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/csky/mm/fault.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/csky/mm') 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; -- cgit v1.2.3 From 0d70836013f2da08fa190e99a1d50ebf28a09ef5 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Mon, 11 Jul 2022 12:35:51 +0530 Subject: csky/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/20220711070600.2378316-18-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Acked-by: Guo Ren Cc: Geert Uytterhoeven 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: 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/csky/Kconfig | 1 + arch/csky/include/asm/pgtable.h | 18 ------------------ arch/csky/mm/init.c | 20 ++++++++++++++++++++ 3 files changed, 21 insertions(+), 18 deletions(-) (limited to 'arch/csky/mm') diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 21d72b078eef..588b8a9c68ed 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -6,6 +6,7 @@ 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/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h index bbe245117777..229a5f4ad7fc 100644 --- a/arch/csky/include/asm/pgtable.h +++ b/arch/csky/include/asm/pgtable.h @@ -77,24 +77,6 @@ #define MAX_SWAPFILES_CHECK() \ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT != 5) -#define __P000 PAGE_NONE -#define __P001 PAGE_READ -#define __P010 PAGE_READ -#define __P011 PAGE_READ -#define __P100 PAGE_READ -#define __P101 PAGE_READ -#define __P110 PAGE_READ -#define __P111 PAGE_READ - -#define __S000 PAGE_NONE -#define __S001 PAGE_READ -#define __S010 PAGE_WRITE -#define __S011 PAGE_WRITE -#define __S100 PAGE_READ -#define __S101 PAGE_READ -#define __S110 PAGE_WRITE -#define __S111 PAGE_WRITE - extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index bf2004aa811a..bde7cabd23df 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -197,3 +197,23 @@ void __init fixaddr_init(void) vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; fixrange_init(vaddr, vaddr + PMD_SIZE, swapper_pg_dir); } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READ, + [VM_WRITE] = PAGE_READ, + [VM_WRITE | VM_READ] = PAGE_READ, + [VM_EXEC] = PAGE_READ, + [VM_EXEC | VM_READ] = PAGE_READ, + [VM_EXEC | VM_WRITE] = PAGE_READ, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_READ, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READ, + [VM_SHARED | VM_WRITE] = PAGE_WRITE, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_WRITE, + [VM_SHARED | VM_EXEC] = PAGE_READ, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READ, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_WRITE, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_WRITE +}; +DECLARE_VM_GET_PAGE_PROT -- cgit v1.2.3