The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From d57f9da890696af1484f4a47f7f123560197865a Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal(a)wdc.com>
Date: Fri, 30 Nov 2018 15:31:48 +0900
Subject: [PATCH] dm zoned: Fix target BIO completion handling
struct bioctx includes the ref refcount_t to track the number of I/O
fragments used to process a target BIO as well as ensure that the zone
of the BIO is kept in the active state throughout the lifetime of the
BIO. However, since decrementing of this reference count is done in the
target .end_io method, the function bio_endio() must be called multiple
times for read and write target BIOs, which causes problems with the
value of the __bi_remaining struct bio field for chained BIOs (e.g. the
clone BIO passed by dm core is large and splits into fragments by the
block layer), resulting in incorrect values and inconsistencies with the
BIO_CHAIN flag setting. This is turn triggers the BUG_ON() call:
BUG_ON(atomic_read(&bio->__bi_remaining) <= 0);
in bio_remaining_done() called from bio_endio().
Fix this ensuring that bio_endio() is called only once for any target
BIO by always using internal clone BIOs for processing any read or
write target BIO. This allows reference counting using the target BIO
context counter to trigger the target BIO completion bio_endio() call
once all data, metadata and other zone work triggered by the BIO
complete.
Overall, this simplifies the code too as the target .end_io becomes
unnecessary and differences between read and write BIO issuing and
completion processing disappear.
Fixes: 3b1a94c88b79 ("dm zoned: drive-managed zoned block device target")
Cc: stable(a)vger.kernel.org
Signed-off-by: Damien Le Moal <damien.lemoal(a)wdc.com>
Signed-off-by: Mike Snitzer <snitzer(a)redhat.com>
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 981154e59461..6af5babe6837 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -20,7 +20,6 @@ struct dmz_bioctx {
struct dm_zone *zone;
struct bio *bio;
refcount_t ref;
- blk_status_t status;
};
/*
@@ -78,65 +77,66 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status)
{
struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
- if (bioctx->status == BLK_STS_OK && status != BLK_STS_OK)
- bioctx->status = status;
- bio_endio(bio);
+ if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK)
+ bio->bi_status = status;
+
+ if (refcount_dec_and_test(&bioctx->ref)) {
+ struct dm_zone *zone = bioctx->zone;
+
+ if (zone) {
+ if (bio->bi_status != BLK_STS_OK &&
+ bio_op(bio) == REQ_OP_WRITE &&
+ dmz_is_seq(zone))
+ set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags);
+ dmz_deactivate_zone(zone);
+ }
+ bio_endio(bio);
+ }
}
/*
- * Partial clone read BIO completion callback. This terminates the
+ * Completion callback for an internally cloned target BIO. This terminates the
* target BIO when there are no more references to its context.
*/
-static void dmz_read_bio_end_io(struct bio *bio)
+static void dmz_clone_endio(struct bio *clone)
{
- struct dmz_bioctx *bioctx = bio->bi_private;
- blk_status_t status = bio->bi_status;
+ struct dmz_bioctx *bioctx = clone->bi_private;
+ blk_status_t status = clone->bi_status;
- bio_put(bio);
+ bio_put(clone);
dmz_bio_endio(bioctx->bio, status);
}
/*
- * Issue a BIO to a zone. The BIO may only partially process the
+ * Issue a clone of a target BIO. The clone may only partially process the
* original target BIO.
*/
-static int dmz_submit_read_bio(struct dmz_target *dmz, struct dm_zone *zone,
- struct bio *bio, sector_t chunk_block,
- unsigned int nr_blocks)
+static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone,
+ struct bio *bio, sector_t chunk_block,
+ unsigned int nr_blocks)
{
struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
- sector_t sector;
struct bio *clone;
- /* BIO remap sector */
- sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block);
-
- /* If the read is not partial, there is no need to clone the BIO */
- if (nr_blocks == dmz_bio_blocks(bio)) {
- /* Setup and submit the BIO */
- bio->bi_iter.bi_sector = sector;
- refcount_inc(&bioctx->ref);
- generic_make_request(bio);
- return 0;
- }
-
- /* Partial BIO: we need to clone the BIO */
clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set);
if (!clone)
return -ENOMEM;
- /* Setup the clone */
- clone->bi_iter.bi_sector = sector;
+ bio_set_dev(clone, dmz->dev->bdev);
+ clone->bi_iter.bi_sector =
+ dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block);
clone->bi_iter.bi_size = dmz_blk2sect(nr_blocks) << SECTOR_SHIFT;
- clone->bi_end_io = dmz_read_bio_end_io;
+ clone->bi_end_io = dmz_clone_endio;
clone->bi_private = bioctx;
bio_advance(bio, clone->bi_iter.bi_size);
- /* Submit the clone */
refcount_inc(&bioctx->ref);
generic_make_request(clone);
+ if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone))
+ zone->wp_block += nr_blocks;
+
return 0;
}
@@ -214,7 +214,7 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone,
if (nr_blocks) {
/* Valid blocks found: read them */
nr_blocks = min_t(unsigned int, nr_blocks, end_block - chunk_block);
- ret = dmz_submit_read_bio(dmz, rzone, bio, chunk_block, nr_blocks);
+ ret = dmz_submit_bio(dmz, rzone, bio, chunk_block, nr_blocks);
if (ret)
return ret;
chunk_block += nr_blocks;
@@ -228,25 +228,6 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone,
return 0;
}
-/*
- * Issue a write BIO to a zone.
- */
-static void dmz_submit_write_bio(struct dmz_target *dmz, struct dm_zone *zone,
- struct bio *bio, sector_t chunk_block,
- unsigned int nr_blocks)
-{
- struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
-
- /* Setup and submit the BIO */
- bio_set_dev(bio, dmz->dev->bdev);
- bio->bi_iter.bi_sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block);
- refcount_inc(&bioctx->ref);
- generic_make_request(bio);
-
- if (dmz_is_seq(zone))
- zone->wp_block += nr_blocks;
-}
-
/*
* Write blocks directly in a data zone, at the write pointer.
* If a buffer zone is assigned, invalidate the blocks written
@@ -265,7 +246,9 @@ static int dmz_handle_direct_write(struct dmz_target *dmz,
return -EROFS;
/* Submit write */
- dmz_submit_write_bio(dmz, zone, bio, chunk_block, nr_blocks);
+ ret = dmz_submit_bio(dmz, zone, bio, chunk_block, nr_blocks);
+ if (ret)
+ return ret;
/*
* Validate the blocks in the data zone and invalidate
@@ -301,7 +284,9 @@ static int dmz_handle_buffered_write(struct dmz_target *dmz,
return -EROFS;
/* Submit write */
- dmz_submit_write_bio(dmz, bzone, bio, chunk_block, nr_blocks);
+ ret = dmz_submit_bio(dmz, bzone, bio, chunk_block, nr_blocks);
+ if (ret)
+ return ret;
/*
* Validate the blocks in the buffer zone
@@ -600,7 +585,6 @@ static int dmz_map(struct dm_target *ti, struct bio *bio)
bioctx->zone = NULL;
bioctx->bio = bio;
refcount_set(&bioctx->ref, 1);
- bioctx->status = BLK_STS_OK;
/* Set the BIO pending in the flush list */
if (!nr_sectors && bio_op(bio) == REQ_OP_WRITE) {
@@ -623,35 +607,6 @@ static int dmz_map(struct dm_target *ti, struct bio *bio)
return DM_MAPIO_SUBMITTED;
}
-/*
- * Completed target BIO processing.
- */
-static int dmz_end_io(struct dm_target *ti, struct bio *bio, blk_status_t *error)
-{
- struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
-
- if (bioctx->status == BLK_STS_OK && *error)
- bioctx->status = *error;
-
- if (!refcount_dec_and_test(&bioctx->ref))
- return DM_ENDIO_INCOMPLETE;
-
- /* Done */
- bio->bi_status = bioctx->status;
-
- if (bioctx->zone) {
- struct dm_zone *zone = bioctx->zone;
-
- if (*error && bio_op(bio) == REQ_OP_WRITE) {
- if (dmz_is_seq(zone))
- set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags);
- }
- dmz_deactivate_zone(zone);
- }
-
- return DM_ENDIO_DONE;
-}
-
/*
* Get zoned device information.
*/
@@ -946,7 +901,6 @@ static struct target_type dmz_type = {
.ctr = dmz_ctr,
.dtr = dmz_dtr,
.map = dmz_map,
- .end_io = dmz_end_io,
.io_hints = dmz_io_hints,
.prepare_ioctl = dmz_prepare_ioctl,
.postsuspend = dmz_suspend,
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From f6c367585d0d851349d3a9e607c43e5bea993fa1 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer(a)redhat.com>
Date: Tue, 11 Dec 2018 13:31:40 -0500
Subject: [PATCH] dm thin: send event about thin-pool state change _after_
making it
Sending a DM event before a thin-pool state change is about to happen is
a bug. It wasn't realized until it became clear that userspace response
to the event raced with the actual state change that the event was
meant to notify about.
Fix this by first updating internal thin-pool state to reflect what the
DM event is being issued about. This fixes a long-standing racey/buggy
userspace device-mapper-test-suite 'resize_io' test that would get an
event but not find the state it was looking for -- so it would just go
on to hang because no other events caused the test to reevaluate the
thin-pool's state.
Cc: stable(a)vger.kernel.org
Signed-off-by: Mike Snitzer <snitzer(a)redhat.com>
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 0bd8d498b3b9..53f8d03f76f7 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -195,7 +195,7 @@ static void throttle_unlock(struct throttle *t)
struct dm_thin_new_mapping;
/*
- * The pool runs in 4 modes. Ordered in degraded order for comparisons.
+ * The pool runs in various modes. Ordered in degraded order for comparisons.
*/
enum pool_mode {
PM_WRITE, /* metadata may be changed */
@@ -282,9 +282,38 @@ struct pool {
mempool_t mapping_pool;
};
-static enum pool_mode get_pool_mode(struct pool *pool);
static void metadata_operation_failed(struct pool *pool, const char *op, int r);
+static enum pool_mode get_pool_mode(struct pool *pool)
+{
+ return pool->pf.mode;
+}
+
+static void notify_of_pool_mode_change(struct pool *pool)
+{
+ const char *descs[] = {
+ "write",
+ "out-of-data-space",
+ "read-only",
+ "read-only",
+ "fail"
+ };
+ const char *extra_desc = NULL;
+ enum pool_mode mode = get_pool_mode(pool);
+
+ if (mode == PM_OUT_OF_DATA_SPACE) {
+ if (!pool->pf.error_if_no_space)
+ extra_desc = " (queue IO)";
+ else
+ extra_desc = " (error IO)";
+ }
+
+ dm_table_event(pool->ti->table);
+ DMINFO("%s: switching pool to %s%s mode",
+ dm_device_name(pool->pool_md),
+ descs[(int)mode], extra_desc ? : "");
+}
+
/*
* Target context for a pool.
*/
@@ -2351,8 +2380,6 @@ static void do_waker(struct work_struct *ws)
queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD);
}
-static void notify_of_pool_mode_change_to_oods(struct pool *pool);
-
/*
* We're holding onto IO to allow userland time to react. After the
* timeout either the pool will have been resized (and thus back in
@@ -2365,7 +2392,7 @@ static void do_no_space_timeout(struct work_struct *ws)
if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) {
pool->pf.error_if_no_space = true;
- notify_of_pool_mode_change_to_oods(pool);
+ notify_of_pool_mode_change(pool);
error_retry_list_with_code(pool, BLK_STS_NOSPC);
}
}
@@ -2433,26 +2460,6 @@ static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *))
/*----------------------------------------------------------------*/
-static enum pool_mode get_pool_mode(struct pool *pool)
-{
- return pool->pf.mode;
-}
-
-static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode)
-{
- dm_table_event(pool->ti->table);
- DMINFO("%s: switching pool to %s mode",
- dm_device_name(pool->pool_md), new_mode);
-}
-
-static void notify_of_pool_mode_change_to_oods(struct pool *pool)
-{
- if (!pool->pf.error_if_no_space)
- notify_of_pool_mode_change(pool, "out-of-data-space (queue IO)");
- else
- notify_of_pool_mode_change(pool, "out-of-data-space (error IO)");
-}
-
static bool passdown_enabled(struct pool_c *pt)
{
return pt->adjusted_pf.discard_passdown;
@@ -2501,8 +2508,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
switch (new_mode) {
case PM_FAIL:
- if (old_mode != new_mode)
- notify_of_pool_mode_change(pool, "failure");
dm_pool_metadata_read_only(pool->pmd);
pool->process_bio = process_bio_fail;
pool->process_discard = process_bio_fail;
@@ -2516,8 +2521,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
case PM_OUT_OF_METADATA_SPACE:
case PM_READ_ONLY:
- if (!is_read_only_pool_mode(old_mode))
- notify_of_pool_mode_change(pool, "read-only");
dm_pool_metadata_read_only(pool->pmd);
pool->process_bio = process_bio_read_only;
pool->process_discard = process_bio_success;
@@ -2538,8 +2541,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
* alarming rate. Adjust your low water mark if you're
* frequently seeing this mode.
*/
- if (old_mode != new_mode)
- notify_of_pool_mode_change_to_oods(pool);
pool->out_of_data_space = true;
pool->process_bio = process_bio_read_only;
pool->process_discard = process_discard_bio;
@@ -2552,8 +2553,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
break;
case PM_WRITE:
- if (old_mode != new_mode)
- notify_of_pool_mode_change(pool, "write");
if (old_mode == PM_OUT_OF_DATA_SPACE)
cancel_delayed_work_sync(&pool->no_space_timeout);
pool->out_of_data_space = false;
@@ -2573,6 +2572,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
* doesn't cause an unexpected mode transition on resume.
*/
pt->adjusted_pf.mode = new_mode;
+
+ if (old_mode != new_mode)
+ notify_of_pool_mode_change(pool);
}
static void abort_transaction(struct pool *pool)
The patch below does not apply to the 4.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From f6c367585d0d851349d3a9e607c43e5bea993fa1 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer(a)redhat.com>
Date: Tue, 11 Dec 2018 13:31:40 -0500
Subject: [PATCH] dm thin: send event about thin-pool state change _after_
making it
Sending a DM event before a thin-pool state change is about to happen is
a bug. It wasn't realized until it became clear that userspace response
to the event raced with the actual state change that the event was
meant to notify about.
Fix this by first updating internal thin-pool state to reflect what the
DM event is being issued about. This fixes a long-standing racey/buggy
userspace device-mapper-test-suite 'resize_io' test that would get an
event but not find the state it was looking for -- so it would just go
on to hang because no other events caused the test to reevaluate the
thin-pool's state.
Cc: stable(a)vger.kernel.org
Signed-off-by: Mike Snitzer <snitzer(a)redhat.com>
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 0bd8d498b3b9..53f8d03f76f7 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -195,7 +195,7 @@ static void throttle_unlock(struct throttle *t)
struct dm_thin_new_mapping;
/*
- * The pool runs in 4 modes. Ordered in degraded order for comparisons.
+ * The pool runs in various modes. Ordered in degraded order for comparisons.
*/
enum pool_mode {
PM_WRITE, /* metadata may be changed */
@@ -282,9 +282,38 @@ struct pool {
mempool_t mapping_pool;
};
-static enum pool_mode get_pool_mode(struct pool *pool);
static void metadata_operation_failed(struct pool *pool, const char *op, int r);
+static enum pool_mode get_pool_mode(struct pool *pool)
+{
+ return pool->pf.mode;
+}
+
+static void notify_of_pool_mode_change(struct pool *pool)
+{
+ const char *descs[] = {
+ "write",
+ "out-of-data-space",
+ "read-only",
+ "read-only",
+ "fail"
+ };
+ const char *extra_desc = NULL;
+ enum pool_mode mode = get_pool_mode(pool);
+
+ if (mode == PM_OUT_OF_DATA_SPACE) {
+ if (!pool->pf.error_if_no_space)
+ extra_desc = " (queue IO)";
+ else
+ extra_desc = " (error IO)";
+ }
+
+ dm_table_event(pool->ti->table);
+ DMINFO("%s: switching pool to %s%s mode",
+ dm_device_name(pool->pool_md),
+ descs[(int)mode], extra_desc ? : "");
+}
+
/*
* Target context for a pool.
*/
@@ -2351,8 +2380,6 @@ static void do_waker(struct work_struct *ws)
queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD);
}
-static void notify_of_pool_mode_change_to_oods(struct pool *pool);
-
/*
* We're holding onto IO to allow userland time to react. After the
* timeout either the pool will have been resized (and thus back in
@@ -2365,7 +2392,7 @@ static void do_no_space_timeout(struct work_struct *ws)
if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) {
pool->pf.error_if_no_space = true;
- notify_of_pool_mode_change_to_oods(pool);
+ notify_of_pool_mode_change(pool);
error_retry_list_with_code(pool, BLK_STS_NOSPC);
}
}
@@ -2433,26 +2460,6 @@ static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *))
/*----------------------------------------------------------------*/
-static enum pool_mode get_pool_mode(struct pool *pool)
-{
- return pool->pf.mode;
-}
-
-static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode)
-{
- dm_table_event(pool->ti->table);
- DMINFO("%s: switching pool to %s mode",
- dm_device_name(pool->pool_md), new_mode);
-}
-
-static void notify_of_pool_mode_change_to_oods(struct pool *pool)
-{
- if (!pool->pf.error_if_no_space)
- notify_of_pool_mode_change(pool, "out-of-data-space (queue IO)");
- else
- notify_of_pool_mode_change(pool, "out-of-data-space (error IO)");
-}
-
static bool passdown_enabled(struct pool_c *pt)
{
return pt->adjusted_pf.discard_passdown;
@@ -2501,8 +2508,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
switch (new_mode) {
case PM_FAIL:
- if (old_mode != new_mode)
- notify_of_pool_mode_change(pool, "failure");
dm_pool_metadata_read_only(pool->pmd);
pool->process_bio = process_bio_fail;
pool->process_discard = process_bio_fail;
@@ -2516,8 +2521,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
case PM_OUT_OF_METADATA_SPACE:
case PM_READ_ONLY:
- if (!is_read_only_pool_mode(old_mode))
- notify_of_pool_mode_change(pool, "read-only");
dm_pool_metadata_read_only(pool->pmd);
pool->process_bio = process_bio_read_only;
pool->process_discard = process_bio_success;
@@ -2538,8 +2541,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
* alarming rate. Adjust your low water mark if you're
* frequently seeing this mode.
*/
- if (old_mode != new_mode)
- notify_of_pool_mode_change_to_oods(pool);
pool->out_of_data_space = true;
pool->process_bio = process_bio_read_only;
pool->process_discard = process_discard_bio;
@@ -2552,8 +2553,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
break;
case PM_WRITE:
- if (old_mode != new_mode)
- notify_of_pool_mode_change(pool, "write");
if (old_mode == PM_OUT_OF_DATA_SPACE)
cancel_delayed_work_sync(&pool->no_space_timeout);
pool->out_of_data_space = false;
@@ -2573,6 +2572,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
* doesn't cause an unexpected mode transition on resume.
*/
pt->adjusted_pf.mode = new_mode;
+
+ if (old_mode != new_mode)
+ notify_of_pool_mode_change(pool);
}
static void abort_transaction(struct pool *pool)
Mediatek Preloader is a proprietary embedded boot loader for loading
Little Kernel and Linux into device DRAM.
This boot loader also handle firmware update. Mediatek Preloader will be
enumerated as a virtual COM port when the device is connected to Windows
or Linux OS via CDC-ACM class driver. When the USB enumeration has been
done, Mediatek Preloader will send out handshake command "READY" to PC
actively instead of waiting command from the download tool.
Since Linux 4.12, the commit "tty: reset termios state on device
registration" (93857edd9829e144acb6c7e72d593f6e01aead66) causes Mediatek
Preloader receiving some abnoraml command like "READYXX" as it sent.
This will be recognized as an incorrect response. The behavior change
also causes the download handshake fail.
By disabling the ECHO termios flag could avoid this problem. However, it
cannot be done by user space configuration when download tool open
/dev/ttyACM0. This is because the device running Mediatek Preloader will
send handshake command "READY" immediately once the CDC-ACM driver is
ready.
This patch wants to fix above problem by introducing "DISABLE_ECHO"
property in driver_info. When Mediatek Preloader is connected, the
CDC-ACM driver could disable ECHO flag in termios to avoid the problem.
Signed-off-by: Macpaul Lin <macpaul.lin(a)mediatek.com>
---
Changes for v2:
- Move quirks testing of DISABLE_ECHO flag into acm_tty_install().
- Change quirks testing into bitwise comparison.
Changes for v3:
- Replace quirks testing from init_termios to tty->termios.
- Remove parenthesis for ECHO flag.
Changes for v4:
- Drop quirks varible to simplify the patch.
- Move termios operation right after the driver_data has been installed.
- Write general style comment for suppressing initial echoing.
drivers/usb/class/cdc-acm.c | 12 +++++++++++-
drivers/usb/class/cdc-acm.h | 1 +
2 files changed, 12 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 1b68fed..ab8609e 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -583,6 +583,13 @@ static int acm_tty_install(struct tty_driver *driver, struct tty_struct *tty)
tty->driver_data = acm;
+ /*
+ * Suppress initial echoing for some devices which might send data
+ * immediately after acm driver has been installed.
+ */
+ if (acm->quirks & DISABLE_ECHO)
+ tty->termios.c_lflag &= ~ECHO;
+
return 0;
error_init_termios:
@@ -1655,7 +1662,10 @@ static int acm_pre_reset(struct usb_interface *intf)
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
{ USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov(a)gmail.com */
- .driver_info = NO_UNION_NORMAL, /* has no union descriptor */
+ .driver_info = DISABLE_ECHO, /* DISABLE ECHO in termios flag */
+ },
+ { USB_DEVICE(0x0e8d, 0x2000), /* FIREFLY, MediaTek Inc; Preloader */
+ .driver_info = DISABLE_ECHO, /* DISABLE ECHO in termios flag */
},
{ USB_DEVICE(0x0e8d, 0x3329), /* MediaTek Inc GPS */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index ca06b20..515aad0 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -140,3 +140,4 @@ struct acm {
#define QUIRK_CONTROL_LINE_STATE BIT(6)
#define CLEAR_HALT_CONDITIONS BIT(7)
#define SEND_ZERO_PACKET BIT(8)
+#define DISABLE_ECHO BIT(9)
--
1.9.1
Mediatek Preloader is a proprietary embedded boot loader for loading
Little Kernel and Linux into device DRAM.
This boot loader also handle firmware update. Mediatek Preloader will be
enumerated as a virtual COM port when the device is connected to Windows
or Linux OS via CDC-ACM class driver. When the USB enumeration has been
done, Mediatek Preloader will send out handshake command "READY" to PC
actively instead of waiting command from the download tool.
Since Linux 4.12, the commit "tty: reset termios state on device
registration" (93857edd9829e144acb6c7e72d593f6e01aead66) causes Mediatek
Preloader receiving some abnoraml command like "READYXX" as it sent.
This will be recognized as an incorrect response. The behavior change
also causes the download handshake fail.
By disabling the ECHO termios flag could avoid this problem. However, it
cannot be done by user space configuration when download tool open
/dev/ttyACM0. This is because the device running Mediatek Preloader will
send handshake command "READY" immediately once the CDC-ACM driver is
ready.
This patch wants to fix above problem by introducing "DISABLE_ECHO"
property in driver_info. When Mediatek Preloader is connected, the
CDC-ACM driver could disable ECHO flag in termios to avoid the problem.
Signed-off-by: Macpaul Lin <macpaul.lin(a)mediatek.com>
---
Changes for v2:
- Move quirks testing of DISABLE_ECHO flag into acm_tty_install().
- Change quirks testing into bitwise comparison.
Changes for v3:
- Replace clear flag operation from driver->init_termios to tty->termios.
- Remove parenthesis of ECHO flag.
drivers/usb/class/cdc-acm.c | 13 ++++++++++++-
drivers/usb/class/cdc-acm.h | 1 +
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 1b68fed..c1b88c3 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -571,6 +571,7 @@ static void acm_softint(struct work_struct *work)
static int acm_tty_install(struct tty_driver *driver, struct tty_struct *tty)
{
struct acm *acm;
+ unsigned long quirks;
int retval;
acm = acm_get_by_minor(tty->index);
@@ -583,6 +584,13 @@ static int acm_tty_install(struct tty_driver *driver, struct tty_struct *tty)
tty->driver_data = acm;
+ /* get normal quirks */
+ quirks = acm->quirks;
+
+ /* handle active handshake triggered by device */
+ if (quirks & DISABLE_ECHO)
+ tty->termios.c_lflag &= ~ECHO;
+
return 0;
error_init_termios:
@@ -1655,7 +1663,10 @@ static int acm_pre_reset(struct usb_interface *intf)
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
{ USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov(a)gmail.com */
- .driver_info = NO_UNION_NORMAL, /* has no union descriptor */
+ .driver_info = DISABLE_ECHO, /* DISABLE ECHO in termios flag */
+ },
+ { USB_DEVICE(0x0e8d, 0x2000), /* FIREFLY, MediaTek Inc; Preloader */
+ .driver_info = DISABLE_ECHO, /* DISABLE ECHO in termios flag */
},
{ USB_DEVICE(0x0e8d, 0x3329), /* MediaTek Inc GPS */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index ca06b20..515aad0 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -140,3 +140,4 @@ struct acm {
#define QUIRK_CONTROL_LINE_STATE BIT(6)
#define CLEAR_HALT_CONDITIONS BIT(7)
#define SEND_ZERO_PACKET BIT(8)
+#define DISABLE_ECHO BIT(9)
--
1.9.1
Mediatek Preloader is a proprietary embedded boot loader for loading
Little Kernel and Linux into device DRAM.
This boot loader also handle firmware update. Mediatek Preloader will be
enumerated as a virtual COM port when the device is connected to Windows
or Linux OS via CDC-ACM class driver. When the USB enumeration has been
done, Mediatek Preloader will send out handshake command "READY" to PC
actively instead of waiting command from the download tool.
Since Linux 4.12, the commit "tty: reset termios state on device
registration" (93857edd9829e144acb6c7e72d593f6e01aead66) causes Mediatek
Preloader receiving some abnoraml command like "READYXX" as it sent.
This will be recognized as an incorrect response. The behavior change
also causes the download handshake fail.
By disabling the ECHO termios flag could avoid this problem. However, it
cannot be done by user space configuration when download tool open
/dev/ttyACM0. This is because the device running Mediatek Preloader will
send handshake command "READY" immediately once the CDC-ACM driver is
ready.
This patch wants to fix above problem by introducing "DISABLE_ECHO"
property in driver_info. When Mediatek Preloader is connected, the
CDC-ACM driver could disable ECHO flag in termios to avoid the problem.
Signed-off-by: Macpaul Lin <macpaul.lin(a)mediatek.com>
---
Change for v2:
- Move quirks testing of DISABLE_ECHO flag into acm_tty_install().
- Change quirks testing into bitwise comparison.
drivers/usb/class/cdc-acm.c | 13 ++++++++++++-
drivers/usb/class/cdc-acm.h | 1 +
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 1b68fed..f1a914d 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -571,12 +571,20 @@ static void acm_softint(struct work_struct *work)
static int acm_tty_install(struct tty_driver *driver, struct tty_struct *tty)
{
struct acm *acm;
+ unsigned long quirks;
int retval;
acm = acm_get_by_minor(tty->index);
if (!acm)
return -ENODEV;
+ /* get normal quirks */
+ quirks = acm->quirks;
+
+ /* handle active handshake triggered by device */
+ if (quirks & DISABLE_ECHO)
+ driver->init_termios.c_lflag &= ~(ECHO);
+
retval = tty_standard_install(driver, tty);
if (retval)
goto error_init_termios;
@@ -1655,7 +1663,10 @@ static int acm_pre_reset(struct usb_interface *intf)
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
{ USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov(a)gmail.com */
- .driver_info = NO_UNION_NORMAL, /* has no union descriptor */
+ .driver_info = DISABLE_ECHO, /* DISABLE ECHO in termios flag */
+ },
+ { USB_DEVICE(0x0e8d, 0x2000), /* FIREFLY, MediaTek Inc; Preloader */
+ .driver_info = DISABLE_ECHO, /* DISABLE ECHO in termios flag */
},
{ USB_DEVICE(0x0e8d, 0x3329), /* MediaTek Inc GPS */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index ca06b20..515aad0 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -140,3 +140,4 @@ struct acm {
#define QUIRK_CONTROL_LINE_STATE BIT(6)
#define CLEAR_HALT_CONDITIONS BIT(7)
#define SEND_ZERO_PACKET BIT(8)
+#define DISABLE_ECHO BIT(9)
--
1.9.1
From: Long Li <longli(a)microsoft.com>
The current code attempts to pin memory using the largest possible wsize
based on the currect SMB credits. This doesn't cause kernel oops but this is
not optimal as we may pin more pages then actually needed.
Fix this by only pinning what are needed for doing this write I/O.
Signed-off-by: Long Li <longli(a)microsoft.com>
Cc: stable(a)vger.kernel.org
---
fs/cifs/file.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 3467351..c23bf9d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2617,11 +2617,13 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
if (rc)
break;
+ cur_len = min_t(const size_t, len, wsize);
+
if (ctx->direct_io) {
ssize_t result;
result = iov_iter_get_pages_alloc(
- from, &pagevec, wsize, &start);
+ from, &pagevec, cur_len, &start);
if (result < 0) {
cifs_dbg(VFS,
"direct_writev couldn't get user pages "
--
2.7.4
Hi folks,
I recently started seeing spurious test failures with rbtree tests,
resulting in boot delays and random "hung task" warnings.
The problems have been fixed upstream with the following patches.
v4.14.y:
0b548e33e6cb lib/rbtree-test: lower default params
v4.4.y, v4.9.y:
a54dae0338b7 lib/interval_tree_test.c: make test options module parameters
c46ecce431eb lib/interval_tree_test.c: allow full tree search
223f8911eace lib/rbtree_test.c: make input module parameters
0b548e33e6cb lib/rbtree-test: lower default params
The first three patches for v4.4.y and v4.9.y are the minimum
set of context patches needed to avoid conflicts when applying
commit 0b548e33e6cb.
I tested all kernel versions with the patches applied and rbtree
testing enabled to ensure that no new problems are introduced.
Please consider applying those patches to the respective releases.
Thanks,
Guenter
From: Emmanuel Grumbach <emmanuel.grumbach(a)intel.com>
NullFunc packets should never be duplicate just like
QoS-NullFunc packets.
We saw a client that enters / exits power save with
NullFunc frames (and not with QoS-NullFunc) despite the
fact that the association supports HT.
This specific client also re-uses a non-zero sequence number
for different NullFunc frames.
At some point, the client had to send a retransmission of
the NullFunc frame and we dropped it, leading to a
misalignment in the power save state.
Fix this by never consider a NullFunc frame as duplicate,
just like we do for QoS NullFunc frames.
This fixes https://bugzilla.kernel.org/show_bug.cgi?id=201449
CC: <stable(a)vger.kernel.org>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach(a)intel.com>
Signed-off-by: Luca Coelho <luciano.coelho(a)intel.com>
---
net/mac80211/rx.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 2394008f82b9..60d179bf2585 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1404,6 +1404,7 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx)
return RX_CONTINUE;
if (ieee80211_is_ctl(hdr->frame_control) ||
+ ieee80211_is_nullfunc(hdr->frame_control) ||
ieee80211_is_qos_nullfunc(hdr->frame_control) ||
is_multicast_ether_addr(hdr->addr1))
return RX_CONTINUE;
--
2.19.2
[ Upstream commit 64c3f648c25d108f346fdc96c15180c6b7d250e9 ]
Once in a while I see build errors similar to the following
when building images from a clean tree.
Building powerpc:virtex-ml507:44x/virtex5_defconfig ... failed
------------
Error log:
arch/powerpc/boot/treeboot-akebono.c:37:20: fatal error:
libfdt.h: No such file or directory
Building powerpc:bamboo:smpdev:44x/bamboo_defconfig ... failed
------------
Error log:
arch/powerpc/boot/treeboot-akebono.c:37:20: fatal error:
libfdt.h: No such file or directory
arch/powerpc/boot/treeboot-currituck.c:35:20: fatal error:
libfdt.h: No such file or directory
Rebuilds will succeed.
Turns out that several source files in arch/powerpc/boot/ include
libfdt.h, but Makefile dependencies are incomplete. Let's fix that.
Signed-off-by: Guenter Roeck <linux(a)roeck-us.net>
Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin(a)microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
[groeck: Backport to v4.4.y]
Signed-off-by: Guenter Roeck <linux(a)roeck-us.net>
---
For some reason I see the build error fixed with this patch more often
lately. It would be great if you can apply it to v3.18.y and v4.4.y.
Tested on both v3.18.y and v4.4.y.
arch/powerpc/boot/Makefile | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 99e4487248ff..57003d1bd243 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -70,7 +70,8 @@ $(addprefix $(obj)/,$(zlib) cuboot-c2k.o gunzip_util.o main.o): \
libfdt := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c
libfdtheader := fdt.h libfdt.h libfdt_internal.h
-$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o): \
+$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o \
+ treeboot-akebono.o treeboot-currituck.o treeboot-iss4xx.o): \
$(addprefix $(obj)/,$(libfdtheader))
src-wlib-y := string.S crt0.S crtsavres.S stdio.c main.c \
--
2.7.4
Please pick this commit for 4.14 and older stable branches:
commit 8e7df2b5b7f245c9bd11064712db5cb69044a362
Author: Ingo Molnar <mingo(a)kernel.org>
Date: Mon Nov 13 07:15:41 2017 +0100
timer/debug: Change /proc/timer_list from 0444 to 0400
In older kernel versions this file makes it far too easy to exploit
arbitrary-write bugs. It's possible to hide the pointers from
unprivileged users by setting the kernel.kptr_restrict sysctl, but that
wasn't done by default.
(Upstream commits c1eba5bcb643 "timer: Pass timer_list pointer to
callbacks unconditionally" and ad67b74d2469 "printk: hash addresses
printed with %p" provide more general mitigations, but don't seem to be
suitable for stable.)
Ben.
--
Ben Hutchings, Software Developer Codethink Ltd
https://www.codethink.co.uk/ Dale House, 35 Dale Street
Manchester, M1 2HF, United Kingdom
The patch titled
Subject: fork,memcg: fix crash in free_thread_stack on memcg charge fail
has been added to the -mm tree. Its filename is
forkmemcg-fix-crash-in-free_thread_stack-on-memcg-charge-fail.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/forkmemcg-fix-crash-in-free_thread…
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/forkmemcg-fix-crash-in-free_thread…
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Rik van Riel <riel(a)surriel.com>
Subject: fork,memcg: fix crash in free_thread_stack on memcg charge fail
Changeset 9b6f7e163cd0 ("mm: rework memcg kernel stack accounting")
will result in fork failing if allocating a kernel stack for a task
in dup_task_struct exceeds the kernel memory allowance for that cgroup.
Unfortunately, it also results in a crash.
This is due to the code jumping to free_stack and calling free_thread_stack
when the memcg kernel stack charge fails, but without tsk->stack pointing
at the freshly allocated stack.
This in turn results in the vfree_atomic in free_thread_stack oopsing
with a backtrace like this:
#5 [ffffc900244efc88] die at ffffffff8101f0ab
#6 [ffffc900244efcb8] do_general_protection at ffffffff8101cb86
#7 [ffffc900244efce0] general_protection at ffffffff818ff082
[exception RIP: llist_add_batch+7]
RIP: ffffffff8150d487 RSP: ffffc900244efd98 RFLAGS: 00010282
RAX: 0000000000000000 RBX: ffff88085ef55980 RCX: 0000000000000000
RDX: ffff88085ef55980 RSI: 343834343531203a RDI: 343834343531203a
RBP: ffffc900244efd98 R8: 0000000000000001 R9: ffff8808578c3600
R10: 0000000000000000 R11: 0000000000000001 R12: ffff88029f6c21c0
R13: 0000000000000286 R14: ffff880147759b00 R15: 0000000000000000
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
#8 [ffffc900244efda0] vfree_atomic at ffffffff811df2c7
#9 [ffffc900244efdb8] copy_process at ffffffff81086e37
#10 [ffffc900244efe98] _do_fork at ffffffff810884e0
#11 [ffffc900244eff10] sys_vfork at ffffffff810887ff
#12 [ffffc900244eff20] do_syscall_64 at ffffffff81002a43
RIP: 000000000049b948 RSP: 00007ffcdb307830 RFLAGS: 00000246
RAX: ffffffffffffffda RBX: 0000000000896030 RCX: 000000000049b948
RDX: 0000000000000000 RSI: 00007ffcdb307790 RDI: 00000000005d7421
RBP: 000000000067370f R8: 00007ffcdb3077b0 R9: 000000000001ed00
R10: 0000000000000008 R11: 0000000000000246 R12: 0000000000000040
R13: 000000000000000f R14: 0000000000000000 R15: 000000000088d018
ORIG_RAX: 000000000000003a CS: 0033 SS: 002b
The simplest fix is to assign tsk->stack right where it is allocated.
Link: http://lkml.kernel.org/r/20181214231726.7ee4843c@imladris.surriel.com
Fixes: 9b6f7e163cd0 ("mm: rework memcg kernel stack accounting")
Signed-off-by: Rik van Riel <riel(a)surriel.com>
Acked-by: Roman Gushchin <guro(a)fb.com>
Acked-by: Michal Hocko <mhocko(a)suse.com>
Cc: Shakeel Butt <shakeelb(a)google.com>
Cc: Johannes Weiner <hannes(a)cmpxchg.org>
Cc: Tejun Heo <tj(a)kernel.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
kernel/fork.c | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
--- a/kernel/fork.c~forkmemcg-fix-crash-in-free_thread_stack-on-memcg-charge-fail
+++ a/kernel/fork.c
@@ -240,8 +240,10 @@ static unsigned long *alloc_thread_stack
* free_thread_stack() can be called in interrupt context,
* so cache the vm_struct.
*/
- if (stack)
+ if (stack) {
tsk->stack_vm_area = find_vm_area(stack);
+ tsk->stack = stack;
+ }
return stack;
#else
struct page *page = alloc_pages_node(node, THREADINFO_GFP,
@@ -288,7 +290,10 @@ static struct kmem_cache *thread_stack_c
static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
- return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
+ unsigned long *stack;
+ stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
+ tsk->stack = stack;
+ return stack;
}
static void free_thread_stack(struct task_struct *tsk)
_
Patches currently in -mm which might be from riel(a)surriel.com are
forkmemcg-fix-crash-in-free_thread_stack-on-memcg-charge-fail.patch
The patch titled
Subject: proc/sysctl: don't return ENOMEM on lookup when a table is unregistering
has been removed from the -mm tree. Its filename was
proc-sysctl-dont-return-enomem-on-lookup-when-a-table-is-unregistering.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Ivan Delalande <colona(a)arista.com>
Subject: proc/sysctl: don't return ENOMEM on lookup when a table is unregistering
proc_sys_lookup can fail with ENOMEM instead of ENOENT when the
corresponding sysctl table is being unregistered. In our case we see this
upon opening /proc/sys/net/*/conf files while network interfaces are being
deleted, which confuses our configuration daemon.
The problem was successfully reproduced and this fix tested on v4.9.122
and v4.20-rc6.
Link: http://lkml.kernel.org/r/20181213232052.GA1513@visor
Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.")
Signed-off-by: Ivan Delalande <colona(a)arista.com>
Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org>
Cc: Luis Chamberlain <mcgrof(a)kernel.org>
Cc: Kees Cook <keescook(a)chromium.org>
Cc: Al Viro <viro(a)zeniv.linux.org.uk>
Cc: "Eric W. Biederman" <ebiederm(a)xmission.com>
Cc: Alexey Dobriyan <adobriyan(a)gmail.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
fs/proc/proc_sysctl.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
--- a/fs/proc/proc_sysctl.c~proc-sysctl-dont-return-enomem-on-lookup-when-a-table-is-unregistering
+++ a/fs/proc/proc_sysctl.c
@@ -464,7 +464,7 @@ static struct inode *proc_sys_make_inode
inode = new_inode(sb);
if (!inode)
- goto out;
+ return ERR_PTR(-ENOMEM);
inode->i_ino = get_next_ino();
@@ -474,7 +474,7 @@ static struct inode *proc_sys_make_inode
if (unlikely(head->unregistering)) {
spin_unlock(&sysctl_lock);
iput(inode);
- inode = NULL;
+ inode = ERR_PTR(-ENOENT);
goto out;
}
ei->sysctl = head;
@@ -549,10 +549,11 @@ static struct dentry *proc_sys_lookup(st
goto out;
}
- err = ERR_PTR(-ENOMEM);
inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
- if (!inode)
+ if (IS_ERR(inode)) {
+ err = ERR_CAST(inode);
goto out;
+ }
d_set_d_op(dentry, &proc_sys_dentry_operations);
err = d_splice_alias(inode, dentry);
@@ -685,7 +686,7 @@ static bool proc_sys_fill_cache(struct f
if (d_in_lookup(child)) {
struct dentry *res;
inode = proc_sys_make_inode(dir->d_sb, head, table);
- if (!inode) {
+ if (IS_ERR(inode)) {
d_lookup_done(child);
dput(child);
return false;
_
Patches currently in -mm which might be from colona(a)arista.com are