From af54d778a03853801d681c98c0c2a6c316ef9ca7 Mon Sep 17 00:00:00 2001 From: Mukesh Ojha Date: Fri, 17 Nov 2023 20:19:32 +0530 Subject: devcoredump: Send uevent once devcd is ready dev_coredumpm() creates a devcoredump device and adds it to the core kernel framework which eventually end up sending uevent to the user space and later creates a symbolic link to the failed device. An application running in userspace may be interested in this symbolic link to get the name of the failed device. In a issue scenario, once uevent sent to the user space it start reading '/sys/class/devcoredump/devcdX/failing_device' to get the actual name of the device which might not been created and it is in its path of creation. To fix this, suppress sending uevent till the failing device symbolic link gets created and send uevent once symbolic link is created successfully. Fixes: 833c95456a70 ("device coredump: add new device coredump class") Signed-off-by: Mukesh Ojha Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1700232572-25823-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/devcoredump.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c index 91536ee05f14..7e2d1f0d903a 100644 --- a/drivers/base/devcoredump.c +++ b/drivers/base/devcoredump.c @@ -362,6 +362,7 @@ void dev_coredumpm(struct device *dev, struct module *owner, devcd->devcd_dev.class = &devcd_class; mutex_lock(&devcd->mutex); + dev_set_uevent_suppress(&devcd->devcd_dev, true); if (device_add(&devcd->devcd_dev)) goto put_device; @@ -376,6 +377,8 @@ void dev_coredumpm(struct device *dev, struct module *owner, "devcoredump")) dev_warn(dev, "devcoredump create_link failed\n"); + dev_set_uevent_suppress(&devcd->devcd_dev, false); + kobject_uevent(&devcd->devcd_dev.kobj, KOBJ_ADD); INIT_DELAYED_WORK(&devcd->del_wk, devcd_del); schedule_delayed_work(&devcd->del_wk, DEVCD_TIMEOUT); mutex_unlock(&devcd->mutex); -- cgit v1.2.3 From 001002e73712cdf6b8d9a103648cda3040ad7647 Mon Sep 17 00:00:00 2001 From: Sumanth Korikkar Date: Mon, 20 Nov 2023 15:53:52 +0100 Subject: mm/memory_hotplug: add missing mem_hotplug_lock From Documentation/core-api/memory-hotplug.rst: When adding/removing/onlining/offlining memory or adding/removing heterogeneous/device memory, we should always hold the mem_hotplug_lock in write mode to serialise memory hotplug (e.g. access to global/zone variables). mhp_(de)init_memmap_on_memory() functions can change zone stats and struct page content, but they are currently called w/o the mem_hotplug_lock. When memory block is being offlined and when kmemleak goes through each populated zone, the following theoretical race conditions could occur: CPU 0: | CPU 1: memory_offline() | -> offline_pages() | -> mem_hotplug_begin() | ... | -> mem_hotplug_done() | | kmemleak_scan() | -> get_online_mems() | ... -> mhp_deinit_memmap_on_memory() | [not protected by mem_hotplug_begin/done()]| Marks memory section as offline, | Retrieves zone_start_pfn poisons vmemmap struct pages and updates | and struct page members. the zone related data | | ... | -> put_online_mems() Fix this by ensuring mem_hotplug_lock is taken before performing mhp_init_memmap_on_memory(). Also ensure that mhp_deinit_memmap_on_memory() holds the lock. online/offline_pages() are currently only called from memory_block_online/offline(), so it is safe to move the locking there. Link: https://lkml.kernel.org/r/20231120145354.308999-2-sumanthk@linux.ibm.com Fixes: a08a2ae34613 ("mm,memory_hotplug: allocate memmap from the added memory range") Signed-off-by: Sumanth Korikkar Reviewed-by: Gerald Schaefer Acked-by: David Hildenbrand Cc: Alexander Gordeev Cc: Aneesh Kumar K.V Cc: Anshuman Khandual Cc: Heiko Carstens Cc: Michal Hocko Cc: Oscar Salvador Cc: Vasily Gorbik Cc: kernel test robot Cc: [5.15+] Signed-off-by: Andrew Morton --- drivers/base/memory.c | 18 +++++++++++++++--- mm/memory_hotplug.c | 13 ++++++------- 2 files changed, 21 insertions(+), 10 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index f3b9a4d0fa3b..8a13babd826c 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -180,6 +180,9 @@ static inline unsigned long memblk_nr_poison(struct memory_block *mem) } #endif +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_online(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -204,10 +207,11 @@ static int memory_block_online(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + mem_hotplug_begin(); if (nr_vmemmap_pages) { ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); if (ret) - return ret; + goto out; } ret = online_pages(start_pfn + nr_vmemmap_pages, @@ -215,7 +219,7 @@ static int memory_block_online(struct memory_block *mem) if (ret) { if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); - return ret; + goto out; } /* @@ -227,9 +231,14 @@ static int memory_block_online(struct memory_block *mem) nr_vmemmap_pages); mem->zone = zone; +out: + mem_hotplug_done(); return ret; } +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_offline(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -247,6 +256,7 @@ static int memory_block_offline(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + mem_hotplug_begin(); if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, -nr_vmemmap_pages); @@ -258,13 +268,15 @@ static int memory_block_offline(struct memory_block *mem) if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, nr_vmemmap_pages); - return ret; + goto out; } if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); mem->zone = NULL; +out: + mem_hotplug_done(); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ab41a511e20a..bb908289679e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1129,6 +1129,9 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1149,7 +1152,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); /* associate pfn range with the zone */ move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE); @@ -1208,7 +1210,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, writeback_set_ratelimit(); memory_notify(MEM_ONLINE, &arg); - mem_hotplug_done(); return 0; failed_addition: @@ -1217,7 +1218,6 @@ failed_addition: (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); remove_pfn_range_from_zone(zone, pfn, nr_pages); - mem_hotplug_done(); return ret; } @@ -1863,6 +1863,9 @@ static int count_system_ram_pages_cb(unsigned long start_pfn, return 0; } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1885,8 +1888,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); - /* * Don't allow to offline memory blocks that contain holes. * Consequently, memory blocks with holes can never get onlined @@ -2031,7 +2032,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, memory_notify(MEM_OFFLINE, &arg); remove_pfn_range_from_zone(zone, start_pfn, nr_pages); - mem_hotplug_done(); return 0; failed_removal_isolated: @@ -2046,7 +2046,6 @@ failed_removal: (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1, reason); - mem_hotplug_done(); return ret; } -- cgit v1.2.3 From 4e9e2e4c65136dfd32dd0afe555961433d1cf906 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Tue, 28 Nov 2023 13:52:48 +0800 Subject: drivers/base/cpu: crash data showing should depends on KEXEC_CORE After commit 88a6f8994421 ("crash: memory and CPU hotplug sysfs attributes"), on x86_64, if only below kernel configs related to kdump are set, compiling error are triggered. ---- CONFIG_CRASH_CORE=y CONFIG_KEXEC_CORE=y CONFIG_CRASH_DUMP=y CONFIG_CRASH_HOTPLUG=y ------ ------------------------------------------------------ drivers/base/cpu.c: In function `crash_hotplug_show': drivers/base/cpu.c:309:40: error: implicit declaration of function `crash_hotplug_cpu_support'; did you mean `crash_hotplug_show'? [-Werror=implicit-function-declaration] 309 | return sysfs_emit(buf, "%d\n", crash_hotplug_cpu_support()); | ^~~~~~~~~~~~~~~~~~~~~~~~~ | crash_hotplug_show cc1: some warnings being treated as errors ------------------------------------------------------ CONFIG_KEXEC is used to enable kexec_load interface, the crash_notes/crash_notes_size/crash_hotplug showing depends on CONFIG_KEXEC is incorrect. It should depend on KEXEC_CORE instead. Fix it now. Link: https://lkml.kernel.org/r/20231128055248.659808-1-bhe@redhat.com Fixes: 88a6f8994421 ("crash: memory and CPU hotplug sysfs attributes") Signed-off-by: Baoquan He Tested-by: Ignat Korchagin [compile-time only] Tested-by: Alexander Gordeev Reviewed-by: Eric DeVolder Cc: Signed-off-by: Andrew Morton --- drivers/base/cpu.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 9ea22e165acd..548491de818e 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -144,7 +144,7 @@ static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store); #endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ #endif /* CONFIG_HOTPLUG_CPU */ -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE #include static ssize_t crash_notes_show(struct device *dev, @@ -189,14 +189,14 @@ static const struct attribute_group crash_note_cpu_attr_group = { #endif static const struct attribute_group *common_cpu_attr_groups[] = { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE &crash_note_cpu_attr_group, #endif NULL }; static const struct attribute_group *hotplugable_cpu_attr_groups[] = { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE &crash_note_cpu_attr_group, #endif NULL -- cgit v1.2.3