summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-11-15 19:42:40 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-15 19:42:40 -0800
commit7c225c69f86c934e3be9be63ecde754e286838d7 (patch)
treeff2df419b0c4886b37407235f7d21215e4cf45e4 /arch
parent6363b3f3ac5be096d08c8c504128befa0c033529 (diff)
parent1b7176aea0a924ac59c6a283129d3e8eb00aa915 (diff)
Merge branch 'akpm' (patches from Andrew)
Merge updates from Andrew Morton: - a few misc bits - ocfs2 updates - almost all of MM * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (131 commits) memory hotplug: fix comments when adding section mm: make alloc_node_mem_map a void call if we don't have CONFIG_FLAT_NODE_MEM_MAP mm: simplify nodemask printing mm,oom_reaper: remove pointless kthread_run() error check mm/page_ext.c: check if page_ext is not prepared writeback: remove unused function parameter mm: do not rely on preempt_count in print_vma_addr mm, sparse: do not swamp log with huge vmemmap allocation failures mm/hmm: remove redundant variable align_end mm/list_lru.c: mark expected switch fall-through mm/shmem.c: mark expected switch fall-through mm/page_alloc.c: broken deferred calculation mm: don't warn about allocations which stall for too long fs: fuse: account fuse_inode slab memory as reclaimable mm, page_alloc: fix potential false positive in __zone_watermark_ok mm: mlock: remove lru_add_drain_all() mm, sysctl: make NUMA stats configurable shmem: convert shmem_init_inodecache() to void Unify migrate_pages and move_pages access checks mm, pagevec: rename pagevec drained field ...
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/include/asm/dma-iommu.h1
-rw-r--r--arch/arm/include/asm/pgalloc.h2
-rw-r--r--arch/arm/mm/pgd.c2
-rw-r--r--arch/arm64/Kconfig2
-rw-r--r--arch/arm64/include/asm/pgalloc.h2
-rw-r--r--arch/arm64/mm/kasan_init.c130
-rw-r--r--arch/frv/mm/init.c14
-rw-r--r--arch/h8300/mm/init.c13
-rw-r--r--arch/m32r/Kconfig4
-rw-r--r--arch/mips/include/asm/pgtable-64.h8
-rw-r--r--arch/mn10300/kernel/head.S8
-rw-r--r--arch/openrisc/include/asm/dma-mapping.h1
-rw-r--r--arch/powerpc/include/asm/pgalloc.h2
-rw-r--r--arch/powerpc/mm/hugetlbpage.c1
-rw-r--r--arch/powerpc/mm/mmu_context_book3s64.c2
-rw-r--r--arch/powerpc/mm/pgtable_64.c2
-rw-r--r--arch/s390/include/asm/mmu_context.h4
-rw-r--r--arch/sh/kernel/dwarf.c4
-rw-r--r--arch/sh/kernel/head_64.S8
-rw-r--r--arch/sh/kernel/process.c2
-rw-r--r--arch/sparc/include/asm/pgtable_64.h30
-rw-r--r--arch/sparc/mm/hugetlbpage.c3
-rw-r--r--arch/sparc/mm/init_64.c38
-rw-r--r--arch/tile/mm/homecache.c2
-rw-r--r--arch/um/kernel/mem.c3
-rw-r--r--arch/unicore32/include/asm/pgalloc.h2
-rw-r--r--arch/unicore32/mm/pgd.c2
-rw-r--r--arch/x86/Kconfig5
-rw-r--r--arch/x86/Makefile5
-rw-r--r--arch/x86/include/asm/dma-mapping.h1
-rw-r--r--arch/x86/include/asm/kmemcheck.h42
-rw-r--r--arch/x86/include/asm/pgtable.h5
-rw-r--r--arch/x86/include/asm/pgtable_types.h13
-rw-r--r--arch/x86/include/asm/string_32.h9
-rw-r--r--arch/x86/include/asm/string_64.h8
-rw-r--r--arch/x86/include/asm/xor.h5
-rw-r--r--arch/x86/kernel/cpu/intel.c15
-rw-r--r--arch/x86/kernel/espfix_64.c2
-rw-r--r--arch/x86/kernel/traps.c5
-rw-r--r--arch/x86/mm/Makefile2
-rw-r--r--arch/x86/mm/fault.c6
-rw-r--r--arch/x86/mm/init.c8
-rw-r--r--arch/x86/mm/init_64.c13
-rw-r--r--arch/x86/mm/kasan_init_64.c143
-rw-r--r--arch/x86/mm/kmemcheck/Makefile1
-rw-r--r--arch/x86/mm/kmemcheck/error.c227
-rw-r--r--arch/x86/mm/kmemcheck/error.h15
-rw-r--r--arch/x86/mm/kmemcheck/kmemcheck.c658
-rw-r--r--arch/x86/mm/kmemcheck/opcode.c106
-rw-r--r--arch/x86/mm/kmemcheck/opcode.h9
-rw-r--r--arch/x86/mm/kmemcheck/pte.c22
-rw-r--r--arch/x86/mm/kmemcheck/pte.h10
-rw-r--r--arch/x86/mm/kmemcheck/selftest.c70
-rw-r--r--arch/x86/mm/kmemcheck/selftest.h6
-rw-r--r--arch/x86/mm/kmemcheck/shadow.c173
-rw-r--r--arch/x86/mm/kmemcheck/shadow.h18
-rw-r--r--arch/x86/mm/pageattr.c10
-rw-r--r--arch/x86/mm/pgtable.c2
-rw-r--r--arch/x86/platform/efi/efi_64.c2
59 files changed, 308 insertions, 1600 deletions
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
index 0722ec6be692..6821f1249300 100644
--- a/arch/arm/include/asm/dma-iommu.h
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -7,7 +7,6 @@
#include <linux/mm_types.h>
#include <linux/scatterlist.h>
#include <linux/dma-debug.h>
-#include <linux/kmemcheck.h>
#include <linux/kref.h>
#define ARM_MAPPING_ERROR (~(dma_addr_t)0x0)
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index b2902a5cd780..2d7344f0e208 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -57,7 +57,7 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
extern pgd_t *pgd_alloc(struct mm_struct *mm);
extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO)
static inline void clean_pte_table(pte_t *pte)
{
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index c1c1a5c67da1..61e281cb29fb 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -141,7 +141,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd_base)
pte = pmd_pgtable(*pmd);
pmd_clear(pmd);
pte_free(mm, pte);
- atomic_long_dec(&mm->nr_ptes);
+ mm_dec_nr_ptes(mm);
no_pmd:
pud_clear(pud);
pmd_free(mm, pmd);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index ba6aab55d464..a93339f5178f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -85,7 +85,7 @@ config ARM64
select HAVE_ARCH_BITREVERSE
select HAVE_ARCH_HUGE_VMAP
select HAVE_ARCH_JUMP_LABEL
- select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
+ select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
select HAVE_ARCH_KGDB
select HAVE_ARCH_MMAP_RND_BITS
select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index d25f4f137c2a..5ca6a573a701 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
#define check_pgt_cache() do { } while (0)
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO)
#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t))
#if CONFIG_PGTABLE_LEVELS > 2
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 81f03959a4ab..acba49fb5aac 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -11,6 +11,7 @@
*/
#define pr_fmt(fmt) "kasan: " fmt
+#include <linux/bootmem.h>
#include <linux/kasan.h>
#include <linux/kernel.h>
#include <linux/sched/task.h>
@@ -35,77 +36,117 @@ static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
* with the physical address from __pa_symbol.
*/
-static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr,
- unsigned long end)
+static phys_addr_t __init kasan_alloc_zeroed_page(int node)
{
- pte_t *pte;
- unsigned long next;
+ void *p = memblock_virt_alloc_try_nid(PAGE_SIZE, PAGE_SIZE,
+ __pa(MAX_DMA_ADDRESS),
+ MEMBLOCK_ALLOC_ACCESSIBLE, node);
+ return __pa(p);
+}
+
+static pte_t *__init kasan_pte_offset(pmd_t *pmd, unsigned long addr, int node,
+ bool early)
+{
+ if (pmd_none(*pmd)) {
+ phys_addr_t pte_phys = early ? __pa_symbol(kasan_zero_pte)
+ : kasan_alloc_zeroed_page(node);
+ __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE);
+ }
+
+ return early ? pte_offset_kimg(pmd, addr)
+ : pte_offset_kernel(pmd, addr);
+}
- if (pmd_none(*pmd))
- __pmd_populate(pmd, __pa_symbol(kasan_zero_pte), PMD_TYPE_TABLE);
+static pmd_t *__init kasan_pmd_offset(pud_t *pud, unsigned long addr, int node,
+ bool early)
+{
+ if (pud_none(*pud)) {
+ phys_addr_t pmd_phys = early ? __pa_symbol(kasan_zero_pmd)
+ : kasan_alloc_zeroed_page(node);
+ __pud_populate(pud, pmd_phys, PMD_TYPE_TABLE);
+ }
+
+ return early ? pmd_offset_kimg(pud, addr) : pmd_offset(pud, addr);
+}
+
+static pud_t *__init kasan_pud_offset(pgd_t *pgd, unsigned long addr, int node,
+ bool early)
+{
+ if (pgd_none(*pgd)) {
+ phys_addr_t pud_phys = early ? __pa_symbol(kasan_zero_pud)
+ : kasan_alloc_zeroed_page(node);
+ __pgd_populate(pgd, pud_phys, PMD_TYPE_TABLE);
+ }
+
+ return early ? pud_offset_kimg(pgd, addr) : pud_offset(pgd, addr);
+}
+
+static void __init kasan_pte_populate(pmd_t *pmd, unsigned long addr,
+ unsigned long end, int node, bool early)
+{
+ unsigned long next;
+ pte_t *pte = kasan_pte_offset(pmd, addr, node, early);
- pte = pte_offset_kimg(pmd, addr);
do {
+ phys_addr_t page_phys = early ? __pa_symbol(kasan_zero_page)
+ : kasan_alloc_zeroed_page(node);
next = addr + PAGE_SIZE;
- set_pte(pte, pfn_pte(sym_to_pfn(kasan_zero_page),
- PAGE_KERNEL));
+ set_pte(pte, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
} while (pte++, addr = next, addr != end && pte_none(*pte));
}
-static void __init kasan_early_pmd_populate(pud_t *pud,
- unsigned long addr,
- unsigned long end)
+static void __init kasan_pmd_populate(pud_t *pud, unsigned long addr,
+ unsigned long end, int node, bool early)
{
- pmd_t *pmd;
unsigned long next;
+ pmd_t *pmd = kasan_pmd_offset(pud, addr, node, early);
- if (pud_none(*pud))
- __pud_populate(pud, __pa_symbol(kasan_zero_pmd), PMD_TYPE_TABLE);
-
- pmd = pmd_offset_kimg(pud, addr);
do {
next = pmd_addr_end(addr, end);
- kasan_early_pte_populate(pmd, addr, next);
+ kasan_pte_populate(pmd, addr, next, node, early);
} while (pmd++, addr = next, addr != end && pmd_none(*pmd));
}
-static void __init kasan_early_pud_populate(pgd_t *pgd,
- unsigned long addr,
- unsigned long end)
+static void __init kasan_pud_populate(pgd_t *pgd, unsigned long addr,
+ unsigned long end, int node, bool early)
{
- pud_t *pud;
unsigned long next;
+ pud_t *pud = kasan_pud_offset(pgd, addr, node, early);
- if (pgd_none(*pgd))
- __pgd_populate(pgd, __pa_symbol(kasan_zero_pud), PUD_TYPE_TABLE);
-
- pud = pud_offset_kimg(pgd, addr);
do {
next = pud_addr_end(addr, end);
- kasan_early_pmd_populate(pud, addr, next);
+ kasan_pmd_populate(pud, addr, next, node, early);
} while (pud++, addr = next, addr != end && pud_none(*pud));
}
-static void __init kasan_map_early_shadow(void)
+static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
+ int node, bool early)
{
- unsigned long addr = KASAN_SHADOW_START;
- unsigned long end = KASAN_SHADOW_END;
unsigned long next;
pgd_t *pgd;
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
- kasan_early_pud_populate(pgd, addr, next);
+ kasan_pud_populate(pgd, addr, next, node, early);
} while (pgd++, addr = next, addr != end);
}
+/* The early shadow maps everything to a single page of zeroes */
asmlinkage void __init kasan_early_init(void)
{
BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_END - (1UL << 61));
BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE));
BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE));
- kasan_map_early_shadow();
+ kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE,
+ true);
+}
+
+/* Set up full kasan mappings, ensuring that the mapped pages are zeroed */
+static void __init kasan_map_populate(unsigned long start, unsigned long end,
+ int node)
+{
+ kasan_pgd_populate(start & PAGE_MASK, PAGE_ALIGN(end), node, false);
}
/*
@@ -142,8 +183,8 @@ void __init kasan_init(void)
struct memblock_region *reg;
int i;
- kimg_shadow_start = (u64)kasan_mem_to_shadow(_text);
- kimg_shadow_end = (u64)kasan_mem_to_shadow(_end);
+ kimg_shadow_start = (u64)kasan_mem_to_shadow(_text) & PAGE_MASK;
+ kimg_shadow_end = PAGE_ALIGN((u64)kasan_mem_to_shadow(_end));
mod_shadow_start = (u64)kasan_mem_to_shadow((void *)MODULES_VADDR);
mod_shadow_end = (u64)kasan_mem_to_shadow((void *)MODULES_END);
@@ -161,19 +202,8 @@ void __init kasan_init(void)
clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
- vmemmap_populate(kimg_shadow_start, kimg_shadow_end,
- pfn_to_nid(virt_to_pfn(lm_alias(_text))));
-
- /*
- * vmemmap_populate() has populated the shadow region that covers the
- * kernel image with SWAPPER_BLOCK_SIZE mappings, so we have to round
- * the start and end addresses to SWAPPER_BLOCK_SIZE as well, to prevent
- * kasan_populate_zero_shadow() from replacing the page table entries
- * (PMD or PTE) at the edges of the shadow region for the kernel
- * image.
- */
- kimg_shadow_start = round_down(kimg_shadow_start, SWAPPER_BLOCK_SIZE);
- kimg_shadow_end = round_up(kimg_shadow_end, SWAPPER_BLOCK_SIZE);
+ kasan_map_populate(kimg_shadow_start, kimg_shadow_end,
+ pfn_to_nid(virt_to_pfn(lm_alias(_text))));
kasan_populate_zero_shadow((void *)KASAN_SHADOW_START,
(void *)mod_shadow_start);
@@ -191,9 +221,9 @@ void __init kasan_init(void)
if (start >= end)
break;
- vmemmap_populate((unsigned long)kasan_mem_to_shadow(start),
- (unsigned long)kasan_mem_to_shadow(end),
- pfn_to_nid(virt_to_pfn(start)));
+ kasan_map_populate((unsigned long)kasan_mem_to_shadow(start),
+ (unsigned long)kasan_mem_to_shadow(end),
+ pfn_to_nid(virt_to_pfn(start)));
}
/*
diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c
index 328f0a292316..cf464100e838 100644
--- a/arch/frv/mm/init.c
+++ b/arch/frv/mm/init.c
@@ -42,21 +42,9 @@
#undef DEBUG
/*
- * BAD_PAGE is the page that is used for page faults when linux
- * is out-of-memory. Older versions of linux just did a
- * do_exit(), but using this instead means there is less risk
- * for a process dying in kernel mode, possibly leaving a inode
- * unused etc..
- *
- * BAD_PAGETABLE is the accompanying page-table: it is initialized
- * to point to BAD_PAGE entries.
- *
* ZERO_PAGE is a special page that is used for zero-initialized
* data and COW.
*/
-static unsigned long empty_bad_page_table;
-static unsigned long empty_bad_page;
-
unsigned long empty_zero_page;
EXPORT_SYMBOL(empty_zero_page);
@@ -72,8 +60,6 @@ void __init paging_init(void)
unsigned long zones_size[MAX_NR_ZONES] = {0, };
/* allocate some pages for kernel housekeeping tasks */
- empty_bad_page_table = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
- empty_bad_page = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
empty_zero_page = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
memset((void *) empty_zero_page, 0, PAGE_SIZE);
diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c
index eeead51bed2d..015287ac8ce8 100644
--- a/arch/h8300/mm/init.c
+++ b/arch/h8300/mm/init.c
@@ -40,20 +40,9 @@
#include <asm/sections.h>
/*
- * BAD_PAGE is the page that is used for page faults when linux
- * is out-of-memory. Older versions of linux just did a
- * do_exit(), but using this instead means there is less risk
- * for a process dying in kernel mode, possibly leaving a inode
- * unused etc..
- *
- * BAD_PAGETABLE is the accompanying page-table: it is initialized
- * to point to BAD_PAGE entries.
- *
* ZERO_PAGE is a special page that is used for zero-initialized
* data and COW.
*/
-static unsigned long empty_bad_page_table;
-static unsigned long empty_bad_page;
unsigned long empty_zero_page;
/*
@@ -78,8 +67,6 @@ void __init paging_init(void)
* Initialize the bad page table and bad page to point
* to a couple of allocated pages.
*/
- empty_bad_page_table = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
- empty_bad_page = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
empty_zero_page = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
memset((void *)empty_zero_page, 0, PAGE_SIZE);
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 0d9446c37ae8..498398d915c1 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -196,8 +196,8 @@ config TIMER_DIVIDE
default "128"
config CPU_BIG_ENDIAN
- bool "Generate big endian code"
- default n
+ bool
+ default !CPU_LITTLE_ENDIAN
config CPU_LITTLE_ENDIAN
bool "Generate little endian code"
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index 67fe6dc5211c..0036ea0c7173 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -31,12 +31,7 @@
* tables. Each page table is also a single 4K page, giving 512 (==
* PTRS_PER_PTE) 8 byte ptes. Each pud entry is initialized to point to
* invalid_pmd_table, each pmd entry is initialized to point to
- * invalid_pte_table, each pte is initialized to 0. When memory is low,
- * and a pmd table or a page table allocation fails, empty_bad_pmd_table
- * and empty_bad_page_table is returned back to higher layer code, so
- * that the failure is recognized later on. Linux does not seem to
- * handle these failures very well though. The empty_bad_page_table has
- * invalid pte entries in it, to force page faults.
+ * invalid_pte_table, each pte is initialized to 0.
*
* Kernel mappings: kernel mappings are held in the swapper_pg_table.
* The layout is identical to userspace except it's indexed with the
@@ -175,7 +170,6 @@
printk("%s:%d: bad pgd %016lx.\n", __FILE__, __LINE__, pgd_val(e))
extern pte_t invalid_pte_table[PTRS_PER_PTE];
-extern pte_t empty_bad_page_table[PTRS_PER_PTE];
#ifndef __PAGETABLE_PUD_FOLDED
/*
diff --git a/arch/mn10300/kernel/head.S b/arch/mn10300/kernel/head.S
index 73e00fc78072..0b15f759e0d2 100644
--- a/arch/mn10300/kernel/head.S
+++ b/arch/mn10300/kernel/head.S
@@ -434,14 +434,6 @@ ENTRY(empty_zero_page)
.space PAGE_SIZE
.balign PAGE_SIZE
-ENTRY(empty_bad_page)
- .space PAGE_SIZE
-
- .balign PAGE_SIZE
-ENTRY(empty_bad_pte_table)
- .space PAGE_SIZE
-
- .balign PAGE_SIZE
ENTRY(large_page_table)
.space PAGE_SIZE
diff --git a/arch/openrisc/include/asm/dma-mapping.h b/arch/openrisc/include/asm/dma-mapping.h
index f41bd3cb76d9..e212a1f0b6d2 100644
--- a/arch/openrisc/include/asm/dma-mapping.h
+++ b/arch/openrisc/include/asm/dma-mapping.h
@@ -23,7 +23,6 @@
*/
#include <linux/dma-debug.h>
-#include <linux/kmemcheck.h>
#include <linux/dma-mapping.h>
extern const struct dma_map_ops or1k_dma_map_ops;
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index a14203c005f1..e11f03007b57 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -18,7 +18,7 @@ static inline gfp_t pgtable_gfp_flags(struct mm_struct *mm, gfp_t gfp)
}
#endif /* MODULE */
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO)
#ifdef CONFIG_PPC_BOOK3S
#include <asm/book3s/pgalloc.h>
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 1571a498a33f..a9b9083c5e49 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -433,6 +433,7 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
pud = pud_offset(pgd, start);
pgd_clear(pgd);
pud_free_tlb(tlb, pud, start);
+ mm_dec_nr_puds(tlb->mm);
}
/*
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 05e15386d4cb..a7e998158f37 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -200,7 +200,7 @@ static void destroy_pagetable_page(struct mm_struct *mm)
/* We allow PTE_FRAG_NR fragments from a PTE page */
if (page_ref_sub_and_test(page, PTE_FRAG_NR - count)) {
pgtable_page_dtor(page);
- free_hot_cold_page(page, 0);
+ free_unref_page(page);
}
}
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index ac0717a90ca6..1ec3aee43624 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -404,7 +404,7 @@ void pte_fragment_free(unsigned long *table, int kernel)
if (put_page_testzero(page)) {
if (!kernel)
pgtable_page_dtor(page);
- free_hot_cold_page(page, 0);
+ free_unref_page(page);
}
}
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 43607bb12cc2..cf4c1cb17dcd 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -44,6 +44,8 @@ static inline int init_new_context(struct task_struct *tsk,
mm->context.asce_limit = STACK_TOP_MAX;
mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
_ASCE_USER_BITS | _ASCE_TYPE_REGION3;
+ /* pgd_alloc() did not account this pud */
+ mm_inc_nr_puds(mm);
break;
case -PAGE_SIZE:
/* forked 5-level task, set new asce with new_mm->pgd */
@@ -59,7 +61,7 @@ static inline int init_new_context(struct task_struct *tsk,
/* forked 2-level compat task, set new asce with new mm->pgd */
mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
_ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
- /* pgd_alloc() did not increase mm->nr_pmds */
+ /* pgd_alloc() did not account this pmd */
mm_inc_nr_pmds(mm);
}
crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
diff --git a/arch/sh/kernel/dwarf.c b/arch/sh/kernel/dwarf.c
index e1d751ae2498..1a2526676a87 100644
--- a/arch/sh/kernel/dwarf.c
+++ b/arch/sh/kernel/dwarf.c
@@ -1172,11 +1172,11 @@ static int __init dwarf_unwinder_init(void)
dwarf_frame_cachep = kmem_cache_create("dwarf_frames",
sizeof(struct dwarf_frame), 0,
- SLAB_PANIC | SLAB_HWCACHE_ALIGN | SLAB_NOTRACK, NULL);
+ SLAB_PANIC | SLAB_HWCACHE_ALIGN, NULL);
dwarf_reg_cachep = kmem_cache_create("dwarf_regs",
sizeof(struct dwarf_reg), 0,
- SLAB_PANIC | SLAB_HWCACHE_ALIGN | SLAB_NOTRACK, NULL);
+ SLAB_PANIC | SLAB_HWCACHE_ALIGN, NULL);
dwarf_frame_pool = mempool_create_slab_pool(DWARF_FRAME_MIN_REQ,
dwarf_frame_cachep);
diff --git a/arch/sh/kernel/head_64.S b/arch/sh/kernel/head_64.S
index defd851abefa..cca491397a28 100644
--- a/arch/sh/kernel/head_64.S
+++ b/arch/sh/kernel/head_64.S
@@ -101,14 +101,6 @@ empty_zero_page:
mmu_pdtp_cache:
.space PAGE_SIZE, 0
- .global empty_bad_page
-empty_bad_page:
- .space PAGE_SIZE, 0
-
- .global empty_bad_pte_table
-empty_bad_pte_table:
- .space PAGE_SIZE, 0
-
.global fpu_in_use
fpu_in_use: .quad 0
diff --git a/arch/sh/kernel/process.c b/arch/sh/kernel/process.c
index b2d9963d5978..68b1a67533ce 100644
--- a/arch/sh/kernel/process.c
+++ b/arch/sh/kernel/process.c
@@ -59,7 +59,7 @@ void arch_task_cache_init(void)
task_xstate_cachep = kmem_cache_create("task_xstate", xstate_size,
__alignof__(union thread_xstate),
- SLAB_PANIC | SLAB_NOTRACK, NULL);
+ SLAB_PANIC, NULL);
}
#ifdef CONFIG_SH_FPU_EMU
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index fd9d9bac7cfa..5a9e96be1665 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -231,6 +231,36 @@ extern unsigned long _PAGE_ALL_SZ_BITS;
extern struct page *mem_map_zero;
#define ZERO_PAGE(vaddr) (mem_map_zero)
+/* This macro must be updated when the size of struct page grows above 80
+ * or reduces below 64.
+ * The idea that compiler optimizes out switch() statement, and only
+ * leaves clrx instructions
+ */
+#define mm_zero_struct_page(pp) do { \
+ unsigned long *_pp = (void *)(pp); \
+ \
+ /* Check that struct page is either 64, 72, or 80 bytes */ \
+ BUILD_BUG_ON(sizeof(struct page) & 7); \
+ BUILD_BUG_ON(sizeof(struct page) < 64); \
+ BUILD_BUG_ON(sizeof(struct page) > 80); \
+ \
+ switch (sizeof(struct page)) { \
+ case 80: \
+ _pp[9] = 0; /* fallthrough */ \
+ case 72: \
+ _pp[8] = 0; /* fallthrough */ \
+ default: \
+ _pp[7] = 0; \
+ _pp[6] = 0; \
+ _pp[5] = 0; \
+ _pp[4] = 0; \
+ _pp[3] = 0; \
+ _pp[2] = 0; \
+ _pp[1] = 0; \
+ _pp[0] = 0; \
+ } \
+} while (0)
+
/* PFNs are real physical page numbers. However, mem_map only begins to record
* per-page information starting at pfn_base. This is to handle systems where
* the first physical page in the machine is at some huge physical address,
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 5078b7f68890..0112d6942288 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -397,7 +397,7 @@ static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
pmd_clear(pmd);
pte_free_tlb(tlb, token, addr);
- atomic_long_dec(&tlb->mm->nr_ptes);
+ mm_dec_nr_ptes(tlb->mm);
}
static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
@@ -472,6 +472,7 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
pud = pud_offset(pgd, start);
pgd_clear(pgd);
pud_free_tlb(tlb, pud, start);
+ mm_dec_nr_puds(tlb->mm);
}
void hugetlb_free_pgd_range(struct mmu_gather *tlb,
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 61bdc1270d19..55ba62957e64 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2540,10 +2540,17 @@ void __init mem_init(void)
{
high_memory = __va(last_valid_pfn << PAGE_SHIFT);
- register_page_bootmem_info();
free_all_bootmem();
/*
+ * Must be done after boot memory is put on freelist, because here we
+ * might set fields in deferred struct pages that have not yet been
+ * initialized, and free_all_bootmem() initializes all the reserved
+ * deferred pages for us.
+ */
+ register_page_bootmem_info();
+
+ /*
* Set up the zero page, mark it reserved, so that page count
* is not manipulated when freeing the page from user ptes.
*/
@@ -2637,30 +2644,19 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
vstart = vstart & PMD_MASK;
vend = ALIGN(vend, PMD_SIZE);
for (; vstart < vend; vstart += PMD_SIZE) {
- pgd_t *pgd = pgd_offset_k(vstart);
+ pgd_t *pgd = vmemmap_pgd_populate(vstart, node);
unsigned long pte;
pud_t *pud;
pmd_t *pmd;
- if (pgd_none(*pgd)) {
- pud_t *new = vmemmap_alloc_block(PAGE_SIZE, node);
-
- if (!new)
- return -ENOMEM;
- pgd_populate(&init_mm, pgd, new);
- }
-
- pud = pud_offset(pgd, vstart);
- if (pud_none(*pud)) {
- pmd_t *new = vmemmap_alloc_block(PAGE_SIZE, node);
+ if (!pgd)
+ return -ENOMEM;
- if (!new)
- return -ENOMEM;
- pud_populate(&init_mm, pud, new);
- }
+ pud = vmemmap_pud_populate(pgd, vstart, node);
+ if (!pud)
+ return -ENOMEM;
pmd = pmd_offset(pud, vstart);
-
pte = pmd_val(*pmd);
if (!(pte & _PAGE_VALID)) {
void *block = vmemmap_alloc_block(PMD_SIZE, node);
@@ -2927,7 +2923,7 @@ void __flush_tlb_all(void)
pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+ struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO);
pte_t *pte = NULL;
if (page)
@@ -2939,11 +2935,11 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
pgtable_t pte_alloc_one(struct mm_struct *mm,
unsigned long address)
{
- struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+ struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (!page)
return NULL;
if (!pgtable_page_ctor(page)) {
- free_hot_cold_page(page, 0);
+ free_unref_page(page);
return NULL;
}
return (pte_t *) page_address(page);
diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c
index b51cc28acd0a..4432f31e8479 100644
--- a/arch/tile/mm/homecache.c
+++ b/arch/tile/mm/homecache.c
@@ -409,7 +409,7 @@ void __homecache_free_pages(struct page *page, unsigned int order)
if (put_page_testzero(page)) {
homecache_change_page_home(page, order, PAGE_HOME_HASH);
if (order == 0) {
- free_hot_cold_page(page, false);
+ free_unref_page(page);
} else {
init_page_count(page);
__free_pages(page, order);
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index e7437ec62710..3c0e470ea646 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -22,8 +22,6 @@
/* allocated in paging_init, zeroed in mem_init, and unchanged thereafter */
unsigned long *empty_zero_page = NULL;
EXPORT_SYMBOL(empty_zero_page);
-/* allocated in paging_init and unchanged thereafter */
-static unsigned long *empty_bad_page = NULL;
/*
* Initialized during boot, and readonly for initializing page tables
@@ -146,7 +144,6 @@ void __init paging_init(void)
int i;
empty_zero_page = (unsigned long *) alloc_bootmem_low_pages(PAGE_SIZE);
- empty_bad_page = (unsigned long *) alloc_bootmem_low_pages(PAGE_SIZE);
for (i = 0; i < ARRAY_SIZE(zones_size); i++)
zones_size[i] = 0;
diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h
index 26775793c204..f0fdb268f8f2 100644
--- a/arch/unicore32/include/asm/pgalloc.h
+++ b/arch/unicore32/include/asm/pgalloc.h
@@ -28,7 +28,7 @@ extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd);
#define pgd_alloc(mm) get_pgd_slow(mm)
#define pgd_free(mm, pgd) free_pgd_slow(mm, pgd)
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO)
/*
* Allocate one PTE table.
diff --git a/arch/unicore32/mm/pgd.c b/arch/unicore32/mm/pgd.c
index c572a28c76c9..a830a300aaa1 100644
--- a/arch/unicore32/mm/pgd.c
+++ b/arch/unicore32/mm/pgd.c
@@ -97,7 +97,7 @@ void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd)
pte = pmd_pgtable(*pmd);
pmd_clear(pmd);
pte_free(mm, pte);
- atomic_long_dec(&mm->nr_ptes);
+ mm_dec_nr_ptes(mm);
pmd_free(mm, pmd);
mm_dec_nr_pmds(mm);
free:
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f08977d82ca0..df3276d6bfe3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -110,9 +110,8 @@ config X86
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
select HAVE_ARCH_JUMP_LABEL
- select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
+ select HAVE_ARCH_KASAN if X86_64
select HAVE_ARCH_KGDB
- select HAVE_ARCH_KMEMCHECK
select HAVE_ARCH_MMAP_RND_BITS if MMU
select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT
select HAVE_ARCH_COMPAT_MMAP_BASES if MMU && COMPAT
@@ -1430,7 +1429,7 @@ config ARCH_DMA_ADDR_T_64BIT
config X86_DIRECT_GBPAGES
def_bool y
- depends on X86_64 && !DEBUG_PAGEALLOC && !KMEMCHECK
+ depends on X86_64 && !DEBUG_PAGEALLOC
---help---
Certain kernel features effectively disable kernel
linear 1 GB mappings (even if the CPU otherwise
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index a20eacd9c7e9..3e73bc255e4e 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -158,11 +158,6 @@ ifdef CONFIG_X86_X32
endif
export CONFIG_X86_X32_ABI
-# Don't unroll struct assignments with kmemcheck enabled
-ifeq ($(CONFIG_KMEMCHECK),y)
- KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy)
-endif
-
#
# If the function graph tracer is used with mcount instead of fentry,
# '-maccumulate-outgoing-args' is needed to prevent a GCC bug
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 43cbe843de8d..0350d99bb8fd 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -7,7 +7,6 @@
* Documentation/DMA-API.txt for documentation.
*/
-#include <linux/kmemcheck.h>
#include <linux/scatterlist.h>
#include <linux/dma-debug.h>
#include <asm/io.h>
diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h
index 945a0337fbcf..ea32a7d3cf1b 100644
--- a/arch/x86/include/asm/kmemcheck.h
+++ b/arch/x86/include/asm/kmemcheck.h
@@ -1,43 +1 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_X86_KMEMCHECK_H
-#define ASM_X86_KMEMCHECK_H
-
-#include <linux/types.h>
-#include <asm/ptrace.h>
-
-#ifdef CONFIG_KMEMCHECK
-bool kmemcheck_active(struct pt_regs *regs);
-
-void kmemcheck_show(struct pt_regs *regs);
-void kmemcheck_hide(struct pt_regs *regs);
-
-bool kmemcheck_fault(struct pt_regs *regs,
- unsigned long address, unsigned long error_code);
-bool kmemcheck_trap(struct pt_regs *regs);
-#else
-static inline bool kmemcheck_active(struct pt_regs *regs)
-{
- return false;
-}
-
-static inline void kmemcheck_show(struct pt_regs *regs)
-{
-}
-
-static inline void kmemcheck_hide(struct pt_regs *regs)
-{
-}
-
-static inline bool kmemcheck_fault(struct pt_regs *regs,
- unsigned long address, unsigned long error_code)
-{
- return false;
-}
-
-static inline bool kmemcheck_trap(struct pt_regs *regs)
-{
- return false;
-}
-#endif /* CONFIG_KMEMCHECK */
-
-#endif
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index f735c3016325..09f9e1e00e3b 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -667,11 +667,6 @@ static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
return false;
}
-static inline int pte_hidden(pte_t pte)
-{
- return pte_flags(pte) & _PAGE_HIDDEN;
-}
-
static inline int pmd_present(pmd_t pmd)
{
/*
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 9e9b05fc4860..3696398a9475 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -32,7 +32,6 @@
#define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1
#define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1
-#define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */
#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */
#define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4
@@ -79,18 +78,6 @@
#define _PAGE_KNL_ERRATUM_MASK 0
#endif
-#ifdef CONFIG_KMEMCHECK
-#define _PAGE_HIDDEN (_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
-#else
-#define _PAGE_HIDDEN (_AT(pteval_t, 0))
-#endif
-
-/*
- * The same hidden bit is used by kmemcheck, but since kmemcheck
- * works on kernel pages while soft-dirty engine on user space,
- * they do not conflict with each other.
- */
-
#ifdef CONFIG_MEM_SOFT_DIRTY
#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY)
#else
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index 076502241eae..55d392c6bd29 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -179,8 +179,6 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len)
* No 3D Now!
*/
-#ifndef CONFIG_KMEMCHECK
-
#if (__GNUC__ >= 4)
#define memcpy(t, f, n) __builtin_memcpy(t, f, n)
#else
@@ -189,13 +187,6 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len)
? __constant_memcpy((t), (f), (n)) \
: __memcpy((t), (f), (n)))
#endif
-#else
-/*
- * kmemcheck becomes very happy if we use the REP instructions unconditionally,
- * because it means that we know both memory operands in advance.
- */
-#define memcpy(t, f, n) __memcpy((t), (f), (n))
-#endif
#endif
#endif /* !CONFIG_FORTIFY_SOURCE */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 0b1b4445f4c5..533f74c300c2 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -33,7 +33,6 @@ extern void *memcpy(void *to, const void *from, size_t len);
extern void *__memcpy(void *to, const void *from, size_t len);
#ifndef CONFIG_FORTIFY_SOURCE
-#ifndef CONFIG_KMEMCHECK
#if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4
#define memcpy(dst, src, len) \
({ \
@@ -46,13 +45,6 @@ extern void *__memcpy(void *to, const void *from, size_t len);
__ret; \
})
#endif
-#else
-/*
- * kmemcheck becomes very happy if we use the REP instructions unconditionally,
- * because it means that we know both memory operands in advance.
- */
-#define memcpy(dst, src, len) __inline_memcpy((dst), (src), (len))
-#endif
#endif /* !CONFIG_FORTIFY_SOURCE */
#define __HAVE_ARCH_MEMSET
diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h
index 1f5c5161ead6..45c8605467f1 100644
--- a/arch/x86/include/asm/xor.h
+++ b/arch/x86/include/asm/xor.h
@@ -1,7 +1,4 @@
-#ifdef CONFIG_KMEMCHECK
-/* kmemcheck doesn't handle MMX/SSE/SSE2 instructions */
-# include <asm-generic/xor.h>
-#elif !defined(_ASM_X86_XOR_H)
+#ifndef _ASM_X86_XOR_H
#define _ASM_X86_XOR_H
/*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b720dacac051..b1af22073e28 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -187,21 +187,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
if (c->x86 == 6 && c->x86_model < 15)
clear_cpu_cap(c, X86_FEATURE_PAT);
-#ifdef CONFIG_KMEMCHECK
- /*
- * P4s have a "fast strings" feature which causes single-
- * stepping REP instructions to only generate a #DB on
- * cache-line boundaries.
- *
- * Ingo Molnar reported a Pentium D (model 6) and a Xeon
- * (model 2) with the same problem.
- */
- if (c->x86 == 15)
- if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
- MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0)
- pr_info("kmemcheck: Disabling fast string operations\n");
-#endif
-
/*
* If fast string is not enabled in IA32_MISC_ENABLE for any reason,
* clear the fast string and enhanced fast string CPU capabilities.
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 7d7715dde901..e5ec3cafa72e 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -57,7 +57,7 @@
# error "Need more virtual address space for the ESPFIX hack"
#endif
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO)
/* This contains the *bottom* address of the espfix stack */
DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index b7b0f74a2150..989514c94a55 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -42,7 +42,6 @@
#include <linux/edac.h>
#endif
-#include <asm/kmemcheck.h>
#include <asm/stacktrace.h>
#include <asm/processor.h>
#include <asm/debugreg.h>
@@ -749,10 +748,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
if (!dr6 && user_mode(regs))
user_icebp = 1;
- /* Catch kmemcheck conditions! */
- if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
- goto exit;
-
/* Store the virtualized DR6 value */
tsk->thread.debugreg6 = dr6;
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 7ba7f3d7f477..8e13b8cc6bed 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -29,8 +29,6 @@ obj-$(CONFIG_X86_PTDUMP) += debug_pagetables.o
obj-$(CONFIG_HIGHMEM) += highmem_32.o
-obj-$(CONFIG_KMEMCHECK) += kmemcheck/
-
KASAN_SANITIZE_kasan_init_$(BITS).o := n
obj-$(CONFIG_KASAN) += kasan_init_$(BITS).o
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 3109ba6c6ede..78ca9a8ee454 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -20,7 +20,6 @@
#include <asm/cpufeature.h> /* boot_cpu_has, ... */
#include <asm/traps.h> /* dotraplinkage, ... */
#include <asm/pgalloc.h> /* pgd_*(), ... */
-#include <asm/kmemcheck.h> /* kmemcheck_*(), ... */
#include <asm/fixmap.h> /* VSYSCALL_ADDR */
#include <asm/vsyscall.h> /* emulate_vsyscall */
#include <asm/vm86.h> /* struct vm86 */
@@ -1256,8 +1255,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
* Detect and handle instructions that would cause a page fault for
* both a tracked kernel page and a userspace page.
*/
- if (kmemcheck_active(regs))
- kmemcheck_hide(regs);
prefetchw(&mm->mmap_sem);
if (unlikely(kmmio_fault(regs, address)))
@@ -1280,9 +1277,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
if (!(error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
if (vmalloc_fault(address) >= 0)
return;
-
- if (kmemcheck_fault(regs, address, error_code))
- return;
}
/* Can handle a stale RO->RW TLB: */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index a22c2b95e513..6fdf91ef130a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -92,8 +92,7 @@ __ref void *alloc_low_pages(unsigned int num)
unsigned int order;
order = get_order((unsigned long)num << PAGE_SHIFT);
- return (void *)__get_free_pages(GFP_ATOMIC | __GFP_NOTRACK |
- __GFP_ZERO, order);
+ return (void *)__get_free_pages(GFP_ATOMIC | __GFP_ZERO, order);
}
if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) {
@@ -164,12 +163,11 @@ static int page_size_mask;
static void __init probe_page_size_mask(void)
{
/*
- * For CONFIG_KMEMCHECK or pagealloc debugging, identity mapping will
- * use small pages.
+ * For pagealloc debugging, identity mapping will use small pages.
* This will simplify cpa(), which otherwise needs to support splitting
* large pages into small in interrupt context, etc.
*/
- if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled() && !IS_ENABLED(CONFIG_KMEMCHECK))
+ if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled())
page_size_mask |= 1 << PG_LEVEL_2M;
else
direct_gbpages = 0;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index adcea90a2046..4a837289f2ad 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -184,7 +184,7 @@ static __ref void *spp_getpage(void)
void *ptr;
if (after_bootmem)
- ptr = (void *) get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK);
+ ptr = (void *) get_zeroed_page(GFP_ATOMIC);
else
ptr = alloc_bootmem_pages(PAGE_SIZE);
@@ -1173,12 +1173,18 @@ void __init mem_init(void)
/* clear_bss() already clear the empty_zero_page */
- register_page_bootmem_info();
-
/* this will put all memory onto the freelists */
free_all_bootmem();
after_bootmem = 1;
+ /*
+ * Must be done after boot memory is put on freelist, because here we
+ * might set fields in deferred struct pages that have not yet been
+ * initialized, and free_all_bootmem() initializes all the reserved
+ * deferred pages for us.
+ */
+ register_page_bootmem_info();
+
/* Register memory areas for /proc/kcore */
kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR,
PAGE_SIZE, KCORE_OTHER);
@@ -1399,7 +1405,6 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
vmemmap_verify((pte_t *)pmd, node, addr, next);
continue;
}
- pr_warn_once("vmemmap: falling back to regular page backing\n");
if (vmemmap_populate_basepages(addr, next, node))
return -ENOMEM;
}
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 2b60dc6e64b1..99dfed6dfef8 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -4,12 +4,14 @@
#include <linux/bootmem.h>
#include <linux/kasan.h>
#include <linux/kdebug.h>
+#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/sched/task.h>
#include <linux/vmalloc.h>
#include <asm/e820/types.h>
+#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/pgtable.h>
@@ -18,7 +20,134 @@ 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)
+static __init void *early_alloc(size_t size, int nid)
+{
+ return memblock_virt_alloc_try_nid_nopanic(size, size,
+ __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
+}
+
+static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
+ unsigned long end, int nid)
+{
+ pte_t *pte;
+
+ if (pmd_none(*pmd)) {
+ void *p;
+
+ if (boot_cpu_has(X86_FEATURE_PSE) &&
+ ((end - addr) == PMD_SIZE) &&
+ IS_ALIGNED(addr, PMD_SIZE)) {
+ p = early_alloc(PMD_SIZE, nid);
+ if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
+ return;
+ else if (p)
+ memblock_free(__pa(p), PMD_SIZE);
+ }
+
+ p = early_alloc(PAGE_SIZE, nid);
+ pmd_populate_kernel(&init_mm, pmd, p);
+ }
+
+ pte = pte_offset_kernel(pmd, addr);
+ do {
+ pte_t entry;
+ void *p;
+
+ if (!pte_none(*pte))
+ continue;
+
+ p = early_alloc(PAGE_SIZE, nid);
+ entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL);
+ set_pte_at(&init_mm, addr, pte, entry);
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+}
+
+static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
+ unsigned long end, int nid)
+{
+ pmd_t *pmd;
+ unsigned long next;
+
+ if (pud_none(*pud)) {
+ void *p;
+
+ if (boot_cpu_has(X86_FEATURE_GBPAGES) &&
+ ((end - addr) == PUD_SIZE) &&
+ IS_ALIGNED(addr, PUD_SIZE)) {
+ p = early_alloc(PUD_SIZE, nid);
+ if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL))
+ return;
+ else if (p)
+ memblock_free(__pa(p), PUD_SIZE);
+ }
+
+ p = early_alloc(PAGE_SIZE, nid);
+ pud_populate(&init_mm, pud, p);
+ }
+
+ pmd = pmd_offset(pud, addr);
+ do {
+ next = pmd_addr_end(addr, end);
+ if (!pmd_large(*pmd))
+ kasan_populate_pmd(pmd, addr, next, nid);
+ } while (pmd++, addr = next, addr != end);
+}
+
+static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr,
+ unsigned long end, int nid)
+{
+ pud_t *pud;
+ unsigned long next;
+
+ if (p4d_none(*p4d)) {
+ void *p = early_alloc(PAGE_SIZE, nid);
+
+ p4d_populate(&init_mm, p4d, p);
+ }
+
+ pud = pud_offset(p4d, addr);
+ do {
+ next = pud_addr_end(addr, end);
+ if (!pud_large(*pud))
+ kasan_populate_pud(pud, addr, next, nid);
+ } while (pud++, addr = next, addr != end);
+}
+
+static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr,
+ unsigned long end, int nid)
+{
+ void *p;
+ p4d_t *p4d;
+ unsigned long next;
+
+ if (pgd_none(*pgd)) {
+ p = early_alloc(PAGE_SIZE, nid);
+ pgd_populate(&init_mm, pgd, p);
+ }
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ kasan_populate_p4d(p4d, addr, next, nid);
+ } while (p4d++, addr = next, addr != end);
+}
+
+static void __init kasan_populate_shadow(unsigned long addr, unsigned long end,
+ int nid)
+{
+ pgd_t *pgd;
+ unsigned long next;
+
+ addr = addr & PAGE_MASK;
+ end = round_up(end, PAGE_SIZE);
+ pgd = pgd_offset_k(addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ kasan_populate_pgd(pgd, addr, next, nid);
+ } while (pgd++, addr = next, addr != end);
+}
+
+static void __init map_range(struct range *range)
{
unsigned long start;
unsigned long end;
@@ -26,7 +155,7 @@ static int __init map_range(struct range *range)
start = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->start));
end = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->end));
- return vmemmap_populate(start, end, NUMA_NO_NODE);
+ kasan_populate_shadow(start, end, early_pfn_to_nid(range->start));
}
static void __init clear_pgds(unsigned long start,
@@ -189,16 +318,16 @@ void __init kasan_init(void)
if (pfn_mapped[i].end == 0)
break;
- if (map_range(&pfn_mapped[i]))
- panic("kasan: unable to allocate shadow!");
+ map_range(&pfn_mapped[i]);
}
+
kasan_populate_zero_shadow(
kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
kasan_mem_to_shadow((void *)__START_KERNEL_map));
- vmemmap_populate((unsigned long)kasan_mem_to_shadow(_stext),
- (unsigned long)kasan_mem_to_shadow(_end),
- NUMA_NO_NODE);
+ kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext),
+ (unsigned long)kasan_mem_to_shadow(_end),
+ early_pfn_to_nid(__pa(_stext)));
kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
(void *)KASAN_SHADOW_END);
diff --git a/arch/x86/mm/kmemcheck/Makefile b/arch/x86/mm/kmemcheck/Makefile
deleted file mode 100644
index 520b3bce4095..000000000000
--- a/arch/x86/mm/kmemcheck/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-y := error.o kmemcheck.o opcode.o pte.o selftest.o shadow.o
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
index 872ec4159a68..cec594032515 100644
--- a/arch/x86/mm/kmemcheck/error.c
+++ b/arch/x86/mm/kmemcheck/error.c
@@ -1,228 +1 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/interrupt.h>
-#include <linux/kdebug.h>
-#include <linux/kmemcheck.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/ptrace.h>
-#include <linux/stacktrace.h>
-#include <linux/string.h>
-
-#include "error.h"
-#include "shadow.h"
-
-enum kmemcheck_error_type {
- KMEMCHECK_ERROR_INVALID_ACCESS,
- KMEMCHECK_ERROR_BUG,
-};
-
-#define SHADOW_COPY_SIZE (1 << CONFIG_KMEMCHECK_SHADOW_COPY_SHIFT)
-
-struct kmemcheck_error {
- enum kmemcheck_error_type type;
-
- union {
- /* KMEMCHECK_ERROR_INVALID_ACCESS */
- struct {
- /* Kind of access that caused the error */
- enum kmemcheck_shadow state;
- /* Address and size of the erroneous read */
- unsigned long address;
- unsigned int size;
- };
- };
-
- struct pt_regs regs;
- struct stack_trace trace;
- unsigned long trace_entries[32];
-
- /* We compress it to a char. */
- unsigned char shadow_copy[SHADOW_COPY_SIZE];
- unsigned char memory_copy[SHADOW_COPY_SIZE];
-};
-
-/*
- * Create a ring queue of errors to output. We can't call printk() directly
- * from the kmemcheck traps, since this may call the console drivers and
- * result in a recursive fault.
- */
-static struct kmemcheck_error error_fifo[CONFIG_KMEMCHECK_QUEUE_SIZE];
-static unsigned int error_count;
-static unsigned int error_rd;
-static unsigned int error_wr;
-static unsigned int error_missed_count;
-
-static struct kmemcheck_error *error_next_wr(void)
-{
- struct kmemcheck_error *e;
-
- if (error_count == ARRAY_SIZE(error_fifo)) {
- ++error_missed_count;
- return NULL;
- }
-
- e = &error_fifo[error_wr];
- if (++error_wr == ARRAY_SIZE(error_fifo))
- error_wr = 0;
- ++error_count;
- return e;
-}
-
-static struct kmemcheck_error *error_next_rd(void)
-{
- struct kmemcheck_error *e;
-
- if (error_count == 0)
- return NULL;
-
- e = &error_fifo[error_rd];
- if (++error_rd == ARRAY_SIZE(error_fifo))
- error_rd = 0;
- --error_count;
- return e;
-}
-
-void kmemcheck_error_recall(void)
-{
- static const char *desc[] = {
- [KMEMCHECK_SHADOW_UNALLOCATED] = "unallocated",
- [KMEMCHECK_SHADOW_UNINITIALIZED] = "uninitialized",
- [KMEMCHECK_SHADOW_INITIALIZED] = "initialized",
- [KMEMCHECK_SHADOW_FREED] = "freed",
- };
-
- static const char short_desc[] = {
- [KMEMCHECK_SHADOW_UNALLOCATED] = 'a',
- [KMEMCHECK_SHADOW_UNINITIALIZED] = 'u',
- [KMEMCHECK_SHADOW_INITIALIZED] = 'i',
- [KMEMCHECK_SHADOW_FREED] = 'f',
- };
-
- struct kmemcheck_error *e;
- unsigned int i;
-
- e = error_next_rd();
- if (!e)
- return;
-
- switch (e->type) {
- case KMEMCHECK_ERROR_INVALID_ACCESS:
- printk(KERN_WARNING "WARNING: kmemcheck: Caught %d-bit read from %s memory (%p)\n",
- 8 * e->size, e->state < ARRAY_SIZE(desc) ?
- desc[e->state] : "(invalid shadow state)",
- (void *) e->address);
-
- printk(KERN_WARNING);
- for (i = 0; i < SHADOW_COPY_SIZE; ++i)
- printk(KERN_CONT "%02x", e->memory_copy[i]);
- printk(KERN_CONT "\n");
-
- printk(KERN_WARNING);
- for (i = 0; i < SHADOW_COPY_SIZE; ++i) {
- if (e->shadow_copy[i] < ARRAY_SIZE(short_desc))
- printk(KERN_CONT " %c", short_desc[e->shadow_copy[i]]);
- else
- printk(KERN_CONT " ?");
- }
- printk(KERN_CONT "\n");
- printk(KERN_WARNING "%*c\n", 2 + 2
- * (int) (e->address & (SHADOW_COPY_SIZE - 1)), '^');
- break;
- case KMEMCHECK_ERROR_BUG:
- printk(KERN_EMERG "ERROR: kmemcheck: Fatal error\n");
- break;
- }
-
- __show_regs(&e->regs, 1);
- print_stack_trace(&e->trace, 0);
-}
-
-static void do_wakeup(unsigned long data)
-{
- while (error_count > 0)
- kmemcheck_error_recall();
-
- if (error_missed_count > 0) {
- printk(KERN_WARNING "kmemcheck: Lost %d error reports because "
- "the queue was too small\n", error_missed_count);
- error_missed_count = 0;
- }
-}
-
-static DECLARE_TASKLET(kmemcheck_tasklet, &do_wakeup, 0);
-
-/*
- * Save the context of an error report.
- */
-void kmemcheck_error_save(enum kmemcheck_shadow state,
- unsigned long address, unsigned int size, struct pt_regs *regs)
-{
- static unsigned long prev_ip;
-
- struct kmemcheck_error *e;
- void *shadow_copy;
- void *memory_copy;
-
- /* Don't report several adjacent errors from the same EIP. */
- if (regs->ip == prev_ip)
- return;
- prev_ip = regs->ip;
-
- e = error_next_wr();
- if (!e)
- return;
-
- e->type = KMEMCHECK_ERROR_INVALID_ACCESS;
-
- e->state = state;
- e->address = address;
- e->size = size;
-
- /* Save regs */
- memcpy(&e->regs, regs, sizeof(*regs));
-
- /* Save stack trace */
- e->trace.nr_entries = 0;
- e->trace.entries = e->trace_entries;
- e->trace.max_entries = ARRAY_SIZE(e->trace_entries);
- e->trace.skip = 0;
- save_stack_trace_regs(regs, &e->trace);
-
- /* Round address down to nearest 16 bytes */
- shadow_copy = kmemcheck_shadow_lookup(address
- & ~(SHADOW_COPY_SIZE - 1));
- BUG_ON(!shadow_copy);
-
- memcpy(e->shadow_copy, shadow_copy, SHADOW_COPY_SIZE);
-
- kmemcheck_show_addr(address);
- memory_copy = (void *) (address & ~(SHADOW_COPY_SIZE - 1));
- memcpy(e->memory_copy, memory_copy, SHADOW_COPY_SIZE);
- kmemcheck_hide_addr(address);
-
- tasklet_hi_schedule_first(&kmemcheck_tasklet);
-}
-
-/*
- * Save the context of a kmemcheck bug.
- */
-void kmemcheck_error_save_bug(struct pt_regs *regs)
-{
- struct kmemcheck_error *e;
-
- e = error_next_wr();
- if (!e)
- return;
-
- e->type = KMEMCHECK_ERROR_BUG;
-
- memcpy(&e->regs, regs, sizeof(*regs));
-
- e->trace.nr_entries = 0;
- e->trace.entries = e->trace_entries;
- e->trace.max_entries = ARRAY_SIZE(e->trace_entries);
- e->trace.skip = 1;
- save_stack_trace(&e->trace);
-
- tasklet_hi_schedule_first(&kmemcheck_tasklet);
-}
diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h
index 39f80d7a874d..ea32a7d3cf1b 100644
--- a/arch/x86/mm/kmemcheck/error.h
+++ b/arch/x86/mm/kmemcheck/error.h
@@ -1,16 +1 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ARCH__X86__MM__KMEMCHECK__ERROR_H
-#define ARCH__X86__MM__KMEMCHECK__ERROR_H
-
-#include <linux/ptrace.h>
-
-#include "shadow.h"
-
-void kmemcheck_error_save(enum kmemcheck_shadow state,
- unsigned long address, unsigned int size, struct pt_regs *regs);
-
-void kmemcheck_error_save_bug(struct pt_regs *regs);
-
-void kmemcheck_error_recall(void);
-
-#endif
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
deleted file mode 100644
index 4515bae36bbe..000000000000
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ /dev/null
@@ -1,658 +0,0 @@
-/**
- * kmemcheck - a heavyweight memory checker for the linux kernel
- * Copyright (C) 2007, 2008 Vegard Nossum <vegardno@ifi.uio.no>
- * (With a lot of help from Ingo Molnar and Pekka Enberg.)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2) as
- * published by the Free Software Foundation.
- */
-
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/kallsyms.h>
-#include <linux/kernel.h>
-#include <linux/kmemcheck.h>
-#include <linux/mm.h>
-#include <linux/page-flags.h>
-#include <linux/percpu.h>
-#include <linux/ptrace.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-#include <asm/cacheflush.h>
-#include <asm/kmemcheck.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-
-#include "error.h"
-#include "opcode.h"
-#include "pte.h"
-#include "selftest.h"
-#include "shadow.h"
-
-
-#ifdef CONFIG_KMEMCHECK_DISABLED_BY_DEFAULT
-# define KMEMCHECK_ENABLED 0
-#endif
-
-#ifdef CONFIG_KMEMCHECK_ENABLED_BY_DEFAULT
-# define KMEMCHECK_ENABLED 1
-#endif
-
-#ifdef CONFIG_KMEMCHECK_ONESHOT_BY_DEFAULT
-# define KMEMCHECK_ENABLED 2
-#endif
-
-int kmemcheck_enabled = KMEMCHECK_ENABLED;
-
-int __init kmemcheck_init(void)
-{
-#ifdef CONFIG_SMP
- /*
- * Limit SMP to use a single CPU. We rely on the fact that this code
- * runs before SMP is set up.
- */
- if (setup_max_cpus > 1) {
- printk(KERN_INFO
- "kmemcheck: Limiting number of CPUs to 1.\n");
- setup_max_cpus = 1;
- }
-#endif
-
- if (!kmemcheck_selftest()) {
- printk(KERN_INFO "kmemcheck: self-tests failed; disabling\n");
- kmemcheck_enabled = 0;
- return -EINVAL;
- }
-
- printk(KERN_INFO "kmemcheck: Initialized\n");
- return 0;
-}
-
-early_initcall(kmemcheck_init);
-
-/*
- * We need to parse the kmemcheck= option before any memory is allocated.
- */
-static int __init param_kmemcheck(char *str)
-{
- int val;
- int ret;
-
- if (!str)
- return -EINVAL;
-
- ret = kstrtoint(str, 0, &val);
- if (ret)
- return ret;
- kmemcheck_enabled = val;
- return 0;
-}
-
-early_param("kmemcheck", param_kmemcheck);
-
-int kmemcheck_show_addr(unsigned long address)
-{
- pte_t *pte;
-
- pte = kmemcheck_pte_lookup(address);
- if (!pte)
- return 0;
-
- set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
- __flush_tlb_one(address);
- return 1;
-}
-
-int kmemcheck_hide_addr(unsigned long address)
-{
- pte_t *pte;
-
- pte = kmemcheck_pte_lookup(address);
- if (!pte)
- return 0;
-
- set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
- __flush_tlb_one(address);
- return 1;
-}
-
-struct kmemcheck_context {
- bool busy;
- int balance;
-
- /*
- * There can be at most two memory operands to an instruction, but
- * each address can cross a page boundary -- so we may need up to
- * four addresses that must be hidden/revealed for each fault.
- */
- unsigned long addr[4];
- unsigned long n_addrs;
- unsigned long flags;
-
- /* Data size of the instruction that caused a fault. */
- unsigned int size;
-};
-
-static DEFINE_PER_CPU(struct kmemcheck_context, kmemcheck_context);
-
-bool kmemcheck_active(struct pt_regs *regs)
-{
- struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
-
- return data->balance > 0;
-}
-
-/* Save an address that needs to be shown/hidden */
-static void kmemcheck_save_addr(unsigned long addr)
-{
- struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
-
- BUG_ON(data->n_addrs >= ARRAY_SIZE(data->addr));
- data->addr[data->n_addrs++] = addr;
-}
-
-static unsigned int kmemcheck_show_all(void)
-{
- struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
- unsigned int i;
- unsigned int n;
-
- n = 0;
- for (i = 0; i < data->n_addrs; ++i)
- n += kmemcheck_show_addr(data->addr[i]);
-
- return n;
-}
-
-static unsigned int kmemcheck_hide_all(void)
-{
- struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
- unsigned int i;
- unsigned int n;
-
- n = 0;
- for (i = 0; i < data->n_addrs; ++i)
- n += kmemcheck_hide_addr(data->addr[i]);
-
- return n;
-}
-
-/*
- * Called from the #PF handler.
- */
-void kmemcheck_show(struct pt_regs *regs)
-{
- struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
-
- BUG_ON(!irqs_disabled());
-
- if (unlikely(data->balance != 0)) {
- kmemcheck_show_all();
- kmemcheck_error_save_bug(regs);
- data->balance = 0;
- return;
- }
-
- /*
- * None of the addresses actually belonged to kmemcheck. Note that
- * this is not an error.
- */
- if (kmemcheck_show_all() == 0)
- return;
-
- ++data->balance;
-
- /*
- * The IF needs to be cleared as well, so that the faulting
- * instruction can run "uninterrupted". Otherwise, we might take
- * an interrupt and start executing that before we've had a chance
- * to hide the page again.
- *
- * NOTE: In the rare case of multiple faults, we must not override
- * the original flags:
- */
- if (!(regs->flags & X86_EFLAGS_TF))
- data->flags = regs->flags;
-
- regs->flags |= X86_EFLAGS_TF;
- regs->flags &= ~X86_EFLAGS_IF;
-}
-
-/*
- * Called from the #DB handler.
- */
-void kmemcheck_hide(struct pt_regs *regs)
-{
- struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
- int n;
-
- BUG_ON(!irqs_disabled());
-
- if (unlikely(data->balance != 1)) {
- kmemcheck_show_all();
- kmemcheck_error_save_bug(regs);
- data->n_addrs = 0;
- data->balance = 0;
-
- if (!(data->flags & X86_EFLAGS_TF))
- regs->flags &= ~X86_EFLAGS_TF;
- if (data->flags & X86_EFLAGS_IF)
- regs->flags |= X86_EFLAGS_IF;
- return;
- }
-
- if (kmemcheck_enabled)
- n = kmemcheck_hide_all();
- else
- n = kmemcheck_show_all();
-
- if (n == 0)
- return;
-
- --data->balance;
-
- data->n_addrs = 0;
-
- if (!(data->flags & X86_EFLAGS_TF))
- regs->flags &= ~X86_EFLAGS_TF;
- if (data->flags & X86_EFLAGS_IF)
- regs->flags |= X86_EFLAGS_IF;
-}
-
-void kmemcheck_show_pages(struct page *p, unsigned int n)
-{
- unsigned int i;
-
- for (i = 0; i < n; ++i) {
- unsigned long address;
- pte_t *pte;
- unsigned int level;
-
- address = (unsigned long) page_address(&p[i]);
- pte = lookup_address(address, &level);
- BUG_ON(!pte);
- BUG_ON(level != PG_LEVEL_4K);
-
- set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
- set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_HIDDEN));
- __flush_tlb_one(address);
- }
-}
-
-bool kmemcheck_page_is_tracked(struct page *p)
-{
- /* This will also check the "hidden" flag of the PTE. */
- return kmemcheck_pte_lookup((unsigned long) page_address(p));
-}
-
-void kmemcheck_hide_pages(struct page *p, unsigned int n)
-{
- unsigned int i;
-
- for (i = 0; i < n; ++i) {
- unsigned long address;
- pte_t *pte;
- unsigned int level;
-
- address = (unsigned long) page_address(&p[i]);
- pte = lookup_address(address, &level);
- BUG_ON(!pte);
- BUG_ON(level != PG_LEVEL_4K);
-
- set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
- set_pte(pte, __pte(pte_val(*pte) | _PAGE_HIDDEN));
- __flush_tlb_one(address);
- }
-}
-
-/* Access may NOT cross page boundary */
-static void kmemcheck_read_strict(struct pt_regs *regs,
- unsigned long addr, unsigned int size)
-{
- void *shadow;
- enum kmemcheck_shadow status;
-
- shadow = kmemcheck_shadow_lookup(addr);
- if (!shadow)
- return;
-
- kmemcheck_save_addr(addr);
- status = kmemcheck_shadow_test(shadow, size);
- if (status == KMEMCHECK_SHADOW_INITIALIZED)
- return;
-
- if (kmemcheck_enabled)
- kmemcheck_error_save(status, addr, size, regs);
-
- if (kmemcheck_enabled == 2)
- kmemcheck_enabled = 0;
-
- /* Don't warn about it again. */
- kmemcheck_shadow_set(shadow, size);
-}
-
-bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size)
-{
- enum kmemcheck_shadow status;
- void *shadow;
-
- shadow = kmemcheck_shadow_lookup(addr);
- if (!shadow)
- return true;
-
- status = kmemcheck_shadow_test_all(shadow, size);
-
- return status == KMEMCHECK_SHADOW_INITIALIZED;
-}
-
-/* Access may cross page boundary */
-static void kmemcheck_read(struct pt_regs *regs,
- unsigned long addr, unsigned int size)
-{
- unsigned long page = addr & PAGE_MASK;
- unsigned long next_addr = addr + size - 1;
- unsigned long next_page = next_addr & PAGE_MASK;
-
- if (likely(page == next_page)) {
- kmemcheck_read_strict(regs, addr, size);
- return;
- }
-
- /*
- * What we do is basically to split the access across the
- * two pages and handle each part separately. Yes, this means
- * that we may now see reads that are 3 + 5 bytes, for
- * example (and if both are uninitialized, there will be two
- * reports), but it makes the code a lot simpler.
- */
- kmemcheck_read_strict(regs, addr, next_page - addr);
- kmemcheck_read_strict(regs, next_page, next_addr - next_page);
-}
-
-static void kmemcheck_write_strict(struct pt_regs *regs,
- unsigned long addr, unsigned int size)
-{
- void *shadow;
-
- shadow = kmemcheck_shadow_lookup(addr);
- if (!shadow)
- return;
-
- kmemcheck_save_addr(addr);
- kmemcheck_shadow_set(shadow, size);
-}
-
-static void kmemcheck_write(struct pt_regs *regs,
- unsigned long addr, unsigned int size)
-{
- unsigned long page = addr & PAGE_MASK;
- unsigned long next_addr = addr + size - 1;
- unsigned long next_page = next_addr & PAGE_MASK;
-
- if (likely(page == next_page)) {
- kmemcheck_write_strict(regs, addr, size);
- return;
- }
-
- /* See comment in kmemcheck_read(). */
- kmemcheck_write_strict(regs, addr, next_page - addr);
- kmemcheck_write_strict(regs, next_page, next_addr - next_page);
-}
-
-/*
- * Copying is hard. We have two addresses, each of which may be split across
- * a page (and each page will have different shadow addresses).
- */
-static void kmemcheck_copy(struct pt_regs *regs,
- unsigned long src_addr, unsigned long dst_addr, unsigned int size)
-{
- uint8_t shadow[8];
- enum kmemcheck_shadow status;
-
- unsigned long page;
- unsigned long next_addr;
- unsigned long next_page;
-
- uint8_t *x;
- unsigned int i;
- unsigned int n;
-
- BUG_ON(size > sizeof(shadow));
-
- page = src_addr & PAGE_MASK;
- next_addr = src_addr + size - 1;
- next_page = next_addr & PAGE_MASK;
-
- if (likely(page == next_page)) {
- /* Same page */
- x = kmemcheck_shadow_lookup(src_addr);
- if (x) {
- kmemcheck_save_addr(src_addr);
- for (i = 0; i < size; ++i)
- shadow[i] = x[i];
- } else {
- for (i = 0; i < size; ++i)
- shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
- }
- } else {
- n = next_page - src_addr;
- BUG_ON(n > sizeof(shadow));
-
- /* First page */
- x = kmemcheck_shadow_lookup(src_addr);
- if (x) {
- kmemcheck_save_addr(src_addr);
- for (i = 0; i < n; ++i)
- shadow[i] = x[i];
- } else {
- /* Not tracked */
- for (i = 0; i < n; ++i)
- shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
- }
-
- /* Second page */
- x = kmemcheck_shadow_lookup(next_page);
- if (x) {
- kmemcheck_save_addr(next_page);
- for (i = n; i < size; ++i)
- shadow[i] = x[i - n];
- } else {
- /* Not tracked */
- for (i = n; i < size; ++i)
- shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
- }
- }
-
- page = dst_addr & PAGE_MASK;
- next_addr = dst_addr + size - 1;
- next_page = next_addr & PAGE_MASK;
-
- if (likely(page == next_page)) {
- /* Same page */
- x = kmemcheck_shadow_lookup(dst_addr);
- if (x) {
- kmemcheck_save_addr(dst_addr);
- for (i = 0; i < size; ++i) {
- x[i] = shadow[i];
- shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
- }
- }
- } else {
- n = next_page - dst_addr;
- BUG_ON(n > sizeof(shadow));
-
- /* First page */
- x = kmemcheck_shadow_lookup(dst_addr);
- if (x) {
- kmemcheck_save_addr(dst_addr);
- for (i = 0; i < n; ++i) {
- x[i] = shadow[i];
- shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
- }
- }
-
- /* Second page */
- x = kmemcheck_shadow_lookup(next_page);
- if (x) {
- kmemcheck_save_addr(next_page);
- for (i = n; i < size; ++i) {
- x[i - n] = shadow[i];
- shadow[i] = KMEMCHECK_SHADOW_INITIALIZED;
- }
- }
- }
-
- status = kmemcheck_shadow_test(shadow, size);
- if (status == KMEMCHECK_SHADOW_INITIALIZED)
- return;
-
- if (kmemcheck_enabled)
- kmemcheck_error_save(status, src_addr, size, regs);
-
- if (kmemcheck_enabled == 2)
- kmemcheck_enabled = 0;
-}
-
-enum kmemcheck_method {
- KMEMCHECK_READ,
- KMEMCHECK_WRITE,
-};
-
-static void kmemcheck_access(struct pt_regs *regs,
- unsigned long fallback_address, enum kmemcheck_method fallback_method)
-{
- const uint8_t *insn;
- const uint8_t *insn_primary;
- unsigned int size;
-
- struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
-
- /* Recursive fault -- ouch. */
- if (data->busy) {
- kmemcheck_show_addr(fallback_address);
- kmemcheck_error_save_bug(regs);
- return;
- }
-
- data->busy = true;
-
- insn = (const uint8_t *) regs->ip;
- insn_primary = kmemcheck_opcode_get_primary(insn);
-
- kmemcheck_opcode_decode(insn, &size);
-
- switch (insn_primary[0]) {
-#ifdef CONFIG_KMEMCHECK_BITOPS_OK
- /* AND, OR, XOR */
- /*
- * Unfortunately, these instructions have to be excluded from
- * our regular checking since they access only some (and not
- * all) bits. This clears out "bogus" bitfield-access warnings.
- */
- case 0x80:
- case 0x81:
- case 0x82:
- case 0x83:
- switch ((insn_primary[1] >> 3) & 7) {
- /* OR */
- case 1:
- /* AND */
- case 4:
- /* XOR */
- case 6:
- kmemcheck_write(regs, fallback_address, size);
- goto out;
-
- /* ADD */
- case 0:
- /* ADC */
- case 2:
- /* SBB */
- case 3:
- /* SUB */
- case 5:
- /* CMP */
- case 7:
- break;
- }
- break;
-#endif
-
- /* MOVS, MOVSB, MOVSW, MOVSD */
- case 0xa4:
- case 0xa5:
- /*
- * These instructions are special because they take two
- * addresses, but we only get one page fault.
- */
- kmemcheck_copy(regs, regs->si, regs->di, size);
- goto out;
-
- /* CMPS, CMPSB, CMPSW, CMPSD */
- case 0xa6:
- case 0xa7:
- kmemcheck_read(regs, regs->si, size);
- kmemcheck_read(regs, regs->di, size);
- goto out;
- }
-
- /*
- * If the opcode isn't special in any way, we use the data from the
- * page fault handler to determine the address and type of memory
- * access.
- */
- switch (fallback_method) {
- case KMEMCHECK_READ:
- kmemcheck_read(regs, fallback_address, size);
- goto out;
- case KMEMCHECK_WRITE:
- kmemcheck_write(regs, fallback_address, size);
- goto out;
- }
-
-out:
- data->busy = false;
-}
-
-bool kmemcheck_fault(struct pt_regs *regs, unsigned long address,
- unsigned long error_code)
-{
- pte_t *pte;
-
- /*
- * XXX: Is it safe to assume that memory accesses from virtual 86
- * mode or non-kernel code segments will _never_ access kernel
- * memory (e.g. tracked pages)? For now, we need this to avoid
- * invoking kmemcheck for PnP BIOS calls.
- */
- if (regs->flags & X86_VM_MASK)
- return false;
- if (regs->cs != __KERNEL_CS)
- return false;
-
- pte = kmemcheck_pte_lookup(address);
- if (!pte)
- return false;
-
- WARN_ON_ONCE(in_nmi());
-
- if (error_code & 2)
- kmemcheck_access(regs, address, KMEMCHECK_WRITE);
- else
- kmemcheck_access(regs, address, KMEMCHECK_READ);
-
- kmemcheck_show(regs);
- return true;
-}
-
-bool kmemcheck_trap(struct pt_regs *regs)
-{
- if (!kmemcheck_active(regs))
- return false;
-
- /* We're done. */
- kmemcheck_hide(regs);
- return true;
-}
diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c
index df8109ddf7fe..cec594032515 100644
--- a/arch/x86/mm/kmemcheck/opcode.c
+++ b/arch/x86/mm/kmemcheck/opcode.c
@@ -1,107 +1 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/types.h>
-
-#include "opcode.h"
-
-static bool opcode_is_prefix(uint8_t b)
-{
- return
- /* Group 1 */
- b == 0xf0 || b == 0xf2 || b == 0xf3
- /* Group 2 */
- || b == 0x2e || b == 0x36 || b == 0x3e || b == 0x26
- || b == 0x64 || b == 0x65
- /* Group 3 */
- || b == 0x66
- /* Group 4 */
- || b == 0x67;
-}
-
-#ifdef CONFIG_X86_64
-static bool opcode_is_rex_prefix(uint8_t b)
-{
- return (b & 0xf0) == 0x40;
-}
-#else
-static bool opcode_is_rex_prefix(uint8_t b)
-{
- return false;
-}
-#endif
-
-#define REX_W (1 << 3)
-
-/*
- * This is a VERY crude opcode decoder. We only need to find the size of the
- * load/store that caused our #PF and this should work for all the opcodes
- * that we care about. Moreover, the ones who invented this instruction set
- * should be shot.
- */
-void kmemcheck_opcode_decode(const uint8_t *op, unsigned int *size)
-{
- /* Default operand size */
- int operand_size_override = 4;
-
- /* prefixes */
- for (; opcode_is_prefix(*op); ++op) {
- if (*op == 0x66)
- operand_size_override = 2;
- }
-
- /* REX prefix */
- if (opcode_is_rex_prefix(*op)) {
- uint8_t rex = *op;
-
- ++op;
- if (rex & REX_W) {
- switch (*op) {
- case 0x63:
- *size = 4;
- return;
- case 0x0f:
- ++op;
-
- switch (*op) {
- case 0xb6:
- case 0xbe:
- *size = 1;
- return;
- case 0xb7:
- case 0xbf:
- *size = 2;
- return;
- }
-
- break;
- }
-
- *size = 8;
- return;
- }
- }
-
- /* escape opcode */
- if (*op == 0x0f) {
- ++op;
-
- /*
- * This is move with zero-extend and sign-extend, respectively;
- * we don't have to think about 0xb6/0xbe, because this is
- * already handled in the conditional below.
- */
- if (*op == 0xb7 || *op == 0xbf)
- operand_size_override = 2;
- }
-
- *size = (*op & 1) ? operand_size_override : 1;
-}
-
-const uint8_t *kmemcheck_opcode_get_primary(const uint8_t *op)
-{
- /* skip prefixes */
- while (opcode_is_prefix(*op))
- ++op;
- if (opcode_is_rex_prefix(*op))
- ++op;
- return op;
-}
diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h
index 51a1ce94c24a..ea32a7d3cf1b 100644
--- a/arch/x86/mm/kmemcheck/opcode.h
+++ b/arch/x86/mm/kmemcheck/opcode.h
@@ -1,10 +1 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ARCH__X86__MM__KMEMCHECK__OPCODE_H
-#define ARCH__X86__MM__KMEMCHECK__OPCODE_H
-
-#include <linux/types.h>
-
-void kmemcheck_opcode_decode(const uint8_t *op, unsigned int *size);
-const uint8_t *kmemcheck_opcode_get_primary(const uint8_t *op);
-
-#endif
diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c
index 8a03be90272a..cec594032515 100644
--- a/arch/x86/mm/kmemcheck/pte.c
+++ b/arch/x86/mm/kmemcheck/pte.c
@@ -1,23 +1 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/mm.h>
-
-#include <asm/pgtable.h>
-
-#include "pte.h"
-
-pte_t *kmemcheck_pte_lookup(unsigned long address)
-{
- pte_t *pte;
- unsigned int level;
-
- pte = lookup_address(address, &level);
- if (!pte)
- return NULL;
- if (level != PG_LEVEL_4K)
- return NULL;
- if (!pte_hidden(*pte))
- return NULL;
-
- return pte;
-}
-
diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h
index b595612382c2..ea32a7d3cf1b 100644
--- a/arch/x86/mm/kmemcheck/pte.h
+++ b/arch/x86/mm/kmemcheck/pte.h
@@ -1,11 +1 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ARCH__X86__MM__KMEMCHECK__PTE_H
-#define ARCH__X86__MM__KMEMCHECK__PTE_H
-
-#include <linux/mm.h>
-
-#include <asm/pgtable.h>
-
-pte_t *kmemcheck_pte_lookup(unsigned long address);
-
-#endif
diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c
index 7ce0be1f99eb..cec594032515 100644
--- a/arch/x86/mm/kmemcheck/selftest.c
+++ b/arch/x86/mm/kmemcheck/selftest.c
@@ -1,71 +1 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/bug.h>
-#include <linux/kernel.h>
-
-#include "opcode.h"
-#include "selftest.h"
-
-struct selftest_opcode {
- unsigned int expected_size;
- const uint8_t *insn;
- const char *desc;
-};
-
-static const struct selftest_opcode selftest_opcodes[] = {
- /* REP MOVS */
- {1, "\xf3\xa4", "rep movsb <mem8>, <mem8>"},
- {4, "\xf3\xa5", "rep movsl <mem32>, <mem32>"},
-
- /* MOVZX / MOVZXD */
- {1, "\x66\x0f\xb6\x51\xf8", "movzwq <mem8>, <reg16>"},
- {1, "\x0f\xb6\x51\xf8", "movzwq <mem8>, <reg32>"},
-
- /* MOVSX / MOVSXD */
- {1, "\x66\x0f\xbe\x51\xf8", "movswq <mem8>, <reg16>"},
- {1, "\x0f\xbe\x51\xf8", "movswq <mem8>, <reg32>"},
-
-#ifdef CONFIG_X86_64
- /* MOVZX / MOVZXD */
- {1, "\x49\x0f\xb6\x51\xf8", "movzbq <mem8>, <reg64>"},
- {2, "\x49\x0f\xb7\x51\xf8", "movzbq <mem16>, <reg64>"},
-
- /* MOVSX / MOVSXD */
- {1, "\x49\x0f\xbe\x51\xf8", "movsbq <mem8>, <reg64>"},
- {2, "\x49\x0f\xbf\x51\xf8", "movsbq <mem16>, <reg64>"},
- {4, "\x49\x63\x51\xf8", "movslq <mem32>, <reg64>"},
-#endif
-};
-
-static bool selftest_opcode_one(const struct selftest_opcode *op)
-{
- unsigned size;
-
- kmemcheck_opcode_decode(op->insn, &size);
-
- if (size == op->expected_size)
- return true;
-
- printk(KERN_WARNING "kmemcheck: opcode %s: expected size %d, got %d\n",
- op->desc, op->expected_size, size);
- return false;
-}
-
-static bool selftest_opcodes_all(void)
-{
- bool pass = true;
- unsigned int i;
-
- for (i = 0; i < ARRAY_SIZE(selftest_opcodes); ++i)
- pass = pass && selftest_opcode_one(&selftest_opcodes[i]);
-
- return pass;
-}
-
-bool kmemcheck_selftest(void)
-{
- bool pass = true;
-
- pass = pass && selftest_opcodes_all();
-
- return pass;
-}
diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h
index 8d759aae453d..ea32a7d3cf1b 100644
--- a/arch/x86/mm/kmemcheck/selftest.h
+++ b/arch/x86/mm/kmemcheck/selftest.h
@@ -1,7 +1 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ARCH_X86_MM_KMEMCHECK_SELFTEST_H
-#define ARCH_X86_MM_KMEMCHECK_SELFTEST_H
-
-bool kmemcheck_selftest(void);
-
-#endif
diff --git a/arch/x86/mm/kmemcheck/shadow.c b/arch/x86/mm/kmemcheck/shadow.c
deleted file mode 100644
index c2638a7d2c10..000000000000
--- a/arch/x86/mm/kmemcheck/shadow.c
+++ /dev/null
@@ -1,173 +0,0 @@
-#include <linux/kmemcheck.h>
-#include <linux/export.h>
-#include <linux/mm.h>
-
-#include <asm/page.h>
-#include <asm/pgtable.h>
-
-#include "pte.h"
-#include "shadow.h"
-
-/*
- * Return the shadow address for the given address. Returns NULL if the
- * address is not tracked.
- *
- * We need to be extremely careful not to follow any invalid pointers,
- * because this function can be called for *any* possible address.
- */
-void *kmemcheck_shadow_lookup(unsigned long address)
-{
- pte_t *pte;
- struct page *page;
-
- if (!virt_addr_valid(address))
- return NULL;
-
- pte = kmemcheck_pte_lookup(address);
- if (!pte)
- return NULL;
-
- page = virt_to_page(address);
- if (!page->shadow)
- return NULL;
- return page->shadow + (address & (PAGE_SIZE - 1));
-}
-
-static void mark_shadow(void *address, unsigned int n,
- enum kmemcheck_shadow status)
-{
- unsigned long addr = (unsigned long) address;
- unsigned long last_addr = addr + n - 1;
- unsigned long page = addr & PAGE_MASK;
- unsigned long last_page = last_addr & PAGE_MASK;
- unsigned int first_n;
- void *shadow;
-
- /* If the memory range crosses a page boundary, stop there. */
- if (page == last_page)
- first_n = n;
- else
- first_n = page + PAGE_SIZE - addr;
-
- shadow = kmemcheck_shadow_lookup(addr);
- if (shadow)
- memset(shadow, status, first_n);
-
- addr += first_n;
- n -= first_n;
-
- /* Do full-page memset()s. */
- while (n >= PAGE_SIZE) {
- shadow = kmemcheck_shadow_lookup(addr);
- if (shadow)
- memset(shadow, status, PAGE_SIZE);
-
- addr += PAGE_SIZE;
- n -= PAGE_SIZE;
- }
-
- /* Do the remaining page, if any. */
- if (n > 0) {
- shadow = kmemcheck_shadow_lookup(addr);
- if (shadow)
- memset(shadow, status, n);
- }
-}
-
-void kmemcheck_mark_unallocated(void *address, unsigned int n)
-{
- mark_shadow(address, n, KMEMCHECK_SHADOW_UNALLOCATED);
-}
-
-void kmemcheck_mark_uninitialized(void *address, unsigned int n)
-{
- mark_shadow(address, n, KMEMCHECK_SHADOW_UNINITIALIZED);
-}
-
-/*
- * Fill the shadow memory of the given address such that the memory at that
- * address is marked as being initialized.
- */
-void kmemcheck_mark_initialized(void *address, unsigned int n)
-{
- mark_shadow(address, n, KMEMCHECK_SHADOW_INITIALIZED);
-}
-EXPORT_SYMBOL_GPL(kmemcheck_mark_initialized);
-
-void kmemcheck_mark_freed(void *address, unsigned int n)
-{
- mark_shadow(address, n, KMEMCHECK_SHADOW_FREED);
-}
-
-void kmemcheck_mark_unallocated_pages(struct page *p, unsigned int n)
-{
- unsigned int i;
-
- for (i = 0; i < n; ++i)
- kmemcheck_mark_unallocated(page_address(&p[i]), PAGE_SIZE);
-}
-
-void kmemcheck_mark_uninitialized_pages(struct page *p, unsigned int n)
-{
- unsigned int i;
-
- for (i = 0; i < n; ++i)
- kmemcheck_mark_uninitialized(page_address(&p[i]), PAGE_SIZE);
-}
-
-void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n)
-{
- unsigned int i;
-
- for (i = 0; i < n; ++i)
- kmemcheck_mark_initialized(page_address(&p[i]), PAGE_SIZE);
-}
-
-enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size)
-{
-#ifdef CONFIG_KMEMCHECK_PARTIAL_OK
- uint8_t *x;
- unsigned int i;
-
- x = shadow;
-
- /*
- * Make sure _some_ bytes are initialized. Gcc frequently generates
- * code to access neighboring bytes.
- */
- for (i = 0; i < size; ++i) {
- if (x[i] == KMEMCHECK_SHADOW_INITIALIZED)
- return x[i];
- }
-
- return x[0];
-#else
- return kmemcheck_shadow_test_all(shadow, size);
-#endif
-}
-
-enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow, unsigned int size)
-{
- uint8_t *x;
- unsigned int i;
-
- x = shadow;
-
- /* All bytes must be initialized. */
- for (i = 0; i < size; ++i) {
- if (x[i] != KMEMCHECK_SHADOW_INITIALIZED)
- return x[i];
- }
-
- return x[0];
-}
-
-void kmemcheck_shadow_set(void *shadow, unsigned int size)
-{
- uint8_t *x;
- unsigned int i;
-
- x = shadow;
- for (i = 0; i < size; ++i)
- x[i] = KMEMCHECK_SHADOW_INITIALIZED;
-}
diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h
index 49768dc18664..ea32a7d3cf1b 100644
--- a/arch/x86/mm/kmemcheck/shadow.h
+++ b/arch/x86/mm/kmemcheck/shadow.h
@@ -1,19 +1 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ARCH__X86__MM__KMEMCHECK__SHADOW_H
-#define ARCH__X86__MM__KMEMCHECK__SHADOW_H
-
-enum kmemcheck_shadow {
- KMEMCHECK_SHADOW_UNALLOCATED,
- KMEMCHECK_SHADOW_UNINITIALIZED,
- KMEMCHECK_SHADOW_INITIALIZED,
- KMEMCHECK_SHADOW_FREED,
-};
-
-void *kmemcheck_shadow_lookup(unsigned long address);
-
-enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size);
-enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow,
- unsigned int size);
-void kmemcheck_shadow_set(void *shadow, unsigned int size);
-
-#endif
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 3fe68483463c..85cf12219dea 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -753,7 +753,7 @@ static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
if (!debug_pagealloc_enabled())
spin_unlock(&cpa_lock);
- base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0);
+ base = alloc_pages(GFP_KERNEL, 0);
if (!debug_pagealloc_enabled())
spin_lock(&cpa_lock);
if (!base)
@@ -904,7 +904,7 @@ static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end)
static int alloc_pte_page(pmd_t *pmd)
{
- pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+ pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL);
if (!pte)
return -1;
@@ -914,7 +914,7 @@ static int alloc_pte_page(pmd_t *pmd)
static int alloc_pmd_page(pud_t *pud)
{
- pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+ pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL);
if (!pmd)
return -1;
@@ -1120,7 +1120,7 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
pgd_entry = cpa->pgd + pgd_index(addr);
if (pgd_none(*pgd_entry)) {
- p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+ p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL);
if (!p4d)
return -1;
@@ -1132,7 +1132,7 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
*/
p4d = p4d_offset(pgd_entry, addr);
if (p4d_none(*p4d)) {
- pud = (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+ pud = (pud_t *)get_zeroed_page(GFP_KERNEL);
if (!pud)
return -1;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 17ebc5a978cc..96d456a94b03 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -7,7 +7,7 @@
#include <asm/fixmap.h>
#include <asm/mtrr.h>
-#define PGALLOC_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO)
#ifdef CONFIG_HIGHPTE
#define PGALLOC_USER_GFP __GFP_HIGHMEM
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 9e4ee5b04b2d..6a151ce70e86 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -207,7 +207,7 @@ int __init efi_alloc_page_tables(void)
if (efi_enabled(EFI_OLD_MEMMAP))
return 0;
- gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO;
+ gfp_mask = GFP_KERNEL | __GFP_ZERO;
efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
if (!efi_pgd)
return -ENOMEM;