July 2025 - Linux-stable-mirror

[PATCH] drm/nouveau: Do not fail module init on debugfs errors

by Aaron Thompson

From: Aaron Thompson <dev(a)aaront.org> If CONFIG_DEBUG_FS is enabled, nouveau_drm_init() returns an error if it fails to create the "nouveau" directory in debugfs. One case where that will happen is when debugfs access is restricted by CONFIG_DEBUG_FS_ALLOW_NONE or by the boot parameter debugfs=off, which cause the debugfs APIs to return -EPERM. So just ignore errors from debugfs. Note that nouveau_debugfs_root may be an error now, but that is a standard pattern for debugfs. From include/linux/debugfs.h: "NOTE: it's expected that most callers should _ignore_ the errors returned by this function. Other debugfs functions handle the fact that the "dentry" passed to them could be an error and they don't crash in that case. Drivers should generally work fine even if debugfs fails to init anyway." Fixes: 97118a1816d2 ("drm/nouveau: create module debugfs root") Cc: stable(a)vger.kernel.org Signed-off-by: Aaron Thompson <dev(a)aaront.org> --- drivers/gpu/drm/nouveau/nouveau_debugfs.c | 6 +----- drivers/gpu/drm/nouveau/nouveau_debugfs.h | 5 ++--- drivers/gpu/drm/nouveau/nouveau_drm.c | 4 +--- 3 files changed, 4 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c index 200e65a7cefc..c7869a639bef 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c @@ -314,14 +314,10 @@ nouveau_debugfs_fini(struct nouveau_drm *drm) drm->debugfs = NULL; } -int +void nouveau_module_debugfs_init(void) { nouveau_debugfs_root = debugfs_create_dir("nouveau", NULL); - if (IS_ERR(nouveau_debugfs_root)) - return PTR_ERR(nouveau_debugfs_root); - - return 0; } void diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.h b/drivers/gpu/drm/nouveau/nouveau_debugfs.h index b7617b344ee2..d05ed0e641c4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.h +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.h @@ -24,7 +24,7 @@ extern void nouveau_debugfs_fini(struct nouveau_drm *); extern struct dentry *nouveau_debugfs_root; -int nouveau_module_debugfs_init(void); +void nouveau_module_debugfs_init(void); void nouveau_module_debugfs_fini(void); #else static inline void @@ -42,10 +42,9 @@ nouveau_debugfs_fini(struct nouveau_drm *drm) { } -static inline int +static inline void nouveau_module_debugfs_init(void) { - return 0; } static inline void diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 0c82a63cd49d..1527b801f013 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1461,9 +1461,7 @@ nouveau_drm_init(void) if (!nouveau_modeset) return 0; - ret = nouveau_module_debugfs_init(); - if (ret) - return ret; + nouveau_module_debugfs_init(); #ifdef CONFIG_NOUVEAU_PLATFORM_DRIVER platform_driver_register(&nouveau_platform_driver); base-commit: d0b3b7b22dfa1f4b515fd3a295b3fd958f9e81af -- 2.39.5

6 months

3
2
0 0

[PATCH v6 01/12] platform/x86/intel/pmt: fix a crashlog NULL pointer access

by Michael J. Ruhl

Usage of the intel_pmt_read() for binary sysfs, requires a pcidev. The current use of the endpoint value is only valid for telemetry endpoint usage. Without the ep, the crashlog usage causes the following NULL pointer exception: BUG: kernel NULL pointer dereference, address: 0000000000000000 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:intel_pmt_read+0x3b/0x70 [pmt_class] Code: Call Trace: <TASK> ? sysfs_kf_bin_read+0xc0/0xe0 kernfs_fop_read_iter+0xac/0x1a0 vfs_read+0x26d/0x350 ksys_read+0x6b/0xe0 __x64_sys_read+0x1d/0x30 x64_sys_call+0x1bc8/0x1d70 do_syscall_64+0x6d/0x110 Augment struct intel_pmt_entry with a pointer to the pcidev to avoid the NULL pointer exception. Reviewed-by: Tejas Upadhyay <tejas.upadhyay(a)intel.com> Fixes: 045a513040cc ("platform/x86/intel/pmt: Use PMT callbacks") Cc: <stable(a)vger.kernel.org> Signed-off-by: Michael J. Ruhl <michael.j.ruhl(a)intel.com> --- drivers/platform/x86/intel/pmt/class.c | 3 ++- drivers/platform/x86/intel/pmt/class.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c index 7233b654bbad..d046e8752173 100644 --- a/drivers/platform/x86/intel/pmt/class.c +++ b/drivers/platform/x86/intel/pmt/class.c @@ -97,7 +97,7 @@ intel_pmt_read(struct file *filp, struct kobject *kobj, if (count > entry->size - off) count = entry->size - off; - count = pmt_telem_read_mmio(entry->ep->pcidev, entry->cb, entry->header.guid, buf, + count = pmt_telem_read_mmio(entry->pcidev, entry->cb, entry->header.guid, buf, entry->base, off, count); return count; @@ -252,6 +252,7 @@ static int intel_pmt_populate_entry(struct intel_pmt_entry *entry, return -EINVAL; } + entry->pcidev = pci_dev; entry->guid = header->guid; entry->size = header->size; entry->cb = ivdev->priv_data; diff --git a/drivers/platform/x86/intel/pmt/class.h b/drivers/platform/x86/intel/pmt/class.h index b2006d57779d..f6ce80c4e051 100644 --- a/drivers/platform/x86/intel/pmt/class.h +++ b/drivers/platform/x86/intel/pmt/class.h @@ -39,6 +39,7 @@ struct intel_pmt_header { struct intel_pmt_entry { struct telem_endpoint *ep; + struct pci_dev *pcidev; struct intel_pmt_header header; struct bin_attribute pmt_bin_attr; struct kobject *kobj; -- 2.49.0

6 months

1
0
0 0

+ kasan-remove-kasan_find_vm_area-to-prevent-possible-deadlock.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: kasan: remove kasan_find_vm_area() to prevent possible deadlock has been added to the -mm mm-hotfixes-unstable branch. Its filename is kasan-remove-kasan_find_vm_area-to-prevent-possible-deadlock.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: Yeoreum Yun <yeoreum.yun(a)arm.com> Subject: kasan: remove kasan_find_vm_area() to prevent possible deadlock Date: Thu, 3 Jul 2025 19:10:18 +0100 find_vm_area() couldn't be called in atomic_context. If find_vm_area() is called to reports vm area information, kasan can trigger deadlock like: CPU0 CPU1 vmalloc(); alloc_vmap_area(); spin_lock(&vn->busy.lock) spin_lock_bh(&some_lock); <interrupt occurs> <in softirq> spin_lock(&some_lock); <access invalid address> kasan_report(); print_report(); print_address_description(); kasan_find_vm_area(); find_vm_area(); spin_lock(&vn->busy.lock) // deadlock! To prevent possible deadlock while kasan reports, remove kasan_find_vm_area(). Link: https://lkml.kernel.org/r/20250703181018.580833-1-yeoreum.yun@arm.com Fixes: c056a364e954 ("kasan: print virtual mapping info in reports") Signed-off-by: Yeoreum Yun <yeoreum.yun(a)arm.com> Reported-by: Yunseong Kim <ysk(a)kzalloc.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Andrey Konovalov <andreyknvl(a)gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Cc: Byungchul Park <byungchul(a)sk.com> Cc: Dmitriy Vyukov <dvyukov(a)google.com> Cc: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Vincenzo Frascino <vincenzo.frascino(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kasan/report.c | 45 +------------------------------------------- 1 file changed, 2 insertions(+), 43 deletions(-) --- a/mm/kasan/report.c~kasan-remove-kasan_find_vm_area-to-prevent-possible-deadlock +++ a/mm/kasan/report.c @@ -370,36 +370,6 @@ static inline bool init_task_stack_addr( sizeof(init_thread_union.stack)); } -/* - * This function is invoked with report_lock (a raw_spinlock) held. A - * PREEMPT_RT kernel cannot call find_vm_area() as it will acquire a sleeping - * rt_spinlock. - * - * For !RT kernel, the PROVE_RAW_LOCK_NESTING config option will print a - * lockdep warning for this raw_spinlock -> spinlock dependency. This config - * option is enabled by default to ensure better test coverage to expose this - * kind of RT kernel problem. This lockdep splat, however, can be suppressed - * by using DEFINE_WAIT_OVERRIDE_MAP() if it serves a useful purpose and the - * invalid PREEMPT_RT case has been taken care of. - */ -static inline struct vm_struct *kasan_find_vm_area(void *addr) -{ - static DEFINE_WAIT_OVERRIDE_MAP(vmalloc_map, LD_WAIT_SLEEP); - struct vm_struct *va; - - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - return NULL; - - /* - * Suppress lockdep warning and fetch vmalloc area of the - * offending address. - */ - lock_map_acquire_try(&vmalloc_map); - va = find_vm_area(addr); - lock_map_release(&vmalloc_map); - return va; -} - static void print_address_description(void *addr, u8 tag, struct kasan_report_info *info) { @@ -429,19 +399,8 @@ static void print_address_description(vo } if (is_vmalloc_addr(addr)) { - struct vm_struct *va = kasan_find_vm_area(addr); - - if (va) { - pr_err("The buggy address belongs to the virtual mapping at\n" - " [%px, %px) created by:\n" - " %pS\n", - va->addr, va->addr + va->size, va->caller); - pr_err("\n"); - - page = vmalloc_to_page(addr); - } else { - pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr); - } + pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr); + page = vmalloc_to_page(addr); } if (page) { _ Patches currently in -mm which might be from yeoreum.yun(a)arm.com are kasan-remove-kasan_find_vm_area-to-prevent-possible-deadlock.patch

6 months

1
0
0 0

[PATCH 6.12.y 0/3] r8169: add support for RTL8125D

by mathieu.tortuyaux＠gmail.com

From: Mathieu Tortuyaux <mtortuyaux(a)microsoft.com> Hi, This backports support for Realtek device 0x688 on Kernel 6.12.y: * Tested in Flatcar CI w/ Kernel 6.12.35 on qemu (for regression): https://github.com/flatcar/scripts/pull/3006 * The user requesting this support has confirmed correct behavior: https://github.com/flatcar/Flatcar/issues/1749#issuecomment-3005483988 The two other commits ("net: phy: realtek: merge the drivers for internal NBase-T PHY's" and "net: phy: realtek: add RTL8125D-internal PHY") are required to add support here as well, otherwise it fails with: ``` $ dmesg ... r8169 ... : no dedicated PHY driver found for PHY ID 0x001cc841 ... ``` Thanks and have a great day, Mathieu (@tormath1) Heiner Kallweit (3): r8169: add support for RTL8125D net: phy: realtek: merge the drivers for internal NBase-T PHY's net: phy: realtek: add RTL8125D-internal PHY drivers/net/ethernet/realtek/r8169.h | 1 + drivers/net/ethernet/realtek/r8169_main.c | 23 +++++--- .../net/ethernet/realtek/r8169_phy_config.c | 10 ++++ drivers/net/phy/realtek.c | 54 +++++++++++++++---- 4 files changed, 71 insertions(+), 17 deletions(-) -- 2.49.0

6 months

3
14
0 0

[PATCH 6.12.y] mm/vmalloc: fix data race in show_numa_info()

by Jeongjun Park

commit 5c5f0468d172ddec2e333d738d2a1f85402cf0bc upstream. The following data-race was found in show_numa_info(): ================================================================== BUG: KCSAN: data-race in vmalloc_info_show / vmalloc_info_show read to 0xffff88800971fe30 of 4 bytes by task 8289 on cpu 0: show_numa_info mm/vmalloc.c:4936 [inline] vmalloc_info_show+0x5a8/0x7e0 mm/vmalloc.c:5016 seq_read_iter+0x373/0xb40 fs/seq_file.c:230 proc_reg_read_iter+0x11e/0x170 fs/proc/inode.c:299 .... write to 0xffff88800971fe30 of 4 bytes by task 8287 on cpu 1: show_numa_info mm/vmalloc.c:4934 [inline] vmalloc_info_show+0x38f/0x7e0 mm/vmalloc.c:5016 seq_read_iter+0x373/0xb40 fs/seq_file.c:230 proc_reg_read_iter+0x11e/0x170 fs/proc/inode.c:299 .... value changed: 0x0000008f -> 0x00000000 ================================================================== According to this report,there is a read/write data-race because m->private is accessible to multiple CPUs. To fix this, instead of allocating the heap in proc_vmalloc_init() and passing the heap address to m->private, vmalloc_info_show() should allocate the heap. Link: https://lkml.kernel.org/r/20250508165620.15321-1-aha310510@gmail.com Fixes: 8e1d743 ("mm: vmalloc: support multiple nodes in vmallocinfo") Signed-off-by: Jeongjun Park <aha310510(a)gmail.com> Suggested-by: Eric Dumazet <edumazet(a)google.com> Suggested-by: Andrew Morton <akpm(a)linux-foundation.org> Reviewed-by: "Uladzislau Rezki (Sony)" <urezki(a)gmail.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmalloc.c | 63 +++++++++++++++++++++++++++++----------------------- 1 file changed, 35 insertions(+), 28 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index cc04e501b1c5..7888600b6a79 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3095,7 +3095,7 @@ static void clear_vm_uninitialized_flag(struct vm_struct *vm) /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. - * Pair with smp_rmb() in show_numa_info(). + * Pair with smp_rmb() in vread_iter() and vmalloc_info_show(). */ smp_wmb(); vm->flags &= ~VM_UNINITIALIZED; @@ -4938,28 +4938,29 @@ bool vmalloc_dump_obj(void *object) #endif #ifdef CONFIG_PROC_FS -static void show_numa_info(struct seq_file *m, struct vm_struct *v) -{ - if (IS_ENABLED(CONFIG_NUMA)) { - unsigned int nr, *counters = m->private; - unsigned int step = 1U << vm_area_page_order(v); - if (!counters) - return; +/* + * Print number of pages allocated on each memory node. + * + * This function can only be called if CONFIG_NUMA is enabled + * and VM_UNINITIALIZED bit in v->flags is disabled. + */ +static void show_numa_info(struct seq_file *m, struct vm_struct *v, + unsigned int *counters) +{ + unsigned int nr; + unsigned int step = 1U << vm_area_page_order(v); - if (v->flags & VM_UNINITIALIZED) - return; - /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ - smp_rmb(); + if (!counters) + return; - memset(counters, 0, nr_node_ids * sizeof(unsigned int)); + memset(counters, 0, nr_node_ids * sizeof(unsigned int)); - for (nr = 0; nr < v->nr_pages; nr += step) - counters[page_to_nid(v->pages[nr])] += step; - for_each_node_state(nr, N_HIGH_MEMORY) - if (counters[nr]) - seq_printf(m, " N%u=%u", nr, counters[nr]); - } + for (nr = 0; nr < v->nr_pages; nr += step) + counters[page_to_nid(v->pages[nr])] += step; + for_each_node_state(nr, N_HIGH_MEMORY) + if (counters[nr]) + seq_printf(m, " N%u=%u", nr, counters[nr]); } static void show_purge_info(struct seq_file *m) @@ -4987,6 +4988,10 @@ static int vmalloc_info_show(struct seq_file *m, void *p) struct vmap_area *va; struct vm_struct *v; int i; + unsigned int *counters; + + if (IS_ENABLED(CONFIG_NUMA)) + counters = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; @@ -5003,6 +5008,11 @@ static int vmalloc_info_show(struct seq_file *m, void *p) } v = va->vm; + if (v->flags & VM_UNINITIALIZED) + continue; + + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ + smp_rmb(); seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); @@ -5037,7 +5047,9 @@ static int vmalloc_info_show(struct seq_file *m, void *p) if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); - show_numa_info(m, v); + if (IS_ENABLED(CONFIG_NUMA)) + show_numa_info(m, v, counters); + seq_putc(m, '\n'); } spin_unlock(&vn->busy.lock); @@ -5047,19 +5059,14 @@ static int vmalloc_info_show(struct seq_file *m, void *p) * As a final step, dump "unpurged" areas. */ show_purge_info(m); + if (IS_ENABLED(CONFIG_NUMA)) + kfree(counters); return 0; } static int __init proc_vmalloc_init(void) { - void *priv_data = NULL; - - if (IS_ENABLED(CONFIG_NUMA)) - priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); - - proc_create_single_data("vmallocinfo", - 0400, NULL, vmalloc_info_show, priv_data); - + proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show); return 0; } module_init(proc_vmalloc_init); --

6 months

3
2
0 0

[PATCH 6.15.y] mm/vmalloc: fix data race in show_numa_info()

by Jeongjun Park

commit 5c5f0468d172ddec2e333d738d2a1f85402cf0bc upstream. The following data-race was found in show_numa_info(): ================================================================== BUG: KCSAN: data-race in vmalloc_info_show / vmalloc_info_show read to 0xffff88800971fe30 of 4 bytes by task 8289 on cpu 0: show_numa_info mm/vmalloc.c:4936 [inline] vmalloc_info_show+0x5a8/0x7e0 mm/vmalloc.c:5016 seq_read_iter+0x373/0xb40 fs/seq_file.c:230 proc_reg_read_iter+0x11e/0x170 fs/proc/inode.c:299 .... write to 0xffff88800971fe30 of 4 bytes by task 8287 on cpu 1: show_numa_info mm/vmalloc.c:4934 [inline] vmalloc_info_show+0x38f/0x7e0 mm/vmalloc.c:5016 seq_read_iter+0x373/0xb40 fs/seq_file.c:230 proc_reg_read_iter+0x11e/0x170 fs/proc/inode.c:299 .... value changed: 0x0000008f -> 0x00000000 ================================================================== According to this report,there is a read/write data-race because m->private is accessible to multiple CPUs. To fix this, instead of allocating the heap in proc_vmalloc_init() and passing the heap address to m->private, vmalloc_info_show() should allocate the heap. Link: https://lkml.kernel.org/r/20250508165620.15321-1-aha310510@gmail.com Fixes: 8e1d743 ("mm: vmalloc: support multiple nodes in vmallocinfo") Signed-off-by: Jeongjun Park <aha310510(a)gmail.com> Suggested-by: Eric Dumazet <edumazet(a)google.com> Suggested-by: Andrew Morton <akpm(a)linux-foundation.org> Reviewed-by: "Uladzislau Rezki (Sony)" <urezki(a)gmail.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmalloc.c | 63 +++++++++++++++++++++++++++++----------------------- 1 file changed, 35 insertions(+), 28 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 00cf1b575c89..3fb534dcf14d 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3100,7 +3100,7 @@ static void clear_vm_uninitialized_flag(struct vm_struct *vm) /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. - * Pair with smp_rmb() in show_numa_info(). + * Pair with smp_rmb() in vread_iter() and vmalloc_info_show(). */ smp_wmb(); vm->flags &= ~VM_UNINITIALIZED; @@ -4934,28 +4934,29 @@ bool vmalloc_dump_obj(void *object) #endif #ifdef CONFIG_PROC_FS -static void show_numa_info(struct seq_file *m, struct vm_struct *v) -{ - if (IS_ENABLED(CONFIG_NUMA)) { - unsigned int nr, *counters = m->private; - unsigned int step = 1U << vm_area_page_order(v); - if (!counters) - return; +/* + * Print number of pages allocated on each memory node. + * + * This function can only be called if CONFIG_NUMA is enabled + * and VM_UNINITIALIZED bit in v->flags is disabled. + */ +static void show_numa_info(struct seq_file *m, struct vm_struct *v, + unsigned int *counters) +{ + unsigned int nr; + unsigned int step = 1U << vm_area_page_order(v); - if (v->flags & VM_UNINITIALIZED) - return; - /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ - smp_rmb(); + if (!counters) + return; - memset(counters, 0, nr_node_ids * sizeof(unsigned int)); + memset(counters, 0, nr_node_ids * sizeof(unsigned int)); - for (nr = 0; nr < v->nr_pages; nr += step) - counters[page_to_nid(v->pages[nr])] += step; - for_each_node_state(nr, N_HIGH_MEMORY) - if (counters[nr]) - seq_printf(m, " N%u=%u", nr, counters[nr]); - } + for (nr = 0; nr < v->nr_pages; nr += step) + counters[page_to_nid(v->pages[nr])] += step; + for_each_node_state(nr, N_HIGH_MEMORY) + if (counters[nr]) + seq_printf(m, " N%u=%u", nr, counters[nr]); } static void show_purge_info(struct seq_file *m) @@ -4983,6 +4984,10 @@ static int vmalloc_info_show(struct seq_file *m, void *p) struct vmap_area *va; struct vm_struct *v; int i; + unsigned int *counters; + + if (IS_ENABLED(CONFIG_NUMA)) + counters = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; @@ -4999,6 +5004,11 @@ static int vmalloc_info_show(struct seq_file *m, void *p) } v = va->vm; + if (v->flags & VM_UNINITIALIZED) + continue; + + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ + smp_rmb(); seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); @@ -5033,7 +5043,9 @@ static int vmalloc_info_show(struct seq_file *m, void *p) if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); - show_numa_info(m, v); + if (IS_ENABLED(CONFIG_NUMA)) + show_numa_info(m, v, counters); + seq_putc(m, '\n'); } spin_unlock(&vn->busy.lock); @@ -5043,19 +5055,14 @@ static int vmalloc_info_show(struct seq_file *m, void *p) * As a final step, dump "unpurged" areas. */ show_purge_info(m); + if (IS_ENABLED(CONFIG_NUMA)) + kfree(counters); return 0; } static int __init proc_vmalloc_init(void) { - void *priv_data = NULL; - - if (IS_ENABLED(CONFIG_NUMA)) - priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); - - proc_create_single_data("vmallocinfo", - 0400, NULL, vmalloc_info_show, priv_data); - + proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show); return 0; } module_init(proc_vmalloc_init); --

6 months

3
3
0 0

[REGRESSION] Linux 6.15.1 xen/dom0 domain_crash_sync called from entry.S

by Chuck Zmudzinski

Hi, I am seeing the following regression between Linux 6.14.8 and 6.15.1. Kernel version 6.14.8 boots fine but version 6.15.1 crashes and reboots on Xen. I don't know if 6.14.9 or 6.14.10 is affected, or if 6.15 or the 6.15 release candidates are affected because I did not test them. Also, Linux 6.15.1 boots fine on bare metal without Xen. Hardware: Intel i5-14500 Raptor Lake CPU, and ASRock B760M PG motherboard and 32 GB RAM. Xen version: 4.19.2 (mockbuild(a)dynavirt.com) (gcc (GCC) 13.3.1 20240611 (Red Hat 13.3.1-2)) debug=n Sun Apr 13 15:24:29 PDT 2025 Xen Command line: placeholder dom0_mem=2G,max:2G conring_size=32k com1=9600,8n1,0x40c0,16,1:0.0 console=com1 Linux version 6.15.1-1.el9.elrepo.x86_64 (mockbuild@5b7a5dab3b71429898b4f8474fab8fa0) (gcc (GCC) 11.5.0 20240719 (Red Hat 11.5.0-5), GNU ld version 2.35.2-63.el9) #1 SMP PREEMPT_DYNAMIC Wed Jun 4 16:42:58 EDT 2025 Linux Kernel Command line: placeholder root=/dev/mapper/systems-rootalma ro crashkernel=1G-4G:192M,4G-64G:256M,64G-:512M resume=UUID=2ddc2e3b-8f7b-498b-a4e8-bb4d33a1e5a7 console=hvc0 The Linux 6.15.1 dom0 kernel causes Xen to crash and reboot, here are the last messages on the serial console (includes messages from both dom0 and Xen) before crash: [ 0.301573] Speculative Store Bypass: Mitigation: Speculative Store Bypass disabled via prctl [ 0.301577] Register File Data Sampling: Vulnerable: No microcode [ 0.301581] ITS: Mitigation: Aligned branch/return thunks [ 0.301594] x86/fpu: Supporting XSAVE feature 0x001: 'x87 floating point registers' [ 0.301598] x86/fpu: Supporting XSAVE feature 0x002: 'SSE registers' [ 0.301602] x86/fpu: Supporting XSAVE feature 0x004: 'AVX registers' [ 0.301605] x86/fpu: xstate_offset[2]: 576, xstate_sizes[2]: 256 [ 0.301609] x86/fpu: Enabled xstate features 0x7, context size is 832 bytes, using 'compacted' format. (XEN) Pagetable walk from ffffc9003ffffff8: (XEN) L4[0x192] = 0000000855bee067 0000000000060e56 (XEN) L3[0x000] = 0000000855bed067 0000000000060e55 (XEN) L2[0x1ff] = 0000000855bf0067 0000000000060e58 (XEN) L1[0x1ff] = 8010000855bf2025 0000000000060e5a (XEN) domain_crash_sync called from entry.S: fault at ffff82d04036e5b0 x86_64/entry.S#domain_crash_page_fault_6x8+0/0x4 (XEN) Domain 0 (vcpu#0) crashed on cpu#11: (XEN) ----[ Xen-4.19.2 x86_64 debug=n Not tainted ]---- (XEN) CPU: 11 (XEN) RIP: e033:[<ffffffff810014fe>] (XEN) RFLAGS: 0000000000010206 EM: 1 CONTEXT: pv guest (d0v0) (XEN) rax: ffffffff81fb12d0 rbx: 000000000000029a rcx: 000000000000000c (XEN) rdx: 000000000000029a rsi: ffffffff81000b99 rdi: ffffc900400000f0 (XEN) rbp: 000000000000014d rsp: ffffc90040000000 r8: 0000000000000f9c (XEN) r9: 0000000000000000 r10: 0000000000000000 r11: 0000000000000000 (XEN) r12: 000000000000000c r13: ffffffff82771530 r14: ffffffff827724cc (XEN) r15: ffffc900400000f0 cr0: 0000000080050033 cr4: 0000000000b526e0 (XEN) cr3: 000000086ae24000 cr2: ffffc9003ffffff8 (XEN) fsb: 0000000000000000 gsb: ffff88819ac55000 gss: 0000000000000000 (XEN) ds: 0000 es: 0000 fs: 0000 gs: 0000 ss: e02b cs: e033 (XEN) Guest stack trace from rsp=ffffc90040000000: (XEN) Stack empty. (XEN) Hardware Dom0 crashed: rebooting machine in 5 seconds. (XEN) Resetting with ACPI MEMORY or I/O RESET_REG. I searched mailing lists but could not find a report similar to what I am seeing here. I don't know what to try except to git bisect, but I have not done that yet. Chuck Zmudzinski

6 months

3
3
0 0

6.12.y longterm regression - IPv6 UDP packet fragmentation

by Brett Sheffield

Hello Stable Maintainers, Longterm kernel 6.12.y backports commit: - a18dfa9925b9ef6107ea3aa5814ca3c704d34a8a "ipv6: save dontfrag in cork" but does not backport these related commits: - 54580ccdd8a9c6821fd6f72171d435480867e4c3 "ipv6: remove leftover ip6 cookie initializer" - 096208592b09c2f5fc0c1a174694efa41c04209d "ipv6: replace ipcm6_init calls with ipcm6_init_sk" This causes a regression when sending IPv6 UDP packets by preventing fragmentation and instead returning EMSGSIZE. I have attached a program which demonstrates the issue. sendmsg() returns correctly (8192) on a working kernel, and returns -1 (EMSGSIZE) when the regression is present. The regression is not present in the mainline kernel. Applying the two missing commits to 6.12.y fixes the regression. Cheers, Brett -- Brett Sheffield (he/him) Librecast - Decentralising the Internet with Multicast https://librecast.net/ https://blog.brettsheffield.com/

6 months

6
14
0 0

[PATCH 5.15.y] xen: replace xen_remap() with memremap()

by Teddy Astie

From: Juergen Gross <jgross(a)suse.com> [ upstream commit 41925b105e345ebc84cedb64f59d20cb14a62613 ] xen_remap() is used to establish mappings for frames not under direct control of the kernel: for Xenstore and console ring pages, and for grant pages of non-PV guests. Today xen_remap() is defined to use ioremap() on x86 (doing uncached mappings), and ioremap_cache() on Arm (doing cached mappings). Uncached mappings for those use cases are bad for performance, so they should be avoided if possible. As all use cases of xen_remap() don't require uncached mappings (the mapped area is always physical RAM), a mapping using the standard WB cache mode is fine. As sparse is flagging some of the xen_remap() use cases to be not appropriate for iomem(), as the result is not annotated with the __iomem modifier, eliminate xen_remap() completely and replace all use cases with memremap() specifying the MEMREMAP_WB caching mode. xen_unmap() can be replaced with memunmap(). Reported-by: kernel test robot <lkp(a)intel.com> Signed-off-by: Juergen Gross <jgross(a)suse.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Acked-by: Stefano Stabellini <sstabellini(a)kernel.org> Link: https://lore.kernel.org/r/20220530082634.6339-1-jgross@suse.com Signed-off-by: Juergen Gross <jgross(a)suse.com> Signed-off-by: Teddy Astie <teddy.astie(a)vates.tech> [backport to 5.15.y] --- arch/x86/include/asm/xen/page.h | 3 --- drivers/xen/grant-table.c | 6 +++--- drivers/xen/xenbus/xenbus_probe.c | 3 +-- 3 files changed, 4 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 1a162e559753..c183b7f9efef 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -355,9 +355,6 @@ unsigned long arbitrary_virt_to_mfn(void *vaddr); void make_lowmem_page_readonly(void *vaddr); void make_lowmem_page_readwrite(void *vaddr); -#define xen_remap(cookie, size) ioremap((cookie), (size)) -#define xen_unmap(cookie) iounmap((cookie)) - static inline bool xen_arch_need_swiotlb(struct device *dev, phys_addr_t phys, dma_addr_t dev_addr) diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 0a2d24d6ac6f..a10e0741bec5 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -743,7 +743,7 @@ int gnttab_setup_auto_xlat_frames(phys_addr_t addr) if (xen_auto_xlat_grant_frames.count) return -EINVAL; - vaddr = xen_remap(addr, XEN_PAGE_SIZE * max_nr_gframes); + vaddr = memremap(addr, XEN_PAGE_SIZE * max_nr_gframes, MEMREMAP_WB); if (vaddr == NULL) { pr_warn("Failed to ioremap gnttab share frames (addr=%pa)!\n", &addr); @@ -751,7 +751,7 @@ int gnttab_setup_auto_xlat_frames(phys_addr_t addr) } pfn = kcalloc(max_nr_gframes, sizeof(pfn[0]), GFP_KERNEL); if (!pfn) { - xen_unmap(vaddr); + memunmap(vaddr); return -ENOMEM; } for (i = 0; i < max_nr_gframes; i++) @@ -770,7 +770,7 @@ void gnttab_free_auto_xlat_frames(void) if (!xen_auto_xlat_grant_frames.count) return; kfree(xen_auto_xlat_grant_frames.pfn); - xen_unmap(xen_auto_xlat_grant_frames.vaddr); + memunmap(xen_auto_xlat_grant_frames.vaddr); xen_auto_xlat_grant_frames.pfn = NULL; xen_auto_xlat_grant_frames.count = 0; diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 2068f83556b7..77ca24611293 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -982,8 +982,7 @@ static int __init xenbus_init(void) #endif xen_store_gfn = (unsigned long)v; xen_store_interface = - xen_remap(xen_store_gfn << XEN_PAGE_SHIFT, - XEN_PAGE_SIZE); + memremap(xen_store_gfn << XEN_PAGE_SHIFT, XEN_PAGE_SIZE, MEMREMAP_WB); break; default: pr_warn("Xenstore state unknown\n"); -- 2.50.0 Teddy Astie | Vates XCP-ng Developer XCP-ng & Xen Orchestra - Vates solutions web: https://vates.tech

6 months

2
1
0 0

[PATCH 5.15.y v2] xen: replace xen_remap() with memremap()

by Teddy Astie

From: Juergen Gross <jgross(a)suse.com> [ upstream commit 41925b105e345ebc84cedb64f59d20cb14a62613 ] xen_remap() is used to establish mappings for frames not under direct control of the kernel: for Xenstore and console ring pages, and for grant pages of non-PV guests. Today xen_remap() is defined to use ioremap() on x86 (doing uncached mappings), and ioremap_cache() on Arm (doing cached mappings). Uncached mappings for those use cases are bad for performance, so they should be avoided if possible. As all use cases of xen_remap() don't require uncached mappings (the mapped area is always physical RAM), a mapping using the standard WB cache mode is fine. As sparse is flagging some of the xen_remap() use cases to be not appropriate for iomem(), as the result is not annotated with the __iomem modifier, eliminate xen_remap() completely and replace all use cases with memremap() specifying the MEMREMAP_WB caching mode. xen_unmap() can be replaced with memunmap(). Reported-by: kernel test robot <lkp(a)intel.com> Signed-off-by: Juergen Gross <jgross(a)suse.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Acked-by: Stefano Stabellini <sstabellini(a)kernel.org> Link: https://lore.kernel.org/r/20220530082634.6339-1-jgross@suse.com Signed-off-by: Juergen Gross <jgross(a)suse.com> Signed-off-by: Teddy Astie <teddy.astie(a)vates.tech> [backport to 5.15.y] --- v2: - also remove xen_remap/xen_unmap on ARM --- arch/x86/include/asm/xen/page.h | 3 --- drivers/xen/grant-table.c | 6 +++--- drivers/xen/xenbus/xenbus_probe.c | 3 +-- include/xen/arm/page.h | 3 --- 4 files changed, 4 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 1a162e559753..c183b7f9efef 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -355,9 +355,6 @@ unsigned long arbitrary_virt_to_mfn(void *vaddr); void make_lowmem_page_readonly(void *vaddr); void make_lowmem_page_readwrite(void *vaddr); -#define xen_remap(cookie, size) ioremap((cookie), (size)) -#define xen_unmap(cookie) iounmap((cookie)) - static inline bool xen_arch_need_swiotlb(struct device *dev, phys_addr_t phys, dma_addr_t dev_addr) diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 0a2d24d6ac6f..a10e0741bec5 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -743,7 +743,7 @@ int gnttab_setup_auto_xlat_frames(phys_addr_t addr) if (xen_auto_xlat_grant_frames.count) return -EINVAL; - vaddr = xen_remap(addr, XEN_PAGE_SIZE * max_nr_gframes); + vaddr = memremap(addr, XEN_PAGE_SIZE * max_nr_gframes, MEMREMAP_WB); if (vaddr == NULL) { pr_warn("Failed to ioremap gnttab share frames (addr=%pa)!\n", &addr); @@ -751,7 +751,7 @@ int gnttab_setup_auto_xlat_frames(phys_addr_t addr) } pfn = kcalloc(max_nr_gframes, sizeof(pfn[0]), GFP_KERNEL); if (!pfn) { - xen_unmap(vaddr); + memunmap(vaddr); return -ENOMEM; } for (i = 0; i < max_nr_gframes; i++) @@ -770,7 +770,7 @@ void gnttab_free_auto_xlat_frames(void) if (!xen_auto_xlat_grant_frames.count) return; kfree(xen_auto_xlat_grant_frames.pfn); - xen_unmap(xen_auto_xlat_grant_frames.vaddr); + memunmap(xen_auto_xlat_grant_frames.vaddr); xen_auto_xlat_grant_frames.pfn = NULL; xen_auto_xlat_grant_frames.count = 0; diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 2068f83556b7..77ca24611293 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -982,8 +982,7 @@ static int __init xenbus_init(void) #endif xen_store_gfn = (unsigned long)v; xen_store_interface = - xen_remap(xen_store_gfn << XEN_PAGE_SHIFT, - XEN_PAGE_SIZE); + memremap(xen_store_gfn << XEN_PAGE_SHIFT, XEN_PAGE_SIZE, MEMREMAP_WB); break; default: pr_warn("Xenstore state unknown\n"); diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h index ac1b65470563..f831cfeca000 100644 --- a/include/xen/arm/page.h +++ b/include/xen/arm/page.h @@ -109,9 +109,6 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) return __set_phys_to_machine(pfn, mfn); } -#define xen_remap(cookie, size) ioremap_cache((cookie), (size)) -#define xen_unmap(cookie) iounmap((cookie)) - bool xen_arch_need_swiotlb(struct device *dev, phys_addr_t phys, dma_addr_t dev_addr); -- 2.50.0 Teddy Astie | Vates XCP-ng Developer XCP-ng & Xen Orchestra - Vates solutions web: https://vates.tech

6 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2025