summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/huge_memory.c12
-rw-r--r--mm/hugetlb.c6
-rw-r--r--mm/kasan/report.c3
-rw-r--r--mm/memblock.c24
-rw-r--r--mm/memory-failure.c8
-rw-r--r--mm/mempolicy.c20
-rw-r--r--mm/mlock.c5
-rw-r--r--mm/page_alloc.c25
-rw-r--r--mm/slub.c6
-rw-r--r--mm/truncate.c2
10 files changed, 82 insertions, 29 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 530e6427f823..47b469663822 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1269,6 +1269,16 @@ out_unlock:
return ret;
}
+/*
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
+ */
+static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
+{
+ return pmd_write(pmd) ||
+ ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+}
+
struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
unsigned long addr,
pmd_t *pmd,
@@ -1279,7 +1289,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
assert_spin_locked(pmd_lockptr(mm, pmd));
- if (flags & FOLL_WRITE && !pmd_write(*pmd))
+ if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags))
goto out;
/* Avoid dumping huge zero page */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ea11123a9249..7294301d8495 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4362,6 +4362,7 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
{
struct page *page = NULL;
spinlock_t *ptl;
+ pte_t pte;
retry:
ptl = pmd_lockptr(mm, pmd);
spin_lock(ptl);
@@ -4371,12 +4372,13 @@ retry:
*/
if (!pmd_huge(*pmd))
goto out;
- if (pmd_present(*pmd)) {
+ pte = huge_ptep_get((pte_t *)pmd);
+ if (pte_present(pte)) {
page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
if (flags & FOLL_GET)
get_page(page);
} else {
- if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) {
+ if (is_hugetlb_entry_migration(pte)) {
spin_unlock(ptl);
__migration_entry_wait(mm, (pte_t *)pmd, ptl);
goto retry;
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 12f222d0224b..b4e31f78ae69 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -13,6 +13,7 @@
*
*/
+#include <linux/ftrace.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/printk.h>
@@ -251,6 +252,8 @@ void kasan_report(unsigned long addr, size_t size,
if (likely(!kasan_report_enabled()))
return;
+ disable_trace_on_warning();
+
info.access_addr = (void *)addr;
info.access_size = size;
info.is_write = is_write;
diff --git a/mm/memblock.c b/mm/memblock.c
index d300f1329814..f8fab45bfdb7 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1634,6 +1634,30 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name
}
}
+extern unsigned long __init_memblock
+memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr)
+{
+ struct memblock_type *type = &memblock.reserved;
+ unsigned long size = 0;
+ int idx;
+
+ for (idx = 0; idx < type->cnt; idx++) {
+ struct memblock_region *rgn = &type->regions[idx];
+ phys_addr_t start, end;
+
+ if (rgn->base + rgn->size < start_addr)
+ continue;
+ if (rgn->base > end_addr)
+ continue;
+
+ start = rgn->base;
+ end = start + rgn->size;
+ size += end - start;
+ }
+
+ return size;
+}
+
void __init_memblock __memblock_dump_all(void)
{
pr_info("MEMBLOCK configuration:\n");
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 750b7893ee3a..43aee7ab143e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1619,12 +1619,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
if (ret) {
pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
pfn, ret, page->flags);
- /*
- * We know that soft_offline_huge_page() tries to migrate
- * only one hugepage pointed to by hpage, so we need not
- * run through the pagelist here.
- */
- putback_active_hugepage(hpage);
+ if (!list_empty(&pagelist))
+ putback_movable_pages(&pagelist);
if (ret > 0)
ret = -EIO;
} else {
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index a4217fe60dff..e09b1a0e2cfe 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1492,7 +1492,6 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
compat_ulong_t, maxnode)
{
- long err = 0;
unsigned long __user *nm = NULL;
unsigned long nr_bits, alloc_size;
DECLARE_BITMAP(bm, MAX_NUMNODES);
@@ -1501,14 +1500,13 @@ COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
if (nmask) {
- err = compat_get_bitmap(bm, nmask, nr_bits);
+ if (compat_get_bitmap(bm, nmask, nr_bits))
+ return -EFAULT;
nm = compat_alloc_user_space(alloc_size);
- err |= copy_to_user(nm, bm, alloc_size);
+ if (copy_to_user(nm, bm, alloc_size))
+ return -EFAULT;
}
- if (err)
- return -EFAULT;
-
return sys_set_mempolicy(mode, nm, nr_bits+1);
}
@@ -1516,7 +1514,6 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
compat_ulong_t, mode, compat_ulong_t __user *, nmask,
compat_ulong_t, maxnode, compat_ulong_t, flags)
{
- long err = 0;
unsigned long __user *nm = NULL;
unsigned long nr_bits, alloc_size;
nodemask_t bm;
@@ -1525,14 +1522,13 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
if (nmask) {
- err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
+ if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits))
+ return -EFAULT;
nm = compat_alloc_user_space(alloc_size);
- err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
+ if (copy_to_user(nm, nodes_addr(bm), alloc_size))
+ return -EFAULT;
}
- if (err)
- return -EFAULT;
-
return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
}
diff --git a/mm/mlock.c b/mm/mlock.c
index d6006b146fea..9d2e773f3a95 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -277,7 +277,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
{
int i;
int nr = pagevec_count(pvec);
- int delta_munlocked;
+ int delta_munlocked = -nr;
struct pagevec pvec_putback;
int pgrescued = 0;
@@ -297,6 +297,8 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
continue;
else
__munlock_isolation_failed(page);
+ } else {
+ delta_munlocked++;
}
/*
@@ -308,7 +310,6 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
pagevec_add(&pvec_putback, pvec->pages[i]);
pvec->pages[i] = NULL;
}
- delta_munlocked = -nr + pagevec_count(&pvec_putback);
__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
spin_unlock_irq(&zone->lru_lock);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6f9005dcca2e..bd17a6bdf131 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -269,6 +269,26 @@ int page_group_by_mobility_disabled __read_mostly;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static inline void reset_deferred_meminit(pg_data_t *pgdat)
{
+ unsigned long max_initialise;
+ unsigned long reserved_lowmem;
+
+ /*
+ * Initialise at least 2G of a node but also take into account that
+ * two large system hashes that can take up 1GB for 0.25TB/node.
+ */
+ max_initialise = max(2UL << (30 - PAGE_SHIFT),
+ (pgdat->node_spanned_pages >> 8));
+
+ /*
+ * Compensate the all the memblock reservations (e.g. crash kernel)
+ * from the initial estimation to make sure we will initialize enough
+ * memory to boot.
+ */
+ reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn,
+ pgdat->node_start_pfn + max_initialise);
+ max_initialise += reserved_lowmem;
+
+ pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages);
pgdat->first_deferred_pfn = ULONG_MAX;
}
@@ -302,10 +322,9 @@ static inline bool update_defer_init(pg_data_t *pgdat,
/* Always populate low zones for address-contrained allocations */
if (zone_end < pgdat_end_pfn(pgdat))
return true;
-
/* Initialise at least 2G of the highest zone */
(*nr_initialised)++;
- if (*nr_initialised > (2UL << (30 - PAGE_SHIFT)) &&
+ if ((*nr_initialised > pgdat->static_init_size) &&
(pfn & (PAGES_PER_SECTION - 1)) == 0) {
pgdat->first_deferred_pfn = pfn;
return false;
@@ -5343,7 +5362,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
/* pg_data_t should be reset to zero when it's allocated */
WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
- reset_deferred_meminit(pgdat);
pgdat->node_id = nid;
pgdat->node_start_pfn = node_start_pfn;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
@@ -5362,6 +5380,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
(unsigned long)pgdat->node_mem_map);
#endif
+ reset_deferred_meminit(pgdat);
free_area_init_core(pgdat);
}
diff --git a/mm/slub.c b/mm/slub.c
index 65d5f92d51d2..4cf3a9c768b1 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5261,6 +5261,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
char mbuf[64];
char *buf;
struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
+ ssize_t len;
if (!attr || !attr->store || !attr->show)
continue;
@@ -5285,8 +5286,9 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
buf = buffer;
}
- attr->show(root_cache, buf);
- attr->store(s, buf, strlen(buf));
+ len = attr->show(root_cache, buf);
+ if (len > 0)
+ attr->store(s, buf, len);
}
if (buffer)
diff --git a/mm/truncate.c b/mm/truncate.c
index 76e35ad97102..f4c8270f7b84 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -732,7 +732,7 @@ EXPORT_SYMBOL(truncate_setsize);
*/
void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
{
- int bsize = 1 << inode->i_blkbits;
+ int bsize = i_blocksize(inode);
loff_t rounded_from;
struct page *page;
pgoff_t index;
generated by cgit v1.2.3 (git 2.0.4) at 2024-05-12 12:18:53 +0000