Merge branch 'x86/mm' into x86/asm to resolve conflict and to create common base

 Conflicts:
	arch/x86/include/asm/cpufeature.h

Signed-off-by: Ingo Molnar <mingo@kernel.org>

10 files changed, 133 insertions, 66 deletions

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/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 97e5f13..c594e04 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -126,7 +126,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #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_pat		boot_cpu_has(X86_FEATURE_PAT)
 #define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
 #define cpu_has_xsaves		boot_cpu_has(X86_FEATURE_XSAVES)
 /*
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/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/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index f1bed30..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);
 }
 
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/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/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ff2a2e6..9b8f1ea 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
@@ -1511,7 +1510,6 @@ 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)
@@ -1618,13 +1616,6 @@ 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
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 3d31d3a..aaec8ae 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);