From: Jens Axboe axboe@kernel.dk

stable inclusion from stable-v5.10.118 commit 3c48558be571e01f67e65edcf03193484eeb2b79 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

Lee reports that there's a use-after-free of the process file table. There's an assumption that we don't need the file table for some variants of statx invocation, but that turns out to be false and we end up with not grabbing a reference for the request even if the deferred execution uses it.

Get rid of the REQ_F_NO_FILE_TABLE optimization for statx, and always grab that reference.

This issues doesn't exist upstream since the native workers got introduced with 5.12.

Link: https://lore.kernel.org/io-uring/YoOJ%2FT4QRKC+fAZE@google.com/ Reported-by: Lee Jones lee.jones@linaro.org Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- fs/io_uring.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c index 040d1aafc968..5a88260a8dd8 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4263,12 +4263,8 @@ static int io_statx(struct io_kiocb *req, bool force_nonblock) struct io_statx *ctx = &req->statx; int ret;

- if (force_nonblock) { - /* only need file table for an actual valid fd */ - if (ctx->dfd == -1 || ctx->dfd == AT_FDCWD) - req->flags |= REQ_F_NO_FILE_TABLE; + if (force_nonblock) return -EAGAIN; - }

ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask, ctx->buffer);

From: Sasha Neftin sasha.neftin@intel.com

stable inclusion from stable-v5.10.118 commit d0229838b63c1f5f33a267c067e7e66e126929aa category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 47bca7de6a4fb8dcb564c7ca14d885c91ed19e03 upstream.

i225 devices have only one phy->type: copper. There is no point checking phy->type during the igc_has_link method from the watchdog that invoked every 2 seconds. This patch comes to clean up these pointless checkings.

Signed-off-by: Sasha Neftin sasha.neftin@intel.com Tested-by: Dvora Fuxbrumer dvorax.fuxbrumer@linux.intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Nobuhiro Iwamatsu nobuhiro1.iwamatsu@toshiba.co.jp Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/net/ethernet/intel/igc/igc_main.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 9190fe16fe26..aa2426cdfa5e 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4160,17 +4160,10 @@ bool igc_has_link(struct igc_adapter *adapter) * false until the igc_check_for_link establishes link * for copper adapters ONLY */ - switch (hw->phy.media_type) { - case igc_media_type_copper: - if (!hw->mac.get_link_status) - return true; - hw->mac.ops.check_for_link(hw); - link_active = !hw->mac.get_link_status; - break; - default: - case igc_media_type_unknown: - break; - } + if (!hw->mac.get_link_status) + return true; + hw->mac.ops.check_for_link(hw); + link_active = !hw->mac.get_link_status;

if (hw->mac.type == igc_i225) { if (!netif_carrier_ok(adapter->netdev)) {

From: Vincent Whitchurch vincent.whitchurch@axis.com

stable inclusion from stable-v5.10.118 commit 2b4e5a2d7da04e6c80a5869fe209caee322a65b6 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit c8fa17d9f08a448184f03d352145099b5beb618e ]

If the irqwork is still scheduled or running while the RTC device is removed, a use-after-free occurs in rtc_timer_do_work(). Cleanup the timerqueue and ensure the work is stopped to fix this.

BUG: KASAN: use-after-free in mutex_lock+0x94/0x110 Write of size 8 at addr ffffff801d846338 by task kworker/3:1/41

Workqueue: events rtc_timer_do_work Call trace: mutex_lock+0x94/0x110 rtc_timer_do_work+0xec/0x630 process_one_work+0x5fc/0x1344 ...

Allocated by task 551: kmem_cache_alloc_trace+0x384/0x6e0 devm_rtc_allocate_device+0xf0/0x574 devm_rtc_device_register+0x2c/0x12c ...

Freed by task 572: kfree+0x114/0x4d0 rtc_device_release+0x64/0x80 device_release+0x8c/0x1f4 kobject_put+0x1c4/0x4b0 put_device+0x20/0x30 devm_rtc_release_device+0x1c/0x30 devm_action_release+0x54/0x90 release_nodes+0x124/0x310 devres_release_group+0x170/0x240 i2c_device_remove+0xd8/0x314 ...

Last potentially related work creation: insert_work+0x5c/0x330 queue_work_on+0xcc/0x154 rtc_set_time+0x188/0x5bc rtc_dev_ioctl+0x2ac/0xbd0 ...

Signed-off-by: Vincent Whitchurch vincent.whitchurch@axis.com Signed-off-by: Alexandre Belloni alexandre.belloni@bootlin.com Link: https://lore.kernel.org/r/20211210160951.7718-1-vincent.whitchurch@axis.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/rtc/class.c | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 7c88d190c51f..625effe6cb65 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -26,6 +26,15 @@ struct class *rtc_class; static void rtc_device_release(struct device *dev) { struct rtc_device *rtc = to_rtc_device(dev); + struct timerqueue_head *head = &rtc->timerqueue; + struct timerqueue_node *node; + + mutex_lock(&rtc->ops_lock); + while ((node = timerqueue_getnext(head))) + timerqueue_del(head, node); + mutex_unlock(&rtc->ops_lock); + + cancel_work_sync(&rtc->irqwork);

ida_simple_remove(&rtc_ida, rtc->id); kfree(rtc);

From: David Gow davidgow@google.com

stable inclusion from stable-v5.10.118 commit ea6a86886caa1ec659dd08b38ca879bacde47123 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit f4f03f299a56ce4d73c5431e0327b3b6cb55ebb9 ]

The syscall_handler_t type for x86_64 was defined as 'long (*)(void)', but always cast to 'long (*)(long, long, long, long, long, long)' before use. This now triggers a warning (see below).

Define syscall_handler_t as the latter instead, and remove the cast. This simplifies the code, and fixes the warning.

Warning: In file included from ../arch/um/include/asm/processor-generic.h:13 from ../arch/x86/um/asm/processor.h:41 from ../include/linux/rcupdate.h:30 from ../include/linux/rculist.h:11 from ../include/linux/pid.h:5 from ../include/linux/sched.h:14 from ../include/linux/ptrace.h:6 from ../arch/um/kernel/skas/syscall.c:7: ../arch/um/kernel/skas/syscall.c: In function ‘handle_syscall’: ../arch/x86/um/shared/sysdep/syscalls_64.h:18:11: warning: cast between incompatible function types from ‘long int (*)(void)’ to ‘long int (*)(long int, long int, long int, long int, long int, long int)’ [ -Wcast-function-type] 18 | (((long (*)(long, long, long, long, long, long)) \ | ^ ../arch/x86/um/asm/ptrace.h:36:62: note: in definition of macro ‘PT_REGS_SET_SYSCALL_RETURN’ 36 | #define PT_REGS_SET_SYSCALL_RETURN(r, res) (PT_REGS_AX(r) = (res)) | ^~~ ../arch/um/kernel/skas/syscall.c:46:33: note: in expansion of macro ‘EXECUTE_SYSCALL’ 46 | EXECUTE_SYSCALL(syscall, regs)); | ^~~~~~~~~~~~~~~

Signed-off-by: David Gow davidgow@google.com Signed-off-by: Richard Weinberger richard@nod.at Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- arch/x86/um/shared/sysdep/syscalls_64.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/x86/um/shared/sysdep/syscalls_64.h b/arch/x86/um/shared/sysdep/syscalls_64.h index 8a7d5e1da98e..1e6875b4ffd8 100644 --- a/arch/x86/um/shared/sysdep/syscalls_64.h +++ b/arch/x86/um/shared/sysdep/syscalls_64.h @@ -10,13 +10,12 @@ #include <linux/msg.h> #include <linux/shm.h>

-typedef long syscall_handler_t(void); +typedef long syscall_handler_t(long, long, long, long, long, long);

extern syscall_handler_t *sys_call_table[];

#define EXECUTE_SYSCALL(syscall, regs) \ - (((long (*)(long, long, long, long, long, long)) \ - (*sys_call_table[syscall]))(UPT_SYSCALL_ARG1(&regs->regs), \ + (((*sys_call_table[syscall]))(UPT_SYSCALL_ARG1(&regs->regs), \ UPT_SYSCALL_ARG2(&regs->regs), \ UPT_SYSCALL_ARG3(&regs->regs), \ UPT_SYSCALL_ARG4(&regs->regs), \

From: Zheng Yongjun zhengyongjun3@huawei.com

stable inclusion from stable-v5.10.118 commit 5565fc538ded8961c9d885ad37200ee72a7bd1a2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 26623eea0da3476446909af96c980768df07bbd9 ]

pm_runtime_get_sync() will increment pm usage counter even it failed. Forgetting to call pm_runtime_put_noidle will result in reference leak in stmfts_input_open, so we should fix it.

Signed-off-by: Zheng Yongjun zhengyongjun3@huawei.com Link: https://lore.kernel.org/r/20220317131604.53538-1-zhengyongjun3@huawei.com Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/input/touchscreen/stmfts.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/input/touchscreen/stmfts.c b/drivers/input/touchscreen/stmfts.c index 9a64e1dbc04a..64b690a72d10 100644 --- a/drivers/input/touchscreen/stmfts.c +++ b/drivers/input/touchscreen/stmfts.c @@ -339,11 +339,11 @@ static int stmfts_input_open(struct input_dev *dev)

err = pm_runtime_get_sync(&sdata->client->dev); if (err < 0) - return err; + goto out;

err = i2c_smbus_write_byte(sdata->client, STMFTS_MS_MT_SENSE_ON); if (err) - return err; + goto out;

mutex_lock(&sdata->mutex); sdata->running = true; @@ -366,7 +366,9 @@ static int stmfts_input_open(struct input_dev *dev) "failed to enable touchkey\n"); }

- return 0; +out: + pm_runtime_put_noidle(&sdata->client->dev); + return err; }

static void stmfts_input_close(struct input_dev *dev)

From: Andreas Gruenbacher agruenba@redhat.com

stable inclusion from stable-v5.10.118 commit bab037ebbe7dbb5f631dfce5b989fcf9e5653c0c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 52f3f033a5dbd023307520af1ff551cadfd7f037 ]

During lockless buffered reads, filemap_read() holds page cache page references while trying to copy data to the user-space buffer. The calling process isn't holding the inode glock, but the page references it holds prevent those pages from being removed from the page cache, and that prevents the underlying inode glock from being moved to another node. Thus, we can end up in the same kinds of distributed deadlock situations as with normal (non-lockless) buffered reads.

Fix that by disabling page faults during lockless reads as well.

Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- fs/gfs2/file.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 2e6f622ed428..55a8eb3c1963 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -858,14 +858,16 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) return ret; iocb->ki_flags &= ~IOCB_DIRECT; } + pagefault_disable(); iocb->ki_flags |= IOCB_NOIO; ret = generic_file_read_iter(iocb, to); iocb->ki_flags &= ~IOCB_NOIO; + pagefault_enable(); if (ret >= 0) { if (!iov_iter_count(to)) return ret; written = ret; - } else { + } else if (ret != -EFAULT) { if (ret != -EAGAIN) return ret; if (iocb->ki_flags & IOCB_NOWAIT)

From: Zheng Yongjun zhengyongjun3@huawei.com

stable inclusion from stable-v5.10.118 commit 39acee8aea3d02f649fb840bf0d72e3603fc9c83 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit e9a36feecee0ee5845f2e0656f50f9942dd0bed3 ]

pm_runtime_get_sync() will increment pm usage counter even it failed. Forgetting to call pm_runtime_put_noidle will result in reference leak in stm32_crc_remove, so we should fix it.

Signed-off-by: Zheng Yongjun zhengyongjun3@huawei.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/crypto/stm32/stm32-crc32.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c index be1bf39a317d..90a920e7f664 100644 --- a/drivers/crypto/stm32/stm32-crc32.c +++ b/drivers/crypto/stm32/stm32-crc32.c @@ -384,8 +384,10 @@ static int stm32_crc_remove(struct platform_device *pdev) struct stm32_crc *crc = platform_get_drvdata(pdev); int ret = pm_runtime_get_sync(crc->dev);

- if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(crc->dev); return ret; + }

spin_lock(&crc_list.lock); list_del(&crc->list);

From: Kai-Heng Feng kai.heng.feng@canonical.com

stable inclusion from stable-v5.10.118 commit 7d3f69cbdec8529cbad3905a41c7b27a1ee39279 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 5a8738571747c1e275a40b69a608657603867b7e ]

Lenovo P360 is another platform equipped with ALC897, and it needs ALC897_FIXUP_HEADSET_MIC_PIN quirk to make its headset mic work.

Signed-off-by: Kai-Heng Feng kai.heng.feng@canonical.com Link: https://lore.kernel.org/r/20220325160501.705221-1-kai.heng.feng@canonical.co... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a5b1fd62a99c..3f880c4fd5e0 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -10876,6 +10876,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS), + SND_PCI_QUIRK(0x17aa, 0x1057, "Lenovo P360", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32ca, "Lenovo ThinkCentre M80", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32cb, "Lenovo ThinkCentre M70", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32cf, "Lenovo ThinkCentre M950", ALC897_FIXUP_HEADSET_MIC_PIN),

From: Zhu Lingshan lingshan.zhu@intel.com

stable inclusion from stable-v5.10.118 commit 5a4cbcb3df45be164bdf9257ea7e0dd89e447cf3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit cce0ab2b2a39072d81f98017f7b076f3410ef740 ]

When irq number is negative(e.g., -EINVAL), the virtqueue may be disabled or the virtqueues are sharing a device irq. In such case, we should not setup irq offloading for a virtqueue.

Signed-off-by: Zhu Lingshan lingshan.zhu@intel.com Link: https://lore.kernel.org/r/20220222115428.998334-3-lingshan.zhu@intel.com Signed-off-by: Michael S. Tsirkin mst@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/vhost/vdpa.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index e4d60009d908..04578aa87e4d 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -97,8 +97,11 @@ static void vhost_vdpa_setup_vq_irq(struct vhost_vdpa *v, u16 qid) return;

irq = ops->get_vq_irq(vdpa, qid); + if (irq < 0) + return; + irq_bypass_unregister_producer(&vq->call_ctx.producer); - if (!vq->call_ctx.ctx || irq < 0) + if (!vq->call_ctx.ctx) return;

vq->call_ctx.producer.token = vq->call_ctx.ctx;

From: Anton Eidelman anton.eidelman@gmail.com

stable inclusion from stable-v5.10.118 commit 87fd0dd43e9c09155f67716ba0f9306fd3d077b8 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit a4a6f3c8f61c3cfbda4998ad94596059ad7e4332 ]

nvme_mpath_init_identify() invoked from nvme_init_identify() fetches a fresh ANA log from the ctrl. This is essential to have an up to date path states for both existing namespaces and for those scan_work may discover once the ctrl is up.

This happens in the following cases: 1) A new ctrl is being connected. 2) An existing ctrl is successfully reconnected. 3) An existing ctrl is being reset.

While in (1) ctrl->namespaces is empty, (2 & 3) may have namespaces, and nvme_read_ana_log() may call nvme_update_ns_ana_state().

This result in a hang when the ANA state of an existing namespace changes and makes the disk live: nvme_mpath_set_live() issues IO to the namespace through the ctrl, which does NOT have IO queues yet.

See sample hang below.

Solution: - nvme_update_ns_ana_state() to call set_live only if ctrl is live - nvme_read_ana_log() call from nvme_mpath_init_identify() therefore only fetches and parses the ANA log; any erros in this process will fail the ctrl setup as appropriate; - a separate function nvme_mpath_update() is called in nvme_start_ctrl(); this parses the ANA log without fetching it. At this point the ctrl is live, therefore, disks can be set live normally.

Sample failure: nvme nvme0: starting error recovery nvme nvme0: Reconnecting in 10 seconds... block nvme0n6: no usable path - requeuing I/O INFO: task kworker/u8:3:312 blocked for more than 122 seconds. Tainted: G E 5.14.5-1.el7.elrepo.x86_64 #1 Workqueue: nvme-wq nvme_tcp_reconnect_ctrl_work [nvme_tcp] Call Trace: __schedule+0x2a2/0x7e0 schedule+0x4e/0xb0 io_schedule+0x16/0x40 wait_on_page_bit_common+0x15c/0x3e0 do_read_cache_page+0x1e0/0x410 read_cache_page+0x12/0x20 read_part_sector+0x46/0x100 read_lba+0x121/0x240 efi_partition+0x1d2/0x6a0 bdev_disk_changed.part.0+0x1df/0x430 bdev_disk_changed+0x18/0x20 blkdev_get_whole+0x77/0xe0 blkdev_get_by_dev+0xd2/0x3a0 __device_add_disk+0x1ed/0x310 device_add_disk+0x13/0x20 nvme_mpath_set_live+0x138/0x1b0 [nvme_core] nvme_update_ns_ana_state+0x2b/0x30 [nvme_core] nvme_update_ana_state+0xca/0xe0 [nvme_core] nvme_parse_ana_log+0xac/0x170 [nvme_core] nvme_read_ana_log+0x7d/0xe0 [nvme_core] nvme_mpath_init_identify+0x105/0x150 [nvme_core] nvme_init_identify+0x2df/0x4d0 [nvme_core] nvme_init_ctrl_finish+0x8d/0x3b0 [nvme_core] nvme_tcp_setup_ctrl+0x337/0x390 [nvme_tcp] nvme_tcp_reconnect_ctrl_work+0x24/0x40 [nvme_tcp] process_one_work+0x1bd/0x360 worker_thread+0x50/0x3d0

Signed-off-by: Anton Eidelman anton@lightbitslabs.com Reviewed-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/nvme/host/core.c | 1 + drivers/nvme/host/multipath.c | 25 +++++++++++++++++++++++-- drivers/nvme/host/nvme.h | 4 ++++ 3 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 274635c0c02a..2de09ce5c9d5 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4400,6 +4400,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) if (ctrl->queue_count > 1) { nvme_queue_scan(ctrl); nvme_start_queues(ctrl); + nvme_mpath_update(ctrl); } } EXPORT_SYMBOL_GPL(nvme_start_ctrl); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 18a756444d5a..a9e15c8f907b 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -484,8 +484,17 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc, ns->ana_grpid = le32_to_cpu(desc->grpid); ns->ana_state = desc->state; clear_bit(NVME_NS_ANA_PENDING, &ns->flags); - - if (nvme_state_is_live(ns->ana_state)) + /* + * nvme_mpath_set_live() will trigger I/O to the multipath path device + * and in turn to this path device. However we cannot accept this I/O + * if the controller is not live. This may deadlock if called from + * nvme_mpath_init_identify() and the ctrl will never complete + * initialization, preventing I/O from completing. For this case we + * will reprocess the ANA log page in nvme_mpath_update() once the + * controller is ready. + */ + if (nvme_state_is_live(ns->ana_state) && + ns->ctrl->state == NVME_CTRL_LIVE) nvme_mpath_set_live(ns); }

@@ -572,6 +581,18 @@ static void nvme_ana_work(struct work_struct *work) nvme_read_ana_log(ctrl); }

+void nvme_mpath_update(struct nvme_ctrl *ctrl) +{ + u32 nr_change_groups = 0; + + if (!ctrl->ana_log_buf) + return; + + mutex_lock(&ctrl->ana_lock); + nvme_parse_ana_log(ctrl, &nr_change_groups, nvme_update_ana_state); + mutex_unlock(&ctrl->ana_lock); +} + static void nvme_anatt_timeout(struct timer_list *t) { struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 11d3cc2890f9..7bb773aca705 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -723,6 +723,7 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id); void nvme_mpath_remove_disk(struct nvme_ns_head *head); int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id); void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl); +void nvme_mpath_update(struct nvme_ctrl *ctrl); void nvme_mpath_uninit(struct nvme_ctrl *ctrl); void nvme_mpath_stop(struct nvme_ctrl *ctrl); bool nvme_mpath_clear_current_path(struct nvme_ns *ns); @@ -809,6 +810,9 @@ static inline int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, "Please enable CONFIG_NVME_MULTIPATH for full support of multi-port devices.\n"); return 0; } +static inline void nvme_mpath_update(struct nvme_ctrl *ctrl) +{ +} static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl) { }

From: Guo Xuenan guoxuenan@huawei.com

stable inclusion from stable-v5.10.118 commit 05c073b1ad2565a9c4eeb05a3414aef19985fe57 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 49df34221804cfd6384135b28b03c9461a31d024 ]

when get fiemap starting from MAX_LFS_FILESIZE, (maxbytes - *len) < start will always true , then *len set zero. because of start offset is beyond file size, for erofs filesystem it will always return iomap.length with zero,iomap iterate will enter infinite loop. it is necessary cover this corner case to avoid this situation.

------------[ cut here ]------------ WARNING: CPU: 7 PID: 905 at fs/iomap/iter.c:35 iomap_iter+0x97f/0xc70 Modules linked in: xfs erofs CPU: 7 PID: 905 Comm: iomap Tainted: G W 5.17.0-rc8 #27 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:iomap_iter+0x97f/0xc70 Code: 85 a1 fc ff ff e8 71 be 9c ff 0f 1f 44 00 00 e9 92 fc ff ff e8 62 be 9c ff 0f 0b b8 fb ff ff ff e9 fc f8 ff ff e8 51 be 9c ff <0f> 0b e9 2b fc ff ff e8 45 be 9c ff 0f 0b e9 e1 fb ff ff e8 39 be RSP: 0018:ffff888060a37ab0 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff888060a37bb0 RCX: 0000000000000000 RDX: ffff88807e19a900 RSI: ffffffff81a7da7f RDI: ffff888060a37be0 RBP: 7fffffffffffffff R08: 0000000000000000 R09: ffff888060a37c20 R10: ffff888060a37c67 R11: ffffed100c146f8c R12: 7fffffffffffffff R13: 0000000000000000 R14: ffff888060a37bd8 R15: ffff888060a37c20 FS: 00007fd3cca01540(0000) GS:ffff888108780000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020010820 CR3: 0000000054b92000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> iomap_fiemap+0x1c9/0x2f0 erofs_fiemap+0x64/0x90 [erofs] do_vfs_ioctl+0x40d/0x12e0 __x64_sys_ioctl+0xaa/0x1c0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae </TASK> ---[ end trace 0000000000000000 ]--- watchdog: BUG: soft lockup - CPU#7 stuck for 26s! [iomap:905]

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Guo Xuenan guoxuenan@huawei.com Reviewed-by: Christoph Hellwig hch@lst.de [djwong: fix some typos] Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- fs/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ioctl.c b/fs/ioctl.c index 4e6cc0a7d69c..7bcc60091287 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -170,7 +170,7 @@ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo,

if (*len == 0) return -EINVAL; - if (start > maxbytes) + if (start >= maxbytes) return -EFBIG;

/*

From: Jakob Koschel jakobkoschel@gmail.com

stable inclusion from stable-v5.10.118 commit 5a19f3c2d3b6e5f5237cb79849626c85831a5fa9 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 901aeda62efa21f2eae937bccb71b49ae531be06 ]

In preparation to limit the scope of a list iterator to the list traversal loop, use a dedicated pointer to iterate through the list [1].

Since that variable should not be used past the loop iteration, a separate variable is used to 'remember the current location within the loop'.

To either continue iterating from that position or skip the iteration (if the previous iteration was complete) list_prepare_entry() is used.

Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWX... [1] Signed-off-by: Jakob Koschel jakobkoschel@gmail.com Link: https://lore.kernel.org/r/20220331220349.885126-1-jakobkoschel@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/block/drbd/drbd_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 65b95aef8dbc..3cdbd81f983f 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -184,7 +184,7 @@ void tl_release(struct drbd_connection *connection, unsigned int barrier_nr, unsigned int set_size) { struct drbd_request *r; - struct drbd_request *req = NULL; + struct drbd_request *req = NULL, *tmp = NULL; int expect_epoch = 0; int expect_size = 0;

@@ -238,8 +238,11 @@ void tl_release(struct drbd_connection *connection, unsigned int barrier_nr, * to catch requests being barrier-acked "unexpectedly". * It usually should find the same req again, or some READ preceding it. */ list_for_each_entry(req, &connection->transfer_log, tl_requests) - if (req->epoch == expect_epoch) + if (req->epoch == expect_epoch) { + tmp = req; break; + } + req = list_prepare_entry(tmp, &connection->transfer_log, tl_requests); list_for_each_entry_safe_from(req, r, &connection->transfer_log, tl_requests) { if (req->epoch != expect_epoch) break;

From: Ryusuke Konishi konishi.ryusuke@gmail.com

stable inclusion from stable-v5.10.118 commit d626fcdabea2258be395a775bdbe09270e9bf73d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit e897be17a441fa637cd166fc3de1445131e57692 ]

Patch series "nilfs2 lockdep warning fixes".

The first two are to resolve the lockdep warning issue, and the last one is the accompanying cleanup and low priority.

Based on your comment, this series solves the issue by separating inode object as needed. Since I was worried about the impact of the object composition changes, I tested the series carefully not to cause regressions especially for delicate functions such like disk space reclamation and snapshots.

This patch (of 3):

If CONFIG_LOCKDEP is enabled, nilfs2 hits lockdep warnings at inode_to_wb() during page/folio operations for btree nodes:

WARNING: CPU: 0 PID: 6575 at include/linux/backing-dev.h:269 inode_to_wb include/linux/backing-dev.h:269 [inline] WARNING: CPU: 0 PID: 6575 at include/linux/backing-dev.h:269 folio_account_dirtied mm/page-writeback.c:2460 [inline] WARNING: CPU: 0 PID: 6575 at include/linux/backing-dev.h:269 __folio_mark_dirty+0xa7c/0xe30 mm/page-writeback.c:2509 Modules linked in: ... RIP: 0010:inode_to_wb include/linux/backing-dev.h:269 [inline] RIP: 0010:folio_account_dirtied mm/page-writeback.c:2460 [inline] RIP: 0010:__folio_mark_dirty+0xa7c/0xe30 mm/page-writeback.c:2509 ... Call Trace: __set_page_dirty include/linux/pagemap.h:834 [inline] mark_buffer_dirty+0x4e6/0x650 fs/buffer.c:1145 nilfs_btree_propagate_p fs/nilfs2/btree.c:1889 [inline] nilfs_btree_propagate+0x4ae/0xea0 fs/nilfs2/btree.c:2085 nilfs_bmap_propagate+0x73/0x170 fs/nilfs2/bmap.c:337 nilfs_collect_dat_data+0x45/0xd0 fs/nilfs2/segment.c:625 nilfs_segctor_apply_buffers+0x14a/0x470 fs/nilfs2/segment.c:1009 nilfs_segctor_scan_file+0x47a/0x700 fs/nilfs2/segment.c:1048 nilfs_segctor_collect_blocks fs/nilfs2/segment.c:1224 [inline] nilfs_segctor_collect fs/nilfs2/segment.c:1494 [inline] nilfs_segctor_do_construct+0x14f3/0x6c60 fs/nilfs2/segment.c:2036 nilfs_segctor_construct+0x7a7/0xb30 fs/nilfs2/segment.c:2372 nilfs_segctor_thread_construct fs/nilfs2/segment.c:2480 [inline] nilfs_segctor_thread+0x3c3/0xf90 fs/nilfs2/segment.c:2563 kthread+0x405/0x4f0 kernel/kthread.c:327 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295

This is because nilfs2 uses two page caches for each inode and inode->i_mapping never points to one of them, the btree node cache.

This causes inode_to_wb(inode) to refer to a different page cache than the caller page/folio operations such like __folio_start_writeback(), __folio_end_writeback(), or __folio_mark_dirty() acquired the lock.

This patch resolves the issue by allocating and using an additional inode to hold the page cache of btree nodes. The inode is attached one-to-one to the traditional nilfs2 inode if it requires a block mapping with b-tree. This setup change is in memory only and does not affect the disk format.

Link: https://lkml.kernel.org/r/1647867427-30498-1-git-send-email-konishi.ryusuke@... Link: https://lkml.kernel.org/r/1647867427-30498-2-git-send-email-konishi.ryusuke@... Link: https://lore.kernel.org/r/YXrYvIo8YRnAOJCj@casper.infradead.org Link: https://lore.kernel.org/r/9a20b33d-b38f-b4a2-4742-c1eb5b8e4d6c@redhat.com Signed-off-by: Ryusuke Konishi konishi.ryusuke@gmail.com Reported-by: syzbot+0d5b462a6f07447991b3@syzkaller.appspotmail.com Reported-by: syzbot+34ef28bb2aeb28724aa0@syzkaller.appspotmail.com Reported-by: Hao Sun sunhao.th@gmail.com Reported-by: David Hildenbrand david@redhat.com Tested-by: Ryusuke Konishi konishi.ryusuke@gmail.com Cc: Matthew Wilcox willy@infradead.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- fs/nilfs2/btnode.c | 23 ++++++++-- fs/nilfs2/btnode.h | 1 + fs/nilfs2/btree.c | 27 ++++++++---- fs/nilfs2/gcinode.c | 7 +-- fs/nilfs2/inode.c | 104 ++++++++++++++++++++++++++++++++++++++------ fs/nilfs2/mdt.c | 7 +-- fs/nilfs2/nilfs.h | 14 +++--- fs/nilfs2/page.c | 7 ++- fs/nilfs2/segment.c | 9 ++-- fs/nilfs2/super.c | 5 +-- 10 files changed, 154 insertions(+), 50 deletions(-)

diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 4391fd3abd8f..e00e184b1261 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -20,6 +20,23 @@ #include "page.h" #include "btnode.h"

+ +/** + * nilfs_init_btnc_inode - initialize B-tree node cache inode + * @btnc_inode: inode to be initialized + * + * nilfs_init_btnc_inode() sets up an inode for B-tree node cache. + */ +void nilfs_init_btnc_inode(struct inode *btnc_inode) +{ + struct nilfs_inode_info *ii = NILFS_I(btnc_inode); + + btnc_inode->i_mode = S_IFREG; + ii->i_flags = 0; + memset(&ii->i_bmap_data, 0, sizeof(struct nilfs_bmap)); + mapping_set_gfp_mask(btnc_inode->i_mapping, GFP_NOFS); +} + void nilfs_btnode_cache_clear(struct address_space *btnc) { invalidate_mapping_pages(btnc, 0, -1); @@ -29,7 +46,7 @@ void nilfs_btnode_cache_clear(struct address_space *btnc) struct buffer_head * nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) { - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; struct buffer_head *bh;

bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node)); @@ -57,7 +74,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr, struct buffer_head **pbh, sector_t *submit_ptr) { struct buffer_head *bh; - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; struct page *page; int err;

@@ -157,7 +174,7 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, struct nilfs_btnode_chkey_ctxt *ctxt) { struct buffer_head *obh, *nbh; - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; __u64 oldkey = ctxt->oldkey, newkey = ctxt->newkey; int err;

diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h index 0f88dbc9bcb3..05ab64d354dc 100644 --- a/fs/nilfs2/btnode.h +++ b/fs/nilfs2/btnode.h @@ -30,6 +30,7 @@ struct nilfs_btnode_chkey_ctxt { struct buffer_head *newbh; };

+void nilfs_init_btnc_inode(struct inode *btnc_inode); void nilfs_btnode_cache_clear(struct address_space *); struct buffer_head *nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr); diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index f42ab57201e7..77efd69213a3 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -58,7 +58,8 @@ static void nilfs_btree_free_path(struct nilfs_btree_path *path) static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp) { - struct address_space *btnc = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh;

bh = nilfs_btnode_create_block(btnc, ptr); @@ -470,7 +471,8 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp, const struct nilfs_btree_readahead_info *ra) { - struct address_space *btnc = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh, *ra_bh; sector_t submit_ptr = 0; int ret; @@ -1742,6 +1744,10 @@ nilfs_btree_prepare_convert_and_insert(struct nilfs_bmap *btree, __u64 key, dat = nilfs_bmap_get_dat(btree); }

+ ret = nilfs_attach_btree_node_cache(&NILFS_BMAP_I(btree)->vfs_inode); + if (ret < 0) + return ret; + ret = nilfs_bmap_prepare_alloc_ptr(btree, dreq, dat); if (ret < 0) return ret; @@ -1914,7 +1920,7 @@ static int nilfs_btree_prepare_update_v(struct nilfs_bmap *btree, path[level].bp_ctxt.newkey = path[level].bp_newreq.bpr_ptr; path[level].bp_ctxt.bh = path[level].bp_bh; ret = nilfs_btnode_prepare_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) { nilfs_dat_abort_update(dat, @@ -1940,7 +1946,7 @@ static void nilfs_btree_commit_update_v(struct nilfs_bmap *btree,

if (buffer_nilfs_node(path[level].bp_bh)) { nilfs_btnode_commit_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); path[level].bp_bh = path[level].bp_ctxt.bh; } @@ -1959,7 +1965,7 @@ static void nilfs_btree_abort_update_v(struct nilfs_bmap *btree, &path[level].bp_newreq.bpr_req); if (buffer_nilfs_node(path[level].bp_bh)) nilfs_btnode_abort_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); }

@@ -2135,7 +2141,8 @@ static void nilfs_btree_add_dirty_buffer(struct nilfs_bmap *btree, static void nilfs_btree_lookup_dirty_buffers(struct nilfs_bmap *btree, struct list_head *listp) { - struct address_space *btcache = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btcache = btnc_inode->i_mapping; struct list_head lists[NILFS_BTREE_LEVEL_MAX]; struct pagevec pvec; struct buffer_head *bh, *head; @@ -2189,12 +2196,12 @@ static int nilfs_btree_assign_p(struct nilfs_bmap *btree, path[level].bp_ctxt.newkey = blocknr; path[level].bp_ctxt.bh = *bh; ret = nilfs_btnode_prepare_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) return ret; nilfs_btnode_commit_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); *bh = path[level].bp_ctxt.bh; } @@ -2399,6 +2406,10 @@ int nilfs_btree_init(struct nilfs_bmap *bmap)

if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap), bmap->b_inode)) ret = -EIO; + else + ret = nilfs_attach_btree_node_cache( + &NILFS_BMAP_I(bmap)->vfs_inode); + return ret; }

diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 448320496856..aadea660c66c 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -126,9 +126,10 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, int nilfs_gccache_submit_read_node(struct inode *inode, sector_t pbn, __u64 vbn, struct buffer_head **out_bh) { + struct inode *btnc_inode = NILFS_I(inode)->i_assoc_inode; int ret;

- ret = nilfs_btnode_submit_block(&NILFS_I(inode)->i_btnode_cache, + ret = nilfs_btnode_submit_block(btnc_inode->i_mapping, vbn ? : pbn, pbn, REQ_OP_READ, 0, out_bh, &pbn); if (ret == -EEXIST) /* internal code (cache hit) */ @@ -170,7 +171,7 @@ int nilfs_init_gcinode(struct inode *inode) ii->i_flags = 0; nilfs_bmap_init_gc(ii->i_bmap);

- return 0; + return nilfs_attach_btree_node_cache(inode); }

/** @@ -185,7 +186,7 @@ void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs) ii = list_first_entry(head, struct nilfs_inode_info, i_dirty); list_del_init(&ii->i_dirty); truncate_inode_pages(&ii->vfs_inode.i_data, 0); - nilfs_btnode_cache_clear(&ii->i_btnode_cache); + nilfs_btnode_cache_clear(ii->i_assoc_inode->i_mapping); iput(&ii->vfs_inode); } } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 745d371d6fea..c3e4e677c679 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -29,12 +29,14 @@ * @cno: checkpoint number * @root: pointer on NILFS root object (mounted checkpoint) * @for_gc: inode for GC flag + * @for_btnc: inode for B-tree node cache flag */ struct nilfs_iget_args { u64 ino; __u64 cno; struct nilfs_root *root; - int for_gc; + bool for_gc; + bool for_btnc; };

static int nilfs_iget_test(struct inode *inode, void *opaque); @@ -314,7 +316,8 @@ static int nilfs_insert_inode_locked(struct inode *inode, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false };

return insert_inode_locked4(inode, ino, nilfs_iget_test, &args); @@ -527,6 +530,13 @@ static int nilfs_iget_test(struct inode *inode, void *opaque) return 0;

ii = NILFS_I(inode); + if (test_bit(NILFS_I_BTNC, &ii->i_state)) { + if (!args->for_btnc) + return 0; + } else if (args->for_btnc) { + return 0; + } + if (!test_bit(NILFS_I_GCINODE, &ii->i_state)) return !args->for_gc;

@@ -538,15 +548,15 @@ static int nilfs_iget_set(struct inode *inode, void *opaque) struct nilfs_iget_args *args = opaque;

inode->i_ino = args->ino; - if (args->for_gc) { + NILFS_I(inode)->i_cno = args->cno; + NILFS_I(inode)->i_root = args->root; + if (args->root && args->ino == NILFS_ROOT_INO) + nilfs_get_root(args->root); + + if (args->for_gc) NILFS_I(inode)->i_state = BIT(NILFS_I_GCINODE); - NILFS_I(inode)->i_cno = args->cno; - NILFS_I(inode)->i_root = NULL; - } else { - if (args->root && args->ino == NILFS_ROOT_INO) - nilfs_get_root(args->root); - NILFS_I(inode)->i_root = args->root; - } + if (args->for_btnc) + NILFS_I(inode)->i_state |= BIT(NILFS_I_BTNC); return 0; }

@@ -554,7 +564,8 @@ struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false };

return ilookup5(sb, ino, nilfs_iget_test, &args); @@ -564,7 +575,8 @@ struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false };

return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args); @@ -595,7 +607,8 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, __u64 cno) { struct nilfs_iget_args args = { - .ino = ino, .root = NULL, .cno = cno, .for_gc = 1 + .ino = ino, .root = NULL, .cno = cno, .for_gc = true, + .for_btnc = false }; struct inode *inode; int err; @@ -615,6 +628,68 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, return inode; }

+/** + * nilfs_attach_btree_node_cache - attach a B-tree node cache to the inode + * @inode: inode object + * + * nilfs_attach_btree_node_cache() attaches a B-tree node cache to @inode, + * or does nothing if the inode already has it. This function allocates + * an additional inode to maintain page cache of B-tree nodes one-on-one. + * + * Return Value: On success, 0 is returned. On errors, one of the following + * negative error code is returned. + * + * %-ENOMEM - Insufficient memory available. + */ +int nilfs_attach_btree_node_cache(struct inode *inode) +{ + struct nilfs_inode_info *ii = NILFS_I(inode); + struct inode *btnc_inode; + struct nilfs_iget_args args; + + if (ii->i_assoc_inode) + return 0; + + args.ino = inode->i_ino; + args.root = ii->i_root; + args.cno = ii->i_cno; + args.for_gc = test_bit(NILFS_I_GCINODE, &ii->i_state) != 0; + args.for_btnc = true; + + btnc_inode = iget5_locked(inode->i_sb, inode->i_ino, nilfs_iget_test, + nilfs_iget_set, &args); + if (unlikely(!btnc_inode)) + return -ENOMEM; + if (btnc_inode->i_state & I_NEW) { + nilfs_init_btnc_inode(btnc_inode); + unlock_new_inode(btnc_inode); + } + NILFS_I(btnc_inode)->i_assoc_inode = inode; + NILFS_I(btnc_inode)->i_bmap = ii->i_bmap; + ii->i_assoc_inode = btnc_inode; + + return 0; +} + +/** + * nilfs_detach_btree_node_cache - detach the B-tree node cache from the inode + * @inode: inode object + * + * nilfs_detach_btree_node_cache() detaches the B-tree node cache and its + * holder inode bound to @inode, or does nothing if @inode doesn't have it. + */ +void nilfs_detach_btree_node_cache(struct inode *inode) +{ + struct nilfs_inode_info *ii = NILFS_I(inode); + struct inode *btnc_inode = ii->i_assoc_inode; + + if (btnc_inode) { + NILFS_I(btnc_inode)->i_assoc_inode = NULL; + ii->i_assoc_inode = NULL; + iput(btnc_inode); + } +} + void nilfs_write_inode_common(struct inode *inode, struct nilfs_inode *raw_inode, int has_bmap) { @@ -762,7 +837,8 @@ static void nilfs_clear_inode(struct inode *inode) if (test_bit(NILFS_I_BMAP, &ii->i_state)) nilfs_bmap_clear(ii->i_bmap);

- nilfs_btnode_cache_clear(&ii->i_btnode_cache); + if (!test_bit(NILFS_I_BTNC, &ii->i_state)) + nilfs_detach_btree_node_cache(inode);

if (ii->i_root && inode->i_ino == NILFS_ROOT_INO) nilfs_put_root(ii->i_root); diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index c0361ce45f62..d3f6cb9c32a0 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -531,7 +531,7 @@ int nilfs_mdt_save_to_shadow_map(struct inode *inode) goto out;

ret = nilfs_copy_dirty_pages(&shadow->frozen_btnodes, - &ii->i_btnode_cache); + ii->i_assoc_inode->i_mapping); if (ret) goto out;

@@ -622,8 +622,9 @@ void nilfs_mdt_restore_from_shadow_map(struct inode *inode) nilfs_clear_dirty_pages(inode->i_mapping, true); nilfs_copy_back_pages(inode->i_mapping, &shadow->frozen_data);

- nilfs_clear_dirty_pages(&ii->i_btnode_cache, true); - nilfs_copy_back_pages(&ii->i_btnode_cache, &shadow->frozen_btnodes); + nilfs_clear_dirty_pages(ii->i_assoc_inode->i_mapping, true); + nilfs_copy_back_pages(ii->i_assoc_inode->i_mapping, + &shadow->frozen_btnodes);

nilfs_bmap_restore(ii->i_bmap, &shadow->bmap_store);

diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index f8450ee3fd06..635383b30d67 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -28,7 +28,7 @@ * @i_xattr: <TODO> * @i_dir_start_lookup: page index of last successful search * @i_cno: checkpoint number for GC inode - * @i_btnode_cache: cached pages of b-tree nodes + * @i_assoc_inode: associated inode (B-tree node cache holder or back pointer) * @i_dirty: list for connecting dirty files * @xattr_sem: semaphore for extended attributes processing * @i_bh: buffer contains disk inode @@ -43,7 +43,7 @@ struct nilfs_inode_info { __u64 i_xattr; /* sector_t ??? */ __u32 i_dir_start_lookup; __u64 i_cno; /* check point number for GC inode */ - struct address_space i_btnode_cache; + struct inode *i_assoc_inode; struct list_head i_dirty; /* List for connecting dirty files */

#ifdef CONFIG_NILFS_XATTR @@ -75,13 +75,6 @@ NILFS_BMAP_I(const struct nilfs_bmap *bmap) return container_of(bmap, struct nilfs_inode_info, i_bmap_data); }

-static inline struct inode *NILFS_BTNC_I(struct address_space *btnc) -{ - struct nilfs_inode_info *ii = - container_of(btnc, struct nilfs_inode_info, i_btnode_cache); - return &ii->vfs_inode; -} - /* * Dynamic state flags of NILFS on-memory inode (i_state) */ @@ -98,6 +91,7 @@ enum { NILFS_I_INODE_SYNC, /* dsync is not allowed for inode */ NILFS_I_BMAP, /* has bmap and btnode_cache */ NILFS_I_GCINODE, /* inode for GC, on memory only */ + NILFS_I_BTNC, /* inode for btree node cache */ };

/* @@ -264,6 +258,8 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root, unsigned long ino); extern struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, __u64 cno); +int nilfs_attach_btree_node_cache(struct inode *inode); +void nilfs_detach_btree_node_cache(struct inode *inode); extern void nilfs_update_inode(struct inode *, struct buffer_head *, int); extern void nilfs_truncate(struct inode *); extern void nilfs_evict_inode(struct inode *); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 171fb5cd427f..d1a148f0cae3 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -448,10 +448,9 @@ void nilfs_mapping_init(struct address_space *mapping, struct inode *inode) /* * NILFS2 needs clear_page_dirty() in the following two cases: * - * 1) For B-tree node pages and data pages of the dat/gcdat, NILFS2 clears - * page dirty flags when it copies back pages from the shadow cache - * (gcdat->{i_mapping,i_btnode_cache}) to its original cache - * (dat->{i_mapping,i_btnode_cache}). + * 1) For B-tree node pages and data pages of DAT file, NILFS2 clears dirty + * flag of pages when it copies back pages from shadow cache to the + * original cache. * * 2) Some B-tree operations like insertion or deletion may dispose buffers * in dirty state, and this needs to cancel the dirty state of their pages. diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index e3726aca28ed..8350c2eaee75 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -738,15 +738,18 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode, struct list_head *listp) { struct nilfs_inode_info *ii = NILFS_I(inode); - struct address_space *mapping = &ii->i_btnode_cache; + struct inode *btnc_inode = ii->i_assoc_inode; struct pagevec pvec; struct buffer_head *bh, *head; unsigned int i; pgoff_t index = 0;

+ if (!btnc_inode) + return; + pagevec_init(&pvec);

- while (pagevec_lookup_tag(&pvec, mapping, &index, + while (pagevec_lookup_tag(&pvec, btnc_inode->i_mapping, &index, PAGECACHE_TAG_DIRTY)) { for (i = 0; i < pagevec_count(&pvec); i++) { bh = head = page_buffers(pvec.pages[i]); @@ -2415,7 +2418,7 @@ nilfs_remove_written_gcinodes(struct the_nilfs *nilfs, struct list_head *head) continue; list_del_init(&ii->i_dirty); truncate_inode_pages(&ii->vfs_inode.i_data, 0); - nilfs_btnode_cache_clear(&ii->i_btnode_cache); + nilfs_btnode_cache_clear(ii->i_assoc_inode->i_mapping); iput(&ii->vfs_inode); } } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 4abd928b0bc8..b9d30e8c43b0 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -157,7 +157,8 @@ struct inode *nilfs_alloc_inode(struct super_block *sb) ii->i_bh = NULL; ii->i_state = 0; ii->i_cno = 0; - nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode); + ii->i_assoc_inode = NULL; + ii->i_bmap = &ii->i_bmap_data; return &ii->vfs_inode; }

@@ -1377,8 +1378,6 @@ static void nilfs_inode_init_once(void *obj) #ifdef CONFIG_NILFS_XATTR init_rwsem(&ii->xattr_sem); #endif - address_space_init_once(&ii->i_btnode_cache); - ii->i_bmap = &ii->i_bmap_data; inode_init_once(&ii->vfs_inode); }

From: Takashi Iwai tiwai@suse.de

stable inclusion from stable-v5.10.118 commit a34d018b6eaba7ffcbafd0f68e66df6003321995 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 5c62383c06837b5719cd5447a5758b791279e653 upstream.

At cleaning up and moving the device rename from the quirk table to its own table, we removed the entry for Rane SL-1 as we thought it's only for renaming. It turned out, however, that the quirk is required for matching with the device that declares itself as no standard audio but only as vendor-specific.

Restore the quirk entry for Rane SL-1 to fix the regression.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=215887 Fixes: 5436f59bc5bc ("ALSA: usb-audio: Move device rename and profile quirks to an internal table") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220516103112.12950-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- sound/usb/quirks-table.h | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index aabd3a10ec5b..1ac91c46da3c 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3208,6 +3208,15 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), } },

+/* Rane SL-1 */ +{ + USB_DEVICE(0x13e5, 0x0001), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + } +}, + /* disabled due to regression for other devices; * see https://bugzilla.kernel.org/show_bug.cgi?id=199905 */

From: Werner Sembach wse@tuxedocomputers.com

stable inclusion from stable-v5.10.118 commit 18fb7d533c79909675749f1795dc312246143c6d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 8b3b2392ed68bcd17c7eb84ca615ce1e5f115b99 upstream.

When audio stops playing there is an audible "pop"-noise when using headphones on the TongFang GMxMRxx, GKxNRxx, GMxZGxx, GMxTGxx and GMxAGxx.

This quirk fixes this mostly.

Signed-off-by: Werner Sembach wse@tuxedocomputers.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220512180956.281804-1-wse@tuxedocomputers.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- sound/pci/hda/patch_realtek.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 3f880c4fd5e0..f630f9257ad1 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9011,6 +9011,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802), SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X), SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_SET_COEF_DEFAULTS), + SND_PCI_QUIRK(0x1d05, 0x1096, "TongFang GMxMRxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1100, "TongFang GKxNRxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1111, "TongFang GMxZGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1119, "TongFang GMxZGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1129, "TongFang GMxZGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1147, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),

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

stable inclusion from stable-v5.10.118 commit ec0d801d1a44d9259377142c6218885ecd685e41 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit fb4554c2232e44d595920f4d5c66cf8f7d13f9bc upstream.

Descriptor table is a shared resource; two fget() on the same descriptor may return different struct file references. get_tap_ptr_ring() is called after we'd found (and pinned) the socket we'll be using and it tries to find the private tun/tap data structures associated with it. Redoing the lookup by the same file descriptor we'd used to get the socket is racy - we need to same struct file.

Thanks to Jason for spotting a braino in the original variant of patch - I'd missed the use of fd == -1 for disabling backend, and in that case we can end up with sock == NULL and sock != oldsock.

Cc: stable@kernel.org Acked-by: Michael S. Tsirkin mst@redhat.com Signed-off-by: Jason Wang jasowang@redhat.com Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/vhost/net.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index eba91da505e0..a6a1a01319d8 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1450,13 +1450,9 @@ static struct socket *get_raw_socket(int fd) return ERR_PTR(r); }

-static struct ptr_ring *get_tap_ptr_ring(int fd) +static struct ptr_ring *get_tap_ptr_ring(struct file *file) { struct ptr_ring *ring; - struct file *file = fget(fd); - - if (!file) - return NULL; ring = tun_get_tx_ring(file); if (!IS_ERR(ring)) goto out; @@ -1465,7 +1461,6 @@ static struct ptr_ring *get_tap_ptr_ring(int fd) goto out; ring = NULL; out: - fput(file); return ring; }

@@ -1552,8 +1547,12 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) r = vhost_net_enable_vq(n, vq); if (r) goto err_used; - if (index == VHOST_NET_VQ_RX) - nvq->rx_ring = get_tap_ptr_ring(fd); + if (index == VHOST_NET_VQ_RX) { + if (sock) + nvq->rx_ring = get_tap_ptr_ring(sock->file); + else + nvq->rx_ring = NULL; + }

oldubufs = nvq->ubufs; nvq->ubufs = ubufs;

From: Sean Christopherson seanjc@google.com

stable inclusion from stable-v5.10.118 commit b49bc8d615eea1043cb238318af04f8876e846b3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit b28cb0cd2c5e80a8c0feb408a0e4b0dbb6d132c5 upstream.

When zapping obsolete pages, update the running count of zapped pages regardless of whether or not the list has become unstable due to zapping a shadow page with its own child shadow pages. If the VM is backed by mostly 4kb pages, KVM can zap an absurd number of SPTEs without bumping the batch count and thus without yielding. In the worst case scenario, this can cause a soft lokcup.

watchdog: BUG: soft lockup - CPU#12 stuck for 22s! [dirty_log_perf_:13020] RIP: 0010:workingset_activation+0x19/0x130 mark_page_accessed+0x266/0x2e0 kvm_set_pfn_accessed+0x31/0x40 mmu_spte_clear_track_bits+0x136/0x1c0 drop_spte+0x1a/0xc0 mmu_page_zap_pte+0xef/0x120 __kvm_mmu_prepare_zap_page+0x205/0x5e0 kvm_mmu_zap_all_fast+0xd7/0x190 kvm_mmu_invalidate_zap_pages_in_memslot+0xe/0x10 kvm_page_track_flush_slot+0x5c/0x80 kvm_arch_flush_shadow_memslot+0xe/0x10 kvm_set_memslot+0x1a8/0x5d0 __kvm_set_memory_region+0x337/0x590 kvm_vm_ioctl+0xb08/0x1040

Fixes: fbb158cb88b6 ("KVM: x86/mmu: Revert "Revert "KVM: MMU: zap pages in batch""") Reported-by: David Matlack dmatlack@google.com Reviewed-by: Ben Gardon bgardon@google.com Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20220511145122.3133334-1-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- arch/x86/kvm/mmu/mmu.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index bcf1bd9424f2..6096d0f1a62a 100755 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5377,6 +5377,7 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; int nr_zapped, batch = 0; + bool unstable;

restart: list_for_each_entry_safe_reverse(sp, node, @@ -5408,11 +5409,12 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm) goto restart; }

- if (__kvm_mmu_prepare_zap_page(kvm, sp, - &kvm->arch.zapped_obsolete_pages, &nr_zapped)) { - batch += nr_zapped; + unstable = __kvm_mmu_prepare_zap_page(kvm, sp, + &kvm->arch.zapped_obsolete_pages, &nr_zapped); + batch += nr_zapped; + + if (unstable) goto restart; - } }

/*

From: Catalin Marinas catalin.marinas@arm.com

stable inclusion from stable-v5.10.118 commit 6013ef5f51e0861a904b74a694e621bb451fe7ae category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 1d0cb4c8864addc362bae98e8ffa5500c87e1227 upstream.

As an optimisation, only pages mapped with PROT_MTE in user space have the MTE tags zeroed. This is done lazily at the set_pte_at() time via mte_sync_tags(). However, this function is missing a barrier and another CPU may see the PTE updated before the zeroed tags are visible. Add an smp_wmb() barrier if the mapping is Normal Tagged.

Signed-off-by: Catalin Marinas catalin.marinas@arm.com Fixes: 34bfeea4a9e9 ("arm64: mte: Clear the tags when a page is mapped in user-space with PROT_MTE") Cc: stable@vger.kernel.org # 5.10.x Reported-by: Vladimir Murzin vladimir.murzin@arm.com Cc: Will Deacon will@kernel.org Reviewed-by: Steven Price steven.price@arm.com Tested-by: Vladimir Murzin vladimir.murzin@arm.com Link: https://lore.kernel.org/r/20220517093532.127095-1-catalin.marinas@arm.com Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- arch/arm64/kernel/mte.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 7a66a7d9c1ff..4a069f85bd91 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -45,6 +45,9 @@ void mte_sync_tags(pte_t *ptep, pte_t pte) if (!test_and_set_bit(PG_mte_tagged, &page->flags)) mte_sync_page_tags(page, ptep, check_swap); } + + /* ensure the tags are visible before the PTE is set */ + smp_wmb(); }

int memcmp_pages(struct page *page1, struct page *page2)

From: Ilya Dryomov idryomov@gmail.com

stable inclusion from stable-v5.10.118 commit 8ceca1a0693a314712e7b1b727795b7be55f32e9 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 75dbb685f4e8786c33ddef8279bab0eadfb0731f upstream.

request_reinit() is not only ugly as the comment rightfully suggests, but also unsafe. Even though it is called with osdc->lock held for write in all cases, resetting the OSD request refcount can still race with handle_reply() and result in use-after-free. Taking linger ping as an example:

handle_timeout thread handle_reply thread

down_read(&osdc->lock) req = lookup_request(...) ... finish_request(req) # unregisters up_read(&osdc->lock) __complete_request(req) linger_ping_cb(req)

# req->r_kref == 2 because handle_reply still holds its ref

down_write(&osdc->lock) send_linger_ping(lreq) req = lreq->ping_req # same req # cancel_linger_request is NOT # called - handle_reply already # unregistered request_reinit(req) WARN_ON(req->r_kref != 1) # fires request_init(req) kref_init(req->r_kref)

# req->r_kref == 1 after kref_init

ceph_osdc_put_request(req) kref_put(req->r_kref)

# req->r_kref == 0 after kref_put, req is freed

<further req initialization/use> !!!

This happens because send_linger_ping() always (re)uses the same OSD request for watch ping requests, relying on cancel_linger_request() to unregister it from the OSD client and rip its messages out from the messenger. send_linger() does the same for watch/notify registration and watch reconnect requests. Unfortunately cancel_request() doesn't guarantee that after it returns the OSD client would be completely done with the OSD request -- a ref could still be held and the callback (if specified) could still be invoked too.

The original motivation for request_reinit() was inability to deal with allocation failures in send_linger() and send_linger_ping(). Switching to using osdc->req_mempool (currently only used by CephFS) respects that and allows us to get rid of request_reinit().

Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov idryomov@gmail.com Reviewed-by: Xiubo Li xiubli@redhat.com Acked-by: Jeff Layton jlayton@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- include/linux/ceph/osd_client.h | 3 + net/ceph/osd_client.c | 302 +++++++++++++------------------- 2 files changed, 122 insertions(+), 183 deletions(-)

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 83fa08a06507..787fff5ec7f5 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -287,6 +287,9 @@ struct ceph_osd_linger_request { rados_watcherrcb_t errcb; void *data;

+ struct ceph_pagelist *request_pl; + struct page **notify_id_pages; + struct page ***preply_pages; size_t *preply_len; }; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 7901ab6c79fd..1e9fab79e245 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -537,43 +537,6 @@ static void request_init(struct ceph_osd_request *req) target_init(&req->r_t); }

-/* - * This is ugly, but it allows us to reuse linger registration and ping - * requests, keeping the structure of the code around send_linger{_ping}() - * reasonable. Setting up a min_nr=2 mempool for each linger request - * and dealing with copying ops (this blasts req only, watch op remains - * intact) isn't any better. - */ -static void request_reinit(struct ceph_osd_request *req) -{ - struct ceph_osd_client *osdc = req->r_osdc; - bool mempool = req->r_mempool; - unsigned int num_ops = req->r_num_ops; - u64 snapid = req->r_snapid; - struct ceph_snap_context *snapc = req->r_snapc; - bool linger = req->r_linger; - struct ceph_msg *request_msg = req->r_request; - struct ceph_msg *reply_msg = req->r_reply; - - dout("%s req %p\n", __func__, req); - WARN_ON(kref_read(&req->r_kref) != 1); - request_release_checks(req); - - WARN_ON(kref_read(&request_msg->kref) != 1); - WARN_ON(kref_read(&reply_msg->kref) != 1); - target_destroy(&req->r_t); - - request_init(req); - req->r_osdc = osdc; - req->r_mempool = mempool; - req->r_num_ops = num_ops; - req->r_snapid = snapid; - req->r_snapc = snapc; - req->r_linger = linger; - req->r_request = request_msg; - req->r_reply = reply_msg; -} - struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, unsigned int num_ops, @@ -918,14 +881,30 @@ EXPORT_SYMBOL(osd_req_op_xattr_init); * @watch_opcode: CEPH_OSD_WATCH_OP_* */ static void osd_req_op_watch_init(struct ceph_osd_request *req, int which, - u64 cookie, u8 watch_opcode) + u8 watch_opcode, u64 cookie, u32 gen) { struct ceph_osd_req_op *op;

op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0); op->watch.cookie = cookie; op->watch.op = watch_opcode; - op->watch.gen = 0; + op->watch.gen = gen; +} + +/* + * prot_ver, timeout and notify payload (may be empty) should already be + * encoded in @request_pl + */ +static void osd_req_op_notify_init(struct ceph_osd_request *req, int which, + u64 cookie, struct ceph_pagelist *request_pl) +{ + struct ceph_osd_req_op *op; + + op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); + op->notify.cookie = cookie; + + ceph_osd_data_pagelist_init(&op->notify.request_data, request_pl); + op->indata_len = request_pl->length; }

/* @@ -2727,10 +2706,13 @@ static void linger_release(struct kref *kref) WARN_ON(!list_empty(&lreq->pending_lworks)); WARN_ON(lreq->osd);

- if (lreq->reg_req) - ceph_osdc_put_request(lreq->reg_req); - if (lreq->ping_req) - ceph_osdc_put_request(lreq->ping_req); + if (lreq->request_pl) + ceph_pagelist_release(lreq->request_pl); + if (lreq->notify_id_pages) + ceph_release_page_vector(lreq->notify_id_pages, 1); + + ceph_osdc_put_request(lreq->reg_req); + ceph_osdc_put_request(lreq->ping_req); target_destroy(&lreq->t); kfree(lreq); } @@ -2999,6 +2981,12 @@ static void linger_commit_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv;

mutex_lock(&lreq->lock); + if (req != lreq->reg_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->reg_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq, lreq->linger_id, req->r_result); linger_reg_commit_complete(lreq, req->r_result); @@ -3022,6 +3010,7 @@ static void linger_commit_cb(struct ceph_osd_request *req) } }

+out: mutex_unlock(&lreq->lock); linger_put(lreq); } @@ -3044,6 +3033,12 @@ static void linger_reconnect_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv;

mutex_lock(&lreq->lock); + if (req != lreq->reg_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->reg_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->last_error); if (req->r_result < 0) { @@ -3053,46 +3048,64 @@ static void linger_reconnect_cb(struct ceph_osd_request *req) } }

+out: mutex_unlock(&lreq->lock); linger_put(lreq); }

static void send_linger(struct ceph_osd_linger_request *lreq) { - struct ceph_osd_request *req = lreq->reg_req; - struct ceph_osd_req_op *op = &req->r_ops[0]; + struct ceph_osd_client *osdc = lreq->osdc; + struct ceph_osd_request *req; + int ret;

- verify_osdc_wrlocked(req->r_osdc); + verify_osdc_wrlocked(osdc); + mutex_lock(&lreq->lock); dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);

- if (req->r_osd) - cancel_linger_request(req); + if (lreq->reg_req) { + if (lreq->reg_req->r_osd) + cancel_linger_request(lreq->reg_req); + ceph_osdc_put_request(lreq->reg_req); + } + + req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); + BUG_ON(!req);

- request_reinit(req); target_copy(&req->r_t, &lreq->t); req->r_mtime = lreq->mtime;

- mutex_lock(&lreq->lock); if (lreq->is_watch && lreq->committed) { - WARN_ON(op->op != CEPH_OSD_OP_WATCH || - op->watch.cookie != lreq->linger_id); - op->watch.op = CEPH_OSD_WATCH_OP_RECONNECT; - op->watch.gen = ++lreq->register_gen; + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_RECONNECT, + lreq->linger_id, ++lreq->register_gen); dout("lreq %p reconnect register_gen %u\n", lreq, - op->watch.gen); + req->r_ops[0].watch.gen); req->r_callback = linger_reconnect_cb; } else { - if (!lreq->is_watch) + if (lreq->is_watch) { + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_WATCH, + lreq->linger_id, 0); + } else { lreq->notify_id = 0; - else - WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH); + + refcount_inc(&lreq->request_pl->refcnt); + osd_req_op_notify_init(req, 0, lreq->linger_id, + lreq->request_pl); + ceph_osd_data_pages_init( + osd_req_op_data(req, 0, notify, response_data), + lreq->notify_id_pages, PAGE_SIZE, 0, false, false); + } dout("lreq %p register\n", lreq); req->r_callback = linger_commit_cb; } - mutex_unlock(&lreq->lock); + + ret = ceph_osdc_alloc_messages(req, GFP_NOIO); + BUG_ON(ret);

req->r_priv = linger_get(lreq); req->r_linger = true; + lreq->reg_req = req; + mutex_unlock(&lreq->lock);

submit_request(req, true); } @@ -3102,6 +3115,12 @@ static void linger_ping_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv;

mutex_lock(&lreq->lock); + if (req != lreq->ping_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->ping_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent, lreq->last_error); @@ -3117,6 +3136,7 @@ static void linger_ping_cb(struct ceph_osd_request *req) lreq->register_gen, req->r_ops[0].watch.gen); }

+out: mutex_unlock(&lreq->lock); linger_put(lreq); } @@ -3124,8 +3144,8 @@ static void linger_ping_cb(struct ceph_osd_request *req) static void send_linger_ping(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; - struct ceph_osd_request *req = lreq->ping_req; - struct ceph_osd_req_op *op = &req->r_ops[0]; + struct ceph_osd_request *req; + int ret;

if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) { dout("%s PAUSERD\n", __func__); @@ -3137,19 +3157,26 @@ static void send_linger_ping(struct ceph_osd_linger_request *lreq) __func__, lreq, lreq->linger_id, lreq->ping_sent, lreq->register_gen);

- if (req->r_osd) - cancel_linger_request(req); + if (lreq->ping_req) { + if (lreq->ping_req->r_osd) + cancel_linger_request(lreq->ping_req); + ceph_osdc_put_request(lreq->ping_req); + }

- request_reinit(req); - target_copy(&req->r_t, &lreq->t); + req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); + BUG_ON(!req);

- WARN_ON(op->op != CEPH_OSD_OP_WATCH || - op->watch.cookie != lreq->linger_id || - op->watch.op != CEPH_OSD_WATCH_OP_PING); - op->watch.gen = lreq->register_gen; + target_copy(&req->r_t, &lreq->t); + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_PING, lreq->linger_id, + lreq->register_gen); req->r_callback = linger_ping_cb; + + ret = ceph_osdc_alloc_messages(req, GFP_NOIO); + BUG_ON(ret); + req->r_priv = linger_get(lreq); req->r_linger = true; + lreq->ping_req = req;

ceph_osdc_get_request(req); account_request(req); @@ -3165,12 +3192,6 @@ static void linger_submit(struct ceph_osd_linger_request *lreq)

down_write(&osdc->lock); linger_register(lreq); - if (lreq->is_watch) { - lreq->reg_req->r_ops[0].watch.cookie = lreq->linger_id; - lreq->ping_req->r_ops[0].watch.cookie = lreq->linger_id; - } else { - lreq->reg_req->r_ops[0].notify.cookie = lreq->linger_id; - }

calc_target(osdc, &lreq->t, false); osd = lookup_create_osd(osdc, lreq->t.osd, true); @@ -3202,9 +3223,9 @@ static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq) */ static void __linger_cancel(struct ceph_osd_linger_request *lreq) { - if (lreq->is_watch && lreq->ping_req->r_osd) + if (lreq->ping_req && lreq->ping_req->r_osd) cancel_linger_request(lreq->ping_req); - if (lreq->reg_req->r_osd) + if (lreq->reg_req && lreq->reg_req->r_osd) cancel_linger_request(lreq->reg_req); cancel_linger_map_check(lreq); unlink_linger(lreq->osd, lreq); @@ -4651,43 +4672,6 @@ void ceph_osdc_sync(struct ceph_osd_client *osdc) } EXPORT_SYMBOL(ceph_osdc_sync);

-static struct ceph_osd_request * -alloc_linger_request(struct ceph_osd_linger_request *lreq) -{ - struct ceph_osd_request *req; - - req = ceph_osdc_alloc_request(lreq->osdc, NULL, 1, false, GFP_NOIO); - if (!req) - return NULL; - - ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid); - ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); - return req; -} - -static struct ceph_osd_request * -alloc_watch_request(struct ceph_osd_linger_request *lreq, u8 watch_opcode) -{ - struct ceph_osd_request *req; - - req = alloc_linger_request(lreq); - if (!req) - return NULL; - - /* - * Pass 0 for cookie because we don't know it yet, it will be - * filled in by linger_submit(). - */ - osd_req_op_watch_init(req, 0, 0, watch_opcode); - - if (ceph_osdc_alloc_messages(req, GFP_NOIO)) { - ceph_osdc_put_request(req); - return NULL; - } - - return req; -} - /* * Returns a handle, caller owns a ref. */ @@ -4717,18 +4701,6 @@ ceph_osdc_watch(struct ceph_osd_client *osdc, lreq->t.flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&lreq->mtime);

- lreq->reg_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_WATCH); - if (!lreq->reg_req) { - ret = -ENOMEM; - goto err_put_lreq; - } - - lreq->ping_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_PING); - if (!lreq->ping_req) { - ret = -ENOMEM; - goto err_put_lreq; - } - linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (ret) { @@ -4766,8 +4738,8 @@ int ceph_osdc_unwatch(struct ceph_osd_client *osdc, ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); req->r_flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&req->r_mtime); - osd_req_op_watch_init(req, 0, lreq->linger_id, - CEPH_OSD_WATCH_OP_UNWATCH); + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_UNWATCH, + lreq->linger_id, 0);

ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) @@ -4853,35 +4825,6 @@ int ceph_osdc_notify_ack(struct ceph_osd_client *osdc, } EXPORT_SYMBOL(ceph_osdc_notify_ack);

-static int osd_req_op_notify_init(struct ceph_osd_request *req, int which, - u64 cookie, u32 prot_ver, u32 timeout, - void *payload, u32 payload_len) -{ - struct ceph_osd_req_op *op; - struct ceph_pagelist *pl; - int ret; - - op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); - op->notify.cookie = cookie; - - pl = ceph_pagelist_alloc(GFP_NOIO); - if (!pl) - return -ENOMEM; - - ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */ - ret |= ceph_pagelist_encode_32(pl, timeout); - ret |= ceph_pagelist_encode_32(pl, payload_len); - ret |= ceph_pagelist_append(pl, payload, payload_len); - if (ret) { - ceph_pagelist_release(pl); - return -ENOMEM; - } - - ceph_osd_data_pagelist_init(&op->notify.request_data, pl); - op->indata_len = pl->length; - return 0; -} - /* * @timeout: in seconds * @@ -4900,7 +4843,6 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, size_t *preply_len) { struct ceph_osd_linger_request *lreq; - struct page **pages; int ret;

WARN_ON(!timeout); @@ -4913,41 +4855,35 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, if (!lreq) return -ENOMEM;

- lreq->preply_pages = preply_pages; - lreq->preply_len = preply_len; - - ceph_oid_copy(&lreq->t.base_oid, oid); - ceph_oloc_copy(&lreq->t.base_oloc, oloc); - lreq->t.flags = CEPH_OSD_FLAG_READ; - - lreq->reg_req = alloc_linger_request(lreq); - if (!lreq->reg_req) { + lreq->request_pl = ceph_pagelist_alloc(GFP_NOIO); + if (!lreq->request_pl) { ret = -ENOMEM; goto out_put_lreq; }

- /* - * Pass 0 for cookie because we don't know it yet, it will be - * filled in by linger_submit(). - */ - ret = osd_req_op_notify_init(lreq->reg_req, 0, 0, 1, timeout, - payload, payload_len); - if (ret) + ret = ceph_pagelist_encode_32(lreq->request_pl, 1); /* prot_ver */ + ret |= ceph_pagelist_encode_32(lreq->request_pl, timeout); + ret |= ceph_pagelist_encode_32(lreq->request_pl, payload_len); + ret |= ceph_pagelist_append(lreq->request_pl, payload, payload_len); + if (ret) { + ret = -ENOMEM; goto out_put_lreq; + }

/* for notify_id */ - pages = ceph_alloc_page_vector(1, GFP_NOIO); - if (IS_ERR(pages)) { - ret = PTR_ERR(pages); + lreq->notify_id_pages = ceph_alloc_page_vector(1, GFP_NOIO); + if (IS_ERR(lreq->notify_id_pages)) { + ret = PTR_ERR(lreq->notify_id_pages); + lreq->notify_id_pages = NULL; goto out_put_lreq; } - ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify, - response_data), - pages, PAGE_SIZE, 0, false, true);

- ret = ceph_osdc_alloc_messages(lreq->reg_req, GFP_NOIO); - if (ret) - goto out_put_lreq; + lreq->preply_pages = preply_pages; + lreq->preply_len = preply_len; + + ceph_oid_copy(&lreq->t.base_oid, oid); + ceph_oloc_copy(&lreq->t.base_oloc, oloc); + lreq->t.flags = CEPH_OSD_FLAG_READ;

linger_submit(lreq); ret = linger_reg_commit_wait(lreq);

From: Jérôme Pouiller jerome.pouiller@silabs.com

stable inclusion from stable-v5.10.118 commit 3fc28460998a7a197ce7bc469effa78e32f34872 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 7c3e9fcad9c7d8bb5d69a576044fb16b1d2e8a01 upstream.

The typedefs u32 and u64 are not available in userspace. Thus user get an error he try to use DMA_BUF_SET_NAME_A or DMA_BUF_SET_NAME_B:

$ gcc -Wall -c -MMD -c -o ioctls_list.o ioctls_list.c In file included from /usr/include/x86_64-linux-gnu/asm/ioctl.h:1, from /usr/include/linux/ioctl.h:5, from /usr/include/asm-generic/ioctls.h:5, from ioctls_list.c:11: ioctls_list.c:463:29: error: ‘u32’ undeclared here (not in a function) 463 | { "DMA_BUF_SET_NAME_A", DMA_BUF_SET_NAME_A, -1, -1 }, // linux/dma-buf.h | ^~~~~~~~~~~~~~~~~~ ioctls_list.c:464:29: error: ‘u64’ undeclared here (not in a function) 464 | { "DMA_BUF_SET_NAME_B", DMA_BUF_SET_NAME_B, -1, -1 }, // linux/dma-buf.h | ^~~~~~~~~~~~~~~~~~

The issue was initially reported here[1].

[1]: https://github.com/jerome-pouiller/ioctl/pull/14

Signed-off-by: Jérôme Pouiller jerome.pouiller@silabs.com Reviewed-by: Christian König christian.koenig@amd.com Fixes: a5bff92eaac4 ("dma-buf: Fix SET_NAME ioctl uapi") CC: stable@vger.kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20220517072708.245265-1-Jerome... Signed-off-by: Christian König christian.koenig@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- include/uapi/linux/dma-buf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 7f30393b92c3..f76d11725c6c 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -44,7 +44,7 @@ struct dma_buf_sync { * between them in actual uapi, they're just different numbers. */ #define DMA_BUF_SET_NAME _IOW(DMA_BUF_BASE, 1, const char *) -#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, u32) -#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, u64) +#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, __u32) +#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, __u64)

#endif

From: Jae Hyun Yoo quic_jaehyoo@quicinc.com

stable inclusion from stable-v5.10.118 commit 0a2847d44812d765623d6676b40a8f0cc612e512 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 3eef2f48ba0933ba995529f522554ad5c276c39b ]

FWSPIDQ2 and FWSPIDQ3 are not part of FWSPI18 interface so remove FWQSPID group in pinctrl. These pins must be used with the FWSPI pins that are dedicated for boot SPI interface which provides same 3.3v logic level.

Fixes: 2eda1cdec49f ("pinctrl: aspeed: Add AST2600 pinmux support") Signed-off-by: Jae Hyun Yoo quic_jaehyoo@quicinc.com Reviewed-by: Andrew Jeffery andrew@aj.id.au Link: https://lore.kernel.org/r/20220329173932.2588289-3-quic_jaehyoo@quicinc.com Signed-off-by: Joel Stanley joel@jms.id.au Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index 5c1a109842a7..c2ba4064ce5b 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -1224,18 +1224,12 @@ FUNC_GROUP_DECL(SALT8, AA12); FUNC_GROUP_DECL(WDTRST4, AA12);

#define AE12 196 -SIG_EXPR_LIST_DECL_SEMG(AE12, FWSPIDQ2, FWQSPID, FWSPID, - SIG_DESC_SET(SCU438, 4)); SIG_EXPR_LIST_DECL_SESG(AE12, GPIOY4, GPIOY4); -PIN_DECL_(AE12, SIG_EXPR_LIST_PTR(AE12, FWSPIDQ2), - SIG_EXPR_LIST_PTR(AE12, GPIOY4)); +PIN_DECL_(AE12, SIG_EXPR_LIST_PTR(AE12, GPIOY4));

#define AF12 197 -SIG_EXPR_LIST_DECL_SEMG(AF12, FWSPIDQ3, FWQSPID, FWSPID, - SIG_DESC_SET(SCU438, 5)); SIG_EXPR_LIST_DECL_SESG(AF12, GPIOY5, GPIOY5); -PIN_DECL_(AF12, SIG_EXPR_LIST_PTR(AF12, FWSPIDQ3), - SIG_EXPR_LIST_PTR(AF12, GPIOY5)); +PIN_DECL_(AF12, SIG_EXPR_LIST_PTR(AF12, GPIOY5));

#define AC12 198 SSSF_PIN_DECL(AC12, GPIOY6, FWSPIABR, SIG_DESC_SET(SCU438, 6)); @@ -1508,9 +1502,8 @@ SIG_EXPR_LIST_DECL_SEMG(Y4, EMMCDAT7, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 3)); PIN_DECL_3(Y4, GPIO18E3, FWSPIDMISO, VBMISO, EMMCDAT7);

GROUP_DECL(FWSPID, Y1, Y2, Y3, Y4); -GROUP_DECL(FWQSPID, Y1, Y2, Y3, Y4, AE12, AF12); GROUP_DECL(EMMCG8, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5, Y1, Y2, Y3, Y4); -FUNC_DECL_2(FWSPID, FWSPID, FWQSPID); +FUNC_DECL_1(FWSPID, FWSPID); FUNC_GROUP_DECL(VB, Y1, Y2, Y3, Y4); FUNC_DECL_3(EMMC, EMMCG1, EMMCG4, EMMCG8); /* @@ -1906,7 +1899,6 @@ static const struct aspeed_pin_group aspeed_g6_groups[] = { ASPEED_PINCTRL_GROUP(FSI2), ASPEED_PINCTRL_GROUP(FWSPIABR), ASPEED_PINCTRL_GROUP(FWSPID), - ASPEED_PINCTRL_GROUP(FWQSPID), ASPEED_PINCTRL_GROUP(FWSPIWP), ASPEED_PINCTRL_GROUP(GPIT0), ASPEED_PINCTRL_GROUP(GPIT1),

From: Alex Elder elder@linaro.org

stable inclusion from stable-v5.10.118 commit 998e305bd160c72b462f4f4c05763c7c6cf9f187 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit d8290cbe1111105f92f0c8ab455bec8bf98d0630 ]

Each time we are notified that some number of transactions on an RX channel has completed, we record the number of bytes that have been transferred since the previous notification. We also track the number of transactions completed, but that is not currently being calculated correctly; we're currently counting the number of such notifications, but each notification can represent many transaction completions. Fix this.

Fixes: 650d1603825d8 ("soc: qcom: ipa: the generic software interface") Signed-off-by: Alex Elder elder@linaro.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/net/ipa/gsi.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index 2a65efd3e8da..fe91b72eca36 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -1209,9 +1209,10 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) struct gsi_event *event_done; struct gsi_event *event; struct gsi_trans *trans; + u32 trans_count = 0; u32 byte_count = 0; - u32 old_index; u32 event_avail; + u32 old_index;

trans_info = &channel->trans_info;

@@ -1232,6 +1233,7 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) do { trans->len = __le16_to_cpu(event->len); byte_count += trans->len; + trans_count++;

/* Move on to the next event and transaction */ if (--event_avail) @@ -1243,7 +1245,7 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index)

/* We record RX bytes when they are received */ channel->byte_count += byte_count; - channel->trans_count++; + channel->trans_count += trans_count; }

/* Initialize a ring, including allocating DMA memory for its entries */

From: Vincent Bernat vincent@bernat.ch

stable inclusion from stable-v5.10.118 commit 243e72e20446b25496887304f3e01e26702b0ac7 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 62679a8d3aa4ba15ff63574a43e5686078d7b804 ]

The disable_policy and disable_xfrm are a per-interface sysctl to disable IPsec policy or encryption on an interface. However, while a "all" variant is exposed, it was a noop since it was never evaluated. We use the usual "or" logic for this kind of sysctls.

Signed-off-by: Vincent Bernat vincent@bernat.ch Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- net/ipv4/route.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 4080e3c6c50d..9bd3cd2177f4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1776,7 +1776,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, flags |= RTCF_LOCAL;

rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, - IN_DEV_CONF_GET(in_dev, NOPOLICY), false); + IN_DEV_ORCONF(in_dev, NOPOLICY), false); if (!rth) return -ENOBUFS;

@@ -1893,8 +1893,8 @@ static int __mkroute_input(struct sk_buff *skb, }

rth = rt_dst_alloc(out_dev->dev, 0, res->type, - IN_DEV_CONF_GET(in_dev, NOPOLICY), - IN_DEV_CONF_GET(out_dev, NOXFRM)); + IN_DEV_ORCONF(in_dev, NOPOLICY), + IN_DEV_ORCONF(out_dev, NOXFRM)); if (!rth) { err = -ENOBUFS; goto cleanup; @@ -2276,7 +2276,7 @@ out: return err;

rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, - IN_DEV_CONF_GET(in_dev, NOPOLICY), false); + IN_DEV_ORCONF(in_dev, NOPOLICY), false); if (!rth) goto e_nobufs;

@@ -2499,8 +2499,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,

add: rth = rt_dst_alloc(dev_out, flags, type, - IN_DEV_CONF_GET(in_dev, NOPOLICY), - IN_DEV_CONF_GET(in_dev, NOXFRM)); + IN_DEV_ORCONF(in_dev, NOPOLICY), + IN_DEV_ORCONF(in_dev, NOXFRM)); if (!rth) return ERR_PTR(-ENOBUFS);

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

stable inclusion from stable-v5.10.118 commit 201e5b5c27996f38e90a54aac866bccca65f8877 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit ef6b1cd11962aec21c58d137006ab122dbc8d6fd ]

if devm_clk_get_optional() fails, we still need to go through the error handling path.

Add the missing goto.

Fixes: 6328a126896ea ("net: systemport: Manage Wake-on-LAN clock") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Acked-by: Florian Fainelli f.fainelli@gmail.com Link: https://lore.kernel.org/r/99d70634a81c229885ae9e4ee69b2035749f7edc.165263404... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/net/ethernet/broadcom/bcmsysport.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index c3a3161ff9ff..467af05a150e 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2596,8 +2596,10 @@ static int bcm_sysport_probe(struct platform_device *pdev) device_set_wakeup_capable(&pdev->dev, 1);

priv->wol_clk = devm_clk_get_optional(&pdev->dev, "sw_sysportwol"); - if (IS_ERR(priv->wol_clk)) - return PTR_ERR(priv->wol_clk); + if (IS_ERR(priv->wol_clk)) { + ret = PTR_ERR(priv->wol_clk); + goto err_deregister_fixed_link; + }

/* Set the needed headroom once and for all */ BUILD_BUG_ON(sizeof(struct bcm_tsb) != 8);

From: Zixuan Fu r33s3n6@gmail.com

stable inclusion from stable-v5.10.118 commit 6e2caee5cddc3d9e0ad0484c9c21b9f10676c044 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit edf410cb74dc612fd47ef5be319c5a0bcd6e6ccd ]

In vmxnet3_rq_create(), when dma_alloc_coherent() fails, vmxnet3_rq_destroy() is called. It sets rq->rx_ring[i].base to NULL. Then vmxnet3_rq_create() returns an error to its callers mxnet3_rq_create_all() -> vmxnet3_change_mtu(). Then vmxnet3_change_mtu() calls vmxnet3_force_close() -> dev_close() in error handling code. And the driver calls vmxnet3_close() -> vmxnet3_quiesce_dev() -> vmxnet3_rq_cleanup_all() -> vmxnet3_rq_cleanup(). In vmxnet3_rq_cleanup(), rq->rx_ring[ring_idx].base is accessed, but this variable is NULL, causing a NULL pointer dereference.

To fix this possible bug, an if statement is added to check whether rq->rx_ring[0].base is NULL in vmxnet3_rq_cleanup() and exit early if so.

The error log in our fault-injection testing is shown as follows:

[ 65.220135] BUG: kernel NULL pointer dereference, address: 0000000000000008 ... [ 65.222633] RIP: 0010:vmxnet3_rq_cleanup_all+0x396/0x4e0 [vmxnet3] ... [ 65.227977] Call Trace: ... [ 65.228262] vmxnet3_quiesce_dev+0x80f/0x8a0 [vmxnet3] [ 65.228580] vmxnet3_close+0x2c4/0x3f0 [vmxnet3] [ 65.228866] __dev_close_many+0x288/0x350 [ 65.229607] dev_close_many+0xa4/0x480 [ 65.231124] dev_close+0x138/0x230 [ 65.231933] vmxnet3_force_close+0x1f0/0x240 [vmxnet3] [ 65.232248] vmxnet3_change_mtu+0x75d/0x920 [vmxnet3] ...

Fixes: d1a890fa37f27 ("net: VMware virtual Ethernet NIC driver: vmxnet3") Reported-by: TOTE Robot oslab@tsinghua.edu.cn Signed-off-by: Zixuan Fu r33s3n6@gmail.com Link: https://lore.kernel.org/r/20220514050711.2636709-1-r33s3n6@gmail.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/net/vmxnet3/vmxnet3_drv.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 530d555988ae..6678a734cc4d 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1656,6 +1656,10 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq, u32 i, ring_idx; struct Vmxnet3_RxDesc *rxd;

+ /* ring has already been cleaned up */ + if (!rq->rx_ring[0].base) + return; + for (ring_idx = 0; ring_idx < 2; ring_idx++) { for (i = 0; i < rq->rx_ring[ring_idx].size; i++) { #ifdef __BIG_ENDIAN_BITFIELD

From: Codrin Ciubotariu codrin.ciubotariu@microchip.com

stable inclusion from stable-v5.10.118 commit d35bf8d766b11e99784cc74be5b7810f2f39240e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit d0031e6fbed955ff8d5f5bbc8fe7382482559cec ]

clk_generated_best_diff() helps in finding the parent and the divisor to compute a rate closest to the required one. However, it doesn't take into account the request's range for the new rate. Make sure the new rate is within the required range.

Fixes: 8a8f4bf0c480 ("clk: at91: clk-generated: create function to find best_diff") Signed-off-by: Codrin Ciubotariu codrin.ciubotariu@microchip.com Link: https://lore.kernel.org/r/20220413071318.244912-1-codrin.ciubotariu@microchi... Reviewed-by: Claudiu Beznea claudiu.beznea@microchip.com Signed-off-by: Stephen Boyd sboyd@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/clk/at91/clk-generated.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c index b656d25a9767..fe772baeb15f 100644 --- a/drivers/clk/at91/clk-generated.c +++ b/drivers/clk/at91/clk-generated.c @@ -106,6 +106,10 @@ static void clk_generated_best_diff(struct clk_rate_request *req, tmp_rate = parent_rate; else tmp_rate = parent_rate / div; + + if (tmp_rate < req->min_rate || tmp_rate > req->max_rate) + return; + tmp_diff = abs(req->rate - tmp_rate);

if (*best_diff < 0 || *best_diff >= tmp_diff) {

From: Duoming Zhou duoming@zju.edu.cn

stable inclusion from stable-v5.10.118 commit b503d0228c9246f090c49c9b2ad54b42164abf46 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 23dd4581350d4ffa23d58976ec46408f8f4c1e16 ]

There are sleep in atomic context bugs when the request to secure element of st-nci is timeout. The root cause is that nci_skb_alloc with GFP_KERNEL parameter is called in st_nci_se_wt_timeout which is a timer handler. The call paths that could trigger bugs are shown below:

(interrupt context 1) st_nci_se_wt_timeout nci_hci_send_event nci_hci_send_data nci_skb_alloc(..., GFP_KERNEL) //may sleep

(interrupt context 2) st_nci_se_wt_timeout nci_hci_send_event nci_hci_send_data nci_send_data nci_queue_tx_data_frags nci_skb_alloc(..., GFP_KERNEL) //may sleep

This patch changes allocation mode of nci_skb_alloc from GFP_KERNEL to GFP_ATOMIC in order to prevent atomic context sleeping. The GFP_ATOMIC flag makes memory allocation operation could be used in atomic context.

Fixes: ed06aeefdac3 ("nfc: st-nci: Rename st21nfcb to st-nci") Signed-off-by: Duoming Zhou duoming@zju.edu.cn Reviewed-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Link: https://lore.kernel.org/r/20220517012530.75714-1-duoming@zju.edu.cn Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- net/nfc/nci/data.c | 2 +- net/nfc/nci/hci.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index ce3382be937f..b002e18f38c8 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -118,7 +118,7 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev,

skb_frag = nci_skb_alloc(ndev, (NCI_DATA_HDR_SIZE + frag_len), - GFP_KERNEL); + GFP_ATOMIC); if (skb_frag == NULL) { rc = -ENOMEM; goto free_exit; diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 04e55ccb3383..4fe336ff2bfa 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -153,7 +153,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe,

i = 0; skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM;

@@ -186,7 +186,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, if (i < data_len) { skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM;

From: Jiasheng Jiang jiasheng@iscas.ac.cn

stable inclusion from stable-v5.10.118 commit 7b676abe328a476ca1f718a6effff3b1e44cde3d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 4dc2a5a8f6754492180741facf2a8787f2c415d7 ]

If skb_clone() returns null pointer, pfkey_broadcast() will return error. Therefore, it should be better to check the return value of pfkey_broadcast() and return error if fails.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Jiasheng Jiang jiasheng@iscas.ac.cn Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- net/key/af_key.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/key/af_key.c b/net/key/af_key.c index bd9b5c573b5a..61505b0df57d 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2830,8 +2830,10 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb void *ext_hdrs[SADB_EXT_MAX]; int err;

- pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, - BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); + err = pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, + BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); + if (err) + return err;

memset(ext_hdrs, 0, sizeof(ext_hdrs)); err = parse_exthdrs(skb, hdr, ext_hdrs);

From: Ard Biesheuvel ardb@kernel.org

stable inclusion from stable-v5.10.118 commit a89888648e0cbc7dd1a46bac3955810fa32b04ad category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 3cfb3019979666bdf33a1010147363cf05e0f17b ]

In Thumb2, 'b . + 4' produces a branch instruction that uses a narrow encoding, and so it does not jump to the following instruction as expected. So use W(b) instead.

Fixes: 6c7cb60bff7a ("ARM: fix Thumb2 regression with Spectre BHB") Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Russell King (Oracle) rmk+kernel@armlinux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- arch/arm/kernel/entry-armv.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index d74678d9598b..4332e5950042 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -1043,7 +1043,7 @@ vector_bhb_loop8_\name:

@ bhb workaround mov r0, #8 -3: b . + 4 +3: W(b) . + 4 subs r0, r0, #1 bne 3b dsb

From: Andrew Lunn andrew@lunn.ch

stable inclusion from stable-v5.10.118 commit dfd1f0cb628bf8a212e5155f53b5c7648a105939 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit fbb3abdf2223cd0dfc07de85fe5a43ba7f435bdf ]

It is possible to stack bridges on top of each other. Consider the following which makes use of an Ethernet switch:

br1 / \ / \ / \ br0.11 wlan0 | br0 / | \ p1 p2 p3

br0 is offloaded to the switch. Above br0 is a vlan interface, for vlan 11. This vlan interface is then a slave of br1. br1 also has a wireless interface as a slave. This setup trunks wireless lan traffic over the copper network inside a VLAN.

A frame received on p1 which is passed up to the bridge has the skb->offload_fwd_mark flag set to true, indicating that the switch has dealt with forwarding the frame out ports p2 and p3 as needed. This flag instructs the software bridge it does not need to pass the frame back down again. However, the flag is not getting reset when the frame is passed upwards. As a result br1 sees the flag, wrongly interprets it, and fails to forward the frame to wlan0.

When passing a frame upwards, clear the flag. This is the Rx equivalent of br_switchdev_frame_unmark() in br_dev_xmit().

Fixes: f1c2eddf4cb6 ("bridge: switchdev: Use an helper to clear forward mark") Signed-off-by: Andrew Lunn andrew@lunn.ch Reviewed-by: Ido Schimmel idosch@nvidia.com Tested-by: Ido Schimmel idosch@nvidia.com Acked-by: Nikolay Aleksandrov razor@blackwall.org Link: https://lore.kernel.org/r/20220518005840.771575-1-andrew@lunn.ch Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- net/bridge/br_input.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 59a318b9f646..bf5bf148091f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -43,6 +43,13 @@ static int br_pass_frame_up(struct sk_buff *skb) u64_stats_update_end(&brstats->syncp);

vg = br_vlan_group_rcu(br); + + /* Reset the offload_fwd_mark because there could be a stacked + * bridge above, and it should not think this bridge it doing + * that bridge's work forwarding out its ports. + */ + br_switchdev_frame_unmark(skb); + /* Bridge is just like any other port. Make sure the * packet is allowed except in promisc modue when someone * may be running packet capture.

From: Haibo Chen haibo.chen@nxp.com

stable inclusion from stable-v5.10.118 commit 30d4721feced120f885e64872f3af0ade0c674c1 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 9bf3ac466faa83d51a8fe9212131701e58fdef74 ]

For gpio controller contain register PDDR, when set one target bit, current logic will clear all other bits, this is wrong. Use operator '|=' to fix it.

Fixes: 659d8a62311f ("gpio: vf610: add imx7ulp support") Reviewed-by: Peng Fan peng.fan@nxp.com Signed-off-by: Haibo Chen haibo.chen@nxp.com Signed-off-by: Bartosz Golaszewski brgl@bgdev.pl Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/gpio/gpio-vf610.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c index 58776f2d69ff..1ae612c796ee 100644 --- a/drivers/gpio/gpio-vf610.c +++ b/drivers/gpio/gpio-vf610.c @@ -125,9 +125,13 @@ static int vf610_gpio_direction_output(struct gpio_chip *chip, unsigned gpio, { struct vf610_gpio_port *port = gpiochip_get_data(chip); unsigned long mask = BIT(gpio); + u32 val;

- if (port->sdata && port->sdata->have_paddr) - vf610_gpio_writel(mask, port->gpio_base + GPIO_PDDR); + if (port->sdata && port->sdata->have_paddr) { + val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR); + val |= mask; + vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR); + }

vf610_gpio_set(chip, gpio, value);

From: Thomas Richter tmricht@linux.ibm.com

stable inclusion from stable-v5.10.118 commit c5af34174733c700bbfb1dde243576c60a2762d5 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit f8ac1c478424a9a14669b8cef7389b1e14e5229d ]

The compilation on s390 results in this error:

# make DEBUG=y bench/numa.o ... bench/numa.c: In function ‘__bench_numa’: bench/numa.c:1749:81: error: ‘%d’ directive output may be truncated writing between 1 and 11 bytes into a region of size between 10 and 20 [-Werror=format-truncation=] 1749 | snprintf(tname, sizeof(tname), "process%d:thread%d", p, t); ^~ ... bench/numa.c:1749:64: note: directive argument in the range [-2147483647, 2147483646] ... #

The maximum length of the %d replacement is 11 characters because of the negative sign. Therefore extend the array by two more characters.

Output after:

# make DEBUG=y bench/numa.o > /dev/null 2>&1; ll bench/numa.o -rw-r--r-- 1 root root 418320 May 19 09:11 bench/numa.o #

Fixes: 3aff8ba0a4c9c919 ("perf bench numa: Avoid possible truncation when using snprintf()") Suggested-by: Namhyung Kim namhyung@gmail.com Signed-off-by: Thomas Richter tmricht@linux.ibm.com Cc: Heiko Carstens hca@linux.ibm.com Cc: Sumanth Korikkar sumanthk@linux.ibm.com Cc: Sven Schnelle svens@linux.ibm.com Cc: Vasily Gorbik gor@linux.ibm.com Link: https://lore.kernel.org/r/20220520081158.2990006-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- tools/perf/bench/numa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 11726ec6285f..88c11305bdd5 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -1656,7 +1656,7 @@ static int __bench_numa(const char *name) "GB/sec,", "total-speed", "GB/sec total speed");

if (g->p.show_details >= 2) { - char tname[14 + 2 * 10 + 1]; + char tname[14 + 2 * 11 + 1]; struct thread_data *td; for (p = 0; p < g->p.nr_proc; p++) { for (t = 0; t < g->p.nr_threads; t++) {

From: Felix Fietkau nbd@nbd.name

stable inclusion from stable-v5.10.118 commit a0f5ff20496bea104bc0d3d791fdb3813fcee989 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 5e469ed9764d4722c59562da13120bd2dc6834c5 ]

When the QoS ack policy was set to non explicit / psmp ack, frames are treated as not being part of a BA session, which causes extra latency on reordering. Fix this by only bypassing reordering for packets with no-ack policy

Signed-off-by: Felix Fietkau nbd@nbd.name Link: https://lore.kernel.org/r/20220420105038.36443-1-nbd@nbd.name Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- net/mac80211/rx.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1e7614abd947..e991abb45f68 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1387,8 +1387,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, goto dont_reorder;

/* not part of a BA session */ - if (ack_policy != IEEE80211_QOS_CTL_ACK_POLICY_BLOCKACK && - ack_policy != IEEE80211_QOS_CTL_ACK_POLICY_NORMAL) + if (ack_policy == IEEE80211_QOS_CTL_ACK_POLICY_NOACK) goto dont_reorder;

/* new, potentially un-ordered, ampdu frame - process it */

From: Nicolas Dichtel nicolas.dichtel@6wind.com

stable inclusion from stable-v5.10.118 commit efe580c436f9102b3142de8ba381b7b280cd1912 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit e71b7f1f44d3d88c677769c85ef0171caf9fc89f ]

The 'ping' utility is able to manage two kind of sockets (raw or icmp), depending on the sysctl ping_group_range. By default, ping_group_range is set to '1 0', which forces ping to use an ip raw socket.

Let's replay the ping tests by allowing 'ping' to use the ip icmp socket. After the previous patch, ipv4 tests results are the same with both kinds of socket. For ipv6, there are a lot a new failures (the previous patch fixes only two cases).

Signed-off-by: Nicolas Dichtel nicolas.dichtel@6wind.com Reviewed-by: David Ahern dsahern@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- tools/testing/selftests/net/fcnal-test.sh | 12 ++++++++++++ 1 file changed, 12 insertions(+)

diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index ace976d89125..4a11ea2261cb 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -794,10 +794,16 @@ ipv4_ping() setup set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null ipv4_ping_novrf + setup + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv4_ping_novrf

log_subsection "With VRF" setup "yes" ipv4_ping_vrf + setup "yes" + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv4_ping_vrf }

################################################################################ @@ -2261,10 +2267,16 @@ ipv6_ping() log_subsection "No VRF" setup ipv6_ping_novrf + setup + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv6_ping_novrf

log_subsection "With VRF" setup "yes" ipv6_ping_vrf + setup "yes" + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv6_ping_vrf }

################################################################################

From: Yang Yingliang yangyingliang@huawei.com

stable inclusion from stable-v5.10.118 commit d4c6e5cebcf5b5d4f90d61074fdbb1cdcb7cdc60 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 51ca86b4c9c7c75f5630fa0dbe5f8f0bd98e3c3e ]

Fix the missing pci_disable_device() before return from tulip_init_one() in the error handling case.

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com Link: https://lore.kernel.org/r/20220506094250.3630615-1-yangyingliang@huawei.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/net/ethernet/dec/tulip/tulip_core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index e7b0d7de40fd..c22d945a79fd 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1396,8 +1396,10 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)

/* alloc_etherdev ensures aligned and zeroed private structures */ dev = alloc_etherdev (sizeof (*tp)); - if (!dev) + if (!dev) { + pci_disable_device(pdev); return -ENOMEM; + }

SET_NETDEV_DEV(dev, &pdev->dev); if (pci_resource_len (pdev, 0) < tulip_tbl[chip_idx].io_size) { @@ -1774,6 +1776,7 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)

err_out_free_netdev: free_netdev (dev); + pci_disable_device(pdev); return -ENODEV; }

From: Grant Grundler grundler@chromium.org

stable inclusion from stable-v5.10.118 commit 9b84e83a92cdacd1a768c4de04ec3d9a81b26c12 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 62e0ae0f4020250f961cf8d0103a4621be74e077 ]

In aq_ring_rx_clean(), if buff->is_eop is not set AND buff->len < AQ_CFG_RX_HDR_SIZE, then hdr_len remains equal to buff->len and skb_add_rx_frag(xxx, *0*, ...) is not called.

The loop following this code starts calling skb_add_rx_frag() starting with i=1 and thus frag[0] is never initialized. Since i is initialized to zero at the top of the primary loop, we can just reference and post-increment i instead of hardcoding the 0 when calling skb_add_rx_frag() the first time.

Reported-by: Aashay Shringarpure aashay@google.com Reported-by: Yi Chou yich@google.com Reported-by: Shervin Oloumi enlightened@google.com Signed-off-by: Grant Grundler grundler@chromium.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 72f8751784c3..7cf5a48e9a7d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -445,7 +445,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self, ALIGN(hdr_len, sizeof(long)));

if (buff->len - hdr_len > 0) { - skb_add_rx_frag(skb, 0, buff->rxdata.page, + skb_add_rx_frag(skb, i++, buff->rxdata.page, buff->rxdata.pg_off + hdr_len, buff->len - hdr_len, AQ_CFG_RX_FRAME_MAX); @@ -454,7 +454,6 @@ int aq_ring_rx_clean(struct aq_ring_s *self,

if (!buff->is_eop) { buff_ = buff; - i = 1U; do { next_ = buff_->next; buff_ = &self->buff_ring[next_];

From: Grant Grundler grundler@chromium.org

stable inclusion from stable-v5.10.118 commit cd66ab20a8f84474564a68fffffd37d998f6c340 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 6aecbba12b5c90b26dc062af3b9de8c4b3a2f19f ]

Enforce that the CPU can not get stuck in an infinite loop.

Reported-by: Aashay Shringarpure aashay@google.com Reported-by: Yi Chou yich@google.com Reported-by: Shervin Oloumi enlightened@google.com Signed-off-by: Grant Grundler grundler@chromium.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 339efdfb1d49..e9c6f1fa0b1a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -362,6 +362,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self, continue;

if (!buff->is_eop) { + unsigned int frag_cnt = 0U; buff_ = buff; do { bool is_rsc_completed = true; @@ -370,6 +371,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, err = -EIO; goto err_exit; } + + frag_cnt++; next_ = buff_->next, buff_ = &self->buff_ring[next_]; is_rsc_completed = @@ -377,7 +380,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, next_, self->hw_head);

- if (unlikely(!is_rsc_completed)) { + if (unlikely(!is_rsc_completed) || + frag_cnt > MAX_SKB_FRAGS) { err = 0; goto err_exit; }

From: Shreyas K K quic_shrekk@quicinc.com

stable inclusion from stable-v5.10.118 commit a698bf1f728c95087a60e0b71cd5cc225ec3332f category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 51f559d66527e238f9a5f82027bff499784d4eac ]

Add KRYO4XX gold/big cores to the list of CPUs that need the repeat TLBI workaround. Apply this to the affected KRYO4XX cores (rcpe to rfpe).

The variant and revision bits are implementation defined and are different from the their Cortex CPU counterparts on which they are based on, i.e., (r0p0 to r3p0) is equivalent to (rcpe to rfpe).

Signed-off-by: Shreyas K K quic_shrekk@quicinc.com Reviewed-by: Sai Prakash Ranjan quic_saipraka@quicinc.com Link: https://lore.kernel.org/r/20220512110134.12179-1-quic_shrekk@quicinc.com Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- Documentation/arm64/silicon-errata.rst | 3 +++ arch/arm64/kernel/cpu_errata.c | 2 ++ 2 files changed, 5 insertions(+)

diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 616570593704..427091fcfcf1 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -162,6 +162,9 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Qualcomm Tech. | Kryo4xx Silver | N/A | ARM64_ERRATUM_1024718 | +----------------+-----------------+-----------------+-----------------------------+ +| Qualcomm Tech. | Kryo4xx Gold | N/A | ARM64_ERRATUM_1286807 | ++----------------+-----------------+-----------------+-----------------------------+ + +----------------+-----------------+-----------------+-----------------------------+ | Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 56848478671e..ba26ef1739a4 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -291,6 +291,8 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { #ifdef CONFIG_ARM64_ERRATUM_1286807 { ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0), + /* Kryo4xx Gold (rcpe to rfpe) => (r0p0 to r3p0) */ + ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe), }, #endif {},

From: Jae Hyun Yoo quic_jaehyoo@quicinc.com

stable inclusion from stable-v5.10.118 commit 355141fdbfef75b91973d2d34049accd1c06fd9e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit a29c96a4053dc3c1d39353b61089882f81c6b23d upstream.

FWQSPID is not a group of FWSPID so remove it.

Fixes: 7488838f2315 ("dt-bindings: pinctrl: aspeed: Document AST2600 pinmux") Signed-off-by: Jae Hyun Yoo quic_jaehyoo@quicinc.com Acked-by: Rob Herring robh@kernel.org Reviewed-by: Andrew Jeffery andrew@aj.id.au Link: https://lore.kernel.org/r/20220329173932.2588289-4-quic_jaehyoo@quicinc.com Signed-off-by: Joel Stanley joel@jms.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- .../devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml index c78ab7e2eee7..fa83c69820f8 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml @@ -58,7 +58,7 @@ patternProperties: $ref: "/schemas/types.yaml#/definitions/string" enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMCG1, EMMCG4, - EMMCG8, ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWQSPID, FWSPIWP, + EMMCG8, ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, HVI3C3, HVI3C4, I2C1, I2C10, I2C11, I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5,

From: Yang Yingliang yangyingliang@huawei.com

stable inclusion from stable-v5.10.118 commit 606011cb6a69b3f211c366aa10594845e6c5ad8c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit a2537c98a8a3b57002e54a262d180b9490bc7190 ]

Fix the missing clk_disable_unprepare() before return from mtk_i2c_probe() in the error handling case.

Fixes: d04913ec5f89 ("i2c: mt7621: Add MediaTek MT7621/7628/7688 I2C driver") Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Stefan Roese sr@denx.de Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- drivers/i2c/busses/i2c-mt7621.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-mt7621.c b/drivers/i2c/busses/i2c-mt7621.c index 45fe4a7fe0c0..901f0fb04fee 100644 --- a/drivers/i2c/busses/i2c-mt7621.c +++ b/drivers/i2c/busses/i2c-mt7621.c @@ -304,7 +304,8 @@ static int mtk_i2c_probe(struct platform_device *pdev)

if (i2c->bus_freq == 0) { dev_warn(i2c->dev, "clock-frequency 0 not supported\n"); - return -EINVAL; + ret = -EINVAL; + goto err_disable_clk; }

adap = &i2c->adap; @@ -322,10 +323,15 @@ static int mtk_i2c_probe(struct platform_device *pdev)

ret = i2c_add_adapter(adap); if (ret < 0) - return ret; + goto err_disable_clk;

dev_info(&pdev->dev, "clock %u kHz\n", i2c->bus_freq / 1000);

+ return 0; + +err_disable_clk: + clk_disable_unprepare(i2c->clk); + return ret; }

From: Jessica Yu jeyu@kernel.org

stable inclusion from stable-v5.10.118 commit 56642f6af2ab3f9a4c77cc5e97ba61b9b46aa92d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 055f23b74b20f2824ce33047b4cf2e2aa856bf3b upstream.

Previously, when CONFIG_MODULE_UNLOAD=n, the module loader just does not attempt to load exit sections since it never expects that any code in those sections will ever execute. However, dynamic code patching (alternatives, jump_label and static_call) can have sites in __exit code, even if __exit is never executed. Therefore __exit must be present at runtime, at least for as long as __init code is.

Commit 33121347fb1c ("module: treat exit sections the same as init sections when !CONFIG_MODULE_UNLOAD") solves the requirements of jump_labels and static_calls by putting the exit sections in the init region of the module so that they are at least present at init, and discarded afterwards. It does this by including a check for exit sections in module_init_section(), so that it also returns true for exit sections, and the module loader will automatically sort them in the init region of the module.

However, the solution there was not completely arch-independent. ARM is a special case where it supplies its own module_{init, exit}_section() functions. Instead of pushing the exit section checks into module_init_section(), just implement the exit section check in layout_sections(), so that we don't have to touch arch-dependent code.

Fixes: 33121347fb1c ("module: treat exit sections the same as init sections when !CONFIG_MODULE_UNLOAD") Reviewed-by: Russell King (Oracle) rmk+kernel@armlinux.org.uk Signed-off-by: Jessica Yu jeyu@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- kernel/module.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/kernel/module.c b/kernel/module.c index de90f989c558..3934ecaf19f7 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2292,6 +2292,15 @@ void *__symbol_get(const char *symbol) } EXPORT_SYMBOL_GPL(__symbol_get);

+static bool module_init_layout_section(const char *sname) +{ +#ifndef CONFIG_MODULE_UNLOAD + if (module_exit_section(sname)) + return true; +#endif + return module_init_section(sname); +} + /* * Ensure that an exported symbol [global namespace] does not already exist * in the kernel or in some other module's exported symbol table. @@ -2501,7 +2510,7 @@ static void layout_sections(struct module *mod, struct load_info *info) if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || module_init_section(sname)) + || module_init_layout_section(sname)) continue; s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i); pr_debug("\t%s\n", sname); @@ -2534,7 +2543,7 @@ static void layout_sections(struct module *mod, struct load_info *info) if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || !module_init_section(sname)) + || !module_init_layout_section(sname)) continue; s->sh_entsize = (get_offset(mod, &mod->init_layout.size, s, i) | INIT_OFFSET_MASK); @@ -2873,11 +2882,7 @@ void * __weak module_alloc(unsigned long size)

bool __weak module_init_section(const char *name) { -#ifndef CONFIG_MODULE_UNLOAD - return strstarts(name, ".init") || module_exit_section(name); -#else return strstarts(name, ".init"); -#endif }

bool __weak module_exit_section(const char *name)