summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAndrew Morton <akpm@linux-foundation.org>2023-10-18 14:32:58 -0700
committerAndrew Morton <akpm@linux-foundation.org>2023-10-18 14:32:58 -0700
commit5ef8f1b2b4d9bd02e4104b9255351fb9279b1b4e (patch)
tree415dc49e56338e498bff9a3b0c5b99b049890e14
parentb0540208a59e11ab55c9b857bf521d8846e515bf (diff)
parentfc7f04dc23db50206bee7891516ed4726c3f64cf (diff)
Merge mm-hotfixes-stable into mm-stable to pick up depended-upon changes.
-rw-r--r--.mailmap6
-rw-r--r--MAINTAINERS2
-rw-r--r--arch/riscv/mm/fault.c2
-rw-r--r--arch/riscv/mm/hugetlbpage.c19
-rw-r--r--include/linux/hugetlb.h41
-rw-r--r--include/linux/kasan.h6
-rw-r--r--lib/maple_tree.c2
-rw-r--r--lib/test_maple_tree.c35
-rw-r--r--mm/damon/sysfs.c7
-rw-r--r--mm/hugetlb.c82
-rw-r--r--mm/kasan/report.c2
-rw-r--r--mm/memory.c13
-rw-r--r--mm/mempolicy.c4
-rw-r--r--mm/migrate.c14
-rw-r--r--mm/mmap.c46
-rw-r--r--mm/page_alloc.c2
-rw-r--r--mm/zswap.c4
-rw-r--r--tools/include/linux/rwsem.h40
-rw-r--r--tools/testing/selftests/clone3/clone3.c7
-rw-r--r--tools/testing/selftests/mm/mremap_dontunmap.c1
20 files changed, 261 insertions, 74 deletions
diff --git a/.mailmap b/.mailmap
index a0a6efe87186..f56aafbc75be 100644
--- a/.mailmap
+++ b/.mailmap
@@ -87,6 +87,7 @@ Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang@unisoc.com>
Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang7@gmail.com>
Bart Van Assche <bvanassche@acm.org> <bart.vanassche@sandisk.com>
Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com>
+Bartosz Golaszewski <brgl@bgdev.pl> <bgolaszewski@baylibre.com>
Ben Dooks <ben-linux@fluff.org> <ben.dooks@simtec.co.uk>
Ben Dooks <ben-linux@fluff.org> <ben.dooks@sifive.com>
Ben Gardner <bgardner@wabtec.com>
@@ -449,9 +450,10 @@ Oleksandr Natalenko <oleksandr@natalenko.name> <oleksandr@redhat.com>
Oleksij Rempel <linux@rempel-privat.de> <bug-track@fisher-privat.net>
Oleksij Rempel <linux@rempel-privat.de> <external.Oleksij.Rempel@de.bosch.com>
Oleksij Rempel <linux@rempel-privat.de> <fixed-term.Oleksij.Rempel@de.bosch.com>
-Oleksij Rempel <linux@rempel-privat.de> <o.rempel@pengutronix.de>
-Oleksij Rempel <linux@rempel-privat.de> <ore@pengutronix.de>
+Oleksij Rempel <o.rempel@pengutronix.de>
+Oleksij Rempel <o.rempel@pengutronix.de> <ore@pengutronix.de>
Oliver Upton <oliver.upton@linux.dev> <oupton@google.com>
+Ondřej Jirman <megi@xff.cz> <megous@megous.com>
Oza Pawandeep <quic_poza@quicinc.com> <poza@codeaurora.org>
Pali Rohár <pali@kernel.org> <pali.rohar@gmail.com>
Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
diff --git a/MAINTAINERS b/MAINTAINERS
index 35977b269d5e..68ff5b62a1d2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6748,7 +6748,7 @@ F: drivers/gpu/drm/panel/panel-sitronix-st7701.c
DRM DRIVER FOR SITRONIX ST7703 PANELS
M: Guido Günther <agx@sigxcpu.org>
R: Purism Kernel Team <kernel@puri.sm>
-R: Ondrej Jirman <megous@megous.com>
+R: Ondrej Jirman <megi@xff.cz>
S: Maintained
F: Documentation/devicetree/bindings/display/panel/rocktech,jh057n00900.yaml
F: drivers/gpu/drm/panel/panel-sitronix-st7703.c
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 6115d7514972..90d4ba36d1d0 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -72,7 +72,7 @@ static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_f
}
pagefault_out_of_memory();
return;
- } else if (fault & VM_FAULT_SIGBUS) {
+ } else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) {
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs)) {
no_context(regs, addr);
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index e4a2ace92dbe..b52f0210481f 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -183,15 +183,22 @@ void set_huge_pte_at(struct mm_struct *mm,
pte_t pte,
unsigned long sz)
{
+ unsigned long hugepage_shift;
int i, pte_num;
- if (!pte_napot(pte)) {
- set_pte_at(mm, addr, ptep, pte);
- return;
- }
+ if (sz >= PGDIR_SIZE)
+ hugepage_shift = PGDIR_SHIFT;
+ else if (sz >= P4D_SIZE)
+ hugepage_shift = P4D_SHIFT;
+ else if (sz >= PUD_SIZE)
+ hugepage_shift = PUD_SHIFT;
+ else if (sz >= PMD_SIZE)
+ hugepage_shift = PMD_SHIFT;
+ else
+ hugepage_shift = PAGE_SHIFT;
- pte_num = napot_pte_num(napot_cont_order(pte));
- for (i = 0; i < pte_num; i++, ptep++, addr += PAGE_SIZE)
+ pte_num = sz >> hugepage_shift;
+ for (i = 0; i < pte_num; i++, ptep++, addr += (1 << hugepage_shift))
set_pte_at(mm, addr, ptep, pte);
}
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d935b0584f1d..e5b9f7e62eeb 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -60,6 +60,7 @@ struct resv_map {
long adds_in_progress;
struct list_head region_cache;
long region_cache_count;
+ struct rw_semaphore rw_sema;
#ifdef CONFIG_CGROUP_HUGETLB
/*
* On private mappings, the counter to uncharge reservations is stored
@@ -138,7 +139,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
void unmap_hugepage_range(struct vm_area_struct *,
unsigned long, unsigned long, struct page *,
zap_flags_t);
-void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+void __unmap_hugepage_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct page *ref_page, zap_flags_t zap_flags);
@@ -245,6 +246,25 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
unsigned long *start, unsigned long *end);
+extern void __hugetlb_zap_begin(struct vm_area_struct *vma,
+ unsigned long *begin, unsigned long *end);
+extern void __hugetlb_zap_end(struct vm_area_struct *vma,
+ struct zap_details *details);
+
+static inline void hugetlb_zap_begin(struct vm_area_struct *vma,
+ unsigned long *start, unsigned long *end)
+{
+ if (is_vm_hugetlb_page(vma))
+ __hugetlb_zap_begin(vma, start, end);
+}
+
+static inline void hugetlb_zap_end(struct vm_area_struct *vma,
+ struct zap_details *details)
+{
+ if (is_vm_hugetlb_page(vma))
+ __hugetlb_zap_end(vma, details);
+}
+
void hugetlb_vma_lock_read(struct vm_area_struct *vma);
void hugetlb_vma_unlock_read(struct vm_area_struct *vma);
void hugetlb_vma_lock_write(struct vm_area_struct *vma);
@@ -296,6 +316,18 @@ static inline void adjust_range_if_pmd_sharing_possible(
{
}
+static inline void hugetlb_zap_begin(
+ struct vm_area_struct *vma,
+ unsigned long *start, unsigned long *end)
+{
+}
+
+static inline void hugetlb_zap_end(
+ struct vm_area_struct *vma,
+ struct zap_details *details)
+{
+}
+
static inline struct page *hugetlb_follow_page_mask(
struct vm_area_struct *vma, unsigned long address, unsigned int flags,
unsigned int *page_mask)
@@ -441,7 +473,7 @@ static inline long hugetlb_change_protection(
return 0;
}
-static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page,
zap_flags_t zap_flags)
@@ -1245,6 +1277,11 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
}
+static inline bool __vma_private_lock(struct vm_area_struct *vma)
+{
+ return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
+}
+
/*
* Safe version of huge_pte_offset() to check the locks. See comments
* above huge_pte_offset().
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 842623d708c2..71fa9a40fb5a 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -466,10 +466,10 @@ static inline void kasan_free_module_shadow(const struct vm_struct *vm) {}
#endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */
-#ifdef CONFIG_KASAN_INLINE
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
void kasan_non_canonical_hook(unsigned long addr);
-#else /* CONFIG_KASAN_INLINE */
+#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
static inline void kasan_non_canonical_hook(unsigned long addr) { }
-#endif /* CONFIG_KASAN_INLINE */
+#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
#endif /* LINUX_KASAN_H */
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 0e00a84e8e8f..bb24d84a4922 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -5627,7 +5627,7 @@ int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries)
/* Internal nodes */
nr_nodes += DIV_ROUND_UP(nr_nodes, nonleaf_cap);
/* Add working room for split (2 nodes) + new parents */
- mas_node_count(mas, nr_nodes + 3);
+ mas_node_count_gfp(mas, nr_nodes + 3, GFP_KERNEL);
/* Detect if allocations run out */
mas->mas_flags |= MA_STATE_PREALLOC;
diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c
index 06959165e2f9..464eeb90d5ad 100644
--- a/lib/test_maple_tree.c
+++ b/lib/test_maple_tree.c
@@ -9,6 +9,7 @@
#include <linux/maple_tree.h>
#include <linux/module.h>
+#include <linux/rwsem.h>
#define MTREE_ALLOC_MAX 0x2000000000000Ul
#define CONFIG_MAPLE_SEARCH
@@ -1841,17 +1842,21 @@ static noinline void __init check_forking(struct maple_tree *mt)
void *val;
MA_STATE(mas, mt, 0, 0);
MA_STATE(newmas, mt, 0, 0);
+ struct rw_semaphore newmt_lock;
+
+ init_rwsem(&newmt_lock);
for (i = 0; i <= nr_entries; i++)
mtree_store_range(mt, i*10, i*10 + 5,
xa_mk_value(i), GFP_KERNEL);
mt_set_non_kernel(99999);
- mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE);
+ mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN);
+ mt_set_external_lock(&newmt, &newmt_lock);
newmas.tree = &newmt;
mas_reset(&newmas);
mas_reset(&mas);
- mas_lock(&newmas);
+ down_write(&newmt_lock);
mas.index = 0;
mas.last = 0;
if (mas_expected_entries(&newmas, nr_entries)) {
@@ -1866,10 +1871,10 @@ static noinline void __init check_forking(struct maple_tree *mt)
}
rcu_read_unlock();
mas_destroy(&newmas);
- mas_unlock(&newmas);
mt_validate(&newmt);
mt_set_non_kernel(0);
- mtree_destroy(&newmt);
+ __mt_destroy(&newmt);
+ up_write(&newmt_lock);
}
static noinline void __init check_iteration(struct maple_tree *mt)
@@ -1980,6 +1985,10 @@ static noinline void __init bench_forking(struct maple_tree *mt)
void *val;
MA_STATE(mas, mt, 0, 0);
MA_STATE(newmas, mt, 0, 0);
+ struct rw_semaphore newmt_lock;
+
+ init_rwsem(&newmt_lock);
+ mt_set_external_lock(&newmt, &newmt_lock);
for (i = 0; i <= nr_entries; i++)
mtree_store_range(mt, i*10, i*10 + 5,
@@ -1994,7 +2003,7 @@ static noinline void __init bench_forking(struct maple_tree *mt)
mas.index = 0;
mas.last = 0;
rcu_read_lock();
- mas_lock(&newmas);
+ down_write(&newmt_lock);
if (mas_expected_entries(&newmas, nr_entries)) {
printk("OOM!");
BUG_ON(1);
@@ -2005,11 +2014,11 @@ static noinline void __init bench_forking(struct maple_tree *mt)
mas_store(&newmas, val);
}
mas_destroy(&newmas);
- mas_unlock(&newmas);
rcu_read_unlock();
mt_validate(&newmt);
mt_set_non_kernel(0);
- mtree_destroy(&newmt);
+ __mt_destroy(&newmt);
+ up_write(&newmt_lock);
}
}
#endif
@@ -2616,6 +2625,10 @@ static noinline void __init check_dup_gaps(struct maple_tree *mt,
void *tmp;
MA_STATE(mas, mt, 0, 0);
MA_STATE(newmas, &newmt, 0, 0);
+ struct rw_semaphore newmt_lock;
+
+ init_rwsem(&newmt_lock);
+ mt_set_external_lock(&newmt, &newmt_lock);
if (!zero_start)
i = 1;
@@ -2625,9 +2638,9 @@ static noinline void __init check_dup_gaps(struct maple_tree *mt,
mtree_store_range(mt, i*10, (i+1)*10 - gap,
xa_mk_value(i), GFP_KERNEL);
- mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE);
+ mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN);
mt_set_non_kernel(99999);
- mas_lock(&newmas);
+ down_write(&newmt_lock);
ret = mas_expected_entries(&newmas, nr_entries);
mt_set_non_kernel(0);
MT_BUG_ON(mt, ret != 0);
@@ -2640,9 +2653,9 @@ static noinline void __init check_dup_gaps(struct maple_tree *mt,
}
rcu_read_unlock();
mas_destroy(&newmas);
- mas_unlock(&newmas);
- mtree_destroy(&newmt);
+ __mt_destroy(&newmt);
+ up_write(&newmt_lock);
}
/* Duplicate many sizes of trees. Mainly to test expected entry values */
diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index b86ba7b0a921..f60e56150feb 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1208,6 +1208,8 @@ static int damon_sysfs_set_targets(struct damon_ctx *ctx,
return 0;
}
+static bool damon_sysfs_schemes_regions_updating;
+
static void damon_sysfs_before_terminate(struct damon_ctx *ctx)
{
struct damon_target *t, *next;
@@ -1219,8 +1221,10 @@ static void damon_sysfs_before_terminate(struct damon_ctx *ctx)
cmd = damon_sysfs_cmd_request.cmd;
if (kdamond && ctx == kdamond->damon_ctx &&
(cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS ||
- cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES)) {
+ cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES) &&
+ damon_sysfs_schemes_regions_updating) {
damon_sysfs_schemes_update_regions_stop(ctx);
+ damon_sysfs_schemes_regions_updating = false;
mutex_unlock(&damon_sysfs_lock);
}
@@ -1340,7 +1344,6 @@ static int damon_sysfs_commit_input(struct damon_sysfs_kdamond *kdamond)
static int damon_sysfs_cmd_request_callback(struct damon_ctx *c)
{
struct damon_sysfs_kdamond *kdamond;
- static bool damon_sysfs_schemes_regions_updating;
bool total_bytes_only = false;
int err = 0;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 36b40bc9ac25..3fb3a5232173 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -97,6 +97,7 @@ static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
+static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
static inline bool subpool_is_free(struct hugepage_subpool *spool)
{
@@ -267,6 +268,10 @@ void hugetlb_vma_lock_read(struct vm_area_struct *vma)
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
down_read(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ down_read(&resv_map->rw_sema);
}
}
@@ -276,6 +281,10 @@ void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
up_read(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ up_read(&resv_map->rw_sema);
}
}
@@ -285,6 +294,10 @@ void hugetlb_vma_lock_write(struct vm_area_struct *vma)
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
down_write(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ down_write(&resv_map->rw_sema);
}
}
@@ -294,17 +307,27 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
up_write(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ up_write(&resv_map->rw_sema);
}
}
int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
{
- struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
- if (!__vma_shareable_lock(vma))
- return 1;
+ if (__vma_shareable_lock(vma)) {
+ struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
- return down_write_trylock(&vma_lock->rw_sema);
+ return down_write_trylock(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ return down_write_trylock(&resv_map->rw_sema);
+ }
+
+ return 1;
}
void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
@@ -313,6 +336,10 @@ void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
lockdep_assert_held(&vma_lock->rw_sema);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ lockdep_assert_held(&resv_map->rw_sema);
}
}
@@ -345,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
__hugetlb_vma_unlock_write_put(vma_lock);
+ } else if (__vma_private_lock(vma)) {
+ struct resv_map *resv_map = vma_resv_map(vma);
+
+ /* no free for anon vmas, but still need to unlock */
+ up_write(&resv_map->rw_sema);
}
}
@@ -1061,6 +1093,7 @@ struct resv_map *resv_map_alloc(void)
kref_init(&resv_map->refs);
spin_lock_init(&resv_map->lock);
INIT_LIST_HEAD(&resv_map->regions);
+ init_rwsem(&resv_map->rw_sema);
resv_map->adds_in_progress = 0;
/*
@@ -1131,8 +1164,7 @@ static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma);
- set_vma_private_data(vma, (get_vma_private_data(vma) &
- HPAGE_RESV_MASK) | (unsigned long)map);
+ set_vma_private_data(vma, (unsigned long)map);
}
static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
@@ -5315,9 +5347,9 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
return len + old_addr - old_end;
}
-static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
- unsigned long start, unsigned long end,
- struct page *ref_page, zap_flags_t zap_flags)
+void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
+ unsigned long start, unsigned long end,
+ struct page *ref_page, zap_flags_t zap_flags)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
@@ -5446,16 +5478,25 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
tlb_flush_mmu_tlbonly(tlb);
}
-void __unmap_hugepage_range_final(struct mmu_gather *tlb,
- struct vm_area_struct *vma, unsigned long start,
- unsigned long end, struct page *ref_page,
- zap_flags_t zap_flags)
+void __hugetlb_zap_begin(struct vm_area_struct *vma,
+ unsigned long *start, unsigned long *end)
{
+ if (!vma->vm_file) /* hugetlbfs_file_mmap error */
+ return;
+
+ adjust_range_if_pmd_sharing_possible(vma, start, end);
hugetlb_vma_lock_write(vma);
- i_mmap_lock_write(vma->vm_file->f_mapping);
+ if (vma->vm_file)
+ i_mmap_lock_write(vma->vm_file->f_mapping);
+}
- /* mmu notification performed in caller */
- __unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags);
+void __hugetlb_zap_end(struct vm_area_struct *vma,
+ struct zap_details *details)
+{
+ zap_flags_t zap_flags = details ? details->zap_flags : 0;
+
+ if (!vma->vm_file) /* hugetlbfs_file_mmap error */
+ return;
if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */
/*
@@ -5468,11 +5509,12 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb,
* someone else.
*/
__hugetlb_vma_unlock_write_free(vma);
- i_mmap_unlock_write(vma->vm_file->f_mapping);
} else {
- i_mmap_unlock_write(vma->vm_file->f_mapping);
hugetlb_vma_unlock_write(vma);
}
+
+ if (vma->vm_file)
+ i_mmap_unlock_write(vma->vm_file->f_mapping);
}
void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
@@ -6853,8 +6895,10 @@ out_err:
*/
if (chg >= 0 && add < 0)
region_abort(resv_map, from, to, regions_needed);
- if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+ if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
kref_put(&resv_map->refs, resv_map_release);
+ set_vma_resv_map(vma, NULL);
+ }
return false;
}
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index ca4b6ff080a6..6e3cb118d20e 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -621,7 +621,7 @@ void kasan_report_async(void)
}
#endif /* CONFIG_KASAN_HW_TAGS */
-#ifdef CONFIG_KASAN_INLINE
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
/*
* With CONFIG_KASAN_INLINE, accesses to bogus pointers (outside the high
* canonical half of the address space) cause out-of-bounds shadow memory reads
diff --git a/mm/memory.c b/mm/memory.c
index 7ca16ed67634..2d209bc4d18c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1691,7 +1691,7 @@ static void unmap_single_vma(struct mmu_gather *tlb,
if (vma->vm_file) {
zap_flags_t zap_flags = details ?
details->zap_flags : 0;
- __unmap_hugepage_range_final(tlb, vma, start, end,
+ __unmap_hugepage_range(tlb, vma, start, end,
NULL, zap_flags);
}
} else
@@ -1736,8 +1736,12 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
start_addr, end_addr);
mmu_notifier_invalidate_range_start(&range);
do {
- unmap_single_vma(tlb, vma, start_addr, end_addr, &details,
+ unsigned long start = start_addr;
+ unsigned long end = end_addr;
+ hugetlb_zap_begin(vma, &start, &end);
+ unmap_single_vma(tlb, vma, start, end, &details,
mm_wr_locked);
+ hugetlb_zap_end(vma, &details);
} while ((vma = mas_find(mas, tree_end - 1)) != NULL);
mmu_notifier_invalidate_range_end(&range);
}
@@ -1761,9 +1765,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
lru_add_drain();
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
address, end);
- if (is_vm_hugetlb_page(vma))
- adjust_range_if_pmd_sharing_possible(vma, &range.start,
- &range.end);
+ hugetlb_zap_begin(vma, &range.start, &range.end);
tlb_gather_mmu(&tlb, vma->vm_mm);
update_hiwater_rss(vma->vm_mm);
mmu_notifier_invalidate_range_start(&range);
@@ -1774,6 +1776,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
unmap_single_vma(&tlb, vma, address, end, details, false);
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb);
+ hugetlb_zap_end(vma, details);
}
/**
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index abd94f4c7f6b..38a47fa33ef4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1543,8 +1543,10 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le
* the home node for vmas we already updated before.
*/
old = vma_policy(vma);
- if (!old)
+ if (!old) {
+ prev = vma;
continue;
+ }
if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) {
err = -EOPNOTSUPP;
break;
diff --git a/mm/migrate.c b/mm/migrate.c
index 942f8c9cd068..482f478ea3fe 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2155,6 +2155,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
const int __user *nodes,
int __user *status, int flags)
{
+ compat_uptr_t __user *compat_pages = (void __user *)pages;
int current_node = NUMA_NO_NODE;
LIST_HEAD(pagelist);
int start, i;
@@ -2167,8 +2168,17 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
int node;
err = -EFAULT;
- if (get_user(p, pages + i))
- goto out_flush;
+ if (in_compat_syscall()) {
+ compat_uptr_t cp;
+
+ if (get_user(cp, compat_pages + i))
+ goto out_flush;
+
+ p = compat_ptr(cp);
+ } else {
+ if (get_user(p, pages + i))
+ goto out_flush;
+ }
if (get_user(node, nodes + i))
goto out_flush;
diff --git a/mm/mmap.c b/mm/mmap.c
index 42870c4d8704..011ba48d9e72 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -583,11 +583,12 @@ again:
* dup_anon_vma() - Helper function to duplicate anon_vma
* @dst: The destination VMA
* @src: The source VMA
+ * @dup: Pointer to the destination VMA when successful.
*
* Returns: 0 on success.
*/
static inline int dup_anon_vma(struct vm_area_struct *dst,
- struct vm_area_struct *src)
+ struct vm_area_struct *src, struct vm_area_struct **dup)
{
/*
* Easily overlooked: when mprotect shifts the boundary, make sure the
@@ -595,9 +596,15 @@ static inline int dup_anon_vma(struct vm_area_struct *dst,
* anon pages imported.
*/
if (src->anon_vma && !dst->anon_vma) {
+ int ret;
+
vma_assert_write_locked(dst);
dst->anon_vma = src->anon_vma;
- return anon_vma_clone(dst, src);
+ ret = anon_vma_clone(dst, src);
+ if (ret)
+ return ret;
+
+ *dup = dst;
}
return 0;
@@ -624,6 +631,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
unsigned long start, unsigned long end, pgoff_t pgoff,
struct vm_area_struct *next)
{
+ struct vm_area_struct *anon_dup = NULL;
bool remove_next = false;
struct vma_prepare vp;
@@ -633,7 +641,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
remove_next = true;
vma_start_write(next);
- ret = dup_anon_vma(vma, next);
+ ret = dup_anon_vma(vma, next, &anon_dup);
if (ret)
return ret;
}
@@ -661,6 +669,8 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
return 0;
nomem:
+ if (anon_dup)
+ unlink_anon_vmas(anon_dup);
return -ENOMEM;
}
@@ -860,6 +870,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
{
struct vm_area_struct *curr, *next, *res;
struct vm_area_struct *vma, *adjust, *remove, *remove2;
+ struct vm_area_struct *anon_dup = NULL;
struct vma_prepare vp;
pgoff_t vma_pgoff;
int err = 0;
@@ -927,18 +938,18 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
vma_start_write(next);
remove = next; /* case 1 */
vma_end = next->vm_end;
- err = dup_anon_vma(prev, next);
+ err = dup_anon_vma(prev, next, &anon_dup);
if (curr) { /* case 6 */
vma_start_write(curr);
remove = curr;
remove2 = next;
if (!next->anon_vma)
- err = dup_anon_vma(prev, curr);
+ err = dup_anon_vma(prev, curr, &anon_dup);
}
} else if (merge_prev) { /* case 2 */
if (curr) {
vma_start_write(curr);
- err = dup_anon_vma(prev, curr);
+ err = dup_anon_vma(prev, curr, &anon_dup);
if (end == curr->vm_end) { /* case 7 */
remove = curr;
} else { /* case 5 */
@@ -954,7 +965,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
vma_end = addr;
adjust = next;
adj_start = -(prev->vm_end - addr);
- err = dup_anon_vma(next, prev);
+ err = dup_anon_vma(next, prev, &anon_dup);
} else {
/*
* Note that cases 3 and 8 are the ONLY ones where prev
@@ -968,14 +979,14 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
vma_pgoff = curr->vm_pgoff;
vma_start_write(curr);
remove = curr;
- err = dup_anon_vma(next, curr);
+ err = dup_anon_vma(next, curr, &anon_dup);
}
}
}
/* Error in anon_vma clone. */
if (err)
- return NULL;
+ goto anon_vma_fail;
if (vma_start < vma->vm_start || vma_end > vma->vm_end)
vma_expanded = true;
@@ -988,7 +999,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
}
if (vma_iter_prealloc(vmi, vma))
- return NULL;
+ goto prealloc_fail;
init_multi_vma_prep(&vp, vma, adjust, remove, remove2);
VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma &&
@@ -1016,6 +1027,15 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
vma_complete(&vp, vmi, mm);
khugepaged_enter_vma(res, vm_flags);
return res;
+
+prealloc_fail:
+ if (anon_dup)
+ unlink_anon_vmas(anon_dup);
+
+anon_vma_fail:
+ vma_iter_set(vmi, addr);
+ vma_iter_load(vmi);
+ return NULL;
}
/*
@@ -3141,13 +3161,13 @@ int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
if (!len)
return 0;
- if (mmap_write_lock_killable(mm))
- return -EINTR;
-
/* Until we need other flags, refuse anything except VM_EXEC. */
if ((flags & (~VM_EXEC)) != 0)
return -EINVAL;
+ if (mmap_write_lock_killable(mm))
+ return -EINTR;
+
ret = check_brk_limits(addr, len);
if (ret)
goto limits_failed;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 95546f376302..85741403948f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6475,6 +6475,7 @@ static void break_down_buddy_pages(struct zone *zone, struct page *page,
next_page = page;
current_buddy = page + size;
}
+ page = next_page;
if (set_page_guard(zone, current_buddy, high, migratetype))
continue;
@@ -6482,7 +6483,6 @@ static void break_down_buddy_pages(struct zone *zone, struct page *page,
if (current_buddy != target) {
add_to_free_list(current_buddy, zone, high, migratetype);
set_buddy_order(current_buddy, high);
- page = next_page;
}
}
}
diff --git a/mm/zswap.c b/mm/zswap.c
index 083c693602b8..37d2b1cb2ecb 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1383,8 +1383,8 @@ reject:
shrink:
pool = zswap_pool_last_get();
- if (pool)
- queue_work(shrink_wq, &pool->shrink_work);
+ if (pool && !queue_work(shrink_wq, &pool->shrink_work))
+ zswap_pool_put(pool);
goto reject;
}
diff --git a/tools/include/linux/rwsem.h b/tools/include/linux/rwsem.h
new file mode 100644
index 000000000000..83971b3cbfce
--- /dev/null
+++ b/tools/include/linux/rwsem.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+#ifndef _TOOLS__RWSEM_H
+#define _TOOLS__RWSEM_H
+
+#include <pthread.h>
+
+struct rw_semaphore {
+ pthread_rwlock_t lock;
+};
+
+static inline int init_rwsem(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_init(&sem->lock, NULL);
+}
+
+static inline int exit_rwsem(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_destroy(&sem->lock);
+}
+
+static inline int down_read(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_rdlock(&sem->lock);
+}
+
+static inline int up_read(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_unlock(&sem->lock);
+}
+
+static inline int down_write(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_wrlock(&sem->lock);
+}
+
+static inline int up_write(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_unlock(&sem->lock);
+}
+#endif /* _TOOLS_RWSEM_H */
diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c
index e60cf4da8fb0..1c61e3c022cb 100644
--- a/tools/testing/selftests/clone3/clone3.c
+++ b/tools/testing/selftests/clone3/clone3.c
@@ -196,7 +196,12 @@ int main(int argc, char *argv[])
CLONE3_ARGS_NO_TEST);
/* Do a clone3() in a new time namespace */
- test_clone3(CLONE_NEWTIME, 0, 0, CLONE3_ARGS_NO_TEST);
+ if (access("/proc/self/ns/time", F_OK) == 0) {
+ test_clone3(CLONE_NEWTIME, 0, 0, CLONE3_ARGS_NO_TEST);
+ } else {
+ ksft_print_msg("Time namespaces are not supported\n");
+ ksft_test_result_skip("Skipping clone3() with CLONE_NEWTIME\n");
+ }
/* Do a clone3() with exit signal (SIGCHLD) in flags */
test_clone3(SIGCHLD, 0, -EINVAL, CLONE3_ARGS_NO_TEST);
diff --git a/tools/testing/selftests/mm/mremap_dontunmap.c b/tools/testing/selftests/mm/mremap_dontunmap.c
index ca2359835e75..a06e73ec8568 100644
--- a/tools/testing/selftests/mm/mremap_dontunmap.c
+++ b/tools/testing/selftests/mm/mremap_dontunmap.c
@@ -7,6 +7,7 @@
*/
#define _GNU_SOURCE
#include <sys/mman.h>
+#include <linux/mman.h>
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>