summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/huge_memory.c9
-rw-r--r--mm/hugetlb.c7
-rw-r--r--mm/khugepaged.c15
-rw-r--r--mm/memblock.c28
-rw-r--r--mm/mempolicy.c3
-rw-r--r--mm/page_alloc.c13
-rw-r--r--mm/shmem.c31
-rw-r--r--mm/vmscan.c31
8 files changed, 66 insertions, 71 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 87ab9b8f56b5..5a68730eebd6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -555,7 +555,8 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
VM_BUG_ON_PAGE(!PageCompound(page), page);
- if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) {
+ if (mem_cgroup_try_charge(page, vma->vm_mm, gfp | __GFP_NORETRY, &memcg,
+ true)) {
put_page(page);
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
@@ -1316,7 +1317,7 @@ alloc:
}
if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm,
- huge_gfp, &memcg, true))) {
+ huge_gfp | __GFP_NORETRY, &memcg, true))) {
put_page(new_page);
split_huge_pmd(vma, vmf->pmd, vmf->address);
if (page)
@@ -2783,11 +2784,13 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
list_for_each_safe(pos, next, &list) {
page = list_entry((void *)pos, struct page, mapping);
- lock_page(page);
+ if (!trylock_page(page))
+ goto next;
/* split_huge_page() removes page from list on success */
if (!split_huge_page(page))
split++;
unlock_page(page);
+next:
put_page(page);
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a963f2034dfc..976bbc5646fe 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -18,6 +18,7 @@
#include <linux/bootmem.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
+#include <linux/mmdebug.h>
#include <linux/sched/signal.h>
#include <linux/rmap.h>
#include <linux/string_helpers.h>
@@ -4374,6 +4375,12 @@ int hugetlb_reserve_pages(struct inode *inode,
struct resv_map *resv_map;
long gbl_reserve;
+ /* This should never happen */
+ if (from > to) {
+ VM_WARN(1, "%s called with a negative range\n", __func__);
+ return -EINVAL;
+ }
+
/*
* Only apply hugepage reservation if asked. At fault time, an
* attempt will be made for VM_NORESERVE to allocate a page
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b7e2268dfc9a..e42568284e06 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -530,7 +530,12 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
goto out;
}
- VM_BUG_ON_PAGE(PageCompound(page), page);
+ /* TODO: teach khugepaged to collapse THP mapped with pte */
+ if (PageCompound(page)) {
+ result = SCAN_PAGE_COMPOUND;
+ goto out;
+ }
+
VM_BUG_ON_PAGE(!PageAnon(page), page);
/*
@@ -960,7 +965,9 @@ static void collapse_huge_page(struct mm_struct *mm,
goto out_nolock;
}
- if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {
+ /* Do not oom kill for khugepaged charges */
+ if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY,
+ &memcg, true))) {
result = SCAN_CGROUP_CHARGE_FAIL;
goto out_nolock;
}
@@ -1319,7 +1326,9 @@ static void collapse_shmem(struct mm_struct *mm,
goto out;
}
- if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {
+ /* Do not oom kill for khugepaged charges */
+ if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY,
+ &memcg, true))) {
result = SCAN_CGROUP_CHARGE_FAIL;
goto out;
}
diff --git a/mm/memblock.c b/mm/memblock.c
index b6ba6b7adadc..48376bd33274 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1101,34 +1101,6 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid,
*out_nid = r->nid;
}
-unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn,
- unsigned long max_pfn)
-{
- struct memblock_type *type = &memblock.memory;
- unsigned int right = type->cnt;
- unsigned int mid, left = 0;
- phys_addr_t addr = PFN_PHYS(++pfn);
-
- do {
- mid = (right + left) / 2;
-
- if (addr < type->regions[mid].base)
- right = mid;
- else if (addr >= (type->regions[mid].base +
- type->regions[mid].size))
- left = mid + 1;
- else {
- /* addr is within the region, so pfn is valid */
- return pfn;
- }
- } while (left < right);
-
- if (right == type->cnt)
- return -1UL;
- else
- return PHYS_PFN(type->regions[right].base);
-}
-
/**
* memblock_set_node - set node ID on memblock regions
* @base: base of area to set node ID for
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d879f1d8a44a..32cba0332787 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2124,6 +2124,9 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
case MPOL_INTERLEAVE:
return !!nodes_equal(a->v.nodes, b->v.nodes);
case MPOL_PREFERRED:
+ /* a's ->flags is the same as b's */
+ if (a->flags & MPOL_F_LOCAL)
+ return true;
return a->v.preferred_node == b->v.preferred_node;
default:
BUG();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 635d7dd29d7f..1741dd23e7c1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3596,7 +3596,7 @@ static bool __need_fs_reclaim(gfp_t gfp_mask)
return false;
/* this guy won't enter reclaim */
- if ((current->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC))
+ if (current->flags & PF_MEMALLOC)
return false;
/* We're only interested __GFP_FS allocations for now */
@@ -5356,17 +5356,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
if (context != MEMMAP_EARLY)
goto not_early;
- if (!early_pfn_valid(pfn)) {
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
- /*
- * Skip to the pfn preceding the next valid one (or
- * end_pfn), such that we hit a valid pfn (or end_pfn)
- * on our next iteration of the loop.
- */
- pfn = memblock_next_valid_pfn(pfn, end_pfn) - 1;
-#endif
+ if (!early_pfn_valid(pfn))
continue;
- }
if (!early_pfn_in_nid(pfn, nid))
continue;
if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised))
diff --git a/mm/shmem.c b/mm/shmem.c
index 1907688b75ee..b85919243399 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -493,36 +493,45 @@ next:
info = list_entry(pos, struct shmem_inode_info, shrinklist);
inode = &info->vfs_inode;
- if (nr_to_split && split >= nr_to_split) {
- iput(inode);
- continue;
- }
+ if (nr_to_split && split >= nr_to_split)
+ goto leave;
- page = find_lock_page(inode->i_mapping,
+ page = find_get_page(inode->i_mapping,
(inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT);
if (!page)
goto drop;
+ /* No huge page at the end of the file: nothing to split */
if (!PageTransHuge(page)) {
- unlock_page(page);
put_page(page);
goto drop;
}
+ /*
+ * Leave the inode on the list if we failed to lock
+ * the page at this time.
+ *
+ * Waiting for the lock may lead to deadlock in the
+ * reclaim path.
+ */
+ if (!trylock_page(page)) {
+ put_page(page);
+ goto leave;
+ }
+
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
- if (ret) {
- /* split failed: leave it on the list */
- iput(inode);
- continue;
- }
+ /* If split failed leave the inode on the list */
+ if (ret)
+ goto leave;
split++;
drop:
list_del_init(&info->shrinklist);
removed++;
+leave:
iput(inode);
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bee53495a829..cd5dc3faaa57 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1780,6 +1780,20 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
set_bit(PGDAT_WRITEBACK, &pgdat->flags);
/*
+ * If dirty pages are scanned that are not queued for IO, it
+ * implies that flushers are not doing their job. This can
+ * happen when memory pressure pushes dirty pages to the end of
+ * the LRU before the dirty limits are breached and the dirty
+ * data has expired. It can also happen when the proportion of
+ * dirty pages grows not through writes but through memory
+ * pressure reclaiming all the clean cache. And in some cases,
+ * the flushers simply cannot keep up with the allocation
+ * rate. Nudge the flusher threads in case they are asleep.
+ */
+ if (stat.nr_unqueued_dirty == nr_taken)
+ wakeup_flusher_threads(WB_REASON_VMSCAN);
+
+ /*
* Legacy memcg will stall in page writeback so avoid forcibly
* stalling here.
*/
@@ -1791,22 +1805,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
if (stat.nr_dirty && stat.nr_dirty == stat.nr_congested)
set_bit(PGDAT_CONGESTED, &pgdat->flags);
- /*
- * If dirty pages are scanned that are not queued for IO, it
- * implies that flushers are not doing their job. This can
- * happen when memory pressure pushes dirty pages to the end of
- * the LRU before the dirty limits are breached and the dirty
- * data has expired. It can also happen when the proportion of
- * dirty pages grows not through writes but through memory
- * pressure reclaiming all the clean cache. And in some cases,
- * the flushers simply cannot keep up with the allocation
- * rate. Nudge the flusher threads in case they are asleep, but
- * also allow kswapd to start writing pages during reclaim.
- */
- if (stat.nr_unqueued_dirty == nr_taken) {
- wakeup_flusher_threads(WB_REASON_VMSCAN);
+ /* Allow kswapd to start writing pages during reclaim. */
+ if (stat.nr_unqueued_dirty == nr_taken)
set_bit(PGDAT_DIRTY, &pgdat->flags);
- }
/*
* If kswapd scans pages marked marked for immediate
generated by cgit v1.2.1 (git 2.18.0) at 2025-04-10 09:57:31 +0000