From 6ea02ee489799317c6640ac014c49b1d1b7124c5 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 3 Apr 2024 16:37:59 +0800 Subject: arm64: mm: cleanup __do_page_fault() Patch series "arch/mm/fault: accelerate pagefault when badaccess", v2. After VMA lock-based page fault handling enabled, if bad access met under per-vma lock, it will fallback to mmap_lock-based handling, so it leads to unnessary mmap lock and vma find again. A test from lmbench shows 34% improve after this changes on arm64, lat_sig -P 1 prot lat_sig 0.29194 -> 0.19198 This patch (of 7): The __do_page_fault() only calls handle_mm_fault() after vm_flags checked, and it is only called by do_page_fault(), let's squash it into do_page_fault() to cleanup code. Link: https://lkml.kernel.org/r/20240403083805.1818160-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20240403083805.1818160-2-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Suren Baghdasaryan Reviewed-by: Catalin Marinas Cc: Albert Ou Cc: Alexander Gordeev Cc: Andy Lutomirski Cc: Christophe Leroy Cc: Dave Hansen Cc: Gerald Schaefer Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Russell King Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/mm/fault.c | 27 +++++++-------------------- 1 file changed, 7 insertions(+), 20 deletions(-) (limited to 'arch/arm64/mm/fault.c') diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 8251e2fea9c7..9bb9f395351a 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -486,25 +486,6 @@ static void do_bad_area(unsigned long far, unsigned long esr, } } -#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) -#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) - -static vm_fault_t __do_page_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long addr, - unsigned int mm_flags, unsigned long vm_flags, - struct pt_regs *regs) -{ - /* - * Ok, we have a good vm_area for this memory access, so we can handle - * it. - * Check that the permissions on the VMA allow for the fault which - * occurred. - */ - if (!(vma->vm_flags & vm_flags)) - return VM_FAULT_BADACCESS; - return handle_mm_fault(vma, addr, mm_flags, regs); -} - static bool is_el0_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; @@ -519,6 +500,9 @@ static bool is_write_abort(unsigned long esr) return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); } +#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) +#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) + static int __kprobes do_page_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { @@ -617,7 +601,10 @@ retry: goto done; } - fault = __do_page_fault(mm, vma, addr, mm_flags, vm_flags, regs); + if (!(vma->vm_flags & vm_flags)) + fault = VM_FAULT_BADACCESS; + else + fault = handle_mm_fault(vma, addr, mm_flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { -- cgit v1.2.3-59-g8ed1b From faab3d0f250aba863b19bb2d72daea0ae90a1d5d Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 3 Apr 2024 16:38:00 +0800 Subject: arm64: mm: accelerate pagefault when VM_FAULT_BADACCESS The vm_flags of vma already checked under per-VMA lock, if it is a bad access, directly set fault to VM_FAULT_BADACCESS and handle error, no need to retry with mmap_lock again, the latency time reduces 34% in 'lat_sig -P 1 prot lat_sig' from lmbench testcase. Since the page fault is handled under per-VMA lock, count it as a vma lock event with VMA_LOCK_SUCCESS. Link: https://lkml.kernel.org/r/20240403083805.1818160-3-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Suren Baghdasaryan Reviewed-by: Catalin Marinas Cc: Albert Ou Cc: Alexander Gordeev Cc: Andy Lutomirski Cc: Christophe Leroy Cc: Dave Hansen Cc: Gerald Schaefer Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Russell King Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/mm/fault.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/arm64/mm/fault.c') diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9bb9f395351a..405f9aa831bd 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -572,7 +572,9 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); - goto lock_mmap; + fault = VM_FAULT_BADACCESS; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + goto done; } fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) -- cgit v1.2.3-59-g8ed1b From eebb5181a02f819cec5e324a9df1015934dc59f3 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 11 Apr 2024 21:09:24 +0800 Subject: arm64: mm: drop VM_FAULT_BADMAP/VM_FAULT_BADACCESS Patch series "mm: remove arch's private VM_FAULT_BADMAP/BADACCESS", v2. Directly set SEGV_MAPRR or SEGV_ACCERR for arm/arm64 to remove the last two arch's private vm_fault reasons. This patch (of 2): If bad map or access, directly set si_code to SEGV_MAPRR or SEGV_ACCERR, also set fault to 0 and goto error handling, which make us to drop the arch's special vm fault reason. Link: https://lkml.kernel.org/r/20240411130925.73281-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20240411130925.73281-2-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Catalin Marinas Cc: Aishwarya TCV Cc: Cristian Marussi Cc: Mark Brown Cc: Russell King Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/mm/fault.c | 43 ++++++++++++++++++++----------------------- 1 file changed, 20 insertions(+), 23 deletions(-) (limited to 'arch/arm64/mm/fault.c') diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 405f9aa831bd..451ba7cbd5ad 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -500,9 +500,6 @@ static bool is_write_abort(unsigned long esr) return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); } -#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) -#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) - static int __kprobes do_page_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { @@ -513,6 +510,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, unsigned int mm_flags = FAULT_FLAG_DEFAULT; unsigned long addr = untagged_addr(far); struct vm_area_struct *vma; + int si_code; if (kprobe_page_fault(regs, esr)) return 0; @@ -572,9 +570,10 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); - fault = VM_FAULT_BADACCESS; + fault = 0; + si_code = SEGV_ACCERR; count_vm_vma_lock_event(VMA_LOCK_SUCCESS); - goto done; + goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) @@ -599,15 +598,19 @@ lock_mmap: retry: vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { - fault = VM_FAULT_BADMAP; - goto done; + fault = 0; + si_code = SEGV_MAPERR; + goto bad_area; } - if (!(vma->vm_flags & vm_flags)) - fault = VM_FAULT_BADACCESS; - else - fault = handle_mm_fault(vma, addr, mm_flags, regs); + if (!(vma->vm_flags & vm_flags)) { + mmap_read_unlock(mm); + fault = 0; + si_code = SEGV_ACCERR; + goto bad_area; + } + fault = handle_mm_fault(vma, addr, mm_flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) @@ -626,13 +629,12 @@ retry: mmap_read_unlock(mm); done: - /* - * Handle the "normal" (no error) case first. - */ - if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | - VM_FAULT_BADACCESS)))) + /* Handle the "normal" (no error) case first. */ + if (likely(!(fault & VM_FAULT_ERROR))) return 0; + si_code = SEGV_MAPERR; +bad_area: /* * If we are in kernel mode at this point, we have no context to * handle this fault with. @@ -667,13 +669,8 @@ done: arm64_force_sig_mceerr(BUS_MCEERR_AR, far, lsb, inf->name); } else { - /* - * Something tried to access memory that isn't in our memory - * map. - */ - arm64_force_sig_fault(SIGSEGV, - fault == VM_FAULT_BADACCESS ? SEGV_ACCERR : SEGV_MAPERR, - far, inf->name); + /* Something tried to access memory that out of memory map */ + arm64_force_sig_fault(SIGSEGV, si_code, far, inf->name); } return 0; -- cgit v1.2.3-59-g8ed1b