summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c148
-rw-r--r--mm/huge_memory.c38
-rw-r--r--mm/memcontrol.c2
-rw-r--r--mm/memory_hotplug.c1
-rw-r--r--mm/mempolicy.c35
-rw-r--r--mm/page_io.c4
-rw-r--r--mm/page_poison.c6
-rw-r--r--mm/percpu.c2
-rw-r--r--mm/shmem.c2
9 files changed, 165 insertions, 73 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index 218d0b2ec82d..81adec8ee02c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2049,7 +2049,7 @@ find_page:
!mapping->a_ops->is_partially_uptodate)
goto page_not_up_to_date;
/* pipes can't handle partially uptodate pages */
- if (unlikely(iter->type & ITER_PIPE))
+ if (unlikely(iov_iter_is_pipe(iter)))
goto page_not_up_to_date;
if (!trylock_page(page))
goto page_not_up_to_date;
@@ -2825,6 +2825,42 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
EXPORT_SYMBOL(read_cache_page_gfp);
/*
+ * Don't operate on ranges the page cache doesn't support, and don't exceed the
+ * LFS limits. If pos is under the limit it becomes a short access. If it
+ * exceeds the limit we return -EFBIG.
+ */
+static int generic_access_check_limits(struct file *file, loff_t pos,
+ loff_t *count)
+{
+ struct inode *inode = file->f_mapping->host;
+ loff_t max_size = inode->i_sb->s_maxbytes;
+
+ if (!(file->f_flags & O_LARGEFILE))
+ max_size = MAX_NON_LFS;
+
+ if (unlikely(pos >= max_size))
+ return -EFBIG;
+ *count = min(*count, max_size - pos);
+ return 0;
+}
+
+static int generic_write_check_limits(struct file *file, loff_t pos,
+ loff_t *count)
+{
+ loff_t limit = rlimit(RLIMIT_FSIZE);
+
+ if (limit != RLIM_INFINITY) {
+ if (pos >= limit) {
+ send_sig(SIGXFSZ, current, 0);
+ return -EFBIG;
+ }
+ *count = min(*count, limit - pos);
+ }
+
+ return generic_access_check_limits(file, pos, count);
+}
+
+/*
* Performs necessary checks before doing a write
*
* Can adjust writing position or amount of bytes to write.
@@ -2835,8 +2871,8 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
- unsigned long limit = rlimit(RLIMIT_FSIZE);
- loff_t pos;
+ loff_t count;
+ int ret;
if (!iov_iter_count(from))
return 0;
@@ -2845,43 +2881,99 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
if (iocb->ki_flags & IOCB_APPEND)
iocb->ki_pos = i_size_read(inode);
- pos = iocb->ki_pos;
-
if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
return -EINVAL;
- if (limit != RLIM_INFINITY) {
- if (iocb->ki_pos >= limit) {
- send_sig(SIGXFSZ, current, 0);
- return -EFBIG;
- }
- iov_iter_truncate(from, limit - (unsigned long)pos);
- }
+ count = iov_iter_count(from);
+ ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+ if (ret)
+ return ret;
+
+ iov_iter_truncate(from, count);
+ return iov_iter_count(from);
+}
+EXPORT_SYMBOL(generic_write_checks);
+
+/*
+ * Performs necessary checks before doing a clone.
+ *
+ * Can adjust amount of bytes to clone.
+ * Returns appropriate error code that caller should return or
+ * zero in case the clone should be allowed.
+ */
+int generic_remap_checks(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t *req_count, unsigned int remap_flags)
+{
+ struct inode *inode_in = file_in->f_mapping->host;
+ struct inode *inode_out = file_out->f_mapping->host;
+ uint64_t count = *req_count;
+ uint64_t bcount;
+ loff_t size_in, size_out;
+ loff_t bs = inode_out->i_sb->s_blocksize;
+ int ret;
+
+ /* The start of both ranges must be aligned to an fs block. */
+ if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
+ return -EINVAL;
+
+ /* Ensure offsets don't wrap. */
+ if (pos_in + count < pos_in || pos_out + count < pos_out)
+ return -EINVAL;
+
+ size_in = i_size_read(inode_in);
+ size_out = i_size_read(inode_out);
+
+ /* Dedupe requires both ranges to be within EOF. */
+ if ((remap_flags & REMAP_FILE_DEDUP) &&
+ (pos_in >= size_in || pos_in + count > size_in ||
+ pos_out >= size_out || pos_out + count > size_out))
+ return -EINVAL;
+
+ /* Ensure the infile range is within the infile. */
+ if (pos_in >= size_in)
+ return -EINVAL;
+ count = min(count, size_in - (uint64_t)pos_in);
+
+ ret = generic_access_check_limits(file_in, pos_in, &count);
+ if (ret)
+ return ret;
+
+ ret = generic_write_check_limits(file_out, pos_out, &count);
+ if (ret)
+ return ret;
/*
- * LFS rule
+ * If the user wanted us to link to the infile's EOF, round up to the
+ * next block boundary for this check.
+ *
+ * Otherwise, make sure the count is also block-aligned, having
+ * already confirmed the starting offsets' block alignment.
*/
- if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS &&
- !(file->f_flags & O_LARGEFILE))) {
- if (pos >= MAX_NON_LFS)
- return -EFBIG;
- iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos);
+ if (pos_in + count == size_in) {
+ bcount = ALIGN(size_in, bs) - pos_in;
+ } else {
+ if (!IS_ALIGNED(count, bs))
+ count = ALIGN_DOWN(count, bs);
+ bcount = count;
}
+ /* Don't allow overlapped cloning within the same file. */
+ if (inode_in == inode_out &&
+ pos_out + bcount > pos_in &&
+ pos_out < pos_in + bcount)
+ return -EINVAL;
+
/*
- * Are we about to exceed the fs block limit ?
- *
- * If we have written data it becomes a short write. If we have
- * exceeded without writing data we send a signal and return EFBIG.
- * Linus frestrict idea will clean these up nicely..
+ * We shortened the request but the caller can't deal with that, so
+ * bounce the request back to userspace.
*/
- if (unlikely(pos >= inode->i_sb->s_maxbytes))
- return -EFBIG;
+ if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
+ return -EINVAL;
- iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos);
- return iov_iter_count(from);
+ *req_count = count;
+ return 0;
}
-EXPORT_SYMBOL(generic_write_checks);
int pagecache_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4e4ef8fa479d..55478ab3c83b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -629,21 +629,40 @@ release:
* available
* never: never stall for any thp allocation
*/
-static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
+static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr)
{
const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+ gfp_t this_node = 0;
+
+#ifdef CONFIG_NUMA
+ struct mempolicy *pol;
+ /*
+ * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not
+ * specified, to express a general desire to stay on the current
+ * node for optimistic allocation attempts. If the defrag mode
+ * and/or madvise hint requires the direct reclaim then we prefer
+ * to fallback to other node rather than node reclaim because that
+ * can lead to excessive reclaim even though there is free memory
+ * on other nodes. We expect that NUMA preferences are specified
+ * by memory policies.
+ */
+ pol = get_vma_policy(vma, addr);
+ if (pol->mode != MPOL_BIND)
+ this_node = __GFP_THISNODE;
+ mpol_cond_put(pol);
+#endif
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
- return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+ return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node;
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
- __GFP_KSWAPD_RECLAIM);
+ __GFP_KSWAPD_RECLAIM | this_node);
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
- 0);
- return GFP_TRANSHUGE_LIGHT;
+ this_node);
+ return GFP_TRANSHUGE_LIGHT | this_node;
}
/* Caller must hold page table lock. */
@@ -715,8 +734,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
pte_free(vma->vm_mm, pgtable);
return ret;
}
- gfp = alloc_hugepage_direct_gfpmask(vma);
- page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
+ gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+ page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id());
if (unlikely(!page)) {
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
@@ -1286,8 +1305,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
alloc:
if (transparent_hugepage_enabled(vma) &&
!transparent_hugepage_debug_cow()) {
- huge_gfp = alloc_hugepage_direct_gfpmask(vma);
- new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
+ huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+ new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma,
+ haddr, numa_node_id());
} else
new_page = NULL;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 54920cbc46bf..6e1469b80cb7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2593,7 +2593,7 @@ int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
struct mem_cgroup *memcg;
int ret = 0;
- if (memcg_kmem_bypass())
+ if (mem_cgroup_disabled() || memcg_kmem_bypass())
return 0;
memcg = get_mem_cgroup_from_current();
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 61972da38d93..2b2b3ccbbfb5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -586,6 +586,7 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
for (i = 0; i < sections_to_remove; i++) {
unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
+ cond_resched();
ret = __remove_section(zone, __pfn_to_section(pfn), map_offset,
altmap);
map_offset = 0;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index cfd26d7e61a1..5837a067124d 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1116,8 +1116,8 @@ static struct page *new_page(struct page *page, unsigned long start)
} else if (PageTransHuge(page)) {
struct page *thp;
- thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
- HPAGE_PMD_ORDER);
+ thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma,
+ address, numa_node_id());
if (!thp)
return NULL;
prep_transhuge_page(thp);
@@ -1662,7 +1662,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
* freeing by another task. It is the caller's responsibility to free the
* extra reference for shared policies.
*/
-static struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
unsigned long addr)
{
struct mempolicy *pol = __get_vma_policy(vma, addr);
@@ -2011,7 +2011,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
* @vma: Pointer to VMA or NULL if not available.
* @addr: Virtual Address of the allocation. Must be inside the VMA.
* @node: Which node to prefer for allocation (modulo policy).
- * @hugepage: for hugepages try only the preferred node if possible
*
* This function allocates a page from the kernel page pool and applies
* a NUMA policy associated with the VMA or the current process.
@@ -2022,7 +2021,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
*/
struct page *
alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
- unsigned long addr, int node, bool hugepage)
+ unsigned long addr, int node)
{
struct mempolicy *pol;
struct page *page;
@@ -2040,32 +2039,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
goto out;
}
- if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
- int hpage_node = node;
-
- /*
- * For hugepage allocation and non-interleave policy which
- * allows the current node (or other explicitly preferred
- * node) we only try to allocate from the current/preferred
- * node and don't fall back to other nodes, as the cost of
- * remote accesses would likely offset THP benefits.
- *
- * If the policy is interleave, or does not allow the current
- * node in its nodemask, we allocate the standard way.
- */
- if (pol->mode == MPOL_PREFERRED &&
- !(pol->flags & MPOL_F_LOCAL))
- hpage_node = pol->v.preferred_node;
-
- nmask = policy_nodemask(gfp, pol);
- if (!nmask || node_isset(hpage_node, *nmask)) {
- mpol_cond_put(pol);
- page = __alloc_pages_node(hpage_node,
- gfp | __GFP_THISNODE, order);
- goto out;
- }
- }
-
nmask = policy_nodemask(gfp, pol);
preferred_nid = policy_node(gfp, pol, node);
page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);
diff --git a/mm/page_io.c b/mm/page_io.c
index a451ffa9491c..d4d1c89bcddd 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -294,7 +294,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
};
struct iov_iter from;
- iov_iter_bvec(&from, ITER_BVEC | WRITE, &bv, 1, PAGE_SIZE);
+ iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE);
init_sync_kiocb(&kiocb, swap_file);
kiocb.ki_pos = page_file_offset(page);
@@ -339,7 +339,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
goto out;
}
bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc);
- bio_associate_blkg_from_page(bio, page);
+ bio_associate_blkcg_from_page(bio, page);
count_swpout_vm_event(page);
set_page_writeback(page);
unlock_page(page);
diff --git a/mm/page_poison.c b/mm/page_poison.c
index f7e2a676365a..f0c15e9017c0 100644
--- a/mm/page_poison.c
+++ b/mm/page_poison.c
@@ -17,6 +17,11 @@ static int __init early_page_poison_param(char *buf)
}
early_param("page_poison", early_page_poison_param);
+/**
+ * page_poisoning_enabled - check if page poisoning is enabled
+ *
+ * Return true if page poisoning is enabled, or false if not.
+ */
bool page_poisoning_enabled(void)
{
/*
@@ -29,6 +34,7 @@ bool page_poisoning_enabled(void)
(!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) &&
debug_pagealloc_enabled()));
}
+EXPORT_SYMBOL_GPL(page_poisoning_enabled);
static void poison_page(struct page *page)
{
diff --git a/mm/percpu.c b/mm/percpu.c
index a6b74c6fe0be..db86282fd024 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -2591,7 +2591,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
BUG_ON(ai->nr_groups != 1);
upa = ai->alloc_size/ai->unit_size;
nr_g0_units = roundup(num_possible_cpus(), upa);
- if (unlikely(WARN_ON(ai->groups[0].nr_units != nr_g0_units))) {
+ if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) {
pcpu_free_alloc_info(ai);
return -EINVAL;
}
diff --git a/mm/shmem.c b/mm/shmem.c
index 56bf122e0bb4..ea26d7a0342d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1435,7 +1435,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
shmem_pseudo_vma_init(&pvma, info, hindex);
page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN,
- HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true);
+ HPAGE_PMD_ORDER, &pvma, 0, numa_node_id());
shmem_pseudo_vma_destroy(&pvma);
if (page)
prep_transhuge_page(page);
generated by cgit (git 2.34.1) at 2025-06-08 10:26:23 +0000