summaryrefslogtreecommitdiff
path: root/mm/memory.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/memory.c')
-rw-r--r--mm/memory.c150
1 files changed, 85 insertions, 65 deletions
diff --git a/mm/memory.c b/mm/memory.c
index 76dcee317714..fa752df6dc85 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -72,7 +72,7 @@
#include "internal.h"
-#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+#if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
#endif
@@ -361,15 +361,6 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
{
struct mmu_table_batch **batch = &tlb->batch;
- /*
- * When there's less then two users of this mm there cannot be a
- * concurrent page-table walk.
- */
- if (atomic_read(&tlb->mm->mm_users) < 2) {
- __tlb_remove_table(table);
- return;
- }
-
if (*batch == NULL) {
*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
if (*batch == NULL) {
@@ -1127,6 +1118,7 @@ again:
init_rss_vec(rss);
start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
pte = start_pte;
+ flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
do {
pte_t ptent = *pte;
@@ -1604,8 +1596,29 @@ out:
int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn)
{
+ return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_insert_pfn);
+
+/**
+ * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @pfn: source kernel pfn
+ * @pgprot: pgprot flags for the inserted page
+ *
+ * This is exactly like vm_insert_pfn, except that it allows drivers to
+ * to override pgprot on a per-page basis.
+ *
+ * This only makes sense for IO mappings, and it makes no sense for
+ * cow mappings. In general, using multiple vmas is preferable;
+ * vm_insert_pfn_prot should only be used if using multiple VMAs is
+ * impractical.
+ */
+int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, pgprot_t pgprot)
+{
int ret;
- pgprot_t pgprot = vma->vm_page_prot;
/*
* Technically, architectures with pte_special can avoid all these
* restrictions (same for remap_pfn_range). However we would like
@@ -1623,19 +1636,29 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
if (track_pfn_insert(vma, &pgprot, pfn))
return -EINVAL;
+ if (!pfn_modify_allowed(pfn, pgprot))
+ return -EACCES;
+
ret = insert_pfn(vma, addr, pfn, pgprot);
return ret;
}
-EXPORT_SYMBOL(vm_insert_pfn);
+EXPORT_SYMBOL(vm_insert_pfn_prot);
int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn)
{
+ pgprot_t pgprot = vma->vm_page_prot;
+
BUG_ON(!(vma->vm_flags & VM_MIXEDMAP));
if (addr < vma->vm_start || addr >= vma->vm_end)
return -EFAULT;
+ if (track_pfn_insert(vma, &pgprot, pfn))
+ return -EINVAL;
+
+ if (!pfn_modify_allowed(pfn, pgprot))
+ return -EACCES;
/*
* If we don't have pte special, then we have to use the pfn_valid()
@@ -1648,9 +1671,9 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
struct page *page;
page = pfn_to_page(pfn);
- return insert_page(vma, addr, page, vma->vm_page_prot);
+ return insert_page(vma, addr, page, pgprot);
}
- return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+ return insert_pfn(vma, addr, pfn, pgprot);
}
EXPORT_SYMBOL(vm_insert_mixed);
@@ -1665,6 +1688,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
{
pte_t *pte;
spinlock_t *ptl;
+ int err = 0;
pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
if (!pte)
@@ -1672,12 +1696,16 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
arch_enter_lazy_mmu_mode();
do {
BUG_ON(!pte_none(*pte));
+ if (!pfn_modify_allowed(pfn, prot)) {
+ err = -EACCES;
+ break;
+ }
set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
- return 0;
+ return err;
}
static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
@@ -1686,6 +1714,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
{
pmd_t *pmd;
unsigned long next;
+ int err;
pfn -= addr >> PAGE_SHIFT;
pmd = pmd_alloc(mm, pud, addr);
@@ -1694,9 +1723,10 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
VM_BUG_ON(pmd_trans_huge(*pmd));
do {
next = pmd_addr_end(addr, end);
- if (remap_pte_range(mm, pmd, addr, next,
- pfn + (addr >> PAGE_SHIFT), prot))
- return -ENOMEM;
+ err = remap_pte_range(mm, pmd, addr, next,
+ pfn + (addr >> PAGE_SHIFT), prot);
+ if (err)
+ return err;
} while (pmd++, addr = next, addr != end);
return 0;
}
@@ -1707,6 +1737,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
{
pud_t *pud;
unsigned long next;
+ int err;
pfn -= addr >> PAGE_SHIFT;
pud = pud_alloc(mm, pgd, addr);
@@ -1714,9 +1745,10 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
- if (remap_pmd_range(mm, pud, addr, next,
- pfn + (addr >> PAGE_SHIFT), prot))
- return -ENOMEM;
+ err = remap_pmd_range(mm, pud, addr, next,
+ pfn + (addr >> PAGE_SHIFT), prot);
+ if (err)
+ return err;
} while (pud++, addr = next, addr != end);
return 0;
}
@@ -1989,6 +2021,20 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
copy_user_highpage(dst, src, va, vma);
}
+static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
+{
+ struct file *vm_file = vma->vm_file;
+
+ if (vm_file)
+ return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO;
+
+ /*
+ * Special mappings (e.g. VDSO) do not have any file so fake
+ * a default GFP_KERNEL for them.
+ */
+ return GFP_KERNEL;
+}
+
/*
* Notify the address space that the page is about to become writable so that
* it can prohibit this or wait for the page to get into an appropriate state.
@@ -2004,6 +2050,7 @@ static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page,
vmf.virtual_address = (void __user *)(address & PAGE_MASK);
vmf.pgoff = page->index;
vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
+ vmf.gfp_mask = __get_fault_gfp_mask(vma);
vmf.page = page;
vmf.cow_page = NULL;
@@ -2662,40 +2709,6 @@ out_release:
}
/*
- * This is like a special single-page "expand_{down|up}wards()",
- * except we must first make sure that 'address{-|+}PAGE_SIZE'
- * doesn't hit another vma.
- */
-static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
-{
- address &= PAGE_MASK;
- if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
- struct vm_area_struct *prev = vma->vm_prev;
-
- /*
- * Is there a mapping abutting this one below?
- *
- * That's only ok if it's the same stack mapping
- * that has gotten split..
- */
- if (prev && prev->vm_end == address)
- return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
-
- return expand_downwards(vma, address - PAGE_SIZE);
- }
- if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
- struct vm_area_struct *next = vma->vm_next;
-
- /* As VM_GROWSDOWN but s/below/above/ */
- if (next && next->vm_start == address + PAGE_SIZE)
- return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
-
- return expand_upwards(vma, address + PAGE_SIZE);
- }
- return 0;
-}
-
-/*
* We enter with non-exclusive mmap_sem (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with mmap_sem still held, but pte unmapped and unlocked.
@@ -2715,10 +2728,6 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
if (vma->vm_flags & VM_SHARED)
return VM_FAULT_SIGBUS;
- /* Check if we need to add a guard page to the stack */
- if (check_stack_guard_page(vma, address) < 0)
- return VM_FAULT_SIGSEGV;
-
/* Use the zero-page for reads */
if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) {
entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
@@ -2807,6 +2816,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
vmf.pgoff = pgoff;
vmf.flags = flags;
vmf.page = NULL;
+ vmf.gfp_mask = __get_fault_gfp_mask(vma);
vmf.cow_page = cow_page;
ret = vma->vm_ops->fault(vma, &vmf);
@@ -2973,6 +2983,7 @@ static void do_fault_around(struct vm_area_struct *vma, unsigned long address,
vmf.pgoff = pgoff;
vmf.max_pgoff = max_pgoff;
vmf.flags = flags;
+ vmf.gfp_mask = __get_fault_gfp_mask(vma);
vma->vm_ops->map_pages(vma, &vmf);
}
@@ -3681,6 +3692,9 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
return -EINVAL;
maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
+ if (!maddr)
+ return -ENOMEM;
+
if (write)
memcpy_toio(maddr + offset, buf, len);
else
@@ -3697,10 +3711,11 @@ EXPORT_SYMBOL_GPL(generic_access_phys);
* given task for page fault accounting.
*/
static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long addr, void *buf, int len, int write)
+ unsigned long addr, void *buf, int len, unsigned int gup_flags)
{
struct vm_area_struct *vma;
void *old_buf = buf;
+ int write = gup_flags & FOLL_WRITE;
down_read(&mm->mmap_sem);
/* ignore errors, just check how much was successfully transferred */
@@ -3710,7 +3725,7 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
struct page *page = NULL;
ret = get_user_pages(tsk, mm, addr, 1,
- write, 1, &page, &vma);
+ gup_flags, &page, &vma);
if (ret <= 0) {
#ifndef CONFIG_HAVE_IOREMAP_PROT
break;
@@ -3762,14 +3777,14 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
* @addr: start address to access
* @buf: source or destination buffer
* @len: number of bytes to transfer
- * @write: whether the access is a write
+ * @gup_flags: flags modifying lookup behaviour
*
* The caller must hold a reference on @mm.
*/
int access_remote_vm(struct mm_struct *mm, unsigned long addr,
- void *buf, int len, int write)
+ void *buf, int len, unsigned int gup_flags)
{
- return __access_remote_vm(NULL, mm, addr, buf, len, write);
+ return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags);
}
/*
@@ -3782,12 +3797,17 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr,
{
struct mm_struct *mm;
int ret;
+ unsigned int flags = FOLL_FORCE;
mm = get_task_mm(tsk);
if (!mm)
return 0;
- ret = __access_remote_vm(tsk, mm, addr, buf, len, write);
+ if (write)
+ flags |= FOLL_WRITE;
+
+ ret = __access_remote_vm(tsk, mm, addr, buf, len, flags);
+
mmput(mm);
return ret;
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-24 16:46:01 +0000