Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Ingo Molnar:
 "Misc changes:
   - fix lguest bug
   - fix /proc/meminfo output on certain configs
   - fix pvclock bug
   - fix reboot on certain iMacs by adding new reboot quirk
   - fix bootup crash
   - fix FPU boot line option parsing
   - add more x86 self-tests
   - small cleanups, documentation improvements, etc"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu/amd: Remove an unneeded condition in srat_detect_node()
  x86/vdso/pvclock: Protect STABLE check with the seqcount
  x86/mm: Improve switch_mm() barrier comments
  selftests/x86: Test __kernel_sigreturn and __kernel_rt_sigreturn
  x86/reboot/quirks: Add iMac10,1 to pci_reboot_dmi_table[]
  lguest: Map switcher text R/O
  x86/boot: Hide local labels in verify_cpu()
  x86/fpu: Disable AVX when eagerfpu is off
  x86/fpu: Disable MPX when eagerfpu is off
  x86/fpu: Disable XGETBV1 when no XSAVE
  x86/fpu: Fix early FPU command-line parsing
  x86/mm: Use PAGE_ALIGNED instead of IS_ALIGNED
  selftests/x86: Disable the ldt_gdt_64 test for now
  x86/mm/pat: Make split_page_count() check for empty levels to fix /proc/meminfo output
  x86/boot: Double BOOT_HEAP_SIZE to 64KB
  x86/mm: Add barriers and document switch_mm()-vs-flush synchronization

5 files changed, 119 insertions, 107 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e678dde..a07956a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -434,8 +434,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 		 */
 		int ht_nodeid = c->initial_apicid;
 
-		if (ht_nodeid >= 0 &&
-		    __apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+		if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
 			node = __apicid_to_node[ht_nodeid];
 		/* Pick a nearby node */
 		if (!node_online(node))
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 7b2978a..6d9f0a7 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -3,8 +3,11 @@
  */
 #include <asm/fpu/internal.h>
 #include <asm/tlbflush.h>
+#include <asm/setup.h>
+#include <asm/cmdline.h>
 
 #include <linux/sched.h>
+#include <linux/init.h>
 
 /*
  * Initialize the TS bit in CR0 according to the style of context-switches
@@ -270,20 +273,52 @@ static void __init fpu__init_system_xstate_size_legacy(void)
  */
 static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
 
-static int __init eager_fpu_setup(char *s)
+/*
+ * Find supported xfeatures based on cpu features and command-line input.
+ * This must be called after fpu__init_parse_early_param() is called and
+ * xfeatures_mask is enumerated.
+ */
+u64 __init fpu__get_supported_xfeatures_mask(void)
 {
-	if (!strcmp(s, "on"))
-		eagerfpu = ENABLE;
-	else if (!strcmp(s, "off"))
-		eagerfpu = DISABLE;
-	else if (!strcmp(s, "auto"))
-		eagerfpu = AUTO;
-	return 1;
+	/* Support all xfeatures known to us */
+	if (eagerfpu != DISABLE)
+		return XCNTXT_MASK;
+
+	/* Warning of xfeatures being disabled for no eagerfpu mode */
+	if (xfeatures_mask & XFEATURE_MASK_EAGER) {
+		pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
+			xfeatures_mask & XFEATURE_MASK_EAGER);
+	}
+
+	/* Return a mask that masks out all features requiring eagerfpu mode */
+	return ~XFEATURE_MASK_EAGER;
+}
+
+/*
+ * Disable features dependent on eagerfpu.
+ */
+static void __init fpu__clear_eager_fpu_features(void)
+{
+	setup_clear_cpu_cap(X86_FEATURE_MPX);
+	setup_clear_cpu_cap(X86_FEATURE_AVX);
+	setup_clear_cpu_cap(X86_FEATURE_AVX2);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512F);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512PF);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512ER);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512CD);
 }
-__setup("eagerfpu=", eager_fpu_setup);
 
 /*
  * Pick the FPU context switching strategy:
+ *
+ * When eagerfpu is AUTO or ENABLE, we ensure it is ENABLE if either of
+ * the following is true:
+ *
+ * (1) the cpu has xsaveopt, as it has the optimization and doing eager
+ *     FPU switching has a relatively low cost compared to a plain xsave;
+ * (2) the cpu has xsave features (e.g. MPX) that depend on eager FPU
+ *     switching. Should the kernel boot with noxsaveopt, we support MPX
+ *     with eager FPU switching at a higher cost.
  */
 static void __init fpu__init_system_ctx_switch(void)
 {
@@ -295,19 +330,11 @@ static void __init fpu__init_system_ctx_switch(void)
 	WARN_ON_FPU(current->thread.fpu.fpstate_active);
 	current_thread_info()->status = 0;
 
-	/* Auto enable eagerfpu for xsaveopt */
 	if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE)
 		eagerfpu = ENABLE;
 
-	if (xfeatures_mask & XFEATURE_MASK_EAGER) {
-		if (eagerfpu == DISABLE) {
-			pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
-			       xfeatures_mask & XFEATURE_MASK_EAGER);
-			xfeatures_mask &= ~XFEATURE_MASK_EAGER;
-		} else {
-			eagerfpu = ENABLE;
-		}
-	}
+	if (xfeatures_mask & XFEATURE_MASK_EAGER)
+		eagerfpu = ENABLE;
 
 	if (eagerfpu == ENABLE)
 		setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
@@ -316,11 +343,48 @@ static void __init fpu__init_system_ctx_switch(void)
 }
 
 /*
+ * We parse fpu parameters early because fpu__init_system() is executed
+ * before parse_early_param().
+ */
+static void __init fpu__init_parse_early_param(void)
+{
+	/*
+	 * No need to check "eagerfpu=auto" again, since it is the
+	 * initial default.
+	 */
+	if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) {
+		eagerfpu = DISABLE;
+		fpu__clear_eager_fpu_features();
+	} else if (cmdline_find_option_bool(boot_command_line, "eagerfpu=on")) {
+		eagerfpu = ENABLE;
+	}
+
+	if (cmdline_find_option_bool(boot_command_line, "no387"))
+		setup_clear_cpu_cap(X86_FEATURE_FPU);
+
+	if (cmdline_find_option_bool(boot_command_line, "nofxsr")) {
+		setup_clear_cpu_cap(X86_FEATURE_FXSR);
+		setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
+		setup_clear_cpu_cap(X86_FEATURE_XMM);
+	}
+
+	if (cmdline_find_option_bool(boot_command_line, "noxsave"))
+		fpu__xstate_clear_all_cpu_caps();
+
+	if (cmdline_find_option_bool(boot_command_line, "noxsaveopt"))
+		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+
+	if (cmdline_find_option_bool(boot_command_line, "noxsaves"))
+		setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+}
+
+/*
  * Called on the boot CPU once per system bootup, to set up the initial
  * FPU state that is later cloned into all processes:
  */
 void __init fpu__init_system(struct cpuinfo_x86 *c)
 {
+	fpu__init_parse_early_param();
 	fpu__init_system_early_generic(c);
 
 	/*
@@ -344,62 +408,3 @@ void __init fpu__init_system(struct cpuinfo_x86 *c)
 
 	fpu__init_system_ctx_switch();
 }
-
-/*
- * Boot parameter to turn off FPU support and fall back to math-emu:
- */
-static int __init no_387(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FPU);
-	return 1;
-}
-__setup("no387", no_387);
-
-/*
- * Disable all xstate CPU features:
- */
-static int __init x86_noxsave_setup(char *s)
-{
-	if (strlen(s))
-		return 0;
-
-	fpu__xstate_clear_all_cpu_caps();
-
-	return 1;
-}
-__setup("noxsave", x86_noxsave_setup);
-
-/*
- * Disable the XSAVEOPT instruction specifically:
- */
-static int __init x86_noxsaveopt_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-
-	return 1;
-}
-__setup("noxsaveopt", x86_noxsaveopt_setup);
-
-/*
- * Disable the XSAVES instruction:
- */
-static int __init x86_noxsaves_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-
-	return 1;
-}
-__setup("noxsaves", x86_noxsaves_setup);
-
-/*
- * Disable FX save/restore and SSE support:
- */
-static int __init x86_nofxsr_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FXSR);
-	setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
-	setup_clear_cpu_cap(X86_FEATURE_XMM);
-
-	return 1;
-}
-__setup("nofxsr", x86_nofxsr_setup);
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 40f1002..d425cda5 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -52,6 +52,7 @@ void fpu__xstate_clear_all_cpu_caps(void)
 	setup_clear_cpu_cap(X86_FEATURE_AVX512ER);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512CD);
 	setup_clear_cpu_cap(X86_FEATURE_MPX);
+	setup_clear_cpu_cap(X86_FEATURE_XGETBV1);
 }
 
 /*
@@ -632,8 +633,7 @@ void __init fpu__init_system_xstate(void)
 		BUG();
 	}
 
-	/* Support only the state known to the OS: */
-	xfeatures_mask = xfeatures_mask & XCNTXT_MASK;
+	xfeatures_mask &= fpu__get_supported_xfeatures_mask();
 
 	/* Enable xstate instructions to be able to continue with initialization: */
 	fpu__init_cpu_xstate();
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index d64889a..ab0adc0 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -182,6 +182,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"),
 		},
 	},
+	{	/* Handle problems with rebooting on the iMac10,1. */
+		.callback = set_pci_reboot,
+		.ident = "Apple iMac10,1",
+		.matches = {
+		    DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+		    DMI_MATCH(DMI_PRODUCT_NAME, "iMac10,1"),
+		},
+	},
 
 	/* ASRock */
 	{	/* Handle problems with rebooting on ASRock Q1900DC-ITX */
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index 4cf401f..07efb35 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -48,31 +48,31 @@ verify_cpu:
 	pushfl
 	popl	%eax
 	cmpl	%eax,%ebx
-	jz	verify_cpu_no_longmode	# cpu has no cpuid
+	jz	.Lverify_cpu_no_longmode	# cpu has no cpuid
 #endif
 
 	movl	$0x0,%eax		# See if cpuid 1 is implemented
 	cpuid
 	cmpl	$0x1,%eax
-	jb	verify_cpu_no_longmode	# no cpuid 1
+	jb	.Lverify_cpu_no_longmode	# no cpuid 1
 
 	xor	%di,%di
 	cmpl	$0x68747541,%ebx	# AuthenticAMD
-	jnz	verify_cpu_noamd
+	jnz	.Lverify_cpu_noamd
 	cmpl	$0x69746e65,%edx
-	jnz	verify_cpu_noamd
+	jnz	.Lverify_cpu_noamd
 	cmpl	$0x444d4163,%ecx
-	jnz	verify_cpu_noamd
+	jnz	.Lverify_cpu_noamd
 	mov	$1,%di			# cpu is from AMD
-	jmp	verify_cpu_check
+	jmp	.Lverify_cpu_check
 
-verify_cpu_noamd:
+.Lverify_cpu_noamd:
 	cmpl	$0x756e6547,%ebx        # GenuineIntel?
-	jnz	verify_cpu_check
+	jnz	.Lverify_cpu_check
 	cmpl	$0x49656e69,%edx
-	jnz	verify_cpu_check
+	jnz	.Lverify_cpu_check
 	cmpl	$0x6c65746e,%ecx
-	jnz	verify_cpu_check
+	jnz	.Lverify_cpu_check
 
 	# only call IA32_MISC_ENABLE when:
 	# family > 6 || (family == 6 && model >= 0xd)
@@ -83,59 +83,59 @@ verify_cpu_noamd:
 	andl	$0x0ff00f00, %eax	# mask family and extended family
 	shrl	$8, %eax
 	cmpl	$6, %eax
-	ja	verify_cpu_clear_xd	# family > 6, ok
-	jb	verify_cpu_check	# family < 6, skip
+	ja	.Lverify_cpu_clear_xd	# family > 6, ok
+	jb	.Lverify_cpu_check	# family < 6, skip
 
 	andl	$0x000f00f0, %ecx	# mask model and extended model
 	shrl	$4, %ecx
 	cmpl	$0xd, %ecx
-	jb	verify_cpu_check	# family == 6, model < 0xd, skip
+	jb	.Lverify_cpu_check	# family == 6, model < 0xd, skip
 
-verify_cpu_clear_xd:
+.Lverify_cpu_clear_xd:
 	movl	$MSR_IA32_MISC_ENABLE, %ecx
 	rdmsr
 	btrl	$2, %edx		# clear MSR_IA32_MISC_ENABLE_XD_DISABLE
-	jnc	verify_cpu_check	# only write MSR if bit was changed
+	jnc	.Lverify_cpu_check	# only write MSR if bit was changed
 	wrmsr
 
-verify_cpu_check:
+.Lverify_cpu_check:
 	movl    $0x1,%eax		# Does the cpu have what it takes
 	cpuid
 	andl	$REQUIRED_MASK0,%edx
 	xorl	$REQUIRED_MASK0,%edx
-	jnz	verify_cpu_no_longmode
+	jnz	.Lverify_cpu_no_longmode
 
 	movl    $0x80000000,%eax	# See if extended cpuid is implemented
 	cpuid
 	cmpl    $0x80000001,%eax
-	jb      verify_cpu_no_longmode	# no extended cpuid
+	jb      .Lverify_cpu_no_longmode	# no extended cpuid
 
 	movl    $0x80000001,%eax	# Does the cpu have what it takes
 	cpuid
 	andl    $REQUIRED_MASK1,%edx
 	xorl    $REQUIRED_MASK1,%edx
-	jnz     verify_cpu_no_longmode
+	jnz     .Lverify_cpu_no_longmode
 
-verify_cpu_sse_test:
+.Lverify_cpu_sse_test:
 	movl	$1,%eax
 	cpuid
 	andl	$SSE_MASK,%edx
 	cmpl	$SSE_MASK,%edx
-	je	verify_cpu_sse_ok
+	je	.Lverify_cpu_sse_ok
 	test	%di,%di
-	jz	verify_cpu_no_longmode	# only try to force SSE on AMD
+	jz	.Lverify_cpu_no_longmode	# only try to force SSE on AMD
 	movl	$MSR_K7_HWCR,%ecx
 	rdmsr
 	btr	$15,%eax		# enable SSE
 	wrmsr
 	xor	%di,%di			# don't loop
-	jmp	verify_cpu_sse_test	# try again
+	jmp	.Lverify_cpu_sse_test	# try again
 
-verify_cpu_no_longmode:
+.Lverify_cpu_no_longmode:
 	popf				# Restore caller passed flags
 	movl $1,%eax
 	ret
-verify_cpu_sse_ok:
+.Lverify_cpu_sse_ok:
 	popf				# Restore caller passed flags
 	xorl %eax, %eax
 	ret