From 34dc2efb39a231280fd6696a59bbe712bf3c5c4a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 12 Mar 2021 21:07:01 -0800 Subject: memblock: fix section mismatch warning The inlining logic in clang-13 is rewritten to often not inline some functions that were inlined by all earlier compilers. In case of the memblock interfaces, this exposed a harmless bug of a missing __init annotation: WARNING: modpost: vmlinux.o(.text+0x507c0a): Section mismatch in reference from the function memblock_bottom_up() to the variable .meminit.data:memblock The function memblock_bottom_up() references the variable __meminitdata memblock. This is often because memblock_bottom_up lacks a __meminitdata annotation or the annotation of memblock is wrong. Interestingly, these annotations were present originally, but got removed with the explanation that the __init annotation prevents the function from getting inlined. I checked this again and found that while this is the case with clang, gcc (version 7 through 10, did not test others) does inline the functions regardless. As the previous change was apparently intended to help the clang builds, reverting it to help the newer clang versions seems appropriate as well. gcc builds don't seem to care either way. Link: https://lkml.kernel.org/r/20210225133808.2188581-1-arnd@kernel.org Fixes: 5bdba520c1b3 ("mm: memblock: drop __init from memblock functions to make it inline") Reference: 2cfb3665e864 ("include/linux/memblock.h: add __init to memblock_set_bottom_up()") Signed-off-by: Arnd Bergmann Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Faiyaz Mohammed Cc: Baoquan He Cc: Thomas Bogendoerfer Cc: Aslan Bakirov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index c88bc24e31aa..d13e3cd938b4 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -460,7 +460,7 @@ static inline void memblock_free_late(phys_addr_t base, phys_addr_t size) /* * Set the allocation direction to bottom-up or top-down. */ -static inline void memblock_set_bottom_up(bool enable) +static inline __init void memblock_set_bottom_up(bool enable) { memblock.bottom_up = enable; } @@ -470,7 +470,7 @@ static inline void memblock_set_bottom_up(bool enable) * if this is true, that said, memblock will allocate memory * in bottom-up direction. */ -static inline bool memblock_bottom_up(void) +static inline __init bool memblock_bottom_up(void) { return memblock.bottom_up; } -- cgit v1.3-14-g43fede From cbf78d85079cee662c45749ef4f744d41be85d48 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 12 Mar 2021 21:07:04 -0800 Subject: stop_machine: mark helpers __always_inline With clang-13, some functions only get partially inlined, with a specialized version referring to a global variable. This triggers a harmless build-time check for the intel-rng driver: WARNING: modpost: drivers/char/hw_random/intel-rng.o(.text+0xe): Section mismatch in reference from the function stop_machine() to the function .init.text:intel_rng_hw_init() The function stop_machine() references the function __init intel_rng_hw_init(). This is often because stop_machine lacks a __init annotation or the annotation of intel_rng_hw_init is wrong. In this instance, an easy workaround is to force the stop_machine() function to be inline, along with related interfaces that did not show the same behavior at the moment, but theoretically could. The combination of the two patches listed below triggers the behavior in clang-13, but individually these commits are correct. Link: https://lkml.kernel.org/r/20210225130153.1956990-1-arnd@kernel.org Fixes: fe5595c07400 ("stop_machine: Provide stop_machine_cpuslocked()") Fixes: ee527cd3a20c ("Use stop_machine_run in the Intel RNG driver") Signed-off-by: Arnd Bergmann Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Thomas Gleixner Cc: Sebastian Andrzej Siewior Cc: "Paul E. McKenney" Cc: Ingo Molnar Cc: Prarit Bhargava Cc: Daniel Bristot de Oliveira Cc: Peter Zijlstra Cc: Valentin Schneider Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stop_machine.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 30577c3aecf8..46fb3ebdd16e 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -128,7 +128,7 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); #else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ -static inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, +static __always_inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { unsigned long flags; @@ -139,14 +139,15 @@ static inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, return ret; } -static inline int stop_machine(cpu_stop_fn_t fn, void *data, - const struct cpumask *cpus) +static __always_inline int +stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { return stop_machine_cpuslocked(fn, data, cpus); } -static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, - const struct cpumask *cpus) +static __always_inline int +stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, + const struct cpumask *cpus) { return stop_machine(fn, data, cpus); } -- cgit v1.3-14-g43fede From 82e69a121be4b1597ce758534816a8ee04c8b761 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 12 Mar 2021 21:07:15 -0800 Subject: mm/fork: clear PASID for new mm When a new mm is created, its PASID should be cleared, i.e. the PASID is initialized to its init state 0 on both ARM and X86. This patch was part of the series introducing mm->pasid, but got lost along the way [1]. It still makes sense to have it, because each address space has a different PASID. And the IOMMU code in iommu_sva_alloc_pasid() expects the pasid field of a new mm struct to be cleared. [1] https://lore.kernel.org/linux-iommu/YDgh53AcQHT+T3L0@otcwcpicx3.sc.intel.com/ Link: https://lkml.kernel.org/r/20210302103837.2562625-1-jean-philippe@linaro.org Signed-off-by: Fenghua Yu Signed-off-by: Jean-Philippe Brucker Reviewed-by: Tony Luck Cc: Jacob Pan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 1 + kernel/fork.c | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0974ad501a47..6613b26a8894 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -23,6 +23,7 @@ #endif #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1)) +#define INIT_PASID 0 struct address_space; struct mem_cgroup; diff --git a/kernel/fork.c b/kernel/fork.c index d3171e8e88e5..54cc905e5fe0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -994,6 +994,13 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) #endif } +static void mm_init_pasid(struct mm_struct *mm) +{ +#ifdef CONFIG_IOMMU_SUPPORT + mm->pasid = INIT_PASID; +#endif +} + static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES @@ -1024,6 +1031,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); + mm_init_pasid(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); -- cgit v1.3-14-g43fede From 97a7e4733b9b221d012ae68fcd3b3251febf6341 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 12 Mar 2021 21:07:26 -0800 Subject: mm: introduce page_needs_cow_for_dma() for deciding whether cow We've got quite a few places (pte, pmd, pud) that explicitly checked against whether we should break the cow right now during fork(). It's easier to provide a helper, especially before we work the same thing on hugetlbfs. Since we'll reference is_cow_mapping() in mm.h, move it there too. Actually it suites mm.h more since internal.h is mm/ only, but mm.h is exported to the whole kernel. With that we should expect another patch to use is_cow_mapping() whenever we can across the kernel since we do use it quite a lot but it's always done with raw code against VM_* flags. Link: https://lkml.kernel.org/r/20210217233547.93892-4-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe Cc: Alexey Dobriyan Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: Daniel Vetter Cc: David Airlie Cc: David Gibson Cc: Gal Pressman Cc: Jan Kara Cc: Jann Horn Cc: Kirill Shutemov Cc: Kirill Tkhai Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mike Kravetz Cc: Mike Rapoport Cc: Roland Scheidegger Cc: VMware Graphics Cc: Wei Zhang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 21 +++++++++++++++++++++ mm/huge_memory.c | 8 ++------ mm/internal.h | 5 ----- mm/memory.c | 8 +------- 4 files changed, 24 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 77e64e3eac80..64a71bf20536 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1300,6 +1300,27 @@ static inline bool page_maybe_dma_pinned(struct page *page) GUP_PIN_COUNTING_BIAS; } +static inline bool is_cow_mapping(vm_flags_t flags) +{ + return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; +} + +/* + * This should most likely only be called during fork() to see whether we + * should break the cow immediately for a page on the src mm. + */ +static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, + struct page *page) +{ + if (!is_cow_mapping(vma->vm_flags)) + return false; + + if (!atomic_read(&vma->vm_mm->has_pinned)) + return false; + + return page_maybe_dma_pinned(page); +} + #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 395c75111d33..da1d63a41aec 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1100,9 +1100,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, * best effort that the pinned pages won't be replaced by another * random page during the coming copy-on-write. */ - if (unlikely(is_cow_mapping(vma->vm_flags) && - atomic_read(&src_mm->has_pinned) && - page_maybe_dma_pinned(src_page))) { + if (unlikely(page_needs_cow_for_dma(vma, src_page))) { pte_free(dst_mm, pgtable); spin_unlock(src_ptl); spin_unlock(dst_ptl); @@ -1214,9 +1212,7 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, } /* Please refer to comments in copy_huge_pmd() */ - if (unlikely(is_cow_mapping(vma->vm_flags) && - atomic_read(&src_mm->has_pinned) && - page_maybe_dma_pinned(pud_page(pud)))) { + if (unlikely(page_needs_cow_for_dma(vma, pud_page(pud)))) { spin_unlock(src_ptl); spin_unlock(dst_ptl); __split_huge_pud(vma, src_pud, addr); diff --git a/mm/internal.h b/mm/internal.h index 9902648f2206..1432feec62df 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -296,11 +296,6 @@ static inline unsigned int buddy_order(struct page *page) */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) -static inline bool is_cow_mapping(vm_flags_t flags) -{ - return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; -} - /* * These three helpers classifies VMAs for virtual memory accounting. */ diff --git a/mm/memory.c b/mm/memory.c index c8e357627318..523230005db1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -809,12 +809,8 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc, pte_t pte, struct page *page) { - struct mm_struct *src_mm = src_vma->vm_mm; struct page *new_page; - if (!is_cow_mapping(src_vma->vm_flags)) - return 1; - /* * What we want to do is to check whether this page may * have been pinned by the parent process. If so, @@ -828,9 +824,7 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma * the page count. That might give false positives for * for pinning, but it will work correctly. */ - if (likely(!atomic_read(&src_mm->has_pinned))) - return 1; - if (likely(!page_maybe_dma_pinned(page))) + if (likely(!page_needs_cow_for_dma(src_vma, page))) return 1; new_page = *prealloc; -- cgit v1.3-14-g43fede From 97e4910232fa1f81e806aa60c25a0450276d99a2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 12 Mar 2021 21:07:47 -0800 Subject: linux/compiler-clang.h: define HAVE_BUILTIN_BSWAP* Separating compiler-clang.h from compiler-gcc.h inadventently dropped the definitions of the three HAVE_BUILTIN_BSWAP macros, which requires falling back to the open-coded version and hoping that the compiler detects it. Since all versions of clang support the __builtin_bswap interfaces, add back the flags and have the headers pick these up automatically. This results in a 4% improvement of compilation speed for arm defconfig. Note: it might also be worth revisiting which architectures set CONFIG_ARCH_USE_BUILTIN_BSWAP for one compiler or the other, today this is set on six architectures (arm32, csky, mips, powerpc, s390, x86), while another ten architectures define custom helpers (alpha, arc, ia64, m68k, mips, nios2, parisc, sh, sparc, xtensa), and the rest (arm64, h8300, hexagon, microblaze, nds32, openrisc, riscv) just get the unoptimized version and rely on the compiler to detect it. A long time ago, the compiler builtins were architecture specific, but nowadays, all compilers that are able to build the kernel have correct implementations of them, though some may not be as optimized as the inline asm versions. The patch that dropped the optimization landed in v4.19, so as discussed it would be fairly safe to backport this revert to stable kernels to the 4.19/5.4/5.10 stable kernels, but there is a remaining risk for regressions, and it has no known side-effects besides compile speed. Link: https://lkml.kernel.org/r/20210226161151.2629097-1-arnd@kernel.org Link: https://lore.kernel.org/lkml/20210225164513.3667778-1-arnd@kernel.org/ Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Signed-off-by: Arnd Bergmann Reviewed-by: Nathan Chancellor Reviewed-by: Kees Cook Acked-by: Miguel Ojeda Acked-by: Nick Desaulniers Acked-by: Luc Van Oostenryck Cc: Masahiro Yamada Cc: Nick Hu Cc: Greentime Hu Cc: Vincent Chen Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Guo Ren Cc: Randy Dunlap Cc: Sami Tolvanen Cc: Marco Elver Cc: Arvind Sankar Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-clang.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 04c0a5a717f7..d217c382b02d 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -31,6 +31,12 @@ #define __no_sanitize_thread #endif +#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) +#define __HAVE_BUILTIN_BSWAP32__ +#define __HAVE_BUILTIN_BSWAP64__ +#define __HAVE_BUILTIN_BSWAP16__ +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ + #if __has_feature(undefined_behavior_sanitizer) /* GCC does not have __SANITIZE_UNDEFINED__ */ #define __no_sanitize_undefined \ -- cgit v1.3-14-g43fede From 149fc787353f65b7e72e05e7b75d34863266c3e2 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 12 Mar 2021 21:08:03 -0800 Subject: include/linux/sched/mm.h: use rcu_dereference in in_vfork() Fix a sparse warning by using rcu_dereference(). Technically this is a bug and a sufficiently aggressive compiler could reload the `real_parent' pointer outside the protection of the rcu lock (and access freed memory), but I think it's pretty unlikely to happen. Link: https://lkml.kernel.org/r/20210221194207.1351703-1-willy@infradead.org Fixes: b18dc5f291c0 ("mm, oom: skip vforked tasks from being selected") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Miaohe Lin Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 1ae08b8462a4..90b2a0bce11c 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -140,7 +140,8 @@ static inline bool in_vfork(struct task_struct *tsk) * another oom-unkillable task does this it should blame itself. */ rcu_read_lock(); - ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm; + ret = tsk->vfork_done && + rcu_dereference(tsk->real_parent)->mm == tsk->mm; rcu_read_unlock(); return ret; -- cgit v1.3-14-g43fede From be6c8982e4ab9a41907555f601b711a7e2a17d4c Mon Sep 17 00:00:00 2001 From: Zhou Guanghui Date: Fri, 12 Mar 2021 21:08:30 -0800 Subject: mm/memcg: rename mem_cgroup_split_huge_fixup to split_page_memcg and add nr_pages argument Rename mem_cgroup_split_huge_fixup to split_page_memcg and explicitly pass in page number argument. In this way, the interface name is more common and can be used by potential users. In addition, the complete info(memcg and flag) of the memcg needs to be set to the tail pages. Link: https://lkml.kernel.org/r/20210304074053.65527-2-zhouguanghui1@huawei.com Signed-off-by: Zhou Guanghui Acked-by: Johannes Weiner Reviewed-by: Zi Yan Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Nicholas Piggin Cc: Kefeng Wang Cc: Hanjun Guo Cc: Tianhong Ding Cc: Weilong Chen Cc: Rui Xiang Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++---- mm/huge_memory.c | 2 +- mm/memcontrol.c | 15 ++++++--------- 3 files changed, 9 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e6dc793d587d..0c04d39a7967 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1061,9 +1061,7 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, rcu_read_unlock(); } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -void mem_cgroup_split_huge_fixup(struct page *head); -#endif +void split_page_memcg(struct page *head, unsigned int nr); #else /* CONFIG_MEMCG */ @@ -1400,7 +1398,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, return 0; } -static inline void mem_cgroup_split_huge_fixup(struct page *head) +static inline void split_page_memcg(struct page *head, unsigned int nr) { } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index da1d63a41aec..ae907a9c2050 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2467,7 +2467,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, int i; /* complete memcg works before add pages to LRU */ - mem_cgroup_split_huge_fixup(head); + split_page_memcg(head, nr); if (PageAnon(head) && PageSwapCache(head)) { swp_entry_t entry = { .val = page_private(head) }; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 845eec01ef9d..e064ac0d850a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3287,24 +3287,21 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) #endif /* CONFIG_MEMCG_KMEM */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* - * Because page_memcg(head) is not set on compound tails, set it now. + * Because page_memcg(head) is not set on tails, set it now. */ -void mem_cgroup_split_huge_fixup(struct page *head) +void split_page_memcg(struct page *head, unsigned int nr) { struct mem_cgroup *memcg = page_memcg(head); int i; - if (mem_cgroup_disabled()) + if (mem_cgroup_disabled() || !memcg) return; - for (i = 1; i < HPAGE_PMD_NR; i++) { - css_get(&memcg->css); - head[i].memcg_data = (unsigned long)memcg; - } + for (i = 1; i < nr; i++) + head[i].memcg_data = head->memcg_data; + css_get_many(&memcg->css, nr - 1); } -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifdef CONFIG_MEMCG_SWAP /** -- cgit v1.3-14-g43fede