4.14.9-stable review

@@ -45,7 +45,7 @@ static inline bool rdrand_long(unsigned
 	bool ok;
 	unsigned int retry = RDRAND_RETRY_LOOPS;
 	do {
-		asm volatile(RDRAND_LONG "\n\t"
+		asm volatile(RDRAND_LONG
 			     CC_SET(c)
 			     : CC_OUT(c) (ok), "=a" (*v));
 		if (ok)

@@ -59,7 +59,7 @@ static inline bool rdrand_int(unsigned i
 	bool ok;
 	unsigned int retry = RDRAND_RETRY_LOOPS;
 	do {
-		asm volatile(RDRAND_INT "\n\t"
+		asm volatile(RDRAND_INT
 			     CC_SET(c)
 			     : CC_OUT(c) (ok), "=a" (*v));
 		if (ok)

@@ -71,7 +71,7 @@ static inline bool rdrand_int(unsigned i
 static inline bool rdseed_long(unsigned long *v)
 {
 	bool ok;
-	asm volatile(RDSEED_LONG "\n\t"
+	asm volatile(RDSEED_LONG
 		     CC_SET(c)
 		     : CC_OUT(c) (ok), "=a" (*v));
 	return ok;

@@ -80,7 +80,7 @@ static inline bool rdseed_long(unsigned
 static inline bool rdseed_int(unsigned int *v)
 {
 	bool ok;
-	asm volatile(RDSEED_INT "\n\t"
+	asm volatile(RDSEED_INT
 		     CC_SET(c)
 		     : CC_OUT(c) (ok), "=a" (*v));
 	return ok;

@@ -143,7 +143,7 @@ static __always_inline void __clear_bit(
 static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
 {
 	bool negative;
-	asm volatile(LOCK_PREFIX "andb %2,%1\n\t"
+	asm volatile(LOCK_PREFIX "andb %2,%1"
 		CC_SET(s)
 		: CC_OUT(s) (negative), ADDR
 		: "ir" ((char) ~(1 << nr)) : "memory");

@@ -246,7 +246,7 @@ static __always_inline bool __test_and_s
 {
 	bool oldbit;
 
-	asm("bts %2,%1\n\t"
+	asm("bts %2,%1"
 	    CC_SET(c)
 	    : CC_OUT(c) (oldbit), ADDR
 	    : "Ir" (nr));

@@ -286,7 +286,7 @@ static __always_inline bool __test_and_c
 {
 	bool oldbit;
 
-	asm volatile("btr %2,%1\n\t"
+	asm volatile("btr %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr));

@@ -298,7 +298,7 @@ static __always_inline bool __test_and_c
 {
 	bool oldbit;
 
-	asm volatile("btc %2,%1\n\t"
+	asm volatile("btc %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr) : "memory");

@@ -329,7 +329,7 @@ static __always_inline bool variable_tes
 {
 	bool oldbit;
 
-	asm volatile("bt %2,%1\n\t"
+	asm volatile("bt %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit)
 		     : "m" (*(unsigned long *)addr), "Ir" (nr));

@@ -526,7 +526,7 @@ static inline bool x86_this_cpu_variable
 {
 	bool oldbit;
 
-	asm volatile("bt "__percpu_arg(2)",%1\n\t"
+	asm volatile("bt "__percpu_arg(2)",%1"
 			CC_SET(c)
 			: CC_OUT(c) (oldbit)
 			: "m" (*(unsigned long __percpu *)addr), "Ir" (nr));

@@ -29,7 +29,7 @@ cc_label:								\
 #define __GEN_RMWcc(fullop, var, cc, clobbers, ...)			\
 do {									\
 	bool c;								\
-	asm volatile (fullop ";" CC_SET(cc)				\
+	asm volatile (fullop CC_SET(cc)					\
 			: [counter] "+m" (var), CC_OUT(cc) (c)		\
 			: __VA_ARGS__ : clobbers);			\
 	return c;							\

@@ -174,7 +174,8 @@ static void __iomem *ghes_ioremap_pfn_nm
 
 static void __iomem *ghes_ioremap_pfn_irq(u64 pfn)
 {
-	unsigned long vaddr, paddr;
+	unsigned long vaddr;
+	phys_addr_t paddr;
 	pgprot_t prot;
 
 	vaddr = (unsigned long)GHES_IOREMAP_IRQ_PAGE(ghes_ioremap_area->addr);

@@ -34,11 +34,6 @@ DECLARE_EVENT_CLASS(x86_fpu,
 	)
 );
 
-DEFINE_EVENT(x86_fpu, x86_fpu_state,
-	TP_PROTO(struct fpu *fpu),
-	TP_ARGS(fpu)
-);
-
 DEFINE_EVENT(x86_fpu, x86_fpu_before_save,
 	TP_PROTO(struct fpu *fpu),
 	TP_ARGS(fpu)

@@ -73,11 +68,6 @@ DEFINE_EVENT(x86_fpu, x86_fpu_activate_s
 	TP_PROTO(struct fpu *fpu),
 	TP_ARGS(fpu)
 );
-
-DEFINE_EVENT(x86_fpu, x86_fpu_deactivate_state,
-	TP_PROTO(struct fpu *fpu),
-	TP_ARGS(fpu)
-);
 
 DEFINE_EVENT(x86_fpu, x86_fpu_init_state,
 	TP_PROTO(struct fpu *fpu),

@@ -6,7 +6,7 @@
 #include <asm/orc_types.h>
 
 struct mod_arch_specific {
-#ifdef CONFIG_ORC_UNWINDER
+#ifdef CONFIG_UNWINDER_ORC
 	unsigned int num_orcs;
 	int *orc_unwind_ip;
 	struct orc_entry *orc_unwind;

@@ -13,11 +13,11 @@ struct unwind_state {
 	struct task_struct *task;
 	int graph_idx;
 	bool error;
-#if defined(CONFIG_ORC_UNWINDER)
+#if defined(CONFIG_UNWINDER_ORC)
 	bool signal, full_regs;
 	unsigned long sp, bp, ip;
 	struct pt_regs *regs;
-#elif defined(CONFIG_FRAME_POINTER_UNWINDER)
+#elif defined(CONFIG_UNWINDER_FRAME_POINTER)
 	bool got_irq;
 	unsigned long *bp, *orig_sp, ip;
 	struct pt_regs *regs;

@@ -51,7 +51,7 @@ void unwind_start(struct unwind_state *s
 	__unwind_start(state, task, regs, first_frame);
 }
 
-#if defined(CONFIG_ORC_UNWINDER) || defined(CONFIG_FRAME_POINTER_UNWINDER)
+#if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER)
 static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
 {
 	if (unwind_done(state))

@@ -66,7 +66,7 @@ static inline struct pt_regs *unwind_get
 }
 #endif
 
-#ifdef CONFIG_ORC_UNWINDER
+#ifdef CONFIG_UNWINDER_ORC
 void unwind_init(void);
 void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size,
 			void *orc, size_t orc_size);

@@ -688,7 +688,7 @@
 #define BUG_TABLE
 #endif
 
-#ifdef CONFIG_ORC_UNWINDER
+#ifdef CONFIG_UNWINDER_ORC
 #define ORC_UNWIND_TABLE						\
 	. = ALIGN(4);							\
 	.orc_unwind_ip : AT(ADDR(.orc_unwind_ip) - LOAD_OFFSET) {	\

@@ -228,6 +228,32 @@ static inline unsigned long __ffs64(u64
 	return __ffs((unsigned long)word);
 }
 
+/*
+ * clear_bit32 - Clear a bit in memory for u32 array
+ * @nr: Bit to clear
+ * @addr: u32 * address of bitmap
+ *
+ * Same as clear_bit, but avoids needing casts for u32 arrays.
+ */
+
+static __always_inline void clear_bit32(long nr, volatile u32 *addr)
+{
+	clear_bit(nr, (volatile unsigned long *)addr);
+}
+
+/*
+ * set_bit32 - Set a bit in memory for u32 array
+ * @nr: Bit to clear
+ * @addr: u32 * address of bitmap
+ *
+ * Same as set_bit, but avoids needing casts for u32 arrays.
+ */
+
+static __always_inline void set_bit32(long nr, volatile u32 *addr)
+{
+	set_bit(nr, (volatile unsigned long *)addr);
+}
+
 #ifdef __KERNEL__
 
 #ifndef set_mask_bits

@@ -15,6 +15,7 @@
 #include <asm/fpu/xstate.h>
 
 #include <asm/tlbflush.h>
+#include <asm/cpufeature.h>
 
 /*
  * Although we spell it out in here, the Processor Trace

@@ -36,6 +37,19 @@ static const char *xfeature_names[] =
 	"unknown xstate feature"	,
 };
 
+static short xsave_cpuid_features[] __initdata = {
+	X86_FEATURE_FPU,
+	X86_FEATURE_XMM,
+	X86_FEATURE_AVX,
+	X86_FEATURE_MPX,
+	X86_FEATURE_MPX,
+	X86_FEATURE_AVX512F,
+	X86_FEATURE_AVX512F,
+	X86_FEATURE_AVX512F,
+	X86_FEATURE_INTEL_PT,
+	X86_FEATURE_PKU,
+};
+
 /*
  * Mask of xstate features supported by the CPU and the kernel:
  */

@@ -726,6 +740,7 @@ void __init fpu__init_system_xstate(void
 	unsigned int eax, ebx, ecx, edx;
 	static int on_boot_cpu __initdata = 1;
 	int err;
+	int i;
 
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;

@@ -759,6 +774,14 @@ void __init fpu__init_system_xstate(void
 		goto out_disable;
 	}
 
+	/*
+	 * Clear XSAVE features that are disabled in the normal CPUID.
+	 */
+	for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) {
+		if (!boot_cpu_has(xsave_cpuid_features[i]))
+			xfeatures_mask &= ~BIT(i);
+	}
+
 	xfeatures_mask &= fpu__get_supported_xfeatures_mask();
 
 	/* Enable xstate instructions to be able to continue with initialization: */

@@ -73,26 +73,6 @@ unsigned int fpu_user_xstate_size;
 void fpu__xstate_clear_all_cpu_caps(void)
 {
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEC);
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-	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_AVX512IFMA);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512PF);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512ER);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512CD);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512DQ);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512BW);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512VL);
-	setup_clear_cpu_cap(X86_FEATURE_MPX);
-	setup_clear_cpu_cap(X86_FEATURE_XGETBV1);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512VBMI);
-	setup_clear_cpu_cap(X86_FEATURE_PKU);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512_VPOPCNTDQ);
 }
 
 /*

@@ -75,11 +75,17 @@ static inline void clear_feature(struct
 		__clear_cpu_cap(c, feature);
 }
 
+/* Take the capabilities and the BUG bits into account */
+#define MAX_FEATURE_BITS ((NCAPINTS + NBUGINTS) * sizeof(u32) * 8)
+
 static void do_clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature)
 {
-	bool changed;
-	DECLARE_BITMAP(disable, NCAPINTS * sizeof(u32) * 8);
+	DECLARE_BITMAP(disable, MAX_FEATURE_BITS);
 	const struct cpuid_dep *d;
+	bool changed;
+
+	if (WARN_ON(feature >= MAX_FEATURE_BITS))
+		return;
 
 	clear_feature(c, feature);
 

@@ -1152,13 +1152,17 @@ struct mem_section {
 #define SECTION_ROOT_MASK	(SECTIONS_PER_ROOT - 1)
 
 #ifdef CONFIG_SPARSEMEM_EXTREME
-extern struct mem_section *mem_section[NR_SECTION_ROOTS];
+extern struct mem_section **mem_section;
 #else
 extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT];
 #endif
 
 static inline struct mem_section *__nr_to_section(unsigned long nr)
 {
+#ifdef CONFIG_SPARSEMEM_EXTREME
+	if (!mem_section)
+		return NULL;
+#endif
 	if (!mem_section[SECTION_NR_TO_ROOT(nr)])
 		return NULL;
 	return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];

@@ -5651,6 +5651,16 @@ void __init sparse_memory_present_with_a
 	unsigned long start_pfn, end_pfn;
 	int i, this_nid;
 
+#ifdef CONFIG_SPARSEMEM_EXTREME
+	if (!mem_section) {
+		unsigned long size, align;
+
+		size = sizeof(struct mem_section) * NR_SECTION_ROOTS;
+		align = 1 << (INTERNODE_CACHE_SHIFT);
+		mem_section = memblock_virt_alloc(size, align);
+	}
+#endif
+
 	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid)
 		memory_present(this_nid, start_pfn, end_pfn);
 }

@@ -23,8 +23,7 @@
  * 1) mem_section	- memory sections, mem_map's for valid memory
  */
 #ifdef CONFIG_SPARSEMEM_EXTREME
-struct mem_section *mem_section[NR_SECTION_ROOTS]
-	____cacheline_internodealigned_in_smp;
+struct mem_section **mem_section;
 #else
 struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
 	____cacheline_internodealigned_in_smp;

@@ -101,7 +100,7 @@ static inline int sparse_index_init(unsi
 int __section_nr(struct mem_section* ms)
 {
 	unsigned long root_nr;
-	struct mem_section* root;
+	struct mem_section *root = NULL;
 
 	for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
 		root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);

@@ -112,7 +111,7 @@ int __section_nr(struct mem_section* ms)
 		     break;
 	}
 
-	VM_BUG_ON(root_nr == NR_SECTION_ROOTS);
+	VM_BUG_ON(!root);
 
 	return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
 }

@@ -330,11 +329,17 @@ again:
 static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
 {
 	unsigned long usemap_snr, pgdat_snr;
-	static unsigned long old_usemap_snr = NR_MEM_SECTIONS;
-	static unsigned long old_pgdat_snr = NR_MEM_SECTIONS;
+	static unsigned long old_usemap_snr;
+	static unsigned long old_pgdat_snr;
 	struct pglist_data *pgdat = NODE_DATA(nid);
 	int usemap_nid;
 
+	/* First call */
+	if (!old_usemap_snr) {
+		old_usemap_snr = NR_MEM_SECTIONS;
+		old_pgdat_snr = NR_MEM_SECTIONS;
+	}
+
 	usemap_snr = pfn_to_section_nr(__pa(usemap) >> PAGE_SHIFT);
 	pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
 	if (usemap_snr == pgdat_snr)

142 lines not on this page · raw message

@@ -449,7 +449,7 @@ __visible pmd_t xen_make_pmd(pmdval_t pm
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd);
 
-#if CONFIG_PGTABLE_LEVELS == 4
+#ifdef CONFIG_X86_64
 __visible pudval_t xen_pud_val(pud_t pud)
 {
 	return pte_mfn_to_pfn(pud.pud);

@@ -538,7 +538,7 @@ static void xen_set_p4d(p4d_t *ptr, p4d_
 
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
-#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
+#endif	/* CONFIG_X86_64 */
 
 static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
 		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),

@@ -580,21 +580,17 @@ static int xen_p4d_walk(struct mm_struct
 		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
 		bool last, unsigned long limit)
 {
-	int i, nr, flush = 0;
+	int flush = 0;
+	pud_t *pud;
 
-	nr = last ? p4d_index(limit) + 1 : PTRS_PER_P4D;
-	for (i = 0; i < nr; i++) {
-		pud_t *pud;
 
-		if (p4d_none(p4d[i]))
-			continue;
+	if (p4d_none(*p4d))
+		return flush;
 
-		pud = pud_offset(&p4d[i], 0);
-		if (PTRS_PER_PUD > 1)
-			flush |= (*func)(mm, virt_to_page(pud), PT_PUD);
-		flush |= xen_pud_walk(mm, pud, func,
-				last && i == nr - 1, limit);
-	}
+	pud = pud_offset(p4d, 0);
+	if (PTRS_PER_PUD > 1)
+		flush |= (*func)(mm, virt_to_page(pud), PT_PUD);
+	flush |= xen_pud_walk(mm, pud, func, last, limit);
 	return flush;
 }
 

@@ -644,8 +640,6 @@ static int __xen_pgd_walk(struct mm_stru
 			continue;
 
 		p4d = p4d_offset(&pgd[i], 0);
-		if (PTRS_PER_P4D > 1)
-			flush |= (*func)(mm, virt_to_page(p4d), PT_P4D);
 		flush |= xen_p4d_walk(mm, p4d, func, i == nr - 1, limit);
 	}
 

@@ -1176,22 +1170,14 @@ static void __init xen_cleanmfnmap(unsig
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
-	unsigned int i;
 	bool unpin;
 
 	unpin = (vaddr == 2 * PGDIR_SIZE);
 	vaddr &= PMD_MASK;
 	pgd = pgd_offset_k(vaddr);
 	p4d = p4d_offset(pgd, 0);
-	for (i = 0; i < PTRS_PER_P4D; i++) {
-		if (p4d_none(p4d[i]))
-			continue;
-		xen_cleanmfnmap_p4d(p4d + i, unpin);
-	}
-	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
-		set_pgd(pgd, __pgd(0));
-		xen_cleanmfnmap_free_pgtbl(p4d, unpin);
-	}
+	if (!p4d_none(*p4d))
+		xen_cleanmfnmap_p4d(p4d, unpin);
 }
 
 static void __init xen_pagetable_p2m_free(void)

@@ -1692,7 +1678,7 @@ static void xen_release_pmd(unsigned lon
 	xen_release_ptpage(pfn, PT_PMD);
 }
 
-#if CONFIG_PGTABLE_LEVELS >= 4
+#ifdef CONFIG_X86_64
 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PUD);

@@ -2029,13 +2015,12 @@ static phys_addr_t __init xen_early_virt
  */
 void __init xen_relocate_p2m(void)
 {
-	phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys, p4d_phys;
+	phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys;
 	unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end;
-	int n_pte, n_pt, n_pmd, n_pud, n_p4d, idx_pte, idx_pt, idx_pmd, idx_pud, idx_p4d;
+	int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud;
 	pte_t *pt;
 	pmd_t *pmd;
 	pud_t *pud;
-	p4d_t *p4d = NULL;
 	pgd_t *pgd;
 	unsigned long *new_p2m;
 	int save_pud;

@@ -2045,11 +2030,7 @@ void __init xen_relocate_p2m(void)
 	n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT;
 	n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT;
 	n_pud = roundup(size, P4D_SIZE) >> P4D_SHIFT;
-	if (PTRS_PER_P4D > 1)
-		n_p4d = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT;
-	else
-		n_p4d = 0;
-	n_frames = n_pte + n_pt + n_pmd + n_pud + n_p4d;
+	n_frames = n_pte + n_pt + n_pmd + n_pud;
 
 	new_area = xen_find_free_area(PFN_PHYS(n_frames));
 	if (!new_area) {

@@ -2065,76 +2046,56 @@ void __init xen_relocate_p2m(void)
 	 * To avoid any possible virtual address collision, just use
 	 * 2 * PUD_SIZE for the new area.
 	 */
-	p4d_phys = new_area;
-	pud_phys = p4d_phys + PFN_PHYS(n_p4d);
+	pud_phys = new_area;
 	pmd_phys = pud_phys + PFN_PHYS(n_pud);
 	pt_phys = pmd_phys + PFN_PHYS(n_pmd);
 	p2m_pfn = PFN_DOWN(pt_phys) + n_pt;
 
 	pgd = __va(read_cr3_pa());
 	new_p2m = (unsigned long *)(2 * PGDIR_SIZE);
-	idx_p4d = 0;
 	save_pud = n_pud;
-	do {
-		if (n_p4d > 0) {
-			p4d = early_memremap(p4d_phys, PAGE_SIZE);
-			clear_page(p4d);
-			n_pud = min(save_pud, PTRS_PER_P4D);
-		}
-		for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
-			pud = early_memremap(pud_phys, PAGE_SIZE);
-			clear_page(pud);
-			for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD);
-				 idx_pmd++) {
-				pmd = early_memremap(pmd_phys, PAGE_SIZE);
-				clear_page(pmd);
-				for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD);
-					 idx_pt++) {
-					pt = early_memremap(pt_phys, PAGE_SIZE);
-					clear_page(pt);
-					for (idx_pte = 0;
-						 idx_pte < min(n_pte, PTRS_PER_PTE);
-						 idx_pte++) {
-						set_pte(pt + idx_pte,
-								pfn_pte(p2m_pfn, PAGE_KERNEL));
-						p2m_pfn++;
-					}
-					n_pte -= PTRS_PER_PTE;
-					early_memunmap(pt, PAGE_SIZE);
-					make_lowmem_page_readonly(__va(pt_phys));
-					pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE,
-							PFN_DOWN(pt_phys));
-					set_pmd(pmd + idx_pt,
-							__pmd(_PAGE_TABLE | pt_phys));
-					pt_phys += PAGE_SIZE;
+	for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
+		pud = early_memremap(pud_phys, PAGE_SIZE);
+		clear_page(pud);
+		for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD);
+				idx_pmd++) {
+			pmd = early_memremap(pmd_phys, PAGE_SIZE);
+			clear_page(pmd);
+			for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD);
+					idx_pt++) {
+				pt = early_memremap(pt_phys, PAGE_SIZE);
+				clear_page(pt);
+				for (idx_pte = 0;
+						idx_pte < min(n_pte, PTRS_PER_PTE);
+						idx_pte++) {
+					set_pte(pt + idx_pte,
+							pfn_pte(p2m_pfn, PAGE_KERNEL));
+					p2m_pfn++;
 				}
-				n_pt -= PTRS_PER_PMD;
-				early_memunmap(pmd, PAGE_SIZE);
-				make_lowmem_page_readonly(__va(pmd_phys));
-				pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE,
-						PFN_DOWN(pmd_phys));
-				set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys));
-				pmd_phys += PAGE_SIZE;
+				n_pte -= PTRS_PER_PTE;
+				early_memunmap(pt, PAGE_SIZE);
+				make_lowmem_page_readonly(__va(pt_phys));
+				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE,
+						PFN_DOWN(pt_phys));
+				set_pmd(pmd + idx_pt,
+						__pmd(_PAGE_TABLE | pt_phys));
+				pt_phys += PAGE_SIZE;
 			}
-			n_pmd -= PTRS_PER_PUD;
-			early_memunmap(pud, PAGE_SIZE);
-			make_lowmem_page_readonly(__va(pud_phys));
-			pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys));
-			if (n_p4d > 0)
-				set_p4d(p4d + idx_pud, __p4d(_PAGE_TABLE | pud_phys));
-			else
-				set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys));
-			pud_phys += PAGE_SIZE;
-		}
-		if (n_p4d > 0) {
-			save_pud -= PTRS_PER_P4D;
-			early_memunmap(p4d, PAGE_SIZE);
-			make_lowmem_page_readonly(__va(p4d_phys));
-			pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, PFN_DOWN(p4d_phys));
-			set_pgd(pgd + 2 + idx_p4d, __pgd(_PAGE_TABLE | p4d_phys));
-			p4d_phys += PAGE_SIZE;
+			n_pt -= PTRS_PER_PMD;
+			early_memunmap(pmd, PAGE_SIZE);
+			make_lowmem_page_readonly(__va(pmd_phys));
+			pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE,
+					PFN_DOWN(pmd_phys));
+			set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys));
+			pmd_phys += PAGE_SIZE;
 		}
-	} while (++idx_p4d < n_p4d);
+		n_pmd -= PTRS_PER_PUD;
+		early_memunmap(pud, PAGE_SIZE);
+		make_lowmem_page_readonly(__va(pud_phys));
+		pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys));
+		set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys));
+		pud_phys += PAGE_SIZE;
+	}
 
 	/* Now copy the old p2m info to the new area. */
 	memcpy(new_p2m, xen_p2m_addr, size);

@@ -2361,7 +2322,7 @@ static void __init xen_post_allocator_in
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
 	pv_mmu_ops.set_pud = xen_set_pud;
-#if CONFIG_PGTABLE_LEVELS >= 4
+#ifdef CONFIG_X86_64
 	pv_mmu_ops.set_p4d = xen_set_p4d;
 #endif
 

@@ -2371,7 +2332,7 @@ static void __init xen_post_allocator_in
 	pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
 	pv_mmu_ops.release_pte = xen_release_pte;
 	pv_mmu_ops.release_pmd = xen_release_pmd;
-#if CONFIG_PGTABLE_LEVELS >= 4
+#ifdef CONFIG_X86_64
 	pv_mmu_ops.alloc_pud = xen_alloc_pud;
 	pv_mmu_ops.release_pud = xen_release_pud;
 #endif

@@ -2435,14 +2396,14 @@ static const struct pv_mmu_ops xen_mmu_o
 	.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
 	.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
 
-#if CONFIG_PGTABLE_LEVELS >= 4
+#ifdef CONFIG_X86_64
 	.pud_val = PV_CALLEE_SAVE(xen_pud_val),
 	.make_pud = PV_CALLEE_SAVE(xen_make_pud),
 	.set_p4d = xen_set_p4d_hyper,
 
 	.alloc_pud = xen_alloc_pmd_init,
 	.release_pud = xen_release_pmd_init,
-#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
+#endif	/* CONFIG_X86_64 */
 
 	.activate_mm = xen_activate_mm,
 	.dup_mmap = xen_dup_mmap,

@@ -852,17 +852,8 @@ static void ghes_sea_remove(struct ghes
 	synchronize_rcu();
 }
 #else /* CONFIG_ACPI_APEI_SEA */
-static inline void ghes_sea_add(struct ghes *ghes)
-{
-	pr_err(GHES_PFX "ID: %d, trying to add SEA notification which is not supported\n",
-	       ghes->generic->header.source_id);
-}
-
-static inline void ghes_sea_remove(struct ghes *ghes)
-{
-	pr_err(GHES_PFX "ID: %d, trying to remove SEA notification which is not supported\n",
-	       ghes->generic->header.source_id);
-}
+static inline void ghes_sea_add(struct ghes *ghes) { }
+static inline void ghes_sea_remove(struct ghes *ghes) { }
 #endif /* CONFIG_ACPI_APEI_SEA */
 
 #ifdef CONFIG_HAVE_ACPI_APEI_NMI

@@ -1064,23 +1055,9 @@ static void ghes_nmi_init_cxt(void)
 	init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq);
 }
 #else /* CONFIG_HAVE_ACPI_APEI_NMI */
-static inline void ghes_nmi_add(struct ghes *ghes)
-{
-	pr_err(GHES_PFX "ID: %d, trying to add NMI notification which is not supported!\n",
-	       ghes->generic->header.source_id);
-	BUG();
-}
-
-static inline void ghes_nmi_remove(struct ghes *ghes)
-{
-	pr_err(GHES_PFX "ID: %d, trying to remove NMI notification which is not supported!\n",
-	       ghes->generic->header.source_id);
-	BUG();
-}
-
-static inline void ghes_nmi_init_cxt(void)
-{
-}
+static inline void ghes_nmi_add(struct ghes *ghes) { }
+static inline void ghes_nmi_remove(struct ghes *ghes) { }
+static inline void ghes_nmi_init_cxt(void) { }
 #endif /* CONFIG_HAVE_ACPI_APEI_NMI */
 
 static int ghes_probe(struct platform_device *ghes_dev)

@@ -1426,16 +1426,16 @@ int __meminit vmemmap_populate(unsigned
 
 #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE)
 void register_page_bootmem_memmap(unsigned long section_nr,
-				  struct page *start_page, unsigned long size)
+				  struct page *start_page, unsigned long nr_pages)
 {
 	unsigned long addr = (unsigned long)start_page;
-	unsigned long end = (unsigned long)(start_page + size);
+	unsigned long end = (unsigned long)(start_page + nr_pages);
 	unsigned long next;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
-	unsigned int nr_pages;
+	unsigned int nr_pmd_pages;
 	struct page *page;
 
 	for (; addr < end; addr = next) {

@@ -1482,9 +1482,9 @@ void register_page_bootmem_memmap(unsign
 			if (pmd_none(*pmd))
 				continue;
 
-			nr_pages = 1 << (get_order(PMD_SIZE));
+			nr_pmd_pages = 1 << get_order(PMD_SIZE);
 			page = pmd_page(*pmd);
-			while (nr_pages--)
+			while (nr_pmd_pages--)
 				get_page_bootmem(section_nr, page++,
 						 SECTION_INFO);
 		}

@@ -2510,7 +2510,7 @@ void vmemmap_populate_print_last(void);
 void vmemmap_free(unsigned long start, unsigned long end);
 #endif
 void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
-				  unsigned long size);
+				  unsigned long nr_pages);
 
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,

@@ -145,4 +145,22 @@ enum {
 	X86_TRAP_IRET = 32,	/* 32, IRET Exception */
 };
 
+/*
+ * Page fault error code bits:
+ *
+ *   bit 0 ==	 0: no page found	1: protection fault
+ *   bit 1 ==	 0: read access		1: write access
+ *   bit 2 ==	 0: kernel-mode access	1: user-mode access
+ *   bit 3 ==				1: use of reserved bit detected
+ *   bit 4 ==				1: fault was an instruction fetch
+ *   bit 5 ==				1: protection keys block access
+ */
+enum x86_pf_error_code {
+	X86_PF_PROT	=		1 << 0,
+	X86_PF_WRITE	=		1 << 1,
+	X86_PF_USER	=		1 << 2,
+	X86_PF_RSVD	=		1 << 3,
+	X86_PF_INSTR	=		1 << 4,
+	X86_PF_PK	=		1 << 5,
+};
 #endif /* _ASM_X86_TRAPS_H */

249 lines not on this page · raw message

@@ -152,5 +152,8 @@
 #define CX86_ARR_BASE	0xc4
 #define CX86_RCR_BASE	0xdc
 
+#define CR0_STATE	(X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \
+			 X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \
+			 X86_CR0_PG)
 
 #endif /* _UAPI_ASM_X86_PROCESSOR_FLAGS_H */

@@ -136,9 +136,9 @@ static inline int v8086_mode(struct pt_r
 #endif
 }
 
-#ifdef CONFIG_X86_64
 static inline bool user_64bit_mode(struct pt_regs *regs)
 {
+#ifdef CONFIG_X86_64
 #ifndef CONFIG_PARAVIRT
 	/*
 	 * On non-paravirt systems, this is the only long mode CPL 3

@@ -149,8 +149,12 @@ static inline bool user_64bit_mode(struc
 	/* Headers are too twisted for this to go in paravirt.h. */
 	return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs;
 #endif
+#else /* !CONFIG_X86_64 */
+	return false;
+#endif
 }
 
+#ifdef CONFIG_X86_64
 #define current_user_stack_pointer()	current_pt_regs()->sp
 #define compat_user_stack_pointer()	current_pt_regs()->sp
 #endif

@@ -142,16 +142,6 @@ For 32-bit we have the following convent
 	UNWIND_HINT_REGS offset=\offset
 	.endm
 
-	.macro RESTORE_EXTRA_REGS offset=0
-	movq 0*8+\offset(%rsp), %r15
-	movq 1*8+\offset(%rsp), %r14
-	movq 2*8+\offset(%rsp), %r13
-	movq 3*8+\offset(%rsp), %r12
-	movq 4*8+\offset(%rsp), %rbp
-	movq 5*8+\offset(%rsp), %rbx
-	UNWIND_HINT_REGS offset=\offset extra=0
-	.endm
-
 	.macro POP_EXTRA_REGS
 	popq %r15
 	popq %r14

@@ -173,48 +163,6 @@ For 32-bit we have the following convent
 	popq %rdi
 	.endm
 
-	.macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
-	.if \rstor_r11
-	movq 6*8(%rsp), %r11
-	.endif
-	.if \rstor_r8910
-	movq 7*8(%rsp), %r10
-	movq 8*8(%rsp), %r9
-	movq 9*8(%rsp), %r8
-	.endif
-	.if \rstor_rax
-	movq 10*8(%rsp), %rax
-	.endif
-	.if \rstor_rcx
-	movq 11*8(%rsp), %rcx
-	.endif
-	.if \rstor_rdx
-	movq 12*8(%rsp), %rdx
-	.endif
-	movq 13*8(%rsp), %rsi
-	movq 14*8(%rsp), %rdi
-	UNWIND_HINT_IRET_REGS offset=16*8
-	.endm
-	.macro RESTORE_C_REGS
-	RESTORE_C_REGS_HELPER 1,1,1,1,1
-	.endm
-	.macro RESTORE_C_REGS_EXCEPT_RAX
-	RESTORE_C_REGS_HELPER 0,1,1,1,1
-	.endm
-	.macro RESTORE_C_REGS_EXCEPT_RCX
-	RESTORE_C_REGS_HELPER 1,0,1,1,1
-	.endm
-	.macro RESTORE_C_REGS_EXCEPT_R11
-	RESTORE_C_REGS_HELPER 1,1,0,1,1
-	.endm
-	.macro RESTORE_C_REGS_EXCEPT_RCX_R11
-	RESTORE_C_REGS_HELPER 1,0,0,1,1
-	.endm
-
-	.macro REMOVE_PT_GPREGS_FROM_STACK addskip=0
-	subq $-(15*8+\addskip), %rsp
-	.endm
-
 	.macro icebp
 	.byte 0xf1
 	.endm

@@ -16,10 +16,9 @@
 #include <linux/cpumask.h>
 #include <asm/frame.h>
 
-static inline void load_sp0(struct tss_struct *tss,
-			     struct thread_struct *thread)
+static inline void load_sp0(unsigned long sp0)
 {
-	PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread);
+	PVOP_VCALL1(pv_cpu_ops.load_sp0, sp0);
 }
 
 /* The paravirtualized CPUID instruction. */

@@ -134,7 +134,7 @@ struct pv_cpu_ops {
 	void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries);
 	void (*free_ldt)(struct desc_struct *ldt, unsigned entries);
 
-	void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t);
+	void (*load_sp0)(unsigned long sp0);
 
 	void (*set_iopl_mask)(unsigned mask);
 

@@ -518,9 +518,9 @@ static inline void native_set_iopl_mask(
 }
 
 static inline void
-native_load_sp0(struct tss_struct *tss, struct thread_struct *thread)
+native_load_sp0(unsigned long sp0)
 {
-	tss->x86_tss.sp0 = thread->sp0;
+	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
 }
 
 static inline void native_swapgs(void)

@@ -545,10 +545,9 @@ static inline unsigned long current_top_
 #else
 #define __cpuid			native_cpuid
 
-static inline void load_sp0(struct tss_struct *tss,
-			    struct thread_struct *thread)
+static inline void load_sp0(unsigned long sp0)
 {
-	native_load_sp0(tss, thread);
+	native_load_sp0(sp0);
 }
 
 #define set_iopl_mask native_set_iopl_mask

@@ -1570,7 +1570,7 @@ void cpu_init(void)
 	initialize_tlbstate_and_flush();
 	enter_lazy_tlb(&init_mm, me);
 
-	load_sp0(t, &current->thread);
+	load_sp0(current->thread.sp0);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
 	load_mm_ldt(&init_mm);

@@ -1625,7 +1625,7 @@ void cpu_init(void)
 	initialize_tlbstate_and_flush();
 	enter_lazy_tlb(&init_mm, curr);
 
-	load_sp0(t, thread);
+	load_sp0(thread->sp0);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
 	load_mm_ldt(&init_mm);

@@ -287,7 +287,7 @@ __switch_to(struct task_struct *prev_p,
 	 * current_thread_info().  Refresh the SYSENTER configuration in
 	 * case prev or next is vm86.
 	 */
-	load_sp0(tss, next);
+	load_sp0(next->sp0);
 	refresh_sysenter_cs(next);
 	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +

@@ -465,7 +465,7 @@ __switch_to(struct task_struct *prev_p,
 	this_cpu_write(current_task, next_p);
 
 	/* Reload sp0. */
-	load_sp0(tss, next);
+	load_sp0(next->sp0);
 
 	/*
 	 * Now maybe reload the debug registers and handle I/O bitmaps

@@ -95,7 +95,6 @@
 
 void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 {
-	struct tss_struct *tss;
 	struct task_struct *tsk = current;
 	struct vm86plus_struct __user *user;
 	struct vm86 *vm86 = current->thread.vm86;

@@ -147,13 +146,13 @@ void save_v86_state(struct kernel_vm86_r
 		do_exit(SIGSEGV);
 	}
 
-	tss = &per_cpu(cpu_tss, get_cpu());
+	preempt_disable();
 	tsk->thread.sp0 = vm86->saved_sp0;
 	tsk->thread.sysenter_cs = __KERNEL_CS;
-	load_sp0(tss, &tsk->thread);
+	load_sp0(tsk->thread.sp0);
 	refresh_sysenter_cs(&tsk->thread);
 	vm86->saved_sp0 = 0;
-	put_cpu();
+	preempt_enable();
 
 	memcpy(&regs->pt, &vm86->regs32, sizeof(struct pt_regs));
 

@@ -239,7 +238,6 @@ SYSCALL_DEFINE2(vm86, unsigned long, cmd
 
 static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 {
-	struct tss_struct *tss;
 	struct task_struct *tsk = current;
 	struct vm86 *vm86 = tsk->thread.vm86;
 	struct kernel_vm86_regs vm86regs;

@@ -367,8 +365,8 @@ static long do_sys_vm86(struct vm86plus_
 	vm86->saved_sp0 = tsk->thread.sp0;
 	lazy_save_gs(vm86->regs32.gs);
 
-	tss = &per_cpu(cpu_tss, get_cpu());
 	/* make room for real-mode segments */
+	preempt_disable();
 	tsk->thread.sp0 += 16;
 
 	if (static_cpu_has(X86_FEATURE_SEP)) {

@@ -376,8 +374,8 @@ static long do_sys_vm86(struct vm86plus_
 		refresh_sysenter_cs(&tsk->thread);
 	}
 
-	load_sp0(tss, &tsk->thread);
-	put_cpu();
+	load_sp0(tsk->thread.sp0);
+	preempt_enable();
 
 	if (vm86->flags & VM86_SCREEN_BITMAP)
 		mark_screen_rdonly(tsk->mm);

@@ -811,15 +811,14 @@ static void __init xen_write_gdt_entry_b
 	}
 }
 
-static void xen_load_sp0(struct tss_struct *tss,
-			 struct thread_struct *thread)
+static void xen_load_sp0(unsigned long sp0)
 {
 	struct multicall_space mcs;
 
 	mcs = xen_mc_entry(0);
-	MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0);
+	MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
-	tss->x86_tss.sp0 = thread->sp0;
+	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
 }
 
 void xen_set_iopl_mask(unsigned mask)

@@ -796,6 +796,8 @@ static inline void spin_lock_prefetch(co
 #define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \
 			   TOP_OF_KERNEL_STACK_PADDING)
 
+#define task_top_of_stack(task) ((unsigned long)(task_pt_regs(task) + 1))
+
 #ifdef CONFIG_X86_32
 /*
  * User space process size: 3GB (default).

@@ -1570,9 +1570,13 @@ void cpu_init(void)
 	initialize_tlbstate_and_flush();
 	enter_lazy_tlb(&init_mm, me);
 
-	load_sp0(current->thread.sp0);
+	/*
+	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
+	 * task never enters user mode.
+	 */
 	set_tss_desc(cpu, t);
 	load_TR_desc();
+
 	load_mm_ldt(&init_mm);
 
 	clear_all_debug_regs();

@@ -1594,7 +1598,6 @@ void cpu_init(void)
 	int cpu = smp_processor_id();
 	struct task_struct *curr = current;
 	struct tss_struct *t = &per_cpu(cpu_tss, cpu);
-	struct thread_struct *thread = &curr->thread;
 
 	wait_for_master_cpu(cpu);
 

@@ -1625,9 +1628,13 @@ void cpu_init(void)
 	initialize_tlbstate_and_flush();
 	enter_lazy_tlb(&init_mm, curr);
 
-	load_sp0(thread->sp0);
+	/*
+	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
+	 * task never enters user mode.
+	 */
 	set_tss_desc(cpu, t);
 	load_TR_desc();
+
 	load_mm_ldt(&init_mm);
 
 	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);

@@ -49,7 +49,13 @@
  */
 __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 	.x86_tss = {
-		.sp0 = TOP_OF_INIT_STACK,
+		/*
+		 * .sp0 is only used when entering ring 0 from a lower
+		 * privilege level.  Since the init task never runs anything
+		 * but ring 0 code, there is no need for a valid value here.
+		 * Poison it.
+		 */
+		.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,
 #ifdef CONFIG_X86_32
 		.ss0 = __KERNEL_DS,
 		.ss1 = __KERNEL_CS,

@@ -962,8 +962,7 @@ void common_cpu_up(unsigned int cpu, str
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
 	irq_ctx_init(cpu);
-	per_cpu(cpu_current_top_of_stack, cpu) =
-		(unsigned long)task_stack_page(idle) + THREAD_SIZE;
+	per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
 #else
 	initial_gs = per_cpu_offset(cpu);
 #endif

@@ -7,6 +7,7 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <asm/processor.h>
 #include <asm/user32.h>
 #include <asm/unistd.h>

@@ -431,7 +431,9 @@ typedef struct {
 struct thread_struct {
 	/* Cached TLS descriptors: */
 	struct desc_struct	tls_array[GDT_ENTRY_TLS_ENTRIES];
+#ifdef CONFIG_X86_32
 	unsigned long		sp0;
+#endif
 	unsigned long		sp;
 #ifdef CONFIG_X86_32
 	unsigned long		sysenter_cs;

@@ -798,6 +800,13 @@ static inline void spin_lock_prefetch(co
 
 #define task_top_of_stack(task) ((unsigned long)(task_pt_regs(task) + 1))
 
+#define task_pt_regs(task) \
+({									\
+	unsigned long __ptr = (unsigned long)task_stack_page(task);	\
+	__ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;		\
+	((struct pt_regs *)__ptr) - 1;					\
+})
+
 #ifdef CONFIG_X86_32
 /*
  * User space process size: 3GB (default).

@@ -817,23 +826,6 @@ static inline void spin_lock_prefetch(co
 	.addr_limit		= KERNEL_DS,				  \
 }
 
-/*
- * TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack.
- * This is necessary to guarantee that the entire "struct pt_regs"
- * is accessible even if the CPU haven't stored the SS/ESP registers
- * on the stack (interrupt gate does not save these registers
- * when switching to the same priv ring).
- * Therefore beware: accessing the ss/esp fields of the
- * "struct pt_regs" is possible, but they may contain the
- * completely wrong values.
- */
-#define task_pt_regs(task) \
-({									\
-	unsigned long __ptr = (unsigned long)task_stack_page(task);	\
-	__ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;		\
-	((struct pt_regs *)__ptr) - 1;					\
-})
-
 #define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
 #else

@@ -867,11 +859,9 @@ static inline void spin_lock_prefetch(co
 #define STACK_TOP_MAX		TASK_SIZE_MAX
 
 #define INIT_THREAD  {						\
-	.sp0			= TOP_OF_INIT_STACK,		\
 	.addr_limit		= KERNEL_DS,			\
 }
 
-#define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
 
 #endif /* CONFIG_X86_64 */

@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_SWITCH_TO_H
 #define _ASM_X86_SWITCH_TO_H
 
+#include <linux/sched/task_stack.h>
+
 struct task_struct; /* one of the stranger aspects of C forward declarations */
 
 struct task_struct *__switch_to_asm(struct task_struct *prev,

@@ -88,7 +90,11 @@ static inline void refresh_sysenter_cs(s
 /* This is used when switching tasks or entering/exiting vm86 mode. */
 static inline void update_sp0(struct task_struct *task)
 {
+#ifdef CONFIG_X86_32
 	load_sp0(task->thread.sp0);
+#else
+	load_sp0(task_top_of_stack(task));
+#endif
 }
 
 #endif /* _ASM_X86_SWITCH_TO_H */

@@ -274,7 +274,6 @@ int copy_thread_tls(unsigned long clone_
 	struct inactive_task_frame *frame;
 	struct task_struct *me = current;
 
-	p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE;
 	childregs = task_pt_regs(p);
 	fork_frame = container_of(childregs, struct fork_frame, regs);
 	frame = &fork_frame->frame;

@@ -542,6 +542,12 @@ static inline unsigned long current_top_
 #endif
 }
 
+static inline bool on_thread_stack(void)
+{
+	return (unsigned long)(current_top_of_stack() -
+			       current_stack_pointer) < THREAD_SIZE;
+}
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else

@@ -141,8 +141,7 @@ void ist_begin_non_atomic(struct pt_regs
 	 * will catch asm bugs and any attempt to use ist_preempt_enable
 	 * from double_fault.
 	 */
-	BUG_ON((unsigned long)(current_top_of_stack() -
-			       current_stack_pointer) >= THREAD_SIZE);
+	BUG_ON(!on_thread_stack());
 
 	preempt_enable_no_resched();
 }

@@ -62,23 +62,19 @@ const static struct cpuid_dep cpuid_deps
 	{}
 };
 
-static inline void __clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit)
-{
-	clear_bit32(bit, c->x86_capability);
-}
-
-static inline void __setup_clear_cpu_cap(unsigned int bit)
-{
-	clear_cpu_cap(&boot_cpu_data, bit);
-	set_bit32(bit, cpu_caps_cleared);
-}
-
 static inline void clear_feature(struct cpuinfo_x86 *c, unsigned int feature)
 {
-	if (!c)
-		__setup_clear_cpu_cap(feature);
-	else
-		__clear_cpu_cap(c, feature);
+	/*
+	 * Note: This could use the non atomic __*_bit() variants, but the
+	 * rest of the cpufeature code uses atomics as well, so keep it for
+	 * consistency. Cleanup all of it separately.
+	 */
+	if (!c) {
+		clear_cpu_cap(&boot_cpu_data, feature);
+		set_bit(feature, (unsigned long *)cpu_caps_cleared);
+	} else {
+		clear_bit(feature, (unsigned long *)c->x86_capability);
+	}
 }
 
 /* Take the capabilities and the BUG bits into account */

@@ -228,32 +228,6 @@ static inline unsigned long __ffs64(u64
 	return __ffs((unsigned long)word);
 }
 
-/*
- * clear_bit32 - Clear a bit in memory for u32 array
- * @nr: Bit to clear
- * @addr: u32 * address of bitmap
- *
- * Same as clear_bit, but avoids needing casts for u32 arrays.
- */
-
-static __always_inline void clear_bit32(long nr, volatile u32 *addr)
-{
-	clear_bit(nr, (volatile unsigned long *)addr);
-}
-
-/*
- * set_bit32 - Set a bit in memory for u32 array
- * @nr: Bit to clear
- * @addr: u32 * address of bitmap
- *
- * Same as set_bit, but avoids needing casts for u32 arrays.
- */
-
-static __always_inline void set_bit32(long nr, volatile u32 *addr)
-{
-	set_bit(nr, (volatile unsigned long *)addr);
-}
-
 #ifdef __KERNEL__
 
 #ifndef set_mask_bits

@@ -200,10 +200,9 @@ enum page_cache_mode {
 
 #define _PAGE_ENC	(_AT(pteval_t, sme_me_mask))
 
-#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |	\
-			 _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_ENC)
 #define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |	\
 			 _PAGE_DIRTY | _PAGE_ENC)
+#define _PAGE_TABLE	(_KERNPG_TABLE | _PAGE_USER)
 
 #define __PAGE_KERNEL_ENC	(__PAGE_KERNEL | _PAGE_ENC)
 #define __PAGE_KERNEL_ENC_WP	(__PAGE_KERNEL_WP | _PAGE_ENC)

@@ -13,8 +13,8 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS	18	/* N 32-bit words worth of info */
-#define NBUGINTS	1	/* N 32-bit bug flags */
+#define NCAPINTS			18	   /* N 32-bit words worth of info */
+#define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
  * Note: If the comment begins with a quoted string, that string is used

@@ -28,163 +28,163 @@
  */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
+#define X86_FEATURE_FPU			( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME			( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE			( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE			( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC			( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR			( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE			( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE			( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8			( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC		( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP			( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR		( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE			( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA			( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV		( 0*32+15) /* CMOV instructions */
 					  /* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
-#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
+#define X86_FEATURE_PAT			( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36		( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN			( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH		( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS			( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI		( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX			( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR		( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM			( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2		( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP		( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT			( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC			( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64		( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE			( 0*32+31) /* Pending Break Enable */
 
 /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
 /* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
+#define X86_FEATURE_SYSCALL		( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP			( 1*32+19) /* MP Capable. */
+#define X86_FEATURE_NX			( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT		( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT		( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES		( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP		( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM			( 1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT		( 1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW		( 1*32+31) /* 3DNow! */
 
 /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
+#define X86_FEATURE_RECOVERY		( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN		( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI		( 2*32+ 3) /* LongRun table interface */
 
 /* Other features, Linux-defined mapping, word 3 */
 /* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
+#define X86_FEATURE_CXMMX		( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR		( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR		( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
 /* cpu types for specific tunings: */
-#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
-#define X86_FEATURE_ART		( 3*32+10) /* Platform has always running timer (ART) */
-#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
-#define X86_FEATURE_ACC_POWER	( 3*32+19) /* AMD Accumulated Power Mechanism */
-#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
-#define X86_FEATURE_CPUID	( 3*32+25) /* CPU has CPUID instruction itself */
-#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
-#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
-#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
+#define X86_FEATURE_K8			( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7			( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3			( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4			( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP			( 3*32+ 9) /* smp kernel running on up */
+#define X86_FEATURE_ART			( 3*32+10) /* Platform has always running timer (ART) */
+#define X86_FEATURE_ARCH_PERFMON	( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS		( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS			( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in ia32 userspace */
+#define X86_FEATURE_REP_GOOD		( 3*32+16) /* rep microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC	( 3*32+17) /* "" Mfence synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" Lfence synchronizes RDTSC */
+#define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
+#define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY		( 3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE	( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC		( 3*32+24) /* TSC does not stop in C states */
+#define X86_FEATURE_CPUID		( 3*32+25) /* CPU has CPUID instruction itself */
+#define X86_FEATURE_EXTD_APICID		( 3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM		( 3*32+27) /* multi-node processor */
+#define X86_FEATURE_APERFMPERF		( 3*32+28) /* APERFMPERF */
+#define X86_FEATURE_NONSTOP_TSC_S3	( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ	( 3*32+31) /* TSC has known frequency */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
-#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
-#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
-#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_XMM3		( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ		( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64		( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT		( 4*32+ 3) /* "monitor" Monitor/Mwait support */
+#define X86_FEATURE_DSCPL		( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+#define X86_FEATURE_VMX			( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX			( 4*32+ 6) /* Safer mode */
+#define X86_FEATURE_EST			( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2			( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3		( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID			( 4*32+10) /* Context ID */
+#define X86_FEATURE_SDBG		( 4*32+11) /* Silicon Debug */
+#define X86_FEATURE_FMA			( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16		( 4*32+13) /* CMPXCHG16B */
+#define X86_FEATURE_XTPR		( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM		( 4*32+15) /* Performance Capabilities */
+#define X86_FEATURE_PCID		( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA			( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1		( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2		( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC		( 4*32+21) /* x2APIC */
+#define X86_FEATURE_MOVBE		( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT		( 4*32+23) /* POPCNT instruction */
 #define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
-#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
+#define X86_FEATURE_AES			( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE		( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+#define X86_FEATURE_OSXSAVE		( 4*32+27) /* "" XSAVE enabled in the OS */
+#define X86_FEATURE_AVX			( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C		( 4*32+29) /* 16-bit fp conversions */
+#define X86_FEATURE_RDRAND		( 4*32+30) /* The RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR		( 4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
+#define X86_FEATURE_XSTORE		( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN		( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT		( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN		( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2		( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN		( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE			( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN		( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM			( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN		( 5*32+13) /* PMM enabled */
 
 /* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
-#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
-#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
-#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_LLC	( 6*32+28) /* Last Level Cache performance counter extensions */
-#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
+#define X86_FEATURE_LAHF_LM		( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY		( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM			( 6*32+ 2) /* Secure virtual machine */
+#define X86_FEATURE_EXTAPIC		( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY		( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM			( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A		( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE		( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH	( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW		( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS			( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP			( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT		( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT			( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP			( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4		( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE			( 6*32+17) /* translation cache extension */
+#define X86_FEATURE_NODEID_MSR		( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM			( 6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT		( 6*32+22) /* topology extensions CPUID leafs */
+#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_LLC		( 6*32+28) /* Last Level Cache performance counter extensions */
+#define X86_FEATURE_MWAITX		( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various