From 8878a539ff19a43cf3729e7562cd528f490246ae Mon Sep 17 00:00:00 2001 From: Kautuk Consul Date: Sun, 27 Nov 2011 17:49:50 +0100 Subject: ARM: 7178/1: fault.c: Port OOM changes into do_page_fault Commit d065bd810b6deb67d4897a14bfe21f8eb526ba99 (mm: retry page fault when blocking on disk transfer) and commit 37b23e0525d393d48a7d59f870b3bc061a30ccdb (x86,mm: make pagefault killable) The above commits introduced changes into the x86 pagefault handler for making the page fault handler retryable as well as killable. These changes reduce the mmap_sem hold time, which is crucial during OOM killer invocation. Port these changes to ARM. Without these changes, my ARM board encounters many hang and livelock scenarios. After applying this patch, OOM feature performance improves according to my testing. Signed-off-by: Kautuk Consul Signed-off-by: Russell King --- arch/arm/mm/fault.c | 58 +++++++++++++++++++++++++++++++++++------------------ 1 file changed, 39 insertions(+), 19 deletions(-) (limited to 'arch/arm/mm/fault.c') diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index aa33949fef60..4aabeaec25df 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -231,7 +231,7 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma) static int __kprobes __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, - struct task_struct *tsk) + unsigned int flags, struct task_struct *tsk) { struct vm_area_struct *vma; int fault; @@ -253,18 +253,7 @@ good_area: goto out; } - /* - * If for any reason at all we couldn't handle the fault, make - * sure we exit gracefully rather than endlessly redo the fault. - */ - fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, (fsr & FSR_WRITE) ? FAULT_FLAG_WRITE : 0); - if (unlikely(fault & VM_FAULT_ERROR)) - return fault; - if (fault & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; - return fault; + return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags); check_stack: if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr)) @@ -279,6 +268,9 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) struct task_struct *tsk; struct mm_struct *mm; int fault, sig, code; + int write = fsr & FSR_WRITE; + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | + (write ? FAULT_FLAG_WRITE : 0); if (notify_page_fault(regs, fsr)) return 0; @@ -305,6 +297,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (!down_read_trylock(&mm->mmap_sem)) { if (!user_mode(regs) && !search_exception_tables(regs->ARM_pc)) goto no_context; +retry: down_read(&mm->mmap_sem); } else { /* @@ -320,14 +313,41 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) #endif } - fault = __do_page_fault(mm, addr, fsr, tsk); - up_read(&mm->mmap_sem); + fault = __do_page_fault(mm, addr, fsr, flags, tsk); + + /* If we need to retry but a fatal signal is pending, handle the + * signal first. We do not need to release the mmap_sem because + * it would already be released in __lock_page_or_retry in + * mm/filemap.c. */ + if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + return 0; + + /* + * Major/minor page fault accounting is only done on the + * initial attempt. If we go through a retry, it is extremely + * likely that the page will be found in page cache at that point. + */ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); - if (fault & VM_FAULT_MAJOR) - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, addr); - else if (fault & VM_FAULT_MINOR) - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, addr); + if (flags & FAULT_FLAG_ALLOW_RETRY) { + if (fault & VM_FAULT_MAJOR) { + tsk->maj_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, + regs, addr); + } else { + tsk->min_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, + regs, addr); + } + if (fault & VM_FAULT_RETRY) { + /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk + * of starvation. */ + flags &= ~FAULT_FLAG_ALLOW_RETRY; + goto retry; + } + } + + up_read(&mm->mmap_sem); /* * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR -- cgit v1.2.3 From 136848d4ca9cf6f08edf6e50cb9bbe19de55c32a Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Tue, 22 Nov 2011 17:30:28 +0000 Subject: ARM: LPAE: Move the FSR definitions to separate files The FSR structure is different with LPAE and this patch moves the classic MMU specific definition to a separate fsr-2level.c file that is included in fault.c. It also moves the fsr_fs and FSR bits to the fault.h file. Signed-off-by: Catalin Marinas --- arch/arm/mm/fault.c | 96 +++-------------------------------------------------- 1 file changed, 4 insertions(+), 92 deletions(-) (limited to 'arch/arm/mm/fault.c') diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index aa33949fef60..2a0271677725 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -27,19 +27,6 @@ #include "fault.h" -/* - * Fault status register encodings. We steal bit 31 for our own purposes. - */ -#define FSR_LNX_PF (1 << 31) -#define FSR_WRITE (1 << 11) -#define FSR_FS4 (1 << 10) -#define FSR_FS3_0 (15) - -static inline int fsr_fs(unsigned int fsr) -{ - return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6; -} - #ifdef CONFIG_MMU #ifdef CONFIG_KPROBES @@ -489,55 +476,16 @@ do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 1; } -static struct fsr_info { +struct fsr_info { int (*fn)(unsigned long addr, unsigned int fsr, struct pt_regs *regs); int sig; int code; const char *name; -} fsr_info[] = { - /* - * The following are the standard ARMv3 and ARMv4 aborts. ARMv5 - * defines these to be "precise" aborts. - */ - { do_bad, SIGSEGV, 0, "vector exception" }, - { do_bad, SIGBUS, BUS_ADRALN, "alignment exception" }, - { do_bad, SIGKILL, 0, "terminal exception" }, - { do_bad, SIGBUS, BUS_ADRALN, "alignment exception" }, - { do_bad, SIGBUS, 0, "external abort on linefetch" }, - { do_translation_fault, SIGSEGV, SEGV_MAPERR, "section translation fault" }, - { do_bad, SIGBUS, 0, "external abort on linefetch" }, - { do_page_fault, SIGSEGV, SEGV_MAPERR, "page translation fault" }, - { do_bad, SIGBUS, 0, "external abort on non-linefetch" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "section domain fault" }, - { do_bad, SIGBUS, 0, "external abort on non-linefetch" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" }, - { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, - { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" }, - /* - * The following are "imprecise" aborts, which are signalled by bit - * 10 of the FSR, and may not be recoverable. These are only - * supported if the CPU abort handler supports bit 10. - */ - { do_bad, SIGBUS, 0, "unknown 16" }, - { do_bad, SIGBUS, 0, "unknown 17" }, - { do_bad, SIGBUS, 0, "unknown 18" }, - { do_bad, SIGBUS, 0, "unknown 19" }, - { do_bad, SIGBUS, 0, "lock abort" }, /* xscale */ - { do_bad, SIGBUS, 0, "unknown 21" }, - { do_bad, SIGBUS, BUS_OBJERR, "imprecise external abort" }, /* xscale */ - { do_bad, SIGBUS, 0, "unknown 23" }, - { do_bad, SIGBUS, 0, "dcache parity error" }, /* xscale */ - { do_bad, SIGBUS, 0, "unknown 25" }, - { do_bad, SIGBUS, 0, "unknown 26" }, - { do_bad, SIGBUS, 0, "unknown 27" }, - { do_bad, SIGBUS, 0, "unknown 28" }, - { do_bad, SIGBUS, 0, "unknown 29" }, - { do_bad, SIGBUS, 0, "unknown 30" }, - { do_bad, SIGBUS, 0, "unknown 31" } }; +/* FSR definition */ +#include "fsr-2level.c" + void __init hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *), int sig, int code, const char *name) @@ -573,42 +521,6 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs) arm_notify_die("", regs, &info, fsr, 0); } - -static struct fsr_info ifsr_info[] = { - { do_bad, SIGBUS, 0, "unknown 0" }, - { do_bad, SIGBUS, 0, "unknown 1" }, - { do_bad, SIGBUS, 0, "debug event" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "section access flag fault" }, - { do_bad, SIGBUS, 0, "unknown 4" }, - { do_translation_fault, SIGSEGV, SEGV_MAPERR, "section translation fault" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "page access flag fault" }, - { do_page_fault, SIGSEGV, SEGV_MAPERR, "page translation fault" }, - { do_bad, SIGBUS, 0, "external abort on non-linefetch" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "section domain fault" }, - { do_bad, SIGBUS, 0, "unknown 10" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" }, - { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, - { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" }, - { do_bad, SIGBUS, 0, "unknown 16" }, - { do_bad, SIGBUS, 0, "unknown 17" }, - { do_bad, SIGBUS, 0, "unknown 18" }, - { do_bad, SIGBUS, 0, "unknown 19" }, - { do_bad, SIGBUS, 0, "unknown 20" }, - { do_bad, SIGBUS, 0, "unknown 21" }, - { do_bad, SIGBUS, 0, "unknown 22" }, - { do_bad, SIGBUS, 0, "unknown 23" }, - { do_bad, SIGBUS, 0, "unknown 24" }, - { do_bad, SIGBUS, 0, "unknown 25" }, - { do_bad, SIGBUS, 0, "unknown 26" }, - { do_bad, SIGBUS, 0, "unknown 27" }, - { do_bad, SIGBUS, 0, "unknown 28" }, - { do_bad, SIGBUS, 0, "unknown 29" }, - { do_bad, SIGBUS, 0, "unknown 30" }, - { do_bad, SIGBUS, 0, "unknown 31" }, -}; - void __init hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *), int sig, int code, const char *name) -- cgit v1.2.3 From f7b8156d150f7383b42622a9219b230b36435b4a Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Tue, 22 Nov 2011 17:30:31 +0000 Subject: ARM: LPAE: Add fault handling support The DFSR and IFSR register format is different when LPAE is enabled. In addition, DFSR and IFSR have similar definitions for the fault type. This modifies the fault code to correctly handle the new format. Signed-off-by: Catalin Marinas --- arch/arm/mm/fault.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'arch/arm/mm/fault.c') diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 2a0271677725..eb5520fc755f 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -110,8 +110,10 @@ void show_pte(struct mm_struct *mm, unsigned long addr) pte = pte_offset_map(pmd, addr); printk(", *pte=%08llx", (long long)pte_val(*pte)); +#ifndef CONFIG_ARM_LPAE printk(", *ppte=%08llx", (long long)pte_val(pte[PTE_HWTABLE_PTRS])); +#endif pte_unmap(pte); } while(0); @@ -428,6 +430,12 @@ do_translation_fault(unsigned long addr, unsigned int fsr, pmd = pmd_offset(pud, addr); pmd_k = pmd_offset(pud_k, addr); +#ifdef CONFIG_ARM_LPAE + /* + * Only one hardware entry per PMD with LPAE. + */ + index = 0; +#else /* * On ARM one Linux PGD entry contains two hardware entries (see page * tables layout in pgtable.h). We normally guarantee that we always @@ -437,6 +445,7 @@ do_translation_fault(unsigned long addr, unsigned int fsr, * for the first of pair. */ index = (addr >> SECTION_SHIFT) & 1; +#endif if (pmd_none(pmd_k[index])) goto bad_area; @@ -484,7 +493,11 @@ struct fsr_info { }; /* FSR definition */ +#ifdef CONFIG_ARM_LPAE +#include "fsr-3level.c" +#else #include "fsr-2level.c" +#endif void __init hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *), @@ -553,6 +566,7 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs) arm_notify_die("", regs, &info, ifsr, 0); } +#ifndef CONFIG_ARM_LPAE static int __init exceptions_init(void) { if (cpu_architecture() >= CPU_ARCH_ARMv6) { @@ -575,3 +589,4 @@ static int __init exceptions_init(void) } arch_initcall(exceptions_init); +#endif -- cgit v1.2.3