From: Christoph Hellwig hch@lst.de

[ Upstream commit 33dc62796cb657a633050138a86253fb2a553713 ]

When blk_throtl_init fails, we need to call blk_ioprio_exit. Switch to proper goto based unwinding to fix this.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Andreas Herrmann aherrmann@suse.de Acked-by: Tejun Heo tj@kernel.org Link: https://lore.kernel.org/r/20220921180501.1539876-2-hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Stable-dep-of: 813e693023ba ("blk-iolatency: Fix memory leak on add_disk() failures") Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-cgroup.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c8f0c865bf4e..bcd3873ac5ff 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1297,17 +1297,18 @@ int blkcg_init_queue(struct request_queue *q)

ret = blk_throtl_init(q); if (ret) - goto err_destroy_all; + goto err_ioprio_exit;

ret = blk_iolatency_init(q); - if (ret) { - blk_throtl_exit(q); - blk_ioprio_exit(q); - goto err_destroy_all; - } + if (ret) + goto err_throtl_exit;

return 0;

+err_throtl_exit: + blk_throtl_exit(q); +err_ioprio_exit: + blk_ioprio_exit(q); err_destroy_all: blkg_destroy_all(q); return ret;

From: Christoph Hellwig hch@lst.de

[ Upstream commit 79fcc5be93e5b17a2a5d36553f7a5c1ad9e953b6 ]

Use blkg_lookup instead of open coding it.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Andreas Herrmann aherrmann@suse.de Acked-by: Tejun Heo tj@kernel.org Link: https://lore.kernel.org/r/20220921180501.1539876-4-hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Stable-dep-of: 813e693023ba ("blk-iolatency: Fix memory leak on add_disk() failures") Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-cgroup.c | 6 +++--- block/blk-cgroup.h | 8 ++++---- 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 11f256214928..ee48b6f4d5d4 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -324,7 +324,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,

/* link parent */ if (blkcg_parent(blkcg)) { - blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false); + blkg->parent = blkg_lookup(blkcg_parent(blkcg), q); if (WARN_ON_ONCE(!blkg->parent)) { ret = -ENODEV; goto err_put_css; @@ -412,7 +412,7 @@ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct blkcg_gq *ret_blkg = q->root_blkg;

while (parent) { - blkg = __blkg_lookup(parent, q, false); + blkg = blkg_lookup(parent, q); if (blkg) { /* remember closest blkg */ ret_blkg = blkg; @@ -724,7 +724,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct blkcg_gq *new_blkg;

parent = blkcg_parent(blkcg); - while (parent && !__blkg_lookup(parent, q, false)) { + while (parent && !blkg_lookup(parent, q)) { pos = parent; parent = blkcg_parent(parent); } diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index c1fb00a1dfc0..30396cad50e9 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -362,8 +362,8 @@ static inline void blkg_put(struct blkcg_gq *blkg) */ #define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ - if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ - (p_blkg)->q, false))) + if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css), \ + (p_blkg)->q)))

/** * blkg_for_each_descendant_post - post-order walk of a blkg's descendants @@ -377,8 +377,8 @@ static inline void blkg_put(struct blkcg_gq *blkg) */ #define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ - if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ - (p_blkg)->q, false))) + if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css), \ + (p_blkg)->q)))

bool __blkcg_punt_bio_submit(struct bio *bio);

From: Christoph Hellwig hch@lst.de

[ Upstream commit 9823538fb7efe66ce987a1e4c0e0f3dc882623c4 ]

Pass the gendisk to blkcg_init_disk and blkcg_exit_disk as part of moving the blk-cgroup infrastructure to be gendisk based. Also remove the rather pointless kerneldoc comments for these internal functions with a single caller each.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Andreas Herrmann aherrmann@suse.de Acked-by: Tejun Heo tj@kernel.org Link: https://lore.kernel.org/r/20220921180501.1539876-7-hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Stable-dep-of: 813e693023ba ("blk-iolatency: Fix memory leak on add_disk() failures") Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-cgroup.c | 25 +++++-------------------- block/blk-cgroup.h | 8 ++++---- block/genhd.c | 5 +++-- 3 files changed, 12 insertions(+), 26 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index f66cf1734e84..4943f36d8a84 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1246,18 +1246,9 @@ static int blkcg_css_online(struct cgroup_subsys_state *css) return 0; }

-/** - * blkcg_init_queue - initialize blkcg part of request queue - * @q: request_queue to initialize - * - * Called from blk_alloc_queue(). Responsible for initializing blkcg - * part of new request_queue @q. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int blkcg_init_queue(struct request_queue *q) +int blkcg_init_disk(struct gendisk *disk) { + struct request_queue *q = disk->queue; struct blkcg_gq *new_blkg, *blkg; bool preloaded; int ret; @@ -1310,16 +1301,10 @@ int blkcg_init_queue(struct request_queue *q) return PTR_ERR(blkg); }

-/** - * blkcg_exit_queue - exit and release blkcg part of request_queue - * @q: request_queue being released - * - * Called from blk_exit_queue(). Responsible for exiting blkcg part. - */ -void blkcg_exit_queue(struct request_queue *q) +void blkcg_exit_disk(struct gendisk *disk) { - blkg_destroy_all(q); - blk_throtl_exit(q); + blkg_destroy_all(disk->queue); + blk_throtl_exit(disk->queue); }

static void blkcg_bind(struct cgroup_subsys_state *root_css) diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 91b7ae0773be..aa2b286bc825 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -178,8 +178,8 @@ struct blkcg_policy { extern struct blkcg blkcg_root; extern bool blkcg_debug_stats;

-int blkcg_init_queue(struct request_queue *q); -void blkcg_exit_queue(struct request_queue *q); +int blkcg_init_disk(struct gendisk *disk); +void blkcg_exit_disk(struct gendisk *disk);

/* Blkio controller policy registration */ int blkcg_policy_register(struct blkcg_policy *pol); @@ -481,8 +481,8 @@ struct blkcg { };

static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } -static inline int blkcg_init_queue(struct request_queue *q) { return 0; } -static inline void blkcg_exit_queue(struct request_queue *q) { } +static inline int blkcg_init_disk(struct gendisk *disk) { return 0; } +static inline void blkcg_exit_disk(struct gendisk *disk) { } static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } static inline int blkcg_activate_policy(struct request_queue *q, diff --git a/block/genhd.c b/block/genhd.c index 28654723bc2b..0568da4c0a2e 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1154,7 +1154,8 @@ static void disk_release(struct device *dev) !test_bit(GD_ADDED, &disk->state)) blk_mq_exit_queue(disk->queue);

- blkcg_exit_queue(disk->queue); + blkcg_exit_disk(disk); + bioset_exit(&disk->bio_split);

disk_release_events(disk); @@ -1367,7 +1368,7 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL)) goto out_destroy_part_tbl;

- if (blkcg_init_queue(q)) + if (blkcg_init_disk(disk)) goto out_erase_part0;

rand_initialize_disk(disk);

From: Christoph Hellwig hch@lst.de

[ Upstream commit 00ad6991bbae116b7c83f68754edd6f4d5e65e01 ]

Pass the gendisk to blkg_destroy_all as part of moving the blk-cgroup infrastructure to be gendisk based.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Andreas Herrmann aherrmann@suse.de Acked-by: Tejun Heo tj@kernel.org Link: https://lore.kernel.org/r/20220921180501.1539876-16-hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Stable-dep-of: 813e693023ba ("blk-iolatency: Fix memory leak on add_disk() failures") Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-cgroup.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index afe802e1180f..cd682fe46d2f 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -462,14 +462,9 @@ static void blkg_destroy(struct blkcg_gq *blkg) percpu_ref_kill(&blkg->refcnt); }

-/** - * blkg_destroy_all - destroy all blkgs associated with a request_queue - * @q: request_queue of interest - * - * Destroy all blkgs associated with @q. - */ -static void blkg_destroy_all(struct request_queue *q) +static void blkg_destroy_all(struct gendisk *disk) { + struct request_queue *q = disk->queue; struct blkcg_gq *blkg, *n; int count = BLKG_DESTROY_BATCH_SIZE;

@@ -1292,7 +1287,7 @@ int blkcg_init_disk(struct gendisk *disk) err_ioprio_exit: blk_ioprio_exit(q); err_destroy_all: - blkg_destroy_all(q); + blkg_destroy_all(disk); return ret; err_unlock: spin_unlock_irq(&q->queue_lock); @@ -1303,7 +1298,7 @@ int blkcg_init_disk(struct gendisk *disk)

void blkcg_exit_disk(struct gendisk *disk) { - blkg_destroy_all(disk->queue); + blkg_destroy_all(disk); blk_throtl_exit(disk); }

From: Paulo Alcantara pc@cjr.nz

[ Upstream commit a9e17d3d74d14e5fd10d54f0a07e0fce4e5f80dd ]

Remove unnecessary NULL check of oparam->cifs_sb when parsing symlink error response as it's already set by all smb2_open_file() callers and deferenced earlier.

This fixes below report:

fs/cifs/smb2file.c:126 smb2_open_file() warn: variable dereferenced before check 'oparms->cifs_sb' (see line 112)

Link: https://lore.kernel.org/r/Y0kt42j2tdpYakRu@kili Reported-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Paulo Alcantara (SUSE) pc@cjr.nz Signed-off-by: Steve French stfrench@microsoft.com Stable-dep-of: f60ffa662d14 ("cifs: don't leak -ENOMEM in smb2_open_file()") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cifs/smb2file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 4992b43616a7..ffbd9a99fc12 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -123,7 +123,7 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32

if (unlikely(!err_iov.iov_base || err_buftype == CIFS_NO_BUFFER)) rc = -ENOMEM; - else if (hdr->Status == STATUS_STOPPED_ON_SYMLINK && oparms->cifs_sb) { + else if (hdr->Status == STATUS_STOPPED_ON_SYMLINK) { rc = smb2_parse_symlink_response(oparms->cifs_sb, &err_iov, &data->symlink_target); if (!rc) {

From: Klaus Jensen k.jensen@samsung.com

[ Upstream commit b5f96cb719d8ba220b565ddd3ba4ac0d8bcfb130 ]

When using shadow doorbells, the event index and the doorbell values are written to host memory. Prior to this patch, the values written would erroneously be written in host endianness. This causes trouble on big-endian platforms. Fix this by adding missing endian conversions.

This issue was noticed by Guenter while testing various big-endian platforms under QEMU[1]. A similar fix required for hw/nvme in QEMU is up for review as well[2].

[1]: https://lore.kernel.org/qemu-devel/20221209110022.GA3396194@roeck-us.net/ [2]: https://lore.kernel.org/qemu-devel/20221212114409.34972-4-its@irrelevant.dk/

Fixes: f9f38e33389c ("nvme: improve performance for virtual NVMe devices") Reported-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Klaus Jensen k.jensen@samsung.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/pci.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 6867620bcc98..0b97e8ce13e4 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -144,9 +144,9 @@ struct nvme_dev { mempool_t *iod_mempool;

/* shadow doorbell buffer support: */ - u32 *dbbuf_dbs; + __le32 *dbbuf_dbs; dma_addr_t dbbuf_dbs_dma_addr; - u32 *dbbuf_eis; + __le32 *dbbuf_eis; dma_addr_t dbbuf_eis_dma_addr;

/* host memory buffer support: */ @@ -210,10 +210,10 @@ struct nvme_queue { #define NVMEQ_SQ_CMB 1 #define NVMEQ_DELETE_ERROR 2 #define NVMEQ_POLLED 3 - u32 *dbbuf_sq_db; - u32 *dbbuf_cq_db; - u32 *dbbuf_sq_ei; - u32 *dbbuf_cq_ei; + __le32 *dbbuf_sq_db; + __le32 *dbbuf_cq_db; + __le32 *dbbuf_sq_ei; + __le32 *dbbuf_cq_ei; struct completion delete_done; };

@@ -340,11 +340,11 @@ static inline int nvme_dbbuf_need_event(u16 event_idx, u16 new_idx, u16 old) }

/* Update dbbuf and return true if an MMIO is required */ -static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, - volatile u32 *dbbuf_ei) +static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db, + volatile __le32 *dbbuf_ei) { if (dbbuf_db) { - u16 old_value; + u16 old_value, event_idx;

/* * Ensure that the queue is written before updating @@ -352,8 +352,8 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, */ wmb();

- old_value = *dbbuf_db; - *dbbuf_db = value; + old_value = le32_to_cpu(*dbbuf_db); + *dbbuf_db = cpu_to_le32(value);

/* * Ensure that the doorbell is updated before reading the event @@ -363,7 +363,8 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, */ mb();

- if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value)) + event_idx = le32_to_cpu(*dbbuf_ei); + if (!nvme_dbbuf_need_event(event_idx, value, old_value)) return false; }

From: Keith Busch kbusch@kernel.org

[ Upstream commit 841734234a28fd5cd0889b84bd4d93a0988fa11e ]

The size allocated out of the dma pool is at most NVME_CTRL_PAGE_SIZE, which may be smaller than the PAGE_SIZE.

Fixes: c61b82c7b7134 ("nvme-pci: fix PRP pool size") Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/pci.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b128e2e36b68..529b424ef9b2 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -35,7 +35,7 @@ #define SQ_SIZE(q) ((q)->q_depth << (q)->sqes) #define CQ_SIZE(q) ((q)->q_depth * sizeof(struct nvme_completion))

-#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct nvme_sgl_desc)) +#define SGES_PER_PAGE (NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc))

/* * These can be higher, but we need to ensure that any command doesn't @@ -380,7 +380,7 @@ static int nvme_pci_npages_prp(void) { unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE; unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE); - return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8); + return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8); }

/* @@ -390,7 +390,7 @@ static int nvme_pci_npages_prp(void) static int nvme_pci_npages_sgl(void) { return DIV_ROUND_UP(NVME_MAX_SEGS * sizeof(struct nvme_sgl_desc), - PAGE_SIZE); + NVME_CTRL_PAGE_SIZE); }

static size_t nvme_pci_iod_alloc_size(void) @@ -721,7 +721,7 @@ static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge, sge->length = cpu_to_le32(entries * sizeof(*sge)); sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4; } else { - sge->length = cpu_to_le32(PAGE_SIZE); + sge->length = cpu_to_le32(NVME_CTRL_PAGE_SIZE); sge->type = NVME_SGL_FMT_SEG_DESC << 4; } }

From: Jiri Slaby (SUSE) jirislaby@kernel.org

[ Upstream commit bfcdf58380b1d9be564a78a9370da722ed1a9965 ]

LENOVO IdeaPad Flex 5 is ryzen-5 based and the commit below removed IRQ overriding for those. This broke touchscreen and trackpad: i2c_designware AMDI0010:00: controller timed out i2c_designware AMDI0010:03: controller timed out i2c_hid_acpi i2c-MSFT0001:00: failed to reset device: -61 i2c_designware AMDI0010:03: controller timed out ... i2c_hid_acpi i2c-MSFT0001:00: can't add hid device: -61 i2c_hid_acpi: probe of i2c-MSFT0001:00 failed with error -61

White-list this specific model in the override_table.

For this to work, the ZEN test needs to be put below the table walk.

Fixes: 37c81d9f1d1b (ACPI: resource: skip IRQ override on AMD Zen platforms) Link: https://bugzilla.suse.com/show_bug.cgi?id=1203794 Signed-off-by: Jiri Slaby (SUSE) jirislaby@kernel.org Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/resource.c | 42 +++++++++++++++++++++++++++-------------- 1 file changed, 28 insertions(+), 14 deletions(-)

diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 2ebc85233bac..30811a9521d4 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -417,17 +417,31 @@ static const struct dmi_system_id asus_laptop[] = { { } };

+static const struct dmi_system_id lenovo_82ra[] = { + { + .ident = "LENOVO IdeaPad Flex 5 16ALC7", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82RA"), + }, + }, + { } +}; + struct irq_override_cmp { const struct dmi_system_id *system; unsigned char irq; unsigned char triggering; unsigned char polarity; unsigned char shareable; + bool override; };

-static const struct irq_override_cmp skip_override_table[] = { - { medion_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0 }, - { asus_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0 }, +static const struct irq_override_cmp override_table[] = { + { medion_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, + { asus_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, + { lenovo_82ra, 6, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, + { lenovo_82ra, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, };

static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, @@ -435,6 +449,17 @@ static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, { int i;

+ for (i = 0; i < ARRAY_SIZE(override_table); i++) { + const struct irq_override_cmp *entry = &override_table[i]; + + if (dmi_check_system(entry->system) && + entry->irq == gsi && + entry->triggering == triggering && + entry->polarity == polarity && + entry->shareable == shareable) + return entry->override; + } + #ifdef CONFIG_X86 /* * IRQ override isn't needed on modern AMD Zen systems and @@ -445,17 +470,6 @@ static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, return false; #endif

- for (i = 0; i < ARRAY_SIZE(skip_override_table); i++) { - const struct irq_override_cmp *entry = &skip_override_table[i]; - - if (dmi_check_system(entry->system) && - entry->irq == gsi && - entry->triggering == triggering && - entry->polarity == polarity && - entry->shareable == shareable) - return false; - } - return true; }

From: Adrian Freund adrian@freund.io

[ Upstream commit f3cb9b740869712d448edf3b9ef5952b847caf8b ]

Commit bfcdf58380b1 ("ACPI: resource: do IRQ override on LENOVO IdeaPad") added an override for Lenovo IdeaPad 5 16ALC7. The 14ALC7 variant also suffers from a broken touchscreen and trackpad.

Fixes: 9946e39fe8d0 ("ACPI: resource: skip IRQ override on AMD Zen platforms") Link: https://bugzilla.kernel.org/show_bug.cgi?id=216804 Signed-off-by: Adrian Freund adrian@freund.io Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/resource.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 504378cc79a2..98daea0db979 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -417,7 +417,14 @@ static const struct dmi_system_id asus_laptop[] = { { } };

-static const struct dmi_system_id lenovo_82ra[] = { +static const struct dmi_system_id lenovo_laptop[] = { + { + .ident = "LENOVO IdeaPad Flex 5 14ALC7", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82R9"), + }, + }, { .ident = "LENOVO IdeaPad Flex 5 16ALC7", .matches = { @@ -451,8 +458,8 @@ struct irq_override_cmp { static const struct irq_override_cmp override_table[] = { { medion_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, { asus_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, - { lenovo_82ra, 6, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, - { lenovo_82ra, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, + { lenovo_laptop, 6, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, + { lenovo_laptop, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, { schenker_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, };

From: Adam Vodopjan grozzly@protonmail.com

[ Upstream commit 37e14e4f3715428b809e4df9a9958baa64c77d51 ]

Since kernel 5.3.4 my laptop (ICH8M controller) does not see Kingston SV300S37A60G SSD disk connected into a SATA connector on wake from suspend. The problem was introduced in c312ef176399 ("libata/ahci: Drop PCS quirk for Denverton and beyond"): the quirk is not applied on wake from suspend as it originally was.

It is worth to mention the commit contained another bug: the quirk is not applied at all to controllers which require it. The fix commit 09d6ac8dc51a ("libata/ahci: Fix PCS quirk application") landed in 5.3.8. So testing my patch anywhere between commits c312ef176399 and 09d6ac8dc51a is pointless.

Not all disks trigger the problem. For example nothing bad happens with Western Digital WD5000LPCX HDD.

Test hardware: - Acer 5920G with ICH8M SATA controller - sda: some SATA HDD connnected into the DVD drive IDE port with a SATA-IDE caddy. It is a boot disk - sdb: Kingston SV300S37A60G SSD connected into the only SATA port

Sample "dmesg --notime | grep -E '^(sd |ata)'" output on wake:

sd 0:0:0:0: [sda] Starting disk sd 2:0:0:0: [sdb] Starting disk ata4: SATA link down (SStatus 4 SControl 300) ata3: SATA link down (SStatus 4 SControl 300) ata1.00: ACPI cmd ef/03:0c:00:00:00:a0 (SET FEATURES) filtered out ata1.00: ACPI cmd ef/03:42:00:00:00:a0 (SET FEATURES) filtered out ata1: FORCE: cable set to 80c ata5: SATA link down (SStatus 0 SControl 300) ata3: SATA link down (SStatus 4 SControl 300) ata3: SATA link down (SStatus 4 SControl 300) ata3.00: disabled sd 2:0:0:0: rejecting I/O to offline device ata3.00: detaching (SCSI 2:0:0:0) sd 2:0:0:0: [sdb] Start/Stop Unit failed: Result: hostbyte=DID_NO_CONNECT driverbyte=DRIVER_OK sd 2:0:0:0: [sdb] Synchronizing SCSI cache sd 2:0:0:0: [sdb] Synchronize Cache(10) failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK sd 2:0:0:0: [sdb] Stopping disk sd 2:0:0:0: [sdb] Start/Stop Unit failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK

Commit c312ef176399 dropped ahci_pci_reset_controller() which internally calls ahci_reset_controller() and applies the PCS quirk if needed after that. It was called each time a reset was required instead of just ahci_reset_controller(). This patch puts the function back in place.

Fixes: c312ef176399 ("libata/ahci: Drop PCS quirk for Denverton and beyond") Signed-off-by: Adam Vodopjan grozzly@protonmail.com Signed-off-by: Damien Le Moal damien.lemoal@opensource.wdc.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/ata/ahci.c | 32 +++++++++++++++++++++++--------- 1 file changed, 23 insertions(+), 9 deletions(-)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index c1eca72b4575..28d8c56cb4dd 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -84,6 +84,7 @@ enum board_ids { static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static void ahci_remove_one(struct pci_dev *dev); static void ahci_shutdown_one(struct pci_dev *dev); +static void ahci_intel_pcs_quirk(struct pci_dev *pdev, struct ahci_host_priv *hpriv); static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline); static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class, @@ -677,6 +678,25 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev, ahci_save_initial_config(&pdev->dev, hpriv); }

+static int ahci_pci_reset_controller(struct ata_host *host) +{ + struct pci_dev *pdev = to_pci_dev(host->dev); + struct ahci_host_priv *hpriv = host->private_data; + int rc; + + rc = ahci_reset_controller(host); + if (rc) + return rc; + + /* + * If platform firmware failed to enable ports, try to enable + * them here. + */ + ahci_intel_pcs_quirk(pdev, hpriv); + + return 0; +} + static void ahci_pci_init_controller(struct ata_host *host) { struct ahci_host_priv *hpriv = host->private_data; @@ -871,7 +891,7 @@ static int ahci_pci_device_runtime_resume(struct device *dev) struct ata_host *host = pci_get_drvdata(pdev); int rc;

- rc = ahci_reset_controller(host); + rc = ahci_pci_reset_controller(host); if (rc) return rc; ahci_pci_init_controller(host); @@ -907,7 +927,7 @@ static int ahci_pci_device_resume(struct device *dev) ahci_mcp89_apple_enable(pdev);

if (pdev->dev.power.power_state.event == PM_EVENT_SUSPEND) { - rc = ahci_reset_controller(host); + rc = ahci_pci_reset_controller(host); if (rc) return rc;

@@ -1788,12 +1808,6 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* save initial config */ ahci_pci_save_initial_config(pdev, hpriv);

- /* - * If platform firmware failed to enable ports, try to enable - * them here. - */ - ahci_intel_pcs_quirk(pdev, hpriv); - /* prepare host */ if (hpriv->cap & HOST_CAP_NCQ) { pi.flags |= ATA_FLAG_NCQ; @@ -1903,7 +1917,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) return rc;

- rc = ahci_reset_controller(host); + rc = ahci_pci_reset_controller(host); if (rc) return rc;

From: Christoph Hellwig hch@lst.de

[ Upstream commit 2a459f6933e1c459bffb7cc73fd6c900edc714bd ]

Mask out the "Command Supported" and "Logical Block Content Change" bits and only defer execution of commands that have non-trivial effects to the workqueue for synchronous execution. This allows to execute admin commands asynchronously on controllers that provide a Command Supported and Effects log page, and will keep allowing to execute Write commands asynchronously once command effects on I/O commands are taken into account.

Fixes: c1fef73f793b ("nvmet: add passthru code to process commands") Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Keith Busch kbusch@kernel.org Reviewed-by: Sagi Grimberg sagi@grimberg.me Reviewed-by: Kanchan Joshi joshi.k@samsung.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/target/passthru.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 94d3153bae54..09537000d817 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -333,14 +333,13 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req) }

/* - * If there are effects for the command we are about to execute, or - * an end_req function we need to use nvme_execute_passthru_rq() - * synchronously in a work item seeing the end_req function and - * nvme_passthru_end() can't be called in the request done callback - * which is typically in interrupt context. + * If a command needs post-execution fixups, or there are any + * non-trivial effects, make sure to execute the command synchronously + * in a workqueue so that nvme_passthru_end gets called. */ effects = nvme_command_effects(ctrl, ns, req->cmd->common.opcode); - if (req->p.use_workqueue || effects) { + if (req->p.use_workqueue || + (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))) { INIT_WORK(&req->p.work, nvmet_passthru_execute_cmd_work); req->p.rq = rq; queue_work(nvmet_wq, &req->p.work);

From: edward lo edward.lo@ambergroup.io

[ Upstream commit e19c6277652efba203af4ecd8eed4bd30a0054c9 ]

The offset addition could overflow and pass the used size check given an attribute with very large size (e.g., 0xffffff7f) while parsing MFT attributes. This could lead to out-of-bound memory R/W if we try to access the next attribute derived by Add2Ptr(attr, asize)

[ 32.963847] BUG: unable to handle page fault for address: ffff956a83c76067 [ 32.964301] #PF: supervisor read access in kernel mode [ 32.964526] #PF: error_code(0x0000) - not-present page [ 32.964893] PGD 4dc01067 P4D 4dc01067 PUD 0 [ 32.965316] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 32.965727] CPU: 0 PID: 243 Comm: mount Not tainted 5.19.0+ #6 [ 32.966050] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 32.966628] RIP: 0010:mi_enum_attr+0x44/0x110 [ 32.967239] Code: 89 f0 48 29 c8 48 89 c1 39 c7 0f 86 94 00 00 00 8b 56 04 83 fa 17 0f 86 88 00 00 00 89 d0 01 ca 48 01 f0 8d 4a 08 39 f9a [ 32.968101] RSP: 0018:ffffba15c06a7c38 EFLAGS: 00000283 [ 32.968364] RAX: ffff956a83c76067 RBX: ffff956983c76050 RCX: 000000000000006f [ 32.968651] RDX: 0000000000000067 RSI: ffff956983c760e8 RDI: 00000000000001c8 [ 32.968963] RBP: ffffba15c06a7c38 R08: 0000000000000064 R09: 00000000ffffff7f [ 32.969249] R10: 0000000000000007 R11: ffff956983c760e8 R12: ffff95698225e000 [ 32.969870] R13: 0000000000000000 R14: ffffba15c06a7cd8 R15: ffff95698225e170 [ 32.970655] FS: 00007fdab8189e40(0000) GS:ffff9569fdc00000(0000) knlGS:0000000000000000 [ 32.971098] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 32.971378] CR2: ffff956a83c76067 CR3: 0000000002c58000 CR4: 00000000000006f0 [ 32.972098] Call Trace: [ 32.972842] <TASK> [ 32.973341] ni_enum_attr_ex+0xda/0xf0 [ 32.974087] ntfs_iget5+0x1db/0xde0 [ 32.974386] ? slab_post_alloc_hook+0x53/0x270 [ 32.974778] ? ntfs_fill_super+0x4c7/0x12a0 [ 32.975115] ntfs_fill_super+0x5d6/0x12a0 [ 32.975336] get_tree_bdev+0x175/0x270 [ 32.975709] ? put_ntfs+0x150/0x150 [ 32.975956] ntfs_fs_get_tree+0x15/0x20 [ 32.976191] vfs_get_tree+0x2a/0xc0 [ 32.976374] ? capable+0x19/0x20 [ 32.976572] path_mount+0x484/0xaa0 [ 32.977025] ? putname+0x57/0x70 [ 32.977380] do_mount+0x80/0xa0 [ 32.977555] __x64_sys_mount+0x8b/0xe0 [ 32.978105] do_syscall_64+0x3b/0x90 [ 32.978830] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 32.979311] RIP: 0033:0x7fdab72e948a [ 32.980015] Code: 48 8b 0d 11 fa 2a 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 008 [ 32.981251] RSP: 002b:00007ffd15b87588 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 [ 32.981832] RAX: ffffffffffffffda RBX: 0000557de0aaf060 RCX: 00007fdab72e948a [ 32.982234] RDX: 0000557de0aaf260 RSI: 0000557de0aaf2e0 RDI: 0000557de0ab7ce0 [ 32.982714] RBP: 0000000000000000 R08: 0000557de0aaf280 R09: 0000000000000020 [ 32.983046] R10: 00000000c0ed0000 R11: 0000000000000206 R12: 0000557de0ab7ce0 [ 32.983494] R13: 0000557de0aaf260 R14: 0000000000000000 R15: 00000000ffffffff [ 32.984094] </TASK> [ 32.984352] Modules linked in: [ 32.984753] CR2: ffff956a83c76067 [ 32.985911] ---[ end trace 0000000000000000 ]--- [ 32.986555] RIP: 0010:mi_enum_attr+0x44/0x110 [ 32.987217] Code: 89 f0 48 29 c8 48 89 c1 39 c7 0f 86 94 00 00 00 8b 56 04 83 fa 17 0f 86 88 00 00 00 89 d0 01 ca 48 01 f0 8d 4a 08 39 f9a [ 32.988232] RSP: 0018:ffffba15c06a7c38 EFLAGS: 00000283 [ 32.988532] RAX: ffff956a83c76067 RBX: ffff956983c76050 RCX: 000000000000006f [ 32.988916] RDX: 0000000000000067 RSI: ffff956983c760e8 RDI: 00000000000001c8 [ 32.989356] RBP: ffffba15c06a7c38 R08: 0000000000000064 R09: 00000000ffffff7f [ 32.989994] R10: 0000000000000007 R11: ffff956983c760e8 R12: ffff95698225e000 [ 32.990415] R13: 0000000000000000 R14: ffffba15c06a7cd8 R15: ffff95698225e170 [ 32.991011] FS: 00007fdab8189e40(0000) GS:ffff9569fdc00000(0000) knlGS:0000000000000000 [ 32.991524] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 32.991936] CR2: ffff956a83c76067 CR3: 0000000002c58000 CR4: 00000000000006f0

This patch adds an overflow check

Signed-off-by: edward lo edward.lo@ambergroup.io Signed-off-by: Konstantin Komarov almaz.alexandrovich@paragon-software.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ntfs3/record.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 7d2fac5ee215..9f81944441ae 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -220,6 +220,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return NULL; }

+ if (off + asize < off) { + /* overflow check */ + return NULL; + } + attr = Add2Ptr(attr, asize); off += asize; }

From: Edward Lo edward.lo@ambergroup.io

[ Upstream commit 2681631c29739509eec59cc0b34e977bb04c6cf1 ]

Some metadata files are handled before MFT. This adds a null pointer check for some corner cases that could lead to NPD while reading these metadata files for a malformed NTFS image.

[ 240.190827] BUG: kernel NULL pointer dereference, address: 0000000000000158 [ 240.191583] #PF: supervisor read access in kernel mode [ 240.191956] #PF: error_code(0x0000) - not-present page [ 240.192391] PGD 0 P4D 0 [ 240.192897] Oops: 0000 [#1] PREEMPT SMP KASAN NOPTI [ 240.193805] CPU: 0 PID: 242 Comm: mount Tainted: G B 5.19.0+ #17 [ 240.194477] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 240.195152] RIP: 0010:ni_find_attr+0xae/0x300 [ 240.195679] Code: c8 48 c7 45 88 c0 4e 5e 86 c7 00 f1 f1 f1 f1 c7 40 04 00 f3 f3 f3 65 48 8b 04 25 28 00 00 00 48 89 45 d0 31 c0 e8 e2 d9f [ 240.196642] RSP: 0018:ffff88800812f690 EFLAGS: 00000286 [ 240.197019] RAX: 0000000000000001 RBX: 0000000000000000 RCX: ffffffff85ef037a [ 240.197523] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffffffff88e95f60 [ 240.197877] RBP: ffff88800812f738 R08: 0000000000000001 R09: fffffbfff11d2bed [ 240.198292] R10: ffffffff88e95f67 R11: fffffbfff11d2bec R12: 0000000000000000 [ 240.198647] R13: 0000000000000080 R14: 0000000000000000 R15: 0000000000000000 [ 240.199410] FS: 00007f233c33be40(0000) GS:ffff888058200000(0000) knlGS:0000000000000000 [ 240.199895] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 240.200314] CR2: 0000000000000158 CR3: 0000000004d32000 CR4: 00000000000006f0 [ 240.200839] Call Trace: [ 240.201104] <TASK> [ 240.201502] ? ni_load_mi+0x80/0x80 [ 240.202297] ? ___slab_alloc+0x465/0x830 [ 240.202614] attr_load_runs_vcn+0x8c/0x1a0 [ 240.202886] ? __kasan_slab_alloc+0x32/0x90 [ 240.203157] ? attr_data_write_resident+0x250/0x250 [ 240.203543] mi_read+0x133/0x2c0 [ 240.203785] mi_get+0x70/0x140 [ 240.204012] ni_load_mi_ex+0xfa/0x190 [ 240.204346] ? ni_std5+0x90/0x90 [ 240.204588] ? __kasan_kmalloc+0x88/0xb0 [ 240.204859] ni_enum_attr_ex+0xf1/0x1c0 [ 240.205107] ? ni_fname_type.part.0+0xd0/0xd0 [ 240.205600] ? ntfs_load_attr_list+0xbe/0x300 [ 240.205864] ? ntfs_cmp_names_cpu+0x125/0x180 [ 240.206157] ntfs_iget5+0x56c/0x1870 [ 240.206510] ? ntfs_get_block_bmap+0x70/0x70 [ 240.206776] ? __kasan_kmalloc+0x88/0xb0 [ 240.207030] ? set_blocksize+0x95/0x150 [ 240.207545] ntfs_fill_super+0xb8f/0x1e20 [ 240.207839] ? put_ntfs+0x1d0/0x1d0 [ 240.208069] ? vsprintf+0x20/0x20 [ 240.208467] ? mutex_unlock+0x81/0xd0 [ 240.208846] ? set_blocksize+0x95/0x150 [ 240.209221] get_tree_bdev+0x232/0x370 [ 240.209804] ? put_ntfs+0x1d0/0x1d0 [ 240.210519] ntfs_fs_get_tree+0x15/0x20 [ 240.210991] vfs_get_tree+0x4c/0x130 [ 240.211455] path_mount+0x645/0xfd0 [ 240.211806] ? putname+0x80/0xa0 [ 240.212112] ? finish_automount+0x2e0/0x2e0 [ 240.212559] ? kmem_cache_free+0x110/0x390 [ 240.212906] ? putname+0x80/0xa0 [ 240.213329] do_mount+0xd6/0xf0 [ 240.213829] ? path_mount+0xfd0/0xfd0 [ 240.214246] ? __kasan_check_write+0x14/0x20 [ 240.214774] __x64_sys_mount+0xca/0x110 [ 240.215080] do_syscall_64+0x3b/0x90 [ 240.215442] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 240.215811] RIP: 0033:0x7f233b4e948a [ 240.216104] Code: 48 8b 0d 11 fa 2a 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 008 [ 240.217615] RSP: 002b:00007fff02211ec8 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 [ 240.218718] RAX: ffffffffffffffda RBX: 0000561cdc35b060 RCX: 00007f233b4e948a [ 240.219556] RDX: 0000561cdc35b260 RSI: 0000561cdc35b2e0 RDI: 0000561cdc363af0 [ 240.219975] RBP: 0000000000000000 R08: 0000561cdc35b280 R09: 0000000000000020 [ 240.220403] R10: 00000000c0ed0000 R11: 0000000000000202 R12: 0000561cdc363af0 [ 240.220803] R13: 0000561cdc35b260 R14: 0000000000000000 R15: 00000000ffffffff [ 240.221256] </TASK> [ 240.221567] Modules linked in: [ 240.222028] CR2: 0000000000000158 [ 240.223291] ---[ end trace 0000000000000000 ]--- [ 240.223669] RIP: 0010:ni_find_attr+0xae/0x300 [ 240.224058] Code: c8 48 c7 45 88 c0 4e 5e 86 c7 00 f1 f1 f1 f1 c7 40 04 00 f3 f3 f3 65 48 8b 04 25 28 00 00 00 48 89 45 d0 31 c0 e8 e2 d9f [ 240.225033] RSP: 0018:ffff88800812f690 EFLAGS: 00000286 [ 240.225968] RAX: 0000000000000001 RBX: 0000000000000000 RCX: ffffffff85ef037a [ 240.226624] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffffffff88e95f60 [ 240.227307] RBP: ffff88800812f738 R08: 0000000000000001 R09: fffffbfff11d2bed [ 240.227816] R10: ffffffff88e95f67 R11: fffffbfff11d2bec R12: 0000000000000000 [ 240.228330] R13: 0000000000000080 R14: 0000000000000000 R15: 0000000000000000 [ 240.228729] FS: 00007f233c33be40(0000) GS:ffff888058200000(0000) knlGS:0000000000000000 [ 240.229281] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 240.230298] CR2: 0000000000000158 CR3: 0000000004d32000 CR4: 00000000000006f0

Signed-off-by: Edward Lo edward.lo@ambergroup.io Signed-off-by: Konstantin Komarov almaz.alexandrovich@paragon-software.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ntfs3/attrib.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 0d354560d323..578c2bcfb1d9 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -1221,6 +1221,11 @@ int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST svcn, evcn; u16 ro;

+ if (!ni) { + /* Is record corrupted? */ + return -ENOENT; + } + attr = ni_find_attr(ni, NULL, NULL, type, name, name_len, &vcn, NULL); if (!attr) { /* Is record corrupted? */

From: Edward Lo edward.lo@ambergroup.io

[ Upstream commit c1ca8ef0262b25493631ecbd9cb8c9893e1481a1 ]

This adds a sanity check for the i_op pointer of the inode which is returned after reading Root directory MFT record. We should check the i_op is valid before trying to create the root dentry, otherwise we may encounter a NPD while mounting a image with a funny Root directory MFT record.

[ 114.484325] BUG: kernel NULL pointer dereference, address: 0000000000000008 [ 114.484811] #PF: supervisor read access in kernel mode [ 114.485084] #PF: error_code(0x0000) - not-present page [ 114.485606] PGD 0 P4D 0 [ 114.485975] Oops: 0000 [#1] PREEMPT SMP KASAN NOPTI [ 114.486570] CPU: 0 PID: 237 Comm: mount Tainted: G B 6.0.0-rc4 #28 [ 114.486977] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 114.488169] RIP: 0010:d_flags_for_inode+0xe0/0x110 [ 114.488816] Code: 24 f7 ff 49 83 3e 00 74 41 41 83 cd 02 66 44 89 6b 02 eb 92 48 8d 7b 20 e8 6d 24 f7 ff 4c 8b 73 20 49 8d 7e 08 e8 60 241 [ 114.490326] RSP: 0018:ffff8880065e7aa8 EFLAGS: 00000296 [ 114.490695] RAX: 0000000000000001 RBX: ffff888008ccd750 RCX: ffffffff84af2aea [ 114.490986] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffffffff87abd020 [ 114.491364] RBP: ffff8880065e7ac8 R08: 0000000000000001 R09: fffffbfff0f57a05 [ 114.491675] R10: ffffffff87abd027 R11: fffffbfff0f57a04 R12: 0000000000000000 [ 114.491954] R13: 0000000000000008 R14: 0000000000000000 R15: ffff888008ccd750 [ 114.492397] FS: 00007fdc8a627e40(0000) GS:ffff888058200000(0000) knlGS:0000000000000000 [ 114.492797] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 114.493150] CR2: 0000000000000008 CR3: 00000000013ba000 CR4: 00000000000006f0 [ 114.493671] Call Trace: [ 114.493890] <TASK> [ 114.494075] __d_instantiate+0x24/0x1c0 [ 114.494505] d_instantiate.part.0+0x35/0x50 [ 114.494754] d_make_root+0x53/0x80 [ 114.494998] ntfs_fill_super+0x1232/0x1b50 [ 114.495260] ? put_ntfs+0x1d0/0x1d0 [ 114.495499] ? vsprintf+0x20/0x20 [ 114.495723] ? set_blocksize+0x95/0x150 [ 114.495964] get_tree_bdev+0x232/0x370 [ 114.496272] ? put_ntfs+0x1d0/0x1d0 [ 114.496502] ntfs_fs_get_tree+0x15/0x20 [ 114.496859] vfs_get_tree+0x4c/0x130 [ 114.497099] path_mount+0x654/0xfe0 [ 114.497507] ? putname+0x80/0xa0 [ 114.497933] ? finish_automount+0x2e0/0x2e0 [ 114.498362] ? putname+0x80/0xa0 [ 114.498571] ? kmem_cache_free+0x1c4/0x440 [ 114.498819] ? putname+0x80/0xa0 [ 114.499069] do_mount+0xd6/0xf0 [ 114.499343] ? path_mount+0xfe0/0xfe0 [ 114.499683] ? __kasan_check_write+0x14/0x20 [ 114.500133] __x64_sys_mount+0xca/0x110 [ 114.500592] do_syscall_64+0x3b/0x90 [ 114.500930] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 114.501294] RIP: 0033:0x7fdc898e948a [ 114.501542] Code: 48 8b 0d 11 fa 2a 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 008 [ 114.502716] RSP: 002b:00007ffd793e58f8 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 [ 114.503175] RAX: ffffffffffffffda RBX: 0000564b2228f060 RCX: 00007fdc898e948a [ 114.503588] RDX: 0000564b2228f260 RSI: 0000564b2228f2e0 RDI: 0000564b22297ce0 [ 114.504925] RBP: 0000000000000000 R08: 0000564b2228f280 R09: 0000000000000020 [ 114.505484] R10: 00000000c0ed0000 R11: 0000000000000202 R12: 0000564b22297ce0 [ 114.505823] R13: 0000564b2228f260 R14: 0000000000000000 R15: 00000000ffffffff [ 114.506562] </TASK> [ 114.506887] Modules linked in: [ 114.507648] CR2: 0000000000000008 [ 114.508884] ---[ end trace 0000000000000000 ]--- [ 114.509675] RIP: 0010:d_flags_for_inode+0xe0/0x110 [ 114.510140] Code: 24 f7 ff 49 83 3e 00 74 41 41 83 cd 02 66 44 89 6b 02 eb 92 48 8d 7b 20 e8 6d 24 f7 ff 4c 8b 73 20 49 8d 7e 08 e8 60 241 [ 114.511762] RSP: 0018:ffff8880065e7aa8 EFLAGS: 00000296 [ 114.512401] RAX: 0000000000000001 RBX: ffff888008ccd750 RCX: ffffffff84af2aea [ 114.513103] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffffffff87abd020 [ 114.513512] RBP: ffff8880065e7ac8 R08: 0000000000000001 R09: fffffbfff0f57a05 [ 114.513831] R10: ffffffff87abd027 R11: fffffbfff0f57a04 R12: 0000000000000000 [ 114.514757] R13: 0000000000000008 R14: 0000000000000000 R15: ffff888008ccd750 [ 114.515411] FS: 00007fdc8a627e40(0000) GS:ffff888058200000(0000) knlGS:0000000000000000 [ 114.515794] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 114.516208] CR2: 0000000000000008 CR3: 00000000013ba000 CR4: 00000000000006f0

Signed-off-by: Edward Lo edward.lo@ambergroup.io Signed-off-by: Konstantin Komarov almaz.alexandrovich@paragon-software.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ntfs3/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 170682c2bf67..94f9e4b775a7 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1260,9 +1260,9 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.low = cpu_to_le32(MFT_REC_ROOT); ref.seq = cpu_to_le16(MFT_REC_ROOT); inode = ntfs_iget5(sb, &ref, &NAME_ROOT); - if (IS_ERR(inode)) { + if (IS_ERR(inode) || !inode->i_op) { ntfs_err(sb, "Failed to load root."); - err = PTR_ERR(inode); + err = IS_ERR(inode) ? PTR_ERR(inode) : -EINVAL; goto out; }

From: Edward Lo edward.lo@ambergroup.io

[ Upstream commit 4d42ecda239cc13738d6fd84d098a32e67b368b9 ]

indx_read is called when we have some NTFS directory operations that need more information from the index buffers. This adds a sanity check to make sure the returned index buffer length is legit, or we may have some out-of-bound memory accesses.

[ 560.897595] BUG: KASAN: slab-out-of-bounds in hdr_find_e.isra.0+0x10c/0x320 [ 560.898321] Read of size 2 at addr ffff888009497238 by task exp/245 [ 560.898760] [ 560.899129] CPU: 0 PID: 245 Comm: exp Not tainted 6.0.0-rc6 #37 [ 560.899505] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 560.900170] Call Trace: [ 560.900407] <TASK> [ 560.900732] dump_stack_lvl+0x49/0x63 [ 560.901108] print_report.cold+0xf5/0x689 [ 560.901395] ? hdr_find_e.isra.0+0x10c/0x320 [ 560.901716] kasan_report+0xa7/0x130 [ 560.901950] ? hdr_find_e.isra.0+0x10c/0x320 [ 560.902208] __asan_load2+0x68/0x90 [ 560.902427] hdr_find_e.isra.0+0x10c/0x320 [ 560.902846] ? cmp_uints+0xe0/0xe0 [ 560.903363] ? cmp_sdh+0x90/0x90 [ 560.903883] ? ntfs_bread_run+0x190/0x190 [ 560.904196] ? rwsem_down_read_slowpath+0x750/0x750 [ 560.904969] ? ntfs_fix_post_read+0xe0/0x130 [ 560.905259] ? __kasan_check_write+0x14/0x20 [ 560.905599] ? up_read+0x1a/0x90 [ 560.905853] ? indx_read+0x22c/0x380 [ 560.906096] indx_find+0x2ef/0x470 [ 560.906352] ? indx_find_buffer+0x2d0/0x2d0 [ 560.906692] ? __kasan_kmalloc+0x88/0xb0 [ 560.906977] dir_search_u+0x196/0x2f0 [ 560.907220] ? ntfs_nls_to_utf16+0x450/0x450 [ 560.907464] ? __kasan_check_write+0x14/0x20 [ 560.907747] ? mutex_lock+0x8f/0xe0 [ 560.907970] ? __mutex_lock_slowpath+0x20/0x20 [ 560.908214] ? kmem_cache_alloc+0x143/0x4b0 [ 560.908459] ntfs_lookup+0xe0/0x100 [ 560.908788] __lookup_slow+0x116/0x220 [ 560.909050] ? lookup_fast+0x1b0/0x1b0 [ 560.909309] ? lookup_fast+0x13f/0x1b0 [ 560.909601] walk_component+0x187/0x230 [ 560.909944] link_path_walk.part.0+0x3f0/0x660 [ 560.910285] ? handle_lookup_down+0x90/0x90 [ 560.910618] ? path_init+0x642/0x6e0 [ 560.911084] ? percpu_counter_add_batch+0x6e/0xf0 [ 560.912559] ? __alloc_file+0x114/0x170 [ 560.913008] path_openat+0x19c/0x1d10 [ 560.913419] ? getname_flags+0x73/0x2b0 [ 560.913815] ? kasan_save_stack+0x3a/0x50 [ 560.914125] ? kasan_save_stack+0x26/0x50 [ 560.914542] ? __kasan_slab_alloc+0x6d/0x90 [ 560.914924] ? kmem_cache_alloc+0x143/0x4b0 [ 560.915339] ? getname_flags+0x73/0x2b0 [ 560.915647] ? getname+0x12/0x20 [ 560.916114] ? __x64_sys_open+0x4c/0x60 [ 560.916460] ? path_lookupat.isra.0+0x230/0x230 [ 560.916867] ? __isolate_free_page+0x2e0/0x2e0 [ 560.917194] do_filp_open+0x15c/0x1f0 [ 560.917448] ? may_open_dev+0x60/0x60 [ 560.917696] ? expand_files+0xa4/0x3a0 [ 560.917923] ? __kasan_check_write+0x14/0x20 [ 560.918185] ? _raw_spin_lock+0x88/0xdb [ 560.918409] ? _raw_spin_lock_irqsave+0x100/0x100 [ 560.918783] ? _find_next_bit+0x4a/0x130 [ 560.919026] ? _raw_spin_unlock+0x19/0x40 [ 560.919276] ? alloc_fd+0x14b/0x2d0 [ 560.919635] do_sys_openat2+0x32a/0x4b0 [ 560.920035] ? file_open_root+0x230/0x230 [ 560.920336] ? __rcu_read_unlock+0x5b/0x280 [ 560.920813] do_sys_open+0x99/0xf0 [ 560.921208] ? filp_open+0x60/0x60 [ 560.921482] ? exit_to_user_mode_prepare+0x49/0x180 [ 560.921867] __x64_sys_open+0x4c/0x60 [ 560.922128] do_syscall_64+0x3b/0x90 [ 560.922369] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 560.923030] RIP: 0033:0x7f7dff2e4469 [ 560.923681] Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 088 [ 560.924451] RSP: 002b:00007ffd41a210b8 EFLAGS: 00000206 ORIG_RAX: 0000000000000002 [ 560.925168] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f7dff2e4469 [ 560.925655] RDX: 0000000000000000 RSI: 0000000000000002 RDI: 00007ffd41a211f0 [ 560.926085] RBP: 00007ffd41a252a0 R08: 00007f7dff60fba0 R09: 00007ffd41a25388 [ 560.926405] R10: 0000000000400b80 R11: 0000000000000206 R12: 00000000004004e0 [ 560.926867] R13: 00007ffd41a25380 R14: 0000000000000000 R15: 0000000000000000 [ 560.927241] </TASK> [ 560.927491] [ 560.927755] Allocated by task 245: [ 560.928409] kasan_save_stack+0x26/0x50 [ 560.929271] __kasan_kmalloc+0x88/0xb0 [ 560.929778] __kmalloc+0x192/0x320 [ 560.930023] indx_read+0x249/0x380 [ 560.930224] indx_find+0x2a2/0x470 [ 560.930695] dir_search_u+0x196/0x2f0 [ 560.930892] ntfs_lookup+0xe0/0x100 [ 560.931115] __lookup_slow+0x116/0x220 [ 560.931323] walk_component+0x187/0x230 [ 560.931570] link_path_walk.part.0+0x3f0/0x660 [ 560.931791] path_openat+0x19c/0x1d10 [ 560.932008] do_filp_open+0x15c/0x1f0 [ 560.932226] do_sys_openat2+0x32a/0x4b0 [ 560.932413] do_sys_open+0x99/0xf0 [ 560.932709] __x64_sys_open+0x4c/0x60 [ 560.933417] do_syscall_64+0x3b/0x90 [ 560.933776] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 560.934235] [ 560.934486] The buggy address belongs to the object at ffff888009497000 [ 560.934486] which belongs to the cache kmalloc-512 of size 512 [ 560.935239] The buggy address is located 56 bytes to the right of [ 560.935239] 512-byte region [ffff888009497000, ffff888009497200) [ 560.936153] [ 560.937326] The buggy address belongs to the physical page: [ 560.938228] page:0000000062a3dfae refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x9496 [ 560.939616] head:0000000062a3dfae order:1 compound_mapcount:0 compound_pincount:0 [ 560.940219] flags: 0xfffffc0010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) [ 560.942702] raw: 000fffffc0010200 ffffea0000164f80 dead000000000005 ffff888001041c80 [ 560.943932] raw: 0000000000000000 0000000080080008 00000001ffffffff 0000000000000000 [ 560.944568] page dumped because: kasan: bad access detected [ 560.945735] [ 560.946112] Memory state around the buggy address: [ 560.946870] ffff888009497100: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 560.947242] ffff888009497180: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 560.947611] >ffff888009497200: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 560.947915] ^ [ 560.948249] ffff888009497280: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 560.948687] ffff888009497300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc

Signed-off-by: Edward Lo edward.lo@ambergroup.io Signed-off-by: Konstantin Komarov almaz.alexandrovich@paragon-software.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ntfs3/index.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 440328147e7e..c27b4fe57513 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1017,6 +1017,12 @@ int indx_read(struct ntfs_index *indx, struct ntfs_inode *ni, CLST vbn, err = 0; }

+ /* check for index header length */ + if (offsetof(struct INDEX_BUFFER, ihdr) + ib->ihdr.used > bytes) { + err = -EINVAL; + goto out; + } + in->index = ib; *node = in;

From: Hawkins Jiawei yin31149@gmail.com

[ Upstream commit 887bfc546097fbe8071dac13b2fef73b77920899 ]

Syzkaller reports slab-out-of-bounds bug as follows: ================================================================== BUG: KASAN: slab-out-of-bounds in run_unpack+0x8b7/0x970 fs/ntfs3/run.c:944 Read of size 1 at addr ffff88801bbdff02 by task syz-executor131/3611

[...] Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:317 [inline] print_report.cold+0x2ba/0x719 mm/kasan/report.c:433 kasan_report+0xb1/0x1e0 mm/kasan/report.c:495 run_unpack+0x8b7/0x970 fs/ntfs3/run.c:944 run_unpack_ex+0xb0/0x7c0 fs/ntfs3/run.c:1057 ntfs_read_mft fs/ntfs3/inode.c:368 [inline] ntfs_iget5+0xc20/0x3280 fs/ntfs3/inode.c:501 ntfs_loadlog_and_replay+0x124/0x5d0 fs/ntfs3/fsntfs.c:272 ntfs_fill_super+0x1eff/0x37f0 fs/ntfs3/super.c:1018 get_tree_bdev+0x440/0x760 fs/super.c:1323 vfs_get_tree+0x89/0x2f0 fs/super.c:1530 do_new_mount fs/namespace.c:3040 [inline] path_mount+0x1326/0x1e20 fs/namespace.c:3370 do_mount fs/namespace.c:3383 [inline] __do_sys_mount fs/namespace.c:3591 [inline] __se_sys_mount fs/namespace.c:3568 [inline] __x64_sys_mount+0x27f/0x300 fs/namespace.c:3568 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd [...] </TASK>

The buggy address belongs to the physical page: page:ffffea00006ef600 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1bbd8 head:ffffea00006ef600 order:3 compound_mapcount:0 compound_pincount:0 flags: 0xfff00000010200(slab|head|node=0|zone=1|lastcpupid=0x7ff) page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff88801bbdfe00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88801bbdfe80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc

ffff88801bbdff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc

^ ffff88801bbdff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88801bbe0000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ==================================================================

Kernel will tries to read record and parse MFT from disk in ntfs_read_mft().

Yet the problem is that during enumerating attributes in record, kernel doesn't check whether run_off field loading from the disk is a valid value.

To be more specific, if attr->nres.run_off is larger than attr->size, kernel will passes an invalid argument run_buf_size in run_unpack_ex(), which having an integer overflow. Then this invalid argument will triggers the slab-out-of-bounds Read bug as above.

This patch solves it by adding the sanity check between the offset to packed runs and attribute size.

link: https://lore.kernel.org/all/0000000000009145fc05e94bd5c3@google.com/#t Reported-and-tested-by: syzbot+8d6fbb27a6aded64b25b@syzkaller.appspotmail.com Signed-off-by: Hawkins Jiawei yin31149@gmail.com Signed-off-by: Konstantin Komarov almaz.alexandrovich@paragon-software.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ntfs3/inode.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 791d049a9ad7..ba2005c12ee3 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -373,6 +373,13 @@ static struct inode *ntfs_read_mft(struct inode *inode, }

t64 = le64_to_cpu(attr->nres.svcn); + + /* offset to packed runs is out-of-bounds */ + if (roff > asize) { + err = -EINVAL; + goto out; + } + err = run_unpack_ex(run, sbi, ino, t64, le64_to_cpu(attr->nres.evcn), t64, Add2Ptr(attr, roff), asize - roff); if (err < 0)

From: Edward Lo edward.lo@ambergroup.io

[ Upstream commit bfcdbae0523bd95eb75a739ffb6221a37109881e ]

This enhances the sanity check for $SDH and $SII while initializing NTFS security, guarantees these index root are legit.

[ 162.459513] BUG: KASAN: use-after-free in hdr_find_e.isra.0+0x10c/0x320 [ 162.460176] Read of size 2 at addr ffff8880037bca99 by task mount/243 [ 162.460851] [ 162.461252] CPU: 0 PID: 243 Comm: mount Not tainted 6.0.0-rc7 #42 [ 162.461744] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 162.462609] Call Trace: [ 162.462954] <TASK> [ 162.463276] dump_stack_lvl+0x49/0x63 [ 162.463822] print_report.cold+0xf5/0x689 [ 162.464608] ? unwind_get_return_address+0x3a/0x60 [ 162.465766] ? hdr_find_e.isra.0+0x10c/0x320 [ 162.466975] kasan_report+0xa7/0x130 [ 162.467506] ? _raw_spin_lock_irq+0xc0/0xf0 [ 162.467998] ? hdr_find_e.isra.0+0x10c/0x320 [ 162.468536] __asan_load2+0x68/0x90 [ 162.468923] hdr_find_e.isra.0+0x10c/0x320 [ 162.469282] ? cmp_uints+0xe0/0xe0 [ 162.469557] ? cmp_sdh+0x90/0x90 [ 162.469864] ? ni_find_attr+0x214/0x300 [ 162.470217] ? ni_load_mi+0x80/0x80 [ 162.470479] ? entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 162.470931] ? ntfs_bread_run+0x190/0x190 [ 162.471307] ? indx_get_root+0xe4/0x190 [ 162.471556] ? indx_get_root+0x140/0x190 [ 162.471833] ? indx_init+0x1e0/0x1e0 [ 162.472069] ? fnd_clear+0x115/0x140 [ 162.472363] ? _raw_spin_lock_irqsave+0x100/0x100 [ 162.472731] indx_find+0x184/0x470 [ 162.473461] ? sysvec_apic_timer_interrupt+0x57/0xc0 [ 162.474429] ? indx_find_buffer+0x2d0/0x2d0 [ 162.474704] ? do_syscall_64+0x3b/0x90 [ 162.474962] dir_search_u+0x196/0x2f0 [ 162.475381] ? ntfs_nls_to_utf16+0x450/0x450 [ 162.475661] ? ntfs_security_init+0x3d6/0x440 [ 162.475906] ? is_sd_valid+0x180/0x180 [ 162.476191] ntfs_extend_init+0x13f/0x2c0 [ 162.476496] ? ntfs_fix_post_read+0x130/0x130 [ 162.476861] ? iput.part.0+0x286/0x320 [ 162.477325] ntfs_fill_super+0x11e0/0x1b50 [ 162.477709] ? put_ntfs+0x1d0/0x1d0 [ 162.477970] ? vsprintf+0x20/0x20 [ 162.478258] ? set_blocksize+0x95/0x150 [ 162.478538] get_tree_bdev+0x232/0x370 [ 162.478789] ? put_ntfs+0x1d0/0x1d0 [ 162.479038] ntfs_fs_get_tree+0x15/0x20 [ 162.479374] vfs_get_tree+0x4c/0x130 [ 162.479729] path_mount+0x654/0xfe0 [ 162.480124] ? putname+0x80/0xa0 [ 162.480484] ? finish_automount+0x2e0/0x2e0 [ 162.480894] ? putname+0x80/0xa0 [ 162.481467] ? kmem_cache_free+0x1c4/0x440 [ 162.482280] ? putname+0x80/0xa0 [ 162.482714] do_mount+0xd6/0xf0 [ 162.483264] ? path_mount+0xfe0/0xfe0 [ 162.484782] ? __kasan_check_write+0x14/0x20 [ 162.485593] __x64_sys_mount+0xca/0x110 [ 162.486024] do_syscall_64+0x3b/0x90 [ 162.486543] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 162.487141] RIP: 0033:0x7f9d374e948a [ 162.488324] Code: 48 8b 0d 11 fa 2a 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 008 [ 162.489728] RSP: 002b:00007ffe30e73d18 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 [ 162.490971] RAX: ffffffffffffffda RBX: 0000561cdb43a060 RCX: 00007f9d374e948a [ 162.491669] RDX: 0000561cdb43a260 RSI: 0000561cdb43a2e0 RDI: 0000561cdb442af0 [ 162.492050] RBP: 0000000000000000 R08: 0000561cdb43a280 R09: 0000000000000020 [ 162.492459] R10: 00000000c0ed0000 R11: 0000000000000206 R12: 0000561cdb442af0 [ 162.493183] R13: 0000561cdb43a260 R14: 0000000000000000 R15: 00000000ffffffff [ 162.493644] </TASK> [ 162.493908] [ 162.494214] The buggy address belongs to the physical page: [ 162.494761] page:000000003e38a3d5 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x37bc [ 162.496064] flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff) [ 162.497278] raw: 000fffffc0000000 ffffea00000df1c8 ffffea00000df008 0000000000000000 [ 162.498928] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 162.500542] page dumped because: kasan: bad access detected [ 162.501057] [ 162.501242] Memory state around the buggy address: [ 162.502230] ffff8880037bc980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 162.502977] ffff8880037bca00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 162.503522] >ffff8880037bca80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 162.503963] ^ [ 162.504370] ffff8880037bcb00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 162.504766] ffff8880037bcb80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

Signed-off-by: Edward Lo edward.lo@ambergroup.io Signed-off-by: Konstantin Komarov almaz.alexandrovich@paragon-software.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ntfs3/fsntfs.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 4ed15f64b17f..b6e22bcb929b 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -1849,9 +1849,10 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) goto out; }

- root_sdh = resident_data(attr); + root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT)); if (root_sdh->type != ATTR_ZERO || - root_sdh->rule != NTFS_COLLATION_TYPE_SECURITY_HASH) { + root_sdh->rule != NTFS_COLLATION_TYPE_SECURITY_HASH || + offsetof(struct INDEX_ROOT, ihdr) + root_sdh->ihdr.used > attr->res.data_size) { err = -EINVAL; goto out; } @@ -1867,9 +1868,10 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) goto out; }

- root_sii = resident_data(attr); + root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT)); if (root_sii->type != ATTR_ZERO || - root_sii->rule != NTFS_COLLATION_TYPE_UINT) { + root_sii->rule != NTFS_COLLATION_TYPE_UINT || + offsetof(struct INDEX_ROOT, ihdr) + root_sii->ihdr.used > attr->res.data_size) { err = -EINVAL; goto out; }

From: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp

[ Upstream commit 59bfd7a483da36bd202532a3d9ea1f14f3bf3aaf ]

syzbot is reporting too large allocation at ntfs_fill_super() [1], for a crafted filesystem can contain bogus inode->i_size. Add __GFP_NOWARN in order to avoid too large allocation warning, than exhausting memory by using kvmalloc().

Link: https://syzkaller.appspot.com/bug?extid=33f3faaa0c08744f7d40 [1] Reported-by: syzot syzbot+33f3faaa0c08744f7d40@syzkaller.appspotmail.com Signed-off-by: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Signed-off-by: Konstantin Komarov almaz.alexandrovich@paragon-software.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ntfs3/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 94f9e4b775a7..8e2fe0f69203 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1141,7 +1141,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) goto put_inode_out; } bytes = inode->i_size; - sbi->def_table = t = kmalloc(bytes, GFP_NOFS); + sbi->def_table = t = kmalloc(bytes, GFP_NOFS | __GFP_NOWARN); if (!t) { err = -ENOMEM; goto put_inode_out;

From: Yin Xiujiang yinxiujiang@kylinos.cn

[ Upstream commit ecfbd57cf9c5ca225184ae266ce44ae473792132 ]

When PAGE_SIZE is 64K, if read_log_page is called by log_read_rst for the first time, the size of *buffer would be equal to DefaultLogPageSize(4K).But for *buffer operations like memcpy, if the memory area size(n) which being assigned to buffer is larger than 4K (log->page_size(64K) or bytes(64K-page_off)), it will cause an out of boundary error. Call trace: [...] kasan_report+0x44/0x130 check_memory_region+0xf8/0x1a0 memcpy+0xc8/0x100 ntfs_read_run_nb+0x20c/0x460 read_log_page+0xd0/0x1f4 log_read_rst+0x110/0x75c log_replay+0x1e8/0x4aa0 ntfs_loadlog_and_replay+0x290/0x2d0 ntfs_fill_super+0x508/0xec0 get_tree_bdev+0x1fc/0x34c [...]

Fix this by setting variable r_page to NULL in log_read_rst.

Signed-off-by: Yin Xiujiang yinxiujiang@kylinos.cn Signed-off-by: Konstantin Komarov almaz.alexandrovich@paragon-software.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ntfs3/fslog.c | 26 ++------------------------ 1 file changed, 2 insertions(+), 24 deletions(-)

diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 138050b1aa93..4236194af35e 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -1132,7 +1132,7 @@ static int read_log_page(struct ntfs_log *log, u32 vbo, return -EINVAL;

if (!*buffer) { - to_free = kmalloc(bytes, GFP_NOFS); + to_free = kmalloc(log->page_size, GFP_NOFS); if (!to_free) return -ENOMEM; *buffer = to_free; @@ -1180,10 +1180,7 @@ static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first, struct restart_info *info) { u32 skip, vbo; - struct RESTART_HDR *r_page = kmalloc(DefaultLogPageSize, GFP_NOFS); - - if (!r_page) - return -ENOMEM; + struct RESTART_HDR *r_page = NULL;

/* Determine which restart area we are looking for. */ if (first) { @@ -1197,7 +1194,6 @@ static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first, /* Loop continuously until we succeed. */ for (; vbo < l_size; vbo = 2 * vbo + skip, skip = 0) { bool usa_error; - u32 sys_page_size; bool brst, bchk; struct RESTART_AREA *ra;

@@ -1251,24 +1247,6 @@ static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first, goto check_result; }

- /* Read the entire restart area. */ - sys_page_size = le32_to_cpu(r_page->sys_page_size); - if (DefaultLogPageSize != sys_page_size) { - kfree(r_page); - r_page = kzalloc(sys_page_size, GFP_NOFS); - if (!r_page) - return -ENOMEM; - - if (read_log_page(log, vbo, - (struct RECORD_PAGE_HDR **)&r_page, - &usa_error)) { - /* Ignore any errors. */ - kfree(r_page); - r_page = NULL; - continue; - } - } - if (is_client_area_valid(r_page, usa_error)) { info->valid_page = true; ra = Add2Ptr(r_page, le16_to_cpu(r_page->ra_off));

From: Ricardo Ribalda ribalda@chromium.org

[ Upstream commit 00ef8885a945c37551547d8ac8361cacd20c4e42 ]

If the system is rebooted via isr(), the IRQ handler might be triggered before the domain is initialized. Resulting on an invalid memory access error.

Fix: [ 0.500930] Unable to handle kernel read from unreadable memory at virtual address 0000000000000070 [ 0.501166] Call trace: [ 0.501174] report_iommu_fault+0x28/0xfc [ 0.501180] mtk_iommu_isr+0x10c/0x1c0

Signed-off-by: Ricardo Ribalda ribalda@chromium.org Reviewed-by: AngeloGioacchino Del Regno angelogioacchino.delregno@collabora.com Reviewed-by: Robin Murphy robin.murphy@arm.com Link: https://lore.kernel.org/r/20221125-mtk-iommu-v2-0-e168dff7d43e@chromium.org [ joro: Fixed spelling in commit message ] Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/mtk_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index ec73720e239b..15fa380b1f84 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -452,7 +452,7 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id) fault_larb = data->plat_data->larbid_remap[fault_larb][sub_comm]; }

- if (report_iommu_fault(&dom->domain, bank->parent_dev, fault_iova, + if (!dom || report_iommu_fault(&dom->domain, bank->parent_dev, fault_iova, write ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ)) { dev_err_ratelimited( bank->parent_dev,

From: Nathan Lynch nathanl@linux.ibm.com

[ Upstream commit 6c606e57eecc37d6b36d732b1ff7e55b7dc32dd4 ]

It's unsafe to use rtas_busy_delay() to handle a busy status from the ibm,os-term RTAS function in rtas_os_term():

Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b BUG: sleeping function called from invalid context at arch/powerpc/kernel/rtas.c:618 in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 1, name: swapper/0 preempt_count: 2, expected: 0 CPU: 7 PID: 1 Comm: swapper/0 Tainted: G D 6.0.0-rc5-02182-gf8553a572277-dirty #9 Call Trace: [c000000007b8f000] [c000000001337110] dump_stack_lvl+0xb4/0x110 (unreliable) [c000000007b8f040] [c0000000002440e4] __might_resched+0x394/0x3c0 [c000000007b8f0e0] [c00000000004f680] rtas_busy_delay+0x120/0x1b0 [c000000007b8f100] [c000000000052d04] rtas_os_term+0xb8/0xf4 [c000000007b8f180] [c0000000001150fc] pseries_panic+0x50/0x68 [c000000007b8f1f0] [c000000000036354] ppc_panic_platform_handler+0x34/0x50 [c000000007b8f210] [c0000000002303c4] notifier_call_chain+0xd4/0x1c0 [c000000007b8f2b0] [c0000000002306cc] atomic_notifier_call_chain+0xac/0x1c0 [c000000007b8f2f0] [c0000000001d62b8] panic+0x228/0x4d0 [c000000007b8f390] [c0000000001e573c] do_exit+0x140c/0x1420 [c000000007b8f480] [c0000000001e586c] make_task_dead+0xdc/0x200

Use rtas_busy_delay_time() instead, which signals without side effects whether to attempt the ibm,os-term RTAS call again.

Signed-off-by: Nathan Lynch nathanl@linux.ibm.com Reviewed-by: Nicholas Piggin npiggin@gmail.com Reviewed-by: Andrew Donnellan ajd@linux.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20221118150751.469393-5-nathanl@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/kernel/rtas.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 082b0c9e0c8a..5a873d4fbd7b 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -892,10 +892,15 @@ void rtas_os_term(char *str)

snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);

+ /* + * Keep calling as long as RTAS returns a "try again" status, + * but don't use rtas_busy_delay(), which potentially + * schedules. + */ do { status = rtas_call(ibm_os_term_token, 1, 1, NULL, __pa(rtas_os_term_buf)); - } while (rtas_busy_delay(status)); + } while (rtas_busy_delay_time(status));

if (status != 0) printk(KERN_EMERG "ibm,os-term call failed %d\n", status);

From: wuqiang wuqiang.matt@bytedance.com

[ Upstream commit 3b7ddab8a19aefc768f345fd3782af35b4a68d9b ]

Default value of maxactive is set as num_possible_cpus() for nonpreemptable systems. For a 2-core system, only 2 kretprobe instances would be allocated in default, then these 2 instances for execve kretprobe are very likely to be used up with a pipelined command.

Here's the testcase: a shell script was added to crontab, and the content of the script is:

#!/bin/sh do_something_magic `tr -dc a-z < /dev/urandom | head -c 10`

cron will trigger a series of program executions (4 times every hour). Then events loss would be noticed normally after 3-4 hours of testings.

The issue is caused by a burst of series of execve requests. The best number of kretprobe instances could be different case by case, and should be user's duty to determine, but num_possible_cpus() as the default value is inadequate especially for systems with small number of cpus.

This patch enables the logic for preemption as default, thus increases the minimum of maxactive to 10 for nonpreemptable systems.

Link: https://lore.kernel.org/all/20221110081502.492289-1-wuqiang.matt@bytedance.c...

Signed-off-by: wuqiang wuqiang.matt@bytedance.com Reviewed-by: Solar Designer solar@openwall.com Acked-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- Documentation/trace/kprobes.rst | 3 +-- kernel/kprobes.c | 8 ++------ 2 files changed, 3 insertions(+), 8 deletions(-)

diff --git a/Documentation/trace/kprobes.rst b/Documentation/trace/kprobes.rst index f318bceda1e6..97d086b23ce8 100644 --- a/Documentation/trace/kprobes.rst +++ b/Documentation/trace/kprobes.rst @@ -131,8 +131,7 @@ For example, if the function is non-recursive and is called with a spinlock held, maxactive = 1 should be enough. If the function is non-recursive and can never relinquish the CPU (e.g., via a semaphore or preemption), NR_CPUS should be enough. If maxactive <= 0, it is -set to a default value. If CONFIG_PREEMPT is enabled, the default -is max(10, 2*NR_CPUS). Otherwise, the default is NR_CPUS. +set to a default value: max(10, 2*NR_CPUS).

It's not a disaster if you set maxactive too low; you'll just miss some probes. In the kretprobe struct, the nmissed field is set to diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 771fcce54fac..fb88278978fe 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2209,13 +2209,9 @@ int register_kretprobe(struct kretprobe *rp) rp->kp.post_handler = NULL;

/* Pre-allocate memory for max kretprobe instances */ - if (rp->maxactive <= 0) { -#ifdef CONFIG_PREEMPTION + if (rp->maxactive <= 0) rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus()); -#else - rp->maxactive = num_possible_cpus(); -#endif - } + #ifdef CONFIG_KRETPROBE_ON_RETHOOK rp->rh = rethook_alloc((void *)rp, kretprobe_rethook_handler); if (!rp->rh)

From: Terry Junge linuxhid@cosmicgizmosystems.com

[ Upstream commit 3d57f36c89d8ba32b2c312f397a37fd1a2dc7cfc ]

I no longer work for Plantronics (aka Poly, aka HP) and do not have access to the headsets in order to test. However, as noted by Maxim, the other 32xx models that share the same base code set as the 3220 would need the same quirk. This patch adds the PIDs for the rest of the Blackwire 32XX product family that require the quirk.

Plantronics Blackwire 3210 Series (047f:c055) Plantronics Blackwire 3215 Series (047f:c057) Plantronics Blackwire 3225 Series (047f:c058)

Quote from previous patch by Maxim Mikityanskiy Plantronics Blackwire 3220 Series (047f:c056) sends HID reports twice for each volume key press. This patch adds a quirk to hid-plantronics for this product ID, which will ignore the second volume key press if it happens within 5 ms from the last one that was handled.

The patch was tested on the mentioned model only, it shouldn't affect other models, however, this quirk might be needed for them too. Auto-repeat (when a key is held pressed) is not affected, because the rate is about 3 times per second, which is far less frequent than once in 5 ms. End quote

Signed-off-by: Terry Junge linuxhid@cosmicgizmosystems.com Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/hid-ids.h | 3 +++ drivers/hid/hid-plantronics.c | 9 +++++++++ 2 files changed, 12 insertions(+)

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 86e754b9400f..5680543e97fd 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -995,7 +995,10 @@ #define USB_DEVICE_ID_ORTEK_IHOME_IMAC_A210S 0x8003

#define USB_VENDOR_ID_PLANTRONICS 0x047f +#define USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3210_SERIES 0xc055 #define USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3220_SERIES 0xc056 +#define USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3215_SERIES 0xc057 +#define USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3225_SERIES 0xc058

#define USB_VENDOR_ID_PANASONIC 0x04da #define USB_DEVICE_ID_PANABOARD_UBT780 0x1044 diff --git a/drivers/hid/hid-plantronics.c b/drivers/hid/hid-plantronics.c index e81b7cec2d12..3d414ae194ac 100644 --- a/drivers/hid/hid-plantronics.c +++ b/drivers/hid/hid-plantronics.c @@ -198,9 +198,18 @@ static int plantronics_probe(struct hid_device *hdev, }

static const struct hid_device_id plantronics_devices[] = { + { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, + USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3210_SERIES), + .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3220_SERIES), .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, + { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, + USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3215_SERIES), + .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, + { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, + USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3225_SERIES), + .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, HID_ANY_ID) }, { } };

From: Mel Gorman mgorman@techsingularity.net

commit 1c0908d8e441631f5b8ba433523cf39339ee2ba0 upstream.

Jan Kara reported the following bug triggering on 6.0.5-rt14 running dbench on XFS on arm64.

kernel BUG at fs/inode.c:625! Internal error: Oops - BUG: 0 [#1] PREEMPT_RT SMP CPU: 11 PID: 6611 Comm: dbench Tainted: G E 6.0.0-rt14-rt+ #1 pc : clear_inode+0xa0/0xc0 lr : clear_inode+0x38/0xc0 Call trace: clear_inode+0xa0/0xc0 evict+0x160/0x180 iput+0x154/0x240 do_unlinkat+0x184/0x300 __arm64_sys_unlinkat+0x48/0xc0 el0_svc_common.constprop.4+0xe4/0x2c0 do_el0_svc+0xac/0x100 el0_svc+0x78/0x200 el0t_64_sync_handler+0x9c/0xc0 el0t_64_sync+0x19c/0x1a0

It also affects 6.1-rc7-rt5 and affects a preempt-rt fork of 5.14 so this is likely a bug that existed forever and only became visible when ARM support was added to preempt-rt. The same problem does not occur on x86-64 and he also reported that converting sb->s_inode_wblist_lock to raw_spinlock_t makes the problem disappear indicating that the RT spinlock variant is the problem.

Which in turn means that RT mutexes on ARM64 and any other weakly ordered architecture are affected by this independent of RT.

Will Deacon observed:

"I'd be more inclined to be suspicious of the slowpath tbh, as we need to make sure that we have acquire semantics on all paths where the lock can be taken. Looking at the rtmutex code, this really isn't obvious to me -- for example, try_to_take_rt_mutex() appears to be able to return via the 'takeit' label without acquire semantics and it looks like we might be relying on the caller's subsequent _unlock_ of the wait_lock for ordering, but that will give us release semantics which aren't correct."

Sebastian Andrzej Siewior prototyped a fix that does work based on that comment but it was a little bit overkill and added some fences that should not be necessary.

The lock owner is updated with an IRQ-safe raw spinlock held, but the spin_unlock does not provide acquire semantics which are needed when acquiring a mutex.

Adds the necessary acquire semantics for lock owner updates in the slow path acquisition and the waiter bit logic.

It successfully completed 10 iterations of the dbench workload while the vanilla kernel fails on the first iteration.

[ bigeasy@linutronix.de: Initial prototype fix ]

Fixes: 700318d1d7b38 ("locking/rtmutex: Use acquire/release semantics") Fixes: 23f78d4a03c5 ("[PATCH] pi-futex: rt mutex core") Reported-by: Jan Kara jack@suse.cz Signed-off-by: Mel Gorman mgorman@techsingularity.net Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221202100223.6mevpbl7i6x5udfd@techsingularity.ne... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/locking/rtmutex.c | 55 +++++++++++++++++++++++++++++++++++-------- kernel/locking/rtmutex_api.c | 6 ++-- 2 files changed, 49 insertions(+), 12 deletions(-)

--- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -89,15 +89,31 @@ static inline int __ww_mutex_check_kill( * set this bit before looking at the lock. */

-static __always_inline void -rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner) +static __always_inline struct task_struct * +rt_mutex_owner_encode(struct rt_mutex_base *lock, struct task_struct *owner) { unsigned long val = (unsigned long)owner;

if (rt_mutex_has_waiters(lock)) val |= RT_MUTEX_HAS_WAITERS;

- WRITE_ONCE(lock->owner, (struct task_struct *)val); + return (struct task_struct *)val; +} + +static __always_inline void +rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner) +{ + /* + * lock->wait_lock is held but explicit acquire semantics are needed + * for a new lock owner so WRITE_ONCE is insufficient. + */ + xchg_acquire(&lock->owner, rt_mutex_owner_encode(lock, owner)); +} + +static __always_inline void rt_mutex_clear_owner(struct rt_mutex_base *lock) +{ + /* lock->wait_lock is held so the unlock provides release semantics. */ + WRITE_ONCE(lock->owner, rt_mutex_owner_encode(lock, NULL)); }

static __always_inline void clear_rt_mutex_waiters(struct rt_mutex_base *lock) @@ -106,7 +122,8 @@ static __always_inline void clear_rt_mut ((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS); }

-static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex_base *lock) +static __always_inline void +fixup_rt_mutex_waiters(struct rt_mutex_base *lock, bool acquire_lock) { unsigned long owner, *p = (unsigned long *) &lock->owner;

@@ -172,8 +189,21 @@ static __always_inline void fixup_rt_mut * still set. */ owner = READ_ONCE(*p); - if (owner & RT_MUTEX_HAS_WAITERS) - WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); + if (owner & RT_MUTEX_HAS_WAITERS) { + /* + * See rt_mutex_set_owner() and rt_mutex_clear_owner() on + * why xchg_acquire() is used for updating owner for + * locking and WRITE_ONCE() for unlocking. + * + * WRITE_ONCE() would work for the acquire case too, but + * in case that the lock acquisition failed it might + * force other lockers into the slow path unnecessarily. + */ + if (acquire_lock) + xchg_acquire(p, owner & ~RT_MUTEX_HAS_WAITERS); + else + WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); + } }

/* @@ -208,6 +238,13 @@ static __always_inline void mark_rt_mute owner = *p; } while (cmpxchg_relaxed(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner); + + /* + * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE + * operations in the event of contention. Ensure the successful + * cmpxchg is visible. + */ + smp_mb__after_atomic(); }

/* @@ -1243,7 +1280,7 @@ static int __sched __rt_mutex_slowtryloc * try_to_take_rt_mutex() sets the lock waiters bit * unconditionally. Clean this up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true);

return ret; } @@ -1604,7 +1641,7 @@ static int __sched __rt_mutex_slowlock(s * try_to_take_rt_mutex() sets the waiter bit * unconditionally. We might have to fix that up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true);

trace_contention_end(lock, ret);

@@ -1719,7 +1756,7 @@ static void __sched rtlock_slowlock_lock * try_to_take_rt_mutex() sets the waiter bit unconditionally. * We might have to fix that up: */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true); debug_rt_mutex_free_waiter(&waiter);

trace_contention_end(lock, 0); --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -267,7 +267,7 @@ void __sched rt_mutex_init_proxy_locked( void __sched rt_mutex_proxy_unlock(struct rt_mutex_base *lock) { debug_rt_mutex_proxy_unlock(lock); - rt_mutex_set_owner(lock, NULL); + rt_mutex_clear_owner(lock); }

/** @@ -382,7 +382,7 @@ int __sched rt_mutex_wait_proxy_lock(str * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true); raw_spin_unlock_irq(&lock->wait_lock);

return ret; @@ -438,7 +438,7 @@ bool __sched rt_mutex_cleanup_proxy_lock * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, false);

raw_spin_unlock_irq(&lock->wait_lock);

From: Luca Stefani luca@osomprivacy.com

commit beca3e311a49cd3c55a056096531737d7afa4361 upstream.

If mem-type is specified in the device tree it would end up overriding the record_size field instead of populating mem_type.

As record_size is currently parsed after the improper assignment with default size 0 it continued to work as expected regardless of the value found in the device tree.

Simply changing the target field of the struct is enough to get mem-type working as expected.

Fixes: 9d843e8fafc7 ("pstore: Add mem_type property DT parsing support") Cc: stable@vger.kernel.org Signed-off-by: Luca Stefani luca@osomprivacy.com Signed-off-by: Kees Cook keescook@chromium.org Link: https://lore.kernel.org/r/20221222131049.286288-1-luca@osomprivacy.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/pstore/ram.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -670,7 +670,7 @@ static int ramoops_parse_dt(struct platf field = value; \ }

- parse_u32("mem-type", pdata->record_size, pdata->mem_type); + parse_u32("mem-type", pdata->mem_type, pdata->mem_type); parse_u32("record-size", pdata->record_size, 0); parse_u32("console-size", pdata->console_size, 0); parse_u32("ftrace-size", pdata->ftrace_size, 0);

From: Aditya Garg gargaditya08@live.com

commit 9f2b5debc07073e6dfdd774e3594d0224b991927 upstream.

Despite specifying UID and GID in mount command, the specified UID and GID were not being assigned. This patch fixes this issue.

Link: https://lkml.kernel.org/r/C0264BF5-059C-45CF-B8DA-3A3BD2C803A2@live.com Signed-off-by: Aditya Garg gargaditya08@live.com Reviewed-by: Viacheslav Dubeyko slava@dubeyko.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/hfsplus/hfsplus_fs.h | 2 ++ fs/hfsplus/inode.c | 4 ++-- fs/hfsplus/options.c | 4 ++++ 3 files changed, 8 insertions(+), 2 deletions(-)

--- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -198,6 +198,8 @@ struct hfsplus_sb_info { #define HFSPLUS_SB_HFSX 3 #define HFSPLUS_SB_CASEFOLD 4 #define HFSPLUS_SB_NOBARRIER 5 +#define HFSPLUS_SB_UID 6 +#define HFSPLUS_SB_GID 7

static inline struct hfsplus_sb_info *HFSPLUS_SB(struct super_block *sb) { --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -192,11 +192,11 @@ static void hfsplus_get_perms(struct ino mode = be16_to_cpu(perms->mode);

i_uid_write(inode, be32_to_cpu(perms->owner)); - if (!i_uid_read(inode) && !mode) + if ((test_bit(HFSPLUS_SB_UID, &sbi->flags)) || (!i_uid_read(inode) && !mode)) inode->i_uid = sbi->uid;

i_gid_write(inode, be32_to_cpu(perms->group)); - if (!i_gid_read(inode) && !mode) + if ((test_bit(HFSPLUS_SB_GID, &sbi->flags)) || (!i_gid_read(inode) && !mode)) inode->i_gid = sbi->gid;

if (dir) { --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -140,6 +140,8 @@ int hfsplus_parse_options(char *input, s if (!uid_valid(sbi->uid)) { pr_err("invalid uid specified\n"); return 0; + } else { + set_bit(HFSPLUS_SB_UID, &sbi->flags); } break; case opt_gid: @@ -151,6 +153,8 @@ int hfsplus_parse_options(char *input, s if (!gid_valid(sbi->gid)) { pr_err("invalid gid specified\n"); return 0; + } else { + set_bit(HFSPLUS_SB_GID, &sbi->flags); } break; case opt_part:

From: Jens Axboe axboe@kernel.dk

commit 03e02acda8e267a8183e1e0ed289ff1ef9cd7ed8 upstream.

This is identical to eventfd_signal(), but it allows the caller to pass in a mask to be used for the poll wakeup key. The use case is avoiding repeated multishot triggers if we have a dependency between eventfd and io_uring.

If we setup an eventfd context and register that as the io_uring eventfd, and at the same time queue a multishot poll request for the eventfd context, then any CQE posted will repeatedly trigger the multishot request until it terminates when the CQ ring overflows.

In preparation for io_uring detecting this circular dependency, add the mentioned helper so that io_uring can pass in EPOLL_URING as part of the poll wakeup key.

Cc: stable@vger.kernel.org # 6.0 [axboe: fold in !CONFIG_EVENTFD fix from Zhang Qilong] Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/eventfd.c | 37 +++++++++++++++++++++---------------- include/linux/eventfd.h | 7 +++++++ 2 files changed, 28 insertions(+), 16 deletions(-)

diff --git a/fs/eventfd.c b/fs/eventfd.c index c0ffee99ad23..249ca6c0b784 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -43,21 +43,7 @@ struct eventfd_ctx { int id; };

-/** - * eventfd_signal - Adds @n to the eventfd counter. - * @ctx: [in] Pointer to the eventfd context. - * @n: [in] Value of the counter to be added to the eventfd internal counter. - * The value cannot be negative. - * - * This function is supposed to be called by the kernel in paths that do not - * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX - * value, and we signal this as overflow condition by returning a EPOLLERR - * to poll(2). - * - * Returns the amount by which the counter was incremented. This will be less - * than @n if the counter has overflowed. - */ -__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) +__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask) { unsigned long flags;

@@ -78,12 +64,31 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) n = ULLONG_MAX - ctx->count; ctx->count += n; if (waitqueue_active(&ctx->wqh)) - wake_up_locked_poll(&ctx->wqh, EPOLLIN); + wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask); current->in_eventfd = 0; spin_unlock_irqrestore(&ctx->wqh.lock, flags);

return n; } + +/** + * eventfd_signal - Adds @n to the eventfd counter. + * @ctx: [in] Pointer to the eventfd context. + * @n: [in] Value of the counter to be added to the eventfd internal counter. + * The value cannot be negative. + * + * This function is supposed to be called by the kernel in paths that do not + * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX + * value, and we signal this as overflow condition by returning a EPOLLERR + * to poll(2). + * + * Returns the amount by which the counter was incremented. This will be less + * than @n if the counter has overflowed. + */ +__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) +{ + return eventfd_signal_mask(ctx, n, 0); +} EXPORT_SYMBOL_GPL(eventfd_signal);

static void eventfd_free_ctx(struct eventfd_ctx *ctx) diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 30eb30d6909b..786824f58d3d 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -40,6 +40,7 @@ struct file *eventfd_fget(int fd); struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); +__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask); int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt); @@ -66,6 +67,12 @@ static inline int eventfd_signal(struct eventfd_ctx *ctx, int n) return -ENOSYS; }

+static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, + unsigned mask) +{ + return -ENOSYS; +} + static inline void eventfd_ctx_put(struct eventfd_ctx *ctx) {

From: Wang Yufen wangyufen@huawei.com

commit e7f703ff2507f4e9f496da96cd4b78fd3026120c upstream.

Fix to return a negative error code from create_elf_fdpic_tables() instead of 0.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Wang Yufen wangyufen@huawei.com Signed-off-by: Kees Cook keescook@chromium.org Link: https://lore.kernel.org/r/1669945261-30271-1-git-send-email-wangyufen@huawei... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/binfmt_elf_fdpic.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -434,8 +434,9 @@ static int load_elf_fdpic_binary(struct current->mm->start_stack = current->mm->start_brk + stack_size; #endif

- if (create_elf_fdpic_tables(bprm, current->mm, - &exec_params, &interp_params) < 0) + retval = create_elf_fdpic_tables(bprm, current->mm, &exec_params, + &interp_params); + if (retval < 0) goto error;

kdebug("- start_code %lx", current->mm->start_code);

From: Al Viro viro@zeniv.linux.org.uk

commit 456b59e757b0c558df550764a4fd5ae6877e93f8 upstream.

ovl_change_flags() is an open-coded variant of fs/fcntl.c:setfl() and it got missed by commit 164f4064ca81 ("keep iocb_flags() result cached in struct file"); the same change applies there.

Reported-by: Pierre Labastie pierre.labastie@neuf.fr Fixes: 164f4064ca81 ("keep iocb_flags() result cached in struct file") Cc: stable@vger.kernel.org # v6.0 Link: https://bugzilla.kernel.org/show_bug.cgi?id=216738 Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Miklos Szeredi mszeredi@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/overlayfs/file.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index a1a22f58ba18..dd688a842b0b 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -96,6 +96,7 @@ static int ovl_change_flags(struct file *file, unsigned int flags)

spin_lock(&file->f_lock); file->f_flags = (file->f_flags & ~OVL_SETFL_MASK) | flags; + file->f_iocb_flags = iocb_flags(file); spin_unlock(&file->f_lock);

return 0;

From: Artem Egorkine arteme@gmail.com

commit b8800d324abb50160560c636bfafe2c81001b66c upstream.

Correctly calculate available space including the size of the chunk buffer. This fixes a buffer overflow when multiple MIDI sysex messages are sent to a PODxt device.

Signed-off-by: Artem Egorkine arteme@gmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221225105728.1153989-2-arteme@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/line6/midi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/sound/usb/line6/midi.c +++ b/sound/usb/line6/midi.c @@ -44,7 +44,8 @@ static void line6_midi_transmit(struct s int req, done;

for (;;) { - req = min(line6_midibuf_bytes_free(mb), line6->max_packet_size); + req = min3(line6_midibuf_bytes_free(mb), line6->max_packet_size, + LINE6_FALLBACK_MAXPACKETSIZE); done = snd_rawmidi_transmit_peek(substream, chunk, req);

if (done == 0)

From: Christian Brauner brauner@kernel.org

commit 11933cf1d91d57da9e5c53822a540bbdc2656c16 upstream.

The propagate_mnt() function handles mount propagation when creating mounts and propagates the source mount tree @source_mnt to all applicable nodes of the destination propagation mount tree headed by @dest_mnt.

Unfortunately it contains a bug where it fails to terminate at peers of @source_mnt when looking up copies of the source mount that become masters for copies of the source mount tree mounted on top of slaves in the destination propagation tree causing a NULL dereference.

Once the mechanics of the bug are understood it's easy to trigger. Because of unprivileged user namespaces it is available to unprivileged users.

While fixing this bug we've gotten confused multiple times due to unclear terminology or missing concepts. So let's start this with some clarifications:

* The terms "master" or "peer" denote a shared mount. A shared mount belongs to a peer group.

* A peer group is a set of shared mounts that propagate to each other. They are identified by a peer group id. The peer group id is available in @shared_mnt->mnt_group_id. Shared mounts within the same peer group have the same peer group id. The peers in a peer group can be reached via @shared_mnt->mnt_share.

* The terms "slave mount" or "dependent mount" denote a mount that receives propagation from a peer in a peer group. IOW, shared mounts may have slave mounts and slave mounts have shared mounts as their master. Slave mounts of a given peer in a peer group are listed on that peers slave list available at @shared_mnt->mnt_slave_list.

* The term "master mount" denotes a mount in a peer group. IOW, it denotes a shared mount or a peer mount in a peer group. The term "master mount" - or "master" for short - is mostly used when talking in the context of slave mounts that receive propagation from a master mount. A master mount of a slave identifies the closest peer group a slave mount receives propagation from. The master mount of a slave can be identified via @slave_mount->mnt_master. Different slaves may point to different masters in the same peer group.

* Multiple peers in a peer group can have non-empty ->mnt_slave_lists. Non-empty ->mnt_slave_lists of peers don't intersect. Consequently, to ensure all slave mounts of a peer group are visited the ->mnt_slave_lists of all peers in a peer group have to be walked.

* Slave mounts point to a peer in the closest peer group they receive propagation from via @slave_mnt->mnt_master (see above). Together with these peers they form a propagation group (see below). The closest peer group can thus be identified through the peer group id @slave_mnt->mnt_master->mnt_group_id of the peer/master that a slave mount receives propagation from.

* A shared-slave mount is a slave mount to a peer group pg1 while also a peer in another peer group pg2. IOW, a peer group may receive propagation from another peer group.

If a peer group pg1 is a slave to another peer group pg2 then all peers in peer group pg1 point to the same peer in peer group pg2 via ->mnt_master. IOW, all peers in peer group pg1 appear on the same ->mnt_slave_list. IOW, they cannot be slaves to different peer groups.

* A pure slave mount is a slave mount that is a slave to a peer group but is not a peer in another peer group.

* A propagation group denotes the set of mounts consisting of a single peer group pg1 and all slave mounts and shared-slave mounts that point to a peer in that peer group via ->mnt_master. IOW, all slave mounts such that @slave_mnt->mnt_master->mnt_group_id is equal to @shared_mnt->mnt_group_id.

The concept of a propagation group makes it easier to talk about a single propagation level in a propagation tree.

For example, in propagate_mnt() the immediate peers of @dest_mnt and all slaves of @dest_mnt's peer group form a propagation group propg1. So a shared-slave mount that is a slave in propg1 and that is a peer in another peer group pg2 forms another propagation group propg2 together with all slaves that point to that shared-slave mount in their ->mnt_master.

* A propagation tree refers to all mounts that receive propagation starting from a specific shared mount.

For example, for propagate_mnt() @dest_mnt is the start of a propagation tree. The propagation tree ecompasses all mounts that receive propagation from @dest_mnt's peer group down to the leafs.

With that out of the way let's get to the actual algorithm.

We know that @dest_mnt is guaranteed to be a pure shared mount or a shared-slave mount. This is guaranteed by a check in attach_recursive_mnt(). So propagate_mnt() will first propagate the source mount tree to all peers in @dest_mnt's peer group:

for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) { ret = propagate_one(n); if (ret) goto out; }

Notice, that the peer propagation loop of propagate_mnt() doesn't propagate @dest_mnt itself. @dest_mnt is mounted directly in attach_recursive_mnt() after we propagated to the destination propagation tree.

The mount that will be mounted on top of @dest_mnt is @source_mnt. This copy was created earlier even before we entered attach_recursive_mnt() and doesn't concern us a lot here.

It's just important to notice that when propagate_mnt() is called @source_mnt will not yet have been mounted on top of @dest_mnt. Thus, @source_mnt->mnt_parent will either still point to @source_mnt or - in the case @source_mnt is moved and thus already attached - still to its former parent.

For each peer @m in @dest_mnt's peer group propagate_one() will create a new copy of the source mount tree and mount that copy @child on @m such that @child->mnt_parent points to @m after propagate_one() returns.

propagate_one() will stash the last destination propagation node @m in @last_dest and the last copy it created for the source mount tree in @last_source.

Hence, if we call into propagate_one() again for the next destination propagation node @m, @last_dest will point to the previous destination propagation node and @last_source will point to the previous copy of the source mount tree and mounted on @last_dest.

Each new copy of the source mount tree is created from the previous copy of the source mount tree. This will become important later.

The peer loop in propagate_mnt() is straightforward. We iterate through the peers copying and updating @last_source and @last_dest as we go through them and mount each copy of the source mount tree @child on a peer @m in @dest_mnt's peer group.

After propagate_mnt() handled the peers in @dest_mnt's peer group propagate_mnt() will propagate the source mount tree down the propagation tree that @dest_mnt's peer group propagates to:

for (m = next_group(dest_mnt, dest_mnt); m; m = next_group(m, dest_mnt)) { /* everything in that slave group */ n = m; do { ret = propagate_one(n); if (ret) goto out; n = next_peer(n); } while (n != m); }

The next_group() helper will recursively walk the destination propagation tree, descending into each propagation group of the propagation tree.

The important part is that it takes care to propagate the source mount tree to all peers in the peer group of a propagation group before it propagates to the slaves to those peers in the propagation group. IOW, it creates and mounts copies of the source mount tree that become masters before it creates and mounts copies of the source mount tree that become slaves to these masters.

It is important to remember that propagating the source mount tree to each mount @m in the destination propagation tree simply means that we create and mount new copies @child of the source mount tree on @m such that @child->mnt_parent points to @m.

Since we know that each node @m in the destination propagation tree headed by @dest_mnt's peer group will be overmounted with a copy of the source mount tree and since we know that the propagation properties of each copy of the source mount tree we create and mount at @m will mostly mirror the propagation properties of @m. We can use that information to create and mount the copies of the source mount tree that become masters before their slaves.

The easy case is always when @m and @last_dest are peers in a peer group of a given propagation group. In that case we know that we can simply copy @last_source without having to figure out what the master for the new copy @child of the source mount tree needs to be as we've done that in a previous call to propagate_one().

The hard case is when we're dealing with a slave mount or a shared-slave mount @m in a destination propagation group that we need to create and mount a copy of the source mount tree on.

For each propagation group in the destination propagation tree we propagate the source mount tree to we want to make sure that the copies @child of the source mount tree we create and mount on slaves @m pick an ealier copy of the source mount tree that we mounted on a master @m of the destination propagation group as their master. This is a mouthful but as far as we can tell that's the core of it all.

But, if we keep track of the masters in the destination propagation tree @m we can use the information to find the correct master for each copy of the source mount tree we create and mount at the slaves in the destination propagation tree @m.

Let's walk through the base case as that's still fairly easy to grasp.

If we're dealing with the first slave in the propagation group that @dest_mnt is in then we don't yet have marked any masters in the destination propagation tree.

We know the master for the first slave to @dest_mnt's peer group is simple @dest_mnt. So we expect this algorithm to yield a copy of the source mount tree that was mounted on a peer in @dest_mnt's peer group as the master for the copy of the source mount tree we want to mount at the first slave @m:

for (n = m; ; n = p) { p = n->mnt_master; if (p == dest_master || IS_MNT_MARKED(p)) break; }

For the first slave we walk the destination propagation tree all the way up to a peer in @dest_mnt's peer group. IOW, the propagation hierarchy can be walked by walking up the @mnt->mnt_master hierarchy of the destination propagation tree @m. We will ultimately find a peer in @dest_mnt's peer group and thus ultimately @dest_mnt->mnt_master.

Btw, here the assumption we listed at the beginning becomes important. Namely, that peers in a peer group pg1 that are slaves in another peer group pg2 appear on the same ->mnt_slave_list. IOW, all slaves who are peers in peer group pg1 point to the same peer in peer group pg2 via their ->mnt_master. Otherwise the termination condition in the code above would be wrong and next_group() would be broken too.

So the first iteration sets:

n = m; p = n->mnt_master;

such that @p now points to a peer or @dest_mnt itself. We walk up one more level since we don't have any marked mounts. So we end up with:

n = dest_mnt; p = dest_mnt->mnt_master;

If @dest_mnt's peer group is not slave to another peer group then @p is now NULL. If @dest_mnt's peer group is a slave to another peer group then @p now points to @dest_mnt->mnt_master points which is a master outside the propagation tree we're dealing with.

Now we need to figure out the master for the copy of the source mount tree we're about to create and mount on the first slave of @dest_mnt's peer group:

do { struct mount *parent = last_source->mnt_parent; if (last_source == first_source) break; done = parent->mnt_master == p; if (done && peers(n, parent)) break; last_source = last_source->mnt_master; } while (!done);

We know that @last_source->mnt_parent points to @last_dest and @last_dest is the last peer in @dest_mnt's peer group we propagated to in the peer loop in propagate_mnt().

Consequently, @last_source is the last copy we created and mount on that last peer in @dest_mnt's peer group. So @last_source is the master we want to pick.

We know that @last_source->mnt_parent->mnt_master points to @last_dest->mnt_master. We also know that @last_dest->mnt_master is either NULL or points to a master outside of the destination propagation tree and so does @p. Hence:

done = parent->mnt_master == p;

is trivially true in the base condition.

We also know that for the first slave mount of @dest_mnt's peer group that @last_dest either points @dest_mnt itself because it was initialized to:

last_dest = dest_mnt;

at the beginning of propagate_mnt() or it will point to a peer of @dest_mnt in its peer group. In both cases it is guaranteed that on the first iteration @n and @parent are peers (Please note the check for peers here as that's important.):

if (done && peers(n, parent)) break;

So, as we expected, we select @last_source, which referes to the last copy of the source mount tree we mounted on the last peer in @dest_mnt's peer group, as the master of the first slave in @dest_mnt's peer group. The rest is taken care of by clone_mnt(last_source, ...). We'll skip over that part otherwise this becomes a blogpost.

At the end of propagate_mnt() we now mark @m->mnt_master as the first master in the destination propagation tree that is distinct from @dest_mnt->mnt_master. IOW, we mark @dest_mnt itself as a master.

By marking @dest_mnt or one of it's peers we are able to easily find it again when we later lookup masters for other copies of the source mount tree we mount copies of the source mount tree on slaves @m to @dest_mnt's peer group. This, in turn allows us to find the master we selected for the copies of the source mount tree we mounted on master in the destination propagation tree again.

The important part is to realize that the code makes use of the fact that the last copy of the source mount tree stashed in @last_source was mounted on top of the previous destination propagation node @last_dest. What this means is that @last_source allows us to walk the destination propagation hierarchy the same way each destination propagation node @m does.

If we take @last_source, which is the copy of @source_mnt we have mounted on @last_dest in the previous iteration of propagate_one(), then we know @last_source->mnt_parent points to @last_dest but we also know that as we walk through the destination propagation tree that @last_source->mnt_master will point to an earlier copy of the source mount tree we mounted one an earlier destination propagation node @m.

IOW, @last_source->mnt_parent will be our hook into the destination propagation tree and each consecutive @last_source->mnt_master will lead us to an earlier propagation node @m via @last_source->mnt_master->mnt_parent.

Hence, by walking up @last_source->mnt_master, each of which is mounted on a node that is a master @m in the destination propagation tree we can also walk up the destination propagation hierarchy.

So, for each new destination propagation node @m we use the previous copy of @last_source and the fact it's mounted on the previous propagation node @last_dest via @last_source->mnt_master->mnt_parent to determine what the master of the new copy of @last_source needs to be.

The goal is to find the _closest_ master that the new copy of the source mount tree we are about to create and mount on a slave @m in the destination propagation tree needs to pick. IOW, we want to find a suitable master in the propagation group.

As the propagation structure of the source mount propagation tree we create mirrors the propagation structure of the destination propagation tree we can find @m's closest master - i.e., a marked master - which is a peer in the closest peer group that @m receives propagation from. We store that closest master of @m in @p as before and record the slave to that master in @n

We then search for this master @p via @last_source by walking up the master hierarchy starting from the last copy of the source mount tree stored in @last_source that we created and mounted on the previous destination propagation node @m.

We will try to find the master by walking @last_source->mnt_master and by comparing @last_source->mnt_master->mnt_parent->mnt_master to @p. If we find @p then we can figure out what earlier copy of the source mount tree needs to be the master for the new copy of the source mount tree we're about to create and mount at the current destination propagation node @m.

If @last_source->mnt_master->mnt_parent and @n are peers then we know that the closest master they receive propagation from is @last_source->mnt_master->mnt_parent->mnt_master. If not then the closest immediate peer group that they receive propagation from must be one level higher up.

This builds on the earlier clarification at the beginning that all peers in a peer group which are slaves of other peer groups all point to the same ->mnt_master, i.e., appear on the same ->mnt_slave_list, of the closest peer group that they receive propagation from.

However, terminating the walk has corner cases.

If the closest marked master for a given destination node @m cannot be found by walking up the master hierarchy via @last_source->mnt_master then we need to terminate the walk when we encounter @source_mnt again.

This isn't an arbitrary termination. It simply means that the new copy of the source mount tree we're about to create has a copy of the source mount tree we created and mounted on a peer in @dest_mnt's peer group as its master. IOW, @source_mnt is the peer in the closest peer group that the new copy of the source mount tree receives propagation from.

We absolutely have to stop @source_mnt because @last_source->mnt_master either points outside the propagation hierarchy we're dealing with or it is NULL because @source_mnt isn't a shared-slave.

So continuing the walk past @source_mnt would cause a NULL dereference via @last_source->mnt_master->mnt_parent. And so we have to stop the walk when we encounter @source_mnt again.

One scenario where this can happen is when we first handled a series of slaves of @dest_mnt's peer group and then encounter peers in a new peer group that is a slave to @dest_mnt's peer group. We handle them and then we encounter another slave mount to @dest_mnt that is a pure slave to @dest_mnt's peer group. That pure slave will have a peer in @dest_mnt's peer group as its master. Consequently, the new copy of the source mount tree will need to have @source_mnt as it's master. So we walk the propagation hierarchy all the way up to @source_mnt based on @last_source->mnt_master.

So terminate on @source_mnt, easy peasy. Except, that the check misses something that the rest of the algorithm already handles.

If @dest_mnt has peers in it's peer group the peer loop in propagate_mnt():

for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) { ret = propagate_one(n); if (ret) goto out; }

will consecutively update @last_source with each previous copy of the source mount tree we created and mounted at the previous peer in @dest_mnt's peer group. So after that loop terminates @last_source will point to whatever copy of the source mount tree was created and mounted on the last peer in @dest_mnt's peer group.

Furthermore, if there is even a single additional peer in @dest_mnt's peer group then @last_source will __not__ point to @source_mnt anymore. Because, as we mentioned above, @dest_mnt isn't even handled in this loop but directly in attach_recursive_mnt(). So it can't even accidently come last in that peer loop.

So the first time we handle a slave mount @m of @dest_mnt's peer group the copy of the source mount tree we create will make the __last copy of the source mount tree we created and mounted on the last peer in @dest_mnt's peer group the master of the new copy of the source mount tree we create and mount on the first slave of @dest_mnt's peer group__.

But this means that the termination condition that checks for @source_mnt is wrong. The @source_mnt cannot be found anymore by propagate_one(). Instead it will find the last copy of the source mount tree we created and mounted for the last peer of @dest_mnt's peer group again. And that is a peer of @source_mnt not @source_mnt itself.

IOW, we fail to terminate the loop correctly and ultimately dereference @last_source->mnt_master->mnt_parent. When @source_mnt's peer group isn't slave to another peer group then @last_source->mnt_master is NULL causing the splat below.

For example, assume @dest_mnt is a pure shared mount and has three peers in its peer group:

=================================================================================== mount-id mount-parent-id peer-group-id =================================================================================== (@dest_mnt) mnt_master[216] 309 297 shared:216 \ (@source_mnt) mnt_master[218]: 609 609 shared:218

(1) mnt_master[216]: 607 605 shared:216 \ (P1) mnt_master[218]: 624 607 shared:218

(2) mnt_master[216]: 576 574 shared:216 \ (P2) mnt_master[218]: 625 576 shared:218

(3) mnt_master[216]: 545 543 shared:216 \ (P3) mnt_master[218]: 626 545 shared:218

After this sequence has been processed @last_source will point to (P3), the copy generated for the third peer in @dest_mnt's peer group we handled. So the copy of the source mount tree (P4) we create and mount on the first slave of @dest_mnt's peer group:

=================================================================================== mount-id mount-parent-id peer-group-id =================================================================================== mnt_master[216] 309 297 shared:216 / / (S0) mnt_slave 483 481 master:216 \ \ (P3) mnt_master[218] 626 545 shared:218 \ / / (P4) mnt_slave 627 483 master:218

will pick the last copy of the source mount tree (P3) as master, not (S0).

When walking the propagation hierarchy via @last_source's master hierarchy we encounter (P3) but not (S0), i.e., @source_mnt.

We can fix this in multiple ways:

(1) By setting @last_source to @source_mnt after we processed the peers in @dest_mnt's peer group right after the peer loop in propagate_mnt().

(2) By changing the termination condition that relies on finding exactly @source_mnt to finding a peer of @source_mnt.

(3) By only moving @last_source when we actually venture into a new peer group or some clever variant thereof.

The first two options are minimally invasive and what we want as a fix. The third option is more intrusive but something we'd like to explore in the near future.

This passes all LTP tests and specifically the mount propagation testsuite part of it. It also holds up against all known reproducers of this issues.

Final words. First, this is a clever but __worringly__ underdocumented algorithm. There isn't a single detailed comment to be found in next_group(), propagate_one() or anywhere else in that file for that matter. This has been a giant pain to understand and work through and a bug like this is insanely difficult to fix without a detailed understanding of what's happening. Let's not talk about the amount of time that was sunk into fixing this.

Second, all the cool kids with access to unshare --mount --user --map-root --propagation=unchanged are going to have a lot of fun. IOW, triggerable by unprivileged users while namespace_lock() lock is held.

[ 115.848393] BUG: kernel NULL pointer dereference, address: 0000000000000010 [ 115.848967] #PF: supervisor read access in kernel mode [ 115.849386] #PF: error_code(0x0000) - not-present page [ 115.849803] PGD 0 P4D 0 [ 115.850012] Oops: 0000 [#1] PREEMPT SMP PTI [ 115.850354] CPU: 0 PID: 15591 Comm: mount Not tainted 6.1.0-rc7 #3 [ 115.850851] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 115.851510] RIP: 0010:propagate_one.part.0+0x7f/0x1a0 [ 115.851924] Code: 75 eb 4c 8b 05 c2 25 37 02 4c 89 ca 48 8b 4a 10 49 39 d0 74 1e 48 3b 81 e0 00 00 00 74 26 48 8b 92 e0 00 00 00 be 01 00 00 00 <48> 8b 4a 10 49 39 d0 75 e2 40 84 f6 74 38 4c 89 05 84 25 37 02 4d [ 115.853441] RSP: 0018:ffffb8d5443d7d50 EFLAGS: 00010282 [ 115.853865] RAX: ffff8e4d87c41c80 RBX: ffff8e4d88ded780 RCX: ffff8e4da4333a00 [ 115.854458] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8e4d88ded780 [ 115.855044] RBP: ffff8e4d88ded780 R08: ffff8e4da4338000 R09: ffff8e4da43388c0 [ 115.855693] R10: 0000000000000002 R11: ffffb8d540158000 R12: ffffb8d5443d7da8 [ 115.856304] R13: ffff8e4d88ded780 R14: 0000000000000000 R15: 0000000000000000 [ 115.856859] FS: 00007f92c90c9800(0000) GS:ffff8e4dfdc00000(0000) knlGS:0000000000000000 [ 115.857531] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 115.858006] CR2: 0000000000000010 CR3: 0000000022f4c002 CR4: 00000000000706f0 [ 115.858598] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 115.859393] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 115.860099] Call Trace: [ 115.860358] <TASK> [ 115.860535] propagate_mnt+0x14d/0x190 [ 115.860848] attach_recursive_mnt+0x274/0x3e0 [ 115.861212] path_mount+0x8c8/0xa60 [ 115.861503] __x64_sys_mount+0xf6/0x140 [ 115.861819] do_syscall_64+0x5b/0x80 [ 115.862117] ? do_faccessat+0x123/0x250 [ 115.862435] ? syscall_exit_to_user_mode+0x17/0x40 [ 115.862826] ? do_syscall_64+0x67/0x80 [ 115.863133] ? syscall_exit_to_user_mode+0x17/0x40 [ 115.863527] ? do_syscall_64+0x67/0x80 [ 115.863835] ? do_syscall_64+0x67/0x80 [ 115.864144] ? do_syscall_64+0x67/0x80 [ 115.864452] ? exc_page_fault+0x70/0x170 [ 115.864775] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 115.865187] RIP: 0033:0x7f92c92b0ebe [ 115.865480] Code: 48 8b 0d 75 4f 0c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 42 4f 0c 00 f7 d8 64 89 01 48 [ 115.866984] RSP: 002b:00007fff000aa728 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 [ 115.867607] RAX: ffffffffffffffda RBX: 000055a77888d6b0 RCX: 00007f92c92b0ebe [ 115.868240] RDX: 000055a77888d8e0 RSI: 000055a77888e6e0 RDI: 000055a77888e620 [ 115.868823] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000001 [ 115.869403] R10: 0000000000001000 R11: 0000000000000246 R12: 000055a77888e620 [ 115.869994] R13: 000055a77888d8e0 R14: 00000000ffffffff R15: 00007f92c93e4076 [ 115.870581] </TASK> [ 115.870763] Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set rfkill nf_tables nfnetlink qrtr snd_intel8x0 sunrpc snd_ac97_codec ac97_bus snd_pcm snd_timer intel_rapl_msr intel_rapl_common snd vboxguest intel_powerclamp video rapl joydev soundcore i2c_piix4 wmi fuse zram xfs vmwgfx crct10dif_pclmul crc32_pclmul crc32c_intel polyval_clmulni polyval_generic drm_ttm_helper ttm e1000 ghash_clmulni_intel serio_raw ata_generic pata_acpi scsi_dh_rdac scsi_dh_emc scsi_dh_alua dm_multipath [ 115.875288] CR2: 0000000000000010 [ 115.875641] ---[ end trace 0000000000000000 ]--- [ 115.876135] RIP: 0010:propagate_one.part.0+0x7f/0x1a0 [ 115.876551] Code: 75 eb 4c 8b 05 c2 25 37 02 4c 89 ca 48 8b 4a 10 49 39 d0 74 1e 48 3b 81 e0 00 00 00 74 26 48 8b 92 e0 00 00 00 be 01 00 00 00 <48> 8b 4a 10 49 39 d0 75 e2 40 84 f6 74 38 4c 89 05 84 25 37 02 4d [ 115.878086] RSP: 0018:ffffb8d5443d7d50 EFLAGS: 00010282 [ 115.878511] RAX: ffff8e4d87c41c80 RBX: ffff8e4d88ded780 RCX: ffff8e4da4333a00 [ 115.879128] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8e4d88ded780 [ 115.879715] RBP: ffff8e4d88ded780 R08: ffff8e4da4338000 R09: ffff8e4da43388c0 [ 115.880359] R10: 0000000000000002 R11: ffffb8d540158000 R12: ffffb8d5443d7da8 [ 115.880962] R13: ffff8e4d88ded780 R14: 0000000000000000 R15: 0000000000000000 [ 115.881548] FS: 00007f92c90c9800(0000) GS:ffff8e4dfdc00000(0000) knlGS:0000000000000000 [ 115.882234] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 115.882713] CR2: 0000000000000010 CR3: 0000000022f4c002 CR4: 00000000000706f0 [ 115.883314] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 115.883966] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fixes: f2ebb3a921c1 ("smarter propagate_mnt()") Fixes: 5ec0811d3037 ("propogate_mnt: Handle the first propogated copy being a slave") Cc: stable@vger.kernel.org Reported-by: Ditang Chen ditang.c@gmail.com Signed-off-by: Seth Forshee (Digital Ocean) sforshee@kernel.org Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- If there are no big objections I'll get this to Linus rather sooner than later. --- fs/pnode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/pnode.c +++ b/fs/pnode.c @@ -244,7 +244,7 @@ static int propagate_one(struct mount *m } do { struct mount *parent = last_source->mnt_parent; - if (last_source == first_source) + if (peers(last_source, first_source)) break; done = parent->mnt_master == p; if (done && peers(n, parent))

From: Mikulas Patocka mpatocka@redhat.com

commit 341097ee53573e06ab9fc675d96a052385b851fa upstream.

There's a crash in mempool_free when running the lvm test shell/lvchange-rebuild-raid.sh.

The reason for the crash is this: * super_written calls atomic_dec_and_test(&mddev->pending_writes) and wake_up(&mddev->sb_wait). Then it calls rdev_dec_pending(rdev, mddev) and bio_put(bio). * so, the process that waited on sb_wait and that is woken up is racing with bio_put(bio). * if the process wins the race, it calls bioset_exit before bio_put(bio) is executed. * bio_put(bio) attempts to free a bio into a destroyed bio set - causing a crash in mempool_free.

We fix this bug by moving bio_put before atomic_dec_and_test.

We also move rdev_dec_pending before atomic_dec_and_test as suggested by Neil Brown.

The function md_end_flush has a similar bug - we must call bio_put before we decrement the number of in-progress bios.

BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 11557f0067 P4D 11557f0067 PUD 0 Oops: 0002 [#1] PREEMPT SMP CPU: 0 PID: 73 Comm: kworker/0:1 Not tainted 6.1.0-rc3 #5 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 Workqueue: kdelayd flush_expired_bios [dm_delay] RIP: 0010:mempool_free+0x47/0x80 Code: 48 89 ef 5b 5d ff e0 f3 c3 48 89 f7 e8 32 45 3f 00 48 63 53 08 48 89 c6 3b 53 04 7d 2d 48 8b 43 10 8d 4a 01 48 89 df 89 4b 08 <48> 89 2c d0 e8 b0 45 3f 00 48 8d 7b 30 5b 5d 31 c9 ba 01 00 00 00 RSP: 0018:ffff88910036bda8 EFLAGS: 00010093 RAX: 0000000000000000 RBX: ffff8891037b65d8 RCX: 0000000000000001 RDX: 0000000000000000 RSI: 0000000000000202 RDI: ffff8891037b65d8 RBP: ffff8891447ba240 R08: 0000000000012908 R09: 00000000003d0900 R10: 0000000000000000 R11: 0000000000173544 R12: ffff889101a14000 R13: ffff8891562ac300 R14: ffff889102b41440 R15: ffffe8ffffa00d05 FS: 0000000000000000(0000) GS:ffff88942fa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000001102e99000 CR4: 00000000000006b0 Call Trace: <TASK> clone_endio+0xf4/0x1c0 [dm_mod] clone_endio+0xf4/0x1c0 [dm_mod] __submit_bio+0x76/0x120 submit_bio_noacct_nocheck+0xb6/0x2a0 flush_expired_bios+0x28/0x2f [dm_delay] process_one_work+0x1b4/0x300 worker_thread+0x45/0x3e0 ? rescuer_thread+0x380/0x380 kthread+0xc2/0x100 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 </TASK> Modules linked in: brd dm_delay dm_raid dm_mod af_packet uvesafb cfbfillrect cfbimgblt cn cfbcopyarea fb font fbdev tun autofs4 binfmt_misc configfs ipv6 virtio_rng virtio_balloon rng_core virtio_net pcspkr net_failover failover qemu_fw_cfg button mousedev raid10 raid456 libcrc32c async_raid6_recov async_memcpy async_pq raid6_pq async_xor xor async_tx raid1 raid0 md_mod sd_mod t10_pi crc64_rocksoft crc64 virtio_scsi scsi_mod evdev psmouse bsg scsi_common [last unloaded: brd] CR2: 0000000000000000 ---[ end trace 0000000000000000 ]---

Signed-off-by: Mikulas Patocka mpatocka@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Song Liu song@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/md/md.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

--- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -509,13 +509,14 @@ static void md_end_flush(struct bio *bio struct md_rdev *rdev = bio->bi_private; struct mddev *mddev = rdev->mddev;

+ bio_put(bio); + rdev_dec_pending(rdev, mddev);

if (atomic_dec_and_test(&mddev->flush_pending)) { /* The pre-request flush has finished */ queue_work(md_wq, &mddev->flush_work); } - bio_put(bio); }

static void md_submit_flush_data(struct work_struct *ws); @@ -913,10 +914,12 @@ static void super_written(struct bio *bi } else clear_bit(LastDev, &rdev->flags);

+ bio_put(bio); + + rdev_dec_pending(rdev, mddev); + if (atomic_dec_and_test(&mddev->pending_writes)) wake_up(&mddev->sb_wait); - rdev_dec_pending(rdev, mddev); - bio_put(bio); }

void md_super_write(struct mddev *mddev, struct md_rdev *rdev,

From: Pavel Machek pavel@denx.de

commit c3db3c2fd9992c08f49aa93752d3c103c3a4f6aa upstream.

The commit introduces another bug.

Cc: stable@vger.kernel.org Fixes: c6ad7fd16657e ("f2fs: fix to do sanity check on summary info") Signed-off-by: Pavel Machek pavel@denx.de Reviewed-by: Chao Yu chao@kernel.org Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/gc.c | 1 + 1 file changed, 1 insertion(+)

--- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1109,6 +1109,7 @@ static bool is_alive(struct f2fs_sb_info if (ofs_in_node >= max_addrs) { f2fs_err(sbi, "Inconsistent ofs_in_node:%u in summary, ino:%u, nid:%u, max:%u", ofs_in_node, dni->ino, dni->nid, max_addrs); + f2fs_put_page(node_page, 1); return false; }

From: Jan Kara jack@suse.cz

commit 36369f46e91785688a5f39d7a5590e3f07981316 upstream.

Since commit 10c70d95c0f2 ("block: remove the bd_openers checks in blk_drop_partitions") we allow rereading of partition table although there are users of the block device. This has an undesirable consequence that e.g. if sda and sdb are assembled to a RAID1 device md0 with partitions, BLKRRPART ioctl on sda will rescan partition table and create sda1 device. This partition device under a raid device confuses some programs (such as libstorage-ng used for initial partitioning for distribution installation) leading to failures.

Fix the problem refusing to rescan partitions if there is another user that has the block device exclusively open.

Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20221130135344.2ul4cyfstfs3znxg@quack3 Fixes: 10c70d95c0f2 ("block: remove the bd_openers checks in blk_drop_partitions") Signed-off-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20221130175653.24299-1-jack@suse.cz [axboe: fold in followup fix] Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- block/blk.h | 2 +- block/genhd.c | 7 +++++-- block/ioctl.c | 12 +++++++----- 3 files changed, 13 insertions(+), 8 deletions(-)

--- a/block/blk.h +++ b/block/blk.h @@ -429,7 +429,7 @@ static inline struct kmem_cache *blk_get } struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu);

-int disk_scan_partitions(struct gendisk *disk, fmode_t mode); +int disk_scan_partitions(struct gendisk *disk, fmode_t mode, void *owner);

int disk_alloc_events(struct gendisk *disk); void disk_add_events(struct gendisk *disk); --- a/block/genhd.c +++ b/block/genhd.c @@ -356,7 +356,7 @@ void disk_uevent(struct gendisk *disk, e } EXPORT_SYMBOL_GPL(disk_uevent);

-int disk_scan_partitions(struct gendisk *disk, fmode_t mode) +int disk_scan_partitions(struct gendisk *disk, fmode_t mode, void *owner) { struct block_device *bdev;

@@ -366,6 +366,9 @@ int disk_scan_partitions(struct gendisk return -EINVAL; if (disk->open_partitions) return -EBUSY; + /* Someone else has bdev exclusively open? */ + if (disk->part0->bd_holder && disk->part0->bd_holder != owner) + return -EBUSY;

set_bit(GD_NEED_PART_SCAN, &disk->state); bdev = blkdev_get_by_dev(disk_devt(disk), mode, NULL); @@ -499,7 +502,7 @@ int __must_check device_add_disk(struct

bdev_add(disk->part0, ddev->devt); if (get_capacity(disk)) - disk_scan_partitions(disk, FMODE_READ); + disk_scan_partitions(disk, FMODE_READ, NULL);

/* * Announce the disk and partitions after all partitions are --- a/block/ioctl.c +++ b/block/ioctl.c @@ -467,9 +467,10 @@ static int blkdev_bszset(struct block_de * user space. Note the separate arg/argp parameters that are needed * to deal with the compat_ptr() conversion. */ -static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, - unsigned cmd, unsigned long arg, void __user *argp) +static int blkdev_common_ioctl(struct file *file, fmode_t mode, unsigned cmd, + unsigned long arg, void __user *argp) { + struct block_device *bdev = I_BDEV(file->f_mapping->host); unsigned int max_sectors;

switch (cmd) { @@ -527,7 +528,8 @@ static int blkdev_common_ioctl(struct bl return -EACCES; if (bdev_is_partition(bdev)) return -EINVAL; - return disk_scan_partitions(bdev->bd_disk, mode & ~FMODE_EXCL); + return disk_scan_partitions(bdev->bd_disk, mode & ~FMODE_EXCL, + file); case BLKTRACESTART: case BLKTRACESTOP: case BLKTRACETEARDOWN: @@ -605,7 +607,7 @@ long blkdev_ioctl(struct file *file, uns break; }

- ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp); + ret = blkdev_common_ioctl(file, mode, cmd, arg, argp); if (ret != -ENOIOCTLCMD) return ret;

@@ -674,7 +676,7 @@ long compat_blkdev_ioctl(struct file *fi break; }

- ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp); + ret = blkdev_common_ioctl(file, mode, cmd, arg, argp); if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl) ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg);

From: Hanjun Guo guohanjun@huawei.com

commit 8740a12ca2e2959531ad253bac99ada338b33d80 upstream.

The start and length of the event log area are obtained from TPM2 or TCPA table, so we call acpi_get_table() to get the ACPI information, but the acpi_get_table() should be coupled with acpi_put_table() to release the ACPI memory, add the acpi_put_table() properly to fix the memory leak.

While we are at it, remove the redundant empty line at the end of the tpm_read_log_acpi().

Fixes: 0bfb23746052 ("tpm: Move eventlog files to a subdirectory") Fixes: 85467f63a05c ("tpm: Add support for event log pointer found in TPM2 ACPI table") Cc: stable@vger.kernel.org Signed-off-by: Hanjun Guo guohanjun@huawei.com Reviewed-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/char/tpm/eventlog/acpi.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-)

--- a/drivers/char/tpm/eventlog/acpi.c +++ b/drivers/char/tpm/eventlog/acpi.c @@ -90,16 +90,21 @@ int tpm_read_log_acpi(struct tpm_chip *c return -ENODEV;

if (tbl->header.length < - sizeof(*tbl) + sizeof(struct acpi_tpm2_phy)) + sizeof(*tbl) + sizeof(struct acpi_tpm2_phy)) { + acpi_put_table((struct acpi_table_header *)tbl); return -ENODEV; + }

tpm2_phy = (void *)tbl + sizeof(*tbl); len = tpm2_phy->log_area_minimum_length;

start = tpm2_phy->log_area_start_address; - if (!start || !len) + if (!start || !len) { + acpi_put_table((struct acpi_table_header *)tbl); return -ENODEV; + }

+ acpi_put_table((struct acpi_table_header *)tbl); format = EFI_TCG2_EVENT_LOG_FORMAT_TCG_2; } else { /* Find TCPA entry in RSDT (ACPI_LOGICAL_ADDRESSING) */ @@ -120,8 +125,10 @@ int tpm_read_log_acpi(struct tpm_chip *c break; }

+ acpi_put_table((struct acpi_table_header *)buff); format = EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2; } + if (!len) { dev_warn(&chip->dev, "%s: TCPA log area empty\n", __func__); return -EIO; @@ -156,5 +163,4 @@ err: kfree(log->bios_event_log); log->bios_event_log = NULL; return ret; - }

From: Hanjun Guo guohanjun@huawei.com

commit db9622f762104459ff87ecdf885cc42c18053fd9 upstream.

In check_acpi_tpm2(), we get the TPM2 table just to make sure the table is there, not used after the init, so the acpi_put_table() should be added to release the ACPI memory.

Fixes: 4cb586a188d4 ("tpm_tis: Consolidate the platform and acpi probe flow") Cc: stable@vger.kernel.org Signed-off-by: Hanjun Guo guohanjun@huawei.com Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/char/tpm/tpm_tis.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

--- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -125,6 +125,7 @@ static int check_acpi_tpm2(struct device const struct acpi_device_id *aid = acpi_match_device(tpm_acpi_tbl, dev); struct acpi_table_tpm2 *tbl; acpi_status st; + int ret = 0;

if (!aid || aid->driver_data != DEVICE_IS_TPM2) return 0; @@ -132,8 +133,7 @@ static int check_acpi_tpm2(struct device /* If the ACPI TPM2 signature is matched then a global ACPI_SIG_TPM2 * table is mandatory */ - st = - acpi_get_table(ACPI_SIG_TPM2, 1, (struct acpi_table_header **)&tbl); + st = acpi_get_table(ACPI_SIG_TPM2, 1, (struct acpi_table_header **)&tbl); if (ACPI_FAILURE(st) || tbl->header.length < sizeof(*tbl)) { dev_err(dev, FW_BUG "failed to get TPM2 ACPI table\n"); return -EINVAL; @@ -141,9 +141,10 @@ static int check_acpi_tpm2(struct device

/* The tpm2_crb driver handles this device */ if (tbl->start_method != ACPI_TPM2_MEMORY_MAPPED) - return -ENODEV; + ret = -ENODEV;

- return 0; + acpi_put_table((struct acpi_table_header *)tbl); + return ret; } #else static int check_acpi_tpm2(struct device *dev)

From: Marco Elver elver@google.com

commit 7c201739beef1a586d806463f1465429cdce34c5 upstream.

With Clang version 16+, -fsanitize=thread will turn memcpy/memset/memmove calls in instrumented functions into __tsan_memcpy/__tsan_memset/__tsan_memmove calls respectively.

Add these functions to the core KCSAN runtime, so that we (a) catch data races with mem* functions, and (b) won't run into linker errors with such newer compilers.

Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: Marco Elver elver@google.com Signed-off-by: Paul E. McKenney paulmck@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/kcsan/core.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+)

--- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -14,10 +14,12 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> +#include <linux/minmax.h> #include <linux/moduleparam.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/sched.h> +#include <linux/string.h> #include <linux/uaccess.h>

#include "encoding.h" @@ -1308,3 +1310,51 @@ noinline void __tsan_atomic_signal_fence } } EXPORT_SYMBOL(__tsan_atomic_signal_fence); + +#ifdef __HAVE_ARCH_MEMSET +void *__tsan_memset(void *s, int c, size_t count); +noinline void *__tsan_memset(void *s, int c, size_t count) +{ + /* + * Instead of not setting up watchpoints where accessed size is greater + * than MAX_ENCODABLE_SIZE, truncate checked size to MAX_ENCODABLE_SIZE. + */ + size_t check_len = min_t(size_t, count, MAX_ENCODABLE_SIZE); + + check_access(s, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); + return memset(s, c, count); +} +#else +void *__tsan_memset(void *s, int c, size_t count) __alias(memset); +#endif +EXPORT_SYMBOL(__tsan_memset); + +#ifdef __HAVE_ARCH_MEMMOVE +void *__tsan_memmove(void *dst, const void *src, size_t len); +noinline void *__tsan_memmove(void *dst, const void *src, size_t len) +{ + size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); + + check_access(dst, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); + check_access(src, check_len, 0, _RET_IP_); + return memmove(dst, src, len); +} +#else +void *__tsan_memmove(void *dst, const void *src, size_t len) __alias(memmove); +#endif +EXPORT_SYMBOL(__tsan_memmove); + +#ifdef __HAVE_ARCH_MEMCPY +void *__tsan_memcpy(void *dst, const void *src, size_t len); +noinline void *__tsan_memcpy(void *dst, const void *src, size_t len) +{ + size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); + + check_access(dst, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); + check_access(src, check_len, 0, _RET_IP_); + return memcpy(dst, src, len); +} +#else +void *__tsan_memcpy(void *dst, const void *src, size_t len) __alias(memcpy); +#endif +EXPORT_SYMBOL(__tsan_memcpy);