diff options
44 files changed, 238 insertions, 177 deletions
diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt index 88d5a863712..6c0b9f27e46 100644 --- a/Documentation/kdump/kdump.txt +++ b/Documentation/kdump/kdump.txt @@ -18,7 +18,7 @@ memory image to a dump file on the local disk, or across the network to a remote system. Kdump and kexec are currently supported on the x86, x86_64, ppc64, ia64, -and s390x architectures. +s390x and arm architectures. When the system kernel boots, it reserves a small section of memory for the dump-capture kernel. This ensures that ongoing Direct Memory Access @@ -112,7 +112,7 @@ There are two possible methods of using Kdump. 2) Or use the system kernel binary itself as dump-capture kernel and there is no need to build a separate dump-capture kernel. This is possible only with the architectures which support a relocatable kernel. As - of today, i386, x86_64, ppc64 and ia64 architectures support relocatable + of today, i386, x86_64, ppc64, ia64 and arm architectures support relocatable kernel. Building a relocatable kernel is advantageous from the point of view that @@ -241,6 +241,13 @@ Dump-capture kernel config options (Arch Dependent, ia64) kernel will be aligned to 64Mb, so if the start address is not then any space below the alignment point will be wasted. +Dump-capture kernel config options (Arch Dependent, arm) +---------------------------------------------------------- + +- To use a relocatable kernel, + Enable "AUTO_ZRELADDR" support under "Boot" options: + + AUTO_ZRELADDR=y Extended crashkernel syntax =========================== @@ -256,6 +263,10 @@ The syntax is: crashkernel=<range1>:<size1>[,<range2>:<size2>,...][@offset] range=start-[end] +Please note, on arm, the offset is required. + crashkernel=<range1>:<size1>[,<range2>:<size2>,...]@offset + range=start-[end] + 'start' is inclusive and 'end' is exclusive. For example: @@ -296,6 +307,12 @@ Boot into System Kernel on the memory consumption of the kdump system. In general this is not dependent on the memory size of the production system. + On arm, use "crashkernel=Y@X". Note that the start address of the kernel + will be aligned to 128MiB (0x08000000), so if the start address is not then + any space below the alignment point may be overwritten by the dump-capture kernel, + which means it is possible that the vmcore is not that precise as expected. + + Load the Dump-capture Kernel ============================ @@ -315,7 +332,8 @@ For ia64: - Use vmlinux or vmlinuz.gz For s390x: - Use image or bzImage - +For arm: + - Use zImage If you are using a uncompressed vmlinux image then use following command to load dump-capture kernel. @@ -331,6 +349,15 @@ to load dump-capture kernel. --initrd=<initrd-for-dump-capture-kernel> \ --append="root=<root-dev> <arch-specific-options>" +If you are using a compressed zImage, then use following command +to load dump-capture kernel. + + kexec --type zImage -p <dump-capture-kernel-bzImage> \ + --initrd=<initrd-for-dump-capture-kernel> \ + --dtb=<dtb-for-dump-capture-kernel> \ + --append="root=<root-dev> <arch-specific-options>" + + Please note, that --args-linux does not need to be specified for ia64. It is planned to make this a no-op on that architecture, but for now it should be omitted @@ -347,6 +374,9 @@ For ppc64: For s390x: "1 maxcpus=1 cgroup_disable=memory" +For arm: + "1 maxcpus=1 reset_devices" + Notes on loading the dump-capture kernel: * By default, the ELF headers are stored in ELF64 format to support diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c index 4670afc3b97..e88ddbf990e 100644 --- a/arch/arc/mm/cache_arc700.c +++ b/arch/arc/mm/cache_arc700.c @@ -581,6 +581,7 @@ void flush_icache_range(unsigned long kstart, unsigned long kend) tot_sz -= sz; } } +EXPORT_SYMBOL(flush_icache_range); /* * General purpose helper to make I and D cache lines consistent. diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index c49a775937d..32cbbd56590 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1983,8 +1983,6 @@ config XIP_PHYS_ADDR config KEXEC bool "Kexec system call (EXPERIMENTAL)" depends on (!SMP || PM_SLEEP_SMP) - select CRYPTO - select CRYPTO_SHA256 help kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot diff --git a/arch/hexagon/mm/cache.c b/arch/hexagon/mm/cache.c index fe14ccf2856..0c76c802e31 100644 --- a/arch/hexagon/mm/cache.c +++ b/arch/hexagon/mm/cache.c @@ -68,6 +68,7 @@ void flush_icache_range(unsigned long start, unsigned long end) ); local_irq_restore(flags); } +EXPORT_SYMBOL(flush_icache_range); void hexagon_clean_dcache_range(unsigned long start, unsigned long end) { diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 64aefb76bd6..c84c88bbbbd 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -549,8 +549,6 @@ source "drivers/sn/Kconfig" config KEXEC bool "kexec system call" depends on !IA64_HP_SIM && (!SMP || HOTPLUG_CPU) - select CRYPTO - select CRYPTO_SHA256 help kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 3ff8c9a2533..87b7c7581b1 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -91,8 +91,6 @@ config MMU_SUN3 config KEXEC bool "kexec system call" depends on M68KCLASSIC - select CRYPTO - select CRYPTO_SHA256 help kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index df51e78a72c..900c7e5333b 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2396,8 +2396,6 @@ source "kernel/Kconfig.preempt" config KEXEC bool "Kexec system call" - select CRYPTO - select CRYPTO_SHA256 help kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a577609f8ed..4bc7b62fb4b 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -399,8 +399,6 @@ config PPC64_SUPPORTS_MEMORY_FAILURE config KEXEC bool "kexec system call" depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP)) - select CRYPTO - select CRYPTO_SHA256 help kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index ab39ceb89ec..05c78bb5f57 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -48,8 +48,6 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC config KEXEC def_bool y - select CRYPTO - select CRYPTO_SHA256 config AUDIT_ARCH def_bool y diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index b319846ad97..244fb4c81e2 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -598,8 +598,6 @@ source kernel/Kconfig.hz config KEXEC bool "kexec system call (EXPERIMENTAL)" depends on SUPERH32 && MMU - select CRYPTO - select CRYPTO_SHA256 help kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c index 097c2cdd117..f770e399262 100644 --- a/arch/sh/mm/cache.c +++ b/arch/sh/mm/cache.c @@ -229,6 +229,7 @@ void flush_icache_range(unsigned long start, unsigned long end) cacheop_on_each_cpu(local_flush_icache_range, (void *)&data, 1); } +EXPORT_SYMBOL(flush_icache_range); void flush_icache_page(struct vm_area_struct *vma, struct page *page) { diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index a3ffe2dd483..7fcd492adbf 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -191,8 +191,6 @@ source "kernel/Kconfig.hz" config KEXEC bool "kexec system call" - select CRYPTO - select CRYPTO_SHA256 ---help--- kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c index 01e8ab29f43..19eaa62d456 100644 --- a/arch/tile/kernel/smp.c +++ b/arch/tile/kernel/smp.c @@ -183,6 +183,7 @@ void flush_icache_range(unsigned long start, unsigned long end) preempt_enable(); } } +EXPORT_SYMBOL(flush_icache_range); /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */ diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 61b6d51866f..3942f74c92d 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -17,6 +17,4 @@ obj-$(CONFIG_IA32_EMULATION) += ia32/ obj-y += platform/ obj-y += net/ -ifeq ($(CONFIG_X86_64),y) -obj-$(CONFIG_KEXEC) += purgatory/ -endif +obj-$(CONFIG_KEXEC_FILE) += purgatory/ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5d0bf1aa9dc..778178f4c7d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1585,9 +1585,6 @@ source kernel/Kconfig.hz config KEXEC bool "kexec system call" - select BUILD_BIN2C - select CRYPTO - select CRYPTO_SHA256 ---help--- kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot @@ -1602,9 +1599,22 @@ config KEXEC interface is strongly in flux, so no good recommendation can be made. +config KEXEC_FILE + bool "kexec file based system call" + select BUILD_BIN2C + depends on KEXEC + depends on X86_64 + depends on CRYPTO=y + depends on CRYPTO_SHA256=y + ---help--- + This is new version of kexec system call. This system call is + file based and takes file descriptors as system call argument + for kernel and initramfs as opposed to list of segments as + accepted by previous system call. + config KEXEC_VERIFY_SIG bool "Verify kernel signature during kexec_file_load() syscall" - depends on KEXEC + depends on KEXEC_FILE ---help--- This option makes kernel signature verification mandatory for kexec_file_load() syscall. If kernel is signature can not be diff --git a/arch/x86/Makefile b/arch/x86/Makefile index c1aa3688784..60087ca3767 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -184,11 +184,8 @@ archheaders: $(Q)$(MAKE) $(build)=arch/x86/syscalls all archprepare: -ifeq ($(CONFIG_KEXEC),y) -# Build only for 64bit. No loaders for 32bit yet. - ifeq ($(CONFIG_X86_64),y) +ifeq ($(CONFIG_KEXEC_FILE),y) $(Q)$(MAKE) $(build)=arch/x86/purgatory arch/x86/purgatory/kexec-purgatory.c - endif endif ### @@ -254,6 +251,7 @@ archclean: $(Q)rm -rf $(objtree)/arch/x86_64 $(Q)$(MAKE) $(clean)=$(boot) $(Q)$(MAKE) $(clean)=arch/x86/tools + $(Q)$(MAKE) $(clean)=arch/x86/purgatory PHONY += kvmconfig kvmconfig: diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 0ec05601261..aa97a070f09 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -131,8 +131,13 @@ static inline int pte_exec(pte_t pte) static inline int pte_special(pte_t pte) { - return (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_SPECIAL)) == - (_PAGE_PRESENT|_PAGE_SPECIAL); + /* + * See CONFIG_NUMA_BALANCING pte_numa in include/asm-generic/pgtable.h. + * On x86 we have _PAGE_BIT_NUMA == _PAGE_BIT_GLOBAL+1 == + * __PAGE_BIT_SOFTW1 == _PAGE_BIT_SPECIAL. + */ + return (pte_flags(pte) & _PAGE_SPECIAL) && + (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_PROTNONE)); } static inline unsigned long pte_pfn(pte_t pte) diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index b5ea75c4a4b..ada2e2d6be3 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -71,6 +71,7 @@ obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o +obj-$(CONFIG_KEXEC_FILE) += kexec-bzimage64.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o obj-y += kprobes/ obj-$(CONFIG_MODULES) += module.o @@ -118,5 +119,4 @@ ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o obj-y += vsmp_64.o - obj-$(CONFIG_KEXEC) += kexec-bzimage64.o endif diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 0553a34fa0d..a618fcd2c07 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -182,8 +182,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs) crash_save_cpu(regs, safe_smp_processor_id()); } -#ifdef CONFIG_X86_64 - +#ifdef CONFIG_KEXEC_FILE static int get_nr_ram_ranges_callback(unsigned long start_pfn, unsigned long nr_pfn, void *arg) { @@ -696,5 +695,4 @@ int crash_load_segments(struct kimage *image) return ret; } - -#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_KEXEC_FILE */ diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 8b04018e5d1..485981059a4 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -25,9 +25,11 @@ #include <asm/debugreg.h> #include <asm/kexec-bzimage64.h> +#ifdef CONFIG_KEXEC_FILE static struct kexec_file_ops *kexec_file_loaders[] = { &kexec_bzImage64_ops, }; +#endif static void free_transition_pgtable(struct kimage *image) { @@ -178,6 +180,7 @@ static void load_segments(void) ); } +#ifdef CONFIG_KEXEC_FILE /* Update purgatory as needed after various image segments have been prepared */ static int arch_update_purgatory(struct kimage *image) { @@ -209,6 +212,12 @@ static int arch_update_purgatory(struct kimage *image) return ret; } +#else /* !CONFIG_KEXEC_FILE */ +static inline int arch_update_purgatory(struct kimage *image) +{ + return 0; +} +#endif /* CONFIG_KEXEC_FILE */ int machine_kexec_prepare(struct kimage *image) { @@ -329,6 +338,7 @@ void arch_crash_save_vmcoreinfo(void) /* arch-dependent functionality related to kexec file-based syscall */ +#ifdef CONFIG_KEXEC_FILE int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, unsigned long buf_len) { @@ -522,3 +532,4 @@ overflow: (int)ELF64_R_TYPE(rel[i].r_info), value); return -ENOEXEC; } +#endif /* CONFIG_KEXEC_FILE */ diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 7fde9ee438a..899dd245425 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -11,6 +11,7 @@ targets += purgatory.ro # sure how to relocate those. Like kexec-tools, use custom flags. KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large +KBUILD_CFLAGS += -m$(BITS) $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE $(call if_changed,ld) @@ -24,7 +25,4 @@ $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE $(call if_changed,bin2c) -# No loaders for 32bits yet. -ifeq ($(CONFIG_X86_64),y) - obj-$(CONFIG_KEXEC) += kexec-purgatory.o -endif +obj-$(CONFIG_KEXEC_FILE) += kexec-purgatory.o diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 40b5a3771fb..4d02e38514f 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -571,6 +571,7 @@ void flush_icache_range(unsigned long start, unsigned long end) }; on_each_cpu(ipi_flush_icache_range, &fd, 1); } +EXPORT_SYMBOL(flush_icache_range); /* ------------------------------------------------------------------------- */ diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index dfa4024c448..d00831c3d73 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -378,7 +378,6 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index) /* Should NEVER happen. Return bio error if it does. */ if (unlikely(ret)) { pr_err("Decompression failed! err=%d, page=%u\n", ret, index); - atomic64_inc(&zram->stats.failed_reads); return ret; } @@ -547,8 +546,6 @@ out: zcomp_strm_release(zram->comp, zstrm); if (is_partial_io(bvec)) kfree(uncmem); - if (ret) - atomic64_inc(&zram->stats.failed_writes); return ret; } @@ -566,6 +563,13 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, ret = zram_bvec_write(zram, bvec, index, offset); } + if (unlikely(ret)) { + if (rw == READ) + atomic64_inc(&zram->stats.failed_reads); + else + atomic64_inc(&zram->stats.failed_writes); + } + return ret; } diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 5b0afde729c..e0f725c87cc 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -84,7 +84,7 @@ struct zram_stats { atomic64_t compr_data_size; /* compressed size of pages stored */ atomic64_t num_reads; /* failed + successful */ atomic64_t num_writes; /* --do-- */ - atomic64_t failed_reads; /* should NEVER! happen */ + atomic64_t failed_reads; /* can happen when memory is too low */ atomic64_t failed_writes; /* can happen when memory is too low */ atomic64_t invalid_io; /* non-page-aligned I/O requests */ atomic64_t notify_free; /* no. of swap slot free notifications */ diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c index 8f06250a038..8754c33361e 100644 --- a/drivers/rtc/rtc-s5m.c +++ b/drivers/rtc/rtc-s5m.c @@ -717,12 +717,14 @@ static int s5m_rtc_probe(struct platform_device *pdev) info->device_type = s5m87xx->device_type; info->wtsr_smpl = s5m87xx->wtsr_smpl; - info->irq = regmap_irq_get_virq(s5m87xx->irq_data, alarm_irq); - if (info->irq <= 0) { - ret = -EINVAL; - dev_err(&pdev->dev, "Failed to get virtual IRQ %d\n", + if (s5m87xx->irq_data) { + info->irq = regmap_irq_get_virq(s5m87xx->irq_data, alarm_irq); + if (info->irq <= 0) { + ret = -EINVAL; + dev_err(&pdev->dev, "Failed to get virtual IRQ %d\n", alarm_irq); - goto err; + goto err; + } } platform_set_drvdata(pdev, info); @@ -744,6 +746,11 @@ static int s5m_rtc_probe(struct platform_device *pdev) goto err; } + if (!info->irq) { + dev_info(&pdev->dev, "Alarm IRQ not available\n"); + return 0; + } + ret = devm_request_threaded_irq(&pdev->dev, info->irq, NULL, s5m_rtc_alarm_irq, 0, "rtc-alarm0", info); @@ -802,7 +809,7 @@ static int s5m_rtc_resume(struct device *dev) struct s5m_rtc_info *info = dev_get_drvdata(dev); int ret = 0; - if (device_may_wakeup(dev)) + if (info->irq && device_may_wakeup(dev)) ret = disable_irq_wake(info->irq); return ret; @@ -813,7 +820,7 @@ static int s5m_rtc_suspend(struct device *dev) struct s5m_rtc_info *info = dev_get_drvdata(dev); int ret = 0; - if (device_may_wakeup(dev)) + if (info->irq && device_may_wakeup(dev)) ret = enable_irq_wake(info->irq); return ret; diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c index 1ec141e758d..62e8ec619b4 100644 --- a/fs/ocfs2/cluster/quorum.c +++ b/fs/ocfs2/cluster/quorum.c @@ -160,9 +160,18 @@ static void o2quo_make_decision(struct work_struct *work) } out: - spin_unlock(&qs->qs_lock); - if (fence) + if (fence) { + spin_unlock(&qs->qs_lock); o2quo_fence_self(); + } else { + mlog(ML_NOTICE, "not fencing this node, heartbeating: %d, " + "connected: %d, lowest: %d (%sreachable)\n", + qs->qs_heartbeating, qs->qs_connected, lowest_hb, + lowest_reachable ? "" : "un"); + spin_unlock(&qs->qs_lock); + + } + } static void o2quo_set_hold(struct o2quo_state *qs, u8 node) diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 681691bc233..ea34952f949 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1480,6 +1480,14 @@ static int o2net_set_nodelay(struct socket *sock) return ret; } +static int o2net_set_usertimeout(struct socket *sock) +{ + int user_timeout = O2NET_TCP_USER_TIMEOUT; + + return kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT, + (char *)&user_timeout, sizeof(user_timeout)); +} + static void o2net_initialize_handshake(void) { o2net_hand->o2hb_heartbeat_timeout_ms = cpu_to_be32( @@ -1536,16 +1544,20 @@ static void o2net_idle_timer(unsigned long data) #endif printk(KERN_NOTICE "o2net: Connection to " SC_NODEF_FMT " has been " - "idle for %lu.%lu secs, shutting it down.\n", SC_NODEF_ARGS(sc), - msecs / 1000, msecs % 1000); + "idle for %lu.%lu secs.\n", + SC_NODEF_ARGS(sc), msecs / 1000, msecs % 1000); - /* - * Initialize the nn_timeout so that the next connection attempt - * will continue in o2net_start_connect. + /* idle timerout happen, don't shutdown the connection, but + * make fence decision. Maybe the connection can recover before + * the decision is made. */ atomic_set(&nn->nn_timeout, 1); + o2quo_conn_err(o2net_num_from_nn(nn)); + queue_delayed_work(o2net_wq, &nn->nn_still_up, + msecs_to_jiffies(O2NET_QUORUM_DELAY_MS)); + + o2net_sc_reset_idle_timer(sc); - o2net_sc_queue_work(sc, &sc->sc_shutdown_work); } static void o2net_sc_reset_idle_timer(struct o2net_sock_container *sc) @@ -1560,6 +1572,15 @@ static void o2net_sc_reset_idle_timer(struct o2net_sock_container *sc) static void o2net_sc_postpone_idle(struct o2net_sock_container *sc) { + struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num); + + /* clear fence decision since the connection recover from timeout*/ + if (atomic_read(&nn->nn_timeout)) { + o2quo_conn_up(o2net_num_from_nn(nn)); + cancel_delayed_work(&nn->nn_still_up); + atomic_set(&nn->nn_timeout, 0); + } + /* Only push out an existing timer */ if (timer_pending(&sc->sc_idle_timeout)) o2net_sc_reset_idle_timer(sc); @@ -1650,6 +1671,12 @@ static void o2net_start_connect(struct work_struct *work) goto out; } + ret = o2net_set_usertimeout(sock); + if (ret) { + mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret); + goto out; + } + o2net_register_callbacks(sc->sc_sock->sk, sc); spin_lock(&nn->nn_lock); @@ -1831,6 +1858,12 @@ static int o2net_accept_one(struct socket *sock, int *more) goto out; } + ret = o2net_set_usertimeout(new_sock); + if (ret) { + mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret); + goto out; + } + slen = sizeof(sin); ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin, &slen, 1); diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h index 5bada2a69b5..c571e849fda 100644 --- a/fs/ocfs2/cluster/tcp.h +++ b/fs/ocfs2/cluster/tcp.h @@ -63,6 +63,7 @@ typedef void (o2net_post_msg_handler_func)(int status, void *data, #define O2NET_KEEPALIVE_DELAY_MS_DEFAULT 2000 #define O2NET_IDLE_TIMEOUT_MS_DEFAULT 30000 +#define O2NET_TCP_USER_TIMEOUT 0x7fffffff /* TODO: figure this out.... */ static inline int o2net_link_down(int err, struct socket *sock) diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 6f66b3751ac..53e6c40ed4c 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -35,9 +35,8 @@ copy_to_user((typeof(a) __user *)b, &(a), sizeof(a)) /* - * This call is void because we are already reporting an error that may - * be -EFAULT. The error will be returned from the ioctl(2) call. It's - * just a best-effort to tell userspace that this request caused the error. + * This is just a best-effort to tell userspace that this request + * caused the error. */ static inline void o2info_set_request_error(struct ocfs2_info_request *kreq, struct ocfs2_info_request __user *req) @@ -146,136 +145,105 @@ bail: static int ocfs2_info_handle_blocksize(struct inode *inode, struct ocfs2_info_request __user *req) { - int status = -EFAULT; struct ocfs2_info_blocksize oib; if (o2info_from_user(oib, req)) - goto bail; + return -EFAULT; oib.ib_blocksize = inode->i_sb->s_blocksize; o2info_set_request_filled(&oib.ib_req); if (o2info_to_user(oib, req)) - goto bail; - - status = 0; -bail: - if (status) - o2info_set_request_error(&oib.ib_req, req); + return -EFAULT; - return status; + return 0; } static int ocfs2_info_handle_clustersize(struct inode *inode, struct ocfs2_info_request __user *req) { - int status = -EFAULT; struct ocfs2_info_clustersize oic; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (o2info_from_user(oic, req)) - goto bail; + return -EFAULT; oic.ic_clustersize = osb->s_clustersize; o2info_set_request_filled(&oic.ic_req); if (o2info_to_user(oic, req)) - goto bail; - - status = 0; -bail: - if (status) - o2info_set_request_error(&oic.ic_req, req); + return -EFAULT; - return status; + return 0; } static int ocfs2_info_handle_maxslots(struct inode *inode, struct ocfs2_info_request __user *req) { - int status = -EFAULT; struct ocfs2_info_maxslots oim; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (o2info_from_user(oim, req)) - goto bail; + return -EFAULT; oim.im_max_slots = osb->max_slots; o2info_set_request_filled(&oim.im_req); if (o2info_to_user(oim, req)) - goto bail; + return -EFAULT; - status = 0; -bail: - if (status) - o2info_set_request_error(&oim.im_req, req); - - return status; + return 0; } static int ocfs2_info_handle_label(struct inode *inode, struct ocfs2_info_request __user *req) { - int status = -EFAULT; struct ocfs2_info_label oil; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (o2info_from_user(oil, req)) - goto bail; + return -EFAULT; memcpy(oil.il_label, osb->vol_label, OCFS2_MAX_VOL_LABEL_LEN); o2info_set_request_filled(&oil.il_req); if (o2info_to_user(oil, req)) - goto bail; + return -EFAULT; - status = 0; -bail: - if (status) - o2info_set_request_error(&oil.il_req, req); - - return status; + return 0; } static int ocfs2_info_handle_uuid(struct inode *inode, struct ocfs2_info_request __user *req) { - int status = -EFAULT; struct ocfs2_info_uuid oiu; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (o2info_from_user(oiu, req)) - goto bail; + return -EFAULT; memcpy(oiu.iu_uuid_str, osb->uuid_str, OCFS2_TEXT_UUID_LEN + 1); o2info_set_request_filled(&oiu.iu_req); if (o2info_to_user(oiu, req)) - goto bail; - - status = 0; -bail: - if (status) - o2info_set_request_error(&oiu.iu_req, req); + return -EFAULT; - return status; + return 0; } static int ocfs2_info_handle_fs_features(struct inode *inode, struct ocfs2_info_request __user *req) { - int status = -EFAULT; struct ocfs2_info_fs_features oif; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (o2info_from_user(oif, req)) - goto bail; + return -EFAULT; oif.if_compat_features = osb->s_feature_compat; oif.if_incompat_features = osb->s_feature_incompat; @@ -284,39 +252,28 @@ static int ocfs2_info_handle_fs_features(struct inode *inode, o2info_set_request_filled(&oif.if_req); if (o2info_to_user(oif, req)) - goto bail; + return -EFAULT; - status = 0; -bail: - if (status) - o2info_set_request_error(&oif.if_req, req); - - return status; + return 0; } static int ocfs2_info_handle_journal_size(struct inode *inode, struct ocfs2_info_request __user *req) { - int status = -EFAULT; struct ocfs2_info_journal_size oij; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (o2info_from_user(oij, req)) - goto bail; + return -EFAULT; oij.ij_journal_size = i_size_read(osb->journal->j_inode); o2info_set_request_filled(&oij.ij_req); if (o2info_to_user(oij, req)) - goto bail; + return -EFAULT; - status = 0; -bail: - if (status) - o2info_set_request_error(&oij.ij_req, req); - - return status; + return 0; } static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb, @@ -373,7 +330,7 @@ static int ocfs2_info_handle_freeinode(struct inode *inode, u32 i; u64 blkno = -1; char namebuf[40]; - int status = -EFAULT, type = INODE_ALLOC_SYSTEM_INODE; + int status, type = INODE_ALLOC_SYSTEM_INODE; struct ocfs2_info_freeinode *oifi = NULL; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct inode *inode_alloc = NULL; @@ -385,8 +342,10 @@ static int ocfs2_info_handle_freeinode(struct inode *inode, goto out_err; } - if (o2info_from_user(*oifi, req)) - goto bail; + if (o2info_from_user(*oifi, req)) { + status = -EFAULT; + goto out_free; + } oifi->ifi_slotnum = osb->max_slots; @@ -424,14 +383,16 @@ static int ocfs2_info_handle_freeinode(struct inode *inode, o2info_set_request_filled(&oifi->ifi_req); - if (o2info_to_user(*oifi, req)) - goto bail; + if (o2info_to_user(*oifi, req)) { + status = -EFAULT; + goto out_free; + } status = 0; bail: if (status) o2info_set_request_error(&oifi->ifi_req, req); - +out_free: kfree(oifi); out_err: return status; @@ -658,7 +619,7 @@ static int ocfs2_info_handle_freefrag(struct inode *inode, { u64 blkno = -1; char namebuf[40]; - int status = -EFAULT, type = GLOBAL_BITMAP_SYSTEM_INODE; + int status, type = GLOBAL_BITMAP_SYSTEM_INODE; struct ocfs2_info_freefrag *oiff; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); @@ -671,8 +632,10 @@ static int ocfs2_info_handle_freefrag(struct inode *inode, goto out_err; } - if (o2info_from_user(*oiff, req)) - goto bail; + if (o2info_from_user(*oiff, req)) { + status = -EFAULT; + goto out_free; + } /* * chunksize from userspace should be power of 2. */ @@ -711,14 +674,14 @@ static int ocfs2_info_handle_freefrag(struct inode *inode, if (o2info_to_user(*oiff, req)) { status = -EFAULT; - goto bail; + goto out_free; } status = 0; bail: if (status) o2info_set_request_error(&oiff->iff_req, req); - +out_free: kfree(oiff); out_err: return status; @@ -727,23 +690,17 @@ out_err: static int ocfs2_info_handle_unknown(struct inode *inode, struct ocfs2_info_request __user *req) { - int status = -EFAULT; struct ocfs2_info_request oir; if (o2info_from_user(oir, req)) - goto bail; + return -EFAULT; o2info_clear_request_filled(&oir); if (o2info_to_user(oir, req)) - goto bail; + return -EFAULT; - status = 0; -bail: - if (status) - o2info_set_request_error(&oir, req); - - return status; + return 0; } /* diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index c38355c1f3c..1590c49cae5 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -13,7 +13,7 @@ #ifndef _UAPI_LINUX_XATTR_H #define _UAPI_LINUX_XATTR_H -#ifdef __UAPI_DEF_XATTR +#if __UAPI_DEF_XATTR #define __USE_KERNEL_XATTR_DEFS #define XATTR_CREATE 0x1 /* set value, fail if attr already exists */ diff --git a/kernel/kexec.c b/kernel/kexec.c index 0b49a0a5810..2bee072268d 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -64,7 +64,9 @@ bool kexec_in_progress = false; char __weak kexec_purgatory[0]; size_t __weak kexec_purgatory_size = 0; +#ifdef CONFIG_KEXEC_FILE static int kexec_calculate_store_digests(struct kimage *image); +#endif /* Location of the reserved area for the crash kernel */ struct resource crashk_res = { @@ -341,6 +343,7 @@ out_free_image: return ret; } +#ifdef CONFIG_KEXEC_FILE static int copy_file_from_fd(int fd, void **buf, unsigned long *buf_len) { struct fd f = fdget(fd); @@ -612,6 +615,9 @@ out_free_image: kfree(image); return ret; } +#else /* CONFIG_KEXEC_FILE */ +static inline void kimage_file_post_load_cleanup(struct kimage *image) { } +#endif /* CONFIG_KEXEC_FILE */ static int kimage_is_destination_range(struct kimage *image, unsigned long start, @@ -1375,6 +1381,7 @@ COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry, } #endif +#ifdef CONFIG_KEXEC_FILE SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags) @@ -1451,6 +1458,8 @@ out: return ret; } +#endif /* CONFIG_KEXEC_FILE */ + void crash_kexec(struct pt_regs *regs) { /* Take the kexec_mutex here to prevent sys_kexec_load @@ -2006,6 +2015,7 @@ static int __init crash_save_vmcoreinfo_init(void) subsys_initcall(crash_save_vmcoreinfo_init); +#ifdef CONFIG_KEXEC_FILE static int __kexec_add_segment(struct kimage *image, char *buf, unsigned long bufsz, unsigned long mem, unsigned long memsz) @@ -2682,6 +2692,7 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, return 0; } +#endif /* CONFIG_KEXEC_FILE */ /* * Move into place and start executing a preloaded standalone diff --git a/kernel/resource.c b/kernel/resource.c index da14b8d0929..60c5a3856ab 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -351,15 +351,12 @@ static int find_next_iomem_res(struct resource *res, char *name, end = res->end; BUG_ON(start >= end); - read_lock(&resource_lock); - - if (first_level_children_only) { - p = iomem_resource.child; + if (first_level_children_only) sibling_only = true; - } else - p = &iomem_resource; - while ((p = next_resource(p, sibling_only))) { + read_lock(&resource_lock); + + for (p = iomem_resource.child; p; p = next_resource(p, sibling_only)) { if (p->flags != res->flags) continue; if (name && strcmp(p->name, name)) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1b233fc6746..a2859008362 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1036,8 +1036,13 @@ config TRACE_IRQFLAGS either tracing or lock debugging. config STACKTRACE - bool + bool "Stack backtrace support" depends on STACKTRACE_SUPPORT + help + This option causes the kernel to create a /proc/pid/stack for + every process, showing its current stack trace. + It is also used by various kernel debugging features that require + stack trace generation. config DEBUG_KOBJECT bool "kobject debugging" diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 9eebfadeeee..a67c26e0f36 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -217,7 +217,7 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, if (hugetlb_cgroup_disabled()) return; - VM_BUG_ON(!spin_is_locked(&hugetlb_lock)); + lockdep_assert_held(&hugetlb_lock); h_cg = hugetlb_cgroup_from_page(page); if (unlikely(!h_cg)) return; diff --git a/mm/memblock.c b/mm/memblock.c index 6d2f219a48b..70fad0c0daf 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -192,8 +192,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid) { - int ret; - phys_addr_t kernel_end; + phys_addr_t kernel_end, ret; /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE) diff --git a/mm/memory.c b/mm/memory.c index ab3537bcfed..adeac306610 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -751,7 +751,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn = pte_pfn(pte); if (HAVE_PTE_SPECIAL) { - if (likely(!pte_special(pte) || pte_numa(pte))) + if (likely(!pte_special(pte))) goto check_pfn; if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; @@ -777,15 +777,14 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, } } + if (is_zero_pfn(pfn)) + return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } - if (is_zero_pfn(pfn)) - return NULL; - /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index a8b91992593..dfb79e028ec 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -195,7 +195,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t entry = *pmdp; if (pmd_numa(entry)) entry = pmd_mknonnuma(entry); - set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp)); + set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(entry)); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/mm/zbud.c b/mm/zbud.c index a05790b1915..f26e7fcc7fa 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -195,6 +195,7 @@ static struct zpool_driver zbud_zpool_driver = { .total_size = zbud_zpool_total_size, }; +MODULE_ALIAS("zpool-zbud"); #endif /* CONFIG_ZPOOL */ /***************** diff --git a/mm/zpool.c b/mm/zpool.c index e40612a1df0..739cdf0d183 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -150,7 +150,7 @@ struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops) driver = zpool_get_driver(type); if (!driver) { - request_module(type); + request_module("zpool-%s", type); driver = zpool_get_driver(type); } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 4e2fc83cb39..94f38fac5e8 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -315,6 +315,7 @@ static struct zpool_driver zs_zpool_driver = { .total_size = zs_zpool_total_size, }; +MODULE_ALIAS("zpool-zsmalloc"); #endif /* CONFIG_ZPOOL */ /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 31a731e06f5..b385bcbbf2f 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -2133,7 +2133,7 @@ sub process { # Check for improperly formed commit descriptions if ($in_commit_log && $line =~ /\bcommit\s+[0-9a-f]{5,}/i && - $line !~ /\b[Cc]ommit [0-9a-f]{12,16} \("/) { + $line !~ /\b[Cc]ommit [0-9a-f]{12,40} \("/) { $line =~ /\b(c)ommit\s+([0-9a-f]{5,})/i; my $init_char = $1; my $orig_commit = lc($2); @@ -2141,7 +2141,7 @@ sub process { my $desc = 'commit description'; ($id, $desc) = git_commit_info($orig_commit, $id, $desc); ERROR("GIT_COMMIT_ID", - "Please use 12 to 16 chars for the git commit ID like: '${init_char}ommit $id (\"$desc\")'\n" . $herecurr); + "Please use 12 or more chars for the git commit ID like: '${init_char}ommit $id (\"$desc\")'\n" . $herecurr); } # Check for added, moved or deleted files diff --git a/tools/testing/selftests/ipc/Makefile b/tools/testing/selftests/ipc/Makefile index 5386fd7c43a..74bbefdeaf4 100644 --- a/tools/testing/selftests/ipc/Makefile +++ b/tools/testing/selftests/ipc/Makefile @@ -1,18 +1,18 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/) ifeq ($(ARCH),i386) - ARCH := X86 + ARCH := x86 CFLAGS := -DCONFIG_X86_32 -D__i386__ endif ifeq ($(ARCH),x86_64) - ARCH := X86 + ARCH := x86 CFLAGS := -DCONFIG_X86_64 -D__x86_64__ endif CFLAGS += -I../../../../usr/include/ all: -ifeq ($(ARCH),X86) +ifeq ($(ARCH),x86) gcc $(CFLAGS) msgque.c -o msgque_test else echo "Not an x86 target, can't build msgque selftest" diff --git a/tools/testing/selftests/kcmp/Makefile b/tools/testing/selftests/kcmp/Makefile index d7d6bbeeff2..8aabd82db9e 100644 --- a/tools/testing/selftests/kcmp/Makefile +++ b/tools/testing/selftests/kcmp/Makefile @@ -1,11 +1,11 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/) ifeq ($(ARCH),i386) - ARCH := X86 + ARCH := x86 CFLAGS := -DCONFIG_X86_32 -D__i386__ endif ifeq ($(ARCH),x86_64) - ARCH := X86 + ARCH := x86 CFLAGS := -DCONFIG_X86_64 -D__x86_64__ endif @@ -15,7 +15,7 @@ CFLAGS += -I../../../../usr/include/ CFLAGS += -I../../../../arch/x86/include/ all: -ifeq ($(ARCH),X86) +ifeq ($(ARCH),x86) gcc $(CFLAGS) kcmp_test.c -o kcmp_test else echo "Not an x86 target, can't build kcmp selftest" diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile index 6816c491c5f..ad4ab01cd28 100644 --- a/tools/testing/selftests/memfd/Makefile +++ b/tools/testing/selftests/memfd/Makefile @@ -1,10 +1,10 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/) ifeq ($(ARCH),i386) - ARCH := X86 + ARCH := x86 endif ifeq ($(ARCH),x86_64) - ARCH := X86 + ARCH := x86 endif CFLAGS += -D_FILE_OFFSET_BITS=64 @@ -14,20 +14,20 @@ CFLAGS += -I../../../../include/uapi/ CFLAGS += -I../../../../include/ all: -ifeq ($(ARCH),X86) +ifeq ($(ARCH),x86) gcc $(CFLAGS) memfd_test.c -o memfd_test else echo "Not an x86 target, can't build memfd selftest" endif run_tests: all -ifeq ($(ARCH),X86) +ifeq ($(ARCH),x86) gcc $(CFLAGS) memfd_test.c -o memfd_test endif @./memfd_test || echo "memfd_test: [FAIL]" build_fuse: -ifeq ($(ARCH),X86) +ifeq ($(ARCH),x86) gcc $(CFLAGS) fuse_mnt.c `pkg-config fuse --cflags --libs` -o fuse_mnt gcc $(CFLAGS) fuse_test.c -o fuse_test else |