Merge tag 'urgent-rcu.2024.01.24a' of https://github.com/neeraju/linux
Pull RCU fix from Neeraj Upadhyay:
"This fixes RCU grace period stalls, which are observed when an
outgoing CPU's quiescent state reporting results in wakeup of one of
the grace period kthreads, to complete the grace period.
If those kthreads have SCHED_FIFO policy, the wake up can indirectly
arm the RT bandwith timer to the local offline CPU.
Earlier migration of the hrtimers from the CPU introduced in commit
5c0930ccaad5 ("hrtimers: Push pending hrtimers away from outgoing CPU
earlier") results in this timer getting ignored.
If the RCU grace period kthreads are waiting for RT bandwidth to be
available, they may never be actually scheduled, resulting in RCU
stall warnings"
* tag 'urgent-rcu.2024.01.24a' of https://github.com/neeraju/linux:
rcu: Defer RCU kthreads wakeup when CPU is dying
diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052f..39219b1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7955,12 +7955,13 @@
S: Maintained
F: rust/kernel/net/phy.rs
-EXEC & BINFMT API
+EXEC & BINFMT API, ELF
R: Eric Biederman <ebiederm@xmission.com>
R: Kees Cook <keescook@chromium.org>
L: linux-mm@kvack.org
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve
+F: Documentation/userspace-api/ELF.rst
F: fs/*binfmt_*.c
F: fs/exec.c
F: include/linux/binfmts.h
diff --git a/Makefile b/Makefile
index 9869f57..9f9b76d 100644
--- a/Makefile
+++ b/Makefile
@@ -986,6 +986,10 @@
# perform bounds checking.
KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3)
+#Currently, disable -Wstringop-overflow for GCC 11, globally.
+KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow)
+KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
+
# disable invalid "can't wrap" optimizations for signed / pointers
KBUILD_CFLAGS += -fno-strict-overflow
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index a999b69..12b5d53 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3452,14 +3452,15 @@ static bool rbd_lock_add_request(struct rbd_img_request *img_req)
static void rbd_lock_del_request(struct rbd_img_request *img_req)
{
struct rbd_device *rbd_dev = img_req->rbd_dev;
- bool need_wakeup;
+ bool need_wakeup = false;
lockdep_assert_held(&rbd_dev->lock_rwsem);
spin_lock(&rbd_dev->lock_lists_lock);
- rbd_assert(!list_empty(&img_req->lock_item));
- list_del_init(&img_req->lock_item);
- need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
- list_empty(&rbd_dev->running_list));
+ if (!list_empty(&img_req->lock_item)) {
+ list_del_init(&img_req->lock_item);
+ need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
+ list_empty(&rbd_dev->running_list));
+ }
spin_unlock(&rbd_dev->lock_lists_lock);
if (need_wakeup)
complete(&rbd_dev->releasing_wait);
@@ -3842,14 +3843,19 @@ static void wake_lock_waiters(struct rbd_device *rbd_dev, int result)
return;
}
- list_for_each_entry(img_req, &rbd_dev->acquiring_list, lock_item) {
+ while (!list_empty(&rbd_dev->acquiring_list)) {
+ img_req = list_first_entry(&rbd_dev->acquiring_list,
+ struct rbd_img_request, lock_item);
mutex_lock(&img_req->state_mutex);
rbd_assert(img_req->state == RBD_IMG_EXCLUSIVE_LOCK);
+ if (!result)
+ list_move_tail(&img_req->lock_item,
+ &rbd_dev->running_list);
+ else
+ list_del_init(&img_req->lock_item);
rbd_img_schedule(img_req, result);
mutex_unlock(&img_req->state_mutex);
}
-
- list_splice_tail_init(&rbd_dev->acquiring_list, &rbd_dev->running_list);
}
static bool locker_equal(const struct ceph_locker *lhs,
@@ -5326,7 +5332,7 @@ static void rbd_dev_release(struct device *dev)
if (need_put) {
destroy_workqueue(rbd_dev->task_wq);
- ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id);
+ ida_free(&rbd_dev_id_ida, rbd_dev->dev_id);
}
rbd_dev_free(rbd_dev);
@@ -5402,9 +5408,9 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
return NULL;
/* get an id and fill in device name */
- rbd_dev->dev_id = ida_simple_get(&rbd_dev_id_ida, 0,
- minor_to_rbd_dev_id(1 << MINORBITS),
- GFP_KERNEL);
+ rbd_dev->dev_id = ida_alloc_max(&rbd_dev_id_ida,
+ minor_to_rbd_dev_id(1 << MINORBITS) - 1,
+ GFP_KERNEL);
if (rbd_dev->dev_id < 0)
goto fail_rbd_dev;
@@ -5425,7 +5431,7 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
return rbd_dev;
fail_dev_id:
- ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id);
+ ida_free(&rbd_dev_id_ida, rbd_dev->dev_id);
fail_rbd_dev:
rbd_dev_free(rbd_dev);
return NULL;
diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index f5187b3..4130945 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -195,7 +195,7 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
bool use_dma_alloc, bool use_dma32)
{
struct ttm_global *glob = &ttm_glob;
- int ret;
+ int ret, nid;
if (WARN_ON(vma_manager == NULL))
return -EINVAL;
@@ -215,7 +215,12 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func
ttm_sys_man_init(bdev);
- ttm_pool_init(&bdev->pool, dev, dev_to_node(dev), use_dma_alloc, use_dma32);
+ if (dev)
+ nid = dev_to_node(dev);
+ else
+ nid = NUMA_NO_NODE;
+
+ ttm_pool_init(&bdev->pool, dev, nid, use_dma_alloc, use_dma32);
bdev->vma_manager = vma_manager;
spin_lock_init(&bdev->lru_lock);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 88f760a..d7503ae 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -463,12 +463,25 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
}
for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS;
- shinfo->nr_frags++, gop++, nr_slots--) {
+ nr_slots--) {
+ if (unlikely(!txp->size)) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&queue->response_lock, flags);
+ make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY);
+ push_tx_responses(queue);
+ spin_unlock_irqrestore(&queue->response_lock, flags);
+ ++txp;
+ continue;
+ }
+
index = pending_index(queue->pending_cons++);
pending_idx = queue->pending_ring[index];
xenvif_tx_create_map_op(queue, pending_idx, txp,
txp == first ? extra_count : 0, gop);
frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx);
+ ++shinfo->nr_frags;
+ ++gop;
if (txp == first)
txp = txfrags;
@@ -481,20 +494,39 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
shinfo = skb_shinfo(nskb);
frags = shinfo->frags;
- for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots;
- shinfo->nr_frags++, txp++, gop++) {
+ for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) {
+ if (unlikely(!txp->size)) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&queue->response_lock, flags);
+ make_tx_response(queue, txp, 0,
+ XEN_NETIF_RSP_OKAY);
+ push_tx_responses(queue);
+ spin_unlock_irqrestore(&queue->response_lock,
+ flags);
+ continue;
+ }
+
index = pending_index(queue->pending_cons++);
pending_idx = queue->pending_ring[index];
xenvif_tx_create_map_op(queue, pending_idx, txp, 0,
gop);
frag_set_pending_idx(&frags[shinfo->nr_frags],
pending_idx);
+ ++shinfo->nr_frags;
+ ++gop;
}
- skb_shinfo(skb)->frag_list = nskb;
- } else if (nskb) {
+ if (shinfo->nr_frags) {
+ skb_shinfo(skb)->frag_list = nskb;
+ nskb = NULL;
+ }
+ }
+
+ if (nskb) {
/* A frag_list skb was allocated but it is no longer needed
- * because enough slots were converted to copy ops above.
+ * because enough slots were converted to copy ops above or some
+ * were empty.
*/
kfree_skb(nskb);
}
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 63af6ab..1183e7a 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -631,8 +631,7 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info,
if (logo_lines > vc->vc_bottom) {
logo_shown = FBCON_LOGO_CANSHOW;
- printk(KERN_INFO
- "fbcon_init: disable boot-logo (boot-logo bigger than screen).\n");
+ pr_info("fbcon: disable boot-logo (boot-logo bigger than screen).\n");
} else {
logo_shown = FBCON_LOGO_DRAW;
vc->vc_top = logo_lines;
diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c
index dddd6af..ebc9aef 100644
--- a/drivers/video/fbdev/savage/savagefb_driver.c
+++ b/drivers/video/fbdev/savage/savagefb_driver.c
@@ -869,6 +869,9 @@ static int savagefb_check_var(struct fb_var_screeninfo *var,
DBG("savagefb_check_var");
+ if (!var->pixclock)
+ return -EINVAL;
+
var->transp.offset = 0;
var->transp.length = 0;
switch (var->bits_per_pixel) {
diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c
index 803ccb6..009bf1d 100644
--- a/drivers/video/fbdev/sis/sis_main.c
+++ b/drivers/video/fbdev/sis/sis_main.c
@@ -1444,6 +1444,8 @@ sisfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
vtotal = var->upper_margin + var->lower_margin + var->vsync_len;
+ if (!var->pixclock)
+ return -EINVAL;
pixclock = var->pixclock;
if((var->vmode & FB_VMODE_MASK) == FB_VMODE_NONINTERLACED) {
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 2de0e67..8e5bac2 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -1158,7 +1158,7 @@ stifb_init_display(struct stifb_info *fb)
}
break;
}
- stifb_blank(0, (struct fb_info *)fb); /* 0=enable screen */
+ stifb_blank(0, fb->info); /* 0=enable screen */
SETUP_FB(fb);
}
diff --git a/drivers/video/fbdev/vt8500lcdfb.c b/drivers/video/fbdev/vt8500lcdfb.c
index 42c25dc..ac73937 100644
--- a/drivers/video/fbdev/vt8500lcdfb.c
+++ b/drivers/video/fbdev/vt8500lcdfb.c
@@ -374,7 +374,6 @@ static int vt8500lcd_probe(struct platform_device *pdev)
irq = platform_get_irq(pdev, 0);
if (irq < 0) {
- dev_err(&pdev->dev, "no IRQ defined\n");
ret = -ENODEV;
goto failed_free_palette;
}
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 1931682..68345f7 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -141,16 +141,16 @@ static int compression_decompress_bio(struct list_head *ws,
}
static int compression_decompress(int type, struct list_head *ws,
- const u8 *data_in, struct page *dest_page,
- unsigned long start_byte, size_t srclen, size_t destlen)
+ const u8 *data_in, struct page *dest_page,
+ unsigned long dest_pgoff, size_t srclen, size_t destlen)
{
switch (type) {
case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page,
- start_byte, srclen, destlen);
+ dest_pgoff, srclen, destlen);
case BTRFS_COMPRESS_LZO: return lzo_decompress(ws, data_in, dest_page,
- start_byte, srclen, destlen);
+ dest_pgoff, srclen, destlen);
case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page,
- start_byte, srclen, destlen);
+ dest_pgoff, srclen, destlen);
case BTRFS_COMPRESS_NONE:
default:
/*
@@ -1037,14 +1037,23 @@ static int btrfs_decompress_bio(struct compressed_bio *cb)
* start_byte tells us the offset into the compressed data we're interested in
*/
int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page,
- unsigned long start_byte, size_t srclen, size_t destlen)
+ unsigned long dest_pgoff, size_t srclen, size_t destlen)
{
+ struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
struct list_head *workspace;
+ const u32 sectorsize = fs_info->sectorsize;
int ret;
+ /*
+ * The full destination page range should not exceed the page size.
+ * And the @destlen should not exceed sectorsize, as this is only called for
+ * inline file extents, which should not exceed sectorsize.
+ */
+ ASSERT(dest_pgoff + destlen <= PAGE_SIZE && destlen <= sectorsize);
+
workspace = get_workspace(type, 0);
ret = compression_decompress(type, workspace, data_in, dest_page,
- start_byte, srclen, destlen);
+ dest_pgoff, srclen, destlen);
put_workspace(type, workspace);
return ret;
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 93cc929..afd7e50 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -148,7 +148,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
unsigned long *total_in, unsigned long *total_out);
int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
int zlib_decompress(struct list_head *ws, const u8 *data_in,
- struct page *dest_page, unsigned long start_byte, size_t srclen,
+ struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
size_t destlen);
struct list_head *zlib_alloc_workspace(unsigned int level);
void zlib_free_workspace(struct list_head *ws);
@@ -159,7 +159,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
unsigned long *total_in, unsigned long *total_out);
int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
int lzo_decompress(struct list_head *ws, const u8 *data_in,
- struct page *dest_page, unsigned long start_byte, size_t srclen,
+ struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
size_t destlen);
struct list_head *lzo_alloc_workspace(unsigned int level);
void lzo_free_workspace(struct list_head *ws);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index f396aba..8e8cc11 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1260,7 +1260,8 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
u64 bytes_left, end;
u64 aligned_start = ALIGN(start, 1 << SECTOR_SHIFT);
- if (WARN_ON(start != aligned_start)) {
+ /* Adjust the range to be aligned to 512B sectors if necessary. */
+ if (start != aligned_start) {
len -= aligned_start - start;
len = round_down(len, 1 << SECTOR_SHIFT);
start = aligned_start;
@@ -4298,6 +4299,42 @@ static int prepare_allocation_clustered(struct btrfs_fs_info *fs_info,
return 0;
}
+static int prepare_allocation_zoned(struct btrfs_fs_info *fs_info,
+ struct find_free_extent_ctl *ffe_ctl)
+{
+ if (ffe_ctl->for_treelog) {
+ spin_lock(&fs_info->treelog_bg_lock);
+ if (fs_info->treelog_bg)
+ ffe_ctl->hint_byte = fs_info->treelog_bg;
+ spin_unlock(&fs_info->treelog_bg_lock);
+ } else if (ffe_ctl->for_data_reloc) {
+ spin_lock(&fs_info->relocation_bg_lock);
+ if (fs_info->data_reloc_bg)
+ ffe_ctl->hint_byte = fs_info->data_reloc_bg;
+ spin_unlock(&fs_info->relocation_bg_lock);
+ } else if (ffe_ctl->flags & BTRFS_BLOCK_GROUP_DATA) {
+ struct btrfs_block_group *block_group;
+
+ spin_lock(&fs_info->zone_active_bgs_lock);
+ list_for_each_entry(block_group, &fs_info->zone_active_bgs, active_bg_list) {
+ /*
+ * No lock is OK here because avail is monotinically
+ * decreasing, and this is just a hint.
+ */
+ u64 avail = block_group->zone_capacity - block_group->alloc_offset;
+
+ if (block_group_bits(block_group, ffe_ctl->flags) &&
+ avail >= ffe_ctl->num_bytes) {
+ ffe_ctl->hint_byte = block_group->start;
+ break;
+ }
+ }
+ spin_unlock(&fs_info->zone_active_bgs_lock);
+ }
+
+ return 0;
+}
+
static int prepare_allocation(struct btrfs_fs_info *fs_info,
struct find_free_extent_ctl *ffe_ctl,
struct btrfs_space_info *space_info,
@@ -4308,19 +4345,7 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info,
return prepare_allocation_clustered(fs_info, ffe_ctl,
space_info, ins);
case BTRFS_EXTENT_ALLOC_ZONED:
- if (ffe_ctl->for_treelog) {
- spin_lock(&fs_info->treelog_bg_lock);
- if (fs_info->treelog_bg)
- ffe_ctl->hint_byte = fs_info->treelog_bg;
- spin_unlock(&fs_info->treelog_bg_lock);
- }
- if (ffe_ctl->for_data_reloc) {
- spin_lock(&fs_info->relocation_bg_lock);
- if (fs_info->data_reloc_bg)
- ffe_ctl->hint_byte = fs_info->data_reloc_bg;
- spin_unlock(&fs_info->relocation_bg_lock);
- }
- return 0;
+ return prepare_allocation_zoned(fs_info, ffe_ctl);
default:
BUG();
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 809b114..1eb93d3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4458,6 +4458,8 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
u64 root_flags;
int ret;
+ down_write(&fs_info->subvol_sem);
+
/*
* Don't allow to delete a subvolume with send in progress. This is
* inside the inode lock so the error handling that has to drop the bit
@@ -4469,25 +4471,25 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
btrfs_warn(fs_info,
"attempt to delete subvolume %llu during send",
dest->root_key.objectid);
- return -EPERM;
+ ret = -EPERM;
+ goto out_up_write;
}
if (atomic_read(&dest->nr_swapfiles)) {
spin_unlock(&dest->root_item_lock);
btrfs_warn(fs_info,
"attempt to delete subvolume %llu with active swapfile",
root->root_key.objectid);
- return -EPERM;
+ ret = -EPERM;
+ goto out_up_write;
}
root_flags = btrfs_root_flags(&dest->root_item);
btrfs_set_root_flags(&dest->root_item,
root_flags | BTRFS_ROOT_SUBVOL_DEAD);
spin_unlock(&dest->root_item_lock);
- down_write(&fs_info->subvol_sem);
-
ret = may_destroy_subvol(dest);
if (ret)
- goto out_up_write;
+ goto out_undead;
btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
/*
@@ -4497,7 +4499,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
*/
ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
if (ret)
- goto out_up_write;
+ goto out_undead;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
@@ -4563,15 +4565,17 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
inode->i_flags |= S_DEAD;
out_release:
btrfs_subvolume_release_metadata(root, &block_rsv);
-out_up_write:
- up_write(&fs_info->subvol_sem);
+out_undead:
if (ret) {
spin_lock(&dest->root_item_lock);
root_flags = btrfs_root_flags(&dest->root_item);
btrfs_set_root_flags(&dest->root_item,
root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
spin_unlock(&dest->root_item_lock);
- } else {
+ }
+out_up_write:
+ up_write(&fs_info->subvol_sem);
+ if (!ret) {
d_invalidate(dentry);
btrfs_prune_dentries(dest);
ASSERT(dest->send_in_progress == 0);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 41b4798..dfed9dd 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -790,6 +790,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
return -EOPNOTSUPP;
}
+ if (btrfs_root_refs(&root->root_item) == 0)
+ return -ENOENT;
+
if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
return -EINVAL;
@@ -2608,6 +2611,10 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
ret = -EFAULT;
goto out;
}
+ if (range.flags & ~BTRFS_DEFRAG_RANGE_FLAGS_SUPP) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
/* compression requires us to start the IO */
if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
range.flags |= BTRFS_DEFRAG_RANGE_START_IO;
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 1131d5a..e43bc0f 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -425,16 +425,16 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
}
int lzo_decompress(struct list_head *ws, const u8 *data_in,
- struct page *dest_page, unsigned long start_byte, size_t srclen,
+ struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
size_t destlen)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
+ struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
+ const u32 sectorsize = fs_info->sectorsize;
size_t in_len;
size_t out_len;
size_t max_segment_len = WORKSPACE_BUF_LENGTH;
int ret = 0;
- char *kaddr;
- unsigned long bytes;
if (srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)
return -EUCLEAN;
@@ -451,7 +451,7 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in,
}
data_in += LZO_LEN;
- out_len = PAGE_SIZE;
+ out_len = sectorsize;
ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
if (ret != LZO_E_OK) {
pr_warn("BTRFS: decompress failed!\n");
@@ -459,29 +459,13 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in,
goto out;
}
- if (out_len < start_byte) {
+ ASSERT(out_len <= sectorsize);
+ memcpy_to_page(dest_page, dest_pgoff, workspace->buf, out_len);
+ /* Early end, considered as an error. */
+ if (unlikely(out_len < destlen)) {
ret = -EIO;
- goto out;
+ memzero_page(dest_page, dest_pgoff + out_len, destlen - out_len);
}
-
- /*
- * the caller is already checking against PAGE_SIZE, but lets
- * move this check closer to the memcpy/memset
- */
- destlen = min_t(unsigned long, destlen, PAGE_SIZE);
- bytes = min_t(unsigned long, destlen, out_len - start_byte);
-
- kaddr = kmap_local_page(dest_page);
- memcpy(kaddr, workspace->buf + start_byte, bytes);
-
- /*
- * btrfs_getblock is doing a zero on the tail of the page too,
- * but this will cover anything missing from the decompressed
- * data.
- */
- if (bytes < destlen)
- memset(kaddr+bytes, 0, destlen-bytes);
- kunmap_local(kaddr);
out:
return ret;
}
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 6486f0d..8c4fc98 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -889,8 +889,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
out_unlock:
spin_unlock(&fs_info->ref_verify_lock);
out:
- if (ret)
+ if (ret) {
+ btrfs_free_ref_cache(fs_info);
btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
+ }
return ret;
}
@@ -1021,8 +1023,8 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info)
}
}
if (ret) {
- btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
btrfs_free_ref_cache(fs_info);
+ btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
}
btrfs_free_path(path);
return ret;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index a01807c..0123d27 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1098,12 +1098,22 @@ static void scrub_stripe_read_repair_worker(struct work_struct *work)
static void scrub_read_endio(struct btrfs_bio *bbio)
{
struct scrub_stripe *stripe = bbio->private;
+ struct bio_vec *bvec;
+ int sector_nr = calc_sector_number(stripe, bio_first_bvec_all(&bbio->bio));
+ int num_sectors;
+ u32 bio_size = 0;
+ int i;
+
+ ASSERT(sector_nr < stripe->nr_sectors);
+ bio_for_each_bvec_all(bvec, &bbio->bio, i)
+ bio_size += bvec->bv_len;
+ num_sectors = bio_size >> stripe->bg->fs_info->sectorsize_bits;
if (bbio->bio.bi_status) {
- bitmap_set(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
- bitmap_set(&stripe->error_bitmap, 0, stripe->nr_sectors);
+ bitmap_set(&stripe->io_error_bitmap, sector_nr, num_sectors);
+ bitmap_set(&stripe->error_bitmap, sector_nr, num_sectors);
} else {
- bitmap_clear(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
+ bitmap_clear(&stripe->io_error_bitmap, sector_nr, num_sectors);
}
bio_put(&bbio->bio);
if (atomic_dec_and_test(&stripe->pending_io)) {
@@ -1636,6 +1646,9 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
{
struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
struct btrfs_bio *bbio = NULL;
+ unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
+ stripe->bg->length - stripe->logical) >>
+ fs_info->sectorsize_bits;
u64 stripe_len = BTRFS_STRIPE_LEN;
int mirror = stripe->mirror_num;
int i;
@@ -1646,6 +1659,10 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
struct page *page = scrub_stripe_get_page(stripe, i);
unsigned int pgoff = scrub_stripe_get_page_offset(stripe, i);
+ /* We're beyond the chunk boundary, no need to read anymore. */
+ if (i >= nr_sectors)
+ break;
+
/* The current sector cannot be merged, submit the bio. */
if (bbio &&
((i > 0 &&
@@ -1701,6 +1718,9 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
{
struct btrfs_fs_info *fs_info = sctx->fs_info;
struct btrfs_bio *bbio;
+ unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
+ stripe->bg->length - stripe->logical) >>
+ fs_info->sectorsize_bits;
int mirror = stripe->mirror_num;
ASSERT(stripe->bg);
@@ -1715,14 +1735,16 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
bbio = btrfs_bio_alloc(SCRUB_STRIPE_PAGES, REQ_OP_READ, fs_info,
scrub_read_endio, stripe);
- /* Read the whole stripe. */
bbio->bio.bi_iter.bi_sector = stripe->logical >> SECTOR_SHIFT;
- for (int i = 0; i < BTRFS_STRIPE_LEN >> PAGE_SHIFT; i++) {
+ /* Read the whole range inside the chunk boundary. */
+ for (unsigned int cur = 0; cur < nr_sectors; cur++) {
+ struct page *page = scrub_stripe_get_page(stripe, cur);
+ unsigned int pgoff = scrub_stripe_get_page_offset(stripe, cur);
int ret;
- ret = bio_add_page(&bbio->bio, stripe->pages[i], PAGE_SIZE, 0);
+ ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff);
/* We should have allocated enough bio vectors. */
- ASSERT(ret == PAGE_SIZE);
+ ASSERT(ret == fs_info->sectorsize);
}
atomic_inc(&stripe->pending_io);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 4e36550..2d7519a 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -8205,8 +8205,8 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
goto out;
}
- sctx->clone_roots = kvcalloc(sizeof(*sctx->clone_roots),
- arg->clone_sources_count + 1,
+ sctx->clone_roots = kvcalloc(arg->clone_sources_count + 1,
+ sizeof(*sctx->clone_roots),
GFP_KERNEL);
if (!sctx->clone_roots) {
ret = -ENOMEM;
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 93511d5..0e49dab 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -475,7 +475,8 @@ void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info,
spin_lock_irqsave(&subpage->lock, flags);
bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
- folio_start_writeback(folio);
+ if (!folio_test_writeback(folio))
+ folio_start_writeback(folio);
spin_unlock_irqrestore(&subpage->lock, flags);
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 896acfd..101f786 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1457,6 +1457,14 @@ static int btrfs_reconfigure(struct fs_context *fc)
btrfs_info_to_ctx(fs_info, &old_ctx);
+ /*
+ * This is our "bind mount" trick, we don't want to allow the user to do
+ * anything other than mount a different ro/rw and a different subvol,
+ * all of the mount options should be maintained.
+ */
+ if (mount_reconfigure)
+ ctx->mount_opt = old_ctx.mount_opt;
+
sync_filesystem(sb);
set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 50fdc69..6eccf849 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1436,7 +1436,7 @@ static int check_extent_item(struct extent_buffer *leaf,
if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) {
extent_err(leaf, slot,
"inline ref item overflows extent item, ptr %lu iref size %u end %lu",
- ptr, inline_type, end);
+ ptr, btrfs_extent_inline_ref_size(inline_type), end);
return -EUCLEAN;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 4c32497..d67785b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3087,7 +3087,6 @@ struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
map = btrfs_find_chunk_map(fs_info, logical, length);
if (unlikely(!map)) {
- read_unlock(&fs_info->mapping_tree_lock);
btrfs_crit(fs_info,
"unable to find chunk map for logical %llu length %llu",
logical, length);
@@ -3095,7 +3094,6 @@ struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
}
if (unlikely(map->start > logical || map->start + map->chunk_len <= logical)) {
- read_unlock(&fs_info->mapping_tree_lock);
btrfs_crit(fs_info,
"found a bad chunk map, wanted %llu-%llu, found %llu-%llu",
logical, logical + length, map->start,
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 36cf1f0e..8da66ea 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -354,18 +354,13 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
}
int zlib_decompress(struct list_head *ws, const u8 *data_in,
- struct page *dest_page, unsigned long start_byte, size_t srclen,
+ struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
size_t destlen)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
int ret = 0;
int wbits = MAX_WBITS;
- unsigned long bytes_left;
- unsigned long total_out = 0;
- unsigned long pg_offset = 0;
-
- destlen = min_t(unsigned long, destlen, PAGE_SIZE);
- bytes_left = destlen;
+ unsigned long to_copy;
workspace->strm.next_in = data_in;
workspace->strm.avail_in = srclen;
@@ -390,60 +385,30 @@ int zlib_decompress(struct list_head *ws, const u8 *data_in,
return -EIO;
}
- while (bytes_left > 0) {
- unsigned long buf_start;
- unsigned long buf_offset;
- unsigned long bytes;
+ /*
+ * Everything (in/out buf) should be at most one sector, there should
+ * be no need to switch any input/output buffer.
+ */
+ ret = zlib_inflate(&workspace->strm, Z_FINISH);
+ to_copy = min(workspace->strm.total_out, destlen);
+ if (ret != Z_STREAM_END)
+ goto out;
- ret = zlib_inflate(&workspace->strm, Z_NO_FLUSH);
- if (ret != Z_OK && ret != Z_STREAM_END)
- break;
+ memcpy_to_page(dest_page, dest_pgoff, workspace->buf, to_copy);
- buf_start = total_out;
- total_out = workspace->strm.total_out;
-
- if (total_out == buf_start) {
- ret = -EIO;
- break;
- }
-
- if (total_out <= start_byte)
- goto next;
-
- if (total_out > start_byte && buf_start < start_byte)
- buf_offset = start_byte - buf_start;
- else
- buf_offset = 0;
-
- bytes = min(PAGE_SIZE - pg_offset,
- PAGE_SIZE - (buf_offset % PAGE_SIZE));
- bytes = min(bytes, bytes_left);
-
- memcpy_to_page(dest_page, pg_offset,
- workspace->buf + buf_offset, bytes);
-
- pg_offset += bytes;
- bytes_left -= bytes;
-next:
- workspace->strm.next_out = workspace->buf;
- workspace->strm.avail_out = workspace->buf_size;
- }
-
- if (ret != Z_STREAM_END && bytes_left != 0)
+out:
+ if (unlikely(to_copy != destlen)) {
+ pr_warn_ratelimited("BTRFS: infalte failed, decompressed=%lu expected=%zu\n",
+ to_copy, destlen);
ret = -EIO;
- else
+ } else {
ret = 0;
+ }
zlib_inflateEnd(&workspace->strm);
- /*
- * this should only happen if zlib returned fewer bytes than we
- * expected. btrfs_get_block is responsible for zeroing from the
- * end of the inline extent (destlen) to the end of the page
- */
- if (pg_offset < destlen) {
- memzero_page(dest_page, pg_offset, destlen - pg_offset);
- }
+ if (unlikely(to_copy < destlen))
+ memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy);
return ret;
}
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 5bd7681..168af9d 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2055,6 +2055,7 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
map = block_group->physical_map;
+ spin_lock(&fs_info->zone_active_bgs_lock);
spin_lock(&block_group->lock);
if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) {
ret = true;
@@ -2067,7 +2068,6 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
goto out_unlock;
}
- spin_lock(&fs_info->zone_active_bgs_lock);
for (i = 0; i < map->num_stripes; i++) {
struct btrfs_zoned_device_info *zinfo;
int reserved = 0;
@@ -2087,20 +2087,17 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
*/
if (atomic_read(&zinfo->active_zones_left) <= reserved) {
ret = false;
- spin_unlock(&fs_info->zone_active_bgs_lock);
goto out_unlock;
}
if (!btrfs_dev_set_active_zone(device, physical)) {
/* Cannot activate the zone */
ret = false;
- spin_unlock(&fs_info->zone_active_bgs_lock);
goto out_unlock;
}
if (!is_data)
zinfo->reserved_active_zones--;
}
- spin_unlock(&fs_info->zone_active_bgs_lock);
/* Successfully activated all the zones */
set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags);
@@ -2108,8 +2105,6 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
/* For the active block group list */
btrfs_get_block_group(block_group);
-
- spin_lock(&fs_info->zone_active_bgs_lock);
list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs);
spin_unlock(&fs_info->zone_active_bgs_lock);
@@ -2117,6 +2112,7 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
out_unlock:
spin_unlock(&block_group->lock);
+ spin_unlock(&fs_info->zone_active_bgs_lock);
return ret;
}
diff --git a/fs/exec.c b/fs/exec.c
index 8cdd5b2..af4fbb6 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -128,7 +128,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
struct filename *tmp = getname(library);
int error = PTR_ERR(tmp);
static const struct open_flags uselib_flags = {
- .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+ .open_flag = O_LARGEFILE | O_RDONLY,
.acc_mode = MAY_READ | MAY_EXEC,
.intent = LOOKUP_OPEN,
.lookup_flags = LOOKUP_FOLLOW,
@@ -904,6 +904,10 @@ EXPORT_SYMBOL(transfer_args_to_stack);
#endif /* CONFIG_MMU */
+/*
+ * On success, caller must call do_close_execat() on the returned
+ * struct file to close it.
+ */
static struct file *do_open_execat(int fd, struct filename *name, int flags)
{
struct file *file;
@@ -948,6 +952,17 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
return ERR_PTR(err);
}
+/**
+ * open_exec - Open a path name for execution
+ *
+ * @name: path name to open with the intent of executing it.
+ *
+ * Returns ERR_PTR on failure or allocated struct file on success.
+ *
+ * As this is a wrapper for the internal do_open_execat(), callers
+ * must call allow_write_access() before fput() on release. Also see
+ * do_close_execat().
+ */
struct file *open_exec(const char *name)
{
struct filename *filename = getname_kernel(name);
@@ -1409,6 +1424,9 @@ int begin_new_exec(struct linux_binprm * bprm)
out_unlock:
up_write(&me->signal->exec_update_lock);
+ if (!bprm->cred)
+ mutex_unlock(&me->signal->cred_guard_mutex);
+
out:
return retval;
}
@@ -1484,6 +1502,15 @@ static int prepare_bprm_creds(struct linux_binprm *bprm)
return -ENOMEM;
}
+/* Matches do_open_execat() */
+static void do_close_execat(struct file *file)
+{
+ if (!file)
+ return;
+ allow_write_access(file);
+ fput(file);
+}
+
static void free_bprm(struct linux_binprm *bprm)
{
if (bprm->mm) {
@@ -1495,10 +1522,7 @@ static void free_bprm(struct linux_binprm *bprm)
mutex_unlock(¤t->signal->cred_guard_mutex);
abort_creds(bprm->cred);
}
- if (bprm->file) {
- allow_write_access(bprm->file);
- fput(bprm->file);
- }
+ do_close_execat(bprm->file);
if (bprm->executable)
fput(bprm->executable);
/* If a binfmt changed the interp, free it. */
@@ -1520,8 +1544,7 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int fl
bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
if (!bprm) {
- allow_write_access(file);
- fput(file);
+ do_close_execat(file);
return ERR_PTR(-ENOMEM);
}
@@ -1610,6 +1633,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
}
rcu_read_unlock();
+ /* "users" and "in_exec" locked for copy_fs() */
if (p->fs->users > n_fs)
bprm->unsafe |= LSM_UNSAFE_SHARE;
else
@@ -1826,9 +1850,6 @@ static int exec_binprm(struct linux_binprm *bprm)
return 0;
}
-/*
- * sys_execve() executes a new program.
- */
static int bprm_execve(struct linux_binprm *bprm)
{
int retval;
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 6795fda..6b21152 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -34,7 +34,15 @@ static DEFINE_MUTEX(eventfs_mutex);
/* Choose something "unique" ;-) */
#define EVENTFS_FILE_INODE_INO 0x12c4e37
-#define EVENTFS_DIR_INODE_INO 0x134b2f5
+
+/* Just try to make something consistent and unique */
+static int eventfs_dir_ino(struct eventfs_inode *ei)
+{
+ if (!ei->ino)
+ ei->ino = get_next_ino();
+
+ return ei->ino;
+}
/*
* The eventfs_inode (ei) itself is protected by SRCU. It is released from
@@ -396,7 +404,7 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent
inode->i_fop = &eventfs_file_operations;
/* All directories will have the same inode number */
- inode->i_ino = EVENTFS_DIR_INODE_INO;
+ inode->i_ino = eventfs_dir_ino(ei);
ti = get_tracefs(inode);
ti->flags |= TRACEFS_EVENT_INODE;
@@ -802,7 +810,7 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
name = ei_child->name;
- ino = EVENTFS_DIR_INODE_INO;
+ ino = eventfs_dir_ino(ei_child);
if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR))
goto out_dec;
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 12b7d01..45397df 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -55,6 +55,10 @@ struct eventfs_inode {
struct eventfs_attr *entry_attrs;
struct eventfs_attr attr;
void *data;
+ unsigned int is_freed:1;
+ unsigned int is_events:1;
+ unsigned int nr_entries:30;
+ unsigned int ino;
/*
* Union - used for deletion
* @llist: for calling dput() if needed after RCU
@@ -64,9 +68,6 @@ struct eventfs_inode {
struct llist_node llist;
struct rcu_head rcu;
};
- unsigned int is_freed:1;
- unsigned int is_events:1;
- unsigned int nr_entries:30;
};
static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index cdb8ea5..ffe8f61 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -920,7 +920,7 @@ struct task_struct {
unsigned sched_rt_mutex:1;
#endif
- /* Bit to tell LSMs we're in execve(): */
+ /* Bit to tell TOMOYO we're in execve(): */
unsigned in_execve:1;
unsigned in_iowait:1;
#ifndef TIF_RESTORE_SIGMASK
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 7c29d82..f8bc34a 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -614,6 +614,9 @@ struct btrfs_ioctl_clone_range_args {
*/
#define BTRFS_DEFRAG_RANGE_COMPRESS 1
#define BTRFS_DEFRAG_RANGE_START_IO 2
+#define BTRFS_DEFRAG_RANGE_FLAGS_SUPP (BTRFS_DEFRAG_RANGE_COMPRESS | \
+ BTRFS_DEFRAG_RANGE_START_IO)
+
struct btrfs_ioctl_defrag_range_args {
/* start of the defrag operation */
__u64 start;
diff --git a/init/Kconfig b/init/Kconfig
index 8df18f3..8d4e836 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -876,6 +876,18 @@
bool
default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC11_NO_ARRAY_BOUNDS
+# Currently, disable -Wstringop-overflow for GCC 11, globally.
+config GCC11_NO_STRINGOP_OVERFLOW
+ def_bool y
+
+config CC_NO_STRINGOP_OVERFLOW
+ bool
+ default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_STRINGOP_OVERFLOW
+
+config CC_STRINGOP_OVERFLOW
+ bool
+ default y if CC_IS_GCC && !CC_NO_STRINGOP_OVERFLOW
+
#
# For architectures that know their GCC __int128 support is sound
#
diff --git a/kernel/fork.c b/kernel/fork.c
index 47ff3b3..0d944e9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1748,6 +1748,7 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
if (clone_flags & CLONE_FS) {
/* tsk->fs is already what we want */
spin_lock(&fs->lock);
+ /* "users" and "in_exec" locked for check_unsafe_exec() */
if (fs->in_exec) {
spin_unlock(&fs->lock);
return -EAGAIN;
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index c774e56..a4dcf0f 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -574,7 +574,12 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
}
memcpy(elt->key, key, map->key_size);
- entry->val = elt;
+ /*
+ * Ensure the initialization is visible and
+ * publish the elt.
+ */
+ smp_wmb();
+ WRITE_ONCE(entry->val, elt);
atomic64_inc(&map->hits);
return entry->val;
diff --git a/samples/cgroup/.gitignore b/samples/cgroup/.gitignore
new file mode 100644
index 0000000..3a01611
--- /dev/null
+++ b/samples/cgroup/.gitignore
@@ -0,0 +1,3 @@
+/cgroup_event_listener
+/memcg_event_listener
+
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index 9b7a37a..a9e552a 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -97,7 +97,6 @@
KBUILD_CFLAGS += $(call cc-option, -Wpacked-not-aligned)
KBUILD_CFLAGS += $(call cc-option, -Wformat-overflow)
KBUILD_CFLAGS += $(call cc-option, -Wformat-truncation)
-KBUILD_CFLAGS += $(call cc-option, -Wstringop-overflow)
KBUILD_CFLAGS += $(call cc-option, -Wstringop-truncation)
KBUILD_CPPFLAGS += -Wundef
@@ -113,7 +112,6 @@
KBUILD_CFLAGS += $(call cc-disable-warning, packed-not-aligned)
KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow)
KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation)
-KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow)
KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation)
ifdef CONFIG_CC_IS_CLANG
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 7717354..98e1150 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -469,8 +469,10 @@ static int apparmor_file_open(struct file *file)
* Cache permissions granted by the previous exec check, with
* implicit read and executable mmap which are required to
* actually execute the image.
+ *
+ * Illogically, FMODE_EXEC is in f_flags, not f_mode.
*/
- if (current->in_execve) {
+ if (file->f_flags & __FMODE_EXEC) {
fctx->allow = MAY_EXEC | MAY_READ | AA_EXEC_MMAP;
return 0;
}
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 76f55dd..8af2136 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -237,10 +237,6 @@ static int datablob_parse(char *datablob, const char **format,
break;
}
*decrypted_data = strsep(&datablob, " \t");
- if (!*decrypted_data) {
- pr_info("encrypted_key: decrypted_data is missing\n");
- break;
- }
ret = 0;
break;
case Opt_load:
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index 3c3af14..04a92c3 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -328,7 +328,8 @@ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd,
static int tomoyo_file_open(struct file *f)
{
/* Don't check read permission here if called from execve(). */
- if (current->in_execve)
+ /* Illogically, FMODE_EXEC is in f_flags, not f_mode. */
+ if (f->f_flags & __FMODE_EXEC)
return 0;
return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path,
f->f_flags);
