summaryrefslogtreecommitdiff
path: root/arch/x86/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm')
-rw-r--r--arch/x86/mm/dump_pagetables.c24
-rw-r--r--arch/x86/mm/fault.c16
-rw-r--r--arch/x86/mm/ident_map.c2
-rw-r--r--arch/x86/mm/init_32.c4
-rw-r--r--arch/x86/mm/init_64.c16
-rw-r--r--arch/x86/mm/kasan_init_64.c4
-rw-r--r--arch/x86/mm/mem_encrypt_identity.c6
-rw-r--r--arch/x86/mm/pat/set_memory.c14
-rw-r--r--arch/x86/mm/pgtable.c4
-rw-r--r--arch/x86/mm/pti.c10
-rw-r--r--arch/x86/mm/tlb.c39
11 files changed, 70 insertions, 69 deletions
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index b7b88c1d91ec..89079ea73e65 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -362,9 +362,9 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
}
}
-static void ptdump_walk_pgd_level_core(struct seq_file *m,
- struct mm_struct *mm, pgd_t *pgd,
- bool checkwx, bool dmesg)
+bool ptdump_walk_pgd_level_core(struct seq_file *m,
+ struct mm_struct *mm, pgd_t *pgd,
+ bool checkwx, bool dmesg)
{
const struct ptdump_range ptdump_ranges[] = {
#ifdef CONFIG_X86_64
@@ -391,12 +391,17 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m,
ptdump_walk_pgd(&st.ptdump, mm, pgd);
if (!checkwx)
- return;
- if (st.wx_pages)
+ return true;
+ if (st.wx_pages) {
pr_info("x86/mm: Checked W+X mappings: FAILED, %lu W+X pages found.\n",
st.wx_pages);
- else
+
+ return false;
+ } else {
pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n");
+
+ return true;
+ }
}
void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm)
@@ -431,9 +436,12 @@ void ptdump_walk_user_pgd_level_checkwx(void)
#endif
}
-void ptdump_walk_pgd_level_checkwx(void)
+bool ptdump_walk_pgd_level_checkwx(void)
{
- ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false);
+ if (!(__supported_pte_mask & _PAGE_NX))
+ return true;
+
+ return ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false);
}
static int __init pt_dump_init(void)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 402e08f6b7ec..622d12ec7f08 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -252,7 +252,7 @@ static noinline int vmalloc_fault(unsigned long address)
if (!pmd_k)
return -1;
- if (pmd_large(*pmd_k))
+ if (pmd_leaf(*pmd_k))
return 0;
pte_k = pte_offset_kernel(pmd_k, address);
@@ -321,7 +321,7 @@ static void dump_pagetable(unsigned long address)
* And let's rather not kmap-atomic the pte, just in case
* it's allocated already:
*/
- if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_large(*pmd))
+ if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_leaf(*pmd))
goto out;
pte = pte_offset_kernel(pmd, address);
@@ -370,7 +370,7 @@ static void dump_pagetable(unsigned long address)
goto bad;
pr_cont("P4D %lx ", p4d_val(*p4d));
- if (!p4d_present(*p4d) || p4d_large(*p4d))
+ if (!p4d_present(*p4d) || p4d_leaf(*p4d))
goto out;
pud = pud_offset(p4d, address);
@@ -378,7 +378,7 @@ static void dump_pagetable(unsigned long address)
goto bad;
pr_cont("PUD %lx ", pud_val(*pud));
- if (!pud_present(*pud) || pud_large(*pud))
+ if (!pud_present(*pud) || pud_leaf(*pud))
goto out;
pmd = pmd_offset(pud, address);
@@ -386,7 +386,7 @@ static void dump_pagetable(unsigned long address)
goto bad;
pr_cont("PMD %lx ", pmd_val(*pmd));
- if (!pmd_present(*pmd) || pmd_large(*pmd))
+ if (!pmd_present(*pmd) || pmd_leaf(*pmd))
goto out;
pte = pte_offset_kernel(pmd, address);
@@ -1036,21 +1036,21 @@ spurious_kernel_fault(unsigned long error_code, unsigned long address)
if (!p4d_present(*p4d))
return 0;
- if (p4d_large(*p4d))
+ if (p4d_leaf(*p4d))
return spurious_kernel_fault_check(error_code, (pte_t *) p4d);
pud = pud_offset(p4d, address);
if (!pud_present(*pud))
return 0;
- if (pud_large(*pud))
+ if (pud_leaf(*pud))
return spurious_kernel_fault_check(error_code, (pte_t *) pud);
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
return 0;
- if (pmd_large(*pmd))
+ if (pmd_leaf(*pmd))
return spurious_kernel_fault_check(error_code, (pte_t *) pmd);
pte = pte_offset_kernel(pmd, address);
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index f50cc210a981..a204a332c71f 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -33,7 +33,7 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
next = end;
/* if this is already a gbpage, this portion is already mapped */
- if (pud_large(*pud))
+ if (pud_leaf(*pud))
continue;
/* Is using a gbpage allowed? */
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index b63403d7179d..ac41b1e0940d 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -463,7 +463,7 @@ void __init native_pagetable_init(void)
break;
/* should not be large page here */
- if (pmd_large(*pmd)) {
+ if (pmd_leaf(*pmd)) {
pr_warn("try to clear pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx, but pmd is big page and is not using pte !\n",
pfn, pmd, __pa(pmd));
BUG_ON(1);
@@ -800,6 +800,4 @@ void mark_rodata_ro(void)
set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
#endif
mark_nxdata_nx();
- if (__supported_pte_mask & _PAGE_NX)
- debug_checkwx();
}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a0dffaca6d2b..7e177856ee4f 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -530,7 +530,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
}
if (!pmd_none(*pmd)) {
- if (!pmd_large(*pmd)) {
+ if (!pmd_leaf(*pmd)) {
spin_lock(&init_mm.page_table_lock);
pte = (pte_t *)pmd_page_vaddr(*pmd);
paddr_last = phys_pte_init(pte, paddr,
@@ -617,7 +617,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
}
if (!pud_none(*pud)) {
- if (!pud_large(*pud)) {
+ if (!pud_leaf(*pud)) {
pmd = pmd_offset(pud, 0);
paddr_last = phys_pmd_init(pmd, paddr,
paddr_end,
@@ -1114,7 +1114,7 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
if (!pmd_present(*pmd))
continue;
- if (pmd_large(*pmd)) {
+ if (pmd_leaf(*pmd)) {
if (IS_ALIGNED(addr, PMD_SIZE) &&
IS_ALIGNED(next, PMD_SIZE)) {
if (!direct)
@@ -1163,7 +1163,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
if (!pud_present(*pud))
continue;
- if (pud_large(*pud) &&
+ if (pud_leaf(*pud) &&
IS_ALIGNED(addr, PUD_SIZE) &&
IS_ALIGNED(next, PUD_SIZE)) {
spin_lock(&init_mm.page_table_lock);
@@ -1197,7 +1197,7 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end,
if (!p4d_present(*p4d))
continue;
- BUILD_BUG_ON(p4d_large(*p4d));
+ BUILD_BUG_ON(p4d_leaf(*p4d));
pud_base = pud_offset(p4d, 0);
remove_pud_table(pud_base, addr, next, altmap, direct);
@@ -1412,8 +1412,6 @@ void mark_rodata_ro(void)
(void *)text_end, (void *)rodata_start);
free_kernel_image_pages("unused kernel image (rodata/data gap)",
(void *)rodata_end, (void *)_sdata);
-
- debug_checkwx();
}
/*
@@ -1522,9 +1520,9 @@ void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
int __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
unsigned long addr, unsigned long next)
{
- int large = pmd_large(*pmd);
+ int large = pmd_leaf(*pmd);
- if (pmd_large(*pmd)) {
+ if (pmd_leaf(*pmd)) {
vmemmap_verify((pte_t *)pmd, node, addr, next);
vmemmap_use_sub_pmd(addr, next);
}
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 0302491d799d..9dddf19a5571 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -95,7 +95,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
- if (!pmd_large(*pmd))
+ if (!pmd_leaf(*pmd))
kasan_populate_pmd(pmd, addr, next, nid);
} while (pmd++, addr = next, addr != end);
}
@@ -115,7 +115,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr,
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
- if (!pud_large(*pud))
+ if (!pud_leaf(*pud))
kasan_populate_pud(pud, addr, next, nid);
} while (pud++, addr = next, addr != end);
}
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 64b5005d49e5..ac33b2263a43 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -141,7 +141,7 @@ static pud_t __head *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
set_pud(pud, __pud(PUD_FLAGS | __pa(pmd)));
}
- if (pud_large(*pud))
+ if (pud_leaf(*pud))
return NULL;
return pud;
@@ -157,7 +157,7 @@ static void __head sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
return;
pmd = pmd_offset(pud, ppd->vaddr);
- if (pmd_large(*pmd))
+ if (pmd_leaf(*pmd))
return;
set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags));
@@ -181,7 +181,7 @@ static void __head sme_populate_pgd(struct sme_populate_pgd_data *ppd)
set_pmd(pmd, __pmd(PMD_FLAGS | __pa(pte)));
}
- if (pmd_large(*pmd))
+ if (pmd_leaf(*pmd))
return;
pte = pte_offset_kernel(pmd, ppd->vaddr);
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index e5b2985a7c51..80c9037ffadf 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -676,7 +676,7 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
return NULL;
*level = PG_LEVEL_512G;
- if (p4d_large(*p4d) || !p4d_present(*p4d))
+ if (p4d_leaf(*p4d) || !p4d_present(*p4d))
return (pte_t *)p4d;
pud = pud_offset(p4d, address);
@@ -684,7 +684,7 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
return NULL;
*level = PG_LEVEL_1G;
- if (pud_large(*pud) || !pud_present(*pud))
+ if (pud_leaf(*pud) || !pud_present(*pud))
return (pte_t *)pud;
pmd = pmd_offset(pud, address);
@@ -692,7 +692,7 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
return NULL;
*level = PG_LEVEL_2M;
- if (pmd_large(*pmd) || !pmd_present(*pmd))
+ if (pmd_leaf(*pmd) || !pmd_present(*pmd))
return (pte_t *)pmd;
*level = PG_LEVEL_4K;
@@ -739,11 +739,11 @@ pmd_t *lookup_pmd_address(unsigned long address)
return NULL;
p4d = p4d_offset(pgd, address);
- if (p4d_none(*p4d) || p4d_large(*p4d) || !p4d_present(*p4d))
+ if (p4d_none(*p4d) || p4d_leaf(*p4d) || !p4d_present(*p4d))
return NULL;
pud = pud_offset(p4d, address);
- if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud))
+ if (pud_none(*pud) || pud_leaf(*pud) || !pud_present(*pud))
return NULL;
return pmd_offset(pud, address);
@@ -1233,7 +1233,7 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
* Try to unmap in 2M chunks.
*/
while (end - start >= PMD_SIZE) {
- if (pmd_large(*pmd))
+ if (pmd_leaf(*pmd))
pmd_clear(pmd);
else
__unmap_pmd_range(pud, pmd, start, start + PMD_SIZE);
@@ -1278,7 +1278,7 @@ static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end)
*/
while (end - start >= PUD_SIZE) {
- if (pud_large(*pud))
+ if (pud_leaf(*pud))
pud_clear(pud);
else
unmap_pmd_range(pud, start, start + PUD_SIZE);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index cceb779d882d..d007591b8059 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -777,7 +777,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
*/
int pud_clear_huge(pud_t *pud)
{
- if (pud_large(*pud)) {
+ if (pud_leaf(*pud)) {
pud_clear(pud);
return 1;
}
@@ -792,7 +792,7 @@ int pud_clear_huge(pud_t *pud)
*/
int pmd_clear_huge(pmd_t *pmd)
{
- if (pmd_large(*pmd)) {
+ if (pmd_leaf(*pmd)) {
pmd_clear(pmd);
return 1;
}
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 669ba1c345b3..2e69abf4f852 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -185,7 +185,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
}
- BUILD_BUG_ON(pgd_large(*pgd) != 0);
+ BUILD_BUG_ON(pgd_leaf(*pgd) != 0);
return p4d_offset(pgd, address);
}
@@ -206,7 +206,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
if (!p4d)
return NULL;
- BUILD_BUG_ON(p4d_large(*p4d) != 0);
+ BUILD_BUG_ON(p4d_leaf(*p4d) != 0);
if (p4d_none(*p4d)) {
unsigned long new_pud_page = __get_free_page(gfp);
if (WARN_ON_ONCE(!new_pud_page))
@@ -217,7 +217,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
pud = pud_offset(p4d, address);
/* The user page tables do not use large mappings: */
- if (pud_large(*pud)) {
+ if (pud_leaf(*pud)) {
WARN_ON(1);
return NULL;
}
@@ -252,7 +252,7 @@ static pte_t *pti_user_pagetable_walk_pte(unsigned long address)
return NULL;
/* We can't do anything sensible if we hit a large mapping. */
- if (pmd_large(*pmd)) {
+ if (pmd_leaf(*pmd)) {
WARN_ON(1);
return NULL;
}
@@ -341,7 +341,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
continue;
}
- if (pmd_large(*pmd) || level == PTI_CLONE_PMD) {
+ if (pmd_leaf(*pmd) || level == PTI_CLONE_PMD) {
target_pmd = pti_user_pagetable_walk_pmd(addr);
if (WARN_ON(!target_pmd))
return;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 4af930947380..44ac64f3a047 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -299,7 +299,7 @@ static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, unsigned long lam,
write_cr3(new_mm_cr3);
}
-void leave_mm(int cpu)
+void leave_mm(void)
{
struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
@@ -327,7 +327,7 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
unsigned long flags;
local_irq_save(flags);
- switch_mm_irqs_off(prev, next, tsk);
+ switch_mm_irqs_off(NULL, next, tsk);
local_irq_restore(flags);
}
@@ -492,10 +492,16 @@ void cr4_update_pce(void *ignored)
static inline void cr4_update_pce_mm(struct mm_struct *mm) { }
#endif
-void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
+/*
+ * This optimizes when not actually switching mm's. Some architectures use the
+ * 'unused' argument for this optimization, but x86 must use
+ * 'cpu_tlbstate.loaded_mm' instead because it does not always keep
+ * 'current->active_mm' up to date.
+ */
+void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
struct task_struct *tsk)
{
- struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
+ struct mm_struct *prev = this_cpu_read(cpu_tlbstate.loaded_mm);
u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
unsigned long new_lam = mm_lam_cr3_mask(next);
bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
@@ -504,15 +510,6 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
bool need_flush;
u16 new_asid;
- /*
- * NB: The scheduler will call us with prev == next when switching
- * from lazy TLB mode to normal mode if active_mm isn't changing.
- * When this happens, we don't assume that CR3 (and hence
- * cpu_tlbstate.loaded_mm) matches next.
- *
- * NB: leave_mm() calls us with prev == NULL and tsk == NULL.
- */
-
/* We don't want flush_tlb_func() to run concurrently with us. */
if (IS_ENABLED(CONFIG_PROVE_LOCKING))
WARN_ON_ONCE(!irqs_disabled());
@@ -527,7 +524,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
* isn't free.
*/
#ifdef CONFIG_DEBUG_VM
- if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid,
+ if (WARN_ON_ONCE(__read_cr3() != build_cr3(prev->pgd, prev_asid,
tlbstate_lam_cr3_mask()))) {
/*
* If we were to BUG here, we'd be very likely to kill
@@ -559,7 +556,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
* provides that full memory barrier and core serializing
* instruction.
*/
- if (real_prev == next) {
+ if (prev == next) {
/* Not actually switching mm's */
VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
next->context.ctx_id);
@@ -574,7 +571,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
* mm_cpumask. The TLB shootdown code can figure out from
* cpu_tlbstate_shared.is_lazy whether or not to send an IPI.
*/
- if (WARN_ON_ONCE(real_prev != &init_mm &&
+ if (WARN_ON_ONCE(prev != &init_mm &&
!cpumask_test_cpu(cpu, mm_cpumask(next))))
cpumask_set_cpu(cpu, mm_cpumask(next));
@@ -616,10 +613,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
* Skip kernel threads; we never send init_mm TLB flushing IPIs,
* but the bitmap manipulation can cause cache line contention.
*/
- if (real_prev != &init_mm) {
+ if (prev != &init_mm) {
VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu,
- mm_cpumask(real_prev)));
- cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
+ mm_cpumask(prev)));
+ cpumask_clear_cpu(cpu, mm_cpumask(prev));
}
/*
@@ -656,9 +653,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
this_cpu_write(cpu_tlbstate.loaded_mm, next);
this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
- if (next != real_prev) {
+ if (next != prev) {
cr4_update_pce_mm(next);
- switch_ldt(real_prev, next);
+ switch_ldt(prev, next);
}
}
generated by cgit v1.2.3 (git 2.39.0) at 2024-10-13 12:32:38 +0300