From ededb49a9aa54960fce35c705d505d409f5b5483 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Mon, 23 May 2016 16:22:23 -0700 Subject: m32r: fix build failure m32r allmodconfig build was failing with the error: ERROR: "smp_flush_cache_all" [drivers/misc/lkdtm.ko] undefined! lkdtm driver at drivers/misc is using flush_icache_range() which for m32r is defined as smp_flush_cache_all() if CONFIG_SMP is defined. But as smp_flush_cache_all() was not exported so the build was failing with the error of undefined symbol. Link: http://lkml.kernel.org/r/1464001182-8329-1-git-send-email-sudipm.mukherjee@gmail.com Signed-off-by: Sudip Mukherjee Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/m32r/kernel/smp.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c index 62d6961e7f2b..564052e3d3a0 100644 --- a/arch/m32r/kernel/smp.c +++ b/arch/m32r/kernel/smp.c @@ -164,6 +164,7 @@ void smp_flush_cache_all(void) spin_unlock(&flushcache_lock); preempt_enable(); } +EXPORT_SYMBOL(smp_flush_cache_all); void smp_flush_cache_all_interrupt(void) { -- cgit v1.2.3 From f43edca7ed08fc02279f2a62015da5cb6aa0ad61 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Mon, 23 May 2016 16:22:26 -0700 Subject: ELF/MIPS build fix CONFIG_MIPS32_N32=y but CONFIG_BINFMT_ELF disabled results in the following linker errors: arch/mips/built-in.o: In function `elf_core_dump': binfmt_elfn32.c:(.text+0x23dbc): undefined reference to `elf_core_extra_phdrs' binfmt_elfn32.c:(.text+0x246e4): undefined reference to `elf_core_extra_data_size' binfmt_elfn32.c:(.text+0x248d0): undefined reference to `elf_core_write_extra_phdrs' binfmt_elfn32.c:(.text+0x24ac4): undefined reference to `elf_core_write_extra_data' CONFIG_MIPS32_O32=y but CONFIG_BINFMT_ELF disabled results in the following linker errors: arch/mips/built-in.o: In function `elf_core_dump': binfmt_elfo32.c:(.text+0x28a04): undefined reference to `elf_core_extra_phdrs' binfmt_elfo32.c:(.text+0x29330): undefined reference to `elf_core_extra_data_size' binfmt_elfo32.c:(.text+0x2951c): undefined reference to `elf_core_write_extra_phdrs' binfmt_elfo32.c:(.text+0x29710): undefined reference to `elf_core_write_extra_data' This is because binfmt_elfn32 and binfmt_elfo32 are using symbols from elfcore but for these configurations elfcore will not be built. Fixed by making elfcore selectable by a separate config symbol which unlike the current mechanism can also be used from other directories than kernel/, then having each flavor of ELF that relies on elfcore.o, select it in Kconfig, including CONFIG_MIPS32_N32 and CONFIG_MIPS32_O32 which fixes this issue. Link: http://lkml.kernel.org/r/20160520141705.GA1913@linux-mips.org Signed-off-by: Ralf Baechle Reviewed-by: James Hogan Cc: "Maciej W. Rozycki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/Kconfig | 1 + fs/Kconfig.binfmt | 8 ++++++++ kernel/Makefile | 4 +--- 3 files changed, 10 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 8040fb1845b4..46938847e794 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -3117,6 +3117,7 @@ config MIPS32_N32 config BINFMT_ELF32 bool default y if MIPS32_O32 || MIPS32_N32 + select ELFCORE endmenu diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 2d0cbbd14cfc..72c03354c14b 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -1,6 +1,7 @@ config BINFMT_ELF bool "Kernel support for ELF binaries" depends on MMU && (BROKEN || !FRV) + select ELFCORE default y ---help--- ELF (Executable and Linkable Format) is a format for libraries and @@ -26,6 +27,7 @@ config BINFMT_ELF config COMPAT_BINFMT_ELF bool depends on COMPAT && BINFMT_ELF + select ELFCORE config ARCH_BINFMT_ELF_STATE bool @@ -34,6 +36,7 @@ config BINFMT_ELF_FDPIC bool "Kernel support for FDPIC ELF binaries" default y depends on (FRV || BLACKFIN || (SUPERH32 && !MMU) || C6X) + select ELFCORE help ELF FDPIC binaries are based on ELF, but allow the individual load segments of a binary to be located in memory independently of each @@ -43,6 +46,11 @@ config BINFMT_ELF_FDPIC It is also possible to run FDPIC ELF binaries on MMU linux also. +config ELFCORE + bool + help + This option enables kernel/elfcore.o. + config CORE_DUMP_DEFAULT_ELF_HEADERS bool "Write ELF core dumps with partial segments" default y diff --git a/kernel/Makefile b/kernel/Makefile index f0c40bf49d9f..e2ec54e2b952 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -91,9 +91,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_TRACEPOINTS) += tracepoint.o obj-$(CONFIG_LATENCYTOP) += latencytop.o -obj-$(CONFIG_BINFMT_ELF) += elfcore.o -obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o -obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o +obj-$(CONFIG_ELFCORE) += elfcore.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_TRACE_CLOCK) += trace/ -- cgit v1.2.3 From 1e5768ae7500e7ce6eb73e1b263574d5c19606cf Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Mon, 23 May 2016 16:24:13 -0700 Subject: kexec: provide arch_kexec_protect(unprotect)_crashkres() Implement the protection method for the crash kernel memory reservation for the 64-bit x86 kdump. Signed-off-by: Xunlei Pang Cc: Eric Biederman Cc: Dave Young Cc: Minfei Huang Cc: Vivek Goyal Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/machine_kexec_64.c | 45 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index ba7fbba9831b..5a294e48b185 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -538,3 +538,48 @@ overflow: return -ENOEXEC; } #endif /* CONFIG_KEXEC_FILE */ + +static int +kexec_mark_range(unsigned long start, unsigned long end, bool protect) +{ + struct page *page; + unsigned int nr_pages; + + /* + * For physical range: [start, end]. We must skip the unassigned + * crashk resource with zero-valued "end" member. + */ + if (!end || start > end) + return 0; + + page = pfn_to_page(start >> PAGE_SHIFT); + nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1; + if (protect) + return set_pages_ro(page, nr_pages); + else + return set_pages_rw(page, nr_pages); +} + +static void kexec_mark_crashkres(bool protect) +{ + unsigned long control; + + kexec_mark_range(crashk_low_res.start, crashk_low_res.end, protect); + + /* Don't touch the control code page used in crash_kexec().*/ + control = PFN_PHYS(page_to_pfn(kexec_crash_image->control_code_page)); + /* Control code page is located in the 2nd page. */ + kexec_mark_range(crashk_res.start, control + PAGE_SIZE - 1, protect); + control += KEXEC_CONTROL_PAGE_SIZE; + kexec_mark_range(control, crashk_res.end, protect); +} + +void arch_kexec_protect_crashkres(void) +{ + kexec_mark_crashkres(true); +} + +void arch_kexec_unprotect_crashkres(void) +{ + kexec_mark_crashkres(false); +} -- cgit v1.2.3 From 7a0058ec78602da02b34fa2ae3afc523e90d1ab2 Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Mon, 23 May 2016 16:24:22 -0700 Subject: s390/kexec: consolidate crash_map/unmap_reserved_pages() and arch_kexec_protect(unprotect)_crashkres() Commit 3f625002581b ("kexec: introduce a protection mechanism for the crashkernel reserved memory") is a similar mechanism for protecting the crash kernel reserved memory to previous crash_map/unmap_reserved_pages() implementation, the new one is more generic in name and cleaner in code (besides, some arch may not be allowed to unmap the pgtable). Therefore, this patch consolidates them, and uses the new arch_kexec_protect(unprotect)_crashkres() to replace former crash_map/unmap_reserved_pages() which by now has been only used by S390. The consolidation work needs the crash memory to be mapped initially, this is done in machine_kdump_pm_init() which is after reserve_crashkernel(). Once kdump kernel is loaded, the new arch_kexec_protect_crashkres() implemented for S390 will actually unmap the pgtable like before. Signed-off-by: Xunlei Pang Signed-off-by: Michael Holzheu Acked-by: Michael Holzheu Cc: Heiko Carstens Cc: "Eric W. Biederman" Cc: Minfei Huang Cc: Vivek Goyal Cc: Dave Young Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/kernel/machine_kexec.c | 28 ++++++++++++++++++---------- include/linux/kexec.h | 2 -- kernel/kexec.c | 12 ------------ kernel/kexec_core.c | 11 ++--------- 4 files changed, 20 insertions(+), 33 deletions(-) (limited to 'arch') diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 2f1b7217c25c..0e64f08d3d69 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -43,13 +43,13 @@ static int machine_kdump_pm_cb(struct notifier_block *nb, unsigned long action, switch (action) { case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: - if (crashk_res.start) - crash_map_reserved_pages(); + if (kexec_crash_image) + arch_kexec_unprotect_crashkres(); break; case PM_POST_SUSPEND: case PM_POST_HIBERNATION: - if (crashk_res.start) - crash_unmap_reserved_pages(); + if (kexec_crash_image) + arch_kexec_protect_crashkres(); break; default: return NOTIFY_DONE; @@ -60,6 +60,8 @@ static int machine_kdump_pm_cb(struct notifier_block *nb, unsigned long action, static int __init machine_kdump_pm_init(void) { pm_notifier(machine_kdump_pm_cb, 0); + /* Create initial mapping for crashkernel memory */ + arch_kexec_unprotect_crashkres(); return 0; } arch_initcall(machine_kdump_pm_init); @@ -146,6 +148,8 @@ static int kdump_csum_valid(struct kimage *image) #endif } +#ifdef CONFIG_CRASH_DUMP + /* * Map or unmap crashkernel memory */ @@ -167,21 +171,25 @@ static void crash_map_pages(int enable) } /* - * Map crashkernel memory + * Unmap crashkernel memory */ -void crash_map_reserved_pages(void) +void arch_kexec_protect_crashkres(void) { - crash_map_pages(1); + if (crashk_res.end) + crash_map_pages(0); } /* - * Unmap crashkernel memory + * Map crashkernel memory */ -void crash_unmap_reserved_pages(void) +void arch_kexec_unprotect_crashkres(void) { - crash_map_pages(0); + if (crashk_res.end) + crash_map_pages(1); } +#endif + /* * Give back memory to hypervisor before new kdump is loaded */ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 643ff4a3fbf6..e8acb2b43dd9 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -230,8 +230,6 @@ extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); void crash_save_cpu(struct pt_regs *regs, int cpu); void crash_save_vmcoreinfo(void); -void crash_map_reserved_pages(void); -void crash_unmap_reserved_pages(void); void arch_crash_save_vmcoreinfo(void); __printf(1, 2) void vmcoreinfo_append_str(const char *fmt, ...); diff --git a/kernel/kexec.c b/kernel/kexec.c index b73dc211fcfd..4384672d3245 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -136,9 +136,6 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, if (ret) return ret; - if (flags & KEXEC_ON_CRASH) - crash_map_reserved_pages(); - if (flags & KEXEC_PRESERVE_CONTEXT) image->preserve_context = 1; @@ -161,12 +158,6 @@ out: if ((flags & KEXEC_ON_CRASH) && kexec_crash_image) arch_kexec_protect_crashkres(); - /* - * Once the reserved memory is mapped, we should unmap this memory - * before returning - */ - if (flags & KEXEC_ON_CRASH) - crash_unmap_reserved_pages(); kimage_free(image); return ret; } @@ -232,9 +223,6 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, result = do_kexec_load(entry, nr_segments, segments, flags); - if ((flags & KEXEC_ON_CRASH) && kexec_crash_image) - arch_kexec_protect_crashkres(); - mutex_unlock(&kexec_mutex); return result; diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 48b73cc8e425..56b3ed0927b0 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -954,7 +954,6 @@ int crash_shrink_memory(unsigned long new_size) start = roundup(start, KEXEC_CRASH_MEM_ALIGN); end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN); - crash_map_reserved_pages(); crash_free_reserved_phys_range(end, crashk_res.end); if ((start == end) && (crashk_res.parent != NULL)) @@ -968,7 +967,6 @@ int crash_shrink_memory(unsigned long new_size) crashk_res.end = end - 1; insert_resource(&iomem_resource, ram_res); - crash_unmap_reserved_pages(); unlock: mutex_unlock(&kexec_mutex); @@ -1553,17 +1551,12 @@ int kernel_kexec(void) } /* - * Add and remove page tables for crashkernel memory + * Protection mechanism for crashkernel reserved memory after + * the kdump kernel is loaded. * * Provide an empty default implementation here -- architecture * code may override this */ -void __weak crash_map_reserved_pages(void) -{} - -void __weak crash_unmap_reserved_pages(void) -{} - void __weak arch_kexec_protect_crashkres(void) {} -- cgit v1.2.3 From 7efb2a7b85f2d2a53ae50e35cf5df260dd5278b7 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 23 May 2016 16:24:34 -0700 Subject: arch/defconfig: remove CONFIG_RESOURCE_COUNTERS This option was replaced by PAGE_COUNTER which is selected by MEMCG. Signed-off-by: Konstantin Khlebnikov Acked-by: Arnd Bergmann Acked-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/configs/bcm_defconfig | 1 - arch/arm/configs/zx_defconfig | 1 - arch/mips/configs/db1xxx_defconfig | 1 - arch/mips/configs/loongson3_defconfig | 1 - arch/mn10300/configs/asb2364_defconfig | 1 - arch/sh/configs/apsh4ad0a_defconfig | 1 - arch/sh/configs/sdk7786_defconfig | 1 - arch/sh/configs/se7206_defconfig | 1 - arch/sh/configs/shx3_defconfig | 1 - arch/sh/configs/urquell_defconfig | 1 - arch/tile/configs/tilegx_defconfig | 1 - arch/tile/configs/tilepro_defconfig | 1 - arch/um/configs/i386_defconfig | 1 - arch/um/configs/x86_64_defconfig | 1 - arch/x86/configs/i386_defconfig | 1 - arch/x86/configs/x86_64_defconfig | 1 - arch/xtensa/configs/generic_kc705_defconfig | 1 - arch/xtensa/configs/smp_lx200_defconfig | 1 - 18 files changed, 18 deletions(-) (limited to 'arch') diff --git a/arch/arm/configs/bcm_defconfig b/arch/arm/configs/bcm_defconfig index 7117662bab2e..909049a280ec 100644 --- a/arch/arm/configs/bcm_defconfig +++ b/arch/arm/configs/bcm_defconfig @@ -12,7 +12,6 @@ CONFIG_CGROUPS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_SCHED=y CONFIG_BLK_CGROUP=y CONFIG_NAMESPACES=y diff --git a/arch/arm/configs/zx_defconfig b/arch/arm/configs/zx_defconfig index ab683fbbb954..d6253a48a9fa 100644 --- a/arch/arm/configs/zx_defconfig +++ b/arch/arm/configs/zx_defconfig @@ -7,7 +7,6 @@ CONFIG_CGROUPS=y CONFIG_CGROUP_DEBUG=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_SCHED=y CONFIG_RT_GROUP_SCHED=y CONFIG_NAMESPACES=y diff --git a/arch/mips/configs/db1xxx_defconfig b/arch/mips/configs/db1xxx_defconfig index 3bdb72a70364..f0c8971030c4 100644 --- a/arch/mips/configs/db1xxx_defconfig +++ b/arch/mips/configs/db1xxx_defconfig @@ -18,7 +18,6 @@ CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y CONFIG_MEMCG_KMEM=y diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig index f8bf915c6d6b..7f95c4b3ab2c 100644 --- a/arch/mips/configs/loongson3_defconfig +++ b/arch/mips/configs/loongson3_defconfig @@ -25,7 +25,6 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_CPUSETS=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y CONFIG_BLK_CGROUP=y diff --git a/arch/mn10300/configs/asb2364_defconfig b/arch/mn10300/configs/asb2364_defconfig index fbb96ae3122a..cd0a6cb17dee 100644 --- a/arch/mn10300/configs/asb2364_defconfig +++ b/arch/mn10300/configs/asb2364_defconfig @@ -11,7 +11,6 @@ CONFIG_CGROUPS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_RELAY=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set CONFIG_EXPERT=y diff --git a/arch/sh/configs/apsh4ad0a_defconfig b/arch/sh/configs/apsh4ad0a_defconfig index a8d975793b6d..fe45d2c9b151 100644 --- a/arch/sh/configs/apsh4ad0a_defconfig +++ b/arch/sh/configs/apsh4ad0a_defconfig @@ -10,7 +10,6 @@ CONFIG_CGROUPS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_MEMCG=y CONFIG_BLK_CGROUP=y CONFIG_NAMESPACES=y diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig index e7e56a4131b4..36642ec2cb97 100644 --- a/arch/sh/configs/sdk7786_defconfig +++ b/arch/sh/configs/sdk7786_defconfig @@ -17,7 +17,6 @@ CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y # CONFIG_PROC_PID_CPUSET is not set CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_MEMCG=y CONFIG_CGROUP_MEMCG_SWAP=y CONFIG_CGROUP_SCHED=y diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig index 6bc30ab9fd18..91853a67ec34 100644 --- a/arch/sh/configs/se7206_defconfig +++ b/arch/sh/configs/se7206_defconfig @@ -10,7 +10,6 @@ CONFIG_CGROUPS=y CONFIG_CGROUP_DEBUG=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_MEMCG=y CONFIG_RELAY=y CONFIG_NAMESPACES=y diff --git a/arch/sh/configs/shx3_defconfig b/arch/sh/configs/shx3_defconfig index cd6c519f8fad..4a4269ad5b04 100644 --- a/arch/sh/configs/shx3_defconfig +++ b/arch/sh/configs/shx3_defconfig @@ -12,7 +12,6 @@ CONFIG_CGROUPS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_MEMCG=y CONFIG_RELAY=y CONFIG_NAMESPACES=y diff --git a/arch/sh/configs/urquell_defconfig b/arch/sh/configs/urquell_defconfig index 1e843dbed5f0..01c9a91ee896 100644 --- a/arch/sh/configs/urquell_defconfig +++ b/arch/sh/configs/urquell_defconfig @@ -14,7 +14,6 @@ CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y # CONFIG_PROC_PID_CPUSET is not set CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_MEMCG=y CONFIG_CGROUP_MEMCG_SWAP=y CONFIG_CGROUP_SCHED=y diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig index 718905557f7e..48357a4e30a0 100644 --- a/arch/tile/configs/tilegx_defconfig +++ b/arch/tile/configs/tilegx_defconfig @@ -16,7 +16,6 @@ CONFIG_CGROUP_DEBUG=y CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_SCHED=y CONFIG_RT_GROUP_SCHED=y CONFIG_BLK_CGROUP=y diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig index dc85468afd5e..a56c58424a22 100644 --- a/arch/tile/configs/tilepro_defconfig +++ b/arch/tile/configs/tilepro_defconfig @@ -15,7 +15,6 @@ CONFIG_CGROUP_DEBUG=y CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_SCHED=y CONFIG_RT_GROUP_SCHED=y CONFIG_BLK_CGROUP=y diff --git a/arch/um/configs/i386_defconfig b/arch/um/configs/i386_defconfig index a12bf68c9f3a..5636221b8785 100644 --- a/arch/um/configs/i386_defconfig +++ b/arch/um/configs/i386_defconfig @@ -17,7 +17,6 @@ CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_SCHED=y CONFIG_BLK_CGROUP=y # CONFIG_PID_NS is not set diff --git a/arch/um/configs/x86_64_defconfig b/arch/um/configs/x86_64_defconfig index 3aab117bd553..7a67b7ac1a7e 100644 --- a/arch/um/configs/x86_64_defconfig +++ b/arch/um/configs/x86_64_defconfig @@ -15,7 +15,6 @@ CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_SCHED=y CONFIG_BLK_CGROUP=y # CONFIG_PID_NS is not set diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 265901a84f3f..5fa6ee2c2dde 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -17,7 +17,6 @@ CONFIG_CGROUPS=y CONFIG_CGROUP_FREEZER=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_SCHED=y CONFIG_BLK_DEV_INITRD=y # CONFIG_COMPAT_BRK is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 0c8d7963483c..d28bdabcc87e 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -16,7 +16,6 @@ CONFIG_CGROUPS=y CONFIG_CGROUP_FREEZER=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_SCHED=y CONFIG_BLK_DEV_INITRD=y # CONFIG_COMPAT_BRK is not set diff --git a/arch/xtensa/configs/generic_kc705_defconfig b/arch/xtensa/configs/generic_kc705_defconfig index f4b7b3888da8..d9444f01f4da 100644 --- a/arch/xtensa/configs/generic_kc705_defconfig +++ b/arch/xtensa/configs/generic_kc705_defconfig @@ -11,7 +11,6 @@ CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_MEMCG=y CONFIG_NAMESPACES=y CONFIG_SCHED_AUTOGROUP=y diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig index 22eeacba37cc..61f943c95619 100644 --- a/arch/xtensa/configs/smp_lx200_defconfig +++ b/arch/xtensa/configs/smp_lx200_defconfig @@ -11,7 +11,6 @@ CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_MEMCG=y CONFIG_NAMESPACES=y CONFIG_SCHED_AUTOGROUP=y -- cgit v1.2.3 From 864778b154233d3a673c520aa9606777589ecee7 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 23 May 2016 16:25:36 -0700 Subject: mm, aout: handle vm_brk failures vm_brk is allowed to fail but load_aout_binary simply ignores the error and happily continues. I haven't noticed any problem from that in real life but later patches will make the failure more likely because vm_brk will become killable (resp. mmap_sem for write waiting will become killable) so we should be more careful now. The error handling should be quite straightforward because there are calls to vm_mmap which check the error properly already. The only notable exception is set_brk which is called after beyond_if label. But nothing indicates that we cannot move it above set_binfmt as the two do not depend on each other and fail before we do set_binfmt and alter reference counting. Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32_aout.c | 22 +++++++++++++++------- fs/binfmt_aout.c | 11 ++++++++--- 2 files changed, 23 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index ae6aad1d24f7..f5e737ff0022 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -116,13 +116,13 @@ static struct linux_binfmt aout_format = { .min_coredump = PAGE_SIZE }; -static void set_brk(unsigned long start, unsigned long end) +static unsigned long set_brk(unsigned long start, unsigned long end) { start = PAGE_ALIGN(start); end = PAGE_ALIGN(end); if (end <= start) - return; - vm_brk(start, end - start); + return start; + return vm_brk(start, end - start); } #ifdef CONFIG_COREDUMP @@ -349,7 +349,10 @@ static int load_aout_binary(struct linux_binprm *bprm) #endif if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) { - vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); + error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); + if (IS_ERR_VALUE(error)) + return error; + read_code(bprm->file, N_TXTADDR(ex), fd_offset, ex.a_text+ex.a_data); goto beyond_if; @@ -372,10 +375,13 @@ static int load_aout_binary(struct linux_binprm *bprm) if (error != N_DATADDR(ex)) return error; } + beyond_if: - set_binfmt(&aout_format); + error = set_brk(current->mm->start_brk, current->mm->brk); + if (IS_ERR_VALUE(error)) + return error; - set_brk(current->mm->start_brk, current->mm->brk); + set_binfmt(&aout_format); current->mm->start_stack = (unsigned long)create_aout_tables((char __user *)bprm->p, bprm); @@ -434,7 +440,9 @@ static int load_aout_library(struct file *file) error_time = jiffies; } #endif - vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); + retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); + if (IS_ERR_VALUE(retval)) + goto out; read_code(file, start_addr, N_TXTOFF(ex), ex.a_text + ex.a_data); diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 4c556680fa74..2fab9f130e51 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -297,7 +297,10 @@ static int load_aout_binary(struct linux_binprm * bprm) } if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) { - vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); + error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); + if (IS_ERR_VALUE(error)) + return error; + read_code(bprm->file, N_TXTADDR(ex), fd_offset, ex.a_text + ex.a_data); goto beyond_if; @@ -378,8 +381,10 @@ static int load_aout_library(struct file *file) "N_TXTOFF is not page aligned. Please convert library: %pD\n", file); } - vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); - + retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); + if (IS_ERR_VALUE(retval)) + goto out; + read_code(file, start_addr, N_TXTOFF(ex), ex.a_text + ex.a_data); retval = 0; -- cgit v1.2.3 From 69048176078adda4087a648c9b1812ddd800fad1 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 23 May 2016 16:25:54 -0700 Subject: vdso: make arch_setup_additional_pages wait for mmap_sem for write killable most architectures are relying on mmap_sem for write in their arch_setup_additional_pages. If the waiting task gets killed by the oom killer it would block oom_reaper from asynchronous address space reclaim and reduce the chances of timely OOM resolving. Wait for the lock in the killable mode and return with EINTR if the task got killed while waiting. Signed-off-by: Michal Hocko Acked-by: Andy Lutomirski [x86 vdso] Acked-by: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/kernel/process.c | 3 ++- arch/arm64/kernel/vdso.c | 6 ++++-- arch/hexagon/kernel/vdso.c | 3 ++- arch/mips/kernel/vdso.c | 3 ++- arch/powerpc/kernel/vdso.c | 3 ++- arch/s390/kernel/vdso.c | 3 ++- arch/sh/kernel/vsyscall/vsyscall.c | 4 +++- arch/x86/entry/vdso/vma.c | 3 ++- arch/x86/um/vdso/vma.c | 3 ++- 9 files changed, 21 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index a647d6642f3e..4a803c5a1ff7 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -420,7 +420,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) npages = 1; /* for sigpage */ npages += vdso_total_pages; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; hint = sigpage_addr(mm, npages); addr = get_unmapped_area(NULL, hint, npages << PAGE_SHIFT, 0, 0); if (IS_ERR_VALUE(addr)) { diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 64fc030be0f2..9fefb005812a 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -95,7 +95,8 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp) }; void *ret; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; current->mm->context.vdso = (void *)addr; /* Map vectors page at the high address. */ @@ -163,7 +164,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, /* Be sure to map the data page */ vdso_mapping_len = vdso_text_len + PAGE_SIZE; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); if (IS_ERR_VALUE(vdso_base)) { ret = ERR_PTR(vdso_base); diff --git a/arch/hexagon/kernel/vdso.c b/arch/hexagon/kernel/vdso.c index 0bf5a87e4d0a..3ea968415539 100644 --- a/arch/hexagon/kernel/vdso.c +++ b/arch/hexagon/kernel/vdso.c @@ -65,7 +65,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) unsigned long vdso_base; struct mm_struct *mm = current->mm; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; /* Try to get it loaded right near ld.so/glibc. */ vdso_base = STACK_TOP; diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 975e99759bab..54e1663ce639 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -104,7 +104,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) struct resource gic_res; int ret; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; /* * Determine total area size. This includes the VDSO data itself, the diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index def1b8b5e6c1..6767605ea8da 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -195,7 +195,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) * and end up putting it elsewhere. * Add enough to the size so that the result can be aligned. */ - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; vdso_base = get_unmapped_area(NULL, vdso_base, (vdso_pages << PAGE_SHIFT) + ((VDSO_ALIGNMENT - 1) & PAGE_MASK), diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 94495cac8be3..5904abf6b1ae 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -216,7 +216,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) * it at vdso_base which is the "natural" base for it, but we might * fail and end up putting it elsewhere. */ - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; vdso_base = get_unmapped_area(NULL, 0, vdso_pages << PAGE_SHIFT, 0, 0); if (IS_ERR_VALUE(vdso_base)) { rc = vdso_base; diff --git a/arch/sh/kernel/vsyscall/vsyscall.c b/arch/sh/kernel/vsyscall/vsyscall.c index ea2aa1393b87..cc0cc5b4ff18 100644 --- a/arch/sh/kernel/vsyscall/vsyscall.c +++ b/arch/sh/kernel/vsyscall/vsyscall.c @@ -64,7 +64,9 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) unsigned long addr; int ret; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0); if (IS_ERR_VALUE(addr)) { ret = addr; diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index b3cf81333a54..ab220ac9b3b9 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -163,7 +163,8 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) addr = 0; } - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; addr = get_unmapped_area(NULL, addr, image->size - image->sym_vvar_start, 0, 0); diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index 237c6831e095..6be22f991b59 100644 --- a/arch/x86/um/vdso/vma.c +++ b/arch/x86/um/vdso/vma.c @@ -61,7 +61,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (!vdso_enabled) return 0; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; err = install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, VM_READ|VM_EXEC| -- cgit v1.2.3