diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-05-23 19:42:28 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-05-23 19:42:28 -0700 |
| commit | 84787c572d402644dca4874aba73324d9f8e3948 (patch) | |
| tree | 31783e50b09fee00ee7ff87c0c9708a3c7106482 | |
| parent | d62a0234c87f1457a3d2ba519ef90cf164a5eb23 (diff) | |
| parent | c5d2cac0f1caaf7dd21350146fb29c55b3e74249 (diff) | |
| download | op-kernel-dev-84787c572d402644dca4874aba73324d9f8e3948.zip op-kernel-dev-84787c572d402644dca4874aba73324d9f8e3948.tar.gz | |
Merge branch 'akpm' (patches from Andrew)
Merge yet more updates from Andrew Morton:
- Oleg's "wait/ptrace: assume __WALL if the child is traced". It's a
kernel-based workaround for existing userspace issues.
- A few hotfixes
- befs cleanups
- nilfs2 updates
- sys_wait() changes
- kexec updates
- kdump
- scripts/gdb updates
- the last of the MM queue
- a few other misc things
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (84 commits)
kgdb: depends on VT
drm/amdgpu: make amdgpu_mn_get wait for mmap_sem killable
drm/radeon: make radeon_mn_get wait for mmap_sem killable
drm/i915: make i915_gem_mmap_ioctl wait for mmap_sem killable
uprobes: wait for mmap_sem for write killable
prctl: make PR_SET_THP_DISABLE wait for mmap_sem killable
exec: make exec path waiting for mmap_sem killable
aio: make aio_setup_ring killable
coredump: make coredump_wait wait for mmap_sem for write killable
vdso: make arch_setup_additional_pages wait for mmap_sem for write killable
ipc, shm: make shmem attach/detach wait for mmap_sem killable
mm, fork: make dup_mmap wait for mmap_sem for write killable
mm, proc: make clear_refs killable
mm: make vm_brk killable
mm, elf: handle vm_brk error
mm, aout: handle vm_brk failures
mm: make vm_munmap killable
mm: make vm_mmap killable
mm: make mmap_sem for write waits killable for mm syscalls
MAINTAINERS: add co-maintainer for scripts/gdb
...
129 files changed, 1355 insertions, 786 deletions
diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt index 41c3d33..5b21ef7 100644 --- a/Documentation/filesystems/nilfs2.txt +++ b/Documentation/filesystems/nilfs2.txt @@ -268,3 +268,8 @@ among NILFS2 files can be depicted as follows: ( regular file, directory, or symlink ) For detail on the format of each file, please see include/linux/nilfs2_fs.h. + +There are no patents or other intellectual property that we protect +with regard to the design of NILFS2. It is allowed to replicate the +design in hopes that other operating systems could share (mount, read, +write, etc.) data stored in this format. diff --git a/Documentation/gdb-kernel-debugging.txt b/Documentation/gdb-kernel-debugging.txt index 7050ce8..4ab7d43 100644 --- a/Documentation/gdb-kernel-debugging.txt +++ b/Documentation/gdb-kernel-debugging.txt @@ -139,6 +139,27 @@ Examples of using the Linux-provided gdb helpers start_comm = "swapper/2\000\000\000\000\000\000" } + o Dig into a radix tree data structure, such as the IRQ descriptors: + (gdb) print (struct irq_desc)$lx_radix_tree_lookup(irq_desc_tree, 18) + $6 = { + irq_common_data = { + state_use_accessors = 67584, + handler_data = 0x0 <__vectors_start>, + msi_desc = 0x0 <__vectors_start>, + affinity = {{ + bits = {65535} + }} + }, + irq_data = { + mask = 0, + irq = 18, + hwirq = 27, + common = 0xee803d80, + chip = 0xc0eb0854 <gic_data>, + domain = 0xee808000, + parent_data = 0x0 <__vectors_start>, + chip_data = 0xc0eb0854 <gic_data> + } <... trimmed ...> List of commands and functions ------------------------------ diff --git a/Documentation/kdump/gdbmacros.txt b/Documentation/kdump/gdbmacros.txt index 9b9b454..35f6a98 100644 --- a/Documentation/kdump/gdbmacros.txt +++ b/Documentation/kdump/gdbmacros.txt @@ -15,15 +15,16 @@ define bttnobp set $tasks_off=((size_t)&((struct task_struct *)0)->tasks) - set $pid_off=((size_t)&((struct task_struct *)0)->pids[1].pid_list.next) + set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next) set $init_t=&init_task set $next_t=(((char *)($init_t->tasks).next) - $tasks_off) + set var $stacksize = sizeof(union thread_union) while ($next_t != $init_t) set $next_t=(struct task_struct *)$next_t printf "\npid %d; comm %s:\n", $next_t.pid, $next_t.comm printf "===================\n" - set var $stackp = $next_t.thread.esp - set var $stack_top = ($stackp & ~4095) + 4096 + set var $stackp = $next_t.thread.sp + set var $stack_top = ($stackp & ~($stacksize - 1)) + $stacksize while ($stackp < $stack_top) if (*($stackp) > _stext && *($stackp) < _sinittext) @@ -31,13 +32,13 @@ define bttnobp end set $stackp += 4 end - set $next_th=(((char *)$next_t->pids[1].pid_list.next) - $pid_off) + set $next_th=(((char *)$next_t->thread_group.next) - $pid_off) while ($next_th != $next_t) set $next_th=(struct task_struct *)$next_th printf "\npid %d; comm %s:\n", $next_t.pid, $next_t.comm printf "===================\n" - set var $stackp = $next_t.thread.esp - set var $stack_top = ($stackp & ~4095) + 4096 + set var $stackp = $next_t.thread.sp + set var $stack_top = ($stackp & ~($stacksize - 1)) + stacksize while ($stackp < $stack_top) if (*($stackp) > _stext && *($stackp) < _sinittext) @@ -45,7 +46,7 @@ define bttnobp end set $stackp += 4 end - set $next_th=(((char *)$next_th->pids[1].pid_list.next) - $pid_off) + set $next_th=(((char *)$next_th->thread_group.next) - $pid_off) end set $next_t=(char *)($next_t->tasks.next) - $tasks_off end @@ -54,42 +55,44 @@ document bttnobp dump all thread stack traces on a kernel compiled with !CONFIG_FRAME_POINTER end +define btthreadstack + set var $pid_task = $arg0 + + printf "\npid %d; comm %s:\n", $pid_task.pid, $pid_task.comm + printf "task struct: " + print $pid_task + printf "===================\n" + set var $stackp = $pid_task.thread.sp + set var $stacksize = sizeof(union thread_union) + set var $stack_top = ($stackp & ~($stacksize - 1)) + $stacksize + set var $stack_bot = ($stackp & ~($stacksize - 1)) + + set $stackp = *((unsigned long *) $stackp) + while (($stackp < $stack_top) && ($stackp > $stack_bot)) + set var $addr = *(((unsigned long *) $stackp) + 1) + info symbol $addr + set $stackp = *((unsigned long *) $stackp) + end +end +document btthreadstack + dump a thread stack using the given task structure pointer +end + + define btt set $tasks_off=((size_t)&((struct task_struct *)0)->tasks) - set $pid_off=((size_t)&((struct task_struct *)0)->pids[1].pid_list.next) + set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next) set $init_t=&init_task set $next_t=(((char *)($init_t->tasks).next) - $tasks_off) while ($next_t != $init_t) set $next_t=(struct task_struct *)$next_t - printf "\npid %d; comm %s:\n", $next_t.pid, $next_t.comm - printf "===================\n" - set var $stackp = $next_t.thread.esp - set var $stack_top = ($stackp & ~4095) + 4096 - set var $stack_bot = ($stackp & ~4095) - - set $stackp = *($stackp) - while (($stackp < $stack_top) && ($stackp > $stack_bot)) - set var $addr = *($stackp + 4) - info symbol $addr - set $stackp = *($stackp) - end + btthreadstack $next_t - set $next_th=(((char *)$next_t->pids[1].pid_list.next) - $pid_off) + set $next_th=(((char *)$next_t->thread_group.next) - $pid_off) while ($next_th != $next_t) set $next_th=(struct task_struct *)$next_th - printf "\npid %d; comm %s:\n", $next_t.pid, $next_t.comm - printf "===================\n" - set var $stackp = $next_t.thread.esp - set var $stack_top = ($stackp & ~4095) + 4096 - set var $stack_bot = ($stackp & ~4095) - - set $stackp = *($stackp) - while (($stackp < $stack_top) && ($stackp > $stack_bot)) - set var $addr = *($stackp + 4) - info symbol $addr - set $stackp = *($stackp) - end - set $next_th=(((char *)$next_th->pids[1].pid_list.next) - $pid_off) + btthreadstack $next_th + set $next_th=(((char *)$next_th->thread_group.next) - $pid_off) end set $next_t=(char *)($next_t->tasks.next) - $tasks_off end @@ -101,7 +104,7 @@ end define btpid set var $pid = $arg0 set $tasks_off=((size_t)&((struct task_struct *)0)->tasks) - set $pid_off=((size_t)&((struct task_struct *)0)->pids[1].pid_list.next) + set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next) set $init_t=&init_task set $next_t=(((char *)($init_t->tasks).next) - $tasks_off) set var $pid_task = 0 @@ -113,29 +116,18 @@ define btpid set $pid_task = $next_t end - set $next_th=(((char *)$next_t->pids[1].pid_list.next) - $pid_off) + set $next_th=(((char *)$next_t->thread_group.next) - $pid_off) while ($next_th != $next_t) set $next_th=(struct task_struct *)$next_th if ($next_th.pid == $pid) set $pid_task = $next_th end - set $next_th=(((char *)$next_th->pids[1].pid_list.next) - $pid_off) + set $next_th=(((char *)$next_th->thread_group.next) - $pid_off) end set $next_t=(char *)($next_t->tasks.next) - $tasks_off end - printf "\npid %d; comm %s:\n", $pid_task.pid, $pid_task.comm - printf "===================\n" - set var $stackp = $pid_task.thread.esp - set var $stack_top = ($stackp & ~4095) + 4096 - set var $stack_bot = ($stackp & ~4095) - - set $stackp = *($stackp) - while (($stackp < $stack_top) && ($stackp > $stack_bot)) - set var $addr = *($stackp + 4) - info symbol $addr - set $stackp = *($stackp) - end + btthreadstack $pid_task end document btpid backtrace of pid @@ -145,7 +137,7 @@ end define trapinfo set var $pid = $arg0 set $tasks_off=((size_t)&((struct task_struct *)0)->tasks) - set $pid_off=((size_t)&((struct task_struct *)0)->pids[1].pid_list.next) + set $pid_off=((size_t)&((struct task_struct *)0)->thread_group.next) set $init_t=&init_task set $next_t=(((char *)($init_t->tasks).next) - $tasks_off) set var $pid_task = 0 @@ -157,13 +149,13 @@ define trapinfo set $pid_task = $next_t end - set $next_th=(((char *)$next_t->pids[1].pid_list.next) - $pid_off) + set $next_th=(((char *)$next_t->thread_group.next) - $pid_off) while ($next_th != $next_t) set $next_th=(struct task_struct *)$next_th if ($next_th.pid == $pid) set $pid_task = $next_th end - set $next_th=(((char *)$next_th->pids[1].pid_list.next) - $pid_off) + set $next_th=(((char *)$next_th->thread_group.next) - $pid_off) end set $next_t=(char *)($next_t->tasks.next) - $tasks_off end @@ -5,6 +5,7 @@ # 2) Generate timeconst.h # 3) Generate asm-offsets.h (may need bounds.h and timeconst.h) # 4) Check for missing system calls +# 5) Generate constants.py (may need bounds.h) # Default sed regexp - multiline due to syntax constraints define sed-y @@ -96,5 +97,14 @@ quiet_cmd_syscalls = CALL $< missing-syscalls: scripts/checksyscalls.sh $(offsets-file) FORCE $(call cmd,syscalls) +##### +# 5) Generate constants for Python GDB integration +# + +extra-$(CONFIG_GDB_SCRIPTS) += build_constants_py + +build_constants_py: $(obj)/$(timeconst-file) $(obj)/$(bounds-file) + @$(MAKE) $(build)=scripts/gdb/linux $@ + # Keep these three files during make clean no-clean-files := $(bounds-file) $(offsets-file) $(timeconst-file) diff --git a/MAINTAINERS b/MAINTAINERS index f27ff1b..3302006 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4993,6 +4993,7 @@ F: drivers/scsi/gdt* GDB KERNEL DEBUGGING HELPER SCRIPTS M: Jan Kiszka <jan.kiszka@siemens.com> +M: Kieran Bingham <kieran@bingham.xyz> S: Supported F: scripts/gdb/ @@ -8038,6 +8039,7 @@ NILFS2 FILESYSTEM M: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> L: linux-nilfs@vger.kernel.org W: http://nilfs.sourceforge.net/ +W: http://nilfs.osdn.jp/ T: git git://github.com/konis/nilfs2.git S: Supported F: Documentation/filesystems/nilfs2.txt diff --git a/arch/arm/configs/bcm_defconfig b/arch/arm/configs/bcm_defconfig index 7117662..909049a2 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 ab683fb..d6253a4 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/arm/kernel/process.c b/arch/arm/kernel/process.c index a647d66..4a803c5 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 64fc030..9fefb00 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 0bf5a87..3ea96841 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/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c index 62d6961..564052e 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) { diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 8040fb1..4693884 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/arch/mips/configs/db1xxx_defconfig b/arch/mips/configs/db1xxx_defconfig index 3bdb72a..f0c8971 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 f8bf915c..7f95c4b 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/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 975e997..54e1663 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/mn10300/configs/asb2364_defconfig b/arch/mn10300/configs/asb2364_defconfig index fbb96ae..cd0a6cb 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/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index def1b8b..6767605 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/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 2f1b721..0e64f08 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/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 94495ca..5904abf 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/configs/apsh4ad0a_defconfig b/arch/sh/configs/apsh4ad0a_defconfig index a8d9757..fe45d2c 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 e7e56a4..36642ec2 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 6bc30ab..91853a6 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 cd6c519..4a4269a 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 1e843db..01c9a91 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/sh/kernel/vsyscall/vsyscall.c b/arch/sh/kernel/vsyscall/vsyscall.c index ea2aa13..cc0cc5b 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/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig index dea47c3..fd122ef 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 95743ee..eb6a559 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 a12bf68..5636221 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 3aab117..7a67b7a 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 265901a..5fa6ee2 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 0c8d796..d28bdab 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/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index b3cf813..ab220ac 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/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index ae6aad1..f5e737f 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/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index ba7fbba..5a294e4 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); +} diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index 237c683..6be22f9 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| diff --git a/arch/xtensa/configs/generic_kc705_defconfig b/arch/xtensa/configs/generic_kc705_defconfig index f4b7b38..d9444f0 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 22eeacb..61f943c 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 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index 9f4a45c..32fa7b7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -232,7 +232,10 @@ static struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev) int r; mutex_lock(&adev->mn_lock); - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) { + mutex_unlock(&adev->mn_lock); + return ERR_PTR(-EINTR); + } hash_for_each_possible(adev->mn_hash, rmn, node, (unsigned long)mm) if (rmn->mm == mm) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 94bbc43..9b99490 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1721,7 +1721,10 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) { + drm_gem_object_unreference_unlocked(obj); + return -EINTR; + } vma = find_vma(mm, addr); if (vma) vma->vm_page_prot = diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c index eef006c..896f2cf 100644 --- a/drivers/gpu/drm/radeon/radeon_mn.c +++ b/drivers/gpu/drm/radeon/radeon_mn.c @@ -186,7 +186,9 @@ static struct radeon_mn *radeon_mn_get(struct radeon_device *rdev) struct radeon_mn *rmn; int r; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return ERR_PTR(-EINTR); + mutex_lock(&rdev->mn_lock); hash_for_each_possible(rdev->mn_hash, rmn, node, (unsigned long)mm) diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index 922a750..0fb27d3 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -1033,12 +1033,11 @@ static int mspro_block_read_attributes(struct memstick_dev *card) } msb->attr_group.name = "media_attributes"; - buffer = kmalloc(attr_len, GFP_KERNEL); + buffer = kmemdup(attr, attr_len, GFP_KERNEL); if (!buffer) { rc = -ENOMEM; goto out_free_attr; } - memcpy(buffer, (char *)attr, attr_len); for (cnt = 0; cnt < attr_count; ++cnt) { s_attr = kzalloc(sizeof(struct mspro_sys_attr), GFP_KERNEL); diff --git a/drivers/memstick/host/rtsx_usb_ms.c b/drivers/memstick/host/rtsx_usb_ms.c index 1105db2..d34bc35 100644 --- a/drivers/memstick/host/rtsx_usb_ms.c +++ b/drivers/memstick/host/rtsx_usb_ms.c @@ -706,7 +706,7 @@ poll_again: if (host->eject) break; - msleep(1000); + schedule_timeout_idle(HZ); } complete(&host->detect_ms_exit); diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 2d0cbbd..72c0335 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 @@ -496,7 +496,12 @@ static int aio_setup_ring(struct kioctx *ctx) ctx->mmap_size = nr_pages * PAGE_SIZE; pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size); - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) { + ctx->mmap_size = 0; + aio_free_ring(ctx); + return -EINTR; + } + ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, 0, &unused); diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c index dde0b79..af1bc19 100644 --- a/fs/befs/datastream.c +++ b/fs/befs/datastream.c @@ -48,7 +48,7 @@ struct buffer_head * befs_read_datastream(struct super_block *sb, const befs_data_stream *ds, befs_off_t pos, uint * off) { - struct buffer_head *bh = NULL; + struct buffer_head *bh; befs_block_run run; befs_blocknr_t block; /* block coresponding to pos */ @@ -127,7 +127,7 @@ befs_read_lsymlink(struct super_block *sb, const befs_data_stream *ds, { befs_off_t bytes_read = 0; /* bytes readed */ u16 plen; - struct buffer_head *bh = NULL; + struct buffer_head *bh; befs_debug(sb, "---> %s length: %llu", __func__, len); while (bytes_read < len) { @@ -429,7 +429,7 @@ befs_find_brun_dblindirect(struct super_block *sb, struct buffer_head *dbl_indir_block; struct buffer_head *indir_block; befs_block_run indir_run; - befs_disk_inode_addr *iaddr_array = NULL; + befs_disk_inode_addr *iaddr_array; struct befs_sb_info *befs_sb = BEFS_SB(sb); befs_blocknr_t indir_start_blk = @@ -488,7 +488,6 @@ befs_find_brun_dblindirect(struct super_block *sb, iaddr_array = (befs_disk_inode_addr *) dbl_indir_block->b_data; indir_run = fsrun_to_cpu(sb, iaddr_array[dbl_block_indx]); brelse(dbl_indir_block); - iaddr_array = NULL; /* Read indirect block */ which_block = indir_indx / befs_iaddrs_per_block(sb); @@ -513,7 +512,6 @@ befs_find_brun_dblindirect(struct super_block *sb, iaddr_array = (befs_disk_inode_addr *) indir_block->b_data; *run = fsrun_to_cpu(sb, iaddr_array[block_indx]); brelse(indir_block); - iaddr_array = NULL; blockno_at_run_start = indir_start_blk; blockno_at_run_start += diblklen * dblindir_indx; diff --git a/fs/befs/io.c b/fs/befs/io.c index 7a5b4ec..523c8af 100644 --- a/fs/befs/io.c +++ b/fs/befs/io.c @@ -26,7 +26,7 @@ struct buffer_head * befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr) { - struct buffer_head *bh = NULL; + struct buffer_head *bh; befs_blocknr_t block = 0; struct befs_sb_info *befs_sb = BEFS_SB(sb); @@ -63,7 +63,7 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr) struct buffer_head * befs_bread(struct super_block *sb, befs_blocknr_t block) { - struct buffer_head *bh = NULL; + struct buffer_head *bh; befs_debug(sb, "---> Enter %s %lu", __func__, (unsigned long)block); diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 71112aa..7da05b1 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -155,7 +155,7 @@ befs_get_block(struct inode *inode, sector_t block, static struct dentry * befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - struct inode *inode = NULL; + struct inode *inode; struct super_block *sb = dir->i_sb; const befs_data_stream *ds = &BEFS_I(dir)->i_data.ds; befs_off_t offset; @@ -294,10 +294,10 @@ static void init_once(void *foo) static struct inode *befs_iget(struct super_block *sb, unsigned long ino) { - struct buffer_head *bh = NULL; - befs_inode *raw_inode = NULL; + struct buffer_head *bh; + befs_inode *raw_inode; struct befs_sb_info *befs_sb = BEFS_SB(sb); - struct befs_inode_info *befs_ino = NULL; + struct befs_inode_info *befs_ino; struct inode *inode; long ret = -EIO; diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 4c55668..2fab9f1 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; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 56224ff..938fc4e 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1176,8 +1176,11 @@ static int load_elf_library(struct file *file) len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr + ELF_MIN_ALIGN - 1); bss = eppnt->p_memsz + eppnt->p_vaddr; - if (bss > len) - vm_brk(len, bss - len); + if (bss > len) { + error = vm_brk(len, bss - len); + if (BAD_ADDR(error)) + goto out_free_ph; + } error = 0; out_free_ph: diff --git a/fs/coredump.c b/fs/coredump.c index 492c2db..38a7ab8 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -413,7 +413,9 @@ static int coredump_wait(int exit_code, struct core_state *core_state) core_state->dumper.task = tsk; core_state->dumper.next = NULL; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + if (!mm->core_state) core_waiters = zap_threads(tsk, mm, core_state, exit_code); up_write(&mm->mmap_sem); @@ -243,10 +243,6 @@ static void put_arg_page(struct page *page) put_page(page); } -static void free_arg_page(struct linux_binprm *bprm, int i) -{ -} - static void free_arg_pages(struct linux_binprm *bprm) { } @@ -267,7 +263,10 @@ static int __bprm_mm_init(struct linux_binprm *bprm) if (!vma) return -ENOMEM; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) { + err = -EINTR; + goto err_free; + } vma->vm_mm = mm; /* @@ -294,6 +293,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) return 0; err: up_write(&mm->mmap_sem); +err_free: bprm->vma = NULL; kmem_cache_free(vm_area_cachep, vma); return err; @@ -700,7 +700,9 @@ int setup_arg_pages(struct linux_binprm *bprm, bprm->loader -= stack_shift; bprm->exec -= stack_shift; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + vm_flags = VM_STACK_FLAGS; /* @@ -1499,9 +1501,6 @@ int remove_arg_zero(struct linux_binprm *bprm) kunmap_atomic(kaddr); put_arg_page(page); - - if (offset == PAGE_SIZE) - free_arg_page(bprm, (bprm->p >> PAGE_SHIFT) - 1); } while (offset == PAGE_SIZE); bprm->p++; diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 2ccbf55..1a85d94 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -13,13 +13,8 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Original code was written by Koji Sato <koji@osrg.net>. - * Two allocators were unified by Ryusuke Konishi <ryusuke@osrg.net>, - * Amagai Yoshiji <amagai@osrg.net>. + * Originally written by Koji Sato. + * Two allocators were unified by Ryusuke Konishi and Amagai Yoshiji. */ #include <linux/types.h> @@ -58,7 +53,7 @@ nilfs_palloc_groups_count(const struct inode *inode) * @inode: inode of metadata file using this allocator * @entry_size: size of the persistent object */ -int nilfs_palloc_init_blockgroup(struct inode *inode, unsigned entry_size) +int nilfs_palloc_init_blockgroup(struct inode *inode, unsigned int entry_size) { struct nilfs_mdt_info *mi = NILFS_MDT(inode); @@ -73,13 +68,17 @@ int nilfs_palloc_init_blockgroup(struct inode *inode, unsigned entry_size) mi->mi_blocks_per_group = DIV_ROUND_UP(nilfs_palloc_entries_per_group(inode), mi->mi_entries_per_block) + 1; - /* Number of blocks in a group including entry blocks and - a bitmap block */ + /* + * Number of blocks in a group including entry blocks + * and a bitmap block + */ mi->mi_blocks_per_desc_block = nilfs_palloc_groups_per_desc_block(inode) * mi->mi_blocks_per_group + 1; - /* Number of blocks per descriptor including the - descriptor block */ + /* + * Number of blocks per descriptor including the + * descriptor block + */ return 0; } @@ -389,7 +388,7 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr, */ static int nilfs_palloc_find_available_slot(unsigned char *bitmap, unsigned long target, - unsigned bsize, + unsigned int bsize, spinlock_t *lock) { int pos, end = bsize; @@ -624,7 +623,7 @@ void nilfs_palloc_commit_free_entry(struct inode *inode, if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) nilfs_warning(inode->i_sb, __func__, - "entry number %llu already freed: ino=%lu\n", + "entry number %llu already freed: ino=%lu", (unsigned long long)req->pr_entry_nr, (unsigned long)inode->i_ino); else @@ -665,7 +664,7 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode, if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) nilfs_warning(inode->i_sb, __func__, - "entry number %llu already freed: ino=%lu\n", + "entry number %llu already freed: ino=%lu", (unsigned long long)req->pr_entry_nr, (unsigned long)inode->i_ino); else @@ -740,8 +739,8 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) unsigned long group, group_offset; __u64 group_min_nr, last_nrs[8]; const unsigned long epg = nilfs_palloc_entries_per_group(inode); - const unsigned epb = NILFS_MDT(inode)->mi_entries_per_block; - unsigned entry_start, end, pos; + const unsigned int epb = NILFS_MDT(inode)->mi_entries_per_block; + unsigned int entry_start, end, pos; spinlock_t *lock; int i, j, k, ret; u32 nfree; @@ -774,7 +773,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) { nilfs_warning(inode->i_sb, __func__, - "entry number %llu already freed: ino=%lu\n", + "entry number %llu already freed: ino=%lu", (unsigned long long)entry_nrs[j], (unsigned long)inode->i_ino); } else { @@ -819,7 +818,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) last_nrs[k]); if (ret && ret != -ENOENT) { nilfs_warning(inode->i_sb, __func__, - "failed to delete block of entry %llu: ino=%lu, err=%d\n", + "failed to delete block of entry %llu: ino=%lu, err=%d", (unsigned long long)last_nrs[k], (unsigned long)inode->i_ino, ret); } @@ -838,7 +837,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) ret = nilfs_palloc_delete_bitmap_block(inode, group); if (ret && ret != -ENOENT) { nilfs_warning(inode->i_sb, __func__, - "failed to delete bitmap block of group %lu: ino=%lu, err=%d\n", + "failed to delete bitmap block of group %lu: ino=%lu, err=%d", group, (unsigned long)inode->i_ino, ret); } diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h index 6e6f49a..05149e6 100644 --- a/fs/nilfs2/alloc.h +++ b/fs/nilfs2/alloc.h @@ -13,13 +13,8 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Original code was written by Koji Sato <koji@osrg.net>. - * Two allocators were unified by Ryusuke Konishi <ryusuke@osrg.net>, - * Amagai Yoshiji <amagai@osrg.net>. + * Originally written by Koji Sato. + * Two allocators were unified by Ryusuke Konishi and Amagai Yoshiji. */ #ifndef _NILFS_ALLOC_H @@ -42,7 +37,7 @@ nilfs_palloc_entries_per_group(const struct inode *inode) return 1UL << (inode->i_blkbits + 3 /* log2(8 = CHAR_BITS) */); } -int nilfs_palloc_init_blockgroup(struct inode *, unsigned); +int nilfs_palloc_init_blockgroup(struct inode *, unsigned int); int nilfs_palloc_get_entry_block(struct inode *, __u64, int, struct buffer_head **); void *nilfs_palloc_block_get_entry(const struct inode *, __u64, diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index a9fb363..f2a7877 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #include <linux/fs.h> @@ -46,7 +42,7 @@ static int nilfs_bmap_convert_error(struct nilfs_bmap *bmap, if (err == -EINVAL) { nilfs_error(inode->i_sb, fname, - "broken bmap (inode number=%lu)\n", inode->i_ino); + "broken bmap (inode number=%lu)", inode->i_ino); err = -EIO; } return err; @@ -97,7 +93,7 @@ int nilfs_bmap_lookup_at_level(struct nilfs_bmap *bmap, __u64 key, int level, } int nilfs_bmap_lookup_contig(struct nilfs_bmap *bmap, __u64 key, __u64 *ptrp, - unsigned maxblocks) + unsigned int maxblocks) { int ret; diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h index bfa817c..b6a4c8f9 100644 --- a/fs/nilfs2/bmap.h +++ b/fs/nilfs2/bmap.h @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #ifndef _NILFS_BMAP_H @@ -61,7 +57,7 @@ struct nilfs_bmap_stats { struct nilfs_bmap_operations { int (*bop_lookup)(const struct nilfs_bmap *, __u64, int, __u64 *); int (*bop_lookup_contig)(const struct nilfs_bmap *, __u64, __u64 *, - unsigned); + unsigned int); int (*bop_insert)(struct nilfs_bmap *, __u64, __u64); int (*bop_delete)(struct nilfs_bmap *, __u64); void (*bop_clear)(struct nilfs_bmap *); @@ -126,10 +122,14 @@ struct nilfs_bmap { /* pointer type */ #define NILFS_BMAP_PTR_P 0 /* physical block number (i.e. LBN) */ -#define NILFS_BMAP_PTR_VS 1 /* virtual block number (single - version) */ -#define NILFS_BMAP_PTR_VM 2 /* virtual block number (has multiple - versions) */ +#define NILFS_BMAP_PTR_VS 1 /* + * virtual block number (single + * version) + */ +#define NILFS_BMAP_PTR_VM 2 /* + * virtual block number (has multiple + * versions) + */ #define NILFS_BMAP_PTR_U (-1) /* never perform pointer operations */ #define NILFS_BMAP_USE_VBN(bmap) ((bmap)->b_ptr_type > 0) @@ -154,7 +154,7 @@ struct nilfs_bmap_store { int nilfs_bmap_test_and_clear_dirty(struct nilfs_bmap *); int nilfs_bmap_read(struct nilfs_bmap *, struct nilfs_inode *); void nilfs_bmap_write(struct nilfs_bmap *, struct nilfs_inode *); -int nilfs_bmap_lookup_contig(struct nilfs_bmap *, __u64, __u64 *, unsigned); +int nilfs_bmap_lookup_contig(struct nilfs_bmap *, __u64, __u64 *, unsigned int); int nilfs_bmap_insert(struct nilfs_bmap *bmap, __u64 key, unsigned long rec); int nilfs_bmap_delete(struct nilfs_bmap *bmap, __u64 key); int nilfs_bmap_seek_key(struct nilfs_bmap *bmap, __u64 start, __u64 *keyp); diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index e0c9daf..0576033 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -13,13 +13,8 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * This file was originally written by Seiji Kihara <kihara@osrg.net> - * and fully revised by Ryusuke Konishi <ryusuke@osrg.net> for - * stabilization and simplification. + * Originally written by Seiji Kihara. + * Fully revised by Ryusuke Konishi for stabilization and simplification. * */ diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h index d876b56..2cc1b80 100644 --- a/fs/nilfs2/btnode.h +++ b/fs/nilfs2/btnode.h @@ -13,12 +13,8 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Seiji Kihara <kihara@osrg.net> - * Revised by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Seiji Kihara. + * Revised by Ryusuke Konishi. */ #ifndef _NILFS_BTNODE_H diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 3a3821b..eccb1c8 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #include <linux/slab.h> @@ -689,7 +685,8 @@ static int nilfs_btree_lookup(const struct nilfs_bmap *btree, } static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, - __u64 key, __u64 *ptrp, unsigned maxblocks) + __u64 key, __u64 *ptrp, + unsigned int maxblocks) { struct nilfs_btree_path *path; struct nilfs_btree_node *node; @@ -1032,12 +1029,12 @@ static __u64 nilfs_btree_find_target_v(const struct nilfs_bmap *btree, if (ptr != NILFS_BMAP_INVALID_PTR) /* sequential access */ return ptr; - else { - ptr = nilfs_btree_find_near(btree, path); - if (ptr != NILFS_BMAP_INVALID_PTR) - /* near */ - return ptr; - } + + ptr = nilfs_btree_find_near(btree, path); + if (ptr != NILFS_BMAP_INVALID_PTR) + /* near */ + return ptr; + /* block group */ return nilfs_bmap_find_target_in_group(btree); } diff --git a/fs/nilfs2/btree.h b/fs/nilfs2/btree.h index 22c02e3..df1a25f 100644 --- a/fs/nilfs2/btree.h +++ b/fs/nilfs2/btree.h @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #ifndef _NILFS_BTREE_H diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c index b6596ca..8a3d3b6 100644 --- a/fs/nilfs2/cpfile.c +++ b/fs/nilfs2/cpfile.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #include <linux/kernel.h> @@ -41,6 +37,7 @@ static unsigned long nilfs_cpfile_get_blkoff(const struct inode *cpfile, __u64 cno) { __u64 tcno = cno + NILFS_MDT(cpfile)->mi_first_entry_offset - 1; + do_div(tcno, nilfs_cpfile_checkpoints_per_block(cpfile)); return (unsigned long)tcno; } @@ -50,6 +47,7 @@ static unsigned long nilfs_cpfile_get_offset(const struct inode *cpfile, __u64 cno) { __u64 tcno = cno + NILFS_MDT(cpfile)->mi_first_entry_offset - 1; + return do_div(tcno, nilfs_cpfile_checkpoints_per_block(cpfile)); } @@ -433,7 +431,8 @@ static void nilfs_cpfile_checkpoint_to_cpinfo(struct inode *cpfile, } static ssize_t nilfs_cpfile_do_get_cpinfo(struct inode *cpfile, __u64 *cnop, - void *buf, unsigned cisz, size_t nci) + void *buf, unsigned int cisz, + size_t nci) { struct nilfs_checkpoint *cp; struct nilfs_cpinfo *ci = buf; @@ -484,7 +483,8 @@ static ssize_t nilfs_cpfile_do_get_cpinfo(struct inode *cpfile, __u64 *cnop, } static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop, - void *buf, unsigned cisz, size_t nci) + void *buf, unsigned int cisz, + size_t nci) { struct buffer_head *bh; struct nilfs_cpfile_header *header; @@ -570,7 +570,7 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop, */ ssize_t nilfs_cpfile_get_cpinfo(struct inode *cpfile, __u64 *cnop, int mode, - void *buf, unsigned cisz, size_t nci) + void *buf, unsigned int cisz, size_t nci) { switch (mode) { case NILFS_CHECKPOINT: @@ -870,8 +870,10 @@ int nilfs_cpfile_is_snapshot(struct inode *cpfile, __u64 cno) void *kaddr; int ret; - /* CP number is invalid if it's zero or larger than the - largest exist one.*/ + /* + * CP number is invalid if it's zero or larger than the + * largest existing one. + */ if (cno == 0 || cno >= nilfs_mdt_cno(cpfile)) return -ENOENT; down_read(&NILFS_MDT(cpfile)->mi_sem); diff --git a/fs/nilfs2/cpfile.h b/fs/nilfs2/cpfile.h index a242b9a..0249744 100644 --- a/fs/nilfs2/cpfile.h +++ b/fs/nilfs2/cpfile.h @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #ifndef _NILFS_CPFILE_H @@ -37,8 +33,8 @@ int nilfs_cpfile_delete_checkpoint(struct inode *, __u64); int nilfs_cpfile_change_cpmode(struct inode *, __u64, int); int nilfs_cpfile_is_snapshot(struct inode *, __u64); int nilfs_cpfile_get_stat(struct inode *, struct nilfs_cpstat *); -ssize_t nilfs_cpfile_get_cpinfo(struct inode *, __u64 *, int, void *, unsigned, - size_t); +ssize_t nilfs_cpfile_get_cpinfo(struct inode *, __u64 *, int, void *, + unsigned int, size_t); int nilfs_cpfile_read(struct super_block *sb, size_t cpsize, struct nilfs_inode *raw_inode, struct inode **inodep); diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 7dc23f1..7367610 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #include <linux/types.h> @@ -428,7 +424,7 @@ int nilfs_dat_translate(struct inode *dat, __u64 vblocknr, sector_t *blocknrp) return ret; } -ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned visz, +ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned int visz, size_t nvi) { struct buffer_head *entry_bh; diff --git a/fs/nilfs2/dat.h b/fs/nilfs2/dat.h index cbd8e97..abbfdab 100644 --- a/fs/nilfs2/dat.h +++ b/fs/nilfs2/dat.h @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #ifndef _NILFS_DAT_H @@ -51,7 +47,7 @@ void nilfs_dat_abort_update(struct inode *, struct nilfs_palloc_req *, int nilfs_dat_mark_dirty(struct inode *, __u64); int nilfs_dat_freev(struct inode *, __u64 *, size_t); int nilfs_dat_move(struct inode *, __u64, sector_t); -ssize_t nilfs_dat_get_vinfo(struct inode *, void *, unsigned, size_t); +ssize_t nilfs_dat_get_vinfo(struct inode *, void *, unsigned int, size_t); int nilfs_dat_read(struct super_block *sb, size_t entry_size, struct nilfs_inode *raw_inode, struct inode **inodep); diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 6723d45..e506f4f 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Modified for NILFS by Amagai Yoshiji <amagai@osrg.net> + * Modified for NILFS by Amagai Yoshiji. */ /* * linux/fs/ext2/dir.c @@ -50,7 +46,7 @@ * nilfs uses block-sized chunks. Arguably, sector-sized ones would be * more robust, but we have what we have */ -static inline unsigned nilfs_chunk_size(struct inode *inode) +static inline unsigned int nilfs_chunk_size(struct inode *inode) { return inode->i_sb->s_blocksize; } @@ -65,9 +61,9 @@ static inline void nilfs_put_page(struct page *page) * Return the offset into page `page_nr' of the last valid * byte in that page, plus one. */ -static unsigned nilfs_last_byte(struct inode *inode, unsigned long page_nr) +static unsigned int nilfs_last_byte(struct inode *inode, unsigned long page_nr) { - unsigned last_byte = inode->i_size; + unsigned int last_byte = inode->i_size; last_byte -= page_nr << PAGE_SHIFT; if (last_byte > PAGE_SIZE) @@ -75,20 +71,22 @@ static unsigned nilfs_last_byte(struct inode *inode, unsigned long page_nr) return last_byte; } -static int nilfs_prepare_chunk(struct page *page, unsigned from, unsigned to) +static int nilfs_prepare_chunk(struct page *page, unsigned int from, + unsigned int to) { loff_t pos = page_offset(page) + from; + return __block_write_begin(page, pos, to - from, nilfs_get_block); } static void nilfs_commit_chunk(struct page *page, struct address_space *mapping, - unsigned from, unsigned to) + unsigned int from, unsigned int to) { struct inode *dir = mapping->host; loff_t pos = page_offset(page) + from; - unsigned len = to - from; - unsigned nr_dirty, copied; + unsigned int len = to - from; + unsigned int nr_dirty, copied; int err; nr_dirty = nilfs_page_count_clean_buffers(page, from, to); @@ -106,10 +104,10 @@ static bool nilfs_check_page(struct page *page) { struct inode *dir = page->mapping->host; struct super_block *sb = dir->i_sb; - unsigned chunk_size = nilfs_chunk_size(dir); + unsigned int chunk_size = nilfs_chunk_size(dir); char *kaddr = page_address(page); - unsigned offs, rec_len; - unsigned limit = PAGE_SIZE; + unsigned int offs, rec_len; + unsigned int limit = PAGE_SIZE; struct nilfs_dir_entry *p; char *error; @@ -259,7 +257,6 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx) unsigned int offset = pos & ~PAGE_MASK; unsigned long n = pos >> PAGE_SHIFT; unsigned long npages = dir_pages(inode); -/* unsigned chunk_mask = ~(nilfs_chunk_size(inode)-1); */ if (pos > inode->i_size - NILFS_DIR_REC_LEN(1)) return 0; @@ -321,7 +318,7 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr, { const unsigned char *name = qstr->name; int namelen = qstr->len; - unsigned reclen = NILFS_DIR_REC_LEN(namelen); + unsigned int reclen = NILFS_DIR_REC_LEN(namelen); unsigned long start, n; unsigned long npages = dir_pages(dir); struct page *page = NULL; @@ -340,6 +337,7 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr, n = start; do { char *kaddr; + page = nilfs_get_page(dir, n); if (!IS_ERR(page)) { kaddr = page_address(page); @@ -410,8 +408,8 @@ ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr) void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, struct page *page, struct inode *inode) { - unsigned from = (char *) de - (char *) page_address(page); - unsigned to = from + nilfs_rec_len_from_disk(de->rec_len); + unsigned int from = (char *)de - (char *)page_address(page); + unsigned int to = from + nilfs_rec_len_from_disk(de->rec_len); struct address_space *mapping = page->mapping; int err; @@ -433,15 +431,15 @@ int nilfs_add_link(struct dentry *dentry, struct inode *inode) struct inode *dir = d_inode(dentry->d_parent); const unsigned char *name = dentry->d_name.name; int namelen = dentry->d_name.len; - unsigned chunk_size = nilfs_chunk_size(dir); - unsigned reclen = NILFS_DIR_REC_LEN(namelen); + unsigned int chunk_size = nilfs_chunk_size(dir); + unsigned int reclen = NILFS_DIR_REC_LEN(namelen); unsigned short rec_len, name_len; struct page *page = NULL; struct nilfs_dir_entry *de; unsigned long npages = dir_pages(dir); unsigned long n; char *kaddr; - unsigned from, to; + unsigned int from, to; int err; /* @@ -533,13 +531,14 @@ int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct page *page) struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; char *kaddr = page_address(page); - unsigned from = ((char *)dir - kaddr) & ~(nilfs_chunk_size(inode) - 1); - unsigned to = ((char *)dir - kaddr) + - nilfs_rec_len_from_disk(dir->rec_len); - struct nilfs_dir_entry *pde = NULL; - struct nilfs_dir_entry *de = (struct nilfs_dir_entry *)(kaddr + from); + unsigned int from, to; + struct nilfs_dir_entry *de, *pde = NULL; int err; + from = ((char *)dir - kaddr) & ~(nilfs_chunk_size(inode) - 1); + to = ((char *)dir - kaddr) + nilfs_rec_len_from_disk(dir->rec_len); + de = (struct nilfs_dir_entry *)(kaddr + from); + while ((char *)de < (char *)dir) { if (de->rec_len == 0) { nilfs_error(inode->i_sb, __func__, @@ -572,7 +571,7 @@ int nilfs_make_empty(struct inode *inode, struct inode *parent) { struct address_space *mapping = inode->i_mapping; struct page *page = grab_cache_page(mapping, 0); - unsigned chunk_size = nilfs_chunk_size(inode); + unsigned int chunk_size = nilfs_chunk_size(inode); struct nilfs_dir_entry *de; int err; void *kaddr; @@ -630,8 +629,8 @@ int nilfs_empty_dir(struct inode *inode) while ((char *)de <= kaddr) { if (de->rec_len == 0) { nilfs_error(inode->i_sb, __func__, - "zero-length directory entry " - "(kaddr=%p, de=%p)\n", kaddr, de); + "zero-length directory entry (kaddr=%p, de=%p)", + kaddr, de); goto not_empty; } if (de->inode != 0) { diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index ebf89fd..251a4492 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #include <linux/errno.h> @@ -62,7 +58,7 @@ static int nilfs_direct_lookup(const struct nilfs_bmap *direct, static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, __u64 key, __u64 *ptrp, - unsigned maxblocks) + unsigned int maxblocks) { struct inode *dat = NULL; __u64 ptr, ptr2; @@ -83,7 +79,8 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, ptr = blocknr; } - maxblocks = min_t(unsigned, maxblocks, NILFS_DIRECT_KEY_MAX - key + 1); + maxblocks = min_t(unsigned int, maxblocks, + NILFS_DIRECT_KEY_MAX - key + 1); for (cnt = 1; cnt < maxblocks && (ptr2 = nilfs_direct_get_ptr(direct, key + cnt)) != NILFS_BMAP_INVALID_PTR; @@ -110,9 +107,9 @@ nilfs_direct_find_target_v(const struct nilfs_bmap *direct, __u64 key) if (ptr != NILFS_BMAP_INVALID_PTR) /* sequential access */ return ptr; - else - /* block group */ - return nilfs_bmap_find_target_in_group(direct); + + /* block group */ + return nilfs_bmap_find_target_in_group(direct); } static int nilfs_direct_insert(struct nilfs_bmap *bmap, __u64 key, __u64 ptr) diff --git a/fs/nilfs2/direct.h b/fs/nilfs2/direct.h index dc643de..3015a6e 100644 --- a/fs/nilfs2/direct.h +++ b/fs/nilfs2/direct.h @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #ifndef _NILFS_DIRECT_H diff --git a/fs/nilfs2/export.h b/fs/nilfs2/export.h index 19ccbf9..00107fd 100644 --- a/fs/nilfs2/export.h +++ b/fs/nilfs2/export.h @@ -20,6 +20,6 @@ struct nilfs_fid { u32 parent_gen; u64 parent_ino; -} __attribute__ ((packed)); +} __packed; #endif diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 088ba00..547381f 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -13,12 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Amagai Yoshiji <amagai@osrg.net>, - * Ryusuke Konishi <ryusuke@osrg.net> + * Written by Amagai Yoshiji and Ryusuke Konishi. */ #include <linux/fs.h> diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 0224b78..693aded 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -13,13 +13,8 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Seiji Kihara <kihara@osrg.net>, Amagai Yoshiji <amagai@osrg.net>, - * and Ryusuke Konishi <ryusuke@osrg.net>. - * Revised by Ryusuke Konishi <ryusuke@osrg.net>. + * Written by Seiji Kihara, Amagai Yoshiji, and Ryusuke Konishi. + * Revised by Ryusuke Konishi. * */ /* diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c index 6548c78..1d2b180 100644 --- a/fs/nilfs2/ifile.c +++ b/fs/nilfs2/ifile.c @@ -13,12 +13,8 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Amagai Yoshiji <amagai@osrg.net>. - * Revised by Ryusuke Konishi <ryusuke@osrg.net>. + * Written by Amagai Yoshiji. + * Revised by Ryusuke Konishi. * */ @@ -68,8 +64,10 @@ int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino, struct nilfs_palloc_req req; int ret; - req.pr_entry_nr = 0; /* 0 says find free inode from beginning of - a group. dull code!! */ + req.pr_entry_nr = 0; /* + * 0 says find free inode from beginning + * of a group. dull code!! + */ req.pr_entry_bh = NULL; ret = nilfs_palloc_prepare_alloc_entry(ifile, &req); diff --git a/fs/nilfs2/ifile.h b/fs/nilfs2/ifile.h index 679674d..23ad2f0 100644 --- a/fs/nilfs2/ifile.h +++ b/fs/nilfs2/ifile.h @@ -13,12 +13,8 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Amagai Yoshiji <amagai@osrg.net> - * Revised by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Amagai Yoshiji. + * Revised by Ryusuke Konishi. * */ @@ -36,6 +32,7 @@ static inline struct nilfs_inode * nilfs_ifile_map_inode(struct inode *ifile, ino_t ino, struct buffer_head *ibh) { void *kaddr = kmap(ibh->b_page); + return nilfs_palloc_block_get_entry(ifile, ino, ibh, kaddr); } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index cfebcd2..a0ebdb1 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Ryusuke Konishi. * */ @@ -87,7 +83,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, struct the_nilfs *nilfs = inode->i_sb->s_fs_info; __u64 blknum = 0; int err = 0, ret; - unsigned maxblocks = bh_result->b_size >> inode->i_blkbits; + unsigned int maxblocks = bh_result->b_size >> inode->i_blkbits; down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); ret = nilfs_bmap_lookup_contig(ii->i_bmap, blkoff, &blknum, maxblocks); @@ -133,11 +129,14 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, /* Error handling should be detailed */ set_buffer_new(bh_result); set_buffer_delay(bh_result); - map_bh(bh_result, inode->i_sb, 0); /* dbn must be changed - to proper value */ + map_bh(bh_result, inode->i_sb, 0); + /* Disk block number must be changed to proper value */ + } else if (ret == -ENOENT) { - /* not found is not error (e.g. hole); must return without - the mapped state flag. */ + /* + * not found is not error (e.g. hole); must return without + * the mapped state flag. + */ ; } else { err = ret; @@ -167,7 +166,7 @@ static int nilfs_readpage(struct file *file, struct page *page) * @nr_pages - number of pages to be read */ static int nilfs_readpages(struct file *file, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages) + struct list_head *pages, unsigned int nr_pages) { return mpage_readpages(mapping, pages, nr_pages, nilfs_get_block); } @@ -226,7 +225,7 @@ static int nilfs_set_page_dirty(struct page *page) int ret = __set_page_dirty_nobuffers(page); if (page_has_buffers(page)) { - unsigned nr_dirty = 0; + unsigned int nr_dirty = 0; struct buffer_head *bh, *head; /* @@ -249,7 +248,7 @@ static int nilfs_set_page_dirty(struct page *page) if (nr_dirty) nilfs_set_file_dirty(inode, nr_dirty); } else if (ret) { - unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits); + unsigned int nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits); nilfs_set_file_dirty(inode, nr_dirty); } @@ -291,8 +290,8 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct inode *inode = mapping->host; - unsigned start = pos & (PAGE_SIZE - 1); - unsigned nr_dirty; + unsigned int start = pos & (PAGE_SIZE - 1); + unsigned int nr_dirty; int err; nr_dirty = nilfs_page_count_clean_buffers(page, start, @@ -399,23 +398,26 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) err = nilfs_init_acl(inode, dir); if (unlikely(err)) - goto failed_after_creation; /* never occur. When supporting - nilfs_init_acl(), proper cancellation of - above jobs should be considered */ + /* + * Never occur. When supporting nilfs_init_acl(), + * proper cancellation of above jobs should be considered. + */ + goto failed_after_creation; return inode; failed_after_creation: clear_nlink(inode); unlock_new_inode(inode); - iput(inode); /* raw_inode will be deleted through - nilfs_evict_inode() */ + iput(inode); /* + * raw_inode will be deleted through + * nilfs_evict_inode(). + */ goto failed; failed_ifile_create_inode: make_bad_inode(inode); - iput(inode); /* if i_nlink == 1, generic_forget_inode() will be - called */ + iput(inode); failed: return ERR_PTR(err); } @@ -666,8 +668,10 @@ void nilfs_write_inode_common(struct inode *inode, else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) raw_inode->i_device_code = cpu_to_le64(huge_encode_dev(inode->i_rdev)); - /* When extending inode, nilfs->ns_inode_size should be checked - for substitutions of appended fields */ + /* + * When extending inode, nilfs->ns_inode_size should be checked + * for substitutions of appended fields. + */ } void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh, int flags) @@ -685,9 +689,12 @@ void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh, int flags) set_bit(NILFS_I_INODE_SYNC, &ii->i_state); nilfs_write_inode_common(inode, raw_inode, 0); - /* XXX: call with has_bmap = 0 is a workaround to avoid - deadlock of bmap. This delays update of i_bmap to just - before writing */ + /* + * XXX: call with has_bmap = 0 is a workaround to avoid + * deadlock of bmap. This delays update of i_bmap to just + * before writing. + */ + nilfs_ifile_unmap_inode(ifile, ino, ibh); } @@ -752,14 +759,15 @@ void nilfs_truncate(struct inode *inode) nilfs_mark_inode_dirty(inode); nilfs_set_file_dirty(inode, 0); nilfs_transaction_commit(sb); - /* May construct a logical segment and may fail in sync mode. - But truncate has no return value. */ + /* + * May construct a logical segment and may fail in sync mode. + * But truncate has no return value. + */ } static void nilfs_clear_inode(struct inode *inode) { struct nilfs_inode_info *ii = NILFS_I(inode); - struct nilfs_mdt_info *mdi = NILFS_MDT(inode); /* * Free resources allocated in nilfs_read_inode(), here. @@ -768,8 +776,8 @@ static void nilfs_clear_inode(struct inode *inode) brelse(ii->i_bh); ii->i_bh = NULL; - if (mdi && mdi->mi_palloc_cache) - nilfs_palloc_destroy_cache(inode); + if (nilfs_is_metadata_file_inode(inode)) + nilfs_mdt_clear(inode); if (test_bit(NILFS_I_BMAP, &ii->i_state)) nilfs_bmap_clear(ii->i_bmap); @@ -811,8 +819,10 @@ void nilfs_evict_inode(struct inode *inode) if (IS_SYNC(inode)) nilfs_set_transaction_flag(NILFS_TI_SYNC); nilfs_transaction_commit(sb); - /* May construct a logical segment and may fail in sync mode. - But delete_inode has no return value. */ + /* + * May construct a logical segment and may fail in sync mode. + * But delete_inode has no return value. + */ } int nilfs_setattr(struct dentry *dentry, struct iattr *iattr) @@ -856,6 +866,7 @@ out_err: int nilfs_permission(struct inode *inode, int mask) { struct nilfs_root *root = NILFS_I(inode)->i_root; + if ((mask & MAY_WRITE) && root && root->cno != NILFS_CPTREE_CURRENT_CNO) return -EROFS; /* snapshot is not writable */ @@ -906,7 +917,7 @@ int nilfs_inode_dirty(struct inode *inode) return ret; } -int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty) +int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty) { struct nilfs_inode_info *ii = NILFS_I(inode); struct the_nilfs *nilfs = inode->i_sb->s_fs_info; @@ -919,17 +930,23 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty) spin_lock(&nilfs->ns_inode_lock); if (!test_bit(NILFS_I_QUEUED, &ii->i_state) && !test_bit(NILFS_I_BUSY, &ii->i_state)) { - /* Because this routine may race with nilfs_dispose_list(), - we have to check NILFS_I_QUEUED here, too. */ + /* + * Because this routine may race with nilfs_dispose_list(), + * we have to check NILFS_I_QUEUED here, too. + */ if (list_empty(&ii->i_dirty) && igrab(inode) == NULL) { - /* This will happen when somebody is freeing - this inode. */ + /* + * This will happen when somebody is freeing + * this inode. + */ nilfs_warning(inode->i_sb, __func__, - "cannot get inode (ino=%lu)\n", + "cannot get inode (ino=%lu)", inode->i_ino); spin_unlock(&nilfs->ns_inode_lock); - return -EINVAL; /* NILFS_I_DIRTY may remain for - freeing inode */ + return -EINVAL; /* + * NILFS_I_DIRTY may remain for + * freeing inode. + */ } list_move_tail(&ii->i_dirty, &nilfs->ns_dirty_files); set_bit(NILFS_I_QUEUED, &ii->i_state); @@ -946,7 +963,7 @@ int __nilfs_mark_inode_dirty(struct inode *inode, int flags) err = nilfs_load_inode_block(inode, &ibh); if (unlikely(err)) { nilfs_warning(inode->i_sb, __func__, - "failed to reget inode block.\n"); + "failed to reget inode block."); return err; } nilfs_update_inode(inode, ibh, flags); @@ -973,7 +990,7 @@ void nilfs_dirty_inode(struct inode *inode, int flags) if (is_bad_inode(inode)) { nilfs_warning(inode->i_sb, __func__, - "tried to mark bad_inode dirty. ignored.\n"); + "tried to mark bad_inode dirty. ignored."); dump_stack(); return; } diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index e8fe248..358b57e 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #include <linux/fs.h> @@ -783,6 +779,7 @@ static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs, size_t nmembs = argv->v_nmembs; struct nilfs_bmap *bmap = NILFS_I(nilfs->ns_dat)->i_bmap; struct nilfs_bdesc *bdescs = buf; + struct buffer_head *bh; int ret, i; for (i = 0; i < nmembs; i++) { @@ -800,12 +797,16 @@ static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs, /* skip dead block */ continue; if (bdescs[i].bd_level == 0) { - ret = nilfs_mdt_mark_block_dirty(nilfs->ns_dat, - bdescs[i].bd_offset); - if (ret < 0) { + ret = nilfs_mdt_get_block(nilfs->ns_dat, + bdescs[i].bd_offset, + false, NULL, &bh); + if (unlikely(ret)) { WARN_ON(ret == -ENOENT); return ret; } + mark_buffer_dirty(bh); + nilfs_mdt_mark_dirty(nilfs->ns_dat); + put_bh(bh); } else { ret = nilfs_bmap_mark(bmap, bdescs[i].bd_offset, bdescs[i].bd_level); diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index f6982b9..3417d85 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Ryusuke Konishi. */ #include <linux/buffer_head.h> @@ -32,6 +28,7 @@ #include "segment.h" #include "page.h" #include "mdt.h" +#include "alloc.h" /* nilfs_palloc_destroy_cache() */ #include <trace/events/nilfs2.h> @@ -393,34 +390,6 @@ int nilfs_mdt_forget_block(struct inode *inode, unsigned long block) return ret; } -/** - * nilfs_mdt_mark_block_dirty - mark a block on the meta data file dirty. - * @inode: inode of the meta data file - * @block: block offset - * - * Return Value: On success, it returns 0. On error, the following negative - * error code is returned. - * - * %-ENOMEM - Insufficient memory available. - * - * %-EIO - I/O error - * - * %-ENOENT - the specified block does not exist (hole block) - */ -int nilfs_mdt_mark_block_dirty(struct inode *inode, unsigned long block) -{ - struct buffer_head *bh; - int err; - - err = nilfs_mdt_read_block(inode, block, 0, &bh); - if (unlikely(err)) - return err; - mark_buffer_dirty(bh); - nilfs_mdt_mark_dirty(inode); - brelse(bh); - return 0; -} - int nilfs_mdt_fetch_dirty(struct inode *inode) { struct nilfs_inode_info *ii = NILFS_I(inode); @@ -497,8 +466,32 @@ int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz) return 0; } -void nilfs_mdt_set_entry_size(struct inode *inode, unsigned entry_size, - unsigned header_size) +/** + * nilfs_mdt_clear - do cleanup for the metadata file + * @inode: inode of the metadata file + */ +void nilfs_mdt_clear(struct inode *inode) +{ + struct nilfs_mdt_info *mdi = NILFS_MDT(inode); + + if (mdi->mi_palloc_cache) + nilfs_palloc_destroy_cache(inode); +} + +/** + * nilfs_mdt_destroy - release resources used by the metadata file + * @inode: inode of the metadata file + */ +void nilfs_mdt_destroy(struct inode *inode) +{ + struct nilfs_mdt_info *mdi = NILFS_MDT(inode); + + kfree(mdi->mi_bgl); /* kfree(NULL) is safe */ + kfree(mdi); +} + +void nilfs_mdt_set_entry_size(struct inode *inode, unsigned int entry_size, + unsigned int header_size) { struct nilfs_mdt_info *mi = NILFS_MDT(inode); diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h index 03246ca..3f67f39 100644 --- a/fs/nilfs2/mdt.h +++ b/fs/nilfs2/mdt.h @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Ryusuke Konishi. */ #ifndef _NILFS_MDT_H @@ -57,8 +53,8 @@ struct nilfs_shadow_map { struct nilfs_mdt_info { struct rw_semaphore mi_sem; struct blockgroup_lock *mi_bgl; - unsigned mi_entry_size; - unsigned mi_first_entry_offset; + unsigned int mi_entry_size; + unsigned int mi_first_entry_offset; unsigned long mi_entries_per_block; struct nilfs_palloc_cache *mi_palloc_cache; struct nilfs_shadow_map *mi_shadow; @@ -71,6 +67,11 @@ static inline struct nilfs_mdt_info *NILFS_MDT(const struct inode *inode) return inode->i_private; } +static inline int nilfs_is_metadata_file_inode(const struct inode *inode) +{ + return inode->i_private != NULL; +} + /* Default GFP flags using highmem */ #define NILFS_MDT_GFP (__GFP_RECLAIM | __GFP_IO | __GFP_HIGHMEM) @@ -83,11 +84,13 @@ int nilfs_mdt_find_block(struct inode *inode, unsigned long start, struct buffer_head **out_bh); int nilfs_mdt_delete_block(struct inode *, unsigned long); int nilfs_mdt_forget_block(struct inode *, unsigned long); -int nilfs_mdt_mark_block_dirty(struct inode *, unsigned long); int nilfs_mdt_fetch_dirty(struct inode *); int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz); -void nilfs_mdt_set_entry_size(struct inode *, unsigned, unsigned); +void nilfs_mdt_clear(struct inode *inode); +void nilfs_mdt_destroy(struct inode *inode); + +void nilfs_mdt_set_entry_size(struct inode *, unsigned int, unsigned int); int nilfs_mdt_setup_shadow_map(struct inode *inode, struct nilfs_shadow_map *shadow); diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 3b2af05..1ec8ae5 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -13,12 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Modified for NILFS by Amagai Yoshiji <amagai@osrg.net>, - * Ryusuke Konishi <ryusuke@osrg.net> + * Modified for NILFS by Amagai Yoshiji and Ryusuke Konishi. */ /* * linux/fs/ext2/namei.c @@ -49,6 +44,7 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode) { int err = nilfs_add_link(dentry, inode); + if (!err) { d_instantiate(dentry, inode); unlock_new_inode(inode); @@ -143,7 +139,7 @@ static int nilfs_symlink(struct inode *dir, struct dentry *dentry, { struct nilfs_transaction_info ti; struct super_block *sb = dir->i_sb; - unsigned l = strlen(symname)+1; + unsigned int l = strlen(symname) + 1; struct inode *inode; int err; @@ -288,7 +284,7 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry) if (!inode->i_nlink) { nilfs_warning(inode->i_sb, __func__, - "deleting nonexistent file (%lu), %d\n", + "deleting nonexistent file (%lu), %d", inode->i_ino, inode->i_nlink); set_nlink(inode, 1); } diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 3857040..b1d48bc 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -13,12 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net> - * Ryusuke Konishi <ryusuke@osrg.net> + * Written by Koji Sato and Ryusuke Konishi. */ #ifndef _NILFS_H @@ -69,8 +64,10 @@ struct nilfs_inode_info { */ struct rw_semaphore xattr_sem; #endif - struct buffer_head *i_bh; /* i_bh contains a new or dirty - disk inode */ + struct buffer_head *i_bh; /* + * i_bh contains a new or dirty + * disk inode. + */ struct nilfs_root *i_root; struct inode vfs_inode; }; @@ -100,8 +97,10 @@ enum { NILFS_I_NEW = 0, /* Inode is newly created */ NILFS_I_DIRTY, /* The file is dirty */ NILFS_I_QUEUED, /* inode is in dirty_files list */ - NILFS_I_BUSY, /* inode is grabbed by a segment - constructor */ + NILFS_I_BUSY, /* + * Inode is grabbed by a segment + * constructor + */ NILFS_I_COLLECTED, /* All dirty blocks are collected */ NILFS_I_UPDATED, /* The file has been written back */ NILFS_I_INODE_SYNC, /* dsync is not allowed for inode */ @@ -145,8 +144,10 @@ enum { struct nilfs_transaction_info { u32 ti_magic; void *ti_save; - /* This should never used. If this happens, - one of other filesystems has a bug. */ + /* + * This should never be used. If it happens, + * one of other filesystems has a bug. + */ unsigned short ti_flags; unsigned short ti_count; }; @@ -156,8 +157,10 @@ struct nilfs_transaction_info { /* ti_flags */ #define NILFS_TI_DYNAMIC_ALLOC 0x0001 /* Allocated from slab */ -#define NILFS_TI_SYNC 0x0002 /* Force to construct segment at the - end of transaction. */ +#define NILFS_TI_SYNC 0x0002 /* + * Force to construct segment at the + * end of transaction. + */ #define NILFS_TI_GC 0x0004 /* GC context */ #define NILFS_TI_COMMIT 0x0008 /* Change happened or not */ #define NILFS_TI_WRITER 0x0010 /* Constructor context */ @@ -279,7 +282,7 @@ extern void nilfs_write_failed(struct address_space *mapping, loff_t to); int nilfs_permission(struct inode *inode, int mask); int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh); extern int nilfs_inode_dirty(struct inode *); -int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty); +int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty); extern int __nilfs_mark_inode_dirty(struct inode *, int); extern void nilfs_dirty_inode(struct inode *, int flags); int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 4893915..d97ba5f 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -13,12 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net>, - * Seiji Kihara <kihara@osrg.net>. + * Written by Ryusuke Konishi and Seiji Kihara. */ #include <linux/pagemap.h> @@ -440,12 +435,12 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) __nilfs_clear_page_dirty(page); } -unsigned nilfs_page_count_clean_buffers(struct page *page, - unsigned from, unsigned to) +unsigned int nilfs_page_count_clean_buffers(struct page *page, + unsigned int from, unsigned int to) { - unsigned block_start, block_end; + unsigned int block_start, block_end; struct buffer_head *bh, *head; - unsigned nc = 0; + unsigned int nc = 0; for (bh = head = page_buffers(page), block_start = 0; bh != head || !block_start; diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index a43b8287..f3687c9 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -13,12 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net>, - * Seiji Kihara <kihara@osrg.net>. + * Written by Ryusuke Konishi and Seiji Kihara. */ #ifndef _NILFS_PAGE_H @@ -58,7 +53,8 @@ void nilfs_copy_back_pages(struct address_space *, struct address_space *); void nilfs_clear_dirty_page(struct page *, bool); void nilfs_clear_dirty_pages(struct address_space *, bool); void nilfs_mapping_init(struct address_space *mapping, struct inode *inode); -unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned); +unsigned int nilfs_page_count_clean_buffers(struct page *, unsigned int, + unsigned int); unsigned long nilfs_find_uncommitted_extent(struct inode *inode, sector_t start_blk, sector_t *blkoff); diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 5afa77f..d893dc9 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Ryusuke Konishi. */ #include <linux/buffer_head.h> @@ -47,8 +43,10 @@ enum { /* work structure for recovery */ struct nilfs_recovery_block { - ino_t ino; /* Inode number of the file that this block - belongs to */ + ino_t ino; /* + * Inode number of the file that this block + * belongs to + */ sector_t blocknr; /* block number */ __u64 vblocknr; /* virtual block number */ unsigned long blkoff; /* File offset of the data block (per block) */ @@ -156,7 +154,7 @@ int nilfs_read_super_root_block(struct the_nilfs *nilfs, sector_t sr_block, sr = (struct nilfs_super_root *)bh_sr->b_data; if (check) { - unsigned bytes = le16_to_cpu(sr->sr_bytes); + unsigned int bytes = le16_to_cpu(sr->sr_bytes); if (bytes == 0 || bytes > nilfs->ns_blocksize) { ret = NILFS_SEG_FAIL_CHECKSUM_SUPER_ROOT; @@ -508,7 +506,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, { struct inode *inode; struct nilfs_recovery_block *rb, *n; - unsigned blocksize = nilfs->ns_blocksize; + unsigned int blocksize = nilfs->ns_blocksize; struct page *page; loff_t pos; int err = 0, err2 = 0; @@ -526,6 +524,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, 0, &page, nilfs_get_block); if (unlikely(err)) { loff_t isize = inode->i_size; + if (pos + blocksize > isize) nilfs_write_failed(inode->i_mapping, pos + blocksize); @@ -872,9 +871,11 @@ int nilfs_search_super_root(struct the_nilfs *nilfs, flags = le16_to_cpu(sum->ss_flags); if (!(flags & NILFS_SS_SR) && !scan_newer) { - /* This will never happen because a superblock - (last_segment) always points to a pseg - having a super root. */ + /* + * This will never happen because a superblock + * (last_segment) always points to a pseg with + * a super root. + */ ret = NILFS_SEG_FAIL_CONSISTENCY; goto failed; } diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index f63620c..bf36df1 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Ryusuke Konishi. * */ @@ -133,7 +129,7 @@ int nilfs_segbuf_extend_payload(struct nilfs_segment_buffer *segbuf, return 0; } -int nilfs_segbuf_reset(struct nilfs_segment_buffer *segbuf, unsigned flags, +int nilfs_segbuf_reset(struct nilfs_segment_buffer *segbuf, unsigned int flags, time_t ctime, __u64 cno) { int err; @@ -240,7 +236,7 @@ nilfs_segbuf_fill_in_super_root_crc(struct nilfs_segment_buffer *segbuf, { struct nilfs_super_root *raw_sr; struct the_nilfs *nilfs = segbuf->sb_super->s_fs_info; - unsigned srsize; + unsigned int srsize; u32 crc; raw_sr = (struct nilfs_super_root *)segbuf->sb_super_root->b_data; diff --git a/fs/nilfs2/segbuf.h b/fs/nilfs2/segbuf.h index b04f08c..7bbccc0 100644 --- a/fs/nilfs2/segbuf.h +++ b/fs/nilfs2/segbuf.h @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Ryusuke Konishi. * */ #ifndef _NILFS_SEGBUF_H @@ -82,7 +78,7 @@ struct nilfs_segment_buffer { __u64 sb_nextnum; sector_t sb_fseg_start, sb_fseg_end; sector_t sb_pseg_start; - unsigned sb_rest_blocks; + unsigned int sb_rest_blocks; /* Buffers */ struct list_head sb_segsum_buffers; @@ -124,7 +120,8 @@ void nilfs_segbuf_map_cont(struct nilfs_segment_buffer *segbuf, struct nilfs_segment_buffer *prev); void nilfs_segbuf_set_next_segnum(struct nilfs_segment_buffer *, __u64, struct the_nilfs *); -int nilfs_segbuf_reset(struct nilfs_segment_buffer *, unsigned, time_t, __u64); +int nilfs_segbuf_reset(struct nilfs_segment_buffer *, unsigned int, time_t, + __u64); int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *); int nilfs_segbuf_extend_payload(struct nilfs_segment_buffer *, struct buffer_head **); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 4317f72..e78b68a8 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Ryusuke Konishi. * */ @@ -49,18 +45,26 @@ */ #define SC_N_INODEVEC 16 /* Size of locally allocated inode vector */ -#define SC_MAX_SEGDELTA 64 /* Upper limit of the number of segments - appended in collection retry loop */ +#define SC_MAX_SEGDELTA 64 /* + * Upper limit of the number of segments + * appended in collection retry loop + */ /* Construction mode */ enum { SC_LSEG_SR = 1, /* Make a logical segment having a super root */ - SC_LSEG_DSYNC, /* Flush data blocks of a given file and make - a logical segment without a super root */ - SC_FLUSH_FILE, /* Flush data files, leads to segment writes without - creating a checkpoint */ - SC_FLUSH_DAT, /* Flush DAT file. This also creates segments without - a checkpoint */ + SC_LSEG_DSYNC, /* + * Flush data blocks of a given file and make + * a logical segment without a super root. + */ + SC_FLUSH_FILE, /* + * Flush data files, leads to segment writes without + * creating a checkpoint. + */ + SC_FLUSH_DAT, /* + * Flush DAT file. This also creates segments + * without a checkpoint. + */ }; /* Stage numbers of dirty block collection */ @@ -154,17 +158,15 @@ static int nilfs_prepare_segment_lock(struct nilfs_transaction_info *ti) if (cur_ti) { if (cur_ti->ti_magic == NILFS_TI_MAGIC) return ++cur_ti->ti_count; - else { - /* - * If journal_info field is occupied by other FS, - * it is saved and will be restored on - * nilfs_transaction_commit(). - */ - printk(KERN_WARNING - "NILFS warning: journal info from a different " - "FS\n"); - save = current->journal_info; - } + + /* + * If journal_info field is occupied by other FS, + * it is saved and will be restored on + * nilfs_transaction_commit(). + */ + printk(KERN_WARNING + "NILFS warning: journal info from a different FS\n"); + save = current->journal_info; } if (!ti) { ti = kmem_cache_alloc(nilfs_transaction_cachep, GFP_NOFS); @@ -397,10 +399,10 @@ static void nilfs_transaction_unlock(struct super_block *sb) static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci, struct nilfs_segsum_pointer *ssp, - unsigned bytes) + unsigned int bytes) { struct nilfs_segment_buffer *segbuf = sci->sc_curseg; - unsigned blocksize = sci->sc_super->s_blocksize; + unsigned int blocksize = sci->sc_super->s_blocksize; void *p; if (unlikely(ssp->offset + bytes > blocksize)) { @@ -422,8 +424,8 @@ static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci) { struct nilfs_segment_buffer *segbuf = sci->sc_curseg; struct buffer_head *sumbh; - unsigned sumbytes; - unsigned flags = 0; + unsigned int sumbytes; + unsigned int flags = 0; int err; if (nilfs_doing_gc()) @@ -444,8 +446,10 @@ static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) { sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks; if (NILFS_SEGBUF_IS_LAST(sci->sc_curseg, &sci->sc_segbufs)) - return -E2BIG; /* The current segment is filled up - (internal code) */ + return -E2BIG; /* + * The current segment is filled up + * (internal code) + */ sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg); return nilfs_segctor_reset_segment_buffer(sci); } @@ -472,9 +476,9 @@ static int nilfs_segctor_add_super_root(struct nilfs_sc_info *sci) */ static int nilfs_segctor_segsum_block_required( struct nilfs_sc_info *sci, const struct nilfs_segsum_pointer *ssp, - unsigned binfo_size) + unsigned int binfo_size) { - unsigned blocksize = sci->sc_super->s_blocksize; + unsigned int blocksize = sci->sc_super->s_blocksize; /* Size of finfo and binfo is enough small against blocksize */ return ssp->offset + binfo_size + @@ -533,7 +537,7 @@ static void nilfs_segctor_end_finfo(struct nilfs_sc_info *sci, static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci, struct buffer_head *bh, struct inode *inode, - unsigned binfo_size) + unsigned int binfo_size) { struct nilfs_segment_buffer *segbuf; int required, err = 0; @@ -617,7 +621,7 @@ static void nilfs_write_file_node_binfo(struct nilfs_sc_info *sci, *vblocknr = binfo->bi_v.bi_vblocknr; } -static struct nilfs_sc_operations nilfs_sc_file_ops = { +static const struct nilfs_sc_operations nilfs_sc_file_ops = { .collect_data = nilfs_collect_file_data, .collect_node = nilfs_collect_file_node, .collect_bmap = nilfs_collect_file_bmap, @@ -666,7 +670,7 @@ static void nilfs_write_dat_node_binfo(struct nilfs_sc_info *sci, *binfo_dat = binfo->bi_dat; } -static struct nilfs_sc_operations nilfs_sc_dat_ops = { +static const struct nilfs_sc_operations nilfs_sc_dat_ops = { .collect_data = nilfs_collect_dat_data, .collect_node = nilfs_collect_file_node, .collect_bmap = nilfs_collect_dat_bmap, @@ -674,7 +678,7 @@ static struct nilfs_sc_operations nilfs_sc_dat_ops = { .write_node_binfo = nilfs_write_dat_node_binfo, }; -static struct nilfs_sc_operations nilfs_sc_dsync_ops = { +static const struct nilfs_sc_operations nilfs_sc_dsync_ops = { .collect_data = nilfs_collect_file_data, .collect_node = NULL, .collect_bmap = NULL, @@ -777,7 +781,7 @@ static void nilfs_dispose_list(struct the_nilfs *nilfs, { struct nilfs_inode_info *ii, *n; struct nilfs_inode_info *ivec[SC_N_INODEVEC], **pii; - unsigned nv = 0; + unsigned int nv = 0; while (!list_empty(head)) { spin_lock(&nilfs->ns_inode_lock); @@ -875,9 +879,11 @@ static int nilfs_segctor_create_checkpoint(struct nilfs_sc_info *sci) err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, 1, &raw_cp, &bh_cp); if (likely(!err)) { - /* The following code is duplicated with cpfile. But, it is - needed to collect the checkpoint even if it was not newly - created */ + /* + * The following code is duplicated with cpfile. But, it is + * needed to collect the checkpoint even if it was not newly + * created. + */ mark_buffer_dirty(bh_cp); nilfs_mdt_mark_dirty(nilfs->ns_cpfile); nilfs_cpfile_put_checkpoint( @@ -958,7 +964,7 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, { struct buffer_head *bh_sr; struct nilfs_super_root *raw_sr; - unsigned isz, srsz; + unsigned int isz, srsz; bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root; raw_sr = (struct nilfs_super_root *)bh_sr->b_data; @@ -1043,7 +1049,7 @@ static size_t nilfs_segctor_buffer_rest(struct nilfs_sc_info *sci) static int nilfs_segctor_scan_file(struct nilfs_sc_info *sci, struct inode *inode, - struct nilfs_sc_operations *sc_ops) + const struct nilfs_sc_operations *sc_ops) { LIST_HEAD(data_buffers); LIST_HEAD(node_buffers); @@ -1406,8 +1412,10 @@ static void nilfs_free_incomplete_logs(struct list_head *logs, if (atomic_read(&segbuf->sb_err)) { /* Case 1: The first segment failed */ if (segbuf->sb_pseg_start != segbuf->sb_fseg_start) - /* Case 1a: Partial segment appended into an existing - segment */ + /* + * Case 1a: Partial segment appended into an existing + * segment + */ nilfs_terminate_segment(nilfs, segbuf->sb_fseg_start, segbuf->sb_fseg_end); else /* Case 1b: New full segment */ @@ -1550,7 +1558,7 @@ nilfs_segctor_update_payload_blocknr(struct nilfs_sc_info *sci, sector_t blocknr; unsigned long nfinfo = segbuf->sb_sum.nfinfo; unsigned long nblocks = 0, ndatablk = 0; - struct nilfs_sc_operations *sc_op = NULL; + const struct nilfs_sc_operations *sc_op = NULL; struct nilfs_segsum_pointer ssp; struct nilfs_finfo *finfo = NULL; union nilfs_binfo binfo; @@ -1631,8 +1639,10 @@ static int nilfs_segctor_assign(struct nilfs_sc_info *sci, int mode) static void nilfs_begin_page_io(struct page *page) { if (!page || PageWriteback(page)) - /* For split b-tree node pages, this function may be called - twice. We ignore the 2nd or later calls by this check. */ + /* + * For split b-tree node pages, this function may be called + * twice. We ignore the 2nd or later calls by this check. + */ return; lock_page(page); @@ -1942,7 +1952,7 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci, ifile, ii->vfs_inode.i_ino, &ibh); if (unlikely(err)) { nilfs_warning(sci->sc_super, __func__, - "failed to get inode block.\n"); + "failed to get inode block."); return err; } mark_buffer_dirty(ibh); @@ -2395,6 +2405,7 @@ static int nilfs_segctor_construct(struct nilfs_sc_info *sci, int mode) static void nilfs_construction_timeout(unsigned long data) { struct task_struct *p = (struct task_struct *)data; + wake_up_process(p); } @@ -2555,10 +2566,10 @@ static int nilfs_segctor_thread(void *arg) if (timeout || sci->sc_seq_request != sci->sc_seq_done) mode = SC_LSEG_SR; - else if (!sci->sc_flush_request) - break; - else + else if (sci->sc_flush_request) mode = nilfs_segctor_flush_mode(sci); + else + break; spin_unlock(&sci->sc_state_lock); nilfs_segctor_thread_construct(sci, mode); @@ -2684,8 +2695,10 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) { int ret, retrycount = NILFS_SC_CLEANUP_RETRY; - /* The segctord thread was stopped and its timer was removed. - But some tasks remain. */ + /* + * The segctord thread was stopped and its timer was removed. + * But some tasks remain. + */ do { struct nilfs_transaction_info ti; @@ -2727,13 +2740,13 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) if (!list_empty(&sci->sc_dirty_files)) { nilfs_warning(sci->sc_super, __func__, - "dirty file(s) after the final construction\n"); + "dirty file(s) after the final construction"); nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1); } if (!list_empty(&sci->sc_iput_queue)) { nilfs_warning(sci->sc_super, __func__, - "iput queue is not empty\n"); + "iput queue is not empty"); nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1); } @@ -2810,7 +2823,7 @@ void nilfs_detach_log_writer(struct super_block *sb) if (!list_empty(&nilfs->ns_dirty_files)) { list_splice_init(&nilfs->ns_dirty_files, &garbage_list); nilfs_warning(sb, __func__, - "Hit dirty file after stopped log writer\n"); + "Hit dirty file after stopped log writer"); } spin_unlock(&nilfs->ns_inode_lock); up_write(&nilfs->ns_segctor_sem); diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 0408b9b..6565c10 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Ryusuke Konishi. * */ #ifndef _NILFS_SEGMENT_H @@ -75,7 +71,7 @@ struct nilfs_recovery_info { */ struct nilfs_cstage { int scnt; - unsigned flags; + unsigned int flags; struct nilfs_inode_info *dirty_file_ptr; struct nilfs_inode_info *gc_inode_ptr; }; @@ -84,7 +80,7 @@ struct nilfs_segment_buffer; struct nilfs_segsum_pointer { struct buffer_head *bh; - unsigned offset; /* offset in bytes */ + unsigned int offset; /* offset in bytes */ }; /** @@ -193,11 +189,15 @@ enum { NILFS_SC_DIRTY, /* One or more dirty meta-data blocks exist */ NILFS_SC_UNCLOSED, /* Logical segment is not closed */ NILFS_SC_SUPER_ROOT, /* The latest segment has a super root */ - NILFS_SC_PRIOR_FLUSH, /* Requesting immediate flush without making a - checkpoint */ - NILFS_SC_HAVE_DELTA, /* Next checkpoint will have update of files - other than DAT, cpfile, sufile, or files - moved by GC */ + NILFS_SC_PRIOR_FLUSH, /* + * Requesting immediate flush without making a + * checkpoint + */ + NILFS_SC_HAVE_DELTA, /* + * Next checkpoint will have update of files + * other than DAT, cpfile, sufile, or files + * moved by GC. + */ }; /* sc_state */ @@ -207,17 +207,23 @@ enum { /* * Constant parameters */ -#define NILFS_SC_CLEANUP_RETRY 3 /* Retry count of construction when - destroying segctord */ +#define NILFS_SC_CLEANUP_RETRY 3 /* + * Retry count of construction when + * destroying segctord + */ /* * Default values of timeout, in seconds. */ -#define NILFS_SC_DEFAULT_TIMEOUT 5 /* Timeout value of dirty blocks. - It triggers construction of a - logical segment with a super root */ -#define NILFS_SC_DEFAULT_SR_FREQ 30 /* Maximum frequency of super root - creation */ +#define NILFS_SC_DEFAULT_TIMEOUT 5 /* + * Timeout value of dirty blocks. + * It triggers construction of a + * logical segment with a super root. + */ +#define NILFS_SC_DEFAULT_SR_FREQ 30 /* + * Maximum frequency of super root + * creation + */ /* * The default threshold amount of data, in block counts. diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 52821ff..1963595 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -13,12 +13,8 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. - * Revised by Ryusuke Konishi <ryusuke@osrg.net>. + * Written by Koji Sato. + * Revised by Ryusuke Konishi. */ #include <linux/kernel.h> @@ -61,6 +57,7 @@ static unsigned long nilfs_sufile_get_blkoff(const struct inode *sufile, __u64 segnum) { __u64 t = segnum + NILFS_MDT(sufile)->mi_first_entry_offset; + do_div(t, nilfs_sufile_segment_usages_per_block(sufile)); return (unsigned long)t; } @@ -69,6 +66,7 @@ static unsigned long nilfs_sufile_get_offset(const struct inode *sufile, __u64 segnum) { __u64 t = segnum + NILFS_MDT(sufile)->mi_first_entry_offset; + return do_div(t, nilfs_sufile_segment_usages_per_block(sufile)); } @@ -819,7 +817,7 @@ out: * %-ENOMEM - Insufficient amount of memory available. */ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf, - unsigned sisz, size_t nsi) + unsigned int sisz, size_t nsi) { struct buffer_head *su_bh; struct nilfs_segment_usage *su; @@ -897,7 +895,7 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf, * %-EINVAL - Invalid values in input (segment number, flags or nblocks) */ ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf, - unsigned supsz, size_t nsup) + unsigned int supsz, size_t nsup) { struct the_nilfs *nilfs = sufile->i_sb->s_fs_info; struct buffer_head *header_bh, *bh; diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h index b8afd72..46e8987 100644 --- a/fs/nilfs2/sufile.h +++ b/fs/nilfs2/sufile.h @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net>. + * Written by Koji Sato. */ #ifndef _NILFS_SUFILE_H @@ -42,9 +38,9 @@ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum); int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum, unsigned long nblocks, time_t modtime); int nilfs_sufile_get_stat(struct inode *, struct nilfs_sustat *); -ssize_t nilfs_sufile_get_suinfo(struct inode *, __u64, void *, unsigned, +ssize_t nilfs_sufile_get_suinfo(struct inode *, __u64, void *, unsigned int, size_t); -ssize_t nilfs_sufile_set_suinfo(struct inode *, void *, unsigned , size_t); +ssize_t nilfs_sufile_set_suinfo(struct inode *, void *, unsigned int, size_t); int nilfs_sufile_updatev(struct inode *, __u64 *, size_t, int, size_t *, void (*dofunc)(struct inode *, __u64, diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 7f5d3d9..666107a 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Ryusuke Konishi. */ /* * linux/fs/ext2/super.c @@ -173,12 +169,10 @@ struct inode *nilfs_alloc_inode(struct super_block *sb) static void nilfs_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - struct nilfs_mdt_info *mdi = NILFS_MDT(inode); - if (mdi) { - kfree(mdi->mi_bgl); /* kfree(NULL) is safe */ - kfree(mdi); - } + if (nilfs_is_metadata_file_inode(inode)) + nilfs_mdt_destroy(inode); + kmem_cache_free(nilfs_inode_cachep, NILFS_I(inode)); } @@ -279,7 +273,7 @@ struct nilfs_super_block **nilfs_prepare_super(struct super_block *sb, } } else if (sbp[1] && sbp[1]->s_magic != cpu_to_le16(NILFS_SUPER_MAGIC)) { - memcpy(sbp[1], sbp[0], nilfs->ns_sbsize); + memcpy(sbp[1], sbp[0], nilfs->ns_sbsize); } if (flip && sbp[1]) @@ -749,6 +743,7 @@ static int parse_options(char *options, struct super_block *sb, int is_remount) while ((p = strsep(&options, ",")) != NULL) { int token; + if (!*p) continue; @@ -891,7 +886,7 @@ int nilfs_store_magic_and_option(struct super_block *sb, nilfs->ns_interval = le32_to_cpu(sbp->s_c_interval); nilfs->ns_watermark = le32_to_cpu(sbp->s_c_block_max); - return !parse_options(data, sb, 0) ? -EINVAL : 0 ; + return !parse_options(data, sb, 0) ? -EINVAL : 0; } int nilfs_check_feature_compatibility(struct super_block *sb, @@ -1316,7 +1311,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags, } if (!s->s_root) { - s_new = true; + s_new = true; /* New superblock instance created */ s->s_mode = mode; diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index bbb0dcc..8ffa42b 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -68,7 +68,7 @@ static ssize_t nilfs_##name##_attr_store(struct kobject *kobj, \ static const struct sysfs_ops nilfs_##name##_attr_ops = { \ .show = nilfs_##name##_attr_show, \ .store = nilfs_##name##_attr_store, \ -}; +} #define NILFS_DEV_INT_GROUP_TYPE(name, parent_name) \ static void nilfs_##name##_attr_release(struct kobject *kobj) \ @@ -84,7 +84,7 @@ static struct kobj_type nilfs_##name##_ktype = { \ .default_attrs = nilfs_##name##_attrs, \ .sysfs_ops = &nilfs_##name##_attr_ops, \ .release = nilfs_##name##_attr_release, \ -}; +} #define NILFS_DEV_INT_GROUP_FNS(name, parent_name) \ static int nilfs_sysfs_create_##name##_group(struct the_nilfs *nilfs) \ @@ -756,7 +756,7 @@ nilfs_superblock_sb_write_count_show(struct nilfs_superblock_attr *attr, struct the_nilfs *nilfs, char *buf) { - unsigned sbwcount; + unsigned int sbwcount; down_read(&nilfs->ns_sem); sbwcount = nilfs->ns_sbwcount; @@ -770,7 +770,7 @@ nilfs_superblock_sb_update_frequency_show(struct nilfs_superblock_attr *attr, struct the_nilfs *nilfs, char *buf) { - unsigned sb_update_freq; + unsigned int sb_update_freq; down_read(&nilfs->ns_sem); sb_update_freq = nilfs->ns_sb_update_freq; @@ -784,7 +784,7 @@ nilfs_superblock_sb_update_frequency_store(struct nilfs_superblock_attr *attr, struct the_nilfs *nilfs, const char *buf, size_t count) { - unsigned val; + unsigned int val; int err; err = kstrtouint(skip_spaces(buf), 0, &val); diff --git a/fs/nilfs2/sysfs.h b/fs/nilfs2/sysfs.h index 677e3a1..648cedf 100644 --- a/fs/nilfs2/sysfs.h +++ b/fs/nilfs2/sysfs.h @@ -66,7 +66,7 @@ struct nilfs_##name##_attr { \ char *); \ ssize_t (*store)(struct kobject *, struct attribute *, \ const char *, size_t); \ -}; +} NILFS_COMMON_ATTR_STRUCT(feature); @@ -77,7 +77,7 @@ struct nilfs_##name##_attr { \ char *); \ ssize_t (*store)(struct nilfs_##name##_attr *, struct the_nilfs *, \ const char *, size_t); \ -}; +} NILFS_DEV_ATTR_STRUCT(dev); NILFS_DEV_ATTR_STRUCT(segments); @@ -93,7 +93,7 @@ struct nilfs_##name##_attr { \ char *); \ ssize_t (*store)(struct nilfs_##name##_attr *, struct nilfs_root *, \ const char *, size_t); \ -}; +} NILFS_CP_ATTR_STRUCT(snapshot); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 69bd801..809bd2d 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Ryusuke Konishi. * */ @@ -112,8 +108,8 @@ static int nilfs_load_super_root(struct the_nilfs *nilfs, struct nilfs_super_root *raw_sr; struct nilfs_super_block **sbp = nilfs->ns_sbp; struct nilfs_inode *rawi; - unsigned dat_entry_size, segment_usage_size, checkpoint_size; - unsigned inode_size; + unsigned int dat_entry_size, segment_usage_size, checkpoint_size; + unsigned int inode_size; int err; err = nilfs_read_super_root_block(nilfs, sr_block, &bh_sr, 1); @@ -621,8 +617,10 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp); if (err) goto out; - /* not failed_sbh; sbh is released automatically - when reloading fails. */ + /* + * Not to failed_sbh; sbh is released automatically + * when reloading fails. + */ } nilfs->ns_blocksize_bits = sb->s_blocksize_bits; nilfs->ns_blocksize = blocksize; diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 23778d3..79369fd 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -13,11 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Ryusuke Konishi <ryusuke@osrg.net> + * Written by Ryusuke Konishi. * */ @@ -118,10 +114,10 @@ struct the_nilfs { struct buffer_head *ns_sbh[2]; struct nilfs_super_block *ns_sbp[2]; time_t ns_sbwtime; - unsigned ns_sbwcount; - unsigned ns_sbsize; - unsigned ns_mount_state; - unsigned ns_sb_update_freq; + unsigned int ns_sbwcount; + unsigned int ns_sbsize; + unsigned int ns_mount_state; + unsigned int ns_sb_update_freq; /* * Following fields are dedicated to a writable FS-instance. @@ -226,15 +222,14 @@ THE_NILFS_FNS(SB_DIRTY, sb_dirty) * Mount option operations */ #define nilfs_clear_opt(nilfs, opt) \ - do { (nilfs)->ns_mount_opt &= ~NILFS_MOUNT_##opt; } while (0) + ((nilfs)->ns_mount_opt &= ~NILFS_MOUNT_##opt) #define nilfs_set_opt(nilfs, opt) \ - do { (nilfs)->ns_mount_opt |= NILFS_MOUNT_##opt; } while (0) + ((nilfs)->ns_mount_opt |= NILFS_MOUNT_##opt) #define nilfs_test_opt(nilfs, opt) ((nilfs)->ns_mount_opt & NILFS_MOUNT_##opt) #define nilfs_write_opt(nilfs, mask, opt) \ - do { (nilfs)->ns_mount_opt = \ + ((nilfs)->ns_mount_opt = \ (((nilfs)->ns_mount_opt & ~NILFS_MOUNT_##mask) | \ - NILFS_MOUNT_##opt); \ - } while (0) + NILFS_MOUNT_##opt)) \ /** * struct nilfs_root - nilfs root object @@ -273,6 +268,7 @@ struct nilfs_root { static inline int nilfs_sb_need_update(struct the_nilfs *nilfs) { u64 t = get_seconds(); + return t < nilfs->ns_sbwtime || t > nilfs->ns_sbwtime + nilfs->ns_sb_update_freq; } @@ -280,6 +276,7 @@ static inline int nilfs_sb_need_update(struct the_nilfs *nilfs) static inline int nilfs_sb_will_flip(struct the_nilfs *nilfs) { int flip_bits = nilfs->ns_sbwcount & 0x0FL; + return (flip_bits != 0x08 && flip_bits != 0x0F); } @@ -308,7 +305,7 @@ static inline void nilfs_get_root(struct nilfs_root *root) static inline int nilfs_valid_fs(struct the_nilfs *nilfs) { - unsigned valid_fs; + unsigned int valid_fs; down_read(&nilfs->ns_sem); valid_fs = (nilfs->ns_mount_state & NILFS_VALID_FS); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5415835..4648c7f 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1027,11 +1027,15 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, }; if (type == CLEAR_REFS_MM_HIWATER_RSS) { + if (down_write_killable(&mm->mmap_sem)) { + count = -EINTR; + goto out_mm; + } + /* * Writing 5 to /proc/pid/clear_refs resets the peak * resident set size to this mm's current rss value. */ - down_write(&mm->mmap_sem); reset_mm_hiwater_rss(mm); up_write(&mm->mmap_sem); goto out_mm; @@ -1043,7 +1047,10 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, if (!(vma->vm_flags & VM_SOFTDIRTY)) continue; up_read(&mm->mmap_sem); - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) { + count = -EINTR; + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 2cc643c..e8acb2b 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, ...); @@ -317,6 +315,8 @@ int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, unsigned int relsec); int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, unsigned int relsec); +void arch_kexec_protect_crashkres(void); +void arch_kexec_unprotect_crashkres(void); #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; diff --git a/include/linux/mm.h b/include/linux/mm.h index b530c99..2835d59 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2011,9 +2011,9 @@ static inline void mm_populate(unsigned long addr, unsigned long len) {} #endif /* These take the mm semaphore themselves */ -extern unsigned long vm_brk(unsigned long, unsigned long); +extern unsigned long __must_check vm_brk(unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); -extern unsigned long vm_mmap(struct file *, unsigned long, +extern unsigned long __must_check vm_mmap(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index e9fcf90..5988dd5 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -13,12 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU Lesser General Public License for more details. * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * - * Written by Koji Sato <koji@osrg.net> - * Ryusuke Konishi <ryusuke@osrg.net> + * Written by Koji Sato and Ryusuke Konishi. */ /* * linux/include/linux/ext2_fs.h @@ -132,10 +127,14 @@ struct nilfs_super_root { #define NILFS_MOUNT_ERRORS_RO 0x0020 /* Remount fs ro on errors */ #define NILFS_MOUNT_ERRORS_PANIC 0x0040 /* Panic on errors */ #define NILFS_MOUNT_BARRIER 0x1000 /* Use block barriers */ -#define NILFS_MOUNT_STRICT_ORDER 0x2000 /* Apply strict in-order - semantics also for data */ -#define NILFS_MOUNT_NORECOVERY 0x4000 /* Disable write access during - mount-time recovery */ +#define NILFS_MOUNT_STRICT_ORDER 0x2000 /* + * Apply strict in-order + * semantics also for data + */ +#define NILFS_MOUNT_NORECOVERY 0x4000 /* + * Disable write access during + * mount-time recovery + */ #define NILFS_MOUNT_DISCARD 0x8000 /* Issue DISCARD requests */ @@ -147,16 +146,20 @@ struct nilfs_super_block { __le16 s_minor_rev_level; /* minor revision level */ __le16 s_magic; /* Magic signature */ - __le16 s_bytes; /* Bytes count of CRC calculation - for this structure. s_reserved - is excluded. */ + __le16 s_bytes; /* + * Bytes count of CRC calculation + * for this structure. s_reserved + * is excluded. + */ __le16 s_flags; /* flags */ __le32 s_crc_seed; /* Seed value of CRC calculation */ /*10*/ __le32 s_sum; /* Check sum of super block */ - __le32 s_log_block_size; /* Block size represented as follows - blocksize = - 1 << (s_log_block_size + 10) */ + __le32 s_log_block_size; /* + * Block size represented as follows + * blocksize = + * 1 << (s_log_block_size + 10) + */ __le64 s_nsegments; /* Number of segments in filesystem */ /*20*/ __le64 s_dev_size; /* block device size in bytes */ __le64 s_first_data_block; /* 1st seg disk block number */ @@ -168,8 +171,10 @@ struct nilfs_super_block { __le64 s_last_seq; /* seq. number of seg written last */ /*50*/ __le64 s_free_blocks_count; /* Free blocks count */ - __le64 s_ctime; /* Creation time (execution time of - newfs) */ + __le64 s_ctime; /* + * Creation time (execution time of + * newfs) + */ /*60*/ __le64 s_mtime; /* Mount time */ __le64 s_wtime; /* Write time */ /*70*/ __le16 s_mnt_count; /* Mount count */ @@ -193,8 +198,10 @@ struct nilfs_super_block { /*A8*/ char s_volume_name[80]; /* volume name */ /*F8*/ __le32 s_c_interval; /* Commit interval of segment */ - __le32 s_c_block_max; /* Threshold of data amount for - the segment construction */ + __le32 s_c_block_max; /* + * Threshold of data amount for + * the segment construction + */ /*100*/ __le64 s_feature_compat; /* Compatible feature set */ __le64 s_feature_compat_ro; /* Read-only compatible feature set */ __le64 s_feature_incompat; /* Incompatible feature set */ @@ -247,12 +254,18 @@ struct nilfs_super_block { #define NILFS_SB_OFFSET_BYTES 1024 /* byte offset of nilfs superblock */ -#define NILFS_SEG_MIN_BLOCKS 16 /* Minimum number of blocks in - a full segment */ -#define NILFS_PSEG_MIN_BLOCKS 2 /* Minimum number of blocks in - a partial segment */ -#define NILFS_MIN_NRSVSEGS 8 /* Minimum number of reserved - segments */ +#define NILFS_SEG_MIN_BLOCKS 16 /* + * Minimum number of blocks in + * a full segment + */ +#define NILFS_PSEG_MIN_BLOCKS 2 /* + * Minimum number of blocks in + * a partial segment + */ +#define NILFS_MIN_NRSVSEGS 8 /* + * Minimum number of reserved + * segments + */ /* * We call DAT, cpfile, and sufile root metadata files. Inodes of @@ -327,9 +340,9 @@ enum { ~NILFS_DIR_ROUND) #define NILFS_MAX_REC_LEN ((1<<16)-1) -static inline unsigned nilfs_rec_len_from_disk(__le16 dlen) +static inline unsigned int nilfs_rec_len_from_disk(__le16 dlen) { - unsigned len = le16_to_cpu(dlen); + unsigned int len = le16_to_cpu(dlen); #if !defined(__KERNEL__) || (PAGE_SIZE >= 65536) if (len == NILFS_MAX_REC_LEN) @@ -338,7 +351,7 @@ static inline unsigned nilfs_rec_len_from_disk(__le16 dlen) return len; } -static inline __le16 nilfs_rec_len_to_disk(unsigned len) +static inline __le16 nilfs_rec_len_to_disk(unsigned int len) { #if !defined(__KERNEL__) || (PAGE_SIZE >= 65536) if (len == (1 << 16)) @@ -518,9 +531,11 @@ struct nilfs_checkpoint { __le64 cp_inodes_count; __le64 cp_blocks_count; - /* Do not change the byte offset of ifile inode. - To keep the compatibility of the disk format, - additional fields should be added behind cp_ifile_inode. */ + /* + * Do not change the byte offset of ifile inode. + * To keep the compatibility of the disk format, + * additional fields should be added behind cp_ifile_inode. + */ struct nilfs_inode cp_ifile_inode; }; diff --git a/include/linux/oom.h b/include/linux/oom.h index d3f533f..8346952 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -50,24 +50,21 @@ enum oom_scan_t { OOM_SCAN_SELECT, /* always select this thread first */ }; -/* Thread is the potential origin of an oom condition; kill first on oom */ -#define OOM_FLAG_ORIGIN ((__force oom_flags_t)0x1) - extern struct mutex oom_lock; static inline void set_current_oom_origin(void) { - current->signal->oom_flags |= OOM_FLAG_ORIGIN; + current->signal->oom_flag_origin = true; } static inline void clear_current_oom_origin(void) { - current->signal->oom_flags &= ~OOM_FLAG_ORIGIN; + current->signal->oom_flag_origin = false; } static inline bool oom_task_origin(const struct task_struct *p) { - return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN); + return p->signal->oom_flag_origin; } extern void mark_oom_victim(struct task_struct *tsk); diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c036de..21c26e7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -794,7 +794,11 @@ struct signal_struct { struct tty_audit_buf *tty_audit_buf; #endif - oom_flags_t oom_flags; + /* + * Thread is the potential origin of an oom condition; kill first on + * oom + */ + bool oom_flag_origin; short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ diff --git a/include/linux/signal.h b/include/linux/signal.h index 639be26..b63f63e 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -400,7 +400,9 @@ int unhandled_signal(struct task_struct *tsk, int sig); #else #define rt_sigmask(sig) sigmask(sig) #endif -#define siginmask(sig, mask) (rt_sigmask(sig) & (mask)) + +#define siginmask(sig, mask) \ + ((sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) @@ -421,14 +423,10 @@ int unhandled_signal(struct task_struct *tsk, int sig); rt_sigmask(SIGCONT) | rt_sigmask(SIGCHLD) | \ rt_sigmask(SIGWINCH) | rt_sigmask(SIGURG) ) -#define sig_kernel_only(sig) \ - (((sig) < SIGRTMIN) && siginmask(sig, SIG_KERNEL_ONLY_MASK)) -#define sig_kernel_coredump(sig) \ - (((sig) < SIGRTMIN) && siginmask(sig, SIG_KERNEL_COREDUMP_MASK)) -#define sig_kernel_ignore(sig) \ - (((sig) < SIGRTMIN) && siginmask(sig, SIG_KERNEL_IGNORE_MASK)) -#define sig_kernel_stop(sig) \ - (((sig) < SIGRTMIN) && siginmask(sig, SIG_KERNEL_STOP_MASK)) +#define sig_kernel_only(sig) siginmask(sig, SIG_KERNEL_ONLY_MASK) +#define sig_kernel_coredump(sig) siginmask(sig, SIG_KERNEL_COREDUMP_MASK) +#define sig_kernel_ignore(sig) siginmask(sig, SIG_KERNEL_IGNORE_MASK) +#define sig_kernel_stop(sig) siginmask(sig, SIG_KERNEL_STOP_MASK) #define sig_user_defined(t, signr) \ (((t)->sighand->action[(signr)-1].sa.sa_handler != SIG_DFL) && \ diff --git a/include/linux/types.h b/include/linux/types.h index 70dd3df..baf7183 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -156,7 +156,6 @@ typedef u32 dma_addr_t; typedef unsigned __bitwise__ gfp_t; typedef unsigned __bitwise__ fmode_t; -typedef unsigned __bitwise__ oom_flags_t; #ifdef CONFIG_PHYS_ADDR_T_64BIT typedef u64 phys_addr_t; @@ -1200,7 +1200,11 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, if (err) goto out_fput; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) { + err = -EINTR; + goto out_fput; + } + if (addr && !(shmflg & SHM_REMAP)) { err = -EINVAL; if (addr + size < addr) @@ -1271,7 +1275,8 @@ SYSCALL_DEFINE1(shmdt, char __user *, shmaddr) if (addr & ~PAGE_MASK) return retval; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; /* * This function tries to be smart and unmap shm segments that diff --git a/kernel/Makefile b/kernel/Makefile index f0c40bf..e2ec54e 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/ diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index c01f733..b7a525a 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1130,7 +1130,9 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area) struct vm_area_struct *vma; int ret; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + if (mm->uprobes_state.xol_area) { ret = -EALREADY; goto fail; @@ -1469,7 +1471,8 @@ static void dup_xol_work(struct callback_head *work) if (current->flags & PF_EXITING) return; - if (!__create_xol_area(current->utask->dup_xol_addr)) + if (!__create_xol_area(current->utask->dup_xol_addr) && + !fatal_signal_pending(current)) uprobe_warn(current, "dup xol area"); } diff --git a/kernel/exit.c b/kernel/exit.c index 75b34fe..9e6e135 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -918,17 +918,28 @@ static int eligible_pid(struct wait_opts *wo, struct task_struct *p) task_pid_type(p, wo->wo_type) == wo->wo_pid; } -static int eligible_child(struct wait_opts *wo, struct task_struct *p) +static int +eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p) { if (!eligible_pid(wo, p)) return 0; - /* Wait for all children (clone and not) if __WALL is set; - * otherwise, wait for clone children *only* if __WCLONE is - * set; otherwise, wait for non-clone children *only*. (Note: - * A "clone" child here is one that reports to its parent - * using a signal other than SIGCHLD.) */ - if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) - && !(wo->wo_flags & __WALL)) + + /* + * Wait for all children (clone and not) if __WALL is set or + * if it is traced by us. + */ + if (ptrace || (wo->wo_flags & __WALL)) + return 1; + + /* + * Otherwise, wait for clone children *only* if __WCLONE is set; + * otherwise, wait for non-clone children *only*. + * + * Note: a "clone" child here is one that reports to its parent + * using a signal other than SIGCHLD, or a non-leader thread which + * we can only see if it is traced by us. + */ + if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) return 0; return 1; @@ -1300,7 +1311,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace, if (unlikely(exit_state == EXIT_DEAD)) return 0; - ret = eligible_child(wo, p); + ret = eligible_child(wo, ptrace, p); if (!ret) return ret; @@ -1524,7 +1535,8 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, enum pid_type type; long ret; - if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED)) + if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED| + __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; if (!(options & (WEXITED|WSTOPPED|WCONTINUED))) return -EINVAL; diff --git a/kernel/fork.c b/kernel/fork.c index 103d78f..47887bb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -340,13 +340,14 @@ void set_task_stack_end_magic(struct task_struct *tsk) *stackend = STACK_END_MAGIC; /* for overflow detection */ } -static struct task_struct *dup_task_struct(struct task_struct *orig) +static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; struct thread_info *ti; - int node = tsk_fork_get_node(orig); int err; + if (node == NUMA_NO_NODE) + node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; @@ -413,7 +414,10 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) unsigned long charge; uprobe_start_dup_mmap(); - down_write(&oldmm->mmap_sem); + if (down_write_killable(&oldmm->mmap_sem)) { + retval = -EINTR; + goto fail_uprobe_end; + } flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* @@ -525,6 +529,7 @@ out: up_write(&mm->mmap_sem); flush_tlb_mm(oldmm); up_write(&oldmm->mmap_sem); +fail_uprobe_end: uprobe_end_dup_mmap(); return retval; fail_nomem_anon_vma_fork: @@ -1276,7 +1281,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, int __user *child_tidptr, struct pid *pid, int trace, - unsigned long tls) + unsigned long tls, + int node) { int retval; struct task_struct *p; @@ -1328,7 +1334,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto fork_out; retval = -ENOMEM; - p = dup_task_struct(current); + p = dup_task_struct(current, node); if (!p) goto fork_out; @@ -1706,7 +1712,8 @@ static inline void init_idle_pids(struct pid_link *links) struct task_struct *fork_idle(int cpu) { struct task_struct *task; - task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0); + task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0, + cpu_to_node(cpu)); if (!IS_ERR(task)) { init_idle_pids(task->pids); init_idle(task, cpu); @@ -1751,7 +1758,7 @@ long _do_fork(unsigned long clone_flags, } p = copy_process(clone_flags, stack_start, stack_size, - child_tidptr, NULL, trace, tls); + child_tidptr, NULL, trace, tls, NUMA_NO_NODE); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. diff --git a/kernel/kexec.c b/kernel/kexec.c index ee70aef..4384672 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -103,6 +103,65 @@ out_free_image: return ret; } +static int do_kexec_load(unsigned long entry, unsigned long nr_segments, + struct kexec_segment __user *segments, unsigned long flags) +{ + struct kimage **dest_image, *image; + unsigned long i; + int ret; + + if (flags & KEXEC_ON_CRASH) { + dest_image = &kexec_crash_image; + if (kexec_crash_image) + arch_kexec_unprotect_crashkres(); + } else { + dest_image = &kexec_image; + } + + if (nr_segments == 0) { + /* Uninstall image */ + kimage_free(xchg(dest_image, NULL)); + return 0; + } + if (flags & KEXEC_ON_CRASH) { + /* + * Loading another kernel to switch to if this one + * crashes. Free any current crash dump kernel before + * we corrupt it. + */ + kimage_free(xchg(&kexec_crash_image, NULL)); + } + + ret = kimage_alloc_init(&image, entry, nr_segments, segments, flags); + if (ret) + return ret; + + if (flags & KEXEC_PRESERVE_CONTEXT) + image->preserve_context = 1; + + ret = machine_kexec_prepare(image); + if (ret) + goto out; + + for (i = 0; i < nr_segments; i++) { + ret = kimage_load_segment(image, &image->segment[i]); + if (ret) + goto out; + } + + kimage_terminate(image); + + /* Install the new kernel and uninstall the old */ + image = xchg(dest_image, image); + +out: + if ((flags & KEXEC_ON_CRASH) && kexec_crash_image) + arch_kexec_protect_crashkres(); + + kimage_free(image); + return ret; +} + /* * Exec Kernel system call: for obvious reasons only root may call it. * @@ -127,7 +186,6 @@ out_free_image: SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, struct kexec_segment __user *, segments, unsigned long, flags) { - struct kimage **dest_image, *image; int result; /* We only trust the superuser with rebooting the system. */ @@ -152,9 +210,6 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, if (nr_segments > KEXEC_SEGMENT_MAX) return -EINVAL; - image = NULL; - result = 0; - /* Because we write directly to the reserved memory * region when loading crash kernels we need a mutex here to * prevent multiple crash kernels from attempting to load @@ -166,53 +221,9 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, if (!mutex_trylock(&kexec_mutex)) return -EBUSY; - dest_image = &kexec_image; - if (flags & KEXEC_ON_CRASH) - dest_image = &kexec_crash_image; - if (nr_segments > 0) { - unsigned long i; - - if (flags & KEXEC_ON_CRASH) { - /* - * Loading another kernel to switch to if this one - * crashes. Free any current crash dump kernel before - * we corrupt it. - */ - - kimage_free(xchg(&kexec_crash_image, NULL)); - result = kimage_alloc_init(&image, entry, nr_segments, - segments, flags); - crash_map_reserved_pages(); - } else { - /* Loading another kernel to reboot into. */ - - result = kimage_alloc_init(&image, entry, nr_segments, - segments, flags); - } - if (result) - goto out; - - if (flags & KEXEC_PRESERVE_CONTEXT) - image->preserve_context = 1; - result = machine_kexec_prepare(image); - if (result) - goto out; - - for (i = 0; i < nr_segments; i++) { - result = kimage_load_segment(image, &image->segment[i]); - if (result) - goto out; - } - kimage_terminate(image); - if (flags & KEXEC_ON_CRASH) - crash_unmap_reserved_pages(); - } - /* Install the new kernel, and Uninstall the old */ - image = xchg(dest_image, image); + result = do_kexec_load(entry, nr_segments, segments, flags); -out: mutex_unlock(&kexec_mutex); - kimage_free(image); return result; } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index d5d4082..56b3ed0 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); @@ -1553,13 +1551,14 @@ 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 arch_kexec_protect_crashkres(void) {} -void __weak crash_unmap_reserved_pages(void) +void __weak arch_kexec_unprotect_crashkres(void) {} diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index c72d2ff..503bc2d 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -274,8 +274,11 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, return -EBUSY; dest_image = &kexec_image; - if (flags & KEXEC_FILE_ON_CRASH) + if (flags & KEXEC_FILE_ON_CRASH) { dest_image = &kexec_crash_image; + if (kexec_crash_image) + arch_kexec_unprotect_crashkres(); + } if (flags & KEXEC_FILE_UNLOAD) goto exchange; @@ -324,6 +327,9 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, exchange: image = xchg(dest_image, image); out: + if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image) + arch_kexec_protect_crashkres(); + mutex_unlock(&kexec_mutex); kimage_free(image); return ret; diff --git a/kernel/signal.c b/kernel/signal.c index ab122a2..96e9bc4 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -224,7 +224,7 @@ static inline void print_dropped_signal(int sig) if (!__ratelimit(&ratelimit_state)) return; - printk(KERN_INFO "%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n", + pr_info("%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n", current->comm, current->pid, sig); } @@ -1089,10 +1089,10 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t, static void print_fatal_signal(int signr) { struct pt_regs *regs = signal_pt_regs(); - printk(KERN_INFO "potentially unexpected fatal signal %d.\n", signr); + pr_info("potentially unexpected fatal signal %d.\n", signr); #if defined(__i386__) && !defined(__arch_um__) - printk(KERN_INFO "code at %08lx: ", regs->ip); + pr_info("code at %08lx: ", regs->ip); { int i; for (i = 0; i < 16; i++) { @@ -1100,10 +1100,10 @@ static void print_fatal_signal(int signr) if (get_user(insn, (unsigned char *)(regs->ip + i))) break; - printk(KERN_CONT "%02x ", insn); + pr_cont("%02x ", insn); } } - printk(KERN_CONT "\n"); + pr_cont("\n"); #endif preempt_disable(); show_regs(regs); diff --git a/kernel/sys.c b/kernel/sys.c index cf8ba54..89d5be4 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2246,7 +2246,8 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SET_THP_DISABLE: if (arg3 || arg4 || arg5) return -EINVAL; - down_write(&me->mm->mmap_sem); + if (down_write_killable(&me->mm->mmap_sem)) + return -EINTR; if (arg2) me->mm->def_flags |= VM_NOHUGEPAGE; else diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index c635a10..533f912 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -22,7 +22,7 @@ config KGDB_SERIAL_CONSOLE tristate "KGDB: use kgdb over the serial console" select CONSOLE_POLL select MAGIC_SYSRQ - depends on TTY + depends on TTY && HW_CONSOLE default y help Share a serial console with kgdb. Sysrq-g must be used diff --git a/mm/internal.h b/mm/internal.h index f6f3353..a37e5b6 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -442,7 +442,7 @@ extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; -extern unsigned long vm_mmap_pgoff(struct file *, unsigned long, +extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/mm/madvise.c b/mm/madvise.c index 07427d3..93fb63e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -707,10 +707,12 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) return error; write = madvise_need_mmap_write(behavior); - if (write) - down_write(¤t->mm->mmap_sem); - else + if (write) { + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; + } else { down_read(¤t->mm->mmap_sem); + } /* * If the interval [start,end) covers some unmapped address diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b3f16ab..cf428d7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1604,7 +1604,7 @@ static void memcg_oom_recover(struct mem_cgroup *memcg) static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) { - if (!current->memcg_may_oom) + if (!current->memcg_may_oom || current->memcg_in_oom) return; /* * We are in the middle of the charge context here, so we @@ -617,7 +617,7 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, return error; } -static int do_mlock(unsigned long start, size_t len, vm_flags_t flags) +static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) { unsigned long locked; unsigned long lock_limit; @@ -635,7 +635,8 @@ static int do_mlock(unsigned long start, size_t len, vm_flags_t flags) lock_limit >>= PAGE_SHIFT; locked = len >> PAGE_SHIFT; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; locked += current->mm->locked_vm; @@ -678,7 +679,8 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; ret = apply_vma_lock_flags(start, len, 0); up_write(¤t->mm->mmap_sem); @@ -748,9 +750,10 @@ SYSCALL_DEFINE1(mlockall, int, flags) lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; - ret = -ENOMEM; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; + ret = -ENOMEM; if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || capable(CAP_IPC_LOCK)) ret = apply_mlockall_flags(flags); @@ -765,7 +768,8 @@ SYSCALL_DEFINE0(munlockall) { int ret; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; ret = apply_mlockall_flags(0); up_write(¤t->mm->mmap_sem); return ret; @@ -178,7 +178,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) unsigned long min_brk; bool populate; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; #ifdef CONFIG_COMPAT_BRK /* @@ -2493,7 +2494,9 @@ int vm_munmap(unsigned long start, size_t len) int ret; struct mm_struct *mm = current->mm; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + ret = do_munmap(mm, start, len); up_write(&mm->mmap_sem); return ret; @@ -2502,8 +2505,15 @@ EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { + int ret; + struct mm_struct *mm = current->mm; + profile_munmap(addr); - return vm_munmap(addr, len); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + ret = do_munmap(mm, addr, len); + up_write(&mm->mmap_sem); + return ret; } @@ -2535,7 +2545,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (pgoff + (size >> PAGE_SHIFT) < pgoff) return ret; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + vma = find_vma(mm, start); if (!vma || !(vma->vm_flags & VM_SHARED)) @@ -2700,7 +2712,9 @@ unsigned long vm_brk(unsigned long addr, unsigned long len) unsigned long ret; bool populate; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + ret = do_brk(addr, len); populate = ((mm->def_flags & VM_LOCKED) != 0); up_write(&mm->mmap_sem); diff --git a/mm/mprotect.c b/mm/mprotect.c index b650c54..5019a1e 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -379,7 +379,8 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, reqprot = prot; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; vma = find_vma(current->mm, start); error = -ENOMEM; diff --git a/mm/mremap.c b/mm/mremap.c index 9dc4999..1f157ad 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -503,7 +503,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, if (!new_len) return ret; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; if (flags & MREMAP_FIXED) { ret = mremap_to(addr, old_len, new_addr, new_len, @@ -297,7 +297,8 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, ret = security_mmap_file(file, prot, flag); if (!ret) { - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff, &populate); up_write(&mm->mmap_sem); diff --git a/scripts/gdb/linux/Makefile b/scripts/gdb/linux/Makefile index 6cf1ecf..cd129e6 100644 --- a/scripts/gdb/linux/Makefile +++ b/scripts/gdb/linux/Makefile @@ -8,4 +8,14 @@ ifneq ($(KBUILD_SRC),) endif @: -clean-files := *.pyc *.pyo $(if $(KBUILD_SRC),*.py) +quiet_cmd_gen_constants_py = GEN $@ + cmd_gen_constants_py = \ + $(CPP) -E -x c -P $(c_flags) $< > $@ ;\ + sed -i '1,/<!-- end-c-headers -->/d;' $@ + +$(obj)/constants.py: $(SRCTREE)/$(obj)/constants.py.in + $(call if_changed,gen_constants_py) + +build_constants_py: $(obj)/constants.py + +clean-files := *.pyc *.pyo $(if $(KBUILD_SRC),*.py) $(obj)/constants.py diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in new file mode 100644 index 0000000..07e6c2b --- /dev/null +++ b/scripts/gdb/linux/constants.py.in @@ -0,0 +1,59 @@ +/* + * gdb helper commands and functions for Linux kernel debugging + * + * Kernel constants derived from include files. + * + * Copyright (c) 2016 Linaro Ltd + * + * Authors: + * Kieran Bingham <kieran.bingham@linaro.org> + * + * This work is licensed under the terms of the GNU GPL version 2. + * + */ + +#include <linux/fs.h> +#include <linux/mount.h> +#include <linux/radix-tree.h> + +/* We need to stringify expanded macros so that they can be parsed */ + +#define STRING(x) #x +#define XSTRING(x) STRING(x) + +#define LX_VALUE(x) LX_##x = x +#define LX_GDBPARSED(x) LX_##x = gdb.parse_and_eval(XSTRING(x)) + +/* + * IS_ENABLED generates (a || b) which is not compatible with python + * We can only switch on configuration items we know are available + * Therefore - IS_BUILTIN() is more appropriate + */ +#define LX_CONFIG(x) LX_##x = IS_BUILTIN(x) + +/* The build system will take care of deleting everything above this marker */ +<!-- end-c-headers --> + +import gdb + +/* linux/fs.h */ +LX_VALUE(MS_RDONLY) +LX_VALUE(MS_SYNCHRONOUS) +LX_VALUE(MS_MANDLOCK) +LX_VALUE(MS_DIRSYNC) +LX_VALUE(MS_NOATIME) +LX_VALUE(MS_NODIRATIME) + +/* linux/mount.h */ +LX_VALUE(MNT_NOSUID) +LX_VALUE(MNT_NODEV) +LX_VALUE(MNT_NOEXEC) +LX_VALUE(MNT_NOATIME) +LX_VALUE(MNT_NODIRATIME) +LX_VALUE(MNT_RELATIME) + +/* linux/radix-tree.h */ +LX_VALUE(RADIX_TREE_INDIRECT_PTR) +LX_GDBPARSED(RADIX_TREE_HEIGHT_MASK) +LX_GDBPARSED(RADIX_TREE_MAP_SHIFT) +LX_GDBPARSED(RADIX_TREE_MAP_MASK) diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py index 4297b83..ca11e8d 100644 --- a/scripts/gdb/linux/cpus.py +++ b/scripts/gdb/linux/cpus.py @@ -97,9 +97,47 @@ def cpu_list(mask_name): bits >>= 1 bit += 1 + yield int(cpu) + + +def each_online_cpu(): + for cpu in cpu_list("__cpu_online_mask"): + yield cpu + + +def each_present_cpu(): + for cpu in cpu_list("__cpu_present_mask"): + yield cpu + + +def each_possible_cpu(): + for cpu in cpu_list("__cpu_possible_mask"): + yield cpu + + +def each_active_cpu(): + for cpu in cpu_list("__cpu_active_mask"): yield cpu +class LxCpus(gdb.Command): + """List CPU status arrays + +Displays the known state of each CPU based on the kernel masks +and can help identify the state of hotplugged CPUs""" + + def __init__(self): + super(LxCpus, self).__init__("lx-cpus", gdb.COMMAND_DATA) + + def invoke(self, arg, from_tty): + gdb.write("Possible CPUs : {}\n".format(list(each_possible_cpu()))) + gdb.write("Present CPUs : {}\n".format(list(each_present_cpu()))) + gdb.write("Online CPUs : {}\n".format(list(each_online_cpu()))) + gdb.write("Active CPUs : {}\n".format(list(each_active_cpu()))) + +LxCpus() + + class PerCpu(gdb.Function): """Return per-cpu variable. diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py index 927d0d2..f9b92ec 100644 --- a/scripts/gdb/linux/dmesg.py +++ b/scripts/gdb/linux/dmesg.py @@ -33,11 +33,12 @@ class LxDmesg(gdb.Command): if log_first_idx < log_next_idx: log_buf_2nd_half = -1 length = log_next_idx - log_first_idx - log_buf = inf.read_memory(start, length) + log_buf = utils.read_memoryview(inf, start, length).tobytes() else: log_buf_2nd_half = log_buf_len - log_first_idx - log_buf = inf.read_memory(start, log_buf_2nd_half) + \ - inf.read_memory(log_buf_addr, log_next_idx) + a = utils.read_memoryview(inf, start, log_buf_2nd_half) + b = utils.read_memoryview(inf, log_buf_addr, log_next_idx) + log_buf = a.tobytes() + b.tobytes() pos = 0 while pos < log_buf.__len__(): @@ -50,10 +51,10 @@ class LxDmesg(gdb.Command): continue text_len = utils.read_u16(log_buf[pos + 10:pos + 12]) - text = log_buf[pos + 16:pos + 16 + text_len] + text = log_buf[pos + 16:pos + 16 + text_len].decode() time_stamp = utils.read_u64(log_buf[pos:pos + 8]) - for line in memoryview(text).tobytes().splitlines(): + for line in text.splitlines(): gdb.write("[{time:12.6f}] {line}\n".format( time=time_stamp / 1000000000.0, line=line)) diff --git a/scripts/gdb/linux/lists.py b/scripts/gdb/linux/lists.py index 3a3775b..2f335fb 100644 --- a/scripts/gdb/linux/lists.py +++ b/scripts/gdb/linux/lists.py @@ -18,6 +18,27 @@ from linux import utils list_head = utils.CachedType("struct list_head") +def list_for_each(head): + if head.type == list_head.get_type().pointer(): + head = head.dereference() + elif head.type != list_head.get_type(): + raise gdb.GdbError("Must be struct list_head not {}" + .format(head.type)) + + node = head['next'].dereference() + while node.address != head.address: + yield node.address + node = node['next'].dereference() + + +def list_for_each_entry(head, gdbtype, member): + for node in list_for_each(head): + if node.type != list_head.get_type().pointer(): + raise TypeError("Type {} found. Expected struct list_head *." + .format(node.type)) + yield utils.container_of(node, gdbtype, member) + + def list_check(head): nb = 0 if (head.type == list_head.get_type().pointer()): diff --git a/scripts/gdb/linux/modules.py b/scripts/gdb/linux/modules.py index 0a35d6d..441b2323 100644 --- a/scripts/gdb/linux/modules.py +++ b/scripts/gdb/linux/modules.py @@ -13,7 +13,7 @@ import gdb -from linux import cpus, utils +from linux import cpus, utils, lists module_type = utils.CachedType("struct module") @@ -21,14 +21,14 @@ module_type = utils.CachedType("struct module") def module_list(): global module_type + modules = utils.gdb_eval_or_none("modules") + if modules is None: + return + module_ptr_type = module_type.get_type().pointer() - modules = gdb.parse_and_eval("modules") - entry = modules['next'] - end_of_list = modules.address - while entry != end_of_list: - yield utils.container_of(entry, module_ptr_type, "list") - entry = entry['next'] + for module in lists.list_for_each_entry(modules, module_ptr_type, "list"): + yield module def find_module_by_name(name): @@ -78,19 +78,17 @@ class LxLsmod(gdb.Command): address=str(layout['base']).split()[0], name=module['name'].string(), size=str(layout['size']), - ref=str(module['refcnt']['counter']))) + ref=str(module['refcnt']['counter'] - 1))) - source_list = module['source_list'] t = self._module_use_type.get_type().pointer() - entry = source_list['next'] first = True - while entry != source_list.address: - use = utils.container_of(entry, t, "source_list") + sources = module['source_list'] + for use in lists.list_for_each_entry(sources, t, "source_list"): gdb.write("{separator}{name}".format( separator=" " if first else ",", name=use['source']['name'].string())) first = False - entry = entry['next'] + gdb.write("\n") diff --git a/scripts/gdb/linux/proc.py b/scripts/gdb/linux/proc.py index 6e6709c..38b1f09 100644 --- a/scripts/gdb/linux/proc.py +++ b/scripts/gdb/linux/proc.py @@ -12,6 +12,10 @@ # import gdb +from linux import constants +from linux import utils +from linux import tasks +from linux import lists class LxCmdLine(gdb.Command): @@ -39,3 +43,155 @@ class LxVersion(gdb.Command): gdb.write(gdb.parse_and_eval("linux_banner").string()) LxVersion() + + +# Resource Structure Printers +# /proc/iomem +# /proc/ioports + +def get_resources(resource, depth): + while resource: + yield resource, depth + + child = resource['child'] + if child: + for res, deep in get_resources(child, depth + 1): + yield res, deep + + resource = resource['sibling'] + + +def show_lx_resources(resource_str): + resource = gdb.parse_and_eval(resource_str) + width = 4 if resource['end'] < 0x10000 else 8 + # Iterate straight to the first child + for res, depth in get_resources(resource['child'], 0): + start = int(res['start']) + end = int(res['end']) + gdb.write(" " * depth * 2 + + "{0:0{1}x}-".format(start, width) + + "{0:0{1}x} : ".format(end, width) + + res['name'].string() + "\n") + + +class LxIOMem(gdb.Command): + """Identify the IO memory resource locations defined by the kernel + +Equivalent to cat /proc/iomem on a running target""" + + def __init__(self): + super(LxIOMem, self).__init__("lx-iomem", gdb.COMMAND_DATA) + + def invoke(self, arg, from_tty): + return show_lx_resources("iomem_resource") + +LxIOMem() + + +class LxIOPorts(gdb.Command): + """Identify the IO port resource locations defined by the kernel + +Equivalent to cat /proc/ioports on a running target""" + + def __init__(self): + super(LxIOPorts, self).__init__("lx-ioports", gdb.COMMAND_DATA) + + def invoke(self, arg, from_tty): + return show_lx_resources("ioport_resource") + +LxIOPorts() + + +# Mount namespace viewer +# /proc/mounts + +def info_opts(lst, opt): + opts = "" + for key, string in lst.items(): + if opt & key: + opts += string + return opts + + +FS_INFO = {constants.LX_MS_SYNCHRONOUS: ",sync", + constants.LX_MS_MANDLOCK: ",mand", + constants.LX_MS_DIRSYNC: ",dirsync", + constants.LX_MS_NOATIME: ",noatime", + constants.LX_MS_NODIRATIME: ",nodiratime"} + +MNT_INFO = {constants.LX_MNT_NOSUID: ",nosuid", + constants.LX_MNT_NODEV: ",nodev", + constants.LX_MNT_NOEXEC: ",noexec", + constants.LX_MNT_NOATIME: ",noatime", + constants.LX_MNT_NODIRATIME: ",nodiratime", + constants.LX_MNT_RELATIME: ",relatime"} + +mount_type = utils.CachedType("struct mount") +mount_ptr_type = mount_type.get_type().pointer() + + +class LxMounts(gdb.Command): + """Report the VFS mounts of the current process namespace. + +Equivalent to cat /proc/mounts on a running target +An integer value can be supplied to display the mount +values of that process namespace""" + + def __init__(self): + super(LxMounts, self).__init__("lx-mounts", gdb.COMMAND_DATA) + + # Equivalent to proc_namespace.c:show_vfsmnt + # However, that has the ability to call into s_op functions + # whereas we cannot and must make do with the information we can obtain. + def invoke(self, arg, from_tty): + argv = gdb.string_to_argv(arg) + if len(argv) >= 1: + try: + pid = int(argv[0]) + except: + raise gdb.GdbError("Provide a PID as integer value") + else: + pid = 1 + + task = tasks.get_task_by_pid(pid) + if not task: + raise gdb.GdbError("Couldn't find a process with PID {}" + .format(pid)) + + namespace = task['nsproxy']['mnt_ns'] + if not namespace: + raise gdb.GdbError("No namespace for current process") + + for vfs in lists.list_for_each_entry(namespace['list'], + mount_ptr_type, "mnt_list"): + devname = vfs['mnt_devname'].string() + devname = devname if devname else "none" + + pathname = "" + parent = vfs + while True: + mntpoint = parent['mnt_mountpoint'] + pathname = utils.dentry_name(mntpoint) + pathname + if (parent == parent['mnt_parent']): + break + parent = parent['mnt_parent'] + + if (pathname == ""): + pathname = "/" + + superblock = vfs['mnt']['mnt_sb'] + fstype = superblock['s_type']['name'].string() + s_flags = int(superblock['s_flags']) + m_flags = int(vfs['mnt']['mnt_flags']) + rd = "ro" if (s_flags & constants.LX_MS_RDONLY) else "rw" + + gdb.write( + "{} {} {} {}{}{} 0 0\n" + .format(devname, + pathname, + fstype, + rd, + info_opts(FS_INFO, s_flags), + info_opts(MNT_INFO, m_flags))) + +LxMounts() diff --git a/scripts/gdb/linux/radixtree.py b/scripts/gdb/linux/radixtree.py new file mode 100644 index 0000000..0fdef4e --- /dev/null +++ b/scripts/gdb/linux/radixtree.py @@ -0,0 +1,97 @@ +# +# gdb helper commands and functions for Linux kernel debugging +# +# Radix Tree Parser +# +# Copyright (c) 2016 Linaro Ltd +# +# Authors: +# Kieran Bingham <kieran.bingham@linaro.org> +# +# This work is licensed under the terms of the GNU GPL version 2. +# + +import gdb + +from linux import utils +from linux import constants + +radix_tree_root_type = utils.CachedType("struct radix_tree_root") +radix_tree_node_type = utils.CachedType("struct radix_tree_node") + + +def is_indirect_ptr(node): + long_type = utils.get_long_type() + return (node.cast(long_type) & constants.LX_RADIX_TREE_INDIRECT_PTR) + + +def indirect_to_ptr(node): + long_type = utils.get_long_type() + node_type = node.type + indirect_ptr = node.cast(long_type) & ~constants.LX_RADIX_TREE_INDIRECT_PTR + return indirect_ptr.cast(node_type) + + +def maxindex(height): + height = height & constants.LX_RADIX_TREE_HEIGHT_MASK + return gdb.parse_and_eval("height_to_maxindex["+str(height)+"]") + + +def lookup(root, index): + if root.type == radix_tree_root_type.get_type().pointer(): + root = root.dereference() + elif root.type != radix_tree_root_type.get_type(): + raise gdb.GdbError("Must be struct radix_tree_root not {}" + .format(root.type)) + + node = root['rnode'] + if node is 0: + return None + + if not (is_indirect_ptr(node)): + if (index > 0): + return None + return node + + node = indirect_to_ptr(node) + + height = node['path'] & constants.LX_RADIX_TREE_HEIGHT_MASK + if (index > maxindex(height)): + return None + + shift = (height-1) * constants.LX_RADIX_TREE_MAP_SHIFT + + while True: + new_index = (index >> shift) & constants.LX_RADIX_TREE_MAP_MASK + slot = node['slots'][new_index] + + node = slot.cast(node.type.pointer()).dereference() + if node is 0: + return None + + shift -= constants.LX_RADIX_TREE_MAP_SHIFT + height -= 1 + + if (height <= 0): + break + + return node + + +class LxRadixTree(gdb.Function): + """ Lookup and return a node from a RadixTree. + +$lx_radix_tree_lookup(root_node [, index]): Return the node at the given index. +If index is omitted, the root node is dereferenced and returned.""" + + def __init__(self): + super(LxRadixTree, self).__init__("lx_radix_tree_lookup") + + def invoke(self, root, index=0): + result = lookup(root, index) + if result is None: + raise gdb.GdbError("No entry in tree at index {}".format(index)) + + return result + +LxRadixTree() diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py index 862a4ae..1bf949c 100644 --- a/scripts/gdb/linux/tasks.py +++ b/scripts/gdb/linux/tasks.py @@ -114,3 +114,22 @@ variable.""" LxThreadInfoFunc() + + +class LxThreadInfoByPidFunc (gdb.Function): + """Calculate Linux thread_info from task variable found by pid + +$lx_thread_info_by_pid(PID): Given PID, return the corresponding thread_info +variable.""" + + def __init__(self): + super(LxThreadInfoByPidFunc, self).__init__("lx_thread_info_by_pid") + + def invoke(self, pid): + task = get_task_by_pid(pid) + if task: + return get_thread_info(task.dereference()) + else: + raise gdb.GdbError("No task of PID " + str(pid)) + +LxThreadInfoByPidFunc() diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py index 0893b32..5080587 100644 --- a/scripts/gdb/linux/utils.py +++ b/scripts/gdb/linux/utils.py @@ -87,11 +87,24 @@ def get_target_endianness(): return target_endianness +def read_memoryview(inf, start, length): + return memoryview(inf.read_memory(start, length)) + + def read_u16(buffer): + value = [0, 0] + + if type(buffer[0]) is str: + value[0] = ord(buffer[0]) + value[1] = ord(buffer[1]) + else: + value[0] = buffer[0] + value[1] = buffer[1] + if get_target_endianness() == LITTLE_ENDIAN: - return ord(buffer[0]) + (ord(buffer[1]) << 8) + return value[0] + (value[1] << 8) else: - return ord(buffer[1]) + (ord(buffer[0]) << 8) + return value[1] + (value[0] << 8) def read_u32(buffer): @@ -154,3 +167,18 @@ def get_gdbserver_type(): if gdbserver_type is not None and hasattr(gdb, 'events'): gdb.events.exited.connect(exit_handler) return gdbserver_type + + +def gdb_eval_or_none(expresssion): + try: + return gdb.parse_and_eval(expresssion) + except: + return None + + +def dentry_name(d): + parent = d['d_parent'] + if parent == d or parent == 0: + return "" + p = dentry_name(d['d_parent']) + "/" + return p + d['d_iname'].string() diff --git a/scripts/gdb/vmlinux-gdb.py b/scripts/gdb/vmlinux-gdb.py index d5943ec..3a80ad6 100644 --- a/scripts/gdb/vmlinux-gdb.py +++ b/scripts/gdb/vmlinux-gdb.py @@ -30,3 +30,5 @@ else: import linux.cpus import linux.lists import linux.proc + import linux.constants + import linux.radixtree |
