aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm')
-rw-r--r--arch/x86/mm/fault.c2
-rw-r--r--arch/x86/mm/gup.c9
-rw-r--r--arch/x86/mm/hugetlbpage.c31
-rw-r--r--arch/x86/mm/init.c43
-rw-r--r--arch/x86/mm/mpx.c6
-rw-r--r--arch/x86/mm/pat.c7
-rw-r--r--arch/x86/mm/pgtable.c14
7 files changed, 65 insertions, 47 deletions
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 38dcec403b46..e3ff27a5b634 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -898,6 +898,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
VM_FAULT_HWPOISON_LARGE))
do_sigbus(regs, error_code, address, fault);
+ else if (fault & VM_FAULT_SIGSEGV)
+ bad_area_nosemaphore(regs, error_code, address);
else
BUG();
}
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index d7547824e763..89df70e0caa6 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -172,7 +172,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
*/
if (pmd_none(pmd) || pmd_trans_splitting(pmd))
return 0;
- if (unlikely(pmd_large(pmd))) {
+ if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) {
/*
* NUMA hinting faults need to be handled in the GUP
* slowpath for accounting purposes and so that they
@@ -388,10 +388,9 @@ slow_irqon:
start += nr << PAGE_SHIFT;
pages += nr;
- down_read(&mm->mmap_sem);
- ret = get_user_pages(current, mm, start,
- (end - start) >> PAGE_SHIFT, write, 0, pages, NULL);
- up_read(&mm->mmap_sem);
+ ret = get_user_pages_unlocked(current, mm, start,
+ (end - start) >> PAGE_SHIFT,
+ write, 0, pages);
/* Have to be a bit careful with return values */
if (nr > 0) {
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 8b977ebf9388..42982b26e32b 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -52,23 +52,17 @@ int pud_huge(pud_t pud)
return 0;
}
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
- pmd_t *pmd, int write)
-{
- return NULL;
-}
#else
-struct page *
-follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
-{
- return ERR_PTR(-EINVAL);
-}
-
+/*
+ * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal
+ * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
+ * Otherwise, returns 0.
+ */
int pmd_huge(pmd_t pmd)
{
- return !!(pmd_val(pmd) & _PAGE_PSE);
+ return !pmd_none(pmd) &&
+ (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
}
int pud_huge(pud_t pud)
@@ -178,4 +172,15 @@ static __init int setup_hugepagesz(char *opt)
return 1;
}
__setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_CMA
+static __init int gigantic_pages_init(void)
+{
+ /* With CMA we can allocate gigantic pages at runtime */
+ if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT))
+ hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+ return 0;
+}
+arch_initcall(gigantic_pages_init);
+#endif
#endif
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index a97ee0801475..649da47d3827 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -43,7 +43,7 @@ uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
[_PAGE_CACHE_MODE_WT] = _PAGE_PCD,
[_PAGE_CACHE_MODE_WP] = _PAGE_PCD,
};
-EXPORT_SYMBOL_GPL(__cachemode2pte_tbl);
+EXPORT_SYMBOL(__cachemode2pte_tbl);
uint8_t __pte2cachemode_tbl[8] = {
[__pte2cm_idx(0)] = _PAGE_CACHE_MODE_WB,
[__pte2cm_idx(_PAGE_PWT)] = _PAGE_CACHE_MODE_WC,
@@ -54,7 +54,7 @@ uint8_t __pte2cachemode_tbl[8] = {
[__pte2cm_idx(_PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
};
-EXPORT_SYMBOL_GPL(__pte2cachemode_tbl);
+EXPORT_SYMBOL(__pte2cachemode_tbl);
static unsigned long __initdata pgt_buf_start;
static unsigned long __initdata pgt_buf_end;
@@ -438,20 +438,20 @@ static unsigned long __init init_range_memory_mapping(
static unsigned long __init get_new_step_size(unsigned long step_size)
{
/*
- * Explain why we shift by 5 and why we don't have to worry about
- * 'step_size << 5' overflowing:
- *
- * initial mapped size is PMD_SIZE (2M).
+ * Initial mapped size is PMD_SIZE (2M).
* We can not set step_size to be PUD_SIZE (1G) yet.
* In worse case, when we cross the 1G boundary, and
* PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k)
- * to map 1G range with PTE. Use 5 as shift for now.
+ * to map 1G range with PTE. Hence we use one less than the
+ * difference of page table level shifts.
*
- * Don't need to worry about overflow, on 32bit, when step_size
- * is 0, round_down() returns 0 for start, and that turns it
- * into 0x100000000ULL.
+ * Don't need to worry about overflow in the top-down case, on 32bit,
+ * when step_size is 0, round_down() returns 0 for start, and that
+ * turns it into 0x100000000ULL.
+ * In the bottom-up case, round_up(x, 0) returns 0 though too, which
+ * needs to be taken into consideration by the code below.
*/
- return step_size << 5;
+ return step_size << (PMD_SHIFT - PAGE_SHIFT - 1);
}
/**
@@ -471,7 +471,6 @@ static void __init memory_map_top_down(unsigned long map_start,
unsigned long step_size;
unsigned long addr;
unsigned long mapped_ram_size = 0;
- unsigned long new_mapped_ram_size;
/* xen has big range in reserved near end of ram, skip it at first.*/
addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE);
@@ -496,14 +495,12 @@ static void __init memory_map_top_down(unsigned long map_start,
start = map_start;
} else
start = map_start;
- new_mapped_ram_size = init_range_memory_mapping(start,
+ mapped_ram_size += init_range_memory_mapping(start,
last_start);
last_start = start;
min_pfn_mapped = last_start >> PAGE_SHIFT;
- /* only increase step_size after big range get mapped */
- if (new_mapped_ram_size > mapped_ram_size)
+ if (mapped_ram_size >= step_size)
step_size = get_new_step_size(step_size);
- mapped_ram_size += new_mapped_ram_size;
}
if (real_end < map_end)
@@ -524,7 +521,7 @@ static void __init memory_map_top_down(unsigned long map_start,
static void __init memory_map_bottom_up(unsigned long map_start,
unsigned long map_end)
{
- unsigned long next, new_mapped_ram_size, start;
+ unsigned long next, start;
unsigned long mapped_ram_size = 0;
/* step_size need to be small so pgt_buf from BRK could cover it */
unsigned long step_size = PMD_SIZE;
@@ -539,19 +536,19 @@ static void __init memory_map_bottom_up(unsigned long map_start,
* for page table.
*/
while (start < map_end) {
- if (map_end - start > step_size) {
+ if (step_size && map_end - start > step_size) {
next = round_up(start + 1, step_size);
if (next > map_end)
next = map_end;
- } else
+ } else {
next = map_end;
+ }
- new_mapped_ram_size = init_range_memory_mapping(start, next);
+ mapped_ram_size += init_range_memory_mapping(start, next);
start = next;
- if (new_mapped_ram_size > mapped_ram_size)
+ if (mapped_ram_size >= step_size)
step_size = get_new_step_size(step_size);
- mapped_ram_size += new_mapped_ram_size;
}
}
@@ -611,7 +608,7 @@ void __init init_mem_mapping(void)
*
*
* On x86, access has to be given to the first megabyte of ram because that area
- * contains bios code and data regions used by X and dosemu and similar apps.
+ * contains BIOS code and data regions used by X and dosemu and similar apps.
* Access has to be given to non-kernel-ram areas as well, these contain the PCI
* mmio resources as well as potential bios/acpi data regions.
*/
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 67ebf5751222..c439ec478216 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -349,6 +349,12 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk)
return MPX_INVALID_BOUNDS_DIR;
/*
+ * 32-bit binaries on 64-bit kernels are currently
+ * unsupported.
+ */
+ if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32))
+ return MPX_INVALID_BOUNDS_DIR;
+ /*
* The bounds directory pointer is stored in a register
* only accessible if we first do an xsave.
*/
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index edf299c8ff6c..7ac68698406c 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -234,8 +234,13 @@ void pat_init(void)
PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
/* Boot CPU check */
- if (!boot_pat_state)
+ if (!boot_pat_state) {
rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
+ if (!boot_pat_state) {
+ pat_disable("PAT read returns always zero, disabled.");
+ return;
+ }
+ }
wrmsrl(MSR_IA32_CR_PAT, pat);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 6fb6927f9e76..7b22adaad4f1 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -190,7 +190,7 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
#endif /* CONFIG_X86_PAE */
-static void free_pmds(pmd_t *pmds[])
+static void free_pmds(struct mm_struct *mm, pmd_t *pmds[])
{
int i;
@@ -198,10 +198,11 @@ static void free_pmds(pmd_t *pmds[])
if (pmds[i]) {
pgtable_pmd_page_dtor(virt_to_page(pmds[i]));
free_page((unsigned long)pmds[i]);
+ mm_dec_nr_pmds(mm);
}
}
-static int preallocate_pmds(pmd_t *pmds[])
+static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
{
int i;
bool failed = false;
@@ -215,11 +216,13 @@ static int preallocate_pmds(pmd_t *pmds[])
pmd = NULL;
failed = true;
}
+ if (pmd)
+ mm_inc_nr_pmds(mm);
pmds[i] = pmd;
}
if (failed) {
- free_pmds(pmds);
+ free_pmds(mm, pmds);
return -ENOMEM;
}
@@ -246,6 +249,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
pmd_free(mm, pmd);
+ mm_dec_nr_pmds(mm);
}
}
}
@@ -283,7 +287,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
mm->pgd = pgd;
- if (preallocate_pmds(pmds) != 0)
+ if (preallocate_pmds(mm, pmds) != 0)
goto out_free_pgd;
if (paravirt_pgd_alloc(mm) != 0)
@@ -304,7 +308,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
return pgd;
out_free_pmds:
- free_pmds(pmds);
+ free_pmds(mm, pmds);
out_free_pgd:
free_page((unsigned long)pgd);
out:
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.