diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2013-09-04 17:43:16 +1000 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2013-09-04 17:43:16 +1000 |
commit | 3b502f84e6ad9c8f90f76de87e0ad0bc8cd59c87 (patch) | |
tree | f8ab4f0609de319dee53f6604f0619864e2ff366 | |
parent | 54b35c5105ecd7ebcd5d8c38c5ea48b5bdce66af (diff) | |
parent | ea192ea9969092d78b2d116ed31b2960271b52cd (diff) |
Merge branch 'akpm/master'
131 files changed, 2733 insertions, 2056 deletions
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 2a3330696372..8af4ad121828 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -490,6 +490,8 @@ pgpgin - # of charging events to the memory cgroup. The charging pgpgout - # of uncharging events to the memory cgroup. The uncharging event happens each time a page is unaccounted from the cgroup. swap - # of bytes of swap usage +writeback - # of bytes of file/anon cache that are queued for syncing to + disk. inactive_anon - # of bytes of anonymous and swap cache memory on inactive LRU list. active_anon - # of bytes of anonymous and swap cache memory on active diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 0c4132dd3507..98838a05ba6d 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -89,8 +89,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr, const struct exception_table_entry *fixup; int fault, si_code = SEGV_MAPERR; siginfo_t info; - unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (cause > 0 ? FAULT_FLAG_WRITE : 0)); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* As of EV6, a load into $31/$f31 is a prefetch, and never faults (or is suppressed by the PALcode). Support that for older CPUs @@ -115,7 +114,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr, if (address >= TASK_SIZE) goto vmalloc_fault; #endif - + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); vma = find_vma(mm, address); @@ -142,6 +142,7 @@ retry: } else { if (!(vma->vm_flags & VM_WRITE)) goto bad_area; + flags |= FAULT_FLAG_WRITE; } /* If for any reason at all we couldn't handle the fault, diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 0fd1f0d515ff..d63f3de0cd5b 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -60,8 +60,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address) siginfo_t info; int fault, ret; int write = regs->ecr_cause & ECR_C_PROTV_STORE; /* ST/EX */ - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (write ? FAULT_FLAG_WRITE : 0); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* * We fault-in kernel-space virtual memory on-demand. The @@ -89,6 +88,8 @@ void do_page_fault(struct pt_regs *regs, unsigned long address) if (in_atomic() || !mm) goto no_context; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); vma = find_vma(mm, address); @@ -117,12 +118,12 @@ good_area: if (write) { if (!(vma->vm_flags & VM_WRITE)) goto bad_area; + flags |= FAULT_FLAG_WRITE; } else { if (!(vma->vm_flags & (VM_READ | VM_EXEC))) goto bad_area; } -survive: /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo @@ -201,10 +202,6 @@ no_context: die("Oops", regs, address); out_of_memory: - if (is_global_init(tsk)) { - yield(); - goto survive; - } up_read(&mm->mmap_sem); if (user_mode(regs)) { diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index c97f7940cb95..eb8830a4c5ed 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -261,9 +261,7 @@ 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); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (notify_page_fault(regs, fsr)) return 0; @@ -282,6 +280,11 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (in_atomic() || !mm) goto no_context; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + if (fsr & FSR_WRITE) + flags |= FAULT_FLAG_WRITE; + /* * As per x86, we may deadlock here. However, since the kernel only * validly references user space from well defined areas of the code, @@ -349,6 +352,13 @@ retry: if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS)))) return 0; + /* + * If we are in kernel mode at this point, we + * have no context to handle this fault with. + */ + if (!user_mode(regs)) + goto no_context; + if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return to @@ -359,13 +369,6 @@ retry: return 0; } - /* - * If we are in kernel mode at this point, we - * have no context to handle this fault with. - */ - if (!user_mode(regs)) - goto no_context; - if (fault & VM_FAULT_SIGBUS) { /* * We had some memory, but were unable to diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 6c8ba25bf6bb..6d6acf153bff 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -199,13 +199,6 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC; unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; - if (esr & ESR_LNX_EXEC) { - vm_flags = VM_EXEC; - } else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) { - vm_flags = VM_WRITE; - mm_flags |= FAULT_FLAG_WRITE; - } - tsk = current; mm = tsk->mm; @@ -220,6 +213,16 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, if (in_atomic() || !mm) goto no_context; + if (user_mode(regs)) + mm_flags |= FAULT_FLAG_USER; + + if (esr & ESR_LNX_EXEC) { + vm_flags = VM_EXEC; + } else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) { + vm_flags = VM_WRITE; + mm_flags |= FAULT_FLAG_WRITE; + } + /* * As per x86, we may deadlock here. However, since the kernel only * validly references user space from well defined areas of the code, @@ -288,6 +291,13 @@ retry: VM_FAULT_BADACCESS)))) return 0; + /* + * If we are in kernel mode at this point, we have no context to + * handle this fault with. + */ + if (!user_mode(regs)) + goto no_context; + if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return to @@ -298,13 +308,6 @@ retry: return 0; } - /* - * If we are in kernel mode at this point, we have no context to - * handle this fault with. - */ - if (!user_mode(regs)) - goto no_context; - if (fault & VM_FAULT_SIGBUS) { /* * We had some memory, but were unable to successfully fix up diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index b2f2d2d66849..0eca93327195 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -86,6 +86,8 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs) local_irq_enable(); + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); @@ -228,9 +230,9 @@ no_context: */ out_of_memory: up_read(&mm->mmap_sem); - pagefault_out_of_memory(); if (!user_mode(regs)) goto no_context; + pagefault_out_of_memory(); return; do_sigbus: diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index 73312ab6c696..1790f22e71a2 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -58,8 +58,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs, struct vm_area_struct * vma; siginfo_t info; int fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - ((writeaccess & 1) ? FAULT_FLAG_WRITE : 0); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; D(printk(KERN_DEBUG "Page fault for %lX on %X at %lX, prot %d write %d\n", @@ -117,6 +116,8 @@ do_page_fault(unsigned long address, struct pt_regs *regs, if (in_atomic() || !mm) goto no_context; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); vma = find_vma(mm, address); @@ -155,6 +156,7 @@ retry: } else if (writeaccess == 1) { if (!(vma->vm_flags & VM_WRITE)) goto bad_area; + flags |= FAULT_FLAG_WRITE; } else { if (!(vma->vm_flags & (VM_READ | VM_EXEC))) goto bad_area; diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c index 331c1e2cfb67..9a66372fc7c7 100644 --- a/arch/frv/mm/fault.c +++ b/arch/frv/mm/fault.c @@ -34,11 +34,11 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear struct vm_area_struct *vma; struct mm_struct *mm; unsigned long _pme, lrai, lrad, fixup; + unsigned long flags = 0; siginfo_t info; pgd_t *pge; pud_t *pue; pte_t *pte; - int write; int fault; #if 0 @@ -81,6 +81,9 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear if (in_atomic() || !mm) goto no_context; + if (user_mode(__frame)) + flags |= FAULT_FLAG_USER; + down_read(&mm->mmap_sem); vma = find_vma(mm, ear0); @@ -129,7 +132,6 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear */ good_area: info.si_code = SEGV_ACCERR; - write = 0; switch (esr0 & ESR0_ATXC) { default: /* handle write to write protected page */ @@ -140,7 +142,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear #endif if (!(vma->vm_flags & VM_WRITE)) goto bad_area; - write = 1; + flags |= FAULT_FLAG_WRITE; break; /* handle read from protected page */ @@ -162,7 +164,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, ear0, write ? FAULT_FLAG_WRITE : 0); + fault = handle_mm_fault(mm, vma, ear0, flags); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 1bd276dbec7d..8704c9320032 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -53,8 +53,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) int si_code = SEGV_MAPERR; int fault; const struct exception_table_entry *fixup; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (cause > 0 ? FAULT_FLAG_WRITE : 0); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* * If we're in an interrupt or have no user context, @@ -65,6 +64,8 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) local_irq_enable(); + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); vma = find_vma(mm, address); @@ -96,6 +97,7 @@ good_area: case FLT_STORE: if (!(vma->vm_flags & VM_WRITE)) goto bad_area; + flags |= FAULT_FLAG_WRITE; break; } diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 6cf0341f978e..7225dad87094 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -90,8 +90,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT) | (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT)); - flags |= ((mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0); - /* mmap_sem is performance critical.... */ prefetchw(&mm->mmap_sem); @@ -119,6 +117,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (notify_page_fault(regs, TRAP_BRKPT)) return; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + if (mask & VM_WRITE) + flags |= FAULT_FLAG_WRITE; retry: down_read(&mm->mmap_sem); diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c index 3cdfa9c1d091..e9c6a8014bd6 100644 --- a/arch/m32r/mm/fault.c +++ b/arch/m32r/mm/fault.c @@ -78,7 +78,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, struct mm_struct *mm; struct vm_area_struct * vma; unsigned long page, addr; - int write; + unsigned long flags = 0; int fault; siginfo_t info; @@ -117,6 +117,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, if (in_atomic() || !mm) goto bad_area_nosemaphore; + if (error_code & ACE_USERMODE) + flags |= FAULT_FLAG_USER; + /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the * kernel and should generate an OOPS. Unfortunately, in the case of an @@ -166,14 +169,13 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, */ good_area: info.si_code = SEGV_ACCERR; - write = 0; switch (error_code & (ACE_WRITE|ACE_PROTECTION)) { default: /* 3: write, present */ /* fall through */ case ACE_WRITE: /* write, not present */ if (!(vma->vm_flags & VM_WRITE)) goto bad_area; - write++; + flags |= FAULT_FLAG_WRITE; break; case ACE_PROTECTION: /* read, present */ case 0: /* read, not present */ @@ -194,7 +196,7 @@ good_area: */ addr = (address & PAGE_MASK); set_thread_fault_code(error_code); - fault = handle_mm_fault(mm, vma, addr, write ? FAULT_FLAG_WRITE : 0); + fault = handle_mm_fault(mm, vma, addr, flags); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index a563727806bf..eb1d61f68725 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -88,6 +88,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (in_atomic() || !mm) goto no_context; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c index 8fddf46e6c62..332680e5ebf2 100644 --- a/arch/metag/mm/fault.c +++ b/arch/metag/mm/fault.c @@ -53,8 +53,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, struct vm_area_struct *vma, *prev_vma; siginfo_t info; int fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (write_access ? FAULT_FLAG_WRITE : 0); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; tsk = current; @@ -109,6 +108,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (in_atomic() || !mm) goto no_context; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); @@ -121,6 +122,7 @@ good_area: if (write_access) { if (!(vma->vm_flags & VM_WRITE)) goto bad_area; + flags |= FAULT_FLAG_WRITE; } else { if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) goto bad_area; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index 731f739d17a1..fa4cf52aa7a6 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -92,8 +92,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, int code = SEGV_MAPERR; int is_write = error_code & ESR_S; int fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (is_write ? FAULT_FLAG_WRITE : 0); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; regs->ear = address; regs->esr = error_code; @@ -121,6 +120,9 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, die("Weird page fault", regs, SIGSEGV); } + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the * kernel and should generate an OOPS. Unfortunately, in the case of an @@ -199,6 +201,7 @@ good_area: if (unlikely(is_write)) { if (unlikely(!(vma->vm_flags & VM_WRITE))) goto bad_area; + flags |= FAULT_FLAG_WRITE; /* a read */ } else { /* protection fault */ diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 85df1cd8d446..becc42bb1849 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -42,8 +42,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, const int field = sizeof(unsigned long) * 2; siginfo_t info; int fault; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (write ? FAULT_FLAG_WRITE : 0); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; #if 0 printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(), @@ -93,6 +92,8 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, if (in_atomic() || !mm) goto bad_area_nosemaphore; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); vma = find_vma(mm, address); @@ -114,6 +115,7 @@ good_area: if (write) { if (!(vma->vm_flags & VM_WRITE)) goto bad_area; + flags |= FAULT_FLAG_WRITE; } else { if (cpu_has_rixi) { if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) { @@ -241,6 +243,8 @@ out_of_memory: * (which will retry the fault, or kill us if we got oom-killed). */ up_read(&mm->mmap_sem); + if (!user_mode(regs)) + goto no_context; pagefault_out_of_memory(); return; diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c index 8a2e6ded9a44..3516cbdf1ee9 100644 --- a/arch/mn10300/mm/fault.c +++ b/arch/mn10300/mm/fault.c @@ -171,6 +171,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code, if (in_atomic() || !mm) goto no_context; + if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 4a41f8493ab0..0703acf7d327 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -86,6 +86,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, if (user_mode(regs)) { /* Exception was in userspace: reenable interrupts */ local_irq_enable(); + flags |= FAULT_FLAG_USER; } else { /* If exception was in a syscall, then IRQ's may have * been enabled or disabled. If they were enabled, diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f247a3480e8e..d10d27a720c0 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -180,6 +180,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, if (in_atomic() || !mm) goto no_context; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + if (acc_type & VM_WRITE) + flags |= FAULT_FLAG_WRITE; retry: down_read(&mm->mmap_sem); vma = find_vma_prev(mm, address, &prev_vma); @@ -203,8 +207,7 @@ good_area: * fault. */ - fault = handle_mm_fault(mm, vma, address, - flags | ((acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0)); + fault = handle_mm_fault(mm, vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 76d8e7cc7805..de9f66bdd672 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -223,9 +223,6 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, is_write = error_code & ESR_DST; #endif /* CONFIG_4xx || CONFIG_BOOKE */ - if (is_write) - flags |= FAULT_FLAG_WRITE; - #ifdef CONFIG_PPC_ICSWX /* * we need to do this early because this "data storage @@ -280,6 +277,9 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the * kernel and should generate an OOPS. Unfortunately, in the case of an @@ -408,6 +408,7 @@ good_area: } else if (is_write) { if (!(vma->vm_flags & VM_WRITE)) goto bad_area; + flags |= FAULT_FLAG_WRITE; /* a read */ } else { /* protection fault */ diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index f00aefb66a4e..35b81d65a21a 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -302,6 +302,8 @@ static inline int do_exception(struct pt_regs *regs, int access) address = trans_exc_code & __FAIL_ADDR_MASK; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400) flags |= FAULT_FLAG_WRITE; down_read(&mm->mmap_sem); diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c index 6b18fb0189ae..52238983527d 100644 --- a/arch/score/mm/fault.c +++ b/arch/score/mm/fault.c @@ -47,6 +47,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write, struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; const int field = sizeof(unsigned long) * 2; + unsigned long flags = 0; siginfo_t info; int fault; @@ -75,6 +76,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write, if (in_atomic() || !mm) goto bad_area_nosemaphore; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + down_read(&mm->mmap_sem); vma = find_vma(mm, address); if (!vma) @@ -95,18 +99,18 @@ good_area: if (write) { if (!(vma->vm_flags & VM_WRITE)) goto bad_area; + flags |= FAULT_FLAG_WRITE; } else { if (!(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))) goto bad_area; } -survive: /* * 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, address, write); + fault = handle_mm_fault(mm, vma, address, flags); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -167,11 +171,6 @@ no_context: */ out_of_memory: up_read(&mm->mmap_sem); - if (is_global_init(tsk)) { - yield(); - down_read(&mm->mmap_sem); - goto survive; - } if (!user_mode(regs)) goto no_context; pagefault_out_of_memory(); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 1f49c28affa9..541dc6101508 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -400,9 +400,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, struct mm_struct *mm; struct vm_area_struct * vma; int fault; - int write = error_code & FAULT_CODE_WRITE; - unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (write ? FAULT_FLAG_WRITE : 0)); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; tsk = current; mm = tsk->mm; @@ -476,6 +474,11 @@ good_area: set_thread_fault_code(error_code); + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + if (error_code & FAULT_CODE_WRITE) + flags |= FAULT_FLAG_WRITE; + /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index e98bfda205a2..59dbd4645725 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -177,8 +177,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, unsigned long g2; int from_user = !(regs->psr & PSR_PS); int fault, code; - unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (write ? FAULT_FLAG_WRITE : 0)); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (text_fault) address = regs->pc; @@ -235,6 +234,11 @@ good_area: goto bad_area; } + if (from_user) + flags |= FAULT_FLAG_USER; + if (write) + flags |= FAULT_FLAG_WRITE; + /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo @@ -383,6 +387,7 @@ static void force_user_fault(unsigned long address, int write) struct vm_area_struct *vma; struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; + unsigned int flags = FAULT_FLAG_USER; int code; code = SEGV_MAPERR; @@ -402,11 +407,12 @@ good_area: if (write) { if (!(vma->vm_flags & VM_WRITE)) goto bad_area; + flags |= FAULT_FLAG_WRITE; } else { if (!(vma->vm_flags & (VM_READ | VM_EXEC))) goto bad_area; } - switch (handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0)) { + switch (handle_mm_fault(mm, vma, address, flags)) { case VM_FAULT_SIGBUS: case VM_FAULT_OOM: goto do_sigbus; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 5062ff389e83..2ebec263d685 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -315,7 +315,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) bad_kernel_pc(regs, address); return; } - } + } else + flags |= FAULT_FLAG_USER; /* * If we're in an interrupt or have no user @@ -418,13 +419,14 @@ good_area: vma->vm_file != NULL) set_thread_fault_code(fault_code | FAULT_CODE_BLKCOMMIT); + + flags |= FAULT_FLAG_WRITE; } else { /* Allow reads even for write-only mappings */ if (!(vma->vm_flags & (VM_READ | VM_EXEC))) goto bad_area; } - flags |= ((fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0); fault = handle_mm_fault(mm, vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index 111d5a9b76f1..4c288f199453 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -280,8 +280,7 @@ static int handle_page_fault(struct pt_regs *regs, if (!is_page_fault) write = 1; - flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (write ? FAULT_FLAG_WRITE : 0)); + flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; is_kernel_mode = !user_mode(regs); @@ -365,6 +364,9 @@ static int handle_page_fault(struct pt_regs *regs, goto bad_area_nosemaphore; } + if (!is_kernel_mode) + flags |= FAULT_FLAG_USER; + /* * When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the @@ -425,12 +427,12 @@ good_area: #endif if (!(vma->vm_flags & VM_WRITE)) goto bad_area; + flags |= FAULT_FLAG_WRITE; } else { if (!is_page_fault || !(vma->vm_flags & VM_READ)) goto bad_area; } - survive: /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo @@ -555,11 +557,6 @@ no_context: */ out_of_memory: up_read(&mm->mmap_sem); - if (is_global_init(tsk)) { - yield(); - down_read(&mm->mmap_sem); - goto survive; - } if (is_kernel_mode) goto no_context; pagefault_out_of_memory(); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 089f3987e273..5c3aef74237f 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -30,8 +30,7 @@ int handle_page_fault(unsigned long address, unsigned long ip, pmd_t *pmd; pte_t *pte; int err = -EFAULT; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (is_write ? FAULT_FLAG_WRITE : 0); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; *code_out = SEGV_MAPERR; @@ -42,6 +41,8 @@ int handle_page_fault(unsigned long address, unsigned long ip, if (in_atomic()) goto out_nosemaphore; + if (is_user) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); vma = find_vma(mm, address); @@ -58,12 +59,15 @@ retry: good_area: *code_out = SEGV_ACCERR; - if (is_write && !(vma->vm_flags & VM_WRITE)) - goto out; - - /* Don't require VM_READ|VM_EXEC for write faults! */ - if (!is_write && !(vma->vm_flags & (VM_READ | VM_EXEC))) - goto out; + if (is_write) { + if (!(vma->vm_flags & VM_WRITE)) + goto out; + flags |= FAULT_FLAG_WRITE; + } else { + /* Don't require VM_READ|VM_EXEC for write faults! */ + if (!(vma->vm_flags & (VM_READ | VM_EXEC))) + goto out; + } do { int fault; @@ -124,6 +128,8 @@ out_of_memory: * (which will retry the fault, or kill us if we got oom-killed). */ up_read(&mm->mmap_sem); + if (!is_user) + goto out_nosemaphore; pagefault_out_of_memory(); return 0; } diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c index f9b5c10bccee..0dc922dba915 100644 --- a/arch/unicore32/mm/fault.c +++ b/arch/unicore32/mm/fault.c @@ -209,8 +209,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs) struct task_struct *tsk; struct mm_struct *mm; int fault, sig, code; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - ((!(fsr ^ 0x12)) ? FAULT_FLAG_WRITE : 0); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; tsk = current; mm = tsk->mm; @@ -222,6 +221,11 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (in_atomic() || !mm) goto no_context; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + if (!(fsr ^ 0x12)) + flags |= FAULT_FLAG_WRITE; + /* * As per x86, we may deadlock here. However, since the kernel only * validly references user space from well defined areas of the code, @@ -278,6 +282,13 @@ retry: (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS)))) return 0; + /* + * If we are in kernel mode at this point, we + * have no context to handle this fault with. + */ + if (!user_mode(regs)) + goto no_context; + if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return to @@ -288,13 +299,6 @@ retry: return 0; } - /* - * If we are in kernel mode at this point, we - * have no context to handle this fault with. - */ - if (!user_mode(regs)) - goto no_context; - if (fault & VM_FAULT_SIGBUS) { /* * We had some memory, but were unable to diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 6e2d2c8f230b..dce0df8150df 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4421,13 +4421,12 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) } } -static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long +mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { struct kvm *kvm; int nr_to_scan = sc->nr_to_scan; - - if (nr_to_scan == 0) - goto out; + unsigned long freed = 0; raw_spin_lock(&kvm_lock); @@ -4462,25 +4461,37 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) goto unlock; } - prepare_zap_oldest_mmu_page(kvm, &invalid_list); + if (prepare_zap_oldest_mmu_page(kvm, &invalid_list)) + freed++; kvm_mmu_commit_zap_page(kvm, &invalid_list); unlock: spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); + /* + * unfair on small ones + * per-vm shrinkers cry out + * sadness comes quickly + */ list_move_tail(&kvm->vm_list, &vm_list); break; } raw_spin_unlock(&kvm_lock); + return freed; -out: +} + +static unsigned long +mmu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ return percpu_counter_read_positive(&kvm_total_used_mmu_pages); } static struct shrinker mmu_shrinker = { - .shrink = mmu_shrink, + .count_objects = mmu_shrink_count, + .scan_objects = mmu_shrink_scan, .seeks = DEFAULT_SEEKS * 10, }; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 654be4ae3047..3aaeffcfd67a 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -842,23 +842,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, force_sig_info_fault(SIGBUS, code, address, tsk, fault); } -static noinline int +static noinline void mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { - /* - * Pagefault was interrupted by SIGKILL. We have no reason to - * continue pagefault. - */ - if (fatal_signal_pending(current)) { - if (!(fault & VM_FAULT_RETRY)) - up_read(¤t->mm->mmap_sem); - if (!(error_code & PF_USER)) - no_context(regs, error_code, address, 0, 0); - return 1; + if (fatal_signal_pending(current) && !(error_code & PF_USER)) { + up_read(¤t->mm->mmap_sem); + no_context(regs, error_code, address, 0, 0); + return; } - if (!(fault & VM_FAULT_ERROR)) - return 0; if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ @@ -866,7 +858,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, up_read(¤t->mm->mmap_sem); no_context(regs, error_code, address, SIGSEGV, SEGV_MAPERR); - return 1; + return; } up_read(¤t->mm->mmap_sem); @@ -884,7 +876,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, else BUG(); } - return 1; } static int spurious_fault_check(unsigned long error_code, pte_t *pte) @@ -1011,9 +1002,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) unsigned long address; struct mm_struct *mm; int fault; - int write = error_code & PF_WRITE; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (write ? FAULT_FLAG_WRITE : 0); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; tsk = current; mm = tsk->mm; @@ -1083,6 +1072,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) if (user_mode_vm(regs)) { local_irq_enable(); error_code |= PF_USER; + flags |= FAULT_FLAG_USER; } else { if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); @@ -1109,6 +1099,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) return; } + if (error_code & PF_WRITE) + flags |= FAULT_FLAG_WRITE; + /* * When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in @@ -1187,9 +1180,17 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, flags); - if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { - if (mm_fault_error(regs, error_code, address, fault)) - return; + /* + * 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 (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))) + return; + + if (unlikely(fault & VM_FAULT_ERROR)) { + mm_fault_error(regs, error_code, address, fault); + return; } /* diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 4b7bc8db170f..70fa7bc42b4a 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -72,6 +72,8 @@ void do_page_fault(struct pt_regs *regs) address, exccause, regs->pc, is_write? "w":"", is_exec? "x":""); #endif + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; retry: down_read(&mm->mmap_sem); vma = find_vma(mm, address); diff --git a/drivers/base/node.c b/drivers/base/node.c index 7616a77ca322..bc9f43bf7e29 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -125,13 +125,7 @@ static ssize_t node_read_meminfo(struct device *dev, nid, K(node_page_state(nid, NR_WRITEBACK)), nid, K(node_page_state(nid, NR_FILE_PAGES)), nid, K(node_page_state(nid, NR_FILE_MAPPED)), -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - nid, K(node_page_state(nid, NR_ANON_PAGES) - + node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) * - HPAGE_PMD_NR), -#else nid, K(node_page_state(nid, NR_ANON_PAGES)), -#endif nid, K(node_page_state(nid, NR_SHMEM)), nid, node_page_state(nid, NR_KERNEL_STACK) * THREAD_SIZE / 1024, diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 3de60503378e..52f5ad8037cc 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1670,7 +1670,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) return 0; out_gem_unload: - if (dev_priv->mm.inactive_shrinker.shrink) + if (dev_priv->mm.inactive_shrinker.scan_objects) unregister_shrinker(&dev_priv->mm.inactive_shrinker); if (dev->pdev->msi_enabled) @@ -1709,7 +1709,7 @@ int i915_driver_unload(struct drm_device *dev) i915_teardown_sysfs(dev); - if (dev_priv->mm.inactive_shrinker.shrink) + if (dev_priv->mm.inactive_shrinker.scan_objects) unregister_shrinker(&dev_priv->mm.inactive_shrinker); mutex_lock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index f21a0c36a40b..ed9f4e71662f 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -57,10 +57,12 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj, struct drm_i915_fence_reg *fence, bool enable); -static int i915_gem_inactive_shrink(struct shrinker *shrinker, - struct shrink_control *sc); +static unsigned long i915_gem_inactive_count(struct shrinker *shrinker, + struct shrink_control *sc); +static unsigned long i915_gem_inactive_scan(struct shrinker *shrinker, + struct shrink_control *sc); static long i915_gem_purge(struct drm_i915_private *dev_priv, long target); -static void i915_gem_shrink_all(struct drm_i915_private *dev_priv); +static long i915_gem_shrink_all(struct drm_i915_private *dev_priv); static void i915_gem_object_truncate(struct drm_i915_gem_object *obj); static bool cpu_cache_is_coherent(struct drm_device *dev, @@ -1736,16 +1738,21 @@ i915_gem_purge(struct drm_i915_private *dev_priv, long target) return __i915_gem_shrink(dev_priv, target, true); } -static void +static long i915_gem_shrink_all(struct drm_i915_private *dev_priv) { struct drm_i915_gem_object *obj, *next; + long freed = 0; i915_gem_evict_everything(dev_priv->dev); list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, - global_list) + global_list) { + if (obj->pages_pin_count == 0) + freed += obj->base.size >> PAGE_SHIFT; i915_gem_object_put_pages(obj); + } + return freed; } static int @@ -4525,7 +4532,8 @@ i915_gem_load(struct drm_device *dev) dev_priv->mm.interruptible = true; - dev_priv->mm.inactive_shrinker.shrink = i915_gem_inactive_shrink; + dev_priv->mm.inactive_shrinker.scan_objects = i915_gem_inactive_scan; + dev_priv->mm.inactive_shrinker.count_objects = i915_gem_inactive_count; dev_priv->mm.inactive_shrinker.seeks = DEFAULT_SEEKS; register_shrinker(&dev_priv->mm.inactive_shrinker); } @@ -4748,8 +4756,8 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task) #endif } -static int -i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc) +static unsigned long +i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc) { struct drm_i915_private *dev_priv = container_of(shrinker, @@ -4757,45 +4765,35 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc) mm.inactive_shrinker); struct drm_device *dev = dev_priv->dev; struct drm_i915_gem_object *obj; - int nr_to_scan = sc->nr_to_scan; bool unlock = true; - int cnt; + unsigned long count; if (!mutex_trylock(&dev->struct_mutex)) { if (!mutex_is_locked_by(&dev->struct_mutex, current)) - return 0; + return SHRINK_STOP; if (dev_priv->mm.shrinker_no_lock_stealing) - return 0; + return SHRINK_STOP; unlock = false; } - if (nr_to_scan) { - nr_to_scan -= i915_gem_purge(dev_priv, nr_to_scan); - if (nr_to_scan > 0) - nr_to_scan -= __i915_gem_shrink(dev_priv, nr_to_scan, - false); - if (nr_to_scan > 0) - i915_gem_shrink_all(dev_priv); - } - - cnt = 0; + count = 0; list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) if (obj->pages_pin_count == 0) - cnt += obj->base.size >> PAGE_SHIFT; + count += obj->base.size >> PAGE_SHIFT; list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { if (obj->active) continue; if (obj->pin_count == 0 && obj->pages_pin_count == 0) - cnt += obj->base.size >> PAGE_SHIFT; + count += obj->base.size >> PAGE_SHIFT; } if (unlock) mutex_unlock(&dev->struct_mutex); - return cnt; + return count; } /* All the new VM stuff */ @@ -4859,6 +4857,40 @@ unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o, return 0; } +static unsigned long +i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc) +{ + struct drm_i915_private *dev_priv = + container_of(shrinker, + struct drm_i915_private, + mm.inactive_shrinker); + struct drm_device *dev = dev_priv->dev; + int nr_to_scan = sc->nr_to_scan; + unsigned long freed; + bool unlock = true; + + if (!mutex_trylock(&dev->struct_mutex)) { + if (!mutex_is_locked_by(&dev->struct_mutex, current)) + return 0; + + if (dev_priv->mm.shrinker_no_lock_stealing) + return 0; + + unlock = false; + } + + freed = i915_gem_purge(dev_priv, nr_to_scan); + if (freed < nr_to_scan) + freed += __i915_gem_shrink(dev_priv, nr_to_scan, + false); + if (freed < nr_to_scan) + freed += i915_gem_shrink_all(dev_priv); + + if (unlock) + mutex_unlock(&dev->struct_mutex); + return freed; +} + struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj, struct i915_address_space *vm) { diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index bd2a3b40cd12..863bef9f9234 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -377,28 +377,26 @@ out: return nr_free; } -/* Get good estimation how many pages are free in pools */ -static int ttm_pool_get_num_unused_pages(void) -{ - unsigned i; - int total = 0; - for (i = 0; i < NUM_POOLS; ++i) - total += _manager->pools[i].npages; - - return total; -} - /** * Callback for mm to request pool to reduce number of page held. + * + * XXX: (dchinner) Deadlock warning! + * + * ttm_page_pool_free() does memory allocation using GFP_KERNEL. that means + * this can deadlock when called a sc->gfp_mask that is not equal to + * GFP_KERNEL. + * + * This code is crying out for a shrinker per pool.... */ -static int ttm_pool_mm_shrink(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long +ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { static atomic_t start_pool = ATOMIC_INIT(0); unsigned i; unsigned pool_offset = atomic_add_return(1, &start_pool); struct ttm_page_pool *pool; int shrink_pages = sc->nr_to_scan; + unsigned long freed = 0; pool_offset = pool_offset % NUM_POOLS; /* select start pool in round robin fashion */ @@ -408,14 +406,28 @@ static int ttm_pool_mm_shrink(struct shrinker *shrink, break; pool = &_manager->pools[(i + pool_offset)%NUM_POOLS]; shrink_pages = ttm_page_pool_free(pool, nr_free); + freed += nr_free - shrink_pages; } - /* return estimated number of unused pages in pool */ - return ttm_pool_get_num_unused_pages(); + return freed; +} + + +static unsigned long +ttm_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ + unsigned i; + unsigned long count = 0; + + for (i = 0; i < NUM_POOLS; ++i) + count += _manager->pools[i].npages; + + return count; } static void ttm_pool_mm_shrink_init(struct ttm_pool_manager *manager) { - manager->mm_shrink.shrink = &ttm_pool_mm_shrink; + manager->mm_shrink.count_objects = ttm_pool_shrink_count; + manager->mm_shrink.scan_objects = ttm_pool_shrink_scan; manager->mm_shrink.seeks = 1; register_shrinker(&manager->mm_shrink); } diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c index b8b394319b45..7957beeeaf73 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c @@ -918,19 +918,6 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev) } EXPORT_SYMBOL_GPL(ttm_dma_populate); -/* Get good estimation how many pages are free in pools */ -static int ttm_dma_pool_get_num_unused_pages(void) -{ - struct device_pools *p; - unsigned total = 0; - - mutex_lock(&_manager->lock); - list_for_each_entry(p, &_manager->pools, pools) - total += p->pool->npages_free; - mutex_unlock(&_manager->lock); - return total; -} - /* Put all pages in pages list to correct pool to wait for reuse */ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev) { @@ -1002,18 +989,29 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate); /** * Callback for mm to request pool to reduce number of page held. + * + * XXX: (dchinner) Deadlock warning! + * + * ttm_dma_page_pool_free() does GFP_KERNEL memory allocation, and so attention + * needs to be paid to sc->gfp_mask to determine if this can be done or not. + * GFP_KERNEL memory allocation in a GFP_ATOMIC reclaim context woul dbe really + * bad. + * + * I'm getting sadder as I hear more pathetical whimpers about needing per-pool + * shrinkers */ -static int ttm_dma_pool_mm_shrink(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long +ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { static atomic_t start_pool = ATOMIC_INIT(0); unsigned idx = 0; unsigned pool_offset = atomic_add_return(1, &start_pool); unsigned shrink_pages = sc->nr_to_scan; struct device_pools *p; + unsigned long freed = 0; if (list_empty(&_manager->pools)) - return 0; + return SHRINK_STOP; mutex_lock(&_manager->lock); pool_offset = pool_offset % _manager->npools; @@ -1029,18 +1027,33 @@ static int ttm_dma_pool_mm_shrink(struct shrinker *shrink, continue; nr_free = shrink_pages; shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free); + freed += nr_free - shrink_pages; + pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n", p->pool->dev_name, p->pool->name, current->pid, nr_free, shrink_pages); } mutex_unlock(&_manager->lock); - /* return estimated number of unused pages in pool */ - return ttm_dma_pool_get_num_unused_pages(); + return freed; +} + +static unsigned long +ttm_dma_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ + struct device_pools *p; + unsigned long count = 0; + + mutex_lock(&_manager->lock); + list_for_each_entry(p, &_manager->pools, pools) + count += p->pool->npages_free; + mutex_unlock(&_manager->lock); + return count; } static void ttm_dma_pool_mm_shrink_init(struct ttm_pool_manager *manager) { - manager->mm_shrink.shrink = &ttm_dma_pool_mm_shrink; + manager->mm_shrink.count_objects = ttm_dma_pool_shrink_count; + manager->mm_shrink.scan_objects = &ttm_dma_pool_shrink_scan; manager->mm_shrink.seeks = 1; register_shrinker(&manager->mm_shrink); } diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index ee372884c405..f9764e61978b 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -597,24 +597,19 @@ static int mca_reap(struct btree *b, struct closure *cl, unsigned min_order) return 0; } -static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long bch_mca_scan(struct shrinker *shrink, + struct shrink_control *sc) { struct cache_set *c = container_of(shrink, struct cache_set, shrink); struct btree *b, *t; unsigned long i, nr = sc->nr_to_scan; + unsigned long freed = 0; if (c->shrinker_disabled) - return 0; + return SHRINK_STOP; if (c->try_harder) - return 0; - - /* - * If nr == 0, we're supposed to return the number of items we have - * cached. Not allowed to return -1. - */ - if (!nr) - return mca_can_free(c) * c->btree_pages; + return SHRINK_STOP; /* Return -1 if we can't do anything right now */ if (sc->gfp_mask & __GFP_WAIT) @@ -634,14 +629,14 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc) i = 0; list_for_each_entry_safe(b, t, &c->btree_cache_freeable, list) { - if (!nr) + if (freed >= nr) break; if (++i > 3 && !mca_reap(b, NULL, 0)) { mca_data_free(b); rw_unlock(true, b); - --nr; + freed++; } } @@ -652,7 +647,7 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc) if (list_empty(&c->btree_cache)) goto out; - for (i = 0; nr && i < c->bucket_cache_used; i++) { + for (i = 0; (nr--) && i < c->bucket_cache_used; i++) { b = list_first_entry(&c->btree_cache, struct btree, list); list_rotate_left(&c->btree_cache); @@ -661,14 +656,27 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc) mca_bucket_free(b); mca_data_free(b); rw_unlock(true, b); - --nr; + freed++; } else b->accessed = 0; } out: - nr = mca_can_free(c) * c->btree_pages; mutex_unlock(&c->bucket_lock); - return nr; + return freed; +} + +static unsigned long bch_mca_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct cache_set *c = container_of(shrink, struct cache_set, shrink); + + if (c->shrinker_disabled) + return 0; + + if (c->try_harder) + return 0; + + return mca_can_free(c) * c->btree_pages; } void bch_btree_cache_free(struct cache_set *c) @@ -737,7 +745,8 @@ int bch_btree_cache_alloc(struct cache_set *c) c->verify_data = NULL; #endif - c->shrink.shrink = bch_mca_shrink; + c->shrink.count_objects = bch_mca_count; + c->shrink.scan_objects = bch_mca_scan; c->shrink.seeks = 4; c->shrink.batch = c->btree_pages * 2; register_shrinker(&c->shrink); diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 12a2c2846f99..4fe6ab2fbe2e 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -556,7 +556,7 @@ STORE(__bch_cache_set) struct shrink_control sc; sc.gfp_mask = GFP_KERNEL; sc.nr_to_scan = strtoul_or_return(buf); - c->shrink.shrink(&c->shrink, &sc); + c->shrink.scan_objects(&c->shrink, &sc); } sysfs_strtoul(congested_read_threshold_us, diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 5227e079a6e3..173cbb20d104 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1425,62 +1425,75 @@ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp, unsigned long max_jiffies) { if (jiffies - b->last_accessed < max_jiffies) - return 1; + return 0; if (!(gfp & __GFP_IO)) { if (test_bit(B_READING, &b->state) || test_bit(B_WRITING, &b->state) || test_bit(B_DIRTY, &b->state)) - return 1; + return 0; } if (b->hold_count) - return 1; + return 0; __make_buffer_clean(b); __unlink_buffer(b); __free_buffer_wake(b); - return 0; + return 1; } -static void __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, - struct shrink_control *sc) +static long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, + gfp_t gfp_mask) { int l; struct dm_buffer *b, *tmp; + long freed = 0; for (l = 0; l < LIST_SIZE; l++) { - list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) - if (!__cleanup_old_buffer(b, sc->gfp_mask, 0) && - !--nr_to_scan) - return; + list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) { + freed += __cleanup_old_buffer(b, gfp_mask, 0); + if (!--nr_to_scan) + break; + } dm_bufio_cond_resched(); } + return freed; } -static int shrink(struct shrinker *shrinker, struct shrink_control *sc) +static unsigned long +dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { - struct dm_bufio_client *c = - container_of(shrinker, struct dm_bufio_client, shrinker); - unsigned long r; - unsigned long nr_to_scan = sc->nr_to_scan; + struct dm_bufio_client *c; + unsigned long freed; + c = container_of(shrink, struct dm_bufio_client, shrinker); if (sc->gfp_mask & __GFP_IO) dm_bufio_lock(c); else if (!dm_bufio_trylock(c)) - return !nr_to_scan ? 0 : -1; + return SHRINK_STOP; - if (nr_to_scan) - __scan(c, nr_to_scan, sc); + freed = __scan(c, sc->nr_to_scan, sc->gfp_mask); + dm_bufio_unlock(c); + return freed; +} - r = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY]; - if (r > INT_MAX) - r = INT_MAX; +static unsigned long +dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ + struct dm_bufio_client *c; + unsigned long count; - dm_bufio_unlock(c); + c = container_of(shrink, struct dm_bufio_client, shrinker); + if (sc->gfp_mask & __GFP_IO) + dm_bufio_lock(c); + else if (!dm_bufio_trylock(c)) + return 0; - return r; + count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY]; + dm_bufio_unlock(c); + return count; } /* @@ -1582,7 +1595,8 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign __cache_size_refresh(); mutex_unlock(&dm_bufio_clients_lock); - c->shrinker.shrink = shrink; + c->shrinker.count_objects = dm_bufio_shrink_count; + c->shrinker.scan_objects = dm_bufio_shrink_scan; c->shrinker.seeks = 1; c->shrinker.batch = 0; register_shrinker(&c->shrinker); @@ -1669,7 +1683,7 @@ static void cleanup_old_buffers(void) struct dm_buffer *b; b = list_entry(c->lru[LIST_CLEAN].prev, struct dm_buffer, lru_list); - if (__cleanup_old_buffer(b, 0, max_age * HZ)) + if (!__cleanup_old_buffer(b, 0, max_age * HZ)) break; dm_bufio_cond_resched(); } diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 21a3f7250531..8e76ddca0999 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -341,27 +341,26 @@ out: /* * ashmem_shrink - our cache shrinker, called from mm/vmscan.c :: shrink_slab * - * 'nr_to_scan' is the number of objects (pages) to prune, or 0 to query how - * many objects (pages) we have in total. + * 'nr_to_scan' is the number of objects to scan for freeing. * * 'gfp_mask' is the mask of the allocation that got us into this mess. * - * Return value is the number of objects (pages) remaining, or -1 if we cannot + * Return value is the number of objects freed or -1 if we cannot * proceed without risk of deadlock (due to gfp_mask). * * We approximate LRU via least-recently-unpinned, jettisoning unpinned partial * chunks of ashmem regions LRU-wise one-at-a-time until we hit 'nr_to_scan' * pages freed. */ -static int ashmem_shrink(struct shrinker *s, struct shrink_control *sc) +static unsigned long +ashmem_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { struct ashmem_range *range, *next; + unsigned long freed = 0; /* We might recurse into filesystem code, so bail out if necessary */ - if (sc->nr_to_scan && !(sc->gfp_mask & __GFP_FS)) - return -1; - if (!sc->nr_to_scan) - return lru_count; + if (!(sc->gfp_mask & __GFP_FS)) + return SHRINK_STOP; mutex_lock(&ashmem_mutex); list_for_each_entry_safe(range, next, &ashmem_lru_list, lru) { @@ -374,17 +373,32 @@ static int ashmem_shrink(struct shrinker *s, struct shrink_control *sc) range->purged = ASHMEM_WAS_PURGED; lru_del(range); - sc->nr_to_scan -= range_size(range); - if (sc->nr_to_scan <= 0) + freed += range_size(range); + if (--sc->nr_to_scan <= 0) break; } mutex_unlock(&ashmem_mutex); + return freed; +} +static unsigned long +ashmem_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ + /* + * note that lru_count is count of pages on the lru, not a count of + * objects on the list. This means the scan function needs to return the + * number of pages freed, not the number of objects scanned. + */ return lru_count; } static struct shrinker ashmem_shrinker = { - .shrink = ashmem_shrink, + .count_objects = ashmem_shrink_count, + .scan_objects = ashmem_shrink_scan, + /* + * XXX (dchinner): I wish people would comment on why they need on + * significant changes to the default value here + */ .seeks = DEFAULT_SEEKS * 4, }; @@ -690,11 +704,11 @@ static long ashmem_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (capable(CAP_SYS_ADMIN)) { struct shrink_control sc = { .gfp_mask = GFP_KERNEL, - .nr_to_scan = 0, + .nr_to_scan = LONG_MAX, }; - ret = ashmem_shrink(&ashmem_shrinker, &sc); - sc.nr_to_scan = ret; - ashmem_shrink(&ashmem_shrinker, &sc); + + nodes_setall(sc.nodes_to_scan); + ashmem_shrink_scan(&ashmem_shrinker, &sc); } break; } diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c index fe74494868ef..6f094b37f1f1 100644 --- a/drivers/staging/android/lowmemorykiller.c +++ b/drivers/staging/android/lowmemorykiller.c @@ -66,11 +66,20 @@ static unsigned long lowmem_deathpending_timeout; pr_info(x); \ } while (0) -static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc) +static unsigned long lowmem_count(struct shrinker *s, + struct shrink_control *sc) +{ + return global_page_state(NR_ACTIVE_ANON) + + global_page_state(NR_ACTIVE_FILE) + + global_page_state(NR_INACTIVE_ANON) + + global_page_state(NR_INACTIVE_FILE); +} + +static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc) { struct task_struct *tsk; struct task_struct *selected = NULL; - int rem = 0; + unsigned long rem = 0; int tasksize; int i; short min_score_adj = OOM_SCORE_ADJ_MAX + 1; @@ -92,19 +101,17 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc) break; } } - if (sc->nr_to_scan > 0) - lowmem_print(3, "lowmem_shrink %lu, %x, ofree %d %d, ma %hd\n", - sc->nr_to_scan, sc->gfp_mask, other_free, - other_file, min_score_adj); - rem = global_page_state(NR_ACTIVE_ANON) + - global_page_state(NR_ACTIVE_FILE) + - global_page_state(NR_INACTIVE_ANON) + - global_page_state(NR_INACTIVE_FILE); - if (sc->nr_to_scan <= 0 || min_score_adj == OOM_SCORE_ADJ_MAX + 1) { - lowmem_print(5, "lowmem_shrink %lu, %x, return %d\n", - sc->nr_to_scan, sc->gfp_mask, rem); - return rem; + + lowmem_print(3, "lowmem_scan %lu, %x, ofree %d %d, ma %hd\n", + sc->nr_to_scan, sc->gfp_mask, other_free, + other_file, min_score_adj); + + if (min_score_adj == OOM_SCORE_ADJ_MAX + 1) { + lowmem_print(5, "lowmem_scan %lu, %x, return 0\n", + sc->nr_to_scan, sc->gfp_mask); + return 0; } + selected_oom_score_adj = min_score_adj; rcu_read_lock(); @@ -154,16 +161,18 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc) lowmem_deathpending_timeout = jiffies + HZ; send_sig(SIGKILL, selected, 0); set_tsk_thread_flag(selected, TIF_MEMDIE); - rem -= selected_tasksize; + rem += selected_tasksize; } - lowmem_print(4, "lowmem_shrink %lu, %x, return %d\n", + + lowmem_print(4, "lowmem_scan %lu, %x, return %lu\n", sc->nr_to_scan, sc->gfp_mask, rem); rcu_read_unlock(); return rem; } static struct shrinker lowmem_shrinker = { - .shrink = lowmem_shrink, + .scan_objects = lowmem_scan, + .count_objects = lowmem_count, .seeks = DEFAULT_SEEKS * 16 }; diff --git a/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h b/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h index 63efb7b456c6..2af15d41e77a 100644 --- a/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h +++ b/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h @@ -79,42 +79,4 @@ do { __oldfs = get_fs(); set_fs(get_ds());} while(0) #define MMSPACE_CLOSE set_fs(__oldfs) -/* - * Shrinker - */ - -# define SHRINKER_ARGS(sc, nr_to_scan, gfp_mask) \ - struct shrinker *shrinker, \ - struct shrink_control *sc -# define shrink_param(sc, var) ((sc)->var) - -typedef int (*shrinker_t)(SHRINKER_ARGS(sc, nr_to_scan, gfp_mask)); - -static inline -struct shrinker *set_shrinker(int seek, shrinker_t func) -{ - struct shrinker *s; - - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (s == NULL) - return (NULL); - - s->shrink = func; - s->seeks = seek; - - register_shrinker(s); - - return s; -} - -static inline -void remove_shrinker(struct shrinker *shrinker) -{ - if (shrinker == NULL) - return; - - unregister_shrinker(shrinker); - kfree(shrinker); -} - #endif /* __LINUX_CFS_MEM_H__ */ diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c b/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c index 454027d68d54..0025ee6356da 100644 --- a/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c +++ b/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c @@ -521,7 +521,7 @@ static int ldlm_cli_pool_shrink(struct ldlm_pool *pl, int nr, unsigned int gfp_mask) { struct ldlm_namespace *ns; - int canceled = 0, unused; + int unused; ns = ldlm_pl2ns(pl); @@ -540,14 +540,10 @@ static int ldlm_cli_pool_shrink(struct ldlm_pool *pl, unused = ns->ns_nr_unused; spin_unlock(&ns->ns_lock); - if (nr) { - canceled = ldlm_cancel_lru(ns, nr, LCF_ASYNC, - LDLM_CANCEL_SHRINK); - } - /* - * Return the number of potentially reclaimable locks. - */ - return ((unused - canceled) / 100) * sysctl_vfs_cache_pressure; + if (nr == 0) + return (unused / 100) * sysctl_vfs_cache_pressure; + else + return ldlm_cancel_lru(ns, nr, LCF_ASYNC, LDLM_CANCEL_SHRINK); } struct ldlm_pool_ops ldlm_srv_pool_ops = { @@ -601,9 +597,10 @@ int ldlm_pool_recalc(struct ldlm_pool *pl) return recalc_interval_sec; } -/** +/* * Pool shrink wrapper. Will call either client or server pool recalc callback - * depending what pool \a pl is used. + * depending what pool pl is used. When nr == 0, just return the number of + * freeable locks. Otherwise, return the number of canceled locks. */ int ldlm_pool_shrink(struct ldlm_pool *pl, int nr, unsigned int gfp_mask) @@ -1017,29 +1014,24 @@ static int ldlm_pool_granted(struct ldlm_pool *pl) } static struct ptlrpc_thread *ldlm_pools_thread; -static struct shrinker *ldlm_pools_srv_shrinker; -static struct shrinker *ldlm_pools_cli_shrinker; static struct completion ldlm_pools_comp; /* - * Cancel \a nr locks from all namespaces (if possible). Returns number of - * cached locks after shrink is finished. All namespaces are asked to - * cancel approximately equal amount of locks to keep balancing. + * count locks from all namespaces (if possible). Returns number of + * cached locks. */ -static int ldlm_pools_shrink(ldlm_side_t client, int nr, - unsigned int gfp_mask) +static unsigned long ldlm_pools_count(ldlm_side_t client, unsigned int gfp_mask) { - int total = 0, cached = 0, nr_ns; + int total = 0, nr_ns; struct ldlm_namespace *ns; struct ldlm_namespace *ns_old = NULL; /* loop detection */ void *cookie; - if (client == LDLM_NAMESPACE_CLIENT && nr != 0 && - !(gfp_mask & __GFP_FS)) - return -1; + if (client == LDLM_NAMESPACE_CLIENT && !(gfp_mask & __GFP_FS)) + return 0; - CDEBUG(D_DLMTRACE, "Request to shrink %d %s locks from all pools\n", - nr, client == LDLM_NAMESPACE_CLIENT ? "client" : "server"); + CDEBUG(D_DLMTRACE, "Request to count %s locks from all pools\n", + client == LDLM_NAMESPACE_CLIENT ? "client" : "server"); cookie = cl_env_reenter(); @@ -1047,8 +1039,7 @@ static int ldlm_pools_shrink(ldlm_side_t client, int nr, * Find out how many resources we may release. */ for (nr_ns = ldlm_namespace_nr_read(client); - nr_ns > 0; nr_ns--) - { + nr_ns > 0; nr_ns--) { mutex_lock(ldlm_namespace_lock(client)); if (list_empty(ldlm_namespace_list(client))) { mutex_unlock(ldlm_namespace_lock(client)); @@ -1078,17 +1069,27 @@ static int ldlm_pools_shrink(ldlm_side_t client, int nr, ldlm_namespace_put(ns); } - if (nr == 0 || total == 0) { - cl_env_reexit(cookie); - return total; - } + cl_env_reexit(cookie); + return total; +} + +static unsigned long ldlm_pools_scan(ldlm_side_t client, int nr, unsigned int gfp_mask) +{ + unsigned long freed = 0; + int tmp, nr_ns; + struct ldlm_namespace *ns; + void *cookie; + + if (client == LDLM_NAMESPACE_CLIENT && !(gfp_mask & __GFP_FS)) + return -1; + + cookie = cl_env_reenter(); /* - * Shrink at least ldlm_namespace_nr(client) namespaces. + * Shrink at least ldlm_namespace_nr_read(client) namespaces. */ - for (nr_ns = ldlm_namespace_nr_read(client) - nr_ns; - nr_ns > 0; nr_ns--) - { + for (tmp = nr_ns = ldlm_namespace_nr_read(client); + tmp > 0; tmp--) { int cancel, nr_locks; /* @@ -1097,12 +1098,6 @@ static int ldlm_pools_shrink(ldlm_side_t client, int nr, mutex_lock(ldlm_namespace_lock(client)); if (list_empty(ldlm_namespace_list(client))) { mutex_unlock(ldlm_namespace_lock(client)); - /* - * If list is empty, we can't return any @cached > 0, - * that probably would cause needless shrinker - * call. - */ - cached = 0; break; } ns = ldlm_namespace_first_locked(client); @@ -1111,29 +1106,42 @@ static int ldlm_pools_shrink(ldlm_side_t client, int nr, mutex_unlock(ldlm_namespace_lock(client)); nr_locks = ldlm_pool_granted(&ns->ns_pool); - cancel = 1 + nr_locks * nr / total; - ldlm_pool_shrink(&ns->ns_pool, cancel, gfp_mask); - cached += ldlm_pool_granted(&ns->ns_pool); + /* + * We use to shrink propotionally but with new shrinker API, + * we lost the total number of freeable locks. + */ + cancel = 1 + min_t(int, nr_locks, nr / nr_ns); + freed += ldlm_pool_shrink(&ns->ns_pool, cancel, gfp_mask); ldlm_namespace_put(ns); } cl_env_reexit(cookie); - /* we only decrease the SLV in server pools shrinker, return -1 to - * kernel to avoid needless loop. LU-1128 */ - return (client == LDLM_NAMESPACE_SERVER) ? -1 : cached; + /* + * we only decrease the SLV in server pools shrinker, return + * SHRINK_STOP to kernel to avoid needless loop. LU-1128 + */ + return (client == LDLM_NAMESPACE_SERVER) ? SHRINK_STOP : freed; +} + +static unsigned long ldlm_pools_srv_count(struct shrinker *s, struct shrink_control *sc) +{ + return ldlm_pools_count(LDLM_NAMESPACE_SERVER, sc->gfp_mask); } -static int ldlm_pools_srv_shrink(SHRINKER_ARGS(sc, nr_to_scan, gfp_mask)) +static unsigned long ldlm_pools_srv_scan(struct shrinker *s, struct shrink_control *sc) { - return ldlm_pools_shrink(LDLM_NAMESPACE_SERVER, - shrink_param(sc, nr_to_scan), - shrink_param(sc, gfp_mask)); + return ldlm_pools_scan(LDLM_NAMESPACE_SERVER, sc->nr_to_scan, + sc->gfp_mask); } -static int ldlm_pools_cli_shrink(SHRINKER_ARGS(sc, nr_to_scan, gfp_mask)) +static unsigned long ldlm_pools_cli_count(struct shrinker *s, struct shrink_control *sc) { - return ldlm_pools_shrink(LDLM_NAMESPACE_CLIENT, - shrink_param(sc, nr_to_scan), - shrink_param(sc, gfp_mask)); + return ldlm_pools_count(LDLM_NAMESPACE_CLIENT, sc->gfp_mask); +} + +static unsigned long ldlm_pools_cli_scan(struct shrinker *s, struct shrink_control *sc) +{ + return ldlm_pools_scan(LDLM_NAMESPACE_CLIENT, sc->nr_to_scan, + sc->gfp_mask); } int ldlm_pools_recalc(ldlm_side_t client) @@ -1216,7 +1224,7 @@ int ldlm_pools_recalc(ldlm_side_t client) } /* - * Recalc at least ldlm_namespace_nr(client) namespaces. + * Recalc at least ldlm_namespace_nr_read(client) namespaces. */ for (nr = ldlm_namespace_nr_read(client); nr > 0; nr--) { int skip; @@ -1383,18 +1391,26 @@ static void ldlm_pools_thread_stop(void) ldlm_pools_thread = NULL; } +static struct shrinker ldlm_pools_srv_shrinker = { + .count_objects = ldlm_pools_srv_count, + .scan_objects = ldlm_pools_srv_scan, + .seeks = DEFAULT_SEEKS, +}; + +static struct shrinker ldlm_pools_cli_shrinker = { + .count_objects = ldlm_pools_cli_count, + .scan_objects = ldlm_pools_cli_scan, + .seeks = DEFAULT_SEEKS, +}; + int ldlm_pools_init(void) { int rc; rc = ldlm_pools_thread_start(); if (rc == 0) { - ldlm_pools_srv_shrinker = - set_shrinker(DEFAULT_SEEKS, - ldlm_pools_srv_shrink); - ldlm_pools_cli_shrinker = - set_shrinker(DEFAULT_SEEKS, - ldlm_pools_cli_shrink); + register_shrinker(&ldlm_pools_srv_shrinker); + register_shrinker(&ldlm_pools_cli_shrinker); } return rc; } @@ -1402,14 +1418,8 @@ EXPORT_SYMBOL(ldlm_pools_init); void ldlm_pools_fini(void) { - if (ldlm_pools_srv_shrinker != NULL) { - remove_shrinker(ldlm_pools_srv_shrinker); - ldlm_pools_srv_shrinker = NULL; - } - if (ldlm_pools_cli_shrinker != NULL) { - remove_shrinker(ldlm_pools_cli_shrinker); - ldlm_pools_cli_shrinker = NULL; - } + unregister_shrinker(&ldlm_pools_srv_shrinker); + unregister_shrinker(&ldlm_pools_cli_shrinker); ldlm_pools_thread_stop(); } EXPORT_SYMBOL(ldlm_pools_fini); diff --git a/drivers/staging/lustre/lustre/obdclass/lu_object.c b/drivers/staging/lustre/lustre/obdclass/lu_object.c index c29ac1c2defd..3a3d5bc5a628 100644 --- a/drivers/staging/lustre/lustre/obdclass/lu_object.c +++ b/drivers/staging/lustre/lustre/obdclass/lu_object.c @@ -1779,7 +1779,6 @@ int lu_env_refill_by_tags(struct lu_env *env, __u32 ctags, } EXPORT_SYMBOL(lu_env_refill_by_tags); -static struct shrinker *lu_site_shrinker = NULL; typedef struct lu_site_stats{ unsigned lss_populated; @@ -1835,61 +1834,68 @@ static void lu_site_stats_get(cfs_hash_t *hs, * objects without taking the lu_sites_guard lock, but this is not * possible in the current implementation. */ -static int lu_cache_shrink(SHRINKER_ARGS(sc, nr_to_scan, gfp_mask)) +static unsigned long lu_cache_shrink_count(struct shrinker *sk, + struct shrink_control *sc) { lu_site_stats_t stats; struct lu_site *s; struct lu_site *tmp; - int cached = 0; - int remain = shrink_param(sc, nr_to_scan); - LIST_HEAD(splice); - - if (!(shrink_param(sc, gfp_mask) & __GFP_FS)) { - if (remain != 0) - return -1; - else - /* We must not take the lu_sites_guard lock when - * __GFP_FS is *not* set because of the deadlock - * possibility detailed above. Additionally, - * since we cannot determine the number of - * objects in the cache without taking this - * lock, we're in a particularly tough spot. As - * a result, we'll just lie and say our cache is - * empty. This _should_ be ok, as we can't - * reclaim objects when __GFP_FS is *not* set - * anyways. - */ - return 0; - } + unsigned long cached = 0; - CDEBUG(D_INODE, "Shrink %d objects\n", remain); + if (!(sc->gfp_mask & __GFP_FS)) + return 0; mutex_lock(&lu_sites_guard); list_for_each_entry_safe(s, tmp, &lu_sites, ls_linkage) { - if (shrink_param(sc, nr_to_scan) != 0) { - remain = lu_site_purge(&lu_shrink_env, s, remain); - /* - * Move just shrunk site to the tail of site list to - * assure shrinking fairness. - */ - list_move_tail(&s->ls_linkage, &splice); - } - memset(&stats, 0, sizeof(stats)); lu_site_stats_get(s->ls_obj_hash, &stats, 0); cached += stats.lss_total - stats.lss_busy; - if (shrink_param(sc, nr_to_scan) && remain <= 0) - break; } - list_splice(&splice, lu_sites.prev); mutex_unlock(&lu_sites_guard); cached = (cached / 100) * sysctl_vfs_cache_pressure; - if (shrink_param(sc, nr_to_scan) == 0) - CDEBUG(D_INODE, "%d objects cached\n", cached); + CDEBUG(D_INODE, "%ld objects cached\n", cached); return cached; } +static unsigned long lu_cache_shrink_scan(struct shrinker *sk, + struct shrink_control *sc) +{ + struct lu_site *s; + struct lu_site *tmp; + unsigned long remain = sc->nr_to_scan, freed = 0; + LIST_HEAD(splice); + + if (!(sc->gfp_mask & __GFP_FS)) + /* We must not take the lu_sites_guard lock when + * __GFP_FS is *not* set because of the deadlock + * possibility detailed above. Additionally, + * since we cannot determine the number of + * objects in the cache without taking this + * lock, we're in a particularly tough spot. As + * a result, we'll just lie and say our cache is + * empty. This _should_ be ok, as we can't + * reclaim objects when __GFP_FS is *not* set + * anyways. + */ + return SHRINK_STOP; + + mutex_lock(&lu_sites_guard); + list_for_each_entry_safe(s, tmp, &lu_sites, ls_linkage) { + freed = lu_site_purge(&lu_shrink_env, s, remain); + remain -= freed; + /* + * Move just shrunk site to the tail of site list to + * assure shrinking fairness. + */ + list_move_tail(&s->ls_linkage, &splice); + } + list_splice(&splice, lu_sites.prev); + mutex_unlock(&lu_sites_guard); + + return sc->nr_to_scan - remain; +} + /* * Debugging stuff. */ @@ -1913,6 +1919,12 @@ int lu_printk_printer(const struct lu_env *env, return 0; } +static struct shrinker lu_site_shrinker = { + .count_objects = lu_cache_shrink_count, + .scan_objects = lu_cache_shrink_scan, + .seeks = DEFAULT_SEEKS, +}; + /** * Initialization of global lu_* data. */ @@ -1947,9 +1959,7 @@ int lu_global_init(void) * inode, one for ea. Unfortunately setting this high value results in * lu_object/inode cache consuming all the memory. */ - lu_site_shrinker = set_shrinker(DEFAULT_SEEKS, lu_cache_shrink); - if (lu_site_shrinker == NULL) - return -ENOMEM; + register_shrinker(&lu_site_shrinker); return result; } @@ -1959,11 +1969,7 @@ int lu_global_init(void) */ void lu_global_fini(void) { - if (lu_site_shrinker != NULL) { - remove_shrinker(lu_site_shrinker); - lu_site_shrinker = NULL; - } - + unregister_shrinker(&lu_site_shrinker); lu_context_key_degister(&lu_global_key); /* diff --git a/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c b/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c index 9013745ab105..e90c8fb7da6a 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c +++ b/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c @@ -121,13 +121,6 @@ static struct ptlrpc_enc_page_pool { } page_pools; /* - * memory shrinker - */ -const int pools_shrinker_seeks = DEFAULT_SEEKS; -static struct shrinker *pools_shrinker = NULL; - - -/* * /proc/fs/lustre/sptlrpc/encrypt_page_pools */ int sptlrpc_proc_enc_pool_seq_show(struct seq_file *m, void *v) @@ -226,30 +219,46 @@ static void enc_pools_release_free_pages(long npages) } /* - * could be called frequently for query (@nr_to_scan == 0). * we try to keep at least PTLRPC_MAX_BRW_PAGES pages in the pool. */ -static int enc_pools_shrink(SHRINKER_ARGS(sc, nr_to_scan, gfp_mask)) +static unsigned long enc_pools_shrink_count(struct shrinker *s, + struct shrink_control *sc) { - if (unlikely(shrink_param(sc, nr_to_scan) != 0)) { + /* + * if no pool access for a long time, we consider it's fully idle. + * a little race here is fine. + */ + if (unlikely(cfs_time_current_sec() - page_pools.epp_last_access > + CACHE_QUIESCENT_PERIOD)) { spin_lock(&page_pools.epp_lock); - shrink_param(sc, nr_to_scan) = min_t(unsigned long, - shrink_param(sc, nr_to_scan), - page_pools.epp_free_pages - - PTLRPC_MAX_BRW_PAGES); - if (shrink_param(sc, nr_to_scan) > 0) { - enc_pools_release_free_pages(shrink_param(sc, - nr_to_scan)); - CDEBUG(D_SEC, "released %ld pages, %ld left\n", - (long)shrink_param(sc, nr_to_scan), - page_pools.epp_free_pages); - - page_pools.epp_st_shrinks++; - page_pools.epp_last_shrink = cfs_time_current_sec(); - } + page_pools.epp_idle_idx = IDLE_IDX_MAX; spin_unlock(&page_pools.epp_lock); } + LASSERT(page_pools.epp_idle_idx <= IDLE_IDX_MAX); + return max((int)page_pools.epp_free_pages - PTLRPC_MAX_BRW_PAGES, 0) * + (IDLE_IDX_MAX - page_pools.epp_idle_idx) / IDLE_IDX_MAX; +} + +/* + * we try to keep at least PTLRPC_MAX_BRW_PAGES pages in the pool. + */ +static unsigned long enc_pools_shrink_scan(struct shrinker *s, + struct shrink_control *sc) +{ + spin_lock(&page_pools.epp_lock); + sc->nr_to_scan = min_t(unsigned long, sc->nr_to_scan, + page_pools.epp_free_pages - PTLRPC_MAX_BRW_PAGES); + if (sc->nr_to_scan > 0) { + enc_pools_release_free_pages(sc->nr_to_scan); + CDEBUG(D_SEC, "released %ld pages, %ld left\n", + (long)sc->nr_to_scan, page_pools.epp_free_pages); + + page_pools.epp_st_shrinks++; + page_pools.epp_last_shrink = cfs_time_current_sec(); + } + spin_unlock(&page_pools.epp_lock); + /* * if no pool access for a long time, we consider it's fully idle. * a little race here is fine. @@ -262,8 +271,7 @@ static int enc_pools_shrink(SHRINKER_ARGS(sc, nr_to_scan, gfp_mask)) } LASSERT(page_pools.epp_idle_idx <= IDLE_IDX_MAX); - return max((int)page_pools.epp_free_pages - PTLRPC_MAX_BRW_PAGES, 0) * - (IDLE_IDX_MAX - page_pools.epp_idle_idx) / IDLE_IDX_MAX; + return sc->nr_to_scan; } static inline @@ -699,6 +707,12 @@ static inline void enc_pools_free(void) sizeof(*page_pools.epp_pools)); } +static struct shrinker pools_shrinker = { + .count_objects = enc_pools_shrink_count, + .scan_objects = enc_pools_shrink_scan, + .seeks = DEFAULT_SEEKS, +}; + int sptlrpc_enc_pool_init(void) { /* @@ -736,12 +750,7 @@ int sptlrpc_enc_pool_init(void) if (page_pools.epp_pools == NULL) return -ENOMEM; - pools_shrinker = set_shrinker(pools_shrinker_seeks, - enc_pools_shrink); - if (pools_shrinker == NULL) { - enc_pools_free(); - return -ENOMEM; - } + register_shrinker(&pools_shrinker); return 0; } @@ -750,11 +759,10 @@ void sptlrpc_enc_pool_fini(void) { unsigned long cleaned, npools; - LASSERT(pools_shrinker); LASSERT(page_pools.epp_pools); LASSERT(page_pools.epp_total_pages == page_pools.epp_free_pages); - remove_shrinker(pools_shrinker); + unregister_shrinker(&pools_shrinker); npools = npages_to_npools(page_pools.epp_total_pages); cleaned = enc_pools_cleanup(page_pools.epp_pools, npools); diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 5f95d1ed9c6d..b9acadafa4a1 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -50,7 +50,7 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); } static int adfs_write_begin(struct file *file, struct address_space *mapping, diff --git a/fs/affs/file.c b/fs/affs/file.c index 6e32e3b4b681..664f743c2d8d 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -406,7 +406,7 @@ static void affs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); affs_truncate(inode); } } diff --git a/fs/bfs/file.c b/fs/bfs/file.c index 3d14806d5393..d150660d598b 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -166,7 +166,7 @@ static void bfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); } static int bfs_write_begin(struct file *file, struct address_space *mapping, diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index ef3bea7bb257..3f0ddfce96e6 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -221,12 +221,10 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root, struct btrfs_path *path, struct inode *inode) { - loff_t oldsize; int ret = 0; - oldsize = i_size_read(inode); btrfs_i_size_write(inode, 0); - truncate_pagecache(inode, oldsize, 0); + truncate_pagecache(inode, 0); /* * We don't need an orphan item because truncating the free space cache diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a7704121e3a8..f19be0a6494a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4349,7 +4349,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb); if (newsize > oldsize) { - truncate_pagecache(inode, oldsize, newsize); + truncate_pagecache(inode, newsize); ret = btrfs_cont_expand(inode, oldsize, newsize); if (ret) return ret; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index ec0f3423cdac..90ef28717160 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1856,14 +1856,11 @@ static int cifs_truncate_page(struct address_space *mapping, loff_t from) static void cifs_setsize(struct inode *inode, loff_t offset) { - loff_t oldsize; - spin_lock(&inode->i_lock); - oldsize = inode->i_size; i_size_write(inode, offset); spin_unlock(&inode->i_lock); - truncate_pagecache(inode, oldsize, offset); + truncate_pagecache(inode, offset); } static int diff --git a/fs/dcache.c b/fs/dcache.c index 5e4c1ce6d7b8..35c8ee4f23bf 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -38,6 +38,7 @@ #include <linux/rculist_bl.h> #include <linux/prefetch.h> #include <linux/ratelimit.h> +#include <linux/list_lru.h> #include "internal.h" #include "mount.h" @@ -49,7 +50,7 @@ * - the dcache hash table * s_anon bl list spinlock protects: * - the s_anon list (see __d_drop) - * dcache_lru_lock protects: + * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags @@ -64,7 +65,7 @@ * Ordering: * dentry->d_inode->i_lock * dentry->d_lock - * dcache_lru_lock + * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_anon lock * @@ -82,7 +83,6 @@ int sysctl_vfs_cache_pressure __read_mostly = 100; EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure); -static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); @@ -118,23 +118,47 @@ struct dentry_stat_t dentry_stat = { .age_limit = 45, }; -static DEFINE_PER_CPU(unsigned int, nr_dentry); +static DEFINE_PER_CPU(long, nr_dentry); +static DEFINE_PER_CPU(long, nr_dentry_unused); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) -static int get_nr_dentry(void) + +/* + * Here we resort to our own counters instead of using generic per-cpu counters + * for consistency with what the vfs inode code does. We are expected to harvest + * better code and performance by having our own specialized counters. + * + * Please note that the loop is done over all possible CPUs, not over all online + * CPUs. The reason for this is that we don't want to play games with CPUs going + * on and off. If one of them goes off, we will just keep their counters. + * + * glommer: See cffbc8a for details, and if you ever intend to change this, + * please update all vfs counters to match. + */ +static long get_nr_dentry(void) { int i; - int sum = 0; + long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } +static long get_nr_dentry_unused(void) +{ + int i; + long sum = 0; + for_each_possible_cpu(i) + sum += per_cpu(nr_dentry_unused, i); + return sum < 0 ? 0 : sum; +} + int proc_nr_dentry(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); - return proc_dointvec(table, write, buffer, lenp, ppos); + dentry_stat.nr_unused = get_nr_dentry_unused(); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif @@ -305,50 +329,31 @@ static void dentry_unlink_inode(struct dentry * dentry) } /* - * dentry_lru_(add|del|prune|move_tail) must be called with d_lock held. + * dentry_lru_(add|del|move_list) must be called with d_lock held. */ static void dentry_lru_add(struct dentry *dentry) { - if (list_empty(&dentry->d_lru)) { - spin_lock(&dcache_lru_lock); - list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); - dentry->d_sb->s_nr_dentry_unused++; - dentry_stat.nr_unused++; - spin_unlock(&dcache_lru_lock); - } -} - -static void __dentry_lru_del(struct dentry *dentry) -{ - list_del_init(&dentry->d_lru); - dentry->d_flags &= ~DCACHE_SHRINK_LIST; - dentry->d_sb->s_nr_dentry_unused--; - dentry_stat.nr_unused--; + if (list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)) + this_cpu_inc(nr_dentry_unused); } /* * Remove a dentry with references from the LRU. + * + * If we are on the shrink list, then we can get to try_prune_one_dentry() and + * lose our last reference through the parent walk. In this case, we need to + * remove ourselves from the shrink list, not the LRU. */ static void dentry_lru_del(struct dentry *dentry) { - if (!list_empty(&dentry->d_lru)) { - spin_lock(&dcache_lru_lock); - __dentry_lru_del(dentry); - spin_unlock(&dcache_lru_lock); + if (dentry->d_flags & DCACHE_SHRINK_LIST) { + list_del_init(&dentry->d_lru); + dentry->d_flags &= ~DCACHE_SHRINK_LIST; + return; } -} -static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list) -{ - spin_lock(&dcache_lru_lock); - if (list_empty(&dentry->d_lru)) { - list_add_tail(&dentry->d_lru, list); - dentry->d_sb->s_nr_dentry_unused++; - dentry_stat.nr_unused++; - } else { - list_move_tail(&dentry->d_lru, list); - } - spin_unlock(&dcache_lru_lock); + if (list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)) + this_cpu_dec(nr_dentry_unused); } /** @@ -444,7 +449,8 @@ EXPORT_SYMBOL(d_drop); * If ref is non-zero, then decrement the refcount too. * Returns dentry requiring refcount drop, or NULL if we're done. */ -static inline struct dentry *dentry_kill(struct dentry *dentry, int ref) +static inline struct dentry * +dentry_kill(struct dentry *dentry, int ref, int unlock_on_failure) __releases(dentry->d_lock) { struct inode *inode; @@ -453,8 +459,10 @@ static inline struct dentry *dentry_kill(struct dentry *dentry, int ref) inode = dentry->d_inode; if (inode && !spin_trylock(&inode->i_lock)) { relock: - spin_unlock(&dentry->d_lock); - cpu_relax(); + if (unlock_on_failure) { + spin_unlock(&dentry->d_lock); + cpu_relax(); + } return dentry; /* try again with same dentry */ } if (IS_ROOT(dentry)) @@ -536,7 +544,7 @@ repeat: return; kill_it: - dentry = dentry_kill(dentry, 1); + dentry = dentry_kill(dentry, 1, 1); if (dentry) goto repeat; } @@ -748,12 +756,12 @@ EXPORT_SYMBOL(d_prune_aliases); * * This may fail if locks cannot be acquired no problem, just try again. */ -static void try_prune_one_dentry(struct dentry *dentry) +static struct dentry * try_prune_one_dentry(struct dentry *dentry) __releases(dentry->d_lock) { struct dentry *parent; - parent = dentry_kill(dentry, 0); + parent = dentry_kill(dentry, 0, 0); /* * If dentry_kill returns NULL, we have nothing more to do. * if it returns the same dentry, trylocks failed. In either @@ -765,17 +773,18 @@ static void try_prune_one_dentry(struct dentry *dentry) * fragmentation. */ if (!parent) - return; + return NULL; if (parent == dentry) - return; + return dentry; /* Prune ancestors. */ dentry = parent; while (dentry) { if (lockref_put_or_lock(&dentry->d_lockref)) - return; - dentry = dentry_kill(dentry, 1); + return NULL; + dentry = dentry_kill(dentry, 1, 1); } + return NULL; } static void shrink_dentry_list(struct list_head *list) @@ -794,76 +803,143 @@ static void shrink_dentry_list(struct list_head *list) } /* + * The dispose list is isolated and dentries are not accounted + * to the LRU here, so we can simply remove it from the list + * here regardless of whether it is referenced or not. + */ + list_del_init(&dentry->d_lru); + dentry->d_flags &= ~DCACHE_SHRINK_LIST; + + /* * We found an inuse dentry which was not removed from - * the LRU because of laziness during lookup. Do not free - * it - just keep it off the LRU list. + * the LRU because of laziness during lookup. Do not free it. */ if (dentry->d_lockref.count) { - dentry_lru_del(dentry); spin_unlock(&dentry->d_lock); continue; } - rcu_read_unlock(); - try_prune_one_dentry(dentry); + dentry = try_prune_one_dentry(dentry); rcu_read_lock(); + if (dentry) { + dentry->d_flags |= DCACHE_SHRINK_LIST; + list_add(&dentry->d_lru, list); + spin_unlock(&dentry->d_lock); + } } rcu_read_unlock(); } +static enum lru_status +dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg) +{ + struct list_head *freeable = arg; + struct dentry *dentry = container_of(item, struct dentry, d_lru); + + + /* + * we are inverting the lru lock/dentry->d_lock here, + * so use a trylock. If we fail to get the lock, just skip + * it + */ + if (!spin_trylock(&dentry->d_lock)) + return LRU_SKIP; + + /* + * Referenced dentries are still in use. If they have active + * counts, just remove them from the LRU. Otherwise give them + * another pass through the LRU. + */ + if (dentry->d_lockref.count) { + list_del_init(&dentry->d_lru); + spin_unlock(&dentry->d_lock); + return LRU_REMOVED; + } + + if (dentry->d_flags & DCACHE_REFERENCED) { + dentry->d_flags &= ~DCACHE_REFERENCED; + spin_unlock(&dentry->d_lock); + + /* + * The list move itself will be made by the common LRU code. At + * this point, we've dropped the dentry->d_lock but keep the + * lru lock. This is safe to do, since every list movement is + * protected by the lru lock even if both locks are held. + * + * This is guaranteed by the fact that all LRU management + * functions are intermediated by the LRU API calls like + * list_lru_add and list_lru_del. List movement in this file + * only ever occur through this functions or through callbacks + * like this one, that are called from the LRU API. + * + * The only exceptions to this are functions like + * shrink_dentry_list, and code that first checks for the + * DCACHE_SHRINK_LIST flag. Those are guaranteed to be + * operating only with stack provided lists after they are + * properly isolated from the main list. It is thus, always a + * local access. + */ + return LRU_ROTATE; + } + + dentry->d_flags |= DCACHE_SHRINK_LIST; + list_move_tail(&dentry->d_lru, freeable); + this_cpu_dec(nr_dentry_unused); + spin_unlock(&dentry->d_lock); + + return LRU_REMOVED; +} + /** * prune_dcache_sb - shrink the dcache * @sb: superblock - * @count: number of entries to try to free + * @nr_to_scan : number of entries to try to free + * @nid: which node to scan for freeable entities * - * Attempt to shrink the superblock dcache LRU by @count entries. This is + * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is * done when we need more memory an called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ -void prune_dcache_sb(struct super_block *sb, int count) +long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan, + int nid) { - struct dentry *dentry; - LIST_HEAD(referenced); - LIST_HEAD(tmp); + LIST_HEAD(dispose); + long freed; -relock: - spin_lock(&dcache_lru_lock); - while (!list_empty(&sb->s_dentry_lru)) { - dentry = list_entry(sb->s_dentry_lru.prev, - struct dentry, d_lru); - BUG_ON(dentry->d_sb != sb); - - if (!spin_trylock(&dentry->d_lock)) { - spin_unlock(&dcache_lru_lock); - cpu_relax(); - goto relock; - } + freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate, + &dispose, &nr_to_scan); + shrink_dentry_list(&dispose); + return freed; +} - if (dentry->d_flags & DCACHE_REFERENCED) { - dentry->d_flags &= ~DCACHE_REFERENCED; - list_move(&dentry->d_lru, &referenced); - spin_unlock(&dentry->d_lock); - } else { - list_move_tail(&dentry->d_lru, &tmp); - dentry->d_flags |= DCACHE_SHRINK_LIST; - spin_unlock(&dentry->d_lock); - if (!--count) - break; - } - cond_resched_lock(&dcache_lru_lock); - } - if (!list_empty(&referenced)) - list_splice(&referenced, &sb->s_dentry_lru); - spin_unlock(&dcache_lru_lock); +static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, + spinlock_t *lru_lock, void *arg) +{ + struct list_head *freeable = arg; + struct dentry *dentry = container_of(item, struct dentry, d_lru); + + /* + * we are inverting the lru lock/dentry->d_lock here, + * so use a trylock. If we fail to get the lock, just skip + * it + */ + if (!spin_trylock(&dentry->d_lock)) + return LRU_SKIP; + + dentry->d_flags |= DCACHE_SHRINK_LIST; + list_move_tail(&dentry->d_lru, freeable); + this_cpu_dec(nr_dentry_unused); + spin_unlock(&dentry->d_lock); - shrink_dentry_list(&tmp); + return LRU_REMOVED; } + /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock @@ -873,16 +949,17 @@ relock: */ void shrink_dcache_sb(struct super_block *sb) { - LIST_HEAD(tmp); + long freed; - spin_lock(&dcache_lru_lock); - while (!list_empty(&sb->s_dentry_lru)) { - list_splice_init(&sb->s_dentry_lru, &tmp); - spin_unlock(&dcache_lru_lock); - shrink_dentry_list(&tmp); - spin_lock(&dcache_lru_lock); - } - spin_unlock(&dcache_lru_lock); + do { + LIST_HEAD(dispose); + + freed = list_lru_walk(&sb->s_dentry_lru, + dentry_lru_isolate_shrink, &dispose, UINT_MAX); + + this_cpu_sub(nr_dentry_unused, freed); + shrink_dentry_list(&dispose); + } while (freed > 0); } EXPORT_SYMBOL(shrink_dcache_sb); @@ -1155,7 +1232,8 @@ resume: if (dentry->d_lockref.count) { dentry_lru_del(dentry); } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { - dentry_lru_move_list(dentry, dispose); + dentry_lru_del(dentry); + list_add_tail(&dentry->d_lru, dispose); dentry->d_flags |= DCACHE_SHRINK_LIST; found++; } @@ -1220,9 +1298,8 @@ rename_retry: void shrink_dcache_parent(struct dentry * parent) { LIST_HEAD(dispose); - int found; - while ((found = select_parent(parent, &dispose)) != 0) { + while (select_parent(parent, &dispose)) { shrink_dentry_list(&dispose); cond_resched(); } diff --git a/fs/drop_caches.c b/fs/drop_caches.c index c00e055b6282..9fd702f5bfb2 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -44,6 +44,7 @@ static void drop_slab(void) .gfp_mask = GFP_KERNEL, }; + nodes_setall(shrink.nodes_to_scan); do { nr_objects = shrink_slab(&shrink, 1000, 1000); } while (nr_objects > 10); diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 2ec8eb1ab269..a52a5d23c30b 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -861,7 +861,7 @@ static int exofs_writepage(struct page *page, struct writeback_control *wbc) static void _write_failed(struct inode *inode, loff_t to) { if (to > inode->i_size) - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); } int exofs_write_begin(struct file *file, struct address_space *mapping, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index e3e8e3bd6293..cf91b336e3df 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -58,7 +58,7 @@ static void ext2_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); ext2_truncate_blocks(inode, inode->i_size); } } diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 2d1bdbe78c04..3981ff783950 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -931,13 +931,15 @@ static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *ei; struct list_head *cur, *tmp; LIST_HEAD(skipped); - int ret, nr_shrunk = 0; + int nr_shrunk = 0; int retried = 0, skip_precached = 1, nr_skipped = 0; spin_lock(&sbi->s_es_lru_lock); retry: list_for_each_safe(cur, tmp, &sbi->s_es_lru) { + int shrunk; + /* * If we have already reclaimed all extents from extent * status tree, just stop the loop immediately. @@ -964,13 +966,13 @@ retry: continue; write_lock(&ei->i_es_lock); - ret = __es_try_to_reclaim_extents(ei, nr_to_scan); + shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan); if (ei->i_es_lru_nr == 0) list_del_init(&ei->i_es_lru); write_unlock(&ei->i_es_lock); - nr_shrunk += ret; - nr_to_scan -= ret; + nr_shrunk += shrunk; + nr_to_scan -= shrunk; if (nr_to_scan == 0) break; } @@ -1007,7 +1009,20 @@ retry: return nr_shrunk; } -static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long ext4_es_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + unsigned long nr; + struct ext4_sb_info *sbi; + + sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker); + nr = percpu_counter_read_positive(&sbi->s_extent_cache_cnt); + trace_ext4_es_shrink_enter(sbi->s_sb, sc->nr_to_scan, nr); + return nr; +} + +static unsigned long ext4_es_scan(struct shrinker *shrink, + struct shrink_control *sc) { struct ext4_sb_info *sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker); @@ -1022,9 +1037,8 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc) nr_shrunk = __ext4_es_shrink(sbi, nr_to_scan, NULL); - ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt); trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret); - return ret; + return nr_shrunk; } void ext4_es_register_shrinker(struct ext4_sb_info *sbi) @@ -1032,7 +1046,8 @@ void ext4_es_register_shrinker(struct ext4_sb_info *sbi) INIT_LIST_HEAD(&sbi->s_es_lru); spin_lock_init(&sbi->s_es_lru_lock); sbi->s_es_last_sorted = 0; - sbi->s_es_shrinker.shrink = ext4_es_shrink; + 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; register_shrinker(&sbi->s_es_shrinker); } @@ -1076,7 +1091,7 @@ static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei, struct ext4_es_tree *tree = &ei->i_es_tree; struct rb_node *node; struct extent_status *es; - int nr_shrunk = 0; + unsigned long nr_shrunk = 0; static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 25d9bde7da47..5c6c52727725 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4599,7 +4599,6 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) { handle_t *handle; - loff_t oldsize = inode->i_size; if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -4662,7 +4661,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) * Truncate pagecache after we've waited for commit * in data=journal mode to make pages freeable. */ - truncate_pagecache(inode, oldsize, inode->i_size); + truncate_pagecache(inode, inode->i_size); } /* * We want to call ext4_truncate() even if attr->ia_size == diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 5917c13bd6b3..7152c07ca378 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -147,7 +147,7 @@ static void fat_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); fat_truncate_blocks(inode, inode->i_size); } } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 8fec28ff4a0d..7bbc075a08ac 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1683,7 +1683,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, * FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock. */ if (S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) { - truncate_pagecache(inode, oldsize, outarg.attr.size); + truncate_pagecache(inode, outarg.attr.size); invalidate_inode_pages2(inode->i_mapping); } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 84434594e80e..a8ce6dab60a0 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -218,7 +218,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, bool inval = false; if (oldsize != attr->size) { - truncate_pagecache(inode, oldsize, attr->size); + truncate_pagecache(inode, attr->size); inval = true; } else if (fc->auto_inval_data) { struct timespec new_mtime = { diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 5e2f56fccf6b..62a65fc448dc 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1016,7 +1016,7 @@ static int gfs2_journaled_truncate(struct inode *inode, u64 oldsize, u64 newsize chunk = oldsize - newsize; if (chunk > max_chunk) chunk = max_chunk; - truncate_pagecache(inode, oldsize, oldsize - chunk); + truncate_pagecache(inode, oldsize - chunk); oldsize -= chunk; gfs2_trans_end(sdp); error = gfs2_trans_begin(sdp, RES_DINODE, GFS2_JTRUNC_REVOKES); @@ -1067,7 +1067,7 @@ static int trunc_start(struct inode *inode, u64 oldsize, u64 newsize) if (journaled) error = gfs2_journaled_truncate(inode, oldsize, newsize); else - truncate_pagecache(inode, oldsize, newsize); + truncate_pagecache(inode, newsize); if (error) { brelse(dibh); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index ce7078d5aa97..8fee1eecbf1f 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1428,21 +1428,22 @@ __acquires(&lru_lock) * gfs2_dispose_glock_lru() above. */ -static void gfs2_scan_glock_lru(int nr) +static long gfs2_scan_glock_lru(int nr) { struct gfs2_glock *gl; LIST_HEAD(skipped); LIST_HEAD(dispose); + long freed = 0; spin_lock(&lru_lock); - while(nr && !list_empty(&lru_list)) { + while ((nr-- >= 0) && !list_empty(&lru_list)) { gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru); /* Test for being demotable */ if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); - nr--; + freed++; continue; } @@ -1452,23 +1453,28 @@ static void gfs2_scan_glock_lru(int nr) if (!list_empty(&dispose)) gfs2_dispose_glock_lru(&dispose); spin_unlock(&lru_lock); + + return freed; } -static int gfs2_shrink_glock_memory(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long gfs2_glock_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) { - if (sc->nr_to_scan) { - if (!(sc->gfp_mask & __GFP_FS)) - return -1; - gfs2_scan_glock_lru(sc->nr_to_scan); - } + if (!(sc->gfp_mask & __GFP_FS)) + return SHRINK_STOP; + return gfs2_scan_glock_lru(sc->nr_to_scan); +} - return (atomic_read(&lru_count) / 100) * sysctl_vfs_cache_pressure; +static unsigned long gfs2_glock_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + return vfs_pressure_ratio(atomic_read(&lru_count)); } static struct shrinker glock_shrinker = { - .shrink = gfs2_shrink_glock_memory, .seeks = DEFAULT_SEEKS, + .count_objects = gfs2_glock_shrink_count, + .scan_objects = gfs2_glock_shrink_scan, }; /** diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 7b0f5043cf24..351586e24e30 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -32,7 +32,8 @@ struct workqueue_struct *gfs2_control_wq; static struct shrinker qd_shrinker = { - .shrink = gfs2_shrink_qd_memory, + .count_objects = gfs2_qd_shrink_count, + .scan_objects = gfs2_qd_shrink_scan, .seeks = DEFAULT_SEEKS, }; diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 3768c2f40e43..db441359ee8c 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -75,17 +75,16 @@ static LIST_HEAD(qd_lru_list); static atomic_t qd_lru_count = ATOMIC_INIT(0); static DEFINE_SPINLOCK(qd_lru_lock); -int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc) +unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) { struct gfs2_quota_data *qd; struct gfs2_sbd *sdp; int nr_to_scan = sc->nr_to_scan; - - if (nr_to_scan == 0) - goto out; + long freed = 0; if (!(sc->gfp_mask & __GFP_FS)) - return -1; + return SHRINK_STOP; spin_lock(&qd_lru_lock); while (nr_to_scan && !list_empty(&qd_lru_list)) { @@ -110,11 +109,16 @@ int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc) kmem_cache_free(gfs2_quotad_cachep, qd); spin_lock(&qd_lru_lock); nr_to_scan--; + freed++; } spin_unlock(&qd_lru_lock); + return freed; +} -out: - return (atomic_read(&qd_lru_count) * sysctl_vfs_cache_pressure) / 100; +unsigned long gfs2_qd_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + return vfs_pressure_ratio(atomic_read(&qd_lru_count)); } static u64 qd2index(struct gfs2_quota_data *qd) diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 4f5e6e44ed83..0f64d9deb1b0 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -53,8 +53,10 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) return ret; } -extern int gfs2_shrink_qd_memory(struct shrinker *shrink, - struct shrink_control *sc); +extern unsigned long gfs2_qd_shrink_count(struct shrinker *shrink, + struct shrink_control *sc); +extern unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc); extern const struct quotactl_ops gfs2_quotactl_ops; #endif /* __QUOTA_DOT_H__ */ diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index f9242b8075da..3fe7b8e53290 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -41,7 +41,7 @@ static void hfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); hfs_file_truncate(inode); } } diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 0a152c59381a..96d7a2ccded2 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -36,7 +36,7 @@ static void hfsplus_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); hfsplus_file_truncate(inode); } } diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 2561eba66c9f..1ff95c19a469 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -138,7 +138,7 @@ static void hpfs_write_failed(struct address_space *mapping, loff_t to) hpfs_lock(inode->i_sb); if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); hpfs_truncate(inode); } diff --git a/fs/inode.c b/fs/inode.c index ef3a12d7158a..26489b35a097 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -18,6 +18,7 @@ #include <linux/prefetch.h> #include <linux/buffer_head.h> /* for inode_has_buffers */ #include <linux/ratelimit.h> +#include <linux/list_lru.h> #include "internal.h" /* @@ -25,7 +26,7 @@ * * inode->i_lock protects: * inode->i_state, inode->i_hash, __iget() - * inode->i_sb->s_inode_lru_lock protects: + * Inode LRU list locks protect: * inode->i_sb->s_inode_lru, inode->i_lru * inode_sb_list_lock protects: * sb->s_inodes, inode->i_sb_list @@ -38,7 +39,7 @@ * * inode_sb_list_lock * inode->i_lock - * inode->i_sb->s_inode_lru_lock + * Inode LRU list locks * * bdi->wb.list_lock * inode->i_lock @@ -71,33 +72,33 @@ EXPORT_SYMBOL(empty_aops); */ struct inodes_stat_t inodes_stat; -static DEFINE_PER_CPU(unsigned int, nr_inodes); -static DEFINE_PER_CPU(unsigned int, nr_unused); +static DEFINE_PER_CPU(unsigned long, nr_inodes); +static DEFINE_PER_CPU(unsigned long, nr_unused); static struct kmem_cache *inode_cachep __read_mostly; -static int get_nr_inodes(void) +static long get_nr_inodes(void) { int i; - int sum = 0; + long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_inodes, i); return sum < 0 ? 0 : sum; } -static inline int get_nr_inodes_unused(void) +static inline long get_nr_inodes_unused(void) { int i; - int sum = 0; + long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_unused, i); return sum < 0 ? 0 : sum; } -int get_nr_dirty_inodes(void) +long get_nr_dirty_inodes(void) { /* not actually dirty inodes, but a wild approximation */ - int nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); + long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; } @@ -110,7 +111,7 @@ int proc_nr_inodes(ctl_table *table, int write, { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); - return proc_dointvec(table, write, buffer, lenp, ppos); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif @@ -402,13 +403,8 @@ EXPORT_SYMBOL(ihold); static void inode_lru_list_add(struct inode *inode) { - spin_lock(&inode->i_sb->s_inode_lru_lock); - if (list_empty(&inode->i_lru)) { - list_add(&inode->i_lru, &inode->i_sb->s_inode_lru); - inode->i_sb->s_nr_inodes_unused++; + if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); - } - spin_unlock(&inode->i_sb->s_inode_lru_lock); } /* @@ -426,13 +422,9 @@ void inode_add_lru(struct inode *inode) static void inode_lru_list_del(struct inode *inode) { - spin_lock(&inode->i_sb->s_inode_lru_lock); - if (!list_empty(&inode->i_lru)) { - list_del_init(&inode->i_lru); - inode->i_sb->s_nr_inodes_unused--; + + if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); - } - spin_unlock(&inode->i_sb->s_inode_lru_lock); } /** @@ -676,24 +668,8 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty) return busy; } -static int can_unuse(struct inode *inode) -{ - if (inode->i_state & ~I_REFERENCED) - return 0; - if (inode_has_buffers(inode)) - return 0; - if (atomic_read(&inode->i_count)) - return 0; - if (inode->i_data.nrpages) - return 0; - return 1; -} - /* - * Walk the superblock inode LRU for freeable inodes and attempt to free them. - * This is called from the superblock shrinker function with a number of inodes - * to trim from the LRU. Inodes to be freed are moved to a temporary list and - * then are freed outside inode_lock by dispose_list(). + * Isolate the inode from the LRU in preparation for freeing it. * * Any inodes which are pinned purely because of attached pagecache have their * pagecache removed. If the inode has metadata buffers attached to @@ -707,89 +683,82 @@ static int can_unuse(struct inode *inode) * LRU does not have strict ordering. Hence we don't want to reclaim inodes * with this flag set because they are the inodes that are out of order. */ -void prune_icache_sb(struct super_block *sb, int nr_to_scan) +static enum lru_status +inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg) { - LIST_HEAD(freeable); - int nr_scanned; - unsigned long reap = 0; + struct list_head *freeable = arg; + struct inode *inode = container_of(item, struct inode, i_lru); - spin_lock(&sb->s_inode_lru_lock); - for (nr_scanned = nr_to_scan; nr_scanned >= 0; nr_scanned--) { - struct inode *inode; + /* + * we are inverting the lru lock/inode->i_lock here, so use a trylock. + * If we fail to get the lock, just skip it. + */ + if (!spin_trylock(&inode->i_lock)) + return LRU_SKIP; - if (list_empty(&sb->s_inode_lru)) - break; + /* + * Referenced or dirty inodes are still in use. Give them another pass + * through the LRU as we canot reclaim them now. + */ + if (atomic_read(&inode->i_count) || + (inode->i_state & ~I_REFERENCED)) { + list_del_init(&inode->i_lru); + spin_unlock(&inode->i_lock); + this_cpu_dec(nr_unused); + return LRU_REMOVED; + } - inode = list_entry(sb->s_inode_lru.prev, struct inode, i_lru); + /* recently referenced inodes get one more pass */ + if (inode->i_state & I_REFERENCED) { + inode->i_state &= ~I_REFERENCED; + spin_unlock(&inode->i_lock); + return LRU_ROTATE; + } - /* - * we are inverting the sb->s_inode_lru_lock/inode->i_lock here, - * so use a trylock. If we fail to get the lock, just move the - * inode to the back of the list so we don't spin on it. - */ - if (!spin_trylock(&inode->i_lock)) { - list_move(&inode->i_lru, &sb->s_inode_lru); - continue; + if (inode_has_buffers(inode) || inode->i_data.nrpages) { + __iget(inode); + spin_unlock(&inode->i_lock); + spin_unlock(lru_lock); + if (remove_inode_buffers(inode)) { + unsigned long reap; + reap = invalidate_mapping_pages(&inode->i_data, 0, -1); + if (current_is_kswapd()) + __count_vm_events(KSWAPD_INODESTEAL, reap); + else + __count_vm_events(PGINODESTEAL, reap); + if (current->reclaim_state) + current->reclaim_state->reclaimed_slab += reap; } + iput(inode); + spin_lock(lru_lock); + return LRU_RETRY; + } - /* - * Referenced or dirty inodes are still in use. Give them - * another pass through the LRU as we canot reclaim them now. - */ - if (atomic_read(&inode->i_count) || - (inode->i_state & ~I_REFERENCED)) { - list_del_init(&inode->i_lru); - spin_unlock(&inode->i_lock); - sb->s_nr_inodes_unused--; - this_cpu_dec(nr_unused); - continue; - } + WARN_ON(inode->i_state & I_NEW); + inode->i_state |= I_FREEING; + list_move(&inode->i_lru, freeable); + spin_unlock(&inode->i_lock); - /* recently referenced inodes get one more pass */ - if (inode->i_state & I_REFERENCED) { - inode->i_state &= ~I_REFERENCED; - list_move(&inode->i_lru, &sb->s_inode_lru); - spin_unlock(&inode->i_lock); - continue; - } - if (inode_has_buffers(inode) || inode->i_data.nrpages) { - __iget(inode); - spin_unlock(&inode->i_lock); - spin_unlock(&sb->s_inode_lru_lock); - if (remove_inode_buffers(inode)) - reap += invalidate_mapping_pages(&inode->i_data, - 0, -1); - iput(inode); - spin_lock(&sb->s_inode_lru_lock); - - if (inode != list_entry(sb->s_inode_lru.next, - struct inode, i_lru)) - continue; /* wrong inode or list_empty */ - /* avoid lock inversions with trylock */ - if (!spin_trylock(&inode->i_lock)) - continue; - if (!can_unuse(inode)) { - spin_unlock(&inode->i_lock); - continue; - } - } - WARN_ON(inode->i_state & I_NEW); - inode->i_state |= I_FREEING; - spin_unlock(&inode->i_lock); + this_cpu_dec(nr_unused); + return LRU_REMOVED; +} - list_move(&inode->i_lru, &freeable); - sb->s_nr_inodes_unused--; - this_cpu_dec(nr_unused); - } - if (current_is_kswapd()) - __count_vm_events(KSWAPD_INODESTEAL, reap); - else - __count_vm_events(PGINODESTEAL, reap); - spin_unlock(&sb->s_inode_lru_lock); - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += reap; +/* + * Walk the superblock inode LRU for freeable inodes and attempt to free them. + * This is called from the superblock shrinker function with a number of inodes + * to trim from the LRU. Inodes to be freed are moved to a temporary list and + * then are freed outside inode_lock by dispose_list(). + */ +long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan, + int nid) +{ + LIST_HEAD(freeable); + long freed; + freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate, + &freeable, &nr_to_scan); dispose_list(&freeable); + return freed; } static void __wait_on_freeing_inode(struct inode *inode); diff --git a/fs/internal.h b/fs/internal.h index 143a903deb3d..fca5e077298f 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -111,6 +111,8 @@ extern int open_check_o_direct(struct file *f); * inode.c */ extern spinlock_t inode_sb_list_lock; +extern long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan, + int nid); extern void inode_add_lru(struct inode *inode); /* @@ -118,7 +120,7 @@ extern void inode_add_lru(struct inode *inode); */ extern void inode_wb_list_del(struct inode *inode); -extern int get_nr_dirty_inodes(void); +extern long get_nr_dirty_inodes(void); extern void evict_inodes(struct super_block *); extern int invalidate_inodes(struct super_block *, bool); @@ -126,6 +128,8 @@ extern int invalidate_inodes(struct super_block *, bool); * dcache.c */ extern struct dentry *__d_alloc(struct super_block *, const struct qstr *); +extern long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan, + int nid); /* * read_write.c diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 0a0453a66659..51652aaa3dc8 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -306,7 +306,7 @@ static void jfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); jfs_truncate(inode); } } diff --git a/fs/mbcache.c b/fs/mbcache.c index 8c32ef3ba88e..e519e45bf673 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -86,18 +86,6 @@ static LIST_HEAD(mb_cache_list); static LIST_HEAD(mb_cache_lru_list); static DEFINE_SPINLOCK(mb_cache_spinlock); -/* - * What the mbcache registers as to get shrunk dynamically. - */ - -static int mb_cache_shrink_fn(struct shrinker *shrink, - struct shrink_control *sc); - -static struct shrinker mb_cache_shrinker = { - .shrink = mb_cache_shrink_fn, - .seeks = DEFAULT_SEEKS, -}; - static inline int __mb_cache_entry_is_hashed(struct mb_cache_entry *ce) { @@ -151,7 +139,7 @@ forget: /* - * mb_cache_shrink_fn() memory pressure callback + * mb_cache_shrink_scan() memory pressure callback * * This function is called by the kernel memory management when memory * gets low. @@ -159,17 +147,16 @@ forget: * @shrink: (ignored) * @sc: shrink_control passed from reclaim * - * Returns the number of objects which are present in the cache. + * Returns the number of objects freed. */ -static int -mb_cache_shrink_fn(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long +mb_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(free_list); - struct mb_cache *cache; struct mb_cache_entry *entry, *tmp; - int count = 0; int nr_to_scan = sc->nr_to_scan; gfp_t gfp_mask = sc->gfp_mask; + unsigned long freed = 0; mb_debug("trying to free %d entries", nr_to_scan); spin_lock(&mb_cache_spinlock); @@ -179,19 +166,37 @@ mb_cache_shrink_fn(struct shrinker *shrink, struct shrink_control *sc) struct mb_cache_entry, e_lru_list); list_move_tail(&ce->e_lru_list, &free_list); __mb_cache_entry_unhash(ce); + freed++; + } + spin_unlock(&mb_cache_spinlock); + list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) { + __mb_cache_entry_forget(entry, gfp_mask); } + return freed; +} + +static unsigned long +mb_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ + struct mb_cache *cache; + unsigned long count = 0; + + spin_lock(&mb_cache_spinlock); list_for_each_entry(cache, &mb_cache_list, c_cache_list) { mb_debug("cache %s (%d)", cache->c_name, atomic_read(&cache->c_entry_count)); count += atomic_read(&cache->c_entry_count); } spin_unlock(&mb_cache_spinlock); - list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) { - __mb_cache_entry_forget(entry, gfp_mask); - } - return (count / 100) * sysctl_vfs_cache_pressure; + + return vfs_pressure_ratio(count); } +static struct shrinker mb_cache_shrinker = { + .count_objects = mb_cache_shrink_count, + .scan_objects = mb_cache_shrink_scan, + .seeks = DEFAULT_SEEKS, +}; /* * mb_cache_create() create a new cache diff --git a/fs/minix/inode.c b/fs/minix/inode.c index df122496f328..0332109162a5 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -400,7 +400,7 @@ static void minix_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); minix_truncate(inode); } } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 187caa47dad9..05068da89a8b 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2007,17 +2007,18 @@ static void nfs_access_free_list(struct list_head *head) } } -int nfs_access_cache_shrinker(struct shrinker *shrink, - struct shrink_control *sc) +unsigned long +nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(head); struct nfs_inode *nfsi, *next; struct nfs_access_entry *cache; int nr_to_scan = sc->nr_to_scan; gfp_t gfp_mask = sc->gfp_mask; + long freed = 0; if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL) - return (nr_to_scan == 0) ? 0 : -1; + return SHRINK_STOP; spin_lock(&nfs_access_lru_lock); list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) { @@ -2033,6 +2034,7 @@ int nfs_access_cache_shrinker(struct shrinker *shrink, struct nfs_access_entry, lru); list_move(&cache->lru, &head); rb_erase(&cache->rb_node, &nfsi->access_cache); + freed++; if (!list_empty(&nfsi->access_cache_entry_lru)) list_move_tail(&nfsi->access_cache_inode_lru, &nfs_access_lru_list); @@ -2047,7 +2049,13 @@ remove_lru_entry: } spin_unlock(&nfs_access_lru_lock); nfs_access_free_list(&head); - return (atomic_long_read(&nfs_access_nr_entries) / 100) * sysctl_vfs_cache_pressure; + return freed; +} + +unsigned long +nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc) +{ + return vfs_pressure_ratio(atomic_long_read(&nfs_access_nr_entries)); } static void __nfs_access_zap_cache(struct nfs_inode *nfsi, struct list_head *head) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 87e797640828..eda8879171c4 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -541,7 +541,6 @@ EXPORT_SYMBOL_GPL(nfs_setattr); */ static int nfs_vmtruncate(struct inode * inode, loff_t offset) { - loff_t oldsize; int err; err = inode_newsize_ok(inode, offset); @@ -549,11 +548,10 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset) goto out; spin_lock(&inode->i_lock); - oldsize = inode->i_size; i_size_write(inode, offset); spin_unlock(&inode->i_lock); - truncate_pagecache(inode, oldsize, offset); + truncate_pagecache(inode, offset); out: return err; } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index e808ed2fea67..2cbcaec28abd 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -271,8 +271,10 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const char *ip_addr); /* dir.c */ -extern int nfs_access_cache_shrinker(struct shrinker *shrink, - struct shrink_control *sc); +extern unsigned long nfs_access_cache_count(struct shrinker *shrink, + struct shrink_control *sc); +extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, + struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); int nfs_create(struct inode *, struct dentry *, umode_t, bool); int nfs_mkdir(struct inode *, struct dentry *, umode_t); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index d26bd63e93ce..d643165aee59 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -360,7 +360,8 @@ static void unregister_nfs4_fs(void) #endif static struct shrinker acl_shrinker = { - .shrink = nfs_access_cache_shrinker, + .count_objects = nfs_access_cache_count, + .scan_objects = nfs_access_cache_scan, .seeks = DEFAULT_SEEKS, }; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index e76244edd748..9186c7ce0b14 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -59,11 +59,14 @@ static unsigned int longest_chain_cachesize; static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec); static void cache_cleaner_func(struct work_struct *unused); -static int nfsd_reply_cache_shrink(struct shrinker *shrink, - struct shrink_control *sc); +static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, + struct shrink_control *sc); +static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink, + struct shrink_control *sc); static struct shrinker nfsd_reply_cache_shrinker = { - .shrink = nfsd_reply_cache_shrink, + .scan_objects = nfsd_reply_cache_scan, + .count_objects = nfsd_reply_cache_count, .seeks = 1, }; @@ -232,16 +235,18 @@ nfsd_cache_entry_expired(struct svc_cacherep *rp) * Walk the LRU list and prune off entries that are older than RC_EXPIRE. * Also prune the oldest ones when the total exceeds the max number of entries. */ -static void +static long prune_cache_entries(void) { struct svc_cacherep *rp, *tmp; + long freed = 0; list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) { if (!nfsd_cache_entry_expired(rp) && num_drc_entries <= max_drc_entries) break; nfsd_reply_cache_free_locked(rp); + freed++; } /* @@ -254,6 +259,7 @@ prune_cache_entries(void) cancel_delayed_work(&cache_cleaner); else mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE); + return freed; } static void @@ -264,20 +270,28 @@ cache_cleaner_func(struct work_struct *unused) spin_unlock(&cache_lock); } -static int -nfsd_reply_cache_shrink(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long +nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) { - unsigned int num; + unsigned long num; spin_lock(&cache_lock); - if (sc->nr_to_scan) - prune_cache_entries(); num = num_drc_entries; spin_unlock(&cache_lock); return num; } +static unsigned long +nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + unsigned long freed; + + spin_lock(&cache_lock); + freed = prune_cache_entries(); + spin_unlock(&cache_lock); + return freed; +} /* * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes */ diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 059b760f7f62..4a99a24b54a2 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -254,7 +254,7 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); nilfs_truncate(inode); } } diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index c5670b8d198c..ea4ba9daeb47 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1768,7 +1768,7 @@ static void ntfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); ntfs_truncate_vfs(inode); } } diff --git a/fs/omfs/file.c b/fs/omfs/file.c index badafd8ef4c7..0fe505b2cded 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -311,7 +311,7 @@ static void omfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); omfs_truncate(inode); } } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 5aa847a603c0..59d85d608898 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -132,13 +132,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(i.freeswap), K(global_page_state(NR_FILE_DIRTY)), K(global_page_state(NR_WRITEBACK)), -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - K(global_page_state(NR_ANON_PAGES) - + global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * - HPAGE_PMD_NR), -#else K(global_page_state(NR_ANON_PAGES)), -#endif K(global_page_state(NR_FILE_MAPPED)), K(global_page_state(NR_SHMEM)), K(global_page_state(NR_SLAB_RECLAIMABLE) + diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 9a702e193538..831d49a4111f 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -687,45 +687,37 @@ int dquot_quota_sync(struct super_block *sb, int type) } EXPORT_SYMBOL(dquot_quota_sync); -/* Free unused dquots from cache */ -static void prune_dqcache(int count) +static unsigned long +dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { struct list_head *head; struct dquot *dquot; + unsigned long freed = 0; head = free_dquots.prev; - while (head != &free_dquots && count) { + while (head != &free_dquots && sc->nr_to_scan) { dquot = list_entry(head, struct dquot, dq_free); remove_dquot_hash(dquot); remove_free_dquot(dquot); remove_inuse(dquot); do_destroy_dquot(dquot); - count--; + sc->nr_to_scan--; + freed++; head = free_dquots.prev; } + return freed; } -/* - * This is called from kswapd when we think we need some - * more memory - */ -static int shrink_dqcache_memory(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long +dqcache_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { - int nr = sc->nr_to_scan; - - if (nr) { - spin_lock(&dq_list_lock); - prune_dqcache(nr); - spin_unlock(&dq_list_lock); - } - return ((unsigned) - percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS]) - /100) * sysctl_vfs_cache_pressure; + return vfs_pressure_ratio( + percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS])); } static struct shrinker dqcache_shrinker = { - .shrink = shrink_dqcache_memory, + .count_objects = dqcache_shrink_count, + .scan_objects = dqcache_shrink_scan, .seeks = DEFAULT_SEEKS, }; diff --git a/fs/super.c b/fs/super.c index 68307c029228..73d09522943a 100644 --- a/fs/super.c +++ b/fs/super.c @@ -53,11 +53,15 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = { * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we * take a passive reference to the superblock to avoid this from occurring. */ -static int prune_super(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long super_cache_scan(struct shrinker *shrink, + struct shrink_control *sc) { struct super_block *sb; - int fs_objects = 0; - int total_objects; + long fs_objects = 0; + long total_objects; + long freed = 0; + long dentries; + long inodes; sb = container_of(shrink, struct super_block, s_shrink); @@ -65,46 +69,62 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc) * Deadlock avoidance. We may hold various FS locks, and we don't want * to recurse into the FS that called us in clear_inode() and friends.. */ - if (sc->nr_to_scan && !(sc->gfp_mask & __GFP_FS)) - return -1; + if (!(sc->gfp_mask & __GFP_FS)) + return SHRINK_STOP; if (!grab_super_passive(sb)) - return -1; + return SHRINK_STOP; if (sb->s_op && sb->s_op->nr_cached_objects) - fs_objects = sb->s_op->nr_cached_objects(sb); - - total_objects = sb->s_nr_dentry_unused + - sb->s_nr_inodes_unused + fs_objects + 1; - - if (sc->nr_to_scan) { - int dentries; - int inodes; - - /* proportion the scan between the caches */ - dentries = (sc->nr_to_scan * sb->s_nr_dentry_unused) / - total_objects; - inodes = (sc->nr_to_scan * sb->s_nr_inodes_unused) / - total_objects; - if (fs_objects) - fs_objects = (sc->nr_to_scan * fs_objects) / - total_objects; - /* - * prune the dcache first as the icache is pinned by it, then - * prune the icache, followed by the filesystem specific caches - */ - prune_dcache_sb(sb, dentries); - prune_icache_sb(sb, inodes); + fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid); - if (fs_objects && sb->s_op->free_cached_objects) { - sb->s_op->free_cached_objects(sb, fs_objects); - fs_objects = sb->s_op->nr_cached_objects(sb); - } - total_objects = sb->s_nr_dentry_unused + - sb->s_nr_inodes_unused + fs_objects; + inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid); + dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid); + total_objects = dentries + inodes + fs_objects + 1; + + /* proportion the scan between the caches */ + dentries = mult_frac(sc->nr_to_scan, dentries, total_objects); + inodes = mult_frac(sc->nr_to_scan, inodes, total_objects); + + /* + * prune the dcache first as the icache is pinned by it, then + * prune the icache, followed by the filesystem specific caches + */ + freed = prune_dcache_sb(sb, dentries, sc->nid); + freed += prune_icache_sb(sb, inodes, sc->nid); + + if (fs_objects) { + fs_objects = mult_frac(sc->nr_to_scan, fs_objects, + total_objects); + freed += sb->s_op->free_cached_objects(sb, fs_objects, + sc->nid); } - total_objects = (total_objects / 100) * sysctl_vfs_cache_pressure; + drop_super(sb); + return freed; +} + +static unsigned long super_cache_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct super_block *sb; + long total_objects = 0; + + sb = container_of(shrink, struct super_block, s_shrink); + + if (!grab_super_passive(sb)) + return 0; + + if (sb->s_op && sb->s_op->nr_cached_objects) + total_objects = sb->s_op->nr_cached_objects(sb, + sc->nid); + + total_objects += list_lru_count_node(&sb->s_dentry_lru, + sc->nid); + total_objects += list_lru_count_node(&sb->s_inode_lru, + sc->nid); + + total_objects = vfs_pressure_ratio(total_objects); drop_super(sb); return total_objects; } @@ -181,9 +201,12 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) INIT_HLIST_NODE(&s->s_instances); INIT_HLIST_BL_HEAD(&s->s_anon); INIT_LIST_HEAD(&s->s_inodes); - INIT_LIST_HEAD(&s->s_dentry_lru); - INIT_LIST_HEAD(&s->s_inode_lru); - spin_lock_init(&s->s_inode_lru_lock); + + if (list_lru_init(&s->s_dentry_lru)) + goto err_out; + if (list_lru_init(&s->s_inode_lru)) + goto err_out_dentry_lru; + INIT_LIST_HEAD(&s->s_mounts); init_rwsem(&s->s_umount); lockdep_set_class(&s->s_umount, &type->s_umount_key); @@ -216,11 +239,16 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) s->cleancache_poolid = -1; s->s_shrink.seeks = DEFAULT_SEEKS; - s->s_shrink.shrink = prune_super; + s->s_shrink.scan_objects = super_cache_scan; + s->s_shrink.count_objects = super_cache_count; s->s_shrink.batch = 1024; + s->s_shrink.flags = SHRINKER_NUMA_AWARE; } out: return s; + +err_out_dentry_lru: + list_lru_destroy(&s->s_dentry_lru); err_out: security_sb_free(s); #ifdef CONFIG_SMP @@ -300,6 +328,9 @@ void deactivate_locked_super(struct super_block *s) /* caches are now gone, we can safely kill the shrinker now */ unregister_shrinker(&s->s_shrink); + list_lru_destroy(&s->s_dentry_lru); + list_lru_destroy(&s->s_inode_lru); + put_filesystem(fs); put_super(s); } else { diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index c1a591a4725b..66bc316927e8 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -469,7 +469,7 @@ static void sysv_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); sysv_truncate(inode); } } diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c index 9e1d05666fed..f35135e28e96 100644 --- a/fs/ubifs/shrinker.c +++ b/fs/ubifs/shrinker.c @@ -277,18 +277,25 @@ static int kick_a_thread(void) return 0; } -int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc) +unsigned long ubifs_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) { - int nr = sc->nr_to_scan; - int freed, contention = 0; long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt); - if (nr == 0) - /* - * Due to the way UBIFS updates the clean znode counter it may - * temporarily be negative. - */ - return clean_zn_cnt >= 0 ? clean_zn_cnt : 1; + /* + * Due to the way UBIFS updates the clean znode counter it may + * temporarily be negative. + */ + return clean_zn_cnt >= 0 ? clean_zn_cnt : 1; +} + +unsigned long ubifs_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + unsigned long nr = sc->nr_to_scan; + int contention = 0; + unsigned long freed; + long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt); if (!clean_zn_cnt) { /* @@ -316,10 +323,10 @@ int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc) if (!freed && contention) { dbg_tnc("freed nothing, but contention"); - return -1; + return SHRINK_STOP; } out: - dbg_tnc("%d znodes were freed, requested %d", freed, nr); + dbg_tnc("%lu znodes were freed, requested %lu", freed, nr); return freed; } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 879b9976c12b..3e4aa7281e04 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -49,7 +49,8 @@ struct kmem_cache *ubifs_inode_slab; /* UBIFS TNC shrinker description */ static struct shrinker ubifs_shrinker_info = { - .shrink = ubifs_shrinker, + .scan_objects = ubifs_shrink_scan, + .count_objects = ubifs_shrink_count, .seeks = DEFAULT_SEEKS, }; diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index b2babce4d70f..e8c8cfe1435c 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1624,7 +1624,10 @@ int ubifs_tnc_start_commit(struct ubifs_info *c, struct ubifs_zbranch *zroot); int ubifs_tnc_end_commit(struct ubifs_info *c); /* shrinker.c */ -int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc); +unsigned long ubifs_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc); +unsigned long ubifs_shrink_count(struct shrinker *shrink, + struct shrink_control *sc); /* commit.c */ int ubifs_bg_thread(void *info); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index fad32d5f62e5..986e11ad176b 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -172,7 +172,7 @@ static void udf_write_failed(struct address_space *mapping, loff_t to) loff_t isize = inode->i_size; if (to > isize) { - truncate_pagecache(inode, to, isize); + truncate_pagecache(inode, isize); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index ff24e4449ece..c8ca96086784 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -531,7 +531,7 @@ static void ufs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); } static int ufs_write_begin(struct file *file, struct address_space *mapping, diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 5a2a38c677d8..2291218f098c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1597,7 +1597,7 @@ xfs_vm_write_begin( unlock_page(page); if (pos + len > i_size_read(inode)) - truncate_pagecache(inode, pos + len, i_size_read(inode)); + truncate_pagecache(inode, i_size_read(inode)); page_cache_release(page); page = NULL; @@ -1633,7 +1633,7 @@ xfs_vm_write_end( loff_t to = pos + len; if (to > isize) { - truncate_pagecache(inode, to, isize); + truncate_pagecache(inode, isize); xfs_vm_kill_delalloc_range(inode, isize, to); } } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index c06823fe10d3..263470075ea2 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -81,54 +81,6 @@ xfs_buf_vmap_len( } /* - * xfs_buf_lru_add - add a buffer to the LRU. - * - * The LRU takes a new reference to the buffer so that it will only be freed - * once the shrinker takes the buffer off the LRU. - */ -STATIC void -xfs_buf_lru_add( - struct xfs_buf *bp) -{ - struct xfs_buftarg *btp = bp->b_target; - - spin_lock(&btp->bt_lru_lock); - if (list_empty(&bp->b_lru)) { - atomic_inc(&bp->b_hold); - list_add_tail(&bp->b_lru, &btp->bt_lru); - btp->bt_lru_nr++; - bp->b_lru_flags &= ~_XBF_LRU_DISPOSE; - } - spin_unlock(&btp->bt_lru_lock); -} - -/* - * xfs_buf_lru_del - remove a buffer from the LRU - * - * The unlocked check is safe here because it only occurs when there are not - * b_lru_ref counts left on the inode under the pag->pag_buf_lock. it is there - * to optimise the shrinker removing the buffer from the LRU and calling - * xfs_buf_free(). i.e. it removes an unnecessary round trip on the - * bt_lru_lock. - */ -STATIC void -xfs_buf_lru_del( - struct xfs_buf *bp) -{ - struct xfs_buftarg *btp = bp->b_target; - - if (list_empty(&bp->b_lru)) - return; - - spin_lock(&btp->bt_lru_lock); - if (!list_empty(&bp->b_lru)) { - list_del_init(&bp->b_lru); - btp->bt_lru_nr--; - } - spin_unlock(&btp->bt_lru_lock); -} - -/* * When we mark a buffer stale, we remove the buffer from the LRU and clear the * b_lru_ref count so that the buffer is freed immediately when the buffer * reference count falls to zero. If the buffer is already on the LRU, we need @@ -151,20 +103,14 @@ xfs_buf_stale( */ bp->b_flags &= ~_XBF_DELWRI_Q; - atomic_set(&(bp)->b_lru_ref, 0); - if (!list_empty(&bp->b_lru)) { - struct xfs_buftarg *btp = bp->b_target; + spin_lock(&bp->b_lock); + atomic_set(&bp->b_lru_ref, 0); + if (!(bp->b_state & XFS_BSTATE_DISPOSE) && + (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru))) + atomic_dec(&bp->b_hold); - spin_lock(&btp->bt_lru_lock); - if (!list_empty(&bp->b_lru) && - !(bp->b_lru_flags & _XBF_LRU_DISPOSE)) { - list_del_init(&bp->b_lru); - btp->bt_lru_nr--; - atomic_dec(&bp->b_hold); - } - spin_unlock(&btp->bt_lru_lock); - } ASSERT(atomic_read(&bp->b_hold) >= 1); + spin_unlock(&bp->b_lock); } static int @@ -228,6 +174,7 @@ _xfs_buf_alloc( INIT_LIST_HEAD(&bp->b_list); RB_CLEAR_NODE(&bp->b_rbnode); sema_init(&bp->b_sema, 0); /* held, no waiters */ + spin_lock_init(&bp->b_lock); XB_SET_OWNER(bp); bp->b_target = target; bp->b_flags = flags; @@ -917,12 +864,33 @@ xfs_buf_rele( ASSERT(atomic_read(&bp->b_hold) > 0); if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) { - if (!(bp->b_flags & XBF_STALE) && - atomic_read(&bp->b_lru_ref)) { - xfs_buf_lru_add(bp); + spin_lock(&bp->b_lock); + if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) { + /* + * If the buffer is added to the LRU take a new + * reference to the buffer for the LRU and clear the + * (now stale) dispose list state flag + */ + if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) { + bp->b_state &= ~XFS_BSTATE_DISPOSE; + atomic_inc(&bp->b_hold); + } + spin_unlock(&bp->b_lock); spin_unlock(&pag->pag_buf_lock); } else { - xfs_buf_lru_del(bp); + /* + * most of the time buffers will already be removed from + * the LRU, so optimise that case by checking for the + * XFS_BSTATE_DISPOSE flag indicating the last list the + * buffer was on was the disposal list + */ + if (!(bp->b_state & XFS_BSTATE_DISPOSE)) { + list_lru_del(&bp->b_target->bt_lru, &bp->b_lru); + } else { + ASSERT(list_empty(&bp->b_lru)); + } + spin_unlock(&bp->b_lock); + ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); rb_erase(&bp->b_rbnode, &pag->pag_buf_tree); spin_unlock(&pag->pag_buf_lock); @@ -1502,83 +1470,121 @@ xfs_buf_iomove( * returned. These buffers will have an elevated hold count, so wait on those * while freeing all the buffers only held by the LRU. */ +static enum lru_status +xfs_buftarg_wait_rele( + struct list_head *item, + spinlock_t *lru_lock, + void *arg) + +{ + struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru); + struct list_head *dispose = arg; + + if (atomic_read(&bp->b_hold) > 1) { + /* need to wait, so skip it this pass */ + trace_xfs_buf_wait_buftarg(bp, _RET_IP_); + return LRU_SKIP; + } + if (!spin_trylock(&bp->b_lock)) + return LRU_SKIP; + + /* + * clear the LRU reference count so the buffer doesn't get + * ignored in xfs_buf_rele(). + */ + atomic_set(&bp->b_lru_ref, 0); + bp->b_state |= XFS_BSTATE_DISPOSE; + list_move(item, dispose); + spin_unlock(&bp->b_lock); + return LRU_REMOVED; +} + void xfs_wait_buftarg( struct xfs_buftarg *btp) { - struct xfs_buf *bp; + LIST_HEAD(dispose); + int loop = 0; -restart: - spin_lock(&btp->bt_lru_lock); - while (!list_empty(&btp->bt_lru)) { - bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru); - if (atomic_read(&bp->b_hold) > 1) { - trace_xfs_buf_wait_buftarg(bp, _RET_IP_); - list_move_tail(&bp->b_lru, &btp->bt_lru); - spin_unlock(&btp->bt_lru_lock); - delay(100); - goto restart; + /* loop until there is nothing left on the lru list. */ + while (list_lru_count(&btp->bt_lru)) { + list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele, + &dispose, LONG_MAX); + + while (!list_empty(&dispose)) { + struct xfs_buf *bp; + bp = list_first_entry(&dispose, struct xfs_buf, b_lru); + list_del_init(&bp->b_lru); + xfs_buf_rele(bp); } - /* - * clear the LRU reference count so the buffer doesn't get - * ignored in xfs_buf_rele(). - */ - atomic_set(&bp->b_lru_ref, 0); - spin_unlock(&btp->bt_lru_lock); - xfs_buf_rele(bp); - spin_lock(&btp->bt_lru_lock); + if (loop++ != 0) + delay(100); } - spin_unlock(&btp->bt_lru_lock); } -int -xfs_buftarg_shrink( +static enum lru_status +xfs_buftarg_isolate( + struct list_head *item, + spinlock_t *lru_lock, + void *arg) +{ + struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru); + struct list_head *dispose = arg; + + /* + * we are inverting the lru lock/bp->b_lock here, so use a trylock. + * If we fail to get the lock, just skip it. + */ + if (!spin_trylock(&bp->b_lock)) + return LRU_SKIP; + /* + * Decrement the b_lru_ref count unless the value is already + * zero. If the value is already zero, we need to reclaim the + * buffer, otherwise it gets another trip through the LRU. + */ + if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) { + spin_unlock(&bp->b_lock); + return LRU_ROTATE; + } + + bp->b_state |= XFS_BSTATE_DISPOSE; + list_move(item, dispose); + spin_unlock(&bp->b_lock); + return LRU_REMOVED; +} + +static unsigned long +xfs_buftarg_shrink_scan( struct shrinker *shrink, struct shrink_control *sc) { struct xfs_buftarg *btp = container_of(shrink, struct xfs_buftarg, bt_shrinker); - struct xfs_buf *bp; - int nr_to_scan = sc->nr_to_scan; LIST_HEAD(dispose); + unsigned long freed; + unsigned long nr_to_scan = sc->nr_to_scan; - if (!nr_to_scan) - return btp->bt_lru_nr; - - spin_lock(&btp->bt_lru_lock); - while (!list_empty(&btp->bt_lru)) { - if (nr_to_scan-- <= 0) - break; - - bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru); - - /* - * Decrement the b_lru_ref count unless the value is already - * zero. If the value is already zero, we need to reclaim the - * buffer, otherwise it gets another trip through the LRU. - */ - if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) { - list_move_tail(&bp->b_lru, &btp->bt_lru); - continue; - } - - /* - * remove the buffer from the LRU now to avoid needing another - * lock round trip inside xfs_buf_rele(). - */ - list_move(&bp->b_lru, &dispose); - btp->bt_lru_nr--; - bp->b_lru_flags |= _XBF_LRU_DISPOSE; - } - spin_unlock(&btp->bt_lru_lock); + freed = list_lru_walk_node(&btp->bt_lru, sc->nid, xfs_buftarg_isolate, + &dispose, &nr_to_scan); while (!list_empty(&dispose)) { + struct xfs_buf *bp; bp = list_first_entry(&dispose, struct xfs_buf, b_lru); list_del_init(&bp->b_lru); xfs_buf_rele(bp); } - return btp->bt_lru_nr; + return freed; +} + +static unsigned long +xfs_buftarg_shrink_count( + struct shrinker *shrink, + struct shrink_control *sc) +{ + struct xfs_buftarg *btp = container_of(shrink, + struct xfs_buftarg, bt_shrinker); + return list_lru_count_node(&btp->bt_lru, sc->nid); } void @@ -1587,6 +1593,7 @@ xfs_free_buftarg( struct xfs_buftarg *btp) { unregister_shrinker(&btp->bt_shrinker); + list_lru_destroy(&btp->bt_lru); if (mp->m_flags & XFS_MOUNT_BARRIER) xfs_blkdev_issue_flush(btp); @@ -1660,12 +1667,16 @@ xfs_alloc_buftarg( if (!btp->bt_bdi) goto error; - INIT_LIST_HEAD(&btp->bt_lru); - spin_lock_init(&btp->bt_lru_lock); if (xfs_setsize_buftarg_early(btp, bdev)) goto error; - btp->bt_shrinker.shrink = xfs_buftarg_shrink; + + if (list_lru_init(&btp->bt_lru)) + goto error; + + btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count; + btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan; btp->bt_shrinker.seeks = DEFAULT_SEEKS; + btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE; register_shrinker(&btp->bt_shrinker); return btp; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 433a12ed7b17..e65683361017 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -25,6 +25,7 @@ #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/uio.h> +#include <linux/list_lru.h> /* * Base types @@ -59,7 +60,6 @@ typedef enum { #define _XBF_KMEM (1 << 21)/* backed by heap memory */ #define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ #define _XBF_COMPOUND (1 << 23)/* compound buffer */ -#define _XBF_LRU_DISPOSE (1 << 24)/* buffer being discarded */ typedef unsigned int xfs_buf_flags_t; @@ -78,8 +78,12 @@ typedef unsigned int xfs_buf_flags_t; { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ - { _XBF_COMPOUND, "COMPOUND" }, \ - { _XBF_LRU_DISPOSE, "LRU_DISPOSE" } + { _XBF_COMPOUND, "COMPOUND" } + +/* + * Internal state flags. + */ +#define XFS_BSTATE_DISPOSE (1 << 0) /* buffer being discarded */ typedef struct xfs_buftarg { dev_t bt_dev; @@ -92,9 +96,7 @@ typedef struct xfs_buftarg { /* LRU control structures */ struct shrinker bt_shrinker; - struct list_head bt_lru; - spinlock_t bt_lru_lock; - unsigned int bt_lru_nr; + struct list_lru bt_lru; } xfs_buftarg_t; struct xfs_buf; @@ -137,7 +139,8 @@ typedef struct xfs_buf { * bt_lru_lock and not by b_sema */ struct list_head b_lru; /* lru list */ - xfs_buf_flags_t b_lru_flags; /* internal lru status flags */ + spinlock_t b_lock; /* internal state lock */ + unsigned int b_state; /* internal state flags */ wait_queue_head_t b_waiters; /* unpin waiters */ struct list_head b_list; struct xfs_perag *b_pag; /* contains rbtree root */ diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 251c66632e5e..71520e6e5d65 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -940,13 +940,8 @@ xfs_qm_dqput_final( trace_xfs_dqput_free(dqp); - mutex_lock(&qi->qi_lru_lock); - if (list_empty(&dqp->q_lru)) { - list_add_tail(&dqp->q_lru, &qi->qi_lru_list); - qi->qi_lru_count++; + if (list_lru_add(&qi->qi_lru, &dqp->q_lru)) XFS_STATS_INC(xs_qm_dquot_unused); - } - mutex_unlock(&qi->qi_lru_lock); /* * If we just added a udquot to the freelist, then we want to release diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 16219b9c6790..73b62a24ceac 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1167,7 +1167,7 @@ xfs_reclaim_inodes( * them to be cleaned, which we hope will not be very long due to the * background walker having already kicked the IO off on those dirty inodes. */ -void +long xfs_reclaim_inodes_nr( struct xfs_mount *mp, int nr_to_scan) @@ -1176,7 +1176,7 @@ xfs_reclaim_inodes_nr( xfs_reclaim_work_queue(mp); xfs_ail_push_all(mp->m_ail); - xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan); + return xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan); } /* diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index 8a89f7d791bd..456f0144e1b6 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -46,7 +46,7 @@ void xfs_reclaim_worker(struct work_struct *work); int xfs_reclaim_inodes(struct xfs_mount *mp, int mode); int xfs_reclaim_inodes_count(struct xfs_mount *mp); -void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan); +long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan); void xfs_inode_set_reclaim_tag(struct xfs_inode *ip); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 6218a0aeeeea..3e6c2e6c9cd2 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -51,8 +51,9 @@ */ STATIC int xfs_qm_init_quotainos(xfs_mount_t *); STATIC int xfs_qm_init_quotainfo(xfs_mount_t *); -STATIC int xfs_qm_shake(struct shrinker *, struct shrink_control *); + +STATIC void xfs_qm_dqfree_one(struct xfs_dquot *dqp); /* * We use the batch lookup interface to iterate over the dquots as it * currently is the only interface into the radix tree code that allows @@ -203,12 +204,9 @@ xfs_qm_dqpurge( * We move dquots to the freelist as soon as their reference count * hits zero, so it really should be on the freelist here. */ - mutex_lock(&qi->qi_lru_lock); ASSERT(!list_empty(&dqp->q_lru)); - list_del_init(&dqp->q_lru); - qi->qi_lru_count--; + list_lru_del(&qi->qi_lru, &dqp->q_lru); XFS_STATS_DEC(xs_qm_dquot_unused); - mutex_unlock(&qi->qi_lru_lock); xfs_qm_dqdestroy(dqp); @@ -680,6 +678,143 @@ xfs_qm_calc_dquots_per_chunk( return ndquots; } +struct xfs_qm_isolate { + struct list_head buffers; + struct list_head dispose; +}; + +static enum lru_status +xfs_qm_dquot_isolate( + struct list_head *item, + spinlock_t *lru_lock, + void *arg) +{ + struct xfs_dquot *dqp = container_of(item, + struct xfs_dquot, q_lru); + struct xfs_qm_isolate *isol = arg; + + if (!xfs_dqlock_nowait(dqp)) + goto out_miss_busy; + + /* + * This dquot has acquired a reference in the meantime remove it from + * the freelist and try again. + */ + if (dqp->q_nrefs) { + xfs_dqunlock(dqp); + XFS_STATS_INC(xs_qm_dqwants); + + trace_xfs_dqreclaim_want(dqp); + list_del_init(&dqp->q_lru); + XFS_STATS_DEC(xs_qm_dquot_unused); + return LRU_REMOVED; + } + + /* + * If the dquot is dirty, flush it. If it's already being flushed, just + * skip it so there is time for the IO to complete before we try to + * reclaim it again on the next LRU pass. + */ + if (!xfs_dqflock_nowait(dqp)) { + xfs_dqunlock(dqp); + goto out_miss_busy; + } + + if (XFS_DQ_IS_DIRTY(dqp)) { + struct xfs_buf *bp = NULL; + int error; + + trace_xfs_dqreclaim_dirty(dqp); + + /* we have to drop the LRU lock to flush the dquot */ + spin_unlock(lru_lock); + + error = xfs_qm_dqflush(dqp, &bp); + if (error) { + xfs_warn(dqp->q_mount, "%s: dquot %p flush failed", + __func__, dqp); + goto out_unlock_dirty; + } + + xfs_buf_delwri_queue(bp, &isol->buffers); + xfs_buf_relse(bp); + goto out_unlock_dirty; + } + xfs_dqfunlock(dqp); + + /* + * Prevent lookups now that we are past the point of no return. + */ + dqp->dq_flags |= XFS_DQ_FREEING; + xfs_dqunlock(dqp); + + ASSERT(dqp->q_nrefs == 0); + list_move_tail(&dqp->q_lru, &isol->dispose); + XFS_STATS_DEC(xs_qm_dquot_unused); + trace_xfs_dqreclaim_done(dqp); + XFS_STATS_INC(xs_qm_dqreclaims); + return LRU_REMOVED; + +out_miss_busy: + trace_xfs_dqreclaim_busy(dqp); + XFS_STATS_INC(xs_qm_dqreclaim_misses); + return LRU_SKIP; + +out_unlock_dirty: + trace_xfs_dqreclaim_busy(dqp); + XFS_STATS_INC(xs_qm_dqreclaim_misses); + xfs_dqunlock(dqp); + spin_lock(lru_lock); + return LRU_RETRY; +} + +static unsigned long +xfs_qm_shrink_scan( + struct shrinker *shrink, + struct shrink_control *sc) +{ + struct xfs_quotainfo *qi = container_of(shrink, + struct xfs_quotainfo, qi_shrinker); + struct xfs_qm_isolate isol; + unsigned long freed; + int error; + unsigned long nr_to_scan = sc->nr_to_scan; + + if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT)) + return 0; + + INIT_LIST_HEAD(&isol.buffers); + INIT_LIST_HEAD(&isol.dispose); + + freed = list_lru_walk_node(&qi->qi_lru, sc->nid, xfs_qm_dquot_isolate, &isol, + &nr_to_scan); + + error = xfs_buf_delwri_submit(&isol.buffers); + if (error) + xfs_warn(NULL, "%s: dquot reclaim failed", __func__); + + while (!list_empty(&isol.dispose)) { + struct xfs_dquot *dqp; + + dqp = list_first_entry(&isol.dispose, struct xfs_dquot, q_lru); + list_del_init(&dqp->q_lru); + xfs_qm_dqfree_one(dqp); + } + + return freed; +} + +static unsigned long +xfs_qm_shrink_count( + struct shrinker *shrink, + struct shrink_control *sc) +{ + struct xfs_quotainfo *qi = container_of(shrink, + struct xfs_quotainfo, qi_shrinker); + + return list_lru_count_node(&qi->qi_lru, sc->nid); +} + /* * This initializes all the quota information that's kept in the * mount structure @@ -696,11 +831,18 @@ xfs_qm_init_quotainfo( qinf = mp->m_quotainfo = kmem_zalloc(sizeof(xfs_quotainfo_t), KM_SLEEP); + if ((error = list_lru_init(&qinf->qi_lru))) { + kmem_free(qinf); + mp->m_quotainfo = NULL; + return error; + } + /* * See if quotainodes are setup, and if not, allocate them, * and change the superblock accordingly. */ if ((error = xfs_qm_init_quotainos(mp))) { + list_lru_destroy(&qinf->qi_lru); kmem_free(qinf); mp->m_quotainfo = NULL; return error; @@ -711,10 +853,6 @@ xfs_qm_init_quotainfo( INIT_RADIX_TREE(&qinf->qi_pquota_tree, GFP_NOFS); mutex_init(&qinf->qi_tree_lock); - INIT_LIST_HEAD(&qinf->qi_lru_list); - qinf->qi_lru_count = 0; - mutex_init(&qinf->qi_lru_lock); - /* mutex used to serialize quotaoffs */ mutex_init(&qinf->qi_quotaofflock); @@ -779,8 +917,10 @@ xfs_qm_init_quotainfo( qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT; } - qinf->qi_shrinker.shrink = xfs_qm_shake; + qinf->qi_shrinker.count_objects = xfs_qm_shrink_count; + qinf->qi_shrinker.scan_objects = xfs_qm_shrink_scan; qinf->qi_shrinker.seeks = DEFAULT_SEEKS; + qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE; register_shrinker(&qinf->qi_shrinker); return 0; } @@ -801,6 +941,7 @@ xfs_qm_destroy_quotainfo( ASSERT(qi != NULL); unregister_shrinker(&qi->qi_shrinker); + list_lru_destroy(&qi->qi_lru); if (qi->qi_uquotaip) { IRELE(qi->qi_uquotaip); @@ -1599,132 +1740,6 @@ xfs_qm_dqfree_one( xfs_qm_dqdestroy(dqp); } -STATIC void -xfs_qm_dqreclaim_one( - struct xfs_dquot *dqp, - struct list_head *buffer_list, - struct list_head *dispose_list) -{ - struct xfs_mount *mp = dqp->q_mount; - struct xfs_quotainfo *qi = mp->m_quotainfo; - int error; - - if (!xfs_dqlock_nowait(dqp)) - goto out_move_tail; - - /* - * This dquot has acquired a reference in the meantime remove it from - * the freelist and try again. - */ - if (dqp->q_nrefs) { - xfs_dqunlock(dqp); - - trace_xfs_dqreclaim_want(dqp); - XFS_STATS_INC(xs_qm_dqwants); - - list_del_init(&dqp->q_lru); - qi->qi_lru_count--; - XFS_STATS_DEC(xs_qm_dquot_unused); - return; - } - - /* - * Try to grab the flush lock. If this dquot is in the process of - * getting flushed to disk, we don't want to reclaim it. - */ - if (!xfs_dqflock_nowait(dqp)) - goto out_unlock_move_tail; - - if (XFS_DQ_IS_DIRTY(dqp)) { - struct xfs_buf *bp = NULL; - - trace_xfs_dqreclaim_dirty(dqp); - - error = xfs_qm_dqflush(dqp, &bp); - if (error) { - xfs_warn(mp, "%s: dquot %p flush failed", - __func__, dqp); - goto out_unlock_move_tail; - } - - xfs_buf_delwri_queue(bp, buffer_list); - xfs_buf_relse(bp); - /* - * Give the dquot another try on the freelist, as the - * flushing will take some time. - */ - goto out_unlock_move_tail; - } - xfs_dqfunlock(dqp); - - /* - * Prevent lookups now that we are past the point of no return. - */ - dqp->dq_flags |= XFS_DQ_FREEING; - xfs_dqunlock(dqp); - - ASSERT(dqp->q_nrefs == 0); - list_move_tail(&dqp->q_lru, dispose_list); - qi->qi_lru_count--; - XFS_STATS_DEC(xs_qm_dquot_unused); - - trace_xfs_dqreclaim_done(dqp); - XFS_STATS_INC(xs_qm_dqreclaims); - return; - - /* - * Move the dquot to the tail of the list so that we don't spin on it. - */ -out_unlock_move_tail: - xfs_dqunlock(dqp); -out_move_tail: - list_move_tail(&dqp->q_lru, &qi->qi_lru_list); - trace_xfs_dqreclaim_busy(dqp); - XFS_STATS_INC(xs_qm_dqreclaim_misses); -} - -STATIC int -xfs_qm_shake( - struct shrinker *shrink, - struct shrink_control *sc) -{ - struct xfs_quotainfo *qi = - container_of(shrink, struct xfs_quotainfo, qi_shrinker); - int nr_to_scan = sc->nr_to_scan; - LIST_HEAD (buffer_list); - LIST_HEAD (dispose_list); - struct xfs_dquot *dqp; - int error; - - if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT)) - return 0; - if (!nr_to_scan) - goto out; - - mutex_lock(&qi->qi_lru_lock); - while (!list_empty(&qi->qi_lru_list)) { - if (nr_to_scan-- <= 0) - break; - dqp = list_first_entry(&qi->qi_lru_list, struct xfs_dquot, - q_lru); - xfs_qm_dqreclaim_one(dqp, &buffer_list, &dispose_list); - } - mutex_unlock(&qi->qi_lru_lock); - - error = xfs_buf_delwri_submit(&buffer_list); - if (error) - xfs_warn(NULL, "%s: dquot reclaim failed", __func__); - - while (!list_empty(&dispose_list)) { - dqp = list_first_entry(&dispose_list, struct xfs_dquot, q_lru); - list_del_init(&dqp->q_lru); - xfs_qm_dqfree_one(dqp); - } - -out: - return (qi->qi_lru_count / 100) * sysctl_vfs_cache_pressure; -} - /* * Start a transaction and write the incore superblock changes to * disk. flags parameter indicates which fields have changed. diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index 670cd4464070..2b602df9c242 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -49,9 +49,7 @@ typedef struct xfs_quotainfo { struct xfs_inode *qi_uquotaip; /* user quota inode */ struct xfs_inode *qi_gquotaip; /* group quota inode */ struct xfs_inode *qi_pquotaip; /* project quota inode */ - struct list_head qi_lru_list; - struct mutex qi_lru_lock; - int qi_lru_count; + struct list_lru qi_lru; int qi_dquots; time_t qi_btimelimit; /* limit for blks timer */ time_t qi_itimelimit; /* limit for inodes timer */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 979a77d4b87d..15188cc99449 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1535,19 +1535,21 @@ xfs_fs_mount( return mount_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super); } -static int +static long xfs_fs_nr_cached_objects( - struct super_block *sb) + struct super_block *sb, + int nid) { return xfs_reclaim_inodes_count(XFS_M(sb)); } -static void +static long xfs_fs_free_cached_objects( struct super_block *sb, - int nr_to_scan) + long nr_to_scan, + int nid) { - xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan); + return xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan); } static const struct super_operations xfs_super_operations = { diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 9169b91ea2d2..b3b7c74f1ed7 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -55,11 +55,11 @@ struct qstr { #define hashlen_len(hashlen) ((u32)((hashlen) >> 32)) struct dentry_stat_t { - int nr_dentry; - int nr_unused; - int age_limit; /* age in seconds */ - int want_pages; /* pages requested by system */ - int dummy[2]; + long nr_dentry; + long nr_unused; + long age_limit; /* age in seconds */ + long want_pages; /* pages requested by system */ + long dummy[2]; }; extern struct dentry_stat_t dentry_stat; @@ -393,4 +393,8 @@ static inline bool d_mountpoint(struct dentry *dentry) extern int sysctl_vfs_cache_pressure; +static inline unsigned long vfs_pressure_ratio(unsigned long val) +{ + return mult_frac(val, sysctl_vfs_cache_pressure, 100); +} #endif /* __LINUX_DCACHE_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index d607666007ea..3725d29d0255 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -10,6 +10,7 @@ #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> +#include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/rbtree.h> @@ -1361,15 +1362,6 @@ struct super_block { struct list_head s_files; #endif struct list_head s_mounts; /* list of mounts; _not_ for fs use */ - /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */ - struct list_head s_dentry_lru; /* unused dentry lru */ - int s_nr_dentry_unused; /* # of dentry on lru */ - - /* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */ - spinlock_t s_inode_lru_lock ____cacheline_aligned_in_smp; - struct list_head s_inode_lru; /* unused inode lru */ - int s_nr_inodes_unused; /* # of inodes on lru */ - struct block_device *s_bdev; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; @@ -1420,11 +1412,14 @@ struct super_block { /* Being remounted read-only */ int s_readonly_remount; -}; -/* superblock cache pruning functions */ -extern void prune_icache_sb(struct super_block *sb, int nr_to_scan); -extern void prune_dcache_sb(struct super_block *sb, int nr_to_scan); + /* + * Keep the lru lists last in the structure so they always sit on their + * own individual cachelines. + */ + struct list_lru s_dentry_lru ____cacheline_aligned_in_smp; + struct list_lru s_inode_lru ____cacheline_aligned_in_smp; +}; extern struct timespec current_fs_time(struct super_block *sb); @@ -1732,8 +1727,8 @@ struct super_operations { ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); - int (*nr_cached_objects)(struct super_block *); - void (*free_cached_objects)(struct super_block *, int); + long (*nr_cached_objects)(struct super_block *, int); + long (*free_cached_objects)(struct super_block *, long, int); }; /* diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b60de92e2edc..3935428c57cf 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -96,9 +96,6 @@ extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, unsigned long addr, unsigned long end); -extern int handle_pte_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - pte_t *pte, pmd_t *pmd, unsigned int flags); extern int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h new file mode 100644 index 000000000000..3ce541753c88 --- /dev/null +++ b/include/linux/list_lru.h @@ -0,0 +1,131 @@ +/* + * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. + * Authors: David Chinner and Glauber Costa + * + * Generic LRU infrastructure + */ +#ifndef _LRU_LIST_H +#define _LRU_LIST_H + +#include <linux/list.h> +#include <linux/nodemask.h> + +/* list_lru_walk_cb has to always return one of those */ +enum lru_status { + LRU_REMOVED, /* item removed from list */ + LRU_ROTATE, /* item referenced, give another pass */ + LRU_SKIP, /* item cannot be locked, skip */ + LRU_RETRY, /* item not freeable. May drop the lock + internally, but has to return locked. */ +}; + +struct list_lru_node { + spinlock_t lock; + struct list_head list; + /* kept as signed so we can catch imbalance bugs */ + long nr_items; +} ____cacheline_aligned_in_smp; + +struct list_lru { + struct list_lru_node *node; + nodemask_t active_nodes; +}; + +void list_lru_destroy(struct list_lru *lru); +int list_lru_init(struct list_lru *lru); + +/** + * list_lru_add: add an element to the lru list's tail + * @list_lru: the lru pointer + * @item: the item to be added. + * + * If the element is already part of a list, this function returns doing + * nothing. Therefore the caller does not need to keep state about whether or + * not the element already belongs in the list and is allowed to lazy update + * it. Note however that this is valid for *a* list, not *this* list. If + * the caller organize itself in a way that elements can be in more than + * one type of list, it is up to the caller to fully remove the item from + * the previous list (with list_lru_del() for instance) before moving it + * to @list_lru + * + * Return value: true if the list was updated, false otherwise + */ +bool list_lru_add(struct list_lru *lru, struct list_head *item); + +/** + * list_lru_del: delete an element to the lru list + * @list_lru: the lru pointer + * @item: the item to be deleted. + * + * This function works analogously as list_lru_add in terms of list + * manipulation. The comments about an element already pertaining to + * a list are also valid for list_lru_del. + * + * Return value: true if the list was updated, false otherwise + */ +bool list_lru_del(struct list_lru *lru, struct list_head *item); + +/** + * list_lru_count_node: return the number of objects currently held by @lru + * @lru: the lru pointer. + * @nid: the node id to count from. + * + * Always return a non-negative number, 0 for empty lists. There is no + * guarantee that the list is not updated while the count is being computed. + * Callers that want such a guarantee need to provide an outer lock. + */ +unsigned long list_lru_count_node(struct list_lru *lru, int nid); +static inline unsigned long list_lru_count(struct list_lru *lru) +{ + long count = 0; + int nid; + + for_each_node_mask(nid, lru->active_nodes) + count += list_lru_count_node(lru, nid); + + return count; +} + +typedef enum lru_status +(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg); +/** + * list_lru_walk_node: walk a list_lru, isolating and disposing freeable items. + * @lru: the lru pointer. + * @nid: the node id to scan from. + * @isolate: callback function that is resposible for deciding what to do with + * the item currently being scanned + * @cb_arg: opaque type that will be passed to @isolate + * @nr_to_walk: how many items to scan. + * + * This function will scan all elements in a particular list_lru, calling the + * @isolate callback for each of those items, along with the current list + * spinlock and a caller-provided opaque. The @isolate callback can choose to + * drop the lock internally, but *must* return with the lock held. The callback + * will return an enum lru_status telling the list_lru infrastructure what to + * do with the object being scanned. + * + * Please note that nr_to_walk does not mean how many objects will be freed, + * just how many objects will be scanned. + * + * Return value: the number of objects effectively removed from the LRU. + */ +unsigned long list_lru_walk_node(struct list_lru *lru, int nid, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk); + +static inline unsigned long +list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, + void *cb_arg, unsigned long nr_to_walk) +{ + long isolated = 0; + int nid; + + for_each_node_mask(nid, lru->active_nodes) { + isolated += list_lru_walk_node(lru, nid, isolate, + cb_arg, &nr_to_walk); + if (nr_to_walk <= 0) + break; + } + return isolated; +} +#endif /* _LRU_LIST_H */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6c416092e324..60e95872da29 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -30,9 +30,21 @@ struct page; struct mm_struct; struct kmem_cache; -/* Stats that can be updated by kernel. */ -enum mem_cgroup_page_stat_item { - MEMCG_NR_FILE_MAPPED, /* # of pages charged as file rss */ +/* + * The corresponding mem_cgroup_stat_names is defined in mm/memcontrol.c, + * These two lists should keep in accord with each other. + */ +enum mem_cgroup_stat_index { + /* + * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss. + */ + MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ + MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ + MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */ + MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ + MEM_CGROUP_STAT_WRITEBACK, /* # of pages under writeback */ + MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ + MEM_CGROUP_STAT_NSTATS, }; struct mem_cgroup_reclaim_cookie { @@ -41,6 +53,23 @@ struct mem_cgroup_reclaim_cookie { unsigned int generation; }; +enum mem_cgroup_filter_t { + VISIT, /* visit current node */ + SKIP, /* skip the current node and continue traversal */ + SKIP_TREE, /* skip the whole subtree and continue traversal */ +}; + +/* + * mem_cgroup_filter_t predicate might instruct mem_cgroup_iter_cond how to + * iterate through the hierarchy tree. Each tree element is checked by the + * predicate before it is returned by the iterator. If a filter returns + * SKIP or SKIP_TREE then the iterator code continues traversal (with the + * next node down the hierarchy or the next node that doesn't belong under the + * memcg's subtree). + */ +typedef enum mem_cgroup_filter_t +(*mem_cgroup_iter_filter)(struct mem_cgroup *memcg, struct mem_cgroup *root); + #ifdef CONFIG_MEMCG /* * All "charge" functions with gfp_mask should use GFP_KERNEL or @@ -108,9 +137,18 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage, extern void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok); -struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, - struct mem_cgroup *, - struct mem_cgroup_reclaim_cookie *); +struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, + struct mem_cgroup *prev, + struct mem_cgroup_reclaim_cookie *reclaim, + mem_cgroup_iter_filter cond); + +static inline struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, + struct mem_cgroup *prev, + struct mem_cgroup_reclaim_cookie *reclaim) +{ + return mem_cgroup_iter_cond(root, prev, reclaim, NULL); +} + void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); /* @@ -125,6 +163,48 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, extern void mem_cgroup_replace_page_cache(struct page *oldpage, struct page *newpage); +/** + * mem_cgroup_toggle_oom - toggle the memcg OOM killer for the current task + * @new: true to enable, false to disable + * + * Toggle whether a failed memcg charge should invoke the OOM killer + * or just return -ENOMEM. Returns the previous toggle state. + * + * NOTE: Any path that enables the OOM killer before charging must + * call mem_cgroup_oom_synchronize() afterward to finalize the + * OOM handling and clean up. + */ +static inline bool mem_cgroup_toggle_oom(bool new) +{ + bool old; + + old = current->memcg_oom.may_oom; + current->memcg_oom.may_oom = new; + + return old; +} + +static inline void mem_cgroup_enable_oom(void) +{ + bool old = mem_cgroup_toggle_oom(true); + + WARN_ON(old == true); +} + +static inline void mem_cgroup_disable_oom(void) +{ + bool old = mem_cgroup_toggle_oom(false); + + WARN_ON(old == false); +} + +static inline bool task_in_memcg_oom(struct task_struct *p) +{ + return p->memcg_oom.in_memcg_oom; +} + +bool mem_cgroup_oom_synchronize(void); + #ifdef CONFIG_MEMCG_SWAP extern int do_swap_account; #endif @@ -165,24 +245,24 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page, } void mem_cgroup_update_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx, + enum mem_cgroup_stat_index idx, int val); static inline void mem_cgroup_inc_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx) + enum mem_cgroup_stat_index idx) { mem_cgroup_update_page_stat(page, idx, 1); } static inline void mem_cgroup_dec_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx) + enum mem_cgroup_stat_index idx) { mem_cgroup_update_page_stat(page, idx, -1); } -unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, - gfp_t gfp_mask, - unsigned long *total_scanned); +enum mem_cgroup_filter_t +mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, + struct mem_cgroup *root); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, @@ -296,6 +376,15 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok) { } +static inline struct mem_cgroup * +mem_cgroup_iter_cond(struct mem_cgroup *root, + struct mem_cgroup *prev, + struct mem_cgroup_reclaim_cookie *reclaim, + mem_cgroup_iter_filter cond) +{ + /* first call must return non-NULL, second return NULL */ + return (struct mem_cgroup *)(unsigned long)!prev; +} static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, @@ -348,22 +437,45 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page, { } +static inline bool mem_cgroup_toggle_oom(bool new) +{ + return false; +} + +static inline void mem_cgroup_enable_oom(void) +{ +} + +static inline void mem_cgroup_disable_oom(void) +{ +} + +static inline bool task_in_memcg_oom(struct task_struct *p) +{ + return false; +} + +static inline bool mem_cgroup_oom_synchronize(void) +{ + return false; +} + static inline void mem_cgroup_inc_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx) + enum mem_cgroup_stat_index idx) { } static inline void mem_cgroup_dec_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx) + enum mem_cgroup_stat_index idx) { } static inline -unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, - gfp_t gfp_mask, - unsigned long *total_scanned) +enum mem_cgroup_filter_t +mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, + struct mem_cgroup *root) { - return 0; + return VISIT; } static inline void mem_cgroup_split_huge_fixup(struct page *head) diff --git a/include/linux/mm.h b/include/linux/mm.h index a77f10f256e8..e9bab9cfe09d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -176,6 +176,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */ #define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */ #define FAULT_FLAG_TRIED 0x40 /* second try */ +#define FAULT_FLAG_USER 0x80 /* The fault originated in userspace */ /* * vm_fault is filled by the the pagefault handler and passed to the vma's @@ -876,11 +877,12 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ #define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */ +#define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */ #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \ - VM_FAULT_HWPOISON_LARGE) + VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE) /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((x) << 12) @@ -984,7 +986,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, unmap_mapping_range(mapping, holebegin, holelen, 0); } -extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new); +extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 96a509b6be04..201a69749659 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -54,7 +54,7 @@ struct res_counter { struct res_counter *parent; }; -#define RESOURCE_MAX (unsigned long long)LLONG_MAX +#define RES_COUNTER_MAX ULLONG_MAX /** * Helpers to interact with userspace diff --git a/include/linux/sched.h b/include/linux/sched.h index 45f254dddafc..6682da36b293 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1393,6 +1393,13 @@ struct task_struct { unsigned long memsw_nr_pages; /* uncharged mem+swap usage */ } memcg_batch; unsigned int memcg_kmem_skip_account; + struct memcg_oom_info { + unsigned int may_oom:1; + unsigned int in_memcg_oom:1; + unsigned int oom_locked:1; + int wakeups; + struct mem_cgroup *wait_on_memcg; + } memcg_oom; #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index ac6b8ee07825..68c097077ef0 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -4,39 +4,67 @@ /* * This struct is used to pass information from page reclaim to the shrinkers. * We consolidate the values for easier extention later. + * + * The 'gfpmask' refers to the allocation we are currently trying to + * fulfil. */ struct shrink_control { gfp_t gfp_mask; - /* How many slab objects shrinker() should scan and try to reclaim */ + /* + * How many objects scan_objects should scan and try to reclaim. + * This is reset before every call, so it is safe for callees + * to modify. + */ unsigned long nr_to_scan; + + /* shrink from these nodes */ + nodemask_t nodes_to_scan; + /* current node being shrunk (for NUMA aware shrinkers) */ + int nid; }; +#define SHRINK_STOP (~0UL) /* * A callback you can register to apply pressure to ageable caches. * - * 'sc' is passed shrink_control which includes a count 'nr_to_scan' - * and a 'gfpmask'. It should look through the least-recently-used - * 'nr_to_scan' entries and attempt to free them up. It should return - * the number of objects which remain in the cache. If it returns -1, it means - * it cannot do any scanning at this time (eg. there is a risk of deadlock). + * @count_objects should return the number of freeable items in the cache. If + * there are no objects to free or the number of freeable items cannot be + * determined, it should return 0. No deadlock checks should be done during the + * count callback - the shrinker relies on aggregating scan counts that couldn't + * be executed due to potential deadlocks to be run at a later call when the + * deadlock condition is no longer pending. * - * The 'gfpmask' refers to the allocation we are currently trying to - * fulfil. + * @scan_objects will only be called if @count_objects returned a non-zero + * value for the number of freeable objects. The callout should scan the cache + * and attempt to free items from the cache. It should then return the number + * of objects freed during the scan, or SHRINK_STOP if progress cannot be made + * due to potential deadlocks. If SHRINK_STOP is returned, then no further + * attempts to call the @scan_objects will be made from the current reclaim + * context. * - * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is - * querying the cache size, so a fastpath for that case is appropriate. + * @flags determine the shrinker abilities, like numa awareness */ struct shrinker { - int (*shrink)(struct shrinker *, struct shrink_control *sc); + unsigned long (*count_objects)(struct shrinker *, + struct shrink_control *sc); + unsigned long (*scan_objects)(struct shrinker *, + struct shrink_control *sc); + int seeks; /* seeks to recreate an obj */ long batch; /* reclaim batch size, 0 = default */ + unsigned long flags; /* These are for internal use */ struct list_head list; - atomic_long_t nr_in_batch; /* objs pending delete */ + /* objs pending delete, per node */ + atomic_long_t *nr_deferred; }; #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ -extern void register_shrinker(struct shrinker *); + +/* Flags */ +#define SHRINKER_NUMA_AWARE (1 << 0) + +extern int register_shrinker(struct shrinker *); extern void unregister_shrinker(struct shrinker *); #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index c03c139219c9..46ba0c6c219f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -280,7 +280,7 @@ extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); -extern int lru_add_drain_all(void); +extern void lru_add_drain_all(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_page(struct page *page); extern void swap_setup(void); diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 63cfcccaebb3..132a985aba8b 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -202,7 +202,7 @@ TRACE_EVENT(mm_shrink_slab_start, TP_fast_assign( __entry->shr = shr; - __entry->shrink = shr->shrink; + __entry->shrink = shr->scan_objects; __entry->nr_objects_to_shrink = nr_objects_to_shrink; __entry->gfp_flags = sc->gfp_mask; __entry->pgs_scanned = pgs_scanned; @@ -241,7 +241,7 @@ TRACE_EVENT(mm_shrink_slab_end, TP_fast_assign( __entry->shr = shr; - __entry->shrink = shr->shrink; + __entry->shrink = shr->scan_objects; __entry->unused_scan = unused_scan_cnt; __entry->new_scan = new_scan_cnt; __entry->retval = shrinker_retval; diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index a4ed56cf0eac..6c28b61bb690 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -49,9 +49,9 @@ struct files_stat_struct { }; struct inodes_stat_t { - int nr_inodes; - int nr_unused; - int dummy[5]; /* padding for sysctl ABI compatibility */ + long nr_inodes; + long nr_unused; + long dummy[5]; /* padding for sysctl ABI compatibility */ }; diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c index 9bd0934f6c33..7a7d2ee96d42 100644 --- a/kernel/gcov/fs.c +++ b/kernel/gcov/fs.c @@ -74,7 +74,7 @@ static int __init gcov_persist_setup(char *str) { unsigned long val; - if (strict_strtoul(str, 0, &val)) { + if (kstrtoul(str, 0, &val)) { pr_warning("invalid gcov_persist parameter '%s'\n", str); return 0; } diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 6ada93c23a9a..9659d38e008f 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -113,7 +113,7 @@ static ssize_t kexec_crash_size_store(struct kobject *kobj, unsigned long cnt; int ret; - if (strict_strtoul(buf, 0, &cnt)) + if (kstrtoul(buf, 0, &cnt)) return -EINVAL; ret = crash_shrink_memory(cnt); diff --git a/kernel/params.c b/kernel/params.c index 501bde4f3bee..81c4e78c8f4c 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -253,13 +253,13 @@ int parse_args(const char *doing, EXPORT_SYMBOL(param_ops_##name) -STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, strict_strtoul); -STANDARD_PARAM_DEF(short, short, "%hi", long, strict_strtol); -STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, strict_strtoul); -STANDARD_PARAM_DEF(int, int, "%i", long, strict_strtol); -STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, strict_strtoul); -STANDARD_PARAM_DEF(long, long, "%li", long, strict_strtol); -STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, strict_strtoul); +STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul); +STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtoul); +STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul); +STANDARD_PARAM_DEF(int, int, "%i", long, kstrtoul); +STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul); +STANDARD_PARAM_DEF(long, long, "%li", long, kstrtoul); +STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul); int param_set_charp(const char *val, const struct kernel_param *kp) { diff --git a/kernel/res_counter.c b/kernel/res_counter.c index ff55247e7049..4aa8a305aede 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -17,8 +17,8 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent) { spin_lock_init(&counter->lock); - counter->limit = RESOURCE_MAX; - counter->soft_limit = RESOURCE_MAX; + counter->limit = RES_COUNTER_MAX; + counter->soft_limit = RES_COUNTER_MAX; counter->parent = parent; } @@ -178,23 +178,30 @@ u64 res_counter_read_u64(struct res_counter *counter, int member) #endif int res_counter_memparse_write_strategy(const char *buf, - unsigned long long *res) + unsigned long long *resp) { char *end; + unsigned long long res; - /* return RESOURCE_MAX(unlimited) if "-1" is specified */ + /* return RES_COUNTER_MAX(unlimited) if "-1" is specified */ if (*buf == '-') { - *res = simple_strtoull(buf + 1, &end, 10); - if (*res != 1 || *end != '\0') + res = simple_strtoull(buf + 1, &end, 10); + if (res != 1 || *end != '\0') return -EINVAL; - *res = RESOURCE_MAX; + *resp = RES_COUNTER_MAX; return 0; } - *res = memparse(buf, &end); + res = memparse(buf, &end); if (*end != '\0') return -EINVAL; - *res = PAGE_ALIGN(*res); + if (PAGE_ALIGN(res) >= res) + res = PAGE_ALIGN(res); + else + res = RES_COUNTER_MAX; + + *resp = res; + return 0; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index dc69093a8ec4..b2f06f3c6a3f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1471,14 +1471,14 @@ static struct ctl_table fs_table[] = { { .procname = "inode-nr", .data = &inodes_stat, - .maxlen = 2*sizeof(int), + .maxlen = 2*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, { .procname = "inode-state", .data = &inodes_stat, - .maxlen = 7*sizeof(int), + .maxlen = 7*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, @@ -1508,7 +1508,7 @@ static struct ctl_table fs_table[] = { { .procname = "dentry-state", .data = &dentry_stat, - .maxlen = 6*sizeof(int), + .maxlen = 6*sizeof(long), .mode = 0444, .proc_handler = proc_nr_dentry, }, diff --git a/mm/Kconfig b/mm/Kconfig index 6cdd27043303..026771a9b097 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -245,7 +245,7 @@ config COMPACTION config MIGRATION bool "Page migration" def_bool y - depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA + depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU help Allows the migration of the physical location of pages of processes while the virtual addresses are not changed. This is useful in @@ -480,7 +480,7 @@ config FRONTSWAP config CMA bool "Contiguous Memory Allocator" - depends on HAVE_MEMBLOCK + depends on HAVE_MEMBLOCK && MMU select MIGRATION select MEMORY_ISOLATION help diff --git a/mm/Makefile b/mm/Makefile index f00803386a67..305d10acd081 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -17,7 +17,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o balloon_compaction.o \ - interval_tree.o $(mmu-y) + interval_tree.o list_lru.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/filemap.c b/mm/filemap.c index 7c1f81649db8..e85684793852 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -467,32 +467,34 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, error = mem_cgroup_cache_charge(page, current->mm, gfp_mask & GFP_RECLAIM_MASK); if (error) - goto out; + return error; error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM); - if (error == 0) { - page_cache_get(page); - page->mapping = mapping; - page->index = offset; - - spin_lock_irq(&mapping->tree_lock); - error = radix_tree_insert(&mapping->page_tree, offset, page); - if (likely(!error)) { - mapping->nrpages++; - __inc_zone_page_state(page, NR_FILE_PAGES); - spin_unlock_irq(&mapping->tree_lock); - trace_mm_filemap_add_to_page_cache(page); - } else { - page->mapping = NULL; - /* Leave page->index set: truncation relies upon it */ - spin_unlock_irq(&mapping->tree_lock); - mem_cgroup_uncharge_cache_page(page); - page_cache_release(page); - } - radix_tree_preload_end(); - } else + if (error) { mem_cgroup_uncharge_cache_page(page); -out: + return error; + } + + page_cache_get(page); + page->mapping = mapping; + page->index = offset; + + spin_lock_irq(&mapping->tree_lock); + error = radix_tree_insert(&mapping->page_tree, offset, page); + radix_tree_preload_end(); + if (unlikely(error)) + goto err_insert; + mapping->nrpages++; + __inc_zone_page_state(page, NR_FILE_PAGES); + spin_unlock_irq(&mapping->tree_lock); + trace_mm_filemap_add_to_page_cache(page); + return 0; +err_insert: + page->mapping = NULL; + /* Leave page->index set: truncation relies upon it */ + spin_unlock_irq(&mapping->tree_lock); + mem_cgroup_uncharge_cache_page(page); + page_cache_release(page); return error; } EXPORT_SYMBOL(add_to_page_cache_locked); @@ -1090,7 +1092,6 @@ static void shrink_readahead_size_eio(struct file *filp, * @filp: the file to read * @ppos: current file position * @desc: read_descriptor - * @actor: read method * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. @@ -1099,7 +1100,7 @@ static void shrink_readahead_size_eio(struct file *filp, * of the logic when it comes to error handling etc. */ static void do_generic_file_read(struct file *filp, loff_t *ppos, - read_descriptor_t *desc, read_actor_t actor) + read_descriptor_t *desc) { struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; @@ -1200,13 +1201,14 @@ page_ok: * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... * - * The actor routine returns how many bytes were actually used.. + * The file_read_actor routine returns how many bytes were + * actually used.. * NOTE! This may not be the same as how much of a user buffer * we filled up (we may be padding etc), so we can only update * "pos" here (the actor routine has to update the user buffer * pointers and the remaining count). */ - ret = actor(desc, page, offset, nr); + ret = file_read_iter_actor(desc, page, offset, nr); offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; @@ -1430,7 +1432,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) desc.arg.data = iter; desc.count = count; desc.error = 0; - do_generic_file_read(filp, ppos, &desc, file_read_iter_actor); + do_generic_file_read(filp, ppos, &desc); if (desc.written) retval = desc.written; else @@ -1592,6 +1594,7 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct inode *inode = mapping->host; pgoff_t offset = vmf->pgoff; struct page *page; + bool memcg_oom; pgoff_t size; int ret = 0; @@ -1600,7 +1603,11 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return VM_FAULT_SIGBUS; /* - * Do we have something in the page cache already? + * Do we have something in the page cache already? Either + * way, try readahead, but disable the memcg OOM killer for it + * as readahead is optional and no errors are propagated up + * the fault stack. The OOM killer is enabled while trying to + * instantiate the faulting page individually below. */ page = find_get_page(mapping, offset); if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) { @@ -1608,10 +1615,14 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) * We found the page, so try async readahead before * waiting for the lock. */ + memcg_oom = mem_cgroup_toggle_oom(false); do_async_mmap_readahead(vma, ra, file, page, offset); + mem_cgroup_toggle_oom(memcg_oom); } else if (!page) { /* No page in the page cache at all */ + memcg_oom = mem_cgroup_toggle_oom(false); do_sync_mmap_readahead(vma, ra, file, offset); + mem_cgroup_toggle_oom(memcg_oom); count_vm_event(PGMAJFAULT); mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 963e14c0486f..7489884682d8 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -211,24 +211,29 @@ static void put_huge_zero_page(void) BUG_ON(atomic_dec_and_test(&huge_zero_refcount)); } -static int shrink_huge_zero_page(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink, + struct shrink_control *sc) { - if (!sc->nr_to_scan) - /* we can free zero page only if last reference remains */ - return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; + /* we can free zero page only if last reference remains */ + return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; +} +static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); __free_page(zero_page); + return HPAGE_PMD_NR; } return 0; } static struct shrinker huge_zero_page_shrinker = { - .shrink = shrink_huge_zero_page, + .count_objects = shrink_huge_zero_page_count, + .scan_objects = shrink_huge_zero_page_scan, .seeks = DEFAULT_SEEKS, }; @@ -690,11 +695,10 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) return pmd; } -static inline pmd_t mk_huge_pmd(struct page *page, struct vm_area_struct *vma) +static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot) { pmd_t entry; - entry = mk_pmd(page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + entry = mk_pmd(page, prot); entry = pmd_mkhuge(entry); return entry; } @@ -727,7 +731,8 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, pte_free(mm, pgtable); } else { pmd_t entry; - entry = mk_huge_pmd(page, vma); + entry = mk_huge_pmd(page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); page_add_new_anon_rmap(page, vma, haddr); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); @@ -783,77 +788,57 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, { struct page *page; unsigned long haddr = address & HPAGE_PMD_MASK; - pte_t *pte; - if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) { - if (unlikely(anon_vma_prepare(vma))) - return VM_FAULT_OOM; - if (unlikely(khugepaged_enter(vma))) + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) + return VM_FAULT_FALLBACK; + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; + if (unlikely(khugepaged_enter(vma))) + return VM_FAULT_OOM; + if (!(flags & FAULT_FLAG_WRITE) && + transparent_hugepage_use_zero_page()) { + pgtable_t pgtable; + struct page *zero_page; + bool set; + pgtable = pte_alloc_one(mm, haddr); + if (unlikely(!pgtable)) return VM_FAULT_OOM; - if (!(flags & FAULT_FLAG_WRITE) && - transparent_hugepage_use_zero_page()) { - pgtable_t pgtable; - struct page *zero_page; - bool set; - pgtable = pte_alloc_one(mm, haddr); - if (unlikely(!pgtable)) - return VM_FAULT_OOM; - zero_page = get_huge_zero_page(); - if (unlikely(!zero_page)) { - pte_free(mm, pgtable); - count_vm_event(THP_FAULT_FALLBACK); - goto out; - } - spin_lock(&mm->page_table_lock); - set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd, - zero_page); - spin_unlock(&mm->page_table_lock); - if (!set) { - pte_free(mm, pgtable); - put_huge_zero_page(); - } - return 0; - } - page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr, numa_node_id(), 0); - if (unlikely(!page)) { + zero_page = get_huge_zero_page(); + if (unlikely(!zero_page)) { + pte_free(mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); - goto out; + return VM_FAULT_FALLBACK; } - count_vm_event(THP_FAULT_ALLOC); - if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { - put_page(page); - goto out; - } - if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, - page))) { - mem_cgroup_uncharge_page(page); - put_page(page); - goto out; + spin_lock(&mm->page_table_lock); + set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd, + zero_page); + spin_unlock(&mm->page_table_lock); + if (!set) { + pte_free(mm, pgtable); + put_huge_zero_page(); } - return 0; } -out: - /* - * Use __pte_alloc instead of pte_alloc_map, because we can't - * run pte_offset_map on the pmd, if an huge pmd could - * materialize from under us from a different thread. - */ - if (unlikely(pmd_none(*pmd)) && - unlikely(__pte_alloc(mm, vma, pmd, address))) - return VM_FAULT_OOM; - /* if an huge pmd materialized from under us just retry later */ - if (unlikely(pmd_trans_huge(*pmd))) - return 0; - /* - * A regular pmd is established and it can't morph into a huge pmd - * from under us anymore at this point because we hold the mmap_sem - * read mode and khugepaged takes it in write mode. So now it's - * safe to run pte_offset_map(). - */ - pte = pte_offset_map(pmd, address); - return handle_pte_fault(mm, vma, address, pte, pmd, flags); + page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), + vma, haddr, numa_node_id(), 0); + if (unlikely(!page)) { + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { + put_page(page); + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) { + mem_cgroup_uncharge_page(page); + put_page(page); + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + + count_vm_event(THP_FAULT_ALLOC); + return 0; } int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, @@ -1165,7 +1150,6 @@ alloc: new_page = NULL; if (unlikely(!new_page)) { - count_vm_event(THP_FAULT_FALLBACK); if (is_huge_zero_pmd(orig_pmd)) { ret = do_huge_pmd_wp_zero_page_fallback(mm, vma, address, pmd, orig_pmd, haddr); @@ -1176,9 +1160,9 @@ alloc: split_huge_page(page); put_page(page); } + count_vm_event(THP_FAULT_FALLBACK); goto out; } - count_vm_event(THP_FAULT_ALLOC); if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { put_page(new_page); @@ -1186,10 +1170,13 @@ alloc: split_huge_page(page); put_page(page); } + count_vm_event(THP_FAULT_FALLBACK); ret |= VM_FAULT_OOM; goto out; } + count_vm_event(THP_FAULT_ALLOC); + if (is_huge_zero_pmd(orig_pmd)) clear_huge_page(new_page, haddr, HPAGE_PMD_NR); else @@ -1210,7 +1197,8 @@ alloc: goto out_mn; } else { pmd_t entry; - entry = mk_huge_pmd(new_page, vma); + entry = mk_huge_pmd(new_page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); pmdp_clear_flush(vma, haddr, pmd); page_add_new_anon_rmap(new_page, vma, haddr); set_pmd_at(mm, haddr, pmd, entry); @@ -1661,7 +1649,6 @@ static void __split_huge_page_refcount(struct page *page, BUG_ON(atomic_read(&page->_count) <= 0); __mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1); - __mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR); ClearPageCompound(page); compound_unlock(page); @@ -2359,7 +2346,8 @@ static void collapse_huge_page(struct mm_struct *mm, __SetPageUptodate(new_page); pgtable = pmd_pgtable(_pmd); - _pmd = mk_huge_pmd(new_page, vma); + _pmd = mk_huge_pmd(new_page, vma->vm_page_prot); + _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); /* * spin_lock() below is not the equivalent of smp_wmb(), so diff --git a/mm/list_lru.c b/mm/list_lru.c new file mode 100644 index 000000000000..72467914b856 --- /dev/null +++ b/mm/list_lru.c @@ -0,0 +1,139 @@ +/* + * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. + * Authors: David Chinner and Glauber Costa + * + * Generic LRU infrastructure + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/list_lru.h> +#include <linux/slab.h> + +bool list_lru_add(struct list_lru *lru, struct list_head *item) +{ + int nid = page_to_nid(virt_to_page(item)); + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); + WARN_ON_ONCE(nlru->nr_items < 0); + if (list_empty(item)) { + list_add_tail(item, &nlru->list); + if (nlru->nr_items++ == 0) + node_set(nid, lru->active_nodes); + spin_unlock(&nlru->lock); + return true; + } + spin_unlock(&nlru->lock); + return false; +} +EXPORT_SYMBOL_GPL(list_lru_add); + +bool list_lru_del(struct list_lru *lru, struct list_head *item) +{ + int nid = page_to_nid(virt_to_page(item)); + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); + if (!list_empty(item)) { + list_del_init(item); + if (--nlru->nr_items == 0) + node_clear(nid, lru->active_nodes); + WARN_ON_ONCE(nlru->nr_items < 0); + spin_unlock(&nlru->lock); + return true; + } + spin_unlock(&nlru->lock); + return false; +} +EXPORT_SYMBOL_GPL(list_lru_del); + +unsigned long +list_lru_count_node(struct list_lru *lru, int nid) +{ + unsigned long count = 0; + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); + WARN_ON_ONCE(nlru->nr_items < 0); + count += nlru->nr_items; + spin_unlock(&nlru->lock); + + return count; +} +EXPORT_SYMBOL_GPL(list_lru_count_node); + +unsigned long +list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, + void *cb_arg, unsigned long *nr_to_walk) +{ + + struct list_lru_node *nlru = &lru->node[nid]; + struct list_head *item, *n; + unsigned long isolated = 0; + + spin_lock(&nlru->lock); +restart: + list_for_each_safe(item, n, &nlru->list) { + enum lru_status ret; + + /* + * decrement nr_to_walk first so that we don't livelock if we + * get stuck on large numbesr of LRU_RETRY items + */ + if (--(*nr_to_walk) == 0) + break; + + ret = isolate(item, &nlru->lock, cb_arg); + switch (ret) { + case LRU_REMOVED: + if (--nlru->nr_items == 0) + node_clear(nid, lru->active_nodes); + WARN_ON_ONCE(nlru->nr_items < 0); + isolated++; + break; + case LRU_ROTATE: + list_move_tail(item, &nlru->list); + break; + case LRU_SKIP: + break; + case LRU_RETRY: + /* + * The lru lock has been dropped, our list traversal is + * now invalid and so we have to restart from scratch. + */ + goto restart; + default: + BUG(); + } + } + + spin_unlock(&nlru->lock); + return isolated; +} +EXPORT_SYMBOL_GPL(list_lru_walk_node); + +int list_lru_init(struct list_lru *lru) +{ + int i; + size_t size = sizeof(*lru->node) * nr_node_ids; + + lru->node = kzalloc(size, GFP_KERNEL); + if (!lru->node) + return -ENOMEM; + + nodes_clear(lru->active_nodes); + for (i = 0; i < nr_node_ids; i++) { + spin_lock_init(&lru->node[i].lock); + INIT_LIST_HEAD(&lru->node[i].list); + lru->node[i].nr_items = 0; + } + return 0; +} +EXPORT_SYMBOL_GPL(list_lru_init); + +void list_lru_destroy(struct list_lru *lru) +{ + kfree(lru->node); +} +EXPORT_SYMBOL_GPL(list_lru_destroy); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5ca1dcf77ce9..1660da68d0f2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -39,7 +39,6 @@ #include <linux/limits.h> #include <linux/export.h> #include <linux/mutex.h> -#include <linux/rbtree.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/swapops.h> @@ -85,26 +84,12 @@ static int really_do_swap_account __initdata = 0; #endif -/* - * Statistics for memory cgroup. - */ -enum mem_cgroup_stat_index { - /* - * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss. - */ - MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ - MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ - MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */ - MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ - MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ - MEM_CGROUP_STAT_NSTATS, -}; - static const char * const mem_cgroup_stat_names[] = { "cache", "rss", "rss_huge", "mapped_file", + "writeback", "swap", }; @@ -175,10 +160,6 @@ struct mem_cgroup_per_zone { struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1]; - struct rb_node tree_node; /* RB tree node */ - unsigned long long usage_in_excess;/* Set to the value by which */ - /* the soft limit is exceeded*/ - bool on_tree; struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; @@ -187,26 +168,6 @@ struct mem_cgroup_per_node { struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; }; -/* - * Cgroups above their limits are maintained in a RB-Tree, independent of - * their hierarchy representation - */ - -struct mem_cgroup_tree_per_zone { - struct rb_root rb_root; - spinlock_t lock; -}; - -struct mem_cgroup_tree_per_node { - struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES]; -}; - -struct mem_cgroup_tree { - struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; -}; - -static struct mem_cgroup_tree soft_limit_tree __read_mostly; - struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; u64 threshold; @@ -280,6 +241,7 @@ struct mem_cgroup { bool oom_lock; atomic_t under_oom; + atomic_t oom_wakeups; int swappiness; /* OOM-Killer disable */ @@ -304,7 +266,7 @@ struct mem_cgroup { * Should we move charges of a task when a task is moved into this * mem_cgroup ? And what type of charges should we move ? */ - unsigned long move_charge_at_immigrate; + unsigned long move_charge_at_immigrate; /* * set > 0 if pages under this cgroup are moving to other cgroup. */ @@ -341,6 +303,22 @@ struct mem_cgroup { atomic_t numainfo_events; atomic_t numainfo_updating; #endif + /* + * Protects soft_contributed transitions. + * See mem_cgroup_update_soft_limit + */ + spinlock_t soft_lock; + + /* + * If true then this group has increased parents' children_in_excess + * when it got over the soft limit. + * When a group falls bellow the soft limit, parents' children_in_excess + * is decreased and soft_contributed changed to false. + */ + bool soft_contributed; + + /* Number of children that are in soft limit excess */ + atomic_t children_in_excess; struct mem_cgroup_per_node *nodeinfo[0]; /* WARNING: nodeinfo must be the last member here */ @@ -444,7 +422,6 @@ static bool move_file(void) * limit reclaim to prevent infinite loops, if they ever occur. */ #define MEM_CGROUP_MAX_RECLAIM_LOOPS 100 -#define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2 enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, @@ -671,164 +648,6 @@ page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page) return mem_cgroup_zoneinfo(memcg, nid, zid); } -static struct mem_cgroup_tree_per_zone * -soft_limit_tree_node_zone(int nid, int zid) -{ - return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; -} - -static struct mem_cgroup_tree_per_zone * -soft_limit_tree_from_page(struct page *page) -{ - int nid = page_to_nid(page); - int zid = page_zonenum(page); - - return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; -} - -static void -__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz, - unsigned long long new_usage_in_excess) -{ - struct rb_node **p = &mctz->rb_root.rb_node; - struct rb_node *parent = NULL; - struct mem_cgroup_per_zone *mz_node; - - if (mz->on_tree) - return; - - mz->usage_in_excess = new_usage_in_excess; - if (!mz->usage_in_excess) - return; - while (*p) { - parent = *p; - mz_node = rb_entry(parent, struct mem_cgroup_per_zone, - tree_node); - if (mz->usage_in_excess < mz_node->usage_in_excess) - p = &(*p)->rb_left; - /* - * We can't avoid mem cgroups that are over their soft - * limit by the same amount - */ - else if (mz->usage_in_excess >= mz_node->usage_in_excess) - p = &(*p)->rb_right; - } - rb_link_node(&mz->tree_node, parent, p); - rb_insert_color(&mz->tree_node, &mctz->rb_root); - mz->on_tree = true; -} - -static void -__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) -{ - if (!mz->on_tree) - return; - rb_erase(&mz->tree_node, &mctz->rb_root); - mz->on_tree = false; -} - -static void -mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) -{ - spin_lock(&mctz->lock); - __mem_cgroup_remove_exceeded(memcg, mz, mctz); - spin_unlock(&mctz->lock); -} - - -static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) -{ - unsigned long long excess; - struct mem_cgroup_per_zone *mz; - struct mem_cgroup_tree_per_zone *mctz; - int nid = page_to_nid(page); - int zid = page_zonenum(page); - mctz = soft_limit_tree_from_page(page); - - /* - * Necessary to update all ancestors when hierarchy is used. - * because their event counter is not touched. - */ - for (; memcg; memcg = parent_mem_cgroup(memcg)) { - mz = mem_cgroup_zoneinfo(memcg, nid, zid); - excess = res_counter_soft_limit_excess(&memcg->res); - /* - * We have to update the tree if mz is on RB-tree or - * mem is over its softlimit. - */ - if (excess || mz->on_tree) { - spin_lock(&mctz->lock); - /* if on-tree, remove it */ - if (mz->on_tree) - __mem_cgroup_remove_exceeded(memcg, mz, mctz); - /* - * Insert again. mz->usage_in_excess will be updated. - * If excess is 0, no tree ops. - */ - __mem_cgroup_insert_exceeded(memcg, mz, mctz, excess); - spin_unlock(&mctz->lock); - } - } -} - -static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) -{ - int node, zone; - struct mem_cgroup_per_zone *mz; - struct mem_cgroup_tree_per_zone *mctz; - - for_each_node(node) { - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - mz = mem_cgroup_zoneinfo(memcg, node, zone); - mctz = soft_limit_tree_node_zone(node, zone); - mem_cgroup_remove_exceeded(memcg, mz, mctz); - } - } -} - -static struct mem_cgroup_per_zone * -__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) -{ - struct rb_node *rightmost = NULL; - struct mem_cgroup_per_zone *mz; - -retry: - mz = NULL; - rightmost = rb_last(&mctz->rb_root); - if (!rightmost) - goto done; /* Nothing to reclaim from */ - - mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node); - /* - * Remove the node now but someone else can add it back, - * we will to add it back at the end of reclaim to its correct - * position in the tree. - */ - __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); - if (!res_counter_soft_limit_excess(&mz->memcg->res) || - !css_tryget(&mz->memcg->css)) - goto retry; -done: - return mz; -} - -static struct mem_cgroup_per_zone * -mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) -{ - struct mem_cgroup_per_zone *mz; - - spin_lock(&mctz->lock); - mz = __mem_cgroup_largest_soft_limit_node(mctz); - spin_unlock(&mctz->lock); - return mz; -} - /* * Implementation Note: reading percpu statistics for memcg. * @@ -1003,6 +822,48 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, } /* + * Called from rate-limited memcg_check_events when enough + * MEM_CGROUP_TARGET_SOFTLIMIT events are accumulated and it makes sure + * that all the parents up the hierarchy will be notified that this group + * is in excess or that it is not in excess anymore. mmecg->soft_contributed + * makes the transition a single action whenever the state flips from one to + * the other. + */ +static void mem_cgroup_update_soft_limit(struct mem_cgroup *memcg) +{ + unsigned long long excess = res_counter_soft_limit_excess(&memcg->res); + struct mem_cgroup *parent = memcg; + int delta = 0; + + spin_lock(&memcg->soft_lock); + if (excess) { + if (!memcg->soft_contributed) { + delta = 1; + memcg->soft_contributed = true; + } + } else { + if (memcg->soft_contributed) { + delta = -1; + memcg->soft_contributed = false; + } + } + + /* + * Necessary to update all ancestors when hierarchy is used + * because their event counter is not touched. + * We track children even outside the hierarchy for the root + * cgroup because tree walk starting at root should visit + * all cgroups and we want to prevent from pointless tree + * walk if no children is below the limit. + */ + while (delta && (parent = parent_mem_cgroup(parent))) + atomic_add(delta, &parent->children_in_excess); + if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy) + atomic_add(delta, &root_mem_cgroup->children_in_excess); + spin_unlock(&memcg->soft_lock); +} + +/* * Check events in order. * */ @@ -1025,7 +886,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) mem_cgroup_threshold(memcg); if (unlikely(do_softlimit)) - mem_cgroup_update_tree(memcg, page); + mem_cgroup_update_soft_limit(memcg); #if MAX_NUMNODES > 1 if (unlikely(do_numainfo)) atomic_inc(&memcg->numainfo_events); @@ -1068,6 +929,15 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) return memcg; } +static enum mem_cgroup_filter_t +mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root, + mem_cgroup_iter_filter cond) +{ + if (!cond) + return VISIT; + return cond(memcg, root); +} + /* * Returns a next (in a pre-order walk) alive memcg (with elevated css * ref. count) or NULL if the whole root's subtree has been visited. @@ -1075,7 +945,7 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) * helper function to be used by mem_cgroup_iter */ static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root, - struct mem_cgroup *last_visited) + struct mem_cgroup *last_visited, mem_cgroup_iter_filter cond) { struct cgroup_subsys_state *prev_css, *next_css; @@ -1093,11 +963,31 @@ skip_node: if (next_css) { struct mem_cgroup *mem = mem_cgroup_from_css(next_css); - if (css_tryget(&mem->css)) - return mem; - else { + switch (mem_cgroup_filter(mem, root, cond)) { + case SKIP: prev_css = next_css; goto skip_node; + case SKIP_TREE: + if (mem == root) + return NULL; + /* + * css_rightmost_descendant is not an optimal way to + * skip through a subtree (especially for imbalanced + * trees leaning to right) but that's what we have right + * now. More effective solution would be traversing + * right-up for first non-NULL without calling + * css_next_descendant_pre afterwards. + */ + prev_css = css_rightmost_descendant(next_css); + goto skip_node; + case VISIT: + if (css_tryget(&mem->css)) + return mem; + else { + prev_css = next_css; + goto skip_node; + } + break; } } @@ -1161,6 +1051,7 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter, * @root: hierarchy root * @prev: previously returned memcg, NULL on first invocation * @reclaim: cookie for shared reclaim walks, NULL for full walks + * @cond: filter for visited nodes, NULL for no filter * * Returns references to children of the hierarchy below @root, or * @root itself, or %NULL after a full round-trip. @@ -1173,15 +1064,18 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter, * divide up the memcgs in the hierarchy among all concurrent * reclaimers operating on the same zone and priority. */ -struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, +struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim) + struct mem_cgroup_reclaim_cookie *reclaim, + mem_cgroup_iter_filter cond) { struct mem_cgroup *memcg = NULL; struct mem_cgroup *last_visited = NULL; - if (mem_cgroup_disabled()) - return NULL; + if (mem_cgroup_disabled()) { + /* first call must return non-NULL, second return NULL */ + return (struct mem_cgroup *)(unsigned long)!prev; + } if (!root) root = root_mem_cgroup; @@ -1192,7 +1086,9 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, if (!root->use_hierarchy && root != root_mem_cgroup) { if (prev) goto out_css_put; - return root; + if (mem_cgroup_filter(root, root, cond) == VISIT) + return root; + return NULL; } rcu_read_lock(); @@ -1215,7 +1111,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, last_visited = mem_cgroup_iter_load(iter, root, &seq); } - memcg = __mem_cgroup_iter_next(root, last_visited); + memcg = __mem_cgroup_iter_next(root, last_visited, cond); if (reclaim) { mem_cgroup_iter_update(iter, last_visited, memcg, seq); @@ -1226,7 +1122,11 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, reclaim->generation = iter->generation; } - if (prev && !memcg) + /* + * We have finished the whole tree walk or no group has been + * visited because filter told us to skip the root node. + */ + if (!memcg && (prev || (cond && !last_visited))) goto out_unlock; } out_unlock: @@ -1867,6 +1767,7 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg, return total; } +#if MAX_NUMNODES > 1 /** * test_mem_cgroup_node_reclaimable * @memcg: the target memcg @@ -1889,7 +1790,6 @@ static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg, return false; } -#if MAX_NUMNODES > 1 /* * Always updating the nodemask is not very good - even if we have an empty @@ -1957,115 +1857,64 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) return node; } -/* - * Check all nodes whether it contains reclaimable pages or not. - * For quick scan, we make use of scan_nodes. This will allow us to skip - * unused nodes. But scan_nodes is lazily updated and may not cotain - * enough new information. We need to do double check. - */ -static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap) -{ - int nid; - - /* - * quick check...making use of scan_node. - * We can skip unused nodes. - */ - if (!nodes_empty(memcg->scan_nodes)) { - for (nid = first_node(memcg->scan_nodes); - nid < MAX_NUMNODES; - nid = next_node(nid, memcg->scan_nodes)) { - - if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap)) - return true; - } - } - /* - * Check rest of nodes. - */ - for_each_node_state(nid, N_MEMORY) { - if (node_isset(nid, memcg->scan_nodes)) - continue; - if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap)) - return true; - } - return false; -} - #else int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) { return 0; } -static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap) -{ - return test_mem_cgroup_node_reclaimable(memcg, 0, noswap); -} #endif -static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, - struct zone *zone, - gfp_t gfp_mask, - unsigned long *total_scanned) -{ - struct mem_cgroup *victim = NULL; - int total = 0; - int loop = 0; - unsigned long excess; - unsigned long nr_scanned; - struct mem_cgroup_reclaim_cookie reclaim = { - .zone = zone, - .priority = 0, - }; - - excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT; - - while (1) { - victim = mem_cgroup_iter(root_memcg, victim, &reclaim); - if (!victim) { - loop++; - if (loop >= 2) { - /* - * If we have not been able to reclaim - * anything, it might because there are - * no reclaimable pages under this hierarchy - */ - if (!total) - break; - /* - * We want to do more targeted reclaim. - * excess >> 2 is not to excessive so as to - * reclaim too much, nor too less that we keep - * coming back to reclaim from this cgroup - */ - if (total >= (excess >> 2) || - (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) - break; - } - continue; - } - if (!mem_cgroup_reclaimable(victim, false)) - continue; - total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false, - zone, &nr_scanned); - *total_scanned += nr_scanned; - if (!res_counter_soft_limit_excess(&root_memcg->res)) +/* + * A group is eligible for the soft limit reclaim under the given root + * hierarchy if + * a) it is over its soft limit + * b) any parent up the hierarchy is over its soft limit + * + * If the given group doesn't have any children over the limit then it + * doesn't make any sense to iterate its subtree. + */ +enum mem_cgroup_filter_t +mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, + struct mem_cgroup *root) +{ + struct mem_cgroup *parent; + + if (!memcg) + memcg = root_mem_cgroup; + parent = memcg; + + if (res_counter_soft_limit_excess(&memcg->res)) + return VISIT; + + /* + * If any parent up to the root in the hierarchy is over its soft limit + * then we have to obey and reclaim from this group as well. + */ + while ((parent = parent_mem_cgroup(parent))) { + if (res_counter_soft_limit_excess(&parent->res)) + return VISIT; + if (parent == root) break; } - mem_cgroup_iter_break(root_memcg, victim); - return total; + + if (!atomic_read(&memcg->children_in_excess)) + return SKIP_TREE; + return SKIP; } +static DEFINE_SPINLOCK(memcg_oom_lock); + /* * Check OOM-Killer is already running under our hierarchy. * If someone is running, return false. - * Has to be called with memcg_oom_lock */ -static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg) +static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg) { struct mem_cgroup *iter, *failed = NULL; + spin_lock(&memcg_oom_lock); + for_each_mem_cgroup_tree(iter, memcg) { if (iter->oom_lock) { /* @@ -2079,33 +1928,33 @@ static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg) iter->oom_lock = true; } - if (!failed) - return true; - - /* - * OK, we failed to lock the whole subtree so we have to clean up - * what we set up to the failing subtree - */ - for_each_mem_cgroup_tree(iter, memcg) { - if (iter == failed) { - mem_cgroup_iter_break(memcg, iter); - break; + if (failed) { + /* + * OK, we failed to lock the whole subtree so we have + * to clean up what we set up to the failing subtree + */ + for_each_mem_cgroup_tree(iter, memcg) { + if (iter == failed) { + mem_cgroup_iter_break(memcg, iter); + break; + } + iter->oom_lock = false; } - iter->oom_lock = false; } - return false; + + spin_unlock(&memcg_oom_lock); + + return !failed; } -/* - * Has to be called with memcg_oom_lock - */ -static int mem_cgroup_oom_unlock(struct mem_cgroup *memcg) +static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg) { struct mem_cgroup *iter; + spin_lock(&memcg_oom_lock); for_each_mem_cgroup_tree(iter, memcg) iter->oom_lock = false; - return 0; + spin_unlock(&memcg_oom_lock); } static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg) @@ -2129,7 +1978,6 @@ static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg) atomic_add_unless(&iter->under_oom, -1, 0); } -static DEFINE_SPINLOCK(memcg_oom_lock); static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); struct oom_wait_info { @@ -2159,6 +2007,7 @@ static int memcg_oom_wake_function(wait_queue_t *wait, static void memcg_wakeup_oom(struct mem_cgroup *memcg) { + atomic_inc(&memcg->oom_wakeups); /* for filtering, pass "memcg" as argument. */ __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg); } @@ -2170,56 +2019,136 @@ static void memcg_oom_recover(struct mem_cgroup *memcg) } /* - * try to call OOM killer. returns false if we should exit memory-reclaim loop. + * try to call OOM killer */ -static bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask, - int order) +static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) { - struct oom_wait_info owait; - bool locked, need_to_kill; + bool locked; + int wakeups; - owait.memcg = memcg; - owait.wait.flags = 0; - owait.wait.func = memcg_oom_wake_function; - owait.wait.private = current; - INIT_LIST_HEAD(&owait.wait.task_list); - need_to_kill = true; - mem_cgroup_mark_under_oom(memcg); + if (!current->memcg_oom.may_oom) + return; + + current->memcg_oom.in_memcg_oom = 1; - /* At first, try to OOM lock hierarchy under memcg.*/ - spin_lock(&memcg_oom_lock); - locked = mem_cgroup_oom_lock(memcg); /* - * Even if signal_pending(), we can't quit charge() loop without - * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL - * under OOM is always welcomed, use TASK_KILLABLE here. + * As with any blocking lock, a contender needs to start + * listening for wakeups before attempting the trylock, + * otherwise it can miss the wakeup from the unlock and sleep + * indefinitely. This is just open-coded because our locking + * is so particular to memcg hierarchies. */ - prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE); - if (!locked || memcg->oom_kill_disable) - need_to_kill = false; + wakeups = atomic_read(&memcg->oom_wakeups); + mem_cgroup_mark_under_oom(memcg); + + locked = mem_cgroup_oom_trylock(memcg); + if (locked) mem_cgroup_oom_notify(memcg); - spin_unlock(&memcg_oom_lock); - if (need_to_kill) { - finish_wait(&memcg_oom_waitq, &owait.wait); + if (locked && !memcg->oom_kill_disable) { + mem_cgroup_unmark_under_oom(memcg); mem_cgroup_out_of_memory(memcg, mask, order); + mem_cgroup_oom_unlock(memcg); + /* + * There is no guarantee that an OOM-lock contender + * sees the wakeups triggered by the OOM kill + * uncharges. Wake any sleepers explicitely. + */ + memcg_oom_recover(memcg); } else { - schedule(); - finish_wait(&memcg_oom_waitq, &owait.wait); + /* + * A system call can just return -ENOMEM, but if this + * is a page fault and somebody else is handling the + * OOM already, we need to sleep on the OOM waitqueue + * for this memcg until the situation is resolved. + * Which can take some time because it might be + * handled by a userspace task. + * + * However, this is the charge context, which means + * that we may sit on a large call stack and hold + * various filesystem locks, the mmap_sem etc. and we + * don't want the OOM handler to deadlock on them + * while we sit here and wait. Store the current OOM + * context in the task_struct, then return -ENOMEM. + * At the end of the page fault handler, with the + * stack unwound, pagefault_out_of_memory() will check + * back with us by calling + * mem_cgroup_oom_synchronize(), possibly putting the + * task to sleep. + */ + current->memcg_oom.oom_locked = locked; + current->memcg_oom.wakeups = wakeups; + css_get(&memcg->css); + current->memcg_oom.wait_on_memcg = memcg; } - spin_lock(&memcg_oom_lock); - if (locked) - mem_cgroup_oom_unlock(memcg); - memcg_wakeup_oom(memcg); - spin_unlock(&memcg_oom_lock); +} - mem_cgroup_unmark_under_oom(memcg); +/** + * mem_cgroup_oom_synchronize - complete memcg OOM handling + * + * This has to be called at the end of a page fault if the the memcg + * OOM handler was enabled and the fault is returning %VM_FAULT_OOM. + * + * Memcg supports userspace OOM handling, so failed allocations must + * sleep on a waitqueue until the userspace task resolves the + * situation. Sleeping directly in the charge context with all kinds + * of locks held is not a good idea, instead we remember an OOM state + * in the task and mem_cgroup_oom_synchronize() has to be called at + * the end of the page fault to put the task to sleep and clean up the + * OOM state. + * + * Returns %true if an ongoing memcg OOM situation was detected and + * finalized, %false otherwise. + */ +bool mem_cgroup_oom_synchronize(void) +{ + struct oom_wait_info owait; + struct mem_cgroup *memcg; - if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current)) + /* OOM is global, do not handle */ + if (!current->memcg_oom.in_memcg_oom) return false; - /* Give chance to dying process */ - schedule_timeout_uninterruptible(1); + + /* + * We invoked the OOM killer but there is a chance that a kill + * did not free up any charges. Everybody else might already + * be sleeping, so restart the fault and keep the rampage + * going until some charges are released. + */ + memcg = current->memcg_oom.wait_on_memcg; + if (!memcg) + goto out; + + if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current)) + goto out_memcg; + + owait.memcg = memcg; + owait.wait.flags = 0; + owait.wait.func = memcg_oom_wake_function; + owait.wait.private = current; + INIT_LIST_HEAD(&owait.wait.task_list); + + prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE); + /* Only sleep if we didn't miss any wakeups since OOM */ + if (atomic_read(&memcg->oom_wakeups) == current->memcg_oom.wakeups) + schedule(); + finish_wait(&memcg_oom_waitq, &owait.wait); +out_memcg: + mem_cgroup_unmark_under_oom(memcg); + if (current->memcg_oom.oom_locked) { + mem_cgroup_oom_unlock(memcg); + /* + * There is no guarantee that an OOM-lock contender + * sees the wakeups triggered by the OOM kill + * uncharges. Wake any sleepers explicitely. + */ + memcg_oom_recover(memcg); + } + css_put(&memcg->css); + current->memcg_oom.wait_on_memcg = NULL; +out: + current->memcg_oom.in_memcg_oom = 0; return true; } @@ -2288,7 +2217,7 @@ void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags) } void mem_cgroup_update_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx, int val) + enum mem_cgroup_stat_index idx, int val) { struct mem_cgroup *memcg; struct page_cgroup *pc = lookup_page_cgroup(page); @@ -2297,18 +2226,11 @@ void mem_cgroup_update_page_stat(struct page *page, if (mem_cgroup_disabled()) return; + VM_BUG_ON(!rcu_read_lock_held()); memcg = pc->mem_cgroup; if (unlikely(!memcg || !PageCgroupUsed(pc))) return; - switch (idx) { - case MEMCG_NR_FILE_MAPPED: - idx = MEM_CGROUP_STAT_FILE_MAPPED; - break; - default: - BUG(); - } - this_cpu_add(memcg->stat->count[idx], val); } @@ -2450,7 +2372,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync) flush_work(&stock->work); } out: - put_online_cpus(); + put_online_cpus(); } /* @@ -2532,12 +2454,11 @@ enum { CHARGE_RETRY, /* need to retry but retry is not bad */ CHARGE_NOMEM, /* we can't do more. return -ENOMEM */ CHARGE_WOULDBLOCK, /* GFP_WAIT wasn't set and no enough res. */ - CHARGE_OOM_DIE, /* the current is killed because of OOM */ }; static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned int nr_pages, unsigned int min_pages, - bool oom_check) + bool invoke_oom) { unsigned long csize = nr_pages * PAGE_SIZE; struct mem_cgroup *mem_over_limit; @@ -2594,14 +2515,10 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, if (mem_cgroup_wait_acct_move(mem_over_limit)) return CHARGE_RETRY; - /* If we don't need to call oom-killer at el, return immediately */ - if (!oom_check) - return CHARGE_NOMEM; - /* check OOM */ - if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize))) - return CHARGE_OOM_DIE; + if (invoke_oom) + mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize)); - return CHARGE_RETRY; + return CHARGE_NOMEM; } /* @@ -2704,7 +2621,7 @@ again: } do { - bool oom_check; + bool invoke_oom = oom && !nr_oom_retries; /* If killed, bypass charge */ if (fatal_signal_pending(current)) { @@ -2712,14 +2629,8 @@ again: goto bypass; } - oom_check = false; - if (oom && !nr_oom_retries) { - oom_check = true; - nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES; - } - - ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages, - oom_check); + ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, + nr_pages, invoke_oom); switch (ret) { case CHARGE_OK: break; @@ -2732,16 +2643,12 @@ again: css_put(&memcg->css); goto nomem; case CHARGE_NOMEM: /* OOM routine works */ - if (!oom) { + if (!oom || invoke_oom) { css_put(&memcg->css); goto nomem; } - /* If oom, we never return -ENOMEM */ nr_oom_retries--; break; - case CHARGE_OOM_DIE: /* Killed by OOM Killer */ - css_put(&memcg->css); - goto bypass; } } while (ret != CHARGE_OK); @@ -2882,7 +2789,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, * is accessed after testing USED bit. To make pc->mem_cgroup visible * before USED bit, we need memory barrier here. * See mem_cgroup_add_lru_list(), etc. - */ + */ smp_wmb(); SetPageCgroupUsed(pc); @@ -2905,9 +2812,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, unlock_page_cgroup(pc); /* - * "charge_statistics" updated event counter. Then, check it. - * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. - * if they exceeds softlimit. + * "charge_statistics" updated event counter. */ memcg_check_events(memcg, page); } @@ -3626,9 +3531,9 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order) * the page allocator. Therefore, the following sequence when backed by * the SLUB allocator: * - * memcg_stop_kmem_account(); - * kmalloc(<large_number>) - * memcg_resume_kmem_account(); + * memcg_stop_kmem_account(); + * kmalloc(<large_number>) + * memcg_resume_kmem_account(); * * would effectively ignore the fact that we should skip accounting, * since it will drive us directly to this function without passing @@ -3750,6 +3655,20 @@ void mem_cgroup_split_huge_fixup(struct page *head) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline +void mem_cgroup_move_account_page_stat(struct mem_cgroup *from, + struct mem_cgroup *to, + unsigned int nr_pages, + enum mem_cgroup_stat_index idx) +{ + /* Update stat data for mem_cgroup */ + preempt_disable(); + WARN_ON_ONCE(from->stat->count[idx] < nr_pages); + __this_cpu_add(from->stat->count[idx], -nr_pages); + __this_cpu_add(to->stat->count[idx], nr_pages); + preempt_enable(); +} + /** * mem_cgroup_move_account - move account of the page * @page: the page @@ -3795,13 +3714,14 @@ static int mem_cgroup_move_account(struct page *page, move_lock_mem_cgroup(from, &flags); - if (!anon && page_mapped(page)) { - /* Update mapped_file data for mem_cgroup */ - preempt_disable(); - __this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); - __this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); - preempt_enable(); - } + if (!anon && page_mapped(page)) + mem_cgroup_move_account_page_stat(from, to, nr_pages, + MEM_CGROUP_STAT_FILE_MAPPED); + + if (PageWriteback(page)) + mem_cgroup_move_account_page_stat(from, to, nr_pages, + MEM_CGROUP_STAT_WRITEBACK); + mem_cgroup_charge_statistics(from, page, anon, -nr_pages); /* caller should have done css_get */ @@ -4657,7 +4577,7 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, MEM_CGROUP_RECLAIM_SHRINK); curusage = res_counter_read_u64(&memcg->res, RES_USAGE); /* Usage is reduced ? */ - if (curusage >= oldusage) + if (curusage >= oldusage) retry_count--; else oldusage = curusage; @@ -4678,7 +4598,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, int enlarge = 0; /* see mem_cgroup_resize_res_limit */ - retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; + retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); while (retry_count) { if (signal_pending(current)) { @@ -4727,98 +4647,6 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, return ret; } -unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, - gfp_t gfp_mask, - unsigned long *total_scanned) -{ - unsigned long nr_reclaimed = 0; - struct mem_cgroup_per_zone *mz, *next_mz = NULL; - unsigned long reclaimed; - int loop = 0; - struct mem_cgroup_tree_per_zone *mctz; - unsigned long long excess; - unsigned long nr_scanned; - - if (order > 0) - return 0; - - mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone)); - /* - * This loop can run a while, specially if mem_cgroup's continuously - * keep exceeding their soft limit and putting the system under - * pressure - */ - do { - if (next_mz) - mz = next_mz; - else - mz = mem_cgroup_largest_soft_limit_node(mctz); - if (!mz) - break; - - nr_scanned = 0; - reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone, - gfp_mask, &nr_scanned); - nr_reclaimed += reclaimed; - *total_scanned += nr_scanned; - spin_lock(&mctz->lock); - - /* - * If we failed to reclaim anything from this memory cgroup - * it is time to move on to the next cgroup - */ - next_mz = NULL; - if (!reclaimed) { - do { - /* - * Loop until we find yet another one. - * - * By the time we get the soft_limit lock - * again, someone might have aded the - * group back on the RB tree. Iterate to - * make sure we get a different mem. - * mem_cgroup_largest_soft_limit_node returns - * NULL if no other cgroup is present on - * the tree - */ - next_mz = - __mem_cgroup_largest_soft_limit_node(mctz); - if (next_mz == mz) - css_put(&next_mz->memcg->css); - else /* next_mz == NULL or other memcg */ - break; - } while (1); - } - __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); - excess = res_counter_soft_limit_excess(&mz->memcg->res); - /* - * One school of thought says that we should not add - * back the node to the tree if reclaim returns 0. - * But our reclaim could return 0, simply because due - * to priority we are exposing a smaller subset of - * memory to reclaim from. Consider this as a longer - * term TODO. - */ - /* If excess == 0, no tree ops */ - __mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess); - spin_unlock(&mctz->lock); - css_put(&mz->memcg->css); - loop++; - /* - * Could not reclaim anything and there are no more - * mem cgroups to try or we seem to be looping without - * reclaiming anything. - */ - if (!nr_reclaimed && - (next_mz == NULL || - loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS)) - break; - } while (!nr_reclaimed); - if (next_mz) - css_put(&next_mz->memcg->css); - return nr_reclaimed; -} - /** * mem_cgroup_force_empty_list - clears LRU of a group * @memcg: group to clear @@ -4990,18 +4818,12 @@ static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css, unsigned int event) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - int ret; if (mem_cgroup_is_root(memcg)) return -EINVAL; - css_get(&memcg->css); - ret = mem_cgroup_force_empty(memcg); - css_put(&memcg->css); - - return ret; + return mem_cgroup_force_empty(memcg); } - static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -5139,7 +4961,7 @@ static int memcg_update_kmem_limit(struct cgroup_subsys_state *css, u64 val) */ mutex_lock(&memcg_create_mutex); mutex_lock(&set_limit_mutex); - if (!memcg->kmem_account_flags && val != RESOURCE_MAX) { + if (!memcg->kmem_account_flags && val != RES_COUNTER_MAX) { if (cgroup_task_count(css->cgroup) || memcg_has_children(memcg)) { ret = -EBUSY; goto out; @@ -5149,7 +4971,7 @@ static int memcg_update_kmem_limit(struct cgroup_subsys_state *css, u64 val) ret = memcg_update_cache_sizes(memcg); if (ret) { - res_counter_set_limit(&memcg->kmem, RESOURCE_MAX); + res_counter_set_limit(&memcg->kmem, RES_COUNTER_MAX); goto out; } static_key_slow_inc(&memcg_kmem_enabled_key); @@ -6083,8 +5905,6 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) for (zone = 0; zone < MAX_NR_ZONES; zone++) { mz = &pn->zoneinfo[zone]; lruvec_init(&mz->lruvec); - mz->usage_in_excess = 0; - mz->on_tree = false; mz->memcg = memcg; } memcg->nodeinfo[node] = pn; @@ -6140,7 +5960,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) int node; size_t size = memcg_size(); - mem_cgroup_remove_from_trees(memcg); free_css_id(&mem_cgroup_subsys, &memcg->css); for_each_node(node) @@ -6177,29 +5996,6 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(parent_mem_cgroup); -static void __init mem_cgroup_soft_limit_tree_init(void) -{ - struct mem_cgroup_tree_per_node *rtpn; - struct mem_cgroup_tree_per_zone *rtpz; - int tmp, node, zone; - - for_each_node(node) { - tmp = node; - if (!node_state(node, N_NORMAL_MEMORY)) - tmp = -1; - rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp); - BUG_ON(!rtpn); - - soft_limit_tree.rb_tree_per_node[node] = rtpn; - - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - rtpz = &rtpn->rb_tree_per_zone[zone]; - rtpz->rb_root = RB_ROOT; - spin_lock_init(&rtpz->lock); - } - } -} - static struct cgroup_subsys_state * __ref mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { @@ -6229,6 +6025,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) mutex_init(&memcg->thresholds_lock); spin_lock_init(&memcg->move_lock); vmpressure_init(&memcg->vmpressure); + spin_lock_init(&memcg->soft_lock); return &memcg->css; @@ -6306,6 +6103,13 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) mem_cgroup_invalidate_reclaim_iterators(memcg); mem_cgroup_reparent_charges(memcg); + if (memcg->soft_contributed) { + while ((memcg = parent_mem_cgroup(memcg))) + atomic_dec(&memcg->children_in_excess); + + if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy) + atomic_dec(&root_mem_cgroup->children_in_excess); + } mem_cgroup_destroy_all_caches(memcg); vmpressure_cleanup(&memcg->vmpressure); } @@ -6980,7 +6784,6 @@ static int __init mem_cgroup_init(void) { hotcpu_notifier(memcg_cpu_hotplug_callback, 0); enable_swap_cgroup(); - mem_cgroup_soft_limit_tree_init(); memcg_stock_init(); return 0; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d472e14c6808..947ed5413279 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -248,10 +248,12 @@ void shake_page(struct page *p, int access) */ if (access) { int nr; + int nid = page_to_nid(p); do { struct shrink_control shrink = { .gfp_mask = GFP_KERNEL, }; + node_set(nid, shrink.nodes_to_scan); nr = shrink_slab(&shrink, 1000, 1000); if (page_count(p) == 1) diff --git a/mm/memory.c b/mm/memory.c index 35236e4e2ae6..1cc2a5c32dc9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3696,7 +3696,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_sem still held, but pte unmapped and unlocked. */ -int handle_pte_fault(struct mm_struct *mm, +static int handle_pte_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *pte, pmd_t *pmd, unsigned int flags) { @@ -3755,22 +3755,14 @@ unlock: /* * By the time we get here, we already hold the mm semaphore */ -int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, unsigned int flags) +static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, unsigned int flags) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - __set_current_state(TASK_RUNNING); - - count_vm_event(PGFAULT); - mem_cgroup_count_vm_event(mm, PGFAULT); - - /* do counter updates before entering really critical section. */ - check_sync_rss_stat(current); - if (unlikely(is_vm_hugetlb_page(vma))) return hugetlb_fault(mm, vma, address, flags); @@ -3783,9 +3775,12 @@ retry: if (!pmd) return VM_FAULT_OOM; if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) { + int ret = VM_FAULT_FALLBACK; if (!vma->vm_ops) - return do_huge_pmd_anonymous_page(mm, vma, address, - pmd, flags); + ret = do_huge_pmd_anonymous_page(mm, vma, address, + pmd, flags); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; } else { pmd_t orig_pmd = *pmd; int ret; @@ -3851,6 +3846,37 @@ retry: return handle_pte_fault(mm, vma, address, pte, pmd, flags); } +int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, unsigned int flags) +{ + int ret; + + __set_current_state(TASK_RUNNING); + + count_vm_event(PGFAULT); + mem_cgroup_count_vm_event(mm, PGFAULT); + + /* do counter updates before entering really critical section. */ + check_sync_rss_stat(current); + + /* + * Enable the memcg OOM handling for faults triggered in user + * space. Kernel faults are handled more gracefully. + */ + if (flags & FAULT_FLAG_USER) + mem_cgroup_enable_oom(); + + ret = __handle_mm_fault(mm, vma, address, flags); + + if (flags & FAULT_FLAG_USER) + mem_cgroup_disable_oom(); + + if (WARN_ON(task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))) + mem_cgroup_oom_synchronize(); + + return ret; +} + #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 98e75f2ac7bc..314e9d274381 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -678,9 +678,12 @@ out: */ void pagefault_out_of_memory(void) { - struct zonelist *zonelist = node_zonelist(first_online_node, - GFP_KERNEL); + struct zonelist *zonelist; + if (mem_cgroup_oom_synchronize()) + return; + + zonelist = node_zonelist(first_online_node, GFP_KERNEL); if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) { out_of_memory(NULL, 0, 0, NULL, false); clear_zonelist_oom(zonelist, GFP_KERNEL); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 6c7b0187be8e..f5236f804aa6 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2143,11 +2143,17 @@ EXPORT_SYMBOL(account_page_dirtied); /* * Helper function for set_page_writeback family. + * + * The caller must hold mem_cgroup_begin/end_update_page_stat() lock + * while calling this function. + * See test_set_page_writeback for example. + * * NOTE: Unlike account_page_dirtied this does not rely on being atomic * wrt interrupts. */ void account_page_writeback(struct page *page) { + mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); inc_zone_page_state(page, NR_WRITEBACK); } EXPORT_SYMBOL(account_page_writeback); @@ -2364,7 +2370,10 @@ int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); int ret; + bool locked; + unsigned long memcg_flags; + mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2385,9 +2394,11 @@ int test_clear_page_writeback(struct page *page) ret = TestClearPageWriteback(page); } if (ret) { + mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); dec_zone_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_WRITTEN); } + mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags); return ret; } @@ -2395,7 +2406,10 @@ int test_set_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); int ret; + bool locked; + unsigned long memcg_flags; + mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2422,6 +2436,7 @@ int test_set_page_writeback(struct page *page) } if (!ret) account_page_writeback(page); + mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags); return ret; } diff --git a/mm/rmap.c b/mm/rmap.c index c21ef372e531..4011cb42bb00 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1053,11 +1053,11 @@ void do_page_add_anon_rmap(struct page *page, { int first = atomic_inc_and_test(&page->_mapcount); if (first) { - if (!PageTransHuge(page)) - __inc_zone_page_state(page, NR_ANON_PAGES); - else + if (PageTransHuge(page)) __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + hpage_nr_pages(page)); } if (unlikely(PageKsm(page))) return; @@ -1086,10 +1086,10 @@ void page_add_new_anon_rmap(struct page *page, VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); SetPageSwapBacked(page); atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */ - if (!PageTransHuge(page)) - __inc_zone_page_state(page, NR_ANON_PAGES); - else + if (PageTransHuge(page)) __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + hpage_nr_pages(page)); __page_set_anon_rmap(page, vma, address, 1); if (!mlocked_vma_newpage(vma, page)) { SetPageActive(page); @@ -1112,7 +1112,7 @@ void page_add_file_rmap(struct page *page) mem_cgroup_begin_update_page_stat(page, &locked, &flags); if (atomic_inc_and_test(&page->_mapcount)) { __inc_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_inc_page_stat(page, MEMCG_NR_FILE_MAPPED); + mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); } mem_cgroup_end_update_page_stat(page, &locked, &flags); } @@ -1149,14 +1149,14 @@ void page_remove_rmap(struct page *page) goto out; if (anon) { mem_cgroup_uncharge_page(page); - if (!PageTransHuge(page)) - __dec_zone_page_state(page, NR_ANON_PAGES); - else + if (PageTransHuge(page)) __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + hpage_nr_pages(page)); } else { __dec_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_dec_page_stat(page, MEMCG_NR_FILE_MAPPED); + mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); mem_cgroup_end_update_page_stat(page, &locked, &flags); } if (unlikely(PageMlocked(page))) diff --git a/mm/swap.c b/mm/swap.c index c899502d3e36..759c3caf44bd 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -432,6 +432,11 @@ static void activate_page_drain(int cpu) pagevec_lru_move_fn(pvec, __activate_page, NULL); } +static bool need_activate_page_drain(int cpu) +{ + return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0; +} + void activate_page(struct page *page) { if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { @@ -449,6 +454,11 @@ static inline void activate_page_drain(int cpu) { } +static bool need_activate_page_drain(int cpu) +{ + return false; +} + void activate_page(struct page *page) { struct zone *zone = page_zone(page); @@ -701,12 +711,36 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) lru_add_drain(); } -/* - * Returns 0 for success - */ -int lru_add_drain_all(void) +static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); + +void lru_add_drain_all(void) { - return schedule_on_each_cpu(lru_add_drain_per_cpu); + static DEFINE_MUTEX(lock); + static struct cpumask has_work; + int cpu; + + mutex_lock(&lock); + get_online_cpus(); + cpumask_clear(&has_work); + + for_each_online_cpu(cpu) { + struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); + + if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || + pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || + need_activate_page_drain(cpu)) { + INIT_WORK(work, lru_add_drain_per_cpu); + schedule_work_on(cpu, work); + cpumask_set_cpu(cpu, &has_work); + } + } + + for_each_cpu(cpu, &has_work) + flush_work(&per_cpu(lru_add_drain_work, cpu)); + + put_online_cpus(); + mutex_unlock(&lock); } /* diff --git a/mm/truncate.c b/mm/truncate.c index e2e8a8a7eb9d..353b683afd6e 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -567,7 +567,6 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode - * @oldsize: old file size * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache @@ -580,7 +579,7 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2); * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ -void truncate_pagecache(struct inode *inode, loff_t oldsize, loff_t newsize) +void truncate_pagecache(struct inode *inode, loff_t newsize) { struct address_space *mapping = inode->i_mapping; loff_t holebegin = round_up(newsize, PAGE_SIZE); @@ -614,12 +613,8 @@ EXPORT_SYMBOL(truncate_pagecache); */ void truncate_setsize(struct inode *inode, loff_t newsize) { - loff_t oldsize; - - oldsize = inode->i_size; i_size_write(inode, newsize); - - truncate_pagecache(inode, oldsize, newsize); + truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); diff --git a/mm/vmscan.c b/mm/vmscan.c index fe715daeb8bc..8ed1b775bdc9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -139,11 +139,23 @@ static bool global_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup; } + +static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc) +{ + struct mem_cgroup *root = sc->target_mem_cgroup; + return !mem_cgroup_disabled() && + mem_cgroup_soft_reclaim_eligible(root, root) != SKIP_TREE; +} #else static bool global_reclaim(struct scan_control *sc) { return true; } + +static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc) +{ + return false; +} #endif unsigned long zone_reclaimable_pages(struct zone *zone) @@ -174,14 +186,31 @@ static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) } /* - * Add a shrinker callback to be called from the vm + * Add a shrinker callback to be called from the vm. */ -void register_shrinker(struct shrinker *shrinker) +int register_shrinker(struct shrinker *shrinker) { - atomic_long_set(&shrinker->nr_in_batch, 0); + size_t size = sizeof(*shrinker->nr_deferred); + + /* + * If we only have one possible node in the system anyway, save + * ourselves the trouble and disable NUMA aware behavior. This way we + * will save memory and some small loop time later. + */ + if (nr_node_ids == 1) + shrinker->flags &= ~SHRINKER_NUMA_AWARE; + + if (shrinker->flags & SHRINKER_NUMA_AWARE) + size *= nr_node_ids; + + shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); + if (!shrinker->nr_deferred) + return -ENOMEM; + down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); up_write(&shrinker_rwsem); + return 0; } EXPORT_SYMBOL(register_shrinker); @@ -196,15 +225,102 @@ void unregister_shrinker(struct shrinker *shrinker) } EXPORT_SYMBOL(unregister_shrinker); -static inline int do_shrinker_shrink(struct shrinker *shrinker, - struct shrink_control *sc, - unsigned long nr_to_scan) -{ - sc->nr_to_scan = nr_to_scan; - return (*shrinker->shrink)(shrinker, sc); +#define SHRINK_BATCH 128 + +static unsigned long +shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, + unsigned long nr_pages_scanned, unsigned long lru_pages) +{ + unsigned long freed = 0; + unsigned long long delta; + long total_scan; + long max_pass; + long nr; + long new_nr; + int nid = shrinkctl->nid; + long batch_size = shrinker->batch ? shrinker->batch + : SHRINK_BATCH; + + max_pass = shrinker->count_objects(shrinker, shrinkctl); + if (max_pass == 0) + return 0; + + /* + * copy the current shrinker scan count into a local variable + * and zero it so that other concurrent shrinker invocations + * don't also do this scanning work. + */ + nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); + + total_scan = nr; + delta = (4 * nr_pages_scanned) / shrinker->seeks; + delta *= max_pass; + do_div(delta, lru_pages + 1); + total_scan += delta; + if (total_scan < 0) { + printk(KERN_ERR + "shrink_slab: %pF negative objects to delete nr=%ld\n", + shrinker->scan_objects, total_scan); + total_scan = max_pass; + } + + /* + * We need to avoid excessive windup on filesystem shrinkers + * due to large numbers of GFP_NOFS allocations causing the + * shrinkers to return -1 all the time. This results in a large + * nr being built up so when a shrink that can do some work + * comes along it empties the entire cache due to nr >>> + * max_pass. This is bad for sustaining a working set in + * memory. + * + * Hence only allow the shrinker to scan the entire cache when + * a large delta change is calculated directly. + */ + if (delta < max_pass / 4) + total_scan = min(total_scan, max_pass / 2); + + /* + * Avoid risking looping forever due to too large nr value: + * never try to free more than twice the estimate number of + * freeable entries. + */ + if (total_scan > max_pass * 2) + total_scan = max_pass * 2; + + trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, + nr_pages_scanned, lru_pages, + max_pass, delta, total_scan); + + while (total_scan >= batch_size) { + unsigned long ret; + + shrinkctl->nr_to_scan = batch_size; + ret = shrinker->scan_objects(shrinker, shrinkctl); + if (ret == SHRINK_STOP) + break; + freed += ret; + + count_vm_events(SLABS_SCANNED, batch_size); + total_scan -= batch_size; + + cond_resched(); + } + + /* + * move the unused scan count back into the shrinker in a + * manner that handles concurrent updates. If we exhausted the + * scan, there is no need to do an update. + */ + if (total_scan > 0) + new_nr = atomic_long_add_return(total_scan, + &shrinker->nr_deferred[nid]); + else + new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); + + trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr); + return freed; } -#define SHRINK_BATCH 128 /* * Call the shrink functions to age shrinkable caches * @@ -224,115 +340,45 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker, * * Returns the number of slab objects which we shrunk. */ -unsigned long shrink_slab(struct shrink_control *shrink, +unsigned long shrink_slab(struct shrink_control *shrinkctl, unsigned long nr_pages_scanned, unsigned long lru_pages) { struct shrinker *shrinker; - unsigned long ret = 0; + unsigned long freed = 0; if (nr_pages_scanned == 0) nr_pages_scanned = SWAP_CLUSTER_MAX; if (!down_read_trylock(&shrinker_rwsem)) { - /* Assume we'll be able to shrink next time */ - ret = 1; + /* + * If we would return 0, our callers would understand that we + * have nothing else to shrink and give up trying. By returning + * 1 we keep it going and assume we'll be able to shrink next + * time. + */ + freed = 1; goto out; } list_for_each_entry(shrinker, &shrinker_list, list) { - unsigned long long delta; - long total_scan; - long max_pass; - int shrink_ret = 0; - long nr; - long new_nr; - long batch_size = shrinker->batch ? shrinker->batch - : SHRINK_BATCH; - - max_pass = do_shrinker_shrink(shrinker, shrink, 0); - if (max_pass <= 0) - continue; - - /* - * copy the current shrinker scan count into a local variable - * and zero it so that other concurrent shrinker invocations - * don't also do this scanning work. - */ - nr = atomic_long_xchg(&shrinker->nr_in_batch, 0); - - total_scan = nr; - delta = (4 * nr_pages_scanned) / shrinker->seeks; - delta *= max_pass; - do_div(delta, lru_pages + 1); - total_scan += delta; - if (total_scan < 0) { - printk(KERN_ERR "shrink_slab: %pF negative objects to " - "delete nr=%ld\n", - shrinker->shrink, total_scan); - total_scan = max_pass; - } - - /* - * We need to avoid excessive windup on filesystem shrinkers - * due to large numbers of GFP_NOFS allocations causing the - * shrinkers to return -1 all the time. This results in a large - * nr being built up so when a shrink that can do some work - * comes along it empties the entire cache due to nr >>> - * max_pass. This is bad for sustaining a working set in - * memory. - * - * Hence only allow the shrinker to scan the entire cache when - * a large delta change is calculated directly. - */ - if (delta < max_pass / 4) - total_scan = min(total_scan, max_pass / 2); - - /* - * Avoid risking looping forever due to too large nr value: - * never try to free more than twice the estimate number of - * freeable entries. - */ - if (total_scan > max_pass * 2) - total_scan = max_pass * 2; - - trace_mm_shrink_slab_start(shrinker, shrink, nr, - nr_pages_scanned, lru_pages, - max_pass, delta, total_scan); - - while (total_scan >= batch_size) { - int nr_before; + for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) { + if (!node_online(shrinkctl->nid)) + continue; - nr_before = do_shrinker_shrink(shrinker, shrink, 0); - shrink_ret = do_shrinker_shrink(shrinker, shrink, - batch_size); - if (shrink_ret == -1) + if (!(shrinker->flags & SHRINKER_NUMA_AWARE) && + (shrinkctl->nid != 0)) break; - if (shrink_ret < nr_before) - ret += nr_before - shrink_ret; - count_vm_events(SLABS_SCANNED, batch_size); - total_scan -= batch_size; - cond_resched(); - } + freed += shrink_slab_node(shrinkctl, shrinker, + nr_pages_scanned, lru_pages); - /* - * move the unused scan count back into the shrinker in a - * manner that handles concurrent updates. If we exhausted the - * scan, there is no need to do an update. - */ - if (total_scan > 0) - new_nr = atomic_long_add_return(total_scan, - &shrinker->nr_in_batch); - else - new_nr = atomic_long_read(&shrinker->nr_in_batch); - - trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr); + } } up_read(&shrinker_rwsem); out: cond_resched(); - return ret; + return freed; } static inline int is_page_cache_freeable(struct page *page) @@ -2130,9 +2176,11 @@ static inline bool should_continue_reclaim(struct zone *zone, } } -static void shrink_zone(struct zone *zone, struct scan_control *sc) +static int +__shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim) { unsigned long nr_reclaimed, nr_scanned; + int groups_scanned = 0; do { struct mem_cgroup *root = sc->target_mem_cgroup; @@ -2140,15 +2188,17 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc) .zone = zone, .priority = sc->priority, }; - struct mem_cgroup *memcg; + struct mem_cgroup *memcg = NULL; + mem_cgroup_iter_filter filter = (soft_reclaim) ? + mem_cgroup_soft_reclaim_eligible : NULL; nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; - memcg = mem_cgroup_iter(root, NULL, &reclaim); - do { + while ((memcg = mem_cgroup_iter_cond(root, memcg, &reclaim, filter))) { struct lruvec *lruvec; + groups_scanned++; lruvec = mem_cgroup_zone_lruvec(zone, memcg); shrink_lruvec(lruvec, sc); @@ -2168,8 +2218,7 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc) mem_cgroup_iter_break(root, memcg); break; } - memcg = mem_cgroup_iter(root, memcg, &reclaim); - } while (memcg); + } vmpressure(sc->gfp_mask, sc->target_mem_cgroup, sc->nr_scanned - nr_scanned, @@ -2177,6 +2226,37 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc) } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed, sc->nr_scanned - nr_scanned, sc)); + + return groups_scanned; +} + + +static void shrink_zone(struct zone *zone, struct scan_control *sc) +{ + bool do_soft_reclaim = mem_cgroup_should_soft_reclaim(sc); + unsigned long nr_scanned = sc->nr_scanned; + int scanned_groups; + + scanned_groups = __shrink_zone(zone, sc, do_soft_reclaim); + /* + * memcg iterator might race with other reclaimer or start from + * a incomplete tree walk so the tree walk in __shrink_zone + * might have missed groups that are above the soft limit. Try + * another loop to catch up with others. Do it just once to + * prevent from reclaim latencies when other reclaimers always + * preempt this one. + */ + if (do_soft_reclaim && !scanned_groups) + __shrink_zone(zone, sc, do_soft_reclaim); + + /* + * No group is over the soft limit or those that are do not have + * pages in the zone we are reclaiming so we have to reclaim everybody + */ + if (do_soft_reclaim && (sc->nr_scanned == nr_scanned)) { + __shrink_zone(zone, sc, false); + return; + } } /* Returns true if compaction should go ahead for a high-order request */ @@ -2240,8 +2320,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; - unsigned long nr_soft_reclaimed; - unsigned long nr_soft_scanned; bool aborted_reclaim = false; /* @@ -2281,18 +2359,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) continue; } } - /* - * This steals pages from memory cgroups over softlimit - * and returns the number of reclaimed pages and - * scanned pages. This works for global memory pressure - * and balancing, not for a memcg's limit. - */ - nr_soft_scanned = 0; - nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, - sc->order, sc->gfp_mask, - &nr_soft_scanned); - sc->nr_reclaimed += nr_soft_reclaimed; - sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } @@ -2368,12 +2434,16 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, */ if (global_reclaim(sc)) { unsigned long lru_pages = 0; + + nodes_clear(shrink->nodes_to_scan); for_each_zone_zonelist(zone, z, zonelist, gfp_zone(sc->gfp_mask)) { if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; lru_pages += zone_reclaimable_pages(zone); + node_set(zone_to_nid(zone), + shrink->nodes_to_scan); } shrink_slab(shrink, sc->nr_scanned, lru_pages); @@ -2829,6 +2899,8 @@ static bool kswapd_shrink_zone(struct zone *zone, return true; shrink_zone(zone, sc); + nodes_clear(shrink.nodes_to_scan); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); reclaim_state->reclaimed_slab = 0; shrink_slab(&shrink, sc->nr_scanned, lru_pages); @@ -2880,8 +2952,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, { int i; int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ - unsigned long nr_soft_reclaimed; - unsigned long nr_soft_scanned; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .priority = DEF_PRIORITY, @@ -2996,15 +3066,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, sc.nr_scanned = 0; - nr_soft_scanned = 0; - /* - * Call soft limit reclaim before calling shrink_zone. - */ - nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, - order, sc.gfp_mask, - &nr_soft_scanned); - sc.nr_reclaimed += nr_soft_reclaimed; - /* * There should be no need to raise the scanning * priority if enough pages are already being scanned @@ -3520,10 +3581,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) * number of slab pages and shake the slab until it is reduced * by the same nr_pages that we used for reclaiming unmapped * pages. - * - * Note that shrink_slab will free memory on all zones and may - * take a long time. */ + nodes_clear(shrink.nodes_to_scan); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); for (;;) { unsigned long lru_pages = zone_reclaimable_pages(zone); diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 8a57d79b0b16..559d4ae6ebf4 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -87,8 +87,8 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) if (!cg_proto) return -EINVAL; - if (val > RESOURCE_MAX) - val = RESOURCE_MAX; + if (val > RES_COUNTER_MAX) + val = RES_COUNTER_MAX; tcp = tcp_from_cgproto(cg_proto); @@ -101,9 +101,9 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT, net->ipv4.sysctl_tcp_mem[i]); - if (val == RESOURCE_MAX) + if (val == RES_COUNTER_MAX) clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); - else if (val != RESOURCE_MAX) { + else if (val != RES_COUNTER_MAX) { /* * The active bit needs to be written after the static_key * update. This is what guarantees that the socket activation @@ -187,7 +187,7 @@ static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft) switch (cft->private) { case RES_LIMIT: - val = tcp_read_stat(memcg, RES_LIMIT, RESOURCE_MAX); + val = tcp_read_stat(memcg, RES_LIMIT, RES_COUNTER_MAX); break; case RES_USAGE: val = tcp_read_usage(memcg); diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 415159061cd0..5285ead196c0 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -434,12 +434,13 @@ EXPORT_SYMBOL_GPL(rpcauth_destroy_credcache); /* * Remove stale credentials. Avoid sleeping inside the loop. */ -static int +static long rpcauth_prune_expired(struct list_head *free, int nr_to_scan) { spinlock_t *cache_lock; struct rpc_cred *cred, *next; unsigned long expired = jiffies - RPC_AUTH_EXPIRY_MORATORIUM; + long freed = 0; list_for_each_entry_safe(cred, next, &cred_unused, cr_lru) { @@ -451,10 +452,11 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan) */ if (time_in_range(cred->cr_expire, expired, jiffies) && test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) - return 0; + break; list_del_init(&cred->cr_lru); number_cred_unused--; + freed++; if (atomic_read(&cred->cr_count) != 0) continue; @@ -467,29 +469,39 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan) } spin_unlock(cache_lock); } - return (number_cred_unused / 100) * sysctl_vfs_cache_pressure; + return freed; } /* * Run memory cache shrinker. */ -static int -rpcauth_cache_shrinker(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long +rpcauth_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) + { LIST_HEAD(free); - int res; - int nr_to_scan = sc->nr_to_scan; - gfp_t gfp_mask = sc->gfp_mask; + unsigned long freed; + + if ((sc->gfp_mask & GFP_KERNEL) != GFP_KERNEL) + return SHRINK_STOP; - if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL) - return (nr_to_scan == 0) ? 0 : -1; + /* nothing left, don't come back */ if (list_empty(&cred_unused)) - return 0; + return SHRINK_STOP; + spin_lock(&rpc_credcache_lock); - res = rpcauth_prune_expired(&free, nr_to_scan); + freed = rpcauth_prune_expired(&free, sc->nr_to_scan); spin_unlock(&rpc_credcache_lock); rpcauth_destroy_credlist(&free); - return res; + + return freed; +} + +static unsigned long +rpcauth_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc) + +{ + return (number_cred_unused / 100) * sysctl_vfs_cache_pressure; } /* @@ -805,7 +817,8 @@ rpcauth_uptodatecred(struct rpc_task *task) } static struct shrinker rpc_cred_shrinker = { - .shrink = rpcauth_cache_shrinker, + .count_objects = rpcauth_cache_shrink_count, + .scan_objects = rpcauth_cache_shrink_scan, .seeks = DEFAULT_SEEKS, }; |