April 2025 - Linux-stable-mirror

+ selftests-mm-compaction_test-support-platform-with-huge-mount-of-memory.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: selftests/mm: compaction_test: support platform with huge mount of memory has been added to the -mm mm-hotfixes-unstable branch. Its filename is selftests-mm-compaction_test-support-platform-with-huge-mount-of-memory.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Feng Tang <feng.tang(a)linux.alibaba.com> Subject: selftests/mm: compaction_test: support platform with huge mount of memory Date: Wed, 23 Apr 2025 18:36:45 +0800 When running mm selftest to verify mm patches, 'compaction_test' case failed on an x86 server with 1TB memory. And the root cause is that it has too much free memory than what the test supports. The test case tries to allocate 100000 huge pages, which is about 200 GB for that x86 server, and when it succeeds, it expects it's large than 1/3 of 80% of the free memory in system. This logic only works for platform with 750 GB ( 200 / (1/3) / 80% ) or less free memory, and may raise false alarm for others. Fix it by changing the fixed page number to self-adjustable number according to the real number of free memory. Link: https://lkml.kernel.org/r/20250423103645.2758-1-feng.tang@linux.alibaba.com Fixes: bd67d5c15cc19 ("Test compaction of mlocked memory") Signed-off-by: Feng Tang <feng.tang(a)linux.alibaba.com> Acked-by: Dev Jain <dev.jain(a)arm.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Sri Jayaramappa <sjayaram(a)akamai.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- tools/testing/selftests/mm/compaction_test.c | 19 ++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) --- a/tools/testing/selftests/mm/compaction_test.c~selftests-mm-compaction_test-support-platform-with-huge-mount-of-memory +++ a/tools/testing/selftests/mm/compaction_test.c @@ -90,6 +90,8 @@ int check_compaction(unsigned long mem_f int compaction_index = 0; char nr_hugepages[20] = {0}; char init_nr_hugepages[24] = {0}; + char target_nr_hugepages[24] = {0}; + int slen; snprintf(init_nr_hugepages, sizeof(init_nr_hugepages), "%lu", initial_nr_hugepages); @@ -106,11 +108,18 @@ int check_compaction(unsigned long mem_f goto out; } - /* Request a large number of huge pages. The Kernel will allocate - as much as it can */ - if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + /* + * Request huge pages for about half of the free memory. The Kernel + * will allocate as much as it can, and we expect it will get at least 1/3 + */ + nr_hugepages_ul = mem_free / hugepage_size / 2; + snprintf(target_nr_hugepages, sizeof(target_nr_hugepages), + "%lu", nr_hugepages_ul); + + slen = strlen(target_nr_hugepages); + if (write(fd, target_nr_hugepages, slen) != slen) { + ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n", + nr_hugepages_ul, strerror(errno)); goto close_fd; } _ Patches currently in -mm which might be from feng.tang(a)linux.alibaba.com are selftests-mm-compaction_test-support-platform-with-huge-mount-of-memory.patch

2 months

1
0
0 0

[PATCH 1/2] Drivers: hv: Allocate interrupt and monitor pages aligned to system page boundary

by longli＠linuxonhyperv.com

From: Long Li <longli(a)microsoft.com> There are use cases that interrupt and monitor pages are mapped to user-mode through UIO, they need to be system page aligned. Some Hyper-V allocation APIs introduced earlier broke those requirements. Fix those APIs by always allocating Hyper-V page at system page boundaries. Cc: stable(a)vger.kernel.org Fixes: ca48739e59df ("Drivers: hv: vmbus: Move Hyper-V page allocator to arch neutral code") Signed-off-by: Long Li <longli(a)microsoft.com> --- drivers/hv/hv_common.c | 29 +++++++---------------------- 1 file changed, 7 insertions(+), 22 deletions(-) diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index a7d7494feaca..f426aaa9b8f9 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -106,41 +106,26 @@ void __init hv_common_free(void) } /* - * Functions for allocating and freeing memory with size and - * alignment HV_HYP_PAGE_SIZE. These functions are needed because - * the guest page size may not be the same as the Hyper-V page - * size. We depend upon kmalloc() aligning power-of-two size - * allocations to the allocation size boundary, so that the - * allocated memory appears to Hyper-V as a page of the size - * it expects. + * A Hyper-V page can be used by UIO for mapping to user-space, it should + * always be allocated on system page boundaries. */ - void *hv_alloc_hyperv_page(void) { - BUILD_BUG_ON(PAGE_SIZE < HV_HYP_PAGE_SIZE); - - if (PAGE_SIZE == HV_HYP_PAGE_SIZE) - return (void *)__get_free_page(GFP_KERNEL); - else - return kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); + BUILD_BUG_ON(PAGE_SIZE < HV_HYP_PAGE_SIZE); + return (void *)__get_free_page(GFP_KERNEL); } EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page); void *hv_alloc_hyperv_zeroed_page(void) { - if (PAGE_SIZE == HV_HYP_PAGE_SIZE) - return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - else - return kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); + BUILD_BUG_ON(PAGE_SIZE < HV_HYP_PAGE_SIZE); + return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL_GPL(hv_alloc_hyperv_zeroed_page); void hv_free_hyperv_page(void *addr) { - if (PAGE_SIZE == HV_HYP_PAGE_SIZE) - free_page((unsigned long)addr); - else - kfree(addr); + free_page((unsigned long)addr); } EXPORT_SYMBOL_GPL(hv_free_hyperv_page); -- 2.34.1

2 months

3
3
0 0

[PATCH 2/2] uio_hv_generic: Use correct size for interrupt and monitor pages

by longli＠linuxonhyperv.com

From: Long Li <longli(a)microsoft.com> Interrupt and monitor pages should be in Hyper-V page size (4k bytes). This can be different to the system page size. Cc: stable(a)vger.kernel.org Fixes: 95096f2fbd10 ("uio-hv-generic: new userspace i/o driver for VMBus") Signed-off-by: Long Li <longli(a)microsoft.com> --- drivers/uio/uio_hv_generic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index 1b19b5647495..08385b04c4ab 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -287,13 +287,13 @@ hv_uio_probe(struct hv_device *dev, pdata->info.mem[INT_PAGE_MAP].name = "int_page"; pdata->info.mem[INT_PAGE_MAP].addr = (uintptr_t)vmbus_connection.int_page; - pdata->info.mem[INT_PAGE_MAP].size = PAGE_SIZE; + pdata->info.mem[INT_PAGE_MAP].size = HV_HYP_PAGE_SIZE; pdata->info.mem[INT_PAGE_MAP].memtype = UIO_MEM_LOGICAL; pdata->info.mem[MON_PAGE_MAP].name = "monitor_page"; pdata->info.mem[MON_PAGE_MAP].addr = (uintptr_t)vmbus_connection.monitor_pages[1]; - pdata->info.mem[MON_PAGE_MAP].size = PAGE_SIZE; + pdata->info.mem[MON_PAGE_MAP].size = HV_HYP_PAGE_SIZE; pdata->info.mem[MON_PAGE_MAP].memtype = UIO_MEM_LOGICAL; if (channel->device_id == HV_NIC) { -- 2.34.1

2 months

3
3
0 0

[PATCH] ext4: fix off-by-one error in do_split

by Artem Sadovnikov

Syzkaller detected a use-after-free issue in ext4_insert_dentry that was caused by out-of-bounds access due to incorrect splitting in do_split. BUG: KASAN: use-after-free in ext4_insert_dentry+0x36a/0x6d0 fs/ext4/namei.c:2109 Write of size 251 at addr ffff888074572f14 by task syz-executor335/5847 CPU: 0 UID: 0 PID: 5847 Comm: syz-executor335 Not tainted 6.12.0-rc6-syzkaller-00318-ga9cda7c0ffed #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/30/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 kasan_check_range+0x282/0x290 mm/kasan/generic.c:189 __asan_memcpy+0x40/0x70 mm/kasan/shadow.c:106 ext4_insert_dentry+0x36a/0x6d0 fs/ext4/namei.c:2109 add_dirent_to_buf+0x3d9/0x750 fs/ext4/namei.c:2154 make_indexed_dir+0xf98/0x1600 fs/ext4/namei.c:2351 ext4_add_entry+0x222a/0x25d0 fs/ext4/namei.c:2455 ext4_add_nondir+0x8d/0x290 fs/ext4/namei.c:2796 ext4_symlink+0x920/0xb50 fs/ext4/namei.c:3431 vfs_symlink+0x137/0x2e0 fs/namei.c:4615 do_symlinkat+0x222/0x3a0 fs/namei.c:4641 __do_sys_symlink fs/namei.c:4662 [inline] __se_sys_symlink fs/namei.c:4660 [inline] __x64_sys_symlink+0x7a/0x90 fs/namei.c:4660 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK> The following loop is located right above 'if' statement. for (i = count-1; i >= 0; i--) { /* is more than half of this entry in 2nd half of the block? */ if (size + map[i].size/2 > blocksize/2) break; size += map[i].size; move++; } 'i' in this case could go down to -1, in which case sum of active entries wouldn't exceed half the block size, but previous behaviour would also do split in half if sum would exceed at the very last block, which in case of having too many long name files in a single block could lead to out-of-bounds access and following use-after-free. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Cc: stable(a)vger.kernel.org Fixes: 5872331b3d91 ("ext4: fix potential negative array index in do_split()") Signed-off-by: Artem Sadovnikov <a.sadovnikov(a)ispras.ru> --- fs/ext4/namei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index cb5cb33b1d91..e9712e64ec8f 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1971,7 +1971,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, * split it in half by count; each resulting block will have at least * half the space free. */ - if (i > 0) + if (i >= 0) split = count - move; else split = count/2; -- 2.43.0

2 months

3
4
0 0

[PATCH v4 5/6] media: mt9m114: Fix deadlock in get_frame_interval/set_frame_interval

by Mathis Foerst

Getting / Setting the frame interval using the V4L2 subdev pad ops get_frame_interval/set_frame_interval causes a deadlock, as the subdev state is locked in the [1] but also in the driver itself. In [2] it's described that the caller is responsible to acquire and release the lock in this case. Therefore, acquiring the lock in the driver is wrong. Remove the lock acquisitions/releases from mt9m114_ifp_get_frame_interval() and mt9m114_ifp_set_frame_interval(). [1] drivers/media/v4l2-core/v4l2-subdev.c - line 1129 [2] Documentation/driver-api/media/v4l2-subdev.rst Fixes: 24d756e914fc ("media: i2c: Add driver for onsemi MT9M114 camera sensor") Cc: stable(a)vger.kernel.org Signed-off-by: Mathis Foerst <mathis.foerst(a)mt.com> --- drivers/media/i2c/mt9m114.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/media/i2c/mt9m114.c b/drivers/media/i2c/mt9m114.c index 65b9124e464f..79c97ab19be9 100644 --- a/drivers/media/i2c/mt9m114.c +++ b/drivers/media/i2c/mt9m114.c @@ -1644,13 +1644,9 @@ static int mt9m114_ifp_get_frame_interval(struct v4l2_subdev *sd, if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) return -EINVAL; - mutex_lock(sensor->ifp.hdl.lock); - ival->numerator = 1; ival->denominator = sensor->ifp.frame_rate; - mutex_unlock(sensor->ifp.hdl.lock); - return 0; } @@ -1669,8 +1665,6 @@ static int mt9m114_ifp_set_frame_interval(struct v4l2_subdev *sd, if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) return -EINVAL; - mutex_lock(sensor->ifp.hdl.lock); - if (ival->numerator != 0 && ival->denominator != 0) sensor->ifp.frame_rate = min_t(unsigned int, ival->denominator / ival->numerator, @@ -1684,8 +1678,6 @@ static int mt9m114_ifp_set_frame_interval(struct v4l2_subdev *sd, if (sensor->streaming) ret = mt9m114_set_frame_rate(sensor); - mutex_unlock(sensor->ifp.hdl.lock); - return ret; } -- 2.34.1

2 months

2
1
0 0

[PATCH 5.15.y] scsi: lpfc: Fix null pointer dereference after failing to issue FLOGI and PLOGI

by bin.lan.cn＠windriver.com

From: James Smart <jsmart2021(a)gmail.com> [ Upstream commit 577a942df3de2666f6947bdd3a5c9e8d30073424 ] If lpfc_issue_els_flogi() fails and returns non-zero status, the node reference count is decremented to trigger the release of the nodelist structure. However, if there is a prior registration or dev-loss-evt work pending, the node may be released prematurely. When dev-loss-evt completes, the released node is referenced causing a use-after-free null pointer dereference. Similarly, when processing non-zero ELS PLOGI completion status in lpfc_cmpl_els_plogi(), the ndlp flags are checked for a transport registration before triggering node removal. If dev-loss-evt work is pending, the node may be released prematurely and a subsequent call to lpfc_dev_loss_tmo_handler() results in a use after free ndlp dereference. Add test for pending dev-loss before decrementing the node reference count for FLOGI, PLOGI, PRLI, and ADISC handling. Link: https://lore.kernel.org/r/20220412222008.126521-9-jsmart2021@gmail.com Co-developed-by: Justin Tee <justin.tee(a)broadcom.com> Signed-off-by: Justin Tee <justin.tee(a)broadcom.com> Signed-off-by: James Smart <jsmart2021(a)gmail.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> [Minor context change fixed.] Signed-off-by: Bin Lan <bin.lan.cn(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Build test passed. --- drivers/scsi/lpfc/lpfc_els.c | 51 +++++++++++++++++++++++++----------- 1 file changed, 35 insertions(+), 16 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 5f44a0763f37..134d56bd00da 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -1517,10 +1517,13 @@ lpfc_initial_flogi(struct lpfc_vport *vport) } if (lpfc_issue_els_flogi(vport, ndlp, 0)) { - /* This decrement of reference count to node shall kick off - * the release of the node. + /* A node reference should be retained while registered with a + * transport or dev-loss-evt work is pending. + * Otherwise, decrement node reference to trigger release. */ - lpfc_nlp_put(ndlp); + if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD)) && + !(ndlp->nlp_flag & NLP_IN_DEV_LOSS)) + lpfc_nlp_put(ndlp); return 0; } return 1; @@ -1563,10 +1566,13 @@ lpfc_initial_fdisc(struct lpfc_vport *vport) } if (lpfc_issue_els_fdisc(vport, ndlp, 0)) { - /* decrement node reference count to trigger the release of - * the node. + /* A node reference should be retained while registered with a + * transport or dev-loss-evt work is pending. + * Otherwise, decrement node reference to trigger release. */ - lpfc_nlp_put(ndlp); + if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD)) && + !(ndlp->nlp_flag & NLP_IN_DEV_LOSS)) + lpfc_nlp_put(ndlp); return 0; } return 1; @@ -1967,6 +1973,7 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, struct lpfc_dmabuf *prsp; int disc; struct serv_parm *sp = NULL; + bool release_node = false; /* we pass cmdiocb to state machine which needs rspiocb as well */ cmdiocb->context_un.rsp_iocb = rspiocb; @@ -2047,19 +2054,21 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, spin_unlock_irq(&ndlp->lock); goto out; } - spin_unlock_irq(&ndlp->lock); /* No PLOGI collision and the node is not registered with the * scsi or nvme transport. It is no longer an active node. Just * start the device remove process. */ if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD))) { - spin_lock_irq(&ndlp->lock); ndlp->nlp_flag &= ~NLP_NPR_2B_DISC; - spin_unlock_irq(&ndlp->lock); + if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS)) + release_node = true; + } + spin_unlock_irq(&ndlp->lock); + + if (release_node) lpfc_disc_state_machine(vport, ndlp, cmdiocb, NLP_EVT_DEVICE_RM); - } } else { /* Good status, call state machine */ prsp = list_entry(((struct lpfc_dmabuf *) @@ -2269,6 +2278,7 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, struct lpfc_nodelist *ndlp; char *mode; u32 loglevel; + bool release_node = false; /* we pass cmdiocb to state machine which needs rspiocb as well */ cmdiocb->context_un.rsp_iocb = rspiocb; @@ -2335,14 +2345,18 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, * it is no longer an active node. Otherwise devloss * handles the final cleanup. */ + spin_lock_irq(&ndlp->lock); if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD)) && !ndlp->fc4_prli_sent) { - spin_lock_irq(&ndlp->lock); ndlp->nlp_flag &= ~NLP_NPR_2B_DISC; - spin_unlock_irq(&ndlp->lock); + if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS)) + release_node = true; + } + spin_unlock_irq(&ndlp->lock); + + if (release_node) lpfc_disc_state_machine(vport, ndlp, cmdiocb, NLP_EVT_DEVICE_RM); - } } else { /* Good status, call state machine. However, if another * PRLI is outstanding, don't call the state machine @@ -2713,6 +2727,7 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, IOCB_t *irsp; struct lpfc_nodelist *ndlp; int disc; + bool release_node = false; /* we pass cmdiocb to state machine which needs rspiocb as well */ cmdiocb->context_un.rsp_iocb = rspiocb; @@ -2771,13 +2786,17 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, * transport, it is no longer an active node. Otherwise * devloss handles the final cleanup. */ + spin_lock_irq(&ndlp->lock); if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD))) { - spin_lock_irq(&ndlp->lock); ndlp->nlp_flag &= ~NLP_NPR_2B_DISC; - spin_unlock_irq(&ndlp->lock); + if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS)) + release_node = true; + } + spin_unlock_irq(&ndlp->lock); + + if (release_node) lpfc_disc_state_machine(vport, ndlp, cmdiocb, NLP_EVT_DEVICE_RM); - } } else /* Good status, call state machine */ lpfc_disc_state_machine(vport, ndlp, cmdiocb, -- 2.34.1

2 months

2
1
0 0

[REGRESSION] stable-rc/linux-5.15.y: (build) variable 'is_redirect' is used uninitialized whenever 'if' conditi...

by KernelCI bot

Hello, New build issue found on stable-rc/linux-5.15.y: --- variable 'is_redirect' is used uninitialized whenever 'if' condition is true [-Werror,-Wsometimes-uninitialized] in net/sched/act_mirred.o (net/sched/act_mirred.c) [logspec:kbuild,kbuild.compiler.error] --- - dashboard: https://d.kernelci.org/i/maestro:72f9cc14e764580fd20bda28956c2ddf82023571 - giturl: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git - commit HEAD: dd688b41d9038dbc86718bae12ed995d596c1de5 Log excerpt: ===================================================== net/sched/act_mirred.c:264:6: error: variable 'is_redirect' is used uninitialized whenever 'if' condition is true [-Werror,-Wsometimes-uninitialized] 264 | if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/compiler.h:78:22: note: expanded from macro 'unlikely' 78 | # define unlikely(x) __builtin_expect(!!(x), 0) | ^ net/sched/act_mirred.c:331:6: note: uninitialized use occurs here 331 | if (is_redirect) | ^~~~~~~~~~~ net/sched/act_mirred.c:264:2: note: remove the 'if' if its condition is always false 264 | if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 265 | net_notice_ratelimited("tc mirred to Houston: device %s is down\n", | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 266 | dev->name); | ~~~~~~~~~~~ 267 | goto err_cant_do; | ~~~~~~~~~~~~~~~~~ 268 | } | ~ net/sched/act_mirred.c:264:6: error: variable 'is_redirect' is used uninitialized whenever '||' condition is true [-Werror,-Wsometimes-uninitialized] 264 | if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/compiler.h:78:22: note: expanded from macro 'unlikely' 78 | # define unlikely(x) __builtin_expect(!!(x), 0) | ^~~~~~~~~~~~~~~~~~~~~~~~~~ net/sched/act_mirred.c:331:6: note: uninitialized use occurs here 331 | if (is_redirect) | ^~~~~~~~~~~ net/sched/act_mirred.c:264:6: note: remove the '||' if its condition is always false 264 | if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/compiler.h:78:22: note: expanded from macro 'unlikely' 78 | # define unlikely(x) __builtin_expect(!!(x), 0) | ^ net/sched/act_mirred.c:259:6: error: variable 'is_redirect' is used uninitialized whenever 'if' condition is true [-Werror,-Wsometimes-uninitialized] 259 | if (unlikely(!dev)) { | ^~~~~~~~~~~~~~ ./include/linux/compiler.h:78:22: note: expanded from macro 'unlikely' 78 | # define unlikely(x) __builtin_expect(!!(x), 0) | ^~~~~~~~~~~~~~~~~~~~~~~~~~ net/sched/act_mirred.c:331:6: note: uninitialized use occurs here 331 | if (is_redirect) | ^~~~~~~~~~~ net/sched/act_mirred.c:259:2: note: remove the 'if' if its condition is always false 259 | if (unlikely(!dev)) { | ^~~~~~~~~~~~~~~~~~~~~ 260 | pr_notice_once("tc mirred: target device is gone\n"); | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 261 | goto err_cant_do; | ~~~~~~~~~~~~~~~~~ 262 | } | ~ net/sched/act_mirred.c:237:18: note: initialize the variable 'is_redirect' to silence this warning 237 | bool is_redirect; | ^ | = 0 3 errors generated. ===================================================== # Builds where the incident occurred: ## defconfig+allmodconfig+CONFIG_FRAME_WARN=2048 on (arm): - compiler: clang-17 - dashboard: https://d.kernelci.org/build/maestro:6808fe8b43948caad9509059 #kernelci issue maestro:72f9cc14e764580fd20bda28956c2ddf82023571 Reported-by: kernelci.org bot <bot(a)kernelci.org> -- This is an experimental report format. Please send feedback in! Talk to us at kernelci(a)lists.linux.dev Made with love by the KernelCI team - https://kernelci.org

2 months

1
0
0 0

[PATCH v2 1/2] drm/nouveau: Fix WARN_ON in nouveau_fence_context_kill()

by Philipp Stanner

Nouveau is mostly designed in a way that it's expected that fences only ever get signaled through nouveau_fence_signal(). However, in at least one other place, nouveau_fence_done(), can signal fences, too. If that happens (race) a signaled fence remains in the pending list for a while, until it gets removed by nouveau_fence_update(). Should nouveau_fence_context_kill() run in the meantime, this would be a bug because the function would attempt to set an error code on an already signaled fence. Have nouveau_fence_context_kill() check for a fence being signaled. Cc: <stable(a)vger.kernel.org> # v5.10+ Fixes: ea13e5abf807 ("drm/nouveau: signal pending fences when channel has been killed") Suggested-by: Christian König <christian.koenig(a)amd.com> Signed-off-by: Philipp Stanner <phasta(a)kernel.org> --- drivers/gpu/drm/nouveau/nouveau_fence.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 7622587f149e..6ded8c2b6d3b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -90,7 +90,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error) while (!list_empty(&fctx->pending)) { fence = list_entry(fctx->pending.next, typeof(*fence), head); - if (error) + if (error && !dma_fence_is_signaled_locked(&fence->base)) dma_fence_set_error(&fence->base, error); if (nouveau_fence_signal(fence)) -- 2.48.1

2 months

2
1
0 0

Potential Linux Crash: WARNING in ext4_mb_load_buddy_gfp in linux6.12.24(longterm maintenance)

by ffhgfv

Hello, I found a potential bug titled " WARNING in ext4_mb_load_buddy_gfp " with modified syzkaller in the Linux6.12.24(longterm maintenance, last updated on April 20, 2025). It seems to be a problem with the ext4 subsystem. Unfortunately, I am unable to reproduce this bug. If you fix this issue, please add the following tag to the commit: Reported-by: Jianzhou Zhao <xnxc22xnxc22(a)qq.com>, xingwei lee <xrivendell7(a)gmail.com>,Penglei Jiang <superman.xpt(a)gmail.com> The commit of the kernel is : b6efa8ce222e58cfe2bbaa4e3329818c2b4bd74e kernel config: https://syzkaller.appspot.com/text?tag=KernelConfig&x=55f8591b98dd132 compiler: gcc version 11.4.0 ------------[ cut here ]----------------------------------------- TITLE: WARNING in ext4_mb_load_buddy_gfp ------------[ cut here ]------------ WARNING: CPU: 0 PID: 96 at mm/page_alloc.c:4240 __alloc_pages_slowpath mm/page_alloc.c:4240 [inline] WARNING: CPU: 0 PID: 96 at mm/page_alloc.c:4240 __alloc_pages_noprof+0x1a1d/0x21f0 mm/page_alloc.c:4767 Modules linked in: CPU: 0 UID: 0 PID: 96 Comm: kswapd0 Not tainted 6.12.24 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:__alloc_pages_slowpath mm/page_alloc.c:4240 [inline] RIP: 0010:__alloc_pages_noprof+0x1a1d/0x21f0 mm/page_alloc.c:4767 Code: 89 fa 48 c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85 a2 07 00 00 f6 43 2d 08 0f 84 bd ea ff ff 90 <0f> 0b 90 e9 b4 ea ff ff 65 8b 15 70 e5 23 7e 83 fa 07 0f 87 56 06 RSP: 0000:ffffc90001376e18 EFLAGS: 00010202 RAX: 0000000000000007 RBX: ffff888042ac4a00 RCX: ffffc90001376f44 RDX: 0000000000000000 RSI: 1ffff9200026edb0 RDI: ffff888042ac4a2c RBP: ffff88803fffbc80 R08: 000000000000699a R09: 0000000000000400 R10: ffff88807ffda357 R11: 0000000000000000 R12: 0000000000000000 R13: ffffffffffffffff R14: 0000000000048c40 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff88802b800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f4969a4e7b0 CR3: 000000002719c000 CR4: 0000000000752ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <task> alloc_pages_mpol_noprof+0x2b6/0x600 mm/mempolicy.c:2269 folio_alloc_noprof+0x21/0xc0 mm/mempolicy.c:2356 filemap_alloc_folio_noprof+0x3d2/0x470 mm/filemap.c:1010 __filemap_get_folio+0x57f/0xb00 mm/filemap.c:1952 ext4_mb_load_buddy_gfp+0x74d/0x10c0 fs/ext4/mballoc.c:1640 ext4_discard_preallocations+0x539/0xf00 fs/ext4/mballoc.c:5592 ext4_clear_inode+0x3d/0x230 fs/ext4/super.c:1523 ext4_evict_inode+0x243/0x18c0 fs/ext4/inode.c:323 evict+0x3ef/0x940 fs/inode.c:725 dispose_list+0x117/0x1e0 fs/inode.c:774 prune_icache_sb+0xeb/0x150 fs/inode.c:963 super_cache_scan+0x37f/0x570 fs/super.c:223 do_shrink_slab+0x44b/0x1190 mm/shrinker.c:437 shrink_slab_memcg mm/shrinker.c:550 [inline] shrink_slab+0xb61/0x12a0 mm/shrinker.c:628 shrink_one+0x4ad/0x7c0 mm/vmscan.c:4835 shrink_many mm/vmscan.c:4896 [inline] lru_gen_shrink_node mm/vmscan.c:4974 [inline] shrink_node+0x2420/0x3890 mm/vmscan.c:5954 kswapd_shrink_node mm/vmscan.c:6782 [inline] balance_pgdat+0xbe5/0x18c0 mm/vmscan.c:6974 kswapd+0x702/0xd50 mm/vmscan.c:7243 kthread+0x2c7/0x3b0 kernel/kthread.c:389 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:152 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </task> ================================================================== I hope it helps. Best regards Jianzhou Zhao</superman.xpt(a)gmail.com></xrivendell7(a)gmail.com></xnxc22xnxc22(a)qq.com>

2 months

1
0
0 0

[tip: x86/urgent] x86/mm: Fix _pgd_alloc() for Xen PV mode

by tip-bot2 for Juergen Gross

The following commit has been merged into the x86/urgent branch of tip: Commit-ID: 4ce385f56434f3810ef103e1baea357ddcc6667e Gitweb: https://git.kernel.org/tip/4ce385f56434f3810ef103e1baea357ddcc6667e Author: Juergen Gross <jgross(a)suse.com> AuthorDate: Tue, 22 Apr 2025 15:17:17 +02:00 Committer: Dave Hansen <dave.hansen(a)linux.intel.com> CommitterDate: Wed, 23 Apr 2025 07:49:14 -07:00 x86/mm: Fix _pgd_alloc() for Xen PV mode Recently _pgd_alloc() was switched from using __get_free_pages() to pagetable_alloc_noprof(), which might return a compound page in case the allocation order is larger than 0. On x86 this will be the case if CONFIG_MITIGATION_PAGE_TABLE_ISOLATION is set, even if PTI has been disabled at runtime. When running as a Xen PV guest (this will always disable PTI), using a compound page for a PGD will result in VM_BUG_ON_PGFLAGS being triggered when the Xen code tries to pin the PGD. Fix the Xen issue together with the not needed 8k allocation for a PGD with PTI disabled by replacing PGD_ALLOCATION_ORDER with an inline helper returning the needed order for PGD allocations. Fixes: a9b3c355c2e6 ("asm-generic: pgalloc: provide generic __pgd_{alloc,free}") Reported-by: Petr Vaněk <arkamar(a)atlas.cz> Signed-off-by: Juergen Gross <jgross(a)suse.com> Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> Tested-by: Petr Vaněk <arkamar(a)atlas.cz> Cc:stable@vger.kernel.org Link: https://lore.kernel.org/all/20250422131717.25724-1-jgross%40suse.com --- arch/x86/include/asm/pgalloc.h | 19 +++++++++++-------- arch/x86/kernel/machine_kexec_32.c | 4 ++-- arch/x86/mm/pgtable.c | 4 ++-- arch/x86/platform/efi/efi_64.c | 4 ++-- 4 files changed, 17 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index a331475..c88691b 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -6,6 +6,8 @@ #include <linux/mm.h> /* for struct page */ #include <linux/pagemap.h> +#include <asm/cpufeature.h> + #define __HAVE_ARCH_PTE_ALLOC_ONE #define __HAVE_ARCH_PGD_FREE #include <asm-generic/pgalloc.h> @@ -29,16 +31,17 @@ static inline void paravirt_release_pud(unsigned long pfn) {} static inline void paravirt_release_p4d(unsigned long pfn) {} #endif -#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* - * Instead of one PGD, we acquire two PGDs. Being order-1, it is - * both 8k in size and 8k-aligned. That lets us just flip bit 12 - * in a pointer to swap between the two 4k halves. + * In case of Page Table Isolation active, we acquire two PGDs instead of one. + * Being order-1, it is both 8k in size and 8k-aligned. That lets us just + * flip bit 12 in a pointer to swap between the two 4k halves. */ -#define PGD_ALLOCATION_ORDER 1 -#else -#define PGD_ALLOCATION_ORDER 0 -#endif +static inline unsigned int pgd_allocation_order(void) +{ + if (cpu_feature_enabled(X86_FEATURE_PTI)) + return 1; + return 0; +} /* * Allocate and free page tables. diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 8026516..1f32530 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -42,7 +42,7 @@ static void load_segments(void) static void machine_kexec_free_page_tables(struct kimage *image) { - free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER); + free_pages((unsigned long)image->arch.pgd, pgd_allocation_order()); image->arch.pgd = NULL; #ifdef CONFIG_X86_PAE free_page((unsigned long)image->arch.pmd0); @@ -59,7 +59,7 @@ static void machine_kexec_free_page_tables(struct kimage *image) static int machine_kexec_alloc_page_tables(struct kimage *image) { image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - PGD_ALLOCATION_ORDER); + pgd_allocation_order()); #ifdef CONFIG_X86_PAE image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL); image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index a05fcdd..f7ae44d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -360,7 +360,7 @@ static inline pgd_t *_pgd_alloc(struct mm_struct *mm) * We allocate one page for pgd. */ if (!SHARED_KERNEL_PMD) - return __pgd_alloc(mm, PGD_ALLOCATION_ORDER); + return __pgd_alloc(mm, pgd_allocation_order()); /* * Now PAE kernel is not running as a Xen domain. We can allocate @@ -380,7 +380,7 @@ static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pgd_t *_pgd_alloc(struct mm_struct *mm) { - return __pgd_alloc(mm, PGD_ALLOCATION_ORDER); + return __pgd_alloc(mm, pgd_allocation_order()); } static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index ac57259..a4b4ebd 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -73,7 +73,7 @@ int __init efi_alloc_page_tables(void) gfp_t gfp_mask; gfp_mask = GFP_KERNEL | __GFP_ZERO; - efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER); + efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, pgd_allocation_order()); if (!efi_pgd) goto fail; @@ -96,7 +96,7 @@ free_p4d: if (pgtable_l5_enabled()) free_page((unsigned long)pgd_page_vaddr(*pgd)); free_pgd: - free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); + free_pages((unsigned long)efi_pgd, pgd_allocation_order()); fail: return -ENOMEM; }

2 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror April 2025