From cd16dd03737c30608b78d235b17b3ab935ed18db Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 25 May 2022 15:52:20 -0400 Subject: mm/x86: remove dead code for hugetlbpage.c It seems to exist since the old times and never used once. Remove them. Link: https://lkml.kernel.org/r/20220525195220.10241-1-peterx@redhat.com Signed-off-by: Peter Xu Acked-by: Muchun Song Signed-off-by: Andrew Morton --- arch/x86/mm/hugetlbpage.c | 39 --------------------------------------- 1 file changed, 39 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index a0d023cb4292..509408da0da1 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -19,44 +19,6 @@ #include #include -#if 0 /* This is just for testing */ -struct page * -follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) -{ - unsigned long start = address; - int length = 1; - int nr; - struct page *page; - struct vm_area_struct *vma; - - vma = find_vma(mm, addr); - if (!vma || !is_vm_hugetlb_page(vma)) - return ERR_PTR(-EINVAL); - - pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); - - /* hugetlb should be locked, and hence, prefaulted */ - WARN_ON(!pte || pte_none(*pte)); - - page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)]; - - WARN_ON(!PageHead(page)); - - return page; -} - -int pmd_huge(pmd_t pmd) -{ - return 0; -} - -int pud_huge(pud_t pud) -{ - return 0; -} - -#else - /* * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. @@ -72,7 +34,6 @@ int pud_huge(pud_t pud) { return !!(pud_val(pud) & _PAGE_PSE); } -#endif #ifdef CONFIG_HUGETLB_PAGE static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, -- cgit v1.2.3 From d92725256b4f22d084b813b37ddc394da79aacab Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 30 May 2022 14:34:50 -0400 Subject: mm: avoid unnecessary page fault retires on shared memory types I observed that for each of the shared file-backed page faults, we're very likely to retry one more time for the 1st write fault upon no page. It's because we'll need to release the mmap lock for dirty rate limit purpose with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()). Then after that throttling we return VM_FAULT_RETRY. We did that probably because VM_FAULT_RETRY is the only way we can return to the fault handler at that time telling it we've released the mmap lock. However that's not ideal because it's very likely the fault does not need to be retried at all since the pgtable was well installed before the throttling, so the next continuous fault (including taking mmap read lock, walk the pgtable, etc.) could be in most cases unnecessary. It's not only slowing down page faults for shared file-backed, but also add more mmap lock contention which is in most cases not needed at all. To observe this, one could try to write to some shmem page and look at "pgfault" value in /proc/vmstat, then we should expect 2 counts for each shmem write simply because we retried, and vm event "pgfault" will capture that. To make it more efficient, add a new VM_FAULT_COMPLETED return code just to show that we've completed the whole fault and released the lock. It's also a hint that we should very possibly not need another fault immediately on this page because we've just completed it. This patch provides a ~12% perf boost on my aarch64 test VM with a simple program sequentially dirtying 400MB shmem file being mmap()ed and these are the time it needs: Before: 650.980 ms (+-1.94%) After: 569.396 ms (+-1.38%) I believe it could help more than that. We need some special care on GUP and the s390 pgfault handler (for gmap code before returning from pgfault), the rest changes in the page fault handlers should be relatively straightforward. Another thing to mention is that mm_account_fault() does take this new fault as a generic fault to be accounted, unlike VM_FAULT_RETRY. I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping them as-is. Link: https://lkml.kernel.org/r/20220530183450.42886-1-peterx@redhat.com Signed-off-by: Peter Xu Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Acked-by: Vineet Gupta Acked-by: Guo Ren Acked-by: Max Filippov Acked-by: Christian Borntraeger Acked-by: Michael Ellerman (powerpc) Acked-by: Catalin Marinas Reviewed-by: Alistair Popple Reviewed-by: Ingo Molnar Acked-by: Russell King (Oracle) [arm part] Acked-by: Heiko Carstens Cc: Vasily Gorbik Cc: Stafford Horne Cc: David S. Miller Cc: Johannes Berg Cc: Brian Cain Cc: Richard Henderson Cc: Richard Weinberger Cc: Benjamin Herrenschmidt Cc: Thomas Gleixner Cc: Janosch Frank Cc: Albert Ou Cc: Anton Ivanov Cc: Dave Hansen Cc: Borislav Petkov Cc: Sven Schnelle Cc: Andrea Arcangeli Cc: James Bottomley Cc: Al Viro Cc: Alexander Gordeev Cc: Jonas Bonn Cc: Will Deacon Cc: Vlastimil Babka Cc: Michal Simek Cc: Matt Turner Cc: Paul Mackerras Cc: David Hildenbrand Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Stefan Kristiansson Cc: Paul Walmsley Cc: Ivan Kokshaysky Cc: Chris Zankel Cc: Hugh Dickins Cc: Dinh Nguyen Cc: Rich Felker Cc: H. Peter Anvin Cc: Andy Lutomirski Cc: Thomas Bogendoerfer Cc: Helge Deller Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/alpha/mm/fault.c | 4 ++++ arch/arc/mm/fault.c | 4 ++++ arch/arm/mm/fault.c | 4 ++++ arch/arm64/mm/fault.c | 4 ++++ arch/csky/mm/fault.c | 4 ++++ arch/hexagon/mm/vm_fault.c | 4 ++++ arch/ia64/mm/fault.c | 4 ++++ arch/m68k/mm/fault.c | 4 ++++ arch/microblaze/mm/fault.c | 4 ++++ arch/mips/mm/fault.c | 4 ++++ arch/nios2/mm/fault.c | 4 ++++ arch/openrisc/mm/fault.c | 4 ++++ arch/parisc/mm/fault.c | 4 ++++ arch/powerpc/mm/copro_fault.c | 5 +++++ arch/powerpc/mm/fault.c | 5 +++++ arch/riscv/mm/fault.c | 4 ++++ arch/s390/mm/fault.c | 12 ++++++++++++ arch/sh/mm/fault.c | 4 ++++ arch/sparc/mm/fault_32.c | 4 ++++ arch/sparc/mm/fault_64.c | 5 +++++ arch/um/kernel/trap.c | 4 ++++ arch/x86/mm/fault.c | 4 ++++ arch/xtensa/mm/fault.c | 4 ++++ include/linux/mm_types.h | 2 ++ mm/gup.c | 34 +++++++++++++++++++++++++++++++++- mm/memory.c | 2 +- 26 files changed, 139 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index ec20c1004abf..ef427a6bdd1a 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -155,6 +155,10 @@ retry: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index dad27e4d69ff..5ca59a482632 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -146,6 +146,10 @@ retry: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * Fault retry nuances, mmap_lock already relinquished by core mm */ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a062e07516dd..46cccd6bf705 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -322,6 +322,10 @@ retry: return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index c5e11768e5c1..de166cdeb89a 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -608,6 +608,10 @@ retry: return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 7215a46b6b8e..e15f736cca4b 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -285,6 +285,10 @@ good_area: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 4fac4b9eb316..f73c7cbfe326 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -96,6 +96,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (fault & VM_FAULT_RETRY) { diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 07379d1a227f..ef78c2d66cdd 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -139,6 +139,10 @@ retry: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 71aa9f6315dc..4d2837eb3e2a 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -141,6 +141,10 @@ good_area: if (fault_signal_pending(fault, regs)) return 0; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a9626e6a68af..5c40c3ebe52f 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -222,6 +222,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index b08bc556d30d..a27045f5a556 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -162,6 +162,10 @@ good_area: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index a32f14cd72f2..edaca0a6c1c1 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -139,6 +139,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 53b760af3bb7..b4762d66e9ef 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -165,6 +165,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 84bc437be5cd..9ad80d4d3389 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -311,6 +311,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We hit a shared mapping outside of the file, or some diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index c1cb21a00884..7c507fb48182 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -65,6 +65,11 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, ret = 0; *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); + + /* The fault is fully completed (including releasing mmap lock) */ + if (*flt & VM_FAULT_COMPLETED) + return 0; + if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d53fed4eccbd..014005428687 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -511,6 +511,10 @@ retry: if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto out; + /* * Handle the retry right now, the mmap_lock has been released in that * case. @@ -525,6 +529,7 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); +out: /* * Major/minor page fault accounting. */ diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 40694f0cab9e..f2fbd1400b7c 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -326,6 +326,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e173b6187ad5..973dcd05c293 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,6 +433,17 @@ retry: goto out_up; goto out; } + + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) { + if (gmap) { + mmap_read_lock(mm); + goto out_gmap; + } + fault = 0; + goto out; + } + if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; @@ -452,6 +463,7 @@ retry: mmap_read_lock(mm); goto retry; } +out_gmap: if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index e175667b1363..acd2f5e50bfc 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -485,6 +485,10 @@ good_area: if (mm_fault_error(regs, error_code, address, fault)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index ad569d9bd124..91259f291c54 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -190,6 +190,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 253e07043298..4acc12eafbf5 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -427,6 +427,10 @@ good_area: if (fault_signal_pending(fault, regs)) goto exit_exception; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto lock_released; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -449,6 +453,7 @@ good_area: } mmap_read_unlock(mm); +lock_released: mm_rss = get_mm_rss(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE)); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index d1d5d0be0308..d3ce21c4ca32 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -76,6 +76,10 @@ good_area: if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fad8faa29d04..fe10c6d76bac 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1408,6 +1408,10 @@ good_area: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 16f0a5ff5799..8c781b05c0bd 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -172,6 +172,10 @@ good_area: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c29ab4c0cd5c..6b961a29bf26 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -729,6 +729,7 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) + * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -746,6 +747,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; diff --git a/mm/gup.c b/mm/gup.c index 551264407624..407a81d5ca03 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -951,6 +951,25 @@ static int faultin_page(struct vm_area_struct *vma, } ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * With FAULT_FLAG_RETRY_NOWAIT we'll never release the + * mmap lock in the page fault handler. Sanity check this. + */ + WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); + if (locked) + *locked = 0; + /* + * We should do the same as VM_FAULT_RETRY, but let's not + * return -EBUSY since that's not reflecting the reality of + * what has happened - we've just fully completed a page + * fault, with the mmap lock released. Use -EAGAIN to show + * that we want to take the mmap lock _again_. + */ + return -EAGAIN; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -1177,6 +1196,7 @@ retry: case 0: goto retry; case -EBUSY: + case -EAGAIN: ret = 0; fallthrough; case -EFAULT: @@ -1303,6 +1323,18 @@ retry: return -EINTR; ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * NOTE: it's a pity that we need to retake the lock here + * to pair with the unlock() in the callers. Ideally we + * could tell the callers so they do not need to unlock. + */ + mmap_read_lock(mm); + *unlocked = true; + return 0; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1368,7 +1400,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, /* VM_FAULT_RETRY couldn't trigger, bypass */ return ret; - /* VM_FAULT_RETRY cannot return errors */ + /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 7a089145cad4..580c62febe42 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3020,7 +3020,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); - return VM_FAULT_RETRY; + return VM_FAULT_COMPLETED; } } -- cgit v1.2.3 From e33c267ab70de4249d22d7eab1cc7d68a889bac2 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 31 May 2022 20:22:24 -0700 Subject: mm: shrinkers: provide shrinkers with names Currently shrinkers are anonymous objects. For debugging purposes they can be identified by count/scan function names, but it's not always useful: e.g. for superblock's shrinkers it's nice to have at least an idea of to which superblock the shrinker belongs. This commit adds names to shrinkers. register_shrinker() and prealloc_shrinker() functions are extended to take a format and arguments to master a name. In some cases it's not possible to determine a good name at the time when a shrinker is allocated. For such cases shrinker_debugfs_rename() is provided. The expected format is: -[:]- For some shrinkers an instance can be encoded as (MAJOR:MINOR) pair. After this change the shrinker debugfs directory looks like: $ cd /sys/kernel/debug/shrinker/ $ ls dquota-cache-16 sb-devpts-28 sb-proc-47 sb-tmpfs-42 mm-shadow-18 sb-devtmpfs-5 sb-proc-48 sb-tmpfs-43 mm-zspool:zram0-34 sb-hugetlbfs-17 sb-pstore-31 sb-tmpfs-44 rcu-kfree-0 sb-hugetlbfs-33 sb-rootfs-2 sb-tmpfs-49 sb-aio-20 sb-iomem-12 sb-securityfs-6 sb-tracefs-13 sb-anon_inodefs-15 sb-mqueue-21 sb-selinuxfs-22 sb-xfs:vda1-36 sb-bdev-3 sb-nsfs-4 sb-sockfs-8 sb-zsmalloc-19 sb-bpf-32 sb-pipefs-14 sb-sysfs-26 thp-deferred_split-10 sb-btrfs:vda2-24 sb-proc-25 sb-tmpfs-1 thp-zero-9 sb-cgroup2-30 sb-proc-39 sb-tmpfs-27 xfs-buf:vda1-37 sb-configfs-23 sb-proc-41 sb-tmpfs-29 xfs-inodegc:vda1-38 sb-dax-11 sb-proc-45 sb-tmpfs-35 sb-debugfs-7 sb-proc-46 sb-tmpfs-40 [roman.gushchin@linux.dev: fix build warnings] Link: https://lkml.kernel.org/r/Yr+ZTnLb9lJk6fJO@castle Reported-by: kernel test robot Link: https://lkml.kernel.org/r/20220601032227.4076670-4-roman.gushchin@linux.dev Signed-off-by: Roman Gushchin Cc: Christophe JAILLET Cc: Dave Chinner Cc: Hillf Danton Cc: Kent Overstreet Cc: Muchun Song Signed-off-by: Andrew Morton --- arch/x86/kvm/mmu/mmu.c | 2 +- drivers/android/binder_alloc.c | 2 +- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 3 +- drivers/gpu/drm/msm/msm_gem_shrinker.c | 2 +- drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c | 2 +- drivers/gpu/drm/ttm/ttm_pool.c | 2 +- drivers/md/bcache/btree.c | 2 +- drivers/md/dm-bufio.c | 3 +- drivers/md/dm-zoned-metadata.c | 4 +- drivers/md/raid5.c | 2 +- drivers/misc/vmw_balloon.c | 2 +- drivers/virtio/virtio_balloon.c | 2 +- drivers/xen/xenbus/xenbus_probe_backend.c | 2 +- fs/btrfs/super.c | 2 + fs/erofs/utils.c | 2 +- fs/ext4/extents_status.c | 3 +- fs/f2fs/super.c | 2 +- fs/gfs2/glock.c | 2 +- fs/gfs2/main.c | 2 +- fs/jbd2/journal.c | 3 +- fs/mbcache.c | 2 +- fs/nfs/nfs42xattr.c | 7 +-- fs/nfs/super.c | 2 +- fs/nfsd/filecache.c | 2 +- fs/nfsd/nfscache.c | 3 +- fs/quota/dquot.c | 2 +- fs/super.c | 6 ++- fs/ubifs/super.c | 2 +- fs/xfs/xfs_buf.c | 3 +- fs/xfs/xfs_icache.c | 2 +- fs/xfs/xfs_qm.c | 3 +- include/linux/shrinker.h | 14 +++++- kernel/rcu/tree.c | 2 +- mm/huge_memory.c | 4 +- mm/shrinker_debug.c | 47 ++++++++++++++++++- mm/vmscan.c | 58 ++++++++++++++++++++++-- mm/workingset.c | 2 +- mm/zsmalloc.c | 3 +- net/sunrpc/auth.c | 2 +- 39 files changed, 167 insertions(+), 45 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 17252f39bd7c..797d3286ecc1 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6317,7 +6317,7 @@ int kvm_mmu_vendor_module_init(void) if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL)) goto out; - ret = register_shrinker(&mmu_shrinker); + ret = register_shrinker(&mmu_shrinker, "x86-mmu"); if (ret) goto out; diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 5649a0371a1f..51b502217d00 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -1084,7 +1084,7 @@ int binder_alloc_shrinker_init(void) int ret = list_lru_init(&binder_alloc_lru); if (ret == 0) { - ret = register_shrinker(&binder_shrinker); + ret = register_shrinker(&binder_shrinker, "android-binder"); if (ret) list_lru_destroy(&binder_alloc_lru); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 6a6ff98a8746..e43577e03067 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -426,7 +426,8 @@ void i915_gem_driver_register__shrinker(struct drm_i915_private *i915) i915->mm.shrinker.count_objects = i915_gem_shrinker_count; i915->mm.shrinker.seeks = DEFAULT_SEEKS; i915->mm.shrinker.batch = 4096; - drm_WARN_ON(&i915->drm, register_shrinker(&i915->mm.shrinker)); + drm_WARN_ON(&i915->drm, register_shrinker(&i915->mm.shrinker, + "drm-i915_gem")); i915->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom; drm_WARN_ON(&i915->drm, register_oom_notifier(&i915->mm.oom_notifier)); diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 086dacf2f26a..26e84d2ea6ae 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -221,7 +221,7 @@ void msm_gem_shrinker_init(struct drm_device *dev) priv->shrinker.count_objects = msm_gem_shrinker_count; priv->shrinker.scan_objects = msm_gem_shrinker_scan; priv->shrinker.seeks = DEFAULT_SEEKS; - WARN_ON(register_shrinker(&priv->shrinker)); + WARN_ON(register_shrinker(&priv->shrinker, "drm-msm_gem")); priv->vmap_notifier.notifier_call = msm_gem_shrinker_vmap; WARN_ON(register_vmap_purge_notifier(&priv->vmap_notifier)); diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c index 77e7cb6d1ae3..bf0170782f25 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c @@ -103,7 +103,7 @@ void panfrost_gem_shrinker_init(struct drm_device *dev) pfdev->shrinker.count_objects = panfrost_gem_shrinker_count; pfdev->shrinker.scan_objects = panfrost_gem_shrinker_scan; pfdev->shrinker.seeks = DEFAULT_SEEKS; - WARN_ON(register_shrinker(&pfdev->shrinker)); + WARN_ON(register_shrinker(&pfdev->shrinker, "drm-panfrost")); } /** diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 1bba0a0ed3f9..21b61631f73a 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -722,7 +722,7 @@ int ttm_pool_mgr_init(unsigned long num_pages) mm_shrinker.count_objects = ttm_pool_shrinker_count; mm_shrinker.scan_objects = ttm_pool_shrinker_scan; mm_shrinker.seeks = 1; - return register_shrinker(&mm_shrinker); + return register_shrinker(&mm_shrinker, "drm-ttm_pool"); } /** diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index e136d6edc1ed..147c493a989a 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -812,7 +812,7 @@ int bch_btree_cache_alloc(struct cache_set *c) c->shrink.seeks = 4; c->shrink.batch = c->btree_pages * 2; - if (register_shrinker(&c->shrink)) + if (register_shrinker(&c->shrink, "md-bcache:%pU", c->set_uuid)) pr_warn("bcache: %s: could not register shrinker\n", __func__); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 5ffa1dcf84cf..3ff571b20f14 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1806,7 +1806,8 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign c->shrinker.scan_objects = dm_bufio_shrink_scan; c->shrinker.seeks = 1; c->shrinker.batch = 0; - r = register_shrinker(&c->shrinker); + r = register_shrinker(&c->shrinker, "md-%s:(%u:%u)", slab_name, + MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); if (r) goto bad; diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index d1ea66114d14..46648f6100fb 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -2944,7 +2944,9 @@ int dmz_ctr_metadata(struct dmz_dev *dev, int num_dev, zmd->mblk_shrinker.seeks = DEFAULT_SEEKS; /* Metadata cache shrinker */ - ret = register_shrinker(&zmd->mblk_shrinker); + ret = register_shrinker(&zmd->mblk_shrinker, "md-meta:(%u:%u)", + MAJOR(dev->bdev->bd_dev), + MINOR(dev->bdev->bd_dev)); if (ret) { dmz_zmd_err(zmd, "Register metadata cache shrinker failed"); goto err; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 5d09256d7f81..780ae66840b7 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7414,7 +7414,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf->shrinker.count_objects = raid5_cache_count; conf->shrinker.batch = 128; conf->shrinker.flags = 0; - ret = register_shrinker(&conf->shrinker); + ret = register_shrinker(&conf->shrinker, "md-raid5:%s", mdname(mddev)); if (ret) { pr_warn("md/raid:%s: couldn't register shrinker.\n", mdname(mddev)); diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c index 086ce77d9074..c2d2fa114e65 100644 --- a/drivers/misc/vmw_balloon.c +++ b/drivers/misc/vmw_balloon.c @@ -1587,7 +1587,7 @@ static int vmballoon_register_shrinker(struct vmballoon *b) b->shrinker.count_objects = vmballoon_shrinker_count; b->shrinker.seeks = DEFAULT_SEEKS; - r = register_shrinker(&b->shrinker); + r = register_shrinker(&b->shrinker, "vmw-balloon"); if (r == 0) b->shrinker_registered = true; diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index b9737da6c4dd..cba57b1f382f 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -875,7 +875,7 @@ static int virtio_balloon_register_shrinker(struct virtio_balloon *vb) vb->shrinker.count_objects = virtio_balloon_shrinker_count; vb->shrinker.seeks = DEFAULT_SEEKS; - return register_shrinker(&vb->shrinker); + return register_shrinker(&vb->shrinker, "virtio-balloon"); } static int virtballoon_probe(struct virtio_device *vdev) diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c index 5abded97e1a7..9c09f89d8278 100644 --- a/drivers/xen/xenbus/xenbus_probe_backend.c +++ b/drivers/xen/xenbus/xenbus_probe_backend.c @@ -305,7 +305,7 @@ static int __init xenbus_probe_backend_init(void) register_xenstore_notifier(&xenstore_notifier); - if (register_shrinker(&backend_memory_shrinker)) + if (register_shrinker(&backend_memory_shrinker, "xen-backend")) pr_warn("shrinker registration failed\n"); return 0; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 6627dd7875ee..eee3e96d877f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1815,6 +1815,8 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, error = -EBUSY; } else { snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); + shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name, + s->s_id); btrfs_sb(s)->bdev_holder = fs_type; if (!strstr(crc32c_impl(), "generic")) set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c index ec9a1d780dc1..46627cb69abe 100644 --- a/fs/erofs/utils.c +++ b/fs/erofs/utils.c @@ -282,7 +282,7 @@ static struct shrinker erofs_shrinker_info = { int __init erofs_init_shrinker(void) { - return register_shrinker(&erofs_shrinker_info); + return register_shrinker(&erofs_shrinker_info, "erofs-shrinker"); } void erofs_exit_shrinker(void) diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 9a3a8996aacf..23167efda95e 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -1654,7 +1654,8 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi) sbi->s_es_shrinker.scan_objects = ext4_es_scan; sbi->s_es_shrinker.count_objects = ext4_es_count; sbi->s_es_shrinker.seeks = DEFAULT_SEEKS; - err = register_shrinker(&sbi->s_es_shrinker); + err = register_shrinker(&sbi->s_es_shrinker, "ext4-es:%s", + sbi->s_sb->s_id); if (err) goto err4; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 37221e94e5ef..bce02306f7a0 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -4579,7 +4579,7 @@ static int __init init_f2fs_fs(void) err = f2fs_init_sysfs(); if (err) goto free_garbage_collection_cache; - err = register_shrinker(&f2fs_shrinker_info); + err = register_shrinker(&f2fs_shrinker_info, "f2fs-shrinker"); if (err) goto free_sysfs; err = register_filesystem(&f2fs_fs_type); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index c992d53013d3..dca842379cab 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -2533,7 +2533,7 @@ int __init gfs2_glock_init(void) return -ENOMEM; } - ret = register_shrinker(&glock_shrinker); + ret = register_shrinker(&glock_shrinker, "gfs2-glock"); if (ret) { destroy_workqueue(gfs2_delete_workqueue); destroy_workqueue(glock_workqueue); diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 244187e3e70f..b66a3e1ec152 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -148,7 +148,7 @@ static int __init init_gfs2_fs(void) if (!gfs2_trans_cachep) goto fail_cachep8; - error = register_shrinker(&gfs2_qd_shrinker); + error = register_shrinker(&gfs2_qd_shrinker, "gfs2-qd"); if (error) goto fail_shrinker; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index c0cbeeaec2d1..45e4655c8033 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1418,7 +1418,8 @@ static journal_t *journal_init_common(struct block_device *bdev, if (percpu_counter_init(&journal->j_checkpoint_jh_count, 0, GFP_KERNEL)) goto err_cleanup; - if (register_shrinker(&journal->j_shrinker)) { + if (register_shrinker(&journal->j_shrinker, "jbd2-journal:(%u:%u)", + MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev))) { percpu_counter_destroy(&journal->j_checkpoint_jh_count); goto err_cleanup; } diff --git a/fs/mbcache.c b/fs/mbcache.c index 97c54d3a2227..0b833da0a9a5 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -367,7 +367,7 @@ struct mb_cache *mb_cache_create(int bucket_bits) cache->c_shrink.count_objects = mb_cache_count; cache->c_shrink.scan_objects = mb_cache_scan; cache->c_shrink.seeks = DEFAULT_SEEKS; - if (register_shrinker(&cache->c_shrink)) { + if (register_shrinker(&cache->c_shrink, "mbcache-shrinker")) { kfree(cache->c_hash); kfree(cache); goto err_out; diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index e7b34f7e0614..a9bf09fdf2c3 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -1017,15 +1017,16 @@ int __init nfs4_xattr_cache_init(void) if (ret) goto out2; - ret = register_shrinker(&nfs4_xattr_cache_shrinker); + ret = register_shrinker(&nfs4_xattr_cache_shrinker, "nfs-xattr_cache"); if (ret) goto out1; - ret = register_shrinker(&nfs4_xattr_entry_shrinker); + ret = register_shrinker(&nfs4_xattr_entry_shrinker, "nfs-xattr_entry"); if (ret) goto out; - ret = register_shrinker(&nfs4_xattr_large_entry_shrinker); + ret = register_shrinker(&nfs4_xattr_large_entry_shrinker, + "nfs-xattr_large_entry"); if (!ret) return 0; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 6ab5eeb000dc..82944e14fcea 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -149,7 +149,7 @@ int __init register_nfs_fs(void) ret = nfs_register_sysctl(); if (ret < 0) goto error_2; - ret = register_shrinker(&acl_shrinker); + ret = register_shrinker(&acl_shrinker, "nfs-acl"); if (ret < 0) goto error_3; #ifdef CONFIG_NFS_V4_2 diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 9cb2d590c036..a605c0e39b09 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -670,7 +670,7 @@ nfsd_file_cache_init(void) goto out_err; } - ret = register_shrinker(&nfsd_file_shrinker); + ret = register_shrinker(&nfsd_file_shrinker, "nfsd-filecache"); if (ret) { pr_err("nfsd: failed to register nfsd_file_shrinker: %d\n", ret); goto out_lru; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 7da88bdc0d6c..9b31e1103e7b 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -176,7 +176,8 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) nn->nfsd_reply_cache_shrinker.scan_objects = nfsd_reply_cache_scan; nn->nfsd_reply_cache_shrinker.count_objects = nfsd_reply_cache_count; nn->nfsd_reply_cache_shrinker.seeks = 1; - status = register_shrinker(&nn->nfsd_reply_cache_shrinker); + status = register_shrinker(&nn->nfsd_reply_cache_shrinker, + "nfsd-reply:%s", nn->nfsd_name); if (status) goto out_stats_destroy; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 09d1307959d0..e0b659900e70 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2995,7 +2995,7 @@ static int __init dquot_init(void) pr_info("VFS: Dquot-cache hash table entries: %ld (order %ld," " %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order)); - if (register_shrinker(&dqcache_shrinker)) + if (register_shrinker(&dqcache_shrinker, "dquota-cache")) panic("Cannot register dquot shrinker"); return 0; diff --git a/fs/super.c b/fs/super.c index 60f57c7bc0a6..4fca6657f442 100644 --- a/fs/super.c +++ b/fs/super.c @@ -265,7 +265,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, s->s_shrink.count_objects = super_cache_count; s->s_shrink.batch = 1024; s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE; - if (prealloc_shrinker(&s->s_shrink)) + if (prealloc_shrinker(&s->s_shrink, "sb-%s", type->name)) goto fail; if (list_lru_init_memcg(&s->s_dentry_lru, &s->s_shrink)) goto fail; @@ -1288,6 +1288,8 @@ int get_tree_bdev(struct fs_context *fc, } else { s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); + shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", + fc->fs_type->name, s->s_id); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, fc); if (error) { @@ -1363,6 +1365,8 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, } else { s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); + shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", + fs_type->name, s->s_id); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (error) { diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 0978d01b0ea4..d0c9a09988bc 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2430,7 +2430,7 @@ static int __init ubifs_init(void) if (!ubifs_inode_slab) return -ENOMEM; - err = register_shrinker(&ubifs_shrinker_info); + err = register_shrinker(&ubifs_shrinker_info, "ubifs-slab"); if (err) goto out_slab; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index bf4e60871068..4aa9c9cf5b6e 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1986,7 +1986,8 @@ xfs_alloc_buftarg( btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan; btp->bt_shrinker.seeks = DEFAULT_SEEKS; btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE; - if (register_shrinker(&btp->bt_shrinker)) + if (register_shrinker(&btp->bt_shrinker, "xfs-buf:%s", + mp->m_super->s_id)) goto error_pcpu; return btp; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 5269354b1b69..a1941c8b8630 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -2201,5 +2201,5 @@ xfs_inodegc_register_shrinker( shrink->flags = SHRINKER_NONSLAB; shrink->batch = XFS_INODEGC_SHRINKER_BATCH; - return register_shrinker(shrink); + return register_shrinker(shrink, "xfs-inodegc:%s", mp->m_super->s_id); } diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index abf08bbf34a9..c31d57453ceb 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -677,7 +677,8 @@ xfs_qm_init_quotainfo( qinf->qi_shrinker.seeks = DEFAULT_SEEKS; qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE; - error = register_shrinker(&qinf->qi_shrinker); + error = register_shrinker(&qinf->qi_shrinker, "xfs-qm:%s", + mp->m_super->s_id); if (error) goto out_free_inos; diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 2ced8149c513..08e6054e061f 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -75,6 +75,7 @@ struct shrinker { #endif #ifdef CONFIG_SHRINKER_DEBUG int debugfs_id; + const char *name; struct dentry *debugfs_entry; #endif /* objs pending delete, per node */ @@ -92,9 +93,11 @@ struct shrinker { */ #define SHRINKER_NONSLAB (1 << 3) -extern int prealloc_shrinker(struct shrinker *shrinker); +extern int __printf(2, 3) prealloc_shrinker(struct shrinker *shrinker, + const char *fmt, ...); extern void register_shrinker_prepared(struct shrinker *shrinker); -extern int register_shrinker(struct shrinker *shrinker); +extern int __printf(2, 3) register_shrinker(struct shrinker *shrinker, + const char *fmt, ...); extern void unregister_shrinker(struct shrinker *shrinker); extern void free_prealloced_shrinker(struct shrinker *shrinker); extern void synchronize_shrinkers(void); @@ -102,6 +105,8 @@ extern void synchronize_shrinkers(void); #ifdef CONFIG_SHRINKER_DEBUG extern int shrinker_debugfs_add(struct shrinker *shrinker); extern void shrinker_debugfs_remove(struct shrinker *shrinker); +extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, + const char *fmt, ...); #else /* CONFIG_SHRINKER_DEBUG */ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { @@ -110,5 +115,10 @@ static inline int shrinker_debugfs_add(struct shrinker *shrinker) static inline void shrinker_debugfs_remove(struct shrinker *shrinker) { } +static inline __printf(2, 3) +int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) +{ + return 0; +} #endif /* CONFIG_SHRINKER_DEBUG */ #endif /* _LINUX_SHRINKER_H */ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index c25ba442044a..4b3bf6ebb1eb 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4884,7 +4884,7 @@ static void __init kfree_rcu_batch_init(void) INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func); krcp->initialized = true; } - if (register_shrinker(&kfree_rcu_shrinker)) + if (register_shrinker(&kfree_rcu_shrinker, "rcu-kfree")) pr_err("Failed to register kfree_rcu() shrinker!\n"); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f9b90a8d7dfa..60d742c33de3 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -423,10 +423,10 @@ static int __init hugepage_init(void) if (err) goto err_slab; - err = register_shrinker(&huge_zero_page_shrinker); + err = register_shrinker(&huge_zero_page_shrinker, "thp-zero"); if (err) goto err_hzp_shrinker; - err = register_shrinker(&deferred_split_shrinker); + err = register_shrinker(&deferred_split_shrinker, "thp-deferred_split"); if (err) goto err_split_shrinker; diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 1a70556bd46c..781ecbd3d608 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -102,7 +102,7 @@ DEFINE_SHOW_ATTRIBUTE(shrinker_debugfs_count); int shrinker_debugfs_add(struct shrinker *shrinker) { struct dentry *entry; - char buf[16]; + char buf[128]; int id; lockdep_assert_held(&shrinker_rwsem); @@ -116,7 +116,7 @@ int shrinker_debugfs_add(struct shrinker *shrinker) return id; shrinker->debugfs_id = id; - snprintf(buf, sizeof(buf), "%d", id); + snprintf(buf, sizeof(buf), "%s-%d", shrinker->name, id); /* create debugfs entry */ entry = debugfs_create_dir(buf, shrinker_debugfs_root); @@ -131,10 +131,53 @@ int shrinker_debugfs_add(struct shrinker *shrinker) return 0; } +int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) +{ + struct dentry *entry; + char buf[128]; + const char *new, *old; + va_list ap; + int ret = 0; + + va_start(ap, fmt); + new = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + + if (!new) + return -ENOMEM; + + down_write(&shrinker_rwsem); + + old = shrinker->name; + shrinker->name = new; + + if (shrinker->debugfs_entry) { + snprintf(buf, sizeof(buf), "%s-%d", shrinker->name, + shrinker->debugfs_id); + + entry = debugfs_rename(shrinker_debugfs_root, + shrinker->debugfs_entry, + shrinker_debugfs_root, buf); + if (IS_ERR(entry)) + ret = PTR_ERR(entry); + else + shrinker->debugfs_entry = entry; + } + + up_write(&shrinker_rwsem); + + kfree_const(old); + + return ret; +} +EXPORT_SYMBOL(shrinker_debugfs_rename); + void shrinker_debugfs_remove(struct shrinker *shrinker) { lockdep_assert_held(&shrinker_rwsem); + kfree_const(shrinker->name); + if (!shrinker->debugfs_entry) return; diff --git a/mm/vmscan.c b/mm/vmscan.c index 35dedff79eb4..97ac6c6c026d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -608,7 +608,7 @@ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, /* * Add a shrinker callback to be called from the vm. */ -int prealloc_shrinker(struct shrinker *shrinker) +static int __prealloc_shrinker(struct shrinker *shrinker) { unsigned int size; int err; @@ -632,8 +632,36 @@ int prealloc_shrinker(struct shrinker *shrinker) return 0; } +#ifdef CONFIG_SHRINKER_DEBUG +int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + va_list ap; + int err; + + va_start(ap, fmt); + shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!shrinker->name) + return -ENOMEM; + + err = __prealloc_shrinker(shrinker); + if (err) + kfree_const(shrinker->name); + + return err; +} +#else +int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + return __prealloc_shrinker(shrinker); +} +#endif + void free_prealloced_shrinker(struct shrinker *shrinker) { +#ifdef CONFIG_SHRINKER_DEBUG + kfree_const(shrinker->name); +#endif if (shrinker->flags & SHRINKER_MEMCG_AWARE) { down_write(&shrinker_rwsem); unregister_memcg_shrinker(shrinker); @@ -654,15 +682,39 @@ void register_shrinker_prepared(struct shrinker *shrinker) up_write(&shrinker_rwsem); } -int register_shrinker(struct shrinker *shrinker) +static int __register_shrinker(struct shrinker *shrinker) { - int err = prealloc_shrinker(shrinker); + int err = __prealloc_shrinker(shrinker); if (err) return err; register_shrinker_prepared(shrinker); return 0; } + +#ifdef CONFIG_SHRINKER_DEBUG +int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + va_list ap; + int err; + + va_start(ap, fmt); + shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!shrinker->name) + return -ENOMEM; + + err = __register_shrinker(shrinker); + if (err) + kfree_const(shrinker->name); + return err; +} +#else +int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + return __register_shrinker(shrinker); +} +#endif EXPORT_SYMBOL(register_shrinker); /* diff --git a/mm/workingset.c b/mm/workingset.c index 592569a8974c..a5e84862fc86 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -625,7 +625,7 @@ static int __init workingset_init(void) pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); - ret = prealloc_shrinker(&workingset_shadow_shrinker); + ret = prealloc_shrinker(&workingset_shadow_shrinker, "mm-shadow"); if (ret) goto err; ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key, diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 5d5fc04385b8..f24b71568e83 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -2217,7 +2217,8 @@ static int zs_register_shrinker(struct zs_pool *pool) pool->shrinker.batch = 0; pool->shrinker.seeks = DEFAULT_SEEKS; - return register_shrinker(&pool->shrinker); + return register_shrinker(&pool->shrinker, "mm-zspool:%s", + pool->name); } /** diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 682fcd24bf43..04e7b55fe0d9 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -874,7 +874,7 @@ int __init rpcauth_init_module(void) err = rpc_init_authunix(); if (err < 0) goto out1; - err = register_shrinker(&rpc_cred_shrinker); + err = register_shrinker(&rpc_cred_shrinker, "sunrpc_cred"); if (err < 0) goto out2; return 0; -- cgit v1.2.3 From 4867fbbdd6b362400d154417e08ce76b14200ba1 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Mon, 11 Jul 2022 12:35:40 +0530 Subject: x86/mm: move protection_map[] inside the platform This moves protection_map[] inside the platform and makes it a static. This also defines a helper function add_encrypt_protection_map() that can update the protection_map[] array with pgprot_encrypted(). Link: https://lkml.kernel.org/r/20220711070600.2378316-7-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Christoph Hellwig Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Arnd Bergmann Cc: Brian Cain Cc: Catalin Marinas Cc: Christophe Leroy Cc: Christoph Hellwig Cc: Chris Zankel Cc: "David S. Miller" Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: Heiko Carstens Cc: Huacai Chen Cc: "James E.J. Bottomley" Cc: Jeff Dike Cc: Jonas Bonn Cc: Michael Ellerman Cc: Michal Simek Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Richard Henderson Cc: Rich Felker Cc: Russell King Cc: Sam Ravnborg Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: WANG Xuerui Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/x86/include/asm/mem_encrypt.h | 2 ++ arch/x86/include/asm/pgtable_types.h | 19 ------------------- arch/x86/mm/mem_encrypt_amd.c | 6 ++---- arch/x86/mm/pgprot.c | 28 ++++++++++++++++++++++++++++ 4 files changed, 32 insertions(+), 23 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 88ceaf3648b3..72ca90552b6a 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -89,6 +89,8 @@ static inline void mem_encrypt_free_decrypted_mem(void) { } /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void); +void add_encrypt_protection_map(void); + /* * The __sme_pa() and __sme_pa_nodebug() macros are meant for use when * writing to or comparing values from the cr3 register. Having the diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index bdaf8391e2e0..aa174fed3a71 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -230,25 +230,6 @@ enum page_cache_mode { #endif /* __ASSEMBLY__ */ -/* xwr */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY_EXEC -#define __P101 PAGE_READONLY_EXEC -#define __P110 PAGE_COPY_EXEC -#define __P111 PAGE_COPY_EXEC - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY_EXEC -#define __S101 PAGE_READONLY_EXEC -#define __S110 PAGE_SHARED_EXEC -#define __S111 PAGE_SHARED_EXEC - /* * early identity mapping pte attrib macros. */ diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index f6d038e2cd8e..5c3c3ed46f5a 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -486,8 +487,6 @@ void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, boo void __init sme_early_init(void) { - unsigned int i; - if (!sme_me_mask) return; @@ -496,8 +495,7 @@ void __init sme_early_init(void) __supported_pte_mask = __sme_set(__supported_pte_mask); /* Update the protection map with memory encryption mask */ - for (i = 0; i < ARRAY_SIZE(protection_map); i++) - protection_map[i] = pgprot_encrypted(protection_map[i]); + add_encrypt_protection_map(); x86_platform.guest.enc_status_change_prepare = amd_enc_status_change_prepare; x86_platform.guest.enc_status_change_finish = amd_enc_status_change_finish; diff --git a/arch/x86/mm/pgprot.c b/arch/x86/mm/pgprot.c index 763742782286..c84bd9540b16 100644 --- a/arch/x86/mm/pgprot.c +++ b/arch/x86/mm/pgprot.c @@ -3,6 +3,34 @@ #include #include #include +#include + +static pgprot_t protection_map[16] __ro_after_init = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY, + [VM_EXEC] = PAGE_READONLY_EXEC, + [VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, + [VM_EXEC | VM_WRITE] = PAGE_COPY_EXEC, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY_EXEC, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_EXEC +}; + +void add_encrypt_protection_map(void) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(protection_map); i++) + protection_map[i] = pgprot_encrypted(protection_map[i]); +} pgprot_t vm_get_page_prot(unsigned long vm_flags) { -- cgit v1.2.3 From 91a8da021c4d767704086386b08bf276f926ebfd Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Mon, 11 Jul 2022 12:35:58 +0530 Subject: um/mm: enable ARCH_HAS_VM_GET_PAGE_PROT This enables ARCH_HAS_VM_GET_PAGE_PROT on the platform and exports standard vm_get_page_prot() implementation via DECLARE_VM_GET_PAGE_PROT, which looks up a private and static protection_map[] array. Subsequently all __SXXX and __PXXX macros can be dropped which are no longer needed. Link: https://lkml.kernel.org/r/20220711070600.2378316-25-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Cc: Jeff Dike Cc: Arnd Bergmann Cc: Brian Cain Cc: Catalin Marinas Cc: Christophe Leroy Cc: Christoph Hellwig Cc: Christoph Hellwig Cc: Chris Zankel Cc: "David S. Miller" Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: Heiko Carstens Cc: Huacai Chen Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Michael Ellerman Cc: Michal Simek Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Richard Henderson Cc: Rich Felker Cc: Russell King Cc: Sam Ravnborg Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: WANG Xuerui Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/um/Kconfig | 1 + arch/um/include/asm/pgtable.h | 17 ----------------- arch/um/kernel/mem.c | 20 ++++++++++++++++++++ arch/x86/um/mem_32.c | 2 +- 4 files changed, 22 insertions(+), 18 deletions(-) (limited to 'arch/x86') diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 4ec22e156a2e..7fb43654e5b5 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -10,6 +10,7 @@ config UML select ARCH_HAS_KCOV select ARCH_HAS_STRNCPY_FROM_USER select ARCH_HAS_STRNLEN_USER + select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_NO_PREEMPT select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_SECCOMP_FILTER diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 167e236d9bb8..66bc3f99d9be 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -68,23 +68,6 @@ extern unsigned long end_iomem; * Also, write permissions imply read permissions. This is the closest we can * get.. */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY -#define __P101 PAGE_READONLY -#define __P110 PAGE_COPY -#define __P111 PAGE_COPY - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY -#define __S101 PAGE_READONLY -#define __S110 PAGE_SHARED -#define __S111 PAGE_SHARED /* * ZERO_PAGE is a global shared page that is always zero: used diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 15295c3237a0..5b259f0a1f94 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -197,3 +197,23 @@ void *uml_kmalloc(int size, int flags) { return kmalloc(size, flags); } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY, + [VM_EXEC] = PAGE_READONLY, + [VM_EXEC | VM_READ] = PAGE_READONLY, + [VM_EXEC | VM_WRITE] = PAGE_COPY, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_READONLY, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index 19c5dbd46770..cafd01f730da 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -17,7 +17,7 @@ static int __init gate_vma_init(void) gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; - gate_vma.vm_page_prot = __P101; + gate_vma.vm_page_prot = PAGE_READONLY; return 0; } -- cgit v1.2.3 From 3d923c5f1e21ad491acd4c0d62bf2481ce94016c Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Mon, 11 Jul 2022 12:36:00 +0530 Subject: mm/mmap: drop ARCH_HAS_VM_GET_PAGE_PROT Now all the platforms enable ARCH_HAS_GET_PAGE_PROT. They define and export own vm_get_page_prot() whether custom or standard DECLARE_VM_GET_PAGE_PROT. Hence there is no need for default generic fallback for vm_get_page_prot(). Just drop this fallback and also ARCH_HAS_GET_PAGE_PROT mechanism. Link: https://lkml.kernel.org/r/20220711070600.2378316-27-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Geert Uytterhoeven Reviewed-by: Christoph Hellwig Reviewed-by: Christophe Leroy Acked-by: Geert Uytterhoeven Cc: Arnd Bergmann Cc: Brian Cain Cc: Catalin Marinas Cc: Christoph Hellwig Cc: Chris Zankel Cc: "David S. Miller" Cc: Dinh Nguyen Cc: Guo Ren Cc: Heiko Carstens Cc: Huacai Chen Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jeff Dike Cc: Jonas Bonn Cc: Michael Ellerman Cc: Michal Simek Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Richard Henderson Cc: Rich Felker Cc: Russell King Cc: Sam Ravnborg Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: WANG Xuerui Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/alpha/Kconfig | 1 - arch/arc/Kconfig | 1 - arch/arm/Kconfig | 1 - arch/arm64/Kconfig | 1 - arch/csky/Kconfig | 1 - arch/hexagon/Kconfig | 1 - arch/ia64/Kconfig | 1 - arch/loongarch/Kconfig | 1 - arch/m68k/Kconfig | 1 - arch/microblaze/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/nios2/Kconfig | 1 - arch/openrisc/Kconfig | 1 - arch/parisc/Kconfig | 1 - arch/powerpc/Kconfig | 1 - arch/riscv/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/sh/Kconfig | 1 - arch/sparc/Kconfig | 1 - arch/um/Kconfig | 1 - arch/x86/Kconfig | 1 - arch/xtensa/Kconfig | 1 - include/linux/mm.h | 3 --- mm/Kconfig | 3 --- mm/mmap.c | 22 ---------------------- 25 files changed, 50 deletions(-) (limited to 'arch/x86') diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index db1c8b329461..7d0d26b5b3f5 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -2,7 +2,6 @@ config ALPHA bool default y - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_32BIT_USTAT_F_TINODE select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 8be56a5d8a9b..9e3653253ef2 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -13,7 +13,6 @@ config ARC select ARCH_HAS_SETUP_DMA_OPS select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC select ARCH_32BIT_OFF_T select BUILDTIME_TABLE_SORT diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index e153b6d4fc5b..7630ba9cb6cc 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -24,7 +24,6 @@ config ARM select ARCH_HAS_SYNC_DMA_FOR_CPU if SWIOTLB || !MMU select ARCH_HAS_TEARDOWN_DMA_OPS if MMU select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAVE_CUSTOM_GPIO_H select ARCH_HAVE_NMI_SAFE_CMPXCHG if CPU_V7 || CPU_V7M || CPU_V6K select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1652a9800ebe..7030bf3f8d6f 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -45,7 +45,6 @@ config ARM64 select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_ELF_PROT select ARCH_HAVE_NMI_SAFE_CMPXCHG diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 588b8a9c68ed..21d72b078eef 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -6,7 +6,6 @@ config CSKY select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_QUEUED_RWLOCKS select ARCH_WANT_FRAME_POINTERS if !CPU_CK610 && $(cc-option,-mbacktrace) diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index bc4ceecd0588..54eadf265178 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -6,7 +6,6 @@ config HEXAGON def_bool y select ARCH_32BIT_OFF_T select ARCH_HAS_SYNC_DMA_FOR_DEVICE - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_NO_PREEMPT select DMA_GLOBAL_POOL # Other pending projects/to-do items. diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 0510a5737711..cb93769a9f2a 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -12,7 +12,6 @@ config IA64 select ARCH_HAS_DMA_MARK_CLEAN select ARCH_HAS_STRNCPY_FROM_USER select ARCH_HAS_STRNLEN_USER - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select ACPI diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index adf8cf6ec5d5..db2838cf8c02 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -9,7 +9,6 @@ config LOONGARCH select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_PTE_SPECIAL - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_INLINE_READ_LOCK if !PREEMPTION select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 49aa0cf13e96..936cce42ae9a 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -7,7 +7,6 @@ config M68K select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DMA_PREP_COHERENT if HAS_DMA && MMU && !COLDFIRE select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS select ARCH_MIGHT_HAVE_PC_PARPORT if ISA select ARCH_NO_PREEMPT if !COLDFIRE diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 15f91ba8a0c4..8cf429ad1c84 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -7,7 +7,6 @@ config MICROBLAZE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_TABLE_SORT diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index d0b7eb11ec81..db09d45d59ec 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -14,7 +14,6 @@ config MIPS select ARCH_HAS_STRNLEN_USER select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UBSAN_SANITIZE_ALL - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_KEEP_MEMBLOCK select ARCH_SUPPORTS_UPROBES diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index e0459dffd218..4167f1eb4cd8 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -6,7 +6,6 @@ config NIOS2 select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_DMA_SET_UNCACHED - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_NO_SWAP select COMMON_CLK select TIMER_OF diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index fe0dfb50eb86..e814df4c483c 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -10,7 +10,6 @@ config OPENRISC select ARCH_HAS_DMA_SET_UNCACHED select ARCH_HAS_DMA_CLEAR_UNCACHED select ARCH_HAS_SYNC_DMA_FOR_DEVICE - select ARCH_HAS_VM_GET_PAGE_PROT select COMMON_CLK select OF select OF_EARLY_FLATTREE diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 891d82393957..fa400055b2d5 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -12,7 +12,6 @@ config PARISC select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_UBSAN_SANITIZE_ALL - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAS_PTE_SPECIAL select ARCH_NO_SG_CHAIN select ARCH_SUPPORTS_HUGETLBFS if PA20 diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 1035d172c7dd..250b8658b2d4 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -140,7 +140,6 @@ config PPC select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE select ARCH_HAS_UBSAN_SANITIZE_ALL - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_KEEP_MEMBLOCK select ARCH_MIGHT_HAVE_PC_PARPORT diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 583389d4e43a..32ffef9f6e5b 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -32,7 +32,6 @@ config RISCV select ARCH_HAS_STRICT_MODULE_RWX if MMU && !XIP_KERNEL select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UBSAN_SANITIZE_ALL - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT select ARCH_STACKWALK diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index c4481377ca83..91c0b80a8bf0 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -81,7 +81,6 @@ config S390 select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAS_VDSO_DATA - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK select ARCH_INLINE_READ_LOCK_BH diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 91f3ea325388..5f220e903e5a 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -12,7 +12,6 @@ config SUPERH select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HIBERNATION_POSSIBLE if MMU select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_WANT_IPC_PARSE_VERSION diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 09f868613a4d..9c1cce74953a 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -13,7 +13,6 @@ config 64BIT config SPARC bool default y - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_MIGHT_HAVE_PC_PARPORT if SPARC64 && PCI select ARCH_MIGHT_HAVE_PC_SERIO select DMA_OPS diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 7fb43654e5b5..4ec22e156a2e 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -10,7 +10,6 @@ config UML select ARCH_HAS_KCOV select ARCH_HAS_STRNCPY_FROM_USER select ARCH_HAS_STRNLEN_USER - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_NO_PREEMPT select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_SECCOMP_FILTER diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index be0b95e51df6..841e4843d0c4 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -94,7 +94,6 @@ config X86 select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_UBSAN_SANITIZE_ALL - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAS_DEBUG_WX select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_NMI_SAFE_CMPXCHG diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 4c0d83520ff1..0b0f0172cced 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -11,7 +11,6 @@ config XTENSA select ARCH_HAS_DMA_SET_UNCACHED if MMU select ARCH_HAS_STRNCPY_FROM_USER if !KASAN select ARCH_HAS_STRNLEN_USER - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS diff --git a/include/linux/mm.h b/include/linux/mm.h index 4b4dc93f9bc3..61e3101c44ea 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -425,9 +425,6 @@ extern unsigned int kobjsize(const void *objp); * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ -#ifndef CONFIG_ARCH_HAS_VM_GET_PAGE_PROT -extern pgprot_t protection_map[16]; -#endif /* * The default fault flags that should be used by most of the diff --git a/mm/Kconfig b/mm/Kconfig index c1fa4993a56f..56ca0e7c6f9a 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -951,9 +951,6 @@ config ARCH_HAS_CURRENT_STACK_POINTER register alias named "current_stack_pointer", this config can be selected. -config ARCH_HAS_VM_GET_PAGE_PROT - bool - config ARCH_HAS_PTE_DEVMAP bool diff --git a/mm/mmap.c b/mm/mmap.c index 2a58a9cd0752..edf27a2789a2 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -81,28 +81,6 @@ static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end); -#ifndef CONFIG_ARCH_HAS_VM_GET_PAGE_PROT -pgprot_t protection_map[16] __ro_after_init = { - [VM_NONE] = __P000, - [VM_READ] = __P001, - [VM_WRITE] = __P010, - [VM_WRITE | VM_READ] = __P011, - [VM_EXEC] = __P100, - [VM_EXEC | VM_READ] = __P101, - [VM_EXEC | VM_WRITE] = __P110, - [VM_EXEC | VM_WRITE | VM_READ] = __P111, - [VM_SHARED] = __S000, - [VM_SHARED | VM_READ] = __S001, - [VM_SHARED | VM_WRITE] = __S010, - [VM_SHARED | VM_WRITE | VM_READ] = __S011, - [VM_SHARED | VM_EXEC] = __S100, - [VM_SHARED | VM_EXEC | VM_READ] = __S101, - [VM_SHARED | VM_EXEC | VM_WRITE] = __S110, - [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = __S111 -}; -DECLARE_VM_GET_PAGE_PROT -#endif /* CONFIG_ARCH_HAS_VM_GET_PAGE_PROT */ - static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) { return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); -- cgit v1.2.3