June 2025 - Linux-stable-mirror

[PATCH] net: libwx: fix the incorrect display of the queue number

by Jiawen Wu

When setting "ethtool -L eth0 combined 1", the number of RX/TX queue is changed to be 1. RSS is disabled at this moment, and the indices of FDIR have not be changed in wx_set_rss_queues(). So the combined count still shows the previous value. This issue was introduced when supporting FDIR. Fix it for those devices that support FDIR. Fixes: 34744a7749b3 ("net: txgbe: add FDIR info to ethtool ops") Cc: stable(a)vger.kernel.org Signed-off-by: Jiawen Wu <jiawenwu(a)trustnetic.com> --- drivers/net/ethernet/wangxun/libwx/wx_ethtool.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c index c12a4cb951f6..d9de600e685a 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c @@ -438,6 +438,10 @@ void wx_get_channels(struct net_device *dev, /* record RSS queues */ ch->combined_count = wx->ring_feature[RING_F_RSS].indices; + /* nothing else to report if RSS is disabled */ + if (ch->combined_count == 1) + return; + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) ch->combined_count = wx->ring_feature[RING_F_FDIR].indices; } -- 2.48.1

3 weeks, 6 days

3
3
0 0

[PATCH v2] block: Fix a deadlock related to modifying the readahead attribute

by Bart Van Assche

Every time I run test srp/002 the following deadlock is triggered: task:multipathd Call Trace: <TASK> __schedule+0x8c1/0x1bf0 schedule+0xdd/0x270 schedule_preempt_disabled+0x1c/0x30 __mutex_lock+0xb89/0x1650 mutex_lock_nested+0x1f/0x30 dm_table_set_restrictions+0x823/0xdf0 __bind+0x166/0x590 dm_swap_table+0x2a7/0x490 do_resume+0x1b1/0x610 dev_suspend+0x55/0x1a0 ctl_ioctl+0x3a5/0x7e0 dm_ctl_ioctl+0x12/0x20 __x64_sys_ioctl+0x127/0x1a0 x64_sys_call+0xe2b/0x17d0 do_syscall_64+0x96/0x3a0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 </TASK> task:(udev-worker) Call Trace: <TASK> __schedule+0x8c1/0x1bf0 schedule+0xdd/0x270 blk_mq_freeze_queue_wait+0xf2/0x140 blk_mq_freeze_queue_nomemsave+0x23/0x30 queue_ra_store+0x14e/0x290 queue_attr_store+0x23e/0x2c0 sysfs_kf_write+0xde/0x140 kernfs_fop_write_iter+0x3b2/0x630 vfs_write+0x4fd/0x1390 ksys_write+0xfd/0x230 __x64_sys_write+0x76/0xc0 x64_sys_call+0x276/0x17d0 do_syscall_64+0x96/0x3a0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 </TASK> This deadlock happens because blk_mq_freeze_queue_nomemsave() waits for pending requests to finish. The pending requests do never complete because the dm-multipath queue_if_no_path option is enabled and the only path in the dm-multipath configuration is being removed. Fix this deadlock by removing the queue freezing/unfreezing code from queue_ra_store(). Freezing the request queue from inside a block layer sysfs store callback function is essential when modifying parameters that affect how bios or requests are processed, e.g. parameters that affect bio_split_to_limit(). Freezing the request queue when modifying parameters that do not affect bio nor request processing is not necessary. Cc: Nilay Shroff <nilay(a)linux.ibm.com> Cc: stable(a)vger.kernel.org Fixes: b07a889e8335 ("block: move q->sysfs_lock and queue-freeze under show/store method") Signed-off-by: Bart Van Assche <bvanassche(a)acm.org> --- Changes compared to v1: made the patch description more detailed. block/blk-sysfs.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index b2b9b89d6967..1f63b184c6e9 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -105,7 +105,6 @@ queue_ra_store(struct gendisk *disk, const char *page, size_t count) { unsigned long ra_kb; ssize_t ret; - unsigned int memflags; struct request_queue *q = disk->queue; ret = queue_var_store(&ra_kb, page, count); @@ -116,10 +115,8 @@ queue_ra_store(struct gendisk *disk, const char *page, size_t count) * calculated from the queue limits by queue_limits_commit_update. */ mutex_lock(&q->limits_lock); - memflags = blk_mq_freeze_queue(q); disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); mutex_unlock(&q->limits_lock); - blk_mq_unfreeze_queue(q, memflags); return ret; }

4 weeks

4
7
0 0

[PATCH] block: Fix a deadlock related to modifying the readahead attribute

by Bart Van Assche

Every time I run test srp/002 the following deadlock is triggered: task:multipathd Call Trace: <TASK> __schedule+0x8c1/0x1bf0 schedule+0xdd/0x270 schedule_preempt_disabled+0x1c/0x30 __mutex_lock+0xb89/0x1650 mutex_lock_nested+0x1f/0x30 dm_table_set_restrictions+0x823/0xdf0 __bind+0x166/0x590 dm_swap_table+0x2a7/0x490 do_resume+0x1b1/0x610 dev_suspend+0x55/0x1a0 ctl_ioctl+0x3a5/0x7e0 dm_ctl_ioctl+0x12/0x20 __x64_sys_ioctl+0x127/0x1a0 x64_sys_call+0xe2b/0x17d0 do_syscall_64+0x96/0x3a0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 </TASK> task:(udev-worker) Call Trace: <TASK> __schedule+0x8c1/0x1bf0 schedule+0xdd/0x270 blk_mq_freeze_queue_wait+0xf2/0x140 blk_mq_freeze_queue_nomemsave+0x23/0x30 queue_ra_store+0x14e/0x290 queue_attr_store+0x23e/0x2c0 sysfs_kf_write+0xde/0x140 kernfs_fop_write_iter+0x3b2/0x630 vfs_write+0x4fd/0x1390 ksys_write+0xfd/0x230 __x64_sys_write+0x76/0xc0 x64_sys_call+0x276/0x17d0 do_syscall_64+0x96/0x3a0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 </TASK> Fix this by removing the superfluous queue freezing/unfreezing code from queue_ra_store(). Cc: Nilay Shroff <nilay(a)linux.ibm.com> Cc: stable(a)vger.kernel.org Fixes: b07a889e8335 ("block: move q->sysfs_lock and queue-freeze under show/store method") Signed-off-by: Bart Van Assche <bvanassche(a)acm.org> --- block/blk-sysfs.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index b2b9b89d6967..1f63b184c6e9 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -105,7 +105,6 @@ queue_ra_store(struct gendisk *disk, const char *page, size_t count) { unsigned long ra_kb; ssize_t ret; - unsigned int memflags; struct request_queue *q = disk->queue; ret = queue_var_store(&ra_kb, page, count); @@ -116,10 +115,8 @@ queue_ra_store(struct gendisk *disk, const char *page, size_t count) * calculated from the queue limits by queue_limits_commit_update. */ mutex_lock(&q->limits_lock); - memflags = blk_mq_freeze_queue(q); disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); mutex_unlock(&q->limits_lock); - blk_mq_unfreeze_queue(q, memflags); return ret; }

4 weeks

3
9
0 0

[PATCH] cifs: all initializations for tcon should happen in tcon_info_alloc

by nspmangalore＠gmail.com

From: Shyam Prasad N <sprasad(a)microsoft.com> Today, a few work structs inside tcon are initialized inside cifs_get_tcon and not in tcon_info_alloc. As a result, if a tcon is obtained from tcon_info_alloc, but not called as a part of cifs_get_tcon, we may trip over. Cc: <stable(a)vger.kernel.org> Signed-off-by: Shyam Prasad N <sprasad(a)microsoft.com> --- fs/smb/client/cifsproto.h | 1 + fs/smb/client/connect.c | 8 +------- fs/smb/client/misc.c | 6 ++++++ 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 66093fa78aed..045227ed4efc 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -136,6 +136,7 @@ extern int SendReceiveBlockingLock(const unsigned int xid, struct smb_hdr *out_buf, int *bytes_returned); +void smb2_query_server_interfaces(struct work_struct *work); void cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, bool all_channels); diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index c48869c29e15..16c4f7fa1f34 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -97,7 +97,7 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) return rc; } -static void smb2_query_server_interfaces(struct work_struct *work) +void smb2_query_server_interfaces(struct work_struct *work) { int rc; int xid; @@ -2866,20 +2866,14 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) tcon->max_cached_dirs = ctx->max_cached_dirs; tcon->nodelete = ctx->nodelete; tcon->local_lease = ctx->local_lease; - INIT_LIST_HEAD(&tcon->pending_opens); tcon->status = TID_GOOD; - INIT_DELAYED_WORK(&tcon->query_interfaces, - smb2_query_server_interfaces); if (ses->server->dialect >= SMB30_PROT_ID && (ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { /* schedule query interfaces poll */ queue_delayed_work(cifsiod_wq, &tcon->query_interfaces, (SMB_INTERFACE_POLL_INTERVAL * HZ)); } -#ifdef CONFIG_CIFS_DFS_UPCALL - INIT_DELAYED_WORK(&tcon->dfs_cache_work, dfs_cache_refresh); -#endif spin_lock(&cifs_tcp_ses_lock); list_add(&tcon->tcon_list, &ses->tcon_list); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index e77017f47084..da23cc12a52c 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -151,6 +151,12 @@ tcon_info_alloc(bool dir_leases_enabled, enum smb3_tcon_ref_trace trace) #ifdef CONFIG_CIFS_DFS_UPCALL INIT_LIST_HEAD(&ret_buf->dfs_ses_list); #endif + INIT_LIST_HEAD(&ret_buf->pending_opens); + INIT_DELAYED_WORK(&ret_buf->query_interfaces, + smb2_query_server_interfaces); +#ifdef CONFIG_CIFS_DFS_UPCALL + INIT_DELAYED_WORK(&ret_buf->dfs_cache_work, dfs_cache_refresh); +#endif return ret_buf; } -- 2.43.0

4 weeks

4
4
0 0

[PATCH net v2 1/3] virtio-net: ensure the received length does not exceed allocated size

by Bui Quang Minh

In xdp_linearize_page, when reading the following buffers from the ring, we forget to check the received length with the true allocate size. This can lead to an out-of-bound read. This commit adds that missing check. Cc: <stable(a)vger.kernel.org> Fixes: 4941d472bf95 ("virtio-net: do not reset during XDP set") Signed-off-by: Bui Quang Minh <minhquangbui99(a)gmail.com> --- drivers/net/virtio_net.c | 38 ++++++++++++++++++++++++++++++++++---- 1 file changed, 34 insertions(+), 4 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index e53ba600605a..31661bcb3932 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -778,6 +778,26 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx) return (unsigned long)mrg_ctx & ((1 << MRG_CTX_HEADER_SHIFT) - 1); } +static int check_mergeable_len(struct net_device *dev, void *mrg_ctx, + unsigned int len) +{ + unsigned int headroom, tailroom, room, truesize; + + truesize = mergeable_ctx_to_truesize(mrg_ctx); + headroom = mergeable_ctx_to_headroom(mrg_ctx); + tailroom = headroom ? sizeof(struct skb_shared_info) : 0; + room = SKB_DATA_ALIGN(headroom + tailroom); + + if (len > truesize - room) { + pr_debug("%s: rx error: len %u exceeds truesize %lu\n", + dev->name, len, (unsigned long)(truesize - room)); + DEV_STATS_INC(dev, rx_length_errors); + return -1; + } + + return 0; +} + static struct sk_buff *virtnet_build_skb(void *buf, unsigned int buflen, unsigned int headroom, unsigned int len) @@ -1797,7 +1817,8 @@ static unsigned int virtnet_get_headroom(struct virtnet_info *vi) * across multiple buffers (num_buf > 1), and we make sure buffers * have enough headroom. */ -static struct page *xdp_linearize_page(struct receive_queue *rq, +static struct page *xdp_linearize_page(struct net_device *dev, + struct receive_queue *rq, int *num_buf, struct page *p, int offset, @@ -1817,18 +1838,27 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, memcpy(page_address(page) + page_off, page_address(p) + offset, *len); page_off += *len; + /* Only mergeable mode can go inside this while loop. In small mode, + * *num_buf == 1, so it cannot go inside. + */ while (--*num_buf) { unsigned int buflen; void *buf; + void *ctx; int off; - buf = virtnet_rq_get_buf(rq, &buflen, NULL); + buf = virtnet_rq_get_buf(rq, &buflen, &ctx); if (unlikely(!buf)) goto err_buf; p = virt_to_head_page(buf); off = buf - page_address(p); + if (check_mergeable_len(dev, ctx, buflen)) { + put_page(p); + goto err_buf; + } + /* guard against a misconfigured or uncooperative backend that * is sending packet larger than the MTU. */ @@ -1917,7 +1947,7 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev, headroom = vi->hdr_len + header_offset; buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - xdp_page = xdp_linearize_page(rq, &num_buf, page, + xdp_page = xdp_linearize_page(dev, rq, &num_buf, page, offset, header_offset, &tlen); if (!xdp_page) @@ -2252,7 +2282,7 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi, */ if (!xdp_prog->aux->xdp_has_frags) { /* linearize data for XDP */ - xdp_page = xdp_linearize_page(rq, num_buf, + xdp_page = xdp_linearize_page(vi->dev, rq, num_buf, *page, offset, XDP_PACKET_HEADROOM, len); -- 2.43.0

4 weeks

2
1
0 0

FAILED: patch "[PATCH] s390/ptrace: Fix pointer dereferencing in" failed to apply to 6.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.15.y git checkout FETCH_HEAD git cherry-pick -x 7f8073cfb04a97842fe891ca50dad60afd1e3121 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062928-revival-saint-3ba2@gregkh' --subject-prefix 'PATCH 6.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7f8073cfb04a97842fe891ca50dad60afd1e3121 Mon Sep 17 00:00:00 2001 From: Heiko Carstens <hca(a)linux.ibm.com> Date: Fri, 13 Jun 2025 17:53:04 +0200 Subject: [PATCH] s390/ptrace: Fix pointer dereferencing in regs_get_kernel_stack_nth() The recent change which added READ_ONCE_NOCHECK() to read the nth entry from the kernel stack incorrectly dropped dereferencing of the stack pointer in order to read the requested entry. In result the address of the entry is returned instead of its content. Dereference the pointer again to fix this. Reported-by: Will Deacon <will(a)kernel.org> Closes: https://lore.kernel.org/r/20250612163331.GA13384@willie-the-truck Fixes: d93a855c31b7 ("s390/ptrace: Avoid KASAN false positives in regs_get_kernel_stack_nth()") Cc: stable(a)vger.kernel.org Reviewed-by: Alexander Gordeev <agordeev(a)linux.ibm.com> Signed-off-by: Heiko Carstens <hca(a)linux.ibm.com> Signed-off-by: Alexander Gordeev <agordeev(a)linux.ibm.com> diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 62c0ab4a4b9d..0905fa99a31e 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -265,7 +265,7 @@ static __always_inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *r addr = kernel_stack_pointer(regs) + n * sizeof(long); if (!regs_within_kernel_stack(regs, addr)) return 0; - return READ_ONCE_NOCHECK(addr); + return READ_ONCE_NOCHECK(*(unsigned long *)addr); } /**

4 weeks

3
2
0 0

FAILED: patch "[PATCH] spi: spi-cadence-quadspi: Fix pm runtime unbalance" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x b07f349d1864abe29436f45e3047da2bdd476462 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025063006-expose-blandness-ffd5@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b07f349d1864abe29436f45e3047da2bdd476462 Mon Sep 17 00:00:00 2001 From: Khairul Anuar Romli <khairul.anuar.romli(a)altera.com> Date: Mon, 16 Jun 2025 09:13:53 +0800 Subject: [PATCH] spi: spi-cadence-quadspi: Fix pm runtime unbalance Having PM put sync in remove function is causing PM underflow during remove operation. This is caused by the function, runtime_pm_get_sync, not being called anywhere during the op. Ensure that calls to pm_runtime_enable()/pm_runtime_disable() and pm_runtime_get_sync()/pm_runtime_put_sync() match. echo 108d2000.spi > /sys/bus/platform/drivers/cadence-qspi/unbind [ 49.644256] Deleting MTD partitions on "108d2000.spi.0": [ 49.649575] Deleting u-boot MTD partition [ 49.684087] Deleting root MTD partition [ 49.724188] cadence-qspi 108d2000.spi: Runtime PM usage count underflow! Continuous bind/unbind will result in an "Unbalanced pm_runtime_enable" error. Subsequent unbind attempts will return a "No such device" error, while bind attempts will return a "Resource temporarily unavailable" error. [ 47.592434] cadence-qspi 108d2000.spi: Runtime PM usage count underflow! [ 49.592233] cadence-qspi 108d2000.spi: detected FIFO depth (1024) different from config (128) [ 53.232309] cadence-qspi 108d2000.spi: Runtime PM usage count underflow! [ 55.828550] cadence-qspi 108d2000.spi: detected FIFO depth (1024) different from config (128) [ 57.940627] cadence-qspi 108d2000.spi: Runtime PM usage count underflow! [ 59.912490] cadence-qspi 108d2000.spi: detected FIFO depth (1024) different from config (128) [ 61.876243] cadence-qspi 108d2000.spi: Runtime PM usage count underflow! [ 61.883000] platform 108d2000.spi: Unbalanced pm_runtime_enable! [ 532.012270] cadence-qspi 108d2000.spi: probe with driver cadence-qspi failed1 Also, change clk_disable_unprepare() to clk_disable() since continuous bind and unbind operations will trigger a warning indicating that the clock is already unprepared. Fixes: 4892b374c9b7 ("mtd: spi-nor: cadence-quadspi: Add runtime PM support") cc: stable(a)vger.kernel.org # 6.6+ Signed-off-by: Khairul Anuar Romli <khairul.anuar.romli(a)altera.com> Reviewed-by: Matthew Gerlach <matthew.gerlach(a)altera.com> Link: https://patch.msgid.link/4e7a4b8aba300e629b45a04f90bddf665fbdb335.174960187… Signed-off-by: Mark Brown <broonie(a)kernel.org> diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index fe0f122f07b0..aa1932ba17cb 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1958,10 +1958,10 @@ static int cqspi_probe(struct platform_device *pdev) goto probe_setup_failed; } - ret = devm_pm_runtime_enable(dev); - if (ret) { - if (cqspi->rx_chan) - dma_release_channel(cqspi->rx_chan); + pm_runtime_enable(dev); + + if (cqspi->rx_chan) { + dma_release_channel(cqspi->rx_chan); goto probe_setup_failed; } @@ -1981,6 +1981,7 @@ static int cqspi_probe(struct platform_device *pdev) return 0; probe_setup_failed: cqspi_controller_enable(cqspi, 0); + pm_runtime_disable(dev); probe_reset_failed: if (cqspi->is_jh7110) cqspi_jh7110_disable_clk(pdev, cqspi); @@ -1999,7 +2000,8 @@ static void cqspi_remove(struct platform_device *pdev) if (cqspi->rx_chan) dma_release_channel(cqspi->rx_chan); - clk_disable_unprepare(cqspi->clk); + if (pm_runtime_get_sync(&pdev->dev) >= 0) + clk_disable(cqspi->clk); if (cqspi->is_jh7110) cqspi_jh7110_disable_clk(pdev, cqspi);

4 weeks

3
2
0 0

FAILED: patch "[PATCH] mm/vma: reset VMA iterator on commit_merge() OOM failure" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x 0cf4b1687a187ba9247c71721d8b064634eda1f7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062053-gills-deliverer-bafc@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0cf4b1687a187ba9247c71721d8b064634eda1f7 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Date: Fri, 6 Jun 2025 13:50:32 +0100 Subject: [PATCH] mm/vma: reset VMA iterator on commit_merge() OOM failure While an OOM failure in commit_merge() isn't really feasible due to the allocation which might fail (a maple tree pre-allocation) being 'too small to fail', we do need to handle this case correctly regardless. In vma_merge_existing_range(), we can theoretically encounter failures which result in an OOM error in two ways - firstly dup_anon_vma() might fail with an OOM error, and secondly commit_merge() failing, ultimately, to pre-allocate a maple tree node. The abort logic for dup_anon_vma() resets the VMA iterator to the initial range, ensuring that any logic looping on this iterator will correctly proceed to the next VMA. However the commit_merge() abort logic does not do the same thing. This resulted in a syzbot report occurring because mlockall() iterates through VMAs, is tolerant of errors, but ended up with an incorrect previous VMA being specified due to incorrect iterator state. While making this change, it became apparent we are duplicating logic - the logic introduced in commit 41e6ddcaa0f1 ("mm/vma: add give_up_on_oom option on modify/merge, use in uffd release") duplicates the vmg->give_up_on_oom check in both abort branches. Additionally, we observe that we can perform the anon_dup check safely on dup_anon_vma() failure, as this will not be modified should this call fail. Finally, we need to reset the iterator in both cases, so now we can simply use the exact same code to abort for both. We remove the VM_WARN_ON(err != -ENOMEM) as it would be silly for this to be otherwise and it allows us to implement the abort check more neatly. Link: https://lkml.kernel.org/r/20250606125032.164249-1-lorenzo.stoakes@oracle.com Fixes: 47b16d0462a4 ("mm: abort vma_modify() on merge out of memory failure") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reported-by: syzbot+d16409ea9ecc16ed261a(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-mm/6842cc67.a00a0220.29ac89.003b.GAE@google.c… Reviewed-by: Pedro Falcato <pfalcato(a)suse.de> Reviewed-by: Vlastimil Babka <vbabka(a)suse.cz> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Jann Horn <jannh(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/vma.c b/mm/vma.c index 726b2a31ce59..0fb9b2c7b734 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -967,26 +967,9 @@ static __must_check struct vm_area_struct *vma_merge_existing_range( err = dup_anon_vma(next, middle, &anon_dup); } - if (err) + if (err || commit_merge(vmg)) goto abort; - err = commit_merge(vmg); - if (err) { - VM_WARN_ON(err != -ENOMEM); - - if (anon_dup) - unlink_anon_vmas(anon_dup); - - /* - * We've cleaned up any cloned anon_vma's, no VMAs have been - * modified, no harm no foul if the user requests that we not - * report this and just give up, leaving the VMAs unmerged. - */ - if (!vmg->give_up_on_oom) - vmg->state = VMA_MERGE_ERROR_NOMEM; - return NULL; - } - khugepaged_enter_vma(vmg->target, vmg->flags); vmg->state = VMA_MERGE_SUCCESS; return vmg->target; @@ -995,6 +978,9 @@ static __must_check struct vm_area_struct *vma_merge_existing_range( vma_iter_set(vmg->vmi, start); vma_iter_load(vmg->vmi); + if (anon_dup) + unlink_anon_vmas(anon_dup); + /* * This means we have failed to clone anon_vma's correctly, but no * actual changes to VMAs have occurred, so no harm no foul - if the

4 weeks

3
2
0 0

[PATCH v3] x86/sev: Use TSC_FACTOR for Secure TSC frequency calculation

by Nikunj A Dadhania

When using Secure TSC, the GUEST_TSC_FREQ MSR reports a frequency based on the nominal P0 frequency, which deviates slightly (typically ~0.2%) from the actual mean TSC frequency due to clocking parameters. Over extended VM uptime, this discrepancy accumulates, causing clock skew between the hypervisor and SEV-SNP VM, leading to early timer interrupts as perceived by the guest. The guest kernel relies on the reported nominal frequency for TSC-based timekeeping, while the actual frequency set during SNP_LAUNCH_START may differ. This mismatch results in inaccurate time calculations, causing the guest to perceive hrtimers as firing earlier than expected. Utilize the TSC_FACTOR from the SEV firmware's secrets page (see "Secrets Page Format" in the SNP Firmware ABI Specification) to calculate the mean TSC frequency, ensuring accurate timekeeping and mitigating clock skew in SEV-SNP VMs. Use early_ioremap_encrypted() to map the secrets page as ioremap_encrypted() uses kmalloc() which is not available during early TSC initialization and causes a panic. Fixes: 73bbf3b0fbba ("x86/tsc: Init the TSC for Secure TSC guests") Cc: stable(a)vger.kernel.org Signed-off-by: Nikunj A Dadhania <nikunj(a)amd.com> --- v3: * Remove unnecessary parenthesis (Ingo) * To avoid type cast, harmonize the types of snp_tsc_freq_khz and securetsc_get_tsc_khz() (Ingo) * Use rdmsr for GUEST_TSC_FREQ and extract BIT[17:0] from lower 32-bit v2: * Move the SNP TSC scaling constant to the header (Dionna) * Drop the unsigned long cast and add in securetsc_get_tsc_khz (Tom) * Drop the RB from Tom as the code has changed --- arch/x86/include/asm/sev.h | 18 +++++++++++++++++- arch/x86/coco/sev/core.c | 22 ++++++++++++++++++---- 2 files changed, 35 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index a81769a32eaa..cfa3ace227e6 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -223,6 +223,19 @@ struct snp_tsc_info_resp { u8 rsvd2[100]; } __packed; + +/* + * Obtain the mean TSC frequency by decreasing the nominal TSC frequency with + * TSC_FACTOR as documented in the SNP Firmware ABI specification: + * + * GUEST_TSC_FREQ * (1 - (TSC_FACTOR * 0.00001)) + * + * which is equivalent to: + * + * GUEST_TSC_FREQ -= (GUEST_TSC_FREQ * TSC_FACTOR) / 100000; + */ +#define SNP_SCALE_TSC_FREQ(freq, factor) ((freq) - (freq) * (factor) / 100000) + struct snp_guest_req { void *req_buf; size_t req_sz; @@ -283,8 +296,11 @@ struct snp_secrets_page { u8 svsm_guest_vmpl; u8 rsvd3[3]; + /* The percentage decrease from nominal to mean TSC frequency. */ + u32 tsc_factor; + /* Remainder of page */ - u8 rsvd4[3744]; + u8 rsvd4[3740]; } __packed; struct snp_msg_desc { diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index 46bd89578ec7..115a5750c40d 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -88,7 +88,7 @@ static const char * const sev_status_feat_names[] = { */ static u64 snp_tsc_scale __ro_after_init; static u64 snp_tsc_offset __ro_after_init; -static u64 snp_tsc_freq_khz __ro_after_init; +static unsigned long snp_tsc_freq_khz __ro_after_init; DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa); @@ -2174,15 +2174,29 @@ static unsigned long securetsc_get_tsc_khz(void) void __init snp_secure_tsc_init(void) { - unsigned long long tsc_freq_mhz; + unsigned long tsc_freq_mhz, dummy; + struct snp_secrets_page *secrets; + void *mem; if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC)) return; + mem = early_memremap_encrypted(sev_secrets_pa, PAGE_SIZE); + if (!mem) { + pr_err("Unable to get TSC_FACTOR: failed to map the SNP secrets page.\n"); + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECURE_TSC); + } + + secrets = (__force struct snp_secrets_page *)mem; + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); - rdmsrq(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz); - snp_tsc_freq_khz = (unsigned long)(tsc_freq_mhz * 1000); + rdmsr(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz, dummy); + /* Extract the GUEST TSC MHZ from BIT[17:0], rest is reserved space */ + tsc_freq_mhz = tsc_freq_mhz & GENMASK_ULL(17, 0); + snp_tsc_freq_khz = SNP_SCALE_TSC_FREQ(tsc_freq_mhz * 1000, secrets->tsc_factor); x86_platform.calibrate_cpu = securetsc_get_tsc_khz; x86_platform.calibrate_tsc = securetsc_get_tsc_khz; + + early_memunmap(mem, PAGE_SIZE); } base-commit: 4da71e9f8939987cd2063e0b2ab5bb5eafc80a87 -- 2.43.0

4 weeks

2
2
0 0

[PATCH] drm/vmwgfx: handle allocation failure of waiter context

by Fedor Pchelkin

Handle result of kmalloc() to prevent possible NULL pointer dereference. For the sake of not introducing additional layer of indentation, extract seqno_waiter_rm_context creating code into a separate helper function. Judging by commit 0039a3b35b10 ("drm/vmwgfx: Add seqno waiter for sync_files"), possible errors in seqno waiting aren't fatal, thus just skip this block if an allocation failure occurs - no need to propagate upwards. Found by Linux Verification Center (linuxtesting.org) with Svace static analysis tool. Fixes: 0039a3b35b10 ("drm/vmwgfx: Add seqno waiter for sync_files") Cc: stable(a)vger.kernel.org Signed-off-by: Fedor Pchelkin <pchelkin(a)ispras.ru> --- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 27 ++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index e831e324e737..12d897eca410 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -4085,6 +4085,23 @@ static void seqno_waiter_rm_cb(struct dma_fence *f, struct dma_fence_cb *cb) kfree(ctx); } +static void seqno_waiter_create(struct dma_fence *f, + struct vmw_private *dev_priv) +{ + struct seqno_waiter_rm_context *ctx; + + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return; + + ctx->dev_priv = dev_priv; + vmw_seqno_waiter_add(dev_priv); + if (dma_fence_add_callback(f, &ctx->base, seqno_waiter_rm_cb) < 0) { + vmw_seqno_waiter_remove(dev_priv); + kfree(ctx); + } +} + int vmw_execbuf_process(struct drm_file *file_priv, struct vmw_private *dev_priv, void __user *user_commands, void *kernel_commands, @@ -4265,15 +4282,7 @@ int vmw_execbuf_process(struct drm_file *file_priv, } else { /* Link the fence with the FD created earlier */ fd_install(out_fence_fd, sync_file->file); - struct seqno_waiter_rm_context *ctx = - kmalloc(sizeof(*ctx), GFP_KERNEL); - ctx->dev_priv = dev_priv; - vmw_seqno_waiter_add(dev_priv); - if (dma_fence_add_callback(&fence->base, &ctx->base, - seqno_waiter_rm_cb) < 0) { - vmw_seqno_waiter_remove(dev_priv); - kfree(ctx); - } + seqno_waiter_create(&fence->base, dev_priv); } } -- 2.50.0

4 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2025