry, 0) == vfs_select_inode(new_dentry, 0)) return 0; error = may_delete(old_dir, old_dentry, is_dir); diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 0cdf497..2162434 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -322,3 +322,90 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type) brelse(di_bh); return acl; } + +int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh) +{ + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct posix_acl *acl; + int ret; + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + + if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL)) + return 0; + + acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh); + if (IS_ERR(acl) || !acl) + return PTR_ERR(acl); + ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode); + if (ret) + return ret; + ret = ocfs2_set_acl(NULL, inode, NULL, ACL_TYPE_ACCESS, + acl, NULL, NULL); + posix_acl_release(acl); + return ret; +} + +/* + * Initialize the ACLs of a new inode. If parent directory has default ACL, + * then clone to new inode. Called from ocfs2_mknod. + */ +int ocfs2_init_acl(handle_t *handle, + struct inode *inode, + struct inode *dir, + struct buffer_head *di_bh, + struct buffer_head *dir_bh, + struct ocfs2_alloc_context *meta_ac, + struct ocfs2_alloc_context *data_ac) +{ + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct posix_acl *acl = NULL; + int ret = 0, ret2; + umode_t mode; + + if (!S_ISLNK(inode->i_mode)) { + if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) { + acl = ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT, + dir_bh); + if (IS_ERR(acl)) + return PTR_ERR(acl); + } + if (!acl) { + mode = inode->i_mode & ~current_umask(); + ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode); + if (ret) { + mlog_errno(ret); + goto cleanup; + } + } + } + if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) { + if (S_ISDIR(inode->i_mode)) { + ret = ocfs2_set_acl(handle, inode, di_bh, + ACL_TYPE_DEFAULT, acl, + meta_ac, data_ac); + if (ret) + goto cleanup; + } + mode = inode->i_mode; + ret = __posix_acl_create(&acl, GFP_NOFS, &mode); + if (ret < 0) + return ret; + + ret2 = ocfs2_acl_set_mode(inode, di_bh, handle, mode); + if (ret2) { + mlog_errno(ret2); + ret = ret2; + goto cleanup; + } + if (ret > 0) { + ret = ocfs2_set_acl(handle, inode, + di_bh, ACL_TYPE_ACCESS, + acl, meta_ac, data_ac); + } + } +cleanup: + posix_acl_release(acl); + return ret; +} diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h index 3fce68d..2783a75 100644 --- a/fs/ocfs2/acl.h +++ b/fs/ocfs2/acl.h @@ -35,5 +35,10 @@ int ocfs2_set_acl(handle_t *handle, struct posix_acl *acl, struct ocfs2_alloc_context *meta_ac, struct ocfs2_alloc_context *data_ac); +extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *); +extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *, + struct buffer_head *, struct buffer_head *, + struct ocfs2_alloc_context *, + struct ocfs2_alloc_context *); #endif /* OCFS2_ACL_H */ diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 5308841..59cce53 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1268,20 +1268,20 @@ bail_unlock_rw: if (size_change) ocfs2_rw_unlock(inode, 1); bail: - brelse(bh); /* Release quota pointers in case we acquired them */ for (qtype = 0; qtype < OCFS2_MAXQUOTAS; qtype++) dqput(transfer_to[qtype]); if (!status && attr->ia_valid & ATTR_MODE) { - status = posix_acl_chmod(inode, inode->i_mode); + status = ocfs2_acl_chmod(inode, bh); if (status < 0) mlog_errno(status); } if (inode_locked) ocfs2_inode_unlock(inode, 1); + brelse(bh); return status; } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 6b3e871..a8f1225 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -259,7 +259,6 @@ static int ocfs2_mknod(struct inode *dir, struct ocfs2_dir_lookup_result lookup = { NULL, }; sigset_t oldset; int did_block_signals = 0; - struct posix_acl *default_acl = NULL, *acl = NULL; struct ocfs2_dentry_lock *dl = NULL; trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name, @@ -367,12 +366,6 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } - status = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); - if (status) { - mlog_errno(status); - goto leave; - } - handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, S_ISDIR(mode), xattr_credits)); @@ -421,16 +414,8 @@ static int ocfs2_mknod(struct inode *dir, inc_nlink(dir); } - if (default_acl) { - status = ocfs2_set_acl(handle, inode, new_fe_bh, - ACL_TYPE_DEFAULT, default_acl, - meta_ac, data_ac); - } - if (!status && acl) { - status = ocfs2_set_acl(handle, inode, new_fe_bh, - ACL_TYPE_ACCESS, acl, - meta_ac, data_ac); - } + status = ocfs2_init_acl(handle, inode, dir, new_fe_bh, parent_fe_bh, + meta_ac, data_ac); if (status < 0) { mlog_errno(status); @@ -472,10 +457,6 @@ static int ocfs2_mknod(struct inode *dir, d_instantiate(dentry, inode); status = 0; leave: - if (default_acl) - posix_acl_release(default_acl); - if (acl) - posix_acl_release(acl); if (status < 0 && did_quota_inode) dquot_free_inode(inode); if (handle) diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 744d5d9..92bbe93 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4248,20 +4248,12 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, struct inode *inode = d_inode(old_dentry); struct buffer_head *old_bh = NULL; struct inode *new_orphan_inode = NULL; - struct posix_acl *default_acl, *acl; - umode_t mode; if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) return -EOPNOTSUPP; - mode = inode->i_mode; - error = posix_acl_create(dir, &mode, &default_acl, &acl); - if (error) { - mlog_errno(error); - return error; - } - error = ocfs2_create_inode_in_orphan(dir, mode, + error = ocfs2_create_inode_in_orphan(dir, inode->i_mode, &new_orphan_inode); if (error) { mlog_errno(error); @@ -4300,16 +4292,11 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, /* If the security isn't preserved, we need to re-initialize them. */ if (!preserve) { error = ocfs2_init_security_and_acl(dir, new_orphan_inode, - &new_dentry->d_name, - default_acl, acl); + &new_dentry->d_name); if (error) mlog_errno(error); } out: - if (default_acl) - posix_acl_release(default_acl); - if (acl) - posix_acl_release(acl); if (!error) { error = ocfs2_mv_orphaned_inode_to_new(dir, new_orphan_inode, new_dentry); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 7d3d979..f19b738 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -7216,12 +7216,10 @@ out: */ int ocfs2_init_security_and_acl(struct inode *dir, struct inode *inode, - const struct qstr *qstr, - struct posix_acl *default_acl, - struct posix_acl *acl) + const struct qstr *qstr) { - struct buffer_head *dir_bh = NULL; int ret = 0; + struct buffer_head *dir_bh = NULL; ret = ocfs2_init_security_get(inode, dir, qstr, NULL); if (ret) { @@ -7234,11 +7232,9 @@ int ocfs2_init_security_and_acl(struct inode *dir, mlog_errno(ret); goto leave; } - - if (!ret && default_acl) - ret = ocfs2_iop_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); - if (!ret && acl) - ret = ocfs2_iop_set_acl(inode, acl, ACL_TYPE_ACCESS); + ret = ocfs2_init_acl(NULL, inode, dir, NULL, dir_bh, NULL, NULL); + if (ret) + mlog_errno(ret); ocfs2_inode_unlock(dir, 0); brelse(dir_bh); diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h index f10d5b9..1633cc1 100644 --- a/fs/ocfs2/xattr.h +++ b/fs/ocfs2/xattr.h @@ -94,7 +94,5 @@ int ocfs2_reflink_xattrs(struct inode *old_inode, bool preserve_security); int ocfs2_init_security_and_acl(struct inode *dir, struct inode *inode, - const struct qstr *qstr, - struct posix_acl *default_acl, - struct posix_acl *acl); + const struct qstr *qstr); #endif /* OCFS2_XATTR_H */ @@ -840,16 +840,12 @@ EXPORT_SYMBOL(file_path); int vfs_open(const struct path *path, struct file *file, const struct cred *cred) { - struct dentry *dentry = path->dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = vfs_select_inode(path->dentry, file->f_flags); - file->f_path = *path; - if (dentry->d_flags & DCACHE_OP_SELECT_INODE) { - inode = dentry->d_op->d_select_inode(dentry, file->f_flags); - if (IS_ERR(inode)) - return PTR_ERR(inode); - } + if (IS_ERR(inode)) + return PTR_ERR(inode); + file->f_path = *path; return do_dentry_open(file, inode, NULL, cred); } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 5d972e6..791235e 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -411,9 +411,7 @@ static inline struct dentry *ovl_lookup_real(struct dentry *dir, { struct dentry *dentry; - inode_lock(dir->d_inode); - dentry = lookup_one_len(name->name, dir, name->len); - inode_unlock(dir->d_inode); + dentry = lookup_hash(name, dir); if (IS_ERR(dentry)) { if (PTR_ERR(dentry) == -ENOENT) @@ -198,7 +198,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin) /* all accesses are serialized by namespace_sem */ static struct user_namespace *user_ns; -static struct mount *last_dest, *last_source, *dest_master; +static struct mount *last_dest, *first_source, *last_source, *dest_master; static struct mountpoint *mp; static struct hlist_head *list; @@ -221,20 +221,22 @@ static int propagate_one(struct mount *m) type = CL_MAKE_SHARED; } else { struct mount *n, *p; + bool done; for (n = m; ; n = p) { p = n->mnt_master; - if (p == dest_master || IS_MNT_MARKED(p)) { - while (last_dest->mnt_master != p) { - last_source = last_source->mnt_master; - last_dest = last_source->mnt_parent; - } - if (!peers(n, last_dest)) { - last_source = last_source->mnt_master; - last_dest = last_source->mnt_parent; - } + if (p == dest_master || IS_MNT_MARKED(p)) break; - } } + do { + struct mount *parent = last_source->mnt_parent; + if (last_source == first_source) + break; + done = parent->mnt_master == p; + if (done && peers(n, parent)) + break; + last_source = last_source->mnt_master; + } while (!done); + type = CL_SLAVE; /* beginning of peer group among the slaves? */ if (IS_MNT_SHARED(m)) @@ -286,6 +288,7 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, */ user_ns = current->nsproxy->mnt_ns->user_ns; last_dest = dest_mnt; + first_source = source_mnt; last_source = source_mnt; mp = dest_mp; list = tree_list; diff --git a/fs/proc/base.c b/fs/proc/base.c index b1755b2..0d163a8 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -434,7 +434,7 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, && !lookup_symbol_name(wchan, symname)) seq_printf(m, "%s", symname); else - seq_puts(m, "0\n"); + seq_putc(m, '0'); return 0; } @@ -955,7 +955,8 @@ static ssize_t environ_read(struct file *file, char __user *buf, struct mm_struct *mm = file->private_data; unsigned long env_start, env_end; - if (!mm) + /* Ensure the process spawned far enough to have an environment. */ + if (!mm || !mm->env_end) return 0; page = (char *)__get_free_page(GFP_TEMPORARY); diff --git a/fs/splice.c b/fs/splice.c index b018eb4..dd9bf7e 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1143,6 +1143,9 @@ static long do_splice_to(struct file *in, loff_t *ppos, if (unlikely(ret < 0)) return ret; + if (unlikely(len > MAX_RW_COUNT)) + len = MAX_RW_COUNT; + if (in->f_op->splice_read) splice_read = in->f_op->splice_read; else diff --git a/fs/udf/super.c b/fs/udf/super.c index fa92fe8..36661ac 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -919,14 +919,14 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block) #endif } - ret = udf_CS0toUTF8(outstr, 31, pvoldesc->volIdent, 32); + ret = udf_dstrCS0toUTF8(outstr, 31, pvoldesc->volIdent, 32); if (ret < 0) goto out_bh; strncpy(UDF_SB(sb)->s_volume_ident, outstr, ret); udf_debug("volIdent[] = '%s'\n", UDF_SB(sb)->s_volume_ident); - ret = udf_CS0toUTF8(outstr, 127, pvoldesc->volSetIdent, 128); + ret = udf_dstrCS0toUTF8(outstr, 127, pvoldesc->volSetIdent, 128); if (ret < 0) goto out_bh; diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 972b706..263829e 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -212,7 +212,7 @@ extern int udf_get_filename(struct super_block *, const uint8_t *, int, uint8_t *, int); extern int udf_put_filename(struct super_block *, const uint8_t *, int, uint8_t *, int); -extern int udf_CS0toUTF8(uint8_t *, int, const uint8_t *, int); +extern int udf_dstrCS0toUTF8(uint8_t *, int, const uint8_t *, int); /* ialloc.c */ extern void udf_free_inode(struct inode *); diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index 3ff42f4..695389a 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -335,9 +335,21 @@ try_again: return u_len; } -int udf_CS0toUTF8(uint8_t *utf_o, int o_len, const uint8_t *ocu_i, int i_len) +int udf_dstrCS0toUTF8(uint8_t *utf_o, int o_len, + const uint8_t *ocu_i, int i_len) { - return udf_name_from_CS0(utf_o, o_len, ocu_i, i_len, + int s_len = 0; + + if (i_len > 0) { + s_len = ocu_i[i_len - 1]; + if (s_len >= i_len) { + pr_err("incorrect dstring lengths (%d/%d)\n", + s_len, i_len); + return -EINVAL; + } + } + + return udf_name_from_CS0(utf_o, o_len, ocu_i, s_len, udf_uni2char_utf8, 0); } diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 14362a8..3a93250 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -394,13 +394,13 @@ struct acpi_data_node { static inline bool is_acpi_node(struct fwnode_handle *fwnode) { - return fwnode && (fwnode->type == FWNODE_ACPI + return !IS_ERR_OR_NULL(fwnode) && (fwnode->type == FWNODE_ACPI || fwnode->type == FWNODE_ACPI_DATA); } static inline bool is_acpi_device_node(struct fwnode_handle *fwnode) { - return fwnode && fwnode->type == FWNODE_ACPI; + return !IS_ERR_OR_NULL(fwnode) && fwnode->type == FWNODE_ACPI; } static inline struct acpi_device *to_acpi_device_node(struct fwnode_handle *fwnode) diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h index d6d5dc9..3fc94a0 100644 --- a/include/asm-generic/rwsem.h +++ b/include/asm-generic/rwsem.h @@ -53,7 +53,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) /* * lock for writing */ -static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) +static inline void __down_write(struct rw_semaphore *sem) { long tmp; @@ -63,9 +63,16 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) rwsem_down_write_failed(sem); } -static inline void __down_write(struct rw_semaphore *sem) +static inline int __down_write_killable(struct rw_semaphore *sem) { - __down_write_nested(sem, 0); + long tmp; + + tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, + (atomic_long_t *)&sem->count); + if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) + if (IS_ERR(rwsem_down_write_failed_killable(sem))) + return -EINTR; + return 0; } static inline int __down_write_trylock(struct rw_semaphore *sem) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 339125b..6a67ab9 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -245,7 +245,9 @@ #define INIT_TASK_DATA(align) \ . = ALIGN(align); \ - *(.data..init_task) + VMLINUX_SYMBOL(__start_init_task) = .; \ + *(.data..init_task) \ + VMLINUX_SYMBOL(__end_init_task) = .; /* * Read only Data diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 506c353..e451534 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -560,11 +560,11 @@ static inline int atomic_dec_if_positive(atomic_t *v) /** * atomic_fetch_or - perform *p |= mask and return old value of *p - * @p: pointer to atomic_t * @mask: mask to OR on the atomic_t + * @p: pointer to atomic_t */ #ifndef atomic_fetch_or -static inline int atomic_fetch_or(atomic_t *p, int mask) +static inline int atomic_fetch_or(int mask, atomic_t *p) { int old, val = atomic_read(p); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 21ee41b..f1d5c5ac 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -171,12 +171,13 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl); void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); +struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_put_rcu(struct bpf_prog *prog); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); -void bpf_map_inc(struct bpf_map *map, bool uref); +struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index eeae401..3d5202e 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -246,7 +246,7 @@ #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ #endif -#if GCC_VERSION >= 40800 || (defined(__powerpc__) && GCC_VERSION >= 40600) +#if GCC_VERSION >= 40800 #define __HAVE_BUILTIN_BSWAP16__ #endif #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index f9b1fab..21597dc 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -59,25 +59,7 @@ struct notifier_block; * CPU notifier priorities. */ enum { - /* - * SCHED_ACTIVE marks a cpu which is coming up active during - * CPU_ONLINE and CPU_DOWN_FAILED and must be the first - * notifier. CPUSET_ACTIVE adjusts cpuset according to - * cpu_active mask right after SCHED_ACTIVE. During - * CPU_DOWN_PREPARE, SCHED_INACTIVE and CPUSET_INACTIVE are - * ordered in the similar way. - * - * This ordering guarantees consistent cpu_active mask and - * migration behavior to all cpu notifiers. - */ - CPU_PRI_SCHED_ACTIVE = INT_MAX, - CPU_PRI_CPUSET_ACTIVE = INT_MAX - 1, - CPU_PRI_SCHED_INACTIVE = INT_MIN + 1, - CPU_PRI_CPUSET_INACTIVE = INT_MIN, - - /* migration should happen before other stuff but after perf */ CPU_PRI_PERF = 20, - CPU_PRI_MIGRATION = 10, /* bring up workqueues before normal notifiers and down after */ CPU_PRI_WORKQUEUE_UP = 5, diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 5d68e15..386374d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -8,6 +8,7 @@ enum cpuhp_state { CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, CPUHP_AP_OFFLINE, + CPUHP_AP_SCHED_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, @@ -16,6 +17,7 @@ enum cpuhp_state { CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, + CPUHP_AP_ACTIVE, CPUHP_ONLINE, }; diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 40cee6b..e828cf6 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -743,12 +743,10 @@ set_cpu_present(unsigned int cpu, bool present) static inline void set_cpu_online(unsigned int cpu, bool online) { - if (online) { + if (online) cpumask_set_cpu(cpu, &__cpu_online_mask); - cpumask_set_cpu(cpu, &__cpu_active_mask); - } else { + else cpumask_clear_cpu(cpu, &__cpu_online_mask); - } } static inline void diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 4bb4de8..7e9422c 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -565,4 +565,16 @@ static inline struct dentry *d_real(struct dentry *dentry) return dentry; } +static inline struct inode *vfs_select_inode(struct dentry *dentry, + unsigned open_flags) +{ + struct inode *inode = d_inode(dentry); + + if (inode && unlikely(dentry->d_flags & DCACHE_OP_SELECT_INODE)) + inode = dentry->d_op->d_select_inode(dentry, open_flags); + + return inode; +} + + #endif /* __LINUX_DCACHE_H */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 1626474..df7acb5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -21,6 +21,7 @@ #include <linux/pfn.h> #include <linux/pstore.h> #include <linux/reboot.h> +#include <linux/screen_info.h> #include <asm/page.h> @@ -124,6 +125,13 @@ typedef struct { } efi_capsule_header_t; /* + * EFI capsule flags + */ +#define EFI_CAPSULE_PERSIST_ACROSS_RESET 0x00010000 +#define EFI_CAPSULE_POPULATE_SYSTEM_TABLE 0x00020000 +#define EFI_CAPSULE_INITIATE_RESET 0x00040000 + +/* * Allocation types for calls to boottime->allocate_pages. */ #define EFI_ALLOCATE_ANY_PAGES 0 @@ -282,9 +290,10 @@ typedef struct { efi_status_t (*handle_protocol)(efi_handle_t, efi_guid_t *, void **); void *__reserved; void *register_protocol_notify; - void *locate_handle; + efi_status_t (*locate_handle)(int, efi_guid_t *, void *, + unsigned long *, efi_handle_t *); void *locate_device_path; - void *install_configuration_table; + efi_status_t (*install_configuration_table)(efi_guid_t *, void *); void *load_image; void *start_image; void *exit; @@ -623,6 +632,27 @@ void efi_native_runtime_setup(void); EFI_GUID(0x3152bca5, 0xeade, 0x433d, \ 0x86, 0x2e, 0xc0, 0x1c, 0xdc, 0x29, 0x1f, 0x44) +#define EFI_MEMORY_ATTRIBUTES_TABLE_GUID \ + EFI_GUID(0xdcfa911d, 0x26eb, 0x469f, \ + 0xa2, 0x20, 0x38, 0xb7, 0xdc, 0x46, 0x12, 0x20) + +#define EFI_CONSOLE_OUT_DEVICE_GUID \ + EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, \ + 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) + +/* + * This GUID is used to pass to the kernel proper the struct screen_info + * structure that was populated by the stub based on the GOP protocol instance + * associated with ConOut + */ +#define LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID \ + EFI_GUID(0xe03fc20a, 0x85dc, 0x406e, \ + 0xb9, 0xe, 0x4a, 0xb5, 0x02, 0x37, 0x1d, 0x95) + +#define LINUX_EFI_LOADER_ENTRY_GUID \ + EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf, \ + 0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f) + typedef struct { efi_guid_t guid; u64 table; @@ -847,6 +877,14 @@ typedef struct { #define EFI_INVALID_TABLE_ADDR (~0UL) +typedef struct { + u32 version; + u32 num_entries; + u32 desc_size; + u32 reserved; + efi_memory_desc_t entry[0]; +} efi_memory_attributes_table_t; + /* * All runtime access to EFI goes through this structure: */ @@ -868,6 +906,7 @@ extern struct efi { unsigned long config_table; /* config tables */ unsigned long esrt; /* ESRT table */ unsigned long properties_table; /* properties table */ + unsigned long mem_attr_table; /* memory attributes table */ efi_get_time_t *get_time; efi_set_time_t *set_time; efi_get_wakeup_time_t *get_wakeup_time; @@ -883,7 +922,7 @@ extern struct efi { efi_get_next_high_mono_count_t *get_next_high_mono_count; efi_reset_system_t *reset_system; efi_set_virtual_address_map_t *set_virtual_address_map; - struct efi_memory_map *memmap; + struct efi_memory_map memmap; unsigned long flags; } efi; @@ -945,7 +984,6 @@ extern void efi_initialize_iomem_resources(struct resource *code_resource, extern void efi_get_time(struct timespec *now); extern void efi_reserve_boot_services(void); extern int efi_get_fdt_params(struct efi_fdt_params *params); -extern struct efi_memory_map memmap; extern struct kobject *efi_kobj; extern int efi_reboot_quirk_mode; @@ -957,12 +995,34 @@ extern void __init efi_fake_memmap(void); static inline void efi_fake_memmap(void) { } #endif +/* + * efi_memattr_perm_setter - arch specific callback function passed into + * efi_memattr_apply_permissions() that updates the + * mapping permissions described by the second + * argument in the page tables referred to by the + * first argument. + */ +typedef int (*efi_memattr_perm_setter)(struct mm_struct *, efi_memory_desc_t *); + +extern int efi_memattr_init(void); +extern int efi_memattr_apply_permissions(struct mm_struct *mm, + efi_memattr_perm_setter fn); + /* Iterate through an efi_memory_map */ -#define for_each_efi_memory_desc(m, md) \ +#define for_each_efi_memory_desc_in_map(m, md) \ for ((md) = (m)->map; \ (md) <= (efi_memory_desc_t *)((m)->map_end - (m)->desc_size); \ (md) = (void *)(md) + (m)->desc_size) +/** + * for_each_efi_memory_desc - iterate over descriptors in efi.memmap + * @md: the efi_memory_desc_t * iterator + * + * Once the loop finishes @md must not be accessed. + */ +#define for_each_efi_memory_desc(md) \ + for_each_efi_memory_desc_in_map(&efi.memmap, md) + /* * Format an EFI memory descriptor's type and attributes to a user-provided * character buffer, as per snprintf(), and return the buffer. @@ -1000,7 +1060,6 @@ extern int __init efi_setup_pcdp_console(char *); * possible, remove EFI-related code altogether. */ #define EFI_BOOT 0 /* Were we booted from EFI? */ -#define EFI_SYSTEM_TABLES 1 /* Can we use EFI system tables? */ #define EFI_CONFIG_TABLES 2 /* Can we use EFI config tables? */ #define EFI_RUNTIME_SERVICES 3 /* Can we use runtime services? */ #define EFI_MEMMAP 4 /* Can we use EFI memory map? */ @@ -1026,8 +1085,16 @@ static inline bool efi_enabled(int feature) } static inline void efi_reboot(enum reboot_mode reboot_mode, const char *__unused) {} + +static inline bool +efi_capsule_pending(int *reset_type) +{ + return false; +} #endif +extern int efi_status_to_err(efi_status_t status); + /* * Variable Attributes */ @@ -1180,6 +1247,80 @@ struct efi_simple_text_output_protocol { void *test_string; }; +#define PIXEL_RGB_RESERVED_8BIT_PER_COLOR 0 +#define PIXEL_BGR_RESERVED_8BIT_PER_COLOR 1 +#define PIXEL_BIT_MASK 2 +#define PIXEL_BLT_ONLY 3 +#define PIXEL_FORMAT_MAX 4 + +struct efi_pixel_bitmask { + u32 red_mask; + u32 green_mask; + u32 blue_mask; + u32 reserved_mask; +}; + +struct efi_graphics_output_mode_info { + u32 version; + u32 horizontal_resolution; + u32 vertical_resolution; + int pixel_format; + struct efi_pixel_bitmask pixel_information; + u32 pixels_per_scan_line; +} __packed; + +struct efi_graphics_output_protocol_mode_32 { + u32 max_mode; + u32 mode; + u32 info; + u32 size_of_info; + u64 frame_buffer_base; + u32 frame_buffer_size; +} __packed; + +struct efi_graphics_output_protocol_mode_64 { + u32 max_mode; + u32 mode; + u64 info; + u64 size_of_info; + u64 frame_buffer_base; + u64 frame_buffer_size; +} __packed; + +struct efi_graphics_output_protocol_mode { + u32 max_mode; + u32 mode; + unsigned long info; + unsigned long size_of_info; + u64 frame_buffer_base; + unsigned long frame_buffer_size; +} __packed; + +struct efi_graphics_output_protocol_32 { + u32 query_mode; + u32 set_mode; + u32 blt; + u32 mode; +}; + +struct efi_graphics_output_protocol_64 { + u64 query_mode; + u64 set_mode; + u64 blt; + u64 mode; +}; + +struct efi_graphics_output_protocol { + unsigned long query_mode; + unsigned long set_mode; + unsigned long blt; + struct efi_graphics_output_protocol_mode *mode; +}; + +typedef efi_status_t (*efi_graphics_output_protocol_query_mode)( + struct efi_graphics_output_protocol *, u32, unsigned long *, + struct efi_graphics_output_mode_info **); + extern struct list_head efivar_sysfs_list; static inline void @@ -1195,8 +1336,7 @@ int efivars_unregister(struct efivars *efivars); struct kobject *efivars_kobject(void); int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), - void *data, bool atomic, bool duplicates, - struct list_head *head); + void *data, bool duplicates, struct list_head *head); void efivar_entry_add(struct efivar_entry *entry, struct list_head *head); void efivar_entry_remove(struct efivar_entry *entry); @@ -1242,6 +1382,13 @@ int efivars_sysfs_init(void); #define EFIVARS_DATA_SIZE_MAX 1024 #endif /* CONFIG_EFI_VARS */ +extern bool efi_capsule_pending(int *reset_type); + +extern int efi_capsule_supported(efi_guid_t guid, u32 flags, + size_t size, int *reset); + +extern int efi_capsule_update(efi_capsule_header_t *capsule, + struct page **pages); #ifdef CONFIG_EFI_RUNTIME_MAP int efi_runtime_map_init(struct kobject *); @@ -1319,5 +1466,9 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, efi_status_t efi_parse_options(char *cmdline); +efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, + struct screen_info *si, efi_guid_t *proto, + unsigned long size); + bool efi_runtime_disabled(void); #endif /* _LINUX_EFI_H */ diff --git a/include/linux/hash.h b/include/linux/hash.h index 1afde47..79c52fa 100644 --- a/include/linux/hash.h +++ b/include/linux/hash.h @@ -32,12 +32,28 @@ #error Wordsize not 32 or 64 #endif +/* + * The above primes are actively bad for hashing, since they are + * too sparse. The 32-bit one is mostly ok, the 64-bit one causes + * real problems. Besides, the "prime" part is pointless for the + * multiplicative hash. + * + * Although a random odd number will do, it turns out that the golden + * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice + * properties. + * + * These are the negative, (1 - phi) = (phi^2) = (3 - sqrt(5))/2. + * (See Knuth vol 3, section 6.4, exercise 9.) + */ +#define GOLDEN_RATIO_32 0x61C88647 +#define GOLDEN_RATIO_64 0x61C8864680B583EBull + static __always_inline u64 hash_64(u64 val, unsigned int bits) { u64 hash = val; -#if defined(CONFIG_ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64 - hash = hash * GOLDEN_RATIO_PRIME_64; +#if BITS_PER_LONG == 64 + hash = hash * GOLDEN_RATIO_64; #else /* Sigh, gcc can't optimise this alone like it does for 32 bits. */ u64 n = hash; diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index d556973..548fd53 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -28,6 +28,11 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) return (struct ethhdr *)skb_mac_header(skb); } +static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb) +{ + return (struct ethhdr *)skb_inner_mac_header(skb); +} + int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len); diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index c06c442..30f089e 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -152,6 +152,8 @@ struct kernfs_syscall_ops { int (*rmdir)(struct kernfs_node *kn); int (*rename)(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name); + int (*show_path)(struct seq_file *sf, struct kernfs_node *kn, + struct kernfs_root *root); }; struct kernfs_root { diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index d10ef06..eabe013 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -356,8 +356,13 @@ extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask); extern void lockdep_clear_current_reclaim_state(void); extern void lockdep_trace_alloc(gfp_t mask); -extern void lock_pin_lock(struct lockdep_map *lock); -extern void lock_unpin_lock(struct lockdep_map *lock); +struct pin_cookie { unsigned int val; }; + +#define NIL_COOKIE (struct pin_cookie){ .val = 0U, } + +extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock); +extern void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie); +extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); # define INIT_LOCKDEP .lockdep_recursion = 0, .lockdep_reclaim_gfp = 0, @@ -373,8 +378,9 @@ extern void lock_unpin_lock(struct lockdep_map *lock); #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) -#define lockdep_pin_lock(l) lock_pin_lock(&(l)->dep_map) -#define lockdep_unpin_lock(l) lock_unpin_lock(&(l)->dep_map) +#define lockdep_pin_lock(l) lock_pin_lock(&(l)->dep_map) +#define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c)) +#define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c)) #else /* !CONFIG_LOCKDEP */ @@ -427,8 +433,13 @@ struct lock_class_key { }; #define lockdep_recursing(tsk) (0) -#define lockdep_pin_lock(l) do { (void)(l); } while (0) -#define lockdep_unpin_lock(l) do { (void)(l); } while (0) +struct pin_cookie { }; + +#define NIL_COOKIE (struct pin_cookie){ } + +#define lockdep_pin_lock(l) ({ struct pin_cookie cookie; cookie; }) +#define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) +#define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) #endif /* !LOCKDEP */ @@ -446,6 +457,18 @@ do { \ lock_acquired(&(_lock)->dep_map, _RET_IP_); \ } while (0) +#define LOCK_CONTENDED_RETURN(_lock, try, lock) \ +({ \ + int ____err = 0; \ + if (!try(_lock)) { \ + lock_contended(&(_lock)->dep_map, _RET_IP_); \ + ____err = lock(_lock); \ + } \ + if (!____err) \ + lock_acquired(&(_lock)->dep_map, _RET_IP_); \ + ____err; \ +}) + #else /* CONFIG_LOCK_STAT */ #define lock_contended(lockdep_map, ip) do {} while (0) @@ -454,6 +477,9 @@ do { \ #define LOCK_CONTENDED(_lock, try, lock) \ lock(_lock) +#define LOCK_CONTENDED_RETURN(_lock, try, lock) \ + lock(_lock) + #endif /* CONFIG_LOCK_STAT */ #ifdef CONFIG_LOCKDEP diff --git a/include/linux/mfd/samsung/s2mps11.h b/include/linux/mfd/samsung/s2mps11.h index b288965..2c14eeca 100644 --- a/include/linux/mfd/samsung/s2mps11.h +++ b/include/linux/mfd/samsung/s2mps11.h @@ -173,10 +173,12 @@ enum s2mps11_regulators { #define S2MPS11_LDO_VSEL_MASK 0x3F #define S2MPS11_BUCK_VSEL_MASK 0xFF +#define S2MPS11_BUCK9_VSEL_MASK 0x1F #define S2MPS11_ENABLE_MASK (0x03 << S2MPS11_ENABLE_SHIFT) #define S2MPS11_ENABLE_SHIFT 0x06 #define S2MPS11_LDO_N_VOLTAGES (S2MPS11_LDO_VSEL_MASK + 1) #define S2MPS11_BUCK_N_VOLTAGES (S2MPS11_BUCK_VSEL_MASK + 1) +#define S2MPS11_BUCK9_N_VOLTAGES (S2MPS11_BUCK9_VSEL_MASK + 1) #define S2MPS11_RAMP_DELAY 25000 /* uV/us */ #define S2MPS11_CTRL1_PWRHOLD_MASK BIT(4) diff --git a/include/linux/mm.h b/include/linux/mm.h index 864d722..8f468e0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -500,11 +500,20 @@ static inline int page_mapcount(struct page *page) #ifdef CONFIG_TRANSPARENT_HUGEPAGE int total_mapcount(struct page *page); +int page_trans_huge_mapcount(struct page *page, int *total_mapcount); #else static inline int total_mapcount(struct page *page) { return page_mapcount(page); } +static inline int page_trans_huge_mapcount(struct page *page, + int *total_mapcount) +{ + int mapcount = page_mapcount(page); + if (total_mapcount) + *total_mapcount = mapcount; + return mapcount; +} #endif static inline struct page *virt_to_head_page(const void *x) diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index 70fffeb..a444178 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -1,9 +1,16 @@ #ifndef _LINUX_MMU_CONTEXT_H #define _LINUX_MMU_CONTEXT_H +#include <asm/mmu_context.h> + struct mm_struct; void use_mm(struct mm_struct *mm); void unuse_mm(struct mm_struct *mm); +/* Architectures that care about IRQ state in switch_mm can override this. */ +#ifndef switch_mm_irqs_off +# define switch_mm_irqs_off switch_mm +#endif + #endif diff --git a/include/linux/namei.h b/include/linux/namei.h index 77d0170..ec5ec28 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -79,6 +79,8 @@ extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); +struct qstr; +extern struct dentry *lookup_hash(const struct qstr *, struct dentry *); extern int follow_down_one(struct path *); extern int follow_down(struct path *); diff --git a/include/linux/net.h b/include/linux/net.h index 49175e4..f840d77 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -246,7 +246,15 @@ do { \ net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__) #define net_info_ratelimited(fmt, ...) \ net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__) -#if defined(DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) +#define net_dbg_ratelimited(fmt, ...) \ +do { \ + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ + if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \ + net_ratelimit()) \ + __dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__); \ +} while (0) +#elif defined(DEBUG) #define net_dbg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) #else diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8395308..78181a8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2164,6 +2164,9 @@ struct packet_offload { struct udp_offload; +/* 'skb->encapsulation' is set before gro_complete() is called. gro_complete() + * must set 'skb->inner_mac_header' to the beginning of tunnel payload. + */ struct udp_offload_callbacks { struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb, @@ -4004,7 +4007,7 @@ netdev_features_t netif_skb_features(struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) { - netdev_features_t feature = gso_type << NETIF_F_GSO_SHIFT; + netdev_features_t feature = (netdev_features_t)gso_type << NETIF_F_GSO_SHIFT; /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); diff --git a/include/linux/of.h b/include/linux/of.h index 7fcb681..3175803 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -133,7 +133,7 @@ void of_core_init(void); static inline bool is_of_node(struct fwnode_handle *fwnode) { - return fwnode && fwnode->type == FWNODE_OF; + return !IS_ERR_OR_NULL(fwnode) && fwnode->type == FWNODE_OF; } static inline struct device_node *to_of_node(struct fwnode_handle *fwnode) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f4ed4f1b..6b052aa 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -517,6 +517,27 @@ static inline int PageTransCompound(struct page *page) } /* + * PageTransCompoundMap is the same as PageTransCompound, but it also + * guarantees the primary MMU has the entire compound page mapped + * through pmd_trans_huge, which in turn guarantees the secondary MMUs + * can also map the entire compound page. This allows the secondary + * MMUs to call get_user_pages() only once for each compound page and + * to immediately map the entire compound page with a single secondary + * MMU fault. If there will be a pmd split later, the secondary MMUs + * will get an update through the MMU notifier invalidation through + * split_huge_pmd(). + * + * Unlike PageTransCompound, this is safe to be called only while + * split_huge_pmd() cannot run from under us, like if protected by the + * MMU notifier, otherwise it may result in page->_mapcount < 0 false + * positives. + */ +static inline int PageTransCompoundMap(struct page *page) +{ + return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0; +} + +/* * PageTransTail returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. @@ -559,6 +580,7 @@ static inline int TestClearPageDoubleMap(struct page *page) #else TESTPAGEFLAG_FALSE(TransHuge) TESTPAGEFLAG_FALSE(TransCompound) +TESTPAGEFLAG_FALSE(TransCompoundMap) TESTPAGEFLAG_FALSE(TransTail) TESTPAGEFLAG_FALSE(DoubleMap) TESTSETFLAG_FALSE(DoubleMap) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f291275..9e1c3ad 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -58,7 +58,7 @@ struct perf_guest_info_callbacks { struct perf_callchain_entry { __u64 nr; - __u64 ip[PERF_MAX_STACK_DEPTH]; + __u64 ip[0]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_raw_record { @@ -151,6 +151,15 @@ struct hw_perf_event { */ struct task_struct *target; + /* + * PMU would store hardware filter configuration + * here. + */ + void *addr_filters; + + /* Last sync'ed generation of filters */ + unsigned long addr_filters_gen; + /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ @@ -216,6 +225,7 @@ struct perf_event; #define PERF_PMU_CAP_AUX_SW_DOUBLEBUF 0x08 #define PERF_PMU_CAP_EXCLUSIVE 0x10 #define PERF_PMU_CAP_ITRACE 0x20 +#define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 /** * struct pmu - generic performance monitoring unit @@ -240,6 +250,9 @@ struct pmu { int task_ctx_nr; int hrtimer_interval_ms; + /* number of address filters this PMU can do */ + unsigned int nr_addr_filters; + /* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. @@ -393,12 +406,71 @@ struct pmu { void (*free_aux) (void *aux); /* optional */ /* + * Validate address range filters: make sure the HW supports the + * requested configuration and number of filters; return 0 if the + * supplied filters are valid, -errno otherwise. + * + * Runs in the context of the ioctl()ing process and is not serialized + * with the rest of the PMU callbacks. + */ + int (*addr_filters_validate) (struct list_head *filters); + /* optional */ + + /* + * Synchronize address range filter configuration: + * translate hw-agnostic filters into hardware configuration in + * event::hw::addr_filters. + * + * Runs as a part of filter sync sequence that is done in ->start() + * callback by calling perf_event_addr_filters_sync(). + * + * May (and should) traverse event::addr_filters::list, for which its + * caller provides necessary serialization. + */ + void (*addr_filters_sync) (struct perf_event *event); + /* optional */ + + /* * Filter events for PMU-specific reasons. */ int (*filter_match) (struct perf_event *event); /* optional */ }; /** + * struct perf_addr_filter - address range filter definition + * @entry: event's filter list linkage + * @inode: object file's inode for file-based filters + * @offset: filter range offset + * @size: filter range size + * @range: 1: range, 0: address + * @filter: 1: filter/start, 0: stop + * + * This is a hardware-agnostic filter configuration as specified by the user. + */ +struct perf_addr_filter { + struct list_head entry; + struct inode *inode; + unsigned long offset; + unsigned long size; + unsigned int range : 1, + filter : 1; +}; + +/** + * struct perf_addr_filters_head - container for address range filters + * @list: list of filters for this event + * @lock: spinlock that serializes accesses to the @list and event's + * (and its children's) filter generations. + * + * A child event will use parent's @list (and therefore @lock), so they are + * bundled together; see perf_event_addr_filters(). + */ +struct perf_addr_filters_head { + struct list_head list; + raw_spinlock_t lock; +}; + +/** * enum perf_event_active_state - the states of a event */ enum perf_event_active_state { @@ -566,6 +638,12 @@ struct perf_event { atomic_t event_limit; + /* address range filters */ + struct perf_addr_filters_head addr_filters; + /* vma address array for file-based filders */ + unsigned long *addr_filters_offs; + unsigned long addr_filters_gen; + void (*destroy)(struct perf_event *); struct rcu_head rcu_head; @@ -834,9 +912,25 @@ extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); +extern void perf_event_output_forward(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs); +extern void perf_event_output_backward(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs); extern void perf_event_output(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs); + struct perf_sample_data *data, + struct pt_regs *regs); + +static inline bool +is_default_overflow_handler(struct perf_event *event) +{ + if (likely(event->overflow_handler == perf_event_output_forward)) + return true; + if (unlikely(event->overflow_handler == perf_event_output_backward)) + return true; + return false; +} extern void perf_event_header__init_id(struct perf_event_header *header, @@ -977,9 +1071,11 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, extern int get_callchain_buffers(void); extern void put_callchain_buffers(void); +extern int sysctl_perf_event_max_stack; + static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) { - if (entry->nr < PERF_MAX_STACK_DEPTH) { + if (entry->nr < sysctl_perf_event_max_stack) { entry->ip[entry->nr++] = ip; return 0; } else { @@ -1001,6 +1097,8 @@ extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +int perf_event_max_stack_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); static inline bool perf_paranoid_tracepoint_raw(void) { @@ -1045,8 +1143,41 @@ static inline bool has_aux(struct perf_event *event) return event->pmu->setup_aux; } +static inline bool is_write_backward(struct perf_event *event) +{ + return !!event->attr.write_backward; +} + +static inline bool has_addr_filter(struct perf_event *event) +{ + return event->pmu->nr_addr_filters; +} + +/* + * An inherited event uses parent's filters + */ +static inline struct perf_addr_filters_head * +perf_event_addr_filters(struct perf_event *event) +{ + struct perf_addr_filters_head *ifh = &event->addr_filters; + + if (event->parent) + ifh = &event->parent->addr_filters; + + return ifh; +} + +extern void perf_event_addr_filters_sync(struct perf_event *event); + extern int perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size); +extern int perf_output_begin_forward(struct perf_output_handle *handle, + struct perf_event *event, + unsigned int size); +extern int perf_output_begin_backward(struct perf_output_handle *handle, + struct perf_event *event, + unsigned int size); + extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); diff --git a/include/linux/pnp.h b/include/linux/pnp.h index 5df733b..2588ca6 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -337,9 +337,11 @@ extern struct mutex pnp_res_mutex; #ifdef CONFIG_PNPBIOS extern struct pnp_protocol pnpbios_protocol; +extern bool arch_pnpbios_disabled(void); #define pnp_device_is_pnpbios(dev) ((dev)->protocol == (&pnpbios_protocol)) #else #define pnp_device_is_pnpbios(dev) 0 +#define arch_pnpbios_disabled() false #endif #ifdef CONFIG_PNPACPI diff --git a/include/linux/proportions.h b/include/linux/proportions.h deleted file mode 100644 index 2122133..0000000 --- a/include/linux/proportions.h +++ /dev/null @@ -1,137 +0,0 @@ -/* - * FLoating proportions - * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra - * - * This file contains the public data structure and API definitions. - */ - -#ifndef _LINUX_PROPORTIONS_H -#define _LINUX_PROPORTIONS_H - -#include <linux/percpu_counter.h> -#include <linux/spinlock.h> -#include <linux/mutex.h> -#include <linux/gfp.h> - -struct prop_global { - /* - * The period over which we differentiate - * - * period = 2^shift - */ - int shift; - /* - * The total event counter aka 'time'. - * - * Treated as an unsigned long; the lower 'shift - 1' bits are the - * counter bits, the remaining upper bits the period counter. - */ - struct percpu_counter events; -}; - -/* - * global proportion descriptor - * - * this is needed to consistently flip prop_global structures. - */ -struct prop_descriptor { - int index; - struct prop_global pg[2]; - struct mutex mutex; /* serialize the prop_global switch */ -}; - -int prop_descriptor_init(struct prop_descriptor *pd, int shift, gfp_t gfp); -void prop_change_shift(struct prop_descriptor *pd, int new_shift); - -/* - * ----- PERCPU ------ - */ - -struct prop_local_percpu { - /* - * the local events counter - */ - struct percpu_counter events; - - /* - * snapshot of the last seen global state - */ - int shift; - unsigned long period; - raw_spinlock_t lock; /* protect the snapshot state */ -}; - -int prop_local_init_percpu(struct prop_local_percpu *pl, gfp_t gfp); -void prop_local_destroy_percpu(struct prop_local_percpu *pl); -void __prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl); -void prop_fraction_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl, - long *numerator, long *denominator); - -static inline -void prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl) -{ - unsigned long flags; - - local_irq_save(flags); - __prop_inc_percpu(pd, pl); - local_irq_restore(flags); -} - -/* - * Limit the time part in order to ensure there are some bits left for the - * cycle counter and fraction multiply. - */ -#if BITS_PER_LONG == 32 -#define PROP_MAX_SHIFT (3*BITS_PER_LONG/4) -#else -#define PROP_MAX_SHIFT (BITS_PER_LONG/2) -#endif - -#define PROP_FRAC_SHIFT (BITS_PER_LONG - PROP_MAX_SHIFT - 1) -#define PROP_FRAC_BASE (1UL << PROP_FRAC_SHIFT) - -void __prop_inc_percpu_max(struct prop_descriptor *pd, - struct prop_local_percpu *pl, long frac); - - -/* - * ----- SINGLE ------ - */ - -struct prop_local_single { - /* - * the local events counter - */ - unsigned long events; - - /* - * snapshot of the last seen global state - * and a lock protecting this state - */ - unsigned long period; - int shift; - raw_spinlock_t lock; /* protect the snapshot state */ -}; - -#define INIT_PROP_LOCAL_SINGLE(name) \ -{ .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ -} - -int prop_local_init_single(struct prop_local_single *pl); -void prop_local_destroy_single(struct prop_local_single *pl); -void __prop_inc_single(struct prop_descriptor *pd, struct prop_local_single *pl); -void prop_fraction_single(struct prop_descriptor *pd, struct prop_local_single *pl, - long *numerator, long *denominator); - -static inline -void prop_inc_single(struct prop_descriptor *pd, struct prop_local_single *pl) -{ - unsigned long flags; - - local_irq_save(flags); - __prop_inc_single(pd, pl); - local_irq_restore(flags); -} - -#endif /* _LINUX_PROPORTIONS_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 2657aff..5f1533e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -508,14 +508,7 @@ int rcu_read_lock_bh_held(void); * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side * critical section unless it can prove otherwise. */ -#ifdef CONFIG_PREEMPT_COUNT int rcu_read_lock_sched_held(void); -#else /* #ifdef CONFIG_PREEMPT_COUNT */ -static inline int rcu_read_lock_sched_held(void) -{ - return 1; -} -#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */ #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -532,18 +525,10 @@ static inline int rcu_read_lock_bh_held(void) return 1; } -#ifdef CONFIG_PREEMPT_COUNT static inline int rcu_read_lock_sched_held(void) { - return preempt_count() != 0 || irqs_disabled(); -} -#else /* #ifdef CONFIG_PREEMPT_COUNT */ -static inline int rcu_read_lock_sched_held(void) -{ - return 1; + return !preemptible(); } -#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */ - #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU @@ -1144,4 +1129,17 @@ static inline void rcu_sysidle_force_exit(void) #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ +/* + * Dump the ftrace buffer, but only one time per callsite per boot. + */ +#define rcu_ftrace_dump(oops_dump_mode) \ +do { \ + static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \ + \ + if (!atomic_read(&___rfd_beenhere) && \ + !atomic_xchg(&___rfd_beenhere, 1)) \ + ftrace_dump(oops_dump_mode); \ +} while (0) + + #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 64809ae..93aea75 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -149,6 +149,22 @@ static inline unsigned long rcu_batches_completed_sched(void) return 0; } +/* + * Return the number of expedited grace periods completed. + */ +static inline unsigned long rcu_exp_batches_completed(void) +{ + return 0; +} + +/* + * Return the number of expedited sched grace periods completed. + */ +static inline unsigned long rcu_exp_batches_completed_sched(void) +{ + return 0; +} + static inline void rcu_force_quiescent_state(void) { } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index ad1eda9..5043cb8 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -87,6 +87,8 @@ unsigned long rcu_batches_started_sched(void); unsigned long rcu_batches_completed(void); unsigned long rcu_batches_completed_bh(void); unsigned long rcu_batches_completed_sched(void); +unsigned long rcu_exp_batches_completed(void); +unsigned long rcu_exp_batches_completed_sched(void); void show_rcu_gp_kthreads(void); void rcu_force_quiescent_state(void); diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h index 561e861..ae0528b 100644 --- a/include/linux/rwsem-spinlock.h +++ b/include/linux/rwsem-spinlock.h @@ -34,7 +34,7 @@ struct rw_semaphore { extern void __down_read(struct rw_semaphore *sem); extern int __down_read_trylock(struct rw_semaphore *sem); extern void __down_write(struct rw_semaphore *sem); -extern void __down_write_nested(struct rw_semaphore *sem, int subclass); +extern int __must_check __down_write_killable(struct rw_semaphore *sem); extern int __down_write_trylock(struct rw_semaphore *sem); extern void __up_read(struct rw_semaphore *sem); extern void __up_write(struct rw_semaphore *sem); diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 8f498cd..d1c12d1 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -14,6 +14,7 @@ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/atomic.h> +#include <linux/err.h> #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #include <linux/osq_lock.h> #endif @@ -43,6 +44,7 @@ struct rw_semaphore { extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *); extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); @@ -116,6 +118,7 @@ extern int down_read_trylock(struct rw_semaphore *sem); * lock for writing */ extern void down_write(struct rw_semaphore *sem); +extern int __must_check down_write_killable(struct rw_semaphore *sem); /* * trylock for writing -- returns 1 if successful, 0 if contention diff --git a/include/linux/sched.h b/include/linux/sched.h index 52c4847..6cc0df9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -40,7 +40,6 @@ struct sched_param { #include <linux/pid.h> #include <linux/percpu.h> #include <linux/topology.h> -#include <linux/proportions.h> #include <linux/seccomp.h> #include <linux/rcupdate.h> #include <linux/rculist.h> @@ -178,9 +177,11 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); extern void calc_global_load(unsigned long ticks); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -extern void update_cpu_load_nohz(int active); +extern void cpu_load_update_nohz_start(void); +extern void cpu_load_update_nohz_stop(void); #else -static inline void update_cpu_load_nohz(int active) { } +static inline void cpu_load_update_nohz_start(void) { } +static inline void cpu_load_update_nohz_stop(void) { } #endif extern void dump_cpu_task(int cpu); @@ -372,6 +373,15 @@ extern void cpu_init (void); extern void trap_init(void); extern void update_process_times(int user); extern void scheduler_tick(void); +extern int sched_cpu_starting(unsigned int cpu); +extern int sched_cpu_activate(unsigned int cpu); +extern int sched_cpu_deactivate(unsigned int cpu); + +#ifdef CONFIG_HOTPLUG_CPU +extern int sched_cpu_dying(unsigned int cpu); +#else +# define sched_cpu_dying NULL +#endif extern void sched_show_task(struct task_struct *p); @@ -935,9 +945,19 @@ enum cpu_idle_type { }; /* + * Integer metrics need fixed point arithmetic, e.g., sched/fair + * has a few: load, load_avg, util_avg, freq, and capacity. + * + * We define a basic fixed point arithmetic range, and then formalize + * all these metrics based on that basic range. + */ +# define SCHED_FIXEDPOINT_SHIFT 10 +# define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) + +/* * Increase resolution of cpu_capacity calculations */ -#define SCHED_CAPACITY_SHIFT 10 +#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT #define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) /* @@ -1199,18 +1219,56 @@ struct load_weight { }; /* - * The load_avg/util_avg accumulates an infinite geometric series. - * 1) load_avg factors frequency scaling into the amount of time that a - * sched_entity is runnable on a rq into its weight. For cfs_rq, it is the - * aggregated such weights of all runnable and blocked sched_entities. - * 2) util_avg factors frequency and cpu scaling into the amount of time - * that a sched_entity is running on a CPU, in the range [0..SCHED_LOAD_SCALE]. - * For cfs_rq, it is the aggregated such times of all runnable and + * The load_avg/util_avg accumulates an infinite geometric series + * (see __update_load_avg() in kernel/sched/fair.c). + * + * [load_avg definition] + * + * load_avg = runnable% * scale_load_down(load) + * + * where runnable% is the time ratio that a sched_entity is runnable. + * For cfs_rq, it is the aggregated load_avg of all runnable and * blocked sched_entities. - * The 64 bit load_sum can: - * 1) for cfs_rq, afford 4353082796 (=2^64/47742/88761) entities with - * the highest weight (=88761) always runnable, we should not overflow - * 2) for entity, support any load.weight always runnable + * + * load_avg may also take frequency scaling into account: + * + * load_avg = runnable% * scale_load_down(load) * freq% + * + * where freq% is the CPU frequency normalized to the highest frequency. + * + * [util_avg definition] + * + * util_avg = running% * SCHED_CAPACITY_SCALE + * + * where running% is the time ratio that a sched_entity is running on + * a CPU. For cfs_rq, it is the aggregated util_avg of all runnable + * and blocked sched_entities. + * + * util_avg may also factor frequency scaling and CPU capacity scaling: + * + * util_avg = running% * SCHED_CAPACITY_SCALE * freq% * capacity% + * + * where freq% is the same as above, and capacity% is the CPU capacity + * normalized to the greatest capacity (due to uarch differences, etc). + * + * N.B., the above ratios (runnable%, running%, freq%, and capacity%) + * themselves are in the range of [0, 1]. To do fixed point arithmetics, + * we therefore scale them to as large a range as necessary. This is for + * example reflected by util_avg's SCHED_CAPACITY_SCALE. + * + * [Overflow issue] + * + * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities + * with the highest load (=88761), always runnable on a single cfs_rq, + * and should not overflow as the number already hits PID_MAX_LIMIT. + * + * For all other cases (including 32-bit kernels), struct load_weight's + * weight will overflow first before we do, because: + * + * Max(load_avg) <= Max(load.weight) + * + * Then it is the load_weight's responsibility to consider overflow + * issues. */ struct sched_avg { u64 last_update_time, load_sum; @@ -1596,6 +1654,7 @@ struct task_struct { unsigned long sas_ss_sp; size_t sas_ss_size; + unsigned sas_ss_flags; struct callback_head *task_works; @@ -1871,6 +1930,11 @@ extern int arch_task_struct_size __read_mostly; /* Future-safe accessor for struct task_struct's cpus_allowed. */ #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) +static inline int tsk_nr_cpus_allowed(struct task_struct *p) +{ + return p->nr_cpus_allowed; +} + #define TNF_MIGRATED 0x01 #define TNF_NO_GROUP 0x02 #define TNF_SHARED 0x04 @@ -2303,8 +2367,6 @@ extern unsigned long long notrace sched_clock(void); /* * See the comment in kernel/sched/clock.c */ -extern u64 cpu_clock(int cpu); -extern u64 local_clock(void); extern u64 running_clock(void); extern u64 sched_clock_cpu(int cpu); @@ -2323,6 +2385,16 @@ static inline void sched_clock_idle_sleep_event(void) static inline void sched_clock_idle_wakeup_event(u64 delta_ns) { } + +static inline u64 cpu_clock(int cpu) +{ + return sched_clock(); +} + +static inline u64 local_clock(void) +{ + return sched_clock(); +} #else /* * Architectures can set this to 1 if they have specified @@ -2337,6 +2409,26 @@ extern void clear_sched_clock_stable(void); extern void sched_clock_tick(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); + +/* + * As outlined in clock.c, provides a fast, high resolution, nanosecond + * time source that is monotonic per cpu argument and has bounded drift + * between cpus. + * + * ######################### BIG FAT WARNING ########################## + * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # + * # go backwards !! # + * #################################################################### + */ +static inline u64 cpu_clock(int cpu) +{ + return sched_clock_cpu(cpu); +} + +static inline u64 local_clock(void) +{ + return sched_clock_cpu(raw_smp_processor_id()); +} #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING @@ -2575,6 +2667,18 @@ static inline int kill_cad_pid(int sig, int priv) */ static inline int on_sig_stack(unsigned long sp) { + /* + * If the signal stack is SS_AUTODISARM then, by construction, we + * can't be on the signal stack unless user code deliberately set + * SS_AUTODISARM when we were already on it. + * + * This improves reliability: if user state gets corrupted such that + * the stack pointer points very close to the end of the signal stack, + * then this check will enable the signal to be handled anyway. + */ + if (current->sas_ss_flags & SS_AUTODISARM) + return 0; + #ifdef CONFIG_STACK_GROWSUP return sp >= current->sas_ss_sp && sp - current->sas_ss_sp < current->sas_ss_size; @@ -2592,6 +2696,13 @@ static inline int sas_ss_flags(unsigned long sp) return on_sig_stack(sp) ? SS_ONSTACK : 0; } +static inline void sas_ss_reset(struct task_struct *p) +{ + p->sas_ss_sp = 0; + p->sas_ss_size = 0; + p->sas_ss_flags = SS_DISABLE; +} + static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) { if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) diff --git a/include/linux/signal.h b/include/linux/signal.h index 92557bb..3fbe814 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -432,8 +432,10 @@ int __save_altstack(stack_t __user *, unsigned long); stack_t __user *__uss = uss; \ struct task_struct *t = current; \ put_user_ex((void __user *)t->sas_ss_sp, &__uss->ss_sp); \ - put_user_ex(sas_ss_flags(sp), &__uss->ss_flags); \ + put_user_ex(t->sas_ss_flags, &__uss->ss_flags); \ put_user_ex(t->sas_ss_size, &__uss->ss_size); \ + if (t->sas_ss_flags & SS_AUTODISARM) \ + sas_ss_reset(t); \ } while (0); #ifdef CONFIG_PROC_FS diff --git a/include/linux/swap.h b/include/linux/swap.h index 2b83359..ad22035 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -418,7 +418,7 @@ extern sector_t swapdev_block(int, pgoff_t); extern int page_swapcount(struct page *); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); -extern int reuse_swap_page(struct page *); +extern bool reuse_swap_page(struct page *, int *); extern int try_to_free_swap(struct page *); struct backing_dev_info; @@ -513,8 +513,8 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page) \ - (!PageTransCompound(page) && page_mapcount(page) == 1) +#define reuse_swap_page(page, total_mapcount) \ + (page_trans_huge_mapcount(page, total_mapcount) == 1) static inline int try_to_free_swap(struct page *page) { @@ -533,6 +533,10 @@ static inline swp_entry_t get_swap_page(void) #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { + /* Cgroup2 doesn't have per-cgroup swappiness */ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return vm_swappiness; + /* root ? */ if (mem_cgroup_disabled() || !memcg->css.parent) return vm_swappiness; diff --git a/include/linux/uio.h b/include/linux/uio.h index fd9bcfe..1b5d1cd 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -87,6 +87,7 @@ size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); +unsigned long iov_iter_gap_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *kvec, diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 730d82a..24cd394 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -80,6 +80,7 @@ struct netns_xfrm { struct flow_cache flow_cache_global; atomic_t flow_cache_genid; struct list_head flow_cache_gc_list; + atomic_t flow_cache_gc_count; spinlock_t flow_cache_gc_lock; struct work_struct flow_cache_gc_work; struct work_struct flow_cache_flush_work; diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index b831140..a114024 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -106,15 +106,6 @@ static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb, return iptunnel_handle_offloads(skb, type); } -static inline void udp_tunnel_gro_complete(struct sk_buff *skb, int nhoff) -{ - struct udphdr *uh; - - uh = (struct udphdr *)(skb->data + nhoff - sizeof(struct udphdr)); - skb_shinfo(skb)->gso_type |= uh->check ? - SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; -} - static inline void udp_tunnel_encap_enable(struct socket *sock) { #if IS_ENABLED(CONFIG_IPV6) diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 73ed2e9..35437c7 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -252,7 +252,9 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, (skb->inner_protocol_type != ENCAP_TYPE_ETHER || skb->inner_protocol != htons(ETH_P_TEB) || (skb_inner_mac_header(skb) - skb_transport_header(skb) != - sizeof(struct udphdr) + sizeof(struct vxlanhdr)))) + sizeof(struct udphdr) + sizeof(struct vxlanhdr)) || + (skb->ip_summed != CHECKSUM_NONE && + !can_checksum_protocol(features, inner_eth_hdr(skb)->h_proto)))) return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); return features; diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index ef72c4a..d3e7565 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -172,6 +172,77 @@ TRACE_EVENT(rcu_grace_period_init, ); /* + * Tracepoint for expedited grace-period events. Takes a string identifying + * the RCU flavor, the expedited grace-period sequence number, and a string + * identifying the grace-period-related event as follows: + * + * "snap": Captured snapshot of expedited grace period sequence number. + * "start": Started a real expedited grace period. + * "end": Ended a real expedited grace period. + * "endwake": Woke piggybackers up. + * "done": Someone else did the expedited grace period for us. + */ +TRACE_EVENT(rcu_exp_grace_period, + + TP_PROTO(const char *rcuname, unsigned long gpseq, const char *gpevent), + + TP_ARGS(rcuname, gpseq, gpevent), + + TP_STRUCT__entry( + __field(const char *, rcuname) + __field(unsigned long, gpseq) + __field(const char *, gpevent) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->gpseq = gpseq; + __entry->gpevent = gpevent; + ), + + TP_printk("%s %lu %s", + __entry->rcuname, __entry->gpseq, __entry->gpevent) +); + +/* + * Tracepoint for expedited grace-period funnel-locking events. Takes a + * string identifying the RCU flavor, an integer identifying the rcu_node + * combining-tree level, another pair of integers identifying the lowest- + * and highest-numbered CPU associated with the current rcu_node structure, + * and a string. identifying the grace-period-related event as follows: + * + * "nxtlvl": Advance to next level of rcu_node funnel + * "wait": Wait for someone else to do expedited GP + */ +TRACE_EVENT(rcu_exp_funnel_lock, + + TP_PROTO(const char *rcuname, u8 level, int grplo, int grphi, + const char *gpevent), + + TP_ARGS(rcuname, level, grplo, grphi, gpevent), + + TP_STRUCT__entry( + __field(const char *, rcuname) + __field(u8, level) + __field(int, grplo) + __field(int, grphi) + __field(const char *, gpevent) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->level = level; + __entry->grplo = grplo; + __entry->grphi = grphi; + __entry->gpevent = gpevent; + ), + + TP_printk("%s %d %d %d %s", + __entry->rcuname, __entry->level, __entry->grplo, + __entry->grphi, __entry->gpevent) +); + +/* * Tracepoint for RCU no-CBs CPU callback handoffs. This event is intended * to assist debugging of these handoffs. * @@ -704,11 +775,15 @@ TRACE_EVENT(rcu_barrier, #else /* #ifdef CONFIG_RCU_TRACE */ #define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0) -#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \ - qsmask) do { } while (0) #define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \ level, grplo, grphi, event) \ do { } while (0) +#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \ + qsmask) do { } while (0) +#define trace_rcu_exp_grace_period(rcuname, gqseq, gpevent) \ + do { } while (0) +#define trace_rcu_exp_funnel_lock(rcuname, level, grplo, grphi, gpevent) \ + do { } while (0) #define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0) #define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0) #define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0) diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 6e0f5f0..c51afb7 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -718,9 +718,9 @@ __SYSCALL(__NR_mlock2, sys_mlock2) #define __NR_copy_file_range 285 __SYSCALL(__NR_copy_file_range, sys_copy_file_range) #define __NR_preadv2 286 -__SYSCALL(__NR_preadv2, sys_preadv2) +__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2) #define __NR_pwritev2 287 -__SYSCALL(__NR_pwritev2, sys_pwritev2) +__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2) #undef __NR_syscalls #define __NR_syscalls 288 diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h index f802775..e601c8c 100644 --- a/include/uapi/linux/if.h +++ b/include/uapi/linux/if.h @@ -19,14 +19,20 @@ #ifndef _LINUX_IF_H #define _LINUX_IF_H +#include <linux/libc-compat.h> /* for compatibility with glibc */ #include <linux/types.h> /* for "__kernel_caddr_t" et al */ #include <linux/socket.h> /* for "struct sockaddr" et al */ #include <linux/compiler.h> /* for "__user" et al */ +#if __UAPI_DEF_IF_IFNAMSIZ #define IFNAMSIZ 16 +#endif /* __UAPI_DEF_IF_IFNAMSIZ */ #define IFALIASZ 256 #include <linux/hdlc/ioctl.h> +/* For glibc compatibility. An empty enum does not compile. */ +#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && \ + __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 /** * enum net_device_flags - &struct net_device flags * @@ -68,6 +74,8 @@ * @IFF_ECHO: echo sent packets. Volatile. */ enum net_device_flags { +/* for compatibility with glibc net/if.h */ +#if __UAPI_DEF_IF_NET_DEVICE_FLAGS IFF_UP = 1<<0, /* sysfs */ IFF_BROADCAST = 1<<1, /* volatile */ IFF_DEBUG = 1<<2, /* sysfs */ @@ -84,11 +92,17 @@ enum net_device_flags { IFF_PORTSEL = 1<<13, /* sysfs */ IFF_AUTOMEDIA = 1<<14, /* sysfs */ IFF_DYNAMIC = 1<<15, /* sysfs */ +#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS */ +#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO IFF_LOWER_UP = 1<<16, /* volatile */ IFF_DORMANT = 1<<17, /* volatile */ IFF_ECHO = 1<<18, /* volatile */ +#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */ }; +#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 */ +/* for compatibility with glibc net/if.h */ +#if __UAPI_DEF_IF_NET_DEVICE_FLAGS #define IFF_UP IFF_UP #define IFF_BROADCAST IFF_BROADCAST #define IFF_DEBUG IFF_DEBUG @@ -105,9 +119,13 @@ enum net_device_flags { #define IFF_PORTSEL IFF_PORTSEL #define IFF_AUTOMEDIA IFF_AUTOMEDIA #define IFF_DYNAMIC IFF_DYNAMIC +#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS */ + +#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO #define IFF_LOWER_UP IFF_LOWER_UP #define IFF_DORMANT IFF_DORMANT #define IFF_ECHO IFF_ECHO +#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */ #define IFF_VOLATILE (IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_ECHO|\ IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT) @@ -166,6 +184,8 @@ enum { * being very small might be worth keeping for clean configuration. */ +/* for compatibility with glibc net/if.h */ +#if __UAPI_DEF_IF_IFMAP struct ifmap { unsigned long mem_start; unsigned long mem_end; @@ -175,6 +195,7 @@ struct ifmap { unsigned char port; /* 3 bytes spare */ }; +#endif /* __UAPI_DEF_IF_IFMAP */ struct if_settings { unsigned int type; /* Type of physical device or protocol */ @@ -200,6 +221,8 @@ struct if_settings { * remainder may be interface specific. */ +/* for compatibility with glibc net/if.h */ +#if __UAPI_DEF_IF_IFREQ struct ifreq { #define IFHWADDRLEN 6 union @@ -223,6 +246,7 @@ struct ifreq { struct if_settings ifru_settings; } ifr_ifru; }; +#endif /* __UAPI_DEF_IF_IFREQ */ #define ifr_name ifr_ifrn.ifrn_name /* interface name */ #define ifr_hwaddr ifr_ifru.ifru_hwaddr /* MAC address */ @@ -249,6 +273,8 @@ struct ifreq { * must know all networks accessible). */ +/* for compatibility with glibc net/if.h */ +#if __UAPI_DEF_IF_IFCONF struct ifconf { int ifc_len; /* size of buffer */ union { @@ -256,6 +282,8 @@ struct ifconf { struct ifreq __user *ifcu_req; } ifc_ifcu; }; +#endif /* __UAPI_DEF_IF_IFCONF */ + #define ifc_buf ifc_ifcu.ifcu_buf /* buffer address */ #define ifc_req ifc_ifcu.ifcu_req /* array of structures */ diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h index 4c58d99..3411ed0 100644 --- a/include/uapi/linux/if_macsec.h +++ b/include/uapi/linux/if_macsec.h @@ -19,6 +19,8 @@ #define MACSEC_MAX_KEY_LEN 128 +#define MACSEC_KEYID_LEN 16 + #define MACSEC_DEFAULT_CIPHER_ID 0x0080020001000001ULL #define MACSEC_DEFAULT_CIPHER_ALT 0x0080C20001000001ULL @@ -77,7 +79,7 @@ enum macsec_sa_attrs { MACSEC_SA_ATTR_ACTIVE, /* config/dump, u8 0..1 */ MACSEC_SA_ATTR_PN, /* config/dump, u32 */ MACSEC_SA_ATTR_KEY, /* config, data */ - MACSEC_SA_ATTR_KEYID, /* config/dump, u64 */ + MACSEC_SA_ATTR_KEYID, /* config/dump, 128-bit */ MACSEC_SA_ATTR_STATS, /* dump, nested, macsec_sa_stats_attr */ __MACSEC_SA_ATTR_END, NUM_MACSEC_SA_ATTR = __MACSEC_SA_ATTR_END, diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index 7d024ce..d5e38c7 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -51,6 +51,40 @@ /* We have included glibc headers... */ #if defined(__GLIBC__) +/* Coordinate with glibc net/if.h header. */ +#if defined(_NET_IF_H) + +/* GLIBC headers included first so don't define anything + * that would already be defined. */ + +#define __UAPI_DEF_IF_IFCONF 0 +#define __UAPI_DEF_IF_IFMAP 0 +#define __UAPI_DEF_IF_IFNAMSIZ 0 +#define __UAPI_DEF_IF_IFREQ 0 +/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */ +#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 0 +/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */ +#ifndef __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO +#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1 +#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */ + +#else /* _NET_IF_H */ + +/* Linux headers included first, and we must define everything + * we need. The expectation is that glibc will check the + * __UAPI_DEF_* defines and adjust appropriately. */ + +#define __UAPI_DEF_IF_IFCONF 1 +#define __UAPI_DEF_IF_IFMAP 1 +#define __UAPI_DEF_IF_IFNAMSIZ 1 +#define __UAPI_DEF_IF_IFREQ 1 +/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */ +#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1 +/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */ +#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1 + +#endif /* _NET_IF_H */ + /* Coordinate with glibc netinet/in.h header. */ #if defined(_NETINET_IN_H) @@ -117,6 +151,16 @@ * that we need. */ #else /* !defined(__GLIBC__) */ +/* Definitions for if.h */ +#define __UAPI_DEF_IF_IFCONF 1 +#define __UAPI_DEF_IF_IFMAP 1 +#define __UAPI_DEF_IF_IFNAMSIZ 1 +#define __UAPI_DEF_IF_IFREQ 1 +/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */ +#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1 +/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */ +#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1 + /* Definitions for in.h */ #define __UAPI_DEF_IN_ADDR 1 #define __UAPI_DEF_IN_IPPROTO 1 diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 1afe962..43fc8d2 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -340,7 +340,8 @@ struct perf_event_attr { comm_exec : 1, /* flag comm events that are due to an exec */ use_clockid : 1, /* use @clockid for time fields */ context_switch : 1, /* context switch data */ - __reserved_1 : 37; + write_backward : 1, /* Write ring buffer from end to beginning */ + __reserved_1 : 36; union { __u32 wakeup_events; /* wakeup every n events */ @@ -401,6 +402,7 @@ struct perf_event_attr { #define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *) #define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *) #define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32) +#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32) enum perf_event_ioc_flags { PERF_IOC_FLAG_GROUP = 1U << 0, diff --git a/include/linux/rio_mport_cdev.h b/include/uapi/linux/rio_mport_cdev.h index b65d19d..5796bf1 100644 --- a/include/linux/rio_mport_cdev.h +++ b/include/uapi/linux/rio_mport_cdev.h @@ -39,16 +39,16 @@ #ifndef _RIO_MPORT_CDEV_H_ #define _RIO_MPORT_CDEV_H_ -#ifndef __user -#define __user -#endif +#include <linux/ioctl.h> +#include <linux/types.h> struct rio_mport_maint_io { - uint32_t rioid; /* destID of remote device */ - uint32_t hopcount; /* hopcount to remote device */ - uint32_t offset; /* offset in register space */ - size_t length; /* length in bytes */ - void __user *buffer; /* data buffer */ + __u16 rioid; /* destID of remote device */ + __u8 hopcount; /* hopcount to remote device */ + __u8 pad0[5]; + __u32 offset; /* offset in register space */ + __u32 length; /* length in bytes */ + __u64 buffer; /* pointer to data buffer */ }; /* @@ -66,22 +66,23 @@ struct rio_mport_maint_io { #define RIO_CAP_MAP_INB (1 << 7) struct rio_mport_properties { - uint16_t hdid; - uint8_t id; /* Physical port ID */ - uint8_t index; - uint32_t flags; - uint32_t sys_size; /* Default addressing size */ - uint8_t port_ok; - uint8_t link_speed; - uint8_t link_width; - uint32_t dma_max_sge; - uint32_t dma_max_size; - uint32_t dma_align; - uint32_t transfer_mode; /* Default transfer mode */ - uint32_t cap_sys_size; /* Capable system sizes */ - uint32_t cap_addr_size; /* Capable addressing sizes */ - uint32_t cap_transfer_mode; /* Capable transfer modes */ - uint32_t cap_mport; /* Mport capabilities */ + __u16 hdid; + __u8 id; /* Physical port ID */ + __u8 index; + __u32 flags; + __u32 sys_size; /* Default addressing size */ + __u8 port_ok; + __u8 link_speed; + __u8 link_width; + __u8 pad0; + __u32 dma_max_sge; + __u32 dma_max_size; + __u32 dma_align; + __u32 transfer_mode; /* Default transfer mode */ + __u32 cap_sys_size; /* Capable system sizes */ + __u32 cap_addr_size; /* Capable addressing sizes */ + __u32 cap_transfer_mode; /* Capable transfer modes */ + __u32 cap_mport; /* Mport capabilities */ }; /* @@ -93,54 +94,57 @@ struct rio_mport_properties { #define RIO_PORTWRITE (1 << 1) struct rio_doorbell { - uint32_t rioid; - uint16_t payload; + __u16 rioid; + __u16 payload; }; struct rio_doorbell_filter { - uint32_t rioid; /* 0xffffffff to match all ids */ - uint16_t low; - uint16_t high; + __u16 rioid; /* Use RIO_INVALID_DESTID to match all ids */ + __u16 low; + __u16 high; + __u16 pad0; }; struct rio_portwrite { - uint32_t payload[16]; + __u32 payload[16]; }; struct rio_pw_filter { - uint32_t mask; - uint32_t low; - uint32_t high; + __u32 mask; + __u32 low; + __u32 high; + __u32 pad0; }; /* RapidIO base address for inbound requests set to value defined below * indicates that no specific RIO-to-local address translation is requested * and driver should use direct (one-to-one) address mapping. */ -#define RIO_MAP_ANY_ADDR (uint64_t)(~((uint64_t) 0)) +#define RIO_MAP_ANY_ADDR (__u64)(~((__u64) 0)) struct rio_mmap { - uint32_t rioid; - uint64_t rio_addr; - uint64_t length; - uint64_t handle; - void *address; + __u16 rioid; + __u16 pad0[3]; + __u64 rio_addr; + __u64 length; + __u64 handle; + __u64 address; }; struct rio_dma_mem { - uint64_t length; /* length of DMA memory */ - uint64_t dma_handle; /* handle associated with this memory */ - void *buffer; /* pointer to this memory */ + __u64 length; /* length of DMA memory */ + __u64 dma_handle; /* handle associated with this memory */ + __u64 address; }; - struct rio_event { - unsigned int header; /* event type RIO_DOORBELL or RIO_PORTWRITE */ + __u32 header; /* event type RIO_DOORBELL or RIO_PORTWRITE */ union { struct rio_doorbell doorbell; /* header for RIO_DOORBELL */ struct rio_portwrite portwrite; /* header for RIO_PORTWRITE */ } u; + __u32 pad0; }; enum rio_transfer_sync { @@ -184,35 +188,37 @@ enum rio_exchange { }; struct rio_transfer_io { - uint32_t rioid; /* Target destID */ - uint64_t rio_addr; /* Address in target's RIO mem space */ - enum rio_exchange method; /* Data exchange method */ - void __user *loc_addr; - uint64_t handle; - uint64_t offset; /* Offset in buffer */ - uint64_t length; /* Length in bytes */ - uint32_t completion_code; /* Completion code for this transfer */ + __u64 rio_addr; /* Address in target's RIO mem space */ + __u64 loc_addr; + __u64 handle; + __u64 offset; /* Offset in buffer */ + __u64 length; /* Length in bytes */ + __u16 rioid; /* Target destID */ + __u16 method; /* Data exchange method, one of rio_exchange enum */ + __u32 completion_code; /* Completion code for this transfer */ }; struct rio_transaction { - uint32_t transfer_mode; /* Data transfer mode */ - enum rio_transfer_sync sync; /* Synchronization method */ - enum rio_transfer_dir dir; /* Transfer direction */ - size_t count; /* Number of transfers */ - struct rio_transfer_io __user *block; /* Array of <count> transfers */ + __u64 block; /* Pointer to array of <count> transfers */ + __u32 count; /* Number of transfers */ + __u32 transfer_mode; /* Data transfer mode */ + __u16 sync; /* Synch method, one of rio_transfer_sync enum */ + __u16 dir; /* Transfer direction, one of rio_transfer_dir enum */ + __u32 pad0; }; struct rio_async_tx_wait { - uint32_t token; /* DMA transaction ID token */ - uint32_t timeout; /* Wait timeout in msec, if 0 use default TO */ + __u32 token; /* DMA transaction ID token */ + __u32 timeout; /* Wait timeout in msec, if 0 use default TO */ }; #define RIO_MAX_DEVNAME_SZ 20 struct rio_rdev_info { - uint32_t destid; - uint8_t hopcount; - uint32_t comptag; + __u16 destid; + __u8 hopcount; + __u8 pad0; + __u32 comptag; char name[RIO_MAX_DEVNAME_SZ + 1]; }; @@ -220,11 +226,11 @@ struct rio_rdev_info { #define RIO_MPORT_DRV_MAGIC 'm' #define RIO_MPORT_MAINT_HDID_SET \ - _IOW(RIO_MPORT_DRV_MAGIC, 1, uint16_t) + _IOW(RIO_MPORT_DRV_MAGIC, 1, __u16) #define RIO_MPORT_MAINT_COMPTAG_SET \ - _IOW(RIO_MPORT_DRV_MAGIC, 2, uint32_t) + _IOW(RIO_MPORT_DRV_MAGIC, 2, __u32) #define RIO_MPORT_MAINT_PORT_IDX_GET \ - _IOR(RIO_MPORT_DRV_MAGIC, 3, uint32_t) + _IOR(RIO_MPORT_DRV_MAGIC, 3, __u32) #define RIO_MPORT_GET_PROPERTIES \ _IOR(RIO_MPORT_DRV_MAGIC, 4, struct rio_mport_properties) #define RIO_MPORT_MAINT_READ_LOCAL \ @@ -244,9 +250,9 @@ struct rio_rdev_info { #define RIO_DISABLE_PORTWRITE_RANGE \ _IOW(RIO_MPORT_DRV_MAGIC, 12, struct rio_pw_filter) #define RIO_SET_EVENT_MASK \ - _IOW(RIO_MPORT_DRV_MAGIC, 13, unsigned int) + _IOW(RIO_MPORT_DRV_MAGIC, 13, __u32) #define RIO_GET_EVENT_MASK \ - _IOR(RIO_MPORT_DRV_MAGIC, 14, unsigned int) + _IOR(RIO_MPORT_DRV_MAGIC, 14, __u32) #define RIO_MAP_OUTBOUND \ _IOWR(RIO_MPORT_DRV_MAGIC, 15, struct rio_mmap) #define RIO_UNMAP_OUTBOUND \ @@ -254,11 +260,11 @@ struct rio_rdev_info { #define RIO_MAP_INBOUND \ _IOWR(RIO_MPORT_DRV_MAGIC, 17, struct rio_mmap) #define RIO_UNMAP_INBOUND \ - _IOW(RIO_MPORT_DRV_MAGIC, 18, uint64_t) + _IOW(RIO_MPORT_DRV_MAGIC, 18, __u64) #define RIO_ALLOC_DMA \ _IOWR(RIO_MPORT_DRV_MAGIC, 19, struct rio_dma_mem) #define RIO_FREE_DMA \ - _IOW(RIO_MPORT_DRV_MAGIC, 20, uint64_t) + _IOW(RIO_MPORT_DRV_MAGIC, 20, __u64) #define RIO_TRANSFER \ _IOWR(RIO_MPORT_DRV_MAGIC, 21, struct rio_transaction) #define RIO_WAIT_FOR_ASYNC \ diff --git a/include/uapi/linux/signal.h b/include/uapi/linux/signal.h index e1bd50c2..cd0804b 100644 --- a/include/uapi/linux/signal.h +++ b/include/uapi/linux/signal.h @@ -7,4 +7,9 @@ #define SS_ONSTACK 1 #define SS_DISABLE 2 +/* bit-flags */ +#define SS_AUTODISARM (1U << 31) /* disable sas during sighandling */ +/* mask for all SS_xxx flags */ +#define SS_FLAG_BITS SS_AUTODISARM + #endif /* _UAPI_LINUX_SIGNAL_H */ diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h index 3f10e53..8f3a8f6 100644 --- a/include/uapi/linux/swab.h +++ b/include/uapi/linux/swab.h @@ -45,9 +45,7 @@ static inline __attribute_const__ __u16 __fswab16(__u16 val) { -#ifdef __HAVE_BUILTIN_BSWAP16__ - return __builtin_bswap16(val); -#elif defined (__arch_swab16) +#if defined (__arch_swab16) return __arch_swab16(val); #else return ___constant_swab16(val); @@ -56,9 +54,7 @@ static inline __attribute_const__ __u16 __fswab16(__u16 val) static inline __attribute_const__ __u32 __fswab32(__u32 val) { -#ifdef __HAVE_BUILTIN_BSWAP32__ - return __builtin_bswap32(val); -#elif defined(__arch_swab32) +#if defined(__arch_swab32) return __arch_swab32(val); #else return ___constant_swab32(val); @@ -67,9 +63,7 @@ static inline __attribute_const__ __u32 __fswab32(__u32 val) static inline __attribute_const__ __u64 __fswab64(__u64 val) { -#ifdef __HAVE_BUILTIN_BSWAP64__ - return __builtin_bswap64(val); -#elif defined (__arch_swab64) +#if defined (__arch_swab64) return __arch_swab64(val); #elif defined(__SWAB_64_THRU_32__) __u32 h = val >> 32; @@ -102,28 +96,40 @@ static inline __attribute_const__ __u32 __fswahb32(__u32 val) * __swab16 - return a byteswapped 16-bit value * @x: value to byteswap */ +#ifdef __HAVE_BUILTIN_BSWAP16__ +#define __swab16(x) (__u16)__builtin_bswap16((__u16)(x)) +#else #define __swab16(x) \ (__builtin_constant_p((__u16)(x)) ? \ ___constant_swab16(x) : \ __fswab16(x)) +#endif /** * __swab32 - return a byteswapped 32-bit value * @x: value to byteswap */ +#ifdef __HAVE_BUILTIN_BSWAP32__ +#define __swab32(x) (__u32)__builtin_bswap32((__u32)(x)) +#else #define __swab32(x) \ (__builtin_constant_p((__u32)(x)) ? \ ___constant_swab32(x) : \ __fswab32(x)) +#endif /** * __swab64 - return a byteswapped 64-bit value * @x: value to byteswap */ +#ifdef __HAVE_BUILTIN_BSWAP64__ +#define __swab64(x) (__u64)__builtin_bswap64((__u64)(x)) +#else #define __swab64(x) \ (__builtin_constant_p((__u64)(x)) ? \ ___constant_swab64(x) : \ __fswab64(x)) +#endif /** * __swahw32 - return a word-swapped 32-bit value diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild index 242cf0c..e3969bd 100644 --- a/include/uapi/linux/tc_act/Kbuild +++ b/include/uapi/linux/tc_act/Kbuild @@ -10,3 +10,4 @@ header-y += tc_skbedit.h header-y += tc_vlan.h header-y += tc_bpf.h header-y += tc_connmark.h +header-y += tc_ife.h diff --git a/include/xen/page.h b/include/xen/page.h index 96294ac..9dc46cb 100644 --- a/include/xen/page.h +++ b/include/xen/page.h @@ -15,9 +15,9 @@ */ #define xen_pfn_to_page(xen_pfn) \ - ((pfn_to_page(((unsigned long)(xen_pfn) << XEN_PAGE_SHIFT) >> PAGE_SHIFT))) + (pfn_to_page((unsigned long)(xen_pfn) >> (PAGE_SHIFT - XEN_PAGE_SHIFT))) #define page_to_xen_pfn(page) \ - (((page_to_pfn(page)) << PAGE_SHIFT) >> XEN_PAGE_SHIFT) + ((page_to_pfn(page)) << (PAGE_SHIFT - XEN_PAGE_SHIFT)) #define XEN_PFN_PER_PAGE (PAGE_SIZE / XEN_PAGE_SIZE) diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index f2ece3c..8f94ca1 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -31,10 +31,10 @@ static void *bpf_any_get(void *raw, enum bpf_type type) { switch (type) { case BPF_TYPE_PROG: - atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt); + raw = bpf_prog_inc(raw); break; case BPF_TYPE_MAP: - bpf_map_inc(raw, true); + raw = bpf_map_inc(raw, true); break; default: WARN_ON_ONCE(1); @@ -297,7 +297,8 @@ static void *bpf_obj_do_get(const struct filename *pathname, goto out; raw = bpf_any_get(inode->i_private, *type); - touch_atime(&path); + if (!IS_ERR(raw)) + touch_atime(&path); path_put(&path); return raw; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 499d9e9..f5a1954 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -66,7 +66,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || value_size < 8 || value_size % 8 || - value_size / 8 > PERF_MAX_STACK_DEPTH) + value_size / 8 > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); /* hash table size must be power of 2 */ @@ -124,8 +124,8 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) struct perf_callchain_entry *trace; struct stack_map_bucket *bucket, *new_bucket, *old_bucket; u32 max_depth = map->value_size / 8; - /* stack_map_alloc() checks that max_depth <= PERF_MAX_STACK_DEPTH */ - u32 init_nr = PERF_MAX_STACK_DEPTH - max_depth; + /* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */ + u32 init_nr = sysctl_perf_event_max_stack - max_depth; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; u32 hash, id, trace_nr, trace_len; bool user = flags & BPF_F_USER_STACK; @@ -143,7 +143,7 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) return -EFAULT; /* get_perf_callchain() guarantees that trace->nr >= init_nr - * and trace-nr <= PERF_MAX_STACK_DEPTH, so trace_nr <= max_depth + * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth */ trace_nr = trace->nr - init_nr; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index adc5e4b..cf5e9f7 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -218,11 +218,18 @@ struct bpf_map *__bpf_map_get(struct fd f) return f.file->private_data; } -void bpf_map_inc(struct bpf_map *map, bool uref) +/* prog's and map's refcnt limit */ +#define BPF_MAX_REFCNT 32768 + +struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref) { - atomic_inc(&map->refcnt); + if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) { + atomic_dec(&map->refcnt); + return ERR_PTR(-EBUSY); + } if (uref) atomic_inc(&map->usercnt); + return map; } struct bpf_map *bpf_map_get_with_uref(u32 ufd) @@ -234,7 +241,7 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd) if (IS_ERR(map)) return map; - bpf_map_inc(map, true); + map = bpf_map_inc(map, true); fdput(f); return map; @@ -658,6 +665,15 @@ static struct bpf_prog *__bpf_prog_get(struct fd f) return f.file->private_data; } +struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) +{ + if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) { + atomic_dec(&prog->aux->refcnt); + return ERR_PTR(-EBUSY); + } + return prog; +} + /* called by sockets/tracing/seccomp before attaching program to an event * pairs with bpf_prog_put() */ @@ -670,7 +686,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd) if (IS_ERR(prog)) return prog; - atomic_inc(&prog->aux->refcnt); + prog = bpf_prog_inc(prog); fdput(f); return prog; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index db2574e..c5c17a6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -239,16 +239,6 @@ static const char * const reg_type_str[] = { [CONST_IMM] = "imm", }; -static const struct { - int map_type; - int func_id; -} func_limit[] = { - {BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call}, - {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read}, - {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output}, - {BPF_MAP_TYPE_STACK_TRACE, BPF_FUNC_get_stackid}, -}; - static void print_verifier_state(struct verifier_env *env) { enum bpf_reg_type t; @@ -921,27 +911,52 @@ static int check_func_arg(struct verifier_env *env, u32 regno, static int check_map_func_compatibility(struct bpf_map *map, int func_id) { - bool bool_map, bool_func; - int i; - if (!map) return 0; - for (i = 0; i < ARRAY_SIZE(func_limit); i++) { - bool_map = (map->map_type == func_limit[i].map_type); - bool_func = (func_id == func_limit[i].func_id); - /* only when map & func pair match it can continue. - * don't allow any other map type to be passed into - * the special func; - */ - if (bool_func && bool_map != bool_func) { - verbose("cannot pass map_type %d into func %d\n", - map->map_type, func_id); - return -EINVAL; - } + /* We need a two way check, first is from map perspective ... */ + switch (map->map_type) { + case BPF_MAP_TYPE_PROG_ARRAY: + if (func_id != BPF_FUNC_tail_call) + goto error; + break; + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + if (func_id != BPF_FUNC_perf_event_read && + func_id != BPF_FUNC_perf_event_output) + goto error; + break; + case BPF_MAP_TYPE_STACK_TRACE: + if (func_id != BPF_FUNC_get_stackid) + goto error; + break; + default: + break; + } + + /* ... and second from the function itself. */ + switch (func_id) { + case BPF_FUNC_tail_call: + if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) + goto error; + break; + case BPF_FUNC_perf_event_read: + case BPF_FUNC_perf_event_output: + if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) + goto error; + break; + case BPF_FUNC_get_stackid: + if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) + goto error; + break; + default: + break; } return 0; +error: + verbose("cannot pass map_type %d into func %d\n", + map->map_type, func_id); + return -EINVAL; } static int check_call(struct verifier_env *env, int func_id) @@ -2049,15 +2064,18 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env) return -E2BIG; } - /* remember this map */ - env->used_maps[env->used_map_cnt++] = map; - /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded * and all maps are released in free_bpf_prog_info() */ - bpf_map_inc(map, false); + map = bpf_map_inc(map, false); + if (IS_ERR(map)) { + fdput(f); + return PTR_ERR(map); + } + env->used_maps[env->used_map_cnt++] = map; + fdput(f); next_insn: insn++; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 909a7d3..86cb5c6 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1215,6 +1215,41 @@ static void cgroup_destroy_root(struct cgroup_root *root) cgroup_free_root(root); } +/* + * look up cgroup associated with current task's cgroup namespace on the + * specified hierarchy + */ +static struct cgroup * +current_cgns_cgroup_from_root(struct cgroup_root *root) +{ + struct cgroup *res = NULL; + struct css_set *cset; + + lockdep_assert_held(&css_set_lock); + + rcu_read_lock(); + + cset = current->nsproxy->cgroup_ns->root_cset; + if (cset == &init_css_set) { + res = &root->cgrp; + } else { + struct cgrp_cset_link *link; + + list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { + struct cgroup *c = link->cgrp; + + if (c->root == root) { + res = c; + break; + } + } + } + rcu_read_unlock(); + + BUG_ON(!res); + return res; +} + /* look up cgroup associated with given css_set on the specified hierarchy */ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) @@ -1593,6 +1628,33 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) return 0; } +static int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, + struct kernfs_root *kf_root) +{ + int len = 0; + char *buf = NULL; + struct cgroup_root *kf_cgroot = cgroup_root_from_kf(kf_root); + struct cgroup *ns_cgroup; + + buf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + spin_lock_bh(&css_set_lock); + ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot); + len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); + spin_unlock_bh(&css_set_lock); + + if (len >= PATH_MAX) + len = -ERANGE; + else if (len > 0) { + seq_escape(sf, buf, " \t\n\\"); + len = 0; + } + kfree(buf); + return len; +} + static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { @@ -5433,6 +5495,7 @@ static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .rename = cgroup_rename, + .show_path = cgroup_show_path, }; static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) diff --git a/kernel/cpu.c b/kernel/cpu.c index 3e3f6e4..d948e44 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -703,21 +703,6 @@ static int takedown_cpu(unsigned int cpu) struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int err; - /* - * By now we've cleared cpu_active_mask, wait for all preempt-disabled - * and RCU users of this state to go away such that all new such users - * will observe it. - * - * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might - * not imply sync_sched(), so wait for both. - * - * Do sync before park smpboot threads to take care the rcu boost case. - */ - if (IS_ENABLED(CONFIG_PREEMPT)) - synchronize_rcu_mult(call_rcu, call_rcu_sched); - else - synchronize_rcu(); - /* Park the smpboot threads */ kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread); smpboot_park_threads(cpu); @@ -923,8 +908,6 @@ void cpuhp_online_idle(enum cpuhp_state state) st->state = CPUHP_AP_ONLINE_IDLE; - /* The cpu is marked online, set it active now */ - set_cpu_active(cpu, true); /* Unpark the stopper thread and the hotplug thread of this cpu */ stop_machine_unpark(cpu); kthread_unpark(st->thread); @@ -1236,6 +1219,12 @@ static struct cpuhp_step cpuhp_ap_states[] = { .name = "ap:offline", .cant_stop = true, }, + /* First state is scheduler control. Interrupts are disabled */ + [CPUHP_AP_SCHED_STARTING] = { + .name = "sched:starting", + .startup = sched_cpu_starting, + .teardown = sched_cpu_dying, + }, /* * Low level startup/teardown notifiers. Run with interrupts * disabled. Will be removed once the notifiers are converted to @@ -1274,6 +1263,15 @@ static struct cpuhp_step cpuhp_ap_states[] = { * The dynamically registered state space is here */ +#ifdef CONFIG_SMP + /* Last state is scheduler control setting the cpu active */ + [CPUHP_AP_ACTIVE] = { + .name = "sched:active", + .startup = sched_cpu_activate, + .teardown = sched_cpu_deactivate, + }, +#endif + /* CPU is fully up and running. */ [CPUHP_ONLINE] = { .name = "online", diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 343c22f..b9325e7 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -18,6 +18,14 @@ struct callchain_cpus_entries { struct perf_callchain_entry *cpu_entries[0]; }; +int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH; + +static inline size_t perf_callchain_entry__sizeof(void) +{ + return (sizeof(struct perf_callchain_entry) + + sizeof(__u64) * sysctl_perf_event_max_stack); +} + static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]); static atomic_t nr_callchain_events; static DEFINE_MUTEX(callchain_mutex); @@ -73,7 +81,7 @@ static int alloc_callchain_buffers(void) if (!entries) return -ENOMEM; - size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS; + size = perf_callchain_entry__sizeof() * PERF_NR_CONTEXTS; for_each_possible_cpu(cpu) { entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL, @@ -147,7 +155,8 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx) cpu = smp_processor_id(); - return &entries->cpu_entries[cpu][*rctx]; + return (((void *)entries->cpu_entries[cpu]) + + (*rctx * perf_callchain_entry__sizeof())); } static void @@ -215,3 +224,25 @@ exit_put: return entry; } + +int perf_event_max_stack_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int new_value = sysctl_perf_event_max_stack, ret; + struct ctl_table new_table = *table; + + new_table.data = &new_value; + ret = proc_dointvec_minmax(&new_table, write, buffer, lenp, ppos); + if (ret || !write) + return ret; + + mutex_lock(&callchain_mutex); + if (atomic_read(&nr_callchain_events)) + ret = -EBUSY; + else + sysctl_perf_event_max_stack = new_value; + + mutex_unlock(&callchain_mutex); + + return ret; +} diff --git a/kernel/events/core.c b/kernel/events/core.c index 4e2ebf6..050a290 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -44,6 +44,8 @@ #include <linux/compat.h> #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/namei.h> +#include <linux/parser.h> #include "internal.h" @@ -351,7 +353,7 @@ static struct srcu_struct pmus_srcu; * 1 - disallow cpu events for unpriv * 2 - disallow kernel profiling for unpriv */ -int sysctl_perf_event_paranoid __read_mostly = 1; +int sysctl_perf_event_paranoid __read_mostly = 2; /* Minimum for 512 kiB + 1 user control page */ int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */ @@ -1927,8 +1929,13 @@ event_sched_in(struct perf_event *event, if (event->state <= PERF_EVENT_STATE_OFF) return 0; - event->state = PERF_EVENT_STATE_ACTIVE; - event->oncpu = smp_processor_id(); + WRITE_ONCE(event->oncpu, smp_processor_id()); + /* + * Order event::oncpu write to happen before the ACTIVE state + * is visible. + */ + smp_wmb(); + WRITE_ONCE(event->state, PERF_EVENT_STATE_ACTIVE); /* * Unthrottle events, since we scheduled we might have missed several @@ -2360,6 +2367,112 @@ void perf_event_enable(struct perf_event *event) } EXPORT_SYMBOL_GPL(perf_event_enable); +struct stop_event_data { + struct perf_event *event; + unsigned int restart; +}; + +static int __perf_event_stop(void *info) +{ + struct stop_event_data *sd = info; + struct perf_event *event = sd->event; + + /* if it's already INACTIVE, do nothing */ + if (READ_ONCE(event->state) != PERF_EVENT_STATE_ACTIVE) + return 0; + + /* matches smp_wmb() in event_sched_in() */ + smp_rmb(); + + /* + * There is a window with interrupts enabled before we get here, + * so we need to check again lest we try to stop another CPU's event. + */ + if (READ_ONCE(event->oncpu) != smp_processor_id()) + return -EAGAIN; + + event->pmu->stop(event, PERF_EF_UPDATE); + + /* + * May race with the actual stop (through perf_pmu_output_stop()), + * but it is only used for events with AUX ring buffer, and such + * events will refuse to restart because of rb::aux_mmap_count==0, + * see comments in perf_aux_output_begin(). + * + * Since this is happening on a event-local CPU, no trace is lost + * while restarting. + */ + if (sd->restart) + event->pmu->start(event, PERF_EF_START); + + return 0; +} + +static int perf_event_restart(struct perf_event *event) +{ + struct stop_event_data sd = { + .event = event, + .restart = 1, + }; + int ret = 0; + + do { + if (READ_ONCE(event->state) != PERF_EVENT_STATE_ACTIVE) + return 0; + + /* matches smp_wmb() in event_sched_in() */ + smp_rmb(); + + /* + * We only want to restart ACTIVE events, so if the event goes + * inactive here (event->oncpu==-1), there's nothing more to do; + * fall through with ret==-ENXIO. + */ + ret = cpu_function_call(READ_ONCE(event->oncpu), + __perf_event_stop, &sd); + } while (ret == -EAGAIN); + + return ret; +} + +/* + * In order to contain the amount of racy and tricky in the address filter + * configuration management, it is a two part process: + * + * (p1) when userspace mappings change as a result of (1) or (2) or (3) below, + * we update the addresses of corresponding vmas in + * event::addr_filters_offs array and bump the event::addr_filters_gen; + * (p2) when an event is scheduled in (pmu::add), it calls + * perf_event_addr_filters_sync() which calls pmu::addr_filters_sync() + * if the generation has changed since the previous call. + * + * If (p1) happens while the event is active, we restart it to force (p2). + * + * (1) perf_addr_filters_apply(): adjusting filters' offsets based on + * pre-existing mappings, called once when new filters arrive via SET_FILTER + * ioctl; + * (2) perf_addr_filters_adjust(): adjusting filters' offsets based on newly + * registered mapping, called for every new mmap(), with mm::mmap_sem down + * for reading; + * (3) perf_event_addr_filters_exec(): clearing filters' offsets in the process + * of exec. + */ +void perf_event_addr_filters_sync(struct perf_event *event) +{ + struct perf_addr_filters_head *ifh = perf_event_addr_filters(event); + + if (!has_addr_filter(event)) + return; + + raw_spin_lock(&ifh->lock); + if (event->addr_filters_gen != event->hw.addr_filters_gen) { + event->pmu->addr_filters_sync(event); + event->hw.addr_filters_gen = event->addr_filters_gen; + } + raw_spin_unlock(&ifh->lock); +} +EXPORT_SYMBOL_GPL(perf_event_addr_filters_sync); + static int _perf_event_refresh(struct perf_event *event, int refresh) { /* @@ -3209,16 +3322,6 @@ out: put_ctx(clone_ctx); } -void perf_event_exec(void) -{ - int ctxn; - - rcu_read_lock(); - for_each_task_context_nr(ctxn) - perf_event_enable_on_exec(ctxn); - rcu_read_unlock(); -} - struct perf_read_data { struct perf_event *event; bool group; @@ -3720,6 +3823,9 @@ static bool exclusive_event_installable(struct perf_event *event, return true; } +static void perf_addr_filters_splice(struct perf_event *event, + struct list_head *head); + static void _free_event(struct perf_event *event) { irq_work_sync(&event->pending); @@ -3747,6 +3853,8 @@ static void _free_event(struct perf_event *event) } perf_event_free_bpf_prog(event); + perf_addr_filters_splice(event, NULL); + kfree(event->addr_filters_offs); if (event->destroy) event->destroy(event); @@ -4343,6 +4451,19 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon case PERF_EVENT_IOC_SET_BPF: return perf_event_set_bpf_prog(event, arg); + case PERF_EVENT_IOC_PAUSE_OUTPUT: { + struct ring_buffer *rb; + + rcu_read_lock(); + rb = rcu_dereference(event->rb); + if (!rb || !rb->nr_pages) { + rcu_read_unlock(); + return -EINVAL; + } + rb_toggle_paused(rb, !!arg); + rcu_read_unlock(); + return 0; + } default: return -ENOTTY; } @@ -4659,6 +4780,8 @@ static void perf_mmap_open(struct vm_area_struct *vma) event->pmu->event_mapped(event); } +static void perf_pmu_output_stop(struct perf_event *event); + /* * A buffer can be mmap()ed multiple times; either directly through the same * event, or through other events by use of perf_event_set_output(). @@ -4686,10 +4809,22 @@ static void perf_mmap_close(struct vm_area_struct *vma) */ if (rb_has_aux(rb) && vma->vm_pgoff == rb->aux_pgoff && atomic_dec_and_mutex_lock(&rb->aux_mmap_count, &event->mmap_mutex)) { + /* + * Stop all AUX events that are writing to this buffer, + * so that we can free its AUX pages and corresponding PMU + * data. Note that after rb::aux_mmap_count dropped to zero, + * they won't start any more (see perf_aux_output_begin()). + */ + perf_pmu_output_stop(event); + + /* now it's safe to free the pages */ atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm); vma->vm_mm->pinned_vm -= rb->aux_mmap_locked; + /* this has to be the last one */ rb_free_aux(rb); + WARN_ON_ONCE(atomic_read(&rb->aux_refcount)); + mutex_unlock(&event->mmap_mutex); } @@ -5630,9 +5765,13 @@ void perf_prepare_sample(struct perf_event_header *header, } } -void perf_event_output(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) +static void __always_inline +__perf_event_output(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs, + int (*output_begin)(struct perf_output_handle *, + struct perf_event *, + unsigned int)) { struct perf_output_handle handle; struct perf_event_header header; @@ -5642,7 +5781,7 @@ void perf_event_output(struct perf_event *event, perf_prepare_sample(&header, data, event, regs); - if (perf_output_begin(&handle, event, header.size)) + if (output_begin(&handle, event, header.size)) goto exit; perf_output_sample(&handle, &header, data, event); @@ -5653,6 +5792,30 @@ exit: rcu_read_unlock(); } +void +perf_event_output_forward(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + __perf_event_output(event, data, regs, perf_output_begin_forward); +} + +void +perf_event_output_backward(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + __perf_event_output(event, data, regs, perf_output_begin_backward); +} + +void +perf_event_output(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + __perf_event_output(event, data, regs, perf_output_begin); +} + /* * read event_id */ @@ -5698,15 +5861,18 @@ typedef void (perf_event_aux_output_cb)(struct perf_event *event, void *data); static void perf_event_aux_ctx(struct perf_event_context *ctx, perf_event_aux_output_cb output, - void *data) + void *data, bool all) { struct perf_event *event; list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { - if (event->state < PERF_EVENT_STATE_INACTIVE) - continue; - if (!event_filter_match(event)) - continue; + if (!all) { + if (event->state < PERF_EVENT_STATE_INACTIVE) + continue; + if (!event_filter_match(event)) + continue; + } + output(event, data); } } @@ -5717,7 +5883,7 @@ perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data, { rcu_read_lock(); preempt_disable(); - perf_event_aux_ctx(task_ctx, output, data); + perf_event_aux_ctx(task_ctx, output, data, false); preempt_enable(); rcu_read_unlock(); } @@ -5747,13 +5913,13 @@ perf_event_aux(perf_event_aux_output_cb output, void *data, cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); if (cpuctx->unique_pmu != pmu) goto next; - perf_event_aux_ctx(&cpuctx->ctx, output, data); + perf_event_aux_ctx(&cpuctx->ctx, output, data, false); ctxn = pmu->task_ctx_nr; if (ctxn < 0) goto next; ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); if (ctx) - perf_event_aux_ctx(ctx, output, data); + perf_event_aux_ctx(ctx, output, data, false); next: put_cpu_ptr(pmu->pmu_cpu_context); } @@ -5761,6 +5927,134 @@ next: } /* + * Clear all file-based filters at exec, they'll have to be + * re-instated when/if these objects are mmapped again. + */ +static void perf_event_addr_filters_exec(struct perf_event *event, void *data) +{ + struct perf_addr_filters_head *ifh = perf_event_addr_filters(event); + struct perf_addr_filter *filter; + unsigned int restart = 0, count = 0; + unsigned long flags; + + if (!has_addr_filter(event)) + return; + + raw_spin_lock_irqsave(&ifh->lock, flags); + list_for_each_entry(filter, &ifh->list, entry) { + if (filter->inode) { + event->addr_filters_offs[count] = 0; + restart++; + } + + count++; + } + + if (restart) + event->addr_filters_gen++; + raw_spin_unlock_irqrestore(&ifh->lock, flags); + + if (restart) + perf_event_restart(event); +} + +void perf_event_exec(void) +{ + struct perf_event_context *ctx; + int ctxn; + + rcu_read_lock(); + for_each_task_context_nr(ctxn) { + ctx = current->perf_event_ctxp[ctxn]; + if (!ctx) + continue; + + perf_event_enable_on_exec(ctxn); + + perf_event_aux_ctx(ctx, perf_event_addr_filters_exec, NULL, + true); + } + rcu_read_unlock(); +} + +struct remote_output { + struct ring_buffer *rb; + int err; +}; + +static void __perf_event_output_stop(struct perf_event *event, void *data) +{ + struct perf_event *parent = event->parent; + struct remote_output *ro = data; + struct ring_buffer *rb = ro->rb; + struct stop_event_data sd = { + .event = event, + }; + + if (!has_aux(event)) + return; + + if (!parent) + parent = event; + + /* + * In case of inheritance, it will be the parent that links to the + * ring-buffer, but it will be the child that's actually using it: + */ + if (rcu_dereference(parent->rb) == rb) + ro->err = __perf_event_stop(&sd); +} + +static int __perf_pmu_output_stop(void *info) +{ + struct perf_event *event = info; + struct pmu *pmu = event->pmu; + struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + struct remote_output ro = { + .rb = event->rb, + }; + + rcu_read_lock(); + perf_event_aux_ctx(&cpuctx->ctx, __perf_event_output_stop, &ro, false); + if (cpuctx->task_ctx) + perf_event_aux_ctx(cpuctx->task_ctx, __perf_event_output_stop, + &ro, false); + rcu_read_unlock(); + + return ro.err; +} + +static void perf_pmu_output_stop(struct perf_event *event) +{ + struct perf_event *iter; + int err, cpu; + +restart: + rcu_read_lock(); + list_for_each_entry_rcu(iter, &event->rb->event_list, rb_entry) { + /* + * For per-CPU events, we need to make sure that neither they + * nor their children are running; for cpu==-1 events it's + * sufficient to stop the event itself if it's active, since + * it can't have children. + */ + cpu = iter->cpu; + if (cpu == -1) + cpu = READ_ONCE(iter->oncpu); + + if (cpu == -1) + continue; + + err = cpu_function_call(cpu, __perf_pmu_output_stop, event); + if (err == -EAGAIN) { + rcu_read_unlock(); + goto restart; + } + } + rcu_read_unlock(); +} + +/* * task tracking -- fork/exit * * enabled by: attr.comm | attr.mmap | attr.mmap2 | attr.mmap_data | attr.task @@ -6169,6 +6463,87 @@ got_name: kfree(buf); } +/* + * Whether this @filter depends on a dynamic object which is not loaded + * yet or its load addresses are not known. + */ +static bool perf_addr_filter_needs_mmap(struct perf_addr_filter *filter) +{ + return filter->filter && filter->inode; +} + +/* + * Check whether inode and address range match filter criteria. + */ +static bool perf_addr_filter_match(struct perf_addr_filter *filter, + struct file *file, unsigned long offset, + unsigned long size) +{ + if (filter->inode != file->f_inode) + return false; + + if (filter->offset > offset + size) + return false; + + if (filter->offset + filter->size < offset) + return false; + + return true; +} + +static void __perf_addr_filters_adjust(struct perf_event *event, void *data) +{ + struct perf_addr_filters_head *ifh = perf_event_addr_filters(event); + struct vm_area_struct *vma = data; + unsigned long off = vma->vm_pgoff << PAGE_SHIFT, flags; + struct file *file = vma->vm_file; + struct perf_addr_filter *filter; + unsigned int restart = 0, count = 0; + + if (!has_addr_filter(event)) + return; + + if (!file) + return; + + raw_spin_lock_irqsave(&ifh->lock, flags); + list_for_each_entry(filter, &ifh->list, entry) { + if (perf_addr_filter_match(filter, file, off, + vma->vm_end - vma->vm_start)) { + event->addr_filters_offs[count] = vma->vm_start; + restart++; + } + + count++; + } + + if (restart) + event->addr_filters_gen++; + raw_spin_unlock_irqrestore(&ifh->lock, flags); + + if (restart) + perf_event_restart(event); +} + +/* + * Adjust all task's events' filters to the new vma + */ +static void perf_addr_filters_adjust(struct vm_area_struct *vma) +{ + struct perf_event_context *ctx; + int ctxn; + + rcu_read_lock(); + for_each_task_context_nr(ctxn) { + ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); + if (!ctx) + continue; + + perf_event_aux_ctx(ctx, __perf_addr_filters_adjust, vma, true); + } + rcu_read_unlock(); +} + void perf_event_mmap(struct vm_area_struct *vma) { struct perf_mmap_event mmap_event; @@ -6200,6 +6575,7 @@ void perf_event_mmap(struct vm_area_struct *vma) /* .flags (attr_mmap2 only) */ }; + perf_addr_filters_adjust(vma); perf_event_mmap_event(&mmap_event); } @@ -6491,10 +6867,7 @@ static int __perf_event_overflow(struct perf_event *event, irq_work_queue(&event->pending); } - if (event->overflow_handler) - event->overflow_handler(event, data, regs); - else - perf_event_output(event, data, regs); + event->overflow_handler(event, data, regs); if (*perf_event_fasync(event) && event->pending_kill) { event->pending_wakeup = 1; @@ -7081,24 +7454,6 @@ static inline void perf_tp_register(void) perf_pmu_register(&perf_tracepoint, "tracepoint", PERF_TYPE_TRACEPOINT); } -static int perf_event_set_filter(struct perf_event *event, void __user *arg) -{ - char *filter_str; - int ret; - - if (event->attr.type != PERF_TYPE_TRACEPOINT) - return -EINVAL; - - filter_str = strndup_user(arg, PAGE_SIZE); - if (IS_ERR(filter_str)) - return PTR_ERR(filter_str); - - ret = ftrace_profile_set_filter(event, event->attr.config, filter_str); - - kfree(filter_str); - return ret; -} - static void perf_event_free_filter(struct perf_event *event) { ftrace_profile_free_filter(event); @@ -7153,11 +7508,6 @@ static inline void perf_tp_register(void) { } -static int perf_event_set_filter(struct perf_event *event, void __user *arg) -{ - return -ENOENT; -} - static void perf_event_free_filter(struct perf_event *event) { } @@ -7186,6 +7536,387 @@ void perf_bp_event(struct perf_event *bp, void *data) #endif /* + * Allocate a new address filter + */ +static struct perf_addr_filter * +perf_addr_filter_new(struct perf_event *event, struct list_head *filters) +{ + int node = cpu_to_node(event->cpu == -1 ? 0 : event->cpu); + struct perf_addr_filter *filter; + + filter = kzalloc_node(sizeof(*filter), GFP_KERNEL, node); + if (!filter) + return NULL; + + INIT_LIST_HEAD(&filter->entry); + list_add_tail(&filter->entry, filters); + + return filter; +} + +static void free_filters_list(struct list_head *filters) +{ + struct perf_addr_filter *filter, *iter; + + list_for_each_entry_safe(filter, iter, filters, entry) { + if (filter->inode) + iput(filter->inode); + list_del(&filter->entry); + kfree(filter); + } +} + +/* + * Free existing address filters and optionally install new ones + */ +static void perf_addr_filters_splice(struct perf_event *event, + struct list_head *head) +{ + unsigned long flags; + LIST_HEAD(list); + + if (!has_addr_filter(event)) + return; + + /* don't bother with children, they don't have their own filters */ + if (event->parent) + return; + + raw_spin_lock_irqsave(&event->addr_filters.lock, flags); + + list_splice_init(&event->addr_filters.list, &list); + if (head) + list_splice(head, &event->addr_filters.list); + + raw_spin_unlock_irqrestore(&event->addr_filters.lock, flags); + + free_filters_list(&list); +} + +/* + * Scan through mm's vmas and see if one of them matches the + * @filter; if so, adjust filter's address range. + * Called with mm::mmap_sem down for reading. + */ +static unsigned long perf_addr_filter_apply(struct perf_addr_filter *filter, + struct mm_struct *mm) +{ + struct vm_area_struct *vma; + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + struct file *file = vma->vm_file; + unsigned long off = vma->vm_pgoff << PAGE_SHIFT; + unsigned long vma_size = vma->vm_end - vma->vm_start; + + if (!file) + continue; + + if (!perf_addr_filter_match(filter, file, off, vma_size)) + continue; + + return vma->vm_start; + } + + return 0; +} + +/* + * Update event's address range filters based on the + * task's existing mappings, if any. + */ +static void perf_event_addr_filters_apply(struct perf_event *event) +{ + struct perf_addr_filters_head *ifh = perf_event_addr_filters(event); + struct task_struct *task = READ_ONCE(event->ctx->task); + struct perf_addr_filter *filter; + struct mm_struct *mm = NULL; + unsigned int count = 0; + unsigned long flags; + + /* + * We may observe TASK_TOMBSTONE, which means that the event tear-down + * will stop on the parent's child_mutex that our caller is also holding + */ + if (task == TASK_TOMBSTONE) + return; + + mm = get_task_mm(event->ctx->task); + if (!mm) + goto restart; + + down_read(&mm->mmap_sem); + + raw_spin_lock_irqsave(&ifh->lock, flags); + list_for_each_entry(filter, &ifh->list, entry) { + event->addr_filters_offs[count] = 0; + + if (perf_addr_filter_needs_mmap(filter)) + event->addr_filters_offs[count] = + perf_addr_filter_apply(filter, mm); + + count++; + } + + event->addr_filters_gen++; + raw_spin_unlock_irqrestore(&ifh->lock, flags); + + up_read(&mm->mmap_sem); + + mmput(mm); + +restart: + perf_event_restart(event); +} + +/* + * Address range filtering: limiting the data to certain + * instruction address ranges. Filters are ioctl()ed to us from + * userspace as ascii strings. + * + * Filter string format: + * + * ACTION RANGE_SPEC + * where ACTION is one of the + * * "filter": limit the trace to this region + * * "start": start tracing from this address + * * "stop": stop tracing at this address/region; + * RANGE_SPEC is + * * for kernel addresses: <start address>[/<size>] + * * for object files: <start address>[/<size>]@</path/to/object/file> + * + * if <size> is not specified, the range is treated as a single address. + */ +enum { + IF_ACT_FILTER, + IF_ACT_START, + IF_ACT_STOP, + IF_SRC_FILE, + IF_SRC_KERNEL, + IF_SRC_FILEADDR, + IF_SRC_KERNELADDR, +}; + +enum { + IF_STATE_ACTION = 0, + IF_STATE_SOURCE, + IF_STATE_END, +}; + +static const match_table_t if_tokens = { + { IF_ACT_FILTER, "filter" }, + { IF_ACT_START, "start" }, + { IF_ACT_STOP, "stop" }, + { IF_SRC_FILE, "%u/%u@%s" }, + { IF_SRC_KERNEL, "%u/%u" }, + { IF_SRC_FILEADDR, "%u@%s" }, + { IF_SRC_KERNELADDR, "%u" }, +}; + +/* + * Address filter string parser + */ +static int +perf_event_parse_addr_filter(struct perf_event *event, char *fstr, + struct list_head *filters) +{ + struct perf_addr_filter *filter = NULL; + char *start, *orig, *filename = NULL; + struct path path; + substring_t args[MAX_OPT_ARGS]; + int state = IF_STATE_ACTION, token; + unsigned int kernel = 0; + int ret = -EINVAL; + + orig = fstr = kstrdup(fstr, GFP_KERNEL); + if (!fstr) + return -ENOMEM; + + while ((start = strsep(&fstr, " ,\n")) != NULL) { + ret = -EINVAL; + + if (!*start) + continue; + + /* filter definition begins */ + if (state == IF_STATE_ACTION) { + filter = perf_addr_filter_new(event, filters); + if (!filter) + goto fail; + } + + token = match_token(start, if_tokens, args); + switch (token) { + case IF_ACT_FILTER: + case IF_ACT_START: + filter->filter = 1; + + case IF_ACT_STOP: + if (state != IF_STATE_ACTION) + goto fail; + + state = IF_STATE_SOURCE; + break; + + case IF_SRC_KERNELADDR: + case IF_SRC_KERNEL: + kernel = 1; + + case IF_SRC_FILEADDR: + case IF_SRC_FILE: + if (state != IF_STATE_SOURCE) + goto fail; + + if (token == IF_SRC_FILE || token == IF_SRC_KERNEL) + filter->range = 1; + + *args[0].to = 0; + ret = kstrtoul(args[0].from, 0, &filter->offset); + if (ret) + goto fail; + + if (filter->range) { + *args[1].to = 0; + ret = kstrtoul(args[1].from, 0, &filter->size); + if (ret) + goto fail; + } + + if (token == IF_SRC_FILE) { + filename = match_strdup(&args[2]); + if (!filename) { + ret = -ENOMEM; + goto fail; + } + } + + state = IF_STATE_END; + break; + + default: + goto fail; + } + + /* + * Filter definition is fully parsed, validate and install it. + * Make sure that it doesn't contradict itself or the event's + * attribute. + */ + if (state == IF_STATE_END) { + if (kernel && event->attr.exclude_kernel) + goto fail; + + if (!kernel) { + if (!filename) + goto fail; + + /* look up the path and grab its inode */ + ret = kern_path(filename, LOOKUP_FOLLOW, &path); + if (ret) + goto fail_free_name; + + filter->inode = igrab(d_inode(path.dentry)); + path_put(&path); + kfree(filename); + filename = NULL; + + ret = -EINVAL; + if (!filter->inode || + !S_ISREG(filter->inode->i_mode)) + /* free_filters_list() will iput() */ + goto fail; + } + + /* ready to consume more filters */ + state = IF_STATE_ACTION; + filter = NULL; + } + } + + if (state != IF_STATE_ACTION) + goto fail; + + kfree(orig); + + return 0; + +fail_free_name: + kfree(filename); +fail: + free_filters_list(filters); + kfree(orig); + + return ret; +} + +static int +perf_event_set_addr_filter(struct perf_event *event, char *filter_str) +{ + LIST_HEAD(filters); + int ret; + + /* + * Since this is called in perf_ioctl() path, we're already holding + * ctx::mutex. + */ + lockdep_assert_held(&event->ctx->mutex); + + if (WARN_ON_ONCE(event->parent)) + return -EINVAL; + + /* + * For now, we only support filtering in per-task events; doing so + * for CPU-wide events requires additional context switching trickery, + * since same object code will be mapped at different virtual + * addresses in different processes. + */ + if (!event->ctx->task) + return -EOPNOTSUPP; + + ret = perf_event_parse_addr_filter(event, filter_str, &filters); + if (ret) + return ret; + + ret = event->pmu->addr_filters_validate(&filters); + if (ret) { + free_filters_list(&filters); + return ret; + } + + /* remove existing filters, if any */ + perf_addr_filters_splice(event, &filters); + + /* install new filters */ + perf_event_for_each_child(event, perf_event_addr_filters_apply); + + return ret; +} + +static int perf_event_set_filter(struct perf_event *event, void __user *arg) +{ + char *filter_str; + int ret = -EINVAL; + + if ((event->attr.type != PERF_TYPE_TRACEPOINT || + !IS_ENABLED(CONFIG_EVENT_TRACING)) && + !has_addr_filter(event)) + return -EINVAL; + + filter_str = strndup_user(arg, PAGE_SIZE); + if (IS_ERR(filter_str)) + return PTR_ERR(filter_str); + + if (IS_ENABLED(CONFIG_EVENT_TRACING) && + event->attr.type == PERF_TYPE_TRACEPOINT) + ret = ftrace_profile_set_filter(event, event->attr.config, + filter_str); + else if (has_addr_filter(event)) + ret = perf_event_set_addr_filter(event, filter_str); + + kfree(filter_str); + return ret; +} + +/* * hrtimer based swevent callback */ @@ -7542,6 +8273,20 @@ static void free_pmu_context(struct pmu *pmu) out: mutex_unlock(&pmus_lock); } + +/* + * Let userspace know that this PMU supports address range filtering: + */ +static ssize_t nr_addr_filters_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct pmu *pmu = dev_get_drvdata(dev); + + return snprintf(page, PAGE_SIZE - 1, "%d\n", pmu->nr_addr_filters); +} +DEVICE_ATTR_RO(nr_addr_filters); + static struct idr pmu_idr; static ssize_t @@ -7643,9 +8388,19 @@ static int pmu_dev_alloc(struct pmu *pmu) if (ret) goto free_dev; + /* For PMUs with address filters, throw in an extra attribute: */ + if (pmu->nr_addr_filters) + ret = device_create_file(pmu->dev, &dev_attr_nr_addr_filters); + + if (ret) + goto del_dev; + out: return ret; +del_dev: + device_del(pmu->dev); + free_dev: put_device(pmu->dev); goto out; @@ -7685,6 +8440,21 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type) } skip_type: + if (pmu->task_ctx_nr == perf_hw_context) { + static int hw_context_taken = 0; + + /* + * Other than systems with heterogeneous CPUs, it never makes + * sense for two PMUs to share perf_hw_context. PMUs which are + * uncore must use perf_invalid_context. + */ + if (WARN_ON_ONCE(hw_context_taken && + !(pmu->capabilities & PERF_PMU_CAP_HETEROGENEOUS_CPUS))) + pmu->task_ctx_nr = perf_invalid_context; + + hw_context_taken = 1; + } + pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr); if (pmu->pmu_cpu_context) goto got_cpu_context; @@ -7772,6 +8542,8 @@ void perf_pmu_unregister(struct pmu *pmu) free_percpu(pmu->pmu_disable_count); if (pmu->type >= PERF_TYPE_MAX) idr_remove(&pmu_idr, pmu->type); + if (pmu->nr_addr_filters) + device_remove_file(pmu->dev, &dev_attr_nr_addr_filters); device_del(pmu->dev); put_device(pmu->dev); free_pmu_context(pmu); @@ -7965,6 +8737,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, INIT_LIST_HEAD(&event->sibling_list); INIT_LIST_HEAD(&event->rb_entry); INIT_LIST_HEAD(&event->active_entry); + INIT_LIST_HEAD(&event->addr_filters.list); INIT_HLIST_NODE(&event->hlist_entry); @@ -7972,6 +8745,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, init_irq_work(&event->pending, perf_pending_event); mutex_init(&event->mmap_mutex); + raw_spin_lock_init(&event->addr_filters.lock); atomic_long_set(&event->refcount, 1); event->cpu = cpu; @@ -8006,8 +8780,16 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, context = parent_event->overflow_handler_context; } - event->overflow_handler = overflow_handler; - event->overflow_handler_context = context; + if (overflow_handler) { + event->overflow_handler = overflow_handler; + event->overflow_handler_context = context; + } else if (is_write_backward(event)){ + event->overflow_handler = perf_event_output_backward; + event->overflow_handler_context = NULL; + } else { + event->overflow_handler = perf_event_output_forward; + event->overflow_handler_context = NULL; + } perf_event__state_init(event); @@ -8048,11 +8830,22 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, if (err) goto err_pmu; + if (has_addr_filter(event)) { + event->addr_filters_offs = kcalloc(pmu->nr_addr_filters, + sizeof(unsigned long), + GFP_KERNEL); + if (!event->addr_filters_offs) + goto err_per_task; + + /* force hw sync on the address filters */ + event->addr_filters_gen = 1; + } + if (!event->parent) { if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { err = get_callchain_buffers(); if (err) - goto err_per_task; + goto err_addr_filters; } } @@ -8061,6 +8854,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, return event; +err_addr_filters: + kfree(event->addr_filters_offs); + err_per_task: exclusive_event_destroy(event); @@ -8240,6 +9036,13 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) goto out; /* + * Either writing ring buffer from beginning or from end. + * Mixing is not allowed. + */ + if (is_write_backward(output_event) != is_write_backward(event)) + goto out; + + /* * If both events generate aux data, they must be on the same PMU */ if (has_aux(event) && has_aux(output_event) && diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 4199b6d..05f9f6d 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -11,13 +11,13 @@ struct ring_buffer { atomic_t refcount; struct rcu_head rcu_head; - struct irq_work irq_work; #ifdef CONFIG_PERF_USE_VMALLOC struct work_struct work; int page_order; /* allocation order */ #endif int nr_pages; /* nr of data pages */ int overwrite; /* can overwrite itself */ + int paused; /* can write into ring buffer */ atomic_t poll; /* POLL_ for wakeups */ @@ -65,6 +65,14 @@ static inline void rb_free_rcu(struct rcu_head *rcu_head) rb_free(rb); } +static inline void rb_toggle_paused(struct ring_buffer *rb, bool pause) +{ + if (!pause && rb->nr_pages) + rb->paused = 0; + else + rb->paused = 1; +} + extern struct ring_buffer * rb_alloc(int nr_pages, long watermark, int cpu, int flags); extern void perf_event_wakeup(struct perf_event *event); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index c61f0cb..ae9b90d 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -102,8 +102,21 @@ out: preempt_enable(); } -int perf_output_begin(struct perf_output_handle *handle, - struct perf_event *event, unsigned int size) +static bool __always_inline +ring_buffer_has_space(unsigned long head, unsigned long tail, + unsigned long data_size, unsigned int size, + bool backward) +{ + if (!backward) + return CIRC_SPACE(head, tail, data_size) >= size; + else + return CIRC_SPACE(tail, head, data_size) >= size; +} + +static int __always_inline +__perf_output_begin(struct perf_output_handle *handle, + struct perf_event *event, unsigned int size, + bool backward) { struct ring_buffer *rb; unsigned long tail, offset, head; @@ -125,8 +138,11 @@ int perf_output_begin(struct perf_output_handle *handle, if (unlikely(!rb)) goto out; - if (unlikely(!rb->nr_pages)) + if (unlikely(rb->paused)) { + if (rb->nr_pages) + local_inc(&rb->lost); goto out; + } handle->rb = rb; handle->event = event; @@ -143,9 +159,12 @@ int perf_output_begin(struct perf_output_handle *handle, do { tail = READ_ONCE(rb->user_page->data_tail); offset = head = local_read(&rb->head); - if (!rb->overwrite && - unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size)) - goto fail; + if (!rb->overwrite) { + if (unlikely(!ring_buffer_has_space(head, tail, + perf_data_size(rb), + size, backward))) + goto fail; + } /* * The above forms a control dependency barrier separating the @@ -159,9 +178,17 @@ int perf_output_begin(struct perf_output_handle *handle, * See perf_output_put_handle(). */ - head += size; + if (!backward) + head += size; + else + head -= size; } while (local_cmpxchg(&rb->head, offset, head) != offset); + if (backward) { + offset = head; + head = (u64)(-head); + } + /* * We rely on the implied barrier() by local_cmpxchg() to ensure * none of the data stores below can be lifted up by the compiler. @@ -203,6 +230,26 @@ out: return -ENOSPC; } +int perf_output_begin_forward(struct perf_output_handle *handle, + struct perf_event *event, unsigned int size) +{ + return __perf_output_begin(handle, event, size, false); +} + +int perf_output_begin_backward(struct perf_output_handle *handle, + struct perf_event *event, unsigned int size) +{ + return __perf_output_begin(handle, event, size, true); +} + +int perf_output_begin(struct perf_output_handle *handle, + struct perf_event *event, unsigned int size) +{ + + return __perf_output_begin(handle, event, size, + unlikely(is_write_backward(event))); +} + unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len) { @@ -221,8 +268,6 @@ void perf_output_end(struct perf_output_handle *handle) rcu_read_unlock(); } -static void rb_irq_work(struct irq_work *work); - static void ring_buffer_init(struct ring_buffer *rb, long watermark, int flags) { @@ -243,16 +288,13 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags) INIT_LIST_HEAD(&rb->event_list); spin_lock_init(&rb->event_lock); - init_irq_work(&rb->irq_work, rb_irq_work); -} -static void ring_buffer_put_async(struct ring_buffer *rb) -{ - if (!atomic_dec_and_test(&rb->refcount)) - return; - - rb->rcu_head.next = (void *)rb; - irq_work_queue(&rb->irq_work); + /* + * perf_output_begin() only checks rb->paused, therefore + * rb->paused must be true if we have no pages for output. + */ + if (!rb->nr_pages) + rb->paused = 1; } /* @@ -264,6 +306,10 @@ static void ring_buffer_put_async(struct ring_buffer *rb) * The ordering is similar to that of perf_output_{begin,end}, with * the exception of (B), which should be taken care of by the pmu * driver, since ordering rules will differ depending on hardware. + * + * Call this from pmu::start(); see the comment in perf_aux_output_end() + * about its use in pmu callbacks. Both can also be called from the PMI + * handler if needed. */ void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) @@ -288,6 +334,13 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, goto err; /* + * If rb::aux_mmap_count is zero (and rb_has_aux() above went through), + * the aux buffer is in perf_mmap_close(), about to get freed. + */ + if (!atomic_read(&rb->aux_mmap_count)) + goto err_put; + + /* * Nesting is not supported for AUX area, make sure nested * writers are caught early */ @@ -328,10 +381,11 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, return handle->rb->aux_priv; err_put: + /* can't be last */ rb_free_aux(rb); err: - ring_buffer_put_async(rb); + ring_buffer_put(rb); handle->event = NULL; return NULL; @@ -342,11 +396,16 @@ err: * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the * pmu driver's responsibility to observe ordering rules of the hardware, * so that all the data is externally visible before this is called. + * + * Note: this has to be called from pmu::stop() callback, as the assumption + * of the AUX buffer management code is that after pmu::stop(), the AUX + * transaction must be stopped and therefore drop the AUX reference count. */ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size, bool truncated) { struct ring_buffer *rb = handle->rb; + bool wakeup = truncated; unsigned long aux_head; u64 flags = 0; @@ -375,14 +434,22 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size, aux_head = rb->user_page->aux_head = local_read(&rb->aux_head); if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) { - perf_output_wakeup(handle); + wakeup = true; local_add(rb->aux_watermark, &rb->aux_wakeup); } + + if (wakeup) { + if (truncated) + handle->event->pending_disable = 1; + perf_output_wakeup(handle); + } + handle->event = NULL; local_set(&rb->aux_nest, 0); + /* can't be last */ rb_free_aux(rb); - ring_buffer_put_async(rb); + ring_buffer_put(rb); } /* @@ -463,6 +530,14 @@ static void __rb_free_aux(struct ring_buffer *rb) { int pg; + /* + * Should never happen, the last reference should be dropped from + * perf_mmap_close() path, which first stops aux transactions (which + * in turn are the atomic holders of aux_refcount) and then does the + * last rb_free_aux(). + */ + WARN_ON_ONCE(in_atomic()); + if (rb->aux_priv) { rb->free_aux(rb->aux_priv); rb->free_aux = NULL; @@ -574,18 +649,7 @@ out: void rb_free_aux(struct ring_buffer *rb) { if (atomic_dec_and_test(&rb->aux_refcount)) - irq_work_queue(&rb->irq_work); -} - -static void rb_irq_work(struct irq_work *work) -{ - struct ring_buffer *rb = container_of(work, struct ring_buffer, irq_work); - - if (!atomic_read(&rb->aux_refcount)) __rb_free_aux(rb); - - if (rb->rcu_head.next == (void *)rb) - call_rcu(&rb->rcu_head, rb_free_rcu); } #ifndef CONFIG_PERF_USE_VMALLOC diff --git a/kernel/fork.c b/kernel/fork.c index d277e83..3e84515 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1494,7 +1494,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) - p->sas_ss_sp = p->sas_ss_size = 0; + sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 78c1c0e..81f1a71 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -45,6 +45,7 @@ #include <linux/bitops.h> #include <linux/gfp.h> #include <linux/kmemcheck.h> +#include <linux/random.h> #include <asm/sections.h> @@ -708,7 +709,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) * yet. Otherwise we look it up. We cache the result in the lock object * itself, so actual lookup of the hash should be once per lock object. */ -static inline struct lock_class * +static struct lock_class * register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) { struct lockdep_subclass_key *key; @@ -3585,7 +3586,35 @@ static int __lock_is_held(struct lockdep_map *lock) return 0; } -static void __lock_pin_lock(struct lockdep_map *lock) +static struct pin_cookie __lock_pin_lock(struct lockdep_map *lock) +{ + struct pin_cookie cookie = NIL_COOKIE; + struct task_struct *curr = current; + int i; + + if (unlikely(!debug_locks)) + return cookie; + + for (i = 0; i < curr->lockdep_depth; i++) { + struct held_lock *hlock = curr->held_locks + i; + + if (match_held_lock(hlock, lock)) { + /* + * Grab 16bits of randomness; this is sufficient to not + * be guessable and still allows some pin nesting in + * our u32 pin_count. + */ + cookie.val = 1 + (prandom_u32() >> 16); + hlock->pin_count += cookie.val; + return cookie; + } + } + + WARN(1, "pinning an unheld lock\n"); + return cookie; +} + +static void __lock_repin_lock(struct lockdep_map *lock, struct pin_cookie cookie) { struct task_struct *curr = current; int i; @@ -3597,7 +3626,7 @@ static void __lock_pin_lock(struct lockdep_map *lock) struct held_lock *hlock = curr->held_locks + i; if (match_held_lock(hlock, lock)) { - hlock->pin_count++; + hlock->pin_count += cookie.val; return; } } @@ -3605,7 +3634,7 @@ static void __lock_pin_lock(struct lockdep_map *lock) WARN(1, "pinning an unheld lock\n"); } -static void __lock_unpin_lock(struct lockdep_map *lock) +static void __lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie) { struct task_struct *curr = current; int i; @@ -3620,7 +3649,11 @@ static void __lock_unpin_lock(struct lockdep_map *lock) if (WARN(!hlock->pin_count, "unpinning an unpinned lock\n")) return; - hlock->pin_count--; + hlock->pin_count -= cookie.val; + + if (WARN((int)hlock->pin_count < 0, "pin count corrupted\n")) + hlock->pin_count = 0; + return; } } @@ -3751,24 +3784,44 @@ int lock_is_held(struct lockdep_map *lock) } EXPORT_SYMBOL_GPL(lock_is_held); -void lock_pin_lock(struct lockdep_map *lock) +struct pin_cookie lock_pin_lock(struct lockdep_map *lock) { + struct pin_cookie cookie = NIL_COOKIE; unsigned long flags; if (unlikely(current->lockdep_recursion)) - return; + return cookie; raw_local_irq_save(flags); check_flags(flags); current->lockdep_recursion = 1; - __lock_pin_lock(lock); + cookie = __lock_pin_lock(lock); current->lockdep_recursion = 0; raw_local_irq_restore(flags); + + return cookie; } EXPORT_SYMBOL_GPL(lock_pin_lock); -void lock_unpin_lock(struct lockdep_map *lock) +void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie cookie) +{ + unsigned long flags; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + + current->lockdep_recursion = 1; + __lock_repin_lock(lock, cookie); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(lock_repin_lock); + +void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie) { unsigned long flags; @@ -3779,7 +3832,7 @@ void lock_unpin_lock(struct lockdep_map *lock) check_flags(flags); current->lockdep_recursion = 1; - __lock_unpin_lock(lock); + __lock_unpin_lock(lock, cookie); current->lockdep_recursion = 0; raw_local_irq_restore(flags); } diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 8ef1919..f8c5af5 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -75,12 +75,7 @@ struct lock_stress_stats { long n_lock_acquired; }; -#if defined(MODULE) -#define LOCKTORTURE_RUNNABLE_INIT 1 -#else -#define LOCKTORTURE_RUNNABLE_INIT 0 -#endif -int torture_runnable = LOCKTORTURE_RUNNABLE_INIT; +int torture_runnable = IS_ENABLED(MODULE); module_param(torture_runnable, int, 0444); MODULE_PARM_DESC(torture_runnable, "Start locktorture at module init"); @@ -394,12 +389,12 @@ static void torture_rtmutex_boost(struct torture_random_state *trsp) if (!rt_task(current)) { /* - * (1) Boost priority once every ~50k operations. When the + * Boost priority once every ~50k operations. When the * task tries to take the lock, the rtmutex it will account * for the new priority, and do any corresponding pi-dance. */ - if (!(torture_random(trsp) % - (cxt.nrealwriters_stress * factor))) { + if (trsp && !(torture_random(trsp) % + (cxt.nrealwriters_stress * factor))) { policy = SCHED_FIFO; param.sched_priority = MAX_RT_PRIO - 1; } else /* common case, do nothing */ @@ -748,6 +743,15 @@ static void lock_torture_cleanup(void) if (torture_cleanup_begin()) return; + /* + * Indicates early cleanup, meaning that the test has not run, + * such as when passing bogus args when loading the module. As + * such, only perform the underlying torture-specific cleanups, + * and avoid anything related to locktorture. + */ + if (!cxt.lwsa) + goto end; + if (writer_tasks) { for (i = 0; i < cxt.nrealwriters_stress; i++) torture_stop_kthread(lock_torture_writer, @@ -776,6 +780,7 @@ static void lock_torture_cleanup(void) else lock_torture_print_module_parms(cxt.cur_ops, "End of test: SUCCESS"); +end: torture_cleanup_end(); } @@ -870,6 +875,7 @@ static int __init lock_torture_init(void) VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory"); firsterr = -ENOMEM; kfree(cxt.lwsa); + cxt.lwsa = NULL; goto unwind; } @@ -878,6 +884,7 @@ static int __init lock_torture_init(void) cxt.lrsa[i].n_lock_acquired = 0; } } + lock_torture_print_module_parms(cxt.cur_ops, "Start of test"); /* Prepare torture context. */ diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index d734b75..22e0253 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -191,8 +191,6 @@ static ssize_t qstat_write(struct file *file, const char __user *user_buf, for (i = 0 ; i < qstat_num; i++) WRITE_ONCE(ptr[i], 0); - for (i = 0 ; i < qstat_num; i++) - WRITE_ONCE(ptr[i], 0); } return count; } @@ -214,10 +212,8 @@ static int __init init_qspinlock_stat(void) struct dentry *d_qstat = debugfs_create_dir("qlockstat", NULL); int i; - if (!d_qstat) { - pr_warn("Could not create 'qlockstat' debugfs directory\n"); - return 0; - } + if (!d_qstat) + goto out; /* * Create the debugfs files @@ -227,12 +223,20 @@ static int __init init_qspinlock_stat(void) * performance. */ for (i = 0; i < qstat_num; i++) - debugfs_create_file(qstat_names[i], 0400, d_qstat, - (void *)(long)i, &fops_qstat); + if (!debugfs_create_file(qstat_names[i], 0400, d_qstat, + (void *)(long)i, &fops_qstat)) + goto fail_undo; + + if (!debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat, + (void *)(long)qstat_reset_cnts, &fops_qstat)) + goto fail_undo; - debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat, - (void *)(long)qstat_reset_cnts, &fops_qstat); return 0; +fail_undo: + debugfs_remove_recursive(d_qstat); +out: + pr_warn("Could not create 'qlockstat' debugfs entries\n"); + return -ENOMEM; } fs_initcall(init_qspinlock_stat); diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 3a50485..1591f6b 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -191,11 +191,12 @@ int __down_read_trylock(struct rw_semaphore *sem) /* * get a write lock on the semaphore */ -void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) +int __sched __down_write_common(struct rw_semaphore *sem, int state) { struct rwsem_waiter waiter; struct task_struct *tsk; unsigned long flags; + int ret = 0; raw_spin_lock_irqsave(&sem->wait_lock, flags); @@ -215,21 +216,33 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) */ if (sem->count == 0) break; - set_task_state(tsk, TASK_UNINTERRUPTIBLE); + if (signal_pending_state(state, current)) { + ret = -EINTR; + goto out; + } + set_task_state(tsk, state); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); schedule(); raw_spin_lock_irqsave(&sem->wait_lock, flags); } /* got the lock */ sem->count = -1; +out: list_del(&waiter.list); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return ret; } void __sched __down_write(struct rw_semaphore *sem) { - __down_write_nested(sem, 0); + __down_write_common(sem, TASK_UNINTERRUPTIBLE); +} + +int __sched __down_write_killable(struct rw_semaphore *sem) +{ + return __down_write_common(sem, TASK_KILLABLE); } /* diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index a4d4de0..09e30c6 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -433,12 +433,13 @@ static inline bool rwsem_has_spinner(struct rw_semaphore *sem) /* * Wait until we successfully acquire the write lock */ -__visible -struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) +static inline struct rw_semaphore * +__rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) { long count; bool waiting = true; /* any queued threads before us */ struct rwsem_waiter waiter; + struct rw_semaphore *ret = sem; /* undo write bias from down_write operation, stop active locking */ count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem); @@ -478,7 +479,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); /* wait until we successfully acquire the lock */ - set_current_state(TASK_UNINTERRUPTIBLE); + set_current_state(state); while (true) { if (rwsem_try_write_lock(count, sem)) break; @@ -486,21 +487,48 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) /* Block until there are no active lockers. */ do { + if (signal_pending_state(state, current)) + goto out_nolock; + schedule(); - set_current_state(TASK_UNINTERRUPTIBLE); + set_current_state(state); } while ((count = sem->count) & RWSEM_ACTIVE_MASK); raw_spin_lock_irq(&sem->wait_lock); } __set_current_state(TASK_RUNNING); + list_del(&waiter.list); + raw_spin_unlock_irq(&sem->wait_lock); + return ret; + +out_nolock: + __set_current_state(TASK_RUNNING); + raw_spin_lock_irq(&sem->wait_lock); list_del(&waiter.list); + if (list_empty(&sem->wait_list)) + rwsem_atomic_update(-RWSEM_WAITING_BIAS, sem); + else + __rwsem_do_wake(sem, RWSEM_WAKE_ANY); raw_spin_unlock_irq(&sem->wait_lock); - return sem; + return ERR_PTR(-EINTR); +} + +__visible struct rw_semaphore * __sched +rwsem_down_write_failed(struct rw_semaphore *sem) +{ + return __rwsem_down_write_failed_common(sem, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(rwsem_down_write_failed); +__visible struct rw_semaphore * __sched +rwsem_down_write_failed_killable(struct rw_semaphore *sem) +{ + return __rwsem_down_write_failed_common(sem, TASK_KILLABLE); +} +EXPORT_SYMBOL(rwsem_down_write_failed_killable); + /* * handle waking up a waiter on the semaphore * - up_read/up_write has decremented the active part of count if we come here diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 205be0c..c817216 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -55,6 +55,25 @@ void __sched down_write(struct rw_semaphore *sem) EXPORT_SYMBOL(down_write); /* + * lock for writing + */ +int __sched down_write_killable(struct rw_semaphore *sem) +{ + might_sleep(); + rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_); + + if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) { + rwsem_release(&sem->dep_map, 1, _RET_IP_); + return -EINTR; + } + + rwsem_set_owner(sem); + return 0; +} + +EXPORT_SYMBOL(down_write_killable); + +/* * trylock for writing -- returns 1 if successful, 0 if contention */ int down_write_trylock(struct rw_semaphore *sem) diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index 032b2c0..18dfc48 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -5,6 +5,7 @@ KCOV_INSTRUMENT := n obj-y += update.o sync.o obj-$(CONFIG_SRCU) += srcu.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o +obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o obj-$(CONFIG_TREE_RCU) += tree.o obj-$(CONFIG_PREEMPT_RCU) += tree.o obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c new file mode 100644 index 0000000..3cee0d8 --- /dev/null +++ b/kernel/rcu/rcuperf.c @@ -0,0 +1,655 @@ +/* + * Read-Copy Update module-based performance-test facility + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (C) IBM Corporation, 2015 + * + * Authors: Paul E. McKenney <paulmck@us.ibm.com> + */ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kthread.h> +#include <linux/err.h> +#include <linux/spinlock.h> +#include <linux/smp.h> +#include <linux/rcupdate.h> +#include <linux/interrupt.h> +#include <linux/sched.h> +#include <linux/atomic.h> +#include <linux/bitops.h> +#include <linux/completion.h> +#include <linux/moduleparam.h> +#include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/reboot.h> +#include <linux/freezer.h> +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/stat.h> +#include <linux/srcu.h> +#include <linux/slab.h> +#include <asm/byteorder.h> +#include <linux/torture.h> +#include <linux/vmalloc.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>"); + +#define PERF_FLAG "-perf:" +#define PERFOUT_STRING(s) \ + pr_alert("%s" PERF_FLAG s "\n", perf_type) +#define VERBOSE_PERFOUT_STRING(s) \ + do { if (verbose) pr_alert("%s" PERF_FLAG " %s\n", perf_type, s); } while (0) +#define VERBOSE_PERFOUT_ERRSTRING(s) \ + do { if (verbose) pr_alert("%s" PERF_FLAG "!!! %s\n", perf_type, s); } while (0) + +torture_param(bool, gp_exp, true, "Use expedited GP wait primitives"); +torture_param(int, holdoff, 10, "Holdoff time before test start (s)"); +torture_param(int, nreaders, -1, "Number of RCU reader threads"); +torture_param(int, nwriters, -1, "Number of RCU updater threads"); +torture_param(bool, shutdown, false, "Shutdown at end of performance tests."); +torture_param(bool, verbose, true, "Enable verbose debugging printk()s"); + +static char *perf_type = "rcu"; +module_param(perf_type, charp, 0444); +MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, rcu_bh, ...)"); + +static int nrealreaders; +static int nrealwriters; +static struct task_struct **writer_tasks; +static struct task_struct **reader_tasks; +static struct task_struct *shutdown_task; + +static u64 **writer_durations; +static int *writer_n_durations; +static atomic_t n_rcu_perf_reader_started; +static atomic_t n_rcu_perf_writer_started; +static atomic_t n_rcu_perf_writer_finished; +static wait_queue_head_t shutdown_wq; +static u64 t_rcu_perf_writer_started; +static u64 t_rcu_perf_writer_finished; +static unsigned long b_rcu_perf_writer_started; +static unsigned long b_rcu_perf_writer_finished; + +static int rcu_perf_writer_state; +#define RTWS_INIT 0 +#define RTWS_EXP_SYNC 1 +#define RTWS_SYNC 2 +#define RTWS_IDLE 2 +#define RTWS_STOPPING 3 + +#define MAX_MEAS 10000 +#define MIN_MEAS 100 + +#if defined(MODULE) || defined(CONFIG_RCU_PERF_TEST_RUNNABLE) +#define RCUPERF_RUNNABLE_INIT 1 +#else +#define RCUPERF_RUNNABLE_INIT 0 +#endif +static int perf_runnable = RCUPERF_RUNNABLE_INIT; +module_param(perf_runnable, int, 0444); +MODULE_PARM_DESC(perf_runnable, "Start rcuperf at boot"); + +/* + * Operations vector for selecting different types of tests. + */ + +struct rcu_perf_ops { + int ptype; + void (*init)(void); + void (*cleanup)(void); + int (*readlock)(void); + void (*readunlock)(int idx); + unsigned long (*started)(void); + unsigned long (*completed)(void); + unsigned long (*exp_completed)(void); + void (*sync)(void); + void (*exp_sync)(void); + const char *name; +}; + +static struct rcu_perf_ops *cur_ops; + +/* + * Definitions for rcu perf testing. + */ + +static int rcu_perf_read_lock(void) __acquires(RCU) +{ + rcu_read_lock(); + return 0; +} + +static void rcu_perf_read_unlock(int idx) __releases(RCU) +{ + rcu_read_unlock(); +} + +static unsigned long __maybe_unused rcu_no_completed(void) +{ + return 0; +} + +static void rcu_sync_perf_init(void) +{ +} + +static struct rcu_perf_ops rcu_ops = { + .ptype = RCU_FLAVOR, + .init = rcu_sync_perf_init, + .readlock = rcu_perf_read_lock, + .readunlock = rcu_perf_read_unlock, + .started = rcu_batches_started, + .completed = rcu_batches_completed, + .exp_completed = rcu_exp_batches_completed, + .sync = synchronize_rcu, + .exp_sync = synchronize_rcu_expedited, + .name = "rcu" +}; + +/* + * Definitions for rcu_bh perf testing. + */ + +static int rcu_bh_perf_read_lock(void) __acquires(RCU_BH) +{ + rcu_read_lock_bh(); + return 0; +} + +static void rcu_bh_perf_read_unlock(int idx) __releases(RCU_BH) +{ + rcu_read_unlock_bh(); +} + +static struct rcu_perf_ops rcu_bh_ops = { + .ptype = RCU_BH_FLAVOR, + .init = rcu_sync_perf_init, + .readlock = rcu_bh_perf_read_lock, + .readunlock = rcu_bh_perf_read_unlock, + .started = rcu_batches_started_bh, + .completed = rcu_batches_completed_bh, + .exp_completed = rcu_exp_batches_completed_sched, + .sync = synchronize_rcu_bh, + .exp_sync = synchronize_rcu_bh_expedited, + .name = "rcu_bh" +}; + +/* + * Definitions for srcu perf testing. + */ + +DEFINE_STATIC_SRCU(srcu_ctl_perf); +static struct srcu_struct *srcu_ctlp = &srcu_ctl_perf; + +static int srcu_perf_read_lock(void) __acquires(srcu_ctlp) +{ + return srcu_read_lock(srcu_ctlp); +} + +static void srcu_perf_read_unlock(int idx) __releases(srcu_ctlp) +{ + srcu_read_unlock(srcu_ctlp, idx); +} + +static unsigned long srcu_perf_completed(void) +{ + return srcu_batches_completed(srcu_ctlp); +} + +static void srcu_perf_synchronize(void) +{ + synchronize_srcu(srcu_ctlp); +} + +static void srcu_perf_synchronize_expedited(void) +{ + synchronize_srcu_expedited(srcu_ctlp); +} + +static struct rcu_perf_ops srcu_ops = { + .ptype = SRCU_FLAVOR, + .init = rcu_sync_perf_init, + .readlock = srcu_perf_read_lock, + .readunlock = srcu_perf_read_unlock, + .started = NULL, + .completed = srcu_perf_completed, + .exp_completed = srcu_perf_completed, + .sync = srcu_perf_synchronize, + .exp_sync = srcu_perf_synchronize_expedited, + .name = "srcu" +}; + +/* + * Definitions for sched perf testing. + */ + +static int sched_perf_read_lock(void) +{ + preempt_disable(); + return 0; +} + +static void sched_perf_read_unlock(int idx) +{ + preempt_enable(); +} + +static struct rcu_perf_ops sched_ops = { + .ptype = RCU_SCHED_FLAVOR, + .init = rcu_sync_perf_init, + .readlock = sched_perf_read_lock, + .readunlock = sched_perf_read_unlock, + .started = rcu_batches_started_sched, + .completed = rcu_batches_completed_sched, + .exp_completed = rcu_exp_batches_completed_sched, + .sync = synchronize_sched, + .exp_sync = synchronize_sched_expedited, + .name = "sched" +}; + +#ifdef CONFIG_TASKS_RCU + +/* + * Definitions for RCU-tasks perf testing. + */ + +static int tasks_perf_read_lock(void) +{ + return 0; +} + +static void tasks_perf_read_unlock(int idx) +{ +} + +static struct rcu_perf_ops tasks_ops = { + .ptype = RCU_TASKS_FLAVOR, + .init = rcu_sync_perf_init, + .readlock = tasks_perf_read_lock, + .readunlock = tasks_perf_read_unlock, + .started = rcu_no_completed, + .completed = rcu_no_completed, + .sync = synchronize_rcu_tasks, + .exp_sync = synchronize_rcu_tasks, + .name = "tasks" +}; + +#define RCUPERF_TASKS_OPS &tasks_ops, + +static bool __maybe_unused torturing_tasks(void) +{ + return cur_ops == &tasks_ops; +} + +#else /* #ifdef CONFIG_TASKS_RCU */ + +#define RCUPERF_TASKS_OPS + +static bool __maybe_unused torturing_tasks(void) +{ + return false; +} + +#endif /* #else #ifdef CONFIG_TASKS_RCU */ + +/* + * If performance tests complete, wait for shutdown to commence. + */ +static void rcu_perf_wait_shutdown(void) +{ + cond_resched_rcu_qs(); + if (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters) + return; + while (!torture_must_stop()) + schedule_timeout_uninterruptible(1); +} + +/* + * RCU perf reader kthread. Repeatedly does empty RCU read-side + * critical section, minimizing update-side interference. + */ +static int +rcu_perf_reader(void *arg) +{ + unsigned long flags; + int idx; + long me = (long)arg; + + VERBOSE_PERFOUT_STRING("rcu_perf_reader task started"); + set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)); + set_user_nice(current, MAX_NICE); + atomic_inc(&n_rcu_perf_reader_started); + + do { + local_irq_save(flags); + idx = cur_ops->readlock(); + cur_ops->readunlock(idx); + local_irq_restore(flags); + rcu_perf_wait_shutdown(); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_perf_reader"); + return 0; +} + +/* + * RCU perf writer kthread. Repeatedly does a grace period. + */ +static int +rcu_perf_writer(void *arg) +{ + int i = 0; + int i_max; + long me = (long)arg; + struct sched_param sp; + bool started = false, done = false, alldone = false; + u64 t; + u64 *wdp; + u64 *wdpp = writer_durations[me]; + + VERBOSE_PERFOUT_STRING("rcu_perf_writer task started"); + WARN_ON(rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp); + WARN_ON(rcu_gp_is_normal() && gp_exp); + WARN_ON(!wdpp); + set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)); + sp.sched_priority = 1; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); + + if (holdoff) + schedule_timeout_uninterruptible(holdoff * HZ); + + t = ktime_get_mono_fast_ns(); + if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) { + t_rcu_perf_writer_started = t; + if (gp_exp) { + b_rcu_perf_writer_started = + cur_ops->exp_completed() / 2; + } else { + b_rcu_perf_writer_started = + cur_ops->completed(); + } + } + + do { + wdp = &wdpp[i]; + *wdp = ktime_get_mono_fast_ns(); + if (gp_exp) { + rcu_perf_writer_state = RTWS_EXP_SYNC; + cur_ops->exp_sync(); + } else { + rcu_perf_writer_state = RTWS_SYNC; + cur_ops->sync(); + } + rcu_perf_writer_state = RTWS_IDLE; + t = ktime_get_mono_fast_ns(); + *wdp = t - *wdp; + i_max = i; + if (!started && + atomic_read(&n_rcu_perf_writer_started) >= nrealwriters) + started = true; + if (!done && i >= MIN_MEAS) { + done = true; + sp.sched_priority = 0; + sched_setscheduler_nocheck(current, + SCHED_NORMAL, &sp); + pr_alert("%s" PERF_FLAG + "rcu_perf_writer %ld has %d measurements\n", + perf_type, me, MIN_MEAS); + if (atomic_inc_return(&n_rcu_perf_writer_finished) >= + nrealwriters) { + schedule_timeout_interruptible(10); + rcu_ftrace_dump(DUMP_ALL); + PERFOUT_STRING("Test complete"); + t_rcu_perf_writer_finished = t; + if (gp_exp) { + b_rcu_perf_writer_finished = + cur_ops->exp_completed() / 2; + } else { + b_rcu_perf_writer_finished = + cur_ops->completed(); + } + if (shutdown) { + smp_mb(); /* Assign before wake. */ + wake_up(&shutdown_wq); + } + } + } + if (done && !alldone && + atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters) + alldone = true; + if (started && !alldone && i < MAX_MEAS - 1) + i++; + rcu_perf_wait_shutdown(); + } while (!torture_must_stop()); + rcu_perf_writer_state = RTWS_STOPPING; + writer_n_durations[me] = i_max; + torture_kthread_stopping("rcu_perf_writer"); + return 0; +} + +static inline void +rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag) +{ + pr_alert("%s" PERF_FLAG + "--- %s: nreaders=%d nwriters=%d verbose=%d shutdown=%d\n", + perf_type, tag, nrealreaders, nrealwriters, verbose, shutdown); +} + +static void +rcu_perf_cleanup(void) +{ + int i; + int j; + int ngps = 0; + u64 *wdp; + u64 *wdpp; + + if (torture_cleanup_begin()) + return; + + if (reader_tasks) { + for (i = 0; i < nrealreaders; i++) + torture_stop_kthread(rcu_perf_reader, + reader_tasks[i]); + kfree(reader_tasks); + } + + if (writer_tasks) { + for (i = 0; i < nrealwriters; i++) { + torture_stop_kthread(rcu_perf_writer, + writer_tasks[i]); + if (!writer_n_durations) + continue; + j = writer_n_durations[i]; + pr_alert("%s%s writer %d gps: %d\n", + perf_type, PERF_FLAG, i, j); + ngps += j; + } + pr_alert("%s%s start: %llu end: %llu duration: %llu gps: %d batches: %ld\n", + perf_type, PERF_FLAG, + t_rcu_perf_writer_started, t_rcu_perf_writer_finished, + t_rcu_perf_writer_finished - + t_rcu_perf_writer_started, + ngps, + b_rcu_perf_writer_finished - + b_rcu_perf_writer_started); + for (i = 0; i < nrealwriters; i++) { + if (!writer_durations) + break; + if (!writer_n_durations) + continue; + wdpp = writer_durations[i]; + if (!wdpp) + continue; + for (j = 0; j <= writer_n_durations[i]; j++) { + wdp = &wdpp[j]; + pr_alert("%s%s %4d writer-duration: %5d %llu\n", + perf_type, PERF_FLAG, + i, j, *wdp); + if (j % 100 == 0) + schedule_timeout_uninterruptible(1); + } + kfree(writer_durations[i]); + } + kfree(writer_tasks); + kfree(writer_durations); + kfree(writer_n_durations); + } + + /* Do flavor-specific cleanup operations. */ + if (cur_ops->cleanup != NULL) + cur_ops->cleanup(); + + torture_cleanup_end(); +} + +/* + * Return the number if non-negative. If -1, the number of CPUs. + * If less than -1, that much less than the number of CPUs, but + * at least one. + */ +static int compute_real(int n) +{ + int nr; + + if (n >= 0) { + nr = n; + } else { + nr = num_online_cpus() + 1 + n; + if (nr <= 0) + nr = 1; + } + return nr; +} + +/* + * RCU perf shutdown kthread. Just waits to be awakened, then shuts + * down system. + */ +static int +rcu_perf_shutdown(void *arg) +{ + do { + wait_event(shutdown_wq, + atomic_read(&n_rcu_perf_writer_finished) >= + nrealwriters); + } while (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters); + smp_mb(); /* Wake before output. */ + rcu_perf_cleanup(); + kernel_power_off(); + return -EINVAL; +} + +static int __init +rcu_perf_init(void) +{ + long i; + int firsterr = 0; + static struct rcu_perf_ops *perf_ops[] = { + &rcu_ops, &rcu_bh_ops, &srcu_ops, &sched_ops, + RCUPERF_TASKS_OPS + }; + + if (!torture_init_begin(perf_type, verbose, &perf_runnable)) + return -EBUSY; + + /* Process args and tell the world that the perf'er is on the job. */ + for (i = 0; i < ARRAY_SIZE(perf_ops); i++) { + cur_ops = perf_ops[i]; + if (strcmp(perf_type, cur_ops->name) == 0) + break; + } + if (i == ARRAY_SIZE(perf_ops)) { + pr_alert("rcu-perf: invalid perf type: \"%s\"\n", + perf_type); + pr_alert("rcu-perf types:"); + for (i = 0; i < ARRAY_SIZE(perf_ops); i++) + pr_alert(" %s", perf_ops[i]->name); + pr_alert("\n"); + firsterr = -EINVAL; + goto unwind; + } + if (cur_ops->init) + cur_ops->init(); + + nrealwriters = compute_real(nwriters); + nrealreaders = compute_real(nreaders); + atomic_set(&n_rcu_perf_reader_started, 0); + atomic_set(&n_rcu_perf_writer_started, 0); + atomic_set(&n_rcu_perf_writer_finished, 0); + rcu_perf_print_module_parms(cur_ops, "Start of test"); + + /* Start up the kthreads. */ + + if (shutdown) { + init_waitqueue_head(&shutdown_wq); + firsterr = torture_create_kthread(rcu_perf_shutdown, NULL, + shutdown_task); + if (firsterr) + goto unwind; + schedule_timeout_uninterruptible(1); + } + reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]), + GFP_KERNEL); + if (reader_tasks == NULL) { + VERBOSE_PERFOUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < nrealreaders; i++) { + firsterr = torture_create_kthread(rcu_perf_reader, (void *)i, + reader_tasks[i]); + if (firsterr) + goto unwind; + } + while (atomic_read(&n_rcu_perf_reader_started) < nrealreaders) + schedule_timeout_uninterruptible(1); + writer_tasks = kcalloc(nrealwriters, sizeof(reader_tasks[0]), + GFP_KERNEL); + writer_durations = kcalloc(nrealwriters, sizeof(*writer_durations), + GFP_KERNEL); + writer_n_durations = + kcalloc(nrealwriters, sizeof(*writer_n_durations), + GFP_KERNEL); + if (!writer_tasks || !writer_durations || !writer_n_durations) { + VERBOSE_PERFOUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < nrealwriters; i++) { + writer_durations[i] = + kcalloc(MAX_MEAS, sizeof(*writer_durations[i]), + GFP_KERNEL); + if (!writer_durations[i]) + goto unwind; + firsterr = torture_create_kthread(rcu_perf_writer, (void *)i, + writer_tasks[i]); + if (firsterr) + goto unwind; + } + torture_init_end(); + return 0; + +unwind: + torture_init_end(); + rcu_perf_cleanup(); + return firsterr; +} + +module_init(rcu_perf_init); +module_exit(rcu_perf_cleanup); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 250ea67..084a28a 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -130,8 +130,8 @@ static struct rcu_torture __rcu *rcu_torture_current; static unsigned long rcu_torture_current_version; static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN]; static DEFINE_SPINLOCK(rcu_torture_lock); -static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) = { 0 }; -static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch) = { 0 }; +static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count); +static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch); static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1]; static atomic_t n_rcu_torture_alloc; static atomic_t n_rcu_torture_alloc_fail; @@ -916,7 +916,7 @@ rcu_torture_fqs(void *arg) static int rcu_torture_writer(void *arg) { - bool can_expedite = !rcu_gp_is_expedited(); + bool can_expedite = !rcu_gp_is_expedited() && !rcu_gp_is_normal(); int expediting = 0; unsigned long gp_snap; bool gp_cond1 = gp_cond, gp_exp1 = gp_exp, gp_normal1 = gp_normal; @@ -932,7 +932,7 @@ rcu_torture_writer(void *arg) VERBOSE_TOROUT_STRING("rcu_torture_writer task started"); if (!can_expedite) { pr_alert("%s" TORTURE_FLAG - " Grace periods expedited from boot/sysfs for %s,\n", + " GP expediting controlled from boot/sysfs for %s,\n", torture_type, cur_ops->name); pr_alert("%s" TORTURE_FLAG " Disabled dynamic grace-period expediting.\n", @@ -1082,17 +1082,6 @@ rcu_torture_fakewriter(void *arg) return 0; } -static void rcutorture_trace_dump(void) -{ - static atomic_t beenhere = ATOMIC_INIT(0); - - if (atomic_read(&beenhere)) - return; - if (atomic_xchg(&beenhere, 1) != 0) - return; - ftrace_dump(DUMP_ALL); -} - /* * RCU torture reader from timer handler. Dereferences rcu_torture_current, * incrementing the corresponding element of the pipeline array. The @@ -1142,7 +1131,7 @@ static void rcu_torture_timer(unsigned long unused) if (pipe_count > 1) { do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts, started, completed); - rcutorture_trace_dump(); + rcu_ftrace_dump(DUMP_ALL); } __this_cpu_inc(rcu_torture_count[pipe_count]); completed = completed - started; @@ -1215,7 +1204,7 @@ rcu_torture_reader(void *arg) if (pipe_count > 1) { do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts, started, completed); - rcutorture_trace_dump(); + rcu_ftrace_dump(DUMP_ALL); } __this_cpu_inc(rcu_torture_count[pipe_count]); completed = completed - started; @@ -1333,7 +1322,7 @@ rcu_torture_stats_print(void) rcu_torture_writer_state, gpnum, completed, flags); show_rcu_gp_kthreads(); - rcutorture_trace_dump(); + rcu_ftrace_dump(DUMP_ALL); } rtcv_snap = rcu_torture_current_version; } @@ -1489,7 +1478,9 @@ static int rcu_torture_barrier_cbs(void *arg) * The above smp_load_acquire() ensures barrier_phase load * is ordered before the folloiwng ->call(). */ + local_irq_disable(); /* Just to test no-irq call_rcu(). */ cur_ops->call(&rcu, rcu_torture_barrier_cbf); + local_irq_enable(); if (atomic_dec_and_test(&barrier_cbs_count)) wake_up(&barrier_wq); } while (!torture_must_stop()); @@ -1596,7 +1587,7 @@ static int rcutorture_cpu_notify(struct notifier_block *self, { long cpu = (long)hcpu; - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: case CPU_DOWN_FAILED: (void)rcutorture_booster_init(cpu); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 9a535a8..c7f1bc4 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -102,6 +102,8 @@ struct rcu_state sname##_state = { \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ .name = RCU_STATE_NAME(sname), \ .abbr = sabbr, \ + .exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \ + .exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \ } RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); @@ -370,6 +372,21 @@ void rcu_all_qs(void) rcu_momentary_dyntick_idle(); local_irq_restore(flags); } + if (unlikely(raw_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))) { + /* + * Yes, we just checked a per-CPU variable with preemption + * enabled, so we might be migrated to some other CPU at + * this point. That is OK because in that case, the + * migration will supply the needed quiescent state. + * We might end up needlessly disabling preemption and + * invoking rcu_sched_qs() on the destination CPU, but + * the probability and cost are both quite low, so this + * should not be a problem in practice. + */ + preempt_disable(); + rcu_sched_qs(); + preempt_enable(); + } this_cpu_inc(rcu_qs_ctr); barrier(); /* Avoid RCU read-side critical sections leaking up. */ } @@ -385,9 +402,11 @@ module_param(qlowmark, long, 0444); static ulong jiffies_till_first_fqs = ULONG_MAX; static ulong jiffies_till_next_fqs = ULONG_MAX; +static bool rcu_kick_kthreads; module_param(jiffies_till_first_fqs, ulong, 0644); module_param(jiffies_till_next_fqs, ulong, 0644); +module_param(rcu_kick_kthreads, bool, 0644); /* * How long the grace period must be before we start recruiting @@ -460,6 +479,28 @@ unsigned long rcu_batches_completed_bh(void) EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); /* + * Return the number of RCU expedited batches completed thus far for + * debug & stats. Odd numbers mean that a batch is in progress, even + * numbers mean idle. The value returned will thus be roughly double + * the cumulative batches since boot. + */ +unsigned long rcu_exp_batches_completed(void) +{ + return rcu_state_p->expedited_sequence; +} +EXPORT_SYMBOL_GPL(rcu_exp_batches_completed); + +/* + * Return the number of RCU-sched expedited batches completed thus far + * for debug & stats. Similar to rcu_exp_batches_completed(). + */ +unsigned long rcu_exp_batches_completed_sched(void) +{ + return rcu_sched_state.expedited_sequence; +} +EXPORT_SYMBOL_GPL(rcu_exp_batches_completed_sched); + +/* * Force a quiescent state. */ void rcu_force_quiescent_state(void) @@ -637,7 +678,7 @@ static void rcu_eqs_enter_common(long long oldval, bool user) idle_task(smp_processor_id()); trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0); - ftrace_dump(DUMP_ORIG); + rcu_ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ @@ -799,7 +840,7 @@ static void rcu_eqs_exit_common(long long oldval, int user) trace_rcu_dyntick(TPS("Error on exit: not idle task"), oldval, rdtp->dynticks_nesting); - ftrace_dump(DUMP_ORIG); + rcu_ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ @@ -1224,8 +1265,10 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) rsp->gp_flags, gp_state_getname(rsp->gp_state), rsp->gp_state, rsp->gp_kthread ? rsp->gp_kthread->state : ~0); - if (rsp->gp_kthread) + if (rsp->gp_kthread) { sched_show_task(rsp->gp_kthread); + wake_up_process(rsp->gp_kthread); + } } } @@ -1249,6 +1292,25 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp) } } +/* + * If too much time has passed in the current grace period, and if + * so configured, go kick the relevant kthreads. + */ +static void rcu_stall_kick_kthreads(struct rcu_state *rsp) +{ + unsigned long j; + + if (!rcu_kick_kthreads) + return; + j = READ_ONCE(rsp->jiffies_kick_kthreads); + if (time_after(jiffies, j) && rsp->gp_kthread) { + WARN_ONCE(1, "Kicking %s grace-period kthread\n", rsp->name); + rcu_ftrace_dump(DUMP_ALL); + wake_up_process(rsp->gp_kthread); + WRITE_ONCE(rsp->jiffies_kick_kthreads, j + HZ); + } +} + static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) { int cpu; @@ -1260,6 +1322,11 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) struct rcu_node *rnp = rcu_get_root(rsp); long totqlen = 0; + /* Kick and suppress, if so configured. */ + rcu_stall_kick_kthreads(rsp); + if (rcu_cpu_stall_suppress) + return; + /* Only let one CPU complain about others per time interval. */ raw_spin_lock_irqsave_rcu_node(rnp, flags); @@ -1333,6 +1400,11 @@ static void print_cpu_stall(struct rcu_state *rsp) struct rcu_node *rnp = rcu_get_root(rsp); long totqlen = 0; + /* Kick and suppress, if so configured. */ + rcu_stall_kick_kthreads(rsp); + if (rcu_cpu_stall_suppress) + return; + /* * OK, time to rat on ourselves... * See Documentation/RCU/stallwarn.txt for info on how to debug @@ -1377,8 +1449,10 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) unsigned long js; struct rcu_node *rnp; - if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp)) + if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) || + !rcu_gp_in_progress(rsp)) return; + rcu_stall_kick_kthreads(rsp); j = jiffies; /* @@ -2117,8 +2191,11 @@ static int __noreturn rcu_gp_kthread(void *arg) } ret = 0; for (;;) { - if (!ret) + if (!ret) { rsp->jiffies_force_qs = jiffies + j; + WRITE_ONCE(rsp->jiffies_kick_kthreads, + jiffies + 3 * j); + } trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("fqswait")); @@ -2144,6 +2221,15 @@ static int __noreturn rcu_gp_kthread(void *arg) TPS("fqsend")); cond_resched_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); + ret = 0; /* Force full wait till next FQS. */ + j = jiffies_till_next_fqs; + if (j > HZ) { + j = HZ; + jiffies_till_next_fqs = HZ; + } else if (j < 1) { + j = 1; + jiffies_till_next_fqs = 1; + } } else { /* Deal with stray signal. */ cond_resched_rcu_qs(); @@ -2152,14 +2238,12 @@ static int __noreturn rcu_gp_kthread(void *arg) trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("fqswaitsig")); - } - j = jiffies_till_next_fqs; - if (j > HZ) { - j = HZ; - jiffies_till_next_fqs = HZ; - } else if (j < 1) { - j = 1; - jiffies_till_next_fqs = 1; + ret = 1; /* Keep old FQS timing. */ + j = jiffies; + if (time_after(jiffies, rsp->jiffies_force_qs)) + j = 1; + else + j = rsp->jiffies_force_qs - j; } } @@ -3376,8 +3460,12 @@ static void rcu_exp_gp_seq_end(struct rcu_state *rsp) } static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp) { + unsigned long s; + smp_mb(); /* Caller's modifications seen first by other CPUs. */ - return rcu_seq_snap(&rsp->expedited_sequence); + s = rcu_seq_snap(&rsp->expedited_sequence); + trace_rcu_exp_grace_period(rsp->name, s, TPS("snap")); + return s; } static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) { @@ -3469,7 +3557,7 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp) * for the current expedited grace period. Works only for preemptible * RCU -- other RCU implementation use other means. * - * Caller must hold the root rcu_node's exp_funnel_mutex. + * Caller must hold the rcu_state's exp_mutex. */ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) { @@ -3485,8 +3573,8 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) * recursively up the tree. (Calm down, calm down, we do the recursion * iteratively!) * - * Caller must hold the root rcu_node's exp_funnel_mutex and the - * specified rcu_node structure's ->lock. + * Caller must hold the rcu_state's exp_mutex and the specified rcu_node + * structure's ->lock. */ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake, unsigned long flags) @@ -3523,7 +3611,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, * Report expedited quiescent state for specified node. This is a * lock-acquisition wrapper function for __rcu_report_exp_rnp(). * - * Caller must hold the root rcu_node's exp_funnel_mutex. + * Caller must hold the rcu_state's exp_mutex. */ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake) @@ -3536,8 +3624,8 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp, /* * Report expedited quiescent state for multiple CPUs, all covered by the - * specified leaf rcu_node structure. Caller must hold the root - * rcu_node's exp_funnel_mutex. + * specified leaf rcu_node structure. Caller must hold the rcu_state's + * exp_mutex. */ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, unsigned long mask, bool wake) @@ -3555,7 +3643,6 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, /* * Report expedited quiescent state for specified rcu_data (CPU). - * Caller must hold the root rcu_node's exp_funnel_mutex. */ static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp, bool wake) @@ -3564,15 +3651,11 @@ static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp, } /* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */ -static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp, - atomic_long_t *stat, unsigned long s) +static bool sync_exp_work_done(struct rcu_state *rsp, atomic_long_t *stat, + unsigned long s) { if (rcu_exp_gp_seq_done(rsp, s)) { - if (rnp) - mutex_unlock(&rnp->exp_funnel_mutex); - else if (rdp) - mutex_unlock(&rdp->exp_funnel_mutex); + trace_rcu_exp_grace_period(rsp->name, s, TPS("done")); /* Ensure test happens before caller kfree(). */ smp_mb__before_atomic(); /* ^^^ */ atomic_long_inc(stat); @@ -3582,59 +3665,65 @@ static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp, } /* - * Funnel-lock acquisition for expedited grace periods. Returns a - * pointer to the root rcu_node structure, or NULL if some other - * task did the expedited grace period for us. + * Funnel-lock acquisition for expedited grace periods. Returns true + * if some other task completed an expedited grace period that this task + * can piggy-back on, and with no mutex held. Otherwise, returns false + * with the mutex held, indicating that the caller must actually do the + * expedited grace period. */ -static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) +static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s) { struct rcu_data *rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id()); - struct rcu_node *rnp0; - struct rcu_node *rnp1 = NULL; + struct rcu_node *rnp = rdp->mynode; + struct rcu_node *rnp_root = rcu_get_root(rsp); + + /* Low-contention fastpath. */ + if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s) && + (rnp == rnp_root || + ULONG_CMP_LT(READ_ONCE(rnp_root->exp_seq_rq), s)) && + !mutex_is_locked(&rsp->exp_mutex) && + mutex_trylock(&rsp->exp_mutex)) + goto fastpath; /* - * First try directly acquiring the root lock in order to reduce - * latency in the common case where expedited grace periods are - * rare. We check mutex_is_locked() to avoid pathological levels of - * memory contention on ->exp_funnel_mutex in the heavy-load case. + * Each pass through the following loop works its way up + * the rcu_node tree, returning if others have done the work or + * otherwise falls through to acquire rsp->exp_mutex. The mapping + * from CPU to rcu_node structure can be inexact, as it is just + * promoting locality and is not strictly needed for correctness. */ - rnp0 = rcu_get_root(rsp); - if (!mutex_is_locked(&rnp0->exp_funnel_mutex)) { - if (mutex_trylock(&rnp0->exp_funnel_mutex)) { - if (sync_exp_work_done(rsp, rnp0, NULL, - &rdp->expedited_workdone0, s)) - return NULL; - return rnp0; + for (; rnp != NULL; rnp = rnp->parent) { + if (sync_exp_work_done(rsp, &rdp->exp_workdone1, s)) + return true; + + /* Work not done, either wait here or go up. */ + spin_lock(&rnp->exp_lock); + if (ULONG_CMP_GE(rnp->exp_seq_rq, s)) { + + /* Someone else doing GP, so wait for them. */ + spin_unlock(&rnp->exp_lock); + trace_rcu_exp_funnel_lock(rsp->name, rnp->level, + rnp->grplo, rnp->grphi, + TPS("wait")); + wait_event(rnp->exp_wq[(s >> 1) & 0x3], + sync_exp_work_done(rsp, + &rdp->exp_workdone2, s)); + return true; } + rnp->exp_seq_rq = s; /* Followers can wait on us. */ + spin_unlock(&rnp->exp_lock); + trace_rcu_exp_funnel_lock(rsp->name, rnp->level, rnp->grplo, + rnp->grphi, TPS("nxtlvl")); } - - /* - * Each pass through the following loop works its way - * up the rcu_node tree, returning if others have done the - * work or otherwise falls through holding the root rnp's - * ->exp_funnel_mutex. The mapping from CPU to rcu_node structure - * can be inexact, as it is just promoting locality and is not - * strictly needed for correctness. - */ - if (sync_exp_work_done(rsp, NULL, NULL, &rdp->expedited_workdone1, s)) - return NULL; - mutex_lock(&rdp->exp_funnel_mutex); - rnp0 = rdp->mynode; - for (; rnp0 != NULL; rnp0 = rnp0->parent) { - if (sync_exp_work_done(rsp, rnp1, rdp, - &rdp->expedited_workdone2, s)) - return NULL; - mutex_lock(&rnp0->exp_funnel_mutex); - if (rnp1) - mutex_unlock(&rnp1->exp_funnel_mutex); - else - mutex_unlock(&rdp->exp_funnel_mutex); - rnp1 = rnp0; + mutex_lock(&rsp->exp_mutex); +fastpath: + if (sync_exp_work_done(rsp, &rdp->exp_workdone3, s)) { + mutex_unlock(&rsp->exp_mutex); + return true; } - if (sync_exp_work_done(rsp, rnp1, rdp, - &rdp->expedited_workdone3, s)) - return NULL; - return rnp1; + rcu_exp_gp_seq_start(rsp); + trace_rcu_exp_grace_period(rsp->name, s, TPS("start")); + return false; } /* Invoked on each online non-idle CPU for expedited quiescent state. */ @@ -3649,6 +3738,11 @@ static void sync_sched_exp_handler(void *data) if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) || __this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) return; + if (rcu_is_cpu_rrupt_from_idle()) { + rcu_report_exp_rdp(&rcu_sched_state, + this_cpu_ptr(&rcu_sched_data), true); + return; + } __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true); resched_cpu(smp_processor_id()); } @@ -3773,7 +3867,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) rsp->name); ndetected = 0; rcu_for_each_leaf_node(rsp, rnp) { - ndetected = rcu_print_task_exp_stall(rnp); + ndetected += rcu_print_task_exp_stall(rnp); mask = 1; for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { struct rcu_data *rdp; @@ -3783,7 +3877,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) ndetected++; rdp = per_cpu_ptr(rsp->rda, cpu); pr_cont(" %d-%c%c%c", cpu, - "O."[cpu_online(cpu)], + "O."[!!cpu_online(cpu)], "o."[!!(rdp->grpmask & rnp->expmaskinit)], "N."[!!(rdp->grpmask & rnp->expmaskinitnext)]); } @@ -3792,7 +3886,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n", jiffies - jiffies_start, rsp->expedited_sequence, rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]); - if (!ndetected) { + if (ndetected) { pr_err("blocking rcu_node structures:"); rcu_for_each_node_breadth_first(rsp, rnp) { if (rnp == rnp_root) @@ -3818,6 +3912,41 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) } } +/* + * Wait for the current expedited grace period to complete, and then + * wake up everyone who piggybacked on the just-completed expedited + * grace period. Also update all the ->exp_seq_rq counters as needed + * in order to avoid counter-wrap problems. + */ +static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s) +{ + struct rcu_node *rnp; + + synchronize_sched_expedited_wait(rsp); + rcu_exp_gp_seq_end(rsp); + trace_rcu_exp_grace_period(rsp->name, s, TPS("end")); + + /* + * Switch over to wakeup mode, allowing the next GP, but -only- the + * next GP, to proceed. + */ + mutex_lock(&rsp->exp_wake_mutex); + mutex_unlock(&rsp->exp_mutex); + + rcu_for_each_node_breadth_first(rsp, rnp) { + if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) { + spin_lock(&rnp->exp_lock); + /* Recheck, avoid hang in case someone just arrived. */ + if (ULONG_CMP_LT(rnp->exp_seq_rq, s)) + rnp->exp_seq_rq = s; + spin_unlock(&rnp->exp_lock); + } + wake_up_all(&rnp->exp_wq[(rsp->expedited_sequence >> 1) & 0x3]); + } + trace_rcu_exp_grace_period(rsp->name, s, TPS("endwake")); + mutex_unlock(&rsp->exp_wake_mutex); +} + /** * synchronize_sched_expedited - Brute-force RCU-sched grace period * @@ -3837,7 +3966,6 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) void synchronize_sched_expedited(void) { unsigned long s; - struct rcu_node *rnp; struct rcu_state *rsp = &rcu_sched_state; /* If only one CPU, this is automatically a grace period. */ @@ -3852,17 +3980,14 @@ void synchronize_sched_expedited(void) /* Take a snapshot of the sequence number. */ s = rcu_exp_gp_seq_snap(rsp); - - rnp = exp_funnel_lock(rsp, s); - if (rnp == NULL) + if (exp_funnel_lock(rsp, s)) return; /* Someone else did our work for us. */ - rcu_exp_gp_seq_start(rsp); + /* Initialize the rcu_node tree in preparation for the wait. */ sync_rcu_exp_select_cpus(rsp, sync_sched_exp_handler); - synchronize_sched_expedited_wait(rsp); - rcu_exp_gp_seq_end(rsp); - mutex_unlock(&rnp->exp_funnel_mutex); + /* Wait and clean up, including waking everyone. */ + rcu_exp_wait_wake(rsp, s); } EXPORT_SYMBOL_GPL(synchronize_sched_expedited); @@ -4162,7 +4287,6 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); rdp->cpu = cpu; rdp->rsp = rsp; - mutex_init(&rdp->exp_funnel_mutex); rcu_boot_init_nocb_percpu_data(rdp); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } @@ -4420,10 +4544,8 @@ static void __init rcu_init_one(struct rcu_state *rsp) { static const char * const buf[] = RCU_NODE_NAME_INIT; static const char * const fqs[] = RCU_FQS_NAME_INIT; - static const char * const exp[] = RCU_EXP_NAME_INIT; static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; - static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS]; static u8 fl_mask = 0x1; int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */ @@ -4482,9 +4604,11 @@ static void __init rcu_init_one(struct rcu_state *rsp) rnp->level = i; INIT_LIST_HEAD(&rnp->blkd_tasks); rcu_init_one_nocb(rnp); - mutex_init(&rnp->exp_funnel_mutex); - lockdep_set_class_and_name(&rnp->exp_funnel_mutex, - &rcu_exp_class[i], exp[i]); + init_waitqueue_head(&rnp->exp_wq[0]); + init_waitqueue_head(&rnp->exp_wq[1]); + init_waitqueue_head(&rnp->exp_wq[2]); + init_waitqueue_head(&rnp->exp_wq[3]); + spin_lock_init(&rnp->exp_lock); } } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index df668c0..e3959f5 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -70,7 +70,6 @@ # define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 } # define RCU_NODE_NAME_INIT { "rcu_node_0" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" } -# define RCU_EXP_NAME_INIT { "rcu_node_exp_0" } #elif NR_CPUS <= RCU_FANOUT_2 # define RCU_NUM_LVLS 2 # define NUM_RCU_LVL_0 1 @@ -79,7 +78,6 @@ # define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 } # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" } -# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1" } #elif NR_CPUS <= RCU_FANOUT_3 # define RCU_NUM_LVLS 3 # define NUM_RCU_LVL_0 1 @@ -89,7 +87,6 @@ # define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 } # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" } -# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" } #elif NR_CPUS <= RCU_FANOUT_4 # define RCU_NUM_LVLS 4 # define NUM_RCU_LVL_0 1 @@ -100,7 +97,6 @@ # define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 } # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" } -# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" } #else # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" #endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */ @@ -252,7 +248,9 @@ struct rcu_node { /* Counts of upcoming no-CB GP requests. */ raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp; - struct mutex exp_funnel_mutex ____cacheline_internodealigned_in_smp; + spinlock_t exp_lock ____cacheline_internodealigned_in_smp; + unsigned long exp_seq_rq; + wait_queue_head_t exp_wq[4]; } ____cacheline_internodealigned_in_smp; /* @@ -387,11 +385,9 @@ struct rcu_data { #ifdef CONFIG_RCU_FAST_NO_HZ struct rcu_head oom_head; #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ - struct mutex exp_funnel_mutex; - atomic_long_t expedited_workdone0; /* # done by others #0. */ - atomic_long_t expedited_workdone1; /* # done by others #1. */ - atomic_long_t expedited_workdone2; /* # done by others #2. */ - atomic_long_t expedited_workdone3; /* # done by others #3. */ + atomic_long_t exp_workdone1; /* # done by others #1. */ + atomic_long_t exp_workdone2; /* # done by others #2. */ + atomic_long_t exp_workdone3; /* # done by others #3. */ /* 7) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU @@ -505,6 +501,8 @@ struct rcu_state { /* _rcu_barrier(). */ /* End of fields guarded by barrier_mutex. */ + struct mutex exp_mutex; /* Serialize expedited GP. */ + struct mutex exp_wake_mutex; /* Serialize wakeup. */ unsigned long expedited_sequence; /* Take a ticket. */ atomic_long_t expedited_normal; /* # fallbacks to normal. */ atomic_t expedited_need_qs; /* # CPUs left to check in. */ @@ -513,6 +511,8 @@ struct rcu_state { unsigned long jiffies_force_qs; /* Time at which to invoke */ /* force_quiescent_state(). */ + unsigned long jiffies_kick_kthreads; /* Time at which to kick */ + /* kthreads, if configured. */ unsigned long n_force_qs; /* Number of calls to */ /* force_quiescent_state(). */ unsigned long n_force_qs_lh; /* ~Number of calls leaving */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index efdf7b6..ff1cd4e 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -722,18 +722,22 @@ static void sync_rcu_exp_handler(void *info) * synchronize_rcu_expedited - Brute-force RCU grace period * * Wait for an RCU-preempt grace period, but expedite it. The basic - * idea is to invoke synchronize_sched_expedited() to push all the tasks to - * the ->blkd_tasks lists and wait for this list to drain. This consumes - * significant time on all CPUs and is unfriendly to real-time workloads, - * so is thus not recommended for any sort of common-case code. - * In fact, if you are using synchronize_rcu_expedited() in a loop, - * please restructure your code to batch your updates, and then Use a - * single synchronize_rcu() instead. + * idea is to IPI all non-idle non-nohz online CPUs. The IPI handler + * checks whether the CPU is in an RCU-preempt critical section, and + * if so, it sets a flag that causes the outermost rcu_read_unlock() + * to report the quiescent state. On the other hand, if the CPU is + * not in an RCU read-side critical section, the IPI handler reports + * the quiescent state immediately. + * + * Although this is a greate improvement over previous expedited + * implementations, it is still unfriendly to real-time workloads, so is + * thus not recommended for any sort of common-case code. In fact, if + * you are using synchronize_rcu_expedited() in a loop, please restructure + * your code to batch your updates, and then Use a single synchronize_rcu() + * instead. */ void synchronize_rcu_expedited(void) { - struct rcu_node *rnp; - struct rcu_node *rnp_unlock; struct rcu_state *rsp = rcu_state_p; unsigned long s; @@ -744,23 +748,14 @@ void synchronize_rcu_expedited(void) } s = rcu_exp_gp_seq_snap(rsp); - - rnp_unlock = exp_funnel_lock(rsp, s); - if (rnp_unlock == NULL) + if (exp_funnel_lock(rsp, s)) return; /* Someone else did our work for us. */ - rcu_exp_gp_seq_start(rsp); - /* Initialize the rcu_node tree in preparation for the wait. */ sync_rcu_exp_select_cpus(rsp, sync_rcu_exp_handler); - /* Wait for snapshotted ->blkd_tasks lists to drain. */ - rnp = rcu_get_root(rsp); - synchronize_sched_expedited_wait(rsp); - - /* Clean up and exit. */ - rcu_exp_gp_seq_end(rsp); - mutex_unlock(&rnp_unlock->exp_funnel_mutex); + /* Wait for ->blkd_tasks lists to drain, then wake everyone up. */ + rcu_exp_wait_wake(rsp, s); } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index 1088e64..86782f9a 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -185,17 +185,16 @@ static int show_rcuexp(struct seq_file *m, void *v) int cpu; struct rcu_state *rsp = (struct rcu_state *)m->private; struct rcu_data *rdp; - unsigned long s0 = 0, s1 = 0, s2 = 0, s3 = 0; + unsigned long s1 = 0, s2 = 0, s3 = 0; for_each_possible_cpu(cpu) { rdp = per_cpu_ptr(rsp->rda, cpu); - s0 += atomic_long_read(&rdp->expedited_workdone0); - s1 += atomic_long_read(&rdp->expedited_workdone1); - s2 += atomic_long_read(&rdp->expedited_workdone2); - s3 += atomic_long_read(&rdp->expedited_workdone3); + s1 += atomic_long_read(&rdp->exp_workdone1); + s2 += atomic_long_read(&rdp->exp_workdone2); + s3 += atomic_long_read(&rdp->exp_workdone3); } - seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n", - rsp->expedited_sequence, s0, s1, s2, s3, + seq_printf(m, "s=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n", + rsp->expedited_sequence, s1, s2, s3, atomic_long_read(&rsp->expedited_normal), atomic_read(&rsp->expedited_need_qs), rsp->expedited_sequence / 2); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index ca828b4..3ccdc8e 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -67,7 +67,7 @@ static int rcu_normal_after_boot; module_param(rcu_normal_after_boot, int, 0); #endif /* #ifndef CONFIG_TINY_RCU */ -#if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_PREEMPT_COUNT) +#ifdef CONFIG_DEBUG_LOCK_ALLOC /** * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? * @@ -111,7 +111,7 @@ int rcu_read_lock_sched_held(void) return 0; if (debug_locks) lockdep_opinion = lock_is_held(&rcu_sched_lock_map); - return lockdep_opinion || preempt_count() != 0 || irqs_disabled(); + return lockdep_opinion || !preemptible(); } EXPORT_SYMBOL(rcu_read_lock_sched_held); #endif diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index fedb967..e85a725 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -318,6 +318,7 @@ u64 sched_clock_cpu(int cpu) return clock; } +EXPORT_SYMBOL_GPL(sched_clock_cpu); void sched_clock_tick(void) { @@ -363,39 +364,6 @@ void sched_clock_idle_wakeup_event(u64 delta_ns) } EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); -/* - * As outlined at the top, provides a fast, high resolution, nanosecond - * time source that is monotonic per cpu argument and has bounded drift - * between cpus. - * - * ######################### BIG FAT WARNING ########################## - * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # - * # go backwards !! # - * #################################################################### - */ -u64 cpu_clock(int cpu) -{ - if (!sched_clock_stable()) - return sched_clock_cpu(cpu); - - return sched_clock(); -} - -/* - * Similar to cpu_clock() for the current cpu. Time will only be observed - * to be monotonic if care is taken to only compare timestampt taken on the - * same CPU. - * - * See cpu_clock(). - */ -u64 local_clock(void) -{ - if (!sched_clock_stable()) - return sched_clock_cpu(raw_smp_processor_id()); - - return sched_clock(); -} - #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ void sched_clock_init(void) @@ -410,22 +378,8 @@ u64 sched_clock_cpu(int cpu) return sched_clock(); } - -u64 cpu_clock(int cpu) -{ - return sched_clock(); -} - -u64 local_clock(void) -{ - return sched_clock(); -} - #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ -EXPORT_SYMBOL_GPL(cpu_clock); -EXPORT_SYMBOL_GPL(local_clock); - /* * Running clock - returns the time that has elapsed while a guest has been * running. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8b489fc..404c078 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -33,7 +33,7 @@ #include <linux/init.h> #include <linux/uaccess.h> #include <linux/highmem.h> -#include <asm/mmu_context.h> +#include <linux/mmu_context.h> #include <linux/interrupt.h> #include <linux/capability.h> #include <linux/completion.h> @@ -170,6 +170,71 @@ static struct rq *this_rq_lock(void) return rq; } +/* + * __task_rq_lock - lock the rq @p resides on. + */ +struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(rq->lock) +{ + struct rq *rq; + + lockdep_assert_held(&p->pi_lock); + + for (;;) { + rq = task_rq(p); + raw_spin_lock(&rq->lock); + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { + rf->cookie = lockdep_pin_lock(&rq->lock); + return rq; + } + raw_spin_unlock(&rq->lock); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + +/* + * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. + */ +struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(p->pi_lock) + __acquires(rq->lock) +{ + struct rq *rq; + + for (;;) { + raw_spin_lock_irqsave(&p->pi_lock, rf->flags); + rq = task_rq(p); + raw_spin_lock(&rq->lock); + /* + * move_queued_task() task_rq_lock() + * + * ACQUIRE (rq->lock) + * [S] ->on_rq = MIGRATING [L] rq = task_rq() + * WMB (__set_task_cpu()) ACQUIRE (rq->lock); + * [S] ->cpu = new_cpu [L] task_rq() + * [L] ->on_rq + * RELEASE (rq->lock) + * + * If we observe the old cpu in task_rq_lock, the acquire of + * the old rq->lock will fully serialize against the stores. + * + * If we observe the new cpu in task_rq_lock, the acquire will + * pair with the WMB to ensure we must then also see migrating. + */ + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { + rf->cookie = lockdep_pin_lock(&rq->lock); + return rq; + } + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + #ifdef CONFIG_SCHED_HRTICK /* * Use HR-timers to deliver accurate preemption points. @@ -249,29 +314,6 @@ void hrtick_start(struct rq *rq, u64 delay) } } -static int -hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu) -{ - int cpu = (int)(long)hcpu; - - switch (action) { - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: - hrtick_clear(cpu_rq(cpu)); - return NOTIFY_OK; - } - - return NOTIFY_DONE; -} - -static __init void init_hrtick(void) -{ - hotcpu_notifier(hotplug_hrtick, 0); -} #else /* * Called to set the hrtick timer state. @@ -288,10 +330,6 @@ void hrtick_start(struct rq *rq, u64 delay) hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL_PINNED); } - -static inline void init_hrtick(void) -{ -} #endif /* CONFIG_SMP */ static void init_rq_hrtick(struct rq *rq) @@ -315,10 +353,6 @@ static inline void hrtick_clear(struct rq *rq) static inline void init_rq_hrtick(struct rq *rq) { } - -static inline void init_hrtick(void) -{ -} #endif /* CONFIG_SCHED_HRTICK */ /* @@ -400,7 +434,7 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) * wakeup due to that. * * This cmpxchg() implies a full barrier, which pairs with the write - * barrier implied by the wakeup in wake_up_list(). + * barrier implied by the wakeup in wake_up_q(). */ if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) return; @@ -499,7 +533,10 @@ int get_nohz_timer_target(void) rcu_read_lock(); for_each_domain(cpu, sd) { for_each_cpu(i, sched_domain_span(sd)) { - if (!idle_cpu(i) && is_housekeeping_cpu(cpu)) { + if (cpu == i) + continue; + + if (!idle_cpu(i) && is_housekeeping_cpu(i)) { cpu = i; goto unlock; } @@ -596,17 +633,8 @@ bool sched_can_stop_tick(struct rq *rq) return false; /* - * FIFO realtime policy runs the highest priority task (after DEADLINE). - * Other runnable tasks are of a lower priority. The scheduler tick - * isn't needed. - */ - fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running; - if (fifo_nr_running) - return true; - - /* - * Round-robin realtime tasks time slice with other tasks at the same - * realtime priority. + * If there are more than one RR tasks, we need the tick to effect the + * actual RR behaviour. */ if (rq->rt.rr_nr_running) { if (rq->rt.rr_nr_running == 1) @@ -615,8 +643,20 @@ bool sched_can_stop_tick(struct rq *rq) return false; } - /* Normal multitasking need periodic preemption checks */ - if (rq->cfs.nr_running > 1) + /* + * If there's no RR tasks, but FIFO tasks, we can skip the tick, no + * forced preemption between FIFO tasks. + */ + fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running; + if (fifo_nr_running) + return true; + + /* + * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left; + * if there's more than one we need the tick for involuntary + * preemption. + */ + if (rq->nr_running > 1) return false; return true; @@ -1082,12 +1122,20 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) static int __set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask, bool check) { - unsigned long flags; - struct rq *rq; + const struct cpumask *cpu_valid_mask = cpu_active_mask; unsigned int dest_cpu; + struct rq_flags rf; + struct rq *rq; int ret = 0; - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); + + if (p->flags & PF_KTHREAD) { + /* + * Kernel threads are allowed on online && !active CPUs + */ + cpu_valid_mask = cpu_online_mask; + } /* * Must re-check here, to close a race against __kthread_bind(), @@ -1101,22 +1149,32 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, if (cpumask_equal(&p->cpus_allowed, new_mask)) goto out; - if (!cpumask_intersects(new_mask, cpu_active_mask)) { + if (!cpumask_intersects(new_mask, cpu_valid_mask)) { ret = -EINVAL; goto out; } do_set_cpus_allowed(p, new_mask); + if (p->flags & PF_KTHREAD) { + /* + * For kernel threads that do indeed end up on online && + * !active we want to ensure they are strict per-cpu threads. + */ + WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) && + !cpumask_intersects(new_mask, cpu_active_mask) && + p->nr_cpus_allowed != 1); + } + /* Can the task run on the task's current CPU? If so, we're done */ if (cpumask_test_cpu(task_cpu(p), new_mask)) goto out; - dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); + dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask); if (task_running(rq, p) || p->state == TASK_WAKING) { struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); tlb_migrate_finish(p->mm); return 0; @@ -1125,12 +1183,12 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, * OK, since we're going to drop the lock immediately * afterwards anyway. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, rf.cookie); rq = move_queued_task(rq, p, dest_cpu); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, rf.cookie); } out: - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return ret; } @@ -1314,8 +1372,8 @@ out: */ unsigned long wait_task_inactive(struct task_struct *p, long match_state) { - unsigned long flags; int running, queued; + struct rq_flags rf; unsigned long ncsw; struct rq *rq; @@ -1350,14 +1408,14 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * lock now, to be *sure*. If we're wrong, we'll * just go back and repeat. */ - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); trace_sched_wait_task(p); running = task_running(rq, p); queued = task_on_rq_queued(p); ncsw = 0; if (!match_state || p->state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); /* * If it changed from the expected state, bail out now. @@ -1431,6 +1489,25 @@ EXPORT_SYMBOL_GPL(kick_process); /* * ->cpus_allowed is protected by both rq->lock and p->pi_lock + * + * A few notes on cpu_active vs cpu_online: + * + * - cpu_active must be a subset of cpu_online + * + * - on cpu-up we allow per-cpu kthreads on the online && !active cpu, + * see __set_cpus_allowed_ptr(). At this point the newly online + * cpu isn't yet part of the sched domains, and balancing will not + * see it. + * + * - on cpu-down we clear cpu_active() to mask the sched domains and + * avoid the load balancer to place new tasks on the to be removed + * cpu. Existing tasks will remain running there and will be taken + * off. + * + * This means that fallback selection must not select !active CPUs. + * And can assume that any active CPU must be online. Conversely + * select_task_rq() below may allow selection of !active CPUs in order + * to satisfy the above rules. */ static int select_fallback_rq(int cpu, struct task_struct *p) { @@ -1449,8 +1526,6 @@ static int select_fallback_rq(int cpu, struct task_struct *p) /* Look for allowed, online CPU in same node. */ for_each_cpu(dest_cpu, nodemask) { - if (!cpu_online(dest_cpu)) - continue; if (!cpu_active(dest_cpu)) continue; if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) @@ -1461,8 +1536,6 @@ static int select_fallback_rq(int cpu, struct task_struct *p) for (;;) { /* Any allowed, online CPU? */ for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) { - if (!cpu_online(dest_cpu)) - continue; if (!cpu_active(dest_cpu)) continue; goto out; @@ -1512,8 +1585,10 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) { lockdep_assert_held(&p->pi_lock); - if (p->nr_cpus_allowed > 1) + if (tsk_nr_cpus_allowed(p) > 1) cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); + else + cpu = cpumask_any(tsk_cpus_allowed(p)); /* * In order not to call set_task_cpu() on a blocking task we need @@ -1601,8 +1676,8 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl /* * Mark the task runnable and perform wakeup-preemption. */ -static void -ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) +static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, + struct pin_cookie cookie) { check_preempt_curr(rq, p, wake_flags); p->state = TASK_RUNNING; @@ -1614,9 +1689,9 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) * Our task @p is fully woken up and running; so its safe to * drop the rq->lock, hereafter rq is only used for statistics. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); p->sched_class->task_woken(rq, p); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, cookie); } if (rq->idle_stamp) { @@ -1634,17 +1709,23 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) } static void -ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) +ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, + struct pin_cookie cookie) { + int en_flags = ENQUEUE_WAKEUP; + lockdep_assert_held(&rq->lock); #ifdef CONFIG_SMP if (p->sched_contributes_to_load) rq->nr_uninterruptible--; + + if (wake_flags & WF_MIGRATED) + en_flags |= ENQUEUE_MIGRATED; #endif - ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); - ttwu_do_wakeup(rq, p, wake_flags); + ttwu_activate(rq, p, en_flags); + ttwu_do_wakeup(rq, p, wake_flags, cookie); } /* @@ -1655,17 +1736,18 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) */ static int ttwu_remote(struct task_struct *p, int wake_flags) { + struct rq_flags rf; struct rq *rq; int ret = 0; - rq = __task_rq_lock(p); + rq = __task_rq_lock(p, &rf); if (task_on_rq_queued(p)) { /* check_preempt_curr() may use rq clock */ update_rq_clock(rq); - ttwu_do_wakeup(rq, p, wake_flags); + ttwu_do_wakeup(rq, p, wake_flags, rf.cookie); ret = 1; } - __task_rq_unlock(rq); + __task_rq_unlock(rq, &rf); return ret; } @@ -1675,6 +1757,7 @@ void sched_ttwu_pending(void) { struct rq *rq = this_rq(); struct llist_node *llist = llist_del_all(&rq->wake_list); + struct pin_cookie cookie; struct task_struct *p; unsigned long flags; @@ -1682,15 +1765,19 @@ void sched_ttwu_pending(void) return; raw_spin_lock_irqsave(&rq->lock, flags); - lockdep_pin_lock(&rq->lock); + cookie = lockdep_pin_lock(&rq->lock); while (llist) { p = llist_entry(llist, struct task_struct, wake_entry); llist = llist_next(llist); - ttwu_do_activate(rq, p, 0); + /* + * See ttwu_queue(); we only call ttwu_queue_remote() when + * its a x-cpu wakeup. + */ + ttwu_do_activate(rq, p, WF_MIGRATED, cookie); } - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -1774,9 +1861,10 @@ bool cpus_share_cache(int this_cpu, int that_cpu) } #endif /* CONFIG_SMP */ -static void ttwu_queue(struct task_struct *p, int cpu) +static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) { struct rq *rq = cpu_rq(cpu); + struct pin_cookie cookie; #if defined(CONFIG_SMP) if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { @@ -1787,9 +1875,9 @@ static void ttwu_queue(struct task_struct *p, int cpu) #endif raw_spin_lock(&rq->lock); - lockdep_pin_lock(&rq->lock); - ttwu_do_activate(rq, p, 0); - lockdep_unpin_lock(&rq->lock); + cookie = lockdep_pin_lock(&rq->lock); + ttwu_do_activate(rq, p, wake_flags, cookie); + lockdep_unpin_lock(&rq->lock, cookie); raw_spin_unlock(&rq->lock); } @@ -1958,9 +2046,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; - if (p->sched_class->task_waking) - p->sched_class->task_waking(p); - cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; @@ -1968,7 +2053,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) } #endif /* CONFIG_SMP */ - ttwu_queue(p, cpu); + ttwu_queue(p, cpu, wake_flags); stat: if (schedstat_enabled()) ttwu_stat(p, cpu, wake_flags); @@ -1986,7 +2071,7 @@ out: * ensure that this_rq() is locked, @p is bound to this_rq() and not * the current task. */ -static void try_to_wake_up_local(struct task_struct *p) +static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie) { struct rq *rq = task_rq(p); @@ -2003,11 +2088,11 @@ static void try_to_wake_up_local(struct task_struct *p) * disabled avoiding further scheduler activity on it and we've * not yet picked a replacement task. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); raw_spin_unlock(&rq->lock); raw_spin_lock(&p->pi_lock); raw_spin_lock(&rq->lock); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, cookie); } if (!(p->state & TASK_NORMAL)) @@ -2018,7 +2103,7 @@ static void try_to_wake_up_local(struct task_struct *p) if (!task_on_rq_queued(p)) ttwu_activate(rq, p, ENQUEUE_WAKEUP); - ttwu_do_wakeup(rq, p, 0); + ttwu_do_wakeup(rq, p, 0, cookie); if (schedstat_enabled()) ttwu_stat(p, smp_processor_id(), 0); out: @@ -2378,7 +2463,8 @@ static int dl_overflow(struct task_struct *p, int policy, u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; int cpus, err = -1; - if (new_bw == p->dl.dl_bw) + /* !deadline task may carry old deadline bandwidth */ + if (new_bw == p->dl.dl_bw && task_has_dl_policy(p)) return 0; /* @@ -2417,12 +2503,12 @@ extern void init_dl_bw(struct dl_bw *dl_b); */ void wake_up_new_task(struct task_struct *p) { - unsigned long flags; + struct rq_flags rf; struct rq *rq; - raw_spin_lock_irqsave(&p->pi_lock, flags); /* Initialize new task's runnable average */ init_entity_runnable_average(&p->se); + raw_spin_lock_irqsave(&p->pi_lock, rf.flags); #ifdef CONFIG_SMP /* * Fork balancing, do it here and not earlier because: @@ -2431,8 +2517,10 @@ void wake_up_new_task(struct task_struct *p) */ set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); #endif + /* Post initialize new task's util average when its cfs_rq is set */ + post_init_entity_util_avg(&p->se); - rq = __task_rq_lock(p); + rq = __task_rq_lock(p, &rf); activate_task(rq, p, 0); p->on_rq = TASK_ON_RQ_QUEUED; trace_sched_wakeup_new(p); @@ -2443,12 +2531,12 @@ void wake_up_new_task(struct task_struct *p) * Nothing relies on rq->lock after this, so its fine to * drop it. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, rf.cookie); p->sched_class->task_woken(rq, p); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, rf.cookie); } #endif - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); } #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -2710,7 +2798,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) */ static __always_inline struct rq * context_switch(struct rq *rq, struct task_struct *prev, - struct task_struct *next) + struct task_struct *next, struct pin_cookie cookie) { struct mm_struct *mm, *oldmm; @@ -2730,7 +2818,7 @@ context_switch(struct rq *rq, struct task_struct *prev, atomic_inc(&oldmm->mm_count); enter_lazy_tlb(oldmm, next); } else - switch_mm(oldmm, mm, next); + switch_mm_irqs_off(oldmm, mm, next); if (!prev->mm) { prev->active_mm = NULL; @@ -2742,7 +2830,7 @@ context_switch(struct rq *rq, struct task_struct *prev, * of the scheduler it's an obvious special-case), so we * do an early lockdep release here: */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); /* Here we just switch the register state and the stack. */ @@ -2864,7 +2952,7 @@ EXPORT_PER_CPU_SYMBOL(kernel_cpustat); */ unsigned long long task_sched_runtime(struct task_struct *p) { - unsigned long flags; + struct rq_flags rf; struct rq *rq; u64 ns; @@ -2884,7 +2972,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) return p->se.sum_exec_runtime; #endif - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); /* * Must be ->curr _and_ ->on_rq. If dequeued, we would * project cycles that may never be accounted to this @@ -2895,7 +2983,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) p->sched_class->update_curr(rq); } ns = p->se.sum_exec_runtime; - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return ns; } @@ -2915,7 +3003,7 @@ void scheduler_tick(void) raw_spin_lock(&rq->lock); update_rq_clock(rq); curr->sched_class->task_tick(rq, curr, 0); - update_cpu_load_active(rq); + cpu_load_update_active(rq); calc_global_load_tick(rq); raw_spin_unlock(&rq->lock); @@ -2958,6 +3046,20 @@ u64 scheduler_tick_max_deferment(void) #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ defined(CONFIG_PREEMPT_TRACER)) +/* + * If the value passed in is equal to the current preempt count + * then we just disabled preemption. Start timing the latency. + */ +static inline void preempt_latency_start(int val) +{ + if (preempt_count() == val) { + unsigned long ip = get_lock_parent_ip(); +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; +#endif + trace_preempt_off(CALLER_ADDR0, ip); + } +} void preempt_count_add(int val) { @@ -2976,17 +3078,21 @@ void preempt_count_add(int val) DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK - 10); #endif - if (preempt_count() == val) { - unsigned long ip = get_lock_parent_ip(); -#ifdef CONFIG_DEBUG_PREEMPT - current->preempt_disable_ip = ip; -#endif - trace_preempt_off(CALLER_ADDR0, ip); - } + preempt_latency_start(val); } EXPORT_SYMBOL(preempt_count_add); NOKPROBE_SYMBOL(preempt_count_add); +/* + * If the value passed in equals to the current preempt count + * then we just enabled preemption. Stop timing the latency. + */ +static inline void preempt_latency_stop(int val) +{ + if (preempt_count() == val) + trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); +} + void preempt_count_sub(int val) { #ifdef CONFIG_DEBUG_PREEMPT @@ -3003,13 +3109,15 @@ void preempt_count_sub(int val) return; #endif - if (preempt_count() == val) - trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); + preempt_latency_stop(val); __preempt_count_sub(val); } EXPORT_SYMBOL(preempt_count_sub); NOKPROBE_SYMBOL(preempt_count_sub); +#else +static inline void preempt_latency_start(int val) { } +static inline void preempt_latency_stop(int val) { } #endif /* @@ -3062,7 +3170,7 @@ static inline void schedule_debug(struct task_struct *prev) * Pick up the highest-prio task: */ static inline struct task_struct * -pick_next_task(struct rq *rq, struct task_struct *prev) +pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) { const struct sched_class *class = &fair_sched_class; struct task_struct *p; @@ -3073,20 +3181,20 @@ pick_next_task(struct rq *rq, struct task_struct *prev) */ if (likely(prev->sched_class == class && rq->nr_running == rq->cfs.h_nr_running)) { - p = fair_sched_class.pick_next_task(rq, prev); + p = fair_sched_class.pick_next_task(rq, prev, cookie); if (unlikely(p == RETRY_TASK)) goto again; /* assumes fair_sched_class->next == idle_sched_class */ if (unlikely(!p)) - p = idle_sched_class.pick_next_task(rq, prev); + p = idle_sched_class.pick_next_task(rq, prev, cookie); return p; } again: for_each_class(class) { - p = class->pick_next_task(rq, prev); + p = class->pick_next_task(rq, prev, cookie); if (p) { if (unlikely(p == RETRY_TASK)) goto again; @@ -3140,6 +3248,7 @@ static void __sched notrace __schedule(bool preempt) { struct task_struct *prev, *next; unsigned long *switch_count; + struct pin_cookie cookie; struct rq *rq; int cpu; @@ -3173,7 +3282,7 @@ static void __sched notrace __schedule(bool preempt) */ smp_mb__before_spinlock(); raw_spin_lock(&rq->lock); - lockdep_pin_lock(&rq->lock); + cookie = lockdep_pin_lock(&rq->lock); rq->clock_skip_update <<= 1; /* promote REQ to ACT */ @@ -3195,7 +3304,7 @@ static void __sched notrace __schedule(bool preempt) to_wakeup = wq_worker_sleeping(prev); if (to_wakeup) - try_to_wake_up_local(to_wakeup); + try_to_wake_up_local(to_wakeup, cookie); } } switch_count = &prev->nvcsw; @@ -3204,7 +3313,7 @@ static void __sched notrace __schedule(bool preempt) if (task_on_rq_queued(prev)) update_rq_clock(rq); - next = pick_next_task(rq, prev); + next = pick_next_task(rq, prev, cookie); clear_tsk_need_resched(prev); clear_preempt_need_resched(); rq->clock_skip_update = 0; @@ -3215,9 +3324,9 @@ static void __sched notrace __schedule(bool preempt) ++*switch_count; trace_sched_switch(preempt, prev, next); - rq = context_switch(rq, prev, next); /* unlocks the rq */ + rq = context_switch(rq, prev, next, cookie); /* unlocks the rq */ } else { - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); raw_spin_unlock_irq(&rq->lock); } @@ -3284,8 +3393,23 @@ void __sched schedule_preempt_disabled(void) static void __sched notrace preempt_schedule_common(void) { do { + /* + * Because the function tracer can trace preempt_count_sub() + * and it also uses preempt_enable/disable_notrace(), if + * NEED_RESCHED is set, the preempt_enable_notrace() called + * by the function tracer will call this function again and + * cause infinite recursion. + * + * Preemption must be disabled here before the function + * tracer can trace. Break up preempt_disable() into two + * calls. One to disable preemption without fear of being + * traced. The other to still record the preemption latency, + * which can also be traced by the function tracer. + */ preempt_disable_notrace(); + preempt_latency_start(1); __schedule(true); + preempt_latency_stop(1); preempt_enable_no_resched_notrace(); /* @@ -3337,7 +3461,21 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) return; do { + /* + * Because the function tracer can trace preempt_count_sub() + * and it also uses preempt_enable/disable_notrace(), if + * NEED_RESCHED is set, the preempt_enable_notrace() called + * by the function tracer will call this function again and + * cause infinite recursion. + * + * Preemption must be disabled here before the function + * tracer can trace. Break up preempt_disable() into two + * calls. One to disable preemption without fear of being + * traced. The other to still record the preemption latency, + * which can also be traced by the function tracer. + */ preempt_disable_notrace(); + preempt_latency_start(1); /* * Needs preempt disabled in case user_exit() is traced * and the tracer calls preempt_enable_notrace() causing @@ -3347,6 +3485,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) __schedule(true); exception_exit(prev_ctx); + preempt_latency_stop(1); preempt_enable_no_resched_notrace(); } while (need_resched()); } @@ -3403,12 +3542,13 @@ EXPORT_SYMBOL(default_wake_function); void rt_mutex_setprio(struct task_struct *p, int prio) { int oldprio, queued, running, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE; - struct rq *rq; const struct sched_class *prev_class; + struct rq_flags rf; + struct rq *rq; BUG_ON(prio > MAX_PRIO); - rq = __task_rq_lock(p); + rq = __task_rq_lock(p, &rf); /* * Idle task boosting is a nono in general. There is one @@ -3484,7 +3624,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) check_class_changed(rq, p, prev_class, oldprio); out_unlock: preempt_disable(); /* avoid rq from going away on us */ - __task_rq_unlock(rq); + __task_rq_unlock(rq, &rf); balance_callback(rq); preempt_enable(); @@ -3494,7 +3634,7 @@ out_unlock: void set_user_nice(struct task_struct *p, long nice) { int old_prio, delta, queued; - unsigned long flags; + struct rq_flags rf; struct rq *rq; if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) @@ -3503,7 +3643,7 @@ void set_user_nice(struct task_struct *p, long nice) * We have to be careful, if called from sys_setpriority(), * the task might be in the middle of scheduling on another CPU. */ - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); /* * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected @@ -3534,7 +3674,7 @@ void set_user_nice(struct task_struct *p, long nice) resched_curr(rq); } out_unlock: - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); } EXPORT_SYMBOL(set_user_nice); @@ -3831,11 +3971,11 @@ static int __sched_setscheduler(struct task_struct *p, MAX_RT_PRIO - 1 - attr->sched_priority; int retval, oldprio, oldpolicy = -1, queued, running; int new_effective_prio, policy = attr->sched_policy; - unsigned long flags; const struct sched_class *prev_class; - struct rq *rq; + struct rq_flags rf; int reset_on_fork; int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE; + struct rq *rq; /* may grab non-irq protected spin_locks */ BUG_ON(in_interrupt()); @@ -3930,13 +4070,13 @@ recheck: * To be able to change p->policy safely, the appropriate * runqueue lock must be held. */ - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); /* * Changing the policy of the stop threads its a very bad idea */ if (p == rq->stop) { - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return -EINVAL; } @@ -3953,7 +4093,7 @@ recheck: goto change; p->sched_reset_on_fork = reset_on_fork; - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return 0; } change: @@ -3967,7 +4107,7 @@ change: if (rt_bandwidth_enabled() && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0 && !task_group_is_autogroup(task_group(p))) { - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return -EPERM; } #endif @@ -3982,7 +4122,7 @@ change: */ if (!cpumask_subset(span, &p->cpus_allowed) || rq->rd->dl_bw.bw == 0) { - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return -EPERM; } } @@ -3992,7 +4132,7 @@ change: /* recheck policy now with rq lock held */ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); goto recheck; } @@ -4002,7 +4142,7 @@ change: * is available. */ if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) { - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return -EBUSY; } @@ -4047,7 +4187,7 @@ change: check_class_changed(rq, p, prev_class, oldprio); preempt_disable(); /* avoid rq from going away on us */ - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); if (pi) rt_mutex_adjust_pi(p); @@ -4900,10 +5040,10 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, { struct task_struct *p; unsigned int time_slice; - unsigned long flags; + struct rq_flags rf; + struct timespec t; struct rq *rq; int retval; - struct timespec t; if (pid < 0) return -EINVAL; @@ -4918,11 +5058,11 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, if (retval) goto out_unlock; - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); time_slice = 0; if (p->sched_class->get_rr_interval) time_slice = p->sched_class->get_rr_interval(rq, p); - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); rcu_read_unlock(); jiffies_to_timespec(time_slice, &t); @@ -4998,7 +5138,8 @@ void show_state_filter(unsigned long state_filter) touch_all_softlockup_watchdogs(); #ifdef CONFIG_SCHED_DEBUG - sysrq_sched_debug_show(); + if (!state_filter) + sysrq_sched_debug_show(); #endif rcu_read_unlock(); /* @@ -5160,6 +5301,8 @@ out: #ifdef CONFIG_SMP +static bool sched_smp_initialized __read_mostly; + #ifdef CONFIG_NUMA_BALANCING /* Migrate current task p to target_cpu */ int migrate_task_to(struct task_struct *p, int target_cpu) @@ -5185,11 +5328,11 @@ int migrate_task_to(struct task_struct *p, int target_cpu) */ void sched_setnuma(struct task_struct *p, int nid) { - struct rq *rq; - unsigned long flags; bool queued, running; + struct rq_flags rf; + struct rq *rq; - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); queued = task_on_rq_queued(p); running = task_current(rq, p); @@ -5204,7 +5347,7 @@ void sched_setnuma(struct task_struct *p, int nid) p->sched_class->set_curr_task(rq); if (queued) enqueue_task(rq, p, ENQUEUE_RESTORE); - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); } #endif /* CONFIG_NUMA_BALANCING */ @@ -5220,7 +5363,7 @@ void idle_task_exit(void) BUG_ON(cpu_online(smp_processor_id())); if (mm != &init_mm) { - switch_mm(mm, &init_mm, current); + switch_mm_irqs_off(mm, &init_mm, current); finish_arch_post_lock_switch(); } mmdrop(mm); @@ -5268,6 +5411,7 @@ static void migrate_tasks(struct rq *dead_rq) { struct rq *rq = dead_rq; struct task_struct *next, *stop = rq->stop; + struct pin_cookie cookie; int dest_cpu; /* @@ -5299,8 +5443,8 @@ static void migrate_tasks(struct rq *dead_rq) /* * pick_next_task assumes pinned rq->lock. */ - lockdep_pin_lock(&rq->lock); - next = pick_next_task(rq, &fake_task); + cookie = lockdep_pin_lock(&rq->lock); + next = pick_next_task(rq, &fake_task, cookie); BUG_ON(!next); next->sched_class->put_prev_task(rq, next); @@ -5313,7 +5457,7 @@ static void migrate_tasks(struct rq *dead_rq) * because !cpu_active at this point, which means load-balance * will not interfere. Also, stop-machine. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); raw_spin_unlock(&rq->lock); raw_spin_lock(&next->pi_lock); raw_spin_lock(&rq->lock); @@ -5374,127 +5518,13 @@ static void set_rq_offline(struct rq *rq) } } -/* - * migration_call - callback that gets triggered when a CPU is added. - * Here we can start up the necessary migration thread for the new CPU. - */ -static int -migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) +static void set_cpu_rq_start_time(unsigned int cpu) { - int cpu = (long)hcpu; - unsigned long flags; struct rq *rq = cpu_rq(cpu); - switch (action & ~CPU_TASKS_FROZEN) { - - case CPU_UP_PREPARE: - rq->calc_load_update = calc_load_update; - account_reset_rq(rq); - break; - - case CPU_ONLINE: - /* Update our root-domain */ - raw_spin_lock_irqsave(&rq->lock, flags); - if (rq->rd) { - BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); - - set_rq_online(rq); - } - raw_spin_unlock_irqrestore(&rq->lock, flags); - break; - -#ifdef CONFIG_HOTPLUG_CPU - case CPU_DYING: - sched_ttwu_pending(); - /* Update our root-domain */ - raw_spin_lock_irqsave(&rq->lock, flags); - if (rq->rd) { - BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); - set_rq_offline(rq); - } - migrate_tasks(rq); - BUG_ON(rq->nr_running != 1); /* the migration thread */ - raw_spin_unlock_irqrestore(&rq->lock, flags); - break; - - case CPU_DEAD: - calc_load_migrate(rq); - break; -#endif - } - - update_max_interval(); - - return NOTIFY_OK; -} - -/* - * Register at high priority so that task migration (migrate_all_tasks) - * happens before everything else. This has to be lower priority than - * the notifier in the perf_event subsystem, though. - */ -static struct notifier_block migration_notifier = { - .notifier_call = migration_call, - .priority = CPU_PRI_MIGRATION, -}; - -static void set_cpu_rq_start_time(void) -{ - int cpu = smp_processor_id(); - struct rq *rq = cpu_rq(cpu); rq->age_stamp = sched_clock_cpu(cpu); } -static int sched_cpu_active(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - int cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_STARTING: - set_cpu_rq_start_time(); - return NOTIFY_OK; - - case CPU_DOWN_FAILED: - set_cpu_active(cpu, true); - return NOTIFY_OK; - - default: - return NOTIFY_DONE; - } -} - -static int sched_cpu_inactive(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DOWN_PREPARE: - set_cpu_active((long)hcpu, false); - return NOTIFY_OK; - default: - return NOTIFY_DONE; - } -} - -static int __init migration_init(void) -{ - void *cpu = (void *)(long)smp_processor_id(); - int err; - - /* Initialize migration for the boot CPU */ - err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); - BUG_ON(err == NOTIFY_BAD); - migration_call(&migration_notifier, CPU_ONLINE, cpu); - register_cpu_notifier(&migration_notifier); - - /* Register cpu active notifiers */ - cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); - cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); - - return 0; -} -early_initcall(migration_init); - static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ #ifdef CONFIG_SCHED_DEBUG @@ -6642,10 +6672,10 @@ static void sched_init_numa(void) init_numa_topology_type(); } -static void sched_domains_numa_masks_set(int cpu) +static void sched_domains_numa_masks_set(unsigned int cpu) { - int i, j; int node = cpu_to_node(cpu); + int i, j; for (i = 0; i < sched_domains_numa_levels; i++) { for (j = 0; j < nr_node_ids; j++) { @@ -6655,51 +6685,20 @@ static void sched_domains_numa_masks_set(int cpu) } } -static void sched_domains_numa_masks_clear(int cpu) +static void sched_domains_numa_masks_clear(unsigned int cpu) { int i, j; + for (i = 0; i < sched_domains_numa_levels; i++) { for (j = 0; j < nr_node_ids; j++) cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); } } -/* - * Update sched_domains_numa_masks[level][node] array when new cpus - * are onlined. - */ -static int sched_domains_numa_masks_update(struct notifier_block *nfb, - unsigned long action, - void *hcpu) -{ - int cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: - sched_domains_numa_masks_set(cpu); - break; - - case CPU_DEAD: - sched_domains_numa_masks_clear(cpu); - break; - - default: - return NOTIFY_DONE; - } - - return NOTIFY_OK; -} #else -static inline void sched_init_numa(void) -{ -} - -static int sched_domains_numa_masks_update(struct notifier_block *nfb, - unsigned long action, - void *hcpu) -{ - return 0; -} +static inline void sched_init_numa(void) { } +static void sched_domains_numa_masks_set(unsigned int cpu) { } +static void sched_domains_numa_masks_clear(unsigned int cpu) { } #endif /* CONFIG_NUMA */ static int __sdt_alloc(const struct cpumask *cpu_map) @@ -7089,13 +7088,9 @@ static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */ * If we come here as part of a suspend/resume, don't touch cpusets because we * want to restore it back to its original state upon resume anyway. */ -static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, - void *hcpu) +static void cpuset_cpu_active(void) { - switch (action) { - case CPU_ONLINE_FROZEN: - case CPU_DOWN_FAILED_FROZEN: - + if (cpuhp_tasks_frozen) { /* * num_cpus_frozen tracks how many CPUs are involved in suspend * resume sequence. As long as this is not the last online @@ -7105,35 +7100,25 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, num_cpus_frozen--; if (likely(num_cpus_frozen)) { partition_sched_domains(1, NULL, NULL); - break; + return; } - /* * This is the last CPU online operation. So fall through and * restore the original sched domains by considering the * cpuset configurations. */ - - case CPU_ONLINE: - cpuset_update_active_cpus(true); - break; - default: - return NOTIFY_DONE; } - return NOTIFY_OK; + cpuset_update_active_cpus(true); } -static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, - void *hcpu) +static int cpuset_cpu_inactive(unsigned int cpu) { unsigned long flags; - long cpu = (long)hcpu; struct dl_bw *dl_b; bool overflow; int cpus; - switch (action) { - case CPU_DOWN_PREPARE: + if (!cpuhp_tasks_frozen) { rcu_read_lock_sched(); dl_b = dl_bw_of(cpu); @@ -7145,18 +7130,119 @@ static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, rcu_read_unlock_sched(); if (overflow) - return notifier_from_errno(-EBUSY); + return -EBUSY; cpuset_update_active_cpus(false); - break; - case CPU_DOWN_PREPARE_FROZEN: + } else { num_cpus_frozen++; partition_sched_domains(1, NULL, NULL); - break; - default: - return NOTIFY_DONE; } - return NOTIFY_OK; + return 0; +} + +int sched_cpu_activate(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + set_cpu_active(cpu, true); + + if (sched_smp_initialized) { + sched_domains_numa_masks_set(cpu); + cpuset_cpu_active(); + } + + /* + * Put the rq online, if not already. This happens: + * + * 1) In the early boot process, because we build the real domains + * after all cpus have been brought up. + * + * 2) At runtime, if cpuset_cpu_active() fails to rebuild the + * domains. + */ + raw_spin_lock_irqsave(&rq->lock, flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_online(rq); + } + raw_spin_unlock_irqrestore(&rq->lock, flags); + + update_max_interval(); + + return 0; +} + +int sched_cpu_deactivate(unsigned int cpu) +{ + int ret; + + set_cpu_active(cpu, false); + /* + * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU + * users of this state to go away such that all new such users will + * observe it. + * + * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might + * not imply sync_sched(), so wait for both. + * + * Do sync before park smpboot threads to take care the rcu boost case. + */ + if (IS_ENABLED(CONFIG_PREEMPT)) + synchronize_rcu_mult(call_rcu, call_rcu_sched); + else + synchronize_rcu(); + + if (!sched_smp_initialized) + return 0; + + ret = cpuset_cpu_inactive(cpu); + if (ret) { + set_cpu_active(cpu, true); + return ret; + } + sched_domains_numa_masks_clear(cpu); + return 0; +} + +static void sched_rq_cpu_starting(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + rq->calc_load_update = calc_load_update; + account_reset_rq(rq); + update_max_interval(); +} + +int sched_cpu_starting(unsigned int cpu) +{ + set_cpu_rq_start_time(cpu); + sched_rq_cpu_starting(cpu); + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +int sched_cpu_dying(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + /* Handle pending wakeups and then migrate everything off */ + sched_ttwu_pending(); + raw_spin_lock_irqsave(&rq->lock, flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_offline(rq); + } + migrate_tasks(rq); + BUG_ON(rq->nr_running != 1); + raw_spin_unlock_irqrestore(&rq->lock, flags); + calc_load_migrate(rq); + update_max_interval(); + nohz_balance_exit_idle(cpu); + hrtick_clear(rq); + return 0; } +#endif void __init sched_init_smp(void) { @@ -7179,12 +7265,6 @@ void __init sched_init_smp(void) cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); mutex_unlock(&sched_domains_mutex); - hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE); - hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); - hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); - - init_hrtick(); - /* Move init over to a non-isolated CPU */ if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) BUG(); @@ -7193,7 +7273,16 @@ void __init sched_init_smp(void) init_sched_rt_class(); init_sched_dl_class(); + sched_smp_initialized = true; +} + +static int __init migration_init(void) +{ + sched_rq_cpu_starting(smp_processor_id()); + return 0; } +early_initcall(migration_init); + #else void __init sched_init_smp(void) { @@ -7328,8 +7417,6 @@ void __init sched_init(void) for (j = 0; j < CPU_LOAD_IDX_MAX; j++) rq->cpu_load[j] = 0; - rq->last_load_update_tick = jiffies; - #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; @@ -7348,12 +7435,13 @@ void __init sched_init(void) rq_attach_root(rq, &def_root_domain); #ifdef CONFIG_NO_HZ_COMMON + rq->last_load_update_tick = jiffies; rq->nohz_flags = 0; #endif #ifdef CONFIG_NO_HZ_FULL rq->last_sched_tick = 0; #endif -#endif +#endif /* CONFIG_SMP */ init_rq_hrtick(rq); atomic_set(&rq->nr_iowait, 0); } @@ -7391,7 +7479,7 @@ void __init sched_init(void) if (cpu_isolated_map == NULL) zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); idle_thread_set_boot_cpu(); - set_cpu_rq_start_time(); + set_cpu_rq_start_time(smp_processor_id()); #endif init_sched_fair_class(); @@ -7636,10 +7724,10 @@ void sched_move_task(struct task_struct *tsk) { struct task_group *tg; int queued, running; - unsigned long flags; + struct rq_flags rf; struct rq *rq; - rq = task_rq_lock(tsk, &flags); + rq = task_rq_lock(tsk, &rf); running = task_current(rq, tsk); queued = task_on_rq_queued(tsk); @@ -7671,7 +7759,7 @@ void sched_move_task(struct task_struct *tsk) if (queued) enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE); - task_rq_unlock(rq, tsk, &flags); + task_rq_unlock(rq, tsk, &rf); } #endif /* CONFIG_CGROUP_SCHED */ @@ -7891,7 +7979,7 @@ static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) static int sched_rt_global_constraints(void) { unsigned long flags; - int i, ret = 0; + int i; raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); for_each_possible_cpu(i) { @@ -7903,7 +7991,7 @@ static int sched_rt_global_constraints(void) } raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); - return ret; + return 0; } #endif /* CONFIG_RT_GROUP_SCHED */ diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 4a81120..41f85c4 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -25,11 +25,22 @@ enum cpuacct_stat_index { CPUACCT_STAT_NSTATS, }; +enum cpuacct_usage_index { + CPUACCT_USAGE_USER, /* ... user mode */ + CPUACCT_USAGE_SYSTEM, /* ... kernel mode */ + + CPUACCT_USAGE_NRUSAGE, +}; + +struct cpuacct_usage { + u64 usages[CPUACCT_USAGE_NRUSAGE]; +}; + /* track cpu usage of a group of tasks and its child groups */ struct cpuacct { struct cgroup_subsys_state css; /* cpuusage holds pointer to a u64-type object on every cpu */ - u64 __percpu *cpuusage; + struct cpuacct_usage __percpu *cpuusage; struct kernel_cpustat __percpu *cpustat; }; @@ -49,7 +60,7 @@ static inline struct cpuacct *parent_ca(struct cpuacct *ca) return css_ca(ca->css.parent); } -static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage); +static DEFINE_PER_CPU(struct cpuacct_usage, root_cpuacct_cpuusage); static struct cpuacct root_cpuacct = { .cpustat = &kernel_cpustat, .cpuusage = &root_cpuacct_cpuusage, @@ -68,7 +79,7 @@ cpuacct_css_alloc(struct cgroup_subsys_state *parent_css) if (!ca) goto out; - ca->cpuusage = alloc_percpu(u64); + ca->cpuusage = alloc_percpu(struct cpuacct_usage); if (!ca->cpuusage) goto out_free_ca; @@ -96,20 +107,37 @@ static void cpuacct_css_free(struct cgroup_subsys_state *css) kfree(ca); } -static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) +static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu, + enum cpuacct_usage_index index) { - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + struct cpuacct_usage *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); u64 data; + /* + * We allow index == CPUACCT_USAGE_NRUSAGE here to read + * the sum of suages. + */ + BUG_ON(index > CPUACCT_USAGE_NRUSAGE); + #ifndef CONFIG_64BIT /* * Take rq->lock to make 64-bit read safe on 32-bit platforms. */ raw_spin_lock_irq(&cpu_rq(cpu)->lock); - data = *cpuusage; +#endif + + if (index == CPUACCT_USAGE_NRUSAGE) { + int i = 0; + + data = 0; + for (i = 0; i < CPUACCT_USAGE_NRUSAGE; i++) + data += cpuusage->usages[i]; + } else { + data = cpuusage->usages[index]; + } + +#ifndef CONFIG_64BIT raw_spin_unlock_irq(&cpu_rq(cpu)->lock); -#else - data = *cpuusage; #endif return data; @@ -117,69 +145,103 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) { - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + struct cpuacct_usage *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + int i; #ifndef CONFIG_64BIT /* * Take rq->lock to make 64-bit write safe on 32-bit platforms. */ raw_spin_lock_irq(&cpu_rq(cpu)->lock); - *cpuusage = val; +#endif + + for (i = 0; i < CPUACCT_USAGE_NRUSAGE; i++) + cpuusage->usages[i] = val; + +#ifndef CONFIG_64BIT raw_spin_unlock_irq(&cpu_rq(cpu)->lock); -#else - *cpuusage = val; #endif } /* return total cpu usage (in nanoseconds) of a group */ -static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft) +static u64 __cpuusage_read(struct cgroup_subsys_state *css, + enum cpuacct_usage_index index) { struct cpuacct *ca = css_ca(css); u64 totalcpuusage = 0; int i; - for_each_present_cpu(i) - totalcpuusage += cpuacct_cpuusage_read(ca, i); + for_each_possible_cpu(i) + totalcpuusage += cpuacct_cpuusage_read(ca, i, index); return totalcpuusage; } +static u64 cpuusage_user_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return __cpuusage_read(css, CPUACCT_USAGE_USER); +} + +static u64 cpuusage_sys_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return __cpuusage_read(css, CPUACCT_USAGE_SYSTEM); +} + +static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return __cpuusage_read(css, CPUACCT_USAGE_NRUSAGE); +} + static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { struct cpuacct *ca = css_ca(css); - int err = 0; - int i; + int cpu; /* * Only allow '0' here to do a reset. */ - if (val) { - err = -EINVAL; - goto out; - } + if (val) + return -EINVAL; - for_each_present_cpu(i) - cpuacct_cpuusage_write(ca, i, 0); + for_each_possible_cpu(cpu) + cpuacct_cpuusage_write(ca, cpu, 0); -out: - return err; + return 0; } -static int cpuacct_percpu_seq_show(struct seq_file *m, void *V) +static int __cpuacct_percpu_seq_show(struct seq_file *m, + enum cpuacct_usage_index index) { struct cpuacct *ca = css_ca(seq_css(m)); u64 percpu; int i; - for_each_present_cpu(i) { - percpu = cpuacct_cpuusage_read(ca, i); + for_each_possible_cpu(i) { + percpu = cpuacct_cpuusage_read(ca, i, index); seq_printf(m, "%llu ", (unsigned long long) percpu); } seq_printf(m, "\n"); return 0; } +static int cpuacct_percpu_user_seq_show(struct seq_file *m, void *V) +{ + return __cpuacct_percpu_seq_show(m, CPUACCT_USAGE_USER); +} + +static int cpuacct_percpu_sys_seq_show(struct seq_file *m, void *V) +{ + return __cpuacct_percpu_seq_show(m, CPUACCT_USAGE_SYSTEM); +} + +static int cpuacct_percpu_seq_show(struct seq_file *m, void *V) +{ + return __cpuacct_percpu_seq_show(m, CPUACCT_USAGE_NRUSAGE); +} + static const char * const cpuacct_stat_desc[] = { [CPUACCT_STAT_USER] = "user", [CPUACCT_STAT_SYSTEM] = "system", @@ -191,7 +253,7 @@ static int cpuacct_stats_show(struct seq_file *sf, void *v) int cpu; s64 val = 0; - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); val += kcpustat->cpustat[CPUTIME_USER]; val += kcpustat->cpustat[CPUTIME_NICE]; @@ -200,7 +262,7 @@ static int cpuacct_stats_show(struct seq_file *sf, void *v) seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val); val = 0; - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); val += kcpustat->cpustat[CPUTIME_SYSTEM]; val += kcpustat->cpustat[CPUTIME_IRQ]; @@ -220,10 +282,26 @@ static struct cftype files[] = { .write_u64 = cpuusage_write, }, { + .name = "usage_user", + .read_u64 = cpuusage_user_read, + }, + { + .name = "usage_sys", + .read_u64 = cpuusage_sys_read, + }, + { .name = "usage_percpu", .seq_show = cpuacct_percpu_seq_show, }, { + .name = "usage_percpu_user", + .seq_show = cpuacct_percpu_user_seq_show, + }, + { + .name = "usage_percpu_sys", + .seq_show = cpuacct_percpu_sys_seq_show, + }, + { .name = "stat", .seq_show = cpuacct_stats_show, }, @@ -238,10 +316,17 @@ static struct cftype files[] = { void cpuacct_charge(struct task_struct *tsk, u64 cputime) { struct cpuacct *ca; + int index = CPUACCT_USAGE_SYSTEM; + struct pt_regs *regs = task_pt_regs(tsk); + + if (regs && user_mode(regs)) + index = CPUACCT_USAGE_USER; rcu_read_lock(); + for (ca = task_ca(tsk); ca; ca = parent_ca(ca)) - *this_cpu_ptr(ca->cpuusage) += cputime; + this_cpu_ptr(ca->cpuusage)->usages[index] += cputime; + rcu_read_unlock(); } diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 5a75b08..5be5882 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -103,10 +103,10 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, const struct sched_dl_entity *dl_se = &p->dl; if (later_mask && - cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { + cpumask_and(later_mask, cp->free_cpus, tsk_cpus_allowed(p))) { best_cpu = cpumask_any(later_mask); goto out; - } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) && + } else if (cpumask_test_cpu(cpudl_maximum(cp), tsk_cpus_allowed(p)) && dl_time_before(dl_se->deadline, cp->elements[0].dl)) { best_cpu = cpudl_maximum(cp); if (later_mask) diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 981fcd7..11e9705 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -103,11 +103,11 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, if (skip) continue; - if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) + if (cpumask_any_and(tsk_cpus_allowed(p), vec->mask) >= nr_cpu_ids) continue; if (lowest_mask) { - cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); + cpumask_and(lowest_mask, tsk_cpus_allowed(p), vec->mask); /* * We have to ensure that we have at least one bit diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index affd97e..fcb7f02 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -134,7 +134,7 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { struct task_struct *p = dl_task_of(dl_se); - if (p->nr_cpus_allowed > 1) + if (tsk_nr_cpus_allowed(p) > 1) dl_rq->dl_nr_migratory++; update_dl_migration(dl_rq); @@ -144,7 +144,7 @@ static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { struct task_struct *p = dl_task_of(dl_se); - if (p->nr_cpus_allowed > 1) + if (tsk_nr_cpus_allowed(p) > 1) dl_rq->dl_nr_migratory--; update_dl_migration(dl_rq); @@ -591,10 +591,10 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) struct sched_dl_entity, dl_timer); struct task_struct *p = dl_task_of(dl_se); - unsigned long flags; + struct rq_flags rf; struct rq *rq; - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); /* * The task might have changed its scheduling policy to something @@ -670,14 +670,14 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * Nothing relies on rq->lock after this, so its safe to drop * rq->lock. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, rf.cookie); push_dl_task(rq); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, rf.cookie); } #endif unlock: - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); /* * This can free the task_struct, including this hrtimer, do not touch @@ -717,10 +717,6 @@ static void update_curr_dl(struct rq *rq) if (!dl_task(curr) || !on_dl_rq(dl_se)) return; - /* Kick cpufreq (see the comment in linux/cpufreq.h). */ - if (cpu_of(rq) == smp_processor_id()) - cpufreq_trigger_update(rq_clock(rq)); - /* * Consumed budget is computed considering the time as * observed by schedulable tasks (excluding time spent @@ -736,6 +732,10 @@ static void update_curr_dl(struct rq *rq) return; } + /* kick cpufreq (see the comment in linux/cpufreq.h). */ + if (cpu_of(rq) == smp_processor_id()) + cpufreq_trigger_update(rq_clock(rq)); + schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); @@ -966,7 +966,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) enqueue_dl_entity(&p->dl, pi_se, flags); - if (!task_current(rq, p) && p->nr_cpus_allowed > 1) + if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1) enqueue_pushable_dl_task(rq, p); } @@ -1040,9 +1040,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags) * try to make it stay here, it might be important. */ if (unlikely(dl_task(curr)) && - (curr->nr_cpus_allowed < 2 || + (tsk_nr_cpus_allowed(curr) < 2 || !dl_entity_preempt(&p->dl, &curr->dl)) && - (p->nr_cpus_allowed > 1)) { + (tsk_nr_cpus_allowed(p) > 1)) { int target = find_later_rq(p); if (target != -1 && @@ -1063,7 +1063,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) * Current can't be migrated, useless to reschedule, * let's hope p can move out. */ - if (rq->curr->nr_cpus_allowed == 1 || + if (tsk_nr_cpus_allowed(rq->curr) == 1 || cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1) return; @@ -1071,7 +1071,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) * p is migratable, so let's not schedule it and * see if it is pushed or pulled somewhere else. */ - if (p->nr_cpus_allowed != 1 && + if (tsk_nr_cpus_allowed(p) != 1 && cpudl_find(&rq->rd->cpudl, p, NULL) != -1) return; @@ -1125,7 +1125,8 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, return rb_entry(left, struct sched_dl_entity, rb_node); } -struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev) +struct task_struct * +pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) { struct sched_dl_entity *dl_se; struct task_struct *p; @@ -1140,9 +1141,9 @@ struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev) * disabled avoiding further scheduler activity on it and we're * being very careful to re-start the picking loop. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); pull_dl_task(rq); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, cookie); /* * pull_rt_task() can drop (and re-acquire) rq->lock; this * means a stop task can slip in, in which case we need to @@ -1185,7 +1186,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p) { update_curr_dl(rq); - if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) + if (on_dl_rq(&p->dl) && tsk_nr_cpus_allowed(p) > 1) enqueue_pushable_dl_task(rq, p); } @@ -1286,7 +1287,7 @@ static int find_later_rq(struct task_struct *task) if (unlikely(!later_mask)) return -1; - if (task->nr_cpus_allowed == 1) + if (tsk_nr_cpus_allowed(task) == 1) return -1; /* @@ -1392,8 +1393,9 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) if (double_lock_balance(rq, later_rq)) { if (unlikely(task_rq(task) != rq || !cpumask_test_cpu(later_rq->cpu, - &task->cpus_allowed) || + tsk_cpus_allowed(task)) || task_running(rq, task) || + !dl_task(task) || !task_on_rq_queued(task))) { double_unlock_balance(rq, later_rq); later_rq = NULL; @@ -1431,7 +1433,7 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq) BUG_ON(rq->cpu != task_cpu(p)); BUG_ON(task_current(rq, p)); - BUG_ON(p->nr_cpus_allowed <= 1); + BUG_ON(tsk_nr_cpus_allowed(p) <= 1); BUG_ON(!task_on_rq_queued(p)); BUG_ON(!dl_task(p)); @@ -1470,7 +1472,7 @@ retry: */ if (dl_task(rq->curr) && dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) && - rq->curr->nr_cpus_allowed > 1) { + tsk_nr_cpus_allowed(rq->curr) > 1) { resched_curr(rq); return 0; } @@ -1617,9 +1619,9 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p) { if (!task_running(rq, p) && !test_tsk_need_resched(rq->curr) && - p->nr_cpus_allowed > 1 && + tsk_nr_cpus_allowed(p) > 1 && dl_task(rq->curr) && - (rq->curr->nr_cpus_allowed < 2 || + (tsk_nr_cpus_allowed(rq->curr) < 2 || !dl_entity_preempt(&p->dl, &rq->curr->dl))) { push_dl_tasks(rq); } @@ -1723,7 +1725,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP - if (p->nr_cpus_allowed > 1 && rq->dl.overloaded) + if (tsk_nr_cpus_allowed(p) > 1 && rq->dl.overloaded) queue_push_tasks(rq); #else if (dl_task(rq->curr)) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 4fbc3bd..cf905f6 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -626,15 +626,16 @@ do { \ #undef P #undef PN -#ifdef CONFIG_SCHEDSTATS -#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); -#define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n); - #ifdef CONFIG_SMP +#define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n); P64(avg_idle); P64(max_idle_balance_cost); +#undef P64 #endif +#ifdef CONFIG_SCHEDSTATS +#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); + if (schedstat_enabled()) { P(yld_count); P(sched_count); @@ -644,7 +645,6 @@ do { \ } #undef P -#undef P64 #endif spin_lock_irqsave(&sched_debug_lock, flags); print_cfs_stats(m, cpu); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 0fe30e6..218f8e8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -204,7 +204,7 @@ static void __update_inv_weight(struct load_weight *lw) * OR * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT * - * Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case + * Either weight := NICE_0_LOAD and lw \e sched_prio_to_wmult[], in which case * we're guaranteed shift stays positive because inv_weight is guaranteed to * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22. * @@ -682,17 +682,68 @@ void init_entity_runnable_average(struct sched_entity *se) sa->period_contrib = 1023; sa->load_avg = scale_load_down(se->load.weight); sa->load_sum = sa->load_avg * LOAD_AVG_MAX; - sa->util_avg = scale_load_down(SCHED_LOAD_SCALE); - sa->util_sum = sa->util_avg * LOAD_AVG_MAX; + /* + * At this point, util_avg won't be used in select_task_rq_fair anyway + */ + sa->util_avg = 0; + sa->util_sum = 0; /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */ } +/* + * With new tasks being created, their initial util_avgs are extrapolated + * based on the cfs_rq's current util_avg: + * + * util_avg = cfs_rq->util_avg / (cfs_rq->load_avg + 1) * se.load.weight + * + * However, in many cases, the above util_avg does not give a desired + * value. Moreover, the sum of the util_avgs may be divergent, such + * as when the series is a harmonic series. + * + * To solve this problem, we also cap the util_avg of successive tasks to + * only 1/2 of the left utilization budget: + * + * util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n + * + * where n denotes the nth task. + * + * For example, a simplest series from the beginning would be like: + * + * task util_avg: 512, 256, 128, 64, 32, 16, 8, ... + * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ... + * + * Finally, that extrapolated util_avg is clamped to the cap (util_avg_cap) + * if util_avg > util_avg_cap. + */ +void post_init_entity_util_avg(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq = cfs_rq_of(se); + struct sched_avg *sa = &se->avg; + long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2; + + if (cap > 0) { + if (cfs_rq->avg.util_avg != 0) { + sa->util_avg = cfs_rq->avg.util_avg * se->load.weight; + sa->util_avg /= (cfs_rq->avg.load_avg + 1); + + if (sa->util_avg > cap) + sa->util_avg = cap; + } else { + sa->util_avg = cap; + } + sa->util_sum = sa->util_avg * LOAD_AVG_MAX; + } +} + static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq); static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq); #else void init_entity_runnable_average(struct sched_entity *se) { } +void post_init_entity_util_avg(struct sched_entity *se) +{ +} #endif /* @@ -2437,10 +2488,12 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) update_load_sub(&cfs_rq->load, se->load.weight); if (!parent_entity(se)) update_load_sub(&rq_of(cfs_rq)->load, se->load.weight); +#ifdef CONFIG_SMP if (entity_is_task(se)) { account_numa_dequeue(rq_of(cfs_rq), task_of(se)); list_del_init(&se->group_node); } +#endif cfs_rq->nr_running--; } @@ -2550,6 +2603,16 @@ static const u32 runnable_avg_yN_sum[] = { }; /* + * Precomputed \Sum y^k { 1<=k<=n, where n%32=0). Values are rolled down to + * lower integers. See Documentation/scheduler/sched-avg.txt how these + * were generated: + */ +static const u32 __accumulated_sum_N32[] = { + 0, 23371, 35056, 40899, 43820, 45281, + 46011, 46376, 46559, 46650, 46696, 46719, +}; + +/* * Approximate: * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) */ @@ -2597,22 +2660,13 @@ static u32 __compute_runnable_contrib(u64 n) else if (unlikely(n >= LOAD_AVG_MAX_N)) return LOAD_AVG_MAX; - /* Compute \Sum k^n combining precomputed values for k^i, \Sum k^j */ - do { - contrib /= 2; /* y^LOAD_AVG_PERIOD = 1/2 */ - contrib += runnable_avg_yN_sum[LOAD_AVG_PERIOD]; - - n -= LOAD_AVG_PERIOD; - } while (n > LOAD_AVG_PERIOD); - + /* Since n < LOAD_AVG_MAX_N, n/LOAD_AVG_PERIOD < 11 */ + contrib = __accumulated_sum_N32[n/LOAD_AVG_PERIOD]; + n %= LOAD_AVG_PERIOD; contrib = decay_load(contrib, n); return contrib + runnable_avg_yN_sum[n]; } -#if (SCHED_LOAD_SHIFT - SCHED_LOAD_RESOLUTION) != 10 || SCHED_CAPACITY_SHIFT != 10 -#error "load tracking assumes 2^10 as unit" -#endif - #define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT) /* @@ -2821,23 +2875,54 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {} static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); +static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + int cpu = cpu_of(rq); + + if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) { + unsigned long max = rq->cpu_capacity_orig; + + /* + * There are a few boundary cases this might miss but it should + * get called often enough that that should (hopefully) not be + * a real problem -- added to that it only calls on the local + * CPU, so if we enqueue remotely we'll miss an update, but + * the next tick/schedule should update. + * + * It will not get called when we go idle, because the idle + * thread is a different class (!fair), nor will the utilization + * number include things like RT tasks. + * + * As is, the util number is not freq-invariant (we'd have to + * implement arch_scale_freq_capacity() for that). + * + * See cpu_util(). + */ + cpufreq_update_util(rq_clock(rq), + min(cfs_rq->avg.util_avg, max), max); + } +} + /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */ -static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) +static inline int +update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) { struct sched_avg *sa = &cfs_rq->avg; - int decayed, removed = 0; + int decayed, removed_load = 0, removed_util = 0; if (atomic_long_read(&cfs_rq->removed_load_avg)) { s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); sa->load_avg = max_t(long, sa->load_avg - r, 0); sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0); - removed = 1; + removed_load = 1; } if (atomic_long_read(&cfs_rq->removed_util_avg)) { long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0); sa->util_avg = max_t(long, sa->util_avg - r, 0); sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0); + removed_util = 1; } decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa, @@ -2848,7 +2933,10 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) cfs_rq->load_last_update_time_copy = sa->last_update_time; #endif - return decayed || removed; + if (update_freq && (decayed || removed_util)) + cfs_rq_util_change(cfs_rq); + + return decayed || removed_load; } /* Update task and its cfs_rq load average */ @@ -2867,31 +2955,8 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg) se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL); - if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg) + if (update_cfs_rq_load_avg(now, cfs_rq, true) && update_tg) update_tg_load_avg(cfs_rq, 0); - - if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) { - unsigned long max = rq->cpu_capacity_orig; - - /* - * There are a few boundary cases this might miss but it should - * get called often enough that that should (hopefully) not be - * a real problem -- added to that it only calls on the local - * CPU, so if we enqueue remotely we'll miss an update, but - * the next tick/schedule should update. - * - * It will not get called when we go idle, because the idle - * thread is a different class (!fair), nor will the utilization - * number include things like RT tasks. - * - * As is, the util number is not freq-invariant (we'd have to - * implement arch_scale_freq_capacity() for that). - * - * See cpu_util(). - */ - cpufreq_update_util(rq_clock(rq), - min(cfs_rq->avg.util_avg, max), max); - } } static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -2919,6 +2984,8 @@ skip_aging: cfs_rq->avg.load_sum += se->avg.load_sum; cfs_rq->avg.util_avg += se->avg.util_avg; cfs_rq->avg.util_sum += se->avg.util_sum; + + cfs_rq_util_change(cfs_rq); } static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -2931,6 +2998,8 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0); cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0); cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0); + + cfs_rq_util_change(cfs_rq); } /* Add the load generated by se into cfs_rq's load average */ @@ -2948,7 +3017,7 @@ enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) cfs_rq->curr == se, NULL); } - decayed = update_cfs_rq_load_avg(now, cfs_rq); + decayed = update_cfs_rq_load_avg(now, cfs_rq, !migrated); cfs_rq->runnable_load_avg += sa->load_avg; cfs_rq->runnable_load_sum += sa->load_sum; @@ -3030,7 +3099,14 @@ static int idle_balance(struct rq *this_rq); #else /* CONFIG_SMP */ -static inline void update_load_avg(struct sched_entity *se, int update_tg) {} +static inline void update_load_avg(struct sched_entity *se, int not_used) +{ + struct cfs_rq *cfs_rq = cfs_rq_of(se); + struct rq *rq = rq_of(cfs_rq); + + cpufreq_trigger_update(rq_clock(rq)); +} + static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} static inline void @@ -3178,10 +3254,41 @@ static inline void check_schedstat_required(void) #endif } + +/* + * MIGRATION + * + * dequeue + * update_curr() + * update_min_vruntime() + * vruntime -= min_vruntime + * + * enqueue + * update_curr() + * update_min_vruntime() + * vruntime += min_vruntime + * + * this way the vruntime transition between RQs is done when both + * min_vruntime are up-to-date. + * + * WAKEUP (remote) + * + * ->migrate_task_rq_fair() (p->state == TASK_WAKING) + * vruntime -= min_vruntime + * + * enqueue + * update_curr() + * update_min_vruntime() + * vruntime += min_vruntime + * + * this way we don't have the most up-to-date min_vruntime on the originating + * CPU and an up-to-date min_vruntime on the destination CPU. + */ + static void enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { - bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING); + bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATED); bool curr = cfs_rq->curr == se; /* @@ -3195,7 +3302,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) /* * Otherwise, renormalise after, such that we're placed at the current - * moment in time, instead of some random moment in the past. + * moment in time, instead of some random moment in the past. Being + * placed in the past could significantly boost this task to the + * fairness detriment of existing tasks. */ if (renorm && !curr) se->vruntime += cfs_rq->min_vruntime; @@ -4423,7 +4532,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) } #ifdef CONFIG_SMP - +#ifdef CONFIG_NO_HZ_COMMON /* * per rq 'load' arrray crap; XXX kill this. */ @@ -4489,13 +4598,13 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) } return load; } +#endif /* CONFIG_NO_HZ_COMMON */ /** - * __update_cpu_load - update the rq->cpu_load[] statistics + * __cpu_load_update - update the rq->cpu_load[] statistics * @this_rq: The rq to update statistics for * @this_load: The current load * @pending_updates: The number of missed updates - * @active: !0 for NOHZ_FULL * * Update rq->cpu_load[] statistics. This function is usually called every * scheduler tick (TICK_NSEC). @@ -4524,12 +4633,12 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) * load[i]_n = (1 - 1/2^i)^n * load[i]_0 * * see decay_load_misses(). For NOHZ_FULL we get to subtract and add the extra - * term. See the @active paramter. + * term. */ -static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, - unsigned long pending_updates, int active) +static void cpu_load_update(struct rq *this_rq, unsigned long this_load, + unsigned long pending_updates) { - unsigned long tickless_load = active ? this_rq->cpu_load[0] : 0; + unsigned long __maybe_unused tickless_load = this_rq->cpu_load[0]; int i, scale; this_rq->nr_load_updates++; @@ -4542,6 +4651,7 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, /* scale is effectively 1 << i now, and >> i divides by scale */ old_load = this_rq->cpu_load[i]; +#ifdef CONFIG_NO_HZ_COMMON old_load = decay_load_missed(old_load, pending_updates - 1, i); if (tickless_load) { old_load -= decay_load_missed(tickless_load, pending_updates - 1, i); @@ -4552,6 +4662,7 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, */ old_load += tickless_load; } +#endif new_load = this_load; /* * Round up the averaging division if load is increasing. This @@ -4574,10 +4685,23 @@ static unsigned long weighted_cpuload(const int cpu) } #ifdef CONFIG_NO_HZ_COMMON -static void __update_cpu_load_nohz(struct rq *this_rq, - unsigned long curr_jiffies, - unsigned long load, - int active) +/* + * There is no sane way to deal with nohz on smp when using jiffies because the + * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading + * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}. + * + * Therefore we need to avoid the delta approach from the regular tick when + * possible since that would seriously skew the load calculation. This is why we + * use cpu_load_update_periodic() for CPUs out of nohz. However we'll rely on + * jiffies deltas for updates happening while in nohz mode (idle ticks, idle + * loop exit, nohz_idle_balance, nohz full exit...) + * + * This means we might still be one tick off for nohz periods. + */ + +static void cpu_load_update_nohz(struct rq *this_rq, + unsigned long curr_jiffies, + unsigned long load) { unsigned long pending_updates; @@ -4589,28 +4713,15 @@ static void __update_cpu_load_nohz(struct rq *this_rq, * In the NOHZ_FULL case, we were non-idle, we should consider * its weighted load. */ - __update_cpu_load(this_rq, load, pending_updates, active); + cpu_load_update(this_rq, load, pending_updates); } } /* - * There is no sane way to deal with nohz on smp when using jiffies because the - * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading - * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}. - * - * Therefore we cannot use the delta approach from the regular tick since that - * would seriously skew the load calculation. However we'll make do for those - * updates happening while idle (nohz_idle_balance) or coming out of idle - * (tick_nohz_idle_exit). - * - * This means we might still be one tick off for nohz periods. - */ - -/* * Called from nohz_idle_balance() to update the load ratings before doing the * idle balance. */ -static void update_cpu_load_idle(struct rq *this_rq) +static void cpu_load_update_idle(struct rq *this_rq) { /* * bail if there's load or we're actually up-to-date. @@ -4618,38 +4729,71 @@ static void update_cpu_load_idle(struct rq *this_rq) if (weighted_cpuload(cpu_of(this_rq))) return; - __update_cpu_load_nohz(this_rq, READ_ONCE(jiffies), 0, 0); + cpu_load_update_nohz(this_rq, READ_ONCE(jiffies), 0); } /* - * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed. + * Record CPU load on nohz entry so we know the tickless load to account + * on nohz exit. cpu_load[0] happens then to be updated more frequently + * than other cpu_load[idx] but it should be fine as cpu_load readers + * shouldn't rely into synchronized cpu_load[*] updates. */ -void update_cpu_load_nohz(int active) +void cpu_load_update_nohz_start(void) { struct rq *this_rq = this_rq(); + + /* + * This is all lockless but should be fine. If weighted_cpuload changes + * concurrently we'll exit nohz. And cpu_load write can race with + * cpu_load_update_idle() but both updater would be writing the same. + */ + this_rq->cpu_load[0] = weighted_cpuload(cpu_of(this_rq)); +} + +/* + * Account the tickless load in the end of a nohz frame. + */ +void cpu_load_update_nohz_stop(void) +{ unsigned long curr_jiffies = READ_ONCE(jiffies); - unsigned long load = active ? weighted_cpuload(cpu_of(this_rq)) : 0; + struct rq *this_rq = this_rq(); + unsigned long load; if (curr_jiffies == this_rq->last_load_update_tick) return; + load = weighted_cpuload(cpu_of(this_rq)); raw_spin_lock(&this_rq->lock); - __update_cpu_load_nohz(this_rq, curr_jiffies, load, active); + update_rq_clock(this_rq); + cpu_load_update_nohz(this_rq, curr_jiffies, load); raw_spin_unlock(&this_rq->lock); } -#endif /* CONFIG_NO_HZ */ +#else /* !CONFIG_NO_HZ_COMMON */ +static inline void cpu_load_update_nohz(struct rq *this_rq, + unsigned long curr_jiffies, + unsigned long load) { } +#endif /* CONFIG_NO_HZ_COMMON */ + +static void cpu_load_update_periodic(struct rq *this_rq, unsigned long load) +{ +#ifdef CONFIG_NO_HZ_COMMON + /* See the mess around cpu_load_update_nohz(). */ + this_rq->last_load_update_tick = READ_ONCE(jiffies); +#endif + cpu_load_update(this_rq, load, 1); +} /* * Called from scheduler_tick() */ -void update_cpu_load_active(struct rq *this_rq) +void cpu_load_update_active(struct rq *this_rq) { unsigned long load = weighted_cpuload(cpu_of(this_rq)); - /* - * See the mess around update_cpu_load_idle() / update_cpu_load_nohz(). - */ - this_rq->last_load_update_tick = jiffies; - __update_cpu_load(this_rq, load, 1, 1); + + if (tick_nohz_tick_stopped()) + cpu_load_update_nohz(this_rq, READ_ONCE(jiffies), load); + else + cpu_load_update_periodic(this_rq, load); } /* @@ -4707,46 +4851,6 @@ static unsigned long cpu_avg_load_per_task(int cpu) return 0; } -static void record_wakee(struct task_struct *p) -{ - /* - * Rough decay (wiping) for cost saving, don't worry - * about the boundary, really active task won't care - * about the loss. - */ - if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) { - current->wakee_flips >>= 1; - current->wakee_flip_decay_ts = jiffies; - } - - if (current->last_wakee != p) { - current->last_wakee = p; - current->wakee_flips++; - } -} - -static void task_waking_fair(struct task_struct *p) -{ - struct sched_entity *se = &p->se; - struct cfs_rq *cfs_rq = cfs_rq_of(se); - u64 min_vruntime; - -#ifndef CONFIG_64BIT - u64 min_vruntime_copy; - - do { - min_vruntime_copy = cfs_rq->min_vruntime_copy; - smp_rmb(); - min_vruntime = cfs_rq->min_vruntime; - } while (min_vruntime != min_vruntime_copy); -#else - min_vruntime = cfs_rq->min_vruntime; -#endif - - se->vruntime -= min_vruntime; - record_wakee(p); -} - #ifdef CONFIG_FAIR_GROUP_SCHED /* * effective_load() calculates the load change as seen from the root_task_group @@ -4862,17 +4966,39 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) #endif +static void record_wakee(struct task_struct *p) +{ + /* + * Only decay a single time; tasks that have less then 1 wakeup per + * jiffy will not have built up many flips. + */ + if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) { + current->wakee_flips >>= 1; + current->wakee_flip_decay_ts = jiffies; + } + + if (current->last_wakee != p) { + current->last_wakee = p; + current->wakee_flips++; + } +} + /* * Detect M:N waker/wakee relationships via a switching-frequency heuristic. + * * A waker of many should wake a different task than the one last awakened - * at a frequency roughly N times higher than one of its wakees. In order - * to determine whether we should let the load spread vs consolodating to - * shared cache, we look for a minimum 'flip' frequency of llc_size in one - * partner, and a factor of lls_size higher frequency in the other. With - * both conditions met, we can be relatively sure that the relationship is - * non-monogamous, with partner count exceeding socket size. Waker/wakee - * being client/server, worker/dispatcher, interrupt source or whatever is - * irrelevant, spread criteria is apparent partner count exceeds socket size. + * at a frequency roughly N times higher than one of its wakees. + * + * In order to determine whether we should let the load spread vs consolidating + * to shared cache, we look for a minimum 'flip' frequency of llc_size in one + * partner, and a factor of lls_size higher frequency in the other. + * + * With both conditions met, we can be relatively sure that the relationship is + * non-monogamous, with partner count exceeding socket size. + * + * Waker/wakee being client/server, worker/dispatcher, interrupt source or + * whatever is irrelevant, spread criteria is apparent partner count exceeds + * socket size. */ static int wake_wide(struct task_struct *p) { @@ -5177,8 +5303,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f int want_affine = 0; int sync = wake_flags & WF_SYNC; - if (sd_flag & SD_BALANCE_WAKE) + if (sd_flag & SD_BALANCE_WAKE) { + record_wakee(p); want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p)); + } rcu_read_lock(); for_each_domain(cpu, tmp) { @@ -5258,6 +5386,32 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f static void migrate_task_rq_fair(struct task_struct *p) { /* + * As blocked tasks retain absolute vruntime the migration needs to + * deal with this by subtracting the old and adding the new + * min_vruntime -- the latter is done by enqueue_entity() when placing + * the task on the new runqueue. + */ + if (p->state == TASK_WAKING) { + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 min_vruntime; + +#ifndef CONFIG_64BIT + u64 min_vruntime_copy; + + do { + min_vruntime_copy = cfs_rq->min_vruntime_copy; + smp_rmb(); + min_vruntime = cfs_rq->min_vruntime; + } while (min_vruntime != min_vruntime_copy); +#else + min_vruntime = cfs_rq->min_vruntime; +#endif + + se->vruntime -= min_vruntime; + } + + /* * We are supposed to update the task to "current" time, then its up to date * and ready to go to new CPU/cfs_rq. But we have difficulty in getting * what current time is, so simply throw away the out-of-date time. This @@ -5440,7 +5594,7 @@ preempt: } static struct task_struct * -pick_next_task_fair(struct rq *rq, struct task_struct *prev) +pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) { struct cfs_rq *cfs_rq = &rq->cfs; struct sched_entity *se; @@ -5553,9 +5707,9 @@ idle: * further scheduler activity on it and we're being very careful to * re-start the picking loop. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); new_tasks = idle_balance(rq); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, cookie); /* * Because idle_balance() releases (and re-acquires) rq->lock, it is * possible for any higher priority task to appear. In that case we @@ -5654,7 +5808,7 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp * W_i,0 = \Sum_j w_i,j (2) * * Where w_i,j is the weight of the j-th runnable task on cpu i. This weight - * is derived from the nice value as per prio_to_weight[]. + * is derived from the nice value as per sched_prio_to_weight[]. * * The weight average is an exponential decay average of the instantaneous * weight: @@ -6156,7 +6310,7 @@ static void update_blocked_averages(int cpu) if (throttled_hierarchy(cfs_rq)) continue; - if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq)) + if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true)) update_tg_load_avg(cfs_rq, 0); } raw_spin_unlock_irqrestore(&rq->lock, flags); @@ -6217,7 +6371,7 @@ static inline void update_blocked_averages(int cpu) raw_spin_lock_irqsave(&rq->lock, flags); update_rq_clock(rq); - update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); + update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true); raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -6626,6 +6780,9 @@ static bool update_sd_pick_busiest(struct lb_env *env, if (!(env->sd->flags & SD_ASYM_PACKING)) return true; + /* No ASYM_PACKING if target cpu is already busy */ + if (env->idle == CPU_NOT_IDLE) + return true; /* * ASYM_PACKING needs to move all the work to the lowest * numbered CPUs in the group, therefore mark all groups @@ -6635,7 +6792,8 @@ static bool update_sd_pick_busiest(struct lb_env *env, if (!sds->busiest) return true; - if (group_first_cpu(sds->busiest) > group_first_cpu(sg)) + /* Prefer to move from highest possible cpu's work */ + if (group_first_cpu(sds->busiest) < group_first_cpu(sg)) return true; } @@ -6781,6 +6939,9 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) if (!(env->sd->flags & SD_ASYM_PACKING)) return 0; + if (env->idle == CPU_NOT_IDLE) + return 0; + if (!sds->busiest) return 0; @@ -6889,9 +7050,10 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s } /* - * In the presence of smp nice balancing, certain scenarios can have - * max load less than avg load(as we skip the groups at or below - * its cpu_capacity, while calculating max_load..) + * Avg load of busiest sg can be less and avg load of local sg can + * be greater than avg load across all sgs of sd because avg load + * factors in sg capacity and sgs with smaller group_type are + * skipped when updating the busiest sg: */ if (busiest->avg_load <= sds->avg_load || local->avg_load >= sds->avg_load) { @@ -6904,11 +7066,12 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s */ if (busiest->group_type == group_overloaded && local->group_type == group_overloaded) { - load_above_capacity = busiest->sum_nr_running * - SCHED_LOAD_SCALE; - if (load_above_capacity > busiest->group_capacity) + load_above_capacity = busiest->sum_nr_running * SCHED_CAPACITY_SCALE; + if (load_above_capacity > busiest->group_capacity) { load_above_capacity -= busiest->group_capacity; - else + load_above_capacity *= NICE_0_LOAD; + load_above_capacity /= busiest->group_capacity; + } else load_above_capacity = ~0UL; } @@ -6916,9 +7079,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * We're trying to get all the cpus to the average_load, so we don't * want to push ourselves above the average load, nor do we wish to * reduce the max loaded cpu below the average load. At the same time, - * we also don't want to reduce the group load below the group capacity - * (so that we can implement power-savings policies etc). Thus we look - * for the minimum possible imbalance. + * we also don't want to reduce the group load below the group + * capacity. Thus we look for the minimum possible imbalance. */ max_pull = min(busiest->avg_load - sds->avg_load, load_above_capacity); @@ -6942,10 +7104,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /** * find_busiest_group - Returns the busiest group within the sched_domain - * if there is an imbalance. If there isn't an imbalance, and - * the user has opted for power-savings, it returns a group whose - * CPUs can be put to idle by rebalancing those tasks elsewhere, if - * such a group exists. + * if there is an imbalance. * * Also calculates the amount of weighted load which should be moved * to restore balance. @@ -6953,9 +7112,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * @env: The load balancing environment. * * Return: - The busiest group if imbalance exists. - * - If no imbalance and user has opted for power-savings balance, - * return the least loaded group whose CPUs can be - * put to idle by rebalancing its tasks onto our group. */ static struct sched_group *find_busiest_group(struct lb_env *env) { @@ -6973,8 +7129,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) busiest = &sds.busiest_stat; /* ASYM feature bypasses nice load balance check */ - if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) && - check_asym_packing(env, &sds)) + if (check_asym_packing(env, &sds)) return sds.busiest; /* There is no busy sibling group to pull tasks from */ @@ -7399,10 +7554,7 @@ more_balance: &busiest->active_balance_work); } - /* - * We've kicked active balancing, reset the failure - * counter. - */ + /* We've kicked active balancing, force task migration. */ sd->nr_balance_failed = sd->cache_nice_tries+1; } } else @@ -7637,10 +7789,13 @@ static int active_load_balance_cpu_stop(void *data) schedstat_inc(sd, alb_count); p = detach_one_task(&env); - if (p) + if (p) { schedstat_inc(sd, alb_pushed); - else + /* Active balancing done, reset the failure counter. */ + sd->nr_balance_failed = 0; + } else { schedstat_inc(sd, alb_failed); + } } rcu_read_unlock(); out_unlock: @@ -7711,7 +7866,7 @@ static void nohz_balancer_kick(void) return; } -static inline void nohz_balance_exit_idle(int cpu) +void nohz_balance_exit_idle(unsigned int cpu) { if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) { /* @@ -7784,18 +7939,6 @@ void nohz_balance_enter_idle(int cpu) atomic_inc(&nohz.nr_cpus); set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); } - -static int sched_ilb_notifier(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DYING: - nohz_balance_exit_idle(smp_processor_id()); - return NOTIFY_OK; - default: - return NOTIFY_DONE; - } -} #endif static DEFINE_SPINLOCK(balancing); @@ -7957,7 +8100,7 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) if (time_after_eq(jiffies, rq->next_balance)) { raw_spin_lock_irq(&rq->lock); update_rq_clock(rq); - update_cpu_load_idle(rq); + cpu_load_update_idle(rq); raw_spin_unlock_irq(&rq->lock); rebalance_domains(rq, CPU_IDLE); } @@ -8382,6 +8525,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) init_cfs_rq(cfs_rq); init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); init_entity_runnable_average(se); + post_init_entity_util_avg(se); } return 1; @@ -8538,7 +8682,6 @@ const struct sched_class fair_sched_class = { .rq_online = rq_online_fair, .rq_offline = rq_offline_fair, - .task_waking = task_waking_fair, .task_dead = task_dead_fair, .set_cpus_allowed = set_cpus_allowed_common, #endif @@ -8600,7 +8743,6 @@ __init void init_sched_fair_class(void) #ifdef CONFIG_NO_HZ_COMMON nohz.next_balance = jiffies; zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); - cpu_notifier(sched_ilb_notifier, 0); #endif #endif /* SMP */ diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index 47ce949..2ce5458 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -24,7 +24,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl } static struct task_struct * -pick_next_task_idle(struct rq *rq, struct task_struct *prev) +pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) { put_prev_task(rq, prev); diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index ef71590..b0b93fd 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -99,10 +99,13 @@ long calc_load_fold_active(struct rq *this_rq) static unsigned long calc_load(unsigned long load, unsigned long exp, unsigned long active) { - load *= exp; - load += active * (FIXED_1 - exp); - load += 1UL << (FSHIFT - 1); - return load >> FSHIFT; + unsigned long newload; + + newload = load * exp + active * (FIXED_1 - exp); + if (active >= load) + newload += FIXED_1-1; + + return newload / FIXED_1; } #ifdef CONFIG_NO_HZ_COMMON diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index c41ea7a..d5690b7 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -334,7 +334,7 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) rt_rq = &rq_of_rt_rq(rt_rq)->rt; rt_rq->rt_nr_total++; - if (p->nr_cpus_allowed > 1) + if (tsk_nr_cpus_allowed(p) > 1) rt_rq->rt_nr_migratory++; update_rt_migration(rt_rq); @@ -351,7 +351,7 @@ static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) rt_rq = &rq_of_rt_rq(rt_rq)->rt; rt_rq->rt_nr_total--; - if (p->nr_cpus_allowed > 1) + if (tsk_nr_cpus_allowed(p) > 1) rt_rq->rt_nr_migratory--; update_rt_migration(rt_rq); @@ -953,14 +953,14 @@ static void update_curr_rt(struct rq *rq) if (curr->sched_class != &rt_sched_class) return; - /* Kick cpufreq (see the comment in linux/cpufreq.h). */ - if (cpu_of(rq) == smp_processor_id()) - cpufreq_trigger_update(rq_clock(rq)); - delta_exec = rq_clock_task(rq) - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) return; + /* Kick cpufreq (see the comment in linux/cpufreq.h). */ + if (cpu_of(rq) == smp_processor_id()) + cpufreq_trigger_update(rq_clock(rq)); + schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); @@ -1324,7 +1324,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) enqueue_rt_entity(rt_se, flags); - if (!task_current(rq, p) && p->nr_cpus_allowed > 1) + if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1) enqueue_pushable_task(rq, p); } @@ -1413,7 +1413,7 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags) * will have to sort it out. */ if (curr && unlikely(rt_task(curr)) && - (curr->nr_cpus_allowed < 2 || + (tsk_nr_cpus_allowed(curr) < 2 || curr->prio <= p->prio)) { int target = find_lowest_rq(p); @@ -1437,7 +1437,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) * Current can't be migrated, useless to reschedule, * let's hope p can move out. */ - if (rq->curr->nr_cpus_allowed == 1 || + if (tsk_nr_cpus_allowed(rq->curr) == 1 || !cpupri_find(&rq->rd->cpupri, rq->curr, NULL)) return; @@ -1445,7 +1445,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) * p is migratable, so let's not schedule it and * see if it is pushed or pulled somewhere else. */ - if (p->nr_cpus_allowed != 1 + if (tsk_nr_cpus_allowed(p) != 1 && cpupri_find(&rq->rd->cpupri, p, NULL)) return; @@ -1524,7 +1524,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) } static struct task_struct * -pick_next_task_rt(struct rq *rq, struct task_struct *prev) +pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) { struct task_struct *p; struct rt_rq *rt_rq = &rq->rt; @@ -1536,9 +1536,9 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev) * disabled avoiding further scheduler activity on it and we're * being very careful to re-start the picking loop. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); pull_rt_task(rq); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, cookie); /* * pull_rt_task() can drop (and re-acquire) rq->lock; this * means a dl or stop task can slip in, in which case we need @@ -1579,7 +1579,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) * The previous task needs to be made eligible for pushing * if it is still active */ - if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1) + if (on_rt_rq(&p->rt) && tsk_nr_cpus_allowed(p) > 1) enqueue_pushable_task(rq, p); } @@ -1629,7 +1629,7 @@ static int find_lowest_rq(struct task_struct *task) if (unlikely(!lowest_mask)) return -1; - if (task->nr_cpus_allowed == 1) + if (tsk_nr_cpus_allowed(task) == 1) return -1; /* No other targets possible */ if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask)) @@ -1729,6 +1729,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) !cpumask_test_cpu(lowest_rq->cpu, tsk_cpus_allowed(task)) || task_running(rq, task) || + !rt_task(task) || !task_on_rq_queued(task))) { double_unlock_balance(rq, lowest_rq); @@ -1761,7 +1762,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq) BUG_ON(rq->cpu != task_cpu(p)); BUG_ON(task_current(rq, p)); - BUG_ON(p->nr_cpus_allowed <= 1); + BUG_ON(tsk_nr_cpus_allowed(p) <= 1); BUG_ON(!task_on_rq_queued(p)); BUG_ON(!rt_task(p)); @@ -2121,9 +2122,9 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p) { if (!task_running(rq, p) && !test_tsk_need_resched(rq->curr) && - p->nr_cpus_allowed > 1 && + tsk_nr_cpus_allowed(p) > 1 && (dl_task(rq->curr) || rt_task(rq->curr)) && - (rq->curr->nr_cpus_allowed < 2 || + (tsk_nr_cpus_allowed(rq->curr) < 2 || rq->curr->prio <= p->prio)) push_rt_tasks(rq); } @@ -2196,7 +2197,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) */ if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP - if (p->nr_cpus_allowed > 1 && rq->rt.overloaded) + if (tsk_nr_cpus_allowed(p) > 1 && rq->rt.overloaded) queue_push_tasks(rq); #else if (p->prio < rq->curr->prio) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index ec2e8d2..e51145e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -31,9 +31,9 @@ extern void calc_global_load_tick(struct rq *this_rq); extern long calc_load_fold_active(struct rq *this_rq); #ifdef CONFIG_SMP -extern void update_cpu_load_active(struct rq *this_rq); +extern void cpu_load_update_active(struct rq *this_rq); #else -static inline void update_cpu_load_active(struct rq *this_rq) { } +static inline void cpu_load_update_active(struct rq *this_rq) { } #endif /* @@ -49,25 +49,32 @@ static inline void update_cpu_load_active(struct rq *this_rq) { } * and does not change the user-interface for setting shares/weights. * * We increase resolution only if we have enough bits to allow this increased - * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution - * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the - * increased costs. + * resolution (i.e. 64bit). The costs for increasing resolution when 32bit are + * pretty high and the returns do not justify the increased costs. + * + * Really only required when CONFIG_FAIR_GROUP_SCHED is also set, but to + * increase coverage and consistency always enable it on 64bit platforms. */ -#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */ -# define SCHED_LOAD_RESOLUTION 10 -# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION) -# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION) +#ifdef CONFIG_64BIT +# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT) +# define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT) +# define scale_load_down(w) ((w) >> SCHED_FIXEDPOINT_SHIFT) #else -# define SCHED_LOAD_RESOLUTION 0 +# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT) # define scale_load(w) (w) # define scale_load_down(w) (w) #endif -#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION) -#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) - -#define NICE_0_LOAD SCHED_LOAD_SCALE -#define NICE_0_SHIFT SCHED_LOAD_SHIFT +/* + * Task weight (visible to users) and its load (invisible to users) have + * independent resolution, but they should be well calibrated. We use + * scale_load() and scale_load_down(w) to convert between them. The + * following must be true: + * + * scale_load(sched_prio_to_weight[USER_PRIO(NICE_TO_PRIO(0))]) == NICE_0_LOAD + * + */ +#define NICE_0_LOAD (1L << NICE_0_LOAD_SHIFT) /* * Single value that decides SCHED_DEADLINE internal math precision. @@ -585,11 +592,13 @@ struct rq { #endif #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; - unsigned long last_load_update_tick; #ifdef CONFIG_NO_HZ_COMMON +#ifdef CONFIG_SMP + unsigned long last_load_update_tick; +#endif /* CONFIG_SMP */ u64 nohz_stamp; unsigned long nohz_flags; -#endif +#endif /* CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL unsigned long last_sched_tick; #endif @@ -854,7 +863,7 @@ DECLARE_PER_CPU(struct sched_domain *, sd_asym); struct sched_group_capacity { atomic_t ref; /* - * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity + * CPU capacity of this group, SCHED_CAPACITY_SCALE being max capacity * for a single CPU. */ unsigned int capacity; @@ -1159,7 +1168,7 @@ extern const u32 sched_prio_to_wmult[40]; * * ENQUEUE_HEAD - place at front of runqueue (tail if not specified) * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline) - * ENQUEUE_WAKING - sched_class::task_waking was called + * ENQUEUE_MIGRATED - the task was migrated during wakeup * */ @@ -1174,9 +1183,9 @@ extern const u32 sched_prio_to_wmult[40]; #define ENQUEUE_HEAD 0x08 #define ENQUEUE_REPLENISH 0x10 #ifdef CONFIG_SMP -#define ENQUEUE_WAKING 0x20 +#define ENQUEUE_MIGRATED 0x20 #else -#define ENQUEUE_WAKING 0x00 +#define ENQUEUE_MIGRATED 0x00 #endif #define RETRY_TASK ((void *)-1UL) @@ -1200,14 +1209,14 @@ struct sched_class { * tasks. */ struct task_struct * (*pick_next_task) (struct rq *rq, - struct task_struct *prev); + struct task_struct *prev, + struct pin_cookie cookie); void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); void (*migrate_task_rq)(struct task_struct *p); - void (*task_waking) (struct task_struct *task); void (*task_woken) (struct rq *this_rq, struct task_struct *task); void (*set_cpus_allowed)(struct task_struct *p, @@ -1313,6 +1322,7 @@ extern void init_dl_task_timer(struct sched_dl_entity *dl_se); unsigned long to_ratio(u64 period, u64 runtime); extern void init_entity_runnable_average(struct sched_entity *se); +extern void post_init_entity_util_avg(struct sched_entity *se); #ifdef CONFIG_NO_HZ_FULL extern bool sched_can_stop_tick(struct rq *rq); @@ -1448,86 +1458,32 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } static inline void sched_avg_update(struct rq *rq) { } #endif -/* - * __task_rq_lock - lock the rq @p resides on. - */ -static inline struct rq *__task_rq_lock(struct task_struct *p) - __acquires(rq->lock) -{ - struct rq *rq; - - lockdep_assert_held(&p->pi_lock); - - for (;;) { - rq = task_rq(p); - raw_spin_lock(&rq->lock); - if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { - lockdep_pin_lock(&rq->lock); - return rq; - } - raw_spin_unlock(&rq->lock); - - while (unlikely(task_on_rq_migrating(p))) - cpu_relax(); - } -} +struct rq_flags { + unsigned long flags; + struct pin_cookie cookie; +}; -/* - * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. - */ -static inline struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) +struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(rq->lock); +struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) __acquires(p->pi_lock) - __acquires(rq->lock) -{ - struct rq *rq; - - for (;;) { - raw_spin_lock_irqsave(&p->pi_lock, *flags); - rq = task_rq(p); - raw_spin_lock(&rq->lock); - /* - * move_queued_task() task_rq_lock() - * - * ACQUIRE (rq->lock) - * [S] ->on_rq = MIGRATING [L] rq = task_rq() - * WMB (__set_task_cpu()) ACQUIRE (rq->lock); - * [S] ->cpu = new_cpu [L] task_rq() - * [L] ->on_rq - * RELEASE (rq->lock) - * - * If we observe the old cpu in task_rq_lock, the acquire of - * the old rq->lock will fully serialize against the stores. - * - * If we observe the new cpu in task_rq_lock, the acquire will - * pair with the WMB to ensure we must then also see migrating. - */ - if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { - lockdep_pin_lock(&rq->lock); - return rq; - } - raw_spin_unlock(&rq->lock); - raw_spin_unlock_irqrestore(&p->pi_lock, *flags); - - while (unlikely(task_on_rq_migrating(p))) - cpu_relax(); - } -} + __acquires(rq->lock); -static inline void __task_rq_unlock(struct rq *rq) +static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) __releases(rq->lock) { - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, rf->cookie); raw_spin_unlock(&rq->lock); } static inline void -task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags) +task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) __releases(rq->lock) __releases(p->pi_lock) { - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, rf->cookie); raw_spin_unlock(&rq->lock); - raw_spin_unlock_irqrestore(&p->pi_lock, *flags); + raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); } #ifdef CONFIG_SMP @@ -1743,6 +1699,10 @@ enum rq_nohz_flag_bits { }; #define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags) + +extern void nohz_balance_exit_idle(unsigned int cpu); +#else +static inline void nohz_balance_exit_idle(unsigned int cpu) { } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index cbc67da..604297a 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -24,7 +24,7 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags) } static struct task_struct * -pick_next_task_stop(struct rq *rq, struct task_struct *prev) +pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) { struct task_struct *stop = rq->stop; diff --git a/kernel/signal.c b/kernel/signal.c index aa9bf00..ab122a2 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3099,12 +3099,14 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s oss.ss_sp = (void __user *) current->sas_ss_sp; oss.ss_size = current->sas_ss_size; - oss.ss_flags = sas_ss_flags(sp); + oss.ss_flags = sas_ss_flags(sp) | + (current->sas_ss_flags & SS_FLAG_BITS); if (uss) { void __user *ss_sp; size_t ss_size; - int ss_flags; + unsigned ss_flags; + int ss_mode; error = -EFAULT; if (!access_ok(VERIFY_READ, uss, sizeof(*uss))) @@ -3119,18 +3121,13 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s if (on_sig_stack(sp)) goto out; + ss_mode = ss_flags & ~SS_FLAG_BITS; error = -EINVAL; - /* - * Note - this code used to test ss_flags incorrectly: - * old code may have been written using ss_flags==0 - * to mean ss_flags==SS_ONSTACK (as this was the only - * way that worked) - this fix preserves that older - * mechanism. - */ - if (ss_flags != SS_DISABLE && ss_flags != SS_ONSTACK && ss_flags != 0) + if (ss_mode != SS_DISABLE && ss_mode != SS_ONSTACK && + ss_mode != 0) goto out; - if (ss_flags == SS_DISABLE) { + if (ss_mode == SS_DISABLE) { ss_size = 0; ss_sp = NULL; } else { @@ -3141,6 +3138,7 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s current->sas_ss_sp = (unsigned long) ss_sp; current->sas_ss_size = ss_size; + current->sas_ss_flags = ss_flags; } error = 0; @@ -3171,9 +3169,14 @@ int restore_altstack(const stack_t __user *uss) int __save_altstack(stack_t __user *uss, unsigned long sp) { struct task_struct *t = current; - return __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) | - __put_user(sas_ss_flags(sp), &uss->ss_flags) | + int err = __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) | + __put_user(t->sas_ss_flags, &uss->ss_flags) | __put_user(t->sas_ss_size, &uss->ss_size); + if (err) + return err; + if (t->sas_ss_flags & SS_AUTODISARM) + sas_ss_reset(t); + return 0; } #ifdef CONFIG_COMPAT diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 725587f..c8b3186 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -130,6 +130,9 @@ static int one_thousand = 1000; #ifdef CONFIG_PRINTK static int ten_thousand = 10000; #endif +#ifdef CONFIG_PERF_EVENTS +static int six_hundred_forty_kb = 640 * 1024; +#endif /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static unsigned long dirty_bytes_min = 2 * PAGE_SIZE; @@ -1144,6 +1147,15 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one_hundred, }, + { + .procname = "perf_event_max_stack", + .data = NULL, /* filled in by handler */ + .maxlen = sizeof(sysctl_perf_event_max_stack), + .mode = 0644, + .proc_handler = perf_event_max_stack_handler, + .extra1 = &zero, + .extra2 = &six_hundred_forty_kb, + }, #endif #ifdef CONFIG_KMEMCHECK { diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 58e3310..536ada8 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -262,7 +262,7 @@ static void tick_nohz_dep_set_all(atomic_t *dep, { int prev; - prev = atomic_fetch_or(dep, BIT(bit)); + prev = atomic_fetch_or(BIT(bit), dep); if (!prev) tick_nohz_full_kick_all(); } @@ -292,7 +292,7 @@ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) ts = per_cpu_ptr(&tick_cpu_sched, cpu); - prev = atomic_fetch_or(&ts->tick_dep_mask, BIT(bit)); + prev = atomic_fetch_or(BIT(bit), &ts->tick_dep_mask); if (!prev) { preempt_disable(); /* Perf needs local kick that is NMI safe */ @@ -776,6 +776,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, if (!ts->tick_stopped) { nohz_balance_enter_idle(cpu); calc_load_enter_idle(); + cpu_load_update_nohz_start(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; @@ -802,11 +803,11 @@ out: return tick; } -static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now, int active) +static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ tick_do_update_jiffies64(now); - update_cpu_load_nohz(active); + cpu_load_update_nohz_stop(); calc_load_exit_idle(); touch_softlockup_watchdog_sched(); @@ -833,7 +834,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts) if (can_stop_full_tick(ts)) tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); else if (ts->tick_stopped) - tick_nohz_restart_sched_tick(ts, ktime_get(), 1); + tick_nohz_restart_sched_tick(ts, ktime_get()); #endif } @@ -1024,7 +1025,7 @@ void tick_nohz_idle_exit(void) tick_nohz_stop_idle(ts, now); if (ts->tick_stopped) { - tick_nohz_restart_sched_tick(ts, now, 0); + tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_ticks(ts); } diff --git a/kernel/torture.c b/kernel/torture.c index 44aa462..fa0bdee 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -451,6 +451,7 @@ static int torture_shutdown(void *arg) torture_shutdown_hook(); else VERBOSE_TOROUT_STRING("No torture_shutdown_hook(), skipping."); + ftrace_dump(DUMP_ALL); kernel_power_off(); /* Shut down the system. */ return 0; } @@ -602,8 +603,9 @@ bool torture_init_begin(char *ttype, bool v, int *runnable) { mutex_lock(&fullstop_mutex); if (torture_type != NULL) { - pr_alert("torture_init_begin: refusing %s init: %s running", + pr_alert("torture_init_begin: Refusing %s init: %s running.\n", ttype, torture_type); + pr_alert("torture_init_begin: One torture test at a time!\n"); mutex_unlock(&fullstop_mutex); return false; } diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 00df25f..e11108f 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -47,6 +47,9 @@ static int perf_trace_event_perm(struct trace_event_call *tp_event, if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) return -EPERM; + if (!is_sampling_event(p_event)) + return 0; + /* * We don't allow user space callchains for function trace * event, due to issues with page faults while tracing page diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 05ddc08..6f96586 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2095,8 +2095,13 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) trace_create_file("filter", 0644, file->dir, file, &ftrace_event_filter_fops); - trace_create_file("trigger", 0644, file->dir, file, - &event_trigger_fops); + /* + * Only event directories that can be enabled should have + * triggers. + */ + if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) + trace_create_file("trigger", 0644, file->dir, file, + &event_trigger_fops); trace_create_file("format", 0444, file->dir, call, &ftrace_event_format_fops); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3bfdff0..5f5068e 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4554,6 +4554,17 @@ static void rebind_workers(struct worker_pool *pool) pool->attrs->cpumask) < 0); spin_lock_irq(&pool->lock); + + /* + * XXX: CPU hotplug notifiers are weird and can call DOWN_FAILED + * w/o preceding DOWN_PREPARE. Work around it. CPU hotplug is + * being reworked and this can go away in time. + */ + if (!(pool->flags & POOL_DISASSOCIATED)) { + spin_unlock_irq(&pool->lock); + return; + } + pool->flags &= ~POOL_DISASSOCIATED; for_each_pool_worker(worker, pool) { diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1e9a607..f4b797a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1289,6 +1289,39 @@ config TORTURE_TEST tristate default n +config RCU_PERF_TEST + tristate "performance tests for RCU" + depends on DEBUG_KERNEL + select TORTURE_TEST + select SRCU + select TASKS_RCU + default n + help + This option provides a kernel module that runs performance + tests on the RCU infrastructure. The kernel module may be built + after the fact on the running kernel to be tested, if desired. + + Say Y here if you want RCU performance tests to be built into + the kernel. + Say M if you want the RCU performance tests to build as a module. + Say N if you are unsure. + +config RCU_PERF_TEST_RUNNABLE + bool "performance tests for RCU runnable by default" + depends on RCU_PERF_TEST = y + default n + help + This option provides a way to build the RCU performance tests + directly into the kernel without them starting up at boot time. + You can use /sys/module to manually override this setting. + This /proc file is available only when the RCU performance + tests have been built into the kernel. + + Say Y here if you want the RCU performance tests to start during + boot (you probably don't). + Say N here if you want the RCU performance tests to start only + after being manually enabled via /sys/module. + config RCU_TORTURE_TEST tristate "torture tests for RCU" depends on DEBUG_KERNEL diff --git a/lib/Makefile b/lib/Makefile index 7bd6fd4..a65e9a8 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -23,7 +23,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o timerqueue.o\ idr.o int_sqrt.o extable.o \ sha1.o md5.o irq_regs.o argv_split.o \ - proportions.o flex_proportions.o ratelimit.o show_mem.o \ + flex_proportions.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o nmi_backtrace.o diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c index 2b3f46c..5545229 100644 --- a/lib/asn1_decoder.c +++ b/lib/asn1_decoder.c @@ -74,7 +74,7 @@ next_tag: /* Extract a tag from the data */ tag = data[dp++]; - if (tag == 0) { + if (tag == ASN1_EOC) { /* It appears to be an EOC. */ if (data[dp++] != 0) goto invalid_eoc; @@ -96,10 +96,8 @@ next_tag: /* Extract the length */ len = data[dp++]; - if (len <= 0x7f) { - dp += len; - goto next_tag; - } + if (len <= 0x7f) + goto check_length; if (unlikely(len == ASN1_INDEFINITE_LENGTH)) { /* Indefinite length */ @@ -110,14 +108,18 @@ next_tag: } n = len - 0x80; - if (unlikely(n > sizeof(size_t) - 1)) + if (unlikely(n > sizeof(len) - 1)) goto length_too_long; if (unlikely(n > datalen - dp)) goto data_overrun_error; - for (len = 0; n > 0; n--) { + len = 0; + for (; n > 0; n--) { len <<= 8; len |= data[dp++]; } +check_length: + if (len > datalen - dp) + goto data_overrun_error; dp += len; goto next_tag; diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 5fecddc..ca5316e 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -569,6 +569,25 @@ unsigned long iov_iter_alignment(const struct iov_iter *i) } EXPORT_SYMBOL(iov_iter_alignment); +unsigned long iov_iter_gap_alignment(const struct iov_iter *i) +{ + unsigned long res = 0; + size_t size = i->count; + if (!size) + return 0; + + iterate_all_kinds(i, size, v, + (res |= (!res ? 0 : (unsigned long)v.iov_base) | + (size != v.iov_len ? size : 0), 0), + (res |= (!res ? 0 : (unsigned long)v.bv_offset) | + (size != v.bv_len ? size : 0)), + (res |= (!res ? 0 : (unsigned long)v.iov_base) | + (size != v.iov_len ? size : 0)) + ); + return res; +} +EXPORT_SYMBOL(iov_iter_gap_alignment); + ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) diff --git a/lib/proportions.c b/lib/proportions.c deleted file mode 100644 index efa54f25..0000000 --- a/lib/proportions.c +++ /dev/null @@ -1,407 +0,0 @@ -/* - * Floating proportions - * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra - * - * Description: - * - * The floating proportion is a time derivative with an exponentially decaying - * history: - * - * p_{j} = \Sum_{i=0} (dx_{j}/dt_{-i}) / 2^(1+i) - * - * Where j is an element from {prop_local}, x_{j} is j's number of events, - * and i the time period over which the differential is taken. So d/dt_{-i} is - * the differential over the i-th last period. - * - * The decaying history gives smooth transitions. The time differential carries - * the notion of speed. - * - * The denominator is 2^(1+i) because we want the series to be normalised, ie. - * - * \Sum_{i=0} 1/2^(1+i) = 1 - * - * Further more, if we measure time (t) in the same events as x; so that: - * - * t = \Sum_{j} x_{j} - * - * we get that: - * - * \Sum_{j} p_{j} = 1 - * - * Writing this in an iterative fashion we get (dropping the 'd's): - * - * if (++x_{j}, ++t > period) - * t /= 2; - * for_each (j) - * x_{j} /= 2; - * - * so that: - * - * p_{j} = x_{j} / t; - * - * We optimize away the '/= 2' for the global time delta by noting that: - * - * if (++t > period) t /= 2: - * - * Can be approximated by: - * - * period/2 + (++t % period/2) - * - * [ Furthermore, when we choose period to be 2^n it can be written in terms of - * binary operations and wraparound artefacts disappear. ] - * - * Also note that this yields a natural counter of the elapsed periods: - * - * c = t / (period/2) - * - * [ Its monotonic increasing property can be applied to mitigate the wrap- - * around issue. ] - * - * This allows us to do away with the loop over all prop_locals on each period - * expiration. By remembering the period count under which it was last accessed - * as c_{j}, we can obtain the number of 'missed' cycles from: - * - * c - c_{j} - * - * We can then lazily catch up to the global period count every time we are - * going to use x_{j}, by doing: - * - * x_{j} /= 2^(c - c_{j}), c_{j} = c - */ - -#include <linux/proportions.h> -#include <linux/rcupdate.h> - -int prop_descriptor_init(struct prop_descriptor *pd, int shift, gfp_t gfp) -{ - int err; - - if (shift > PROP_MAX_SHIFT) - shift = PROP_MAX_SHIFT; - - pd->index = 0; - pd->pg[0].shift = shift; - mutex_init(&pd->mutex); - err = percpu_counter_init(&pd->pg[0].events, 0, gfp); - if (err) - goto out; - - err = percpu_counter_init(&pd->pg[1].events, 0, gfp); - if (err) - percpu_counter_destroy(&pd->pg[0].events); - -out: - return err; -} - -/* - * We have two copies, and flip between them to make it seem like an atomic - * update. The update is not really atomic wrt the events counter, but - * it is internally consistent with the bit layout depending on shift. - * - * We copy the events count, move the bits around and flip the index. - */ -void prop_change_shift(struct prop_descriptor *pd, int shift) -{ - int index; - int offset; - u64 events; - unsigned long flags; - - if (shift > PROP_MAX_SHIFT) - shift = PROP_MAX_SHIFT; - - mutex_lock(&pd->mutex); - - index = pd->index ^ 1; - offset = pd->pg[pd->index].shift - shift; - if (!offset) - goto out; - - pd->pg[index].shift = shift; - - local_irq_save(flags); - events = percpu_counter_sum(&pd->pg[pd->index].events); - if (offset < 0) - events <<= -offset; - else - events >>= offset; - percpu_counter_set(&pd->pg[index].events, events); - - /* - * ensure the new pg is fully written before the switch - */ - smp_wmb(); - pd->index = index; - local_irq_restore(flags); - - synchronize_rcu(); - -out: - mutex_unlock(&pd->mutex); -} - -/* - * wrap the access to the data in an rcu_read_lock() section; - * this is used to track the active references. - */ -static struct prop_global *prop_get_global(struct prop_descriptor *pd) -__acquires(RCU) -{ - int index; - - rcu_read_lock(); - index = pd->index; - /* - * match the wmb from vcd_flip() - */ - smp_rmb(); - return &pd->pg[index]; -} - -static void prop_put_global(struct prop_descriptor *pd, struct prop_global *pg) -__releases(RCU) -{ - rcu_read_unlock(); -} - -static void -prop_adjust_shift(int *pl_shift, unsigned long *pl_period, int new_shift) -{ - int offset = *pl_shift - new_shift; - - if (!offset) - return; - - if (offset < 0) - *pl_period <<= -offset; - else - *pl_period >>= offset; - - *pl_shift = new_shift; -} - -/* - * PERCPU - */ - -#define PROP_BATCH (8*(1+ilog2(nr_cpu_ids))) - -int prop_local_init_percpu(struct prop_local_percpu *pl, gfp_t gfp) -{ - raw_spin_lock_init(&pl->lock); - pl->shift = 0; - pl->period = 0; - return percpu_counter_init(&pl->events, 0, gfp); -} - -void prop_local_destroy_percpu(struct prop_local_percpu *pl) -{ - percpu_counter_destroy(&pl->events); -} - -/* - * Catch up with missed period expirations. - * - * until (c_{j} == c) - * x_{j} -= x_{j}/2; - * c_{j}++; - */ -static -void prop_norm_percpu(struct prop_global *pg, struct prop_local_percpu *pl) -{ - unsigned long period = 1UL << (pg->shift - 1); - unsigned long period_mask = ~(period - 1); - unsigned long global_period; - unsigned long flags; - - global_period = percpu_counter_read(&pg->events); - global_period &= period_mask; - - /* - * Fast path - check if the local and global period count still match - * outside of the lock. - */ - if (pl->period == global_period) - return; - - raw_spin_lock_irqsave(&pl->lock, flags); - prop_adjust_shift(&pl->shift, &pl->period, pg->shift); - - /* - * For each missed period, we half the local counter. - * basically: - * pl->events >> (global_period - pl->period); - */ - period = (global_period - pl->period) >> (pg->shift - 1); - if (period < BITS_PER_LONG) { - s64 val = percpu_counter_read(&pl->events); - - if (val < (nr_cpu_ids * PROP_BATCH)) - val = percpu_counter_sum(&pl->events); - - __percpu_counter_add(&pl->events, -val + (val >> period), - PROP_BATCH); - } else - percpu_counter_set(&pl->events, 0); - - pl->period = global_period; - raw_spin_unlock_irqrestore(&pl->lock, flags); -} - -/* - * ++x_{j}, ++t - */ -void __prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl) -{ - struct prop_global *pg = prop_get_global(pd); - - prop_norm_percpu(pg, pl); - __percpu_counter_add(&pl->events, 1, PROP_BATCH); - percpu_counter_add(&pg->events, 1); - prop_put_global(pd, pg); -} - -/* - * identical to __prop_inc_percpu, except that it limits this pl's fraction to - * @frac/PROP_FRAC_BASE by ignoring events when this limit has been exceeded. - */ -void __prop_inc_percpu_max(struct prop_descriptor *pd, - struct prop_local_percpu *pl, long frac) -{ - struct prop_global *pg = prop_get_global(pd); - - prop_norm_percpu(pg, pl); - - if (unlikely(frac != PROP_FRAC_BASE)) { - unsigned long period_2 = 1UL << (pg->shift - 1); - unsigned long counter_mask = period_2 - 1; - unsigned long global_count; - long numerator, denominator; - - numerator = percpu_counter_read_positive(&pl->events); - global_count = percpu_counter_read(&pg->events); - denominator = period_2 + (global_count & counter_mask); - - if (numerator > ((denominator * frac) >> PROP_FRAC_SHIFT)) - goto out_put; - } - - percpu_counter_add(&pl->events, 1); - percpu_counter_add(&pg->events, 1); - -out_put: - prop_put_global(pd, pg); -} - -/* - * Obtain a fraction of this proportion - * - * p_{j} = x_{j} / (period/2 + t % period/2) - */ -void prop_fraction_percpu(struct prop_descriptor *pd, - struct prop_local_percpu *pl, - long *numerator, long *denominator) -{ - struct prop_global *pg = prop_get_global(pd); - unsigned long period_2 = 1UL << (pg->shift - 1); - unsigned long counter_mask = period_2 - 1; - unsigned long global_count; - - prop_norm_percpu(pg, pl); - *numerator = percpu_counter_read_positive(&pl->events); - - global_count = percpu_counter_read(&pg->events); - *denominator = period_2 + (global_count & counter_mask); - - prop_put_global(pd, pg); -} - -/* - * SINGLE - */ - -int prop_local_init_single(struct prop_local_single *pl) -{ - raw_spin_lock_init(&pl->lock); - pl->shift = 0; - pl->period = 0; - pl->events = 0; - return 0; -} - -void prop_local_destroy_single(struct prop_local_single *pl) -{ -} - -/* - * Catch up with missed period expirations. - */ -static -void prop_norm_single(struct prop_global *pg, struct prop_local_single *pl) -{ - unsigned long period = 1UL << (pg->shift - 1); - unsigned long period_mask = ~(period - 1); - unsigned long global_period; - unsigned long flags; - - global_period = percpu_counter_read(&pg->events); - global_period &= period_mask; - - /* - * Fast path - check if the local and global period count still match - * outside of the lock. - */ - if (pl->period == global_period) - return; - - raw_spin_lock_irqsave(&pl->lock, flags); - prop_adjust_shift(&pl->shift, &pl->period, pg->shift); - /* - * For each missed period, we half the local counter. - */ - period = (global_period - pl->period) >> (pg->shift - 1); - if (likely(period < BITS_PER_LONG)) - pl->events >>= period; - else - pl->events = 0; - pl->period = global_period; - raw_spin_unlock_irqrestore(&pl->lock, flags); -} - -/* - * ++x_{j}, ++t - */ -void __prop_inc_single(struct prop_descriptor *pd, struct prop_local_single *pl) -{ - struct prop_global *pg = prop_get_global(pd); - - prop_norm_single(pg, pl); - pl->events++; - percpu_counter_add(&pg->events, 1); - prop_put_global(pd, pg); -} - -/* - * Obtain a fraction of this proportion - * - * p_{j} = x_{j} / (period/2 + t % period/2) - */ -void prop_fraction_single(struct prop_descriptor *pd, - struct prop_local_single *pl, - long *numerator, long *denominator) -{ - struct prop_global *pg = prop_get_global(pd); - unsigned long period_2 = 1UL << (pg->shift - 1); - unsigned long counter_mask = period_2 - 1; - unsigned long global_count; - - prop_norm_single(pg, pl); - *numerator = pl->events; - - global_count = percpu_counter_read(&pg->events); - *denominator = period_2 + (global_count & counter_mask); - - prop_put_global(pd, pg); -} diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 9e0b031..53ad6c0 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -42,12 +42,14 @@ #define DEPOT_STACK_BITS (sizeof(depot_stack_handle_t) * 8) +#define STACK_ALLOC_NULL_PROTECTION_BITS 1 #define STACK_ALLOC_ORDER 2 /* 'Slab' size order for stack depot, 4 pages */ #define STACK_ALLOC_SIZE (1LL << (PAGE_SHIFT + STACK_ALLOC_ORDER)) #define STACK_ALLOC_ALIGN 4 #define STACK_ALLOC_OFFSET_BITS (STACK_ALLOC_ORDER + PAGE_SHIFT - \ STACK_ALLOC_ALIGN) -#define STACK_ALLOC_INDEX_BITS (DEPOT_STACK_BITS - STACK_ALLOC_OFFSET_BITS) +#define STACK_ALLOC_INDEX_BITS (DEPOT_STACK_BITS - \ + STACK_ALLOC_NULL_PROTECTION_BITS - STACK_ALLOC_OFFSET_BITS) #define STACK_ALLOC_SLABS_CAP 1024 #define STACK_ALLOC_MAX_SLABS \ (((1LL << (STACK_ALLOC_INDEX_BITS)) < STACK_ALLOC_SLABS_CAP) ? \ @@ -59,6 +61,7 @@ union handle_parts { struct { u32 slabindex : STACK_ALLOC_INDEX_BITS; u32 offset : STACK_ALLOC_OFFSET_BITS; + u32 valid : STACK_ALLOC_NULL_PROTECTION_BITS; }; }; @@ -136,6 +139,7 @@ static struct stack_record *depot_alloc_stack(unsigned long *entries, int size, stack->size = size; stack->handle.slabindex = depot_index; stack->handle.offset = depot_offset >> STACK_ALLOC_ALIGN; + stack->handle.valid = 1; memcpy(stack->entries, entries, size * sizeof(unsigned long)); depot_offset += required_size; diff --git a/mm/compaction.c b/mm/compaction.c index ccf97b0..8fa2540 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -852,16 +852,8 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, pfn = isolate_migratepages_block(cc, pfn, block_end_pfn, ISOLATE_UNEVICTABLE); - /* - * In case of fatal failure, release everything that might - * have been isolated in the previous iteration, and signal - * the failure back to caller. - */ - if (!pfn) { - putback_movable_pages(&cc->migratepages); - cc->nr_migratepages = 0; + if (!pfn) break; - } if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) break; @@ -1741,7 +1733,7 @@ void compaction_unregister_node(struct node *node) static inline bool kcompactd_work_requested(pg_data_t *pgdat) { - return pgdat->kcompactd_max_order > 0; + return pgdat->kcompactd_max_order > 0 || kthread_should_stop(); } static bool kcompactd_node_suitable(pg_data_t *pgdat) @@ -1805,6 +1797,8 @@ static void kcompactd_do_work(pg_data_t *pgdat) INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); + if (kthread_should_stop()) + return; status = compact_zone(zone, &cc); if (zone_watermark_ok(zone, cc.order, low_wmark_pages(zone), diff --git a/mm/huge_memory.c b/mm/huge_memory.c index df67b53..b49ee12 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1298,15 +1298,9 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page); /* * We can only reuse the page if nobody else maps the huge page or it's - * part. We can do it by checking page_mapcount() on each sub-page, but - * it's expensive. - * The cheaper way is to check page_count() to be equal 1: every - * mapcount takes page reference reference, so this way we can - * guarantee, that the PMD is the only mapping. - * This can give false negative if somebody pinned the page, but that's - * fine. + * part. */ - if (page_mapcount(page) == 1 && page_count(page) == 1) { + if (page_trans_huge_mapcount(page, NULL) == 1) { pmd_t entry; entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); @@ -2079,7 +2073,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, if (pte_write(pteval)) { writable = true; } else { - if (PageSwapCache(page) && !reuse_swap_page(page)) { + if (PageSwapCache(page) && + !reuse_swap_page(page, NULL)) { unlock_page(page); result = SCAN_SWAP_CACHE_PAGE; goto out; @@ -3223,6 +3218,64 @@ int total_mapcount(struct page *page) } /* + * This calculates accurately how many mappings a transparent hugepage + * has (unlike page_mapcount() which isn't fully accurate). This full + * accuracy is primarily needed to know if copy-on-write faults can + * reuse the page and change the mapping to read-write instead of + * copying them. At the same time this returns the total_mapcount too. + * + * The function returns the highest mapcount any one of the subpages + * has. If the return value is one, even if different processes are + * mapping different subpages of the transparent hugepage, they can + * all reuse it, because each process is reusing a different subpage. + * + * The total_mapcount is instead counting all virtual mappings of the + * subpages. If the total_mapcount is equal to "one", it tells the + * caller all mappings belong to the same "mm" and in turn the + * anon_vma of the transparent hugepage can become the vma->anon_vma + * local one as no other process may be mapping any of the subpages. + * + * It would be more accurate to replace page_mapcount() with + * page_trans_huge_mapcount(), however we only use + * page_trans_huge_mapcount() in the copy-on-write faults where we + * need full accuracy to avoid breaking page pinning, because + * page_trans_huge_mapcount() is slower than page_mapcount(). + */ +int page_trans_huge_mapcount(struct page *page, int *total_mapcount) +{ + int i, ret, _total_mapcount, mapcount; + + /* hugetlbfs shouldn't call it */ + VM_BUG_ON_PAGE(PageHuge(page), page); + + if (likely(!PageTransCompound(page))) { + mapcount = atomic_read(&page->_mapcount) + 1; + if (total_mapcount) + *total_mapcount = mapcount; + return mapcount; + } + + page = compound_head(page); + + _total_mapcount = ret = 0; + for (i = 0; i < HPAGE_PMD_NR; i++) { + mapcount = atomic_read(&page[i]._mapcount) + 1; + ret = max(ret, mapcount); + _total_mapcount += mapcount; + } + if (PageDoubleMap(page)) { + ret -= 1; + _total_mapcount -= HPAGE_PMD_NR; + } + mapcount = compound_mapcount(page); + ret += mapcount; + _total_mapcount += mapcount; + if (total_mapcount) + *total_mapcount = _total_mapcount; + return ret; +} + +/* * This function splits huge page into normal pages. @page can point to any * subpage of huge page to split. Split doesn't change the position of @page. * @@ -3452,7 +3505,7 @@ next: } } - pr_info("%lu of %lu THP split", split, total); + pr_info("%lu of %lu THP split\n", split, total); return 0; } @@ -3463,7 +3516,7 @@ static int __init split_huge_pages_debugfs(void) { void *ret; - ret = debugfs_create_file("split_huge_pages", 0644, NULL, NULL, + ret = debugfs_create_file("split_huge_pages", 0200, NULL, NULL, &split_huge_pages_fops); if (!ret) pr_warn("Failed to create split_huge_pages in debugfs"); @@ -783,6 +783,7 @@ static int unmerge_and_remove_all_rmap_items(void) } remove_trailing_rmap_items(mm_slot, &mm_slot->rmap_list); + up_read(&mm->mmap_sem); spin_lock(&ksm_mmlist_lock); ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next, @@ -794,12 +795,9 @@ static int unmerge_and_remove_all_rmap_items(void) free_mm_slot(mm_slot); clear_bit(MMF_VM_MERGEABLE, &mm->flags); - up_read(&mm->mmap_sem); mmdrop(mm); - } else { + } else spin_unlock(&ksm_mmlist_lock); - up_read(&mm->mmap_sem); - } } /* Clean up stable nodes, but don't worry if some are still busy */ @@ -1663,8 +1661,15 @@ next_mm: up_read(&mm->mmap_sem); mmdrop(mm); } else { - spin_unlock(&ksm_mmlist_lock); up_read(&mm->mmap_sem); + /* + * up_read(&mm->mmap_sem) first because after + * spin_unlock(&ksm_mmlist_lock) run, the "mm" may + * already have been freed under us by __ksm_exit() + * because the "mm_slot" is still hashed and + * ksm_scan.mm_slot doesn't point to it anymore. + */ + spin_unlock(&ksm_mmlist_lock); } /* Repeat until we've completed scanning the whole list */ diff --git a/mm/memory.c b/mm/memory.c index 305537f..07493e3 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1222,15 +1222,8 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) { -#ifdef CONFIG_DEBUG_VM - if (!rwsem_is_locked(&tlb->mm->mmap_sem)) { - pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n", - __func__, addr, end, - vma->vm_start, - vma->vm_end); - BUG(); - } -#endif + VM_BUG_ON_VMA(vma_is_anonymous(vma) && + !rwsem_is_locked(&tlb->mm->mmap_sem), vma); split_huge_pmd(vma, pmd, addr); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; @@ -2380,6 +2373,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * not dirty accountable. */ if (PageAnon(old_page) && !PageKsm(old_page)) { + int total_mapcount; if (!trylock_page(old_page)) { get_page(old_page); pte_unmap_unlock(page_table, ptl); @@ -2394,13 +2388,18 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, } put_page(old_page); } - if (reuse_swap_page(old_page)) { - /* - * The page is all ours. Move it to our anon_vma so - * the rmap code will not search our parent or siblings. - * Protected against the rmap code by the page lock. - */ - page_move_anon_rmap(old_page, vma, address); + if (reuse_swap_page(old_page, &total_mapcount)) { + if (total_mapcount == 1) { + /* + * The page is all ours. Move it to + * our anon_vma so the rmap code will + * not search our parent or siblings. + * Protected against the rmap code by + * the page lock. + */ + page_move_anon_rmap(compound_head(old_page), + vma, address); + } unlock_page(old_page); return wp_page_reuse(mm, vma, address, page_table, ptl, orig_pte, old_page, 0, 0); @@ -2624,7 +2623,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, inc_mm_counter_fast(mm, MM_ANONPAGES); dec_mm_counter_fast(mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); - if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) { + if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; diff --git a/mm/mmu_context.c b/mm/mmu_context.c index f802c2d..6f4d27c 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -4,9 +4,9 @@ */ #include <linux/mm.h> +#include <linux/sched.h> #include <linux/mmu_context.h> #include <linux/export.h> -#include <linux/sched.h> #include <asm/mmu_context.h> diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 999792d..bc5149d 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1910,7 +1910,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (gdtc->dirty > gdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(gdtc)) + if (wb_stat(wb, WB_RECLAIMABLE) > + wb_calc_thresh(gdtc->wb, gdtc->bg_thresh)) return true; if (mdtc) { @@ -1924,7 +1925,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (mdtc->dirty > mdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(mdtc)) + if (wb_stat(wb, WB_RECLAIMABLE) > + wb_calc_thresh(mdtc->wb, mdtc->bg_thresh)) return true; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 59de90d..c1069ef 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6485,7 +6485,7 @@ int __meminit init_per_zone_wmark_min(void) setup_per_zone_inactive_ratio(); return 0; } -module_init(init_per_zone_wmark_min) +core_initcall(init_per_zone_wmark_min) /* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so diff --git a/mm/swapfile.c b/mm/swapfile.c index 83874ec..031713ab 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -922,18 +922,19 @@ out: * to it. And as a side-effect, free up its swap: because the old content * on disk will never be read, and seeking back there to write new content * later would only waste time away from clustering. + * + * NOTE: total_mapcount should not be relied upon by the caller if + * reuse_swap_page() returns false, but it may be always overwritten + * (see the other implementation for CONFIG_SWAP=n). */ -int reuse_swap_page(struct page *page) +bool reuse_swap_page(struct page *page, int *total_mapcount) { int count; VM_BUG_ON_PAGE(!PageLocked(page), page); if (unlikely(PageKsm(page))) - return 0; - /* The page is part of THP and cannot be reused */ - if (PageTransCompound(page)) - return 0; - count = page_mapcount(page); + return false; + count = page_trans_huge_mapcount(page, total_mapcount); if (count <= 1 && PageSwapCache(page)) { count += page_swapcount(page); if (count == 1 && !PageWriteback(page)) { diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index e72efb10..fe47fbb 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1735,10 +1735,13 @@ static struct page *isolate_source_page(struct size_class *class) static unsigned long zs_can_compact(struct size_class *class) { unsigned long obj_wasted; + unsigned long obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); + unsigned long obj_used = zs_stat_get(class, OBJ_USED); - obj_wasted = zs_stat_get(class, OBJ_ALLOCATED) - - zs_stat_get(class, OBJ_USED); + if (obj_allocated <= obj_used) + return 0; + obj_wasted = obj_allocated - obj_used; obj_wasted /= get_maxobj_per_zspage(class->size, class->pages_per_zspage); @@ -170,6 +170,8 @@ static struct zswap_tree *zswap_trees[MAX_SWAPFILES]; static LIST_HEAD(zswap_pools); /* protects zswap_pools list modification */ static DEFINE_SPINLOCK(zswap_pools_lock); +/* pool counter to provide unique names to zpool */ +static atomic_t zswap_pools_count = ATOMIC_INIT(0); /* used by param callback function */ static bool zswap_init_started; @@ -565,6 +567,7 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) static struct zswap_pool *zswap_pool_create(char *type, char *compressor) { struct zswap_pool *pool; + char name[38]; /* 'zswap' + 32 char (max) num + \0 */ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; pool = kzalloc(sizeof(*pool), GFP_KERNEL); @@ -573,7 +576,10 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) return NULL; } - pool->zpool = zpool_create_pool(type, "zswap", gfp, &zswap_zpool_ops); + /* unique name for each pool specifically required by zsmalloc */ + snprintf(name, 38, "zswap%x", atomic_inc_return(&zswap_pools_count)); + + pool->zpool = zpool_create_pool(type, name, gfp, &zswap_zpool_ops); if (!pool->zpool) { pr_err("%s zpool not available\n", type); goto error; diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 3315b9a..4026f19 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -32,10 +32,21 @@ #include "bat_v_elp.h" #include "bat_v_ogm.h" +#include "hard-interface.h" #include "hash.h" #include "originator.h" #include "packet.h" +static void batadv_v_iface_activate(struct batadv_hard_iface *hard_iface) +{ + /* B.A.T.M.A.N. V does not use any queuing mechanism, therefore it can + * set the interface as ACTIVE right away, without any risk of race + * condition + */ + if (hard_iface->if_status == BATADV_IF_TO_BE_ACTIVATED) + hard_iface->if_status = BATADV_IF_ACTIVE; +} + static int batadv_v_iface_enable(struct batadv_hard_iface *hard_iface) { int ret; @@ -274,6 +285,7 @@ static bool batadv_v_neigh_is_sob(struct batadv_neigh_node *neigh1, static struct batadv_algo_ops batadv_batman_v __read_mostly = { .name = "BATMAN_V", + .bat_iface_activate = batadv_v_iface_activate, .bat_iface_enable = batadv_v_iface_enable, .bat_iface_disable = batadv_v_iface_disable, .bat_iface_update_mac = batadv_v_iface_update_mac, diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index e96d7c7..3e6b262 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -568,6 +568,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, * be sent to * @bat_priv: the bat priv with all the soft interface information * @ip_dst: ipv4 to look up in the DHT + * @vid: VLAN identifier * * An originator O is selected if and only if its DHT_ID value is one of three * closest values (from the LEFT, with wrap around if needed) then the hash @@ -576,7 +577,8 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, * Return: the candidate array of size BATADV_DAT_CANDIDATE_NUM. */ static struct batadv_dat_candidate * -batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) +batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst, + unsigned short vid) { int select; batadv_dat_addr_t last_max = BATADV_DAT_ADDR_MAX, ip_key; @@ -592,7 +594,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) return NULL; dat.ip = ip_dst; - dat.vid = 0; + dat.vid = vid; ip_key = (batadv_dat_addr_t)batadv_hash_dat(&dat, BATADV_DAT_ADDR_MAX); @@ -612,6 +614,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @ip: the DHT key + * @vid: VLAN identifier * @packet_subtype: unicast4addr packet subtype to use * * This function copies the skb with pskb_copy() and is sent as unicast packet @@ -622,7 +625,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) */ static bool batadv_dat_send_data(struct batadv_priv *bat_priv, struct sk_buff *skb, __be32 ip, - int packet_subtype) + unsigned short vid, int packet_subtype) { int i; bool ret = false; @@ -631,7 +634,7 @@ static bool batadv_dat_send_data(struct batadv_priv *bat_priv, struct sk_buff *tmp_skb; struct batadv_dat_candidate *cand; - cand = batadv_dat_select_candidates(bat_priv, ip); + cand = batadv_dat_select_candidates(bat_priv, ip, vid); if (!cand) goto out; @@ -1022,7 +1025,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, ret = true; } else { /* Send the request to the DHT */ - ret = batadv_dat_send_data(bat_priv, skb, ip_dst, + ret = batadv_dat_send_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_GET); } out: @@ -1150,8 +1153,8 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, /* Send the ARP reply to the candidates for both the IP addresses that * the node obtained from the ARP reply */ - batadv_dat_send_data(bat_priv, skb, ip_src, BATADV_P_DAT_DHT_PUT); - batadv_dat_send_data(bat_priv, skb, ip_dst, BATADV_P_DAT_DHT_PUT); + batadv_dat_send_data(bat_priv, skb, ip_src, vid, BATADV_P_DAT_DHT_PUT); + batadv_dat_send_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_PUT); } /** diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index b22b277..0a7deaf 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -407,6 +407,9 @@ batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface) batadv_update_min_mtu(hard_iface->soft_iface); + if (bat_priv->bat_algo_ops->bat_iface_activate) + bat_priv->bat_algo_ops->bat_iface_activate(hard_iface); + out: if (primary_if) batadv_hardif_put(primary_if); @@ -572,8 +575,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hard_iface *primary_if = NULL; - if (hard_iface->if_status == BATADV_IF_ACTIVE) - batadv_hardif_deactivate_interface(hard_iface); + batadv_hardif_deactivate_interface(hard_iface); if (hard_iface->if_status != BATADV_IF_INACTIVE) goto out; diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index e4cbb07..c355a82 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -250,7 +250,6 @@ static void batadv_neigh_node_release(struct kref *ref) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; - struct batadv_hardif_neigh_node *hardif_neigh; struct batadv_neigh_ifinfo *neigh_ifinfo; struct batadv_algo_ops *bao; @@ -262,13 +261,7 @@ static void batadv_neigh_node_release(struct kref *ref) batadv_neigh_ifinfo_put(neigh_ifinfo); } - hardif_neigh = batadv_hardif_neigh_get(neigh_node->if_incoming, - neigh_node->addr); - if (hardif_neigh) { - /* batadv_hardif_neigh_get() increases refcount too */ - batadv_hardif_neigh_put(hardif_neigh); - batadv_hardif_neigh_put(hardif_neigh); - } + batadv_hardif_neigh_put(neigh_node->hardif_neigh); if (bao->bat_neigh_free) bao->bat_neigh_free(neigh_node); @@ -663,6 +656,11 @@ batadv_neigh_node_new(struct batadv_orig_node *orig_node, ether_addr_copy(neigh_node->addr, neigh_addr); neigh_node->if_incoming = hard_iface; neigh_node->orig_node = orig_node; + neigh_node->last_seen = jiffies; + + /* increment unique neighbor refcount */ + kref_get(&hardif_neigh->refcount); + neigh_node->hardif_neigh = hardif_neigh; /* extra reference for return */ kref_init(&neigh_node->refcount); @@ -672,9 +670,6 @@ batadv_neigh_node_new(struct batadv_orig_node *orig_node, hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); spin_unlock_bh(&orig_node->neigh_list_lock); - /* increment unique neighbor refcount */ - kref_get(&hardif_neigh->refcount); - batadv_dbg(BATADV_DBG_BATMAN, orig_node->bat_priv, "Creating new neighbor %pM for orig_node %pM on interface %s\n", neigh_addr, orig_node->orig, hard_iface->net_dev->name); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 4dd646a..b781bf7 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -105,6 +105,15 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, neigh_node = NULL; spin_lock_bh(&orig_node->neigh_list_lock); + /* curr_router used earlier may not be the current orig_ifinfo->router + * anymore because it was dereferenced outside of the neigh_list_lock + * protected region. After the new best neighbor has replace the current + * best neighbor the reference counter needs to decrease. Consequently, + * the code needs to ensure the curr_router variable contains a pointer + * to the replaced best neighbor. + */ + curr_router = rcu_dereference_protected(orig_ifinfo->router, true); + rcu_assign_pointer(orig_ifinfo->router, neigh_node); spin_unlock_bh(&orig_node->neigh_list_lock); batadv_orig_ifinfo_put(orig_ifinfo); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 3ce06e0..7641785 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -675,6 +675,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); + if (!forw_packet->own) + atomic_inc(&bat_priv->bcast_queue_left); + batadv_forw_packet_free(forw_packet); } } @@ -702,6 +705,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); + if (!forw_packet->own) + atomic_inc(&bat_priv->batman_queue_left); + batadv_forw_packet_free(forw_packet); } } diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 0710379..8a136b6 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -408,11 +408,17 @@ void batadv_interface_rx(struct net_device *soft_iface, */ nf_reset(skb); + if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) + goto dropped; + vid = batadv_get_vid(skb, 0); ethhdr = eth_hdr(skb); switch (ntohs(ethhdr->h_proto)) { case ETH_P_8021Q: + if (!pskb_may_pull(skb, VLAN_ETH_HLEN)) + goto dropped; + vhdr = (struct vlan_ethhdr *)skb->data; if (vhdr->h_vlan_encapsulated_proto != ethertype) @@ -424,8 +430,6 @@ void batadv_interface_rx(struct net_device *soft_iface, } /* skb->dev & skb->pkt_type are set here */ - if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) - goto dropped; skb->protocol = eth_type_trans(skb, soft_iface); /* should not be necessary anymore as we use skb_pull_rcsum() diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 0b43e86..9b4551a 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -215,6 +215,8 @@ static void batadv_tt_local_entry_release(struct kref *ref) tt_local_entry = container_of(ref, struct batadv_tt_local_entry, common.refcount); + batadv_softif_vlan_put(tt_local_entry->vlan); + kfree_rcu(tt_local_entry, common.rcu); } @@ -673,6 +675,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, kref_get(&tt_local->common.refcount); tt_local->last_seen = jiffies; tt_local->common.added_at = tt_local->last_seen; + tt_local->vlan = vlan; /* the batman interface mac and multicast addresses should never be * purged @@ -991,7 +994,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; struct batadv_hard_iface *primary_if; - struct batadv_softif_vlan *vlan; struct hlist_head *head; unsigned short vid; u32 i; @@ -1027,14 +1029,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) last_seen_msecs = last_seen_msecs % 1000; no_purge = tt_common_entry->flags & np_flag; - - vlan = batadv_softif_vlan_get(bat_priv, vid); - if (!vlan) { - seq_printf(seq, "Cannot retrieve VLAN %d\n", - BATADV_PRINT_VID(vid)); - continue; - } - seq_printf(seq, " * %pM %4i [%c%c%c%c%c%c] %3u.%03u (%#.8x)\n", tt_common_entry->addr, @@ -1052,9 +1046,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) BATADV_TT_CLIENT_ISOLA) ? 'I' : '.'), no_purge ? 0 : last_seen_secs, no_purge ? 0 : last_seen_msecs, - vlan->tt.crc); - - batadv_softif_vlan_put(vlan); + tt_local->vlan->tt.crc); } rcu_read_unlock(); } @@ -1099,7 +1091,6 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, { struct batadv_tt_local_entry *tt_local_entry; u16 flags, curr_flags = BATADV_NO_FLAGS; - struct batadv_softif_vlan *vlan; void *tt_entry_exists; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); @@ -1139,14 +1130,6 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, /* extra call to free the local tt entry */ batadv_tt_local_entry_put(tt_local_entry); - /* decrease the reference held for this vlan */ - vlan = batadv_softif_vlan_get(bat_priv, vid); - if (!vlan) - goto out; - - batadv_softif_vlan_put(vlan); - batadv_softif_vlan_put(vlan); - out: if (tt_local_entry) batadv_tt_local_entry_put(tt_local_entry); @@ -1219,7 +1202,6 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; - struct batadv_softif_vlan *vlan; struct hlist_node *node_tmp; struct hlist_head *head; u32 i; @@ -1241,14 +1223,6 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) struct batadv_tt_local_entry, common); - /* decrease the reference held for this vlan */ - vlan = batadv_softif_vlan_get(bat_priv, - tt_common_entry->vid); - if (vlan) { - batadv_softif_vlan_put(vlan); - batadv_softif_vlan_put(vlan); - } - batadv_tt_local_entry_put(tt_local); } spin_unlock_bh(list_lock); @@ -3309,7 +3283,6 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common; struct batadv_tt_local_entry *tt_local; - struct batadv_softif_vlan *vlan; struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -3339,13 +3312,6 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) struct batadv_tt_local_entry, common); - /* decrease the reference held for this vlan */ - vlan = batadv_softif_vlan_get(bat_priv, tt_common->vid); - if (vlan) { - batadv_softif_vlan_put(vlan); - batadv_softif_vlan_put(vlan); - } - batadv_tt_local_entry_put(tt_local); } spin_unlock_bh(list_lock); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 9abfb3e..1e47fbe 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -433,6 +433,7 @@ struct batadv_hardif_neigh_node { * @ifinfo_lock: lock protecting private ifinfo members and list * @if_incoming: pointer to incoming hard-interface * @last_seen: when last packet via this neighbor was received + * @hardif_neigh: hardif_neigh of this neighbor * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner */ @@ -444,6 +445,7 @@ struct batadv_neigh_node { spinlock_t ifinfo_lock; /* protects ifinfo_list and its members */ struct batadv_hard_iface *if_incoming; unsigned long last_seen; + struct batadv_hardif_neigh_node *hardif_neigh; struct kref refcount; struct rcu_head rcu; }; @@ -1073,10 +1075,12 @@ struct batadv_tt_common_entry { * struct batadv_tt_local_entry - translation table local entry data * @common: general translation table data * @last_seen: timestamp used for purging stale tt local entries + * @vlan: soft-interface vlan of the entry */ struct batadv_tt_local_entry { struct batadv_tt_common_entry common; unsigned long last_seen; + struct batadv_softif_vlan *vlan; }; /** @@ -1250,6 +1254,8 @@ struct batadv_forw_packet { * struct batadv_algo_ops - mesh algorithm callbacks * @list: list node for the batadv_algo_list * @name: name of the algorithm + * @bat_iface_activate: start routing mechanisms when hard-interface is brought + * up * @bat_iface_enable: init routing info when hard-interface is enabled * @bat_iface_disable: de-init routing info when hard-interface is disabled * @bat_iface_update_mac: (re-)init mac addresses of the protocol information @@ -1277,6 +1283,7 @@ struct batadv_forw_packet { struct batadv_algo_ops { struct hlist_node list; char *name; + void (*bat_iface_activate)(struct batadv_hard_iface *hard_iface); int (*bat_iface_enable)(struct batadv_hard_iface *hard_iface); void (*bat_iface_disable)(struct batadv_hard_iface *hard_iface); void (*bat_iface_update_mac)(struct batadv_hard_iface *hard_iface); diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 263b4de..60a3dbf 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -21,18 +21,19 @@ #include <asm/uaccess.h> #include "br_private.h" -/* called with RTNL */ static int get_bridge_ifindices(struct net *net, int *indices, int num) { struct net_device *dev; int i = 0; - for_each_netdev(net, dev) { + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { if (i >= num) break; if (dev->priv_flags & IFF_EBRIDGE) indices[i++] = dev->ifindex; } + rcu_read_unlock(); return i; } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 191ea66..6852f3c 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1279,6 +1279,7 @@ static int br_ip4_multicast_query(struct net_bridge *br, struct br_ip saddr; unsigned long max_delay; unsigned long now = jiffies; + unsigned int offset = skb_transport_offset(skb); __be32 group; int err = 0; @@ -1289,14 +1290,14 @@ static int br_ip4_multicast_query(struct net_bridge *br, group = ih->group; - if (skb->len == sizeof(*ih)) { + if (skb->len == offset + sizeof(*ih)) { max_delay = ih->code * (HZ / IGMP_TIMER_SCALE); if (!max_delay) { max_delay = 10 * HZ; group = 0; } - } else if (skb->len >= sizeof(*ih3)) { + } else if (skb->len >= offset + sizeof(*ih3)) { ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) goto out; @@ -1357,6 +1358,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, struct br_ip saddr; unsigned long max_delay; unsigned long now = jiffies; + unsigned int offset = skb_transport_offset(skb); const struct in6_addr *group = NULL; bool is_general_query; int err = 0; @@ -1366,8 +1368,8 @@ static int br_ip6_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; - if (skb->len == sizeof(*mld)) { - if (!pskb_may_pull(skb, sizeof(*mld))) { + if (skb->len == offset + sizeof(*mld)) { + if (!pskb_may_pull(skb, offset + sizeof(*mld))) { err = -EINVAL; goto out; } @@ -1376,7 +1378,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (max_delay) group = &mld->mld_mca; } else { - if (!pskb_may_pull(skb, sizeof(*mld2q))) { + if (!pskb_may_pull(skb, offset + sizeof(*mld2q))) { err = -EINVAL; goto out; } diff --git a/net/core/dev.c b/net/core/dev.c index 77a71cd..5c925ac 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2802,7 +2802,7 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { - features &= ~NETIF_F_CSUM_MASK; + features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } else if (illegal_highdma(skb->dev, skb)) { features &= ~NETIF_F_SG; } diff --git a/net/core/flow.c b/net/core/flow.c index 1033725..3937b1b 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -92,8 +92,11 @@ static void flow_cache_gc_task(struct work_struct *work) list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list); spin_unlock_bh(&xfrm->flow_cache_gc_lock); - list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) + list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) { flow_entry_kill(fce, xfrm); + atomic_dec(&xfrm->flow_cache_gc_count); + WARN_ON(atomic_read(&xfrm->flow_cache_gc_count) < 0); + } } static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp, @@ -101,6 +104,7 @@ static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp, struct netns_xfrm *xfrm) { if (deleted) { + atomic_add(deleted, &xfrm->flow_cache_gc_count); fcp->hash_count -= deleted; spin_lock_bh(&xfrm->flow_cache_gc_lock); list_splice_tail(gc_list, &xfrm->flow_cache_gc_list); @@ -232,6 +236,13 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, if (fcp->hash_count > fc->high_watermark) flow_cache_shrink(fc, fcp); + if (fcp->hash_count > 2 * fc->high_watermark || + atomic_read(&net->xfrm.flow_cache_gc_count) > fc->high_watermark) { + atomic_inc(&net->xfrm.flow_cache_genid); + flo = ERR_PTR(-ENOBUFS); + goto ret_object; + } + fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC); if (fle) { fle->net = net; @@ -446,6 +457,7 @@ int flow_cache_init(struct net *net) INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task); INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task); mutex_init(&net->xfrm.flow_flush_sem); + atomic_set(&net->xfrm.flow_cache_gc_count, 0); fc->hash_shift = 10; fc->low_watermark = 2 * flow_cache_hash_size(fc); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a75f7e9..65763c2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1180,14 +1180,16 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) { - struct rtnl_link_ifmap map = { - .mem_start = dev->mem_start, - .mem_end = dev->mem_end, - .base_addr = dev->base_addr, - .irq = dev->irq, - .dma = dev->dma, - .port = dev->if_port, - }; + struct rtnl_link_ifmap map; + + memset(&map, 0, sizeof(map)); + map.mem_start = dev->mem_start; + map.mem_end = dev->mem_end; + map.base_addr = dev->base_addr; + map.irq = dev->irq; + map.dma = dev->dma; + map.port = dev->if_port; + if (nla_put(skb, IFLA_MAP, sizeof(map), &map)) return -EMSGSIZE; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index d97268e..2b68418 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -975,6 +975,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) val = 65535 - 40; if (type == RTAX_MTU && val > 65535 - 15) val = 65535 - 15; + if (type == RTAX_HOPLIMIT && val > 255) + val = 255; if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) return -EINVAL; fi->fib_metrics[type - 1] = val; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index a39068b..a6962cc 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -228,8 +228,6 @@ static int fou_gro_complete(struct sk_buff *skb, int nhoff, int err = -ENOSYS; const struct net_offload **offloads; - udp_tunnel_gro_complete(skb, nhoff); - rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); @@ -238,6 +236,8 @@ static int fou_gro_complete(struct sk_buff *skb, int nhoff, err = ops->callbacks.gro_complete(skb, nhoff); + skb_set_inner_mac_header(skb, nhoff); + out_unlock: rcu_read_unlock(); @@ -414,6 +414,8 @@ static int gue_gro_complete(struct sk_buff *skb, int nhoff, err = ops->callbacks.gro_complete(skb, nhoff + guehlen); + skb_set_inner_mac_header(skb, nhoff + guehlen); + out_unlock: rcu_read_unlock(); return err; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index bc68ece..0d9e9d7 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -470,6 +470,7 @@ static int inet_reuseport_add_sock(struct sock *sk, const struct sock *sk2, bool match_wildcard)) { + struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; struct sock *sk2; struct hlist_nulls_node *node; kuid_t uid = sock_i_uid(sk); @@ -479,6 +480,7 @@ static int inet_reuseport_add_sock(struct sock *sk, sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && sk2->sk_bound_dev_if == sk->sk_bound_dev_if && + inet_csk(sk2)->icsk_bind_hash == tb && sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && saddr_same(sk, sk2, false)) return reuseport_add_sock(sk, sk2); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index af5d1f3..4cc8421 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -179,6 +179,7 @@ static __be16 tnl_flags_to_gre_flags(__be16 tflags) return flags; } +/* Fills in tpi and returns header length to be pulled. */ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err) { @@ -238,7 +239,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, return -EINVAL; } } - return iptunnel_pull_header(skb, hdr_len, tpi->proto, false); + return hdr_len; } static void ipgre_err(struct sk_buff *skb, u32 info, @@ -341,7 +342,7 @@ static void gre_err(struct sk_buff *skb, u32 info) struct tnl_ptk_info tpi; bool csum_err = false; - if (parse_gre_header(skb, &tpi, &csum_err)) { + if (parse_gre_header(skb, &tpi, &csum_err) < 0) { if (!csum_err) /* ignore csum errors. */ return; } @@ -397,7 +398,10 @@ static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) iph->saddr, iph->daddr, tpi->key); if (tunnel) { - skb_pop_mac_header(skb); + if (tunnel->dev->type != ARPHRD_NONE) + skb_pop_mac_header(skb); + else + skb_reset_mac_header(skb); if (tunnel->collect_md) { __be16 flags; __be64 tun_id; @@ -419,6 +423,7 @@ static int gre_rcv(struct sk_buff *skb) { struct tnl_ptk_info tpi; bool csum_err = false; + int hdr_len; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { @@ -428,7 +433,10 @@ static int gre_rcv(struct sk_buff *skb) } #endif - if (parse_gre_header(skb, &tpi, &csum_err) < 0) + hdr_len = parse_gre_header(skb, &tpi, &csum_err); + if (hdr_len < 0) + goto drop; + if (iptunnel_pull_header(skb, hdr_len, tpi.proto, false) < 0) goto drop; if (ipgre_rcv(skb, &tpi) == PACKET_RCVD) @@ -523,7 +531,8 @@ static struct rtable *gre_get_rt(struct sk_buff *skb, return ip_route_output_key(net, fl); } -static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) +static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, + __be16 proto) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; @@ -575,7 +584,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) } flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY); - build_header(skb, tunnel_hlen, flags, htons(ETH_P_TEB), + build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key(tun_info->key.tun_id), 0); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; @@ -616,7 +625,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, const struct iphdr *tnl_params; if (tunnel->collect_md) { - gre_fb_xmit(skb, dev); + gre_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; } @@ -660,7 +669,7 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, struct ip_tunnel *tunnel = netdev_priv(dev); if (tunnel->collect_md) { - gre_fb_xmit(skb, dev); + gre_fb_xmit(skb, dev, htons(ETH_P_TEB)); return NETDEV_TX_OK; } @@ -893,7 +902,7 @@ static int ipgre_tunnel_init(struct net_device *dev) netif_keep_dst(dev); dev->addr_len = 4; - if (iph->daddr) { + if (iph->daddr && !tunnel->collect_md) { #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { if (!iph->saddr) @@ -902,8 +911,9 @@ static int ipgre_tunnel_init(struct net_device *dev) dev->header_ops = &ipgre_header_ops; } #endif - } else + } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; + } return ip_tunnel_init(dev); } @@ -946,6 +956,11 @@ static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) if (flags & (GRE_VERSION|GRE_ROUTING)) return -EINVAL; + if (data[IFLA_GRE_COLLECT_METADATA] && + data[IFLA_GRE_ENCAP_TYPE] && + nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]) != TUNNEL_ENCAP_NONE) + return -EINVAL; + return 0; } @@ -1019,6 +1034,8 @@ static void ipgre_netlink_parms(struct net_device *dev, struct ip_tunnel *t = netdev_priv(dev); t->collect_md = true; + if (dev->type == ARPHRD_IPGRE) + dev->type = ARPHRD_NONE; } } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 6aad019..a69ed94 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -326,12 +326,12 @@ static int ip_tunnel_bind_dev(struct net_device *dev) if (!IS_ERR(rt)) { tdev = rt->dst.dev; - dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, - fl4.saddr); ip_rt_put(rt); } if (dev->type != ARPHRD_ETHER) dev->flags |= IFF_POINTOPOINT; + + dst_cache_reset(&tunnel->dst_cache); } if (!tdev && tunnel->parms.link) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 5cf10b7..a917903 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -156,6 +156,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ int err; + int mtu; if (!dst) { dev->stats.tx_carrier_errors++; @@ -192,6 +193,23 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_count = 0; } + mtu = dst_mtu(dst); + if (skb->len > mtu) { + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); + if (skb->protocol == htons(ETH_P_IP)) { + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + } else { + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + } + + dst_release(dst); + goto tx_error; + } + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 441ae9d..79a03b8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2640,8 +2640,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) */ if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || skb_headroom(skb) >= 0xFFFF)) { - struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, - GFP_ATOMIC); + struct sk_buff *nskb; + + skb_mstamp_get(&skb->skb_mstamp); + nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : -ENOBUFS; } else { diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 0ed2daf..e330c0e 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -399,6 +399,11 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff) uh->len = newlen; + /* Set encapsulation before calling into inner gro_complete() functions + * to make them set up the inner offsets. + */ + skb->encapsulation = 1; + rcu_read_lock(); uo_priv = rcu_dereference(udp_offload_base); @@ -421,9 +426,6 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff) if (skb->remcsum_offload) skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM; - skb->encapsulation = 1; - skb_set_inner_mac_header(skb, nhoff + sizeof(struct udphdr)); - return err; } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 0a37ddc..0013cac 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -445,6 +445,8 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) if (__ipv6_addr_needs_scope_id(addr_type)) iif = skb->dev->ifindex; + else + iif = l3mdev_master_ifindex(skb->dev); /* * Must not send error if the source does not uniquely @@ -499,9 +501,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; - if (!fl6.flowi6_oif) - fl6.flowi6_oif = l3mdev_master_ifindex(skb->dev); - dst = icmpv6_route_lookup(net, skb, sk, &fl6); if (IS_ERR(dst)) goto out; diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 2ae3c4f..41f18de 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -120,8 +120,7 @@ nla_put_failure: static int ila_encap_nlsize(struct lwtunnel_state *lwtstate) { - /* No encapsulation overhead */ - return 0; + return nla_total_size(sizeof(u64)); /* ILA_ATTR_LOCATOR */ } static int ila_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d916d6a..6f32944 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1750,6 +1750,8 @@ static int ip6_convert_metrics(struct mx6_config *mxc, } else { val = nla_get_u32(nla); } + if (type == RTAX_HOPLIMIT && val > 255) + val = 255; if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) goto err; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 711d209..f443c6b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -810,8 +810,13 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 fl6.flowi6_proto = IPPROTO_TCP; if (rt6_need_strict(&fl6.daddr) && !oif) fl6.flowi6_oif = tcp_v6_iif(skb); - else + else { + if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) + oif = skb->skb_iif; + fl6.flowi6_oif = oif; + } + fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark); fl6.fl6_dport = t1->dest; fl6.fl6_sport = t1->source; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index afca2eb..6edfa99 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1376,9 +1376,9 @@ static int l2tp_tunnel_sock_create(struct net *net, memcpy(&udp_conf.peer_ip6, cfg->peer_ip6, sizeof(udp_conf.peer_ip6)); udp_conf.use_udp6_tx_checksums = - cfg->udp6_zero_tx_checksums; + ! cfg->udp6_zero_tx_checksums; udp_conf.use_udp6_rx_checksums = - cfg->udp6_zero_rx_checksums; + ! cfg->udp6_zero_rx_checksums; } else #endif { diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index b3c52e3..8ae3ed9 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -626,6 +626,7 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb) if (llc->cmsg_flags & LLC_CMSG_PKTINFO) { struct llc_pktinfo info; + memset(&info, 0, sizeof(info)); info.lpi_ifindex = llc_sk(skb->sk)->dev->ifindex; llc_pdu_decode_dsap(skb, &info.lpi_sap); llc_pdu_decode_da(skb, info.lpi_mac); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 453b4e74..e1cb22c 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1761,7 +1761,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ret = dev_alloc_name(ndev, ndev->name); if (ret < 0) { - free_netdev(ndev); + ieee80211_if_free(ndev); return ret; } @@ -1847,7 +1847,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ret = register_netdevice(ndev); if (ret) { - free_netdev(ndev); + ieee80211_if_free(ndev); return ret; } } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index afde5f5..e27fd17 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -66,7 +66,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_locks); __cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock); EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock); -static __read_mostly spinlock_t nf_conntrack_locks_all_lock; +static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; void nf_conntrack_lock(spinlock_t *lock) __acquires(lock) @@ -1778,6 +1778,7 @@ void nf_conntrack_init_end(void) int nf_conntrack_init_net(struct net *net) { + static atomic64_t unique_id; int ret = -ENOMEM; int cpu; @@ -1800,7 +1801,8 @@ int nf_conntrack_init_net(struct net *net) if (!net->ct.stat) goto err_pcpu_lists; - net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net); + net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%llu", + (u64)atomic64_inc_return(&unique_id)); if (!net->ct.slabname) goto err_slabname; diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 4c2b4c0..dbd0803 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -96,6 +96,8 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl, return -EINVAL; if (flags & NFACCT_F_OVERQUOTA) return -EINVAL; + if ((flags & NFACCT_F_QUOTA) && !tb[NFACCT_QUOTA]) + return -EINVAL; size += sizeof(u64); } diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 29d2c31..daf45da 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -236,6 +236,7 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par) list_del(&info->timer->entry); del_timer_sync(&info->timer->timer); + cancel_work_sync(&info->timer->work); sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); kfree(info->timer->attr.attr.name); kfree(info->timer); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index b5fea110..10c84d8 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -776,6 +776,19 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, return -EINVAL; } + /* Userspace may decide to perform a ct lookup without a helper + * specified followed by a (recirculate and) commit with one. + * Therefore, for unconfirmed connections which we will commit, + * we need to attach the helper here. + */ + if (!nf_ct_is_confirmed(ct) && info->commit && + info->helper && !nfct_help(ct)) { + int err = __nf_ct_try_assign_helper(ct, info->ct, + GFP_ATOMIC); + if (err) + return err; + } + /* Call the helper only if: * - nf_conntrack_in() was executed above ("!cached") for a * confirmed connection, or diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 61ed2a8..86187da 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -127,7 +127,7 @@ void rds_tcp_restore_callbacks(struct socket *sock, /* * This is the only path that sets tc->t_sock. Send and receive trust that - * it is set. The RDS_CONN_CONNECTED bit protects those paths from being + * it is set. The RDS_CONN_UP bit protects those paths from being * called while it isn't set. */ void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn) @@ -216,6 +216,7 @@ static int rds_tcp_conn_alloc(struct rds_connection *conn, gfp_t gfp) if (!tc) return -ENOMEM; + mutex_init(&tc->t_conn_lock); tc->t_sock = NULL; tc->t_tinc = NULL; tc->t_tinc_hdr_rem = sizeof(struct rds_header); diff --git a/net/rds/tcp.h b/net/rds/tcp.h index 64f873c..41c2283 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -12,6 +12,10 @@ struct rds_tcp_connection { struct list_head t_tcp_node; struct rds_connection *conn; + /* t_conn_lock synchronizes the connection establishment between + * rds_tcp_accept_one and rds_tcp_conn_connect + */ + struct mutex t_conn_lock; struct socket *t_sock; void *t_orig_write_space; void *t_orig_data_ready; diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index 5cb1687..49a3fcf 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -78,7 +78,14 @@ int rds_tcp_conn_connect(struct rds_connection *conn) struct socket *sock = NULL; struct sockaddr_in src, dest; int ret; + struct rds_tcp_connection *tc = conn->c_transport_data; + + mutex_lock(&tc->t_conn_lock); + if (rds_conn_up(conn)) { + mutex_unlock(&tc->t_conn_lock); + return 0; + } ret = sock_create_kern(rds_conn_net(conn), PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); if (ret < 0) @@ -120,6 +127,7 @@ int rds_tcp_conn_connect(struct rds_connection *conn) } out: + mutex_unlock(&tc->t_conn_lock); if (sock) sock_release(sock); return ret; diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 0936a4a..be263cd 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -76,7 +76,9 @@ int rds_tcp_accept_one(struct socket *sock) struct rds_connection *conn; int ret; struct inet_sock *inet; - struct rds_tcp_connection *rs_tcp; + struct rds_tcp_connection *rs_tcp = NULL; + int conn_state; + struct sock *nsk; ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family, sock->sk->sk_type, sock->sk->sk_protocol, @@ -115,28 +117,44 @@ int rds_tcp_accept_one(struct socket *sock) * rds_tcp_state_change() will do that cleanup */ rs_tcp = (struct rds_tcp_connection *)conn->c_transport_data; - if (rs_tcp->t_sock && - ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr)) { - struct sock *nsk = new_sock->sk; - - nsk->sk_user_data = NULL; - nsk->sk_prot->disconnect(nsk, 0); - tcp_done(nsk); - new_sock = NULL; - ret = 0; - goto out; - } else if (rs_tcp->t_sock) { - rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp); - conn->c_outgoing = 0; - } - rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING); + mutex_lock(&rs_tcp->t_conn_lock); + conn_state = rds_conn_state(conn); + if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_UP) + goto rst_nsk; + if (rs_tcp->t_sock) { + /* Need to resolve a duelling SYN between peers. + * We have an outstanding SYN to this peer, which may + * potentially have transitioned to the RDS_CONN_UP state, + * so we must quiesce any send threads before resetting + * c_transport_data. + */ + wait_event(conn->c_waitq, + !test_bit(RDS_IN_XMIT, &conn->c_flags)); + if (ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr)) { + goto rst_nsk; + } else if (rs_tcp->t_sock) { + rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp); + conn->c_outgoing = 0; + } + } rds_tcp_set_callbacks(new_sock, conn); - rds_connect_complete(conn); + rds_connect_complete(conn); /* marks RDS_CONN_UP */ + new_sock = NULL; + ret = 0; + goto out; +rst_nsk: + /* reset the newly returned accept sock and bail */ + nsk = new_sock->sk; + rds_tcp_stats_inc(s_tcp_listen_closed_stale); + nsk->sk_user_data = NULL; + nsk->sk_prot->disconnect(nsk, 0); + tcp_done(nsk); new_sock = NULL; ret = 0; - out: + if (rs_tcp) + mutex_unlock(&rs_tcp->t_conn_lock); if (new_sock) sock_release(new_sock); return ret; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index c589a9b..343d011 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -423,7 +423,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, u16 ife_type = 0; u8 *daddr = NULL; u8 *saddr = NULL; - int ret = 0; + int ret = 0, exists = 0; int err; err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy); @@ -435,25 +435,29 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_IFE_PARMS]); + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; + if (parm->flags & IFE_ENCODE) { /* Until we get issued the ethertype, we cant have * a default.. **/ if (!tb[TCA_IFE_TYPE]) { + if (exists) + tcf_hash_release(a, bind); pr_info("You MUST pass etherype for encoding\n"); return -EINVAL; } } - if (!tcf_hash_check(tn, parm->index, a, bind)) { + if (!exists) { ret = tcf_hash_create(tn, parm->index, est, a, sizeof(*ife), bind, false); if (ret) return ret; ret = ACT_P_CREATED; } else { - if (bind) /* dont override defaults */ - return 0; tcf_hash_release(a, bind); if (!ovr) return -EEXIST; @@ -495,6 +499,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, NULL); if (err) { metadata_parse_err: + if (exists) + tcf_hash_release(a, bind); if (ret == ACT_P_CREATED) _tcf_ife_cleanup(a, bind); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 350e134..8b52700 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -96,7 +96,7 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla, struct tcf_ipt *ipt; struct xt_entry_target *td, *t; char *tname; - int ret = 0, err; + int ret = 0, err, exists = 0; u32 hook = 0; u32 index = 0; @@ -107,18 +107,23 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla, if (err < 0) return err; - if (tb[TCA_IPT_HOOK] == NULL) - return -EINVAL; - if (tb[TCA_IPT_TARG] == NULL) + if (tb[TCA_IPT_INDEX] != NULL) + index = nla_get_u32(tb[TCA_IPT_INDEX]); + + exists = tcf_hash_check(tn, index, a, bind); + if (exists && bind) + return 0; + + if (tb[TCA_IPT_HOOK] == NULL || tb[TCA_IPT_TARG] == NULL) { + if (exists) + tcf_hash_release(a, bind); return -EINVAL; + } td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]); if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) return -EINVAL; - if (tb[TCA_IPT_INDEX] != NULL) - index = nla_get_u32(tb[TCA_IPT_INDEX]); - if (!tcf_hash_check(tn, index, a, bind)) { ret = tcf_hash_create(tn, index, est, a, sizeof(*ipt), bind, false); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index e8a760c..8f3948d 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -61,7 +61,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct tc_mirred *parm; struct tcf_mirred *m; struct net_device *dev; - int ret, ok_push = 0; + int ret, ok_push = 0, exists = 0; if (nla == NULL) return -EINVAL; @@ -71,17 +71,27 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (tb[TCA_MIRRED_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_MIRRED_PARMS]); + + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; + switch (parm->eaction) { case TCA_EGRESS_MIRROR: case TCA_EGRESS_REDIR: break; default: + if (exists) + tcf_hash_release(a, bind); return -EINVAL; } if (parm->ifindex) { dev = __dev_get_by_index(net, parm->ifindex); - if (dev == NULL) + if (dev == NULL) { + if (exists) + tcf_hash_release(a, bind); return -ENODEV; + } switch (dev->type) { case ARPHRD_TUNNEL: case ARPHRD_TUNNEL6: @@ -99,7 +109,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, dev = NULL; } - if (!tcf_hash_check(tn, parm->index, a, bind)) { + if (!exists) { if (dev == NULL) return -EINVAL; ret = tcf_hash_create(tn, parm->index, est, a, @@ -108,9 +118,6 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, return ret; ret = ACT_P_CREATED; } else { - if (bind) - return 0; - tcf_hash_release(a, bind); if (!ovr) return -EEXIST; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 75b2be1..3a33fb6 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -87,7 +87,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, struct tc_defact *parm; struct tcf_defact *d; char *defdata; - int ret = 0, err; + int ret = 0, err, exists = 0; if (nla == NULL) return -EINVAL; @@ -99,13 +99,21 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, if (tb[TCA_DEF_PARMS] == NULL) return -EINVAL; - if (tb[TCA_DEF_DATA] == NULL) - return -EINVAL; parm = nla_data(tb[TCA_DEF_PARMS]); + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; + + if (tb[TCA_DEF_DATA] == NULL) { + if (exists) + tcf_hash_release(a, bind); + return -EINVAL; + } + defdata = nla_data(tb[TCA_DEF_DATA]); - if (!tcf_hash_check(tn, parm->index, a, bind)) { + if (!exists) { ret = tcf_hash_create(tn, parm->index, est, a, sizeof(*d), bind, false); if (ret) @@ -122,8 +130,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, } else { d = to_defact(a); - if (bind) - return 0; tcf_hash_release(a, bind); if (!ovr) return -EEXIST; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index cfcdbdc..69da5a8 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -69,7 +69,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct tcf_skbedit *d; u32 flags = 0, *priority = NULL, *mark = NULL; u16 *queue_mapping = NULL; - int ret = 0, err; + int ret = 0, err, exists = 0; if (nla == NULL) return -EINVAL; @@ -96,12 +96,18 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, mark = nla_data(tb[TCA_SKBEDIT_MARK]); } - if (!flags) - return -EINVAL; - parm = nla_data(tb[TCA_SKBEDIT_PARMS]); - if (!tcf_hash_check(tn, parm->index, a, bind)) { + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; + + if (!flags) { + tcf_hash_release(a, bind); + return -EINVAL; + } + + if (!exists) { ret = tcf_hash_create(tn, parm->index, est, a, sizeof(*d), bind, false); if (ret) @@ -111,8 +117,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, ret = ACT_P_CREATED; } else { d = to_skbedit(a); - if (bind) - return 0; tcf_hash_release(a, bind); if (!ovr) return -EEXIST; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index bab8ae0..c45f926 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -77,7 +77,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, int action; __be16 push_vid = 0; __be16 push_proto = 0; - int ret = 0; + int ret = 0, exists = 0; int err; if (!nla) @@ -90,15 +90,25 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (!tb[TCA_VLAN_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_VLAN_PARMS]); + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; + switch (parm->v_action) { case TCA_VLAN_ACT_POP: break; case TCA_VLAN_ACT_PUSH: - if (!tb[TCA_VLAN_PUSH_VLAN_ID]) + if (!tb[TCA_VLAN_PUSH_VLAN_ID]) { + if (exists) + tcf_hash_release(a, bind); return -EINVAL; + } push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]); - if (push_vid >= VLAN_VID_MASK) + if (push_vid >= VLAN_VID_MASK) { + if (exists) + tcf_hash_release(a, bind); return -ERANGE; + } if (tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]) { push_proto = nla_get_be16(tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]); @@ -114,11 +124,13 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, } break; default: + if (exists) + tcf_hash_release(a, bind); return -EINVAL; } action = parm->v_action; - if (!tcf_hash_check(tn, parm->index, a, bind)) { + if (!exists) { ret = tcf_hash_create(tn, parm->index, est, a, sizeof(*v), bind, false); if (ret) @@ -126,8 +138,6 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, ret = ACT_P_CREATED; } else { - if (bind) - return 0; tcf_hash_release(a, bind); if (!ovr) return -EEXIST; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 9640bb3..4befe97 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -395,6 +395,25 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) sch->q.qlen++; } +/* netem can't properly corrupt a megapacket (like we get from GSO), so instead + * when we statistically choose to corrupt one, we instead segment it, returning + * the first packet to be corrupted, and re-enqueue the remaining frames + */ +static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch) +{ + struct sk_buff *segs; + netdev_features_t features = netif_skb_features(skb); + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + + if (IS_ERR_OR_NULL(segs)) { + qdisc_reshape_fail(skb, sch); + return NULL; + } + consume_skb(skb); + return segs; +} + /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. @@ -407,7 +426,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; struct sk_buff *skb2; + struct sk_buff *segs = NULL; + unsigned int len = 0, last_len, prev_len = qdisc_pkt_len(skb); + int nb = 0; int count = 1; + int rc = NET_XMIT_SUCCESS; /* Random duplication */ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) @@ -453,10 +476,23 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) * do it now in software before we mangle it. */ if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) { + if (skb_is_gso(skb)) { + segs = netem_segment(skb, sch); + if (!segs) + return NET_XMIT_DROP; + } else { + segs = skb; + } + + skb = segs; + segs = segs->next; + if (!(skb = skb_unshare(skb, GFP_ATOMIC)) || (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(skb))) - return qdisc_drop(skb, sch); + skb_checksum_help(skb))) { + rc = qdisc_drop(skb, sch); + goto finish_segs; + } skb->data[prandom_u32() % skb_headlen(skb)] ^= 1<<(prandom_u32() % 8); @@ -516,6 +552,27 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) sch->qstats.requeues++; } +finish_segs: + if (segs) { + while (segs) { + skb2 = segs->next; + segs->next = NULL; + qdisc_skb_cb(segs)->pkt_len = segs->len; + last_len = segs->len; + rc = qdisc_enqueue(segs, sch); + if (rc != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(rc)) + qdisc_qstats_drop(sch); + } else { + nb++; + len += last_len; + } + segs = skb2; + } + sch->q.qlen += nb; + if (nb > 1) + qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len); + } return NET_XMIT_SUCCESS; } diff --git a/net/tipc/node.c b/net/tipc/node.c index ace178f..9aaa1bc 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1444,6 +1444,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) int bearer_id = b->identity; struct tipc_link_entry *le; u16 bc_ack = msg_bcast_ack(hdr); + u32 self = tipc_own_addr(net); int rc = 0; __skb_queue_head_init(&xmitq); @@ -1460,6 +1461,10 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) return tipc_node_bc_rcv(net, skb, bearer_id); } + /* Discard unicast link messages destined for another node */ + if (unlikely(!msg_short(hdr) && (msg_destnode(hdr) != self))) + goto discard; + /* Locate neighboring node that sent packet */ n = tipc_node_find(net, msg_prevnode(hdr)); if (unlikely(!n)) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 3dce53e..b5f1221 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1808,27 +1808,8 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, else if (sk->sk_shutdown & RCV_SHUTDOWN) err = 0; - if (copied > 0) { - /* We only do these additional bookkeeping/notification steps - * if we actually copied something out of the queue pair - * instead of just peeking ahead. - */ - - if (!(flags & MSG_PEEK)) { - /* If the other side has shutdown for sending and there - * is nothing more to read, then modify the socket - * state. - */ - if (vsk->peer_shutdown & SEND_SHUTDOWN) { - if (vsock_stream_has_data(vsk) <= 0) { - sk->sk_state = SS_UNCONNECTED; - sock_set_flag(sk, SOCK_DONE); - sk->sk_state_change(sk); - } - } - } + if (copied > 0) err = copied; - } out: release_sock(sk); diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index 7ecd04c..997ff7b 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -277,6 +277,7 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk, memset(&theirs, 0, sizeof(theirs)); memcpy(new, ours, sizeof(*new)); + memset(dte, 0, sizeof(*dte)); len = x25_parse_facilities(skb, &theirs, dte, &x25->vc_facil_mask); if (len < 0) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index ff4a91f..637387b 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -99,6 +99,9 @@ static int xfrm_output_one(struct sk_buff *skb, int err) skb_dst_force(skb); + /* Inner headers are invalid now. */ + skb->encapsulation = 0; + err = x->type->output(x, skb); if (err == -EINPROGRESS) goto out; diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c index 8d8d1ec..9b96f4f 100644 --- a/samples/bpf/trace_output_kern.c +++ b/samples/bpf/trace_output_kern.c @@ -18,7 +18,6 @@ int bpf_prog1(struct pt_regs *ctx) u64 cookie; } data; - memset(&data, 0, sizeof(data)); data.pid = bpf_get_current_pid_tgid(); data.cookie = 0x12345678; diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 161dd0d..a915507 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -371,6 +371,49 @@ static void do_usb_table(void *symval, unsigned long size, do_usb_entry_multi(symval + i, mod); } +static void do_of_entry_multi(void *symval, struct module *mod) +{ + char alias[500]; + int len; + char *tmp; + + DEF_FIELD_ADDR(symval, of_device_id, name); + DEF_FIELD_ADDR(symval, of_device_id, type); + DEF_FIELD_ADDR(symval, of_device_id, compatible); + + len = sprintf(alias, "of:N%sT%s", (*name)[0] ? *name : "*", + (*type)[0] ? *type : "*"); + + if (compatible[0]) + sprintf(&alias[len], "%sC%s", (*type)[0] ? "*" : "", + *compatible); + + /* Replace all whitespace with underscores */ + for (tmp = alias; tmp && *tmp; tmp++) + if (isspace(*tmp)) + *tmp = '_'; + + buf_printf(&mod->dev_table_buf, "MODULE_ALIAS(\"%s\");\n", alias); + strcat(alias, "C"); + add_wildcard(alias); + buf_printf(&mod->dev_table_buf, "MODULE_ALIAS(\"%s\");\n", alias); +} + +static void do_of_table(void *symval, unsigned long size, + struct module *mod) +{ + unsigned int i; + const unsigned long id_size = SIZE_of_device_id; + + device_id_check(mod->name, "of", size, id_size, symval); + + /* Leave last one: it's the terminator. */ + size -= id_size; + + for (i = 0; i < size; i += id_size) + do_of_entry_multi(symval + i, mod); +} + /* Looks like: hid:bNvNpN */ static int do_hid_entry(const char *filename, void *symval, char *alias) @@ -684,30 +727,6 @@ static int do_pcmcia_entry(const char *filename, } ADD_TO_DEVTABLE("pcmcia", pcmcia_device_id, do_pcmcia_entry); -static int do_of_entry (const char *filename, void *symval, char *alias) -{ - int len; - char *tmp; - DEF_FIELD_ADDR(symval, of_device_id, name); - DEF_FIELD_ADDR(symval, of_device_id, type); - DEF_FIELD_ADDR(symval, of_device_id, compatible); - - len = sprintf(alias, "of:N%sT%s", (*name)[0] ? *name : "*", - (*type)[0] ? *type : "*"); - - if (compatible[0]) - sprintf(&alias[len], "%sC%s", (*type)[0] ? "*" : "", - *compatible); - - /* Replace all whitespace with underscores */ - for (tmp = alias; tmp && *tmp; tmp++) - if (isspace (*tmp)) - *tmp = '_'; - - return 1; -} -ADD_TO_DEVTABLE("of", of_device_id, do_of_entry); - static int do_vio_entry(const char *filename, void *symval, char *alias) { @@ -1348,6 +1367,8 @@ void handle_moddevtable(struct module *mod, struct elf_info *info, /* First handle the "special" cases */ if (sym_is(name, namelen, "usb")) do_usb_table(symval, sym->st_size, mod); + if (sym_is(name, namelen, "of")) + do_of_table(symval, sym->st_size, mod); else if (sym_is(name, namelen, "pnp")) do_pnp_device_entry(symval, sym->st_size, mod); else if (sym_is(name, namelen, "pnp_card")) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index be09e2c..3cd0a58 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -884,10 +884,10 @@ static char *func_tokens[] = { "BPRM_CHECK", "MODULE_CHECK", "FIRMWARE_CHECK", + "POST_SETATTR", "KEXEC_KERNEL_CHECK", "KEXEC_INITRAMFS_CHECK", - "POLICY_CHECK", - "POST_SETATTR" + "POLICY_CHECK" }; void *ima_policy_start(struct seq_file *m, loff_t *pos) diff --git a/sound/pci/hda/hda_sysfs.c b/sound/pci/hda/hda_sysfs.c index 64e0d1d..9739fce 100644 --- a/sound/pci/hda/hda_sysfs.c +++ b/sound/pci/hda/hda_sysfs.c @@ -141,14 +141,6 @@ static int reconfig_codec(struct hda_codec *codec) err = snd_hda_codec_configure(codec); if (err < 0) goto error; - /* rebuild PCMs */ - err = snd_hda_codec_build_pcms(codec); - if (err < 0) - goto error; - /* rebuild mixers */ - err = snd_hda_codec_build_controls(codec); - if (err < 0) - goto error; err = snd_card_register(codec->card); error: snd_hda_power_down(codec); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 1483f85..a010d70 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -3401,6 +3401,9 @@ static int patch_atihdmi(struct hda_codec *codec) spec->ops.pin_hbr_setup = atihdmi_pin_hbr_setup; spec->ops.setup_stream = atihdmi_setup_stream; + spec->chmap.ops.pin_get_slot_channel = atihdmi_pin_get_slot_channel; + spec->chmap.ops.pin_set_slot_channel = atihdmi_pin_set_slot_channel; + if (!has_amd_full_remap_support(codec)) { /* override to ATI/AMD-specific versions with pairwise mapping */ spec->chmap.ops.chmap_cea_alloc_validate_get_type = @@ -3408,10 +3411,6 @@ static int patch_atihdmi(struct hda_codec *codec) spec->chmap.ops.cea_alloc_to_tlv_chmap = atihdmi_paired_cea_alloc_to_tlv_chmap; spec->chmap.ops.chmap_validate = atihdmi_paired_chmap_validate; - spec->chmap.ops.pin_get_slot_channel = - atihdmi_pin_get_slot_channel; - spec->chmap.ops.pin_set_slot_channel = - atihdmi_pin_set_slot_channel; } /* ATI/AMD converters do not advertise all of their capabilities */ diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index ac4490a..4918ffa 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6426,6 +6426,7 @@ enum { ALC668_FIXUP_DELL_DISABLE_AAMIX, ALC668_FIXUP_DELL_XPS13, ALC662_FIXUP_ASUS_Nx50, + ALC668_FIXUP_ASUS_Nx51, }; static const struct hda_fixup alc662_fixups[] = { @@ -6672,6 +6673,15 @@ static const struct hda_fixup alc662_fixups[] = { .chained = true, .chain_id = ALC662_FIXUP_BASS_1A }, + [ALC668_FIXUP_ASUS_Nx51] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + {0x1a, 0x90170151}, /* bass speaker */ + {} + }, + .chained = true, + .chain_id = ALC662_FIXUP_BASS_CHMAP, + }, }; static const struct snd_pci_quirk alc662_fixup_tbl[] = { @@ -6694,11 +6704,14 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0698, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x069f, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), + SND_PCI_QUIRK(0x1043, 0x1080, "Asus UX501VW", ALC668_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_ASUS_Nx50), SND_PCI_QUIRK(0x1043, 0x13df, "Asus N550JX", ALC662_FIXUP_BASS_1A), SND_PCI_QUIRK(0x1043, 0x129d, "Asus N750", ALC662_FIXUP_ASUS_Nx50), SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_MODE4_CHMAP), SND_PCI_QUIRK(0x1043, 0x15a7, "ASUS UX51VZH", ALC662_FIXUP_BASS_16), + SND_PCI_QUIRK(0x1043, 0x177d, "ASUS N551", ALC668_FIXUP_ASUS_Nx51), + SND_PCI_QUIRK(0x1043, 0x17bd, "ASUS N751", ALC668_FIXUP_ASUS_Nx51), SND_PCI_QUIRK(0x1043, 0x1b73, "ASUS N55SF", ALC662_FIXUP_BASS_16), SND_PCI_QUIRK(0x1043, 0x1bf3, "ASUS N76VZ", ALC662_FIXUP_BASS_MODE4_CHMAP), SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT), diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 0adfd95..6adde45 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1137,8 +1137,11 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x047F, 0x0415): /* Plantronics BT-300 */ case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ + case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ + case USB_ID(0x1de7, 0x0013): /* Phoenix Audio MT202exe */ case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */ + case USB_ID(0x1de7, 0x0114): /* Phoenix Audio MT202pcs */ case USB_ID(0x21B4, 0x0081): /* AudioQuest DragonFly */ return true; } diff --git a/tools/Makefile b/tools/Makefile index 60c7e6c..6bf68fe 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -137,7 +137,8 @@ libsubcmd_clean: $(call descend,lib/subcmd,clean) perf_clean: - $(call descend,$(@:_clean=),clean) + $(Q)mkdir -p $(PERF_O) . + $(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir= clean selftests_clean: $(call descend,testing/$(@:_clean=),clean) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 6b77072..57c8f98 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -30,6 +30,7 @@ endef FEATURE_TESTS_BASIC := \ backtrace \ dwarf \ + dwarf_getlocations \ fortify-source \ sync-compare-and-swap \ glibc \ @@ -48,6 +49,10 @@ FEATURE_TESTS_BASIC := \ libslang \ libcrypto \ libunwind \ + libunwind-x86 \ + libunwind-x86_64 \ + libunwind-arm \ + libunwind-aarch64 \ pthread-attr-setaffinity-np \ stackprotector-all \ timerfd \ @@ -68,7 +73,9 @@ FEATURE_TESTS_EXTRA := \ libbabeltrace \ liberty \ liberty-z \ - libunwind-debug-frame + libunwind-debug-frame \ + libunwind-debug-frame-arm \ + libunwind-debug-frame-aarch64 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC) @@ -78,6 +85,7 @@ endif FEATURE_DISPLAY ?= \ dwarf \ + dwarf_getlocations \ glibc \ gtk2 \ libaudit \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index c5f4c41..3d88f09 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -3,6 +3,7 @@ FILES= \ test-backtrace.bin \ test-bionic.bin \ test-dwarf.bin \ + test-dwarf_getlocations.bin \ test-fortify-source.bin \ test-sync-compare-and-swap.bin \ test-glibc.bin \ @@ -26,6 +27,12 @@ FILES= \ test-libcrypto.bin \ test-libunwind.bin \ test-libunwind-debug-frame.bin \ + test-libunwind-x86.bin \ + test-libunwind-x86_64.bin \ + test-libunwind-arm.bin \ + test-libunwind-aarch64.bin \ + test-libunwind-debug-frame-arm.bin \ + test-libunwind-debug-frame-aarch64.bin \ test-pthread-attr-setaffinity-np.bin \ test-stackprotector-all.bin \ test-timerfd.bin \ @@ -82,6 +89,9 @@ endif $(OUTPUT)test-dwarf.bin: $(BUILD) $(DWARFLIBS) +$(OUTPUT)test-dwarf_getlocations.bin: + $(BUILD) $(DWARFLIBS) + $(OUTPUT)test-libelf-mmap.bin: $(BUILD) -lelf @@ -99,6 +109,23 @@ $(OUTPUT)test-libunwind.bin: $(OUTPUT)test-libunwind-debug-frame.bin: $(BUILD) -lelf +$(OUTPUT)test-libunwind-x86.bin: + $(BUILD) -lelf -lunwind-x86 + +$(OUTPUT)test-libunwind-x86_64.bin: + $(BUILD) -lelf -lunwind-x86_64 + +$(OUTPUT)test-libunwind-arm.bin: + $(BUILD) -lelf -lunwind-arm + +$(OUTPUT)test-libunwind-aarch64.bin: + $(BUILD) -lelf -lunwind-aarch64 + +$(OUTPUT)test-libunwind-debug-frame-arm.bin: + $(BUILD) -lelf -lunwind-arm + +$(OUTPUT)test-libunwind-debug-frame-aarch64.bin: + $(BUILD) -lelf -lunwind-aarch64 $(OUTPUT)test-libaudit.bin: $(BUILD) -laudit diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index e499a36..a282e8c 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -41,6 +41,10 @@ # include "test-dwarf.c" #undef main +#define main main_test_dwarf_getlocations +# include "test-dwarf_getlocations.c" +#undef main + #define main main_test_libelf_getphdrnum # include "test-libelf-getphdrnum.c" #undef main @@ -143,6 +147,7 @@ int main(int argc, char *argv[]) main_test_libelf_mmap(); main_test_glibc(); main_test_dwarf(); + main_test_dwarf_getlocations(); main_test_libelf_getphdrnum(); main_test_libunwind(); main_test_libaudit(); diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c index b389026..e04ab89 100644 --- a/tools/build/feature/test-bpf.c +++ b/tools/build/feature/test-bpf.c @@ -27,10 +27,9 @@ int main(void) attr.log_level = 0; attr.kern_version = 0; - attr = attr; /* * Test existence of __NR_bpf and BPF_PROG_LOAD. * This call should fail if we run the testcase. */ - return syscall(__NR_bpf, BPF_PROG_LOAD, attr, sizeof(attr)); + return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); } diff --git a/tools/build/feature/test-dwarf_getlocations.c b/tools/build/feature/test-dwarf_getlocations.c new file mode 100644 index 0000000..7016269 --- /dev/null +++ b/tools/build/feature/test-dwarf_getlocations.c @@ -0,0 +1,12 @@ +#include <stdlib.h> +#include <elfutils/libdw.h> + +int main(void) +{ + Dwarf_Addr base, start, end; + Dwarf_Attribute attr; + Dwarf_Op *op; + size_t nops; + ptrdiff_t offset = 0; + return (int)dwarf_getlocations(&attr, offset, &base, &start, &end, &op, &nops); +} diff --git a/tools/build/feature/test-libunwind-aarch64.c b/tools/build/feature/test-libunwind-aarch64.c new file mode 100644 index 0000000..fc03fb6 --- /dev/null +++ b/tools/build/feature/test-libunwind-aarch64.c @@ -0,0 +1,26 @@ +#include <libunwind-aarch64.h> +#include <stdlib.h> + +extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, + unw_word_t ip, + unw_dyn_info_t *di, + unw_proc_info_t *pi, + int need_unwind_info, void *arg); + +#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) + +static unw_accessors_t accessors; + +int main(void) +{ + unw_addr_space_t addr_space; + + addr_space = unw_create_addr_space(&accessors, 0); + if (addr_space) + return 0; + + unw_init_remote(NULL, addr_space, NULL); + dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL); + + return 0; +} diff --git a/tools/build/feature/test-libunwind-arm.c b/tools/build/feature/test-libunwind-arm.c new file mode 100644 index 0000000..632d95e --- /dev/null +++ b/tools/build/feature/test-libunwind-arm.c @@ -0,0 +1,27 @@ +#include <libunwind-arm.h> +#include <stdlib.h> + +extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, + unw_word_t ip, + unw_dyn_info_t *di, + unw_proc_info_t *pi, + int need_unwind_info, void *arg); + + +#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) + +static unw_accessors_t accessors; + +int main(void) +{ + unw_addr_space_t addr_space; + + addr_space = unw_create_addr_space(&accessors, 0); + if (addr_space) + return 0; + + unw_init_remote(NULL, addr_space, NULL); + dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL); + + return 0; +} diff --git a/tools/build/feature/test-libunwind-debug-frame-aarch64.c b/tools/build/feature/test-libunwind-debug-frame-aarch64.c new file mode 100644 index 0000000..2284467 --- /dev/null +++ b/tools/build/feature/test-libunwind-debug-frame-aarch64.c @@ -0,0 +1,16 @@ +#include <libunwind-aarch64.h> +#include <stdlib.h> + +extern int +UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug, + unw_word_t ip, unw_word_t segbase, + const char *obj_name, unw_word_t start, + unw_word_t end); + +#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame) + +int main(void) +{ + dwarf_find_debug_frame(0, NULL, 0, 0, NULL, 0, 0); + return 0; +} diff --git a/tools/build/feature/test-libunwind-debug-frame-arm.c b/tools/build/feature/test-libunwind-debug-frame-arm.c new file mode 100644 index 0000000..f988596 --- /dev/null +++ b/tools/build/feature/test-libunwind-debug-frame-arm.c @@ -0,0 +1,16 @@ +#include <libunwind-arm.h> +#include <stdlib.h> + +extern int +UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug, + unw_word_t ip, unw_word_t segbase, + const char *obj_name, unw_word_t start, + unw_word_t end); + +#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame) + +int main(void) +{ + dwarf_find_debug_frame(0, NULL, 0, 0, NULL, 0, 0); + return 0; +} diff --git a/tools/build/feature/test-libunwind-x86.c b/tools/build/feature/test-libunwind-x86.c new file mode 100644 index 0000000..3561edc --- /dev/null +++ b/tools/build/feature/test-libunwind-x86.c @@ -0,0 +1,27 @@ +#include <libunwind-x86.h> +#include <stdlib.h> + +extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, + unw_word_t ip, + unw_dyn_info_t *di, + unw_proc_info_t *pi, + int need_unwind_info, void *arg); + + +#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) + +static unw_accessors_t accessors; + +int main(void) +{ + unw_addr_space_t addr_space; + + addr_space = unw_create_addr_space(&accessors, 0); + if (addr_space) + return 0; + + unw_init_remote(NULL, addr_space, NULL); + dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL); + + return 0; +} diff --git a/tools/build/feature/test-libunwind-x86_64.c b/tools/build/feature/test-libunwind-x86_64.c new file mode 100644 index 0000000..5add251 --- /dev/null +++ b/tools/build/feature/test-libunwind-x86_64.c @@ -0,0 +1,27 @@ +#include <libunwind-x86_64.h> +#include <stdlib.h> + +extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, + unw_word_t ip, + unw_dyn_info_t *di, + unw_proc_info_t *pi, + int need_unwind_info, void *arg); + + +#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) + +static unw_accessors_t accessors; + +int main(void) +{ + unw_addr_space_t addr_space; + + addr_space = unw_create_addr_space(&accessors, 0); + if (addr_space) + return 0; + + unw_init_remote(NULL, addr_space, NULL); + dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL); + + return 0; +} diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c index 80159e6..d9836c5 100644 --- a/tools/lguest/lguest.c +++ b/tools/lguest/lguest.c @@ -3351,12 +3351,18 @@ int main(int argc, char *argv[]) /* Boot protocol version: 2.07 supports the fields for lguest. */ boot->hdr.version = 0x207; - /* The hardware_subarch value of "1" tells the Guest it's an lguest. */ - boot->hdr.hardware_subarch = 1; + /* X86_SUBARCH_LGUEST tells the Guest it's an lguest. */ + boot->hdr.hardware_subarch = X86_SUBARCH_LGUEST; /* Tell the entry path not to try to reload segment registers. */ boot->hdr.loadflags |= KEEP_SEGMENTS; + /* We don't support tboot: */ + boot->tboot_addr = 0; + + /* Ensure this is 0 to prevent APM from loading: */ + boot->apm_bios_info.version = 0; + /* We tell the kernel to initialize the Guest. */ tell_kernel(start); diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index ef78c22..08556cf 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -351,6 +351,19 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep) return err; } +int procfs__read_str(const char *entry, char **buf, size_t *sizep) +{ + char path[PATH_MAX]; + const char *procfs = procfs__mountpoint(); + + if (!procfs) + return -1; + + snprintf(path, sizeof(path), "%s/%s", procfs, entry); + + return filename__read_str(path, buf, sizep); +} + int sysfs__read_ull(const char *entry, unsigned long long *value) { char path[PATH_MAX]; diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h index 9f65980..16c9c2e 100644 --- a/tools/lib/api/fs/fs.h +++ b/tools/lib/api/fs/fs.h @@ -29,6 +29,8 @@ int filename__read_int(const char *filename, int *value); int filename__read_ull(const char *filename, unsigned long long *value); int filename__read_str(const char *filename, char **buf, size_t *sizep); +int procfs__read_str(const char *entry, char **buf, size_t *sizep); + int sysctl__read_int(const char *sysctl, int *value); int sysfs__read_int(const char *entry, int *value); int sysfs__read_ull(const char *entry, unsigned long long *value); diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c index 0144b3d..88cccea 100644 --- a/tools/lib/traceevent/parse-filter.c +++ b/tools/lib/traceevent/parse-filter.c @@ -1164,11 +1164,11 @@ process_filter(struct event_format *event, struct filter_arg **parg, current_op = current_exp; ret = collapse_tree(current_op, parg, error_str); + /* collapse_tree() may free current_op, and updates parg accordingly */ + current_op = NULL; if (ret < 0) goto fail; - *parg = current_op; - free(token); return 0; diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c index 5b32413..544b05a 100644 --- a/tools/net/bpf_jit_disasm.c +++ b/tools/net/bpf_jit_disasm.c @@ -98,6 +98,9 @@ static char *get_klog_buff(unsigned int *klen) char *buff; len = klogctl(CMD_ACTION_SIZE_BUFFER, NULL, 0); + if (len < 0) + return NULL; + buff = malloc(len); if (!buff) return NULL; diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt index be764f9..c6c8318 100644 --- a/tools/perf/Documentation/intel-pt.txt +++ b/tools/perf/Documentation/intel-pt.txt @@ -672,6 +672,7 @@ The letters are: d create a debug log g synthesize a call chain (use with i or x) l synthesize last branch entries (use with i or x) + s skip initial number of events "Instructions" events look like they were recorded by "perf record -e instructions". @@ -730,6 +731,12 @@ from one sample to the next. To disable trace decoding entirely, use the option --no-itrace. +It is also possible to skip events generated (instructions, branches, transactions) +at the beginning. This is useful to ignore initialization code. + + --itrace=i0nss1000000 + +skips the first million instructions. dump option ----------- diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index 65453f4..e2a4c5e 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -7,6 +7,7 @@ d create a debug log g synthesize a call chain (use with i or x) l synthesize last branch entries (use with i or x) + s skip initial number of events The default is all events i.e. the same as --itrace=ibxe @@ -24,3 +25,10 @@ Also the number of last branch entries (default 64, max. 1024) for instructions or transactions events can be specified. + + It is also possible to skip events generated (instructions, branches, transactions) + at the beginning. This is useful to ignore initialization code. + + --itrace=i0nss1000000 + + skips the first million instructions. diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index e9cd39a..778f54d 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -33,7 +33,7 @@ OPTIONS -f:: --force:: - Don't complain, do it. + Don't do ownership validation. -v:: --verbose:: diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index d1deb57..3e9490b 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -75,7 +75,7 @@ OPTIONS -f:: --force:: - Don't complain, do it. + Don't do ownership validation. --symfs=<directory>:: Look for files with symbols relative to this directory. diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index ec723d0..a126e97 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -93,6 +93,67 @@ raw encoding of 0x1A8 can be used: You should refer to the processor specific documentation for getting these details. Some of them are referenced in the SEE ALSO section below. +ARBITRARY PMUS +-------------- + +perf also supports an extended syntax for specifying raw parameters +to PMUs. Using this typically requires looking up the specific event +in the CPU vendor specific documentation. + +The available PMUs and their raw parameters can be listed with + + ls /sys/devices/*/format + +For example the raw event "LSD.UOPS" core pmu event above could +be specified as + + perf stat -e cpu/event=0xa8,umask=0x1,name=LSD.UOPS_CYCLES,cmask=1/ ... + +PER SOCKET PMUS +--------------- + +Some PMUs are not associated with a core, but with a whole CPU socket. +Events on these PMUs generally cannot be sampled, but only counted globally +with perf stat -a. They can be bound to one logical CPU, but will measure +all the CPUs in the same socket. + +This example measures memory bandwidth every second +on the first memory controller on socket 0 of a Intel Xeon system + + perf stat -C 0 -a uncore_imc_0/cas_count_read/,uncore_imc_0/cas_count_write/ -I 1000 ... + +Each memory controller has its own PMU. Measuring the complete system +bandwidth would require specifying all imc PMUs (see perf list output), +and adding the values together. + +This example measures the combined core power every second + + perf stat -I 1000 -e power/energy-cores/ -a + +ACCESS RESTRICTIONS +------------------- + +For non root users generally only context switched PMU events are available. +This is normally only the events in the cpu PMU, the predefined events +like cycles and instructions and some software events. + +Other PMUs and global measurements are normally root only. +Some event qualifiers, such as "any", are also root only. + +This can be overriden by setting the kernel.perf_event_paranoid +sysctl to -1, which allows non root to use these events. + +For accessing trace point events perf needs to have read access to +/sys/kernel/debug/tracing, even when perf_event_paranoid is in a relaxed +setting. + +TRACING +------- + +Some PMUs control advanced hardware tracing capabilities, such as Intel PT, +that allows low overhead execution tracing. These are described in a separate +intel-pt.txt document. + PARAMETERIZED EVENTS -------------------- @@ -106,6 +167,50 @@ also be supplied. For example: perf stat -C 0 -e 'hv_gpci/dtbp_ptitc,phys_processor_idx=0x2/' ... +EVENT GROUPS +------------ + +Perf supports time based multiplexing of events, when the number of events +active exceeds the number of hardware performance counters. Multiplexing +can cause measurement errors when the workload changes its execution +profile. + +When metrics are computed using formulas from event counts, it is useful to +ensure some events are always measured together as a group to minimize multiplexing +errors. Event groups can be specified using { }. + + perf stat -e '{instructions,cycles}' ... + +The number of available performance counters depend on the CPU. A group +cannot contain more events than available counters. +For example Intel Core CPUs typically have four generic performance counters +for the core, plus three fixed counters for instructions, cycles and +ref-cycles. Some special events have restrictions on which counter they +can schedule, and may not support multiple instances in a single group. +When too many events are specified in the group none of them will not +be measured. + +Globally pinned events can limit the number of counters available for +other groups. On x86 systems, the NMI watchdog pins a counter by default. +The nmi watchdog can be disabled as root with + + echo 0 > /proc/sys/kernel/nmi_watchdog + +Events from multiple different PMUs cannot be mixed in a group, with +some exceptions for software events. + +LEADER SAMPLING +--------------- + +perf also supports group leader sampling using the :S specifier. + + perf record -e '{cycles,instructions}:S' ... + perf report --group + +Normally all events in a event group sample, but with :S only +the first event (the leader) samples, and it only reads the values of the +other events in the group. + OPTIONS ------- @@ -143,5 +248,5 @@ SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-top[1], linkperf:perf-record[1], -http://www.intel.com/Assets/PDF/manual/253669.pdf[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide], +http://www.intel.com/sdm/[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide], http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming] diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 43310d8..1d6092c 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -48,6 +48,14 @@ OPTIONS option can be passed in record mode. It will be interpreted the same way as perf record. +-K:: +--all-kernel:: + Configure all used events to run in kernel space. + +-U:: +--all-user:: + Configure all used events to run in user space. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 19aa175..8dbee83 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -347,6 +347,19 @@ Configure all used events to run in kernel space. --all-user:: Configure all used events to run in user space. +--timestamp-filename +Append timestamp to output file name. + +--switch-output:: +Generate multiple perf.data files, timestamp prefixed, switching to a new one +when receiving a SIGUSR2. + +A possible use case is to, given an external event, slice the perf.data file +that gets then processed, possibly via a perf script, to decide if that +particular perf.data snapshot should be kept or not. + +Implies --timestamp-filename, --no-buildid and --no-buildid-cache. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 1211399..ebaf849 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -248,7 +248,7 @@ OPTIONS Note that when using the --itrace option the synthesized callchain size will override this value if the synthesized callchain size is bigger. - Default: 127 + Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. -G:: --inverted:: @@ -285,7 +285,7 @@ OPTIONS -f:: --force:: - Don't complain, do it. + Don't do ownership validation. --symfs=<directory>:: Look for files with symbols relative to this directory. diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt index 8ff4df9..1cc08cc 100644 --- a/tools/perf/Documentation/perf-sched.txt +++ b/tools/perf/Documentation/perf-sched.txt @@ -50,6 +50,22 @@ OPTIONS --dump-raw-trace=:: Display verbose dump of the sched data. +OPTIONS for 'perf sched map' +---------------------------- + +--compact:: + Show only CPUs with activity. Helps visualizing on high core + count systems. + +--cpus:: + Show just entries with activities for the given CPUs. + +--color-cpus:: + Highlight the given cpus. + +--color-pids:: + Highlight the given pids. + SEE ALSO -------- linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 382ddfb..a856a10 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -259,9 +259,23 @@ include::itrace.txt[] --full-source-path:: Show the full path for source files for srcline output. +--max-stack:: + Set the stack depth limit when parsing the callchain, anything + beyond the specified depth will be ignored. This is a trade-off + between information loss and faster processing especially for + workloads that can have a very long callchain stack. + Note that when using the --itrace option the synthesized callchain size + will override this value if the synthesized callchain size is bigger. + + Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. + --ns:: Use 9 decimal places when displaying time (i.e. show the nanoseconds) +-f:: +--force:: + Don't do ownership validation. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 19f046f..91d638d 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -177,7 +177,7 @@ Default is to monitor all CPUS. between information loss and faster processing especially for workloads that can have a very long callchain stack. - Default: 127 + Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. --ignore-callees=<regex>:: Ignore callees of the function(s) matching the given regex. diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 13293de..6afe201 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -117,9 +117,41 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. --syscalls:: Trace system calls. This options is enabled by default. +--call-graph [mode,type,min[,limit],order[,key][,branch]]:: + Setup and enable call-graph (stack chain/backtrace) recording. + See `--call-graph` section in perf-record and perf-report + man pages for details. The ones that are most useful in 'perf trace' + are 'dwarf' and 'lbr', where available, try: 'perf trace --call-graph dwarf'. + + Using this will, for the root user, bump the value of --mmap-pages to 4 + times the maximum for non-root users, based on the kernel.perf_event_mlock_kb + sysctl. This is done only if the user doesn't specify a --mmap-pages value. + +--kernel-syscall-graph:: + Show the kernel callchains on the syscall exit path. + --event:: Trace other events, see 'perf list' for a complete list. +--max-stack:: + Set the stack depth limit when parsing the callchain, anything + beyond the specified depth will be ignored. Note that at this point + this is just about the presentation part, i.e. the kernel is still + not limiting, the overhead of callchains needs to be set via the + knobs in --call-graph dwarf. + + Implies '--call-graph dwarf' when --call-graph not present on the + command line, on systems where DWARF unwinding was built in. + + Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. + +--min-stack:: + Set the stack depth limit when parsing the callchain, anything + below the specified depth will be ignored. Disabled by default. + + Implies '--call-graph dwarf' when --call-graph not present on the + command line, on systems where DWARF unwinding was built in. + --proc-map-timeout:: When processing pre-existing threads /proc/XXX/mmap, it may take a long time, because the file may be huge. A time out is needed in such cases. diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 000ea21..bde8cba 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -183,6 +183,11 @@ endif include config/Makefile endif +ifeq ($(config),0) +include $(srctree)/tools/scripts/Makefile.arch +-include arch/$(ARCH)/Makefile +endif + # The FEATURE_DUMP_EXPORT holds location of the actual # FEATURE_DUMP file to be used to bypass feature detection # (for bpf or any other subproject) @@ -297,8 +302,6 @@ endif # because maintaining the nesting to match is a pain. If # we had "elif" things would have been much nicer... --include arch/$(ARCH)/Makefile - ifneq ($(OUTPUT),) CFLAGS += -I$(OUTPUT) endif @@ -390,7 +393,7 @@ endif __build-dir = $(subst $(OUTPUT),,$(dir $@)) build-dir = $(if $(__build-dir),$(__build-dir),.) -prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h fixdep +prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h fixdep archheaders $(OUTPUT)%.o: %.c prepare FORCE $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ @@ -430,7 +433,7 @@ $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h) LIBPERF_IN := $(OUTPUT)libperf-in.o -$(LIBPERF_IN): fixdep FORCE +$(LIBPERF_IN): prepare fixdep FORCE $(Q)$(MAKE) $(build)=libperf $(LIB_FILE): $(LIBPERF_IN) @@ -625,7 +628,7 @@ config-clean: $(call QUIET_CLEAN, config) $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null -clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean +clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) $(OUTPUT).config-detected @@ -662,5 +665,5 @@ FORCE: .PHONY: all install clean config-clean strip install-gtk .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell .PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE prepare -.PHONY: libtraceevent_plugins +.PHONY: libtraceevent_plugins archheaders diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index 56e05f1..cc39309 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -3,4 +3,5 @@ PERF_HAVE_DWARF_REGS := 1 endif HAVE_KVM_STAT_SUPPORT := 1 +PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 PERF_HAVE_JITDUMP := 1 diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c index 733151c..41bdf95 100644 --- a/tools/perf/arch/powerpc/util/dwarf-regs.c +++ b/tools/perf/arch/powerpc/util/dwarf-regs.c @@ -10,19 +10,26 @@ */ #include <stddef.h> +#include <errno.h> +#include <string.h> #include <dwarf-regs.h> - +#include <linux/ptrace.h> +#include <linux/kernel.h> +#include "util.h" struct pt_regs_dwarfnum { const char *name; unsigned int dwarfnum; + unsigned int ptregs_offset; }; -#define STR(s) #s -#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num} -#define GPR_DWARFNUM_NAME(num) \ - {.name = STR(%gpr##num), .dwarfnum = num} -#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0} +#define REG_DWARFNUM_NAME(r, num) \ + {.name = STR(%)STR(r), .dwarfnum = num, \ + .ptregs_offset = offsetof(struct pt_regs, r)} +#define GPR_DWARFNUM_NAME(num) \ + {.name = STR(%gpr##num), .dwarfnum = num, \ + .ptregs_offset = offsetof(struct pt_regs, gpr[num])} +#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0, .ptregs_offset = 0} /* * Reference: @@ -61,12 +68,12 @@ static const struct pt_regs_dwarfnum regdwarfnum_table[] = { GPR_DWARFNUM_NAME(29), GPR_DWARFNUM_NAME(30), GPR_DWARFNUM_NAME(31), - REG_DWARFNUM_NAME("%msr", 66), - REG_DWARFNUM_NAME("%ctr", 109), - REG_DWARFNUM_NAME("%link", 108), - REG_DWARFNUM_NAME("%xer", 101), - REG_DWARFNUM_NAME("%dar", 119), - REG_DWARFNUM_NAME("%dsisr", 118), + REG_DWARFNUM_NAME(msr, 66), + REG_DWARFNUM_NAME(ctr, 109), + REG_DWARFNUM_NAME(link, 108), + REG_DWARFNUM_NAME(xer, 101), + REG_DWARFNUM_NAME(dar, 119), + REG_DWARFNUM_NAME(dsisr, 118), REG_DWARFNUM_END, }; @@ -86,3 +93,12 @@ const char *get_arch_regstr(unsigned int n) return roff->name; return NULL; } + +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_dwarfnum *roff; + for (roff = regdwarfnum_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->ptregs_offset; + return -EINVAL; +} diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index bbc1a50..c6d0f91 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -19,12 +19,6 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) ehdr.e_type == ET_DYN; } -#if defined(_CALL_ELF) && _CALL_ELF == 2 -void arch__elf_sym_adjust(GElf_Sym *sym) -{ - sym->st_value += PPC64_LOCAL_ENTRY_OFFSET(sym->st_other); -} -#endif #endif #if !defined(_CALL_ELF) || _CALL_ELF != 2 @@ -65,18 +59,45 @@ bool arch__prefers_symtab(void) return true; } +#ifdef HAVE_LIBELF_SUPPORT +void arch__sym_update(struct symbol *s, GElf_Sym *sym) +{ + s->arch_sym = sym->st_other; +} +#endif + #define PPC64LE_LEP_OFFSET 8 void arch__fix_tev_from_maps(struct perf_probe_event *pev, - struct probe_trace_event *tev, struct map *map) + struct probe_trace_event *tev, struct map *map, + struct symbol *sym) { + int lep_offset; + /* - * ppc64 ABIv2 local entry point is currently always 2 instructions - * (8 bytes) after the global entry point. + * When probing at a function entry point, we normally always want the + * LEP since that catches calls to the function through both the GEP and + * the LEP. Hence, we would like to probe at an offset of 8 bytes if + * the user only specified the function entry. + * + * However, if the user specifies an offset, we fall back to using the + * GEP since all userspace applications (objdump/readelf) show function + * disassembly with offsets from the GEP. + * + * In addition, we shouldn't specify an offset for kretprobes. */ - if (!pev->uprobes && map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) { - tev->point.address += PPC64LE_LEP_OFFSET; + if (pev->point.offset || pev->point.retprobe || !map || !sym) + return; + + lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym); + + if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) tev->point.offset += PPC64LE_LEP_OFFSET; + else if (lep_offset) { + if (pev->uprobes) + tev->point.address += lep_offset; + else + tev->point.offset += lep_offset; } } #endif diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 269af21..6c9211b 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -4,3 +4,26 @@ endif HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 PERF_HAVE_JITDUMP := 1 + +### +# Syscall table generation +# + +out := $(OUTPUT)arch/x86/include/generated/asm +header := $(out)/syscalls_64.c +sys := $(srctree)/tools/perf/arch/x86/entry/syscalls +systbl := $(sys)/syscalltbl.sh + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header): $(sys)/syscall_64.tbl $(systbl) + @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ + (diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \ + || echo "Warning: x86_64's syscall_64.tbl differs from kernel" >&2 )) || true + $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@ + +clean:: + $(call QUIET_CLEAN, x86) $(RM) $(header) + +archheaders: $(header) diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl new file mode 100644 index 0000000..cac6d17 --- /dev/null +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -0,0 +1,376 @@ +# +# 64-bit system call numbers and entry vectors +# +# The format is: +# <number> <abi> <name> <entry point> +# +# The abi is "common", "64" or "x32" for this file. +# +0 common read sys_read +1 common write sys_write +2 common open sys_open +3 common close sys_close +4 common stat sys_newstat +5 common fstat sys_newfstat +6 common lstat sys_newlstat +7 common poll sys_poll +8 common lseek sys_lseek +9 common mmap sys_mmap +10 common mprotect sys_mprotect +11 common munmap sys_munmap +12 common brk sys_brk +13 64 rt_sigaction sys_rt_sigaction +14 common rt_sigprocmask sys_rt_sigprocmask +15 64 rt_sigreturn sys_rt_sigreturn/ptregs +16 64 ioctl sys_ioctl +17 common pread64 sys_pread64 +18 common pwrite64 sys_pwrite64 +19 64 readv sys_readv +20 64 writev sys_writev +21 common access sys_access +22 common pipe sys_pipe +23 common select sys_select +24 common sched_yield sys_sched_yield +25 common mremap sys_mremap +26 common msync sys_msync +27 common mincore sys_mincore +28 common madvise sys_madvise +29 common shmget sys_shmget +30 common shmat sys_shmat +31 common shmctl sys_shmctl +32 common dup sys_dup +33 common dup2 sys_dup2 +34 common pause sys_pause +35 common nanosleep sys_nanosleep +36 common getitimer sys_getitimer +37 common alarm sys_alarm +38 common setitimer sys_setitimer +39 common getpid sys_getpid +40 common sendfile sys_sendfile64 +41 common socket sys_socket +42 common connect sys_connect +43 common accept sys_accept +44 common sendto sys_sendto +45 64 recvfrom sys_recvfrom +46 64 sendmsg sys_sendmsg +47 64 recvmsg sys_recvmsg +48 common shutdown sys_shutdown +49 common bind sys_bind +50 common listen sys_listen +51 common getsockname sys_getsockname +52 common getpeername sys_getpeername +53 common socketpair sys_socketpair +54 64 setsockopt sys_setsockopt +55 64 getsockopt sys_getsockopt +56 common clone sys_clone/ptregs +57 common fork sys_fork/ptregs +58 common vfork sys_vfork/ptregs +59 64 execve sys_execve/ptregs +60 common exit sys_exit +61 common wait4 sys_wait4 +62 common kill sys_kill +63 common uname sys_newuname +64 common semget sys_semget +65 common semop sys_semop +66 common semctl sys_semctl +67 common shmdt sys_shmdt +68 common msgget sys_msgget +69 common msgsnd sys_msgsnd +70 common msgrcv sys_msgrcv +71 common msgctl sys_msgctl +72 common fcntl sys_fcntl +73 common flock sys_flock +74 common fsync sys_fsync +75 common fdatasync sys_fdatasync +76 common truncate sys_truncate +77 common ftruncate sys_ftruncate +78 common getdents sys_getdents +79 common getcwd sys_getcwd +80 common chdir sys_chdir +81 common fchdir sys_fchdir +82 common rename sys_rename +83 common mkdir sys_mkdir +84 common rmdir sys_rmdir +85 common creat sys_creat +86 common link sys_link +87 common unlink sys_unlink +88 common symlink sys_symlink +89 common readlink sys_readlink +90 common chmod sys_chmod +91 common fchmod sys_fchmod +92 common chown sys_chown +93 common fchown sys_fchown +94 common lchown sys_lchown +95 common umask sys_umask +96 common gettimeofday sys_gettimeofday +97 common getrlimit sys_getrlimit +98 common getrusage sys_getrusage +99 common sysinfo sys_sysinfo +100 common times sys_times +101 64 ptrace sys_ptrace +102 common getuid sys_getuid +103 common syslog sys_syslog +104 common getgid sys_getgid +105 common setuid sys_setuid +106 common setgid sys_setgid +107 common geteuid sys_geteuid +108 common getegid sys_getegid +109 common setpgid sys_setpgid +110 common getppid sys_getppid +111 common getpgrp sys_getpgrp +112 common setsid sys_setsid +113 common setreuid sys_setreuid +114 common setregid sys_setregid +115 common getgroups sys_getgroups +116 common setgroups sys_setgroups +117 common setresuid sys_setresuid +118 common getresuid sys_getresuid +119 common setresgid sys_setresgid +120 common getresgid sys_getresgid +121 common getpgid sys_getpgid +122 common setfsuid sys_setfsuid +123 common setfsgid sys_setfsgid +124 common getsid sys_getsid +125 common capget sys_capget +126 common capset sys_capset +127 64 rt_sigpending sys_rt_sigpending +128 64 rt_sigtimedwait sys_rt_sigtimedwait +129 64 rt_sigqueueinfo sys_rt_sigqueueinfo +130 common rt_sigsuspend sys_rt_sigsuspend +131 64 sigaltstack sys_sigaltstack +132 common utime sys_utime +133 common mknod sys_mknod +134 64 uselib +135 common personality sys_personality +136 common ustat sys_ustat +137 common statfs sys_statfs +138 common fstatfs sys_fstatfs +139 common sysfs sys_sysfs +140 common getpriority sys_getpriority +141 common setpriority sys_setpriority +142 common sched_setparam sys_sched_setparam +143 common sched_getparam sys_sched_getparam +144 common sched_setscheduler sys_sched_setscheduler +145 common sched_getscheduler sys_sched_getscheduler +146 common sched_get_priority_max sys_sched_get_priority_max +147 common sched_get_priority_min sys_sched_get_priority_min +148 common sched_rr_get_interval sys_sched_rr_get_interval +149 common mlock sys_mlock +150 common munlock sys_munlock +151 common mlockall sys_mlockall +152 common munlockall sys_munlockall +153 common vhangup sys_vhangup +154 common modify_ldt sys_modify_ldt +155 common pivot_root sys_pivot_root +156 64 _sysctl sys_sysctl +157 common prctl sys_prctl +158 common arch_prctl sys_arch_prctl +159 common adjtimex sys_adjtimex +160 common setrlimit sys_setrlimit +161 common chroot sys_chroot +162 common sync sys_sync +163 common acct sys_acct +164 common settimeofday sys_settimeofday +165 common mount sys_mount +166 common umount2 sys_umount +167 common swapon sys_swapon +168 common swapoff sys_swapoff +169 common reboot sys_reboot +170 common sethostname sys_sethostname +171 common setdomainname sys_setdomainname +172 common iopl sys_iopl/ptregs +173 common ioperm sys_ioperm +174 64 create_module +175 common init_module sys_init_module +176 common delete_module sys_delete_module +177 64 get_kernel_syms +178 64 query_module +179 common quotactl sys_quotactl +180 64 nfsservctl +181 common getpmsg +182 common putpmsg +183 common afs_syscall +184 common tuxcall +185 common security +186 common gettid sys_gettid +187 common readahead sys_readahead +188 common setxattr sys_setxattr +189 common lsetxattr sys_lsetxattr +190 common fsetxattr sys_fsetxattr +191 common getxattr sys_getxattr +192 common lgetxattr sys_lgetxattr +193 common fgetxattr sys_fgetxattr +194 common listxattr sys_listxattr +195 common llistxattr sys_llistxattr +196 common flistxattr sys_flistxattr +197 common removexattr sys_removexattr +198 common lremovexattr sys_lremovexattr +199 common fremovexattr sys_fremovexattr +200 common tkill sys_tkill +201 common time sys_time +202 common futex sys_futex +203 common sched_setaffinity sys_sched_setaffinity +204 common sched_getaffinity sys_sched_getaffinity +205 64 set_thread_area +206 64 io_setup sys_io_setup +207 common io_destroy sys_io_destroy +208 common io_getevents sys_io_getevents +209 64 io_submit sys_io_submit +210 common io_cancel sys_io_cancel +211 64 get_thread_area +212 common lookup_dcookie sys_lookup_dcookie +213 common epoll_create sys_epoll_create +214 64 epoll_ctl_old +215 64 epoll_wait_old +216 common remap_file_pages sys_remap_file_pages +217 common getdents64 sys_getdents64 +218 common set_tid_address sys_set_tid_address +219 common restart_syscall sys_restart_syscall +220 common semtimedop sys_semtimedop +221 common fadvise64 sys_fadvise64 +222 64 timer_create sys_timer_create +223 common timer_settime sys_timer_settime +224 common timer_gettime sys_timer_gettime +225 common timer_getoverrun sys_timer_getoverrun +226 common timer_delete sys_timer_delete +227 common clock_settime sys_clock_settime +228 common clock_gettime sys_clock_gettime +229 common clock_getres sys_clock_getres +230 common clock_nanosleep sys_clock_nanosleep +231 common exit_group sys_exit_group +232 common epoll_wait sys_epoll_wait +233 common epoll_ctl sys_epoll_ctl +234 common tgkill sys_tgkill +235 common utimes sys_utimes +236 64 vserver +237 common mbind sys_mbind +238 common set_mempolicy sys_set_mempolicy +239 common get_mempolicy sys_get_mempolicy +240 common mq_open sys_mq_open +241 common mq_unlink sys_mq_unlink +242 common mq_timedsend sys_mq_timedsend +243 common mq_timedreceive sys_mq_timedreceive +244 64 mq_notify sys_mq_notify +245 common mq_getsetattr sys_mq_getsetattr +246 64 kexec_load sys_kexec_load +247 64 waitid sys_waitid +248 common add_key sys_add_key +249 common request_key sys_request_key +250 common keyctl sys_keyctl +251 common ioprio_set sys_ioprio_set +252 common ioprio_get sys_ioprio_get +253 common inotify_init sys_inotify_init +254 common inotify_add_watch sys_inotify_add_watch +255 common inotify_rm_watch sys_inotify_rm_watch +256 common migrate_pages sys_migrate_pages +257 common openat sys_openat +258 common mkdirat sys_mkdirat +259 common mknodat sys_mknodat +260 common fchownat sys_fchownat +261 common futimesat sys_futimesat +262 common newfstatat sys_newfstatat +263 common unlinkat sys_unlinkat +264 common renameat sys_renameat +265 common linkat sys_linkat +266 common symlinkat sys_symlinkat +267 common readlinkat sys_readlinkat +268 common fchmodat sys_fchmodat +269 common faccessat sys_faccessat +270 common pselect6 sys_pselect6 +271 common ppoll sys_ppoll +272 common unshare sys_unshare +273 64 set_robust_list sys_set_robust_list +274 64 get_robust_list sys_get_robust_list +275 common splice sys_splice +276 common tee sys_tee +277 common sync_file_range sys_sync_file_range +278 64 vmsplice sys_vmsplice +279 64 move_pages sys_move_pages +280 common utimensat sys_utimensat +281 common epoll_pwait sys_epoll_pwait +282 common signalfd sys_signalfd +283 common timerfd_create sys_timerfd_create +284 common eventfd sys_eventfd +285 common fallocate sys_fallocate +286 common timerfd_settime sys_timerfd_settime +287 common timerfd_gettime sys_timerfd_gettime +288 common accept4 sys_accept4 +289 common signalfd4 sys_signalfd4 +290 common eventfd2 sys_eventfd2 +291 common epoll_create1 sys_epoll_create1 +292 common dup3 sys_dup3 +293 common pipe2 sys_pipe2 +294 common inotify_init1 sys_inotify_init1 +295 64 preadv sys_preadv +296 64 pwritev sys_pwritev +297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +298 common perf_event_open sys_perf_event_open +299 64 recvmmsg sys_recvmmsg +300 common fanotify_init sys_fanotify_init +301 common fanotify_mark sys_fanotify_mark +302 common prlimit64 sys_prlimit64 +303 common name_to_handle_at sys_name_to_handle_at +304 common open_by_handle_at sys_open_by_handle_at +305 common clock_adjtime sys_clock_adjtime +306 common syncfs sys_syncfs +307 64 sendmmsg sys_sendmmsg +308 common setns sys_setns +309 common getcpu sys_getcpu +310 64 process_vm_readv sys_process_vm_readv +311 64 process_vm_writev sys_process_vm_writev +312 common kcmp sys_kcmp +313 common finit_module sys_finit_module +314 common sched_setattr sys_sched_setattr +315 common sched_getattr sys_sched_getattr +316 common renameat2 sys_renameat2 +317 common seccomp sys_seccomp +318 common getrandom sys_getrandom +319 common memfd_create sys_memfd_create +320 common kexec_file_load sys_kexec_file_load +321 common bpf sys_bpf +322 64 execveat sys_execveat/ptregs +323 common userfaultfd sys_userfaultfd +324 common membarrier sys_membarrier +325 common mlock2 sys_mlock2 +326 common copy_file_range sys_copy_file_range +327 64 preadv2 sys_preadv2 +328 64 pwritev2 sys_pwritev2 + +# +# x32-specific system call numbers start at 512 to avoid cache impact +# for native 64-bit operation. +# +512 x32 rt_sigaction compat_sys_rt_sigaction +513 x32 rt_sigreturn sys32_x32_rt_sigreturn +514 x32 ioctl compat_sys_ioctl +515 x32 readv compat_sys_readv +516 x32 writev compat_sys_writev +517 x32 recvfrom compat_sys_recvfrom +518 x32 sendmsg compat_sys_sendmsg +519 x32 recvmsg compat_sys_recvmsg +520 x32 execve compat_sys_execve/ptregs +521 x32 ptrace compat_sys_ptrace +522 x32 rt_sigpending compat_sys_rt_sigpending +523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait +524 x32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo +525 x32 sigaltstack compat_sys_sigaltstack +526 x32 timer_create compat_sys_timer_create +527 x32 mq_notify compat_sys_mq_notify +528 x32 kexec_load compat_sys_kexec_load +529 x32 waitid compat_sys_waitid +530 x32 set_robust_list compat_sys_set_robust_list +531 x32 get_robust_list compat_sys_get_robust_list +532 x32 vmsplice compat_sys_vmsplice +533 x32 move_pages compat_sys_move_pages +534 x32 preadv compat_sys_preadv64 +535 x32 pwritev compat_sys_pwritev64 +536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +537 x32 recvmmsg compat_sys_recvmmsg +538 x32 sendmmsg compat_sys_sendmmsg +539 x32 process_vm_readv compat_sys_process_vm_readv +540 x32 process_vm_writev compat_sys_process_vm_writev +541 x32 setsockopt compat_sys_setsockopt +542 x32 getsockopt compat_sys_getsockopt +543 x32 io_setup compat_sys_io_setup +544 x32 io_submit compat_sys_io_submit +545 x32 execveat compat_sys_execveat/ptregs diff --git a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh new file mode 100755 index 0000000..49a18b9 --- /dev/null +++ b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh @@ -0,0 +1,39 @@ +#!/bin/sh + +in="$1" +arch="$2" + +syscall_macro() { + nr="$1" + name="$2" + + echo " [$nr] = \"$name\"," +} + +emit() { + nr="$1" + entry="$2" + + syscall_macro "$nr" "$entry" +} + +echo "static const char *syscalltbl_${arch}[] = {" + +sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX) +grep '^[0-9]' "$in" | sort -n > $sorted_table + +max_nr=0 +while read nr abi name entry compat; do + if [ $nr -ge 512 ] ; then # discard compat sycalls + break + fi + + emit "$nr" "$name" + max_nr=$nr +done < $sorted_table + +rm -f $sorted_table + +echo "};" + +echo "#define SYSCALLTBL_${arch}_MAX_ID ${max_nr}" diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index 9d29ee2..d4aa567 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -71,7 +71,7 @@ int test__perf_time_to_tsc(int subtest __maybe_unused) CHECK__(parse_events(evlist, "cycles:u", NULL)); - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); evsel = perf_evlist__first(evlist); diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c index 9223c16..1f86ee8 100644 --- a/tools/perf/arch/x86/util/dwarf-regs.c +++ b/tools/perf/arch/x86/util/dwarf-regs.c @@ -63,6 +63,8 @@ struct pt_regs_offset { # define REG_OFFSET_NAME_32(n, r) {.name = n, .offset = offsetof(struct pt_regs, r)} #endif +/* TODO: switching by dwarf address size */ +#ifndef __x86_64__ static const struct pt_regs_offset x86_32_regoffset_table[] = { REG_OFFSET_NAME_32("%ax", eax), REG_OFFSET_NAME_32("%cx", ecx), @@ -75,6 +77,8 @@ static const struct pt_regs_offset x86_32_regoffset_table[] = { REG_OFFSET_END, }; +#define regoffset_table x86_32_regoffset_table +#else static const struct pt_regs_offset x86_64_regoffset_table[] = { REG_OFFSET_NAME_64("%ax", rax), REG_OFFSET_NAME_64("%dx", rdx), @@ -95,11 +99,7 @@ static const struct pt_regs_offset x86_64_regoffset_table[] = { REG_OFFSET_END, }; -/* TODO: switching by dwarf address size */ -#ifdef __x86_64__ #define regoffset_table x86_64_regoffset_table -#else -#define regoffset_table x86_32_regoffset_table #endif /* Minus 1 for the ending REG_OFFSET_END */ diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index d66f9ad..7dc3063 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -438,6 +438,11 @@ struct auxtrace_record *intel_bts_recording_init(int *err) if (!intel_bts_pmu) return NULL; + if (setenv("JITDUMP_USE_ARCH_TIMESTAMP", "1", 1)) { + *err = -errno; + return NULL; + } + btsr = zalloc(sizeof(struct intel_bts_recording)); if (!btsr) { *err = -ENOMEM; diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index a339517..a07b960 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -1027,6 +1027,11 @@ struct auxtrace_record *intel_pt_recording_init(int *err) if (!intel_pt_pmu) return NULL; + if (setenv("JITDUMP_USE_ARCH_TIMESTAMP", "1", 1)) { + *err = -errno; + return NULL; + } + ptr = zalloc(sizeof(struct intel_pt_recording)); if (!ptr) { *err = -ENOMEM; diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index fd28684..357f1b1 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -7,7 +7,6 @@ #include <linux/types.h> #include "../../util/debug.h" #include "../../util/tsc.h" -#include "tsc.h" int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc) @@ -46,3 +45,34 @@ u64 rdtsc(void) return low | ((u64)high) << 32; } + +int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, + struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + union perf_event event = { + .time_conv = { + .header = { + .type = PERF_RECORD_TIME_CONV, + .size = sizeof(struct time_conv_event), + }, + }, + }; + struct perf_tsc_conversion tc; + int err; + + err = perf_read_tsc_conversion(pc, &tc); + if (err == -EOPNOTSUPP) + return 0; + if (err) + return err; + + pr_debug2("Synthesizing TSC conversion information\n"); + + event.time_conv.time_mult = tc.time_mult; + event.time_conv.time_shift = tc.time_shift; + event.time_conv.time_zero = tc.time_zero; + + return process(tool, &event, NULL, machine); +} diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h deleted file mode 100644 index 2edc4d3..0000000 --- a/tools/perf/arch/x86/util/tsc.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ -#define TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ - -#include <linux/types.h> - -struct perf_tsc_conversion { - u16 time_shift; - u32 time_mult; - u64 time_zero; -}; - -struct perf_event_mmap_page; - -int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, - struct perf_tsc_conversion *tc); - -#endif /* TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ */ diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 6a18ce2..6952db6 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -83,7 +83,7 @@ static void *workerfn(void *arg) do { int ret; again: - ret = futex_lock_pi(w->futex, NULL, 0, futex_flag); + ret = futex_lock_pi(w->futex, NULL, futex_flag); if (ret) { /* handle lock acquisition */ if (!silent) diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h index d44de9f..b2e06d1 100644 --- a/tools/perf/bench/futex.h +++ b/tools/perf/bench/futex.h @@ -57,13 +57,11 @@ futex_wake(u_int32_t *uaddr, int nr_wake, int opflags) /** * futex_lock_pi() - block on uaddr as a PI mutex - * @detect: whether (1) or not (0) to perform deadlock detection */ static inline int -futex_lock_pi(u_int32_t *uaddr, struct timespec *timeout, int detect, - int opflags) +futex_lock_pi(u_int32_t *uaddr, struct timespec *timeout, int opflags) { - return futex(uaddr, FUTEX_LOCK_PI, detect, timeout, NULL, 0, opflags); + return futex(uaddr, FUTEX_LOCK_PI, 0, timeout, NULL, 0, opflags); } /** diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c index a91aa85..2b54d0f 100644 --- a/tools/perf/bench/mem-functions.c +++ b/tools/perf/bench/mem-functions.c @@ -6,6 +6,7 @@ * Written by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> */ +#include "debug.h" #include "../perf.h" #include "../util/util.h" #include <subcmd/parse-options.h> @@ -63,14 +64,16 @@ static struct perf_event_attr cycle_attr = { .config = PERF_COUNT_HW_CPU_CYCLES }; -static void init_cycles(void) +static int init_cycles(void) { cycles_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, perf_event_open_cloexec_flag()); - if (cycles_fd < 0 && errno == ENOSYS) - die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); - else - BUG_ON(cycles_fd < 0); + if (cycles_fd < 0 && errno == ENOSYS) { + pr_debug("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); + return -1; + } + + return cycles_fd; } static u64 get_cycles(void) @@ -155,8 +158,13 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info * argc = parse_options(argc, argv, options, info->usage, 0); - if (use_cycles) - init_cycles(); + if (use_cycles) { + i = init_cycles(); + if (i < 0) { + fprintf(stderr, "Failed to open cycles counter\n"); + return i; + } + } size = (size_t)perf_atoll((char *)size_str); size_total = (double)size * nr_loops; diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index c42448e..fe1b77f 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -12,6 +12,7 @@ #include <subcmd/parse-options.h> #include "util/util.h" #include "util/debug.h" +#include "util/config.h" static bool use_system_config, use_user_config; @@ -32,13 +33,28 @@ static struct option config_options[] = { OPT_END() }; -static int show_config(const char *key, const char *value, - void *cb __maybe_unused) +static int show_config(struct perf_config_set *set) { - if (value) - printf("%s=%s\n", key, value); - else - printf("%s\n", key); + struct perf_config_section *section; + struct perf_config_item *item; + struct list_head *sections; + + if (set == NULL) + return -1; + + sections = &set->sections; + if (list_empty(sections)) + return -1; + + list_for_each_entry(section, sections, node) { + list_for_each_entry(item, §ion->items, node) { + char *value = item->value; + + if (value) + printf("%s.%s=%s\n", section->name, + item->name, value); + } + } return 0; } @@ -46,6 +62,7 @@ static int show_config(const char *key, const char *value, int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) { int ret = 0; + struct perf_config_set *set; char *user_config = mkpath("%s/.perfconfig", getenv("HOME")); argc = parse_options(argc, argv, config_options, config_usage, @@ -63,13 +80,19 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) else if (use_user_config) config_exclusive_filename = user_config; + set = perf_config_set__new(); + if (!set) { + ret = -1; + goto out_err; + } + switch (actions) { case ACTION_LIST: if (argc) { pr_err("Error: takes no arguments\n"); parse_options_usage(config_usage, config_options, "l", 1); } else { - ret = perf_config(show_config, NULL); + ret = show_config(set); if (ret < 0) { const char * config_filename = config_exclusive_filename; if (!config_exclusive_filename) @@ -83,5 +106,7 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) usage_with_options(config_usage, config_options); } + perf_config_set__delete(set); +out_err: return ret; } diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 8053a8c..9ce354f 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -428,7 +428,7 @@ static void hists__baseline_only(struct hists *hists) struct rb_root *root; struct rb_node *next; - if (sort__need_collapse) + if (hists__has(hists, need_collapse)) root = &hists->entries_collapsed; else root = hists->entries_in; @@ -450,7 +450,7 @@ static void hists__precompute(struct hists *hists) struct rb_root *root; struct rb_node *next; - if (sort__need_collapse) + if (hists__has(hists, need_collapse)) root = &hists->entries_collapsed; else root = hists->entries_in; diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index bc1de9b..f9830c9 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -61,6 +61,7 @@ static int check_emacsclient_version(void) struct child_process ec_process; const char *argv_ec[] = { "emacsclient", "--version", NULL }; int version; + int ret = -1; /* emacsclient prints its version number on stderr */ memset(&ec_process, 0, sizeof(ec_process)); @@ -71,7 +72,10 @@ static int check_emacsclient_version(void) fprintf(stderr, "Failed to start emacsclient.\n"); return -1; } - strbuf_read(&buffer, ec_process.err, 20); + if (strbuf_read(&buffer, ec_process.err, 20) < 0) { + fprintf(stderr, "Failed to read emacsclient version\n"); + goto out; + } close(ec_process.err); /* @@ -82,8 +86,7 @@ static int check_emacsclient_version(void) if (prefixcmp(buffer.buf, "emacsclient")) { fprintf(stderr, "Failed to parse emacsclient version.\n"); - strbuf_release(&buffer); - return -1; + goto out; } version = atoi(buffer.buf + strlen("emacsclient")); @@ -92,12 +95,11 @@ static int check_emacsclient_version(void) fprintf(stderr, "emacsclient version '%d' too old (< 22).\n", version); - strbuf_release(&buffer); - return -1; - } - + } else + ret = 0; +out: strbuf_release(&buffer); - return 0; + return ret; } static void exec_woman_emacs(const char *path, const char *page) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index d1a2d10..e5afa8f 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -748,6 +748,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) .auxtrace_info = perf_event__repipe_op2_synth, .auxtrace = perf_event__repipe_auxtrace, .auxtrace_error = perf_event__repipe_op2_synth, + .time_conv = perf_event__repipe_op2_synth, .finished_round = perf_event__repipe_oe_synth, .build_id = perf_event__repipe_op2_synth, .id_index = perf_event__repipe_op2_synth, diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index c9cb3be..58adfee 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -375,7 +375,7 @@ static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample) } al.thread = machine__findnew_thread(machine, sample->pid, sample->tid); - sample__resolve_callchain(sample, NULL, evsel, &al, 16); + sample__resolve_callchain(sample, &callchain_cursor, NULL, evsel, &al, 16); callchain_cursor_commit(&callchain_cursor); while (true) { diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index bff6664..6487c06 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -982,7 +982,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm) struct perf_evlist *evlist = kvm->evlist; char sbuf[STRERR_BUFSIZE]; - perf_evlist__config(evlist, &kvm->opts); + perf_evlist__config(evlist, &kvm->opts, NULL); /* * Note: exclude_{guest,host} do not apply here. diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 85db3be..1dc140c 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -62,19 +62,22 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) int rec_argc, i = 0, j; const char **rec_argv; int ret; + bool all_user = false, all_kernel = false; struct option options[] = { OPT_CALLBACK('e', "event", &mem, "event", "event selector. use 'perf mem record -e list' to list available events", parse_record_events), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), + OPT_BOOLEAN('U', "--all-user", &all_user, "collect only user level data"), + OPT_BOOLEAN('K', "--all-kernel", &all_kernel, "collect only kernel level data"), OPT_END() }; argc = parse_options(argc, argv, options, record_mem_usage, PARSE_OPT_STOP_AT_NON_OPTION); - rec_argc = argc + 7; /* max number of arguments */ + rec_argc = argc + 9; /* max number of arguments */ rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (!rec_argv) return -1; @@ -103,6 +106,12 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) rec_argv[i++] = perf_mem_events__name(j); }; + if (all_user) + rec_argv[i++] = "--all-user"; + + if (all_kernel) + rec_argv[i++] = "--all-kernel"; + for (j = 0; j < argc; j++, i++) rec_argv[i] = argv[j]; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 515510e..f3679c4 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -29,10 +29,12 @@ #include "util/data.h" #include "util/perf_regs.h" #include "util/auxtrace.h" +#include "util/tsc.h" #include "util/parse-branch-options.h" #include "util/parse-regs-options.h" #include "util/llvm-utils.h" #include "util/bpf-loader.h" +#include "util/trigger.h" #include "asm/bug.h" #include <unistd.h> @@ -55,6 +57,8 @@ struct record { bool no_buildid_cache; bool no_buildid_cache_set; bool buildid_all; + bool timestamp_filename; + bool switch_output; unsigned long long samples; }; @@ -124,9 +128,10 @@ out: static volatile int done; static volatile int signr = -1; static volatile int child_finished; -static volatile int auxtrace_snapshot_enabled; -static volatile int auxtrace_snapshot_err; + static volatile int auxtrace_record__snapshot_started; +static DEFINE_TRIGGER(auxtrace_snapshot_trigger); +static DEFINE_TRIGGER(switch_output_trigger); static void sig_handler(int sig) { @@ -244,11 +249,12 @@ static void record__read_auxtrace_snapshot(struct record *rec) { pr_debug("Recording AUX area tracing snapshot\n"); if (record__auxtrace_read_snapshot_all(rec) < 0) { - auxtrace_snapshot_err = -1; + trigger_error(&auxtrace_snapshot_trigger); } else { - auxtrace_snapshot_err = auxtrace_record__snapshot_finish(rec->itr); - if (!auxtrace_snapshot_err) - auxtrace_snapshot_enabled = 1; + if (auxtrace_record__snapshot_finish(rec->itr)) + trigger_error(&auxtrace_snapshot_trigger); + else + trigger_ready(&auxtrace_snapshot_trigger); } } @@ -283,7 +289,7 @@ static int record__open(struct record *rec) struct record_opts *opts = &rec->opts; int rc = 0; - perf_evlist__config(evlist, opts); + perf_evlist__config(evlist, opts, &callchain_param); evlist__for_each(evlist, pos) { try_again: @@ -494,6 +500,73 @@ record__finish_output(struct record *rec) return; } +static int record__synthesize_workload(struct record *rec) +{ + struct { + struct thread_map map; + struct thread_map_data map_data; + } thread_map; + + thread_map.map.nr = 1; + thread_map.map.map[0].pid = rec->evlist->workload.pid; + thread_map.map.map[0].comm = NULL; + return perf_event__synthesize_thread_map(&rec->tool, &thread_map.map, + process_synthesized_event, + &rec->session->machines.host, + rec->opts.sample_address, + rec->opts.proc_map_timeout); +} + +static int record__synthesize(struct record *rec); + +static int +record__switch_output(struct record *rec, bool at_exit) +{ + struct perf_data_file *file = &rec->file; + int fd, err; + + /* Same Size: "2015122520103046"*/ + char timestamp[] = "InvalidTimestamp"; + + rec->samples = 0; + record__finish_output(rec); + err = fetch_current_timestamp(timestamp, sizeof(timestamp)); + if (err) { + pr_err("Failed to get current timestamp\n"); + return -EINVAL; + } + + fd = perf_data_file__switch(file, timestamp, + rec->session->header.data_offset, + at_exit); + if (fd >= 0 && !at_exit) { + rec->bytes_written = 0; + rec->session->header.data_size = 0; + } + + if (!quiet) + fprintf(stderr, "[ perf record: Dump %s.%s ]\n", + file->path, timestamp); + + /* Output tracking events */ + if (!at_exit) { + record__synthesize(rec); + + /* + * In 'perf record --switch-output' without -a, + * record__synthesize() in record__switch_output() won't + * generate tracking events because there's no thread_map + * in evlist. Which causes newly created perf.data doesn't + * contain map and comm information. + * Create a fake thread_map and directly call + * perf_event__synthesize_thread_map() for those events. + */ + if (target__none(&rec->opts.target)) + record__synthesize_workload(rec); + } + return fd; +} + static volatile int workload_exec_errno; /* @@ -512,6 +585,15 @@ static void workload_exec_failed_signal(int signo __maybe_unused, static void snapshot_sig_handler(int sig); +int __weak +perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused, + struct perf_tool *tool __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + static int record__synthesize(struct record *rec) { struct perf_session *session = rec->session; @@ -549,6 +631,11 @@ static int record__synthesize(struct record *rec) } } + err = perf_event__synth_time_conv(rec->evlist->mmap[0].base, tool, + process_synthesized_event, machine); + if (err) + goto out; + if (rec->opts.full_auxtrace) { err = perf_event__synthesize_auxtrace_info(rec->itr, tool, session, process_synthesized_event); @@ -600,10 +687,16 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); signal(SIGTERM, sig_handler); - if (rec->opts.auxtrace_snapshot_mode) + + if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) { signal(SIGUSR2, snapshot_sig_handler); - else + if (rec->opts.auxtrace_snapshot_mode) + trigger_on(&auxtrace_snapshot_trigger); + if (rec->switch_output) + trigger_on(&switch_output_trigger); + } else { signal(SIGUSR2, SIG_IGN); + } session = perf_session__new(file, false, tool); if (session == NULL) { @@ -729,27 +822,45 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) perf_evlist__enable(rec->evlist); } - auxtrace_snapshot_enabled = 1; + trigger_ready(&auxtrace_snapshot_trigger); + trigger_ready(&switch_output_trigger); for (;;) { unsigned long long hits = rec->samples; if (record__mmap_read_all(rec) < 0) { - auxtrace_snapshot_enabled = 0; + trigger_error(&auxtrace_snapshot_trigger); + trigger_error(&switch_output_trigger); err = -1; goto out_child; } if (auxtrace_record__snapshot_started) { auxtrace_record__snapshot_started = 0; - if (!auxtrace_snapshot_err) + if (!trigger_is_error(&auxtrace_snapshot_trigger)) record__read_auxtrace_snapshot(rec); - if (auxtrace_snapshot_err) { + if (trigger_is_error(&auxtrace_snapshot_trigger)) { pr_err("AUX area tracing snapshot failed\n"); err = -1; goto out_child; } } + if (trigger_is_hit(&switch_output_trigger)) { + trigger_ready(&switch_output_trigger); + + if (!quiet) + fprintf(stderr, "[ perf record: dump data: Woken up %ld times ]\n", + waking); + waking = 0; + fd = record__switch_output(rec, false); + if (fd < 0) { + pr_err("Failed to switch to new file\n"); + trigger_error(&switch_output_trigger); + err = fd; + goto out_child; + } + } + if (hits == rec->samples) { if (done || draining) break; @@ -772,12 +883,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * disable events in this case. */ if (done && !disabled && !target__none(&opts->target)) { - auxtrace_snapshot_enabled = 0; + trigger_off(&auxtrace_snapshot_trigger); perf_evlist__disable(rec->evlist); disabled = true; } } - auxtrace_snapshot_enabled = 0; + trigger_off(&auxtrace_snapshot_trigger); + trigger_off(&switch_output_trigger); if (forks && workload_exec_errno) { char msg[STRERR_BUFSIZE]; @@ -811,11 +923,22 @@ out_child: /* this will be recalculated during process_buildids() */ rec->samples = 0; - if (!err) - record__finish_output(rec); + if (!err) { + if (!rec->timestamp_filename) { + record__finish_output(rec); + } else { + fd = record__switch_output(rec, true); + if (fd < 0) { + status = fd; + goto out_delete_session; + } + } + } if (!err && !quiet) { char samples[128]; + const char *postfix = rec->timestamp_filename ? + ".<timestamp>" : ""; if (rec->samples && !rec->opts.full_auxtrace) scnprintf(samples, sizeof(samples), @@ -823,9 +946,9 @@ out_child: else samples[0] = '\0'; - fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s ]\n", + fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s%s ]\n", perf_data_file__size(file) / 1024.0 / 1024.0, - file->path, samples); + file->path, postfix, samples); } out_delete_session: @@ -833,58 +956,61 @@ out_delete_session: return status; } -static void callchain_debug(void) +static void callchain_debug(struct callchain_param *callchain) { static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF", "LBR" }; - pr_debug("callchain: type %s\n", str[callchain_param.record_mode]); + pr_debug("callchain: type %s\n", str[callchain->record_mode]); - if (callchain_param.record_mode == CALLCHAIN_DWARF) + if (callchain->record_mode == CALLCHAIN_DWARF) pr_debug("callchain: stack dump size %d\n", - callchain_param.dump_size); + callchain->dump_size); } -int record_parse_callchain_opt(const struct option *opt, - const char *arg, - int unset) +int record_opts__parse_callchain(struct record_opts *record, + struct callchain_param *callchain, + const char *arg, bool unset) { int ret; - struct record_opts *record = (struct record_opts *)opt->value; - - record->callgraph_set = true; - callchain_param.enabled = !unset; + callchain->enabled = !unset; /* --no-call-graph */ if (unset) { - callchain_param.record_mode = CALLCHAIN_NONE; + callchain->record_mode = CALLCHAIN_NONE; pr_debug("callchain: disabled\n"); return 0; } - ret = parse_callchain_record_opt(arg, &callchain_param); + ret = parse_callchain_record_opt(arg, callchain); if (!ret) { /* Enable data address sampling for DWARF unwind. */ - if (callchain_param.record_mode == CALLCHAIN_DWARF) + if (callchain->record_mode == CALLCHAIN_DWARF) record->sample_address = true; - callchain_debug(); + callchain_debug(callchain); } return ret; } +int record_parse_callchain_opt(const struct option *opt, + const char *arg, + int unset) +{ + return record_opts__parse_callchain(opt->value, &callchain_param, arg, unset); +} + int record_callchain_opt(const struct option *opt, const char *arg __maybe_unused, int unset __maybe_unused) { - struct record_opts *record = (struct record_opts *)opt->value; + struct callchain_param *callchain = opt->value; - record->callgraph_set = true; - callchain_param.enabled = true; + callchain->enabled = true; - if (callchain_param.record_mode == CALLCHAIN_NONE) - callchain_param.record_mode = CALLCHAIN_FP; + if (callchain->record_mode == CALLCHAIN_NONE) + callchain->record_mode = CALLCHAIN_FP; - callchain_debug(); + callchain_debug(callchain); return 0; } @@ -1122,7 +1248,7 @@ struct option __record_options[] = { record__parse_mmap_pages), OPT_BOOLEAN(0, "group", &record.opts.group, "put the counters into a counter group"), - OPT_CALLBACK_NOOPT('g', NULL, &record.opts, + OPT_CALLBACK_NOOPT('g', NULL, &callchain_param, NULL, "enables call-graph recording" , &record_callchain_opt), OPT_CALLBACK(0, "call-graph", &record.opts, @@ -1195,6 +1321,10 @@ struct option __record_options[] = { "file", "vmlinux pathname"), OPT_BOOLEAN(0, "buildid-all", &record.buildid_all, "Record build-id of all DSOs regardless of hits"), + OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename, + "append timestamp to output filename"), + OPT_BOOLEAN(0, "switch-output", &record.switch_output, + "Switch output when receive SIGUSR2"), OPT_END() }; @@ -1250,6 +1380,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) return -EINVAL; } + if (rec->switch_output) + rec->timestamp_filename = true; + if (!rec->itr) { rec->itr = auxtrace_record__init(rec->evlist, &err); if (err) @@ -1261,6 +1394,14 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (err) return err; + err = bpf__setup_stdout(rec->evlist); + if (err) { + bpf__strerror_setup_stdout(rec->evlist, err, errbuf, sizeof(errbuf)); + pr_err("ERROR: Setup BPF stdout failed: %s\n", + errbuf); + return err; + } + err = -ENOMEM; symbol__init(NULL); @@ -1275,8 +1416,36 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) "If some relocation was applied (e.g. kexec) symbols may be misresolved\n" "even with a suitable vmlinux or kallsyms file.\n\n"); - if (rec->no_buildid_cache || rec->no_buildid) + if (rec->no_buildid_cache || rec->no_buildid) { disable_buildid_cache(); + } else if (rec->switch_output) { + /* + * In 'perf record --switch-output', disable buildid + * generation by default to reduce data file switching + * overhead. Still generate buildid if they are required + * explicitly using + * + * perf record --signal-trigger --no-no-buildid \ + * --no-no-buildid-cache + * + * Following code equals to: + * + * if ((rec->no_buildid || !rec->no_buildid_set) && + * (rec->no_buildid_cache || !rec->no_buildid_cache_set)) + * disable_buildid_cache(); + */ + bool disable = true; + + if (rec->no_buildid_set && !rec->no_buildid) + disable = false; + if (rec->no_buildid_cache_set && !rec->no_buildid_cache) + disable = false; + if (disable) { + rec->no_buildid = true; + rec->no_buildid_cache = true; + disable_buildid_cache(); + } + } if (rec->evlist->nr_entries == 0 && perf_evlist__add_default(rec->evlist) < 0) { @@ -1335,9 +1504,13 @@ out_symbol_exit: static void snapshot_sig_handler(int sig __maybe_unused) { - if (!auxtrace_snapshot_enabled) - return; - auxtrace_snapshot_enabled = 0; - auxtrace_snapshot_err = auxtrace_record__snapshot_start(record.itr); - auxtrace_record__snapshot_started = 1; + if (trigger_is_ready(&auxtrace_snapshot_trigger)) { + trigger_hit(&auxtrace_snapshot_trigger); + auxtrace_record__snapshot_started = 1; + if (auxtrace_record__snapshot_start(record.itr)) + trigger_error(&auxtrace_snapshot_trigger); + } + + if (trigger_is_ready(&switch_output_trigger)) + trigger_hit(&switch_output_trigger); } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 160ea23..87d40e3 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -47,7 +47,6 @@ struct report { struct perf_tool tool; struct perf_session *session; bool use_tui, use_gtk, use_stdio; - bool dont_use_callchains; bool show_full_info; bool show_threads; bool inverted_callchain; @@ -235,7 +234,7 @@ static int report__setup_sample_type(struct report *rep) sample_type |= PERF_SAMPLE_BRANCH_STACK; if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) { - if (sort__has_parent) { + if (perf_hpp_list.parent) { ui__error("Selected --sort parent, but no " "callchain data. Did you call " "'perf record' without -g?\n"); @@ -247,7 +246,7 @@ static int report__setup_sample_type(struct report *rep) "you call 'perf record' without -g?\n"); return -1; } - } else if (!rep->dont_use_callchains && + } else if (!callchain_param.enabled && callchain_param.mode != CHAIN_NONE && !symbol_conf.use_callchain) { symbol_conf.use_callchain = true; @@ -599,13 +598,15 @@ static int __cmd_report(struct report *rep) static int report_parse_callchain_opt(const struct option *opt, const char *arg, int unset) { - struct report *rep = (struct report *)opt->value; + struct callchain_param *callchain = opt->value; + callchain->enabled = !unset; /* * --no-call-graph */ if (unset) { - rep->dont_use_callchains = true; + symbol_conf.use_callchain = false; + callchain->mode = CHAIN_NONE; return 0; } @@ -690,7 +691,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .ordered_events = true, .ordering_requires_timestamps = true, }, - .max_stack = PERF_MAX_STACK_DEPTH, + .max_stack = sysctl_perf_event_max_stack, .pretty_printing_style = "normal", .socket_filter = -1, }; @@ -734,7 +735,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "regex filter to identify parent, see: '--sort parent'"), OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other, "Only display entries with parent-match"), - OPT_CALLBACK_DEFAULT('g', "call-graph", &report, + OPT_CALLBACK_DEFAULT('g', "call-graph", &callchain_param, "print_type,threshold[,print_limit],order,sort_key[,branch],value", report_callchain_help, &report_parse_callchain_opt, callchain_default_opt), @@ -743,7 +744,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_INTEGER(0, "max-stack", &report.max_stack, "Set the maximum stack depth when parsing the callchain, " "anything beyond the specified depth will be ignored. " - "Default: " __stringify(PERF_MAX_STACK_DEPTH)), + "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)), OPT_BOOLEAN('G', "inverted", &report.inverted_callchain, "alias for inverted call graph"), OPT_CALLBACK(0, "ignore-callees", NULL, "regex", @@ -935,7 +936,7 @@ repeat: goto error; } - sort__need_collapse = true; + perf_hpp_list.need_collapse = true; } /* Force tty output for header output and per-thread stat. */ diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 871b55ae..afa0576 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -11,6 +11,8 @@ #include "util/session.h" #include "util/tool.h" #include "util/cloexec.h" +#include "util/thread_map.h" +#include "util/color.h" #include <subcmd/parse-options.h> #include "util/trace-event.h" @@ -122,6 +124,21 @@ struct trace_sched_handler { struct machine *machine); }; +#define COLOR_PIDS PERF_COLOR_BLUE +#define COLOR_CPUS PERF_COLOR_BG_RED + +struct perf_sched_map { + DECLARE_BITMAP(comp_cpus_mask, MAX_CPUS); + int *comp_cpus; + bool comp; + struct thread_map *color_pids; + const char *color_pids_str; + struct cpu_map *color_cpus; + const char *color_cpus_str; + struct cpu_map *cpus; + const char *cpus_str; +}; + struct perf_sched { struct perf_tool tool; const char *sort_order; @@ -173,6 +190,7 @@ struct perf_sched { struct list_head sort_list, cmp_pid; bool force; bool skip_merge; + struct perf_sched_map map; }; static u64 get_nsecs(void) @@ -1339,6 +1357,38 @@ static int process_sched_wakeup_event(struct perf_tool *tool, return 0; } +union map_priv { + void *ptr; + bool color; +}; + +static bool thread__has_color(struct thread *thread) +{ + union map_priv priv = { + .ptr = thread__priv(thread), + }; + + return priv.color; +} + +static struct thread* +map__findnew_thread(struct perf_sched *sched, struct machine *machine, pid_t pid, pid_t tid) +{ + struct thread *thread = machine__findnew_thread(machine, pid, tid); + union map_priv priv = { + .color = false, + }; + + if (!sched->map.color_pids || !thread || thread__priv(thread)) + return thread; + + if (thread_map__has(sched->map.color_pids, tid)) + priv.color = true; + + thread__set_priv(thread, priv.ptr); + return thread; +} + static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1347,13 +1397,25 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, int new_shortname; u64 timestamp0, timestamp = sample->time; s64 delta; - int cpu, this_cpu = sample->cpu; + int i, this_cpu = sample->cpu; + int cpus_nr; + bool new_cpu = false; + const char *color = PERF_COLOR_NORMAL; BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0); if (this_cpu > sched->max_cpu) sched->max_cpu = this_cpu; + if (sched->map.comp) { + cpus_nr = bitmap_weight(sched->map.comp_cpus_mask, MAX_CPUS); + if (!test_and_set_bit(this_cpu, sched->map.comp_cpus_mask)) { + sched->map.comp_cpus[cpus_nr++] = this_cpu; + new_cpu = true; + } + } else + cpus_nr = sched->max_cpu; + timestamp0 = sched->cpu_last_switched[this_cpu]; sched->cpu_last_switched[this_cpu] = timestamp; if (timestamp0) @@ -1366,7 +1428,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, return -1; } - sched_in = machine__findnew_thread(machine, -1, next_pid); + sched_in = map__findnew_thread(sched, machine, -1, next_pid); if (sched_in == NULL) return -1; @@ -1400,26 +1462,52 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, new_shortname = 1; } - for (cpu = 0; cpu <= sched->max_cpu; cpu++) { + for (i = 0; i < cpus_nr; i++) { + int cpu = sched->map.comp ? sched->map.comp_cpus[i] : i; + struct thread *curr_thread = sched->curr_thread[cpu]; + const char *pid_color = color; + const char *cpu_color = color; + + if (curr_thread && thread__has_color(curr_thread)) + pid_color = COLOR_PIDS; + + if (sched->map.cpus && !cpu_map__has(sched->map.cpus, cpu)) + continue; + + if (sched->map.color_cpus && cpu_map__has(sched->map.color_cpus, cpu)) + cpu_color = COLOR_CPUS; + if (cpu != this_cpu) - printf(" "); + color_fprintf(stdout, cpu_color, " "); else - printf("*"); + color_fprintf(stdout, cpu_color, "*"); if (sched->curr_thread[cpu]) - printf("%2s ", sched->curr_thread[cpu]->shortname); + color_fprintf(stdout, pid_color, "%2s ", sched->curr_thread[cpu]->shortname); else - printf(" "); + color_fprintf(stdout, color, " "); } - printf(" %12.6f secs ", (double)timestamp/1e9); + if (sched->map.cpus && !cpu_map__has(sched->map.cpus, this_cpu)) + goto out; + + color_fprintf(stdout, color, " %12.6f secs ", (double)timestamp/1e9); if (new_shortname) { - printf("%s => %s:%d\n", + const char *pid_color = color; + + if (thread__has_color(sched_in)) + pid_color = COLOR_PIDS; + + color_fprintf(stdout, pid_color, "%s => %s:%d", sched_in->shortname, thread__comm_str(sched_in), sched_in->tid); - } else { - printf("\n"); } + if (sched->map.comp && new_cpu) + color_fprintf(stdout, color, " (CPU %d)", this_cpu); + +out: + color_fprintf(stdout, color, "\n"); + thread__put(sched_in); return 0; @@ -1675,9 +1763,75 @@ static int perf_sched__lat(struct perf_sched *sched) return 0; } +static int setup_map_cpus(struct perf_sched *sched) +{ + struct cpu_map *map; + + sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); + + if (sched->map.comp) { + sched->map.comp_cpus = zalloc(sched->max_cpu * sizeof(int)); + if (!sched->map.comp_cpus) + return -1; + } + + if (!sched->map.cpus_str) + return 0; + + map = cpu_map__new(sched->map.cpus_str); + if (!map) { + pr_err("failed to get cpus map from %s\n", sched->map.cpus_str); + return -1; + } + + sched->map.cpus = map; + return 0; +} + +static int setup_color_pids(struct perf_sched *sched) +{ + struct thread_map *map; + + if (!sched->map.color_pids_str) + return 0; + + map = thread_map__new_by_tid_str(sched->map.color_pids_str); + if (!map) { + pr_err("failed to get thread map from %s\n", sched->map.color_pids_str); + return -1; + } + + sched->map.color_pids = map; + return 0; +} + +static int setup_color_cpus(struct perf_sched *sched) +{ + struct cpu_map *map; + + if (!sched->map.color_cpus_str) + return 0; + + map = cpu_map__new(sched->map.color_cpus_str); + if (!map) { + pr_err("failed to get thread map from %s\n", sched->map.color_cpus_str); + return -1; + } + + sched->map.color_cpus = map; + return 0; +} + static int perf_sched__map(struct perf_sched *sched) { - sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); + if (setup_map_cpus(sched)) + return -1; + + if (setup_color_pids(sched)) + return -1; + + if (setup_color_cpus(sched)) + return -1; setup_pager(); if (perf_sched__read_events(sched)) @@ -1831,6 +1985,17 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) "dump raw trace in ASCII"), OPT_END() }; + const struct option map_options[] = { + OPT_BOOLEAN(0, "compact", &sched.map.comp, + "map output in compact mode"), + OPT_STRING(0, "color-pids", &sched.map.color_pids_str, "pids", + "highlight given pids in map"), + OPT_STRING(0, "color-cpus", &sched.map.color_cpus_str, "cpus", + "highlight given CPUs in map"), + OPT_STRING(0, "cpus", &sched.map.cpus_str, "cpus", + "display given CPUs in map"), + OPT_END() + }; const char * const latency_usage[] = { "perf sched latency [<options>]", NULL @@ -1839,6 +2004,10 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) "perf sched replay [<options>]", NULL }; + const char * const map_usage[] = { + "perf sched map [<options>]", + NULL + }; const char *const sched_subcommands[] = { "record", "latency", "map", "replay", "script", NULL }; const char *sched_usage[] = { @@ -1887,6 +2056,11 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) setup_sorting(&sched, latency_options, latency_usage); return perf_sched__lat(&sched); } else if (!strcmp(argv[0], "map")) { + if (argc) { + argc = parse_options(argc, argv, map_options, map_usage, 0); + if (argc) + usage_with_options(map_usage, map_options); + } sched.tp_handler = &map_ops; setup_sorting(&sched, latency_options, latency_usage); return perf_sched__map(&sched); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 3770c3d..efca816 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -22,6 +22,7 @@ #include "util/thread_map.h" #include "util/stat.h" #include <linux/bitmap.h> +#include <linux/stringify.h> #include "asm/bug.h" #include "util/mem-events.h" @@ -317,19 +318,19 @@ static void set_print_ip_opts(struct perf_event_attr *attr) output[type].print_ip_opts = 0; if (PRINT_FIELD(IP)) - output[type].print_ip_opts |= PRINT_IP_OPT_IP; + output[type].print_ip_opts |= EVSEL__PRINT_IP; if (PRINT_FIELD(SYM)) - output[type].print_ip_opts |= PRINT_IP_OPT_SYM; + output[type].print_ip_opts |= EVSEL__PRINT_SYM; if (PRINT_FIELD(DSO)) - output[type].print_ip_opts |= PRINT_IP_OPT_DSO; + output[type].print_ip_opts |= EVSEL__PRINT_DSO; if (PRINT_FIELD(SYMOFFSET)) - output[type].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET; + output[type].print_ip_opts |= EVSEL__PRINT_SYMOFFSET; if (PRINT_FIELD(SRCLINE)) - output[type].print_ip_opts |= PRINT_IP_OPT_SRCLINE; + output[type].print_ip_opts |= EVSEL__PRINT_SRCLINE; } /* @@ -569,18 +570,23 @@ static void print_sample_bts(struct perf_sample *sample, /* print branch_from information */ if (PRINT_FIELD(IP)) { unsigned int print_opts = output[attr->type].print_ip_opts; + struct callchain_cursor *cursor = NULL; - if (symbol_conf.use_callchain && sample->callchain) { - printf("\n"); - } else { - printf(" "); - if (print_opts & PRINT_IP_OPT_SRCLINE) { + if (symbol_conf.use_callchain && sample->callchain && + thread__resolve_callchain(al->thread, &callchain_cursor, evsel, + sample, NULL, NULL, scripting_max_stack) == 0) + cursor = &callchain_cursor; + + if (cursor == NULL) { + putchar(' '); + if (print_opts & EVSEL__PRINT_SRCLINE) { print_srcline_last = true; - print_opts &= ~PRINT_IP_OPT_SRCLINE; + print_opts &= ~EVSEL__PRINT_SRCLINE; } - } - perf_evsel__print_ip(evsel, sample, al, print_opts, - scripting_max_stack); + } else + putchar('\n'); + + sample__fprintf_sym(sample, al, 0, print_opts, cursor, stdout); } /* print branch_to information */ @@ -783,14 +789,15 @@ static void process_event(struct perf_script *script, printf("%16" PRIu64, sample->weight); if (PRINT_FIELD(IP)) { - if (!symbol_conf.use_callchain) - printf(" "); - else - printf("\n"); + struct callchain_cursor *cursor = NULL; + + if (symbol_conf.use_callchain && sample->callchain && + thread__resolve_callchain(al->thread, &callchain_cursor, evsel, + sample, NULL, NULL, scripting_max_stack) == 0) + cursor = &callchain_cursor; - perf_evsel__print_ip(evsel, sample, al, - output[attr->type].print_ip_opts, - scripting_max_stack); + putchar(cursor ? '\n' : ' '); + sample__fprintf_sym(sample, al, 0, output[attr->type].print_ip_opts, cursor, stdout); } if (PRINT_FIELD(IREGS)) @@ -1415,21 +1422,19 @@ static int is_directory(const char *base_path, const struct dirent *dent) return S_ISDIR(st.st_mode); } -#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\ - while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) && \ - lang_next) \ - if ((lang_dirent.d_type == DT_DIR || \ - (lang_dirent.d_type == DT_UNKNOWN && \ - is_directory(scripts_path, &lang_dirent))) && \ - (strcmp(lang_dirent.d_name, ".")) && \ - (strcmp(lang_dirent.d_name, ".."))) +#define for_each_lang(scripts_path, scripts_dir, lang_dirent) \ + while ((lang_dirent = readdir(scripts_dir)) != NULL) \ + if ((lang_dirent->d_type == DT_DIR || \ + (lang_dirent->d_type == DT_UNKNOWN && \ + is_directory(scripts_path, lang_dirent))) && \ + (strcmp(lang_dirent->d_name, ".")) && \ + (strcmp(lang_dirent->d_name, ".."))) -#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\ - while (!readdir_r(lang_dir, &script_dirent, &script_next) && \ - script_next) \ - if (script_dirent.d_type != DT_DIR && \ - (script_dirent.d_type != DT_UNKNOWN || \ - !is_directory(lang_path, &script_dirent))) +#define for_each_script(lang_path, lang_dir, script_dirent) \ + while ((script_dirent = readdir(lang_dir)) != NULL) \ + if (script_dirent->d_type != DT_DIR && \ + (script_dirent->d_type != DT_UNKNOWN || \ + !is_directory(lang_path, script_dirent))) #define RECORD_SUFFIX "-record" @@ -1575,7 +1580,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused, const char *s __maybe_unused, int unset __maybe_unused) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; char script_path[MAXPATHLEN]; @@ -1590,19 +1595,19 @@ static int list_available_scripts(const struct option *opt __maybe_unused, if (!scripts_dir) return -1; - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { - script_root = get_script_root(&script_dirent, REPORT_SUFFIX); + for_each_script(lang_path, lang_dir, script_dirent) { + script_root = get_script_root(script_dirent, REPORT_SUFFIX); if (script_root) { desc = script_desc__findnew(script_root); snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent.d_name); + lang_path, script_dirent->d_name); read_script_info(desc, script_path); free(script_root); } @@ -1690,7 +1695,7 @@ static int check_ev_match(char *dir_name, char *scriptname, */ int find_scripts(char **scripts_array, char **scripts_path_array) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; struct perf_session *session; @@ -1713,9 +1718,9 @@ int find_scripts(char **scripts_array, char **scripts_path_array) return -1; } - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); #ifdef NO_LIBPERL if (strstr(lang_path, "perl")) continue; @@ -1729,16 +1734,16 @@ int find_scripts(char **scripts_array, char **scripts_path_array) if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { + for_each_script(lang_path, lang_dir, script_dirent) { /* Skip those real time scripts: xxxtop.p[yl] */ - if (strstr(script_dirent.d_name, "top.")) + if (strstr(script_dirent->d_name, "top.")) continue; sprintf(scripts_path_array[i], "%s/%s", lang_path, - script_dirent.d_name); - temp = strchr(script_dirent.d_name, '.'); + script_dirent->d_name); + temp = strchr(script_dirent->d_name, '.'); snprintf(scripts_array[i], - (temp - script_dirent.d_name) + 1, - "%s", script_dirent.d_name); + (temp - script_dirent->d_name) + 1, + "%s", script_dirent->d_name); if (check_ev_match(lang_path, scripts_array[i], session)) @@ -1756,7 +1761,7 @@ int find_scripts(char **scripts_array, char **scripts_path_array) static char *get_script_path(const char *script_root, const char *suffix) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN]; char script_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; @@ -1769,21 +1774,21 @@ static char *get_script_path(const char *script_root, const char *suffix) if (!scripts_dir) return NULL; - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { - __script_root = get_script_root(&script_dirent, suffix); + for_each_script(lang_path, lang_dir, script_dirent) { + __script_root = get_script_root(script_dirent, suffix); if (__script_root && !strcmp(script_root, __script_root)) { free(__script_root); closedir(lang_dir); closedir(scripts_dir); snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent.d_name); + lang_path, script_dirent->d_name); return strdup(script_path); } free(__script_root); @@ -1961,6 +1966,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) .exit = perf_event__process_exit, .fork = perf_event__process_fork, .attr = process_attr, + .event_update = perf_event__process_event_update, .tracing_data = perf_event__process_tracing_data, .build_id = perf_event__process_build_id, .id_index = perf_event__process_id_index, @@ -2022,6 +2028,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "only consider symbols in these pids"), OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]", "only consider symbols in these tids"), + OPT_UINTEGER(0, "max-stack", &scripting_max_stack, + "Set the maximum stack depth when parsing the callchain, " + "anything beyond the specified depth will be ignored. " + "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)), OPT_BOOLEAN('I', "show-info", &show_full_info, "display extended information from perf.data file"), OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path, @@ -2057,6 +2067,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; + scripting_max_stack = sysctl_perf_event_max_stack; + setup_scripting(); argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage, diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 1f19f2f..e459b68 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -298,6 +298,14 @@ static int read_counter(struct perf_evsel *counter) return -1; } } + + if (verbose > 1) { + fprintf(stat_config.output, + "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", + perf_evsel__name(counter), + cpu, + count->val, count->ena, count->run); + } } } @@ -528,6 +536,7 @@ static int __run_perf_stat(int argc, const char **argv) perf_evlist__set_leader(evsel_list); evlist__for_each(evsel_list, counter) { +try_again: if (create_perf_stat_counter(counter) < 0) { /* * PPC returns ENXIO for HW counters until 2.6.37 @@ -544,7 +553,11 @@ static int __run_perf_stat(int argc, const char **argv) if ((counter->leader != counter) || !(counter->leader->nr_members > 1)) continue; - } + } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { + if (verbose) + ui__warning("%s\n", msg); + goto try_again; + } perf_evsel__open_strerror(counter, &target, errno, msg, sizeof(msg)); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 8332149..1793da5 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -688,7 +688,7 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter, struct hist_entry *he = iter->he; struct perf_evsel *evsel = iter->evsel; - if (sort__has_sym && single) + if (perf_hpp_list.sym && single) perf_top__record_precise_ip(top, he, evsel->idx, al->addr); hist__account_cycles(iter->sample->branch_stack, al, iter->sample, @@ -886,7 +886,7 @@ static int perf_top__start_counters(struct perf_top *top) struct perf_evlist *evlist = top->evlist; struct record_opts *opts = &top->record_opts; - perf_evlist__config(evlist, opts); + perf_evlist__config(evlist, opts, &callchain_param); evlist__for_each(evlist, counter) { try_again: @@ -917,15 +917,15 @@ out_err: return -1; } -static int perf_top__setup_sample_type(struct perf_top *top __maybe_unused) +static int callchain_param__setup_sample_type(struct callchain_param *callchain) { - if (!sort__has_sym) { - if (symbol_conf.use_callchain) { + if (!perf_hpp_list.sym) { + if (callchain->enabled) { ui__error("Selected -g but \"sym\" not present in --sort/-s."); return -EINVAL; } - } else if (callchain_param.mode != CHAIN_NONE) { - if (callchain_register_param(&callchain_param) < 0) { + } else if (callchain->mode != CHAIN_NONE) { + if (callchain_register_param(callchain) < 0) { ui__error("Can't register callchain params.\n"); return -EINVAL; } @@ -952,7 +952,7 @@ static int __cmd_top(struct perf_top *top) goto out_delete; } - ret = perf_top__setup_sample_type(top); + ret = callchain_param__setup_sample_type(&callchain_param); if (ret) goto out_delete; @@ -962,7 +962,7 @@ static int __cmd_top(struct perf_top *top) machine__synthesize_threads(&top->session->machines.host, &opts->target, top->evlist->threads, false, opts->proc_map_timeout); - if (sort__has_socket) { + if (perf_hpp_list.socket) { ret = perf_env__read_cpu_topology_map(&perf_env); if (ret < 0) goto out_err_cpu_topo; @@ -1045,18 +1045,17 @@ callchain_opt(const struct option *opt, const char *arg, int unset) static int parse_callchain_opt(const struct option *opt, const char *arg, int unset) { - struct record_opts *record = (struct record_opts *)opt->value; + struct callchain_param *callchain = opt->value; - record->callgraph_set = true; - callchain_param.enabled = !unset; - callchain_param.record_mode = CALLCHAIN_FP; + callchain->enabled = !unset; + callchain->record_mode = CALLCHAIN_FP; /* * --no-call-graph */ if (unset) { symbol_conf.use_callchain = false; - callchain_param.record_mode = CALLCHAIN_NONE; + callchain->record_mode = CALLCHAIN_NONE; return 0; } @@ -1104,7 +1103,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) }, .proc_map_timeout = 500, }, - .max_stack = PERF_MAX_STACK_DEPTH, + .max_stack = sysctl_perf_event_max_stack, .sym_pcnt_filter = 5, }; struct record_opts *opts = &top.record_opts; @@ -1162,17 +1161,17 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "output field(s): overhead, period, sample plus all of sort keys"), OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, "Show a column with the number of samples"), - OPT_CALLBACK_NOOPT('g', NULL, &top.record_opts, + OPT_CALLBACK_NOOPT('g', NULL, &callchain_param, NULL, "enables call-graph recording and display", &callchain_opt), - OPT_CALLBACK(0, "call-graph", &top.record_opts, + OPT_CALLBACK(0, "call-graph", &callchain_param, "record_mode[,record_size],print_type,threshold[,print_limit],order,sort_key[,branch]", top_callchain_help, &parse_callchain_opt), OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain, "Accumulate callchains of children and show total overhead as well"), OPT_INTEGER(0, "max-stack", &top.max_stack, "Set the maximum stack depth when parsing the callchain. " - "Default: " __stringify(PERF_MAX_STACK_DEPTH)), + "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)), OPT_CALLBACK(0, "ignore-callees", NULL, "regex", "ignore callees of these functions in call graphs", report_parse_ignore_callees_opt), @@ -1256,7 +1255,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) sort__mode = SORT_MODE__TOP; /* display thread wants entries to be collapsed in a different tree */ - sort__need_collapse = 1; + perf_hpp_list.need_collapse = 1; if (top.use_stdio) use_browser = 0; @@ -1312,7 +1311,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) top.sym_evsel = perf_evlist__first(top.evlist); - if (!symbol_conf.use_callchain) { + if (!callchain_param.enabled) { symbol_conf.cumulate_callchain = false; perf_hpp__cancel_cumulate(); } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 93ac724..6e5c325 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -34,79 +34,76 @@ #include "trace-event.h" #include "util/parse-events.h" #include "util/bpf-loader.h" +#include "callchain.h" +#include "syscalltbl.h" +#include "rb_resort.h" -#include <libaudit.h> +#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */ #include <stdlib.h> -#include <sys/mman.h> -#include <linux/futex.h> #include <linux/err.h> - -/* For older distros: */ -#ifndef MAP_STACK -# define MAP_STACK 0x20000 -#endif - -#ifndef MADV_HWPOISON -# define MADV_HWPOISON 100 - -#endif - -#ifndef MADV_MERGEABLE -# define MADV_MERGEABLE 12 -#endif - -#ifndef MADV_UNMERGEABLE -# define MADV_UNMERGEABLE 13 -#endif - -#ifndef EFD_SEMAPHORE -# define EFD_SEMAPHORE 1 -#endif - -#ifndef EFD_NONBLOCK -# define EFD_NONBLOCK 00004000 -#endif - -#ifndef EFD_CLOEXEC -# define EFD_CLOEXEC 02000000 -#endif +#include <linux/filter.h> +#include <linux/audit.h> +#include <sys/ptrace.h> +#include <linux/random.h> +#include <linux/stringify.h> #ifndef O_CLOEXEC # define O_CLOEXEC 02000000 #endif -#ifndef SOCK_DCCP -# define SOCK_DCCP 6 -#endif - -#ifndef SOCK_CLOEXEC -# define SOCK_CLOEXEC 02000000 -#endif - -#ifndef SOCK_NONBLOCK -# define SOCK_NONBLOCK 00004000 -#endif - -#ifndef MSG_CMSG_CLOEXEC -# define MSG_CMSG_CLOEXEC 0x40000000 -#endif - -#ifndef PERF_FLAG_FD_NO_GROUP -# define PERF_FLAG_FD_NO_GROUP (1UL << 0) -#endif - -#ifndef PERF_FLAG_FD_OUTPUT -# define PERF_FLAG_FD_OUTPUT (1UL << 1) -#endif - -#ifndef PERF_FLAG_PID_CGROUP -# define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */ -#endif - -#ifndef PERF_FLAG_FD_CLOEXEC -# define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ -#endif - +struct trace { + struct perf_tool tool; + struct syscalltbl *sctbl; + struct { + int max; + struct syscall *table; + struct { + struct perf_evsel *sys_enter, + *sys_exit; + } events; + } syscalls; + struct record_opts opts; + struct perf_evlist *evlist; + struct machine *host; + struct thread *current; + u64 base_time; + FILE *output; + unsigned long nr_events; + struct strlist *ev_qualifier; + struct { + size_t nr; + int *entries; + } ev_qualifier_ids; + struct intlist *tid_list; + struct intlist *pid_list; + struct { + size_t nr; + pid_t *entries; + } filter_pids; + double duration_filter; + double runtime_ms; + struct { + u64 vfs_getname, + proc_getname; + } stats; + unsigned int max_stack; + unsigned int min_stack; + bool not_ev_qualifier; + bool live; + bool full_time; + bool sched; + bool multiple_threads; + bool summary; + bool summary_only; + bool show_comm; + bool show_tool_stats; + bool trace_syscalls; + bool kernel_syscallchains; + bool force; + bool vfs_getname; + int trace_pgfaults; + int open_id; +}; struct tp_field { int offset; @@ -371,221 +368,6 @@ static size_t syscall_arg__scnprintf_int(char *bf, size_t size, #define SCA_INT syscall_arg__scnprintf_int -static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, prot = arg->val; - - if (prot == PROT_NONE) - return scnprintf(bf, size, "NONE"); -#define P_MMAP_PROT(n) \ - if (prot & PROT_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ - prot &= ~PROT_##n; \ - } - - P_MMAP_PROT(EXEC); - P_MMAP_PROT(READ); - P_MMAP_PROT(WRITE); -#ifdef PROT_SEM - P_MMAP_PROT(SEM); -#endif - P_MMAP_PROT(GROWSDOWN); - P_MMAP_PROT(GROWSUP); -#undef P_MMAP_PROT - - if (prot) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", prot); - - return printed; -} - -#define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot - -static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, flags = arg->val; - -#define P_MMAP_FLAG(n) \ - if (flags & MAP_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ - flags &= ~MAP_##n; \ - } - - P_MMAP_FLAG(SHARED); - P_MMAP_FLAG(PRIVATE); -#ifdef MAP_32BIT - P_MMAP_FLAG(32BIT); -#endif - P_MMAP_FLAG(ANONYMOUS); - P_MMAP_FLAG(DENYWRITE); - P_MMAP_FLAG(EXECUTABLE); - P_MMAP_FLAG(FILE); - P_MMAP_FLAG(FIXED); - P_MMAP_FLAG(GROWSDOWN); -#ifdef MAP_HUGETLB - P_MMAP_FLAG(HUGETLB); -#endif - P_MMAP_FLAG(LOCKED); - P_MMAP_FLAG(NONBLOCK); - P_MMAP_FLAG(NORESERVE); - P_MMAP_FLAG(POPULATE); - P_MMAP_FLAG(STACK); -#ifdef MAP_UNINITIALIZED - P_MMAP_FLAG(UNINITIALIZED); -#endif -#undef P_MMAP_FLAG - - if (flags) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); - - return printed; -} - -#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags - -static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, flags = arg->val; - -#define P_MREMAP_FLAG(n) \ - if (flags & MREMAP_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ - flags &= ~MREMAP_##n; \ - } - - P_MREMAP_FLAG(MAYMOVE); -#ifdef MREMAP_FIXED - P_MREMAP_FLAG(FIXED); -#endif -#undef P_MREMAP_FLAG - - if (flags) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); - - return printed; -} - -#define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags - -static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size, - struct syscall_arg *arg) -{ - int behavior = arg->val; - - switch (behavior) { -#define P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n) - P_MADV_BHV(NORMAL); - P_MADV_BHV(RANDOM); - P_MADV_BHV(SEQUENTIAL); - P_MADV_BHV(WILLNEED); - P_MADV_BHV(DONTNEED); - P_MADV_BHV(REMOVE); - P_MADV_BHV(DONTFORK); - P_MADV_BHV(DOFORK); - P_MADV_BHV(HWPOISON); -#ifdef MADV_SOFT_OFFLINE - P_MADV_BHV(SOFT_OFFLINE); -#endif - P_MADV_BHV(MERGEABLE); - P_MADV_BHV(UNMERGEABLE); -#ifdef MADV_HUGEPAGE - P_MADV_BHV(HUGEPAGE); -#endif -#ifdef MADV_NOHUGEPAGE - P_MADV_BHV(NOHUGEPAGE); -#endif -#ifdef MADV_DONTDUMP - P_MADV_BHV(DONTDUMP); -#endif -#ifdef MADV_DODUMP - P_MADV_BHV(DODUMP); -#endif -#undef P_MADV_PHV - default: break; - } - - return scnprintf(bf, size, "%#x", behavior); -} - -#define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior - -static size_t syscall_arg__scnprintf_flock(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, op = arg->val; - - if (op == 0) - return scnprintf(bf, size, "NONE"); -#define P_CMD(cmd) \ - if ((op & LOCK_##cmd) == LOCK_##cmd) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #cmd); \ - op &= ~LOCK_##cmd; \ - } - - P_CMD(SH); - P_CMD(EX); - P_CMD(NB); - P_CMD(UN); - P_CMD(MAND); - P_CMD(RW); - P_CMD(READ); - P_CMD(WRITE); -#undef P_OP - - if (op) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", op); - - return printed; -} - -#define SCA_FLOCK syscall_arg__scnprintf_flock - -static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg) -{ - enum syscall_futex_args { - SCF_UADDR = (1 << 0), - SCF_OP = (1 << 1), - SCF_VAL = (1 << 2), - SCF_TIMEOUT = (1 << 3), - SCF_UADDR2 = (1 << 4), - SCF_VAL3 = (1 << 5), - }; - int op = arg->val; - int cmd = op & FUTEX_CMD_MASK; - size_t printed = 0; - - switch (cmd) { -#define P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n); - P_FUTEX_OP(WAIT); arg->mask |= SCF_VAL3|SCF_UADDR2; break; - P_FUTEX_OP(WAKE); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; - P_FUTEX_OP(FD); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; - P_FUTEX_OP(REQUEUE); arg->mask |= SCF_VAL3|SCF_TIMEOUT; break; - P_FUTEX_OP(CMP_REQUEUE); arg->mask |= SCF_TIMEOUT; break; - P_FUTEX_OP(CMP_REQUEUE_PI); arg->mask |= SCF_TIMEOUT; break; - P_FUTEX_OP(WAKE_OP); break; - P_FUTEX_OP(LOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; - P_FUTEX_OP(UNLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; - P_FUTEX_OP(TRYLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2; break; - P_FUTEX_OP(WAIT_BITSET); arg->mask |= SCF_UADDR2; break; - P_FUTEX_OP(WAKE_BITSET); arg->mask |= SCF_UADDR2; break; - P_FUTEX_OP(WAIT_REQUEUE_PI); break; - default: printed = scnprintf(bf, size, "%#x", cmd); break; - } - - if (op & FUTEX_PRIVATE_FLAG) - printed += scnprintf(bf + printed, size - printed, "|PRIV"); - - if (op & FUTEX_CLOCK_REALTIME) - printed += scnprintf(bf + printed, size - printed, "|CLKRT"); - - return printed; -} - -#define SCA_FUTEX_OP syscall_arg__scnprintf_futex_op - static const char *bpf_cmd[] = { "MAP_CREATE", "MAP_LOOKUP_ELEM", "MAP_UPDATE_ELEM", "MAP_DELETE_ELEM", "MAP_GET_NEXT_KEY", "PROG_LOAD", @@ -652,110 +434,6 @@ static const char *socket_families[] = { }; static DEFINE_STRARRAY(socket_families); -#ifndef SOCK_TYPE_MASK -#define SOCK_TYPE_MASK 0xf -#endif - -static size_t syscall_arg__scnprintf_socket_type(char *bf, size_t size, - struct syscall_arg *arg) -{ - size_t printed; - int type = arg->val, - flags = type & ~SOCK_TYPE_MASK; - - type &= SOCK_TYPE_MASK; - /* - * Can't use a strarray, MIPS may override for ABI reasons. - */ - switch (type) { -#define P_SK_TYPE(n) case SOCK_##n: printed = scnprintf(bf, size, #n); break; - P_SK_TYPE(STREAM); - P_SK_TYPE(DGRAM); - P_SK_TYPE(RAW); - P_SK_TYPE(RDM); - P_SK_TYPE(SEQPACKET); - P_SK_TYPE(DCCP); - P_SK_TYPE(PACKET); -#undef P_SK_TYPE - default: - printed = scnprintf(bf, size, "%#x", type); - } - -#define P_SK_FLAG(n) \ - if (flags & SOCK_##n) { \ - printed += scnprintf(bf + printed, size - printed, "|%s", #n); \ - flags &= ~SOCK_##n; \ - } - - P_SK_FLAG(CLOEXEC); - P_SK_FLAG(NONBLOCK); -#undef P_SK_FLAG - - if (flags) - printed += scnprintf(bf + printed, size - printed, "|%#x", flags); - - return printed; -} - -#define SCA_SK_TYPE syscall_arg__scnprintf_socket_type - -#ifndef MSG_PROBE -#define MSG_PROBE 0x10 -#endif -#ifndef MSG_WAITFORONE -#define MSG_WAITFORONE 0x10000 -#endif -#ifndef MSG_SENDPAGE_NOTLAST -#define MSG_SENDPAGE_NOTLAST 0x20000 -#endif -#ifndef MSG_FASTOPEN -#define MSG_FASTOPEN 0x20000000 -#endif - -static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, flags = arg->val; - - if (flags == 0) - return scnprintf(bf, size, "NONE"); -#define P_MSG_FLAG(n) \ - if (flags & MSG_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ - flags &= ~MSG_##n; \ - } - - P_MSG_FLAG(OOB); - P_MSG_FLAG(PEEK); - P_MSG_FLAG(DONTROUTE); - P_MSG_FLAG(TRYHARD); - P_MSG_FLAG(CTRUNC); - P_MSG_FLAG(PROBE); - P_MSG_FLAG(TRUNC); - P_MSG_FLAG(DONTWAIT); - P_MSG_FLAG(EOR); - P_MSG_FLAG(WAITALL); - P_MSG_FLAG(FIN); - P_MSG_FLAG(SYN); - P_MSG_FLAG(CONFIRM); - P_MSG_FLAG(RST); - P_MSG_FLAG(ERRQUEUE); - P_MSG_FLAG(NOSIGNAL); - P_MSG_FLAG(MORE); - P_MSG_FLAG(WAITFORONE); - P_MSG_FLAG(SENDPAGE_NOTLAST); - P_MSG_FLAG(FASTOPEN); - P_MSG_FLAG(CMSG_CLOEXEC); -#undef P_MSG_FLAG - - if (flags) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); - - return printed; -} - -#define SCA_MSG_FLAGS syscall_arg__scnprintf_msg_flags - static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size, struct syscall_arg *arg) { @@ -788,116 +466,6 @@ static size_t syscall_arg__scnprintf_filename(char *bf, size_t size, #define SCA_FILENAME syscall_arg__scnprintf_filename -static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, flags = arg->val; - - if (!(flags & O_CREAT)) - arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */ - - if (flags == 0) - return scnprintf(bf, size, "RDONLY"); -#define P_FLAG(n) \ - if (flags & O_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ - flags &= ~O_##n; \ - } - - P_FLAG(APPEND); - P_FLAG(ASYNC); - P_FLAG(CLOEXEC); - P_FLAG(CREAT); - P_FLAG(DIRECT); - P_FLAG(DIRECTORY); - P_FLAG(EXCL); - P_FLAG(LARGEFILE); - P_FLAG(NOATIME); - P_FLAG(NOCTTY); -#ifdef O_NONBLOCK - P_FLAG(NONBLOCK); -#elif O_NDELAY - P_FLAG(NDELAY); -#endif -#ifdef O_PATH - P_FLAG(PATH); -#endif - P_FLAG(RDWR); -#ifdef O_DSYNC - if ((flags & O_SYNC) == O_SYNC) - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC"); - else { - P_FLAG(DSYNC); - } -#else - P_FLAG(SYNC); -#endif - P_FLAG(TRUNC); - P_FLAG(WRONLY); -#undef P_FLAG - - if (flags) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); - - return printed; -} - -#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags - -static size_t syscall_arg__scnprintf_perf_flags(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, flags = arg->val; - - if (flags == 0) - return 0; - -#define P_FLAG(n) \ - if (flags & PERF_FLAG_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ - flags &= ~PERF_FLAG_##n; \ - } - - P_FLAG(FD_NO_GROUP); - P_FLAG(FD_OUTPUT); - P_FLAG(PID_CGROUP); - P_FLAG(FD_CLOEXEC); -#undef P_FLAG - - if (flags) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); - - return printed; -} - -#define SCA_PERF_FLAGS syscall_arg__scnprintf_perf_flags - -static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, flags = arg->val; - - if (flags == 0) - return scnprintf(bf, size, "NONE"); -#define P_FLAG(n) \ - if (flags & EFD_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ - flags &= ~EFD_##n; \ - } - - P_FLAG(SEMAPHORE); - P_FLAG(CLOEXEC); - P_FLAG(NONBLOCK); -#undef P_FLAG - - if (flags) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); - - return printed; -} - -#define SCA_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags - static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size, struct syscall_arg *arg) { @@ -921,59 +489,6 @@ static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size, #define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags -static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg) -{ - int sig = arg->val; - - switch (sig) { -#define P_SIGNUM(n) case SIG##n: return scnprintf(bf, size, #n) - P_SIGNUM(HUP); - P_SIGNUM(INT); - P_SIGNUM(QUIT); - P_SIGNUM(ILL); - P_SIGNUM(TRAP); - P_SIGNUM(ABRT); - P_SIGNUM(BUS); - P_SIGNUM(FPE); - P_SIGNUM(KILL); - P_SIGNUM(USR1); - P_SIGNUM(SEGV); - P_SIGNUM(USR2); - P_SIGNUM(PIPE); - P_SIGNUM(ALRM); - P_SIGNUM(TERM); - P_SIGNUM(CHLD); - P_SIGNUM(CONT); - P_SIGNUM(STOP); - P_SIGNUM(TSTP); - P_SIGNUM(TTIN); - P_SIGNUM(TTOU); - P_SIGNUM(URG); - P_SIGNUM(XCPU); - P_SIGNUM(XFSZ); - P_SIGNUM(VTALRM); - P_SIGNUM(PROF); - P_SIGNUM(WINCH); - P_SIGNUM(IO); - P_SIGNUM(PWR); - P_SIGNUM(SYS); -#ifdef SIGEMT - P_SIGNUM(EMT); -#endif -#ifdef SIGSTKFLT - P_SIGNUM(STKFLT); -#endif -#ifdef SIGSWI - P_SIGNUM(SWI); -#endif - default: break; - } - - return scnprintf(bf, size, "%#x", sig); -} - -#define SCA_SIGNUM syscall_arg__scnprintf_signum - #if defined(__i386__) || defined(__x86_64__) /* * FIXME: Make this available to all arches. @@ -1001,16 +516,62 @@ static const char *tioctls[] = { static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401); #endif /* defined(__i386__) || defined(__x86_64__) */ +#ifndef GRND_NONBLOCK +#define GRND_NONBLOCK 0x0001 +#endif +#ifndef GRND_RANDOM +#define GRND_RANDOM 0x0002 +#endif + +static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_FLAG(n) \ + if (flags & GRND_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~GRND_##n; \ + } + + P_FLAG(RANDOM); + P_FLAG(NONBLOCK); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_GETRANDOM_FLAGS syscall_arg__scnprintf_getrandom_flags + #define STRARRAY(arg, name, array) \ .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \ .arg_parm = { [arg] = &strarray__##array, } +#include "trace/beauty/eventfd.c" +#include "trace/beauty/flock.c" +#include "trace/beauty/futex_op.c" +#include "trace/beauty/mmap.c" +#include "trace/beauty/mode_t.c" +#include "trace/beauty/msg_flags.c" +#include "trace/beauty/open_flags.c" +#include "trace/beauty/perf_event_open.c" +#include "trace/beauty/pid.c" +#include "trace/beauty/sched_policy.c" +#include "trace/beauty/seccomp.c" +#include "trace/beauty/signum.c" +#include "trace/beauty/socket_type.c" +#include "trace/beauty/waitid_options.c" + static struct syscall_fmt { const char *name; const char *alias; size_t (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg); void *arg_parm[6]; bool errmsg; + bool errpid; bool timeout; bool hexret; } syscall_fmts[] = { @@ -1028,6 +589,7 @@ static struct syscall_fmt { { .name = "chroot", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, { .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), }, + { .name = "clone", .errpid = true, }, { .name = "close", .errmsg = true, .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, { .name = "connect", .errmsg = true, }, @@ -1093,6 +655,11 @@ static struct syscall_fmt { { .name = "getdents64", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), }, + { .name = "getpid", .errpid = true, }, + { .name = "getpgid", .errpid = true, }, + { .name = "getppid", .errpid = true, }, + { .name = "getrandom", .errmsg = true, + .arg_scnprintf = { [2] = SCA_GETRANDOM_FLAGS, /* flags */ }, }, { .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "getxattr", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, @@ -1186,8 +753,7 @@ static struct syscall_fmt { [1] = SCA_FILENAME, /* filename */ [2] = SCA_OPEN_FLAGS, /* flags */ }, }, { .name = "perf_event_open", .errmsg = true, - .arg_scnprintf = { [1] = SCA_INT, /* pid */ - [2] = SCA_INT, /* cpu */ + .arg_scnprintf = { [2] = SCA_INT, /* cpu */ [3] = SCA_FD, /* group_fd */ [4] = SCA_PERF_FLAGS, /* flags */ }, }, { .name = "pipe2", .errmsg = true, @@ -1234,6 +800,11 @@ static struct syscall_fmt { .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, { .name = "rt_tgsigqueueinfo", .errmsg = true, .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, }, + { .name = "sched_setscheduler", .errmsg = true, + .arg_scnprintf = { [1] = SCA_SCHED_POLICY, /* policy */ }, }, + { .name = "seccomp", .errmsg = true, + .arg_scnprintf = { [0] = SCA_SECCOMP_OP, /* op */ + [1] = SCA_SECCOMP_FLAGS, /* flags */ }, }, { .name = "select", .errmsg = true, .timeout = true, }, { .name = "sendmmsg", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ @@ -1244,7 +815,9 @@ static struct syscall_fmt { { .name = "sendto", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ [3] = SCA_MSG_FLAGS, /* flags */ }, }, + { .name = "set_tid_address", .errpid = true, }, { .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), }, + { .name = "setpgid", .errmsg = true, }, { .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "setxattr", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, @@ -1287,6 +860,10 @@ static struct syscall_fmt { .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, { .name = "vmsplice", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "wait4", .errpid = true, + .arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, }, + { .name = "waitid", .errpid = true, + .arg_scnprintf = { [3] = SCA_WAITID_OPTIONS, /* options */ }, }, { .name = "write", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "writev", .errmsg = true, @@ -1398,59 +975,6 @@ fail: static const size_t trace__entry_str_size = 2048; -struct trace { - struct perf_tool tool; - struct { - int machine; - int open_id; - } audit; - struct { - int max; - struct syscall *table; - struct { - struct perf_evsel *sys_enter, - *sys_exit; - } events; - } syscalls; - struct record_opts opts; - struct perf_evlist *evlist; - struct machine *host; - struct thread *current; - u64 base_time; - FILE *output; - unsigned long nr_events; - struct strlist *ev_qualifier; - struct { - size_t nr; - int *entries; - } ev_qualifier_ids; - struct intlist *tid_list; - struct intlist *pid_list; - struct { - size_t nr; - pid_t *entries; - } filter_pids; - double duration_filter; - double runtime_ms; - struct { - u64 vfs_getname, - proc_getname; - } stats; - bool not_ev_qualifier; - bool live; - bool full_time; - bool sched; - bool multiple_threads; - bool summary; - bool summary_only; - bool show_comm; - bool show_tool_stats; - bool trace_syscalls; - bool force; - bool vfs_getname; - int trace_pgfaults; -}; - static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname) { struct thread_trace *ttrace = thread__priv(thread); @@ -1618,6 +1142,7 @@ static int trace__process_event(struct trace *trace, struct machine *machine, color_fprintf(trace->output, PERF_COLOR_RED, "LOST %" PRIu64 " events!\n", event->lost.lost); ret = machine__process_lost_event(machine, event, sample); + break; default: ret = machine__process_event(machine, event, sample); break; @@ -1675,6 +1200,10 @@ static int syscall__set_arg_fmts(struct syscall *sc) sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx]; else if (field->flags & FIELD_IS_POINTER) sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex; + else if (strcmp(field->type, "pid_t") == 0) + sc->arg_scnprintf[idx] = SCA_PID; + else if (strcmp(field->type, "umode_t") == 0) + sc->arg_scnprintf[idx] = SCA_MODE_T; ++idx; } @@ -1685,7 +1214,7 @@ static int trace__read_syscall_info(struct trace *trace, int id) { char tp_name[128]; struct syscall *sc; - const char *name = audit_syscall_to_name(id, trace->audit.machine); + const char *name = syscalltbl__name(trace->sctbl, id); if (name == NULL) return -1; @@ -1760,7 +1289,7 @@ static int trace__validate_ev_qualifier(struct trace *trace) strlist__for_each(pos, trace->ev_qualifier) { const char *sc = pos->s; - int id = audit_name_to_syscall(sc, trace->audit.machine); + int id = syscalltbl__id(trace->sctbl, sc); if (id < 0) { if (err == 0) { @@ -1846,7 +1375,12 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, "%ld", val); } } - } else { + } else if (IS_ERR(sc->tp_format)) { + /* + * If we managed to read the tracepoint /format file, then we + * may end up not having any args, like with gettid(), so only + * print the raw args when we didn't manage to read it. + */ int i = 0; while (i < 6) { @@ -1987,7 +1521,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, goto out_put; } - if (!trace->summary_only) + if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) trace__printf_interrupted_entry(trace, sample); ttrace->entry_time = sample->time; @@ -1998,7 +1532,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, args, trace, thread); if (sc->is_exit) { - if (!trace->duration_filter && !trace->summary_only) { + if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) { trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output); fprintf(trace->output, "%-70s\n", ttrace->entry_str); } @@ -2018,6 +1552,29 @@ out_put: return err; } +static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evsel, + struct perf_sample *sample, + struct callchain_cursor *cursor) +{ + struct addr_location al; + + if (machine__resolve(trace->host, &al, sample) < 0 || + thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, trace->max_stack)) + return -1; + + return 0; +} + +static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sample) +{ + /* TODO: user-configurable print_opts */ + const unsigned int print_opts = EVSEL__PRINT_SYM | + EVSEL__PRINT_DSO | + EVSEL__PRINT_UNKNOWN_AS_ADDR; + + return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, trace->output); +} + static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) @@ -2025,7 +1582,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, long ret; u64 duration = 0; struct thread *thread; - int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1; + int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0; struct syscall *sc = trace__syscall_info(trace, evsel, id); struct thread_trace *ttrace; @@ -2042,7 +1599,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, ret = perf_evsel__sc_tp_uint(evsel, ret, sample); - if (id == trace->audit.open_id && ret >= 0 && ttrace->filename.pending_open) { + if (id == trace->open_id && ret >= 0 && ttrace->filename.pending_open) { trace__set_fd_pathname(thread, ret, ttrace->filename.name); ttrace->filename.pending_open = false; ++trace->stats.vfs_getname; @@ -2057,6 +1614,15 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, } else if (trace->duration_filter) goto out; + if (sample->callchain) { + callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor); + if (callchain_ret == 0) { + if (callchain_cursor.nr < trace->min_stack) + goto out; + callchain_ret = 1; + } + } + if (trace->summary_only) goto out; @@ -2073,7 +1639,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, if (sc->fmt == NULL) { signed_print: fprintf(trace->output, ") = %ld", ret); - } else if (ret < 0 && sc->fmt->errmsg) { + } else if (ret < 0 && (sc->fmt->errmsg || sc->fmt->errpid)) { char bf[STRERR_BUFSIZE]; const char *emsg = strerror_r(-ret, bf, sizeof(bf)), *e = audit_errno_to_name(-ret); @@ -2083,10 +1649,24 @@ signed_print: fprintf(trace->output, ") = 0 Timeout"); else if (sc->fmt->hexret) fprintf(trace->output, ") = %#lx", ret); - else + else if (sc->fmt->errpid) { + struct thread *child = machine__find_thread(trace->host, ret, ret); + + if (child != NULL) { + fprintf(trace->output, ") = %ld", ret); + if (child->comm_set) + fprintf(trace->output, " (%s)", thread__comm_str(child)); + thread__put(child); + } + } else goto signed_print; fputc('\n', trace->output); + + if (callchain_ret > 0) + trace__fprintf_callchain(trace, sample); + else if (callchain_ret < 0) + pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel)); out: ttrace->entry_pending = false; err = 0; @@ -2217,6 +1797,17 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) { + int callchain_ret = 0; + + if (sample->callchain) { + callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor); + if (callchain_ret == 0) { + if (callchain_cursor.nr < trace->min_stack) + goto out; + callchain_ret = 1; + } + } + trace__printf_interrupted_entry(trace, sample); trace__fprintf_tstamp(trace, sample->time, trace->output); @@ -2234,6 +1825,12 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, } fprintf(trace->output, ")\n"); + + if (callchain_ret > 0) + trace__fprintf_callchain(trace, sample); + else if (callchain_ret < 0) + pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel)); +out: return 0; } @@ -2264,8 +1861,19 @@ static int trace__pgfault(struct trace *trace, char map_type = 'd'; struct thread_trace *ttrace; int err = -1; + int callchain_ret = 0; thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); + + if (sample->callchain) { + callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor); + if (callchain_ret == 0) { + if (callchain_cursor.nr < trace->min_stack) + goto out_put; + callchain_ret = 1; + } + } + ttrace = thread__trace(thread, trace->output); if (ttrace == NULL) goto out_put; @@ -2307,6 +1915,11 @@ static int trace__pgfault(struct trace *trace, print_location(trace->output, sample, &al, true, false); fprintf(trace->output, " (%c%c)\n", map_type, al.level); + + if (callchain_ret > 0) + trace__fprintf_callchain(trace, sample); + else if (callchain_ret < 0) + pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel)); out: err = 0; out_put: @@ -2326,6 +1939,23 @@ static bool skip_sample(struct trace *trace, struct perf_sample *sample) return false; } +static void trace__set_base_time(struct trace *trace, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + /* + * BPF events were not setting PERF_SAMPLE_TIME, so be more robust + * and don't use sample->time unconditionally, we may end up having + * some other event in the future without PERF_SAMPLE_TIME for good + * reason, i.e. we may not be interested in its timestamps, just in + * it taking place, picking some piece of information when it + * appears in our event stream (vfs_getname comes to mind). + */ + if (trace->base_time == 0 && !trace->full_time && + (evsel->attr.sample_type & PERF_SAMPLE_TIME)) + trace->base_time = sample->time; +} + static int trace__process_sample(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -2340,8 +1970,7 @@ static int trace__process_sample(struct perf_tool *tool, if (skip_sample(trace, sample)) return 0; - if (!trace->full_time && trace->base_time == 0) - trace->base_time = sample->time; + trace__set_base_time(trace, evsel, sample); if (handler) { ++trace->nr_events; @@ -2450,8 +2079,7 @@ static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist) return true; } -static int perf_evlist__add_pgfault(struct perf_evlist *evlist, - u64 config) +static struct perf_evsel *perf_evsel__new_pgfault(u64 config) { struct perf_evsel *evsel; struct perf_event_attr attr = { @@ -2465,13 +2093,10 @@ static int perf_evlist__add_pgfault(struct perf_evlist *evlist, event_attr_init(&attr); evsel = perf_evsel__new(&attr); - if (!evsel) - return -ENOMEM; - - evsel->handler = trace__pgfault; - perf_evlist__add(evlist, evsel); + if (evsel) + evsel->handler = trace__pgfault; - return 0; + return evsel; } static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample) @@ -2479,9 +2104,6 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st const u32 type = event->header.type; struct perf_evsel *evsel; - if (!trace->full_time && trace->base_time == 0) - trace->base_time = sample->time; - if (type != PERF_RECORD_SAMPLE) { trace__process_event(trace, trace->host, event, sample); return; @@ -2493,6 +2115,8 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st return; } + trace__set_base_time(trace, evsel, sample); + if (evsel->attr.type == PERF_TYPE_TRACEPOINT && sample->raw_data == NULL) { fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", @@ -2527,6 +2151,15 @@ static int trace__add_syscall_newtp(struct trace *trace) perf_evlist__add(evlist, sys_enter); perf_evlist__add(evlist, sys_exit); + if (callchain_param.enabled && !trace->kernel_syscallchains) { + /* + * We're interested only in the user space callchain + * leading to the syscall, allow overriding that for + * debugging reasons using --kernel_syscall_callchains + */ + sys_exit->attr.exclude_callchain_kernel = 1; + } + trace->syscalls.events.sys_enter = sys_enter; trace->syscalls.events.sys_exit = sys_exit; @@ -2565,7 +2198,7 @@ out_enomem: static int trace__run(struct trace *trace, int argc, const char **argv) { struct perf_evlist *evlist = trace->evlist; - struct perf_evsel *evsel; + struct perf_evsel *evsel, *pgfault_maj = NULL, *pgfault_min = NULL; int err = -1, i; unsigned long before; const bool forks = argc > 0; @@ -2579,14 +2212,19 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (trace->trace_syscalls) trace->vfs_getname = perf_evlist__add_vfs_getname(evlist); - if ((trace->trace_pgfaults & TRACE_PFMAJ) && - perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ)) { - goto out_error_mem; + if ((trace->trace_pgfaults & TRACE_PFMAJ)) { + pgfault_maj = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MAJ); + if (pgfault_maj == NULL) + goto out_error_mem; + perf_evlist__add(evlist, pgfault_maj); } - if ((trace->trace_pgfaults & TRACE_PFMIN) && - perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN)) - goto out_error_mem; + if ((trace->trace_pgfaults & TRACE_PFMIN)) { + pgfault_min = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MIN); + if (pgfault_min == NULL) + goto out_error_mem; + perf_evlist__add(evlist, pgfault_min); + } if (trace->sched && perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime", @@ -2605,7 +2243,45 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out_delete_evlist; } - perf_evlist__config(evlist, &trace->opts); + perf_evlist__config(evlist, &trace->opts, NULL); + + if (callchain_param.enabled) { + bool use_identifier = false; + + if (trace->syscalls.events.sys_exit) { + perf_evsel__config_callchain(trace->syscalls.events.sys_exit, + &trace->opts, &callchain_param); + use_identifier = true; + } + + if (pgfault_maj) { + perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param); + use_identifier = true; + } + + if (pgfault_min) { + perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param); + use_identifier = true; + } + + if (use_identifier) { + /* + * Now we have evsels with different sample_ids, use + * PERF_SAMPLE_IDENTIFIER to map from sample to evsel + * from a fixed position in each ring buffer record. + * + * As of this the changeset introducing this comment, this + * isn't strictly needed, as the fields that can come before + * PERF_SAMPLE_ID are all used, but we'll probably disable + * some of those for things like copying the payload of + * pointer syscall arguments, and for vfs_getname we don't + * need PERF_SAMPLE_ADDR and PERF_SAMPLE_IP, so do this + * here as a warning we need to use PERF_SAMPLE_IDENTIFIER. + */ + perf_evlist__set_sample_bit(evlist, IDENTIFIER); + perf_evlist__reset_sample_bit(evlist, ID); + } + } signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); @@ -2883,15 +2559,29 @@ static size_t trace__fprintf_threads_header(FILE *fp) return printed; } +DEFINE_RESORT_RB(syscall_stats, a->msecs > b->msecs, + struct stats *stats; + double msecs; + int syscall; +) +{ + struct int_node *source = rb_entry(nd, struct int_node, rb_node); + struct stats *stats = source->priv; + + entry->syscall = source->i; + entry->stats = stats; + entry->msecs = stats ? (u64)stats->n * (avg_stats(stats) / NSEC_PER_MSEC) : 0; +} + static size_t thread__dump_stats(struct thread_trace *ttrace, struct trace *trace, FILE *fp) { - struct stats *stats; size_t printed = 0; struct syscall *sc; - struct int_node *inode = intlist__first(ttrace->syscall_stats); + struct rb_node *nd; + DECLARE_RESORT_RB_INTLIST(syscall_stats, ttrace->syscall_stats); - if (inode == NULL) + if (syscall_stats == NULL) return 0; printed += fprintf(fp, "\n"); @@ -2900,9 +2590,8 @@ static size_t thread__dump_stats(struct thread_trace *ttrace, printed += fprintf(fp, " (msec) (msec) (msec) (msec) (%%)\n"); printed += fprintf(fp, " --------------- -------- --------- --------- --------- --------- ------\n"); - /* each int_node is a syscall */ - while (inode) { - stats = inode->priv; + resort_rb__for_each(nd, syscall_stats) { + struct stats *stats = syscall_stats_entry->stats; if (stats) { double min = (double)(stats->min) / NSEC_PER_MSEC; double max = (double)(stats->max) / NSEC_PER_MSEC; @@ -2913,34 +2602,23 @@ static size_t thread__dump_stats(struct thread_trace *ttrace, pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0; avg /= NSEC_PER_MSEC; - sc = &trace->syscalls.table[inode->i]; + sc = &trace->syscalls.table[syscall_stats_entry->syscall]; printed += fprintf(fp, " %-15s", sc->name); printed += fprintf(fp, " %8" PRIu64 " %9.3f %9.3f %9.3f", - n, avg * n, min, avg); + n, syscall_stats_entry->msecs, min, avg); printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct); } - - inode = intlist__next(inode); } + resort_rb__delete(syscall_stats); printed += fprintf(fp, "\n\n"); return printed; } -/* struct used to pass data to per-thread function */ -struct summary_data { - FILE *fp; - struct trace *trace; - size_t printed; -}; - -static int trace__fprintf_one_thread(struct thread *thread, void *priv) +static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trace *trace) { - struct summary_data *data = priv; - FILE *fp = data->fp; - size_t printed = data->printed; - struct trace *trace = data->trace; + size_t printed = 0; struct thread_trace *ttrace = thread__priv(thread); double ratio; @@ -2956,25 +2634,45 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv) printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj); if (ttrace->pfmin) printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin); - printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms); + if (trace->sched) + printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms); + else if (fputc('\n', fp) != EOF) + ++printed; + printed += thread__dump_stats(ttrace, trace, fp); - data->printed += printed; + return printed; +} - return 0; +static unsigned long thread__nr_events(struct thread_trace *ttrace) +{ + return ttrace ? ttrace->nr_events : 0; +} + +DEFINE_RESORT_RB(threads, (thread__nr_events(a->thread->priv) < thread__nr_events(b->thread->priv)), + struct thread *thread; +) +{ + entry->thread = rb_entry(nd, struct thread, rb_node); } static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp) { - struct summary_data data = { - .fp = fp, - .trace = trace - }; - data.printed = trace__fprintf_threads_header(fp); + DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host); + size_t printed = trace__fprintf_threads_header(fp); + struct rb_node *nd; + + if (threads == NULL) { + fprintf(fp, "%s", "Error sorting output by nr_events!\n"); + return 0; + } - machine__for_each_thread(trace->host, trace__fprintf_one_thread, &data); + resort_rb__for_each(nd, threads) + printed += trace__fprintf_thread(fp, threads_entry->thread, trace); - return data.printed; + resort_rb__delete(threads); + + return printed; } static int trace__set_duration(const struct option *opt, const char *str, @@ -3070,10 +2768,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; struct trace trace = { - .audit = { - .machine = audit_detect_machine(), - .open_id = audit_name_to_syscall("open", trace.audit.machine), - }, .syscalls = { . max = -1, }, @@ -3091,6 +2785,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) .output = stderr, .show_comm = true, .trace_syscalls = true, + .kernel_syscallchains = false, + .max_stack = UINT_MAX, }; const char *output_name = NULL; const char *ev_qualifier_str = NULL; @@ -3136,10 +2832,24 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) "Trace pagefaults", parse_pagefaults, "maj"), OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"), OPT_BOOLEAN('f', "force", &trace.force, "don't complain, do it"), + OPT_CALLBACK(0, "call-graph", &trace.opts, + "record_mode[,record_size]", record_callchain_help, + &record_parse_callchain_opt), + OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains, + "Show the kernel callchains on the syscall exit path"), + OPT_UINTEGER(0, "min-stack", &trace.min_stack, + "Set the minimum stack depth when parsing the callchain, " + "anything below the specified depth will be ignored."), + OPT_UINTEGER(0, "max-stack", &trace.max_stack, + "Set the maximum stack depth when parsing the callchain, " + "anything beyond the specified depth will be ignored. " + "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)), OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout, "per thread proc mmap processing timeout in ms"), OPT_END() }; + bool __maybe_unused max_stack_user_set = true; + bool mmap_pages_user_set = true; const char * const trace_subcommands[] = { "record", NULL }; int err; char bf[BUFSIZ]; @@ -3148,8 +2858,9 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) signal(SIGFPE, sighandler_dump_stack); trace.evlist = perf_evlist__new(); + trace.sctbl = syscalltbl__new(); - if (trace.evlist == NULL) { + if (trace.evlist == NULL || trace.sctbl == NULL) { pr_err("Not enough memory to run!\n"); err = -ENOMEM; goto out; @@ -3158,11 +2869,40 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands, trace_usage, PARSE_OPT_STOP_AT_NON_OPTION); + err = bpf__setup_stdout(trace.evlist); + if (err) { + bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf)); + pr_err("ERROR: Setup BPF stdout failed: %s\n", bf); + goto out; + } + + err = -1; + if (trace.trace_pgfaults) { trace.opts.sample_address = true; trace.opts.sample_time = true; } + if (trace.opts.mmap_pages == UINT_MAX) + mmap_pages_user_set = false; + + if (trace.max_stack == UINT_MAX) { + trace.max_stack = sysctl_perf_event_max_stack; + max_stack_user_set = false; + } + +#ifdef HAVE_DWARF_UNWIND_SUPPORT + if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled) + record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false); +#endif + + if (callchain_param.enabled) { + if (!mmap_pages_user_set && geteuid() == 0) + trace.opts.mmap_pages = perf_event_mlock_kb_in_pages() * 4; + + symbol_conf.use_callchain = true; + } + if (trace.evlist->nr_entries > 0) evlist__set_evsel_handler(trace.evlist, trace__event_handler); @@ -3179,6 +2919,11 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) return -1; } + if (!trace.trace_syscalls && ev_qualifier_str) { + pr_err("The -e option can't be used with --no-syscalls.\n"); + goto out; + } + if (output_name != NULL) { err = trace__open_output(&trace, output_name); if (err < 0) { @@ -3187,6 +2932,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) } } + trace.open_id = syscalltbl__id(trace.sctbl, "open"); + if (ev_qualifier_str != NULL) { const char *s = ev_qualifier_str; struct strlist_config slist_config = { diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index f7d7f5a..1e46277 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -27,7 +27,7 @@ NO_PERF_REGS := 1 ifeq ($(ARCH),x86) $(call detected,CONFIG_X86) ifeq (${IS_64_BIT}, 1) - CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT + CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 $(call detected,CONFIG_X86_64) @@ -268,6 +268,12 @@ else ifneq ($(feature-dwarf), 1) msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); NO_DWARF := 1 + else + ifneq ($(feature-dwarf_getlocations), 1) + msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157); + else + CFLAGS += -DHAVE_DWARF_GETLOCATIONS + endif # dwarf_getlocations endif # Dwarf support endif # libelf support endif # NO_LIBELF @@ -289,9 +295,6 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT endif - # include ARCH specific config - -include $(src-perf)/arch/$(ARCH)/Makefile - ifndef NO_DWARF ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined) msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled); diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index 6461e02..3573f31 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -92,6 +92,22 @@ error: return ret; } +static int use_arch_timestamp; + +static inline uint64_t +get_arch_timestamp(void) +{ +#if defined(__i386__) || defined(__x86_64__) + unsigned int low, high; + + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + + return low | ((uint64_t)high) << 32; +#else + return 0; +#endif +} + #define NSEC_PER_SEC 1000000000 static int perf_clk_id = CLOCK_MONOTONIC; @@ -107,6 +123,9 @@ perf_get_timestamp(void) struct timespec ts; int ret; + if (use_arch_timestamp) + return get_arch_timestamp(); + ret = clock_gettime(perf_clk_id, &ts); if (ret) return 0; @@ -203,6 +222,17 @@ perf_close_marker_file(void) munmap(marker_addr, pgsz); } +static void +init_arch_timestamp(void) +{ + char *str = getenv("JITDUMP_USE_ARCH_TIMESTAMP"); + + if (!str || !*str || !strcmp(str, "0")) + return; + + use_arch_timestamp = 1; +} + void *jvmti_open(void) { int pad_cnt; @@ -211,11 +241,17 @@ void *jvmti_open(void) int fd; FILE *fp; + init_arch_timestamp(); + /* * check if clockid is supported */ - if (!perf_get_timestamp()) - warnx("jvmti: kernel does not support %d clock id", perf_clk_id); + if (!perf_get_timestamp()) { + if (use_arch_timestamp) + warnx("jvmti: arch timestamp not supported"); + else + warnx("jvmti: kernel does not support %d clock id", perf_clk_id); + } memset(&header, 0, sizeof(header)); @@ -263,6 +299,9 @@ void *jvmti_open(void) header.timestamp = perf_get_timestamp(); + if (use_arch_timestamp) + header.flags |= JITDUMP_FLAGS_ARCH_TIMESTAMP; + if (!fwrite(&header, sizeof(header), 1, fp)) { warn("jvmti: cannot write dumpfile header"); goto error; diff --git a/tools/perf/perf.c b/tools/perf/perf.c index aaee0a7..7970008 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -17,6 +17,7 @@ #include <subcmd/parse-options.h> #include "util/bpf-loader.h" #include "util/debug.h" +#include <api/fs/fs.h> #include <api/fs/tracing_path.h> #include <pthread.h> #include <stdlib.h> @@ -308,9 +309,11 @@ static int handle_alias(int *argcp, const char ***argv) if (*argcp > 1) { struct strbuf buf; - strbuf_init(&buf, PATH_MAX); - strbuf_addstr(&buf, alias_string); - sq_quote_argv(&buf, (*argv) + 1, PATH_MAX); + if (strbuf_init(&buf, PATH_MAX) < 0 || + strbuf_addstr(&buf, alias_string) < 0 || + sq_quote_argv(&buf, (*argv) + 1, + PATH_MAX) < 0) + die("Failed to allocate memory."); free(alias_string); alias_string = buf.buf; } @@ -533,6 +536,7 @@ int main(int argc, const char **argv) { const char *cmd; char sbuf[STRERR_BUFSIZE]; + int value; /* libsubcmd init */ exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT); @@ -542,6 +546,9 @@ int main(int argc, const char **argv) page_size = sysconf(_SC_PAGE_SIZE); cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE); + if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0) + sysctl_perf_event_max_stack = value; + cmd = extract_argv0_path(argv[0]); if (!cmd) cmd = "perf-help"; @@ -549,6 +556,7 @@ int main(int argc, const char **argv) srandom(time(NULL)); perf_config(perf_default_config, NULL); + set_buildid_dir(NULL); /* get debugfs/tracefs mount point from /proc/mounts */ tracing_path_mount(); @@ -572,7 +580,6 @@ int main(int argc, const char **argv) } if (!prefixcmp(cmd, "trace")) { #ifdef HAVE_LIBAUDIT_SUPPORT - set_buildid_dir(NULL); setup_path(); argv[0] = "trace"; return cmd_trace(argc, argv, NULL); @@ -587,7 +594,6 @@ int main(int argc, const char **argv) argc--; handle_options(&argv, &argc, NULL); commit_pager_choice(); - set_buildid_dir(NULL); if (argc > 0) { if (!prefixcmp(argv[0], "--")) diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 5381a01..cd8f1b1 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -52,7 +52,6 @@ struct record_opts { bool sample_weight; bool sample_time; bool sample_time_set; - bool callgraph_set; bool period; bool running_time; bool full_auxtrace; diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py index 1b02cdc..7656ff8 100644 --- a/tools/perf/scripts/python/export-to-postgresql.py +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -34,10 +34,9 @@ import datetime # # ubuntu: # -# $ sudo apt-get install postgresql +# $ sudo apt-get install postgresql python-pyside.qtsql libqt4-sql-psql # $ sudo su - postgres -# $ createuser <your user id here> -# Shall the new role be a superuser? (y/n) y +# $ createuser -s <your user id here> # # An example of using this script with Intel PT: # @@ -224,11 +223,14 @@ sys.path.append(os.environ['PERF_EXEC_PATH'] + \ perf_db_export_mode = True perf_db_export_calls = False +perf_db_export_callchains = False + def usage(): - print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>]" + print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]" print >> sys.stderr, "where: columns 'all' or 'branches'" - print >> sys.stderr, " calls 'calls' => create calls table" + print >> sys.stderr, " calls 'calls' => create calls and call_paths table" + print >> sys.stderr, " callchains 'callchains' => create call_paths table" raise Exception("Too few arguments") if (len(sys.argv) < 2): @@ -246,9 +248,11 @@ if columns not in ("all", "branches"): branches = (columns == "branches") -if (len(sys.argv) >= 4): - if (sys.argv[3] == "calls"): +for i in range(3,len(sys.argv)): + if (sys.argv[i] == "calls"): perf_db_export_calls = True + elif (sys.argv[i] == "callchains"): + perf_db_export_callchains = True else: usage() @@ -359,14 +363,16 @@ else: 'transaction bigint,' 'data_src bigint,' 'branch_type integer,' - 'in_tx boolean)') + 'in_tx boolean,' + 'call_path_id bigint)') -if perf_db_export_calls: +if perf_db_export_calls or perf_db_export_callchains: do_query(query, 'CREATE TABLE call_paths (' 'id bigint NOT NULL,' 'parent_id bigint,' 'symbol_id bigint,' 'ip bigint)') +if perf_db_export_calls: do_query(query, 'CREATE TABLE calls (' 'id bigint NOT NULL,' 'thread_id bigint,' @@ -428,7 +434,7 @@ do_query(query, 'CREATE VIEW comm_threads_view AS ' '(SELECT tid FROM threads WHERE id = thread_id) AS tid' ' FROM comm_threads') -if perf_db_export_calls: +if perf_db_export_calls or perf_db_export_callchains: do_query(query, 'CREATE VIEW call_paths_view AS ' 'SELECT ' 'c.id,' @@ -444,6 +450,7 @@ if perf_db_export_calls: '(SELECT dso_id FROM symbols WHERE id = p.symbol_id) AS parent_dso_id,' '(SELECT dso FROM symbols_view WHERE id = p.symbol_id) AS parent_dso_short_name' ' FROM call_paths c INNER JOIN call_paths p ON p.id = c.parent_id') +if perf_db_export_calls: do_query(query, 'CREATE VIEW calls_view AS ' 'SELECT ' 'calls.id,' @@ -541,8 +548,9 @@ dso_file = open_output_file("dso_table.bin") symbol_file = open_output_file("symbol_table.bin") branch_type_file = open_output_file("branch_type_table.bin") sample_file = open_output_file("sample_table.bin") -if perf_db_export_calls: +if perf_db_export_calls or perf_db_export_callchains: call_path_file = open_output_file("call_path_table.bin") +if perf_db_export_calls: call_file = open_output_file("call_table.bin") def trace_begin(): @@ -554,8 +562,8 @@ def trace_begin(): comm_table(0, "unknown") dso_table(0, 0, "unknown", "unknown", "") symbol_table(0, 0, 0, 0, 0, "unknown") - sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) - if perf_db_export_calls: + sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) + if perf_db_export_calls or perf_db_export_callchains: call_path_table(0, 0, 0, 0) unhandled_count = 0 @@ -571,8 +579,9 @@ def trace_end(): copy_output_file(symbol_file, "symbols") copy_output_file(branch_type_file, "branch_types") copy_output_file(sample_file, "samples") - if perf_db_export_calls: + if perf_db_export_calls or perf_db_export_callchains: copy_output_file(call_path_file, "call_paths") + if perf_db_export_calls: copy_output_file(call_file, "calls") print datetime.datetime.today(), "Removing intermediate files..." @@ -585,8 +594,9 @@ def trace_end(): remove_output_file(symbol_file) remove_output_file(branch_type_file) remove_output_file(sample_file) - if perf_db_export_calls: + if perf_db_export_calls or perf_db_export_callchains: remove_output_file(call_path_file) + if perf_db_export_calls: remove_output_file(call_file) os.rmdir(output_dir_name) print datetime.datetime.today(), "Adding primary keys" @@ -599,8 +609,9 @@ def trace_end(): do_query(query, 'ALTER TABLE symbols ADD PRIMARY KEY (id)') do_query(query, 'ALTER TABLE branch_types ADD PRIMARY KEY (id)') do_query(query, 'ALTER TABLE samples ADD PRIMARY KEY (id)') - if perf_db_export_calls: + if perf_db_export_calls or perf_db_export_callchains: do_query(query, 'ALTER TABLE call_paths ADD PRIMARY KEY (id)') + if perf_db_export_calls: do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)') print datetime.datetime.today(), "Adding foreign keys" @@ -623,10 +634,11 @@ def trace_end(): 'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id),' 'ADD CONSTRAINT todsofk FOREIGN KEY (to_dso_id) REFERENCES dsos (id),' 'ADD CONSTRAINT tosymbolfk FOREIGN KEY (to_symbol_id) REFERENCES symbols (id)') - if perf_db_export_calls: + if perf_db_export_calls or perf_db_export_callchains: do_query(query, 'ALTER TABLE call_paths ' 'ADD CONSTRAINT parentfk FOREIGN KEY (parent_id) REFERENCES call_paths (id),' 'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id)') + if perf_db_export_calls: do_query(query, 'ALTER TABLE calls ' 'ADD CONSTRAINT threadfk FOREIGN KEY (thread_id) REFERENCES threads (id),' 'ADD CONSTRAINT commfk FOREIGN KEY (comm_id) REFERENCES comms (id),' @@ -694,11 +706,11 @@ def branch_type_table(branch_type, name, *x): value = struct.pack(fmt, 2, 4, branch_type, n, name) branch_type_file.write(value) -def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, *x): +def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, call_path_id, *x): if branches: - value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiB", 17, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx) + value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiBiq", 18, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx, 8, call_path_id) else: - value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx) + value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiBiq", 22, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx, 8, call_path_id) sample_file.write(value) def call_path_table(cp_id, parent_id, symbol_id, ip, *x): diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 1ba628e..66a2898 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -37,6 +37,8 @@ perf-y += topology.o perf-y += cpumap.o perf-y += stat.o perf-y += event_update.o +perf-y += event-times.o +perf-y += backward-ring-buffer.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c new file mode 100644 index 0000000..d9ba991 --- /dev/null +++ b/tools/perf/tests/backward-ring-buffer.c @@ -0,0 +1,151 @@ +/* + * Test backward bit in event attribute, read ring buffer from end to + * beginning + */ + +#include <perf.h> +#include <evlist.h> +#include <sys/prctl.h> +#include "tests.h" +#include "debug.h" + +#define NR_ITERS 111 + +static void testcase(void) +{ + int i; + + for (i = 0; i < NR_ITERS; i++) { + char proc_name[10]; + + snprintf(proc_name, sizeof(proc_name), "p:%d\n", i); + prctl(PR_SET_NAME, proc_name); + } +} + +static int count_samples(struct perf_evlist *evlist, int *sample_count, + int *comm_count) +{ + int i; + + for (i = 0; i < evlist->nr_mmaps; i++) { + union perf_event *event; + + perf_evlist__mmap_read_catchup(evlist, i); + while ((event = perf_evlist__mmap_read_backward(evlist, i)) != NULL) { + const u32 type = event->header.type; + + switch (type) { + case PERF_RECORD_SAMPLE: + (*sample_count)++; + break; + case PERF_RECORD_COMM: + (*comm_count)++; + break; + default: + pr_err("Unexpected record of type %d\n", type); + return TEST_FAIL; + } + } + } + return TEST_OK; +} + +static int do_test(struct perf_evlist *evlist, int mmap_pages, + int *sample_count, int *comm_count) +{ + int err; + char sbuf[STRERR_BUFSIZE]; + + err = perf_evlist__mmap(evlist, mmap_pages, true); + if (err < 0) { + pr_debug("perf_evlist__mmap: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); + return TEST_FAIL; + } + + perf_evlist__enable(evlist); + testcase(); + perf_evlist__disable(evlist); + + err = count_samples(evlist, sample_count, comm_count); + perf_evlist__munmap(evlist); + return err; +} + + +int test__backward_ring_buffer(int subtest __maybe_unused) +{ + int ret = TEST_SKIP, err, sample_count = 0, comm_count = 0; + char pid[16], sbuf[STRERR_BUFSIZE]; + struct perf_evlist *evlist; + struct perf_evsel *evsel __maybe_unused; + struct parse_events_error parse_error; + struct record_opts opts = { + .target = { + .uid = UINT_MAX, + .uses_mmap = true, + }, + .freq = 0, + .mmap_pages = 256, + .default_interval = 1, + }; + + snprintf(pid, sizeof(pid), "%d", getpid()); + pid[sizeof(pid) - 1] = '\0'; + opts.target.tid = opts.target.pid = pid; + + evlist = perf_evlist__new(); + if (!evlist) { + pr_debug("No ehough memory to create evlist\n"); + return TEST_FAIL; + } + + err = perf_evlist__create_maps(evlist, &opts.target); + if (err < 0) { + pr_debug("Not enough memory to create thread/cpu maps\n"); + goto out_delete_evlist; + } + + bzero(&parse_error, sizeof(parse_error)); + err = parse_events(evlist, "syscalls:sys_enter_prctl", &parse_error); + if (err) { + pr_debug("Failed to parse tracepoint event, try use root\n"); + ret = TEST_SKIP; + goto out_delete_evlist; + } + + perf_evlist__config(evlist, &opts, NULL); + + /* Set backward bit, ring buffer should be writing from end */ + evlist__for_each(evlist, evsel) + evsel->attr.write_backward = 1; + + err = perf_evlist__open(evlist); + if (err < 0) { + pr_debug("perf_evlist__open: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); + goto out_delete_evlist; + } + + ret = TEST_FAIL; + err = do_test(evlist, opts.mmap_pages, &sample_count, + &comm_count); + if (err != TEST_OK) + goto out_delete_evlist; + + if ((sample_count != NR_ITERS) || (comm_count != NR_ITERS)) { + pr_err("Unexpected counter: sample_count=%d, comm_count=%d\n", + sample_count, comm_count); + goto out_delete_evlist; + } + + err = do_test(evlist, 1, &sample_count, &comm_count); + if (err != TEST_OK) + goto out_delete_evlist; + + ret = TEST_OK; +out_delete_evlist: + perf_evlist__delete(evlist); + return ret; +} diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 199501c..f31eed3 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -138,7 +138,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), perf_evlist__splice_list_tail(evlist, &parse_evlist.list); evlist->nr_groups = parse_evlist.nr_groups; - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); err = perf_evlist__open(evlist); if (err < 0) { diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index f2b1dca..0e95c20 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -204,6 +204,14 @@ static struct test generic_tests[] = { .func = test__event_update, }, { + .desc = "Test events times", + .func = test__event_times, + }, + { + .desc = "Test backward reading from ring buffer", + .func = test__backward_ring_buffer, + }, + { .func = NULL, }, }; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index abd3f0e..68a69a1 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -532,7 +532,7 @@ static int do_test_code_reading(bool try_kcore) goto out_put; } - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); evsel = perf_evlist__first(evlist); diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index dc673ff..8cf0d9e 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -202,7 +202,7 @@ static int dsos__create(int cnt, int size) { int i; - dsos = malloc(sizeof(dsos) * cnt); + dsos = malloc(sizeof(*dsos) * cnt); TEST_ASSERT_VAL("failed to alloc dsos array", dsos); for (i = 0; i < cnt; i++) { diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c new file mode 100644 index 0000000..95fb744 --- /dev/null +++ b/tools/perf/tests/event-times.c @@ -0,0 +1,236 @@ +#include <linux/compiler.h> +#include <string.h> +#include "tests.h" +#include "evlist.h" +#include "evsel.h" +#include "util.h" +#include "debug.h" +#include "thread_map.h" +#include "target.h" + +static int attach__enable_on_exec(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + struct target target = { + .uid = UINT_MAX, + }; + const char *argv[] = { "true", NULL, }; + char sbuf[STRERR_BUFSIZE]; + int err; + + pr_debug("attaching to spawned child, enable on exec\n"); + + err = perf_evlist__create_maps(evlist, &target); + if (err < 0) { + pr_debug("Not enough memory to create thread/cpu maps\n"); + return err; + } + + err = perf_evlist__prepare_workload(evlist, &target, argv, false, NULL); + if (err < 0) { + pr_debug("Couldn't run the workload!\n"); + return err; + } + + evsel->attr.enable_on_exec = 1; + + err = perf_evlist__open(evlist); + if (err < 0) { + pr_debug("perf_evlist__open: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); + return err; + } + + return perf_evlist__start_workload(evlist) == 1 ? TEST_OK : TEST_FAIL; +} + +static int detach__enable_on_exec(struct perf_evlist *evlist) +{ + waitpid(evlist->workload.pid, NULL, 0); + return 0; +} + +static int attach__current_disabled(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + struct thread_map *threads; + int err; + + pr_debug("attaching to current thread as disabled\n"); + + threads = thread_map__new(-1, getpid(), UINT_MAX); + if (threads == NULL) { + pr_debug("thread_map__new\n"); + return -1; + } + + evsel->attr.disabled = 1; + + err = perf_evsel__open_per_thread(evsel, threads); + if (err) { + pr_debug("Failed to open event cpu-clock:u\n"); + return err; + } + + thread_map__put(threads); + return perf_evsel__enable(evsel) == 0 ? TEST_OK : TEST_FAIL; +} + +static int attach__current_enabled(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + struct thread_map *threads; + int err; + + pr_debug("attaching to current thread as enabled\n"); + + threads = thread_map__new(-1, getpid(), UINT_MAX); + if (threads == NULL) { + pr_debug("failed to call thread_map__new\n"); + return -1; + } + + err = perf_evsel__open_per_thread(evsel, threads); + + thread_map__put(threads); + return err == 0 ? TEST_OK : TEST_FAIL; +} + +static int detach__disable(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + + return perf_evsel__enable(evsel); +} + +static int attach__cpu_disabled(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + struct cpu_map *cpus; + int err; + + pr_debug("attaching to CPU 0 as enabled\n"); + + cpus = cpu_map__new("0"); + if (cpus == NULL) { + pr_debug("failed to call cpu_map__new\n"); + return -1; + } + + evsel->attr.disabled = 1; + + err = perf_evsel__open_per_cpu(evsel, cpus); + if (err) { + if (err == -EACCES) + return TEST_SKIP; + + pr_debug("Failed to open event cpu-clock:u\n"); + return err; + } + + cpu_map__put(cpus); + return perf_evsel__enable(evsel); +} + +static int attach__cpu_enabled(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + struct cpu_map *cpus; + int err; + + pr_debug("attaching to CPU 0 as enabled\n"); + + cpus = cpu_map__new("0"); + if (cpus == NULL) { + pr_debug("failed to call cpu_map__new\n"); + return -1; + } + + err = perf_evsel__open_per_cpu(evsel, cpus); + if (err == -EACCES) + return TEST_SKIP; + + cpu_map__put(cpus); + return err ? TEST_FAIL : TEST_OK; +} + +static int test_times(int (attach)(struct perf_evlist *), + int (detach)(struct perf_evlist *)) +{ + struct perf_counts_values count; + struct perf_evlist *evlist = NULL; + struct perf_evsel *evsel; + int err = -1, i; + + evlist = perf_evlist__new(); + if (!evlist) { + pr_debug("failed to create event list\n"); + goto out_err; + } + + err = parse_events(evlist, "cpu-clock:u", NULL); + if (err) { + pr_debug("failed to parse event cpu-clock:u\n"); + goto out_err; + } + + evsel = perf_evlist__last(evlist); + evsel->attr.read_format |= + PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING; + + err = attach(evlist); + if (err == TEST_SKIP) { + pr_debug(" SKIP : not enough rights\n"); + return err; + } + + TEST_ASSERT_VAL("failed to attach", !err); + + for (i = 0; i < 100000000; i++) { } + + TEST_ASSERT_VAL("failed to detach", !detach(evlist)); + + perf_evsel__read(evsel, 0, 0, &count); + + err = !(count.ena == count.run); + + pr_debug(" %s: ena %" PRIu64", run %" PRIu64"\n", + !err ? "OK " : "FAILED", + count.ena, count.run); + +out_err: + if (evlist) + perf_evlist__delete(evlist); + return !err ? TEST_OK : TEST_FAIL; +} + +/* + * This test creates software event 'cpu-clock' + * attaches it in several ways (explained below) + * and checks that enabled and running times + * match. + */ +int test__event_times(int subtest __maybe_unused) +{ + int err, ret = 0; + +#define _T(attach, detach) \ + err = test_times(attach, detach); \ + if (err && (ret == TEST_OK || ret == TEST_SKIP)) \ + ret = err; + + /* attach on newly spawned process after exec */ + _T(attach__enable_on_exec, detach__enable_on_exec) + /* attach on current process as enabled */ + _T(attach__current_enabled, detach__disable) + /* attach on current process as disabled */ + _T(attach__current_disabled, detach__disable) + /* attach on cpu as disabled */ + _T(attach__cpu_disabled, detach__disable) + /* attach on cpu as enabled */ + _T(attach__cpu_enabled, detach__disable) + +#undef _T + return ret; +} diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index 012eab5..63ecf21 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -30,7 +30,7 @@ static int process_event_scale(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong id", ev->id == 123); TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__SCALE); - TEST_ASSERT_VAL("wrong scale", ev_data->scale = 0.123); + TEST_ASSERT_VAL("wrong scale", ev_data->scale == 0.123); return 0; } diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c index f55f4bd..6b21746 100644 --- a/tools/perf/tests/hists_common.c +++ b/tools/perf/tests/hists_common.c @@ -161,7 +161,7 @@ void print_hists_in(struct hists *hists) struct rb_root *root; struct rb_node *node; - if (sort__need_collapse) + if (hists__has(hists, need_collapse)) root = &hists->entries_collapsed; else root = hists->entries_in; diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index ed5aa9e..a9e3db3 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -101,7 +101,7 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) if (machine__resolve(machine, &al, &sample) < 0) goto out; - if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH, + if (hist_entry_iter__add(&iter, &al, sysctl_perf_event_max_stack, NULL) < 0) { addr_location__put(&al); goto out; @@ -126,7 +126,7 @@ static void del_hist_entries(struct hists *hists) struct rb_root *root_out; struct rb_node *node; - if (sort__need_collapse) + if (hists__has(hists, need_collapse)) root_in = &hists->entries_collapsed; else root_in = hists->entries_in; diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index b825d24..e846f8c 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -81,7 +81,7 @@ static int add_hist_entries(struct perf_evlist *evlist, al.socket = fake_samples[i].socket; if (hist_entry_iter__add(&iter, &al, - PERF_MAX_STACK_DEPTH, NULL) < 0) { + sysctl_perf_event_max_stack, NULL) < 0) { addr_location__put(&al); goto out; } diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 358324e..acf5a13 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -145,7 +145,7 @@ static int __validate_match(struct hists *hists) /* * Only entries from fake_common_samples should have a pair. */ - if (sort__need_collapse) + if (hists__has(hists, need_collapse)) root = &hists->entries_collapsed; else root = hists->entries_in; @@ -197,7 +197,7 @@ static int __validate_link(struct hists *hists, int idx) * and some entries will have no pair. However every entry * in other hists should have (dummy) pair. */ - if (sort__need_collapse) + if (hists__has(hists, need_collapse)) root = &hists->entries_collapsed; else root = hists->entries_in; diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index d3556fb..63c5efa 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -67,7 +67,7 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) if (machine__resolve(machine, &al, &sample) < 0) goto out; - if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH, + if (hist_entry_iter__add(&iter, &al, sysctl_perf_event_max_stack, NULL) < 0) { addr_location__put(&al); goto out; @@ -92,7 +92,7 @@ static void del_hist_entries(struct hists *hists) struct rb_root *root_out; struct rb_node *node; - if (sort__need_collapse) + if (hists__has(hists, need_collapse)) root_in = &hists->entries_collapsed; else root_in = hists->entries_in; diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index ddb78fa..614e45a 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -80,7 +80,7 @@ int test__keep_tracking(int subtest __maybe_unused) CHECK__(parse_events(evlist, "dummy:u", NULL)); CHECK__(parse_events(evlist, "cycles:u", NULL)); - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); evsel = perf_evlist__first(evlist); diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index eb99a105..4344fe4 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -44,7 +44,7 @@ int test__syscall_openat_tp_fields(int subtest __maybe_unused) goto out_delete_evlist; } - perf_evsel__config(evsel, &opts); + perf_evsel__config(evsel, &opts, NULL); thread_map__set_pid(evlist->threads, 0, getpid()); diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 1cc78ce..b836ee6a 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -99,7 +99,7 @@ int test__PERF_RECORD(int subtest __maybe_unused) perf_evsel__set_sample_bit(evsel, CPU); perf_evsel__set_sample_bit(evsel, TID); perf_evsel__set_sample_bit(evsel, TIME); - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask); if (err < 0) { diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index ebd8016..39a689b 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -417,7 +417,7 @@ int test__switch_tracking(int subtest __maybe_unused) perf_evsel__set_sample_bit(tracking_evsel, TIME); /* Config events */ - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); /* Check moved event is still at the front */ if (cycles_evsel != perf_evlist__first(evlist)) { diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 82b2b5e..c57e72c 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -85,6 +85,8 @@ int test__synthesize_stat_config(int subtest); int test__synthesize_stat(int subtest); int test__synthesize_stat_round(int subtest); int test__event_update(int subtest); +int test__event_times(int subtest); +int test__backward_ring_buffer(int subtest); #if defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 630b0b4..e63abab 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -54,8 +54,14 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused) * Step 3: * * Load and split /proc/kallsyms into multiple maps, one per module. + * Do not use kcore, as this test was designed before kcore support + * and has parts that only make sense if using the non-kcore code. + * XXX: extend it to stress the kcorre code as well, hint: the list + * of modules extracted from /proc/kcore, in its current form, can't + * be compacted against the list of modules found in the "vmlinux" + * code and with the one got from /proc/modules from the "kallsyms" code. */ - if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, NULL) <= 0) { + if (__machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, true, NULL) <= 0) { pr_debug("dso__load_kallsyms "); goto out; } @@ -157,6 +163,9 @@ next_pair: pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", mem_start, sym->name, pair->name); + } else { + pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", + mem_start, sym->name, first_pair->name); } } } else diff --git a/tools/perf/trace/beauty/eventfd.c b/tools/perf/trace/beauty/eventfd.c new file mode 100644 index 0000000..d64f4a9 --- /dev/null +++ b/tools/perf/trace/beauty/eventfd.c @@ -0,0 +1,38 @@ +#include <sys/eventfd.h> + +#ifndef EFD_SEMAPHORE +#define EFD_SEMAPHORE 1 +#endif + +#ifndef EFD_NONBLOCK +#define EFD_NONBLOCK 00004000 +#endif + +#ifndef EFD_CLOEXEC +#define EFD_CLOEXEC 02000000 +#endif + +static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size, struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (flags == 0) + return scnprintf(bf, size, "NONE"); +#define P_FLAG(n) \ + if (flags & EFD_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~EFD_##n; \ + } + + P_FLAG(SEMAPHORE); + P_FLAG(CLOEXEC); + P_FLAG(NONBLOCK); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c new file mode 100644 index 0000000..021bb48 --- /dev/null +++ b/tools/perf/trace/beauty/flock.c @@ -0,0 +1,31 @@ + +static size_t syscall_arg__scnprintf_flock(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, op = arg->val; + + if (op == 0) + return scnprintf(bf, size, "NONE"); +#define P_CMD(cmd) \ + if ((op & LOCK_##cmd) == LOCK_##cmd) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #cmd); \ + op &= ~LOCK_##cmd; \ + } + + P_CMD(SH); + P_CMD(EX); + P_CMD(NB); + P_CMD(UN); + P_CMD(MAND); + P_CMD(RW); + P_CMD(READ); + P_CMD(WRITE); +#undef P_OP + + if (op) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", op); + + return printed; +} + +#define SCA_FLOCK syscall_arg__scnprintf_flock diff --git a/tools/perf/trace/beauty/futex_op.c b/tools/perf/trace/beauty/futex_op.c new file mode 100644 index 0000000..e247621 --- /dev/null +++ b/tools/perf/trace/beauty/futex_op.c @@ -0,0 +1,44 @@ +#include <linux/futex.h> + +static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg) +{ + enum syscall_futex_args { + SCF_UADDR = (1 << 0), + SCF_OP = (1 << 1), + SCF_VAL = (1 << 2), + SCF_TIMEOUT = (1 << 3), + SCF_UADDR2 = (1 << 4), + SCF_VAL3 = (1 << 5), + }; + int op = arg->val; + int cmd = op & FUTEX_CMD_MASK; + size_t printed = 0; + + switch (cmd) { +#define P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n); + P_FUTEX_OP(WAIT); arg->mask |= SCF_VAL3|SCF_UADDR2; break; + P_FUTEX_OP(WAKE); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(FD); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(REQUEUE); arg->mask |= SCF_VAL3|SCF_TIMEOUT; break; + P_FUTEX_OP(CMP_REQUEUE); arg->mask |= SCF_TIMEOUT; break; + P_FUTEX_OP(CMP_REQUEUE_PI); arg->mask |= SCF_TIMEOUT; break; + P_FUTEX_OP(WAKE_OP); break; + P_FUTEX_OP(LOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(UNLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(TRYLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2; break; + P_FUTEX_OP(WAIT_BITSET); arg->mask |= SCF_UADDR2; break; + P_FUTEX_OP(WAKE_BITSET); arg->mask |= SCF_UADDR2; break; + P_FUTEX_OP(WAIT_REQUEUE_PI); break; + default: printed = scnprintf(bf, size, "%#x", cmd); break; + } + + if (op & FUTEX_PRIVATE_FLAG) + printed += scnprintf(bf + printed, size - printed, "|PRIV"); + + if (op & FUTEX_CLOCK_REALTIME) + printed += scnprintf(bf + printed, size - printed, "|CLKRT"); + + return printed; +} + +#define SCA_FUTEX_OP syscall_arg__scnprintf_futex_op diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c new file mode 100644 index 0000000..3444a4d --- /dev/null +++ b/tools/perf/trace/beauty/mmap.c @@ -0,0 +1,158 @@ +#include <sys/mman.h> + +static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, prot = arg->val; + + if (prot == PROT_NONE) + return scnprintf(bf, size, "NONE"); +#define P_MMAP_PROT(n) \ + if (prot & PROT_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + prot &= ~PROT_##n; \ + } + + P_MMAP_PROT(EXEC); + P_MMAP_PROT(READ); + P_MMAP_PROT(WRITE); +#ifdef PROT_SEM + P_MMAP_PROT(SEM); +#endif + P_MMAP_PROT(GROWSDOWN); + P_MMAP_PROT(GROWSUP); +#undef P_MMAP_PROT + + if (prot) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", prot); + + return printed; +} + +#define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot + +#ifndef MAP_STACK +# define MAP_STACK 0x20000 +#endif + +static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_MMAP_FLAG(n) \ + if (flags & MAP_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~MAP_##n; \ + } + + P_MMAP_FLAG(SHARED); + P_MMAP_FLAG(PRIVATE); +#ifdef MAP_32BIT + P_MMAP_FLAG(32BIT); +#endif + P_MMAP_FLAG(ANONYMOUS); + P_MMAP_FLAG(DENYWRITE); + P_MMAP_FLAG(EXECUTABLE); + P_MMAP_FLAG(FILE); + P_MMAP_FLAG(FIXED); + P_MMAP_FLAG(GROWSDOWN); +#ifdef MAP_HUGETLB + P_MMAP_FLAG(HUGETLB); +#endif + P_MMAP_FLAG(LOCKED); + P_MMAP_FLAG(NONBLOCK); + P_MMAP_FLAG(NORESERVE); + P_MMAP_FLAG(POPULATE); + P_MMAP_FLAG(STACK); +#ifdef MAP_UNINITIALIZED + P_MMAP_FLAG(UNINITIALIZED); +#endif +#undef P_MMAP_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags + +static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_MREMAP_FLAG(n) \ + if (flags & MREMAP_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~MREMAP_##n; \ + } + + P_MREMAP_FLAG(MAYMOVE); +#ifdef MREMAP_FIXED + P_MREMAP_FLAG(FIXED); +#endif +#undef P_MREMAP_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags + +#ifndef MADV_HWPOISON +#define MADV_HWPOISON 100 +#endif + +#ifndef MADV_MERGEABLE +#define MADV_MERGEABLE 12 +#endif + +#ifndef MADV_UNMERGEABLE +#define MADV_UNMERGEABLE 13 +#endif + +static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size, + struct syscall_arg *arg) +{ + int behavior = arg->val; + + switch (behavior) { +#define P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n) + P_MADV_BHV(NORMAL); + P_MADV_BHV(RANDOM); + P_MADV_BHV(SEQUENTIAL); + P_MADV_BHV(WILLNEED); + P_MADV_BHV(DONTNEED); + P_MADV_BHV(REMOVE); + P_MADV_BHV(DONTFORK); + P_MADV_BHV(DOFORK); + P_MADV_BHV(HWPOISON); +#ifdef MADV_SOFT_OFFLINE + P_MADV_BHV(SOFT_OFFLINE); +#endif + P_MADV_BHV(MERGEABLE); + P_MADV_BHV(UNMERGEABLE); +#ifdef MADV_HUGEPAGE + P_MADV_BHV(HUGEPAGE); +#endif +#ifdef MADV_NOHUGEPAGE + P_MADV_BHV(NOHUGEPAGE); +#endif +#ifdef MADV_DONTDUMP + P_MADV_BHV(DONTDUMP); +#endif +#ifdef MADV_DODUMP + P_MADV_BHV(DODUMP); +#endif +#undef P_MADV_PHV + default: break; + } + + return scnprintf(bf, size, "%#x", behavior); +} + +#define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior diff --git a/tools/perf/trace/beauty/mode_t.c b/tools/perf/trace/beauty/mode_t.c new file mode 100644 index 0000000..930d8fe --- /dev/null +++ b/tools/perf/trace/beauty/mode_t.c @@ -0,0 +1,68 @@ +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +/* From include/linux/stat.h */ +#ifndef S_IRWXUGO +#define S_IRWXUGO (S_IRWXU|S_IRWXG|S_IRWXO) +#endif +#ifndef S_IALLUGO +#define S_IALLUGO (S_ISUID|S_ISGID|S_ISVTX|S_IRWXUGO) +#endif +#ifndef S_IRUGO +#define S_IRUGO (S_IRUSR|S_IRGRP|S_IROTH) +#endif +#ifndef S_IWUGO +#define S_IWUGO (S_IWUSR|S_IWGRP|S_IWOTH) +#endif +#ifndef S_IXUGO +#define S_IXUGO (S_IXUSR|S_IXGRP|S_IXOTH) +#endif + +static size_t syscall_arg__scnprintf_mode_t(char *bf, size_t size, struct syscall_arg *arg) +{ + int printed = 0, mode = arg->val; + +#define P_MODE(n) \ + if ((mode & S_##n) == S_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + mode &= ~S_##n; \ + } + + P_MODE(IALLUGO); + P_MODE(IRWXUGO); + P_MODE(IRUGO); + P_MODE(IWUGO); + P_MODE(IXUGO); + P_MODE(IFMT); + P_MODE(IFSOCK); + P_MODE(IFLNK); + P_MODE(IFREG); + P_MODE(IFBLK); + P_MODE(IFDIR); + P_MODE(IFCHR); + P_MODE(IFIFO); + P_MODE(ISUID); + P_MODE(ISGID); + P_MODE(ISVTX); + P_MODE(IRWXU); + P_MODE(IRUSR); + P_MODE(IWUSR); + P_MODE(IXUSR); + P_MODE(IRWXG); + P_MODE(IRGRP); + P_MODE(IWGRP); + P_MODE(IXGRP); + P_MODE(IRWXO); + P_MODE(IROTH); + P_MODE(IWOTH); + P_MODE(IXOTH); +#undef P_MODE + + if (mode) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", mode); + + return printed; +} + +#define SCA_MODE_T syscall_arg__scnprintf_mode_t diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c new file mode 100644 index 0000000..07fa8a0 --- /dev/null +++ b/tools/perf/trace/beauty/msg_flags.c @@ -0,0 +1,62 @@ +#include <sys/types.h> +#include <sys/socket.h> + +#ifndef MSG_PROBE +#define MSG_PROBE 0x10 +#endif +#ifndef MSG_WAITFORONE +#define MSG_WAITFORONE 0x10000 +#endif +#ifndef MSG_SENDPAGE_NOTLAST +#define MSG_SENDPAGE_NOTLAST 0x20000 +#endif +#ifndef MSG_FASTOPEN +#define MSG_FASTOPEN 0x20000000 +#endif +#ifndef MSG_CMSG_CLOEXEC +# define MSG_CMSG_CLOEXEC 0x40000000 +#endif + +static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (flags == 0) + return scnprintf(bf, size, "NONE"); +#define P_MSG_FLAG(n) \ + if (flags & MSG_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~MSG_##n; \ + } + + P_MSG_FLAG(OOB); + P_MSG_FLAG(PEEK); + P_MSG_FLAG(DONTROUTE); + P_MSG_FLAG(TRYHARD); + P_MSG_FLAG(CTRUNC); + P_MSG_FLAG(PROBE); + P_MSG_FLAG(TRUNC); + P_MSG_FLAG(DONTWAIT); + P_MSG_FLAG(EOR); + P_MSG_FLAG(WAITALL); + P_MSG_FLAG(FIN); + P_MSG_FLAG(SYN); + P_MSG_FLAG(CONFIRM); + P_MSG_FLAG(RST); + P_MSG_FLAG(ERRQUEUE); + P_MSG_FLAG(NOSIGNAL); + P_MSG_FLAG(MORE); + P_MSG_FLAG(WAITFORONE); + P_MSG_FLAG(SENDPAGE_NOTLAST); + P_MSG_FLAG(FASTOPEN); + P_MSG_FLAG(CMSG_CLOEXEC); +#undef P_MSG_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_MSG_FLAGS syscall_arg__scnprintf_msg_flags diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c new file mode 100644 index 0000000..0f3679e --- /dev/null +++ b/tools/perf/trace/beauty/open_flags.c @@ -0,0 +1,56 @@ + +static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (!(flags & O_CREAT)) + arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */ + + if (flags == 0) + return scnprintf(bf, size, "RDONLY"); +#define P_FLAG(n) \ + if (flags & O_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~O_##n; \ + } + + P_FLAG(APPEND); + P_FLAG(ASYNC); + P_FLAG(CLOEXEC); + P_FLAG(CREAT); + P_FLAG(DIRECT); + P_FLAG(DIRECTORY); + P_FLAG(EXCL); + P_FLAG(LARGEFILE); + P_FLAG(NOATIME); + P_FLAG(NOCTTY); +#ifdef O_NONBLOCK + P_FLAG(NONBLOCK); +#elif O_NDELAY + P_FLAG(NDELAY); +#endif +#ifdef O_PATH + P_FLAG(PATH); +#endif + P_FLAG(RDWR); +#ifdef O_DSYNC + if ((flags & O_SYNC) == O_SYNC) + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC"); + else { + P_FLAG(DSYNC); + } +#else + P_FLAG(SYNC); +#endif + P_FLAG(TRUNC); + P_FLAG(WRONLY); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags diff --git a/tools/perf/trace/beauty/perf_event_open.c b/tools/perf/trace/beauty/perf_event_open.c new file mode 100644 index 0000000..311f09d --- /dev/null +++ b/tools/perf/trace/beauty/perf_event_open.c @@ -0,0 +1,43 @@ +#ifndef PERF_FLAG_FD_NO_GROUP +# define PERF_FLAG_FD_NO_GROUP (1UL << 0) +#endif + +#ifndef PERF_FLAG_FD_OUTPUT +# define PERF_FLAG_FD_OUTPUT (1UL << 1) +#endif + +#ifndef PERF_FLAG_PID_CGROUP +# define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */ +#endif + +#ifndef PERF_FLAG_FD_CLOEXEC +# define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ +#endif + +static size_t syscall_arg__scnprintf_perf_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (flags == 0) + return 0; + +#define P_FLAG(n) \ + if (flags & PERF_FLAG_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~PERF_FLAG_##n; \ + } + + P_FLAG(FD_NO_GROUP); + P_FLAG(FD_OUTPUT); + P_FLAG(PID_CGROUP); + P_FLAG(FD_CLOEXEC); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_PERF_FLAGS syscall_arg__scnprintf_perf_flags diff --git a/tools/perf/trace/beauty/pid.c b/tools/perf/trace/beauty/pid.c new file mode 100644 index 0000000..07486ea --- /dev/null +++ b/tools/perf/trace/beauty/pid.c @@ -0,0 +1,21 @@ +static size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg) +{ + int pid = arg->val; + struct trace *trace = arg->trace; + size_t printed = scnprintf(bf, size, "%d", pid); + struct thread *thread = machine__findnew_thread(trace->host, pid, pid); + + if (thread != NULL) { + if (!thread->comm_set) + thread__set_comm_from_proc(thread); + + if (thread->comm_set) + printed += scnprintf(bf + printed, size - printed, + " (%s)", thread__comm_str(thread)); + thread__put(thread); + } + + return printed; +} + +#define SCA_PID syscall_arg__scnprintf_pid diff --git a/tools/perf/trace/beauty/sched_policy.c b/tools/perf/trace/beauty/sched_policy.c new file mode 100644 index 0000000..c205bc6 --- /dev/null +++ b/tools/perf/trace/beauty/sched_policy.c @@ -0,0 +1,44 @@ +#include <sched.h> + +/* + * Not defined anywhere else, probably, just to make sure we + * catch future flags + */ +#define SCHED_POLICY_MASK 0xff + +#ifndef SCHED_DEADLINE +#define SCHED_DEADLINE 6 +#endif + +static size_t syscall_arg__scnprintf_sched_policy(char *bf, size_t size, + struct syscall_arg *arg) +{ + const char *policies[] = { + "NORMAL", "FIFO", "RR", "BATCH", "ISO", "IDLE", "DEADLINE", + }; + size_t printed; + int policy = arg->val, + flags = policy & ~SCHED_POLICY_MASK; + + policy &= SCHED_POLICY_MASK; + if (policy <= SCHED_DEADLINE) + printed = scnprintf(bf, size, "%s", policies[policy]); + else + printed = scnprintf(bf, size, "%#x", policy); + +#define P_POLICY_FLAG(n) \ + if (flags & SCHED_##n) { \ + printed += scnprintf(bf + printed, size - printed, "|%s", #n); \ + flags &= ~SCHED_##n; \ + } + + P_POLICY_FLAG(RESET_ON_FORK); +#undef P_POLICY_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "|%#x", flags); + + return printed; +} + +#define SCA_SCHED_POLICY syscall_arg__scnprintf_sched_policy diff --git a/tools/perf/trace/beauty/seccomp.c b/tools/perf/trace/beauty/seccomp.c new file mode 100644 index 0000000..213c5a7 --- /dev/null +++ b/tools/perf/trace/beauty/seccomp.c @@ -0,0 +1,52 @@ +#include <linux/seccomp.h> + +#ifndef SECCOMP_SET_MODE_STRICT +#define SECCOMP_SET_MODE_STRICT 0 +#endif +#ifndef SECCOMP_SET_MODE_FILTER +#define SECCOMP_SET_MODE_FILTER 1 +#endif + +static size_t syscall_arg__scnprintf_seccomp_op(char *bf, size_t size, struct syscall_arg *arg) +{ + int op = arg->val; + size_t printed = 0; + + switch (op) { +#define P_SECCOMP_SET_MODE_OP(n) case SECCOMP_SET_MODE_##n: printed = scnprintf(bf, size, #n); break + P_SECCOMP_SET_MODE_OP(STRICT); + P_SECCOMP_SET_MODE_OP(FILTER); +#undef P_SECCOMP_SET_MODE_OP + default: printed = scnprintf(bf, size, "%#x", op); break; + } + + return printed; +} + +#define SCA_SECCOMP_OP syscall_arg__scnprintf_seccomp_op + +#ifndef SECCOMP_FILTER_FLAG_TSYNC +#define SECCOMP_FILTER_FLAG_TSYNC 1 +#endif + +static size_t syscall_arg__scnprintf_seccomp_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_FLAG(n) \ + if (flags & SECCOMP_FILTER_FLAG_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~SECCOMP_FILTER_FLAG_##n; \ + } + + P_FLAG(TSYNC); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_SECCOMP_FLAGS syscall_arg__scnprintf_seccomp_flags diff --git a/tools/perf/trace/beauty/signum.c b/tools/perf/trace/beauty/signum.c new file mode 100644 index 0000000..d3b0b1f --- /dev/null +++ b/tools/perf/trace/beauty/signum.c @@ -0,0 +1,53 @@ + +static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg) +{ + int sig = arg->val; + + switch (sig) { +#define P_SIGNUM(n) case SIG##n: return scnprintf(bf, size, #n) + P_SIGNUM(HUP); + P_SIGNUM(INT); + P_SIGNUM(QUIT); + P_SIGNUM(ILL); + P_SIGNUM(TRAP); + P_SIGNUM(ABRT); + P_SIGNUM(BUS); + P_SIGNUM(FPE); + P_SIGNUM(KILL); + P_SIGNUM(USR1); + P_SIGNUM(SEGV); + P_SIGNUM(USR2); + P_SIGNUM(PIPE); + P_SIGNUM(ALRM); + P_SIGNUM(TERM); + P_SIGNUM(CHLD); + P_SIGNUM(CONT); + P_SIGNUM(STOP); + P_SIGNUM(TSTP); + P_SIGNUM(TTIN); + P_SIGNUM(TTOU); + P_SIGNUM(URG); + P_SIGNUM(XCPU); + P_SIGNUM(XFSZ); + P_SIGNUM(VTALRM); + P_SIGNUM(PROF); + P_SIGNUM(WINCH); + P_SIGNUM(IO); + P_SIGNUM(PWR); + P_SIGNUM(SYS); +#ifdef SIGEMT + P_SIGNUM(EMT); +#endif +#ifdef SIGSTKFLT + P_SIGNUM(STKFLT); +#endif +#ifdef SIGSWI + P_SIGNUM(SWI); +#endif + default: break; + } + + return scnprintf(bf, size, "%#x", sig); +} + +#define SCA_SIGNUM syscall_arg__scnprintf_signum diff --git a/tools/perf/trace/beauty/socket_type.c b/tools/perf/trace/beauty/socket_type.c new file mode 100644 index 0000000..0a5ce81 --- /dev/null +++ b/tools/perf/trace/beauty/socket_type.c @@ -0,0 +1,60 @@ +#include <sys/types.h> +#include <sys/socket.h> + +#ifndef SOCK_DCCP +# define SOCK_DCCP 6 +#endif + +#ifndef SOCK_CLOEXEC +# define SOCK_CLOEXEC 02000000 +#endif + +#ifndef SOCK_NONBLOCK +# define SOCK_NONBLOCK 00004000 +#endif + +#ifndef SOCK_TYPE_MASK +#define SOCK_TYPE_MASK 0xf +#endif + +static size_t syscall_arg__scnprintf_socket_type(char *bf, size_t size, struct syscall_arg *arg) +{ + size_t printed; + int type = arg->val, + flags = type & ~SOCK_TYPE_MASK; + + type &= SOCK_TYPE_MASK; + /* + * Can't use a strarray, MIPS may override for ABI reasons. + */ + switch (type) { +#define P_SK_TYPE(n) case SOCK_##n: printed = scnprintf(bf, size, #n); break; + P_SK_TYPE(STREAM); + P_SK_TYPE(DGRAM); + P_SK_TYPE(RAW); + P_SK_TYPE(RDM); + P_SK_TYPE(SEQPACKET); + P_SK_TYPE(DCCP); + P_SK_TYPE(PACKET); +#undef P_SK_TYPE + default: + printed = scnprintf(bf, size, "%#x", type); + } + +#define P_SK_FLAG(n) \ + if (flags & SOCK_##n) { \ + printed += scnprintf(bf + printed, size - printed, "|%s", #n); \ + flags &= ~SOCK_##n; \ + } + + P_SK_FLAG(CLOEXEC); + P_SK_FLAG(NONBLOCK); +#undef P_SK_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "|%#x", flags); + + return printed; +} + +#define SCA_SK_TYPE syscall_arg__scnprintf_socket_type diff --git a/tools/perf/trace/beauty/waitid_options.c b/tools/perf/trace/beauty/waitid_options.c new file mode 100644 index 0000000..7942724 --- /dev/null +++ b/tools/perf/trace/beauty/waitid_options.c @@ -0,0 +1,26 @@ +#include <sys/types.h> +#include <sys/wait.h> + +static size_t syscall_arg__scnprintf_waitid_options(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, options = arg->val; + +#define P_OPTION(n) \ + if (options & W##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + options &= ~W##n; \ + } + + P_OPTION(NOHANG); + P_OPTION(UNTRACED); + P_OPTION(CONTINUED); +#undef P_OPTION + + if (options) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", options); + + return printed; +} + +#define SCA_WAITID_OPTIONS syscall_arg__scnprintf_waitid_options diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 2a83414..538bae8 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1607,9 +1607,8 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists)); dummy_hpp.buf[ret] = '\0'; - rtrim(dummy_hpp.buf); - start = ltrim(dummy_hpp.buf); + start = trim(dummy_hpp.buf); ret = strlen(start); if (start != dummy_hpp.buf) @@ -1897,11 +1896,10 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, bool first = true; int ret; - if (symbol_conf.use_callchain) + if (symbol_conf.use_callchain) { folded_sign = hist_entry__folded(he); - - if (symbol_conf.use_callchain) printed += fprintf(fp, "%c ", folded_sign); + } hists__for_each_format(browser->hists, fmt) { if (perf_hpp__should_skip(fmt, he->hists)) @@ -2137,7 +2135,7 @@ static int hists__browser_title(struct hists *hists, printed += snprintf(bf + printed, size - printed, ", UID: %s", hists->uid_filter_str); if (thread) { - if (sort__has_thread) { + if (hists__has(hists, thread)) { printed += scnprintf(bf + printed, size - printed, ", Thread: %s(%d)", (thread->comm_set ? thread__comm_str(thread) : ""), @@ -2322,7 +2320,8 @@ do_zoom_thread(struct hist_browser *browser, struct popup_action *act) { struct thread *thread = act->thread; - if ((!sort__has_thread && !sort__has_comm) || thread == NULL) + if ((!hists__has(browser->hists, thread) && + !hists__has(browser->hists, comm)) || thread == NULL) return 0; if (browser->hists->thread_filter) { @@ -2331,7 +2330,7 @@ do_zoom_thread(struct hist_browser *browser, struct popup_action *act) thread__zput(browser->hists->thread_filter); ui_helpline__pop(); } else { - if (sort__has_thread) { + if (hists__has(browser->hists, thread)) { ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"", thread->comm_set ? thread__comm_str(thread) : "", thread->tid); @@ -2356,10 +2355,11 @@ add_thread_opt(struct hist_browser *browser, struct popup_action *act, { int ret; - if ((!sort__has_thread && !sort__has_comm) || thread == NULL) + if ((!hists__has(browser->hists, thread) && + !hists__has(browser->hists, comm)) || thread == NULL) return 0; - if (sort__has_thread) { + if (hists__has(browser->hists, thread)) { ret = asprintf(optstr, "Zoom %s %s(%d) thread", browser->hists->thread_filter ? "out of" : "into", thread->comm_set ? thread__comm_str(thread) : "", @@ -2382,7 +2382,7 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act) { struct map *map = act->ms.map; - if (!sort__has_dso || map == NULL) + if (!hists__has(browser->hists, dso) || map == NULL) return 0; if (browser->hists->dso_filter) { @@ -2409,7 +2409,7 @@ static int add_dso_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, struct map *map) { - if (!sort__has_dso || map == NULL) + if (!hists__has(browser->hists, dso) || map == NULL) return 0; if (asprintf(optstr, "Zoom %s %s DSO", @@ -2431,10 +2431,10 @@ do_browse_map(struct hist_browser *browser __maybe_unused, } static int -add_map_opt(struct hist_browser *browser __maybe_unused, +add_map_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, struct map *map) { - if (!sort__has_dso || map == NULL) + if (!hists__has(browser->hists, dso) || map == NULL) return 0; if (asprintf(optstr, "Browse map details") < 0) @@ -2536,7 +2536,7 @@ add_exit_opt(struct hist_browser *browser __maybe_unused, static int do_zoom_socket(struct hist_browser *browser, struct popup_action *act) { - if (!sort__has_socket || act->socket < 0) + if (!hists__has(browser->hists, socket) || act->socket < 0) return 0; if (browser->hists->socket_filter > -1) { @@ -2558,7 +2558,7 @@ static int add_socket_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, int socket_id) { - if (!sort__has_socket || socket_id < 0) + if (!hists__has(browser->hists, socket) || socket_id < 0) return 0; if (asprintf(optstr, "Zoom %s Processor Socket %d", @@ -2749,7 +2749,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, */ goto out_free_stack; case 'a': - if (!sort__has_sym) { + if (!hists__has(hists, sym)) { ui_browser__warning(&browser->b, delay_secs * 2, "Annotation is only available for symbolic views, " "include \"sym*\" in --sort to use it."); @@ -2912,7 +2912,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, continue; } - if (!sort__has_sym || browser->selection == NULL) + if (!hists__has(hists, sym) || browser->selection == NULL) goto skip_annotation; if (sort__mode == SORT_MODE__BRANCH) { @@ -2956,7 +2956,7 @@ skip_annotation: goto skip_scripting; if (browser->he_selection) { - if (sort__has_thread && thread) { + if (hists__has(hists, thread) && thread) { nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], @@ -2971,7 +2971,7 @@ skip_annotation: * * See hist_browser__show_entry. */ - if (sort__has_sym && browser->selection->sym) { + if (hists__has(hists, sym) && browser->selection->sym) { nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 2aa45b6..932adfa 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -379,7 +379,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, gtk_tree_store_set(store, &iter, col_idx++, s, -1); } - if (symbol_conf.use_callchain && sort__has_sym) { + if (symbol_conf.use_callchain && hists__has(hists, sym)) { if (callchain_param.mode == CHAIN_GRAPH_REL) total = symbol_conf.cumulate_callchain ? h->stat_acc->period : h->stat.period; diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 3baeaa6..af07ffb 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -635,7 +635,7 @@ unsigned int hists__sort_list_width(struct hists *hists) ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists)); } - if (verbose && sort__has_sym) /* Addr + origin */ + if (verbose && hists__has(hists, sym)) /* Addr + origin */ ret += 3 + BITS_PER_LONG / 4; return ret; diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 7aff5ac..560eb47 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -569,9 +569,8 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp, first_col = false; fmt->header(fmt, hpp, hists_to_evsel(hists)); - rtrim(hpp->buf); - header_width += fprintf(fp, "%s", ltrim(hpp->buf)); + header_width += fprintf(fp, "%s", trim(hpp->buf)); } } diff --git a/tools/perf/util/Build b/tools/perf/util/Build index da48fd8..8c6c8a0 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -8,6 +8,7 @@ libperf-y += env.o libperf-y += event.o libperf-y += evlist.o libperf-y += evsel.o +libperf-y += evsel_fprintf.o libperf-y += find_bit.o libperf-y += kallsyms.o libperf-y += levenshtein.o @@ -26,9 +27,9 @@ libperf-y += strlist.o libperf-y += strfilter.o libperf-y += top.o libperf-y += usage.o -libperf-y += wrapper.o libperf-y += dso.o libperf-y += symbol.o +libperf-y += symbol_fprintf.o libperf-y += color.o libperf-y += header.o libperf-y += callchain.o @@ -38,6 +39,7 @@ libperf-y += machine.o libperf-y += map.o libperf-y += pstack.o libperf-y += session.o +libperf-$(CONFIG_AUDIT) += syscalltbl.o libperf-y += ordered-events.o libperf-y += comm.o libperf-y += thread.o @@ -69,9 +71,9 @@ libperf-y += stat-shadow.o libperf-y += record.o libperf-y += srcline.o libperf-y += data.o -libperf-$(CONFIG_X86) += tsc.o -libperf-$(CONFIG_AUXTRACE) += tsc.o +libperf-y += tsc.o libperf-y += cloexec.o +libperf-y += call-path.o libperf-y += thread-stack.o libperf-$(CONFIG_AUXTRACE) += auxtrace.o libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index b795b69..4db73d5 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1138,7 +1138,7 @@ fallback: if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && !dso__is_kcore(dso)) { - char bf[BUILD_ID_SIZE * 2 + 16] = " with build id "; + char bf[SBUILD_ID_SIZE + 15] = " with build id "; char *build_id_msg = NULL; if (dso->annotate_warned) @@ -1665,5 +1665,5 @@ int hist_entry__annotate(struct hist_entry *he, size_t privsize) bool ui__has_annotation(void) { - return use_browser == 1 && sort__has_sym; + return use_browser == 1 && perf_hpp_list.sym; } diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index ec164fe..c916901 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -940,6 +940,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts) synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD; synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ; synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ; + synth_opts->initial_skip = 0; } /* @@ -1064,6 +1065,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, synth_opts->last_branch_sz = val; } break; + case 's': + synth_opts->initial_skip = strtoul(p, &endptr, 10); + if (p == endptr) + goto out_err; + p = endptr; + break; case ' ': case ',': break; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 57ff31e..767989e 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -68,6 +68,7 @@ enum itrace_period_type { * @last_branch_sz: branch context size * @period: 'instructions' events period * @period_type: 'instructions' events period type + * @initial_skip: skip N events at the beginning. */ struct itrace_synth_opts { bool set; @@ -86,6 +87,7 @@ struct itrace_synth_opts { unsigned int last_branch_sz; unsigned long long period; enum itrace_period_type period_type; + unsigned long initial_skip; }; /** diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 0967ce6..493307d 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -842,6 +842,58 @@ bpf_map_op__new(struct parse_events_term *term) return op; } +static struct bpf_map_op * +bpf_map_op__clone(struct bpf_map_op *op) +{ + struct bpf_map_op *newop; + + newop = memdup(op, sizeof(*op)); + if (!newop) { + pr_debug("Failed to alloc bpf_map_op\n"); + return NULL; + } + + INIT_LIST_HEAD(&newop->list); + if (op->key_type == BPF_MAP_KEY_RANGES) { + size_t memsz = op->k.array.nr_ranges * + sizeof(op->k.array.ranges[0]); + + newop->k.array.ranges = memdup(op->k.array.ranges, memsz); + if (!newop->k.array.ranges) { + pr_debug("Failed to alloc indices for map\n"); + free(newop); + return NULL; + } + } + + return newop; +} + +static struct bpf_map_priv * +bpf_map_priv__clone(struct bpf_map_priv *priv) +{ + struct bpf_map_priv *newpriv; + struct bpf_map_op *pos, *newop; + + newpriv = zalloc(sizeof(*newpriv)); + if (!newpriv) { + pr_debug("No enough memory to alloc map private\n"); + return NULL; + } + INIT_LIST_HEAD(&newpriv->ops_list); + + list_for_each_entry(pos, &priv->ops_list, list) { + newop = bpf_map_op__clone(pos); + if (!newop) { + bpf_map_priv__purge(newpriv); + return NULL; + } + list_add_tail(&newop->list, &newpriv->ops_list); + } + + return newpriv; +} + static int bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op) { @@ -1417,6 +1469,89 @@ int bpf__apply_obj_config(void) return 0; } +#define bpf__for_each_map(pos, obj, objtmp) \ + bpf_object__for_each_safe(obj, objtmp) \ + bpf_map__for_each(pos, obj) + +#define bpf__for_each_stdout_map(pos, obj, objtmp) \ + bpf__for_each_map(pos, obj, objtmp) \ + if (bpf_map__get_name(pos) && \ + (strcmp("__bpf_stdout__", \ + bpf_map__get_name(pos)) == 0)) + +int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) +{ + struct bpf_map_priv *tmpl_priv = NULL; + struct bpf_object *obj, *tmp; + struct perf_evsel *evsel = NULL; + struct bpf_map *map; + int err; + bool need_init = false; + + bpf__for_each_stdout_map(map, obj, tmp) { + struct bpf_map_priv *priv; + + err = bpf_map__get_private(map, (void **)&priv); + if (err) + return -BPF_LOADER_ERRNO__INTERNAL; + + /* + * No need to check map type: type should have been + * verified by kernel. + */ + if (!need_init && !priv) + need_init = !priv; + if (!tmpl_priv && priv) + tmpl_priv = priv; + } + + if (!need_init) + return 0; + + if (!tmpl_priv) { + err = parse_events(evlist, "bpf-output/no-inherit=1,name=__bpf_stdout__/", + NULL); + if (err) { + pr_debug("ERROR: failed to create bpf-output event\n"); + return -err; + } + + evsel = perf_evlist__last(evlist); + } + + bpf__for_each_stdout_map(map, obj, tmp) { + struct bpf_map_priv *priv; + + err = bpf_map__get_private(map, (void **)&priv); + if (err) + return -BPF_LOADER_ERRNO__INTERNAL; + if (priv) + continue; + + if (tmpl_priv) { + priv = bpf_map_priv__clone(tmpl_priv); + if (!priv) + return -ENOMEM; + + err = bpf_map__set_private(map, priv, bpf_map_priv__clear); + if (err) { + bpf_map_priv__clear(map, priv); + return err; + } + } else if (evsel) { + struct bpf_map_op *op; + + op = bpf_map__add_newop(map, NULL); + if (IS_ERR(op)) + return PTR_ERR(op); + op->op_type = BPF_MAP_OP_SET_EVSEL; + op->v.evsel = evsel; + } + } + + return 0; +} + #define ERRNO_OFFSET(e) ((e) - __BPF_LOADER_ERRNO__START) #define ERRCODE_OFFSET(c) ERRNO_OFFSET(BPF_LOADER_ERRNO__##c) #define NR_ERRNO (__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START) @@ -1590,3 +1725,11 @@ int bpf__strerror_apply_obj_config(int err, char *buf, size_t size) bpf__strerror_end(buf, size); return 0; } + +int bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused, + int err, char *buf, size_t size) +{ + bpf__strerror_head(err, buf, size); + bpf__strerror_end(buf, size); + return 0; +} diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index be43119..941e172 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -79,6 +79,11 @@ int bpf__strerror_config_obj(struct bpf_object *obj, size_t size); int bpf__apply_obj_config(void); int bpf__strerror_apply_obj_config(int err, char *buf, size_t size); + +int bpf__setup_stdout(struct perf_evlist *evlist); +int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, + char *buf, size_t size); + #else static inline struct bpf_object * bpf__prepare_load(const char *filename __maybe_unused, @@ -125,6 +130,12 @@ bpf__apply_obj_config(void) } static inline int +bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) +{ + return 0; +} + +static inline int __bpf_strerror(char *buf, size_t size) { if (!size) @@ -177,5 +188,13 @@ bpf__strerror_apply_obj_config(int err __maybe_unused, { return __bpf_strerror(buf, size); } + +static inline int +bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused, + int err __maybe_unused, char *buf, + size_t size) +{ + return __bpf_strerror(buf, size); +} #endif #endif diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 0573c2e..bff425e 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -261,14 +261,14 @@ static int machine__write_buildid_table(struct machine *machine, int fd) if (dso__is_vdso(pos)) { name = pos->short_name; - name_len = pos->short_name_len + 1; + name_len = pos->short_name_len; } else if (dso__is_kcore(pos)) { machine__mmap_name(machine, nm, sizeof(nm)); name = nm; - name_len = strlen(nm) + 1; + name_len = strlen(nm); } else { name = pos->long_name; - name_len = pos->long_name_len + 1; + name_len = pos->long_name_len; } in_kernel = pos->kernel || @@ -365,39 +365,17 @@ static char *build_id_cache__dirname_from_path(const char *name, int build_id_cache__list_build_ids(const char *pathname, struct strlist **result) { - struct strlist *list; char *dir_name; - DIR *dir; - struct dirent *d; int ret = 0; - list = strlist__new(NULL, NULL); dir_name = build_id_cache__dirname_from_path(pathname, false, false); - if (!list || !dir_name) { - ret = -ENOMEM; - goto out; - } + if (!dir_name) + return -ENOMEM; - /* List up all dirents */ - dir = opendir(dir_name); - if (!dir) { + *result = lsdir(dir_name, lsdir_no_dot_filter); + if (!*result) ret = -errno; - goto out; - } - - while ((d = readdir(dir)) != NULL) { - if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, "..")) - continue; - strlist__add(list, d->d_name); - } - closedir(dir); - -out: free(dir_name); - if (ret) - strlist__delete(list); - else - *result = list; return ret; } diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 1f5a93c..0d814bb 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -40,25 +40,6 @@ int split_cmdline(char *cmdline, const char ***argv); #define alloc_nr(x) (((x)+16)*3/2) -/* - * Realloc the buffer pointed at by variable 'x' so that it can hold - * at least 'nr' entries; the number of entries currently allocated - * is 'alloc', using the standard growing factor alloc_nr() macro. - * - * DO NOT USE any expression with side-effect for 'x' or 'alloc'. - */ -#define ALLOC_GROW(x, nr, alloc) \ - do { \ - if ((nr) > alloc) { \ - if (alloc_nr(alloc) < (nr)) \ - alloc = (nr); \ - else \ - alloc = alloc_nr(alloc); \ - x = xrealloc((x), alloc * sizeof(*(x))); \ - } \ - } while(0) - - static inline int is_absolute_path(const char *path) { return path[0] == '/'; diff --git a/tools/perf/util/call-path.c b/tools/perf/util/call-path.c new file mode 100644 index 0000000..904a170 --- /dev/null +++ b/tools/perf/util/call-path.c @@ -0,0 +1,122 @@ +/* + * call-path.h: Manipulate a tree data structure containing function call paths + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#include <linux/rbtree.h> +#include <linux/list.h> + +#include "util.h" +#include "call-path.h" + +static void call_path__init(struct call_path *cp, struct call_path *parent, + struct symbol *sym, u64 ip, bool in_kernel) +{ + cp->parent = parent; + cp->sym = sym; + cp->ip = sym ? 0 : ip; + cp->db_id = 0; + cp->in_kernel = in_kernel; + RB_CLEAR_NODE(&cp->rb_node); + cp->children = RB_ROOT; +} + +struct call_path_root *call_path_root__new(void) +{ + struct call_path_root *cpr; + + cpr = zalloc(sizeof(struct call_path_root)); + if (!cpr) + return NULL; + call_path__init(&cpr->call_path, NULL, NULL, 0, false); + INIT_LIST_HEAD(&cpr->blocks); + return cpr; +} + +void call_path_root__free(struct call_path_root *cpr) +{ + struct call_path_block *pos, *n; + + list_for_each_entry_safe(pos, n, &cpr->blocks, node) { + list_del(&pos->node); + free(pos); + } + free(cpr); +} + +static struct call_path *call_path__new(struct call_path_root *cpr, + struct call_path *parent, + struct symbol *sym, u64 ip, + bool in_kernel) +{ + struct call_path_block *cpb; + struct call_path *cp; + size_t n; + + if (cpr->next < cpr->sz) { + cpb = list_last_entry(&cpr->blocks, struct call_path_block, + node); + } else { + cpb = zalloc(sizeof(struct call_path_block)); + if (!cpb) + return NULL; + list_add_tail(&cpb->node, &cpr->blocks); + cpr->sz += CALL_PATH_BLOCK_SIZE; + } + + n = cpr->next++ & CALL_PATH_BLOCK_MASK; + cp = &cpb->cp[n]; + + call_path__init(cp, parent, sym, ip, in_kernel); + + return cp; +} + +struct call_path *call_path__findnew(struct call_path_root *cpr, + struct call_path *parent, + struct symbol *sym, u64 ip, u64 ks) +{ + struct rb_node **p; + struct rb_node *node_parent = NULL; + struct call_path *cp; + bool in_kernel = ip >= ks; + + if (sym) + ip = 0; + + if (!parent) + return call_path__new(cpr, parent, sym, ip, in_kernel); + + p = &parent->children.rb_node; + while (*p != NULL) { + node_parent = *p; + cp = rb_entry(node_parent, struct call_path, rb_node); + + if (cp->sym == sym && cp->ip == ip) + return cp; + + if (sym < cp->sym || (sym == cp->sym && ip < cp->ip)) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + cp = call_path__new(cpr, parent, sym, ip, in_kernel); + if (!cp) + return NULL; + + rb_link_node(&cp->rb_node, node_parent, p); + rb_insert_color(&cp->rb_node, &parent->children); + + return cp; +} diff --git a/tools/perf/util/call-path.h b/tools/perf/util/call-path.h new file mode 100644 index 0000000..477f6d0 --- /dev/null +++ b/tools/perf/util/call-path.h @@ -0,0 +1,77 @@ +/* + * call-path.h: Manipulate a tree data structure containing function call paths + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#ifndef __PERF_CALL_PATH_H +#define __PERF_CALL_PATH_H + +#include <sys/types.h> + +#include <linux/types.h> +#include <linux/rbtree.h> + +/** + * struct call_path - node in list of calls leading to a function call. + * @parent: call path to the parent function call + * @sym: symbol of function called + * @ip: only if sym is null, the ip of the function + * @db_id: id used for db-export + * @in_kernel: whether function is a in the kernel + * @rb_node: node in parent's tree of called functions + * @children: tree of call paths of functions called + * + * In combination with the call_return structure, the call_path structure + * defines a context-sensitve call-graph. + */ +struct call_path { + struct call_path *parent; + struct symbol *sym; + u64 ip; + u64 db_id; + bool in_kernel; + struct rb_node rb_node; + struct rb_root children; +}; + +#define CALL_PATH_BLOCK_SHIFT 8 +#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT) +#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1) + +struct call_path_block { + struct call_path cp[CALL_PATH_BLOCK_SIZE]; + struct list_head node; +}; + +/** + * struct call_path_root - root of all call paths. + * @call_path: root call path + * @blocks: list of blocks to store call paths + * @next: next free space + * @sz: number of spaces + */ +struct call_path_root { + struct call_path call_path; + struct list_head blocks; + size_t next; + size_t sz; +}; + +struct call_path_root *call_path_root__new(void); +void call_path_root__free(struct call_path_root *cpr); + +struct call_path *call_path__findnew(struct call_path_root *cpr, + struct call_path *parent, + struct symbol *sym, u64 ip, u64 ks); + +#endif diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 24b4bd0..07fd30b 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -109,6 +109,7 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt) bool record_opt_set = false; bool try_stack_size = false; + callchain_param.enabled = true; symbol_conf.use_callchain = true; if (!arg) @@ -117,6 +118,7 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt) while ((tok = strtok((char *)arg, ",")) != NULL) { if (!strncmp(tok, "none", strlen(tok))) { callchain_param.mode = CHAIN_NONE; + callchain_param.enabled = false; symbol_conf.use_callchain = false; return 0; } @@ -788,7 +790,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor, return 0; } -int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent, +int sample__resolve_callchain(struct perf_sample *sample, + struct callchain_cursor *cursor, struct symbol **parent, struct perf_evsel *evsel, struct addr_location *al, int max_stack) { @@ -796,8 +799,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent return 0; if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain || - sort__has_parent) { - return thread__resolve_callchain(al->thread, evsel, sample, + perf_hpp_list.parent) { + return thread__resolve_callchain(al->thread, cursor, evsel, sample, parent, al, max_stack); } return 0; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index d2a9e69..65e2a4f 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -212,7 +212,14 @@ struct hist_entry; int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); int record_callchain_opt(const struct option *opt, const char *arg, int unset); -int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent, +struct record_opts; + +int record_opts__parse_callchain(struct record_opts *record, + struct callchain_param *callchain, + const char *arg, bool unset); + +int sample__resolve_callchain(struct perf_sample *sample, + struct callchain_cursor *cursor, struct symbol **parent, struct perf_evsel *evsel, struct addr_location *al, int max_stack); int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample); diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 4e72763..dad7d82 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -13,6 +13,7 @@ #include <subcmd/exec-cmd.h> #include "util/hist.h" /* perf_hist_config */ #include "util/llvm-utils.h" /* perf_llvm_config */ +#include "config.h" #define MAXNAME (256) @@ -377,6 +378,21 @@ const char *perf_config_dirname(const char *name, const char *value) return value; } +static int perf_buildid_config(const char *var, const char *value) +{ + /* same dir for all commands */ + if (!strcmp(var, "buildid.dir")) { + const char *dir = perf_config_dirname(var, value); + + if (!dir) + return -1; + strncpy(buildid_dir, dir, MAXPATHLEN-1); + buildid_dir[MAXPATHLEN-1] = '\0'; + } + + return 0; +} + static int perf_default_core_config(const char *var __maybe_unused, const char *value __maybe_unused) { @@ -412,6 +428,9 @@ int perf_default_config(const char *var, const char *value, if (!prefixcmp(var, "llvm.")) return perf_llvm_config(var, value); + if (!prefixcmp(var, "buildid.")) + return perf_buildid_config(var, value); + /* Add other config variables here. */ return 0; } @@ -506,41 +525,185 @@ out: return ret; } -/* - * Call this to report error for your variable that should not - * get a boolean value (i.e. "[my] var" means "true"). - */ -int config_error_nonbool(const char *var) +static struct perf_config_section *find_section(struct list_head *sections, + const char *section_name) { - return error("Missing value for '%s'", var); + struct perf_config_section *section; + + list_for_each_entry(section, sections, node) + if (!strcmp(section->name, section_name)) + return section; + + return NULL; +} + +static struct perf_config_item *find_config_item(const char *name, + struct perf_config_section *section) +{ + struct perf_config_item *item; + + list_for_each_entry(item, §ion->items, node) + if (!strcmp(item->name, name)) + return item; + + return NULL; } -struct buildid_dir_config { - char *dir; -}; +static struct perf_config_section *add_section(struct list_head *sections, + const char *section_name) +{ + struct perf_config_section *section = zalloc(sizeof(*section)); + + if (!section) + return NULL; + + INIT_LIST_HEAD(§ion->items); + section->name = strdup(section_name); + if (!section->name) { + pr_debug("%s: strdup failed\n", __func__); + free(section); + return NULL; + } + + list_add_tail(§ion->node, sections); + return section; +} -static int buildid_dir_command_config(const char *var, const char *value, - void *data) +static struct perf_config_item *add_config_item(struct perf_config_section *section, + const char *name) { - struct buildid_dir_config *c = data; - const char *v; + struct perf_config_item *item = zalloc(sizeof(*item)); - /* same dir for all commands */ - if (!strcmp(var, "buildid.dir")) { - v = perf_config_dirname(var, value); - if (!v) - return -1; - strncpy(c->dir, v, MAXPATHLEN-1); - c->dir[MAXPATHLEN-1] = '\0'; + if (!item) + return NULL; + + item->name = strdup(name); + if (!item->name) { + pr_debug("%s: strdup failed\n", __func__); + free(item); + return NULL; } + + list_add_tail(&item->node, §ion->items); + return item; +} + +static int set_value(struct perf_config_item *item, const char *value) +{ + char *val = strdup(value); + + if (!val) + return -1; + + zfree(&item->value); + item->value = val; return 0; } -static void check_buildid_dir_config(void) +static int collect_config(const char *var, const char *value, + void *perf_config_set) { - struct buildid_dir_config c; - c.dir = buildid_dir; - perf_config(buildid_dir_command_config, &c); + int ret = -1; + char *ptr, *key; + char *section_name, *name; + struct perf_config_section *section = NULL; + struct perf_config_item *item = NULL; + struct perf_config_set *set = perf_config_set; + struct list_head *sections = &set->sections; + + key = ptr = strdup(var); + if (!key) { + pr_debug("%s: strdup failed\n", __func__); + return -1; + } + + section_name = strsep(&ptr, "."); + name = ptr; + if (name == NULL || value == NULL) + goto out_free; + + section = find_section(sections, section_name); + if (!section) { + section = add_section(sections, section_name); + if (!section) + goto out_free; + } + + item = find_config_item(name, section); + if (!item) { + item = add_config_item(section, name); + if (!item) + goto out_free; + } + + ret = set_value(item, value); + return ret; + +out_free: + free(key); + perf_config_set__delete(set); + return -1; +} + +struct perf_config_set *perf_config_set__new(void) +{ + struct perf_config_set *set = zalloc(sizeof(*set)); + + if (set) { + INIT_LIST_HEAD(&set->sections); + perf_config(collect_config, set); + } + + return set; +} + +static void perf_config_item__delete(struct perf_config_item *item) +{ + zfree(&item->name); + zfree(&item->value); + free(item); +} + +static void perf_config_section__purge(struct perf_config_section *section) +{ + struct perf_config_item *item, *tmp; + + list_for_each_entry_safe(item, tmp, §ion->items, node) { + list_del_init(&item->node); + perf_config_item__delete(item); + } +} + +static void perf_config_section__delete(struct perf_config_section *section) +{ + perf_config_section__purge(section); + zfree(§ion->name); + free(section); +} + +static void perf_config_set__purge(struct perf_config_set *set) +{ + struct perf_config_section *section, *tmp; + + list_for_each_entry_safe(section, tmp, &set->sections, node) { + list_del_init(§ion->node); + perf_config_section__delete(section); + } +} + +void perf_config_set__delete(struct perf_config_set *set) +{ + perf_config_set__purge(set); + free(set); +} + +/* + * Call this to report error for your variable that should not + * get a boolean value (i.e. "[my] var" means "true"). + */ +int config_error_nonbool(const char *var) +{ + return error("Missing value for '%s'", var); } void set_buildid_dir(const char *dir) @@ -548,16 +711,13 @@ void set_buildid_dir(const char *dir) if (dir) scnprintf(buildid_dir, MAXPATHLEN-1, "%s", dir); - /* try config file */ - if (buildid_dir[0] == '\0') - check_buildid_dir_config(); - /* default to $HOME/.debug */ if (buildid_dir[0] == '\0') { - char *v = getenv("HOME"); - if (v) { + char *home = getenv("HOME"); + + if (home) { snprintf(buildid_dir, MAXPATHLEN-1, "%s/%s", - v, DEBUG_CACHE_DIR); + home, DEBUG_CACHE_DIR); } else { strncpy(buildid_dir, DEBUG_CACHE_DIR, MAXPATHLEN-1); } diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h new file mode 100644 index 0000000..22ec626 --- /dev/null +++ b/tools/perf/util/config.h @@ -0,0 +1,26 @@ +#ifndef __PERF_CONFIG_H +#define __PERF_CONFIG_H + +#include <stdbool.h> +#include <linux/list.h> + +struct perf_config_item { + char *name; + char *value; + struct list_head node; +}; + +struct perf_config_section { + char *name; + struct list_head items; + struct list_head node; +}; + +struct perf_config_set { + struct list_head sections; +}; + +struct perf_config_set *perf_config_set__new(void); +void perf_config_set__delete(struct perf_config_set *set); + +#endif /* __PERF_CONFIG_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 9bcf2be..02d8016 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -587,3 +587,15 @@ int cpu__setup_cpunode_map(void) closedir(dir1); return 0; } + +bool cpu_map__has(struct cpu_map *cpus, int cpu) +{ + int i; + + for (i = 0; i < cpus->nr; ++i) { + if (cpus->map[i] == cpu) + return true; + } + + return false; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 81a2562..1a0a350 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -66,4 +66,6 @@ int cpu__get_node(int cpu); int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, int (*f)(struct cpu_map *map, int cpu, void *data), void *data); + +bool cpu_map__has(struct cpu_map *cpus, int cpu); #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 1921942..be835161 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -136,3 +136,44 @@ ssize_t perf_data_file__write(struct perf_data_file *file, { return writen(file->fd, buf, size); } + +int perf_data_file__switch(struct perf_data_file *file, + const char *postfix, + size_t pos, bool at_exit) +{ + char *new_filepath; + int ret; + + if (check_pipe(file)) + return -EINVAL; + if (perf_data_file__is_read(file)) + return -EINVAL; + + if (asprintf(&new_filepath, "%s.%s", file->path, postfix) < 0) + return -ENOMEM; + + /* + * Only fire a warning, don't return error, continue fill + * original file. + */ + if (rename(file->path, new_filepath)) + pr_warning("Failed to rename %s to %s\n", file->path, new_filepath); + + if (!at_exit) { + close(file->fd); + ret = perf_data_file__open(file); + if (ret < 0) + goto out; + + if (lseek(file->fd, pos, SEEK_SET) == (off_t)-1) { + ret = -errno; + pr_debug("Failed to lseek to %zu: %s", + pos, strerror(errno)); + goto out; + } + } + ret = file->fd; +out: + free(new_filepath); + return ret; +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 2b15d0c..ae510ce 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -46,5 +46,14 @@ int perf_data_file__open(struct perf_data_file *file); void perf_data_file__close(struct perf_data_file *file); ssize_t perf_data_file__write(struct perf_data_file *file, void *buf, size_t size); - +/* + * If at_exit is set, only rename current perf.data to + * perf.data.<postfix>, continue write on original file. + * Set at_exit when flushing the last output. + * + * Return value is fd of new output. + */ +int perf_data_file__switch(struct perf_data_file *file, + const char *postfix, + size_t pos, bool at_exit); #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index 049438d..8d96c80 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -23,6 +23,8 @@ #include "event.h" #include "util.h" #include "thread-stack.h" +#include "callchain.h" +#include "call-path.h" #include "db-export.h" struct deferred_export { @@ -258,8 +260,7 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, if (!al->sym) { al->sym = symbol__new(al->addr, 0, 0, "unknown"); if (al->sym) - symbols__insert(&dso->symbols[al->map->type], - al->sym); + dso__insert_symbol(dso, al->map->type, al->sym); } if (al->sym) { @@ -276,6 +277,80 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, return 0; } +static struct call_path *call_path_from_sample(struct db_export *dbe, + struct machine *machine, + struct thread *thread, + struct perf_sample *sample, + struct perf_evsel *evsel) +{ + u64 kernel_start = machine__kernel_start(machine); + struct call_path *current = &dbe->cpr->call_path; + enum chain_order saved_order = callchain_param.order; + int err; + + if (!symbol_conf.use_callchain || !sample->callchain) + return NULL; + + /* + * Since the call path tree must be built starting with the root, we + * must use ORDER_CALL for call chain resolution, in order to process + * the callchain starting with the root node and ending with the leaf. + */ + callchain_param.order = ORDER_CALLER; + err = thread__resolve_callchain(thread, &callchain_cursor, evsel, + sample, NULL, NULL, + sysctl_perf_event_max_stack); + if (err) { + callchain_param.order = saved_order; + return NULL; + } + callchain_cursor_commit(&callchain_cursor); + + while (1) { + struct callchain_cursor_node *node; + struct addr_location al; + u64 dso_db_id = 0, sym_db_id = 0, offset = 0; + + memset(&al, 0, sizeof(al)); + + node = callchain_cursor_current(&callchain_cursor); + if (!node) + break; + /* + * Handle export of symbol and dso for this node by + * constructing an addr_location struct and then passing it to + * db_ids_from_al() to perform the export. + */ + al.sym = node->sym; + al.map = node->map; + al.machine = machine; + al.addr = node->ip; + + if (al.map && !al.sym) + al.sym = dso__find_symbol(al.map->dso, MAP__FUNCTION, + al.addr); + + db_ids_from_al(dbe, &al, &dso_db_id, &sym_db_id, &offset); + + /* add node to the call path tree if it doesn't exist */ + current = call_path__findnew(dbe->cpr, current, + al.sym, node->ip, + kernel_start); + + callchain_cursor_advance(&callchain_cursor); + } + + /* Reset the callchain order to its prior value. */ + callchain_param.order = saved_order; + + if (current == &dbe->cpr->call_path) { + /* Bail because the callchain was empty. */ + return NULL; + } + + return current; +} + int db_export__branch_type(struct db_export *dbe, u32 branch_type, const char *name) { @@ -329,6 +404,16 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, if (err) goto out_put; + if (dbe->cpr) { + struct call_path *cp = call_path_from_sample(dbe, al->machine, + thread, sample, + evsel); + if (cp) { + db_export__call_path(dbe, cp); + es.call_path_id = cp->db_id; + } + } + if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && sample_addr_correlates_sym(&evsel->attr)) { struct addr_location addr_al; diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h index 25e22fd..67bc6b8 100644 --- a/tools/perf/util/db-export.h +++ b/tools/perf/util/db-export.h @@ -27,6 +27,7 @@ struct dso; struct perf_sample; struct addr_location; struct call_return_processor; +struct call_path_root; struct call_path; struct call_return; @@ -43,6 +44,7 @@ struct export_sample { u64 addr_dso_db_id; u64 addr_sym_db_id; u64 addr_offset; /* addr offset from symbol start */ + u64 call_path_id; }; struct db_export { @@ -64,6 +66,7 @@ struct db_export { int (*export_call_return)(struct db_export *dbe, struct call_return *cr); struct call_return_processor *crp; + struct call_path_root *cpr; u64 evsel_last_db_id; u64 machine_last_db_id; u64 thread_last_db_id; diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 8e639543..3357479 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -38,7 +38,7 @@ int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, char *root_dir, char *filename, size_t size) { - char build_id_hex[BUILD_ID_SIZE * 2 + 1]; + char build_id_hex[SBUILD_ID_SIZE]; int ret = 0; size_t len; @@ -1301,7 +1301,7 @@ size_t __dsos__fprintf(struct list_head *head, FILE *fp) size_t dso__fprintf_buildid(struct dso *dso, FILE *fp) { - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + char sbuild_id[SBUILD_ID_SIZE]; build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); return fprintf(fp, "%s", sbuild_id); diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 577e600..a347b19 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -915,8 +915,7 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf) tmp = "*"; else if (tag == DW_TAG_subroutine_type) { /* Function pointer */ - strbuf_add(buf, "(function_type)", 15); - return 0; + return strbuf_add(buf, "(function_type)", 15); } else { if (!dwarf_diename(&type)) return -ENOENT; @@ -927,14 +926,10 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf) else if (tag == DW_TAG_enumeration_type) tmp = "enum "; /* Write a base name */ - strbuf_addf(buf, "%s%s", tmp, dwarf_diename(&type)); - return 0; + return strbuf_addf(buf, "%s%s", tmp, dwarf_diename(&type)); } ret = die_get_typename(&type, buf); - if (ret == 0) - strbuf_addstr(buf, tmp); - - return ret; + return ret ? ret : strbuf_addstr(buf, tmp); } /** @@ -951,14 +946,13 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf) ret = die_get_typename(vr_die, buf); if (ret < 0) { pr_debug("Failed to get type, make it unknown.\n"); - strbuf_add(buf, " (unknown_type)", 14); + ret = strbuf_add(buf, " (unknown_type)", 14); } - strbuf_addf(buf, "\t%s", dwarf_diename(vr_die)); - - return 0; + return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die)); } +#ifdef HAVE_DWARF_GETLOCATIONS /** * die_get_var_innermost_scope - Get innermost scope range of given variable DIE * @sp_die: a subprogram DIE @@ -998,22 +992,24 @@ static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die, } while ((offset = dwarf_ranges(&scopes[1], offset, &base, - &start, &end)) > 0) { + &start, &end)) > 0) { start -= entry; end -= entry; if (first) { - strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64, - name, start, end); + ret = strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64, + name, start, end); first = false; } else { - strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64, - start, end); + ret = strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64, + start, end); } + if (ret < 0) + goto out; } if (!first) - strbuf_add(buf, "]>", 2); + ret = strbuf_add(buf, "]>", 2); out: free(scopes); @@ -1053,30 +1049,39 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf) if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL) return -EINVAL; - while ((offset = dwarf_getlocations( - &attr, offset, &base, - &start, &end, &op, &nops)) > 0) { + while ((offset = dwarf_getlocations(&attr, offset, &base, + &start, &end, &op, &nops)) > 0) { if (start == 0) { /* Single Location Descriptions */ ret = die_get_var_innermost_scope(sp_die, vr_die, buf); - return ret; + goto out; } /* Location Lists */ start -= entry; end -= entry; if (first) { - strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64, - name, start, end); + ret = strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64, + name, start, end); first = false; } else { - strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64, - start, end); + ret = strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64, + start, end); } + if (ret < 0) + goto out; } if (!first) - strbuf_add(buf, "]>", 2); - + ret = strbuf_add(buf, "]>", 2); +out: return ret; } +#else +int die_get_var_range(Dwarf_Die *sp_die __maybe_unused, + Dwarf_Die *vr_die __maybe_unused, + struct strbuf *buf __maybe_unused) +{ + return -ENOTSUP; +} +#endif diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index dad55d0..f6fcc68 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -45,6 +45,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_STAT] = "STAT", [PERF_RECORD_STAT_ROUND] = "STAT_ROUND", [PERF_RECORD_EVENT_UPDATE] = "EVENT_UPDATE", + [PERF_RECORD_TIME_CONV] = "TIME_CONV", }; const char *perf_event__name(unsigned int id) @@ -433,7 +434,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, { char filename[PATH_MAX]; DIR *tasks; - struct dirent dirent, *next; + struct dirent *dirent; pid_t tgid, ppid; int rc = 0; @@ -462,11 +463,11 @@ static int __event__synthesize_thread(union perf_event *comm_event, return 0; } - while (!readdir_r(tasks, &dirent, &next) && next) { + while ((dirent = readdir(tasks)) != NULL) { char *end; pid_t _pid; - _pid = strtol(dirent.d_name, &end, 10); + _pid = strtol(dirent->d_name, &end, 10); if (*end) continue; @@ -575,7 +576,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, { DIR *proc; char proc_path[PATH_MAX]; - struct dirent dirent, *next; + struct dirent *dirent; union perf_event *comm_event, *mmap_event, *fork_event; int err = -1; @@ -600,9 +601,9 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (proc == NULL) goto out_free_fork; - while (!readdir_r(proc, &dirent, &next) && next) { + while ((dirent = readdir(proc)) != NULL) { char *end; - pid_t pid = strtol(dirent.d_name, &end, 10); + pid_t pid = strtol(dirent->d_name, &end, 10); if (*end) /* only interested in proper numerical dirents */ continue; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 6bb1c92..8d363d5 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -233,6 +233,7 @@ enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_STAT = 76, PERF_RECORD_STAT_ROUND = 77, PERF_RECORD_EVENT_UPDATE = 78, + PERF_RECORD_TIME_CONV = 79, PERF_RECORD_HEADER_MAX }; @@ -469,6 +470,13 @@ struct stat_round_event { u64 time; }; +struct time_conv_event { + struct perf_event_header header; + u64 time_shift; + u64 time_mult; + u64 time_zero; +}; + union perf_event { struct perf_event_header header; struct mmap_event mmap; @@ -497,6 +505,7 @@ union perf_event { struct stat_config_event stat_config; struct stat_event stat; struct stat_round_event stat_round; + struct time_conv_event time_conv; }; void perf_event__print_totals(void); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 86a0383..c4bfe11 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -679,53 +679,52 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, return NULL; } -union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) +/* When check_messup is true, 'end' must points to a good entry */ +static union perf_event * +perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start, + u64 end, u64 *prev) { - struct perf_mmap *md = &evlist->mmap[idx]; - u64 head; - u64 old = md->prev; unsigned char *data = md->base + page_size; union perf_event *event = NULL; + int diff = end - start; - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!atomic_read(&md->refcnt)) - return NULL; - - head = perf_mmap__read_head(md); - if (evlist->overwrite) { + if (check_messup) { /* * If we're further behind than half the buffer, there's a chance * the writer will bite our tail and mess up the samples under us. * - * If we somehow ended up ahead of the head, we got messed up. + * If we somehow ended up ahead of the 'end', we got messed up. * - * In either case, truncate and restart at head. + * In either case, truncate and restart at 'end'. */ - int diff = head - old; if (diff > md->mask / 2 || diff < 0) { fprintf(stderr, "WARNING: failed to keep up with mmap data.\n"); /* - * head points to a known good entry, start there. + * 'end' points to a known good entry, start there. */ - old = head; + start = end; + diff = 0; } } - if (old != head) { + if (diff >= (int)sizeof(event->header)) { size_t size; - event = (union perf_event *)&data[old & md->mask]; + event = (union perf_event *)&data[start & md->mask]; size = event->header.size; + if (size < sizeof(event->header) || diff < (int)size) { + event = NULL; + goto broken_event; + } + /* * Event straddles the mmap boundary -- header should always * be inside due to u64 alignment of output. */ - if ((old & md->mask) + size != ((old + size) & md->mask)) { - unsigned int offset = old; + if ((start & md->mask) + size != ((start + size) & md->mask)) { + unsigned int offset = start; unsigned int len = min(sizeof(*event), size), cpy; void *dst = md->event_copy; @@ -740,14 +739,83 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) event = (union perf_event *) md->event_copy; } - old += size; + start += size; } - md->prev = old; +broken_event: + if (prev) + *prev = start; return event; } +union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) +{ + struct perf_mmap *md = &evlist->mmap[idx]; + u64 head; + u64 old = md->prev; + + /* + * Check if event was unmapped due to a POLLHUP/POLLERR. + */ + if (!atomic_read(&md->refcnt)) + return NULL; + + head = perf_mmap__read_head(md); + + return perf_mmap__read(md, evlist->overwrite, old, head, &md->prev); +} + +union perf_event * +perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx) +{ + struct perf_mmap *md = &evlist->mmap[idx]; + u64 head, end; + u64 start = md->prev; + + /* + * Check if event was unmapped due to a POLLHUP/POLLERR. + */ + if (!atomic_read(&md->refcnt)) + return NULL; + + head = perf_mmap__read_head(md); + if (!head) + return NULL; + + /* + * 'head' pointer starts from 0. Kernel minus sizeof(record) form + * it each time when kernel writes to it, so in fact 'head' is + * negative. 'end' pointer is made manually by adding the size of + * the ring buffer to 'head' pointer, means the validate data can + * read is the whole ring buffer. If 'end' is positive, the ring + * buffer has not fully filled, so we must adjust 'end' to 0. + * + * However, since both 'head' and 'end' is unsigned, we can't + * simply compare 'end' against 0. Here we compare '-head' and + * the size of the ring buffer, where -head is the number of bytes + * kernel write to the ring buffer. + */ + if (-head < (u64)(md->mask + 1)) + end = 0; + else + end = head + md->mask + 1; + + return perf_mmap__read(md, false, start, end, &md->prev); +} + +void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx) +{ + struct perf_mmap *md = &evlist->mmap[idx]; + u64 head; + + if (!atomic_read(&md->refcnt)) + return; + + head = perf_mmap__read_head(md); + md->prev = head; +} + static bool perf_mmap__empty(struct perf_mmap *md) { return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base; @@ -986,26 +1054,34 @@ out_unmap: return -1; } -static size_t perf_evlist__mmap_size(unsigned long pages) +unsigned long perf_event_mlock_kb_in_pages(void) { - if (pages == UINT_MAX) { - int max; + unsigned long pages; + int max; - if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) { - /* - * Pick a once upon a time good value, i.e. things look - * strange since we can't read a sysctl value, but lets not - * die yet... - */ - max = 512; - } else { - max -= (page_size / 1024); - } + if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) { + /* + * Pick a once upon a time good value, i.e. things look + * strange since we can't read a sysctl value, but lets not + * die yet... + */ + max = 512; + } else { + max -= (page_size / 1024); + } - pages = (max * 1024) / page_size; - if (!is_power_of_2(pages)) - pages = rounddown_pow_of_two(pages); - } else if (!is_power_of_2(pages)) + pages = (max * 1024) / page_size; + if (!is_power_of_2(pages)) + pages = rounddown_pow_of_two(pages); + + return pages; +} + +static size_t perf_evlist__mmap_size(unsigned long pages) +{ + if (pages == UINT_MAX) + pages = perf_event_mlock_kb_in_pages(); + else if (!is_power_of_2(pages)) return 0; return (pages + 1) * page_size; @@ -1192,6 +1268,24 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, perf_evlist__propagate_maps(evlist); } +void __perf_evlist__set_sample_bit(struct perf_evlist *evlist, + enum perf_event_sample_format bit) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) + __perf_evsel__set_sample_bit(evsel, bit); +} + +void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist, + enum perf_event_sample_format bit) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) + __perf_evsel__reset_sample_bit(evsel, bit); +} + int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel) { struct perf_evsel *evsel; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index a0d1522..85d1b598 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -87,6 +87,17 @@ int perf_evlist__add_dummy(struct perf_evlist *evlist); int perf_evlist__add_newtp(struct perf_evlist *evlist, const char *sys, const char *name, void *handler); +void __perf_evlist__set_sample_bit(struct perf_evlist *evlist, + enum perf_event_sample_format bit); +void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist, + enum perf_event_sample_format bit); + +#define perf_evlist__set_sample_bit(evlist, bit) \ + __perf_evlist__set_sample_bit(evlist, PERF_SAMPLE_##bit) + +#define perf_evlist__reset_sample_bit(evlist, bit) \ + __perf_evlist__reset_sample_bit(evlist, PERF_SAMPLE_##bit) + int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter); int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid); int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids); @@ -118,16 +129,23 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id); union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx); +union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, + int idx); +void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx); + void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); int perf_evlist__open(struct perf_evlist *evlist); void perf_evlist__close(struct perf_evlist *evlist); +struct callchain_param; + void perf_evlist__set_id_pos(struct perf_evlist *evlist); bool perf_can_sample_identifier(void); bool perf_can_record_switch_events(void); bool perf_can_record_cpu_wide(void); -void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts); +void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, + struct callchain_param *callchain); int record_opts__config(struct record_opts *opts); int perf_evlist__prepare_workload(struct perf_evlist *evlist, @@ -144,6 +162,8 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset); +unsigned long perf_event_mlock_kb_in_pages(void); + int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, bool overwrite, unsigned int auxtrace_pages, bool auxtrace_overwrite); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 738ce22..964c7c3 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -226,7 +226,8 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) perf_evsel__init(evsel, attr, idx); if (perf_evsel__is_bpf_output(evsel)) { - evsel->attr.sample_type |= PERF_SAMPLE_RAW; + evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | + PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), evsel->attr.sample_period = 1; } @@ -561,10 +562,9 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) return ret; } -static void -perf_evsel__config_callgraph(struct perf_evsel *evsel, - struct record_opts *opts, - struct callchain_param *param) +void perf_evsel__config_callchain(struct perf_evsel *evsel, + struct record_opts *opts, + struct callchain_param *param) { bool function = perf_evsel__is_function_event(evsel); struct perf_event_attr *attr = &evsel->attr; @@ -704,7 +704,7 @@ static void apply_config_terms(struct perf_evsel *evsel, /* set perf-event callgraph */ if (param.enabled) - perf_evsel__config_callgraph(evsel, opts, ¶m); + perf_evsel__config_callchain(evsel, opts, ¶m); } } @@ -736,7 +736,8 @@ static void apply_config_terms(struct perf_evsel *evsel, * enable/disable events specifically, as there's no * initial traced exec call. */ -void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) +void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, + struct callchain_param *callchain) { struct perf_evsel *leader = evsel->leader; struct perf_event_attr *attr = &evsel->attr; @@ -811,8 +812,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (perf_evsel__is_function_event(evsel)) evsel->attr.exclude_callchain_user = 1; - if (callchain_param.enabled && !evsel->no_aux_samples) - perf_evsel__config_callgraph(evsel, opts, &callchain_param); + if (callchain && callchain->enabled && !evsel->no_aux_samples) + perf_evsel__config_callchain(evsel, opts, callchain); if (opts->sample_intr_regs) { attr->sample_regs_intr = opts->sample_intr_regs; @@ -1230,6 +1231,21 @@ static void __p_sample_type(char *buf, size_t size, u64 value) __p_bits(buf, size, value, bits); } +static void __p_branch_sample_type(char *buf, size_t size, u64 value) +{ +#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n } + struct bit_names bits[] = { + bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY), + bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL), + bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX), + bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP), + bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES), + { .name = NULL, } + }; +#undef bit_name + __p_bits(buf, size, value, bits); +} + static void __p_read_format(char *buf, size_t size, u64 value) { #define bit_name(n) { PERF_FORMAT_##n, #n } @@ -1248,6 +1264,7 @@ static void __p_read_format(char *buf, size_t size, u64 value) #define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val)) #define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val)) #define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val) +#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val) #define p_read_format(val) __p_read_format(buf, BUF_SIZE, val) #define PRINT_ATTRn(_n, _f, _p) \ @@ -1299,12 +1316,13 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(comm_exec, p_unsigned); PRINT_ATTRf(use_clockid, p_unsigned); PRINT_ATTRf(context_switch, p_unsigned); + PRINT_ATTRf(write_backward, p_unsigned); PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); PRINT_ATTRf(bp_type, p_unsigned); PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex); PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex); - PRINT_ATTRf(branch_sample_type, p_unsigned); + PRINT_ATTRf(branch_sample_type, p_branch_sample_type); PRINT_ATTRf(sample_regs_user, p_hex); PRINT_ATTRf(sample_stack_user, p_unsigned); PRINT_ATTRf(clockid, p_signed); @@ -2253,98 +2271,11 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, return 0; } -static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) -{ - va_list args; - int ret = 0; - - if (!*first) { - ret += fprintf(fp, ","); - } else { - ret += fprintf(fp, ":"); - *first = false; - } - - va_start(args, fmt); - ret += vfprintf(fp, fmt, args); - va_end(args); - return ret; -} - -static int __print_attr__fprintf(FILE *fp, const char *name, const char *val, void *priv) -{ - return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val); -} - -int perf_evsel__fprintf(struct perf_evsel *evsel, - struct perf_attr_details *details, FILE *fp) -{ - bool first = true; - int printed = 0; - - if (details->event_group) { - struct perf_evsel *pos; - - if (!perf_evsel__is_group_leader(evsel)) - return 0; - - if (evsel->nr_members > 1) - printed += fprintf(fp, "%s{", evsel->group_name ?: ""); - - printed += fprintf(fp, "%s", perf_evsel__name(evsel)); - for_each_group_member(pos, evsel) - printed += fprintf(fp, ",%s", perf_evsel__name(pos)); - - if (evsel->nr_members > 1) - printed += fprintf(fp, "}"); - goto out; - } - - printed += fprintf(fp, "%s", perf_evsel__name(evsel)); - - if (details->verbose) { - printed += perf_event_attr__fprintf(fp, &evsel->attr, - __print_attr__fprintf, &first); - } else if (details->freq) { - const char *term = "sample_freq"; - - if (!evsel->attr.freq) - term = "sample_period"; - - printed += comma_fprintf(fp, &first, " %s=%" PRIu64, - term, (u64)evsel->attr.sample_freq); - } - - if (details->trace_fields) { - struct format_field *field; - - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { - printed += comma_fprintf(fp, &first, " (not a tracepoint)"); - goto out; - } - - field = evsel->tp_format->format.fields; - if (field == NULL) { - printed += comma_fprintf(fp, &first, " (no trace field)"); - goto out; - } - - printed += comma_fprintf(fp, &first, " trace_fields: %s", field->name); - - field = field->next; - while (field) { - printed += comma_fprintf(fp, &first, "%s", field->name); - field = field->next; - } - } -out: - fputc('\n', fp); - return ++printed; -} - bool perf_evsel__fallback(struct perf_evsel *evsel, int err, char *msg, size_t msgsize) { + int paranoid; + if ((err == ENOENT || err == ENXIO || err == ENODEV) && evsel->attr.type == PERF_TYPE_HARDWARE && evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) { @@ -2364,6 +2295,22 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, zfree(&evsel->name); return true; + } else if (err == EACCES && !evsel->attr.exclude_kernel && + (paranoid = perf_event_paranoid()) > 1) { + const char *name = perf_evsel__name(evsel); + char *new_name; + + if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0) + return false; + + if (evsel->name) + free(evsel->name); + evsel->name = new_name; + scnprintf(msg, msgsize, +"kernel.perf_event_paranoid=%d, trying to fall back to excluding kernel samples", paranoid); + evsel->attr.exclude_kernel = 1; + + return true; } return false; @@ -2382,12 +2329,13 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n" "which controls use of the performance events system by\n" "unprivileged users (without CAP_SYS_ADMIN).\n\n" - "The default value is 1:\n\n" + "The current value is %d:\n\n" " -1: Allow use of (almost) all events by all users\n" ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n" ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN", - target->system_wide ? "system-wide " : ""); + target->system_wide ? "system-wide " : "", + perf_event_paranoid()); case ENOENT: return scnprintf(msg, size, "The %s event is not supported.", perf_evsel__name(evsel)); @@ -2397,10 +2345,18 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "Probably the maximum number of open file descriptors has been reached.\n" "Hint: Try again after reducing the number of events.\n" "Hint: Try increasing the limit with 'ulimit -n <limit>'"); + case ENOMEM: + if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0 && + access("/proc/sys/kernel/perf_event_max_stack", F_OK) == 0) + return scnprintf(msg, size, + "Not enough memory to setup event with callchain.\n" + "Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n" + "Hint: Current value: %d", sysctl_perf_event_max_stack); + break; case ENODEV: if (target->cpu_list) return scnprintf(msg, size, "%s", - "No such device - did you specify an out-of-range profile CPU?\n"); + "No such device - did you specify an out-of-range profile CPU?"); break; case EOPNOTSUPP: if (evsel->attr.precise_ip) @@ -2432,7 +2388,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, return scnprintf(msg, size, "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n" "/bin/dmesg may provide additional information.\n" - "No CONFIG_PERF_EVENTS=y kernel support configured?\n", + "No CONFIG_PERF_EVENTS=y kernel support configured?", err, strerror_r(err, sbuf, sizeof(sbuf)), perf_evsel__name(evsel)); } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 501ea6e..8a644fe 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -178,8 +178,14 @@ void perf_evsel__init(struct perf_evsel *evsel, void perf_evsel__exit(struct perf_evsel *evsel); void perf_evsel__delete(struct perf_evsel *evsel); +struct callchain_param; + void perf_evsel__config(struct perf_evsel *evsel, - struct record_opts *opts); + struct record_opts *opts, + struct callchain_param *callchain); +void perf_evsel__config_callchain(struct perf_evsel *evsel, + struct record_opts *opts, + struct callchain_param *callchain); int __perf_evsel__sample_size(u64 sample_type); void perf_evsel__calc_id_pos(struct perf_evsel *evsel); @@ -381,6 +387,24 @@ struct perf_attr_details { int perf_evsel__fprintf(struct perf_evsel *evsel, struct perf_attr_details *details, FILE *fp); +#define EVSEL__PRINT_IP (1<<0) +#define EVSEL__PRINT_SYM (1<<1) +#define EVSEL__PRINT_DSO (1<<2) +#define EVSEL__PRINT_SYMOFFSET (1<<3) +#define EVSEL__PRINT_ONELINE (1<<4) +#define EVSEL__PRINT_SRCLINE (1<<5) +#define EVSEL__PRINT_UNKNOWN_AS_ADDR (1<<6) + +struct callchain_cursor; + +int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, + unsigned int print_opts, + struct callchain_cursor *cursor, FILE *fp); + +int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, + int left_alignment, unsigned int print_opts, + struct callchain_cursor *cursor, FILE *fp); + bool perf_evsel__fallback(struct perf_evsel *evsel, int err, char *msg, size_t msgsize); int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, @@ -396,7 +420,7 @@ for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); \ (_evsel) && (_evsel)->leader == (_leader); \ (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) -static inline bool has_branch_callstack(struct perf_evsel *evsel) +static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evsel) { return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c new file mode 100644 index 0000000..3674e77 --- /dev/null +++ b/tools/perf/util/evsel_fprintf.c @@ -0,0 +1,212 @@ +#include <stdio.h> +#include <stdbool.h> +#include <traceevent/event-parse.h> +#include "evsel.h" +#include "callchain.h" +#include "map.h" +#include "symbol.h" + +static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) +{ + va_list args; + int ret = 0; + + if (!*first) { + ret += fprintf(fp, ","); + } else { + ret += fprintf(fp, ":"); + *first = false; + } + + va_start(args, fmt); + ret += vfprintf(fp, fmt, args); + va_end(args); + return ret; +} + +static int __print_attr__fprintf(FILE *fp, const char *name, const char *val, void *priv) +{ + return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val); +} + +int perf_evsel__fprintf(struct perf_evsel *evsel, + struct perf_attr_details *details, FILE *fp) +{ + bool first = true; + int printed = 0; + + if (details->event_group) { + struct perf_evsel *pos; + + if (!perf_evsel__is_group_leader(evsel)) + return 0; + + if (evsel->nr_members > 1) + printed += fprintf(fp, "%s{", evsel->group_name ?: ""); + + printed += fprintf(fp, "%s", perf_evsel__name(evsel)); + for_each_group_member(pos, evsel) + printed += fprintf(fp, ",%s", perf_evsel__name(pos)); + + if (evsel->nr_members > 1) + printed += fprintf(fp, "}"); + goto out; + } + + printed += fprintf(fp, "%s", perf_evsel__name(evsel)); + + if (details->verbose) { + printed += perf_event_attr__fprintf(fp, &evsel->attr, + __print_attr__fprintf, &first); + } else if (details->freq) { + const char *term = "sample_freq"; + + if (!evsel->attr.freq) + term = "sample_period"; + + printed += comma_fprintf(fp, &first, " %s=%" PRIu64, + term, (u64)evsel->attr.sample_freq); + } + + if (details->trace_fields) { + struct format_field *field; + + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + printed += comma_fprintf(fp, &first, " (not a tracepoint)"); + goto out; + } + + field = evsel->tp_format->format.fields; + if (field == NULL) { + printed += comma_fprintf(fp, &first, " (no trace field)"); + goto out; + } + + printed += comma_fprintf(fp, &first, " trace_fields: %s", field->name); + + field = field->next; + while (field) { + printed += comma_fprintf(fp, &first, "%s", field->name); + field = field->next; + } + } +out: + fputc('\n', fp); + return ++printed; +} + +int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, + unsigned int print_opts, struct callchain_cursor *cursor, + FILE *fp) +{ + int printed = 0; + struct callchain_cursor_node *node; + int print_ip = print_opts & EVSEL__PRINT_IP; + int print_sym = print_opts & EVSEL__PRINT_SYM; + int print_dso = print_opts & EVSEL__PRINT_DSO; + int print_symoffset = print_opts & EVSEL__PRINT_SYMOFFSET; + int print_oneline = print_opts & EVSEL__PRINT_ONELINE; + int print_srcline = print_opts & EVSEL__PRINT_SRCLINE; + int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR; + char s = print_oneline ? ' ' : '\t'; + + if (sample->callchain) { + struct addr_location node_al; + + callchain_cursor_commit(cursor); + + while (1) { + u64 addr = 0; + + node = callchain_cursor_current(cursor); + if (!node) + break; + + if (node->sym && node->sym->ignore) + goto next; + + printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " "); + + if (print_ip) + printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); + + if (node->map) + addr = node->map->map_ip(node->map, node->ip); + + if (print_sym) { + printed += fprintf(fp, " "); + node_al.addr = addr; + node_al.map = node->map; + + if (print_symoffset) { + printed += __symbol__fprintf_symname_offs(node->sym, &node_al, + print_unknown_as_addr, fp); + } else { + printed += __symbol__fprintf_symname(node->sym, &node_al, + print_unknown_as_addr, fp); + } + } + + if (print_dso) { + printed += fprintf(fp, " ("); + printed += map__fprintf_dsoname(node->map, fp); + printed += fprintf(fp, ")"); + } + + if (print_srcline) + printed += map__fprintf_srcline(node->map, addr, "\n ", fp); + + if (!print_oneline) + printed += fprintf(fp, "\n"); +next: + callchain_cursor_advance(cursor); + } + } + + return printed; +} + +int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, + int left_alignment, unsigned int print_opts, + struct callchain_cursor *cursor, FILE *fp) +{ + int printed = 0; + int print_ip = print_opts & EVSEL__PRINT_IP; + int print_sym = print_opts & EVSEL__PRINT_SYM; + int print_dso = print_opts & EVSEL__PRINT_DSO; + int print_symoffset = print_opts & EVSEL__PRINT_SYMOFFSET; + int print_srcline = print_opts & EVSEL__PRINT_SRCLINE; + int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR; + + if (cursor != NULL) { + printed += sample__fprintf_callchain(sample, left_alignment, + print_opts, cursor, fp); + } else if (!(al->sym && al->sym->ignore)) { + printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " "); + + if (print_ip) + printed += fprintf(fp, "%16" PRIx64, sample->ip); + + if (print_sym) { + printed += fprintf(fp, " "); + if (print_symoffset) { + printed += __symbol__fprintf_symname_offs(al->sym, al, + print_unknown_as_addr, fp); + } else { + printed += __symbol__fprintf_symname(al->sym, al, + print_unknown_as_addr, fp); + } + } + + if (print_dso) { + printed += fprintf(fp, " ("); + printed += map__fprintf_dsoname(al->map, fp); + printed += fprintf(fp, ")"); + } + + if (print_srcline) + printed += map__fprintf_srcline(al->map, al->addr, "\n ", fp); + } + + return printed; +} diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 90680ec..08852dd 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1474,7 +1474,7 @@ static int __event_process_build_id(struct build_id_event *bev, dso = machine__findnew_dso(machine, filename); if (dso != NULL) { - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + char sbuild_id[SBUILD_ID_SIZE]; dso__set_build_id(dso, &bev->build_id); @@ -1819,7 +1819,8 @@ static int process_cpu_topology(struct perf_file_section *section, ph->env.nr_sibling_cores = nr; size += sizeof(u32); - strbuf_init(&sb, 128); + if (strbuf_init(&sb, 128) < 0) + goto free_cpu; for (i = 0; i < nr; i++) { str = do_read_string(fd, ph); @@ -1827,7 +1828,8 @@ static int process_cpu_topology(struct perf_file_section *section, goto error; /* include a NULL character at the end */ - strbuf_add(&sb, str, strlen(str) + 1); + if (strbuf_add(&sb, str, strlen(str) + 1) < 0) + goto error; size += string_size(str); free(str); } @@ -1849,7 +1851,8 @@ static int process_cpu_topology(struct perf_file_section *section, goto error; /* include a NULL character at the end */ - strbuf_add(&sb, str, strlen(str) + 1); + if (strbuf_add(&sb, str, strlen(str) + 1) < 0) + goto error; size += string_size(str); free(str); } @@ -1912,13 +1915,14 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse /* nr nodes */ ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) - goto error; + return -1; if (ph->needs_swap) nr = bswap_32(nr); ph->env.nr_numa_nodes = nr; - strbuf_init(&sb, 256); + if (strbuf_init(&sb, 256) < 0) + return -1; for (i = 0; i < nr; i++) { /* node number */ @@ -1940,15 +1944,17 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse mem_free = bswap_64(mem_free); } - strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":", - node, mem_total, mem_free); + if (strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":", + node, mem_total, mem_free) < 0) + goto error; str = do_read_string(fd, ph); if (!str) goto error; /* include a NULL character at the end */ - strbuf_add(&sb, str, strlen(str) + 1); + if (strbuf_add(&sb, str, strlen(str) + 1) < 0) + goto error; free(str); } ph->env.numa_nodes = strbuf_detach(&sb, NULL); @@ -1982,7 +1988,8 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused } ph->env.nr_pmu_mappings = pmu_num; - strbuf_init(&sb, 128); + if (strbuf_init(&sb, 128) < 0) + return -1; while (pmu_num) { if (readn(fd, &type, sizeof(type)) != sizeof(type)) @@ -1994,9 +2001,11 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused if (!name) goto error; - strbuf_addf(&sb, "%u:%s", type, name); + if (strbuf_addf(&sb, "%u:%s", type, name) < 0) + goto error; /* include a NULL character at the end */ - strbuf_add(&sb, "", 1); + if (strbuf_add(&sb, "", 1) < 0) + goto error; if (!strcmp(name, "msr")) ph->env.msr_pmu_type = type; diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c index 43a98a4..d62ccae 100644 --- a/tools/perf/util/help-unknown-cmd.c +++ b/tools/perf/util/help-unknown-cmd.c @@ -27,16 +27,27 @@ static int levenshtein_compare(const void *p1, const void *p2) return l1 != l2 ? l1 - l2 : strcmp(s1, s2); } -static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old) +static int add_cmd_list(struct cmdnames *cmds, struct cmdnames *old) { - unsigned int i; - - ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc); - + unsigned int i, nr = cmds->cnt + old->cnt; + void *tmp; + + if (nr > cmds->alloc) { + /* Choose bigger one to alloc */ + if (alloc_nr(cmds->alloc) < nr) + cmds->alloc = nr; + else + cmds->alloc = alloc_nr(cmds->alloc); + tmp = realloc(cmds->names, cmds->alloc * sizeof(*cmds->names)); + if (!tmp) + return -1; + cmds->names = tmp; + } for (i = 0; i < old->cnt; i++) cmds->names[cmds->cnt++] = old->names[i]; zfree(&old->names); old->cnt = 0; + return 0; } const char *help_unknown_cmd(const char *cmd) @@ -52,8 +63,11 @@ const char *help_unknown_cmd(const char *cmd) load_command_list("perf-", &main_cmds, &other_cmds); - add_cmd_list(&main_cmds, &aliases); - add_cmd_list(&main_cmds, &other_cmds); + if (add_cmd_list(&main_cmds, &aliases) < 0 || + add_cmd_list(&main_cmds, &other_cmds) < 0) { + fprintf(stderr, "ERROR: Failed to allocate command list for unknown command.\n"); + goto end; + } qsort(main_cmds.names, main_cmds.cnt, sizeof(main_cmds.names), cmdname_compare); uniq(&main_cmds); @@ -99,6 +113,6 @@ const char *help_unknown_cmd(const char *cmd) for (i = 0; i < n; i++) fprintf(stderr, "\t%s\n", main_cmds.names[i]->name); } - +end: exit(1); } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 31c4641..cfab531 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -295,7 +295,7 @@ static void hists__delete_entry(struct hists *hists, struct hist_entry *he) root_in = &he->parent_he->hroot_in; root_out = &he->parent_he->hroot_out; } else { - if (sort__need_collapse) + if (hists__has(hists, need_collapse)) root_in = &hists->entries_collapsed; else root_in = hists->entries_in; @@ -953,7 +953,7 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, { int err, err2; - err = sample__resolve_callchain(iter->sample, &iter->parent, + err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent, iter->evsel, al, max_stack_depth); if (err) return err; @@ -1295,8 +1295,9 @@ static int hists__hierarchy_insert_entry(struct hists *hists, return ret; } -int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root, - struct hist_entry *he) +static int hists__collapse_insert_entry(struct hists *hists, + struct rb_root *root, + struct hist_entry *he) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -1372,7 +1373,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) struct hist_entry *n; int ret; - if (!sort__need_collapse) + if (!hists__has(hists, need_collapse)) return 0; hists->nr_entries = 0; @@ -1631,7 +1632,7 @@ static void output_resort(struct hists *hists, struct ui_progress *prog, return; } - if (sort__need_collapse) + if (hists__has(hists, need_collapse)) root = &hists->entries_collapsed; else root = hists->entries_in; @@ -2035,7 +2036,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, struct hist_entry *he; int64_t cmp; - if (sort__need_collapse) + if (hists__has(hists, need_collapse)) root = &hists->entries_collapsed; else root = hists->entries_in; @@ -2061,6 +2062,8 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, if (he) { memset(&he->stat, 0, sizeof(he->stat)); he->hists = hists; + if (symbol_conf.cumulate_callchain) + memset(he->stat_acc, 0, sizeof(he->stat)); rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, root); hists__inc_stats(hists, he); @@ -2075,7 +2078,7 @@ static struct hist_entry *hists__find_entry(struct hists *hists, { struct rb_node *n; - if (sort__need_collapse) + if (hists__has(hists, need_collapse)) n = hists->entries_collapsed.rb_node; else n = hists->entries_in->rb_node; @@ -2104,7 +2107,7 @@ void hists__match(struct hists *leader, struct hists *other) struct rb_node *nd; struct hist_entry *pos, *pair; - if (sort__need_collapse) + if (hists__has(leader, need_collapse)) root = &leader->entries_collapsed; else root = leader->entries_in; @@ -2129,7 +2132,7 @@ int hists__link(struct hists *leader, struct hists *other) struct rb_node *nd; struct hist_entry *pos, *pair; - if (sort__need_collapse) + if (hists__has(other, need_collapse)) root = &other->entries_collapsed; else root = other->entries_in; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index bec0cd6..0f84bfb 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -82,6 +82,8 @@ struct hists { int nr_hpp_node; }; +#define hists__has(__h, __f) (__h)->hpp_list->__f + struct hist_entry_iter; struct hist_iter_ops { @@ -199,8 +201,6 @@ int hists__init(void); int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list); struct rb_root *hists__get_rotate_entries_in(struct hists *hists); -int hists__collapse_insert_entry(struct hists *hists, - struct rb_root *root, struct hist_entry *he); struct perf_hpp { char *buf; @@ -240,6 +240,14 @@ struct perf_hpp_fmt { struct perf_hpp_list { struct list_head fields; struct list_head sorts; + + int need_collapse; + int parent; + int sym; + int dso; + int socket; + int thread; + int comm; }; extern struct perf_hpp_list perf_hpp_list; diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index abf1366..9df9960 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -66,6 +66,7 @@ struct intel_bts { u64 branches_id; size_t branches_event_size; bool synth_needs_swap; + unsigned long num_events; }; struct intel_bts_queue { @@ -275,6 +276,10 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq, union perf_event event; struct perf_sample sample = { .ip = 0, }; + if (bts->synth_opts.initial_skip && + bts->num_events++ <= bts->synth_opts.initial_skip) + return 0; + event.sample.header.type = PERF_RECORD_SAMPLE; event.sample.header.misc = PERF_RECORD_MISC_USER; event.sample.header.size = sizeof(struct perf_event_header); diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 9409d01..9c8f15d 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -356,7 +356,7 @@ static const char *intel_pt_err_msgs[] = { int intel_pt__strerror(int code, char *buf, size_t buflen) { - if (code < 1 || code > INTEL_PT_ERR_MAX) + if (code < 1 || code >= INTEL_PT_ERR_MAX) code = INTEL_PT_ERR_UNK; strlcpy(buf, intel_pt_err_msgs[code], buflen); return 0; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 6175784..1371969 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -100,6 +100,8 @@ struct intel_pt { u64 cyc_bit; u64 noretcomp_bit; unsigned max_non_turbo_ratio; + + unsigned long num_events; }; enum switch_state { @@ -972,6 +974,10 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) if (pt->branches_filter && !(pt->branches_filter & ptq->flags)) return 0; + if (pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip) + return 0; + event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = PERF_RECORD_MISC_USER; event->sample.header.size = sizeof(struct perf_event_header); @@ -1029,6 +1035,10 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; + if (pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip) + return 0; + event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = PERF_RECORD_MISC_USER; event->sample.header.size = sizeof(struct perf_event_header); @@ -1087,6 +1097,10 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; + if (pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip) + return 0; + event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = PERF_RECORD_MISC_USER; event->sample.header.size = sizeof(struct perf_event_header); @@ -1199,14 +1213,18 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) ptq->have_sample = false; if (pt->sample_instructions && - (state->type & INTEL_PT_INSTRUCTION)) { + (state->type & INTEL_PT_INSTRUCTION) && + (!pt->synth_opts.initial_skip || + pt->num_events++ >= pt->synth_opts.initial_skip)) { err = intel_pt_synth_instruction_sample(ptq); if (err) return err; } if (pt->sample_transactions && - (state->type & INTEL_PT_TRANSACTION)) { + (state->type & INTEL_PT_TRANSACTION) && + (!pt->synth_opts.initial_skip || + pt->num_events++ >= pt->synth_opts.initial_skip)) { err = intel_pt_synth_transaction_sample(ptq); if (err) return err; diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index ad0c0bb..86afe96 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -17,6 +17,7 @@ #include "strlist.h" #include <elf.h> +#include "tsc.h" #include "session.h" #include "jit.h" #include "jitdump.h" @@ -33,6 +34,7 @@ struct jit_buf_desc { size_t bufsize; FILE *in; bool needs_bswap; /* handles cross-endianess */ + bool use_arch_timestamp; void *debug_data; size_t nr_debug_entries; uint32_t code_load_count; @@ -158,13 +160,16 @@ jit_open(struct jit_buf_desc *jd, const char *name) header.flags = bswap_64(header.flags); } + jd->use_arch_timestamp = header.flags & JITDUMP_FLAGS_ARCH_TIMESTAMP; + if (verbose > 2) - pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\n", + pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\nuse_arch_timestamp=%d\n", header.version, header.total_size, (unsigned long long)header.timestamp, header.pid, - header.elf_mach); + header.elf_mach, + jd->use_arch_timestamp); if (header.flags & JITDUMP_FLAGS_RESERVED) { pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n", @@ -172,10 +177,15 @@ jit_open(struct jit_buf_desc *jd, const char *name) goto error; } + if (jd->use_arch_timestamp && !jd->session->time_conv.time_mult) { + pr_err("jitdump file uses arch timestamps but there is no timestamp conversion\n"); + goto error; + } + /* * validate event is using the correct clockid */ - if (jit_validate_events(jd->session)) { + if (!jd->use_arch_timestamp && jit_validate_events(jd->session)) { pr_err("error, jitted code must be sampled with perf record -k 1\n"); goto error; } @@ -329,6 +339,23 @@ jit_inject_event(struct jit_buf_desc *jd, union perf_event *event) return 0; } +static uint64_t convert_timestamp(struct jit_buf_desc *jd, uint64_t timestamp) +{ + struct perf_tsc_conversion tc; + + if (!jd->use_arch_timestamp) + return timestamp; + + tc.time_shift = jd->session->time_conv.time_shift; + tc.time_mult = jd->session->time_conv.time_mult; + tc.time_zero = jd->session->time_conv.time_zero; + + if (!tc.time_mult) + return 0; + + return tsc_to_perf_time(timestamp, &tc); +} + static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) { struct perf_sample sample; @@ -385,7 +412,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) return -1; } if (stat(filename, &st)) - memset(&st, 0, sizeof(stat)); + memset(&st, 0, sizeof(st)); event->mmap2.header.type = PERF_RECORD_MMAP2; event->mmap2.header.misc = PERF_RECORD_MISC_USER; @@ -410,7 +437,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) id->tid = tid; } if (jd->sample_type & PERF_SAMPLE_TIME) - id->time = jr->load.p.timestamp; + id->time = convert_timestamp(jd, jr->load.p.timestamp); /* * create pseudo sample to induce dso hit increment @@ -473,7 +500,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) size++; /* for \0 */ if (stat(filename, &st)) - memset(&st, 0, sizeof(stat)); + memset(&st, 0, sizeof(st)); size = PERF_ALIGN(size, sizeof(u64)); @@ -499,7 +526,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) id->tid = tid; } if (jd->sample_type & PERF_SAMPLE_TIME) - id->time = jr->load.p.timestamp; + id->time = convert_timestamp(jd, jr->load.p.timestamp); /* * create pseudo sample to induce dso hit increment diff --git a/tools/perf/util/jitdump.h b/tools/perf/util/jitdump.h index b66c1f5..bcacd20 100644 --- a/tools/perf/util/jitdump.h +++ b/tools/perf/util/jitdump.h @@ -23,9 +23,12 @@ #define JITHEADER_VERSION 1 enum jitdump_flags_bits { + JITDUMP_FLAGS_ARCH_TIMESTAMP_BIT, JITDUMP_FLAGS_MAX_BIT, }; +#define JITDUMP_FLAGS_ARCH_TIMESTAMP (1ULL << JITDUMP_FLAGS_ARCH_TIMESTAMP_BIT) + #define JITDUMP_FLAGS_RESERVED (JITDUMP_FLAGS_MAX_BIT < 64 ? \ (~((1ULL << JITDUMP_FLAGS_MAX_BIT) - 1)) : 0) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 80b9b6a..639a290 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -32,6 +32,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->threads = RB_ROOT; pthread_rwlock_init(&machine->threads_lock, NULL); + machine->nr_threads = 0; INIT_LIST_HEAD(&machine->dead_threads); machine->last_match = NULL; @@ -430,6 +431,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, */ thread__get(th); machine->last_match = th; + ++machine->nr_threads; } return th; @@ -681,11 +683,13 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) size_t machine__fprintf(struct machine *machine, FILE *fp) { - size_t ret = 0; + size_t ret; struct rb_node *nd; pthread_rwlock_rdlock(&machine->threads_lock); + ret = fprintf(fp, "Threads: %u\n", machine->nr_threads); + for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { struct thread *pos = rb_entry(nd, struct thread, rb_node); @@ -908,11 +912,11 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid) return machine__create_kernel_maps(machine); } -int machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type, symbol_filter_t filter) +int __machine__load_kallsyms(struct machine *machine, const char *filename, + enum map_type type, bool no_kcore, symbol_filter_t filter) { struct map *map = machine__kernel_map(machine); - int ret = dso__load_kallsyms(map->dso, filename, map, filter); + int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore, filter); if (ret > 0) { dso__set_loaded(map->dso, type); @@ -927,6 +931,12 @@ int machine__load_kallsyms(struct machine *machine, const char *filename, return ret; } +int machine__load_kallsyms(struct machine *machine, const char *filename, + enum map_type type, symbol_filter_t filter) +{ + return __machine__load_kallsyms(machine, filename, type, false, filter); +} + int machine__load_vmlinux_path(struct machine *machine, enum map_type type, symbol_filter_t filter) { @@ -1413,6 +1423,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th, pthread_rwlock_wrlock(&machine->threads_lock); rb_erase_init(&th->rb_node, &machine->threads); RB_CLEAR_NODE(&th->rb_node); + --machine->nr_threads; /* * Move it first to the dead_threads list, then drop the reference, * if this is the last reference, then the thread__delete destructor @@ -1599,6 +1610,7 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, } static int add_callchain_ip(struct thread *thread, + struct callchain_cursor *cursor, struct symbol **parent, struct addr_location *root_al, u8 *cpumode, @@ -1630,7 +1642,7 @@ static int add_callchain_ip(struct thread *thread, * It seems the callchain is corrupted. * Discard all. */ - callchain_cursor_reset(&callchain_cursor); + callchain_cursor_reset(cursor); return 1; } return 0; @@ -1640,7 +1652,7 @@ static int add_callchain_ip(struct thread *thread, } if (al.sym != NULL) { - if (sort__has_parent && !*parent && + if (perf_hpp_list.parent && !*parent && symbol__match_regex(al.sym, &parent_regex)) *parent = al.sym; else if (have_ignore_callees && root_al && @@ -1648,13 +1660,13 @@ static int add_callchain_ip(struct thread *thread, /* Treat this symbol as the root, forgetting its callees. */ *root_al = al; - callchain_cursor_reset(&callchain_cursor); + callchain_cursor_reset(cursor); } } if (symbol_conf.hide_unresolved && al.sym == NULL) return 0; - return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym); + return callchain_cursor_append(cursor, al.addr, al.map, al.sym); } struct branch_info *sample__resolve_bstack(struct perf_sample *sample, @@ -1724,6 +1736,7 @@ static int remove_loops(struct branch_entry *l, int nr) * negative error code on other errors. */ static int resolve_lbr_callchain_sample(struct thread *thread, + struct callchain_cursor *cursor, struct perf_sample *sample, struct symbol **parent, struct addr_location *root_al, @@ -1756,7 +1769,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, */ int mix_chain_nr = i + 1 + lbr_nr + 1; - if (mix_chain_nr > PERF_MAX_STACK_DEPTH + PERF_MAX_BRANCH_DEPTH) { + if (mix_chain_nr > (int)sysctl_perf_event_max_stack + PERF_MAX_BRANCH_DEPTH) { pr_warning("corrupted callchain. skipping...\n"); return 0; } @@ -1778,7 +1791,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, ip = lbr_stack->entries[0].to; } - err = add_callchain_ip(thread, parent, root_al, &cpumode, ip); + err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip); if (err) return (err < 0) ? err : 0; } @@ -1789,6 +1802,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, } static int thread__resolve_callchain_sample(struct thread *thread, + struct callchain_cursor *cursor, struct perf_evsel *evsel, struct perf_sample *sample, struct symbol **parent, @@ -1803,10 +1817,8 @@ static int thread__resolve_callchain_sample(struct thread *thread, int skip_idx = -1; int first_call = 0; - callchain_cursor_reset(&callchain_cursor); - - if (has_branch_callstack(evsel)) { - err = resolve_lbr_callchain_sample(thread, sample, parent, + if (perf_evsel__has_branch_callstack(evsel)) { + err = resolve_lbr_callchain_sample(thread, cursor, sample, parent, root_al, max_stack); if (err) return (err < 0) ? err : 0; @@ -1816,7 +1828,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, * Based on DWARF debug information, some architectures skip * a callchain entry saved by the kernel. */ - if (chain->nr < PERF_MAX_STACK_DEPTH) + if (chain->nr < sysctl_perf_event_max_stack) skip_idx = arch_skip_callchain_idx(thread, chain); /* @@ -1863,10 +1875,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, nr = remove_loops(be, nr); for (i = 0; i < nr; i++) { - err = add_callchain_ip(thread, parent, root_al, + err = add_callchain_ip(thread, cursor, parent, root_al, NULL, be[i].to); if (!err) - err = add_callchain_ip(thread, parent, root_al, + err = add_callchain_ip(thread, cursor, parent, root_al, NULL, be[i].from); if (err == -EINVAL) break; @@ -1877,7 +1889,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, } check_calls: - if (chain->nr > PERF_MAX_STACK_DEPTH && (int)chain->nr > max_stack) { + if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) { pr_warning("corrupted callchain. skipping...\n"); return 0; } @@ -1896,7 +1908,7 @@ check_calls: #endif ip = chain->ips[j]; - err = add_callchain_ip(thread, parent, root_al, &cpumode, ip); + err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip); if (err) return (err < 0) ? err : 0; @@ -1915,19 +1927,12 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) entry->map, entry->sym); } -int thread__resolve_callchain(struct thread *thread, - struct perf_evsel *evsel, - struct perf_sample *sample, - struct symbol **parent, - struct addr_location *root_al, - int max_stack) +static int thread__resolve_callchain_unwind(struct thread *thread, + struct callchain_cursor *cursor, + struct perf_evsel *evsel, + struct perf_sample *sample, + int max_stack) { - int ret = thread__resolve_callchain_sample(thread, evsel, - sample, parent, - root_al, max_stack); - if (ret) - return ret; - /* Can we do dwarf post unwind? */ if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) && (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER))) @@ -1938,9 +1943,45 @@ int thread__resolve_callchain(struct thread *thread, (!sample->user_stack.size)) return 0; - return unwind__get_entries(unwind_entry, &callchain_cursor, + return unwind__get_entries(unwind_entry, cursor, thread, sample, max_stack); +} + +int thread__resolve_callchain(struct thread *thread, + struct callchain_cursor *cursor, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct symbol **parent, + struct addr_location *root_al, + int max_stack) +{ + int ret = 0; + + callchain_cursor_reset(&callchain_cursor); + if (callchain_param.order == ORDER_CALLEE) { + ret = thread__resolve_callchain_sample(thread, cursor, + evsel, sample, + parent, root_al, + max_stack); + if (ret) + return ret; + ret = thread__resolve_callchain_unwind(thread, cursor, + evsel, sample, + max_stack); + } else { + ret = thread__resolve_callchain_unwind(thread, cursor, + evsel, sample, + max_stack); + if (ret) + return ret; + ret = thread__resolve_callchain_sample(thread, cursor, + evsel, sample, + parent, root_al, + max_stack); + } + + return ret; } int machine__for_each_thread(struct machine *machine, diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 8499db2..83f4679 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -31,6 +31,7 @@ struct machine { char *root_dir; struct rb_root threads; pthread_rwlock_t threads_lock; + unsigned int nr_threads; struct list_head dead_threads; struct thread *last_match; struct vdso_info *vdso_info; @@ -141,7 +142,11 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample, struct addr_location *al); struct mem_info *sample__resolve_mem(struct perf_sample *sample, struct addr_location *al); + +struct callchain_cursor; + int thread__resolve_callchain(struct thread *thread, + struct callchain_cursor *cursor, struct perf_evsel *evsel, struct perf_sample *sample, struct symbol **parent, @@ -211,6 +216,8 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine, struct map *machine__findnew_module_map(struct machine *machine, u64 start, const char *filename); +int __machine__load_kallsyms(struct machine *machine, const char *filename, + enum map_type type, bool no_kcore, symbol_filter_t filter); int machine__load_kallsyms(struct machine *machine, const char *filename, enum map_type type, symbol_filter_t filter); int machine__load_vmlinux_path(struct machine *machine, enum map_type type, diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 171b6d1..b19bcd3 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -289,7 +289,7 @@ int map__load(struct map *map, symbol_filter_t filter) nr = dso__load(map->dso, map, filter); if (nr < 0) { if (map->dso->has_build_id) { - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + char sbuild_id[SBUILD_ID_SIZE]; build_id__sprintf(map->dso->build_id, sizeof(map->dso->build_id), @@ -431,6 +431,13 @@ u64 map__rip_2objdump(struct map *map, u64 rip) if (map->dso->rel) return rip - map->pgoff; + /* + * kernel modules also have DSO_TYPE_USER in dso->kernel, + * but all kernel modules are ET_REL, so won't get here. + */ + if (map->dso->kernel == DSO_TYPE_USER) + return rip + map->dso->text_offset; + return map->unmap_ip(map, rip) - map->reloc; } @@ -454,6 +461,13 @@ u64 map__objdump_2mem(struct map *map, u64 ip) if (map->dso->rel) return map->unmap_ip(map, ip + map->pgoff); + /* + * kernel modules also have DSO_TYPE_USER in dso->kernel, + * but all kernel modules are ET_REL, so won't get here. + */ + if (map->dso->kernel == DSO_TYPE_USER) + return map->unmap_ip(map, ip - map->dso->text_offset); + return ip + map->reloc; } diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index b1b9e23..fe84df1 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -308,3 +308,12 @@ void ordered_events__free(struct ordered_events *oe) free(event); } } + +void ordered_events__reinit(struct ordered_events *oe) +{ + ordered_events__deliver_t old_deliver = oe->deliver; + + ordered_events__free(oe); + memset(oe, '\0', sizeof(*oe)); + ordered_events__init(oe, old_deliver); +} diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h index f403991..e11468a 100644 --- a/tools/perf/util/ordered-events.h +++ b/tools/perf/util/ordered-events.h @@ -49,6 +49,7 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve int ordered_events__flush(struct ordered_events *oe, enum oe_flush how); void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t deliver); void ordered_events__free(struct ordered_events *oe); +void ordered_events__reinit(struct ordered_events *oe); static inline void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4c19d5e..bcbc983 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -138,11 +138,11 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { #define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE) #define PERF_EVENT_ID(config) __PERF_EVENT_FIELD(config, EVENT) -#define for_each_subsystem(sys_dir, sys_dirent, sys_next) \ - while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next) \ - if (sys_dirent.d_type == DT_DIR && \ - (strcmp(sys_dirent.d_name, ".")) && \ - (strcmp(sys_dirent.d_name, ".."))) +#define for_each_subsystem(sys_dir, sys_dirent) \ + while ((sys_dirent = readdir(sys_dir)) != NULL) \ + if (sys_dirent->d_type == DT_DIR && \ + (strcmp(sys_dirent->d_name, ".")) && \ + (strcmp(sys_dirent->d_name, ".."))) static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) { @@ -159,12 +159,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) return 0; } -#define for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) \ - while (!readdir_r(evt_dir, &evt_dirent, &evt_next) && evt_next) \ - if (evt_dirent.d_type == DT_DIR && \ - (strcmp(evt_dirent.d_name, ".")) && \ - (strcmp(evt_dirent.d_name, "..")) && \ - (!tp_event_has_id(&sys_dirent, &evt_dirent))) +#define for_each_event(sys_dirent, evt_dir, evt_dirent) \ + while ((evt_dirent = readdir(evt_dir)) != NULL) \ + if (evt_dirent->d_type == DT_DIR && \ + (strcmp(evt_dirent->d_name, ".")) && \ + (strcmp(evt_dirent->d_name, "..")) && \ + (!tp_event_has_id(sys_dirent, evt_dirent))) #define MAX_EVENT_LENGTH 512 @@ -173,7 +173,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) { struct tracepoint_path *path = NULL; DIR *sys_dir, *evt_dir; - struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; + struct dirent *sys_dirent, *evt_dirent; char id_buf[24]; int fd; u64 id; @@ -184,18 +184,18 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) if (!sys_dir) return NULL; - for_each_subsystem(sys_dir, sys_dirent, sys_next) { + for_each_subsystem(sys_dir, sys_dirent) { snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent.d_name); + sys_dirent->d_name); evt_dir = opendir(dir_path); if (!evt_dir) continue; - for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + for_each_event(sys_dirent, evt_dir, evt_dirent) { snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, - evt_dirent.d_name); + evt_dirent->d_name); fd = open(evt_path, O_RDONLY); if (fd < 0) continue; @@ -220,9 +220,9 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) free(path); return NULL; } - strncpy(path->system, sys_dirent.d_name, + strncpy(path->system, sys_dirent->d_name, MAX_EVENT_LENGTH); - strncpy(path->name, evt_dirent.d_name, + strncpy(path->name, evt_dirent->d_name, MAX_EVENT_LENGTH); return path; } @@ -1812,7 +1812,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, bool name_only) { DIR *sys_dir, *evt_dir; - struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; + struct dirent *sys_dirent, *evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; char **evt_list = NULL; @@ -1830,20 +1830,20 @@ restart: goto out_close_sys_dir; } - for_each_subsystem(sys_dir, sys_dirent, sys_next) { + for_each_subsystem(sys_dir, sys_dirent) { if (subsys_glob != NULL && - !strglobmatch(sys_dirent.d_name, subsys_glob)) + !strglobmatch(sys_dirent->d_name, subsys_glob)) continue; snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent.d_name); + sys_dirent->d_name); evt_dir = opendir(dir_path); if (!evt_dir) continue; - for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + for_each_event(sys_dirent, evt_dir, evt_dirent) { if (event_glob != NULL && - !strglobmatch(evt_dirent.d_name, event_glob)) + !strglobmatch(evt_dirent->d_name, event_glob)) continue; if (!evt_num_known) { @@ -1852,7 +1852,7 @@ restart: } snprintf(evt_path, MAXPATHLEN, "%s:%s", - sys_dirent.d_name, evt_dirent.d_name); + sys_dirent->d_name, evt_dirent->d_name); evt_list[evt_i] = strdup(evt_path); if (evt_list[evt_i] == NULL) @@ -1905,7 +1905,7 @@ out_close_sys_dir: int is_valid_tracepoint(const char *event_string) { DIR *sys_dir, *evt_dir; - struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; + struct dirent *sys_dirent, *evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; @@ -1913,17 +1913,17 @@ int is_valid_tracepoint(const char *event_string) if (!sys_dir) return 0; - for_each_subsystem(sys_dir, sys_dirent, sys_next) { + for_each_subsystem(sys_dir, sys_dirent) { snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent.d_name); + sys_dirent->d_name); evt_dir = opendir(dir_path); if (!evt_dir) continue; - for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + for_each_event(sys_dirent, evt_dir, evt_dirent) { snprintf(evt_path, MAXPATHLEN, "%s:%s", - sys_dirent.d_name, evt_dirent.d_name); + sys_dirent->d_name, evt_dirent->d_name); if (!strcmp(evt_path, event_string)) { closedir(evt_dir); closedir(sys_dir); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index adef23b..ddb0261 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -602,14 +602,13 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v, static __u64 pmu_format_max_value(const unsigned long *format) { - int w; + __u64 w = 0; + int fbit; - w = bitmap_weight(format, PERF_PMU_FORMAT_BITS); - if (!w) - return 0; - if (w < 64) - return (1ULL << w) - 1; - return -1; + for_each_set_bit(fbit, format, PERF_PMU_FORMAT_BITS) + w |= (1ULL << fbit); + + return w; } /* @@ -644,20 +643,20 @@ static int pmu_resolve_param_term(struct parse_events_term *term, static char *pmu_formats_string(struct list_head *formats) { struct perf_pmu_format *format; - char *str; - struct strbuf buf; + char *str = NULL; + struct strbuf buf = STRBUF_INIT; unsigned i = 0; if (!formats) return NULL; - strbuf_init(&buf, 0); /* sysfs exported terms */ list_for_each_entry(format, formats, list) - strbuf_addf(&buf, i++ ? ",%s" : "%s", - format->name); + if (strbuf_addf(&buf, i++ ? ",%s" : "%s", format->name) < 0) + goto error; str = strbuf_detach(&buf, NULL); +error: strbuf_release(&buf); return str; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 8319fbb..74401a2 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -265,6 +265,65 @@ static bool kprobe_warn_out_range(const char *symbol, unsigned long address) return true; } +/* + * NOTE: + * '.gnu.linkonce.this_module' section of kernel module elf directly + * maps to 'struct module' from linux/module.h. This section contains + * actual module name which will be used by kernel after loading it. + * But, we cannot use 'struct module' here since linux/module.h is not + * exposed to user-space. Offset of 'name' has remained same from long + * time, so hardcoding it here. + */ +#ifdef __LP64__ +#define MOD_NAME_OFFSET 24 +#else +#define MOD_NAME_OFFSET 12 +#endif + +/* + * @module can be module name of module file path. In case of path, + * inspect elf and find out what is actual module name. + * Caller has to free mod_name after using it. + */ +static char *find_module_name(const char *module) +{ + int fd; + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *data; + Elf_Scn *sec; + char *mod_name = NULL; + + fd = open(module, O_RDONLY); + if (fd < 0) + return NULL; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + goto elf_err; + + if (gelf_getehdr(elf, &ehdr) == NULL) + goto ret_err; + + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".gnu.linkonce.this_module", NULL); + if (!sec) + goto ret_err; + + data = elf_getdata(sec, NULL); + if (!data || !data->d_buf) + goto ret_err; + + mod_name = strdup((char *)data->d_buf + MOD_NAME_OFFSET); + +ret_err: + elf_end(elf); +elf_err: + close(fd); + return mod_name; +} + #ifdef HAVE_DWARF_SUPPORT static int kernel_get_module_dso(const char *module, struct dso **pdso) @@ -486,8 +545,10 @@ static int get_text_start_address(const char *exec, unsigned long *address) return -errno; elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); - if (elf == NULL) - return -EINVAL; + if (elf == NULL) { + ret = -EINVAL; + goto out_close; + } if (gelf_getehdr(elf, &ehdr) == NULL) goto out; @@ -499,6 +560,9 @@ static int get_text_start_address(const char *exec, unsigned long *address) ret = 0; out: elf_end(elf); +out_close: + close(fd); + return ret; } @@ -583,32 +647,23 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs, int ntevs, const char *module) { int i, ret = 0; - char *tmp; + char *mod_name = NULL; if (!module) return 0; - tmp = strrchr(module, '/'); - if (tmp) { - /* This is a module path -- get the module name */ - module = strdup(tmp + 1); - if (!module) - return -ENOMEM; - tmp = strchr(module, '.'); - if (tmp) - *tmp = '\0'; - tmp = (char *)module; /* For free() */ - } + mod_name = find_module_name(module); for (i = 0; i < ntevs; i++) { - tevs[i].point.module = strdup(module); + tevs[i].point.module = + strdup(mod_name ? mod_name : module); if (!tevs[i].point.module) { ret = -ENOMEM; break; } } - free(tmp); + free(mod_name); return ret; } @@ -1618,69 +1673,65 @@ out: } /* Compose only probe arg */ -int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len) +char *synthesize_perf_probe_arg(struct perf_probe_arg *pa) { struct perf_probe_arg_field *field = pa->field; - int ret; - char *tmp = buf; + struct strbuf buf; + char *ret = NULL; + int err; + + if (strbuf_init(&buf, 64) < 0) + return NULL; if (pa->name && pa->var) - ret = e_snprintf(tmp, len, "%s=%s", pa->name, pa->var); + err = strbuf_addf(&buf, "%s=%s", pa->name, pa->var); else - ret = e_snprintf(tmp, len, "%s", pa->name ? pa->name : pa->var); - if (ret <= 0) - goto error; - tmp += ret; - len -= ret; + err = strbuf_addstr(&buf, pa->name ?: pa->var); + if (err) + goto out; while (field) { if (field->name[0] == '[') - ret = e_snprintf(tmp, len, "%s", field->name); + err = strbuf_addstr(&buf, field->name); else - ret = e_snprintf(tmp, len, "%s%s", - field->ref ? "->" : ".", field->name); - if (ret <= 0) - goto error; - tmp += ret; - len -= ret; + err = strbuf_addf(&buf, "%s%s", field->ref ? "->" : ".", + field->name); field = field->next; + if (err) + goto out; } - if (pa->type) { - ret = e_snprintf(tmp, len, ":%s", pa->type); - if (ret <= 0) - goto error; - tmp += ret; - len -= ret; - } + if (pa->type) + if (strbuf_addf(&buf, ":%s", pa->type) < 0) + goto out; - return tmp - buf; -error: - pr_debug("Failed to synthesize perf probe argument: %d\n", ret); + ret = strbuf_detach(&buf, NULL); +out: + strbuf_release(&buf); return ret; } /* Compose only probe point (not argument) */ static char *synthesize_perf_probe_point(struct perf_probe_point *pp) { - char *buf, *tmp; - char offs[32] = "", line[32] = "", file[32] = ""; - int ret, len; + struct strbuf buf; + char *tmp, *ret = NULL; + int len, err = 0; - buf = zalloc(MAX_CMDLEN); - if (buf == NULL) { - ret = -ENOMEM; - goto error; - } - if (pp->offset) { - ret = e_snprintf(offs, 32, "+%lu", pp->offset); - if (ret <= 0) - goto error; - } - if (pp->line) { - ret = e_snprintf(line, 32, ":%d", pp->line); - if (ret <= 0) - goto error; + if (strbuf_init(&buf, 64) < 0) + return NULL; + + if (pp->function) { + if (strbuf_addstr(&buf, pp->function) < 0) + goto out; + if (pp->offset) + err = strbuf_addf(&buf, "+%lu", pp->offset); + else if (pp->line) + err = strbuf_addf(&buf, ":%d", pp->line); + else if (pp->retprobe) + err = strbuf_addstr(&buf, "%return"); + if (err) + goto out; } if (pp->file) { tmp = pp->file; @@ -1689,25 +1740,15 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp) tmp = strchr(pp->file + len - 30, '/'); tmp = tmp ? tmp + 1 : pp->file + len - 30; } - ret = e_snprintf(file, 32, "@%s", tmp); - if (ret <= 0) - goto error; + err = strbuf_addf(&buf, "@%s", tmp); + if (!err && !pp->function && pp->line) + err = strbuf_addf(&buf, ":%d", pp->line); } - - if (pp->function) - ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s%s", pp->function, - offs, pp->retprobe ? "%return" : "", line, - file); - else - ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", file, line); - if (ret <= 0) - goto error; - - return buf; -error: - pr_debug("Failed to synthesize perf probe point: %d\n", ret); - free(buf); - return NULL; + if (!err) + ret = strbuf_detach(&buf, NULL); +out: + strbuf_release(&buf); + return ret; } #if 0 @@ -1736,45 +1777,32 @@ char *synthesize_perf_probe_command(struct perf_probe_event *pev) #endif static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref, - char **buf, size_t *buflen, - int depth) + struct strbuf *buf, int depth) { - int ret; + int err; if (ref->next) { depth = __synthesize_probe_trace_arg_ref(ref->next, buf, - buflen, depth + 1); + depth + 1); if (depth < 0) - goto out; - } - - ret = e_snprintf(*buf, *buflen, "%+ld(", ref->offset); - if (ret < 0) - depth = ret; - else { - *buf += ret; - *buflen -= ret; + return depth; } -out: - return depth; - + err = strbuf_addf(buf, "%+ld(", ref->offset); + return (err < 0) ? err : depth; } static int synthesize_probe_trace_arg(struct probe_trace_arg *arg, - char *buf, size_t buflen) + struct strbuf *buf) { struct probe_trace_arg_ref *ref = arg->ref; - int ret, depth = 0; - char *tmp = buf; + int depth = 0, err; /* Argument name or separator */ if (arg->name) - ret = e_snprintf(buf, buflen, " %s=", arg->name); + err = strbuf_addf(buf, " %s=", arg->name); else - ret = e_snprintf(buf, buflen, " "); - if (ret < 0) - return ret; - buf += ret; - buflen -= ret; + err = strbuf_addch(buf, ' '); + if (err) + return err; /* Special case: @XXX */ if (arg->value[0] == '@' && arg->ref) @@ -1782,59 +1810,44 @@ static int synthesize_probe_trace_arg(struct probe_trace_arg *arg, /* Dereferencing arguments */ if (ref) { - depth = __synthesize_probe_trace_arg_ref(ref, &buf, - &buflen, 1); + depth = __synthesize_probe_trace_arg_ref(ref, buf, 1); if (depth < 0) return depth; } /* Print argument value */ if (arg->value[0] == '@' && arg->ref) - ret = e_snprintf(buf, buflen, "%s%+ld", arg->value, - arg->ref->offset); + err = strbuf_addf(buf, "%s%+ld", arg->value, arg->ref->offset); else - ret = e_snprintf(buf, buflen, "%s", arg->value); - if (ret < 0) - return ret; - buf += ret; - buflen -= ret; + err = strbuf_addstr(buf, arg->value); /* Closing */ - while (depth--) { - ret = e_snprintf(buf, buflen, ")"); - if (ret < 0) - return ret; - buf += ret; - buflen -= ret; - } + while (!err && depth--) + err = strbuf_addch(buf, ')'); + /* Print argument type */ - if (arg->type) { - ret = e_snprintf(buf, buflen, ":%s", arg->type); - if (ret <= 0) - return ret; - buf += ret; - } + if (!err && arg->type) + err = strbuf_addf(buf, ":%s", arg->type); - return buf - tmp; + return err; } char *synthesize_probe_trace_command(struct probe_trace_event *tev) { struct probe_trace_point *tp = &tev->point; - char *buf; - int i, len, ret; + struct strbuf buf; + char *ret = NULL; + int i, err; - buf = zalloc(MAX_CMDLEN); - if (buf == NULL) + /* Uprobes must have tp->module */ + if (tev->uprobes && !tp->module) return NULL; - len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s ", tp->retprobe ? 'r' : 'p', - tev->group, tev->event); - if (len <= 0) - goto error; + if (strbuf_init(&buf, 32) < 0) + return NULL; - /* Uprobes must have tp->module */ - if (tev->uprobes && !tp->module) + if (strbuf_addf(&buf, "%c:%s/%s ", tp->retprobe ? 'r' : 'p', + tev->group, tev->event) < 0) goto error; /* * If tp->address == 0, then this point must be a @@ -1849,34 +1862,25 @@ char *synthesize_probe_trace_command(struct probe_trace_event *tev) /* Use the tp->address for uprobes */ if (tev->uprobes) - ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s:0x%lx", - tp->module, tp->address); + err = strbuf_addf(&buf, "%s:0x%lx", tp->module, tp->address); else if (!strncmp(tp->symbol, "0x", 2)) /* Absolute address. See try_to_find_absolute_address() */ - ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s0x%lx", - tp->module ?: "", tp->module ? ":" : "", - tp->address); + err = strbuf_addf(&buf, "%s%s0x%lx", tp->module ?: "", + tp->module ? ":" : "", tp->address); else - ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s%s+%lu", - tp->module ?: "", tp->module ? ":" : "", - tp->symbol, tp->offset); - - if (ret <= 0) + err = strbuf_addf(&buf, "%s%s%s+%lu", tp->module ?: "", + tp->module ? ":" : "", tp->symbol, tp->offset); + if (err) goto error; - len += ret; - for (i = 0; i < tev->nargs; i++) { - ret = synthesize_probe_trace_arg(&tev->args[i], buf + len, - MAX_CMDLEN - len); - if (ret <= 0) + for (i = 0; i < tev->nargs; i++) + if (synthesize_probe_trace_arg(&tev->args[i], &buf) < 0) goto error; - len += ret; - } - return buf; + ret = strbuf_detach(&buf, NULL); error: - free(buf); - return NULL; + strbuf_release(&buf); + return ret; } static int find_perf_probe_point_from_map(struct probe_trace_point *tp, @@ -1958,7 +1962,7 @@ static int convert_to_perf_probe_point(struct probe_trace_point *tp, static int convert_to_perf_probe_event(struct probe_trace_event *tev, struct perf_probe_event *pev, bool is_kprobe) { - char buf[64] = ""; + struct strbuf buf = STRBUF_INIT; int i, ret; /* Convert event/group name */ @@ -1981,14 +1985,15 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev, if (tev->args[i].name) pev->args[i].name = strdup(tev->args[i].name); else { - ret = synthesize_probe_trace_arg(&tev->args[i], - buf, 64); - pev->args[i].name = strdup(buf); + if ((ret = strbuf_init(&buf, 32)) < 0) + goto error; + ret = synthesize_probe_trace_arg(&tev->args[i], &buf); + pev->args[i].name = strbuf_detach(&buf, NULL); } if (pev->args[i].name == NULL && ret >= 0) ret = -ENOMEM; } - +error: if (ret < 0) clear_perf_probe_event(pev); @@ -2162,35 +2167,38 @@ static int perf_probe_event__sprintf(const char *group, const char *event, struct strbuf *result) { int i, ret; - char buf[128]; - char *place; + char *buf; - /* Synthesize only event probe point */ - place = synthesize_perf_probe_point(&pev->point); - if (!place) - return -EINVAL; + if (asprintf(&buf, "%s:%s", group, event) < 0) + return -errno; + ret = strbuf_addf(result, " %-20s (on ", buf); + free(buf); + if (ret) + return ret; - ret = e_snprintf(buf, 128, "%s:%s", group, event); - if (ret < 0) - goto out; + /* Synthesize only event probe point */ + buf = synthesize_perf_probe_point(&pev->point); + if (!buf) + return -ENOMEM; + ret = strbuf_addstr(result, buf); + free(buf); - strbuf_addf(result, " %-20s (on %s", buf, place); - if (module) - strbuf_addf(result, " in %s", module); + if (!ret && module) + ret = strbuf_addf(result, " in %s", module); - if (pev->nargs > 0) { - strbuf_add(result, " with", 5); - for (i = 0; i < pev->nargs; i++) { - ret = synthesize_perf_probe_arg(&pev->args[i], - buf, 128); - if (ret < 0) - goto out; - strbuf_addf(result, " %s", buf); + if (!ret && pev->nargs > 0) { + ret = strbuf_add(result, " with", 5); + for (i = 0; !ret && i < pev->nargs; i++) { + buf = synthesize_perf_probe_arg(&pev->args[i]); + if (!buf) + return -ENOMEM; + ret = strbuf_addf(result, " %s", buf); + free(buf); } } - strbuf_addch(result, ')'); -out: - free(place); + if (!ret) + ret = strbuf_addch(result, ')'); + return ret; } @@ -2498,7 +2506,8 @@ static int find_probe_functions(struct map *map, char *name, void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused, struct probe_trace_event *tev __maybe_unused, - struct map *map __maybe_unused) { } + struct map *map __maybe_unused, + struct symbol *sym __maybe_unused) { } /* * Find probe function addresses from map. @@ -2516,6 +2525,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, struct probe_trace_point *tp; int num_matched_functions; int ret, i, j, skipped = 0; + char *mod_name; map = get_target_map(pev->target, pev->uprobes); if (!map) { @@ -2600,9 +2610,19 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, tp->realname = strdup_or_goto(sym->name, nomem_out); tp->retprobe = pp->retprobe; - if (pev->target) - tev->point.module = strdup_or_goto(pev->target, - nomem_out); + if (pev->target) { + if (pev->uprobes) { + tev->point.module = strdup_or_goto(pev->target, + nomem_out); + } else { + mod_name = find_module_name(pev->target); + tev->point.module = + strdup(mod_name ? mod_name : pev->target); + free(mod_name); + if (!tev->point.module) + goto nomem_out; + } + } tev->uprobes = pev->uprobes; tev->nargs = pev->nargs; if (tev->nargs) { @@ -2624,7 +2644,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, strdup_or_goto(pev->args[i].type, nomem_out); } - arch__fix_tev_from_maps(pev, tev, map); + arch__fix_tev_from_maps(pev, tev, map, sym); } if (ret == skipped) { ret = -ENOENT; @@ -2743,9 +2763,13 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev, { int ret; - if (pev->uprobes && !pev->group) { - /* Replace group name if not given */ - ret = convert_exec_to_group(pev->target, &pev->group); + if (!pev->group) { + /* Set group name if not given */ + if (!pev->uprobes) { + pev->group = strdup(PERFPROBE_GROUP); + ret = pev->group ? 0 : -ENOMEM; + } else + ret = convert_exec_to_group(pev->target, &pev->group); if (ret != 0) { pr_warning("Failed to make a group name.\n"); return ret; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index e54e7b0..5a27eb4 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -120,7 +120,7 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev); /* Events to command string */ char *synthesize_perf_probe_command(struct perf_probe_event *pev); char *synthesize_probe_trace_command(struct probe_trace_event *tev); -int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len); +char *synthesize_perf_probe_arg(struct perf_probe_arg *pa); /* Check the perf_probe_event needs debuginfo */ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev); @@ -154,7 +154,8 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, int show_available_funcs(const char *module, struct strfilter *filter, bool user); bool arch__prefers_symtab(void); void arch__fix_tev_from_maps(struct perf_probe_event *pev, - struct probe_trace_event *tev, struct map *map); + struct probe_trace_event *tev, struct map *map, + struct symbol *sym); /* If there is no space to write, returns -E2BIG. */ int e_snprintf(char *str, size_t size, const char *format, ...) diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index e3b3b92..3fe6214 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -220,8 +220,7 @@ int probe_file__add_event(int fd, struct probe_trace_event *tev) pr_debug("Writing event: %s\n", buf); if (!probe_event_dry_run) { - ret = write(fd, buf, strlen(buf)); - if (ret <= 0) { + if (write(fd, buf, strlen(buf)) < (int)strlen(buf)) { ret = -errno; pr_warning("Failed to write event: %s\n", strerror_r(errno, sbuf, sizeof(sbuf))); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index b3bd0fb..1259839 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -553,7 +553,7 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) { Dwarf_Die vr_die; - char buf[32], *ptr; + char *buf, *ptr; int ret = 0; /* Copy raw parameters */ @@ -563,13 +563,13 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) if (pf->pvar->name) pf->tvar->name = strdup(pf->pvar->name); else { - ret = synthesize_perf_probe_arg(pf->pvar, buf, 32); - if (ret < 0) - return ret; + buf = synthesize_perf_probe_arg(pf->pvar); + if (!buf) + return -ENOMEM; ptr = strchr(buf, ':'); /* Change type separator to _ */ if (ptr) *ptr = '_'; - pf->tvar->name = strdup(buf); + pf->tvar->name = buf; } if (pf->tvar->name == NULL) return -ENOMEM; @@ -1294,6 +1294,7 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data) { struct available_var_finder *af = data; struct variable_list *vl; + struct strbuf buf = STRBUF_INIT; int tag, ret; vl = &af->vls[af->nvls - 1]; @@ -1307,25 +1308,26 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data) if (ret == 0 || ret == -ERANGE) { int ret2; bool externs = !af->child; - struct strbuf buf; - strbuf_init(&buf, 64); + if (strbuf_init(&buf, 64) < 0) + goto error; if (probe_conf.show_location_range) { - if (!externs) { - if (ret) - strbuf_add(&buf, "[INV]\t", 6); - else - strbuf_add(&buf, "[VAL]\t", 6); - } else - strbuf_add(&buf, "[EXT]\t", 6); + if (!externs) + ret2 = strbuf_add(&buf, + ret ? "[INV]\t" : "[VAL]\t", 6); + else + ret2 = strbuf_add(&buf, "[EXT]\t", 6); + if (ret2) + goto error; } ret2 = die_get_varname(die_mem, &buf); if (!ret2 && probe_conf.show_location_range && !externs) { - strbuf_addch(&buf, '\t'); + if (strbuf_addch(&buf, '\t') < 0) + goto error; ret2 = die_get_var_range(&af->pf.sp_die, die_mem, &buf); } @@ -1343,6 +1345,10 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data) return DIE_FIND_CB_CONTINUE; else return DIE_FIND_CB_SIBLING; +error: + strbuf_release(&buf); + pr_debug("Error in strbuf\n"); + return DIE_FIND_CB_END; } /* Add a found vars into available variables list */ diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 8162ba0..36c6862 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -23,3 +23,4 @@ util/strlist.c util/trace-event.c ../lib/rbtree.c util/string.c +util/symbol_fprintf.c diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c index 01f0324..c6d4ee2 100644 --- a/tools/perf/util/quote.c +++ b/tools/perf/util/quote.c @@ -17,38 +17,42 @@ static inline int need_bs_quote(char c) return (c == '\'' || c == '!'); } -static void sq_quote_buf(struct strbuf *dst, const char *src) +static int sq_quote_buf(struct strbuf *dst, const char *src) { char *to_free = NULL; + int ret; if (dst->buf == src) to_free = strbuf_detach(dst, NULL); - strbuf_addch(dst, '\''); - while (*src) { + ret = strbuf_addch(dst, '\''); + while (!ret && *src) { size_t len = strcspn(src, "'!"); - strbuf_add(dst, src, len); + ret = strbuf_add(dst, src, len); src += len; - while (need_bs_quote(*src)) { - strbuf_addstr(dst, "'\\"); - strbuf_addch(dst, *src++); - strbuf_addch(dst, '\''); - } + while (!ret && need_bs_quote(*src)) + ret = strbuf_addf(dst, "'\\%c\'", *src++); } - strbuf_addch(dst, '\''); + if (!ret) + ret = strbuf_addch(dst, '\''); free(to_free); + + return ret; } -void sq_quote_argv(struct strbuf *dst, const char** argv, size_t maxlen) +int sq_quote_argv(struct strbuf *dst, const char** argv, size_t maxlen) { - int i; + int i, ret; /* Copy into destination buffer. */ - strbuf_grow(dst, 255); - for (i = 0; argv[i]; ++i) { - strbuf_addch(dst, ' '); - sq_quote_buf(dst, argv[i]); + ret = strbuf_grow(dst, 255); + for (i = 0; !ret && argv[i]; ++i) { + ret = strbuf_addch(dst, ' '); + if (ret) + break; + ret = sq_quote_buf(dst, argv[i]); if (maxlen && dst->len > maxlen) die("Too many or long arguments"); } + return ret; } diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h index 3340c9c..e1ec191 100644 --- a/tools/perf/util/quote.h +++ b/tools/perf/util/quote.h @@ -24,6 +24,6 @@ * sq_quote() in a real application. */ -void sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen); +int sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen); #endif /* __PERF_QUOTE_H */ diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h new file mode 100644 index 0000000..abc76e3 --- /dev/null +++ b/tools/perf/util/rb_resort.h @@ -0,0 +1,149 @@ +#ifndef _PERF_RESORT_RB_H_ +#define _PERF_RESORT_RB_H_ +/* + * Template for creating a class to resort an existing rb_tree according to + * a new sort criteria, that must be present in the entries of the source + * rb_tree. + * + * (c) 2016 Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Quick example, resorting threads by its shortname: + * + * First define the prefix (threads) to be used for the functions and data + * structures created, and provide an expression for the sorting, then the + * fields to be present in each of the entries in the new, sorted, rb_tree. + * + * The body of the init function should collect the fields, maybe + * pre-calculating them from multiple entries in the original 'entry' from + * the rb_tree used as a source for the entries to be sorted: + +DEFINE_RB_RESORT_RB(threads, strcmp(a->thread->shortname, + b->thread->shortname) < 0, + struct thread *thread; +) +{ + entry->thread = rb_entry(nd, struct thread, rb_node); +} + + * After this it is just a matter of instantiating it and iterating it, + * for a few data structures with existing rb_trees, such as 'struct machine', + * helpers are available to get the rb_root and the nr_entries: + + DECLARE_RESORT_RB_MACHINE_THREADS(threads, machine_ptr); + + * This will instantiate the new rb_tree and a cursor for it, that can be used as: + + struct rb_node *nd; + + resort_rb__for_each(nd, threads) { + struct thread *t = threads_entry; + printf("%s: %d\n", t->shortname, t->tid); + } + + * Then delete it: + + resort_rb__delete(threads); + + * The name of the data structures and functions will have a _sorted suffix + * right before the method names, i.e. will look like: + * + * struct threads_sorted_entry {} + * threads_sorted__insert() + */ + +#define DEFINE_RESORT_RB(__name, __comp, ...) \ +struct __name##_sorted_entry { \ + struct rb_node rb_node; \ + __VA_ARGS__ \ +}; \ +static void __name##_sorted__init_entry(struct rb_node *nd, \ + struct __name##_sorted_entry *entry); \ + \ +static int __name##_sorted__cmp(struct rb_node *nda, struct rb_node *ndb) \ +{ \ + struct __name##_sorted_entry *a, *b; \ + a = rb_entry(nda, struct __name##_sorted_entry, rb_node); \ + b = rb_entry(ndb, struct __name##_sorted_entry, rb_node); \ + return __comp; \ +} \ + \ +struct __name##_sorted { \ + struct rb_root entries; \ + struct __name##_sorted_entry nd[0]; \ +}; \ + \ +static void __name##_sorted__insert(struct __name##_sorted *sorted, \ + struct rb_node *sorted_nd) \ +{ \ + struct rb_node **p = &sorted->entries.rb_node, *parent = NULL; \ + while (*p != NULL) { \ + parent = *p; \ + if (__name##_sorted__cmp(sorted_nd, parent)) \ + p = &(*p)->rb_left; \ + else \ + p = &(*p)->rb_right; \ + } \ + rb_link_node(sorted_nd, parent, p); \ + rb_insert_color(sorted_nd, &sorted->entries); \ +} \ + \ +static void __name##_sorted__sort(struct __name##_sorted *sorted, \ + struct rb_root *entries) \ +{ \ + struct rb_node *nd; \ + unsigned int i = 0; \ + for (nd = rb_first(entries); nd; nd = rb_next(nd)) { \ + struct __name##_sorted_entry *snd = &sorted->nd[i++]; \ + __name##_sorted__init_entry(nd, snd); \ + __name##_sorted__insert(sorted, &snd->rb_node); \ + } \ +} \ + \ +static struct __name##_sorted *__name##_sorted__new(struct rb_root *entries, \ + int nr_entries) \ +{ \ + struct __name##_sorted *sorted; \ + sorted = malloc(sizeof(*sorted) + sizeof(sorted->nd[0]) * nr_entries); \ + if (sorted) { \ + sorted->entries = RB_ROOT; \ + __name##_sorted__sort(sorted, entries); \ + } \ + return sorted; \ +} \ + \ +static void __name##_sorted__delete(struct __name##_sorted *sorted) \ +{ \ + free(sorted); \ +} \ + \ +static void __name##_sorted__init_entry(struct rb_node *nd, \ + struct __name##_sorted_entry *entry) + +#define DECLARE_RESORT_RB(__name) \ +struct __name##_sorted_entry *__name##_entry; \ +struct __name##_sorted *__name = __name##_sorted__new + +#define resort_rb__for_each(__nd, __name) \ + for (__nd = rb_first(&__name->entries); \ + __name##_entry = rb_entry(__nd, struct __name##_sorted_entry, \ + rb_node), __nd; \ + __nd = rb_next(__nd)) + +#define resort_rb__delete(__name) \ + __name##_sorted__delete(__name), __name = NULL + +/* + * Helpers for other classes that contains both an rbtree and the + * number of entries in it: + */ + +/* For 'struct intlist' */ +#define DECLARE_RESORT_RB_INTLIST(__name, __ilist) \ + DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries, \ + __ilist->rblist.nr_entries) + +/* For 'struct machine->threads' */ +#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine) \ + DECLARE_RESORT_RB(__name)(&__machine->threads, __machine->nr_threads) + +#endif /* _PERF_RESORT_RB_H_ */ diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 0467367..481792c 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -129,7 +129,8 @@ bool perf_can_record_cpu_wide(void) return true; } -void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) +void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, + struct callchain_param *callchain) { struct perf_evsel *evsel; bool use_sample_identifier = false; @@ -148,7 +149,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) use_comm_exec = perf_can_comm_exec(); evlist__for_each(evlist, evsel) { - perf_evsel__config(evsel, opts); + perf_evsel__config(evsel, opts, callchain); if (evsel->tracking && use_comm_exec) evsel->attr.comm_exec = 1; } diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index b3aabc0..62c7f69 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -31,6 +31,8 @@ #include <perl.h> #include "../../perf.h" +#include "../callchain.h" +#include "../machine.h" #include "../thread.h" #include "../event.h" #include "../trace-event.h" @@ -248,10 +250,90 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } +static SV *perl_process_callchain(struct perf_sample *sample, + struct perf_evsel *evsel, + struct addr_location *al) +{ + AV *list; + + list = newAV(); + if (!list) + goto exit; + + if (!symbol_conf.use_callchain || !sample->callchain) + goto exit; + + if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel, + sample, NULL, NULL, + sysctl_perf_event_max_stack) != 0) { + pr_err("Failed to resolve callchain. Skipping\n"); + goto exit; + } + callchain_cursor_commit(&callchain_cursor); + + + while (1) { + HV *elem; + struct callchain_cursor_node *node; + node = callchain_cursor_current(&callchain_cursor); + if (!node) + break; + + elem = newHV(); + if (!elem) + goto exit; + + if (!hv_stores(elem, "ip", newSVuv(node->ip))) { + hv_undef(elem); + goto exit; + } + + if (node->sym) { + HV *sym = newHV(); + if (!sym) { + hv_undef(elem); + goto exit; + } + if (!hv_stores(sym, "start", newSVuv(node->sym->start)) || + !hv_stores(sym, "end", newSVuv(node->sym->end)) || + !hv_stores(sym, "binding", newSVuv(node->sym->binding)) || + !hv_stores(sym, "name", newSVpvn(node->sym->name, + node->sym->namelen)) || + !hv_stores(elem, "sym", newRV_noinc((SV*)sym))) { + hv_undef(sym); + hv_undef(elem); + goto exit; + } + } + + if (node->map) { + struct map *map = node->map; + const char *dsoname = "[unknown]"; + if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (symbol_conf.show_kernel_path && map->dso->long_name) + dsoname = map->dso->long_name; + else if (map->dso->name) + dsoname = map->dso->name; + } + if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) { + hv_undef(elem); + goto exit; + } + } + + callchain_cursor_advance(&callchain_cursor); + av_push(list, newRV_noinc((SV*)elem)); + } + +exit: + return newRV_noinc((SV*)list); +} + static void perl_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, - struct thread *thread) + struct addr_location *al) { + struct thread *thread = al->thread; struct event_format *event = evsel->tp_format; struct format_field *field; static char handler[256]; @@ -295,6 +377,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, XPUSHs(sv_2mortal(newSVuv(ns))); XPUSHs(sv_2mortal(newSViv(pid))); XPUSHs(sv_2mortal(newSVpv(comm, 0))); + XPUSHs(sv_2mortal(perl_process_callchain(sample, evsel, al))); /* common fields other than pid can be accessed via xsub fns */ @@ -329,6 +412,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, XPUSHs(sv_2mortal(newSVuv(nsecs))); XPUSHs(sv_2mortal(newSViv(pid))); XPUSHs(sv_2mortal(newSVpv(comm, 0))); + XPUSHs(sv_2mortal(perl_process_callchain(sample, evsel, al))); call_pv("main::trace_unhandled", G_SCALAR); } SPAGAIN; @@ -366,7 +450,7 @@ static void perl_process_event(union perf_event *event, struct perf_evsel *evsel, struct addr_location *al) { - perl_process_tracepoint(sample, evsel, al->thread); + perl_process_tracepoint(sample, evsel, al); perl_process_event_generic(event, sample, evsel); } @@ -490,7 +574,27 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "use Perf::Trace::Util;\n\n"); fprintf(ofp, "sub trace_begin\n{\n\t# optional\n}\n\n"); - fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n\n"); + fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n"); + + + fprintf(ofp, "\n\ +sub print_backtrace\n\ +{\n\ + my $callchain = shift;\n\ + for my $node (@$callchain)\n\ + {\n\ + if(exists $node->{sym})\n\ + {\n\ + printf( \"\\t[\\%%x] \\%%s\\n\", $node->{ip}, $node->{sym}{name});\n\ + }\n\ + else\n\ + {\n\ + printf( \"\\t[\\%%x]\\n\", $node{ip});\n\ + }\n\ + }\n\ +}\n\n\ +"); + while ((event = trace_find_next_event(pevent, event))) { fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); @@ -502,7 +606,8 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "$common_secs, "); fprintf(ofp, "$common_nsecs,\n"); fprintf(ofp, "\t $common_pid, "); - fprintf(ofp, "$common_comm,\n\t "); + fprintf(ofp, "$common_comm, "); + fprintf(ofp, "$common_callchain,\n\t "); not_first = 0; count = 0; @@ -519,7 +624,7 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "\tprint_header($event_name, $common_cpu, " "$common_secs, $common_nsecs,\n\t " - "$common_pid, $common_comm);\n\n"); + "$common_pid, $common_comm, $common_callchain);\n\n"); fprintf(ofp, "\tprintf(\""); @@ -581,17 +686,22 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "$%s", f->name); } - fprintf(ofp, ");\n"); + fprintf(ofp, ");\n\n"); + + fprintf(ofp, "\tprint_backtrace($common_callchain);\n"); + fprintf(ofp, "}\n\n"); } fprintf(ofp, "sub trace_unhandled\n{\n\tmy ($event_name, $context, " "$common_cpu, $common_secs, $common_nsecs,\n\t " - "$common_pid, $common_comm) = @_;\n\n"); + "$common_pid, $common_comm, $common_callchain) = @_;\n\n"); fprintf(ofp, "\tprint_header($event_name, $common_cpu, " "$common_secs, $common_nsecs,\n\t $common_pid, " - "$common_comm);\n}\n\n"); + "$common_comm, $common_callchain);\n"); + fprintf(ofp, "\tprint_backtrace($common_callchain);\n"); + fprintf(ofp, "}\n\n"); fprintf(ofp, "sub print_header\n{\n" "\tmy ($event_name, $cpu, $secs, $nsecs, $pid, $comm) = @_;\n\n" diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index fbd0524..ff13470 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -41,6 +41,7 @@ #include "../thread-stack.h" #include "../trace-event.h" #include "../machine.h" +#include "../call-path.h" #include "thread_map.h" #include "cpumap.h" #include "stat.h" @@ -323,7 +324,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample, if (!symbol_conf.use_callchain || !sample->callchain) goto exit; - if (thread__resolve_callchain(al->thread, evsel, + if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel, sample, NULL, NULL, scripting_max_stack) != 0) { pr_err("Failed to resolve callchain. Skipping\n"); @@ -407,8 +408,11 @@ static void python_process_tracepoint(struct perf_sample *sample, if (!t) Py_FatalError("couldn't create Python tuple"); - if (!event) - die("ug! no event found for type %d", (int)evsel->attr.config); + if (!event) { + snprintf(handler_name, sizeof(handler_name), + "ug! no event found for type %" PRIu64, (u64)evsel->attr.config); + Py_FatalError(handler_name); + } pid = raw_field_value(event, "common_pid", data); @@ -614,7 +618,7 @@ static int python_export_dso(struct db_export *dbe, struct dso *dso, struct machine *machine) { struct tables *tables = container_of(dbe, struct tables, dbe); - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + char sbuild_id[SBUILD_ID_SIZE]; PyObject *t; build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); @@ -681,7 +685,7 @@ static int python_export_sample(struct db_export *dbe, struct tables *tables = container_of(dbe, struct tables, dbe); PyObject *t; - t = tuple_new(21); + t = tuple_new(22); tuple_set_u64(t, 0, es->db_id); tuple_set_u64(t, 1, es->evsel->db_id); @@ -704,6 +708,7 @@ static int python_export_sample(struct db_export *dbe, tuple_set_u64(t, 18, es->sample->data_src); tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK); tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX)); + tuple_set_u64(t, 21, es->call_path_id); call_object(tables->sample_handler, t, "sample_table"); @@ -998,8 +1003,10 @@ static void set_table_handlers(struct tables *tables) { const char *perf_db_export_mode = "perf_db_export_mode"; const char *perf_db_export_calls = "perf_db_export_calls"; - PyObject *db_export_mode, *db_export_calls; + const char *perf_db_export_callchains = "perf_db_export_callchains"; + PyObject *db_export_mode, *db_export_calls, *db_export_callchains; bool export_calls = false; + bool export_callchains = false; int ret; memset(tables, 0, sizeof(struct tables)); @@ -1016,6 +1023,7 @@ static void set_table_handlers(struct tables *tables) if (!ret) return; + /* handle export calls */ tables->dbe.crp = NULL; db_export_calls = PyDict_GetItemString(main_dict, perf_db_export_calls); if (db_export_calls) { @@ -1033,6 +1041,33 @@ static void set_table_handlers(struct tables *tables) Py_FatalError("failed to create calls processor"); } + /* handle export callchains */ + tables->dbe.cpr = NULL; + db_export_callchains = PyDict_GetItemString(main_dict, + perf_db_export_callchains); + if (db_export_callchains) { + ret = PyObject_IsTrue(db_export_callchains); + if (ret == -1) + handler_call_die(perf_db_export_callchains); + export_callchains = !!ret; + } + + if (export_callchains) { + /* + * Attempt to use the call path root from the call return + * processor, if the call return processor is in use. Otherwise, + * we allocate a new call path root. This prevents exporting + * duplicate call path ids when both are in use simultaniously. + */ + if (tables->dbe.crp) + tables->dbe.cpr = tables->dbe.crp->cpr; + else + tables->dbe.cpr = call_path_root__new(); + + if (!tables->dbe.cpr) + Py_FatalError("failed to create call path root"); + } + tables->db_export_mode = true; /* * Reserve per symbol space for symbol->db_id via symbol__priv() diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 4abd85c..2335b28 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -409,6 +409,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->stat = process_stat_stub; if (tool->stat_round == NULL) tool->stat_round = process_stat_round_stub; + if (tool->time_conv == NULL) + tool->time_conv = process_event_op2_stub; } static void swap_sample_id_all(union perf_event *event, void *data) @@ -794,6 +796,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_STAT] = perf_event__stat_swap, [PERF_RECORD_STAT_ROUND] = perf_event__stat_round_swap, [PERF_RECORD_EVENT_UPDATE] = perf_event__event_update_swap, + [PERF_RECORD_TIME_CONV] = perf_event__all64_swap, [PERF_RECORD_HEADER_MAX] = NULL, }; @@ -904,7 +907,7 @@ static void callchain__printf(struct perf_evsel *evsel, unsigned int i; struct ip_callchain *callchain = sample->callchain; - if (has_branch_callstack(evsel)) + if (perf_evsel__has_branch_callstack(evsel)) callchain__lbr_callstack_printf(sample); printf("... FP chain: nr:%" PRIu64 "\n", callchain->nr); @@ -1078,7 +1081,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_CALLCHAIN) callchain__printf(evsel, sample); - if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !has_branch_callstack(evsel)) + if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel)) branch_stack__printf(sample); if (sample_type & PERF_SAMPLE_REGS_USER) @@ -1341,6 +1344,9 @@ static s64 perf_session__process_user_event(struct perf_session *session, return tool->stat(tool, event, session); case PERF_RECORD_STAT_ROUND: return tool->stat_round(tool, event, session); + case PERF_RECORD_TIME_CONV: + session->time_conv = event->time_conv; + return tool->time_conv(tool, event, session); default: return -EINVAL; } @@ -1830,7 +1836,11 @@ out: out_err: ui_progress__finish(); perf_session__warn_about_errors(session); - ordered_events__free(&session->ordered_events); + /* + * We may switching perf.data output, make ordered_events + * reusable. + */ + ordered_events__reinit(&session->ordered_events); auxtrace__free_events(session); session->one_mmap = false; return err; @@ -1947,105 +1957,6 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, return NULL; } -void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample, - struct addr_location *al, - unsigned int print_opts, unsigned int stack_depth) -{ - struct callchain_cursor_node *node; - int print_ip = print_opts & PRINT_IP_OPT_IP; - int print_sym = print_opts & PRINT_IP_OPT_SYM; - int print_dso = print_opts & PRINT_IP_OPT_DSO; - int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET; - int print_oneline = print_opts & PRINT_IP_OPT_ONELINE; - int print_srcline = print_opts & PRINT_IP_OPT_SRCLINE; - char s = print_oneline ? ' ' : '\t'; - - if (symbol_conf.use_callchain && sample->callchain) { - struct addr_location node_al; - - if (thread__resolve_callchain(al->thread, evsel, - sample, NULL, NULL, - stack_depth) != 0) { - if (verbose) - error("Failed to resolve callchain. Skipping\n"); - return; - } - callchain_cursor_commit(&callchain_cursor); - - if (print_symoffset) - node_al = *al; - - while (stack_depth) { - u64 addr = 0; - - node = callchain_cursor_current(&callchain_cursor); - if (!node) - break; - - if (node->sym && node->sym->ignore) - goto next; - - if (print_ip) - printf("%c%16" PRIx64, s, node->ip); - - if (node->map) - addr = node->map->map_ip(node->map, node->ip); - - if (print_sym) { - printf(" "); - if (print_symoffset) { - node_al.addr = addr; - node_al.map = node->map; - symbol__fprintf_symname_offs(node->sym, &node_al, stdout); - } else - symbol__fprintf_symname(node->sym, stdout); - } - - if (print_dso) { - printf(" ("); - map__fprintf_dsoname(node->map, stdout); - printf(")"); - } - - if (print_srcline) - map__fprintf_srcline(node->map, addr, "\n ", - stdout); - - if (!print_oneline) - printf("\n"); - - stack_depth--; -next: - callchain_cursor_advance(&callchain_cursor); - } - - } else { - if (al->sym && al->sym->ignore) - return; - - if (print_ip) - printf("%16" PRIx64, sample->ip); - - if (print_sym) { - printf(" "); - if (print_symoffset) - symbol__fprintf_symname_offs(al->sym, al, - stdout); - else - symbol__fprintf_symname(al->sym, stdout); - } - - if (print_dso) { - printf(" ("); - map__fprintf_dsoname(al->map, stdout); - printf(")"); - } - - if (print_srcline) - map__fprintf_srcline(al->map, al->addr, "\n ", stdout); - } -} - int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap) { diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 5f792e3..4bd7585 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -26,6 +26,7 @@ struct perf_session { struct itrace_synth_opts *itrace_synth_opts; struct list_head auxtrace_index; struct trace_event tevent; + struct time_conv_event time_conv; bool repipe; bool one_mmap; void *one_mmap_addr; @@ -35,13 +36,6 @@ struct perf_session { struct perf_tool *tool; }; -#define PRINT_IP_OPT_IP (1<<0) -#define PRINT_IP_OPT_SYM (1<<1) -#define PRINT_IP_OPT_DSO (1<<2) -#define PRINT_IP_OPT_SYMOFFSET (1<<3) -#define PRINT_IP_OPT_ONELINE (1<<4) -#define PRINT_IP_OPT_SRCLINE (1<<5) - struct perf_tool; struct perf_session *perf_session__new(struct perf_data_file *file, @@ -103,10 +97,6 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp); struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type); -void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample, - struct addr_location *al, - unsigned int print_opts, unsigned int stack_depth); - int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 47966a1..20e69ed 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -21,13 +21,6 @@ const char *sort_order; const char *field_order; regex_t ignore_callees_regex; int have_ignore_callees = 0; -int sort__need_collapse = 0; -int sort__has_parent = 0; -int sort__has_sym = 0; -int sort__has_dso = 0; -int sort__has_socket = 0; -int sort__has_thread = 0; -int sort__has_comm = 0; enum sort_mode sort__mode = SORT_MODE__NORMAL; /* @@ -244,7 +237,7 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) * comparing symbol address alone is not enough since it's a * relative address within a dso. */ - if (!sort__has_dso) { + if (!hists__has(left->hists, dso) || hists__has(right->hists, dso)) { ret = sort__dso_cmp(left, right); if (ret != 0) return ret; @@ -2163,7 +2156,7 @@ static int __sort_dimension__add(struct sort_dimension *sd, return -1; if (sd->entry->se_collapse) - sort__need_collapse = 1; + list->need_collapse = 1; sd->taken = 1; @@ -2245,9 +2238,9 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok, pr_err("Invalid regex: %s\n%s", parent_pattern, err); return -EINVAL; } - sort__has_parent = 1; + list->parent = 1; } else if (sd->entry == &sort_sym) { - sort__has_sym = 1; + list->sym = 1; /* * perf diff displays the performance difference amongst * two or more perf.data files. Those files could come @@ -2258,13 +2251,13 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok, sd->entry->se_collapse = sort__sym_sort; } else if (sd->entry == &sort_dso) { - sort__has_dso = 1; + list->dso = 1; } else if (sd->entry == &sort_socket) { - sort__has_socket = 1; + list->socket = 1; } else if (sd->entry == &sort_thread) { - sort__has_thread = 1; + list->thread = 1; } else if (sd->entry == &sort_comm) { - sort__has_comm = 1; + list->comm = 1; } return __sort_dimension__add(sd, list, level); @@ -2289,7 +2282,7 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok, return -EINVAL; if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to) - sort__has_sym = 1; + list->sym = 1; __sort_dimension__add(sd, list, level); return 0; @@ -2305,7 +2298,7 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok, return -EINVAL; if (sd->entry == &sort_mem_daddr_sym) - sort__has_sym = 1; + list->sym = 1; __sort_dimension__add(sd, list, level); return 0; @@ -2445,6 +2438,9 @@ static char *prefix_if_not_in(const char *pre, char *str) static char *setup_overhead(char *keys) { + if (sort__mode == SORT_MODE__DIFF) + return keys; + keys = prefix_if_not_in("overhead", keys); if (symbol_conf.cumulate_callchain) @@ -2746,10 +2742,10 @@ int setup_sorting(struct perf_evlist *evlist) void reset_output_field(void) { - sort__need_collapse = 0; - sort__has_parent = 0; - sort__has_sym = 0; - sort__has_dso = 0; + perf_hpp_list.need_collapse = 0; + perf_hpp_list.parent = 0; + perf_hpp_list.sym = 0; + perf_hpp_list.dso = 0; field_order = NULL; sort_order = NULL; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 3f4e359..42927f4 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -31,13 +31,6 @@ extern const char *parent_pattern; extern const char default_sort_order[]; extern regex_t ignore_callees_regex; extern int have_ignore_callees; -extern int sort__need_collapse; -extern int sort__has_dso; -extern int sort__has_parent; -extern int sort__has_sym; -extern int sort__has_socket; -extern int sort__has_thread; -extern int sort__has_comm; extern enum sort_mode sort__mode; extern struct sort_entry sort_comm; extern struct sort_entry sort_dso; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 4d9b481..ffa1d06 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -307,6 +307,7 @@ int perf_stat_process_counter(struct perf_stat_config *config, struct perf_counts_values *aggr = &counter->counts->aggr; struct perf_stat_evsel *ps = counter->priv; u64 *count = counter->counts->aggr.values; + u64 val; int i, ret; aggr->val = aggr->ena = aggr->run = 0; @@ -346,7 +347,8 @@ int perf_stat_process_counter(struct perf_stat_config *config, /* * Save the full runtime - to allow normalization during printout: */ - perf_stat__update_shadow_stats(counter, count, 0); + val = counter->scale * *count; + perf_stat__update_shadow_stats(counter, &val, 0); return 0; } diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index 8fb7329..f95f682 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -1,3 +1,4 @@ +#include "debug.h" #include "cache.h" #include <linux/kernel.h> @@ -17,12 +18,13 @@ int prefixcmp(const char *str, const char *prefix) */ char strbuf_slopbuf[1]; -void strbuf_init(struct strbuf *sb, ssize_t hint) +int strbuf_init(struct strbuf *sb, ssize_t hint) { sb->alloc = sb->len = 0; sb->buf = strbuf_slopbuf; if (hint) - strbuf_grow(sb, hint); + return strbuf_grow(sb, hint); + return 0; } void strbuf_release(struct strbuf *sb) @@ -42,67 +44,104 @@ char *strbuf_detach(struct strbuf *sb, size_t *sz) return res; } -void strbuf_grow(struct strbuf *sb, size_t extra) +int strbuf_grow(struct strbuf *sb, size_t extra) { - if (sb->len + extra + 1 <= sb->len) - die("you want to use way too much memory"); - if (!sb->alloc) - sb->buf = NULL; - ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc); + char *buf; + size_t nr = sb->len + extra + 1; + + if (nr < sb->alloc) + return 0; + + if (nr <= sb->len) + return -E2BIG; + + if (alloc_nr(sb->alloc) > nr) + nr = alloc_nr(sb->alloc); + + /* + * Note that sb->buf == strbuf_slopbuf if sb->alloc == 0, and it is + * a static variable. Thus we have to avoid passing it to realloc. + */ + buf = realloc(sb->alloc ? sb->buf : NULL, nr * sizeof(*buf)); + if (!buf) + return -ENOMEM; + + sb->buf = buf; + sb->alloc = nr; + return 0; } -void strbuf_addch(struct strbuf *sb, int c) +int strbuf_addch(struct strbuf *sb, int c) { - strbuf_grow(sb, 1); + int ret = strbuf_grow(sb, 1); + if (ret) + return ret; + sb->buf[sb->len++] = c; sb->buf[sb->len] = '\0'; + return 0; } -void strbuf_add(struct strbuf *sb, const void *data, size_t len) +int strbuf_add(struct strbuf *sb, const void *data, size_t len) { - strbuf_grow(sb, len); + int ret = strbuf_grow(sb, len); + if (ret) + return ret; + memcpy(sb->buf + sb->len, data, len); - strbuf_setlen(sb, sb->len + len); + return strbuf_setlen(sb, sb->len + len); } -static void strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap) +static int strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap) { - int len; + int len, ret; va_list ap_saved; - if (!strbuf_avail(sb)) - strbuf_grow(sb, 64); + if (!strbuf_avail(sb)) { + ret = strbuf_grow(sb, 64); + if (ret) + return ret; + } va_copy(ap_saved, ap); len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); if (len < 0) - die("your vsnprintf is broken"); + return len; if (len > strbuf_avail(sb)) { - strbuf_grow(sb, len); + ret = strbuf_grow(sb, len); + if (ret) + return ret; len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved); va_end(ap_saved); if (len > strbuf_avail(sb)) { - die("this should not happen, your vsnprintf is broken"); + pr_debug("this should not happen, your vsnprintf is broken"); + return -EINVAL; } } - strbuf_setlen(sb, sb->len + len); + return strbuf_setlen(sb, sb->len + len); } -void strbuf_addf(struct strbuf *sb, const char *fmt, ...) +int strbuf_addf(struct strbuf *sb, const char *fmt, ...) { va_list ap; + int ret; va_start(ap, fmt); - strbuf_addv(sb, fmt, ap); + ret = strbuf_addv(sb, fmt, ap); va_end(ap); + return ret; } ssize_t strbuf_read(struct strbuf *sb, int fd, ssize_t hint) { size_t oldlen = sb->len; size_t oldalloc = sb->alloc; + int ret; + + ret = strbuf_grow(sb, hint ? hint : 8192); + if (ret) + return ret; - strbuf_grow(sb, hint ? hint : 8192); for (;;) { ssize_t cnt; @@ -112,12 +151,14 @@ ssize_t strbuf_read(struct strbuf *sb, int fd, ssize_t hint) strbuf_release(sb); else strbuf_setlen(sb, oldlen); - return -1; + return cnt; } if (!cnt) break; sb->len += cnt; - strbuf_grow(sb, 8192); + ret = strbuf_grow(sb, 8192); + if (ret) + return ret; } sb->buf[sb->len] = '\0'; diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index ab9be0fb..54b4092 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -51,7 +51,7 @@ struct strbuf { #define STRBUF_INIT { 0, 0, strbuf_slopbuf } /*----- strbuf life cycle -----*/ -void strbuf_init(struct strbuf *buf, ssize_t hint); +int strbuf_init(struct strbuf *buf, ssize_t hint); void strbuf_release(struct strbuf *buf); char *strbuf_detach(struct strbuf *buf, size_t *); @@ -60,26 +60,31 @@ static inline ssize_t strbuf_avail(const struct strbuf *sb) { return sb->alloc ? sb->alloc - sb->len - 1 : 0; } -void strbuf_grow(struct strbuf *buf, size_t); +int strbuf_grow(struct strbuf *buf, size_t); -static inline void strbuf_setlen(struct strbuf *sb, size_t len) { - if (!sb->alloc) - strbuf_grow(sb, 0); +static inline int strbuf_setlen(struct strbuf *sb, size_t len) { + int ret; + if (!sb->alloc) { + ret = strbuf_grow(sb, 0); + if (ret) + return ret; + } assert(len < sb->alloc); sb->len = len; sb->buf[len] = '\0'; + return 0; } /*----- add data in your buffer -----*/ -void strbuf_addch(struct strbuf *sb, int c); +int strbuf_addch(struct strbuf *sb, int c); -void strbuf_add(struct strbuf *buf, const void *, size_t); -static inline void strbuf_addstr(struct strbuf *sb, const char *s) { - strbuf_add(sb, s, strlen(s)); +int strbuf_add(struct strbuf *buf, const void *, size_t); +static inline int strbuf_addstr(struct strbuf *sb, const char *s) { + return strbuf_add(sb, s, strlen(s)); } __attribute__((format(printf,2,3))) -void strbuf_addf(struct strbuf *sb, const char *fmt, ...); +int strbuf_addf(struct strbuf *sb, const char *fmt, ...); /* XXX: if read fails, any partial read is undone */ ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index bc229a7..87a297d 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -709,17 +709,10 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, if (ss->opdshdr.sh_type != SHT_PROGBITS) ss->opdsec = NULL; - if (dso->kernel == DSO_TYPE_USER) { - GElf_Shdr shdr; - ss->adjust_symbols = (ehdr.e_type == ET_EXEC || - ehdr.e_type == ET_REL || - dso__is_vdso(dso) || - elf_section_by_name(elf, &ehdr, &shdr, - ".gnu.prelink_undo", - NULL) != NULL); - } else { + if (dso->kernel == DSO_TYPE_USER) + ss->adjust_symbols = true; + else ss->adjust_symbols = elf__needs_adjust_symbols(ehdr); - } ss->name = strdup(name); if (!ss->name) { @@ -777,7 +770,8 @@ static bool want_demangle(bool is_kernel_sym) return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; } -void __weak arch__elf_sym_adjust(GElf_Sym *sym __maybe_unused) { } +void __weak arch__sym_update(struct symbol *s __maybe_unused, + GElf_Sym *sym __maybe_unused) { } int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, @@ -954,8 +948,6 @@ int dso__load_sym(struct dso *dso, struct map *map, (sym.st_value & 1)) --sym.st_value; - arch__elf_sym_adjust(&sym); - if (dso->kernel || kmodule) { char dso_name[PATH_MAX]; @@ -1089,6 +1081,8 @@ new_symbol: if (!f) goto out_elf_end; + arch__sym_update(f, &sym); + if (filter && filter(curr_map, f)) symbol__delete(f); else { diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index e7588dc..7fb3330 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -255,40 +255,6 @@ void symbol__delete(struct symbol *sym) free(((void *)sym) - symbol_conf.priv_size); } -size_t symbol__fprintf(struct symbol *sym, FILE *fp) -{ - return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n", - sym->start, sym->end, - sym->binding == STB_GLOBAL ? 'g' : - sym->binding == STB_LOCAL ? 'l' : 'w', - sym->name); -} - -size_t symbol__fprintf_symname_offs(const struct symbol *sym, - const struct addr_location *al, FILE *fp) -{ - unsigned long offset; - size_t length; - - if (sym && sym->name) { - length = fprintf(fp, "%s", sym->name); - if (al) { - if (al->addr < sym->end) - offset = al->addr - sym->start; - else - offset = al->addr - al->map->start - sym->start; - length += fprintf(fp, "+0x%lx", offset); - } - return length; - } else - return fprintf(fp, "[unknown]"); -} - -size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) -{ - return symbol__fprintf_symname_offs(sym, NULL, fp); -} - void symbols__delete(struct rb_root *symbols) { struct symbol *pos; @@ -335,7 +301,7 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip) if (ip < s->start) n = n->rb_left; - else if (ip >= s->end) + else if (ip > s->end || (ip == s->end && ip != s->start)) n = n->rb_right; else return s; @@ -364,11 +330,6 @@ static struct symbol *symbols__next(struct symbol *sym) return NULL; } -struct symbol_name_rb_node { - struct rb_node rb_node; - struct symbol sym; -}; - static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym) { struct rb_node **p = &symbols->rb_node; @@ -452,6 +413,18 @@ void dso__reset_find_symbol_cache(struct dso *dso) } } +void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym) +{ + symbols__insert(&dso->symbols[type], sym); + + /* update the symbol cache if necessary */ + if (dso->last_find_result[type].addr >= sym->start && + (dso->last_find_result[type].addr < sym->end || + sym->start == sym->end)) { + dso->last_find_result[type].symbol = sym; + } +} + struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr) { @@ -497,21 +470,6 @@ void dso__sort_by_name(struct dso *dso, enum map_type type) &dso->symbols[type]); } -size_t dso__fprintf_symbols_by_name(struct dso *dso, - enum map_type type, FILE *fp) -{ - size_t ret = 0; - struct rb_node *nd; - struct symbol_name_rb_node *pos; - - for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) { - pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); - fprintf(fp, "%s\n", pos->sym.name); - } - - return ret; -} - int modules__parse(const char *filename, void *arg, int (*process_module)(void *arg, const char *name, u64 start)) @@ -1262,8 +1220,8 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) return 0; } -int dso__load_kallsyms(struct dso *dso, const char *filename, - struct map *map, symbol_filter_t filter) +int __dso__load_kallsyms(struct dso *dso, const char *filename, + struct map *map, bool no_kcore, symbol_filter_t filter) { u64 delta = 0; @@ -1284,12 +1242,18 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, else dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS; - if (!dso__load_kcore(dso, map, filename)) + if (!no_kcore && !dso__load_kcore(dso, map, filename)) return dso__split_kallsyms_for_kcore(dso, map, filter); else return dso__split_kallsyms(dso, map, delta, filter); } +int dso__load_kallsyms(struct dso *dso, const char *filename, + struct map *map, symbol_filter_t filter) +{ + return __dso__load_kallsyms(dso, filename, map, false, filter); +} + static int dso__load_perf_map(struct dso *dso, struct map *map, symbol_filter_t filter) { @@ -1644,25 +1608,27 @@ out: return err; } +static bool visible_dir_filter(const char *name, struct dirent *d) +{ + if (d->d_type != DT_DIR) + return false; + return lsdir_no_dot_filter(name, d); +} + static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz) { char kallsyms_filename[PATH_MAX]; - struct dirent *dent; int ret = -1; - DIR *d; + struct strlist *dirs; + struct str_node *nd; - d = opendir(dir); - if (!d) + dirs = lsdir(dir, visible_dir_filter); + if (!dirs) return -1; - while (1) { - dent = readdir(d); - if (!dent) - break; - if (dent->d_type != DT_DIR) - continue; + strlist__for_each(nd, dirs) { scnprintf(kallsyms_filename, sizeof(kallsyms_filename), - "%s/%s/kallsyms", dir, dent->d_name); + "%s/%s/kallsyms", dir, nd->s); if (!validate_kcore_addresses(kallsyms_filename, map)) { strlcpy(dir, kallsyms_filename, dir_sz); ret = 0; @@ -1670,7 +1636,7 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz) } } - closedir(d); + strlist__delete(dirs); return ret; } @@ -1678,7 +1644,7 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz) static char *dso__find_kallsyms(struct dso *dso, struct map *map) { u8 host_build_id[BUILD_ID_SIZE]; - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + char sbuild_id[SBUILD_ID_SIZE]; bool is_host = false; char path[PATH_MAX]; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index c8b7544..2b5e4ed 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -55,6 +55,7 @@ struct symbol { u16 namelen; u8 binding; bool ignore; + u8 arch_sym; char name[0]; }; @@ -140,6 +141,11 @@ struct symbol_conf { extern struct symbol_conf symbol_conf; +struct symbol_name_rb_node { + struct rb_node rb_node; + struct symbol sym; +}; + static inline int __symbol__join_symfs(char *bf, size_t size, const char *path) { return path__join(bf, size, symbol_conf.symfs, path); @@ -235,9 +241,14 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, symbol_filter_t filter); int dso__load_vmlinux_path(struct dso *dso, struct map *map, symbol_filter_t filter); +int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, + bool no_kcore, symbol_filter_t filter); int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, symbol_filter_t filter); +void dso__insert_symbol(struct dso *dso, enum map_type type, + struct symbol *sym); + struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, @@ -262,8 +273,14 @@ int symbol__init(struct perf_env *env); void symbol__exit(void); void symbol__elf_init(void); struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name); +size_t __symbol__fprintf_symname_offs(const struct symbol *sym, + const struct addr_location *al, + bool unknown_as_addr, FILE *fp); size_t symbol__fprintf_symname_offs(const struct symbol *sym, const struct addr_location *al, FILE *fp); +size_t __symbol__fprintf_symname(const struct symbol *sym, + const struct addr_location *al, + bool unknown_as_addr, FILE *fp); size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp); size_t symbol__fprintf(struct symbol *sym, FILE *fp); bool symbol_type__is_a(char symbol_type, enum map_type map_type); @@ -310,7 +327,7 @@ int setup_intlist(struct intlist **list, const char *list_str, #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr); -void arch__elf_sym_adjust(GElf_Sym *sym); +void arch__sym_update(struct symbol *s, GElf_Sym *sym); #endif #define SYMBOL_A 0 diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c new file mode 100644 index 0000000..a680bda --- /dev/null +++ b/tools/perf/util/symbol_fprintf.c @@ -0,0 +1,71 @@ +#include <elf.h> +#include <inttypes.h> +#include <stdio.h> + +#include "symbol.h" + +size_t symbol__fprintf(struct symbol *sym, FILE *fp) +{ + return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n", + sym->start, sym->end, + sym->binding == STB_GLOBAL ? 'g' : + sym->binding == STB_LOCAL ? 'l' : 'w', + sym->name); +} + +size_t __symbol__fprintf_symname_offs(const struct symbol *sym, + const struct addr_location *al, + bool unknown_as_addr, FILE *fp) +{ + unsigned long offset; + size_t length; + + if (sym && sym->name) { + length = fprintf(fp, "%s", sym->name); + if (al) { + if (al->addr < sym->end) + offset = al->addr - sym->start; + else + offset = al->addr - al->map->start - sym->start; + length += fprintf(fp, "+0x%lx", offset); + } + return length; + } else if (al && unknown_as_addr) + return fprintf(fp, "[%#" PRIx64 "]", al->addr); + else + return fprintf(fp, "[unknown]"); +} + +size_t symbol__fprintf_symname_offs(const struct symbol *sym, + const struct addr_location *al, + FILE *fp) +{ + return __symbol__fprintf_symname_offs(sym, al, false, fp); +} + +size_t __symbol__fprintf_symname(const struct symbol *sym, + const struct addr_location *al, + bool unknown_as_addr, FILE *fp) +{ + return __symbol__fprintf_symname_offs(sym, al, unknown_as_addr, fp); +} + +size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) +{ + return __symbol__fprintf_symname_offs(sym, NULL, false, fp); +} + +size_t dso__fprintf_symbols_by_name(struct dso *dso, + enum map_type type, FILE *fp) +{ + size_t ret = 0; + struct rb_node *nd; + struct symbol_name_rb_node *pos; + + for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); + fprintf(fp, "%s\n", pos->sym.name); + } + + return ret; +} diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c new file mode 100644 index 0000000..bbb4c19 --- /dev/null +++ b/tools/perf/util/syscalltbl.c @@ -0,0 +1,134 @@ +/* + * System call table mapper + * + * (C) 2016 Arnaldo Carvalho de Melo <acme@redhat.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include "syscalltbl.h" +#include <stdlib.h> + +#ifdef HAVE_SYSCALL_TABLE +#include <linux/compiler.h> +#include <string.h> +#include "util.h" + +#if defined(__x86_64__) +#include <asm/syscalls_64.c> +const int syscalltbl_native_max_id = SYSCALLTBL_x86_64_MAX_ID; +static const char **syscalltbl_native = syscalltbl_x86_64; +#endif + +struct syscall { + int id; + const char *name; +}; + +static int syscallcmpname(const void *vkey, const void *ventry) +{ + const char *key = vkey; + const struct syscall *entry = ventry; + + return strcmp(key, entry->name); +} + +static int syscallcmp(const void *va, const void *vb) +{ + const struct syscall *a = va, *b = vb; + + return strcmp(a->name, b->name); +} + +static int syscalltbl__init_native(struct syscalltbl *tbl) +{ + int nr_entries = 0, i, j; + struct syscall *entries; + + for (i = 0; i <= syscalltbl_native_max_id; ++i) + if (syscalltbl_native[i]) + ++nr_entries; + + entries = tbl->syscalls.entries = malloc(sizeof(struct syscall) * nr_entries); + if (tbl->syscalls.entries == NULL) + return -1; + + for (i = 0, j = 0; i <= syscalltbl_native_max_id; ++i) { + if (syscalltbl_native[i]) { + entries[j].name = syscalltbl_native[i]; + entries[j].id = i; + ++j; + } + } + + qsort(tbl->syscalls.entries, nr_entries, sizeof(struct syscall), syscallcmp); + tbl->syscalls.nr_entries = nr_entries; + return 0; +} + +struct syscalltbl *syscalltbl__new(void) +{ + struct syscalltbl *tbl = malloc(sizeof(*tbl)); + if (tbl) { + if (syscalltbl__init_native(tbl)) { + free(tbl); + return NULL; + } + } + return tbl; +} + +void syscalltbl__delete(struct syscalltbl *tbl) +{ + zfree(&tbl->syscalls.entries); + free(tbl); +} + +const char *syscalltbl__name(const struct syscalltbl *tbl __maybe_unused, int id) +{ + return id <= syscalltbl_native_max_id ? syscalltbl_native[id]: NULL; +} + +int syscalltbl__id(struct syscalltbl *tbl, const char *name) +{ + struct syscall *sc = bsearch(name, tbl->syscalls.entries, + tbl->syscalls.nr_entries, sizeof(*sc), + syscallcmpname); + + return sc ? sc->id : -1; +} + +#else /* HAVE_SYSCALL_TABLE */ + +#include <libaudit.h> + +struct syscalltbl *syscalltbl__new(void) +{ + struct syscalltbl *tbl = malloc(sizeof(*tbl)); + if (tbl) + tbl->audit_machine = audit_detect_machine(); + return tbl; +} + +void syscalltbl__delete(struct syscalltbl *tbl) +{ + free(tbl); +} + +const char *syscalltbl__name(const struct syscalltbl *tbl, int id) +{ + return audit_syscall_to_name(id, tbl->audit_machine); +} + +int syscalltbl__id(struct syscalltbl *tbl, const char *name) +{ + return audit_name_to_syscall(name, tbl->audit_machine); +} +#endif /* HAVE_SYSCALL_TABLE */ diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h new file mode 100644 index 0000000..e295151 --- /dev/null +++ b/tools/perf/util/syscalltbl.h @@ -0,0 +1,20 @@ +#ifndef __PERF_SYSCALLTBL_H +#define __PERF_SYSCALLTBL_H + +struct syscalltbl { + union { + int audit_machine; + struct { + int nr_entries; + void *entries; + } syscalls; + }; +}; + +struct syscalltbl *syscalltbl__new(void); +void syscalltbl__delete(struct syscalltbl *tbl); + +const char *syscalltbl__name(const struct syscalltbl *tbl, int id); +int syscalltbl__id(struct syscalltbl *tbl, const char *name); + +#endif /* __PERF_SYSCALLTBL_H */ diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index 679688e..825086a 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -22,44 +22,9 @@ #include "debug.h" #include "symbol.h" #include "comm.h" +#include "call-path.h" #include "thread-stack.h" -#define CALL_PATH_BLOCK_SHIFT 8 -#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT) -#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1) - -struct call_path_block { - struct call_path cp[CALL_PATH_BLOCK_SIZE]; - struct list_head node; -}; - -/** - * struct call_path_root - root of all call paths. - * @call_path: root call path - * @blocks: list of blocks to store call paths - * @next: next free space - * @sz: number of spaces - */ -struct call_path_root { - struct call_path call_path; - struct list_head blocks; - size_t next; - size_t sz; -}; - -/** - * struct call_return_processor - provides a call-back to consume call-return - * information. - * @cpr: call path root - * @process: call-back that accepts call/return information - * @data: anonymous data for call-back - */ -struct call_return_processor { - struct call_path_root *cpr; - int (*process)(struct call_return *cr, void *data); - void *data; -}; - #define STACK_GROWTH 2048 /** @@ -335,108 +300,6 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain, chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr; } -static void call_path__init(struct call_path *cp, struct call_path *parent, - struct symbol *sym, u64 ip, bool in_kernel) -{ - cp->parent = parent; - cp->sym = sym; - cp->ip = sym ? 0 : ip; - cp->db_id = 0; - cp->in_kernel = in_kernel; - RB_CLEAR_NODE(&cp->rb_node); - cp->children = RB_ROOT; -} - -static struct call_path_root *call_path_root__new(void) -{ - struct call_path_root *cpr; - - cpr = zalloc(sizeof(struct call_path_root)); - if (!cpr) - return NULL; - call_path__init(&cpr->call_path, NULL, NULL, 0, false); - INIT_LIST_HEAD(&cpr->blocks); - return cpr; -} - -static void call_path_root__free(struct call_path_root *cpr) -{ - struct call_path_block *pos, *n; - - list_for_each_entry_safe(pos, n, &cpr->blocks, node) { - list_del(&pos->node); - free(pos); - } - free(cpr); -} - -static struct call_path *call_path__new(struct call_path_root *cpr, - struct call_path *parent, - struct symbol *sym, u64 ip, - bool in_kernel) -{ - struct call_path_block *cpb; - struct call_path *cp; - size_t n; - - if (cpr->next < cpr->sz) { - cpb = list_last_entry(&cpr->blocks, struct call_path_block, - node); - } else { - cpb = zalloc(sizeof(struct call_path_block)); - if (!cpb) - return NULL; - list_add_tail(&cpb->node, &cpr->blocks); - cpr->sz += CALL_PATH_BLOCK_SIZE; - } - - n = cpr->next++ & CALL_PATH_BLOCK_MASK; - cp = &cpb->cp[n]; - - call_path__init(cp, parent, sym, ip, in_kernel); - - return cp; -} - -static struct call_path *call_path__findnew(struct call_path_root *cpr, - struct call_path *parent, - struct symbol *sym, u64 ip, u64 ks) -{ - struct rb_node **p; - struct rb_node *node_parent = NULL; - struct call_path *cp; - bool in_kernel = ip >= ks; - - if (sym) - ip = 0; - - if (!parent) - return call_path__new(cpr, parent, sym, ip, in_kernel); - - p = &parent->children.rb_node; - while (*p != NULL) { - node_parent = *p; - cp = rb_entry(node_parent, struct call_path, rb_node); - - if (cp->sym == sym && cp->ip == ip) - return cp; - - if (sym < cp->sym || (sym == cp->sym && ip < cp->ip)) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - cp = call_path__new(cpr, parent, sym, ip, in_kernel); - if (!cp) - return NULL; - - rb_link_node(&cp->rb_node, node_parent, p); - rb_insert_color(&cp->rb_node, &parent->children); - - return cp; -} - struct call_return_processor * call_return_processor__new(int (*process)(struct call_return *cr, void *data), void *data) diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h index e1528f1..ad44c79 100644 --- a/tools/perf/util/thread-stack.h +++ b/tools/perf/util/thread-stack.h @@ -19,17 +19,16 @@ #include <sys/types.h> #include <linux/types.h> -#include <linux/rbtree.h> struct thread; struct comm; struct ip_callchain; struct symbol; struct dso; -struct call_return_processor; struct comm; struct perf_sample; struct addr_location; +struct call_path; /* * Call/Return flags. @@ -69,26 +68,16 @@ struct call_return { }; /** - * struct call_path - node in list of calls leading to a function call. - * @parent: call path to the parent function call - * @sym: symbol of function called - * @ip: only if sym is null, the ip of the function - * @db_id: id used for db-export - * @in_kernel: whether function is a in the kernel - * @rb_node: node in parent's tree of called functions - * @children: tree of call paths of functions called - * - * In combination with the call_return structure, the call_path structure - * defines a context-sensitve call-graph. + * struct call_return_processor - provides a call-back to consume call-return + * information. + * @cpr: call path root + * @process: call-back that accepts call/return information + * @data: anonymous data for call-back */ -struct call_path { - struct call_path *parent; - struct symbol *sym; - u64 ip; - u64 db_id; - bool in_kernel; - struct rb_node rb_node; - struct rb_root children; +struct call_return_processor { + struct call_path_root *cpr; + int (*process)(struct call_return *cr, void *data); + void *data; }; int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip, diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index dfd00c6..45fcb71 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -10,6 +10,8 @@ #include "comm.h" #include "unwind.h" +#include <api/fs/fs.h> + int thread__init_map_groups(struct thread *thread, struct machine *machine) { struct thread *leader; @@ -153,6 +155,23 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, return 0; } +int thread__set_comm_from_proc(struct thread *thread) +{ + char path[64]; + char *comm = NULL; + size_t sz; + int err = -1; + + if (!(snprintf(path, sizeof(path), "%d/task/%d/comm", + thread->pid_, thread->tid) >= (int)sizeof(path)) && + procfs__read_str(path, &comm, &sz) == 0) { + comm[sz - 1] = '\0'; + err = thread__set_comm(thread, comm, 0); + } + + return err; +} + const char *thread__comm_str(const struct thread *thread) { const struct comm *comm = thread__comm(thread); @@ -233,7 +252,7 @@ void thread__find_cpumode_addr_location(struct thread *thread, struct addr_location *al) { size_t i; - const u8 const cpumodes[] = { + const u8 cpumodes[] = { PERF_RECORD_MISC_USER, PERF_RECORD_MISC_KERNEL, PERF_RECORD_MISC_GUEST_USER, diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index a0ac031..45fba13 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -9,6 +9,9 @@ #include "symbol.h" #include <strlist.h> #include <intlist.h> +#ifdef HAVE_LIBUNWIND_SUPPORT +#include <libunwind.h> +#endif struct thread_stack; @@ -32,6 +35,9 @@ struct thread { void *priv; struct thread_stack *ts; +#ifdef HAVE_LIBUNWIND_SUPPORT + unw_addr_space_t addr_space; +#endif }; struct machine; @@ -65,6 +71,8 @@ static inline int thread__set_comm(struct thread *thread, const char *comm, return __thread__set_comm(thread, comm, timestamp, false); } +int thread__set_comm_from_proc(struct thread *thread); + int thread__comm_len(struct thread *thread); struct comm *thread__comm(const struct thread *thread); struct comm *thread__exec_comm(const struct thread *thread); diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 08afc690..5654fe1 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -94,7 +94,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) DIR *proc; int max_threads = 32, items, i; char path[256]; - struct dirent dirent, *next, **namelist = NULL; + struct dirent *dirent, **namelist = NULL; struct thread_map *threads = thread_map__alloc(max_threads); if (threads == NULL) @@ -107,16 +107,16 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) threads->nr = 0; atomic_set(&threads->refcnt, 1); - while (!readdir_r(proc, &dirent, &next) && next) { + while ((dirent = readdir(proc)) != NULL) { char *end; bool grow = false; struct stat st; - pid_t pid = strtol(dirent.d_name, &end, 10); + pid_t pid = strtol(dirent->d_name, &end, 10); if (*end) /* only interested in proper numerical dirents */ continue; - snprintf(path, sizeof(path), "/proc/%s", dirent.d_name); + snprintf(path, sizeof(path), "/proc/%s", dirent->d_name); if (stat(path, &st) != 0) continue; @@ -260,7 +260,7 @@ struct thread_map *thread_map__new_dummy(void) return threads; } -static struct thread_map *thread_map__new_by_tid_str(const char *tid_str) +struct thread_map *thread_map__new_by_tid_str(const char *tid_str) { struct thread_map *threads = NULL, *nt; int ntasks = 0; @@ -436,3 +436,15 @@ struct thread_map *thread_map__new_event(struct thread_map_event *event) return threads; } + +bool thread_map__has(struct thread_map *threads, pid_t pid) +{ + int i; + + for (i = 0; i < threads->nr; ++i) { + if (threads->map[i].pid == pid) + return true; + } + + return false; +} diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 85e4c7c..bd3b971 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -31,6 +31,8 @@ void thread_map__put(struct thread_map *map); struct thread_map *thread_map__new_str(const char *pid, const char *tid, uid_t uid); +struct thread_map *thread_map__new_by_tid_str(const char *tid_str); + size_t thread_map__fprintf(struct thread_map *threads, FILE *fp); static inline int thread_map__nr(struct thread_map *threads) @@ -55,4 +57,5 @@ static inline char *thread_map__comm(struct thread_map *map, int thread) } void thread_map__read_comms(struct thread_map *threads); +bool thread_map__has(struct thread_map *threads, pid_t pid); #endif /* __PERF_THREAD_MAP_H */ diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 55de4cf..ac2590a 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -57,6 +57,7 @@ struct perf_tool { id_index, auxtrace_info, auxtrace_error, + time_conv, thread_map, cpu_map, stat_config, diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h new file mode 100644 index 0000000..e97d701 --- /dev/null +++ b/tools/perf/util/trigger.h @@ -0,0 +1,94 @@ +#ifndef __TRIGGER_H_ +#define __TRIGGER_H_ 1 + +#include "util/debug.h" +#include "asm/bug.h" + +/* + * Use trigger to model operations which need to be executed when + * an event (a signal, for example) is observed. + * + * States and transits: + * + * + * OFF--(on)--> READY --(hit)--> HIT + * ^ | + * | (ready) + * | | + * \_____________/ + * + * is_hit and is_ready are two key functions to query the state of + * a trigger. is_hit means the event already happen; is_ready means the + * trigger is waiting for the event. + */ + +struct trigger { + volatile enum { + TRIGGER_ERROR = -2, + TRIGGER_OFF = -1, + TRIGGER_READY = 0, + TRIGGER_HIT = 1, + } state; + const char *name; +}; + +#define TRIGGER_WARN_ONCE(t, exp) \ + WARN_ONCE(t->state != exp, "trigger '%s' state transist error: %d in %s()\n", \ + t->name, t->state, __func__) + +static inline bool trigger_is_available(struct trigger *t) +{ + return t->state >= 0; +} + +static inline bool trigger_is_error(struct trigger *t) +{ + return t->state <= TRIGGER_ERROR; +} + +static inline void trigger_on(struct trigger *t) +{ + TRIGGER_WARN_ONCE(t, TRIGGER_OFF); + t->state = TRIGGER_READY; +} + +static inline void trigger_ready(struct trigger *t) +{ + if (!trigger_is_available(t)) + return; + t->state = TRIGGER_READY; +} + +static inline void trigger_hit(struct trigger *t) +{ + if (!trigger_is_available(t)) + return; + TRIGGER_WARN_ONCE(t, TRIGGER_READY); + t->state = TRIGGER_HIT; +} + +static inline void trigger_off(struct trigger *t) +{ + if (!trigger_is_available(t)) + return; + t->state = TRIGGER_OFF; +} + +static inline void trigger_error(struct trigger *t) +{ + t->state = TRIGGER_ERROR; +} + +static inline bool trigger_is_ready(struct trigger *t) +{ + return t->state == TRIGGER_READY; +} + +static inline bool trigger_is_hit(struct trigger *t) +{ + return t->state == TRIGGER_HIT; +} + +#define DEFINE_TRIGGER(n) \ +struct trigger n = {.state = TRIGGER_OFF, .name = #n} +#endif diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h index a8b78f1..d5b11e2 100644 --- a/tools/perf/util/tsc.h +++ b/tools/perf/util/tsc.h @@ -3,10 +3,29 @@ #include <linux/types.h> -#include "../arch/x86/util/tsc.h" +#include "event.h" + +struct perf_tsc_conversion { + u16 time_shift; + u32 time_mult; + u64 time_zero; +}; +struct perf_event_mmap_page; + +int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, + struct perf_tsc_conversion *tc); u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc); u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc); u64 rdtsc(void); +struct perf_event_mmap_page; +struct perf_tool; +struct machine; + +int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, + struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine); + #endif diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index ee7e372..63687d3 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -32,6 +32,7 @@ #include "symbol.h" #include "util.h" #include "debug.h" +#include "asm/bug.h" extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, @@ -580,43 +581,33 @@ static unw_accessors_t accessors = { int unwind__prepare_access(struct thread *thread) { - unw_addr_space_t addr_space; - if (callchain_param.record_mode != CALLCHAIN_DWARF) return 0; - addr_space = unw_create_addr_space(&accessors, 0); - if (!addr_space) { + thread->addr_space = unw_create_addr_space(&accessors, 0); + if (!thread->addr_space) { pr_err("unwind: Can't create unwind address space.\n"); return -ENOMEM; } - unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL); - thread__set_priv(thread, addr_space); - + unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL); return 0; } void unwind__flush_access(struct thread *thread) { - unw_addr_space_t addr_space; - if (callchain_param.record_mode != CALLCHAIN_DWARF) return; - addr_space = thread__priv(thread); - unw_flush_cache(addr_space, 0, 0); + unw_flush_cache(thread->addr_space, 0, 0); } void unwind__finish_access(struct thread *thread) { - unw_addr_space_t addr_space; - if (callchain_param.record_mode != CALLCHAIN_DWARF) return; - addr_space = thread__priv(thread); - unw_destroy_addr_space(addr_space); + unw_destroy_addr_space(thread->addr_space); } static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, @@ -639,7 +630,9 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, * unwind itself. */ if (max_stack - 1 > 0) { - addr_space = thread__priv(ui->thread); + WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL"); + addr_space = ui->thread->addr_space; + if (addr_space == NULL) return -1; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index b7766c5..eab077a 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -33,6 +33,8 @@ struct callchain_param callchain_param = { unsigned int page_size; int cacheline_size; +unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH; + bool test_attr__enabled; bool perf_host = true; @@ -117,6 +119,40 @@ int rm_rf(char *path) return rmdir(path); } +/* A filter which removes dot files */ +bool lsdir_no_dot_filter(const char *name __maybe_unused, struct dirent *d) +{ + return d->d_name[0] != '.'; +} + +/* lsdir reads a directory and store it in strlist */ +struct strlist *lsdir(const char *name, + bool (*filter)(const char *, struct dirent *)) +{ + struct strlist *list = NULL; + DIR *dir; + struct dirent *d; + + dir = opendir(name); + if (!dir) + return NULL; + + list = strlist__new(NULL, NULL); + if (!list) { + errno = ENOMEM; + goto out; + } + + while ((d = readdir(dir)) != NULL) { + if (!filter || filter(name, d)) + strlist__add(list, d->d_name); + } + +out: + closedir(dir); + return list; +} + static int slow_copyfile(const char *from, const char *to) { int err = -1; @@ -471,7 +507,6 @@ int parse_callchain_record(const char *arg, struct callchain_param *param) "needed for --call-graph fp\n"); break; -#ifdef HAVE_DWARF_UNWIND_SUPPORT /* Dwarf style */ } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { const unsigned long default_stack_dump_size = 8192; @@ -487,7 +522,6 @@ int parse_callchain_record(const char *arg, struct callchain_param *param) ret = get_stack_size(tok, &size); param->dump_size = size; } -#endif /* HAVE_DWARF_UNWIND_SUPPORT */ } else if (!strncmp(name, "lbr", sizeof("lbr"))) { if (!strtok_r(NULL, ",", &saveptr)) { param->record_mode = CALLCHAIN_LBR; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 8298d60..7651633 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -79,6 +79,7 @@ #include <termios.h> #include <linux/bitops.h> #include <termios.h> +#include "strlist.h" extern const char *graph_line; extern const char *graph_dotted_line; @@ -159,12 +160,6 @@ static inline char *gitstrchrnul(const char *s, int c) } #endif -/* - * Wrappers: - */ -void *xrealloc(void *ptr, size_t size) __attribute__((weak)); - - static inline void *zalloc(size_t size) { return calloc(1, size); @@ -222,6 +217,8 @@ static inline int sane_case(int x, int high) int mkdir_p(char *path, mode_t mode); int rm_rf(char *path); +struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *)); +bool lsdir_no_dot_filter(const char *name, struct dirent *d); int copyfile(const char *from, const char *to); int copyfile_mode(const char *from, const char *to, mode_t mode); int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size); @@ -254,11 +251,17 @@ int hex2u64(const char *ptr, u64 *val); char *ltrim(char *s); char *rtrim(char *s); +static inline char *trim(char *s) +{ + return ltrim(rtrim(s)); +} + void dump_stack(void); void sighandler_dump_stack(int sig); extern unsigned int page_size; extern int cacheline_size; +extern unsigned int sysctl_perf_event_max_stack; struct parse_tag { char tag; diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c deleted file mode 100644 index 5f1a07c..0000000 --- a/tools/perf/util/wrapper.c +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Various trivial helper wrappers around standard functions - */ -#include "cache.h" - -/* - * There's no pack memory to release - but stay close to the Git - * version so wrap this away: - */ -static inline void release_pack_memory(size_t size __maybe_unused, - int flag __maybe_unused) -{ -} - -void *xrealloc(void *ptr, size_t size) -{ - void *ret = realloc(ptr, size); - if (!ret && !size) - ret = realloc(ptr, 1); - if (!ret) { - release_pack_memory(size, -1); - ret = realloc(ptr, size); - if (!ret && !size) - ret = realloc(ptr, 1); - if (!ret) - die("Out of memory, realloc failed"); - } - return ret; -} diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index b04afc3..ff9e5f2 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -19,6 +19,7 @@ TARGETS += powerpc TARGETS += pstore TARGETS += ptrace TARGETS += seccomp +TARGETS += sigaltstack TARGETS += size TARGETS += static_keys TARGETS += sysctl diff --git a/tools/testing/selftests/rcutorture/bin/jitter.sh b/tools/testing/selftests/rcutorture/bin/jitter.sh new file mode 100755 index 0000000..3633828 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/jitter.sh @@ -0,0 +1,90 @@ +#!/bin/bash +# +# Alternate sleeping and spinning on randomly selected CPUs. The purpose +# of this script is to inflict random OS jitter on a concurrently running +# test. +# +# Usage: jitter.sh me duration [ sleepmax [ spinmax ] ] +# +# me: Random-number-generator seed salt. +# duration: Time to run in seconds. +# sleepmax: Maximum microseconds to sleep, defaults to one second. +# spinmax: Maximum microseconds to spin, defaults to one millisecond. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, you can access it online at +# http://www.gnu.org/licenses/gpl-2.0.html. +# +# Copyright (C) IBM Corporation, 2016 +# +# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + +me=$(($1 * 1000)) +duration=$2 +sleepmax=${3-1000000} +spinmax=${4-1000} + +n=1 + +starttime=`awk 'BEGIN { print systime(); }' < /dev/null` + +while : +do + # Check for done. + t=`awk -v s=$starttime 'BEGIN { print systime() - s; }' < /dev/null` + if test "$t" -gt "$duration" + then + exit 0; + fi + + # Set affinity to randomly selected CPU + cpus=`ls /sys/devices/system/cpu/*/online | + sed -e 's,/[^/]*$,,' -e 's/^[^0-9]*//' | + grep -v '^0*$'` + cpumask=`awk -v cpus="$cpus" -v me=$me -v n=$n 'BEGIN { + srand(n + me + systime()); + ncpus = split(cpus, ca); + curcpu = ca[int(rand() * ncpus + 1)]; + mask = lshift(1, curcpu); + if (mask + 0 <= 0) + mask = 1; + printf("%#x\n", mask); + }' < /dev/null` + n=$(($n+1)) + if ! taskset -p $cpumask $$ > /dev/null 2>&1 + then + echo taskset failure: '"taskset -p ' $cpumask $$ '"' + exit 1 + fi + + # Sleep a random duration + sleeptime=`awk -v me=$me -v n=$n -v sleepmax=$sleepmax 'BEGIN { + srand(n + me + systime()); + printf("%06d", int(rand() * sleepmax)); + }' < /dev/null` + n=$(($n+1)) + sleep .$sleeptime + + # Spin a random duration + limit=`awk -v me=$me -v n=$n -v spinmax=$spinmax 'BEGIN { + srand(n + me + systime()); + printf("%06d", int(rand() * spinmax)); + }' < /dev/null` + n=$(($n+1)) + for i in {1..$limit} + do + echo > /dev/null + done +done + +exit 1 diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh new file mode 100755 index 0000000..f79b0e9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh @@ -0,0 +1,121 @@ +#!/bin/bash +# +# Analyze a given results directory for rcuperf performance measurements, +# looking for ftrace data. Exits with 0 if data was found, analyzed, and +# printed. Intended to be invoked from kvm-recheck-rcuperf.sh after +# argument checking. +# +# Usage: kvm-recheck-rcuperf-ftrace.sh resdir +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, you can access it online at +# http://www.gnu.org/licenses/gpl-2.0.html. +# +# Copyright (C) IBM Corporation, 2016 +# +# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + +i="$1" +. tools/testing/selftests/rcutorture/bin/functions.sh + +if test "`grep -c 'rcu_exp_grace_period.*start' < $i/console.log`" -lt 100 +then + exit 10 +fi + +sed -e 's/^\[[^]]*]//' < $i/console.log | +grep 'us : rcu_exp_grace_period' | +sed -e 's/us : / : /' | +tr -d '\015' | +awk ' +$8 == "start" { + if (starttask != "") + nlost++; + starttask = $1; + starttime = $3; + startseq = $7; +} + +$8 == "end" { + if (starttask == $1 && startseq == $7) { + curgpdur = $3 - starttime; + gptimes[++n] = curgpdur; + gptaskcnt[starttask]++; + sum += curgpdur; + if (curgpdur > 1000) + print "Long GP " starttime "us to " $3 "us (" curgpdur "us)"; + starttask = ""; + } else { + # Lost a message or some such, reset. + starttask = ""; + nlost++; + } +} + +$8 == "done" { + piggybackcnt[$1]++; +} + +END { + newNR = asort(gptimes); + if (newNR <= 0) { + print "No ftrace records found???" + exit 10; + } + pct50 = int(newNR * 50 / 100); + if (pct50 < 1) + pct50 = 1; + pct90 = int(newNR * 90 / 100); + if (pct90 < 1) + pct90 = 1; + pct99 = int(newNR * 99 / 100); + if (pct99 < 1) + pct99 = 1; + div = 10 ** int(log(gptimes[pct90]) / log(10) + .5) / 100; + print "Histogram bucket size: " div; + last = gptimes[1] - 10; + count = 0; + for (i = 1; i <= newNR; i++) { + current = div * int(gptimes[i] / div); + if (last == current) { + count++; + } else { + if (count > 0) + print last, count; + count = 1; + last = current; + } + } + if (count > 0) + print last, count; + print "Distribution of grace periods across tasks:"; + for (i in gptaskcnt) { + print "\t" i, gptaskcnt[i]; + nbatches += gptaskcnt[i]; + } + ngps = nbatches; + print "Distribution of piggybacking across tasks:"; + for (i in piggybackcnt) { + print "\t" i, piggybackcnt[i]; + ngps += piggybackcnt[i]; + } + print "Average grace-period duration: " sum / newNR " microseconds"; + print "Minimum grace-period duration: " gptimes[1]; + print "50th percentile grace-period duration: " gptimes[pct50]; + print "90th percentile grace-period duration: " gptimes[pct90]; + print "99th percentile grace-period duration: " gptimes[pct99]; + print "Maximum grace-period duration: " gptimes[newNR]; + print "Grace periods: " ngps + 0 " Batches: " nbatches + 0 " Ratio: " ngps / nbatches " Lost: " nlost + 0; + print "Computed from ftrace data."; +}' +exit 0 diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh new file mode 100755 index 0000000..8f3121a --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh @@ -0,0 +1,96 @@ +#!/bin/bash +# +# Analyze a given results directory for rcuperf performance measurements. +# +# Usage: kvm-recheck-rcuperf.sh resdir +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, you can access it online at +# http://www.gnu.org/licenses/gpl-2.0.html. +# +# Copyright (C) IBM Corporation, 2016 +# +# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + +i="$1" +if test -d $i +then + : +else + echo Unreadable results directory: $i + exit 1 +fi +PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH +. tools/testing/selftests/rcutorture/bin/functions.sh + +if kvm-recheck-rcuperf-ftrace.sh $i +then + # ftrace data was successfully analyzed, call it good! + exit 0 +fi + +configfile=`echo $i | sed -e 's/^.*\///'` + +sed -e 's/^\[[^]]*]//' < $i/console.log | +awk ' +/-perf: .* gps: .* batches:/ { + ngps = $9; + nbatches = $11; +} + +/-perf: .*writer-duration/ { + gptimes[++n] = $5 / 1000.; + sum += $5 / 1000.; +} + +END { + newNR = asort(gptimes); + if (newNR <= 0) { + print "No rcuperf records found???" + exit; + } + pct50 = int(newNR * 50 / 100); + if (pct50 < 1) + pct50 = 1; + pct90 = int(newNR * 90 / 100); + if (pct90 < 1) + pct90 = 1; + pct99 = int(newNR * 99 / 100); + if (pct99 < 1) + pct99 = 1; + div = 10 ** int(log(gptimes[pct90]) / log(10) + .5) / 100; + print "Histogram bucket size: " div; + last = gptimes[1] - 10; + count = 0; + for (i = 1; i <= newNR; i++) { + current = div * int(gptimes[i] / div); + if (last == current) { + count++; + } else { + if (count > 0) + print last, count; + count = 1; + last = current; + } + } + if (count > 0) + print last, count; + print "Average grace-period duration: " sum / newNR " microseconds"; + print "Minimum grace-period duration: " gptimes[1]; + print "50th percentile grace-period duration: " gptimes[pct50]; + print "90th percentile grace-period duration: " gptimes[pct90]; + print "99th percentile grace-period duration: " gptimes[pct99]; + print "Maximum grace-period duration: " gptimes[newNR]; + print "Grace periods: " ngps + 0 " Batches: " nbatches + 0 " Ratio: " ngps / nbatches; + print "Computed from rcuperf printk output."; +}' diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index d86bdd6..f659346 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -48,7 +48,10 @@ do cat $i/Make.oldconfig.err fi parse-build.sh $i/Make.out $configfile - parse-torture.sh $i/console.log $configfile + if test "$TORTURE_SUITE" != rcuperf + then + parse-torture.sh $i/console.log $configfile + fi parse-console.sh $i/console.log $configfile if test -r $i/Warnings then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 0f80eef..4109f30 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -6,7 +6,7 @@ # Execute this in the source tree. Do not run it as a background task # because qemu does not seem to like that much. # -# Usage: kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args +# Usage: kvm-test-1-run.sh config builddir resdir seconds qemu-args boot_args # # qemu-args defaults to "-enable-kvm -soundhw pcspk -nographic", along with # arguments specifying the number of CPUs and other @@ -91,25 +91,33 @@ fi # CONFIG_PCMCIA=n # CONFIG_CARDBUS=n # CONFIG_YENTA=n -if kvm-build.sh $config_template $builddir $T +base_resdir=`echo $resdir | sed -e 's/\.[0-9]\+$//'` +if test "$base_resdir" != "$resdir" -a -f $base_resdir/bzImage -a -f $base_resdir/vmlinux then + # Rerunning previous test, so use that test's kernel. + QEMU="`identify_qemu $base_resdir/vmlinux`" + KERNEL=$base_resdir/bzImage + ln -s $base_resdir/Make*.out $resdir # for kvm-recheck.sh + ln -s $base_resdir/.config $resdir # for kvm-recheck.sh +elif kvm-build.sh $config_template $builddir $T +then + # Had to build a kernel for this test. QEMU="`identify_qemu $builddir/vmlinux`" BOOT_IMAGE="`identify_boot_image $QEMU`" cp $builddir/Make*.out $resdir + cp $builddir/vmlinux $resdir cp $builddir/.config $resdir if test -n "$BOOT_IMAGE" then cp $builddir/$BOOT_IMAGE $resdir + KERNEL=$resdir/bzImage else echo No identifiable boot image, not running KVM, see $resdir. echo Do the torture scripts know about your architecture? fi parse-build.sh $resdir/Make.out $title - if test -f $builddir.wait - then - mv $builddir.wait $builddir.ready - fi else + # Build failed. cp $builddir/Make*.out $resdir cp $builddir/.config $resdir || : echo Build failed, not running KVM, see $resdir. @@ -119,12 +127,15 @@ else fi exit 1 fi +if test -f $builddir.wait +then + mv $builddir.wait $builddir.ready +fi while test -f $builddir.ready do sleep 1 done -minutes=$4 -seconds=$(($minutes * 60)) +seconds=$4 qemu_args=$5 boot_args=$6 @@ -167,15 +178,26 @@ then exit 0 fi echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log -echo $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd -( $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) & -qemu_pid=$! +echo $QEMU $qemu_args -m 512 -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd +( $QEMU $qemu_args -m 512 -kernel $KERNEL -append "$qemu_append $boot_args"& echo $! > $resdir/qemu_pid; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & commandcompleted=0 -echo Monitoring qemu job at pid $qemu_pid +sleep 10 # Give qemu's pid a chance to reach the file +if test -s "$resdir/qemu_pid" +then + qemu_pid=`cat "$resdir/qemu_pid"` + echo Monitoring qemu job at pid $qemu_pid +else + qemu_pid="" + echo Monitoring qemu job at yet-as-unknown pid +fi while : do + if test -z "$qemu_pid" -a -s "$resdir/qemu_pid" + then + qemu_pid=`cat "$resdir/qemu_pid"` + fi kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` - if kill -0 $qemu_pid > /dev/null 2>&1 + if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1 then if test $kruntime -ge $seconds then @@ -195,12 +217,16 @@ do ps -fp $killpid >> $resdir/Warnings 2>&1 fi else - echo ' ---' `date`: Kernel done + echo ' ---' `date`: "Kernel done" fi break fi done -if test $commandcompleted -eq 0 +if test -z "$qemu_pid" -a -s "$resdir/qemu_pid" +then + qemu_pid=`cat "$resdir/qemu_pid"` +fi +if test $commandcompleted -eq 0 -a -n "$qemu_pid" then echo Grace period for qemu job at pid $qemu_pid while : @@ -220,6 +246,9 @@ then fi sleep 1 done +elif test -z "$qemu_pid" +then + echo Unknown PID, cannot kill qemu command fi parse-torture.sh $resdir/console.log $title diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 4a43176..0d59814 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -34,7 +34,7 @@ T=/tmp/kvm.sh.$$ trap 'rm -rf $T' 0 mkdir $T -dur=30 +dur=$((30*60)) dryrun="" KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM PATH=${KVM}/bin:$PATH; export PATH @@ -48,6 +48,7 @@ resdir="" configs="" cpus=0 ds=`date +%Y.%m.%d-%H:%M:%S` +jitter=0 . functions.sh @@ -63,6 +64,7 @@ usage () { echo " --dryrun sched|script" echo " --duration minutes" echo " --interactive" + echo " --jitter N [ maxsleep (us) [ maxspin (us) ] ]" echo " --kmake-arg kernel-make-arguments" echo " --mac nn:nn:nn:nn:nn:nn" echo " --no-initrd" @@ -116,12 +118,17 @@ do ;; --duration) checkarg --duration "(minutes)" $# "$2" '^[0-9]*$' '^error' - dur=$2 + dur=$(($2*60)) shift ;; --interactive) TORTURE_QEMU_INTERACTIVE=1; export TORTURE_QEMU_INTERACTIVE ;; + --jitter) + checkarg --jitter "(# threads [ sleep [ spin ] ])" $# "$2" '^-\{,1\}[0-9]\+\( \+[0-9]\+\)\{,2\} *$' '^error$' + jitter="$2" + shift + ;; --kmake-arg) checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$' TORTURE_KMAKE_ARG="$2" @@ -156,7 +163,7 @@ do shift ;; --torture) - checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\)$' '^--' + checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\)$' '^--' TORTURE_SUITE=$2 shift ;; @@ -299,6 +306,7 @@ awk < $T/cfgcpu.pack \ -v CONFIGDIR="$CONFIGFRAG/" \ -v KVM="$KVM" \ -v ncpus=$cpus \ + -v jitter="$jitter" \ -v rd=$resdir/$ds/ \ -v dur=$dur \ -v TORTURE_QEMU_ARG="$TORTURE_QEMU_ARG" \ @@ -359,6 +367,16 @@ function dump(first, pastlast, batchnum) print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log"; print "fi" } + njitter = 0; + split(jitter, ja); + if (ja[1] == -1 && ncpus == 0) + njitter = 1; + else if (ja[1] == -1) + njitter = ncpus; + else + njitter = ja[1]; + for (j = 0; j < njitter; j++) + print "jitter.sh " j " " dur " " ja[2] " " ja[3] "&" print "wait" print "if test -z \"$TORTURE_BUILDONLY\"" print "then" diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 39a2c6d..17cbe09 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -14,7 +14,7 @@ CONFIG_HOTPLUG_CPU=n CONFIG_SUSPEND=n CONFIG_HIBERNATION=n CONFIG_RCU_FANOUT=4 -CONFIG_RCU_FANOUT_LEAF=4 +CONFIG_RCU_FANOUT_LEAF=3 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot index 0fc8a34..e34c334 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot @@ -1 +1 @@ -rcutorture.torture_type=rcu_bh +rcutorture.torture_type=rcu_bh rcutree.rcu_fanout_leaf=4 diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/CFLIST b/tools/testing/selftests/rcutorture/configs/rcuperf/CFLIST new file mode 100644 index 0000000..c9f56cf --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcuperf/CFLIST @@ -0,0 +1 @@ +TREE diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/CFcommon b/tools/testing/selftests/rcutorture/configs/rcuperf/CFcommon new file mode 100644 index 0000000..a09816b --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcuperf/CFcommon @@ -0,0 +1,2 @@ +CONFIG_RCU_PERF_TEST=y +CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE new file mode 100644 index 0000000..a312f67 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE @@ -0,0 +1,20 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +#CHECK#CONFIG_PREEMPT_RCU=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_RCU_TRACE=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y +CONFIG_RCU_TRACE=y diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 new file mode 100644 index 0000000..985fb17 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 @@ -0,0 +1,23 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=54 +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +#CHECK#CONFIG_PREEMPT_RCU=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_RCU_TRACE=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_FANOUT=3 +CONFIG_RCU_FANOUT_LEAF=2 +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y +CONFIG_RCU_TRACE=y diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh new file mode 100644 index 0000000..34f2a1b --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh @@ -0,0 +1,52 @@ +#!/bin/bash +# +# Torture-suite-dependent shell functions for the rest of the scripts. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, you can access it online at +# http://www.gnu.org/licenses/gpl-2.0.html. +# +# Copyright (C) IBM Corporation, 2015 +# +# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + +# rcuperf_param_nreaders bootparam-string +# +# Adds nreaders rcuperf module parameter if not already specified. +rcuperf_param_nreaders () { + if ! echo "$1" | grep -q "rcuperf.nreaders" + then + echo rcuperf.nreaders=-1 + fi +} + +# rcuperf_param_nwriters bootparam-string +# +# Adds nwriters rcuperf module parameter if not already specified. +rcuperf_param_nwriters () { + if ! echo "$1" | grep -q "rcuperf.nwriters" + then + echo rcuperf.nwriters=-1 + fi +} + +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +per_version_boot_params () { + echo $1 `rcuperf_param_nreaders "$1"` \ + `rcuperf_param_nwriters "$1"` \ + rcuperf.perf_runnable=1 \ + rcuperf.shutdown=1 \ + rcuperf.verbose=1 +} diff --git a/tools/testing/selftests/sigaltstack/Makefile b/tools/testing/selftests/sigaltstack/Makefile new file mode 100644 index 0000000..56af56e --- /dev/null +++ b/tools/testing/selftests/sigaltstack/Makefile @@ -0,0 +1,8 @@ +CFLAGS = -Wall +BINARIES = sas +all: $(BINARIES) + +include ../lib.mk + +clean: + rm -rf $(BINARIES) diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c new file mode 100644 index 0000000..1bb0125 --- /dev/null +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -0,0 +1,176 @@ +/* + * Stas Sergeev <stsp@users.sourceforge.net> + * + * test sigaltstack(SS_ONSTACK | SS_AUTODISARM) + * If that succeeds, then swapcontext() can be used inside sighandler safely. + * + */ + +#define _GNU_SOURCE +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <ucontext.h> +#include <alloca.h> +#include <string.h> +#include <assert.h> +#include <errno.h> + +#ifndef SS_AUTODISARM +#define SS_AUTODISARM (1U << 31) +#endif + +static void *sstack, *ustack; +static ucontext_t uc, sc; +static const char *msg = "[OK]\tStack preserved"; +static const char *msg2 = "[FAIL]\tStack corrupted"; +struct stk_data { + char msg[128]; + int flag; +}; + +void my_usr1(int sig, siginfo_t *si, void *u) +{ + char *aa; + int err; + stack_t stk; + struct stk_data *p; + + register unsigned long sp asm("sp"); + + if (sp < (unsigned long)sstack || + sp >= (unsigned long)sstack + SIGSTKSZ) { + printf("[FAIL]\tSP is not on sigaltstack\n"); + exit(EXIT_FAILURE); + } + /* put some data on stack. other sighandler will try to overwrite it */ + aa = alloca(1024); + assert(aa); + p = (struct stk_data *)(aa + 512); + strcpy(p->msg, msg); + p->flag = 1; + printf("[RUN]\tsignal USR1\n"); + err = sigaltstack(NULL, &stk); + if (err) { + perror("[FAIL]\tsigaltstack()"); + exit(EXIT_FAILURE); + } + if (stk.ss_flags != SS_DISABLE) + printf("[FAIL]\tss_flags=%i, should be SS_DISABLE\n", + stk.ss_flags); + else + printf("[OK]\tsigaltstack is disabled in sighandler\n"); + swapcontext(&sc, &uc); + printf("%s\n", p->msg); + if (!p->flag) { + printf("[RUN]\tAborting\n"); + exit(EXIT_FAILURE); + } +} + +void my_usr2(int sig, siginfo_t *si, void *u) +{ + char *aa; + struct stk_data *p; + + printf("[RUN]\tsignal USR2\n"); + aa = alloca(1024); + /* dont run valgrind on this */ + /* try to find the data stored by previous sighandler */ + p = memmem(aa, 1024, msg, strlen(msg)); + if (p) { + printf("[FAIL]\tsigaltstack re-used\n"); + /* corrupt the data */ + strcpy(p->msg, msg2); + /* tell other sighandler that his data is corrupted */ + p->flag = 0; + } +} + +static void switch_fn(void) +{ + printf("[RUN]\tswitched to user ctx\n"); + raise(SIGUSR2); + setcontext(&sc); +} + +int main(void) +{ + struct sigaction act; + stack_t stk; + int err; + + sigemptyset(&act.sa_mask); + act.sa_flags = SA_ONSTACK | SA_SIGINFO; + act.sa_sigaction = my_usr1; + sigaction(SIGUSR1, &act, NULL); + act.sa_sigaction = my_usr2; + sigaction(SIGUSR2, &act, NULL); + sstack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (sstack == MAP_FAILED) { + perror("mmap()"); + return EXIT_FAILURE; + } + + err = sigaltstack(NULL, &stk); + if (err) { + perror("[FAIL]\tsigaltstack()"); + exit(EXIT_FAILURE); + } + if (stk.ss_flags == SS_DISABLE) { + printf("[OK]\tInitial sigaltstack state was SS_DISABLE\n"); + } else { + printf("[FAIL]\tInitial sigaltstack state was %i; should have been SS_DISABLE\n", stk.ss_flags); + return EXIT_FAILURE; + } + + stk.ss_sp = sstack; + stk.ss_size = SIGSTKSZ; + stk.ss_flags = SS_ONSTACK | SS_AUTODISARM; + err = sigaltstack(&stk, NULL); + if (err) { + if (errno == EINVAL) { + printf("[NOTE]\tThe running kernel doesn't support SS_AUTODISARM\n"); + /* + * If test cases for the !SS_AUTODISARM variant were + * added, we could still run them. We don't have any + * test cases like that yet, so just exit and report + * success. + */ + return 0; + } else { + perror("[FAIL]\tsigaltstack(SS_ONSTACK | SS_AUTODISARM)"); + return EXIT_FAILURE; + } + } + + ustack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (ustack == MAP_FAILED) { + perror("mmap()"); + return EXIT_FAILURE; + } + getcontext(&uc); + uc.uc_link = NULL; + uc.uc_stack.ss_sp = ustack; + uc.uc_stack.ss_size = SIGSTKSZ; + makecontext(&uc, switch_fn, 0); + raise(SIGUSR1); + + err = sigaltstack(NULL, &stk); + if (err) { + perror("[FAIL]\tsigaltstack()"); + exit(EXIT_FAILURE); + } + if (stk.ss_flags != SS_AUTODISARM) { + printf("[FAIL]\tss_flags=%i, should be SS_AUTODISARM\n", + stk.ss_flags); + exit(EXIT_FAILURE); + } + printf("[OK]\tsigaltstack is still SS_AUTODISARM after signal\n"); + + printf("[OK]\tTest passed\n"); + return 0; +} diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index b47ebd1..c73425d 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -9,6 +9,7 @@ TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_sysc TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer +TARGETS_C_64BIT_ONLY := fsgsbase TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY) diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c new file mode 100644 index 0000000..5b2b4b3 --- /dev/null +++ b/tools/testing/selftests/x86/fsgsbase.c @@ -0,0 +1,398 @@ +/* + * fsgsbase.c, an fsgsbase test + * Copyright (c) 2014-2016 Andy Lutomirski + * GPL v2 + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <err.h> +#include <sys/user.h> +#include <asm/prctl.h> +#include <sys/prctl.h> +#include <signal.h> +#include <limits.h> +#include <sys/ucontext.h> +#include <sched.h> +#include <linux/futex.h> +#include <pthread.h> +#include <asm/ldt.h> +#include <sys/mman.h> + +#ifndef __x86_64__ +# error This test is 64-bit only +#endif + +static volatile sig_atomic_t want_segv; +static volatile unsigned long segv_addr; + +static int nerrs; + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void sigsegv(int sig, siginfo_t *si, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + if (!want_segv) { + clearhandler(SIGSEGV); + return; /* Crash cleanly. */ + } + + want_segv = false; + segv_addr = (unsigned long)si->si_addr; + + ctx->uc_mcontext.gregs[REG_RIP] += 4; /* Skip the faulting mov */ + +} + +enum which_base { FS, GS }; + +static unsigned long read_base(enum which_base which) +{ + unsigned long offset; + /* + * Unless we have FSGSBASE, there's no direct way to do this from + * user mode. We can get at it indirectly using signals, though. + */ + + want_segv = true; + + offset = 0; + if (which == FS) { + /* Use a constant-length instruction here. */ + asm volatile ("mov %%fs:(%%rcx), %%rax" : : "c" (offset) : "rax"); + } else { + asm volatile ("mov %%gs:(%%rcx), %%rax" : : "c" (offset) : "rax"); + } + if (!want_segv) + return segv_addr + offset; + + /* + * If that didn't segfault, try the other end of the address space. + * Unless we get really unlucky and run into the vsyscall page, this + * is guaranteed to segfault. + */ + + offset = (ULONG_MAX >> 1) + 1; + if (which == FS) { + asm volatile ("mov %%fs:(%%rcx), %%rax" + : : "c" (offset) : "rax"); + } else { + asm volatile ("mov %%gs:(%%rcx), %%rax" + : : "c" (offset) : "rax"); + } + if (!want_segv) + return segv_addr + offset; + + abort(); +} + +static void check_gs_value(unsigned long value) +{ + unsigned long base; + unsigned short sel; + + printf("[RUN]\tARCH_SET_GS to 0x%lx\n", value); + if (syscall(SYS_arch_prctl, ARCH_SET_GS, value) != 0) + err(1, "ARCH_SET_GS"); + + asm volatile ("mov %%gs, %0" : "=rm" (sel)); + base = read_base(GS); + if (base == value) { + printf("[OK]\tGSBASE was set as expected (selector 0x%hx)\n", + sel); + } else { + nerrs++; + printf("[FAIL]\tGSBASE was not as expected: got 0x%lx (selector 0x%hx)\n", + base, sel); + } + + if (syscall(SYS_arch_prctl, ARCH_GET_GS, &base) != 0) + err(1, "ARCH_GET_GS"); + if (base == value) { + printf("[OK]\tARCH_GET_GS worked as expected (selector 0x%hx)\n", + sel); + } else { + nerrs++; + printf("[FAIL]\tARCH_GET_GS was not as expected: got 0x%lx (selector 0x%hx)\n", + base, sel); + } +} + +static void mov_0_gs(unsigned long initial_base, bool schedule) +{ + unsigned long base, arch_base; + + printf("[RUN]\tARCH_SET_GS to 0x%lx then mov 0 to %%gs%s\n", initial_base, schedule ? " and schedule " : ""); + if (syscall(SYS_arch_prctl, ARCH_SET_GS, initial_base) != 0) + err(1, "ARCH_SET_GS"); + + if (schedule) + usleep(10); + + asm volatile ("mov %0, %%gs" : : "rm" (0)); + base = read_base(GS); + if (syscall(SYS_arch_prctl, ARCH_GET_GS, &arch_base) != 0) + err(1, "ARCH_GET_GS"); + if (base == arch_base) { + printf("[OK]\tGSBASE is 0x%lx\n", base); + } else { + nerrs++; + printf("[FAIL]\tGSBASE changed to 0x%lx but kernel reports 0x%lx\n", base, arch_base); + } +} + +static volatile unsigned long remote_base; +static volatile bool remote_hard_zero; +static volatile unsigned int ftx; + +/* + * ARCH_SET_FS/GS(0) may or may not program a selector of zero. HARD_ZERO + * means to force the selector to zero to improve test coverage. + */ +#define HARD_ZERO 0xa1fa5f343cb85fa4 + +static void do_remote_base() +{ + unsigned long to_set = remote_base; + bool hard_zero = false; + if (to_set == HARD_ZERO) { + to_set = 0; + hard_zero = true; + } + + if (syscall(SYS_arch_prctl, ARCH_SET_GS, to_set) != 0) + err(1, "ARCH_SET_GS"); + + if (hard_zero) + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0)); + + unsigned short sel; + asm volatile ("mov %%gs, %0" : "=rm" (sel)); + printf("\tother thread: ARCH_SET_GS(0x%lx)%s -- sel is 0x%hx\n", + to_set, hard_zero ? " and clear gs" : "", sel); +} + +void do_unexpected_base(void) +{ + /* + * The goal here is to try to arrange for GS == 0, GSBASE != + * 0, and for the the kernel the think that GSBASE == 0. + * + * To make the test as reliable as possible, this uses + * explicit descriptorss. (This is not the only way. This + * could use ARCH_SET_GS with a low, nonzero base, but the + * relevant side effect of ARCH_SET_GS could change.) + */ + + /* Step 1: tell the kernel that we have GSBASE == 0. */ + if (syscall(SYS_arch_prctl, ARCH_SET_GS, 0) != 0) + err(1, "ARCH_SET_GS"); + + /* Step 2: change GSBASE without telling the kernel. */ + struct user_desc desc = { + .entry_number = 0, + .base_addr = 0xBAADF00D, + .limit = 0xfffff, + .seg_32bit = 1, + .contents = 0, /* Data, grow-up */ + .read_exec_only = 0, + .limit_in_pages = 1, + .seg_not_present = 0, + .useable = 0 + }; + if (syscall(SYS_modify_ldt, 1, &desc, sizeof(desc)) == 0) { + printf("\tother thread: using LDT slot 0\n"); + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0x7)); + } else { + /* No modify_ldt for us (configured out, perhaps) */ + + struct user_desc *low_desc = mmap( + NULL, sizeof(desc), + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0); + memcpy(low_desc, &desc, sizeof(desc)); + + low_desc->entry_number = -1; + + /* 32-bit set_thread_area */ + long ret; + asm volatile ("int $0x80" + : "=a" (ret) : "a" (243), "b" (low_desc) + : "flags"); + memcpy(&desc, low_desc, sizeof(desc)); + munmap(low_desc, sizeof(desc)); + + if (ret != 0) { + printf("[NOTE]\tcould not create a segment -- test won't do anything\n"); + return; + } + printf("\tother thread: using GDT slot %d\n", desc.entry_number); + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)((desc.entry_number << 3) | 0x3))); + } + + /* + * Step 3: set the selector back to zero. On AMD chips, this will + * preserve GSBASE. + */ + + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0)); +} + +static void *threadproc(void *ctx) +{ + while (1) { + while (ftx == 0) + syscall(SYS_futex, &ftx, FUTEX_WAIT, 0, NULL, NULL, 0); + if (ftx == 3) + return NULL; + + if (ftx == 1) + do_remote_base(); + else if (ftx == 2) + do_unexpected_base(); + else + errx(1, "helper thread got bad command"); + + ftx = 0; + syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0); + } +} + +static void set_gs_and_switch_to(unsigned long local, unsigned long remote) +{ + unsigned long base; + + bool hard_zero = false; + if (local == HARD_ZERO) { + hard_zero = true; + local = 0; + } + + printf("[RUN]\tARCH_SET_GS(0x%lx)%s, then schedule to 0x%lx\n", + local, hard_zero ? " and clear gs" : "", remote); + if (syscall(SYS_arch_prctl, ARCH_SET_GS, local) != 0) + err(1, "ARCH_SET_GS"); + if (hard_zero) + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0)); + + if (read_base(GS) != local) { + nerrs++; + printf("[FAIL]\tGSBASE wasn't set as expected\n"); + } + + remote_base = remote; + ftx = 1; + syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0); + while (ftx != 0) + syscall(SYS_futex, &ftx, FUTEX_WAIT, 1, NULL, NULL, 0); + + base = read_base(GS); + if (base == local) { + printf("[OK]\tGSBASE remained 0x%lx\n", local); + } else { + nerrs++; + printf("[FAIL]\tGSBASE changed to 0x%lx\n", base); + } +} + +static void test_unexpected_base(void) +{ + unsigned long base; + + printf("[RUN]\tARCH_SET_GS(0), clear gs, then manipulate GSBASE in a different thread\n"); + if (syscall(SYS_arch_prctl, ARCH_SET_GS, 0) != 0) + err(1, "ARCH_SET_GS"); + asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0)); + + ftx = 2; + syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0); + while (ftx != 0) + syscall(SYS_futex, &ftx, FUTEX_WAIT, 1, NULL, NULL, 0); + + base = read_base(GS); + if (base == 0) { + printf("[OK]\tGSBASE remained 0\n"); + } else { + nerrs++; + printf("[FAIL]\tGSBASE changed to 0x%lx\n", base); + } +} + +int main() +{ + pthread_t thread; + + sethandler(SIGSEGV, sigsegv, 0); + + check_gs_value(0); + check_gs_value(1); + check_gs_value(0x200000000); + check_gs_value(0); + check_gs_value(0x200000000); + check_gs_value(1); + + for (int sched = 0; sched < 2; sched++) { + mov_0_gs(0, !!sched); + mov_0_gs(1, !!sched); + mov_0_gs(0x200000000, !!sched); + } + + /* Set up for multithreading. */ + + cpu_set_t cpuset; + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) + err(1, "sched_setaffinity to CPU 0"); /* should never fail */ + + if (pthread_create(&thread, 0, threadproc, 0) != 0) + err(1, "pthread_create"); + + static unsigned long bases_with_hard_zero[] = { + 0, HARD_ZERO, 1, 0x200000000, + }; + + for (int local = 0; local < 4; local++) { + for (int remote = 0; remote < 4; remote++) { + set_gs_and_switch_to(bases_with_hard_zero[local], + bases_with_hard_zero[remote]); + } + } + + test_unexpected_base(); + + ftx = 3; /* Kill the thread. */ + syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0); + + if (pthread_join(thread, NULL) != 0) + err(1, "pthread_join"); + + return nerrs == 0 ? 0 : 1; +} diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c index 31a3035..4af4707 100644 --- a/tools/testing/selftests/x86/ldt_gdt.c +++ b/tools/testing/selftests/x86/ldt_gdt.c @@ -21,6 +21,9 @@ #include <pthread.h> #include <sched.h> #include <linux/futex.h> +#include <sys/mman.h> +#include <asm/prctl.h> +#include <sys/prctl.h> #define AR_ACCESSED (1<<8) @@ -44,6 +47,12 @@ static int nerrs; +/* Points to an array of 1024 ints, each holding its own index. */ +static const unsigned int *counter_page; +static struct user_desc *low_user_desc; +static struct user_desc *low_user_desc_clear; /* Use to delete GDT entry */ +static int gdt_entry_num; + static void check_invalid_segment(uint16_t index, int ldt) { uint32_t has_limit = 0, has_ar = 0, limit, ar; @@ -561,16 +570,257 @@ static void do_exec_test(void) } } +static void setup_counter_page(void) +{ + unsigned int *page = mmap(NULL, 4096, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_32BIT, -1, 0); + if (page == MAP_FAILED) + err(1, "mmap"); + + for (int i = 0; i < 1024; i++) + page[i] = i; + counter_page = page; +} + +static int invoke_set_thread_area(void) +{ + int ret; + asm volatile ("int $0x80" + : "=a" (ret), "+m" (low_user_desc) : + "a" (243), "b" (low_user_desc) + : "flags"); + return ret; +} + +static void setup_low_user_desc(void) +{ + low_user_desc = mmap(NULL, 2 * sizeof(struct user_desc), + PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_32BIT, -1, 0); + if (low_user_desc == MAP_FAILED) + err(1, "mmap"); + + low_user_desc->entry_number = -1; + low_user_desc->base_addr = (unsigned long)&counter_page[1]; + low_user_desc->limit = 0xfffff; + low_user_desc->seg_32bit = 1; + low_user_desc->contents = 0; /* Data, grow-up*/ + low_user_desc->read_exec_only = 0; + low_user_desc->limit_in_pages = 1; + low_user_desc->seg_not_present = 0; + low_user_desc->useable = 0; + + if (invoke_set_thread_area() == 0) { + gdt_entry_num = low_user_desc->entry_number; + printf("[NOTE]\tset_thread_area is available; will use GDT index %d\n", gdt_entry_num); + } else { + printf("[NOTE]\tset_thread_area is unavailable\n"); + } + + low_user_desc_clear = low_user_desc + 1; + low_user_desc_clear->entry_number = gdt_entry_num; + low_user_desc_clear->read_exec_only = 1; + low_user_desc_clear->seg_not_present = 1; +} + +static void test_gdt_invalidation(void) +{ + if (!gdt_entry_num) + return; /* 64-bit only system -- we can't use set_thread_area */ + + unsigned short prev_sel; + unsigned short sel; + unsigned int eax; + const char *result; +#ifdef __x86_64__ + unsigned long saved_base; + unsigned long new_base; +#endif + + /* Test DS */ + invoke_set_thread_area(); + eax = 243; + sel = (gdt_entry_num << 3) | 3; + asm volatile ("movw %%ds, %[prev_sel]\n\t" + "movw %[sel], %%ds\n\t" +#ifdef __i386__ + "pushl %%ebx\n\t" +#endif + "movl %[arg1], %%ebx\n\t" + "int $0x80\n\t" /* Should invalidate ds */ +#ifdef __i386__ + "popl %%ebx\n\t" +#endif + "movw %%ds, %[sel]\n\t" + "movw %[prev_sel], %%ds" + : [prev_sel] "=&r" (prev_sel), [sel] "+r" (sel), + "+a" (eax) + : "m" (low_user_desc_clear), + [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) + : "flags"); + + if (sel != 0) { + result = "FAIL"; + nerrs++; + } else { + result = "OK"; + } + printf("[%s]\tInvalidate DS with set_thread_area: new DS = 0x%hx\n", + result, sel); + + /* Test ES */ + invoke_set_thread_area(); + eax = 243; + sel = (gdt_entry_num << 3) | 3; + asm volatile ("movw %%es, %[prev_sel]\n\t" + "movw %[sel], %%es\n\t" +#ifdef __i386__ + "pushl %%ebx\n\t" +#endif + "movl %[arg1], %%ebx\n\t" + "int $0x80\n\t" /* Should invalidate es */ +#ifdef __i386__ + "popl %%ebx\n\t" +#endif + "movw %%es, %[sel]\n\t" + "movw %[prev_sel], %%es" + : [prev_sel] "=&r" (prev_sel), [sel] "+r" (sel), + "+a" (eax) + : "m" (low_user_desc_clear), + [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) + : "flags"); + + if (sel != 0) { + result = "FAIL"; + nerrs++; + } else { + result = "OK"; + } + printf("[%s]\tInvalidate ES with set_thread_area: new ES = 0x%hx\n", + result, sel); + + /* Test FS */ + invoke_set_thread_area(); + eax = 243; + sel = (gdt_entry_num << 3) | 3; +#ifdef __x86_64__ + syscall(SYS_arch_prctl, ARCH_GET_FS, &saved_base); +#endif + asm volatile ("movw %%fs, %[prev_sel]\n\t" + "movw %[sel], %%fs\n\t" +#ifdef __i386__ + "pushl %%ebx\n\t" +#endif + "movl %[arg1], %%ebx\n\t" + "int $0x80\n\t" /* Should invalidate fs */ +#ifdef __i386__ + "popl %%ebx\n\t" +#endif + "movw %%fs, %[sel]\n\t" + : [prev_sel] "=&r" (prev_sel), [sel] "+r" (sel), + "+a" (eax) + : "m" (low_user_desc_clear), + [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) + : "flags"); + +#ifdef __x86_64__ + syscall(SYS_arch_prctl, ARCH_GET_FS, &new_base); +#endif + + /* Restore FS/BASE for glibc */ + asm volatile ("movw %[prev_sel], %%fs" : : [prev_sel] "rm" (prev_sel)); +#ifdef __x86_64__ + if (saved_base) + syscall(SYS_arch_prctl, ARCH_SET_FS, saved_base); +#endif + + if (sel != 0) { + result = "FAIL"; + nerrs++; + } else { + result = "OK"; + } + printf("[%s]\tInvalidate FS with set_thread_area: new FS = 0x%hx\n", + result, sel); + +#ifdef __x86_64__ + if (sel == 0 && new_base != 0) { + nerrs++; + printf("[FAIL]\tNew FSBASE was 0x%lx\n", new_base); + } else { + printf("[OK]\tNew FSBASE was zero\n"); + } +#endif + + /* Test GS */ + invoke_set_thread_area(); + eax = 243; + sel = (gdt_entry_num << 3) | 3; +#ifdef __x86_64__ + syscall(SYS_arch_prctl, ARCH_GET_GS, &saved_base); +#endif + asm volatile ("movw %%gs, %[prev_sel]\n\t" + "movw %[sel], %%gs\n\t" +#ifdef __i386__ + "pushl %%ebx\n\t" +#endif + "movl %[arg1], %%ebx\n\t" + "int $0x80\n\t" /* Should invalidate gs */ +#ifdef __i386__ + "popl %%ebx\n\t" +#endif + "movw %%gs, %[sel]\n\t" + : [prev_sel] "=&r" (prev_sel), [sel] "+r" (sel), + "+a" (eax) + : "m" (low_user_desc_clear), + [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) + : "flags"); + +#ifdef __x86_64__ + syscall(SYS_arch_prctl, ARCH_GET_GS, &new_base); +#endif + + /* Restore GS/BASE for glibc */ + asm volatile ("movw %[prev_sel], %%gs" : : [prev_sel] "rm" (prev_sel)); +#ifdef __x86_64__ + if (saved_base) + syscall(SYS_arch_prctl, ARCH_SET_GS, saved_base); +#endif + + if (sel != 0) { + result = "FAIL"; + nerrs++; + } else { + result = "OK"; + } + printf("[%s]\tInvalidate GS with set_thread_area: new GS = 0x%hx\n", + result, sel); + +#ifdef __x86_64__ + if (sel == 0 && new_base != 0) { + nerrs++; + printf("[FAIL]\tNew GSBASE was 0x%lx\n", new_base); + } else { + printf("[OK]\tNew GSBASE was zero\n"); + } +#endif +} + int main(int argc, char **argv) { if (argc == 1 && !strcmp(argv[0], "ldt_gdt_test_exec")) return finish_exec_test(); + setup_counter_page(); + setup_low_user_desc(); + do_simple_tests(); do_multicpu_tests(); do_exec_test(); + test_gdt_invalidation(); + return nerrs ? 1 : 0; } |
