From 43e3aa2a3247c9ca348884866a9846d788ec5ed6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:35 -0700 Subject: mm/memory_hotplug: remove stale function declarations These functions no longer exist. Link: https://lkml.kernel.org/r/20210929143600.49379-6-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux/memory_hotplug.h') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index e5a867c950b2..be48e003a518 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -98,9 +98,6 @@ static inline void zone_seqlock_init(struct zone *zone) { seqlock_init(&zone->span_seqlock); } -extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); -extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); -extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); extern void adjust_present_page_count(struct page *page, struct memory_group *group, long nr_pages); -- cgit v1.2.3 From e930d999715073a70d306fb59a394ea8b84d0b45 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 22 Mar 2022 14:46:51 -0700 Subject: mm, memory_hotplug: make arch_alloc_nodedata independent on CONFIG_MEMORY_HOTPLUG Patch series "mm, memory_hotplug: handle unitialized numa node gracefully". The core of the fix is patch 2 which also links existing bug reports. The high level goal is to have all possible numa nodes have their pgdat allocated and initialized so for_each_possible_node(nid) NODE_DATA(nid) will never return garbage. This has proven to be problem in several places when an offline numa node is used for an allocation just to realize that node_data and therefore allocation fallback zonelists are not initialized and such an allocation request blows up. There were attempts to address that by checking node_online in several places including the page allocator. This patchset approaches the problem from a different perspective and instead of special casing, which just adds a runtime overhead, it allocates pglist_data for each possible node. This can add some memory overhead for platforms with high number of possible nodes if they do not contain any memory. This should be a rather rare configuration though. How to test this? David has provided and excellent howto: http://lkml.kernel.org/r/6e5ebc19-890c-b6dd-1924-9f25c441010d@redhat.com Patches 1 and 3-6 are mostly cleanups. The patchset has been reviewed by Rafael (thanks!) and the core fix tested by Rafael and Alexey (thanks to both). David has tested as per instructions above and hasn't found any fallouts in the memory hotplug scenarios. This patch (of 6): This is a preparatory patch and it doesn't introduce any functional change. It merely pulls out arch_alloc_nodedata (and co) outside of CONFIG_MEMORY_HOTPLUG because the following patch will need to call this from the generic MM code. Link: https://lkml.kernel.org/r/20220127085305.20890-1-mhocko@kernel.org Link: https://lkml.kernel.org/r/20220127085305.20890-2-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Rafael Aquini Acked-by: David Hildenbrand Acked-by: Mike Rapoport Reviewed-by: Oscar Salvador Reviewed-by: Wei Yang Cc: Alexey Makhalov Cc: Christoph Lameter Cc: Dennis Zhou Cc: Eric Dumazet Cc: Nico Pache Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 119 ++++++++++++++++++++--------------------- 1 file changed, 59 insertions(+), 60 deletions(-) (limited to 'include/linux/memory_hotplug.h') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index be48e003a518..4355983b364d 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -16,6 +16,65 @@ struct memory_group; struct resource; struct vmem_altmap; +#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION +/* + * For supporting node-hotadd, we have to allocate a new pgdat. + * + * If an arch has generic style NODE_DATA(), + * node_data[nid] = kzalloc() works well. But it depends on the architecture. + * + * In general, generic_alloc_nodedata() is used. + * Now, arch_free_nodedata() is just defined for error path of node_hot_add. + * + */ +extern pg_data_t *arch_alloc_nodedata(int nid); +extern void arch_free_nodedata(pg_data_t *pgdat); +extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); + +#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ + +#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) +#define arch_free_nodedata(pgdat) generic_free_nodedata(pgdat) + +#ifdef CONFIG_NUMA +/* + * XXX: node aware allocation can't work well to get new node's memory at this time. + * Because, pgdat for the new node is not allocated/initialized yet itself. + * To use new node's memory, more consideration will be necessary. + */ +#define generic_alloc_nodedata(nid) \ +({ \ + kzalloc(sizeof(pg_data_t), GFP_KERNEL); \ +}) +/* + * This definition is just for error path in node hotadd. + * For node hotremove, we have to replace this. + */ +#define generic_free_nodedata(pgdat) kfree(pgdat) + +extern pg_data_t *node_data[]; +static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) +{ + node_data[nid] = pgdat; +} + +#else /* !CONFIG_NUMA */ + +/* never called */ +static inline pg_data_t *generic_alloc_nodedata(int nid) +{ + BUG(); + return NULL; +} +static inline void generic_free_nodedata(pg_data_t *pgdat) +{ +} +static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) +{ +} +#endif /* CONFIG_NUMA */ +#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ + #ifdef CONFIG_MEMORY_HOTPLUG struct page *pfn_to_online_page(unsigned long pfn); @@ -154,66 +213,6 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params); #endif /* ARCH_HAS_ADD_PAGES */ -#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION -/* - * For supporting node-hotadd, we have to allocate a new pgdat. - * - * If an arch has generic style NODE_DATA(), - * node_data[nid] = kzalloc() works well. But it depends on the architecture. - * - * In general, generic_alloc_nodedata() is used. - * Now, arch_free_nodedata() is just defined for error path of node_hot_add. - * - */ -extern pg_data_t *arch_alloc_nodedata(int nid); -extern void arch_free_nodedata(pg_data_t *pgdat); -extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); - -#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - -#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) -#define arch_free_nodedata(pgdat) generic_free_nodedata(pgdat) - -#ifdef CONFIG_NUMA -/* - * If ARCH_HAS_NODEDATA_EXTENSION=n, this func is used to allocate pgdat. - * XXX: kmalloc_node() can't work well to get new node's memory at this time. - * Because, pgdat for the new node is not allocated/initialized yet itself. - * To use new node's memory, more consideration will be necessary. - */ -#define generic_alloc_nodedata(nid) \ -({ \ - kzalloc(sizeof(pg_data_t), GFP_KERNEL); \ -}) -/* - * This definition is just for error path in node hotadd. - * For node hotremove, we have to replace this. - */ -#define generic_free_nodedata(pgdat) kfree(pgdat) - -extern pg_data_t *node_data[]; -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) -{ - node_data[nid] = pgdat; -} - -#else /* !CONFIG_NUMA */ - -/* never called */ -static inline pg_data_t *generic_alloc_nodedata(int nid) -{ - BUG(); - return NULL; -} -static inline void generic_free_nodedata(pg_data_t *pgdat) -{ -} -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) -{ -} -#endif /* CONFIG_NUMA */ -#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - void get_online_mems(void); void put_online_mems(void); -- cgit v1.2.3 From 09f49dca570a917a8c6bccd7e8c61f5141534e3a Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 22 Mar 2022 14:46:54 -0700 Subject: mm: handle uninitialized numa nodes gracefully We have had several reports [1][2][3] that page allocator blows up when an allocation from a possible node is requested. The underlying reason is that NODE_DATA for the specific node is not allocated. NUMA specific initialization is arch specific and it can vary a lot. E.g. x86 tries to initialize all nodes that have some cpu affinity (see init_cpu_to_node) but this can be insufficient because the node might be cpuless for example. One way to address this problem would be to check for !node_online nodes when trying to get a zonelist and silently fall back to another node. That is unfortunately adding a branch into allocator hot path and it doesn't handle any other potential NODE_DATA users. This patch takes a different approach (following a lead of [3]) and it pre allocates pgdat for all possible nodes in an arch indipendent code - free_area_init. All uninitialized nodes are treated as memoryless nodes. node_state of the node is not changed because that would lead to other side effects - e.g. sysfs representation of such a node and from past discussions [4] it is known that some tools might have problems digesting that. Newly allocated pgdat only gets a minimal initialization and the rest of the work is expected to be done by the memory hotplug - hotadd_new_pgdat (renamed to hotadd_init_pgdat). generic_alloc_nodedata is changed to use the memblock allocator because neither page nor slab allocators are available at the stage when all pgdats are allocated. Hotplug doesn't allocate pgdat anymore so we can use the early boot allocator. The only arch specific implementation is ia64 and that is changed to use the early allocator as well. [1] http://lkml.kernel.org/r/20211101201312.11589-1-amakhalov@vmware.com [2] http://lkml.kernel.org/r/20211207224013.880775-1-npache@redhat.com [3] http://lkml.kernel.org/r/20190114082416.30939-1-mhocko@kernel.org [4] http://lkml.kernel.org/r/20200428093836.27190-1-srikar@linux.vnet.ibm.com [akpm@linux-foundation.org: replace comment, per Mike] Link: https://lkml.kernel.org/r/Yfe7RBeLCijnWBON@dhcp22.suse.cz Reported-by: Alexey Makhalov Tested-by: Alexey Makhalov Reported-by: Nico Pache Acked-by: Rafael Aquini Tested-by: Rafael Aquini Acked-by: David Hildenbrand Reviewed-by: Oscar Salvador Acked-by: Mike Rapoport Signed-off-by: Michal Hocko Cc: Christoph Lameter Cc: Dennis Zhou Cc: Eric Dumazet Cc: Tejun Heo Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/memory_hotplug.h') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 4355983b364d..cdd66bfdf855 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -44,7 +44,7 @@ extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); */ #define generic_alloc_nodedata(nid) \ ({ \ - kzalloc(sizeof(pg_data_t), GFP_KERNEL); \ + memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES); \ }) /* * This definition is just for error path in node hotadd. -- cgit v1.2.3 From 390511e1476eb1cc41d420a7661b33f4d8584c3f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 22 Mar 2022 14:46:57 -0700 Subject: mm, memory_hotplug: drop arch_free_nodedata Prior to "mm: handle uninitialized numa nodes gracefully" memory hotplug used to allocate pgdat when memory has been added to a node (hotadd_init_pgdat) arch_free_nodedata has been only used in the failure path because once the pgdat is exported (to be visible by NODA_DATA(nid)) it cannot really be freed because there is no synchronization available for that. pgdat is allocated for each possible nodes now so the memory hotplug doesn't need to do the ever use arch_free_nodedata so drop it. This patch doesn't introduce any functional change. Link: https://lkml.kernel.org/r/20220127085305.20890-4-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Rafael Aquini Acked-by: David Hildenbrand Acked-by: Mike Rapoport Reviewed-by: Oscar Salvador Cc: Alexey Makhalov Cc: Christoph Lameter Cc: Dennis Zhou Cc: Eric Dumazet Cc: Nico Pache Cc: Tejun Heo Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux/memory_hotplug.h') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index cdd66bfdf855..60f09d3ebb3d 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -24,17 +24,14 @@ struct vmem_altmap; * node_data[nid] = kzalloc() works well. But it depends on the architecture. * * In general, generic_alloc_nodedata() is used. - * Now, arch_free_nodedata() is just defined for error path of node_hot_add. * */ extern pg_data_t *arch_alloc_nodedata(int nid); -extern void arch_free_nodedata(pg_data_t *pgdat); extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); #else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ #define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) -#define arch_free_nodedata(pgdat) generic_free_nodedata(pgdat) #ifdef CONFIG_NUMA /* -- cgit v1.2.3 From 70b5b46a754245d383811b4d2f2c76c34bb7e145 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 22 Mar 2022 14:47:00 -0700 Subject: mm, memory_hotplug: reorganize new pgdat initialization When a !node_online node is brought up it needs a hotplug specific initialization because the node could be either uninitialized yet or it could have been recycled after previous hotremove. hotadd_init_pgdat is responsible for that. Internal pgdat state is initialized at two places currently - hotadd_init_pgdat - free_area_init_core_hotplug There is no real clear cut what should go where but this patch's chosen to move the whole internal state initialization into free_area_init_core_hotplug. hotadd_init_pgdat is still responsible to pull all the parts together - most notably to initialize zonelists because those depend on the overall topology. This patch doesn't introduce any functional change. Link: https://lkml.kernel.org/r/20220127085305.20890-5-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Rafael Aquini Acked-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alexey Makhalov Cc: Christoph Lameter Cc: Dennis Zhou Cc: Eric Dumazet Cc: Mike Rapoport Cc: Nico Pache Cc: Tejun Heo Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/memory_hotplug.h') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 60f09d3ebb3d..76bf2de86def 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -319,7 +319,7 @@ extern void set_zone_contiguous(struct zone *zone); extern void clear_zone_contiguous(struct zone *zone); #ifdef CONFIG_MEMORY_HOTPLUG -extern void __ref free_area_init_core_hotplug(int nid); +extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat); extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory_resource(int nid, struct resource *resource, -- cgit v1.2.3 From 395f6081bad49f9c54abafebab49ee23aa985bbd Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 22 Mar 2022 14:47:31 -0700 Subject: drivers/base/memory: determine and store zone for single-zone memory blocks test_pages_in_a_zone() is just another nasty PFN walker that can easily stumble over ZONE_DEVICE memory ranges falling into the same memory block as ordinary system RAM: the memmap of parts of these ranges might possibly be uninitialized. In fact, we observed (on an older kernel) with UBSAN: UBSAN: Undefined behaviour in ./include/linux/mm.h:1133:50 index 7 is out of range for type 'zone [5]' CPU: 121 PID: 35603 Comm: read_all Kdump: loaded Tainted: [...] Hardware name: Dell Inc. PowerEdge R7425/08V001, BIOS 1.12.2 11/15/2019 Call Trace: dump_stack+0x9a/0xf0 ubsan_epilogue+0x9/0x7a __ubsan_handle_out_of_bounds+0x13a/0x181 test_pages_in_a_zone+0x3c4/0x500 show_valid_zones+0x1fa/0x380 dev_attr_show+0x43/0xb0 sysfs_kf_seq_show+0x1c5/0x440 seq_read+0x49d/0x1190 vfs_read+0xff/0x300 ksys_read+0xb8/0x170 do_syscall_64+0xa5/0x4b0 entry_SYSCALL_64_after_hwframe+0x6a/0xdf RIP: 0033:0x7f01f4439b52 We seem to stumble over a memmap that contains a garbage zone id. While we could try inserting pfn_to_online_page() calls, it will just make memory offlining slower, because we use test_pages_in_a_zone() to make sure we're offlining pages that all belong to the same zone. Let's just get rid of this PFN walker and determine the single zone of a memory block -- if any -- for early memory blocks during boot. For memory onlining, we know the single zone already. Let's avoid any additional memmap scanning and just rely on the zone information available during boot. For memory hot(un)plug, we only really care about memory blocks that: * span a single zone (and, thereby, a single node) * are completely System RAM (IOW, no holes, no ZONE_DEVICE) If one of these conditions is not met, we reject memory offlining. Hotplugged memory blocks (starting out offline), always meet both conditions. There are three scenarios to handle: (1) Memory hot(un)plug A memory block with zone == NULL cannot be offlined, corresponding to our previous test_pages_in_a_zone() check. After successful memory onlining/offlining, we simply set the zone accordingly. * Memory onlining: set the zone we just used for onlining * Memory offlining: set zone = NULL So a hotplugged memory block starts with zone = NULL. Once memory onlining is done, we set the proper zone. (2) Boot memory with !CONFIG_NUMA We know that there is just a single pgdat, so we simply scan all zones of that pgdat for an intersection with our memory block PFN range when adding the memory block. If more than one zone intersects (e.g., DMA and DMA32 on x86 for the first memory block) we set zone = NULL and consequently mimic what test_pages_in_a_zone() used to do. (3) Boot memory with CONFIG_NUMA At the point in time we create the memory block devices during boot, we don't know yet which nodes *actually* span a memory block. While we could scan all zones of all nodes for intersections, overlapping nodes complicate the situation and scanning all nodes is possibly expensive. But that problem has already been solved by the code that sets the node of a memory block and creates the link in the sysfs -- do_register_memory_block_under_node(). So, we hook into the code that sets the node id for a memory block. If we already have a different node id set for the memory block, we know that multiple nodes *actually* have PFNs falling into our memory block: we set zone = NULL and consequently mimic what test_pages_in_a_zone() used to do. If there is no node id set, we do the same as (2) for the given node. Note that the call order in driver_init() is: -> memory_dev_init(): create memory block devices -> node_dev_init(): link memory block devices to the node and set the node id So in summary, we detect if there is a single zone responsible for this memory block and we consequently store the zone in that case in the memory block, updating it during memory onlining/offlining. Link: https://lkml.kernel.org/r/20220210184359.235565-3-david@redhat.com Signed-off-by: David Hildenbrand Reported-by: Rafael Parra Reviewed-by: Oscar Salvador Cc: "Rafael J. Wysocki" Cc: Greg Kroah-Hartman Cc: Michal Hocko Cc: Rafael Parra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux/memory_hotplug.h') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 76bf2de86def..1ce6f8044f1e 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -163,8 +163,6 @@ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); -extern struct zone *test_pages_in_a_zone(unsigned long start_pfn, - unsigned long end_pfn); extern void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn); @@ -293,7 +291,7 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {} extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages, - struct memory_group *group); + struct zone *zone, struct memory_group *group); extern int remove_memory(u64 start, u64 size); extern void __remove_memory(u64 start, u64 size); extern int offline_and_remove_memory(u64 start, u64 size); @@ -302,7 +300,7 @@ extern int offline_and_remove_memory(u64 start, u64 size); static inline void try_offline_node(int nid) {} static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages, - struct memory_group *group) + struct zone *zone, struct memory_group *group) { return -EINVAL; } -- cgit v1.2.3