summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig3
-rw-r--r--arch/x86/Kconfig.debug20
-rw-r--r--arch/x86/include/asm/pgtable.h10
-rw-r--r--arch/x86/include/asm/tlb.h4
-rw-r--r--arch/x86/kernel/cpu/mtrr/if.c21
-rw-r--r--arch/x86/mm/Makefile4
-rw-r--r--arch/x86/mm/debug_pagetables.c18
-rw-r--r--arch/x86/mm/dump_pagetables.c322
-rw-r--r--arch/x86/platform/efi/efi_32.c2
-rw-r--r--arch/x86/platform/efi/efi_64.c4
-rw-r--r--arch/x86/platform/uv/tlb_uv.c14
11 files changed, 121 insertions, 301 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 44d279698c0f..beea77046f9b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -120,6 +120,7 @@ config X86
select GENERIC_IRQ_RESERVATION_MODE
select GENERIC_IRQ_SHOW
select GENERIC_PENDING_IRQ if SMP
+ select GENERIC_PTDUMP
select GENERIC_SMP_IDLE_THREAD
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
@@ -202,7 +203,7 @@ config X86
select HAVE_PCI
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
- select HAVE_RCU_TABLE_FREE if PARAVIRT
+ select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
select HAVE_FUNCTION_ARG_ACCESS_API
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index c4eab8ed33a3..2e74690b028a 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -62,26 +62,10 @@ config EARLY_PRINTK_USB_XDBC
config MCSAFE_TEST
def_bool n
-config X86_PTDUMP_CORE
- def_bool n
-
-config X86_PTDUMP
- tristate "Export kernel pagetable layout to userspace via debugfs"
- depends on DEBUG_KERNEL
- select DEBUG_FS
- select X86_PTDUMP_CORE
- ---help---
- Say Y here if you want to show the kernel pagetable layout in a
- debugfs file. This information is only useful for kernel developers
- who are working in architecture specific areas of the kernel.
- It is probably not a good idea to enable this feature in a production
- kernel.
- If in doubt, say "N"
-
config EFI_PGT_DUMP
bool "Dump the EFI pagetable"
depends on EFI
- select X86_PTDUMP_CORE
+ select PTDUMP_CORE
---help---
Enable this if you want to dump the EFI page table before
enabling virtual mode. This can be used to debug miscellaneous
@@ -90,7 +74,7 @@ config EFI_PGT_DUMP
config DEBUG_WX
bool "Warn on W+X mappings at boot"
- select X86_PTDUMP_CORE
+ select PTDUMP_CORE
---help---
Generate a warning if any W+X mappings are found at boot.
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index ad97dc155195..7e118660bbd9 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -29,8 +29,9 @@
extern pgd_t early_top_pgt[PTRS_PER_PGD];
int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
-void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
-void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
+void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm);
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
+ bool user);
void ptdump_walk_pgd_level_checkwx(void);
void ptdump_walk_user_pgd_level_checkwx(void);
@@ -239,6 +240,7 @@ static inline unsigned long pgd_pfn(pgd_t pgd)
return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT;
}
+#define p4d_leaf p4d_large
static inline int p4d_large(p4d_t p4d)
{
/* No 512 GiB pages yet */
@@ -247,6 +249,7 @@ static inline int p4d_large(p4d_t p4d)
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
+#define pmd_leaf pmd_large
static inline int pmd_large(pmd_t pte)
{
return pmd_flags(pte) & _PAGE_PSE;
@@ -874,6 +877,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
}
+#define pud_leaf pud_large
static inline int pud_large(pud_t pud)
{
return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) ==
@@ -885,6 +889,7 @@ static inline int pud_bad(pud_t pud)
return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
}
#else
+#define pud_leaf pud_large
static inline int pud_large(pud_t pud)
{
return 0;
@@ -1233,6 +1238,7 @@ static inline bool pgdp_maps_userspace(void *__ptr)
return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
}
+#define pgd_leaf pgd_large
static inline int pgd_large(pgd_t pgd) { return 0; }
#ifdef CONFIG_PAGE_TABLE_ISOLATION
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index f23e7aaff4cd..820082bd6880 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -29,8 +29,8 @@ static inline void tlb_flush(struct mmu_gather *tlb)
* shootdown, enablement code for several hypervisors overrides
* .flush_tlb_others hook in pv_mmu_ops and implements it by issuing
* a hypercall. To keep software pagetable walkers safe in this case we
- * switch to RCU based table free (HAVE_RCU_TABLE_FREE). See the comment
- * below 'ifdef CONFIG_HAVE_RCU_TABLE_FREE' in include/asm-generic/tlb.h
+ * switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the comment
+ * below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
* for more details.
*/
static inline void __tlb_remove_table(void *table)
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index da532f656a7b..a5c506f6da7f 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -396,15 +396,16 @@ static int mtrr_open(struct inode *inode, struct file *file)
return single_open(file, mtrr_seq_show, NULL);
}
-static const struct file_operations mtrr_fops = {
- .owner = THIS_MODULE,
- .open = mtrr_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .write = mtrr_write,
- .unlocked_ioctl = mtrr_ioctl,
- .compat_ioctl = mtrr_ioctl,
- .release = mtrr_close,
+static const struct proc_ops mtrr_proc_ops = {
+ .proc_open = mtrr_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = mtrr_write,
+ .proc_ioctl = mtrr_ioctl,
+#ifdef CONFIG_COMPAT
+ .proc_compat_ioctl = mtrr_ioctl,
+#endif
+ .proc_release = mtrr_close,
};
static int __init mtrr_if_init(void)
@@ -417,7 +418,7 @@ static int __init mtrr_if_init(void)
(!cpu_has(c, X86_FEATURE_CENTAUR_MCR)))
return -ENODEV;
- proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_fops);
+ proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_proc_ops);
return 0;
}
arch_initcall(mtrr_if_init);
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 98aecb14fbcc..98f7c6fa2eaa 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -28,8 +28,8 @@ CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace
obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
-obj-$(CONFIG_X86_PTDUMP_CORE) += dump_pagetables.o
-obj-$(CONFIG_X86_PTDUMP) += debug_pagetables.o
+obj-$(CONFIG_PTDUMP_CORE) += dump_pagetables.o
+obj-$(CONFIG_PTDUMP_DEBUGFS) += debug_pagetables.o
obj-$(CONFIG_HIGHMEM) += highmem_32.o
diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c
index 39001a401eff..4a3b62f780b4 100644
--- a/arch/x86/mm/debug_pagetables.c
+++ b/arch/x86/mm/debug_pagetables.c
@@ -7,7 +7,7 @@
static int ptdump_show(struct seq_file *m, void *v)
{
- ptdump_walk_pgd_level_debugfs(m, NULL, false);
+ ptdump_walk_pgd_level_debugfs(m, &init_mm, false);
return 0;
}
@@ -15,11 +15,8 @@ DEFINE_SHOW_ATTRIBUTE(ptdump);
static int ptdump_curknl_show(struct seq_file *m, void *v)
{
- if (current->mm->pgd) {
- down_read(&current->mm->mmap_sem);
- ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, false);
- up_read(&current->mm->mmap_sem);
- }
+ if (current->mm->pgd)
+ ptdump_walk_pgd_level_debugfs(m, current->mm, false);
return 0;
}
@@ -28,11 +25,8 @@ DEFINE_SHOW_ATTRIBUTE(ptdump_curknl);
#ifdef CONFIG_PAGE_TABLE_ISOLATION
static int ptdump_curusr_show(struct seq_file *m, void *v)
{
- if (current->mm->pgd) {
- down_read(&current->mm->mmap_sem);
- ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, true);
- up_read(&current->mm->mmap_sem);
- }
+ if (current->mm->pgd)
+ ptdump_walk_pgd_level_debugfs(m, current->mm, true);
return 0;
}
@@ -43,7 +37,7 @@ DEFINE_SHOW_ATTRIBUTE(ptdump_curusr);
static int ptdump_efi_show(struct seq_file *m, void *v)
{
if (efi_mm.pgd)
- ptdump_walk_pgd_level_debugfs(m, efi_mm.pgd, false);
+ ptdump_walk_pgd_level_debugfs(m, &efi_mm, false);
return 0;
}
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ab67822fd2f4..64229dad7eab 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -16,6 +16,7 @@
#include <linux/seq_file.h>
#include <linux/highmem.h>
#include <linux/pci.h>
+#include <linux/ptdump.h>
#include <asm/e820/types.h>
#include <asm/pgtable.h>
@@ -26,16 +27,18 @@
* when a "break" in the continuity is found.
*/
struct pg_state {
+ struct ptdump_state ptdump;
int level;
- pgprot_t current_prot;
+ pgprotval_t current_prot;
pgprotval_t effective_prot;
+ pgprotval_t prot_levels[5];
unsigned long start_address;
- unsigned long current_address;
const struct addr_marker *marker;
unsigned long lines;
bool to_dmesg;
bool check_wx;
unsigned long wx_pages;
+ struct seq_file *seq;
};
struct addr_marker {
@@ -174,11 +177,10 @@ static struct addr_marker address_markers[] = {
/*
* Print a readable form of a pgprot_t to the seq_file
*/
-static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
+static void printk_prot(struct seq_file *m, pgprotval_t pr, int level, bool dmsg)
{
- pgprotval_t pr = pgprot_val(prot);
static const char * const level_name[] =
- { "cr3", "pgd", "p4d", "pud", "pmd", "pte" };
+ { "pgd", "p4d", "pud", "pmd", "pte" };
if (!(pr & _PAGE_PRESENT)) {
/* Not present */
@@ -202,12 +204,12 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
pt_dump_cont_printf(m, dmsg, " ");
/* Bit 7 has a different meaning on level 3 vs 4 */
- if (level <= 4 && pr & _PAGE_PSE)
+ if (level <= 3 && pr & _PAGE_PSE)
pt_dump_cont_printf(m, dmsg, "PSE ");
else
pt_dump_cont_printf(m, dmsg, " ");
- if ((level == 5 && pr & _PAGE_PAT) ||
- ((level == 4 || level == 3) && pr & _PAGE_PAT_LARGE))
+ if ((level == 4 && pr & _PAGE_PAT) ||
+ ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE))
pt_dump_cont_printf(m, dmsg, "PAT ");
else
pt_dump_cont_printf(m, dmsg, " ");
@@ -223,24 +225,11 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
pt_dump_cont_printf(m, dmsg, "%s\n", level_name[level]);
}
-/*
- * On 64 bits, sign-extend the 48 bit address to 64 bit
- */
-static unsigned long normalize_addr(unsigned long u)
-{
- int shift;
- if (!IS_ENABLED(CONFIG_X86_64))
- return u;
-
- shift = 64 - (__VIRTUAL_MASK_SHIFT + 1);
- return (signed long)(u << shift) >> shift;
-}
-
-static void note_wx(struct pg_state *st)
+static void note_wx(struct pg_state *st, unsigned long addr)
{
unsigned long npages;
- npages = (st->current_address - st->start_address) / PAGE_SIZE;
+ npages = (addr - st->start_address) / PAGE_SIZE;
#ifdef CONFIG_PCI_BIOS
/*
@@ -248,7 +237,7 @@ static void note_wx(struct pg_state *st)
* Inform about it, but avoid the warning.
*/
if (pcibios_enabled && st->start_address >= PAGE_OFFSET + BIOS_BEGIN &&
- st->current_address <= PAGE_OFFSET + BIOS_END) {
+ addr <= PAGE_OFFSET + BIOS_END) {
pr_warn_once("x86/mm: PCI BIOS W+X mapping %lu pages\n", npages);
return;
}
@@ -260,27 +249,47 @@ static void note_wx(struct pg_state *st)
(void *)st->start_address);
}
+static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2)
+{
+ return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) |
+ ((prot1 | prot2) & _PAGE_NX);
+}
+
/*
* This function gets called on a break in a continuous series
* of PTE entries; the next one is different so we need to
* print what we collected so far.
*/
-static void note_page(struct seq_file *m, struct pg_state *st,
- pgprot_t new_prot, pgprotval_t new_eff, int level)
+static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
+ unsigned long val)
{
- pgprotval_t prot, cur, eff;
+ struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
+ pgprotval_t new_prot, new_eff;
+ pgprotval_t cur, eff;
static const char units[] = "BKMGTPE";
+ struct seq_file *m = st->seq;
+
+ new_prot = val & PTE_FLAGS_MASK;
+
+ if (level > 0) {
+ new_eff = effective_prot(st->prot_levels[level - 1],
+ new_prot);
+ } else {
+ new_eff = new_prot;
+ }
+
+ if (level >= 0)
+ st->prot_levels[level] = new_eff;
/*
* If we have a "break" in the series, we need to flush the state that
* we have now. "break" is either changing perms, levels or
* address space marker.
*/
- prot = pgprot_val(new_prot);
- cur = pgprot_val(st->current_prot);
+ cur = st->current_prot;
eff = st->effective_prot;
- if (!st->level) {
+ if (st->level == -1) {
/* First entry */
st->current_prot = new_prot;
st->effective_prot = new_eff;
@@ -289,14 +298,14 @@ static void note_page(struct seq_file *m, struct pg_state *st,
st->lines = 0;
pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
st->marker->name);
- } else if (prot != cur || new_eff != eff || level != st->level ||
- st->current_address >= st->marker[1].start_address) {
+ } else if (new_prot != cur || new_eff != eff || level != st->level ||
+ addr >= st->marker[1].start_address) {
const char *unit = units;
unsigned long delta;
int width = sizeof(unsigned long) * 2;
if (st->check_wx && (eff & _PAGE_RW) && !(eff & _PAGE_NX))
- note_wx(st);
+ note_wx(st, addr);
/*
* Now print the actual finished series
@@ -306,9 +315,9 @@ static void note_page(struct seq_file *m, struct pg_state *st,
pt_dump_seq_printf(m, st->to_dmesg,
"0x%0*lx-0x%0*lx ",
width, st->start_address,
- width, st->current_address);
+ width, addr);
- delta = st->current_address - st->start_address;
+ delta = addr - st->start_address;
while (!(delta & 1023) && unit[1]) {
delta >>= 10;
unit++;
@@ -325,7 +334,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
* such as the start of vmalloc space etc.
* This helps in the interpretation.
*/
- if (st->current_address >= st->marker[1].start_address) {
+ if (addr >= st->marker[1].start_address) {
if (st->marker->max_lines &&
st->lines > st->marker->max_lines) {
unsigned long nskip =
@@ -341,222 +350,45 @@ static void note_page(struct seq_file *m, struct pg_state *st,
st->marker->name);
}
- st->start_address = st->current_address;
+ st->start_address = addr;
st->current_prot = new_prot;
st->effective_prot = new_eff;
st->level = level;
}
}
-static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2)
-{
- return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) |
- ((prot1 | prot2) & _PAGE_NX);
-}
-
-static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr,
- pgprotval_t eff_in, unsigned long P)
-{
- int i;
- pte_t *pte;
- pgprotval_t prot, eff;
-
- for (i = 0; i < PTRS_PER_PTE; i++) {
- st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT);
- pte = pte_offset_map(&addr, st->current_address);
- prot = pte_flags(*pte);
- eff = effective_prot(eff_in, prot);
- note_page(m, st, __pgprot(prot), eff, 5);
- pte_unmap(pte);
- }
-}
-#ifdef CONFIG_KASAN
-
-/*
- * This is an optimization for KASAN=y case. Since all kasan page tables
- * eventually point to the kasan_early_shadow_page we could call note_page()
- * right away without walking through lower level page tables. This saves
- * us dozens of seconds (minutes for 5-level config) while checking for
- * W+X mapping or reading kernel_page_tables debugfs file.
- */
-static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st,
- void *pt)
-{
- if (__pa(pt) == __pa(kasan_early_shadow_pmd) ||
- (pgtable_l5_enabled() &&
- __pa(pt) == __pa(kasan_early_shadow_p4d)) ||
- __pa(pt) == __pa(kasan_early_shadow_pud)) {
- pgprotval_t prot = pte_flags(kasan_early_shadow_pte[0]);
- note_page(m, st, __pgprot(prot), 0, 5);
- return true;
- }
- return false;
-}
-#else
-static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st,
- void *pt)
-{
- return false;
-}
-#endif
-
-#if PTRS_PER_PMD > 1
-
-static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
- pgprotval_t eff_in, unsigned long P)
-{
- int i;
- pmd_t *start, *pmd_start;
- pgprotval_t prot, eff;
-
- pmd_start = start = (pmd_t *)pud_page_vaddr(addr);
- for (i = 0; i < PTRS_PER_PMD; i++) {
- st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT);
- if (!pmd_none(*start)) {
- prot = pmd_flags(*start);
- eff = effective_prot(eff_in, prot);
- if (pmd_large(*start) || !pmd_present(*start)) {
- note_page(m, st, __pgprot(prot), eff, 4);
- } else if (!kasan_page_table(m, st, pmd_start)) {
- walk_pte_level(m, st, *start, eff,
- P + i * PMD_LEVEL_MULT);
- }
- } else
- note_page(m, st, __pgprot(0), 0, 4);
- start++;
- }
-}
-
-#else
-#define walk_pmd_level(m,s,a,e,p) walk_pte_level(m,s,__pmd(pud_val(a)),e,p)
-#define pud_large(a) pmd_large(__pmd(pud_val(a)))
-#define pud_none(a) pmd_none(__pmd(pud_val(a)))
-#endif
-
-#if PTRS_PER_PUD > 1
-
-static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr,
- pgprotval_t eff_in, unsigned long P)
-{
- int i;
- pud_t *start, *pud_start;
- pgprotval_t prot, eff;
-
- pud_start = start = (pud_t *)p4d_page_vaddr(addr);
-
- for (i = 0; i < PTRS_PER_PUD; i++) {
- st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
- if (!pud_none(*start)) {
- prot = pud_flags(*start);
- eff = effective_prot(eff_in, prot);
- if (pud_large(*start) || !pud_present(*start)) {
- note_page(m, st, __pgprot(prot), eff, 3);
- } else if (!kasan_page_table(m, st, pud_start)) {
- walk_pmd_level(m, st, *start, eff,
- P + i * PUD_LEVEL_MULT);
- }
- } else
- note_page(m, st, __pgprot(0), 0, 3);
-
- start++;
- }
-}
-
-#else
-#define walk_pud_level(m,s,a,e,p) walk_pmd_level(m,s,__pud(p4d_val(a)),e,p)
-#define p4d_large(a) pud_large(__pud(p4d_val(a)))
-#define p4d_none(a) pud_none(__pud(p4d_val(a)))
-#endif
-
-static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
- pgprotval_t eff_in, unsigned long P)
-{
- int i;
- p4d_t *start, *p4d_start;
- pgprotval_t prot, eff;
-
- if (PTRS_PER_P4D == 1)
- return walk_pud_level(m, st, __p4d(pgd_val(addr)), eff_in, P);
-
- p4d_start = start = (p4d_t *)pgd_page_vaddr(addr);
-
- for (i = 0; i < PTRS_PER_P4D; i++) {
- st->current_address = normalize_addr(P + i * P4D_LEVEL_MULT);
- if (!p4d_none(*start)) {
- prot = p4d_flags(*start);
- eff = effective_prot(eff_in, prot);
- if (p4d_large(*start) || !p4d_present(*start)) {
- note_page(m, st, __pgprot(prot), eff, 2);
- } else if (!kasan_page_table(m, st, p4d_start)) {
- walk_pud_level(m, st, *start, eff,
- P + i * P4D_LEVEL_MULT);
- }
- } else
- note_page(m, st, __pgprot(0), 0, 2);
-
- start++;
- }
-}
-
-#define pgd_large(a) (pgtable_l5_enabled() ? pgd_large(a) : p4d_large(__p4d(pgd_val(a))))
-#define pgd_none(a) (pgtable_l5_enabled() ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
-
-static inline bool is_hypervisor_range(int idx)
-{
-#ifdef CONFIG_X86_64
- /*
- * A hole in the beginning of kernel address space reserved
- * for a hypervisor.
- */
- return (idx >= pgd_index(GUARD_HOLE_BASE_ADDR)) &&
- (idx < pgd_index(GUARD_HOLE_END_ADDR));
-#else
- return false;
-#endif
-}
-
-static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
+static void ptdump_walk_pgd_level_core(struct seq_file *m,
+ struct mm_struct *mm, pgd_t *pgd,
bool checkwx, bool dmesg)
{
- pgd_t *start = INIT_PGD;
- pgprotval_t prot, eff;
- int i;
- struct pg_state st = {};
-
- if (pgd) {
- start = pgd;
- st.to_dmesg = dmesg;
- }
+ const struct ptdump_range ptdump_ranges[] = {
+#ifdef CONFIG_X86_64
- st.check_wx = checkwx;
- if (checkwx)
- st.wx_pages = 0;
+#define normalize_addr_shift (64 - (__VIRTUAL_MASK_SHIFT + 1))
+#define normalize_addr(u) ((signed long)((u) << normalize_addr_shift) >> \
+ normalize_addr_shift)
- for (i = 0; i < PTRS_PER_PGD; i++) {
- st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
- if (!pgd_none(*start) && !is_hypervisor_range(i)) {
- prot = pgd_flags(*start);
-#ifdef CONFIG_X86_PAE
- eff = _PAGE_USER | _PAGE_RW;
+ {0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2},
+ {normalize_addr(PTRS_PER_PGD * PGD_LEVEL_MULT / 2), ~0UL},
#else
- eff = prot;
+ {0, ~0UL},
#endif
- if (pgd_large(*start) || !pgd_present(*start)) {
- note_page(m, &st, __pgprot(prot), eff, 1);
- } else {
- walk_p4d_level(m, &st, *start, eff,
- i * PGD_LEVEL_MULT);
- }
- } else
- note_page(m, &st, __pgprot(0), 0, 1);
+ {0, 0}
+};
- cond_resched();
- start++;
- }
+ struct pg_state st = {
+ .ptdump = {
+ .note_page = note_page,
+ .range = ptdump_ranges
+ },
+ .level = -1,
+ .to_dmesg = dmesg,
+ .check_wx = checkwx,
+ .seq = m
+ };
+
+ ptdump_walk_pgd(&st.ptdump, mm, pgd);
- /* Flush out the last page */
- st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT);
- note_page(m, &st, __pgprot(0), 0, 0);
if (!checkwx)
return;
if (st.wx_pages)
@@ -566,18 +398,20 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n");
}
-void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
+void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm)
{
- ptdump_walk_pgd_level_core(m, pgd, false, true);
+ ptdump_walk_pgd_level_core(m, mm, mm->pgd, false, true);
}
-void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
+ bool user)
{
+ pgd_t *pgd = mm->pgd;
#ifdef CONFIG_PAGE_TABLE_ISOLATION
if (user && boot_cpu_has(X86_FEATURE_PTI))
pgd = kernel_to_user_pgdp(pgd);
#endif
- ptdump_walk_pgd_level_core(m, pgd, false, false);
+ ptdump_walk_pgd_level_core(m, mm, pgd, false, false);
}
EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
@@ -592,13 +426,13 @@ void ptdump_walk_user_pgd_level_checkwx(void)
pr_info("x86/mm: Checking user space page tables\n");
pgd = kernel_to_user_pgdp(pgd);
- ptdump_walk_pgd_level_core(NULL, pgd, true, false);
+ ptdump_walk_pgd_level_core(NULL, &init_mm, pgd, true, false);
#endif
}
void ptdump_walk_pgd_level_checkwx(void)
{
- ptdump_walk_pgd_level_core(NULL, NULL, true, false);
+ ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false);
}
static int __init pt_dump_init(void)
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 71dddd1620f9..081d466002c9 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -49,7 +49,7 @@ void efi_sync_low_kernel_mappings(void) {}
void __init efi_dump_pagetable(void)
{
#ifdef CONFIG_EFI_PGT_DUMP
- ptdump_walk_pgd_level(NULL, swapper_pg_dir);
+ ptdump_walk_pgd_level(NULL, &init_mm);
#endif
}
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index e2accfe636bd..fa8506e76bbe 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -471,9 +471,9 @@ void __init efi_dump_pagetable(void)
{
#ifdef CONFIG_EFI_PGT_DUMP
if (efi_have_uv1_memmap())
- ptdump_walk_pgd_level(NULL, swapper_pg_dir);
+ ptdump_walk_pgd_level(NULL, &init_mm);
else
- ptdump_walk_pgd_level(NULL, efi_mm.pgd);
+ ptdump_walk_pgd_level(NULL, &efi_mm);
#endif
}
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 5f0a96bf27a1..1fd321f37f1b 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1668,12 +1668,12 @@ static int tunables_open(struct inode *inode, struct file *file)
return 0;
}
-static const struct file_operations proc_uv_ptc_operations = {
- .open = ptc_proc_open,
- .read = seq_read,
- .write = ptc_proc_write,
- .llseek = seq_lseek,
- .release = seq_release,
+static const struct proc_ops uv_ptc_proc_ops = {
+ .proc_open = ptc_proc_open,
+ .proc_read = seq_read,
+ .proc_write = ptc_proc_write,
+ .proc_lseek = seq_lseek,
+ .proc_release = seq_release,
};
static const struct file_operations tunables_fops = {
@@ -1691,7 +1691,7 @@ static int __init uv_ptc_init(void)
return 0;
proc_uv_ptc = proc_create(UV_PTC_BASENAME, 0444, NULL,
- &proc_uv_ptc_operations);
+ &uv_ptc_proc_ops);
if (!proc_uv_ptc) {
pr_err("unable to create %s proc entry\n",
UV_PTC_BASENAME);
generated by cgit v1.2.3 (git 2.25.1) at 2024-09-04 02:32:41 +0000