Merge branch 'upstream-x86-selftests' into WIP.x86/pti.base

Conflicts:
	arch/x86/kernel/cpu/Makefile
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/x86/x86_64/mm.txt

@@ -34,7 +34,7 @@ ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space
 ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole
 ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
 ... unused hole ...
-ffd8000000000000 - fff7ffffffffffff (=53 bits) kasan shadow memory (8PB)
+ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB)
 ... unused hole ...
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...

arch/x86/Kconfig

@@ -303,7 +303,6 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN
-	default 0xdff8000000000000 if X86_5LEVEL
 	default 0xdffffc0000000000
 
 config HAVE_INTEL_TXT

arch/x86/entry/syscalls/Makefile

 # SPDX-License-Identifier: GPL-2.0
-out := $(obj)/../../include/generated/asm
-uapi := $(obj)/../../include/generated/uapi/asm
+out := arch/$(SRCARCH)/include/generated/asm
+uapi := arch/$(SRCARCH)/include/generated/uapi/asm
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \

arch/x86/include/asm/pgtable_types.h

@@ -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)

arch/x86/kernel/Makefile

@@ -25,7 +25,8 @@ endif
 KASAN_SANITIZE_head$(BITS).o				:= n
 KASAN_SANITIZE_dumpstack.o				:= n
 KASAN_SANITIZE_dumpstack_$(BITS).o			:= n
-KASAN_SANITIZE_stacktrace.o := n
+KASAN_SANITIZE_stacktrace.o				:= n
+KASAN_SANITIZE_paravirt.o				:= n
 
 OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o	:= y
 OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o		:= y

arch/x86/kernel/cpu/cpuid-deps.c

@@ -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 */

arch/x86/kernel/head_64.S

@@ -38,11 +38,12 @@
  *
  */
 
-#define p4d_index(x)	(((x) >> P4D_SHIFT) & (PTRS_PER_P4D-1))
 #define pud_index(x)	(((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
 
+#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
 PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE)
 PGD_START_KERNEL = pgd_index(__START_KERNEL_map)
+#endif
 L3_START_KERNEL = pud_index(__START_KERNEL_map)
 
 	.text
@@ -362,10 +363,7 @@ NEXT_PAGE(early_dynamic_pgts)
 
 	.data
 
-#ifndef CONFIG_XEN
-NEXT_PAGE(init_top_pgt)
-	.fill	512,8,0
-#else
+#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
 NEXT_PAGE(init_top_pgt)
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.org    init_top_pgt + PGD_PAGE_OFFSET*8, 0
@@ -382,6 +380,9 @@ NEXT_PAGE(level2_ident_pgt)
 	 * Don't set NX because code runs from these pages.
 	 */
 	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
+#else
+NEXT_PAGE(init_top_pgt)
+	.fill	512,8,0
 #endif
 
 #ifdef CONFIG_X86_5LEVEL

arch/x86/mm/init_64.c

@@ -1426,16 +1426,16 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 
 #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(unsigned long section_nr,
 			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);
 		}

arch/x86/mm/kasan_init_64.c

@@ -16,6 +16,8 @@
 
 extern struct range pfn_mapped[E820_MAX_ENTRIES];
 
+static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
+
 static int __init map_range(struct range *range)
 {
 	unsigned long start;
@@ -31,8 +33,10 @@ static void __init clear_pgds(unsigned long start,
 			unsigned long end)
 {
 	pgd_t *pgd;
+	/* See comment in kasan_init() */
+	unsigned long pgd_end = end & PGDIR_MASK;
 
-	for (; start < end; start += PGDIR_SIZE) {
+	for (; start < pgd_end; start += PGDIR_SIZE) {
 		pgd = pgd_offset_k(start);
 		/*
 		 * With folded p4d, pgd_clear() is nop, use p4d_clear()
@@ -43,29 +47,61 @@ static void __init clear_pgds(unsigned long start,
 		else
 			pgd_clear(pgd);
 	}
+
+	pgd = pgd_offset_k(start);
+	for (; start < end; start += P4D_SIZE)
+		p4d_clear(p4d_offset(pgd, start));
+}
+
+static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr)
+{
+	unsigned long p4d;
+
+	if (!IS_ENABLED(CONFIG_X86_5LEVEL))
+		return (p4d_t *)pgd;
+
+	p4d = __pa_nodebug(pgd_val(*pgd)) & PTE_PFN_MASK;
+	p4d += __START_KERNEL_map - phys_base;
+	return (p4d_t *)p4d + p4d_index(addr);
+}
+
+static void __init kasan_early_p4d_populate(pgd_t *pgd,
+		unsigned long addr,
+		unsigned long end)
+{
+	pgd_t pgd_entry;
+	p4d_t *p4d, p4d_entry;
+	unsigned long next;
+
+	if (pgd_none(*pgd)) {
+		pgd_entry = __pgd(_KERNPG_TABLE | __pa_nodebug(kasan_zero_p4d));
+		set_pgd(pgd, pgd_entry);
+	}
+
+	p4d = early_p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+
+		if (!p4d_none(*p4d))
+			continue;
+
+		p4d_entry = __p4d(_KERNPG_TABLE | __pa_nodebug(kasan_zero_pud));
+		set_p4d(p4d, p4d_entry);
+	} while (p4d++, addr = next, addr != end && p4d_none(*p4d));
 }
 
 static void __init kasan_map_early_shadow(pgd_t *pgd)
 {
-	int i;
-	unsigned long start = KASAN_SHADOW_START;
+	/* See comment in kasan_init() */
+	unsigned long addr = KASAN_SHADOW_START & PGDIR_MASK;
 	unsigned long end = KASAN_SHADOW_END;
+	unsigned long next;
 
-	for (i = pgd_index(start); start < end; i++) {
-		switch (CONFIG_PGTABLE_LEVELS) {
-		case 4:
-			pgd[i] = __pgd(__pa_nodebug(kasan_zero_pud) |
-					_KERNPG_TABLE);
-			break;
-		case 5:
-			pgd[i] = __pgd(__pa_nodebug(kasan_zero_p4d) |
-					_KERNPG_TABLE);
-			break;
-		default:
-			BUILD_BUG();
-		}
-		start += PGDIR_SIZE;
-	}
+	pgd += pgd_index(addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		kasan_early_p4d_populate(pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
 }
 
 #ifdef CONFIG_KASAN_INLINE
@@ -102,7 +138,7 @@ void __init kasan_early_init(void)
 	for (i = 0; i < PTRS_PER_PUD; i++)
 		kasan_zero_pud[i] = __pud(pud_val);
 
-	for (i = 0; CONFIG_PGTABLE_LEVELS >= 5 && i < PTRS_PER_P4D; i++)
+	for (i = 0; IS_ENABLED(CONFIG_X86_5LEVEL) && i < PTRS_PER_P4D; i++)
 		kasan_zero_p4d[i] = __p4d(p4d_val);
 
 	kasan_map_early_shadow(early_top_pgt);
@@ -118,12 +154,35 @@ void __init kasan_init(void)
 #endif
 
 	memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt));
+
+	/*
+	 * We use the same shadow offset for 4- and 5-level paging to
+	 * facilitate boot-time switching between paging modes.
+	 * As result in 5-level paging mode KASAN_SHADOW_START and
+	 * KASAN_SHADOW_END are not aligned to PGD boundary.
+	 *
+	 * KASAN_SHADOW_START doesn't share PGD with anything else.
+	 * We claim whole PGD entry to make things easier.
+	 *
+	 * KASAN_SHADOW_END lands in the last PGD entry and it collides with
+	 * bunch of things like kernel code, modules, EFI mapping, etc.
+	 * We need to take extra steps to not overwrite them.
+	 */
+	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+		void *ptr;
+
+		ptr = (void *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
+		memcpy(tmp_p4d_table, (void *)ptr, sizeof(tmp_p4d_table));
+		set_pgd(&early_top_pgt[pgd_index(KASAN_SHADOW_END)],
+				__pgd(__pa(tmp_p4d_table) | _KERNPG_TABLE));
+	}
+
 	load_cr3(early_top_pgt);
 	__flush_tlb_all();
 
-	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
+	clear_pgds(KASAN_SHADOW_START & PGDIR_MASK, KASAN_SHADOW_END);
 
-	kasan_populate_zero_shadow((void *)KASAN_SHADOW_START,
+	kasan_populate_zero_shadow((void *)(KASAN_SHADOW_START & PGDIR_MASK),
 			kasan_mem_to_shadow((void *)PAGE_OFFSET));
 
 	for (i = 0; i < E820_MAX_ENTRIES; i++) {

arch/x86/xen/mmu_pv.c

@@ -449,7 +449,7 @@ __visible pmd_t xen_make_pmd(pmdval_t pmd)
 }
 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_t val)
 
 	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 *mm, p4d_t *p4d,
 		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_struct *mm, pgd_t *pgd,
 			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(unsigned long vaddr)
 {
 	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 long pfn)
 	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_to_phys(unsigned long vaddr)
  */
 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_init(void)
 	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_init(void)
 	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_ops __initconst = {
 	.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,

include/linux/bitops.h

@@ -228,32 +228,6 @@ static inline unsigned long __ffs64(u64 word)
 	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

include/linux/mm.h

@@ -2496,7 +2496,7 @@ 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,

include/linux/mmzone.h

@@ -1151,13 +1151,17 @@ 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];

mm/gup.c

@@ -1643,6 +1643,47 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+static void gup_pgd_range(unsigned long addr, unsigned long end,
+		int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	pgd_t *pgdp;
+
+	pgdp = pgd_offset(current->mm, addr);
+	do {
+		pgd_t pgd = READ_ONCE(*pgdp);
+
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(pgd))
+			return;
+		if (unlikely(pgd_huge(pgd))) {
+			if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
+					  pages, nr))
+				return;
+		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
+			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
+					 PGDIR_SHIFT, next, write, pages, nr))
+				return;
+		} else if (!gup_p4d_range(pgd, addr, next, write, pages, nr))
+			return;
+	} while (pgdp++, addr = next, addr != end);
+}
+
+#ifndef gup_fast_permitted
+/*
+ * Check if it's allowed to use __get_user_pages_fast() for the range, or
+ * we need to fall back to the slow version:
+ */
+bool gup_fast_permitted(unsigned long start, int nr_pages, int write)
+{
+	unsigned long len, end;
+
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	return end >= start;
+}
+#endif
+
 /*
  * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
  * the regular GUP. It will only return non-negative values.
@@ -1650,10 +1691,8 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
 int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			  struct page **pages)
 {
-	struct mm_struct *mm = current->mm;
 	unsigned long addr, len, end;
-	unsigned long next, flags;
-	pgd_t *pgdp;
+	unsigned long flags;
 	int nr = 0;
 
 	start &= PAGE_MASK;
@@ -1677,45 +1716,15 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	 * block IPIs that come from THPs splitting.
 	 */
 
-	local_irq_save(flags);
-	pgdp = pgd_offset(mm, addr);
-	do {
-		pgd_t pgd = READ_ONCE(*pgdp);
-
-		next = pgd_addr_end(addr, end);
-		if (pgd_none(pgd))
-			break;
-		if (unlikely(pgd_huge(pgd))) {
-			if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
-					  pages, &nr))
-				break;
-		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
-			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
-					 PGDIR_SHIFT, next, write, pages, &nr))
-				break;
-		} else if (!gup_p4d_range(pgd, addr, next, write, pages, &nr))
-			break;
-	} while (pgdp++, addr = next, addr != end);
-	local_irq_restore(flags);
+	if (gup_fast_permitted(start, nr_pages, write)) {
+		local_irq_save(flags);
+		gup_pgd_range(addr, end, write, pages, &nr);
+		local_irq_restore(flags);
+	}
 
 	return nr;
 }
 
-#ifndef gup_fast_permitted
-/*
- * Check if it's allowed to use __get_user_pages_fast() for the range, or
- * we need to fall back to the slow version:
- */
-bool gup_fast_permitted(unsigned long start, int nr_pages, int write)
-{
-	unsigned long len, end;
-
-	len = (unsigned long) nr_pages << PAGE_SHIFT;
-	end = start + len;
-	return end >= start;
-}
-#endif
-
 /**
  * get_user_pages_fast() - pin user pages in memory
  * @start:	starting user address
@@ -1735,12 +1744,22 @@ bool gup_fast_permitted(unsigned long start, int nr_pages, int write)
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages)
 {
+	unsigned long addr, len, end;
 	int nr = 0, ret = 0;
 
 	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+
+	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
+					(void __user *)start, len)))
+		return 0;
 
 	if (gup_fast_permitted(start, nr_pages, write)) {
-		nr = __get_user_pages_fast(start, nr_pages, write, pages);
+		local_irq_disable();
+		gup_pgd_range(addr, end, write, pages, &nr);
+		local_irq_enable();
 		ret = nr;
 	}
 

mm/page_alloc.c

@@ -5646,6 +5646,16 @@ void __init sparse_memory_present_with_active_regions(int nid)
 	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);
 }

mm/sparse.c

@@ -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(unsigned long section_nr, int nid)
 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 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 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)

tools/testing/selftests/x86/ldt_gdt.c

@@ -115,7 +115,15 @@ static void check_valid_segment(uint16_t index, int ldt,
 		return;
 	}
 
-	if (ar != expected_ar) {
+	/* The SDM says "bits 19:16 are undefined".  Thanks. */
+	ar &= ~0xF0000;
+
+	/*
+	 * NB: Different Linux versions do different things with the
+	 * accessed bit in set_thread_area().
+	 */
+	if (ar != expected_ar &&
+	    (ldt || ar != (expected_ar | AR_ACCESSED))) {
 		printf("[FAIL]\t%s entry %hu has AR 0x%08X but expected 0x%08X\n",
 		       (ldt ? "LDT" : "GDT"), index, ar, expected_ar);
 		nerrs++;
@@ -129,30 +137,51 @@ static void check_valid_segment(uint16_t index, int ldt,
 	}
 }
 
-static bool install_valid_mode(const struct user_desc *desc, uint32_t ar,
-			       bool oldmode)
+static bool install_valid_mode(const struct user_desc *d, uint32_t ar,
+			       bool oldmode, bool ldt)
 {
-	int ret = syscall(SYS_modify_ldt, oldmode ? 1 : 0x11,
-			  desc, sizeof(*desc));
-	if (ret < -1)
-		errno = -ret;
+	struct user_desc desc = *d;
+	int ret;
+
+	if (!ldt) {
+#ifndef __i386__
+		/* No point testing set_thread_area in a 64-bit build */
+		return false;
+#endif
+		if (!gdt_entry_num)
+			return false;
+		desc.entry_number = gdt_entry_num;
+
+		ret = syscall(SYS_set_thread_area, &desc);
+	} else {
+		ret = syscall(SYS_modify_ldt, oldmode ? 1 : 0x11,
+			      &desc, sizeof(desc));
+
+		if (ret < -1)
+			errno = -ret;
+
+		if (ret != 0 && errno == ENOSYS) {
+			printf("[OK]\tmodify_ldt returned -ENOSYS\n");
+			return false;
+		}
+	}
+
 	if (ret == 0) {
-		uint32_t limit = desc->limit;
-		if (desc->limit_in_pages)
+		uint32_t limit = desc.limit;
+		if (desc.limit_in_pages)
 			limit = (limit << 12) + 4095;
-		check_valid_segment(desc->entry_number, 1, ar, limit, true);
+		check_valid_segment(desc.entry_number, ldt, ar, limit, true);
 		return true;
-	} else if (errno == ENOSYS) {
-		printf("[OK]\tmodify_ldt returned -ENOSYS\n");
-		return false;
 	} else {
-		if (desc->seg_32bit) {
-			printf("[FAIL]\tUnexpected modify_ldt failure %d\n",
+		if (desc.seg_32bit) {
+			printf("[FAIL]\tUnexpected %s failure %d\n",
+			       ldt ? "modify_ldt" : "set_thread_area",
 			       errno);
 			nerrs++;
 			return false;
 		} else {
-			printf("[OK]\tmodify_ldt rejected 16 bit segment\n");
+			printf("[OK]\t%s rejected 16 bit segment\n",
+			       ldt ? "modify_ldt" : "set_thread_area");
 			return false;
 		}
 	}
@@ -160,7 +189,15 @@ static bool install_valid_mode(const struct user_desc *desc, uint32_t ar,
 
 static bool install_valid(const struct user_desc *desc, uint32_t ar)
 {
-	return install_valid_mode(desc, ar, false);
+	bool ret = install_valid_mode(desc, ar, false, true);
+
+	if (desc->contents <= 1 && desc->seg_32bit &&
+	    !desc->seg_not_present) {
+		/* Should work in the GDT, too. */
+		install_valid_mode(desc, ar, false, false);
+	}
+
+	return ret;
 }
 
 static void install_invalid(const struct user_desc *desc, bool oldmode)
@@ -367,9 +404,24 @@ static void do_simple_tests(void)
 	install_invalid(&desc, false);
 
 	desc.seg_not_present = 0;
-	desc.read_exec_only = 0;
 	desc.seg_32bit = 1;
+	desc.read_exec_only = 0;
+	desc.limit = 0xfffff;
+
 	install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S | AR_P | AR_DB);
+
+	desc.limit_in_pages = 1;
+
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S | AR_P | AR_DB | AR_G);
+	desc.read_exec_only = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA | AR_S | AR_P | AR_DB | AR_G);
+	desc.contents = 1;
+	desc.read_exec_only = 0;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA_EXPDOWN | AR_S | AR_P | AR_DB | AR_G);
+	desc.read_exec_only = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA_EXPDOWN | AR_S | AR_P | AR_DB | AR_G);
+
+	desc.limit = 0;
 	install_invalid(&desc, true);
 }
 

tools/testing/selftests/x86/protection_keys.c

@@ -189,17 +189,29 @@ void lots_o_noops_around_write(int *write_to_me)
 #define u64 uint64_t
 
 #ifdef __i386__
-#define SYS_mprotect_key 380
-#define SYS_pkey_alloc	 381
-#define SYS_pkey_free	 382
+
+#ifndef SYS_mprotect_key
+# define SYS_mprotect_key 380
+#endif
+#ifndef SYS_pkey_alloc
+# define SYS_pkey_alloc	 381
+# define SYS_pkey_free	 382
+#endif
 #define REG_IP_IDX REG_EIP
 #define si_pkey_offset 0x14
+
 #else
-#define SYS_mprotect_key 329
-#define SYS_pkey_alloc	 330
-#define SYS_pkey_free	 331
+
+#ifndef SYS_mprotect_key
+# define SYS_mprotect_key 329
+#endif
+#ifndef SYS_pkey_alloc
+# define SYS_pkey_alloc	 330
+# define SYS_pkey_free	 331
+#endif
 #define REG_IP_IDX REG_RIP
 #define si_pkey_offset 0x20
+
 #endif
 
 void dump_mem(void *dumpme, int len_bytes)