Merge tag 'x86_mtrr_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mtrr updates from Borislav Petkov:
 "A serious scrubbing of the MTRR code including adding a new map
  mechanism in order to look up the memory type of a region easily.

  Also address memory range lookup issues like returning an invalid
  memory type. Furthermore, this handles the decoupling of PAT from MTRR
  more naturally.

  All work by Juergen Gross"

* tag 'x86_mtrr_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/xen: Set default memory type for PV guests to WB
  x86/mtrr: Unify debugging printing
  x86/mtrr: Remove unused code
  x86/mm: Only check uniform after calling mtrr_type_lookup()
  x86/mtrr: Don't let mtrr_type_lookup() return MTRR_TYPE_INVALID
  x86/mtrr: Use new cache_map in mtrr_type_lookup()
  x86/mtrr: Add mtrr=debug command line option
  x86/mtrr: Construct a memory map with cache modes
  x86/mtrr: Add get_effective_type() service function
  x86/mtrr: Allocate mtrr_value array dynamically
  x86/mtrr: Move 32-bit code from mtrr.c to legacy.c
  x86/mtrr: Have only one set_mtrr() variant
  x86/mtrr: Replace vendor tests in MTRR code
  x86/xen: Set MTRR state when running as Xen PV initial domain
  x86/hyperv: Set MTRR state when running as SEV-SNP Hyper-V guest
  x86/mtrr: Support setting MTRR state for software defined MTRRs
  x86/mtrr: Replace size_or_mask and size_and_mask with a much easier concept
  x86/mtrr: Remove physical address size calculation

15 files changed, 773 insertions, 482 deletions

diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index cc92388b7a99..6f7c1b5606ad 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -17,6 +17,7 @@
 #include <asm/mem_encrypt.h>
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
+#include <asm/mtrr.h>
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 
@@ -372,6 +373,9 @@ void __init hv_vtom_init(void)
 	x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required;
 	x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required;
 	x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility;
+
+	/* Set WB as the default cache mode. */
+	mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK);
 }
 
 #endif /* CONFIG_AMD_MEM_ENCRYPT */
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index f0eeaf6e5f5f..090d658a85a6 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -23,14 +23,43 @@
 #ifndef _ASM_X86_MTRR_H
 #define _ASM_X86_MTRR_H
 
+#include <linux/bits.h>
 #include <uapi/asm/mtrr.h>
 
+/* Defines for hardware MTRR registers. */
+#define MTRR_CAP_VCNT		GENMASK(7, 0)
+#define MTRR_CAP_FIX		BIT_MASK(8)
+#define MTRR_CAP_WC		BIT_MASK(10)
+
+#define MTRR_DEF_TYPE_TYPE	GENMASK(7, 0)
+#define MTRR_DEF_TYPE_FE	BIT_MASK(10)
+#define MTRR_DEF_TYPE_E		BIT_MASK(11)
+
+#define MTRR_DEF_TYPE_ENABLE	(MTRR_DEF_TYPE_FE | MTRR_DEF_TYPE_E)
+#define MTRR_DEF_TYPE_DISABLE	~(MTRR_DEF_TYPE_TYPE | MTRR_DEF_TYPE_ENABLE)
+
+#define MTRR_PHYSBASE_TYPE	GENMASK(7, 0)
+#define MTRR_PHYSBASE_RSVD	GENMASK(11, 8)
+
+#define MTRR_PHYSMASK_RSVD	GENMASK(10, 0)
+#define MTRR_PHYSMASK_V		BIT_MASK(11)
+
+struct mtrr_state_type {
+	struct mtrr_var_range var_ranges[MTRR_MAX_VAR_RANGES];
+	mtrr_type fixed_ranges[MTRR_NUM_FIXED_RANGES];
+	unsigned char enabled;
+	bool have_fixed;
+	mtrr_type def_type;
+};
+
 /*
  * The following functions are for use by other drivers that cannot use
  * arch_phys_wc_add and arch_phys_wc_del.
  */
 # ifdef CONFIG_MTRR
 void mtrr_bp_init(void);
+void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var,
+			  mtrr_type def_type);
 extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform);
 extern void mtrr_save_fixed_ranges(void *);
 extern void mtrr_save_state(void);
@@ -40,7 +69,6 @@ extern int mtrr_add_page(unsigned long base, unsigned long size,
 			 unsigned int type, bool increment);
 extern int mtrr_del(int reg, unsigned long base, unsigned long size);
 extern int mtrr_del_page(int reg, unsigned long base, unsigned long size);
-extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi);
 extern void mtrr_bp_restore(void);
 extern int mtrr_trim_uncached_memory(unsigned long end_pfn);
 extern int amd_special_default_mtrr(void);
@@ -48,12 +76,21 @@ void mtrr_disable(void);
 void mtrr_enable(void);
 void mtrr_generic_set_state(void);
 #  else
+static inline void mtrr_overwrite_state(struct mtrr_var_range *var,
+					unsigned int num_var,
+					mtrr_type def_type)
+{
+}
+
 static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform)
 {
 	/*
-	 * Return no-MTRRs:
+	 * Return the default MTRR type, without any known other types in
+	 * that range.
 	 */
-	return MTRR_TYPE_INVALID;
+	*uniform = 1;
+
+	return MTRR_TYPE_UNCACHABLE;
 }
 #define mtrr_save_fixed_ranges(arg) do {} while (0)
 #define mtrr_save_state() do {} while (0)
@@ -79,9 +116,6 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
 {
 	return 0;
 }
-static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
-{
-}
 #define mtrr_bp_init() do {} while (0)
 #define mtrr_bp_restore() do {} while (0)
 #define mtrr_disable() do {} while (0)
@@ -121,7 +155,8 @@ struct mtrr_gentry32 {
 #endif /* CONFIG_COMPAT */
 
 /* Bit fields for enabled in struct mtrr_state_type */
-#define MTRR_STATE_MTRR_FIXED_ENABLED	0x01
-#define MTRR_STATE_MTRR_ENABLED		0x02
+#define MTRR_STATE_SHIFT		10
+#define MTRR_STATE_MTRR_FIXED_ENABLED	(MTRR_DEF_TYPE_FE >> MTRR_STATE_SHIFT)
+#define MTRR_STATE_MTRR_ENABLED		(MTRR_DEF_TYPE_E >> MTRR_STATE_SHIFT)
 
 #endif /* _ASM_X86_MTRR_H */
diff --git a/arch/x86/include/uapi/asm/mtrr.h b/arch/x86/include/uapi/asm/mtrr.h
index 376563f2bac1..3a8a8eb8ac3a 100644
--- a/arch/x86/include/uapi/asm/mtrr.h
+++ b/arch/x86/include/uapi/asm/mtrr.h
@@ -81,14 +81,6 @@ typedef __u8 mtrr_type;
 #define MTRR_NUM_FIXED_RANGES 88
 #define MTRR_MAX_VAR_RANGES 256
 
-struct mtrr_state_type {
-	struct mtrr_var_range var_ranges[MTRR_MAX_VAR_RANGES];
-	mtrr_type fixed_ranges[MTRR_NUM_FIXED_RANGES];
-	unsigned char enabled;
-	unsigned char have_fixed;
-	mtrr_type def_type;
-};
-
 #define MTRRphysBase_MSR(reg) (0x200 + 2 * (reg))
 #define MTRRphysMask_MSR(reg) (0x200 + 2 * (reg) + 1)
 
@@ -115,9 +107,9 @@ struct mtrr_state_type {
 #define MTRR_NUM_TYPES       7
 
 /*
- * Invalid MTRR memory type.  mtrr_type_lookup() returns this value when
- * MTRRs are disabled.  Note, this value is allocated from the reserved
- * values (0x7-0xff) of the MTRR memory types.
+ * Invalid MTRR memory type.  No longer used outside of MTRR code.
+ * Note, this value is allocated from the reserved values (0x7-0xff) of
+ * the MTRR memory types.
  */
 #define MTRR_TYPE_INVALID    0xff
 
diff --git a/arch/x86/kernel/cpu/mtrr/Makefile b/arch/x86/kernel/cpu/mtrr/Makefile
index cc4f9f1cb94c..aee4bc5ad496 100644
--- a/arch/x86/kernel/cpu/mtrr/Makefile
+++ b/arch/x86/kernel/cpu/mtrr/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y		:= mtrr.o if.o generic.o cleanup.o
-obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o
+obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o legacy.o
 
diff --git a/arch/x86/kernel/cpu/mtrr/amd.c b/arch/x86/kernel/cpu/mtrr/amd.c
index eff6ac62c0ff..ef3e8e42b782 100644
--- a/arch/x86/kernel/cpu/mtrr/amd.c
+++ b/arch/x86/kernel/cpu/mtrr/amd.c
@@ -110,7 +110,7 @@ amd_validate_add_page(unsigned long base, unsigned long size, unsigned int type)
 }
 
 const struct mtrr_ops amd_mtrr_ops = {
-	.vendor            = X86_VENDOR_AMD,
+	.var_regs          = 2,
 	.set               = amd_set_mtrr,
 	.get               = amd_get_mtrr,
 	.get_free_region   = generic_get_free_region,
diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c
index b8a74eddde83..6f6c3ae92943 100644
--- a/arch/x86/kernel/cpu/mtrr/centaur.c
+++ b/arch/x86/kernel/cpu/mtrr/centaur.c
@@ -45,15 +45,6 @@ centaur_get_free_region(unsigned long base, unsigned long size, int replace_reg)
 	return -ENOSPC;
 }
 
-/*
- * Report boot time MCR setups
- */
-void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
-{
-	centaur_mcr[mcr].low = lo;
-	centaur_mcr[mcr].high = hi;
-}
-
 static void
 centaur_get_mcr(unsigned int reg, unsigned long *base,
 		unsigned long *size, mtrr_type * type)
@@ -112,7 +103,7 @@ centaur_validate_add_page(unsigned long base, unsigned long size, unsigned int t
 }
 
 const struct mtrr_ops centaur_mtrr_ops = {
-	.vendor            = X86_VENDOR_CENTAUR,
+	.var_regs          = 8,
 	.set               = centaur_set_mcr,
 	.get               = centaur_get_mcr,
 	.get_free_region   = centaur_get_free_region,
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index b5f43049fa5f..18cf79d6e2c5 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -55,9 +55,6 @@ static int __initdata				nr_range;
 
 static struct var_mtrr_range_state __initdata	range_state[RANGE_NUM];
 
-static int __initdata debug_print;
-#define Dprintk(x...) do { if (debug_print) pr_debug(x); } while (0)
-
 #define BIOS_BUG_MSG \
 	"WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n"
 
@@ -79,12 +76,11 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 		nr_range = add_range_with_merge(range, RANGE_NUM, nr_range,
 						base, base + size);
 	}
-	if (debug_print) {
-		pr_debug("After WB checking\n");
-		for (i = 0; i < nr_range; i++)
-			pr_debug("MTRR MAP PFN: %016llx - %016llx\n",
-				 range[i].start, range[i].end);
-	}
+
+	Dprintk("After WB checking\n");
+	for (i = 0; i < nr_range; i++)
+		Dprintk("MTRR MAP PFN: %016llx - %016llx\n",
+			 range[i].start, range[i].end);
 
 	/* Take out UC ranges: */
 	for (i = 0; i < num_var_ranges; i++) {
@@ -112,24 +108,22 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 		subtract_range(range, RANGE_NUM, extra_remove_base,
 				 extra_remove_base + extra_remove_size);
 
-	if  (debug_print) {
-		pr_debug("After UC checking\n");
-		for (i = 0; i < RANGE_NUM; i++) {
-			if (!range[i].end)
-				continue;
-			pr_debug("MTRR MAP PFN: %016llx - %016llx\n",
-				 range[i].start, range[i].end);
-		}
+	Dprintk("After UC checking\n");
+	for (i = 0; i < RANGE_NUM; i++) {
+		if (!range[i].end)
+			continue;
+
+		Dprintk("MTRR MAP PFN: %016llx - %016llx\n",
+			 range[i].start, range[i].end);
 	}
 
 	/* sort the ranges */
 	nr_range = clean_sort_range(range, RANGE_NUM);
-	if  (debug_print) {
-		pr_debug("After sorting\n");
-		for (i = 0; i < nr_range; i++)
-			pr_debug("MTRR MAP PFN: %016llx - %016llx\n",
-				 range[i].start, range[i].end);
-	}
+
+	Dprintk("After sorting\n");
+	for (i = 0; i < nr_range; i++)
+		Dprintk("MTRR MAP PFN: %016llx - %016llx\n",
+			range[i].start, range[i].end);
 
 	return nr_range;
 }
@@ -164,16 +158,9 @@ static int __init enable_mtrr_cleanup_setup(char *str)
 }
 early_param("enable_mtrr_cleanup", enable_mtrr_cleanup_setup);
 
-static int __init mtrr_cleanup_debug_setup(char *str)
-{
-	debug_print = 1;
-	return 0;
-}
-early_param("mtrr_cleanup_debug", mtrr_cleanup_debug_setup);
-
 static void __init
 set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek,
-	     unsigned char type, unsigned int address_bits)
+	     unsigned char type)
 {
 	u32 base_lo, base_hi, mask_lo, mask_hi;
 	u64 base, mask;
@@ -183,7 +170,7 @@ set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek,
 		return;
 	}
 
-	mask = (1ULL << address_bits) - 1;
+	mask = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
 	mask &= ~((((u64)sizek) << 10) - 1);
 
 	base = ((u64)basek) << 10;
@@ -209,7 +196,7 @@ save_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek,
 	range_state[reg].type = type;
 }
 
-static void __init set_var_mtrr_all(unsigned int address_bits)
+static void __init set_var_mtrr_all(void)
 {
 	unsigned long basek, sizek;
 	unsigned char type;
@@ -220,7 +207,7 @@ static void __init set_var_mtrr_all(unsigned int address_bits)
 		sizek = range_state[reg].size_pfn << (PAGE_SHIFT - 10);
 		type = range_state[reg].type;
 
-		set_var_mtrr(reg, basek, sizek, type, address_bits);
+		set_var_mtrr(reg, basek, sizek, type);
 	}
 }
 
@@ -267,7 +254,7 @@ range_to_mtrr(unsigned int reg, unsigned long range_startk,
 			align = max_align;
 
 		sizek = 1UL << align;
-		if (debug_print) {
+		if (mtrr_debug) {
 			char start_factor = 'K', size_factor = 'K';
 			unsigned long start_base, size_base;
 
@@ -542,7 +529,7 @@ static void __init print_out_mtrr_range_state(void)
 		start_base = to_size_factor(start_base, &start_factor);
 		type = range_state[i].type;
 
-		pr_debug("reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
+		Dprintk("reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
 			i, start_base, start_factor,
 			size_base, size_factor,
 			(type == MTRR_TYPE_UNCACHABLE) ? "UC" :
@@ -680,7 +667,7 @@ static int __init mtrr_search_optimal_index(void)
 	return index_good;
 }
 
-int __init mtrr_cleanup(unsigned address_bits)
+int __init mtrr_cleanup(void)
 {
 	unsigned long x_remove_base, x_remove_size;
 	unsigned long base, size, def, dummy;
@@ -689,7 +676,10 @@ int __init mtrr_cleanup(unsigned address_bits)
 	int index_good;
 	int i;
 
-	if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
+	if (!mtrr_enabled())
+		return 0;
+
+	if (!cpu_feature_enabled(X86_FEATURE_MTRR) || enable_mtrr_cleanup < 1)
 		return 0;
 
 	rdmsr(MSR_MTRRdefType, def, dummy);
@@ -711,7 +701,7 @@ int __init mtrr_cleanup(unsigned address_bits)
 		return 0;
 
 	/* Print original var MTRRs at first, for debugging: */
-	pr_debug("original variable MTRRs\n");
+	Dprintk("original variable MTRRs\n");
 	print_out_mtrr_range_state();
 
 	memset(range, 0, sizeof(range));
@@ -742,8 +732,8 @@ int __init mtrr_cleanup(unsigned address_bits)
 		mtrr_print_out_one_result(i);
 
 		if (!result[i].bad) {
-			set_var_mtrr_all(address_bits);
-			pr_debug("New variable MTRRs\n");
+			set_var_mtrr_all();
+			Dprintk("New variable MTRRs\n");
 			print_out_mtrr_range_state();
 			return 1;
 		}
@@ -763,7 +753,7 @@ int __init mtrr_cleanup(unsigned address_bits)
 
 			mtrr_calc_range_state(chunk_size, gran_size,
 				      x_remove_base, x_remove_size, i);
-			if (debug_print) {
+			if (mtrr_debug) {
 				mtrr_print_out_one_result(i);
 				pr_info("\n");
 			}
@@ -786,8 +776,8 @@ int __init mtrr_cleanup(unsigned address_bits)
 		gran_size = result[i].gran_sizek;
 		gran_size <<= 10;
 		x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size);
-		set_var_mtrr_all(address_bits);
-		pr_debug("New variable MTRRs\n");
+		set_var_mtrr_all();
+		Dprintk("New variable MTRRs\n");
 		print_out_mtrr_range_state();
 		return 1;
 	} else {
@@ -802,7 +792,7 @@ int __init mtrr_cleanup(unsigned address_bits)
 	return 0;
 }
 #else
-int __init mtrr_cleanup(unsigned address_bits)
+int __init mtrr_cleanup(void)
 {
 	return 0;
 }
@@ -882,15 +872,18 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 	/* extra one for all 0 */
 	int num[MTRR_NUM_TYPES + 1];
 
+	if (!mtrr_enabled())
+		return 0;
+
 	/*
 	 * Make sure we only trim uncachable memory on machines that
 	 * support the Intel MTRR architecture:
 	 */
-	if (!is_cpu(INTEL) || disable_mtrr_trim)
+	if (!cpu_feature_enabled(X86_FEATURE_MTRR) || disable_mtrr_trim)
 		return 0;
 
 	rdmsr(MSR_MTRRdefType, def, dummy);
-	def &= 0xff;
+	def &= MTRR_DEF_TYPE_TYPE;
 	if (def != MTRR_TYPE_UNCACHABLE)
 		return 0;
 
diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c
index 173b9e01e623..238dad57d4d6 100644
--- a/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -235,7 +235,7 @@ static void cyrix_set_arr(unsigned int reg, unsigned long base,
 }
 
 const struct mtrr_ops cyrix_mtrr_ops = {
-	.vendor            = X86_VENDOR_CYRIX,
+	.var_regs          = 8,
 	.set               = cyrix_set_arr,
 	.get               = cyrix_get_arr,
 	.get_free_region   = cyrix_get_free_region,
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index ee09d359e08f..2d6aa5d2e3d7 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -8,10 +8,12 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/mm.h>
-
+#include <linux/cc_platform.h>
 #include <asm/processor-flags.h>
 #include <asm/cacheinfo.h>
 #include <asm/cpufeature.h>
+#include <asm/hypervisor.h>
+#include <asm/mshyperv.h>
 #include <asm/tlbflush.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
@@ -31,6 +33,55 @@ static struct fixed_range_block fixed_range_blocks[] = {
 	{}
 };
 
+struct cache_map {
+	u64 start;
+	u64 end;
+	u64 flags;
+	u64 type:8;
+	u64 fixed:1;
+};
+
+bool mtrr_debug;
+
+static int __init mtrr_param_setup(char *str)
+{
+	int rc = 0;
+
+	if (!str)
+		return -EINVAL;
+	if (!strcmp(str, "debug"))
+		mtrr_debug = true;
+	else
+		rc = -EINVAL;
+
+	return rc;
+}
+early_param("mtrr", mtrr_param_setup);
+
+/*
+ * CACHE_MAP_MAX is the maximum number of memory ranges in cache_map, where
+ * no 2 adjacent ranges have the same cache mode (those would be merged).
+ * The number is based on the worst case:
+ * - no two adjacent fixed MTRRs share the same cache mode
+ * - one variable MTRR is spanning a huge area with mode WB
+ * - 255 variable MTRRs with mode UC all overlap with the WB MTRR, creating 2
+ *   additional ranges each (result like "ababababa...aba" with a = WB, b = UC),
+ *   accounting for MTRR_MAX_VAR_RANGES * 2 - 1 range entries
+ * - a TOP_MEM2 area (even with overlapping an UC MTRR can't add 2 range entries
+ *   to the possible maximum, as it always starts at 4GB, thus it can't be in
+ *   the middle of that MTRR, unless that MTRR starts at 0, which would remove
+ *   the initial "a" from the "abababa" pattern above)
+ * The map won't contain ranges with no matching MTRR (those fall back to the
+ * default cache mode).
+ */
+#define CACHE_MAP_MAX	(MTRR_NUM_FIXED_RANGES + MTRR_MAX_VAR_RANGES * 2)
+
+static struct cache_map init_cache_map[CACHE_MAP_MAX] __initdata;
+static struct cache_map *cache_map __refdata = init_cache_map;
+static unsigned int cache_map_size = CACHE_MAP_MAX;
+static unsigned int cache_map_n;
+static unsigned int cache_map_fixed;
+
 static unsigned long smp_changes_mask;
 static int mtrr_state_set;
 u64 mtrr_tom2;
@@ -38,6 +89,9 @@ u64 mtrr_tom2;
 struct mtrr_state_type mtrr_state;
 EXPORT_SYMBOL_GPL(mtrr_state);
 
+/* Reserved bits in the high portion of the MTRRphysBaseN MSR. */
+u32 phys_hi_rsvd;
+
 /*
  * BIOS is expected to clear MtrrFixDramModEn bit, see for example
  * "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD
@@ -69,175 +123,370 @@ static u64 get_mtrr_size(u64 mask)
 {
 	u64 size;
 
-	mask >>= PAGE_SHIFT;
-	mask |= size_or_mask;
+	mask |= (u64)phys_hi_rsvd << 32;
 	size = -mask;
-	size <<= PAGE_SHIFT;
+
 	return size;
 }
 
+static u8 get_var_mtrr_state(unsigned int reg, u64 *start, u64 *size)
+{
+	struct mtrr_var_range *mtrr = mtrr_state.var_ranges + reg;
+
+	if (!(mtrr->mask_lo & MTRR_PHYSMASK_V))
+		return MTRR_TYPE_INVALID;
+
+	*start = (((u64)mtrr->base_hi) << 32) + (mtrr->base_lo & PAGE_MASK);
+	*size = get_mtrr_size((((u64)mtrr->mask_hi) << 32) +
+			      (mtrr->mask_lo & PAGE_MASK));
+
+	return mtrr->base_lo & MTRR_PHYSBASE_TYPE;
+}
+
+static u8 get_effective_type(u8 type1, u8 type2)
+{
+	if (type1 == MTRR_TYPE_UNCACHABLE || type2 == MTRR_TYPE_UNCACHABLE)
+		return MTRR_TYPE_UNCACHABLE;
+
+	if ((type1 == MTRR_TYPE_WRBACK && type2 == MTRR_TYPE_WRTHROUGH) ||
+	    (type1 == MTRR_TYPE_WRTHROUGH && type2 == MTRR_TYPE_WRBACK))
+		return MTRR_TYPE_WRTHROUGH;
+
+	if (type1 != type2)
+		return MTRR_TYPE_UNCACHABLE;
+
+	return type1;
+}
+
+static void rm_map_entry_at(int idx)
+{
+	cache_map_n--;
+	if (cache_map_n > idx) {
+		memmove(cache_map + idx, cache_map + idx + 1,
+			sizeof(*cache_map) * (cache_map_n - idx));
+	}
+}
+
 /*
- * Check and return the effective type for MTRR-MTRR type overlap.
- * Returns 1 if the effective type is UNCACHEABLE, else returns 0
+ * Add an entry into cache_map at a specific index.  Merges adjacent entries if
+ * appropriate.  Return the number of merges for correcting the scan index
+ * (this is needed as merging will reduce the number of entries, which will
+ * result in skipping entries in future iterations if the scan index isn't
+ * corrected).
+ * Note that the corrected index can never go below -1 (resulting in being 0 in
+ * the next scan iteration), as "2" is returned only if the current index is
+ * larger than zero.
  */
-static int check_type_overlap(u8 *prev, u8 *curr)
+static int add_map_entry_at(u64 start, u64 end, u8 type, int idx)
 {
-	if (*prev == MTRR_TYPE_UNCACHABLE || *curr == MTRR_TYPE_UNCACHABLE) {
-		*prev = MTRR_TYPE_UNCACHABLE;
-		*curr = MTRR_TYPE_UNCACHABLE;
-		return 1;
+	bool merge_prev = false, merge_next = false;
+
+	if (start >= end)
+		return 0;
+
+	if (idx > 0) {
+		struct cache_map *prev = cache_map + idx - 1;
+
+		if (!prev->fixed && start == prev->end && type == prev->type)
+			merge_prev = true;
 	}
 
-	if ((*prev == MTRR_TYPE_WRBACK && *curr == MTRR_TYPE_WRTHROUGH) ||
-	    (*prev == MTRR_TYPE_WRTHROUGH && *curr == MTRR_TYPE_WRBACK)) {
-		*prev = MTRR_TYPE_WRTHROUGH;
-		*curr = MTRR_TYPE_WRTHROUGH;
+	if (idx < cache_map_n) {
+		struct cache_map *next = cache_map + idx;
+
+		if (!next->fixed && end == next->start && type == next->type)
+			merge_next = true;
 	}
 
-	if (*prev != *curr) {
-		*prev = MTRR_TYPE_UNCACHABLE;
-		*curr = MTRR_TYPE_UNCACHABLE;
+	if (merge_prev && merge_next) {
+		cache_map[idx - 1].end = cache_map[idx].end;
+		rm_map_entry_at(idx);
+		return 2;
+	}
+	if (merge_prev) {
+		cache_map[idx - 1].end = end;
 		return 1;
 	}
+	if (merge_next) {
+		cache_map[idx].start = start;
+		return 1;
+	}
+
+	/* Sanity check: the array should NEVER be too small! */
+	if (cache_map_n == cache_map_size) {
+		WARN(1, "MTRR cache mode memory map exhausted!\n");
+		cache_map_n = cache_map_fixed;
+		return 0;
+	}
+
+	if (cache_map_n > idx) {
+		memmove(cache_map + idx + 1, cache_map + idx,
+			sizeof(*cache_map) * (cache_map_n - idx));
+	}
+
+	cache_map[idx].start = start;
+	cache_map[idx].end = end;
+	cache_map[idx].type = type;
+	cache_map[idx].fixed = 0;
+	cache_map_n++;
 
 	return 0;
 }
 
-/**
- * mtrr_type_lookup_fixed - look up memory type in MTRR fixed entries
- *
- * Return the MTRR fixed memory type of 'start'.
- *
- * MTRR fixed entries are divided into the following ways:
- *  0x00000 - 0x7FFFF : This range is divided into eight 64KB sub-ranges
- *  0x80000 - 0xBFFFF : This range is divided into sixteen 16KB sub-ranges
- *  0xC0000 - 0xFFFFF : This range is divided into sixty-four 4KB sub-ranges
- *
- * Return Values:
- * MTRR_TYPE_(type)  - Matched memory type
- * MTRR_TYPE_INVALID - Unmatched
+/* Clear a part of an entry. Return 1 if start of entry is still valid. */
+static int clr_map_range_at(u64 start, u64 end, int idx)
+{
+	int ret = start != cache_map[idx].start;
+	u64 tmp;
+
+	if (start == cache_map[idx].start && end == cache_map[idx].end) {
+		rm_map_entry_at(idx);
+	} else if (start == cache_map[idx].start) {
+		cache_map[idx].start = end;
+	} else if (end == cache_map[idx].end) {
+		cache_map[idx].end = start;
+	} else {
+		tmp = cache_map[idx].end;
+		cache_map[idx].end = start;
+		add_map_entry_at(end, tmp, cache_map[idx].type, idx + 1);
+	}
+
+	return ret;
+}
+
+/*
+ * Add MTRR to the map.  The current map is scanned and each part of the MTRR
+ * either overlapping with an existing entry or with a hole in the map is
+ * handled separately.
  */
-static u8 mtrr_type_lookup_fixed(u64 start, u64 end)
+static void add_map_entry(u64 start, u64 end, u8 type)
 {
-	int idx;
+	u8 new_type, old_type;
+	u64 tmp;
+	int i;
 
-	if (start >= 0x100000)
-		return MTRR_TYPE_INVALID;
+	for (i = 0; i < cache_map_n && start < end; i++) {
+		if (start >= cache_map[i].end)
+			continue;
+
+		if (start < cache_map[i].start) {
+			/* Region start has no overlap. */
+			tmp = min(end, cache_map[i].start);
+			i -= add_map_entry_at(start, tmp,  type, i);
+			start = tmp;
+			continue;
+		}
 
-	/* 0x0 - 0x7FFFF */
-	if (start < 0x80000) {
-		idx = 0;
-		idx += (start >> 16);
-		return mtrr_state.fixed_ranges[idx];
-	/* 0x80000 - 0xBFFFF */
-	} else if (start < 0xC0000) {
-		idx = 1 * 8;
-		idx += ((start - 0x80000) >> 14);
-		return mtrr_state.fixed_ranges[idx];
+		new_type = get_effective_type(type, cache_map[i].type);
+		old_type = cache_map[i].type;
+
+		if (cache_map[i].fixed || new_type == old_type) {
+			/* Cut off start of new entry. */
+			start = cache_map[i].end;
+			continue;
+		}
+
+		/* Handle only overlapping part of region. */
+		tmp = min(end, cache_map[i].end);
+		i += clr_map_range_at(start, tmp, i);
+		i -= add_map_entry_at(start, tmp, new_type, i);
+		start = tmp;
 	}
 
-	/* 0xC0000 - 0xFFFFF */
-	idx = 3 * 8;
-	idx += ((start - 0xC0000) >> 12);
-	return mtrr_state.fixed_ranges[idx];
+	/* Add rest of region after last map entry (rest might be empty). */
+	add_map_entry_at(start, end, type, i);
 }
 
-/**
- * mtrr_type_lookup_variable - look up memory type in MTRR variable entries
- *
- * Return Value:
- * MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched)
- *
- * Output Arguments:
- * repeat - Set to 1 when [start:end] spanned across MTRR range and type
- *	    returned corresponds only to [start:*partial_end].  Caller has
- *	    to lookup again for [*partial_end:end].
- *
- * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
- *	     region is fully covered by a single MTRR entry or the default
- *	     type.
+/* Add variable MTRRs to cache map. */
+static void map_add_var(void)
+{
+	u64 start, size;
+	unsigned int i;
+	u8 type;
+
+	/*
+	 * Add AMD TOP_MEM2 area.  Can't be added in mtrr_build_map(), as it
+	 * needs to be added again when rebuilding the map due to potentially
+	 * having moved as a result of variable MTRRs for memory below 4GB.
+	 */
+	if (mtrr_tom2) {
+		add_map_entry(BIT_ULL(32), mtrr_tom2, MTRR_TYPE_WRBACK);
+		cache_map[cache_map_n - 1].fixed = 1;
+	}
+
+	for (i = 0; i < num_var_ranges; i++) {
+		type = get_var_mtrr_state(i, &start, &size);
+		if (type != MTRR_TYPE_INVALID)
+			add_map_entry(start, start + size, type);
+	}
+}
+
+/*
+ * Rebuild map by replacing variable entries.  Needs to be called when MTRR
+ * registers are being changed after boot, as such changes could include
+ * removals of registers, which are complicated to handle without rebuild of
+ * the map.
  */
-static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
-				    int *repeat, u8 *uniform)
+void generic_rebuild_map(void)
 {
-	int i;
-	u64 base, mask;
-	u8 prev_match, curr_match;
+	if (mtrr_if != &generic_mtrr_ops)
+		return;
 
-	*repeat = 0;
-	*uniform = 1;
+	cache_map_n = cache_map_fixed;
 
-	prev_match = MTRR_TYPE_INVALID;
-	for (i = 0; i < num_var_ranges; ++i) {
-		unsigned short start_state, end_state, inclusive;
+	map_add_var();
+}
 
-		if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11)))
-			continue;
+static unsigned int __init get_cache_map_size(void)
+{
+	return cache_map_fixed + 2 * num_var_ranges + (mtrr_tom2 != 0);
+}
 
-		base = (((u64)mtrr_state.var_ranges[i].base_hi) << 32) +
-		       (mtrr_state.var_ranges[i].base_lo & PAGE_MASK);
-		mask = (((u64)mtrr_state.var_ranges[i].mask_hi) << 32) +
-		       (mtrr_state.var_ranges[i].mask_lo & PAGE_MASK);
-
-		start_state = ((start & mask) == (base & mask));
-		end_state = ((end & mask) == (base & mask));
-		inclusive = ((start < base) && (end > base));
-
-		if ((start_state != end_state) || inclusive) {
-			/*
-			 * We have start:end spanning across an MTRR.
-			 * We split the region into either
-			 *
-			 * - start_state:1
-			 * (start:mtrr_end)(mtrr_end:end)
-			 * - end_state:1
-			 * (start:mtrr_start)(mtrr_start:end)
-			 * - inclusive:1
-			 * (start:mtrr_start)(mtrr_start:mtrr_end)(mtrr_end:end)
-			 *
-			 * depending on kind of overlap.
-			 *
-			 * Return the type of the first region and a pointer
-			 * to the start of next region so that caller will be
-			 * advised to lookup again after having adjusted start
-			 * and end.
-			 *
-			 * Note: This way we handle overlaps with multiple
-			 * entries and the default type properly.
-			 */
-			if (start_state)
-				*partial_end = base + get_mtrr_size(mask);
-			else
-				*partial_end = base;
-
-			if (unlikely(*partial_end <= start)) {
-				WARN_ON(1);
-				*partial_end = start + PAGE_SIZE;
-			}
+/* Build the cache_map containing the cache modes per memory range. */
+void __init mtrr_build_map(void)
+{
+	u64 start, end, size;
+	unsigned int i;
+	u8 type;
 
-			end = *partial_end - 1; /* end is inclusive */
-			*repeat = 1;
-			*uniform = 0;
+	/* Add fixed MTRRs, optimize for adjacent entries with same type. */
+	if (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED) {
+		/*
+		 * Start with 64k size fixed entries, preset 1st one (hence the
+		 * loop below is starting with index 1).
+		 */
+		start = 0;
+		end = size = 0x10000;
+		type = mtrr_state.fixed_ranges[0];
+
+		for (i = 1; i < MTRR_NUM_FIXED_RANGES; i++) {
+			/* 8 64k entries, then 16 16k ones, rest 4k. */
+			if (i == 8 || i == 24)
+				size >>= 2;
+
+			if (mtrr_state.fixed_ranges[i] != type) {
+				add_map_entry(start, end, type);
+				start = end;
+				type = mtrr_state.fixed_ranges[i];
+			}
+			end += size;
 		}
+		add_map_entry(start, end, type);
+	}
 
-		if ((start & mask) != (base & mask))
-			continue;
+	/* Mark fixed, they take precedence. */
+	for (i = 0; i < cache_map_n; i++)
+		cache_map[i].fixed = 1;
+	cache_map_fixed = cache_map_n;
 
-		curr_match