summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/backing-dev.c17
-rw-r--r--mm/debug.c28
-rw-r--r--mm/early_ioremap.c2
-rw-r--r--mm/frame_vector.c14
-rw-r--r--mm/gup.c64
-rw-r--r--mm/huge_memory.c36
-rw-r--r--mm/hugetlb.c12
-rw-r--r--mm/kasan/report.c8
-rw-r--r--mm/kmemcheck.c1
-rw-r--r--mm/kmemleak.c4
-rw-r--r--mm/madvise.c4
-rw-r--r--mm/memcontrol.c2
-rw-r--r--mm/memory.c13
-rw-r--r--mm/mmap.c18
-rw-r--r--mm/mprotect.c6
-rw-r--r--mm/oom_kill.c11
-rw-r--r--mm/page-writeback.c5
-rw-r--r--mm/page_alloc.c26
-rw-r--r--mm/page_owner.c1
-rw-r--r--mm/percpu.c4
-rw-r--r--mm/shmem.c10
-rw-r--r--mm/slab.c23
-rw-r--r--mm/sparse.c2
-rw-r--r--mm/vmscan.c3
-rw-r--r--mm/zsmalloc.c1
25 files changed, 218 insertions, 97 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 74b52dfd5852..b5f940ce0143 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -113,11 +113,23 @@ static const struct file_operations bdi_debug_stats_fops = {
.release = single_release,
};
-static void bdi_debug_register(struct backing_dev_info *bdi, const char *name)
+static int bdi_debug_register(struct backing_dev_info *bdi, const char *name)
{
+ if (!bdi_debug_root)
+ return -ENOMEM;
+
bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root);
+ if (!bdi->debug_dir)
+ return -ENOMEM;
+
bdi->debug_stats = debugfs_create_file("stats", 0444, bdi->debug_dir,
bdi, &bdi_debug_stats_fops);
+ if (!bdi->debug_stats) {
+ debugfs_remove(bdi->debug_dir);
+ return -ENOMEM;
+ }
+
+ return 0;
}
static void bdi_debug_unregister(struct backing_dev_info *bdi)
@@ -129,9 +141,10 @@ static void bdi_debug_unregister(struct backing_dev_info *bdi)
static inline void bdi_debug_init(void)
{
}
-static inline void bdi_debug_register(struct backing_dev_info *bdi,
+static inline int bdi_debug_register(struct backing_dev_info *bdi,
const char *name)
{
+ return 0;
}
static inline void bdi_debug_unregister(struct backing_dev_info *bdi)
{
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 2f98df0d460e..c64dca6e27c2 100644
--- a/mm/frame_vector.c
+++ b/mm/frame_vector.c
@@ -53,6 +53,20 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
ret = -EFAULT;
goto out;
}
+
+ /*
+ * While get_vaddr_frames() could be used for transient (kernel
+ * controlled lifetime) pinning of memory pages all current
+ * users establish long term (userspace controlled lifetime)
+ * page pinning. Treat get_vaddr_frames() like
+ * get_user_pages_longterm() and disallow it for filesystem-dax
+ * mappings.
+ */
+ if (vma_is_fsdax(vma)) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) {
vec->got_ref = true;
vec->is_pfns = false;
diff --git a/mm/gup.c b/mm/gup.c
index dfcde13f289a..e0d82b6706d7 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1095,6 +1095,70 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
}
EXPORT_SYMBOL(get_user_pages);
+#ifdef CONFIG_FS_DAX
+/*
+ * This is the same as get_user_pages() in that it assumes we are
+ * operating on the current task's mm, but it goes further to validate
+ * that the vmas associated with the address range are suitable for
+ * longterm elevated page reference counts. For example, filesystem-dax
+ * mappings are subject to the lifetime enforced by the filesystem and
+ * we need guarantees that longterm users like RDMA and V4L2 only
+ * establish mappings that have a kernel enforced revocation mechanism.
+ *
+ * "longterm" == userspace controlled elevated page count lifetime.
+ * Contrast this to iov_iter_get_pages() usages which are transient.
+ */
+long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas_arg)
+{
+ struct vm_area_struct **vmas = vmas_arg;
+ struct vm_area_struct *vma_prev = NULL;
+ long rc, i;
+
+ if (!pages)
+ return -EINVAL;
+
+ if (!vmas) {
+ vmas = kcalloc(nr_pages, sizeof(struct vm_area_struct *),
+ GFP_KERNEL);
+ if (!vmas)
+ return -ENOMEM;
+ }
+
+ rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+
+ for (i = 0; i < rc; i++) {
+ struct vm_area_struct *vma = vmas[i];
+
+ if (vma == vma_prev)
+ continue;
+
+ vma_prev = vma;
+
+ if (vma_is_fsdax(vma))
+ break;
+ }
+
+ /*
+ * Either get_user_pages() failed, or the vma validation
+ * succeeded, in either case we don't need to put_page() before
+ * returning.
+ */
+ if (i >= rc)
+ goto out;
+
+ for (i = 0; i < rc; i++)
+ put_page(pages[i]);
+ rc = -EOPNOTSUPP;
+out:
+ if (vmas != vmas_arg)
+ kfree(vmas);
+ return rc;
+}
+EXPORT_SYMBOL(get_user_pages_longterm);
+#endif /* CONFIG_FS_DAX */
+
/**
* populate_vma_page_range() - populate a range of pages in the vma.
* @vma: target vma
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 86fe697e8bfb..0e7ded98d114 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -842,20 +842,15 @@ EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd)
+ pmd_t *pmd, int flags)
{
pmd_t _pmd;
- /*
- * We should set the dirty bit only for FOLL_WRITE but for now
- * the dirty bit in the pmd is meaningless. And if the dirty
- * bit will become meaningful and we'll only set it with
- * FOLL_WRITE, an atomic set_bit will be required on the pmd to
- * set the young bit, instead of the current set_pmd_at.
- */
- _pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
+ _pmd = pmd_mkyoung(*pmd);
+ if (flags & FOLL_WRITE)
+ _pmd = pmd_mkdirty(_pmd);
if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
- pmd, _pmd, 1))
+ pmd, _pmd, flags & FOLL_WRITE))
update_mmu_cache_pmd(vma, addr, pmd);
}
@@ -884,7 +879,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
return NULL;
if (flags & FOLL_TOUCH)
- touch_pmd(vma, addr, pmd);
+ touch_pmd(vma, addr, pmd, flags);
/*
* device mapped pages can only be returned if the
@@ -995,20 +990,15 @@ out:
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static void touch_pud(struct vm_area_struct *vma, unsigned long addr,
- pud_t *pud)
+ pud_t *pud, int flags)
{
pud_t _pud;
- /*
- * We should set the dirty bit only for FOLL_WRITE but for now
- * the dirty bit in the pud is meaningless. And if the dirty
- * bit will become meaningful and we'll only set it with
- * FOLL_WRITE, an atomic set_bit will be required on the pud to
- * set the young bit, instead of the current set_pud_at.
- */
- _pud = pud_mkyoung(pud_mkdirty(*pud));
+ _pud = pud_mkyoung(*pud);
+ if (flags & FOLL_WRITE)
+ _pud = pud_mkdirty(_pud);
if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK,
- pud, _pud, 1))
+ pud, _pud, flags & FOLL_WRITE))
update_mmu_cache_pud(vma, addr, pud);
}
@@ -1031,7 +1021,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
return NULL;
if (flags & FOLL_TOUCH)
- touch_pud(vma, addr, pud);
+ touch_pud(vma, addr, pud, flags);
/*
* device mapped pages can only be returned if the
@@ -1424,7 +1414,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
page = pmd_page(*pmd);
VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
if (flags & FOLL_TOUCH)
- touch_pmd(vma, addr, pmd);
+ touch_pmd(vma, addr, pmd, flags);
if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
/*
* We don't mlock() pte-mapped THPs. This way we can avoid
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 681b300185c0..9a334f5fb730 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3125,6 +3125,13 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
}
}
+static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
+{
+ if (addr & ~(huge_page_mask(hstate_vma(vma))))
+ return -EINVAL;
+ return 0;
+}
+
/*
* We cannot handle pagefaults against hugetlb pages at all. They cause
* handle_mm_fault() to try to instantiate regular-sized pages in the
@@ -3141,6 +3148,7 @@ const struct vm_operations_struct hugetlb_vm_ops = {
.fault = hugetlb_vm_op_fault,
.open = hugetlb_vm_op_open,
.close = hugetlb_vm_op_close,
+ .split = hugetlb_vm_op_split,
};
static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
@@ -4627,7 +4635,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
pte_t *pte = NULL;
pgd = pgd_offset(mm, addr);
- p4d = p4d_offset(pgd, addr);
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return NULL;
pud = pud_alloc(mm, p4d, addr);
if (pud) {
if (sz == PUD_SIZE) {
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 6bcfb01ba038..410c8235e671 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -134,7 +134,7 @@ static void print_error_description(struct kasan_access_info *info)
pr_err("BUG: KASAN: %s in %pS\n",
bug_type, (void *)info->ip);
- pr_err("%s of size %zu at addr %p by task %s/%d\n",
+ pr_err("%s of size %zu at addr %px by task %s/%d\n",
info->is_write ? "Write" : "Read", info->access_size,
info->access_addr, current->comm, task_pid_nr(current));
}
@@ -206,7 +206,7 @@ static void describe_object_addr(struct kmem_cache *cache, void *object,
const char *rel_type;
int rel_bytes;
- pr_err("The buggy address belongs to the object at %p\n"
+ pr_err("The buggy address belongs to the object at %px\n"
" which belongs to the cache %s of size %d\n",
object, cache->name, cache->object_size);
@@ -225,7 +225,7 @@ static void describe_object_addr(struct kmem_cache *cache, void *object,
}
pr_err("The buggy address is located %d bytes %s of\n"
- " %d-byte region [%p, %p)\n",
+ " %d-byte region [%px, %px)\n",
rel_bytes, rel_type, cache->object_size, (void *)object_addr,
(void *)(object_addr + cache->object_size));
}
@@ -302,7 +302,7 @@ static void print_shadow_for_address(const void *addr)
char shadow_buf[SHADOW_BYTES_PER_ROW];
snprintf(buffer, sizeof(buffer),
- (i == 0) ? ">%p: " : " %p: ", kaddr);
+ (i == 0) ? ">%px: " : " %px: ", kaddr);
/*
* We should not pass a shadow pointer to generic
* function, because generic functions may try to
diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c
deleted file mode 100644
index cec594032515..000000000000
--- a/mm/kmemcheck.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index e4738d5e9b8c..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 {
@@ -1523,6 +1523,8 @@ static void kmemleak_scan(void)
if (page_count(page) == 0)
continue;
scan_block(page, page + 1, NULL);
+ if (!(pfn & 63))
+ cond_resched();
}
}
put_online_mems();
diff --git a/mm/madvise.c b/mm/madvise.c
index 375cf32087e4..751e97aa2210 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -276,15 +276,14 @@ static long madvise_willneed(struct vm_area_struct *vma,
{
struct file *file = vma->vm_file;
+ *prev = vma;
#ifdef CONFIG_SWAP
if (!file) {
- *prev = vma;
force_swapin_readahead(vma, start, end);
return 0;
}
if (shmem_mapping(file->f_mapping)) {
- *prev = vma;
force_shm_swapin_readahead(vma, start, end,
file->f_mapping);
return 0;
@@ -299,7 +298,6 @@ static long madvise_willneed(struct vm_area_struct *vma,
return 0;
}
- *prev = vma;
start = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
if (end > vma->vm_end)
end = vma->vm_end;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 50e6906314f8..ac2ffd5e02b9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6044,7 +6044,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
memcg_check_events(memcg, page);
if (!mem_cgroup_is_root(memcg))
- css_put(&memcg->css);
+ css_put_many(&memcg->css, nr_entries);
}
/**
diff --git a/mm/memory.c b/mm/memory.c
index 85e7a87da79f..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);
diff --git a/mm/mmap.c b/mm/mmap.c
index 924839fac0e6..9efdc021ad22 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2555,9 +2555,11 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *new;
int err;
- if (is_vm_hugetlb_page(vma) && (addr &
- ~(huge_page_mask(hstate_vma(vma)))))
- return -EINVAL;
+ if (vma->vm_ops && vma->vm_ops->split) {
+ err = vma->vm_ops->split(vma, addr);
+ if (err)
+ return err;
+ }
new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
if (!new)
@@ -3017,20 +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 c86fbd1b590e..29f855551efe 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -550,7 +550,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
*/
set_bit(MMF_UNSTABLE, &mm->flags);
- tlb_gather_mmu(&tlb, mm, 0, -1);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
if (!can_madv_dontneed_vma(vma))
continue;
@@ -565,11 +564,13 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
* we do not want to block exit_mmap by keeping mm ref
* count elevated without a good reason.
*/
- if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED))
+ if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
+ tlb_gather_mmu(&tlb, mm, vma->vm_start, vma->vm_end);
unmap_page_range(&tlb, vma, vma->vm_start, vma->vm_end,
NULL);
+ tlb_finish_mmu(&tlb, vma->vm_start, vma->vm_end);
+ }
}
- tlb_finish_mmu(&tlb, 0, -1);
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
@@ -682,8 +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-writeback.c b/mm/page-writeback.c
index e7095030aa1f..586f31261c83 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -433,11 +433,8 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
else
bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
- if (unlikely(bg_thresh >= thresh)) {
- pr_warn("vm direct limit must be set greater than background limit.\n");
+ if (bg_thresh >= thresh)
bg_thresh = thresh / 2;
- }
-
tsk = current;
if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d4096f4a5c1f..76c9688b6a0a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2507,10 +2507,6 @@ void drain_all_pages(struct zone *zone)
if (WARN_ON_ONCE(!mm_percpu_wq))
return;
- /* Workqueues cannot recurse */
- if (current->flags & PF_WQ_WORKER)
- return;
-
/*
* Do not drain if one is already in progress unless it's specific to
* a zone. Such callers are primarily CMA and memory hotplug and need
@@ -2688,6 +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) {
@@ -2704,6 +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);
}
@@ -6253,6 +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++;
}
@@ -7656,11 +7665,18 @@ int alloc_contig_range(unsigned long start, unsigned long end,
/*
* In case of -EBUSY, we'd like to know which page causes problem.
- * So, just fall through. We will check it in test_pages_isolated().
+ * So, just fall through. test_pages_isolated() has a tracepoint
+ * which will report the busy page.
+ *
+ * It is possible that busy pages could become available before
+ * the call to test_pages_isolated, and the range will actually be
+ * allocated. So, if we fall through be sure to clear ret so that
+ * -EBUSY is not accidentally used or returned to caller.
*/
ret = __alloc_contig_migrate_range(&cc, start, end);
if (ret && ret != -EBUSY)
goto done;
+ ret =0;
/*
* Pages from [start, end) are within a MAX_ORDER_NR_PAGES
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/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/shmem.c b/mm/shmem.c
index 4aa9307feab0..7fbe67be86fa 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3776,7 +3776,7 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent)
* tmpfs instance, limiting inodes to one per page of lowmem;
* but the internal instance is left unlimited.
*/
- if (!(sb->s_flags & MS_KERNMOUNT)) {
+ if (!(sb->s_flags & SB_KERNMOUNT)) {
sbinfo->max_blocks = shmem_default_max_blocks();
sbinfo->max_inodes = shmem_default_max_inodes();
if (shmem_parse_options(data, sbinfo, false)) {
@@ -3784,12 +3784,12 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent)
goto failed;
}
} else {
- sb->s_flags |= MS_NOUSER;
+ sb->s_flags |= SB_NOUSER;
}
sb->s_export_op = &shmem_export_ops;
- sb->s_flags |= MS_NOSEC;
+ sb->s_flags |= SB_NOSEC;
#else
- sb->s_flags |= MS_NOUSER;
+ sb->s_flags |= SB_NOUSER;
#endif
spin_lock_init(&sbinfo->stat_lock);
@@ -3809,7 +3809,7 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent)
sb->s_xattr = shmem_xattr_handlers;
#endif
#ifdef CONFIG_TMPFS_POSIX_ACL
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
#endif
uuid_gen(&sb->s_uuid);
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/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 2.25.1) at 2024-06-02 11:09:42 +0000