summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--.mailmap3
-rw-r--r--fs/ntfs/attrib.c8
-rw-r--r--fs/ocfs2/ocfs2.h4
-rw-r--r--fs/ocfs2/slot_map.c46
-rw-r--r--fs/ocfs2/super.c21
-rw-r--r--fs/read_write.c3
-rw-r--r--fs/userfaultfd.c12
-rw-r--r--include/linux/mm.h14
-rw-r--r--mm/gup.c6
-rw-r--r--mm/hugetlb.c10
-rw-r--r--mm/kfence/core.c18
-rw-r--r--mm/memory.c7
-rw-r--r--mm/memremap.c6
-rw-r--r--mm/secretmem.c33
-rw-r--r--mm/shmem.c7
15 files changed, 105 insertions, 93 deletions
diff --git a/.mailmap b/.mailmap
index 13e4f504e17f..bac1e6664a18 100644
--- a/.mailmap
+++ b/.mailmap
@@ -135,6 +135,8 @@ Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com>
Frank Zago <fzago@systemfabricworks.com>
Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com>
Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com>
+Gao Xiang <xiang@kernel.org> <hsiangkao@linux.alibaba.com>
+Gao Xiang <xiang@kernel.org> <hsiangkao@redhat.com>
Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@linux.vnet.ibm.com>
@@ -371,6 +373,7 @@ Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk>
Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk>
Sebastian Reichel <sre@kernel.org> <sre@debian.org>
Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de>
+Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com>
Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com>
Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com>
Shuah Khan <shuah@kernel.org> <shuah.khan@hp.com>
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index 4de597a83b88..52615e6090e1 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -592,8 +592,12 @@ static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name,
a = (ATTR_RECORD*)((u8*)ctx->attr +
le32_to_cpu(ctx->attr->length));
for (;; a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) {
- if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
- le32_to_cpu(ctx->mrec->bytes_allocated))
+ u8 *mrec_end = (u8 *)ctx->mrec +
+ le32_to_cpu(ctx->mrec->bytes_allocated);
+ u8 *name_end = (u8 *)a + le16_to_cpu(a->name_offset) +
+ a->name_length * sizeof(ntfschar);
+ if ((u8*)a < (u8*)ctx->mrec || (u8*)a > mrec_end ||
+ name_end > mrec_end)
break;
ctx->attr = a;
if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) ||
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 337527571461..740b64238312 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -277,7 +277,6 @@ enum ocfs2_mount_options
OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15, /* Journal Async Commit */
OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */
OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */
- OCFS2_MOUNT_NOCLUSTER = 1 << 18, /* No cluster aware filesystem mount */
};
#define OCFS2_OSB_SOFT_RO 0x0001
@@ -673,8 +672,7 @@ static inline int ocfs2_cluster_o2cb_global_heartbeat(struct ocfs2_super *osb)
static inline int ocfs2_mount_local(struct ocfs2_super *osb)
{
- return ((osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT)
- || (osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER));
+ return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT);
}
static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb)
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index 0b0ae3ebb0cf..da7718cef735 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -252,16 +252,14 @@ static int __ocfs2_find_empty_slot(struct ocfs2_slot_info *si,
int i, ret = -ENOSPC;
if ((preferred >= 0) && (preferred < si->si_num_slots)) {
- if (!si->si_slots[preferred].sl_valid ||
- !si->si_slots[preferred].sl_node_num) {
+ if (!si->si_slots[preferred].sl_valid) {
ret = preferred;
goto out;
}
}
for(i = 0; i < si->si_num_slots; i++) {
- if (!si->si_slots[i].sl_valid ||
- !si->si_slots[i].sl_node_num) {
+ if (!si->si_slots[i].sl_valid) {
ret = i;
break;
}
@@ -456,30 +454,24 @@ int ocfs2_find_slot(struct ocfs2_super *osb)
spin_lock(&osb->osb_lock);
ocfs2_update_slot_info(si);
- if (ocfs2_mount_local(osb))
- /* use slot 0 directly in local mode */
- slot = 0;
- else {
- /* search for ourselves first and take the slot if it already
- * exists. Perhaps we need to mark this in a variable for our
- * own journal recovery? Possibly not, though we certainly
- * need to warn to the user */
- slot = __ocfs2_node_num_to_slot(si, osb->node_num);
+ /* search for ourselves first and take the slot if it already
+ * exists. Perhaps we need to mark this in a variable for our
+ * own journal recovery? Possibly not, though we certainly
+ * need to warn to the user */
+ slot = __ocfs2_node_num_to_slot(si, osb->node_num);
+ if (slot < 0) {
+ /* if no slot yet, then just take 1st available
+ * one. */
+ slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
if (slot < 0) {
- /* if no slot yet, then just take 1st available
- * one. */
- slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
- if (slot < 0) {
- spin_unlock(&osb->osb_lock);
- mlog(ML_ERROR, "no free slots available!\n");
- status = -EINVAL;
- goto bail;
- }
- } else
- printk(KERN_INFO "ocfs2: Slot %d on device (%s) was "
- "already allocated to this node!\n",
- slot, osb->dev_str);
- }
+ spin_unlock(&osb->osb_lock);
+ mlog(ML_ERROR, "no free slots available!\n");
+ status = -EINVAL;
+ goto bail;
+ }
+ } else
+ printk(KERN_INFO "ocfs2: Slot %d on device (%s) was already "
+ "allocated to this node!\n", slot, osb->dev_str);
ocfs2_set_slot(si, slot, osb->node_num);
osb->slot_num = slot;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index f7298816d8d9..438be028935d 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -172,7 +172,6 @@ enum {
Opt_dir_resv_level,
Opt_journal_async_commit,
Opt_err_cont,
- Opt_nocluster,
Opt_err,
};
@@ -206,7 +205,6 @@ static const match_table_t tokens = {
{Opt_dir_resv_level, "dir_resv_level=%u"},
{Opt_journal_async_commit, "journal_async_commit"},
{Opt_err_cont, "errors=continue"},
- {Opt_nocluster, "nocluster"},
{Opt_err, NULL}
};
@@ -618,13 +616,6 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
goto out;
}
- tmp = OCFS2_MOUNT_NOCLUSTER;
- if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
- ret = -EINVAL;
- mlog(ML_ERROR, "Cannot change nocluster option on remount\n");
- goto out;
- }
-
tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
OCFS2_MOUNT_HB_NONE;
if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
@@ -865,7 +856,6 @@ static int ocfs2_verify_userspace_stack(struct ocfs2_super *osb,
}
if (ocfs2_userspace_stack(osb) &&
- !(osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
strncmp(osb->osb_cluster_stack, mopt->cluster_stack,
OCFS2_STACK_LABEL_LEN)) {
mlog(ML_ERROR,
@@ -1137,11 +1127,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK ? "writeback" :
"ordered");
- if ((osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
- !(osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT))
- printk(KERN_NOTICE "ocfs2: The shared device (%s) is mounted "
- "without cluster aware mode.\n", osb->dev_str);
-
atomic_set(&osb->vol_state, VOLUME_MOUNTED);
wake_up(&osb->osb_mount_event);
@@ -1452,9 +1437,6 @@ static int ocfs2_parse_options(struct super_block *sb,
case Opt_journal_async_commit:
mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT;
break;
- case Opt_nocluster:
- mopt->mount_opt |= OCFS2_MOUNT_NOCLUSTER;
- break;
default:
mlog(ML_ERROR,
"Unrecognized mount option \"%s\" "
@@ -1566,9 +1548,6 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT)
seq_printf(s, ",journal_async_commit");
- if (opts & OCFS2_MOUNT_NOCLUSTER)
- seq_printf(s, ",nocluster");
-
return 0;
}
diff --git a/fs/read_write.c b/fs/read_write.c
index e0777eefd846..397da0236607 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1263,6 +1263,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
count, fl);
file_end_write(out.file);
} else {
+ if (out.file->f_flags & O_NONBLOCK)
+ fl |= SPLICE_F_NONBLOCK;
+
retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl);
}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index e943370107d0..de86f5b2859f 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -192,17 +192,19 @@ static inline void msg_init(struct uffd_msg *msg)
}
static inline struct uffd_msg userfault_msg(unsigned long address,
+ unsigned long real_address,
unsigned int flags,
unsigned long reason,
unsigned int features)
{
struct uffd_msg msg;
+
msg_init(&msg);
msg.event = UFFD_EVENT_PAGEFAULT;
- if (!(features & UFFD_FEATURE_EXACT_ADDRESS))
- address &= PAGE_MASK;
- msg.arg.pagefault.address = address;
+ msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ?
+ real_address : address;
+
/*
* These flags indicate why the userfault occurred:
* - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
@@ -488,8 +490,8 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
uwq.wq.private = current;
- uwq.msg = userfault_msg(vmf->real_address, vmf->flags, reason,
- ctx->features);
+ uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags,
+ reason, ctx->features);
uwq.ctx = ctx;
uwq.waken = false;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cf3d0d673f6b..7898e29bcfb5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1130,23 +1130,27 @@ static inline bool is_zone_movable_page(const struct page *page)
#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX)
DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
-bool __put_devmap_managed_page(struct page *page);
-static inline bool put_devmap_managed_page(struct page *page)
+bool __put_devmap_managed_page_refs(struct page *page, int refs);
+static inline bool put_devmap_managed_page_refs(struct page *page, int refs)
{
if (!static_branch_unlikely(&devmap_managed_key))
return false;
if (!is_zone_device_page(page))
return false;
- return __put_devmap_managed_page(page);
+ return __put_devmap_managed_page_refs(page, refs);
}
-
#else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */
-static inline bool put_devmap_managed_page(struct page *page)
+static inline bool put_devmap_managed_page_refs(struct page *page, int refs)
{
return false;
}
#endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */
+static inline bool put_devmap_managed_page(struct page *page)
+{
+ return put_devmap_managed_page_refs(page, 1);
+}
+
/* 127: arbitrary random number, small enough to assemble well */
#define folio_ref_zero_or_close_to_overflow(folio) \
((unsigned int) folio_ref_count(folio) + 127u <= 127u)
diff --git a/mm/gup.c b/mm/gup.c
index 551264407624..e2a39e30756d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -87,7 +87,8 @@ retry:
* belongs to this folio.
*/
if (unlikely(page_folio(page) != folio)) {
- folio_put_refs(folio, refs);
+ if (!put_devmap_managed_page_refs(&folio->page, refs))
+ folio_put_refs(folio, refs);
goto retry;
}
@@ -176,7 +177,8 @@ static void gup_put_folio(struct folio *folio, int refs, unsigned int flags)
refs *= GUP_PIN_COUNTING_BIAS;
}
- folio_put_refs(folio, refs);
+ if (!put_devmap_managed_page_refs(&folio->page, refs))
+ folio_put_refs(folio, refs);
}
/**
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a57e1be41401..a18c071c294e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4788,8 +4788,13 @@ again:
* sharing with another vma.
*/
;
- } else if (unlikely(is_hugetlb_entry_migration(entry) ||
- is_hugetlb_entry_hwpoisoned(entry))) {
+ } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) {
+ bool uffd_wp = huge_pte_uffd_wp(entry);
+
+ if (!userfaultfd_wp(dst_vma) && uffd_wp)
+ entry = huge_pte_clear_uffd_wp(entry);
+ set_huge_pte_at(dst, addr, dst_pte, entry);
+ } else if (unlikely(is_hugetlb_entry_migration(entry))) {
swp_entry_t swp_entry = pte_to_swp_entry(entry);
bool uffd_wp = huge_pte_uffd_wp(entry);
@@ -5947,6 +5952,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
page = alloc_huge_page(dst_vma, dst_addr, 0);
if (IS_ERR(page)) {
+ put_page(*pagep);
ret = -ENOMEM;
*pagep = NULL;
goto out;
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 4b5e5a3d3a63..6aff49f6b79e 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -603,14 +603,6 @@ static unsigned long kfence_init_pool(void)
addr += 2 * PAGE_SIZE;
}
- /*
- * The pool is live and will never be deallocated from this point on.
- * Remove the pool object from the kmemleak object tree, as it would
- * otherwise overlap with allocations returned by kfence_alloc(), which
- * are registered with kmemleak through the slab post-alloc hook.
- */
- kmemleak_free(__kfence_pool);
-
return 0;
}
@@ -623,8 +615,16 @@ static bool __init kfence_init_pool_early(void)
addr = kfence_init_pool();
- if (!addr)
+ if (!addr) {
+ /*
+ * The pool is live and will never be deallocated from this point on.
+ * Ignore the pool object from the kmemleak phys object tree, as it would
+ * otherwise overlap with allocations returned by kfence_alloc(), which
+ * are registered with kmemleak through the slab post-alloc hook.
+ */
+ kmemleak_ignore_phys(__pa(__kfence_pool));
return true;
+ }
/*
* Only release unprotected pages, and do not try to go back and change
diff --git a/mm/memory.c b/mm/memory.c
index 9174918ce3f7..1c6027adc542 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4369,9 +4369,12 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
return VM_FAULT_OOM;
}
- /* See comment in handle_pte_fault() */
+ /*
+ * See comment in handle_pte_fault() for how this scenario happens, we
+ * need to return NOPAGE so that we drop this page.
+ */
if (pmd_devmap_trans_unstable(vmf->pmd))
- return 0;
+ return VM_FAULT_NOPAGE;
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
diff --git a/mm/memremap.c b/mm/memremap.c
index b870a659eee6..745eea0f99c3 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -499,7 +499,7 @@ void free_zone_device_page(struct page *page)
}
#ifdef CONFIG_FS_DAX
-bool __put_devmap_managed_page(struct page *page)
+bool __put_devmap_managed_page_refs(struct page *page, int refs)
{
if (page->pgmap->type != MEMORY_DEVICE_FS_DAX)
return false;
@@ -509,9 +509,9 @@ bool __put_devmap_managed_page(struct page *page)
* refcount is 1, then the page is free and the refcount is
* stable because nobody holds a reference on the page.
*/
- if (page_ref_dec_return(page) == 1)
+ if (page_ref_sub_return(page, refs) == 1)
wake_up_var(&page->_refcount);
return true;
}
-EXPORT_SYMBOL(__put_devmap_managed_page);
+EXPORT_SYMBOL(__put_devmap_managed_page_refs);
#endif /* CONFIG_FS_DAX */
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 206ed6b40c1d..f06279d6190a 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -55,22 +55,28 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf)
gfp_t gfp = vmf->gfp_mask;
unsigned long addr;
struct page *page;
+ vm_fault_t ret;
int err;
if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
return vmf_error(-EINVAL);
+ filemap_invalidate_lock_shared(mapping);
+
retry:
page = find_lock_page(mapping, offset);
if (!page) {
page = alloc_page(gfp | __GFP_ZERO);
- if (!page)
- return VM_FAULT_OOM;
+ if (!page) {
+ ret = VM_FAULT_OOM;
+ goto out;
+ }
err = set_direct_map_invalid_noflush(page);
if (err) {
put_page(page);
- return vmf_error(err);
+ ret = vmf_error(err);
+ goto out;
}
__SetPageUptodate(page);
@@ -86,7 +92,8 @@ retry:
if (err == -EEXIST)
goto retry;
- return vmf_error(err);
+ ret = vmf_error(err);
+ goto out;
}
addr = (unsigned long)page_address(page);
@@ -94,7 +101,11 @@ retry:
}
vmf->page = page;
- return VM_FAULT_LOCKED;
+ ret = VM_FAULT_LOCKED;
+
+out:
+ filemap_invalidate_unlock_shared(mapping);
+ return ret;
}
static const struct vm_operations_struct secretmem_vm_ops = {
@@ -162,12 +173,20 @@ static int secretmem_setattr(struct user_namespace *mnt_userns,
struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
+ struct address_space *mapping = inode->i_mapping;
unsigned int ia_valid = iattr->ia_valid;
+ int ret;
+
+ filemap_invalidate_lock(mapping);
if ((ia_valid & ATTR_SIZE) && inode->i_size)
- return -EINVAL;
+ ret = -EINVAL;
+ else
+ ret = simple_setattr(mnt_userns, dentry, iattr);
- return simple_setattr(mnt_userns, dentry, iattr);
+ filemap_invalidate_unlock(mapping);
+
+ return ret;
}
static const struct inode_operations secretmem_iops = {
diff --git a/mm/shmem.c b/mm/shmem.c
index a6f565308133..b7f2d4a56867 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3392,7 +3392,7 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param)
break;
case Opt_nr_blocks:
ctx->blocks = memparse(param->string, &rest);
- if (*rest)
+ if (*rest || ctx->blocks > S64_MAX)
goto bad_value;
ctx->seen |= SHMEM_SEEN_BLOCKS;
break;
@@ -3514,10 +3514,7 @@ static int shmem_reconfigure(struct fs_context *fc)
raw_spin_lock(&sbinfo->stat_lock);
inodes = sbinfo->max_inodes - sbinfo->free_inodes;
- if (ctx->blocks > S64_MAX) {
- err = "Number of blocks too large";
- goto out;
- }
+
if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) {
if (!sbinfo->max_blocks) {
err = "Cannot retroactively limit size";
View Lorry Controller Status