summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/backing-dev.c5
-rw-r--r--mm/debug.c28
-rw-r--r--mm/early_ioremap.c2
-rw-r--r--mm/frame_vector.c6
-rw-r--r--mm/gup.c48
-rw-r--r--mm/hmm.c8
-rw-r--r--mm/huge_memory.c6
-rw-r--r--mm/hwpoison-inject.c2
-rw-r--r--mm/kmemleak.c4
-rw-r--r--mm/ksm.c9
-rw-r--r--mm/madvise.c2
-rw-r--r--mm/memcontrol.c2
-rw-r--r--mm/memory-failure.c48
-rw-r--r--mm/memory.c21
-rw-r--r--mm/mlock.c2
-rw-r--r--mm/mmap.c10
-rw-r--r--mm/mprotect.c6
-rw-r--r--mm/oom_kill.c4
-rw-r--r--mm/page_alloc.c13
-rw-r--r--mm/page_io.c4
-rw-r--r--mm/page_owner.c1
-rw-r--r--mm/page_vma_mapped.c66
-rw-r--r--mm/percpu.c4
-rw-r--r--mm/slab.c23
-rw-r--r--mm/sparse.c2
-rw-r--r--mm/swapfile.c2
-rw-r--r--mm/util.c36
-rw-r--r--mm/vmscan.c3
-rw-r--r--mm/zsmalloc.c1
29 files changed, 199 insertions, 169 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 84b2dc76f140..b5f940ce0143 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -882,13 +882,10 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args)
if (IS_ERR(dev))
return PTR_ERR(dev);
- if (bdi_debug_register(bdi, dev_name(dev))) {
- device_destroy(bdi_class, dev->devt);
- return -ENOMEM;
- }
cgwb_bdi_register(bdi);
bdi->dev = dev;
+ bdi_debug_register(bdi, dev_name(dev));
set_bit(WB_registered, &bdi->wb.state);
spin_lock_bh(&bdi_lock);
diff --git a/mm/debug.c b/mm/debug.c
index d947f3e03b0d..56e2d9125ea5 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -50,7 +50,7 @@ void __dump_page(struct page *page, const char *reason)
*/
int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
- pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx",
+ pr_emerg("page:%px count:%d mapcount:%d mapping:%px index:%#lx",
page, page_ref_count(page), mapcount,
page->mapping, page_to_pgoff(page));
if (PageCompound(page))
@@ -69,7 +69,7 @@ void __dump_page(struct page *page, const char *reason)
#ifdef CONFIG_MEMCG
if (page->mem_cgroup)
- pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
+ pr_alert("page->mem_cgroup:%px\n", page->mem_cgroup);
#endif
}
@@ -84,10 +84,10 @@ EXPORT_SYMBOL(dump_page);
void dump_vma(const struct vm_area_struct *vma)
{
- pr_emerg("vma %p start %p end %p\n"
- "next %p prev %p mm %p\n"
- "prot %lx anon_vma %p vm_ops %p\n"
- "pgoff %lx file %p private_data %p\n"
+ pr_emerg("vma %px start %px end %px\n"
+ "next %px prev %px mm %px\n"
+ "prot %lx anon_vma %px vm_ops %px\n"
+ "pgoff %lx file %px private_data %px\n"
"flags: %#lx(%pGv)\n",
vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
vma->vm_prev, vma->vm_mm,
@@ -100,27 +100,27 @@ EXPORT_SYMBOL(dump_vma);
void dump_mm(const struct mm_struct *mm)
{
- pr_emerg("mm %p mmap %p seqnum %d task_size %lu\n"
+ pr_emerg("mm %px mmap %px seqnum %d task_size %lu\n"
#ifdef CONFIG_MMU
- "get_unmapped_area %p\n"
+ "get_unmapped_area %px\n"
#endif
"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
- "pgd %p mm_users %d mm_count %d pgtables_bytes %lu map_count %d\n"
+ "pgd %px mm_users %d mm_count %d pgtables_bytes %lu map_count %d\n"
"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
"pinned_vm %lx data_vm %lx exec_vm %lx stack_vm %lx\n"
"start_code %lx end_code %lx start_data %lx end_data %lx\n"
"start_brk %lx brk %lx start_stack %lx\n"
"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
- "binfmt %p flags %lx core_state %p\n"
+ "binfmt %px flags %lx core_state %px\n"
#ifdef CONFIG_AIO
- "ioctx_table %p\n"
+ "ioctx_table %px\n"
#endif
#ifdef CONFIG_MEMCG
- "owner %p "
+ "owner %px "
#endif
- "exe_file %p\n"
+ "exe_file %px\n"
#ifdef CONFIG_MMU_NOTIFIER
- "mmu_notifier_mm %p\n"
+ "mmu_notifier_mm %px\n"
#endif
#ifdef CONFIG_NUMA_BALANCING
"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
index d04ac1ec0559..1826f191e72c 100644
--- a/mm/early_ioremap.c
+++ b/mm/early_ioremap.c
@@ -111,7 +111,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
enum fixed_addresses idx;
int i, slot;
- WARN_ON(system_state != SYSTEM_BOOTING);
+ WARN_ON(system_state >= SYSTEM_RUNNING);
slot = -1;
for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
diff --git a/mm/frame_vector.c b/mm/frame_vector.c
index 297c7238f7d4..c64dca6e27c2 100644
--- a/mm/frame_vector.c
+++ b/mm/frame_vector.c
@@ -62,8 +62,10 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
* get_user_pages_longterm() and disallow it for filesystem-dax
* mappings.
*/
- if (vma_is_fsdax(vma))
- return -EOPNOTSUPP;
+ if (vma_is_fsdax(vma)) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) {
vec->got_ref = true;
diff --git a/mm/gup.c b/mm/gup.c
index d3fb60e5bfac..9e17d8db2d6b 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -66,7 +66,7 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
*/
static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
{
- return pte_access_permitted(pte, WRITE) ||
+ return pte_write(pte) ||
((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
}
@@ -848,7 +848,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
unsigned long nr_pages,
struct page **pages,
struct vm_area_struct **vmas,
- int *locked, bool notify_drop,
+ int *locked,
unsigned int flags)
{
long ret, pages_done;
@@ -922,7 +922,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
pages++;
start += PAGE_SIZE;
}
- if (notify_drop && lock_dropped && *locked) {
+ if (lock_dropped && *locked) {
/*
* We must let the caller know we temporarily dropped the lock
* and so the critical section protected by it was lost.
@@ -959,36 +959,12 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
int *locked)
{
return __get_user_pages_locked(current, current->mm, start, nr_pages,
- pages, NULL, locked, true,
+ pages, NULL, locked,
gup_flags | FOLL_TOUCH);
}
EXPORT_SYMBOL(get_user_pages_locked);
/*
- * Same as get_user_pages_unlocked(...., FOLL_TOUCH) but it allows for
- * tsk, mm to be specified.
- *
- * NOTE: here FOLL_TOUCH is not set implicitly and must be set by the
- * caller if required (just like with __get_user_pages). "FOLL_GET"
- * is set implicitly if "pages" is non-NULL.
- */
-static __always_inline long __get_user_pages_unlocked(struct task_struct *tsk,
- struct mm_struct *mm, unsigned long start,
- unsigned long nr_pages, struct page **pages,
- unsigned int gup_flags)
-{
- long ret;
- int locked = 1;
-
- down_read(&mm->mmap_sem);
- ret = __get_user_pages_locked(tsk, mm, start, nr_pages, pages, NULL,
- &locked, false, gup_flags);
- if (locked)
- up_read(&mm->mmap_sem);
- return ret;
-}
-
-/*
* get_user_pages_unlocked() is suitable to replace the form:
*
* down_read(&mm->mmap_sem);
@@ -1006,8 +982,16 @@ static __always_inline long __get_user_pages_unlocked(struct task_struct *tsk,
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags)
{
- return __get_user_pages_unlocked(current, current->mm, start, nr_pages,
- pages, gup_flags | FOLL_TOUCH);
+ struct mm_struct *mm = current->mm;
+ int locked = 1;
+ long ret;
+
+ down_read(&mm->mmap_sem);
+ ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL,
+ &locked, gup_flags | FOLL_TOUCH);
+ if (locked)
+ up_read(&mm->mmap_sem);
+ return ret;
}
EXPORT_SYMBOL(get_user_pages_unlocked);
@@ -1073,7 +1057,7 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
struct vm_area_struct **vmas, int *locked)
{
return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
- locked, true,
+ locked,
gup_flags | FOLL_TOUCH | FOLL_REMOTE);
}
EXPORT_SYMBOL(get_user_pages_remote);
@@ -1090,7 +1074,7 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
struct vm_area_struct **vmas)
{
return __get_user_pages_locked(current, current->mm, start, nr_pages,
- pages, vmas, NULL, false,
+ pages, vmas, NULL,
gup_flags | FOLL_TOUCH);
}
EXPORT_SYMBOL(get_user_pages);
diff --git a/mm/hmm.c b/mm/hmm.c
index 3a5c172af560..ea19742a5d60 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -391,11 +391,11 @@ again:
if (pmd_protnone(pmd))
return hmm_vma_walk_clear(start, end, walk);
- if (!pmd_access_permitted(pmd, write_fault))
+ if (write_fault && !pmd_write(pmd))
return hmm_vma_walk_clear(start, end, walk);
pfn = pmd_pfn(pmd) + pte_index(addr);
- flag |= pmd_access_permitted(pmd, WRITE) ? HMM_PFN_WRITE : 0;
+ flag |= pmd_write(pmd) ? HMM_PFN_WRITE : 0;
for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
pfns[i] = hmm_pfn_t_from_pfn(pfn) | flag;
return 0;
@@ -456,11 +456,11 @@ again:
continue;
}
- if (!pte_access_permitted(pte, write_fault))
+ if (write_fault && !pte_write(pte))
goto fault;
pfns[i] = hmm_pfn_t_from_pfn(pte_pfn(pte)) | flag;
- pfns[i] |= pte_access_permitted(pte, WRITE) ? HMM_PFN_WRITE : 0;
+ pfns[i] |= pte_write(pte) ? HMM_PFN_WRITE : 0;
continue;
fault:
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2f2f5e774902..0e7ded98d114 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -870,7 +870,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
*/
WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");
- if (!pmd_access_permitted(*pmd, flags & FOLL_WRITE))
+ if (flags & FOLL_WRITE && !pmd_write(*pmd))
return NULL;
if (pmd_present(*pmd) && pmd_devmap(*pmd))
@@ -1012,7 +1012,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
assert_spin_locked(pud_lockptr(mm, pud));
- if (!pud_access_permitted(*pud, flags & FOLL_WRITE))
+ if (flags & FOLL_WRITE && !pud_write(*pud))
return NULL;
if (pud_present(*pud) && pud_devmap(*pud))
@@ -1386,7 +1386,7 @@ out_unlock:
*/
static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
{
- return pmd_access_permitted(pmd, WRITE) ||
+ return pmd_write(pmd) ||
((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
}
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index 356df057a2a8..b6ac70616c32 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -52,7 +52,7 @@ static int hwpoison_inject(void *data, u64 val)
inject:
pr_info("Injecting memory failure at pfn %#lx\n", pfn);
- return memory_failure(pfn, 18, MF_COUNT_INCREASED);
+ return memory_failure(pfn, MF_COUNT_INCREASED);
put_out:
put_hwpoison_page(p);
return 0;
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 3d4781756d50..f656ca27f6c2 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -127,7 +127,7 @@
/* GFP bitmask for kmemleak internal allocations */
#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \
__GFP_NORETRY | __GFP_NOMEMALLOC | \
- __GFP_NOWARN)
+ __GFP_NOWARN | __GFP_NOFAIL)
/* scanning area inside a memory block */
struct kmemleak_scan_area {
@@ -1523,7 +1523,7 @@ static void kmemleak_scan(void)
if (page_count(page) == 0)
continue;
scan_block(page, page + 1, NULL);
- if (!(pfn % (MAX_SCAN_SIZE / sizeof(*page))))
+ if (!(pfn & 63))
cond_resched();
}
}
diff --git a/mm/ksm.c b/mm/ksm.c
index be8f4576f842..c406f75957ad 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -675,15 +675,8 @@ static struct page *get_ksm_page(struct stable_node *stable_node, bool lock_it)
expected_mapping = (void *)((unsigned long)stable_node |
PAGE_MAPPING_KSM);
again:
- kpfn = READ_ONCE(stable_node->kpfn);
+ kpfn = READ_ONCE(stable_node->kpfn); /* Address dependency. */
page = pfn_to_page(kpfn);
-
- /*
- * page is computed from kpfn, so on most architectures reading
- * page->mapping is naturally ordered after reading node->kpfn,
- * but on Alpha we need to be more careful.
- */
- smp_read_barrier_depends();
if (READ_ONCE(page->mapping) != expected_mapping)
goto stale;
diff --git a/mm/madvise.c b/mm/madvise.c
index 751e97aa2210..4d3c922ea1a1 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -661,7 +661,7 @@ static int madvise_inject_error(int behavior,
pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
page_to_pfn(page), start);
- ret = memory_failure(page_to_pfn(page), 0, MF_COUNT_INCREASED);
+ ret = memory_failure(page_to_pfn(page), MF_COUNT_INCREASED);
if (ret)
return ret;
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ac2ffd5e02b9..9011997d8a5c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3777,7 +3777,7 @@ static int memcg_event_wake(wait_queue_entry_t *wait, unsigned mode,
struct mem_cgroup_event *event =
container_of(wait, struct mem_cgroup_event, wait);
struct mem_cgroup *memcg = event->memcg;
- unsigned long flags = (unsigned long)key;
+ __poll_t flags = key_to_poll(key);
if (flags & POLLHUP) {
/*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4acdf393a801..4b80ccee4535 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -178,25 +178,19 @@ EXPORT_SYMBOL_GPL(hwpoison_filter);
* ``action optional'' if they are not immediately affected by the error
* ``action required'' if error happened in current execution context
*/
-static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
+static int kill_proc(struct task_struct *t, unsigned long addr,
unsigned long pfn, struct page *page, int flags)
{
- struct siginfo si;
+ short addr_lsb;
int ret;
pr_err("Memory failure: %#lx: Killing %s:%d due to hardware memory corruption\n",
pfn, t->comm, t->pid);
- si.si_signo = SIGBUS;
- si.si_errno = 0;
- si.si_addr = (void *)addr;
-#ifdef __ARCH_SI_TRAPNO
- si.si_trapno = trapno;
-#endif
- si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
+ addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) {
- si.si_code = BUS_MCEERR_AR;
- ret = force_sig_info(SIGBUS, &si, current);
+ ret = force_sig_mceerr(BUS_MCEERR_AR, (void __user *)addr,
+ addr_lsb, current);
} else {
/*
* Don't use force here, it's convenient if the signal
@@ -204,8 +198,8 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
* This could cause a loop when the user sets SIGBUS
* to SIG_IGN, but hopefully no one will do that?
*/
- si.si_code = BUS_MCEERR_AO;
- ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */
+ ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)addr,
+ addr_lsb, t); /* synchronous? */
}
if (ret < 0)
pr_info("Memory failure: Error sending signal to %s:%d: %d\n",
@@ -323,7 +317,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
* Also when FAIL is set do a force kill because something went
* wrong earlier.
*/
-static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
+static void kill_procs(struct list_head *to_kill, int forcekill,
bool fail, struct page *page, unsigned long pfn,
int flags)
{
@@ -348,7 +342,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
* check for that, but we need to tell the
* process anyways.
*/
- else if (kill_proc(tk->tsk, tk->addr, trapno,
+ else if (kill_proc(tk->tsk, tk->addr,
pfn, page, flags) < 0)
pr_err("Memory failure: %#lx: Cannot send advisory machine check signal to %s:%d\n",
pfn, tk->tsk->comm, tk->tsk->pid);
@@ -927,7 +921,7 @@ EXPORT_SYMBOL_GPL(get_hwpoison_page);
* the pages and send SIGBUS to the processes if the data was dirty.
*/
static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
- int trapno, int flags, struct page **hpagep)
+ int flags, struct page **hpagep)
{
enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
struct address_space *mapping;
@@ -1017,7 +1011,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
* any accesses to the poisoned memory.
*/
forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL);
- kill_procs(&tokill, forcekill, trapno, !unmap_success, p, pfn, flags);
+ kill_procs(&tokill, forcekill, !unmap_success, p, pfn, flags);
return unmap_success;
}
@@ -1045,7 +1039,7 @@ static int identify_page_state(unsigned long pfn, struct page *p,
return page_action(ps, p, pfn);
}
-static int memory_failure_hugetlb(unsigned long pfn, int trapno, int flags)
+static int memory_failure_hugetlb(unsigned long pfn, int flags)
{
struct page *p = pfn_to_page(pfn);
struct page *head = compound_head(p);
@@ -1090,7 +1084,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int trapno, int flags)
return 0;
}
- if (!hwpoison_user_mappings(p, pfn, trapno, flags, &head)) {
+ if (!hwpoison_user_mappings(p, pfn, flags, &head)) {
action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
res = -EBUSY;
goto out;
@@ -1105,7 +1099,6 @@ out:
/**
* memory_failure - Handle memory failure of a page.
* @pfn: Page Number of the corrupted page
- * @trapno: Trap number reported in the signal to user space.
* @flags: fine tune action taken
*
* This function is called by the low level machine check code
@@ -1120,7 +1113,7 @@ out:
* Must run in process context (e.g. a work queue) with interrupts
* enabled and no spinlocks hold.
*/
-int memory_failure(unsigned long pfn, int trapno, int flags)
+int memory_failure(unsigned long pfn, int flags)
{
struct page *p;
struct page *hpage;
@@ -1129,7 +1122,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
unsigned long page_flags;
if (!sysctl_memory_failure_recovery)
- panic("Memory failure from trap %d on page %lx", trapno, pfn);
+ panic("Memory failure on page %lx", pfn);
if (!pfn_valid(pfn)) {
pr_err("Memory failure: %#lx: memory outside kernel control\n",
@@ -1139,7 +1132,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
p = pfn_to_page(pfn);
if (PageHuge(p))
- return memory_failure_hugetlb(pfn, trapno, flags);
+ return memory_failure_hugetlb(pfn, flags);
if (TestSetPageHWPoison(p)) {
pr_err("Memory failure: %#lx: already hardware poisoned\n",
pfn);
@@ -1268,7 +1261,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
* When the raw error page is thp tail page, hpage points to the raw
* page after thp split.
*/
- if (!hwpoison_user_mappings(p, pfn, trapno, flags, &hpage)) {
+ if (!hwpoison_user_mappings(p, pfn, flags, &hpage)) {
action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
res = -EBUSY;
goto out;
@@ -1296,7 +1289,6 @@ EXPORT_SYMBOL_GPL(memory_failure);
struct memory_failure_entry {
unsigned long pfn;
- int trapno;
int flags;
};
@@ -1312,7 +1304,6 @@ static DEFINE_PER_CPU(struct memory_failure_cpu, memory_failure_cpu);
/**
* memory_failure_queue - Schedule handling memory failure of a page.
* @pfn: Page Number of the corrupted page
- * @trapno: Trap number reported in the signal to user space.
* @flags: Flags for memory failure handling
*
* This function is called by the low level hardware error handler
@@ -1326,13 +1317,12 @@ static DEFINE_PER_CPU(struct memory_failure_cpu, memory_failure_cpu);
*
* Can run in IRQ context.
*/
-void memory_failure_queue(unsigned long pfn, int trapno, int flags)
+void memory_failure_queue(unsigned long pfn, int flags)
{
struct memory_failure_cpu *mf_cpu;
unsigned long proc_flags;
struct memory_failure_entry entry = {
.pfn = pfn,
- .trapno = trapno,
.flags = flags,
};
@@ -1365,7 +1355,7 @@ static void memory_failure_work_func(struct work_struct *work)
if (entry.flags & MF_SOFT_OFFLINE)
soft_offline_page(pfn_to_page(entry.pfn), entry.flags);
else
- memory_failure(entry.pfn, entry.trapno, entry.flags);
+ memory_failure(entry.pfn, entry.flags);
}
}
diff --git a/mm/memory.c b/mm/memory.c
index 5eb3d2524bdc..793004608332 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2857,8 +2857,11 @@ int do_swap_page(struct vm_fault *vmf)
int ret = 0;
bool vma_readahead = swap_use_vma_readahead();
- if (vma_readahead)
+ if (vma_readahead) {
page = swap_readahead_detect(vmf, &swap_ra);
+ swapcache = page;
+ }
+
if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) {
if (page)
put_page(page);
@@ -2889,9 +2892,12 @@ int do_swap_page(struct vm_fault *vmf)
delayacct_set_flag(DELAYACCT_PF_SWAPIN);
- if (!page)
+ if (!page) {
page = lookup_swap_cache(entry, vma_readahead ? vma : NULL,
vmf->address);
+ swapcache = page;
+ }
+
if (!page) {
struct swap_info_struct *si = swp_swap_info(entry);
@@ -3831,7 +3837,8 @@ static inline int create_huge_pmd(struct vm_fault *vmf)
return VM_FAULT_FALLBACK;
}
-static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
+/* `inline' is required to avoid gcc 4.1.2 build error */
+static inline int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
{
if (vma_is_anonymous(vmf->vma))
return do_huge_pmd_wp_page(vmf, orig_pmd);
@@ -3948,7 +3955,7 @@ static int handle_pte_fault(struct vm_fault *vmf)
if (unlikely(!pte_same(*vmf->pte, entry)))
goto unlock;
if (vmf->flags & FAULT_FLAG_WRITE) {
- if (!pte_access_permitted(entry, WRITE))
+ if (!pte_write(entry))
return do_wp_page(vmf);
entry = pte_mkdirty(entry);
}
@@ -4013,7 +4020,7 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
/* NUMA case for anonymous PUDs would go here */
- if (dirty && !pud_access_permitted(orig_pud, WRITE)) {
+ if (dirty && !pud_write(orig_pud)) {
ret = wp_huge_pud(&vmf, orig_pud);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
@@ -4046,7 +4053,7 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
return do_huge_pmd_numa_page(&vmf, orig_pmd);
- if (dirty && !pmd_access_permitted(orig_pmd, WRITE)) {
+ if (dirty && !pmd_write(orig_pmd)) {
ret = wp_huge_pmd(&vmf, orig_pmd);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
@@ -4336,7 +4343,7 @@ int follow_phys(struct vm_area_struct *vma,
goto out;
pte = *ptep;
- if (!pte_access_permitted(pte, flags & FOLL_WRITE))
+ if ((flags & FOLL_WRITE) && !pte_write(pte))
goto unlock;
*prot = pgprot_val(pte_pgprot(pte));
diff --git a/mm/mlock.c b/mm/mlock.c
index 30472d438794..f7f54fd2e13f 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -779,7 +779,7 @@ static int apply_mlockall_flags(int flags)
/* Ignore errors */
mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
- cond_resched_rcu_qs();
+ cond_resched();
}
out:
return 0;
diff --git a/mm/mmap.c b/mm/mmap.c
index a4d546821214..9efdc021ad22 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3019,20 +3019,20 @@ void exit_mmap(struct mm_struct *mm)
/* Use -1 here to ensure all VMAs in the mm are unmapped */
unmap_vmas(&tlb, vma, 0, -1);
- set_bit(MMF_OOM_SKIP, &mm->flags);
- if (unlikely(tsk_is_oom_victim(current))) {
+ if (unlikely(mm_is_oom_victim(mm))) {
/*
* Wait for oom_reap_task() to stop working on this
* mm. Because MMF_OOM_SKIP is already set before
* calling down_read(), oom_reap_task() will not run
* on this "mm" post up_write().
*
- * tsk_is_oom_victim() cannot be set from under us
- * either because current->mm is already set to NULL
+ * mm_is_oom_victim() cannot be set from under us
+ * either because victim->mm is already set to NULL
* under task_lock before calling mmput and oom_mm is
- * set not NULL by the OOM killer only if current->mm
+ * set not NULL by the OOM killer only if victim->mm
* is found not NULL while holding the task_lock.
*/
+ set_bit(MMF_OOM_SKIP, &mm->flags);
down_write(&mm->mmap_sem);
up_write(&mm->mmap_sem);
}
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ec39f730a0bf..58b629bb70de 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -166,7 +166,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
next = pmd_addr_end(addr, end);
if (!is_swap_pmd(*pmd) && !pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)
&& pmd_none_or_clear_bad(pmd))
- continue;
+ goto next;
/* invoke the mmu notifier if the pmd is populated */
if (!mni_start) {
@@ -188,7 +188,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
}
/* huge pmd was handled */
- continue;
+ goto next;
}
}
/* fall through, the trans huge pmd just split */
@@ -196,6 +196,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
this_pages = change_pte_range(vma, pmd, addr, next, newprot,
dirty_accountable, prot_numa);
pages += this_pages;
+next:
+ cond_resched();
} while (pmd++, addr = next, addr != end);
if (mni_start)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index c957be32b27a..29f855551efe 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -683,8 +683,10 @@ static void mark_oom_victim(struct task_struct *tsk)
return;
/* oom_mm is bound to the signal struct life time. */
- if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm))
+ if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) {
mmgrab(tsk->signal->oom_mm);
+ set_bit(MMF_OOM_VICTIM, &mm->flags);
+ }
/*
* Make sure that the task is woken up from uninterruptible sleep
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 73f5d4556b3d..76c9688b6a0a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2684,6 +2684,7 @@ void free_unref_page_list(struct list_head *list)
{
struct page *page, *next;
unsigned long flags, pfn;
+ int batch_count = 0;
/* Prepare pages for freeing */
list_for_each_entry_safe(page, next, list, lru) {
@@ -2700,6 +2701,16 @@ void free_unref_page_list(struct list_head *list)
set_page_private(page, 0);
trace_mm_page_free_batched(page);
free_unref_page_commit(page, pfn);
+
+ /*
+ * Guard against excessive IRQ disabled times when we get
+ * a large list of pages to free.
+ */
+ if (++batch_count == SWAP_CLUSTER_MAX) {
+ local_irq_restore(flags);
+ batch_count = 0;
+ local_irq_save(flags);
+ }
}
local_irq_restore(flags);
}
@@ -6249,6 +6260,8 @@ void __paginginit zero_resv_unavail(void)
pgcnt = 0;
for_each_resv_unavail_range(i, &start, &end) {
for (pfn = PFN_DOWN(start); pfn < PFN_UP(end); pfn++) {
+ if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages)))
+ continue;
mm_zero_struct_page(pfn_to_page(pfn));
pgcnt++;
}
diff --git a/mm/page_io.c b/mm/page_io.c
index e93f1a4cacd7..b41cf9644585 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -50,7 +50,7 @@ static struct bio *get_swap_bio(gfp_t gfp_flags,
void end_swap_bio_write(struct bio *bio)
{
- struct page *page = bio->bi_io_vec[0].bv_page;
+ struct page *page = bio_first_page_all(bio);
if (bio->bi_status) {
SetPageError(page);
@@ -122,7 +122,7 @@ static void swap_slot_free_notify(struct page *page)
static void end_swap_bio_read(struct bio *bio)
{
- struct page *page = bio->bi_io_vec[0].bv_page;
+ struct page *page = bio_first_page_all(bio);
struct task_struct *waiter = bio->bi_private;
if (bio->bi_status) {
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 8592543a0f15..270a8219ccd0 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -616,7 +616,6 @@ static void init_early_allocated_pages(void)
{
pg_data_t *pgdat;
- drain_all_pages(NULL);
for_each_online_pgdat(pgdat)
init_zones_in_node(pgdat);
}
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index d22b84310f6d..ae3c2a35d61b 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -30,10 +30,37 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw)
return true;
}
+static inline bool pfn_in_hpage(struct page *hpage, unsigned long pfn)
+{
+ unsigned long hpage_pfn = page_to_pfn(hpage);
+
+ /* THP can be referenced by any subpage */
+ return pfn >= hpage_pfn && pfn - hpage_pfn < hpage_nr_pages(hpage);
+}
+
+/**
+ * check_pte - check if @pvmw->page is mapped at the @pvmw->pte
+ *
+ * page_vma_mapped_walk() found a place where @pvmw->page is *potentially*
+ * mapped. check_pte() has to validate this.
+ *
+ * @pvmw->pte may point to empty PTE, swap PTE or PTE pointing to arbitrary
+ * page.
+ *
+ * If PVMW_MIGRATION flag is set, returns true if @pvmw->pte contains migration
+ * entry that points to @pvmw->page or any subpage in case of THP.
+ *
+ * If PVMW_MIGRATION flag is not set, returns true if @pvmw->pte points to
+ * @pvmw->page or any subpage in case of THP.
+ *
+ * Otherwise, return false.
+ *
+ */
static bool check_pte(struct page_vma_mapped_walk *pvmw)
{
+ unsigned long pfn;
+
if (pvmw->flags & PVMW_MIGRATION) {
-#ifdef CONFIG_MIGRATION
swp_entry_t entry;
if (!is_swap_pte(*pvmw->pte))
return false;
@@ -41,38 +68,25 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
if (!is_migration_entry(entry))
return false;
- if (migration_entry_to_page(entry) - pvmw->page >=
- hpage_nr_pages(pvmw->page)) {
- return false;
- }
- if (migration_entry_to_page(entry) < pvmw->page)
- return false;
-#else
- WARN_ON_ONCE(1);
-#endif
- } else {
- if (is_swap_pte(*pvmw->pte)) {
- swp_entry_t entry;
- entry = pte_to_swp_entry(*pvmw->pte);
- if (is_device_private_entry(entry) &&
- device_private_entry_to_page(entry) == pvmw->page)
- return true;
- }
+ pfn = migration_entry_to_pfn(entry);
+ } else if (is_swap_pte(*pvmw->pte)) {
+ swp_entry_t entry;
- if (!pte_present(*pvmw->pte))
+ /* Handle un-addressable ZONE_DEVICE memory */
+ entry = pte_to_swp_entry(*pvmw->pte);
+ if (!is_device_private_entry(entry))
return false;
- /* THP can be referenced by any subpage */
- if (pte_page(*pvmw->pte) - pvmw->page >=
- hpage_nr_pages(pvmw->page)) {
- return false;
- }
- if (pte_page(*pvmw->pte) < pvmw->page)
+ pfn = device_private_entry_to_pfn(entry);
+ } else {
+ if (!pte_present(*pvmw->pte))
return false;
+
+ pfn = pte_pfn(*pvmw->pte);
}
- return true;
+ return pfn_in_hpage(pvmw->page, pfn);
}
/**
diff --git a/mm/percpu.c b/mm/percpu.c
index 79e3549cab0f..50e7fdf84055 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -2719,7 +2719,11 @@ void __init setup_per_cpu_areas(void)
if (pcpu_setup_first_chunk(ai, fc) < 0)
panic("Failed to initialize percpu areas.");
+#ifdef CONFIG_CRIS
+#warning "the CRIS architecture has physical and virtual addresses confused"
+#else
pcpu_free_alloc_info(ai);
+#endif
}
#endif /* CONFIG_SMP */
diff --git a/mm/slab.c b/mm/slab.c
index 183e996dde5f..4e51ef954026 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1584,11 +1584,8 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
*dbg_redzone2(cachep, objp));
}
- if (cachep->flags & SLAB_STORE_USER) {
- pr_err("Last user: [<%p>](%pSR)\n",
- *dbg_userword(cachep, objp),
- *dbg_userword(cachep, objp));
- }
+ if (cachep->flags & SLAB_STORE_USER)
+ pr_err("Last user: (%pSR)\n", *dbg_userword(cachep, objp));
realobj = (char *)objp + obj_offset(cachep);
size = cachep->object_size;
for (i = 0; i < size && lines; i += 16, lines--) {
@@ -1621,7 +1618,7 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
/* Mismatch ! */
/* Print header */
if (lines == 0) {
- pr_err("Slab corruption (%s): %s start=%p, len=%d\n",
+ pr_err("Slab corruption (%s): %s start=%px, len=%d\n",
print_tainted(), cachep->name,
realobj, size);
print_objinfo(cachep, objp, 0);
@@ -1650,13 +1647,13 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
if (objnr) {
objp = index_to_obj(cachep, page, objnr - 1);
realobj = (char *)objp + obj_offset(cachep);
- pr_err("Prev obj: start=%p, len=%d\n", realobj, size);
+ pr_err("Prev obj: start=%px, len=%d\n", realobj, size);
print_objinfo(cachep, objp, 2);
}
if (objnr + 1 < cachep->num) {
objp = index_to_obj(cachep, page, objnr + 1);
realobj = (char *)objp + obj_offset(cachep);
- pr_err("Next obj: start=%p, len=%d\n", realobj, size);
+ pr_err("Next obj: start=%px, len=%d\n", realobj, size);
print_objinfo(cachep, objp, 2);
}
}
@@ -2608,7 +2605,7 @@ static void slab_put_obj(struct kmem_cache *cachep,
/* Verify double free bug */
for (i = page->active; i < cachep->num; i++) {
if (get_free_obj(page, i) == objnr) {
- pr_err("slab: double free detected in cache '%s', objp %p\n",
+ pr_err("slab: double free detected in cache '%s', objp %px\n",
cachep->name, objp);
BUG();
}
@@ -2772,7 +2769,7 @@ static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
else
slab_error(cache, "memory outside object was overwritten");
- pr_err("%p: redzone 1:0x%llx, redzone 2:0x%llx\n",
+ pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n",
obj, redzone1, redzone2);
}
@@ -3078,7 +3075,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
if (*dbg_redzone1(cachep, objp) != RED_INACTIVE ||
*dbg_redzone2(cachep, objp) != RED_INACTIVE) {
slab_error(cachep, "double free, or memory outside object was overwritten");
- pr_err("%p: redzone 1:0x%llx, redzone 2:0x%llx\n",
+ pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n",
objp, *dbg_redzone1(cachep, objp),
*dbg_redzone2(cachep, objp));
}
@@ -3091,7 +3088,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
cachep->ctor(objp);
if (ARCH_SLAB_MINALIGN &&
((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) {
- pr_err("0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n",
+ pr_err("0x%px: not aligned to ARCH_SLAB_MINALIGN=%d\n",
objp, (int)ARCH_SLAB_MINALIGN);
}
return objp;
@@ -4283,7 +4280,7 @@ static void show_symbol(struct seq_file *m, unsigned long address)
return;
}
#endif
- seq_printf(m, "%p", (void *)address);
+ seq_printf(m, "%px", (void *)address);
}
static int leaks_show(struct seq_file *m, void *p)
diff --git a/mm/sparse.c b/mm/sparse.c
index 7a5dacaa06e3..2609aba121e8 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -211,7 +211,7 @@ void __init memory_present(int nid, unsigned long start, unsigned long end)
if (unlikely(!mem_section)) {
unsigned long size, align;
- size = sizeof(struct mem_section) * NR_SECTION_ROOTS;
+ size = sizeof(struct mem_section*) * NR_SECTION_ROOTS;
align = 1 << (INTERNODE_CACHE_SHIFT);
mem_section = memblock_virt_alloc(size, align);
}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 3074b02eaa09..42fe5653814a 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2697,7 +2697,7 @@ out:
}
#ifdef CONFIG_PROC_FS
-static unsigned swaps_poll(struct file *file, poll_table *wait)
+static __poll_t swaps_poll(struct file *file, poll_table *wait)
{
struct seq_file *seq = file->private_data;
diff --git a/mm/util.c b/mm/util.c
index 34e57fae959d..c1250501364f 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -150,18 +150,14 @@ EXPORT_SYMBOL(kmemdup_nul);
* @src: source address in user space
* @len: number of bytes to copy
*
- * Returns an ERR_PTR() on failure.
+ * Returns an ERR_PTR() on failure. Result is physically
+ * contiguous, to be freed by kfree().
*/
void *memdup_user(const void __user *src, size_t len)
{
void *p;
- /*
- * Always use GFP_KERNEL, since copy_from_user() can sleep and
- * cause pagefault, which makes it pointless to use GFP_NOFS
- * or GFP_ATOMIC.
- */
- p = kmalloc_track_caller(len, GFP_KERNEL);
+ p = kmalloc_track_caller(len, GFP_USER);
if (!p)
return ERR_PTR(-ENOMEM);
@@ -174,6 +170,32 @@ void *memdup_user(const void __user *src, size_t len)
}
EXPORT_SYMBOL(memdup_user);
+/**
+ * vmemdup_user - duplicate memory region from user space
+ *
+ * @src: source address in user space
+ * @len: number of bytes to copy
+ *
+ * Returns an ERR_PTR() on failure. Result may be not
+ * physically contiguous. Use kvfree() to free.
+ */
+void *vmemdup_user(const void __user *src, size_t len)
+{
+ void *p;
+
+ p = kvmalloc(len, GFP_USER);
+ if (!p)
+ return ERR_PTR(-ENOMEM);
+
+ if (copy_from_user(p, src, len)) {
+ kvfree(p);
+ return ERR_PTR(-EFAULT);
+ }
+
+ return p;
+}
+EXPORT_SYMBOL(vmemdup_user);
+
/*
* strndup_user - duplicate an existing string from user space
* @s: The string to duplicate
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c02c850ea349..47d5ced51f2d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -297,10 +297,13 @@ EXPORT_SYMBOL(register_shrinker);
*/
void unregister_shrinker(struct shrinker *shrinker)
{
+ if (!shrinker->nr_deferred)
+ return;
down_write(&shrinker_rwsem);
list_del(&shrinker->list);
up_write(&shrinker_rwsem);
kfree(shrinker->nr_deferred);
+ shrinker->nr_deferred = NULL;
}
EXPORT_SYMBOL(unregister_shrinker);
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 685049a9048d..683c0651098c 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -53,6 +53,7 @@
#include <linux/mount.h>
#include <linux/migrate.h>
#include <linux/pagemap.h>
+#include <linux/fs.h>
#define ZSPAGE_MAGIC 0x58
generated by cgit v1.2.3 (git 2.46.0) at 2025-09-07 05:29:12 +0000