From 76af6a054da4055305ddb28c5eb151b9ee4f74f9 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Mon, 18 Oct 2021 15:15:32 -0700 Subject: mm/migrate: add CPU hotplug to demotion #ifdef Once upon a time, the node demotion updates were driven solely by memory hotplug events. But now, there are handlers for both CPU and memory hotplug. However, the #ifdef around the code checks only memory hotplug. A system that has HOTPLUG_CPU=y but MEMORY_HOTPLUG=n would miss CPU hotplug events. Update the #ifdef around the common code. Add memory and CPU-specific #ifdefs for their handlers. These memory/CPU #ifdefs avoid unused function warnings when their Kconfig option is off. [arnd@arndb.de: rework hotplug_memory_notifier() stub] Link: https://lkml.kernel.org/r/20211013144029.2154629-1-arnd@kernel.org Link: https://lkml.kernel.org/r/20210924161255.E5FE8F7E@davehans-spike.ostc.intel.com Fixes: 884a6e5d1f93 ("mm/migrate: update node demotion order on hotplug events") Signed-off-by: Dave Hansen Signed-off-by: Arnd Bergmann Cc: "Huang, Ying" Cc: Michal Hocko Cc: Wei Xu Cc: Oscar Salvador Cc: David Rientjes Cc: Dan Williams Cc: David Hildenbrand Cc: Greg Thelen Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 7efc0a7c14c9..182c606adb06 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -160,7 +160,10 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) #else -#define hotplug_memory_notifier(fn, pri) ({ 0; }) +static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) +{ + return 0; +} /* These aren't inline functions due to a GCC bug. */ #define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) #define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) -- cgit v1.2.3 From a6a0251c6fce496744121b4e08c899f45270dbcc Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 18 Oct 2021 15:15:35 -0700 Subject: mm/migrate: fix CPUHP state to update node demotion order The node demotion order needs to be updated during CPU hotplug. Because whether a NUMA node has CPU may influence the demotion order. The update function should be called during CPU online/offline after the node_states[N_CPU] has been updated. That is done in CPUHP_AP_ONLINE_DYN during CPU online and in CPUHP_MM_VMSTAT_DEAD during CPU offline. But in commit 884a6e5d1f93 ("mm/migrate: update node demotion order on hotplug events"), the function to update node demotion order is called in CPUHP_AP_ONLINE_DYN during CPU online/offline. This doesn't satisfy the order requirement. For example, there are 4 CPUs (P0, P1, P2, P3) in 2 sockets (P0, P1 in S0 and P2, P3 in S1), the demotion order is - S0 -> NUMA_NO_NODE - S1 -> NUMA_NO_NODE After P2 and P3 is offlined, because S1 has no CPU now, the demotion order should have been changed to - S0 -> S1 - S1 -> NO_NODE but it isn't changed, because the order updating callback for CPU hotplug doesn't see the new nodemask. After that, if P1 is offlined, the demotion order is changed to the expected order as above. So in this patch, we added CPUHP_AP_MM_DEMOTION_ONLINE and CPUHP_MM_DEMOTION_DEAD to be called after CPUHP_AP_ONLINE_DYN and CPUHP_MM_VMSTAT_DEAD during CPU online and offline, and register the update function on them. Link: https://lkml.kernel.org/r/20210929060351.7293-1-ying.huang@intel.com Fixes: 884a6e5d1f93 ("mm/migrate: update node demotion order on hotplug events") Signed-off-by: "Huang, Ying" Cc: Thomas Gleixner Cc: Dave Hansen Cc: Yang Shi Cc: Zi Yan Cc: Michal Hocko Cc: Wei Xu Cc: Oscar Salvador Cc: David Rientjes Cc: Dan Williams Cc: David Hildenbrand Cc: Greg Thelen Cc: Keith Busch Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuhotplug.h | 4 ++++ mm/migrate.c | 8 +++++--- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 832d8a74fa59..991911048857 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -72,6 +72,8 @@ enum cpuhp_state { CPUHP_SLUB_DEAD, CPUHP_DEBUG_OBJ_DEAD, CPUHP_MM_WRITEBACK_DEAD, + /* Must be after CPUHP_MM_VMSTAT_DEAD */ + CPUHP_MM_DEMOTION_DEAD, CPUHP_MM_VMSTAT_DEAD, CPUHP_SOFTIRQ_DEAD, CPUHP_NET_MVNETA_DEAD, @@ -240,6 +242,8 @@ enum cpuhp_state { CPUHP_AP_BASE_CACHEINFO_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, + /* Must be after CPUHP_AP_ONLINE_DYN for node_states[N_CPU] update */ + CPUHP_AP_MM_DEMOTION_ONLINE, CPUHP_AP_X86_HPET_ONLINE, CPUHP_AP_X86_KVM_CLK_ONLINE, CPUHP_AP_DTPM_CPU_ONLINE, diff --git a/mm/migrate.c b/mm/migrate.c index 700112c0123d..1852d787e6ab 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -3288,9 +3288,8 @@ static int __init migrate_on_reclaim_init(void) { int ret; - ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "migrate on reclaim", - migration_online_cpu, - migration_offline_cpu); + ret = cpuhp_setup_state_nocalls(CPUHP_MM_DEMOTION_DEAD, "mm/demotion:offline", + NULL, migration_offline_cpu); /* * In the unlikely case that this fails, the automatic * migration targets may become suboptimal for nodes @@ -3298,6 +3297,9 @@ static int __init migrate_on_reclaim_init(void) * rare case, do not bother trying to do anything special. */ WARN_ON(ret < 0); + ret = cpuhp_setup_state(CPUHP_AP_MM_DEMOTION_ONLINE, "mm/demotion:online", + migration_online_cpu, NULL); + WARN_ON(ret < 0); hotplug_memory_notifier(migrate_on_reclaim_callback, 100); return 0; -- cgit v1.2.3 From b0e901280d9860a0a35055f220e8e457f300f40a Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Mon, 18 Oct 2021 15:16:09 -0700 Subject: elfcore: correct reference to CONFIG_UML Commit 6e7b64b9dd6d ("elfcore: fix building with clang") introduces special handling for two architectures, ia64 and User Mode Linux. However, the wrong name, i.e., CONFIG_UM, for the intended Kconfig symbol for User-Mode Linux was used. Although the directory for User Mode Linux is ./arch/um; the Kconfig symbol for this architecture is called CONFIG_UML. Luckily, ./scripts/checkkconfigsymbols.py warns on non-existing configs: UM Referencing files: include/linux/elfcore.h Similar symbols: UML, NUMA Correct the name of the config to the intended one. [akpm@linux-foundation.org: fix um/x86_64, per Catalin] Link: https://lkml.kernel.org/r/20211006181119.2851441-1-catalin.marinas@arm.com Link: https://lkml.kernel.org/r/YV6pejGzLy5ppEpt@arm.com Link: https://lkml.kernel.org/r/20211006082209.417-1-lukas.bulwahn@gmail.com Fixes: 6e7b64b9dd6d ("elfcore: fix building with clang") Signed-off-by: Lukas Bulwahn Cc: Arnd Bergmann Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Catalin Marinas Cc: Barret Rhoden Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/elfcore.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 2aaa15779d50..957ebec35aad 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -109,7 +109,7 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg #endif } -#if defined(CONFIG_UM) || defined(CONFIG_IA64) +#if (defined(CONFIG_UML) && defined(CONFIG_X86_32)) || defined(CONFIG_IA64) /* * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out * extra segments containing the gate DSO contents. Dumping its -- cgit v1.2.3 From 79f9bc5843142b649575f887dccdf1c07ad75c20 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 18 Oct 2021 15:16:16 -0700 Subject: mm/secretmem: fix NULL page->mapping dereference in page_is_secretmem() Check for a NULL page->mapping before dereferencing the mapping in page_is_secretmem(), as the page's mapping can be nullified while gup() is running, e.g. by reclaim or truncation. BUG: kernel NULL pointer dereference, address: 0000000000000068 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 6 PID: 4173897 Comm: CPU 3/KVM Tainted: G W RIP: 0010:internal_get_user_pages_fast+0x621/0x9d0 Code: <48> 81 7a 68 80 08 04 bc 0f 85 21 ff ff 8 89 c7 be RSP: 0018:ffffaa90087679b0 EFLAGS: 00010046 RAX: ffffe3f37905b900 RBX: 00007f2dd561e000 RCX: ffffe3f37905b934 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffe3f37905b900 ... CR2: 0000000000000068 CR3: 00000004c5898003 CR4: 00000000001726e0 Call Trace: get_user_pages_fast_only+0x13/0x20 hva_to_pfn+0xa9/0x3e0 try_async_pf+0xa1/0x270 direct_page_fault+0x113/0xad0 kvm_mmu_page_fault+0x69/0x680 vmx_handle_exit+0xe1/0x5d0 kvm_arch_vcpu_ioctl_run+0xd81/0x1c70 kvm_vcpu_ioctl+0x267/0x670 __x64_sys_ioctl+0x83/0xa0 do_syscall_64+0x56/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Link: https://lkml.kernel.org/r/20211007231502.3552715-1-seanjc@google.com Fixes: 1507f51255c9 ("mm: introduce memfd_secret system call to create "secret" memory areas") Signed-off-by: Sean Christopherson Reported-by: Darrick J. Wong Reported-by: Stephen Tested-by: Darrick J. Wong Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/secretmem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 21c3771e6a56..988528b5da43 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -23,7 +23,7 @@ static inline bool page_is_secretmem(struct page *page) mapping = (struct address_space *) ((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS); - if (mapping != page->mapping) + if (!mapping || mapping != page->mapping) return false; return mapping->a_ops == &secretmem_aops; -- cgit v1.2.3