diff options
70 files changed, 704 insertions, 382 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 50b8148448f..4d4881d909d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1220,7 +1220,7 @@ F: drivers/auxdisplay/ F: include/linux/cfag12864b.h AVR32 ARCHITECTURE -M: Haavard Skinnemoen <hskinnemoen@atmel.com> +M: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> W: http://www.atmel.com/products/AVR32/ W: http://avr32linux.org/ W: http://avrfreaks.net/ @@ -1228,7 +1228,7 @@ S: Supported F: arch/avr32/ AVR32/AT32AP MACHINE SUPPORT -M: Haavard Skinnemoen <hskinnemoen@atmel.com> +M: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> S: Supported F: arch/avr32/mach-at32ap/ @@ -2199,6 +2199,12 @@ W: http://acpi4asus.sf.net S: Maintained F: drivers/platform/x86/eeepc-laptop.c +EFIFB FRAMEBUFFER DRIVER +L: linux-fbdev@vger.kernel.org +M: Peter Jones <pjones@redhat.com> +S: Maintained +F: drivers/video/efifb.c + EFS FILESYSTEM W: http://aeschi.ch.eu.org/efs/ S: Orphan diff --git a/arch/Kconfig b/arch/Kconfig index 4877a8c8ee1..fe48fc7a3eb 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -32,8 +32,9 @@ config HAVE_OPROFILE config KPROBES bool "Kprobes" - depends on KALLSYMS && MODULES + depends on MODULES depends on HAVE_KPROBES + select KALLSYMS help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes @@ -45,7 +46,6 @@ config OPTPROBES def_bool y depends on KPROBES && HAVE_OPTPROBES depends on !PREEMPT - select KALLSYMS_ALL config HAVE_EFFICIENT_UNALIGNED_ACCESS bool diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c index 7974baacafc..1bec96e8519 100644 --- a/arch/arm/common/it8152.c +++ b/arch/arm/common/it8152.c @@ -271,6 +271,14 @@ int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) ((dma_addr + size - PHYS_OFFSET) >= SZ_64M); } +int dma_set_coherent_mask(struct device *dev, u64 mask) +{ + if (mask >= PHYS_OFFSET + SZ_64M - 1) + return 0; + + return -EIO; +} + int __init it8152_pci_setup(int nr, struct pci_sys_data *sys) { it8152_io.start = IT8152_IO_BASE + 0x12000; diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c index 61cd4d64b98..24498a932ba 100644 --- a/arch/arm/mach-ixp4xx/common-pci.c +++ b/arch/arm/mach-ixp4xx/common-pci.c @@ -503,6 +503,14 @@ struct pci_bus * __devinit ixp4xx_scan_bus(int nr, struct pci_sys_data *sys) return pci_scan_bus(sys->busnr, &ixp4xx_ops, sys); } +int dma_set_coherent_mask(struct device *dev, u64 mask) +{ + if (mask >= SZ_64M - 1) + return 0; + + return -EIO; +} + EXPORT_SYMBOL(ixp4xx_pci_read); EXPORT_SYMBOL(ixp4xx_pci_write); diff --git a/arch/arm/mach-ixp4xx/include/mach/hardware.h b/arch/arm/mach-ixp4xx/include/mach/hardware.h index f91ca6d4fbe..8138371c406 100644 --- a/arch/arm/mach-ixp4xx/include/mach/hardware.h +++ b/arch/arm/mach-ixp4xx/include/mach/hardware.h @@ -26,6 +26,8 @@ #define PCIBIOS_MAX_MEM 0x4BFFFFFF #endif +#define ARCH_HAS_DMA_SET_COHERENT_MASK + #define pcibios_assign_all_busses() 1 /* Register locations and bits */ diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h index 7f64d24cd56..428cc7bda9a 100644 --- a/arch/arm/mach-pxa/include/mach/hardware.h +++ b/arch/arm/mach-pxa/include/mach/hardware.h @@ -309,7 +309,7 @@ extern unsigned long get_clock_tick_rate(void); #define PCIBIOS_MIN_IO 0 #define PCIBIOS_MIN_MEM 0 #define pcibios_assign_all_busses() 1 +#define ARCH_HAS_DMA_SET_COHERENT_MASK #endif - #endif /* _ASM_ARCH_HARDWARE_H */ diff --git a/arch/arm/mach-pxa/include/mach/io.h b/arch/arm/mach-pxa/include/mach/io.h index 262691fb97d..fdca3be47d9 100644 --- a/arch/arm/mach-pxa/include/mach/io.h +++ b/arch/arm/mach-pxa/include/mach/io.h @@ -6,6 +6,8 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H +#include <mach/hardware.h> + #define IO_SPACE_LIMIT 0xffffffff /* diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 7109f5b1baa..2300426e531 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -138,6 +138,7 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs) ti->local_flags &= ~_TLF_RESTORE_SIGMASK; sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); } + regs->trap = 0; return 0; /* no signals delivered */ } @@ -164,6 +165,7 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs) ret = handle_rt_signal64(signr, &ka, &info, oldset, regs); } + regs->trap = 0; if (ret) { spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked, ¤t->blocked, diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 266610119f6..b96a3a010c2 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -511,6 +511,7 @@ static long restore_user_regs(struct pt_regs *regs, if (!sig) save_r2 = (unsigned int)regs->gpr[2]; err = restore_general_regs(regs, sr); + regs->trap = 0; err |= __get_user(msr, &sr->mc_gregs[PT_MSR]); if (!sig) regs->gpr[2] = (unsigned long) save_r2; @@ -884,7 +885,6 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, regs->nip = (unsigned long) ka->sa.sa_handler; /* enter the signal handler in big-endian mode */ regs->msr &= ~MSR_LE; - regs->trap = 0; return 1; badframe: @@ -1228,7 +1228,6 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, regs->nip = (unsigned long) ka->sa.sa_handler; /* enter the signal handler in big-endian mode */ regs->msr &= ~MSR_LE; - regs->trap = 0; return 1; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 2fe6fc64b61..27c4a4584f8 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -178,7 +178,7 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, err |= __get_user(regs->xer, &sc->gp_regs[PT_XER]); err |= __get_user(regs->ccr, &sc->gp_regs[PT_CCR]); /* skip SOFTE */ - err |= __get_user(regs->trap, &sc->gp_regs[PT_TRAP]); + regs->trap = 0; err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]); err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]); err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]); diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 357ced3c33f..6318e622cfb 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1038,6 +1038,7 @@ static int __hw_perf_event_init(struct perf_event *event) if (atomic_read(&nmi_active) < 0) return -ENODEV; + pmap = NULL; if (attr->type == PERF_TYPE_HARDWARE) { if (attr->config >= sparc_pmu->max_events) return -EINVAL; @@ -1046,9 +1047,18 @@ static int __hw_perf_event_init(struct perf_event *event) pmap = sparc_map_cache_event(attr->config); if (IS_ERR(pmap)) return PTR_ERR(pmap); - } else + } else if (attr->type != PERF_TYPE_RAW) return -EOPNOTSUPP; + if (pmap) { + hwc->event_base = perf_event_encode(pmap); + } else { + /* User gives us "(encoding << 16) | pic_mask" for + * PERF_TYPE_RAW events. + */ + hwc->event_base = attr->config; + } + /* We save the enable bits in the config_base. */ hwc->config_base = sparc_pmu->irq_bit; if (!attr->exclude_user) @@ -1058,8 +1068,6 @@ static int __hw_perf_event_init(struct perf_event *event) if (!attr->exclude_hv) hwc->config_base |= sparc_pmu->hv_bit; - hwc->event_base = perf_event_encode(pmap); - n = 0; if (event->group_leader != event) { n = collect_events(event->group_leader, diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index ea22cd373c6..75fad425e24 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -453,8 +453,66 @@ static int save_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) return err; } -static void setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, - int signo, sigset_t *oldset) +/* The I-cache flush instruction only works in the primary ASI, which + * right now is the nucleus, aka. kernel space. + * + * Therefore we have to kick the instructions out using the kernel + * side linear mapping of the physical address backing the user + * instructions. + */ +static void flush_signal_insns(unsigned long address) +{ + unsigned long pstate, paddr; + pte_t *ptep, pte; + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + + /* Commit all stores of the instructions we are about to flush. */ + wmb(); + + /* Disable cross-call reception. In this way even a very wide + * munmap() on another cpu can't tear down the page table + * hierarchy from underneath us, since that can't complete + * until the IPI tlb flush returns. + */ + + __asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate)); + __asm__ __volatile__("wrpr %0, %1, %%pstate" + : : "r" (pstate), "i" (PSTATE_IE)); + + pgdp = pgd_offset(current->mm, address); + if (pgd_none(*pgdp)) + goto out_irqs_on; + pudp = pud_offset(pgdp, address); + if (pud_none(*pudp)) + goto out_irqs_on; + pmdp = pmd_offset(pudp, address); + if (pmd_none(*pmdp)) + goto out_irqs_on; + + ptep = pte_offset_map(pmdp, address); + pte = *ptep; + if (!pte_present(pte)) + goto out_unmap; + + paddr = (unsigned long) page_address(pte_page(pte)); + + __asm__ __volatile__("flush %0 + %1" + : /* no outputs */ + : "r" (paddr), + "r" (address & (PAGE_SIZE - 1)) + : "memory"); + +out_unmap: + pte_unmap(ptep); +out_irqs_on: + __asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate)); + +} + +static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, + int signo, sigset_t *oldset) { struct signal_frame32 __user *sf; int sigframe_size; @@ -547,13 +605,7 @@ static void setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (ka->ka_restorer) { regs->u_regs[UREG_I7] = (unsigned long)ka->ka_restorer; } else { - /* Flush instruction space. */ unsigned long address = ((unsigned long)&(sf->insns[0])); - pgd_t *pgdp = pgd_offset(current->mm, address); - pud_t *pudp = pud_offset(pgdp, address); - pmd_t *pmdp = pmd_offset(pudp, address); - pte_t *ptep; - pte_t pte; regs->u_regs[UREG_I7] = (unsigned long) (&(sf->insns[0]) - 2); @@ -562,34 +614,22 @@ static void setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (err) goto sigsegv; - preempt_disable(); - ptep = pte_offset_map(pmdp, address); - pte = *ptep; - if (pte_present(pte)) { - unsigned long page = (unsigned long) - page_address(pte_page(pte)); - - wmb(); - __asm__ __volatile__("flush %0 + %1" - : /* no outputs */ - : "r" (page), - "r" (address & (PAGE_SIZE - 1)) - : "memory"); - } - pte_unmap(ptep); - preempt_enable(); + flush_signal_insns(address); } - return; + return 0; sigill: do_exit(SIGILL); + return -EINVAL; + sigsegv: force_sigsegv(signo, current); + return -EFAULT; } -static void setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, - unsigned long signr, sigset_t *oldset, - siginfo_t *info) +static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, + unsigned long signr, sigset_t *oldset, + siginfo_t *info) { struct rt_signal_frame32 __user *sf; int sigframe_size; @@ -687,12 +727,7 @@ static void setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (ka->ka_restorer) regs->u_regs[UREG_I7] = (unsigned long)ka->ka_restorer; else { - /* Flush instruction space. */ unsigned long address = ((unsigned long)&(sf->insns[0])); - pgd_t *pgdp = pgd_offset(current->mm, address); - pud_t *pudp = pud_offset(pgdp, address); - pmd_t *pmdp = pmd_offset(pudp, address); - pte_t *ptep; regs->u_regs[UREG_I7] = (unsigned long) (&(sf->insns[0]) - 2); @@ -704,38 +739,32 @@ static void setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (err) goto sigsegv; - preempt_disable(); - ptep = pte_offset_map(pmdp, address); - if (pte_present(*ptep)) { - unsigned long page = (unsigned long) - page_address(pte_page(*ptep)); - - wmb(); - __asm__ __volatile__("flush %0 + %1" - : /* no outputs */ - : "r" (page), - "r" (address & (PAGE_SIZE - 1)) - : "memory"); - } - pte_unmap(ptep); - preempt_enable(); + flush_signal_insns(address); } - return; + return 0; sigill: do_exit(SIGILL); + return -EINVAL; + sigsegv: force_sigsegv(signr, current); + return -EFAULT; } -static inline void handle_signal32(unsigned long signr, struct k_sigaction *ka, - siginfo_t *info, - sigset_t *oldset, struct pt_regs *regs) +static inline int handle_signal32(unsigned long signr, struct k_sigaction *ka, + siginfo_t *info, + sigset_t *oldset, struct pt_regs *regs) { + int err; + if (ka->sa.sa_flags & SA_SIGINFO) - setup_rt_frame32(ka, regs, signr, oldset, info); + err = setup_rt_frame32(ka, regs, signr, oldset, info); else - setup_frame32(ka, regs, signr, oldset); + err = setup_frame32(ka, regs, signr, oldset); + + if (err) + return err; spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); @@ -743,6 +772,10 @@ static inline void handle_signal32(unsigned long signr, struct k_sigaction *ka, sigaddset(¤t->blocked,signr); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); + + tracehook_signal_handler(signr, info, ka, regs, 0); + + return 0; } static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs, @@ -789,16 +822,14 @@ void do_signal32(sigset_t *oldset, struct pt_regs * regs, if (signr > 0) { if (restart_syscall) syscall_restart32(orig_i0, regs, &ka.sa); - handle_signal32(signr, &ka, &info, oldset, regs); - - /* A signal was successfully delivered; the saved - * sigmask will have been stored in the signal frame, - * and will be restored by sigreturn, so we can simply - * clear the TS_RESTORE_SIGMASK flag. - */ - current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - - tracehook_signal_handler(signr, &info, &ka, regs, 0); + if (handle_signal32(signr, &ka, &info, oldset, regs) == 0) { + /* A signal was successfully delivered; the saved + * sigmask will have been stored in the signal frame, + * and will be restored by sigreturn, so we can simply + * clear the TS_RESTORE_SIGMASK flag. + */ + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; + } return; } if (restart_syscall && @@ -809,12 +840,14 @@ void do_signal32(sigset_t *oldset, struct pt_regs * regs, regs->u_regs[UREG_I0] = orig_i0; regs->tpc -= 4; regs->tnpc -= 4; + pt_regs_clear_syscall(regs); } if (restart_syscall && regs->u_regs[UREG_I0] == ERESTART_RESTARTBLOCK) { regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->tpc -= 4; regs->tnpc -= 4; + pt_regs_clear_syscall(regs); } /* If there's no signal to deliver, we just put the saved sigmask diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 9882df92ba0..5e5c5fd0378 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -315,8 +315,8 @@ save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) return err; } -static void setup_frame(struct k_sigaction *ka, struct pt_regs *regs, - int signo, sigset_t *oldset) +static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs, + int signo, sigset_t *oldset) { struct signal_frame __user *sf; int sigframe_size, err; @@ -384,16 +384,19 @@ static void setup_frame(struct k_sigaction *ka, struct pt_regs *regs, /* Flush instruction space. */ flush_sig_insns(current->mm, (unsigned long) &(sf->insns[0])); } - return; + return 0; sigill_and_return: do_exit(SIGILL); + return -EINVAL; + sigsegv: force_sigsegv(signo, current); + return -EFAULT; } -static void setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, - int signo, sigset_t *oldset, siginfo_t *info) +static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, + int signo, sigset_t *oldset, siginfo_t *info) { struct rt_signal_frame __user *sf; int sigframe_size; @@ -466,22 +469,30 @@ static void setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, /* Flush instruction space. */ flush_sig_insns(current->mm, (unsigned long) &(sf->insns[0])); } - return; + return 0; sigill: do_exit(SIGILL); + return -EINVAL; + sigsegv: force_sigsegv(signo, current); + return -EFAULT; } -static inline void +static inline int handle_signal(unsigned long signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + int err; + if (ka->sa.sa_flags & SA_SIGINFO) - setup_rt_frame(ka, regs, signr, oldset, info); + err = setup_rt_frame(ka, regs, signr, oldset, info); else - setup_frame(ka, regs, signr, oldset); + err = setup_frame(ka, regs, signr, oldset); + + if (err) + return err; spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); @@ -489,6 +500,10 @@ handle_signal(unsigned long signr, struct k_sigaction *ka, sigaddset(¤t->blocked, signr); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); + + tracehook_signal_handler(signr, info, ka, regs, 0); + + return 0; } static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs, @@ -546,17 +561,15 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) if (signr > 0) { if (restart_syscall) syscall_restart(orig_i0, regs, &ka.sa); - handle_signal(signr, &ka, &info, oldset, regs); - - /* a signal was successfully delivered; the saved - * sigmask will have been stored in the signal frame, - * and will be restored by sigreturn, so we can simply - * clear the TIF_RESTORE_SIGMASK flag. - */ - if (test_thread_flag(TIF_RESTORE_SIGMASK)) - clear_thread_flag(TIF_RESTORE_SIGMASK); - - tracehook_signal_handler(signr, &info, &ka, regs, 0); + if (handle_signal(signr, &ka, &info, oldset, regs) == 0) { + /* a signal was successfully delivered; the saved + * sigmask will have been stored in the signal frame, + * and will be restored by sigreturn, so we can simply + * clear the TIF_RESTORE_SIGMASK flag. + */ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + clear_thread_flag(TIF_RESTORE_SIGMASK); + } return; } if (restart_syscall && @@ -567,12 +580,14 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) regs->u_regs[UREG_I0] = orig_i0; regs->pc -= 4; regs->npc -= 4; + pt_regs_clear_syscall(regs); } if (restart_syscall && regs->u_regs[UREG_I0] == ERESTART_RESTARTBLOCK) { regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->pc -= 4; regs->npc -= 4; + pt_regs_clear_syscall(regs); } /* if there's no signal to deliver, we just put the saved sigmask diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 9fa48c30037..006fe451588 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -409,7 +409,7 @@ static inline void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs * return (void __user *) sp; } -static inline void +static inline int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, int signo, sigset_t *oldset, siginfo_t *info) { @@ -483,26 +483,37 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, } /* 4. return to kernel instructions */ regs->u_regs[UREG_I7] = (unsigned long)ka->ka_restorer; - return; + return 0; sigill: do_exit(SIGILL); + return -EINVAL; + sigsegv: force_sigsegv(signo, current); + return -EFAULT; } -static inline void handle_signal(unsigned long signr, struct k_sigaction *ka, - siginfo_t *info, - sigset_t *oldset, struct pt_regs *regs) +static inline int handle_signal(unsigned long signr, struct k_sigaction *ka, + siginfo_t *info, + sigset_t *oldset, struct pt_regs *regs) { - setup_rt_frame(ka, regs, signr, oldset, - (ka->sa.sa_flags & SA_SIGINFO) ? info : NULL); + int err; + + err = setup_rt_frame(ka, regs, signr, oldset, + (ka->sa.sa_flags & SA_SIGINFO) ? info : NULL); + if (err) + return err; spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NOMASK)) sigaddset(¤t->blocked,signr); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); + + tracehook_signal_handler(signr, info, ka, regs, 0); + + return 0; } static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs, @@ -571,16 +582,14 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) if (signr > 0) { if (restart_syscall) syscall_restart(orig_i0, regs, &ka.sa); - handle_signal(signr, &ka, &info, oldset, regs); - - /* A signal was successfully delivered; the saved - * sigmask will have been stored in the signal frame, - * and will be restored by sigreturn, so we can simply - * clear the TS_RESTORE_SIGMASK flag. - */ - current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - - tracehook_signal_handler(signr, &info, &ka, regs, 0); + if (handle_signal(signr, &ka, &info, oldset, regs) == 0) { + /* A signal was successfully delivered; the saved + * sigmask will have been stored in the signal frame, + * and will be restored by sigreturn, so we can simply + * clear the TS_RESTORE_SIGMASK flag. + */ + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; + } return; } if (restart_syscall && @@ -591,12 +600,14 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) regs->u_regs[UREG_I0] = orig_i0; regs->tpc -= 4; regs->tnpc -= 4; + pt_regs_clear_syscall(regs); } if (restart_syscall && regs->u_regs[UREG_I0] == ERESTART_RESTARTBLOCK) { regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->tpc -= 4; regs->tnpc -= 4; + pt_regs_clear_syscall(regs); } /* If there's no signal to deliver, we just put the saved sigmask diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index cd145eda357..49b5e1eb326 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -62,7 +62,7 @@ static long execve1(const char *file, return error; } -long um_execve(const char *file, char __user *__user *argv, char __user *__user *env) +long um_execve(const char *file, const char __user *const __user *argv, const char __user *const __user *env) { long err; @@ -72,8 +72,8 @@ long um_execve(const char *file, char __user *__user *argv, char __user *__user return err; } -long sys_execve(const char __user *file, char __user *__user *argv, - char __user *__user *env) +long sys_execve(const char __user *file, const char __user *const __user *argv, + const char __user *const __user *env) { long error; char *filename; diff --git a/arch/um/kernel/internal.h b/arch/um/kernel/internal.h index 1303a105fe9..5bf97db24a0 100644 --- a/arch/um/kernel/internal.h +++ b/arch/um/kernel/internal.h @@ -1 +1 @@ -extern long um_execve(const char *file, char __user *__user *argv, char __user *__user *env); +extern long um_execve(const char *file, const char __user *const __user *argv, const char __user *const __user *env); diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c index 5ddb246626d..f958cb876ee 100644 --- a/arch/um/kernel/syscall.c +++ b/arch/um/kernel/syscall.c @@ -60,8 +60,8 @@ int kernel_execve(const char *filename, fs = get_fs(); set_fs(KERNEL_DS); - ret = um_execve(filename, (char __user *__user *)argv, - (char __user *__user *) envp); + ret = um_execve(filename, (const char __user *const __user *)argv, + (const char __user *const __user *) envp); set_fs(fs); return ret; diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index 528a11e8d3e..824ca07860d 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -20,7 +20,7 @@ struct arch_hw_breakpoint { #include <linux/list.h> /* Available HW breakpoint length encodings */ -#define X86_BREAKPOINT_LEN_X 0x00 +#define X86_BREAKPOINT_LEN_X 0x40 #define X86_BREAKPOINT_LEN_1 0x40 #define X86_BREAKPOINT_LEN_2 0x44 #define X86_BREAKPOINT_LEN_4 0x4c diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index a474ec37c32..ff15c9dcc25 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -206,11 +206,27 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp) int arch_bp_generic_fields(int x86_len, int x86_type, int *gen_len, int *gen_type) { - /* Len */ - switch (x86_len) { - case X86_BREAKPOINT_LEN_X: + /* Type */ + switch (x86_type) { + case X86_BREAKPOINT_EXECUTE: + if (x86_len != X86_BREAKPOINT_LEN_X) + return -EINVAL; + + *gen_type = HW_BREAKPOINT_X; *gen_len = sizeof(long); + return 0; + case X86_BREAKPOINT_WRITE: + *gen_type = HW_BREAKPOINT_W; break; + case X86_BREAKPOINT_RW: + *gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R; + break; + default: + return -EINVAL; + } + + /* Len */ + switch (x86_len) { case X86_BREAKPOINT_LEN_1: *gen_len = HW_BREAKPOINT_LEN_1; break; @@ -229,21 +245,6 @@ int arch_bp_generic_fields(int x86_len, int x86_type, return -EINVAL; } - /* Type */ - switch (x86_type) { - case X86_BREAKPOINT_EXECUTE: - *gen_type = HW_BREAKPOINT_X; - break; - case X86_BREAKPOINT_WRITE: - *gen_type = HW_BREAKPOINT_W; - break; - case X86_BREAKPOINT_RW: - *gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R; - break; - default: - return -EINVAL; - } - return 0; } @@ -316,9 +317,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) ret = -EINVAL; switch (info->len) { - case X86_BREAKPOINT_LEN_X: - align = sizeof(long) -1; - break; case X86_BREAKPOINT_LEN_1: align = 0; break; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 9257510b483..9d5f5584845 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -324,9 +324,8 @@ static void lguest_load_gdt(const struct desc_ptr *desc) } /* - * For a single GDT entry which changes, we do the lazy thing: alter our GDT, - * then tell the Host to reload the entire thing. This operation is so rare - * that this naive implementation is reasonable. + * For a single GDT entry which changes, we simply change our copy and + * then tell the host about it. */ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, const void *desc, int type) @@ -338,9 +337,13 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, } /* - * OK, I lied. There are three "thread local storage" GDT entries which change + * There are three "thread local storage" GDT entries which change * on every context switch (these three entries are how glibc implements - * __thread variables). So we have a hypercall specifically for this case. + * __thread variables). As an optimization, we have a hypercall + * specifically for this case. + * + * Wouldn't it be nicer to have a general LOAD_GDT_ENTRIES hypercall + * which took a range of entries? */ static void lguest_load_tls(struct thread_struct *t, unsigned int cpu) { diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index cfe4faabb0f..009b819f48d 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -671,7 +671,9 @@ static int __init ppro_init(char **cpu_type) case 14: *cpu_type = "i386/core"; break; - case 15: case 23: + case 0x0f: + case 0x16: + case 0x17: *cpu_type = "i386/core_2"; break; case 0x1a: diff --git a/block/blk-map.c b/block/blk-map.c index c65d7593f7f..ade0a08c909 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -307,7 +307,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, return PTR_ERR(bio); if (rq_data_dir(rq) == WRITE) - bio->bi_rw |= (1 << REQ_WRITE); + bio->bi_rw |= REQ_WRITE; if (do_copy) rq->cmd_flags |= REQ_COPY_USER; diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index f65c6f01c47..9eba291eb6f 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -1019,10 +1019,20 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create) */ atomic_set(&cfqg->ref, 1); - /* Add group onto cgroup list */ - sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor); - cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd, + /* + * Add group onto cgroup list. It might happen that bdi->dev is + * not initiliazed yet. Initialize this new group without major + * and minor info and this info will be filled in once a new thread + * comes for IO. See code above. + */ + if (bdi->dev) { + sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor); + cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd, MKDEV(major, minor)); + } else + cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd, + 0); + cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev); /* Add group on cfqd list */ diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 6124c2fd2d3..5e4fadcdece 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -4792,7 +4792,7 @@ static int __devinit cciss_init_one(struct pci_dev *pdev, clean4: kfree(h->cmd_pool_bits); /* Free up sg elements */ - for (k = 0; k < h->nr_cmds; k++) + for (k-- ; k >= 0; k--) kfree(h->scatter_list[k]); kfree(h->scatter_list); cciss_free_sg_chain_blocks(h->cmd_sg_list, h->nr_cmds); diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index eab58db5f91..cd18493c952 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -806,6 +806,8 @@ static const struct intel_driver_description { "G45/G43", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_B43_HB, PCI_DEVICE_ID_INTEL_B43_IG, "B43", NULL, &intel_i965_driver }, + { PCI_DEVICE_ID_INTEL_B43_1_HB, PCI_DEVICE_ID_INTEL_B43_1_IG, + "B43", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_G41_HB, PCI_DEVICE_ID_INTEL_G41_IG, "G41", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_IRONLAKE_D_HB, PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG, diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h index ee189c74d34..d09b1ab7e8a 100644 --- a/drivers/char/agp/intel-agp.h +++ b/drivers/char/agp/intel-agp.h @@ -186,6 +186,8 @@ #define PCI_DEVICE_ID_INTEL_Q33_IG 0x29D2 #define PCI_DEVICE_ID_INTEL_B43_HB 0x2E40 #define PCI_DEVICE_ID_INTEL_B43_IG 0x2E42 +#define PCI_DEVICE_ID_INTEL_B43_1_HB 0x2E90 +#define PCI_DEVICE_ID_INTEL_B43_1_IG 0x2E92 #define PCI_DEVICE_ID_INTEL_GM45_HB 0x2A40 #define PCI_DEVICE_ID_INTEL_GM45_IG 0x2A42 #define PCI_DEVICE_ID_INTEL_EAGLELAKE_HB 0x2E00 diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 3822b4f49c8..7bd7c45b53e 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -305,6 +305,9 @@ static int num_force_kipmid; #ifdef CONFIG_PCI static int pci_registered; #endif +#ifdef CONFIG_ACPI +static int pnp_registered; +#endif #ifdef CONFIG_PPC_OF static int of_registered; #endif @@ -2126,7 +2129,7 @@ static int __devinit ipmi_pnp_probe(struct pnp_dev *dev, { struct acpi_device *acpi_dev; struct smi_info *info; - struct resource *res; + struct resource *res, *res_second; acpi_handle handle; acpi_status status; unsigned long long tmp; @@ -2182,13 +2185,13 @@ static int __devinit ipmi_pnp_probe(struct pnp_dev *dev, info->io.addr_data = res->start; info->io.regspacing = DEFAULT_REGSPACING; - res = pnp_get_resource(dev, + res_second = pnp_get_resource(dev, (info->io.addr_type == IPMI_IO_ADDR_SPACE) ? IORESOURCE_IO : IORESOURCE_MEM, 1); - if (res) { - if (res->start > info->io.addr_data) - info->io.regspacing = res->start - info->io.addr_data; + if (res_second) { + if (res_second->start > info->io.addr_data) + info->io.regspacing = res_second->start - info->io.addr_data; } info->io.regsize = DEFAULT_REGSPACING; info->io.regshift = 0; @@ -3359,6 +3362,7 @@ static __devinit int init_ipmi_si(void) #ifdef CONFIG_ACPI pnp_register_driver(&ipmi_pnp_driver); + pnp_registered = 1; #endif #ifdef CONFIG_DMI @@ -3526,7 +3530,8 @@ static __exit void cleanup_ipmi_si(void) pci_unregister_driver(&ipmi_pci_driver); #endif #ifdef CONFIG_ACPI - pnp_unregister_driver(&ipmi_pnp_driver); + if (pnp_registered) + pnp_unregister_driver(&ipmi_pnp_driver); #endif #ifdef CONFIG_PPC_OF diff --git a/drivers/char/mem.c b/drivers/char/mem.c index a398ecdbd75..1f528fad351 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -788,10 +788,11 @@ static const struct file_operations zero_fops = { /* * capabilities for /dev/zero * - permits private mappings, "copies" are taken of the source of zeros + * - no writeback happens */ static struct backing_dev_info zero_bdi = { .name = "char/mem", - .capabilities = BDI_CAP_MAP_COPY, + .capabilities = BDI_CAP_MAP_COPY | BDI_CAP_NO_ACCT_AND_WRITEBACK, }; static const struct file_operations full_fops = { diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 942a9826bd2..c810481a5bc 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -596,6 +596,10 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf, ssize_t ret; bool nonblock; + /* Userspace could be out to fool us */ + if (!count) + return 0; + port = filp->private_data; nonblock = filp->f_flags & O_NONBLOCK; @@ -642,7 +646,7 @@ static unsigned int port_fops_poll(struct file *filp, poll_table *wait) poll_wait(filp, &port->waitqueue, wait); ret = 0; - if (port->inbuf) + if (!will_read_block(port)) ret |= POLLIN | POLLRDNORM; if (!will_write_block(port)) ret |= POLLOUT; diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 216deb57978..6dbe14cc4f7 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -170,6 +170,7 @@ static const struct pci_device_id pciidlist[] = { /* aka */ INTEL_VGA_DEVICE(0x2e22, &intel_g45_info), /* G45_G */ INTEL_VGA_DEVICE(0x2e32, &intel_g45_info), /* G41_G */ INTEL_VGA_DEVICE(0x2e42, &intel_g45_info), /* B43_G */ + INTEL_VGA_DEVICE(0x2e92, &intel_g45_info), /* B43_G.1 */ INTEL_VGA_DEVICE(0xa001, &intel_pineview_info), INTEL_VGA_DEVICE(0xa011, &intel_pineview_info), INTEL_VGA_DEVICE(0x0042, &intel_ironlake_d_info), diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 16fca1d1799..cf4ffbee1c0 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2351,14 +2351,21 @@ i915_gem_object_get_fence_reg(struct drm_gem_object *obj) reg->obj = obj; - if (IS_GEN6(dev)) + switch (INTEL_INFO(dev)->gen) { + case 6: sandybridge_write_fence_reg(reg); - else if (IS_I965G(dev)) + break; + case 5: + case 4: i965_write_fence_reg(reg); - else if (IS_I9XX(dev)) + break; + case 3: i915_write_fence_reg(reg); - else + break; + case 2: i830_write_fence_reg(reg); + break; + } trace_i915_gem_object_get_fence(obj, obj_priv->fence_reg, obj_priv->tiling_mode); @@ -2381,22 +2388,26 @@ i915_gem_clear_fence_reg(struct drm_gem_object *obj) struct drm_i915_gem_object *obj_priv = to_intel_bo(obj); struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[obj_priv->fence_reg]; + uint32_t fence_reg; - if (IS_GEN6(dev)) { + switch (INTEL_INFO(dev)->gen) { + case 6: I915_WRITE64(FENCE_REG_SANDYBRIDGE_0 + (obj_priv->fence_reg * 8), 0); - } else if (IS_I965G(dev)) { + break; + case 5: + case 4: I915_WRITE64(FENCE_REG_965_0 + (obj_priv->fence_reg * 8), 0); - } else { - uint32_t fence_reg; - - if (obj_priv->fence_reg < 8) - fence_reg = FENCE_REG_830_0 + obj_priv->fence_reg * 4; + break; + case 3: + if (obj_priv->fence_reg > 8) + fence_reg = FENCE_REG_945_8 + (obj_priv->fence_reg - 8) * 4; else - fence_reg = FENCE_REG_945_8 + (obj_priv->fence_reg - - 8) * 4; + case 2: + fence_reg = FENCE_REG_830_0 + obj_priv->fence_reg * 4; I915_WRITE(fence_reg, 0); + break; } reg->obj = NULL; diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index 72cae3cccad..e85246ef691 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -79,6 +79,7 @@ mark_free(struct drm_i915_gem_object *obj_priv, struct list_head *unwind) { list_add(&obj_priv->evict_list, unwind); + drm_gem_object_reference(&obj_priv->base); return drm_mm_scan_add_block(obj_priv->gtt_space); } @@ -165,6 +166,7 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, unsigned alignmen list_for_each_entry(obj_priv, &unwind_list, evict_list) { ret = drm_mm_scan_remove_block(obj_priv->gtt_space); BUG_ON(ret); + drm_gem_object_unreference(&obj_priv->base); } /* We expect the caller to unpin, evict all and try again, or give up. @@ -181,18 +183,21 @@ found: * scanning, therefore store to be evicted objects on a * temporary list. */ list_move(&obj_priv->evict_list, &eviction_list); - } + } else + drm_gem_object_unreference(&obj_priv->base); } /* Unbinding will emit any required flushes */ list_for_each_entry_safe(obj_priv, tmp_obj_priv, &eviction_list, evict_list) { #if WATCH_LRU - DRM_INFO("%s: evicting %p\n", __func__, obj); + DRM_INFO("%s: evicting %p\n", __func__, &obj_priv->base); #endif ret = i915_gem_object_unbind(&obj_priv->base); if (ret) return ret; + + drm_gem_object_unreference(&obj_priv->base); } /* The just created free hole should be on the top of the free stack diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 2c6b98f2440..31f08581e93 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -789,16 +789,25 @@ int i915_save_state(struct drm_device *dev) dev_priv->saveSWF2[i] = I915_READ(SWF30 + (i << 2)); /* Fences */ - if (IS_I965G(dev)) { + switch (INTEL_INFO(dev)->gen) { + case 6: + for (i = 0; i < 16; i++) + dev_priv->saveFENCE[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8)); + break; + case 5: + case 4: for (i = 0; i < 16; i++) dev_priv->saveFENCE[i] = I915_READ64(FENCE_REG_965_0 + (i * 8)); - } else { - for (i = 0; i < 8; i++) - dev_priv->saveFENCE[i] = I915_READ(FENCE_REG_830_0 + (i * 4)); - + break; + case 3: if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) for (i = 0; i < 8; i++) dev_priv->saveFENCE[i+8] = I915_READ(FENCE_REG_945_8 + (i * 4)); + case 2: + for (i = 0; i < 8; i++) + dev_priv->saveFENCE[i] = I915_READ(FENCE_REG_830_0 + (i * 4)); + break; + } return 0; @@ -815,15 +824,24 @@ int i915_restore_state(struct drm_device *dev) I915_WRITE(HWS_PGA, dev_priv->saveHWS); /* Fences */ - if (IS_I965G(dev)) { + switch (INTEL_INFO(dev)->gen) { + case 6: + for (i = 0; i < 16; i++) + I915_WRITE64(FENCE_REG_SANDYBRIDGE_0 + (i * 8), dev_priv->saveFENCE[i]); + break; + case 5: + case 4: for (i = 0; i < 16; i++) I915_WRITE64(FENCE_REG_965_0 + (i * 8), dev_priv->saveFENCE[i]); - } else { - for (i = 0; i < 8; i++) - I915_WRITE(FENCE_REG_830_0 + (i * 4), dev_priv->saveFENCE[i]); + break; + case 3: + case 2: if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) for (i = 0; i < 8; i++) I915_WRITE(FENCE_REG_945_8 + (i * 4), dev_priv->saveFENCE[i+8]); + for (i = 0; i < 8; i++) + I915_WRITE(FENCE_REG_830_0 + (i * 4), dev_priv->saveFENCE[i]); + break; } i915_restore_display(dev); diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index a02a8df7372..197d4f32585 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -188,7 +188,7 @@ static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector) if (wait_for((I915_READ(PCH_ADPA) & ADPA_CRT_HOTPLUG_FORCE_TRIGGER) == 0, 1000, 1)) - DRM_ERROR("timed out waiting for FORCE_TRIGGER"); + DRM_DEBUG_KMS("timed out waiting for FORCE_TRIGGER"); if (turn_off_dac) { I915_WRITE(PCH_ADPA, temp); @@ -245,7 +245,7 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector) if (wait_for((I915_READ(PORT_HOTPLUG_EN) & CRT_HOTPLUG_FORCE_DETECT) == 0, 1000, 1)) - DRM_ERROR("timed out waiting for FORCE_DETECT to go off"); + DRM_DEBUG_KMS("timed out waiting for FORCE_DETECT to go off"); } stat = I915_READ(PORT_HOTPLUG_STAT); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 19daead5b52..b5bf51a4502 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2463,11 +2463,19 @@ static bool intel_crtc_mode_fixup(struct drm_crtc *crtc, struct drm_display_mode *adjusted_mode) { struct drm_device *dev = crtc->dev; + if (HAS_PCH_SPLIT(dev)) { /* FDI link clock is fixed at 2.7G */ if (mode->clock * 3 > IRONLAKE_FDI_FREQ * 4) return false; } + + /* XXX some encoders set the crtcinfo, others don't. + * Obviously we need some form of conflict resolution here... + */ + if (adjusted_mode->crtc_htotal == 0) + drm_mode_set_crtcinfo(adjusted_mode, 0); + return true; } diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 7674efb5537..b33c78586bf 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -680,6 +680,8 @@ omap_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) if (r == 0) r = num; + + omap_i2c_wait_for_bb(dev); out: omap_i2c_idle(dev); return r; diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 0b591b65824..b7433126074 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -368,7 +368,7 @@ config VMWARE_BALLOON If unsure, say N. To compile this driver as a module, choose M here: the - module will be called vmware_balloon. + module will be called vmw_balloon. config ARM_CHARLCD bool "ARM Ltd. Character LCD Driver" diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index 255a80dc9d7..42eab95cde2 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -33,5 +33,5 @@ obj-$(CONFIG_IWMC3200TOP) += iwmc3200top/ obj-$(CONFIG_HMC6352) += hmc6352.o obj-y += eeprom/ obj-y += cb710/ -obj-$(CONFIG_VMWARE_BALLOON) += vmware_balloon.o +obj-$(CONFIG_VMWARE_BALLOON) += vmw_balloon.o obj-$(CONFIG_ARM_CHARLCD) += arm-charlcd.o diff --git a/drivers/misc/vmware_balloon.c b/drivers/misc/vmw_balloon.c index 2a1e804a71a..2a1e804a71a 100644 --- a/drivers/misc/vmware_balloon.c +++ b/drivers/misc/vmw_balloon.c diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index c3ceebb5be8..5ac2aa783f5 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -71,6 +71,49 @@ #define DMA_32BIT_PFN IOVA_PFN(DMA_BIT_MASK(32)) #define DMA_64BIT_PFN IOVA_PFN(DMA_BIT_MASK(64)) +/* page table handling */ +#define LEVEL_STRIDE (9) +#define LEVEL_MASK (((u64)1 << LEVEL_STRIDE) - 1) + +static inline int agaw_to_level(int agaw) +{ + return agaw + 2; +} + +static inline int agaw_to_width(int agaw) +{ + return 30 + agaw * LEVEL_STRIDE; +} + +static inline int width_to_agaw(int width) +{ + return (width - 30) / LEVEL_STRIDE; +} + +static inline unsigned int level_to_offset_bits(int level) +{ + return (level - 1) * LEVEL_STRIDE; +} + +static inline int pfn_level_offset(unsigned long pfn, int level) +{ + return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK; +} + +static inline unsigned long level_mask(int level) +{ + return -1UL << level_to_offset_bits(level); +} + +static inline unsigned long level_size(int level) +{ + return 1UL << level_to_offset_bits(level); +} + +static inline unsigned long align_to_level(unsigned long pfn, int level) +{ + return (pfn + level_size(level) - 1) & level_mask(level); +} /* VT-d pages must always be _smaller_ than MM pages. Otherwise things are never going to work. */ @@ -434,8 +477,6 @@ void free_iova_mem(struct iova *iova) } -static inline int width_to_agaw(int width); - static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw) { unsigned long sagaw; @@ -646,51 +687,6 @@ out: spin_unlock_irqrestore(&iommu->lock, flags); } -/* page table handling */ -#define LEVEL_STRIDE (9) -#define LEVEL_MASK (((u64)1 << LEVEL_STRIDE) - 1) - -static inline int agaw_to_level(int agaw) -{ - return agaw + 2; -} - -static inline int agaw_to_width(int agaw) -{ - return 30 + agaw * LEVEL_STRIDE; - -} - -static inline int width_to_agaw(int width) -{ - return (width - 30) / LEVEL_STRIDE; -} - -static inline unsigned int level_to_offset_bits(int level) -{ - return (level - 1) * LEVEL_STRIDE; -} - -static inline int pfn_level_offset(unsigned long pfn, int level) -{ - return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK; -} - -static inline unsigned long level_mask(int level) -{ - return -1UL << level_to_offset_bits(level); -} - -static inline unsigned long level_size(int level) -{ - return 1UL << level_to_offset_bits(level); -} - -static inline unsigned long align_to_level(unsigned long pfn, int level) -{ - return (pfn + level_size(level) - 1) & level_mask(level); -} - static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, unsigned long pfn) { diff --git a/drivers/rtc/rtc-ab3100.c b/drivers/rtc/rtc-ab3100.c index d26780ea254..261a07e0fb2 100644 --- a/drivers/rtc/rtc-ab3100.c +++ b/drivers/rtc/rtc-ab3100.c @@ -235,6 +235,7 @@ static int __init ab3100_rtc_probe(struct platform_device *pdev) err = PTR_ERR(rtc); return err; } + platform_set_drvdata(pdev, rtc); return 0; } @@ -244,6 +245,7 @@ static int __exit ab3100_rtc_remove(struct platform_device *pdev) struct rtc_device *rtc = platform_get_drvdata(pdev); rtc_device_unregister(rtc); + platform_set_drvdata(pdev, NULL); return 0; } diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index a0d3ec89d41..f57a87f4ae9 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -310,11 +310,6 @@ static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) s3c_rtc_setaie(alrm->enabled); - if (alrm->enabled) - enable_irq_wake(s3c_rtc_alarmno); - else - disable_irq_wake(s3c_rtc_alarmno); - return 0; } @@ -587,6 +582,10 @@ static int s3c_rtc_suspend(struct platform_device *pdev, pm_message_t state) ticnt_en_save &= S3C64XX_RTCCON_TICEN; } s3c_rtc_enable(pdev, 0); + + if (device_may_wakeup(&pdev->dev)) + enable_irq_wake(s3c_rtc_alarmno); + return 0; } @@ -600,6 +599,10 @@ static int s3c_rtc_resume(struct platform_device *pdev) tmp = readb(s3c_rtc_base + S3C2410_RTCCON); writeb(tmp | ticnt_en_save, s3c_rtc_base + S3C2410_RTCCON); } + + if (device_may_wakeup(&pdev->dev)) + disable_irq_wake(s3c_rtc_alarmno); + return 0; } #else diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 84f842331df..7ccc967831f 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -3508,7 +3508,7 @@ static void fbcon_exit(void) softback_buf = 0UL; for (i = 0; i < FB_MAX; i++) { - int pending; + int pending = 0; mapped = 0; info = registered_fb[i]; @@ -3516,7 +3516,8 @@ static void fbcon_exit(void) if (info == NULL) continue; - pending = cancel_work_sync(&info->queue); + if (info->queue.func) + pending = cancel_work_sync(&info->queue); DPRINTK("fbcon: %s pending work\n", (pending ? "canceled" : "no")); diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c index 815f84b0793..70477c2e4b6 100644 --- a/drivers/video/efifb.c +++ b/drivers/video/efifb.c @@ -13,7 +13,7 @@ #include <linux/platform_device.h> #include <linux/screen_info.h> #include <linux/dmi.h> - +#include <linux/pci.h> #include <video/vga.h> static struct fb_var_screeninfo efifb_defined __devinitdata = { @@ -39,17 +39,31 @@ enum { M_I20, /* 20-Inch iMac */ M_I20_SR, /* 20-Inch iMac (Santa Rosa) */ M_I24, /* 24-Inch iMac */ + M_I24_8_1, /* 24-Inch iMac, 8,1th gen */ + M_I24_10_1, /* 24-Inch iMac, 10,1th gen */ + M_I27_11_1, /* 27-Inch iMac, 11,1th gen */ M_MINI, /* Mac Mini */ + M_MINI_3_1, /* Mac Mini, 3,1th gen */ + M_MINI_4_1, /* Mac Mini, 4,1th gen */ M_MB, /* MacBook */ M_MB_2, /* MacBook, 2nd rev. */ M_MB_3, /* MacBook, 3rd rev. */ + M_MB_5_1, /* MacBook, 5th rev. */ + M_MB_6_1, /* MacBook, 6th rev. */ + M_MB_7_1, /* MacBook, 7th rev. */ M_MB_SR, /* MacBook, 2nd gen, (Santa Rosa) */ M_MBA, /* MacBook Air */ M_MBP, /* MacBook Pro */ M_MBP_2, /* MacBook Pro 2nd gen */ + M_MBP_2_2, /* MacBook Pro 2,2nd gen */ M_MBP_SR, /* MacBook Pro (Santa Rosa) */ M_MBP_4, /* MacBook Pro, 4th gen */ M_MBP_5_1, /* MacBook Pro, 5,1th gen */ + M_MBP_5_2, /* MacBook Pro, 5,2th gen */ + M_MBP_5_3, /* MacBook Pro, 5,3rd gen */ + M_MBP_6_1, /* MacBook Pro, 6,1th gen */ + M_MBP_6_2, /* MacBook Pro, 6,2th gen */ + M_MBP_7_1, /* MacBook Pro, 7,1th gen */ M_UNKNOWN /* placeholder */ }; @@ -64,14 +78,28 @@ static struct efifb_dmi_info { [M_I20] = { "i20", 0x80010000, 1728 * 4, 1680, 1050 }, /* guess */ [M_I20_SR] = { "imac7", 0x40010000, 1728 * 4, 1680, 1050 }, [M_I24] = { "i24", 0x80010000, 2048 * 4, 1920, 1200 }, /* guess */ + [M_I24_8_1] = { "imac8", 0xc0060000, 2048 * 4, 1920, 1200 }, + [M_I24_10_1] = { "imac10", 0xc0010000, 2048 * 4, 1920, 1080 }, + [M_I27_11_1] = { "imac11", 0xc0010000, 2560 * 4, 2560, 1440 }, [M_MINI]= { "mini", 0x80000000, 2048 * 4, 1024, 768 }, + [M_MINI_3_1] = { "mini31", 0x40010000, 1024 * 4, 1024, 768 }, + [M_MINI_4_1] = { "mini41", 0xc0010000, 2048 * 4, 1920, 1200 }, [M_MB] = { "macbook", 0x80000000, 2048 * 4, 1280, 800 }, + [M_MB_5_1] = { "macbook51", 0x80010000, 2048 * 4, 1280, 800 }, + [M_MB_6_1] = { "macbook61", 0x80010000, 2048 * 4, 1280, 800 }, + [M_MB_7_1] = { "macbook71", 0x80010000, 2048 * 4, 1280, 800 }, [M_MBA] = { "mba", 0x80000000, 2048 * 4, 1280, 800 }, [M_MBP] = { "mbp", 0x80010000, 1472 * 4, 1440, 900 }, [M_MBP_2] = { "mbp2", 0, 0, 0, 0 }, /* placeholder */ + [M_MBP_2_2] = { "mbp22", 0x80010000, 1472 * 4, 1440, 900 }, [M_MBP_SR] = { "mbp3", 0x80030000, 2048 * 4, 1440, 900 }, [M_MBP_4] = { "mbp4", 0xc0060000, 2048 * 4, 1920, 1200 }, [M_MBP_5_1] = { "mbp51", 0xc0010000, 2048 * 4, 1440, 900 }, + [M_MBP_5_2] = { "mbp52", 0xc0010000, 2048 * 4, 1920, 1200 }, + [M_MBP_5_3] = { "mbp53", 0xd0010000, 2048 * 4, 1440, 900 }, + [M_MBP_6_1] = { "mbp61", 0x90030000, 2048 * 4, 1920, 1200 }, + [M_MBP_6_2] = { "mbp62", 0x90030000, 2048 * 4, 1680, 1050 }, + [M_MBP_7_1] = { "mbp71", 0xc0010000, 2048 * 4, 1280, 800 }, [M_UNKNOWN] = { NULL, 0, 0, 0, 0 } }; @@ -92,7 +120,12 @@ static const struct dmi_system_id dmi_system_table[] __initconst = { EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac6,1", M_I24), EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac6,1", M_I24), EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac7,1", M_I20_SR), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac8,1", M_I24_8_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac10,1", M_I24_10_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac11,1", M_I27_11_1), EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "Macmini1,1", M_MINI), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini3,1", M_MINI_3_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini4,1", M_MINI_4_1), EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook1,1", M_MB), /* At least one of these two will be right; maybe both? */ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook2,1", M_MB), @@ -101,14 +134,23 @@ static const struct dmi_system_id dmi_system_table[] __initconst = { EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook3,1", M_MB), EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook3,1", M_MB), EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook4,1", M_MB), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook5,1", M_MB_5_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook6,1", M_MB_6_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook7,1", M_MB_7_1), EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir1,1", M_MBA), EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro1,1", M_MBP), EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,1", M_MBP_2), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,2", M_MBP_2_2), EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro2,1", M_MBP_2), EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro3,1", M_MBP_SR), EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro3,1", M_MBP_SR), EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro4,1", M_MBP_4), EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,1", M_MBP_5_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,2", M_MBP_5_2), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,3", M_MBP_5_3), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,1", M_MBP_6_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,2", M_MBP_6_2), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro7,1", M_MBP_7_1), {}, }; @@ -116,7 +158,7 @@ static int set_system(const struct dmi_system_id *id) { struct efifb_dmi_info *info = id->driver_data; if (info->base == 0) - return -ENODEV; + return 0; printk(KERN_INFO "efifb: dmi detected %s - framebuffer at %p " "(%dx%d, stride %d)\n", id->ident, @@ -124,18 +166,55 @@ static int set_system(const struct dmi_system_id *id) info->stride); /* Trust the bootloader over the DMI tables */ - if (screen_info.lfb_base == 0) + if (screen_info.lfb_base == 0) { +#if defined(CONFIG_PCI) + struct pci_dev *dev = NULL; + int found_bar = 0; +#endif screen_info.lfb_base = info->base; - if (screen_info.lfb_linelength == 0) - screen_info.lfb_linelength = info->stride; - if (screen_info.lfb_width == 0) - screen_info.lfb_width = info->width; - if (screen_info.lfb_height == 0) - screen_info.lfb_height = info->height; - if (screen_info.orig_video_isVGA == 0) - screen_info.orig_video_isVGA = VIDEO_TYPE_EFI; - return 0; +#if defined(CONFIG_PCI) + /* make sure that the address in the table is actually on a + * VGA device's PCI BAR */ + + for_each_pci_dev(dev) { + int i; + if ((dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) + continue; + for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { + resource_size_t start, end; + + start = pci_resource_start(dev, i); + if (start == 0) + break; + end = pci_resource_end(dev, i); + if (screen_info.lfb_base >= start && + screen_info.lfb_base < end) { + found_bar = 1; + } + } + } + if (!found_bar) + screen_info.lfb_base = 0; +#endif + } + if (screen_info.lfb_base) { + if (screen_info.lfb_linelength == 0) + screen_info.lfb_linelength = info->stride; + if (screen_info.lfb_width == 0) + screen_info.lfb_width = info->width; + if (screen_info.lfb_height == 0) + screen_info.lfb_height = info->height; + if (screen_info.orig_video_isVGA == 0) + screen_info.orig_video_isVGA = VIDEO_TYPE_EFI; + } else { + screen_info.lfb_linelength = 0; + screen_info.lfb_width = 0; + screen_info.lfb_height = 0; + screen_info.orig_video_isVGA = 0; + return 0; + } + return 1; } static int efifb_setcolreg(unsigned regno, unsigned red, unsigned green, diff --git a/drivers/video/sis/sis_main.c b/drivers/video/sis/sis_main.c index 559bf1727a2..b52f8e4ef1f 100644 --- a/drivers/video/sis/sis_main.c +++ b/drivers/video/sis/sis_main.c @@ -1701,6 +1701,9 @@ static int sisfb_ioctl(struct fb_info *info, unsigned int cmd, break; case FBIOGET_VBLANK: + + memset(&sisvbblank, 0, sizeof(struct fb_vblank)); + sisvbblank.count = 0; sisvbblank.flags = sisfb_setupvbblankflags(ivideo, &sisvbblank.vcount, &sisvbblank.hcount); @@ -712,8 +712,16 @@ static ssize_t aio_run_iocb(struct kiocb *iocb) */ ret = retry(iocb); - if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) + if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) { + /* + * There's no easy way to restart the syscall since other AIO's + * may be already running. Just fail this IO with EINTR. + */ + if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR || + ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK)) + ret = -EINTR; aio_complete(iocb, ret, 0); + } out: spin_lock_irq(&ctx->ctx_lock); diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig index bc87b9c1d27..0fcd2640c23 100644 --- a/fs/ceph/Kconfig +++ b/fs/ceph/Kconfig @@ -3,6 +3,7 @@ config CEPH_FS depends on INET && EXPERIMENTAL select LIBCRC32C select CRYPTO_AES + select CRYPTO help Choose Y or M here to include support for mounting the experimental Ceph distributed file system. Ceph is an extremely diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 4cfce1ee31f..efbc604001c 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -411,8 +411,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) if (i_size < page_off + len) len = i_size - page_off; - dout("writepage %p page %p index %lu on %llu~%u\n", - inode, page, page->index, page_off, len); + dout("writepage %p page %p index %lu on %llu~%u snapc %p\n", + inode, page, page->index, page_off, len, snapc); writeback_stat = atomic_long_inc_return(&client->writeback_count); if (writeback_stat > @@ -766,7 +766,8 @@ get_more_pages: /* ok */ if (locked_pages == 0) { /* prepare async write request */ - offset = page->index << PAGE_CACHE_SHIFT; + offset = (unsigned long long)page->index + << PAGE_CACHE_SHIFT; len = wsize; req = ceph_osdc_new_request(&client->osdc, &ci->i_layout, diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index a2069b6680a..73c153092f7 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -814,7 +814,7 @@ int __ceph_caps_used(struct ceph_inode_info *ci) used |= CEPH_CAP_PIN; if (ci->i_rd_ref) used |= CEPH_CAP_FILE_RD; - if (ci->i_rdcache_ref || ci->i_rdcache_gen) + if (ci->i_rdcache_ref || ci->vfs_inode.i_data.nrpages) used |= CEPH_CAP_FILE_CACHE; if (ci->i_wr_ref) used |= CEPH_CAP_FILE_WR; @@ -1195,10 +1195,14 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, * asynchronously back to the MDS once sync writes complete and dirty * data is written out. * + * Unless @again is true, skip cap_snaps that were already sent to + * the MDS (i.e., during this session). + * * Called under i_lock. Takes s_mutex as needed. */ void __ceph_flush_snaps(struct ceph_inode_info *ci, - struct ceph_mds_session **psession) + struct ceph_mds_session **psession, + int again) __releases(ci->vfs_inode->i_lock) __acquires(ci->vfs_inode->i_lock) { @@ -1227,7 +1231,7 @@ retry: * pages to be written out. */ if (capsnap->dirty_pages || capsnap->writing) - continue; + break; /* * if cap writeback already occurred, we should have dropped @@ -1240,6 +1244,13 @@ retry: dout("no auth cap (migrating?), doing nothing\n"); goto out; } + + /* only flush each capsnap once */ + if (!again && !list_empty(&capsnap->flushing_item)) { + dout("already flushed %p, skipping\n", capsnap); + continue; + } + mds = ci->i_auth_cap->session->s_mds; mseq = ci->i_auth_cap->mseq; @@ -1276,8 +1287,8 @@ retry: &session->s_cap_snaps_flushing); spin_unlock(&inode->i_lock); - dout("flush_snaps %p cap_snap %p follows %lld size %llu\n", - inode, capsnap, next_follows, capsnap->size); + dout("flush_snaps %p cap_snap %p follows %lld tid %llu\n", + inode, capsnap, capsnap->follows, capsnap->flush_tid); send_cap_msg(session, ceph_vino(inode).ino, 0, CEPH_CAP_OP_FLUSHSNAP, capsnap->issued, 0, capsnap->dirty, 0, capsnap->flush_tid, 0, mseq, @@ -1314,7 +1325,7 @@ static void ceph_flush_snaps(struct ceph_inode_info *ci) struct inode *inode = &ci->vfs_inode; spin_lock(&inode->i_lock); - __ceph_flush_snaps(ci, NULL); + __ceph_flush_snaps(ci, NULL, 0); spin_unlock(&inode->i_lock); } @@ -1477,7 +1488,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags, /* flush snaps first time around only */ if (!list_empty(&ci->i_cap_snaps)) - __ceph_flush_snaps(ci, &session); + __ceph_flush_snaps(ci, &session, 0); goto retry_locked; retry: spin_lock(&inode->i_lock); @@ -1894,7 +1905,7 @@ static void kick_flushing_capsnaps(struct ceph_mds_client *mdsc, if (cap && cap->session == session) { dout("kick_flushing_caps %p cap %p capsnap %p\n", inode, cap, capsnap); - __ceph_flush_snaps(ci, &session); + __ceph_flush_snaps(ci, &session, 1); } else { pr_err("%p auth cap %p not mds%d ???\n", inode, cap, session->s_mds); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 6e4f43ff23e..a1986eb5204 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1021,11 +1021,15 @@ out_touch: static void ceph_dentry_release(struct dentry *dentry) { struct ceph_dentry_info *di = ceph_dentry(dentry); - struct inode *parent_inode = dentry->d_parent->d_inode; - u64 snapid = ceph_snap(parent_inode); + struct inode *parent_inode = NULL; + u64 snapid = CEPH_NOSNAP; + if (!IS_ROOT(dentry)) { + parent_inode = dentry->d_parent->d_inode; + if (parent_inode) + snapid = ceph_snap(parent_inode); + } dout("dentry_release %p parent %p\n", dentry, parent_inode); - if (parent_inode && snapid != CEPH_SNAPDIR) { struct ceph_inode_info *ci = ceph_inode(parent_inode); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index e7cca414da0..62377ec37ed 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -845,7 +845,7 @@ static void ceph_set_dentry_offset(struct dentry *dn) * the caller) if we fail. */ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, - bool *prehash) + bool *prehash, bool set_offset) { struct dentry *realdn; @@ -877,7 +877,8 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, } if ((!prehash || *prehash) && d_unhashed(dn)) d_rehash(dn); - ceph_set_dentry_offset(dn); + if (set_offset) + ceph_set_dentry_offset(dn); out: return dn; } @@ -1062,7 +1063,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, d_delete(dn); goto done; } - dn = splice_dentry(dn, in, &have_lease); + dn = splice_dentry(dn, in, &have_lease, true); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; @@ -1105,7 +1106,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, goto done; } dout(" linking snapped dir %p to dn %p\n", in, dn); - dn = splice_dentry(dn, in, NULL); + dn = splice_dentry(dn, in, NULL, true); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; @@ -1237,7 +1238,7 @@ retry_lookup: err = PTR_ERR(in); goto out; } - dn = splice_dentry(dn, in, NULL); + dn = splice_dentry(dn, in, NULL, false); if (IS_ERR(dn)) dn = NULL; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index f091b135178..fad95f8f260 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2374,6 +2374,8 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, num_fcntl_locks, num_flock_locks); unlock_kernel(); + } else { + err = ceph_pagelist_append(pagelist, &rec, reclen); } out_free: diff --git a/fs/ceph/pagelist.c b/fs/ceph/pagelist.c index b6859f47d36..46a368b6dce 100644 --- a/fs/ceph/pagelist.c +++ b/fs/ceph/pagelist.c @@ -5,10 +5,18 @@ #include "pagelist.h" +static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl) +{ + struct page *page = list_entry(pl->head.prev, struct page, + lru); + kunmap(page); +} + int ceph_pagelist_release(struct ceph_pagelist *pl) { if (pl->mapped_tail) - kunmap(pl->mapped_tail); + ceph_pagelist_unmap_tail(pl); + while (!list_empty(&pl->head)) { struct page *page = list_first_entry(&pl->head, struct page, lru); @@ -26,7 +34,7 @@ static int ceph_pagelist_addpage(struct ceph_pagelist *pl) pl->room += PAGE_SIZE; list_add_tail(&page->lru, &pl->head); if (pl->mapped_tail) - kunmap(pl->mapped_tail); + ceph_pagelist_unmap_tail(pl); pl->mapped_tail = kmap(page); return 0; } diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 4868b9dcac5..190b6c4a6f2 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -119,6 +119,7 @@ static struct ceph_snap_realm *ceph_create_snap_realm( INIT_LIST_HEAD(&realm->children); INIT_LIST_HEAD(&realm->child_item); INIT_LIST_HEAD(&realm->empty_item); + INIT_LIST_HEAD(&realm->dirty_item); INIT_LIST_HEAD(&realm->inodes_with_caps); spin_lock_init(&realm->inodes_with_caps_lock); __insert_snap_realm(&mdsc->snap_realms, realm); @@ -467,7 +468,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) INIT_LIST_HEAD(&capsnap->ci_item); INIT_LIST_HEAD(&capsnap->flushing_item); - capsnap->follows = snapc->seq - 1; + capsnap->follows = snapc->seq; capsnap->issued = __ceph_caps_issued(ci, NULL); capsnap->dirty = dirty; @@ -604,6 +605,7 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm; int invalidate = 0; int err = -ENOMEM; + LIST_HEAD(dirty_realms); dout("update_snap_trace deletion=%d\n", deletion); more: @@ -626,24 +628,6 @@ more: } } - if (le64_to_cpu(ri->seq) > realm->seq) { - dout("update_snap_trace updating %llx %p %lld -> %lld\n", - realm->ino, realm, realm->seq, le64_to_cpu(ri->seq)); - /* - * if the realm seq has changed, queue a cap_snap for every - * inode with open caps. we do this _before_ we update - * the realm info so that we prepare for writeback under the - * _previous_ snap context. - * - * ...unless it's a snap deletion! - */ - if (!deletion) - queue_realm_cap_snaps(realm); - } else { - dout("update_snap_trace %llx %p seq %lld unchanged\n", - realm->ino, realm, realm->seq); - } - /* ensure the parent is correct */ err = adjust_snap_realm_parent(mdsc, realm, le64_to_cpu(ri->parent)); if (err < 0) @@ -651,6 +635,8 @@ more: invalidate += err; if (le64_to_cpu(ri->seq) > realm->seq) { + dout("update_snap_trace updating %llx %p %lld -> %lld\n", + realm->ino, realm, realm->seq, le64_to_cpu(ri->seq)); /* update realm parameters, snap lists */ realm->seq = le64_to_cpu(ri->seq); realm->created = le64_to_cpu(ri->created); @@ -668,9 +654,17 @@ more: if (err < 0) goto fail; + /* queue realm for cap_snap creation */ + list_add(&realm->dirty_item, &dirty_realms); + invalidate = 1; } else if (!realm->cached_context) { + dout("update_snap_trace %llx %p seq %lld new\n", + realm->ino, realm, realm->seq); invalidate = 1; + } else { + dout("update_snap_trace %llx %p seq %lld unchanged\n", + realm->ino, realm, realm->seq); } dout("done with %llx %p, invalidated=%d, %p %p\n", realm->ino, @@ -683,6 +677,14 @@ more: if (invalidate) rebuild_snap_realms(realm); + /* + * queue cap snaps _after_ we've built the new snap contexts, + * so that i_head_snapc can be set appropriately. + */ + list_for_each_entry(realm, &dirty_realms, dirty_item) { + queue_realm_cap_snaps(realm); + } + __cleanup_empty_realms(mdsc); return 0; @@ -715,7 +717,7 @@ static void flush_snaps(struct ceph_mds_client *mdsc) igrab(inode); spin_unlock(&mdsc->snap_flush_lock); spin_lock(&inode->i_lock); - __ceph_flush_snaps(ci, &session); + __ceph_flush_snaps(ci, &session, 0); spin_unlock(&inode->i_lock); iput(inode); spin_lock(&mdsc->snap_flush_lock); @@ -816,6 +818,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, }; struct inode *inode = ceph_find_inode(sb, vino); struct ceph_inode_info *ci; + struct ceph_snap_realm *oldrealm; if (!inode) continue; @@ -841,18 +844,19 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, dout(" will move %p to split realm %llx %p\n", inode, realm->ino, realm); /* - * Remove the inode from the realm's inode - * list, but don't add it to the new realm - * yet. We don't want the cap_snap to be - * queued (again) by ceph_update_snap_trace() - * below. Queue it _now_, under the old context. + * Move the inode to the new realm */ spin_lock(&realm->inodes_with_caps_lock); list_del_init(&ci->i_snap_realm_item); + list_add(&ci->i_snap_realm_item, + &realm->inodes_with_caps); + oldrealm = ci->i_snap_realm; + ci->i_snap_realm = realm; spin_unlock(&realm->inodes_with_caps_lock); spin_unlock(&inode->i_lock); - ceph_queue_cap_snap(ci); + ceph_get_snap_realm(mdsc, realm); + ceph_put_snap_realm(mdsc, oldrealm); iput(inode); continue; @@ -880,43 +884,9 @@ skip_inode: ceph_update_snap_trace(mdsc, p, e, op == CEPH_SNAP_OP_DESTROY); - if (op == CEPH_SNAP_OP_SPLIT) { - /* - * ok, _now_ add the inodes into the new realm. - */ - for (i = 0; i < num_split_inos; i++) { - struct ceph_vino vino = { - .ino = le64_to_cpu(split_inos[i]), - .snap = CEPH_NOSNAP, - }; - struct inode *inode = ceph_find_inode(sb, vino); - struct ceph_inode_info *ci; - - if (!inode) - continue; - ci = ceph_inode(inode); - spin_lock(&inode->i_lock); - if (list_empty(&ci->i_snap_realm_item)) { - struct ceph_snap_realm *oldrealm = - ci->i_snap_realm; - - dout(" moving %p to split realm %llx %p\n", - inode, realm->ino, realm); - spin_lock(&realm->inodes_with_caps_lock); - list_add(&ci->i_snap_realm_item, - &realm->inodes_with_caps); - ci->i_snap_realm = realm; - spin_unlock(&realm->inodes_with_caps_lock); - ceph_get_snap_realm(mdsc, realm); - ceph_put_snap_realm(mdsc, oldrealm); - } - spin_unlock(&inode->i_lock); - iput(inode); - } - + if (op == CEPH_SNAP_OP_SPLIT) /* we took a reference when we created the realm, above */ ceph_put_snap_realm(mdsc, realm); - } __cleanup_empty_realms(mdsc); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index c33897ae572..b87638e84c4 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -690,6 +690,8 @@ struct ceph_snap_realm { struct list_head empty_item; /* if i have ref==0 */ + struct list_head dirty_item; /* if realm needs new context */ + /* the current set of snaps for this realm */ struct ceph_snap_context *cached_context; @@ -826,7 +828,8 @@ extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had); extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, struct ceph_snap_context *snapc); extern void __ceph_flush_snaps(struct ceph_inode_info *ci, - struct ceph_mds_session **psession); + struct ceph_mds_session **psession, + int again); extern void ceph_check_caps(struct ceph_inode_info *ci, int flags, struct ceph_mds_session *session); extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc); diff --git a/fs/char_dev.c b/fs/char_dev.c index f80a4f25123..143d393881c 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -40,7 +40,9 @@ struct backing_dev_info directly_mappable_cdev_bdi = { #endif /* permit direct mmap, for read, write or exec */ BDI_CAP_MAP_DIRECT | - BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP), + BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP | + /* no writeback happens */ + BDI_CAP_NO_ACCT_AND_WRITEBACK), }; static struct kobj_map *cdev_map; diff --git a/fs/compat.c b/fs/compat.c index 718c7062aec..0644a154672 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1153,7 +1153,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, { compat_ssize_t tot_len; struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov; + struct iovec *iov = iovstack; ssize_t ret; io_fn_t fn; iov_fn_t fnv; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 81e086d8aa5..5581122bd2c 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -52,8 +52,6 @@ struct wb_writeback_work { #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> -#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info) - /* * We don't actually have pdflush, but this one is exported though /proc... */ @@ -71,6 +69,27 @@ int writeback_in_progress(struct backing_dev_info *bdi) return test_bit(BDI_writeback_running, &bdi->state); } +static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info; + + /* + * For inodes on standard filesystems, we use superblock's bdi. For + * inodes on virtual filesystems, we want to use inode mapping's bdi + * because they can possibly point to something useful (think about + * block_dev filesystem). + */ + if (sb->s_bdi && sb->s_bdi != &noop_backing_dev_info) { + /* Some device inodes could play dirty tricks. Catch them... */ + WARN(bdi != sb->s_bdi && bdi_cap_writeback_dirty(bdi), + "Dirtiable inode bdi %s != sb bdi %s\n", + bdi->name, sb->s_bdi->name); + return sb->s_bdi; + } + return bdi; +} + static void bdi_queue_work(struct backing_dev_info *bdi, struct wb_writeback_work *work) { diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 271afc48b9a..1dbca4e8cc1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -363,13 +363,13 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, mss->referenced += PAGE_SIZE; mapcount = page_mapcount(page); if (mapcount >= 2) { - if (pte_dirty(ptent)) + if (pte_dirty(ptent) || PageDirty(page)) mss->shared_dirty += PAGE_SIZE; else mss->shared_clean += PAGE_SIZE; mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount; } else { - if (pte_dirty(ptent)) + if (pte_dirty(ptent) || PageDirty(page)) mss->private_dirty += PAGE_SIZE; else mss->private_clean += PAGE_SIZE; diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 91c817ff02c..2367fb3f70b 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -163,7 +163,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, static const struct file_operations proc_vmcore_operations = { .read = read_vmcore, - .llseek = generic_file_llseek, + .llseek = default_llseek, }; static struct vmcore* __init get_new_element(void) diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index ce29b815119..ba8319ae5fc 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -102,6 +102,9 @@ static inline u64 dma_get_mask(struct device *dev) return DMA_BIT_MASK(32); } +#ifdef ARCH_HAS_DMA_SET_COHERENT_MASK +int dma_set_coherent_mask(struct device *dev, u64 mask); +#else static inline int dma_set_coherent_mask(struct device *dev, u64 mask) { if (!dma_supported(dev, mask)) @@ -109,6 +112,7 @@ static inline int dma_set_coherent_mask(struct device *dev, u64 mask) dev->coherent_dma_mask = mask; return 0; } +#endif extern u64 dma_get_required_mask(struct device *dev); diff --git a/include/linux/fs.h b/include/linux/fs.h index 76041b61475..63d069bd80b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1093,6 +1093,10 @@ struct file_lock { #include <linux/fcntl.h> +/* temporary stubs for BKL removal */ +#define lock_flocks() lock_kernel() +#define unlock_flocks() unlock_kernel() + extern void send_sigio(struct fown_struct *fown, int fd, int band); #ifdef CONFIG_FILE_LOCKING diff --git a/kernel/fork.c b/kernel/fork.c index b7e9d60a675..c445f8cc408 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -356,10 +356,10 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) if (IS_ERR(pol)) goto fail_nomem_policy; vma_set_policy(tmp, pol); + tmp->vm_mm = mm; if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; tmp->vm_flags &= ~VM_LOCKED; - tmp->vm_mm = mm; tmp->vm_next = tmp->vm_prev = NULL; file = tmp->vm_file; if (file) { diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c index d71a987fd2b..c7c2aed9e2d 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/hw_breakpoint.c @@ -433,7 +433,8 @@ register_user_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered, struct task_struct *tsk) { - return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered); + return perf_event_create_kernel_counter(attr, -1, task_pid_vnr(tsk), + triggered); } EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); diff --git a/kernel/sched.c b/kernel/sched.c index ed09d4f2a69..dc85ceb9083 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3513,9 +3513,9 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) rtime = nsecs_to_cputime(p->se.sum_exec_runtime); if (total) { - u64 temp; + u64 temp = rtime; - temp = (u64)(rtime * utime); + temp *= utime; do_div(temp, total); utime = (cputime_t)temp; } else @@ -3546,9 +3546,9 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) rtime = nsecs_to_cputime(cputime.sum_exec_runtime); if (total) { - u64 temp; + u64 temp = rtime; - temp = (u64)(rtime * cputime.utime); + temp *= cputime.utime; do_div(temp, total); utime = (cputime_t)temp; } else diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index a171138a940..db3f674ca49 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -3630,7 +3630,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu) if (time_before(now, nohz.next_balance)) return 0; - if (!rq->nr_running) + if (rq->idle_at_tick) return 0; first_pick_cpu = atomic_read(&nohz.first_pick_cpu); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index c2bf86f470e..65d420499a6 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -30,6 +30,7 @@ EXPORT_SYMBOL_GPL(default_backing_dev_info); struct backing_dev_info noop_backing_dev_info = { .name = "noop", + .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; EXPORT_SYMBOL_GPL(noop_backing_dev_info); @@ -243,6 +244,7 @@ static int __init default_bdi_init(void) err = bdi_init(&default_backing_dev_info); if (!err) bdi_register(&default_backing_dev_info, NULL, "default"); + err = bdi_init(&noop_backing_dev_info); return err; } diff --git a/mm/mmap.c b/mm/mmap.c index 6128dc8e5ed..00161a48a45 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2009,6 +2009,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, removed_exe_file_vma(mm); fput(new->vm_file); } + unlink_anon_vmas(new); out_free_mpol: mpol_put(pol); out_free_vma: diff --git a/mm/oom_kill.c b/mm/oom_kill.c index fc81cb22869..4029583a102 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -121,8 +121,8 @@ struct task_struct *find_lock_task_mm(struct task_struct *p) } /* return true if the task is not adequate as candidate victim task. */ -static bool oom_unkillable_task(struct task_struct *p, struct mem_cgroup *mem, - const nodemask_t *nodemask) +static bool oom_unkillable_task(struct task_struct *p, + const struct mem_cgroup *mem, const nodemask_t *nodemask) { if (is_global_init(p)) return true; @@ -208,8 +208,13 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, */ points += p->signal->oom_score_adj; - if (points < 0) - return 0; + /* + * Never return 0 for an eligible task that may be killed since it's + * possible that no single user task uses more than 0.1% of memory and + * no single admin tasks uses more than 3.0%. + */ + if (points <= 0) + return 1; return (points < 1000) ? points : 1000; } @@ -339,26 +344,24 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, /** * dump_tasks - dump current memory state of all system tasks * @mem: current's memory controller, if constrained + * @nodemask: nodemask passed to page allocator for mempolicy ooms * - * Dumps the current memory state of all system tasks, excluding kernel threads. + * Dumps the current memory state of all eligible tasks. Tasks not in the same + * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes + * are not shown. * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj * value, oom_score_adj value, and name. * - * If the actual is non-NULL, only tasks that are a member of the mem_cgroup are - * shown. - * * Call with tasklist_lock read-locked. */ -static void dump_tasks(const struct mem_cgroup *mem) +static void dump_tasks(const struct mem_cgroup *mem, const nodemask_t *nodemask) { struct task_struct *p; struct task_struct *task; pr_info("[ pid ] uid tgid total_vm rss cpu oom_adj oom_score_adj name\n"); for_each_process(p) { - if (p->flags & PF_KTHREAD) - continue; - if (mem && !task_in_mem_cgroup(p, mem)) + if (oom_unkillable_task(p, mem, nodemask)) continue; task = find_lock_task_mm(p); @@ -381,7 +384,7 @@ static void dump_tasks(const struct mem_cgroup *mem) } static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, - struct mem_cgroup *mem) + struct mem_cgroup *mem, const nodemask_t *nodemask) { task_lock(current); pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, " @@ -394,7 +397,7 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, mem_cgroup_print_oom_info(mem, p); show_mem(); if (sysctl_oom_dump_tasks) - dump_tasks(mem); + dump_tasks(mem, nodemask); } #define K(x) ((x) << (PAGE_SHIFT-10)) @@ -436,7 +439,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, unsigned int victim_points = 0; if (printk_ratelimit()) - dump_header(p, gfp_mask, order, mem); + dump_header(p, gfp_mask, order, mem, nodemask); /* * If the task is already exiting, don't alarm the sysadmin or kill @@ -482,7 +485,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, - int order) + int order, const nodemask_t *nodemask) { if (likely(!sysctl_panic_on_oom)) return; @@ -496,7 +499,7 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, return; } read_lock(&tasklist_lock); - dump_header(NULL, gfp_mask, order, NULL); + dump_header(NULL, gfp_mask, order, NULL, nodemask); read_unlock(&tasklist_lock); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); @@ -509,7 +512,7 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask) unsigned int points = 0; struct task_struct *p; - check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0); + check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0, NULL); limit = mem_cgroup_get_limit(mem) >> PAGE_SHIFT; read_lock(&tasklist_lock); retry: @@ -641,6 +644,7 @@ static void clear_system_oom(void) void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order, nodemask_t *nodemask) { + const nodemask_t *mpol_mask; struct task_struct *p; unsigned long totalpages; unsigned long freed = 0; @@ -670,7 +674,8 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, */ constraint = constrained_alloc(zonelist, gfp_mask, nodemask, &totalpages); - check_panic_on_oom(constraint, gfp_mask, order); + mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL; + check_panic_on_oom(constraint, gfp_mask, order, mpol_mask); read_lock(&tasklist_lock); if (sysctl_oom_kill_allocating_task && @@ -688,15 +693,13 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, } retry: - p = select_bad_process(&points, totalpages, NULL, - constraint == CONSTRAINT_MEMORY_POLICY ? nodemask : - NULL); + p = select_bad_process(&points, totalpages, NULL, mpol_mask); if (PTR_ERR(p) == -1UL) goto out; /* Found nothing?!?! Either we hang forever, or we panic. */ if (!p) { - dump_header(NULL, gfp_mask, order, NULL); + dump_header(NULL, gfp_mask, order, NULL, mpol_mask); read_unlock(&tasklist_lock); panic("Out of memory and no killable processes...\n"); } diff --git a/mm/vmscan.c b/mm/vmscan.c index c391c320dba..c5dfabf25f1 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1804,12 +1804,11 @@ static void shrink_zone(int priority, struct zone *zone, * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ -static bool shrink_zones(int priority, struct zonelist *zonelist, +static void shrink_zones(int priority, struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; - bool all_unreclaimable = true; for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(sc->gfp_mask), sc->nodemask) { @@ -1827,8 +1826,38 @@ static bool shrink_zones(int priority, struct zonelist *zonelist, } shrink_zone(priority, zone, sc); - all_unreclaimable = false; } +} + +static bool zone_reclaimable(struct zone *zone) +{ + return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; +} + +/* + * As hibernation is going on, kswapd is freezed so that it can't mark + * the zone into all_unreclaimable. It can't handle OOM during hibernation. + * So let's check zone's unreclaimable in direct reclaim as well as kswapd. + */ +static bool all_unreclaimable(struct zonelist *zonelist, + struct scan_control *sc) +{ + struct zoneref *z; + struct zone *zone; + bool all_unreclaimable = true; + + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(sc->gfp_mask), sc->nodemask) { + if (!populated_zone(zone)) + continue; + if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) + continue; + if (zone_reclaimable(zone)) { + all_unreclaimable = false; + break; + } + } + return all_unreclaimable; } @@ -1852,7 +1881,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int priority; - bool all_unreclaimable; unsigned long total_scanned = 0; struct reclaim_state *reclaim_state = current->reclaim_state; struct zoneref *z; @@ -1869,7 +1897,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, sc->nr_scanned = 0; if (!priority) disable_swap_token(); - all_unreclaimable = shrink_zones(priority, zonelist, sc); + shrink_zones(priority, zonelist, sc); /* * Don't shrink slabs when reclaiming memory from * over limit cgroups @@ -1931,7 +1959,7 @@ out: return sc->nr_reclaimed; /* top priority shrink_zones still had more to do? don't OOM, then */ - if (scanning_global_lru(sc) && !all_unreclaimable) + if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc)) return 1; return 0; @@ -2197,8 +2225,7 @@ loop_again: total_scanned += sc.nr_scanned; if (zone->all_unreclaimable) continue; - if (nr_slab == 0 && - zone->pages_scanned >= (zone_reclaimable_pages(zone) * 6)) + if (nr_slab == 0 && !zone_reclaimable(zone)) zone->all_unreclaimable = 1; /* * If we've done a decent amount of scanning and |