diff options
-rw-r--r-- | Documentation/prctl/no_new_privs.txt | 50 | ||||
-rw-r--r-- | arch/arm/kernel/vmlinux.lds.S | 2 | ||||
-rw-r--r-- | arch/arm/mm/mmu.c | 74 | ||||
-rw-r--r-- | arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 | ||||
-rw-r--r-- | arch/powerpc/xmon/xmon.c | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/drm_edid.c | 27 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/i915_dma.c | 37 | ||||
-rw-r--r-- | drivers/gpu/drm/radeon/radeon_gart.c | 13 | ||||
-rw-r--r-- | drivers/gpu/drm/radeon/radeon_gem.c | 10 | ||||
-rw-r--r-- | drivers/gpu/drm/radeon/si.c | 4 | ||||
-rw-r--r-- | drivers/md/md.c | 8 | ||||
-rw-r--r-- | drivers/md/multipath.c | 3 | ||||
-rw-r--r-- | drivers/md/raid1.c | 13 | ||||
-rw-r--r-- | drivers/md/raid10.c | 26 | ||||
-rw-r--r-- | drivers/md/raid5.c | 67 | ||||
-rw-r--r-- | security/security.c | 1 |
16 files changed, 277 insertions, 62 deletions
diff --git a/Documentation/prctl/no_new_privs.txt b/Documentation/prctl/no_new_privs.txt new file mode 100644 index 000000000000..cb705ec69abe --- /dev/null +++ b/Documentation/prctl/no_new_privs.txt @@ -0,0 +1,50 @@ +The execve system call can grant a newly-started program privileges that +its parent did not have. The most obvious examples are setuid/setgid +programs and file capabilities. To prevent the parent program from +gaining these privileges as well, the kernel and user code must be +careful to prevent the parent from doing anything that could subvert the +child. For example: + + - The dynamic loader handles LD_* environment variables differently if + a program is setuid. + + - chroot is disallowed to unprivileged processes, since it would allow + /etc/passwd to be replaced from the point of view of a process that + inherited chroot. + + - The exec code has special handling for ptrace. + +These are all ad-hoc fixes. The no_new_privs bit (since Linux 3.5) is a +new, generic mechanism to make it safe for a process to modify its +execution environment in a manner that persists across execve. Any task +can set no_new_privs. Once the bit is set, it is inherited across fork, +clone, and execve and cannot be unset. With no_new_privs set, execve +promises not to grant the privilege to do anything that could not have +been done without the execve call. For example, the setuid and setgid +bits will no longer change the uid or gid; file capabilities will not +add to the permitted set, and LSMs will not relax constraints after +execve. + +Note that no_new_privs does not prevent privilege changes that do not +involve execve. An appropriately privileged task can still call +setuid(2) and receive SCM_RIGHTS datagrams. + +There are two main use cases for no_new_privs so far: + + - Filters installed for the seccomp mode 2 sandbox persist across + execve and can change the behavior of newly-executed programs. + Unprivileged users are therefore only allowed to install such filters + if no_new_privs is set. + + - By itself, no_new_privs can be used to reduce the attack surface + available to an unprivileged user. If everything running with a + given uid has no_new_privs set, then that uid will be unable to + escalate its privileges by directly attacking setuid, setgid, and + fcap-using binaries; it will need to compromise something without the + no_new_privs bit set first. + +In the future, other potentially dangerous kernel features could become +available to unprivileged tasks if no_new_privs is set. In principle, +several options to unshare(2) and clone(2) would be safe when +no_new_privs is set, and no_new_privs + chroot is considerable less +dangerous than chroot by itself. diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 43a31fb06318..36ff15bbfdd4 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -183,7 +183,9 @@ SECTIONS } #endif +#ifdef CONFIG_SMP PERCPU_SECTION(L1_CACHE_BYTES) +#endif #ifdef CONFIG_XIP_KERNEL __data_loc = ALIGN(4); /* location in binary */ diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index e5dad60b558b..cf4528d51774 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -791,6 +791,79 @@ void __init iotable_init(struct map_desc *io_desc, int nr) } } +#ifndef CONFIG_ARM_LPAE + +/* + * The Linux PMD is made of two consecutive section entries covering 2MB + * (see definition in include/asm/pgtable-2level.h). However a call to + * create_mapping() may optimize static mappings by using individual + * 1MB section mappings. This leaves the actual PMD potentially half + * initialized if the top or bottom section entry isn't used, leaving it + * open to problems if a subsequent ioremap() or vmalloc() tries to use + * the virtual space left free by that unused section entry. + * + * Let's avoid the issue by inserting dummy vm entries covering the unused + * PMD halves once the static mappings are in place. + */ + +static void __init pmd_empty_section_gap(unsigned long addr) +{ + struct vm_struct *vm; + + vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm)); + vm->addr = (void *)addr; + vm->size = SECTION_SIZE; + vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING; + vm->caller = pmd_empty_section_gap; + vm_area_add_early(vm); +} + +static void __init fill_pmd_gaps(void) +{ + struct vm_struct *vm; + unsigned long addr, next = 0; + pmd_t *pmd; + + /* we're still single threaded hence no lock needed here */ + for (vm = vmlist; vm; vm = vm->next) { + if (!(vm->flags & VM_ARM_STATIC_MAPPING)) + continue; + addr = (unsigned long)vm->addr; + if (addr < next) + continue; + + /* + * Check if this vm starts on an odd section boundary. + * If so and the first section entry for this PMD is free + * then we block the corresponding virtual address. + */ + if ((addr & ~PMD_MASK) == SECTION_SIZE) { + pmd = pmd_off_k(addr); + if (pmd_none(*pmd)) + pmd_empty_section_gap(addr & PMD_MASK); + } + + /* + * Then check if this vm ends on an odd section boundary. + * If so and the second section entry for this PMD is empty + * then we block the corresponding virtual address. + */ + addr += vm->size; + if ((addr & ~PMD_MASK) == SECTION_SIZE) { + pmd = pmd_off_k(addr) + 1; + if (pmd_none(*pmd)) + pmd_empty_section_gap(addr); + } + + /* no need to look at any vm entry until we hit the next PMD */ + next = (addr + PMD_SIZE - 1) & PMD_MASK; + } +} + +#else +#define fill_pmd_gaps() do { } while (0) +#endif + static void * __initdata vmalloc_min = (void *)(VMALLOC_END - (240 << 20) - VMALLOC_OFFSET); @@ -1072,6 +1145,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc) */ if (mdesc->map_io) mdesc->map_io(); + fill_pmd_gaps(); /* * Finally flush the caches and tlb to ensure that we're in a diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index a84aafce2a12..a1044f43becd 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -810,7 +810,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) lwz r3,VCORE_NAPPING_THREADS(r5) lwz r4,VCPU_PTID(r9) li r0,1 - sldi r0,r0,r4 + sld r0,r0,r4 andc. r3,r3,r0 /* no sense IPI'ing ourselves */ beq 43f mulli r4,r4,PACA_SIZE /* get paca for thread 0 */ diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 0f3ab06d2222..eab3492a45c5 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -971,7 +971,7 @@ static int cpu_cmd(void) /* print cpus waiting or in xmon */ printf("cpus stopped:"); count = 0; - for (cpu = 0; cpu < NR_CPUS; ++cpu) { + for_each_possible_cpu(cpu) { if (cpumask_test_cpu(cpu, &cpus_in_xmon)) { if (count == 0) printf(" %x", cpu); diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 5873e481e5d2..a8743c399e83 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -1039,6 +1039,24 @@ mode_in_range(const struct drm_display_mode *mode, struct edid *edid, return true; } +static bool valid_inferred_mode(const struct drm_connector *connector, + const struct drm_display_mode *mode) +{ + struct drm_display_mode *m; + bool ok = false; + + list_for_each_entry(m, &connector->probed_modes, head) { + if (mode->hdisplay == m->hdisplay && + mode->vdisplay == m->vdisplay && + drm_mode_vrefresh(mode) == drm_mode_vrefresh(m)) + return false; /* duplicated */ + if (mode->hdisplay <= m->hdisplay && + mode->vdisplay <= m->vdisplay) + ok = true; + } + return ok; +} + static int drm_dmt_modes_for_range(struct drm_connector *connector, struct edid *edid, struct detailed_timing *timing) @@ -1048,7 +1066,8 @@ drm_dmt_modes_for_range(struct drm_connector *connector, struct edid *edid, struct drm_device *dev = connector->dev; for (i = 0; i < drm_num_dmt_modes; i++) { - if (mode_in_range(drm_dmt_modes + i, edid, timing)) { + if (mode_in_range(drm_dmt_modes + i, edid, timing) && + valid_inferred_mode(connector, drm_dmt_modes + i)) { newmode = drm_mode_duplicate(dev, &drm_dmt_modes[i]); if (newmode) { drm_mode_probed_add(connector, newmode); @@ -1088,7 +1107,8 @@ drm_gtf_modes_for_range(struct drm_connector *connector, struct edid *edid, return modes; fixup_mode_1366x768(newmode); - if (!mode_in_range(newmode, edid, timing)) { + if (!mode_in_range(newmode, edid, timing) || + !valid_inferred_mode(connector, newmode)) { drm_mode_destroy(dev, newmode); continue; } @@ -1116,7 +1136,8 @@ drm_cvt_modes_for_range(struct drm_connector *connector, struct edid *edid, return modes; fixup_mode_1366x768(newmode); - if (!mode_in_range(newmode, edid, timing)) { + if (!mode_in_range(newmode, edid, timing) || + !valid_inferred_mode(connector, newmode)) { drm_mode_destroy(dev, newmode); continue; } diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index f94792626b94..36822b924eb1 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1401,6 +1401,27 @@ i915_mtrr_setup(struct drm_i915_private *dev_priv, unsigned long base, } } +static void i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv) +{ + struct apertures_struct *ap; + struct pci_dev *pdev = dev_priv->dev->pdev; + bool primary; + + ap = alloc_apertures(1); + if (!ap) + return; + + ap->ranges[0].base = dev_priv->dev->agp->base; + ap->ranges[0].size = + dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT; + primary = + pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; + + remove_conflicting_framebuffers(ap, "inteldrmfb", primary); + + kfree(ap); +} + /** * i915_driver_load - setup chip and create an initial config * @dev: DRM device @@ -1446,6 +1467,15 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) goto free_priv; } + dev_priv->mm.gtt = intel_gtt_get(); + if (!dev_priv->mm.gtt) { + DRM_ERROR("Failed to initialize GTT\n"); + ret = -ENODEV; + goto put_bridge; + } + + i915_kick_out_firmware_fb(dev_priv); + pci_set_master(dev->pdev); /* overlay on gen2 is broken and can't address above 1G */ @@ -1471,13 +1501,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) goto put_bridge; } - dev_priv->mm.gtt = intel_gtt_get(); - if (!dev_priv->mm.gtt) { - DRM_ERROR("Failed to initialize GTT\n"); - ret = -ENODEV; - goto out_rmmap; - } - aperture_size = dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT; dev_priv->mm.gtt_mapping = diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c index 59d44937dd9f..84b648a7ddd8 100644 --- a/drivers/gpu/drm/radeon/radeon_gart.c +++ b/drivers/gpu/drm/radeon/radeon_gart.c @@ -289,8 +289,9 @@ int radeon_vm_manager_init(struct radeon_device *rdev) rdev->vm_manager.enabled = false; /* mark first vm as always in use, it's the system one */ + /* allocate enough for 2 full VM pts */ r = radeon_sa_bo_manager_init(rdev, &rdev->vm_manager.sa_manager, - rdev->vm_manager.max_pfn * 8, + rdev->vm_manager.max_pfn * 8 * 2, RADEON_GEM_DOMAIN_VRAM); if (r) { dev_err(rdev->dev, "failed to allocate vm bo (%dKB)\n", @@ -633,7 +634,15 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm) mutex_init(&vm->mutex); INIT_LIST_HEAD(&vm->list); INIT_LIST_HEAD(&vm->va); - vm->last_pfn = 0; + /* SI requires equal sized PTs for all VMs, so always set + * last_pfn to max_pfn. cayman allows variable sized + * pts so we can grow then as needed. Once we switch + * to two level pts we can unify this again. + */ + if (rdev->family >= CHIP_TAHITI) + vm->last_pfn = rdev->vm_manager.max_pfn; + else + vm->last_pfn = 0; /* map the ib pool buffer at 0 in virtual address space, set * read only */ diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index f28bd4b7ef98..21ec9f5653ce 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -292,6 +292,7 @@ int radeon_gem_mmap_ioctl(struct drm_device *dev, void *data, int radeon_gem_busy_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { + struct radeon_device *rdev = dev->dev_private; struct drm_radeon_gem_busy *args = data; struct drm_gem_object *gobj; struct radeon_bo *robj; @@ -317,13 +318,14 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data, break; } drm_gem_object_unreference_unlocked(gobj); - r = radeon_gem_handle_lockup(robj->rdev, r); + r = radeon_gem_handle_lockup(rdev, r); return r; } int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { + struct radeon_device *rdev = dev->dev_private; struct drm_radeon_gem_wait_idle *args = data; struct drm_gem_object *gobj; struct radeon_bo *robj; @@ -336,10 +338,10 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data, robj = gem_to_radeon_bo(gobj); r = radeon_bo_wait(robj, NULL, false); /* callback hw specific functions if any */ - if (robj->rdev->asic->ioctl_wait_idle) - robj->rdev->asic->ioctl_wait_idle(robj->rdev, robj); + if (rdev->asic->ioctl_wait_idle) + robj->rdev->asic->ioctl_wait_idle(rdev, robj); drm_gem_object_unreference_unlocked(gobj); - r = radeon_gem_handle_lockup(robj->rdev, r); + r = radeon_gem_handle_lockup(rdev, r); return r; } diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index c7b61f16ecfd..0b0279291a73 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -2365,12 +2365,12 @@ int si_pcie_gart_enable(struct radeon_device *rdev) WREG32(0x15DC, 0); /* empty context1-15 */ - /* FIXME start with 1G, once using 2 level pt switch to full + /* FIXME start with 4G, once using 2 level pt switch to full * vm size space */ /* set vm size, must be a multiple of 4 */ WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0); - WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, (1 << 30) / RADEON_GPU_PAGE_SIZE); + WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn); for (i = 1; i < 16; i++) { if (i < 8) WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2), diff --git a/drivers/md/md.c b/drivers/md/md.c index 1c2f9048e1ae..a4c219e3c859 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5784,8 +5784,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info) super_types[mddev->major_version]. validate_super(mddev, rdev); if ((info->state & (1<<MD_DISK_SYNC)) && - (!test_bit(In_sync, &rdev->flags) || - rdev->raid_disk != info->raid_disk)) { + rdev->raid_disk != info->raid_disk) { /* This was a hot-add request, but events doesn't * match, so reject it. */ @@ -6751,7 +6750,7 @@ struct md_thread *md_register_thread(void (*run) (struct mddev *), struct mddev thread->tsk = kthread_run(md_thread, thread, "%s_%s", mdname(thread->mddev), - name ?: mddev->pers->name); + name); if (IS_ERR(thread->tsk)) { kfree(thread); return NULL; @@ -7298,6 +7297,7 @@ void md_do_sync(struct mddev *mddev) int skipped = 0; struct md_rdev *rdev; char *desc; + struct blk_plug plug; /* just incase thread restarts... */ if (test_bit(MD_RECOVERY_DONE, &mddev->recovery)) @@ -7447,6 +7447,7 @@ void md_do_sync(struct mddev *mddev) } mddev->curr_resync_completed = j; + blk_start_plug(&plug); while (j < max_sectors) { sector_t sectors; @@ -7552,6 +7553,7 @@ void md_do_sync(struct mddev *mddev) * this also signals 'finished resyncing' to md_stop */ out: + blk_finish_plug(&plug); wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); /* tell personality that we are finished */ diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 9339e67fcc79..61a1833ebaf3 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -474,7 +474,8 @@ static int multipath_run (struct mddev *mddev) } { - mddev->thread = md_register_thread(multipathd, mddev, NULL); + mddev->thread = md_register_thread(multipathd, mddev, + "multipath"); if (!mddev->thread) { printk(KERN_ERR "multipath: couldn't allocate thread" " for %s\n", mdname(mddev)); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index a9c7981ddd24..8c2754f835ef 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -517,8 +517,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect int bad_sectors; int disk = start_disk + i; - if (disk >= conf->raid_disks) - disk -= conf->raid_disks; + if (disk >= conf->raid_disks * 2) + disk -= conf->raid_disks * 2; rdev = rcu_dereference(conf->mirrors[disk].rdev); if (r1_bio->bios[disk] == IO_BLOCKED @@ -883,7 +883,6 @@ static void make_request(struct mddev *mddev, struct bio * bio) const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA)); struct md_rdev *blocked_rdev; - int plugged; int first_clone; int sectors_handled; int max_sectors; @@ -1034,7 +1033,6 @@ read_again: * the bad blocks. Each set of writes gets it's own r1bio * with a set of bios attached. */ - plugged = mddev_check_plugged(mddev); disks = conf->raid_disks * 2; retry_write: @@ -1191,6 +1189,8 @@ read_again: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev)) + md_wakeup_thread(mddev->thread); } /* Mustn't call r1_bio_write_done before this next test, * as it could result in the bio being freed. @@ -1213,9 +1213,6 @@ read_again: /* In case raid1d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - - if (do_sync || !bitmap || !plugged) - md_wakeup_thread(mddev->thread); } static void status(struct seq_file *seq, struct mddev *mddev) @@ -2621,7 +2618,7 @@ static struct r1conf *setup_conf(struct mddev *mddev) goto abort; } err = -ENOMEM; - conf->thread = md_register_thread(raid1d, mddev, NULL); + conf->thread = md_register_thread(raid1d, mddev, "raid1"); if (!conf->thread) { printk(KERN_ERR "md/raid1:%s: couldn't allocate thread\n", diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 99ae6068e456..acf5a828c7e1 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1039,7 +1039,6 @@ static void make_request(struct mddev *mddev, struct bio * bio) const unsigned long do_fua = (bio->bi_rw & REQ_FUA); unsigned long flags; struct md_rdev *blocked_rdev; - int plugged; int sectors_handled; int max_sectors; int sectors; @@ -1239,7 +1238,6 @@ read_again: * of r10_bios is recored in bio->bi_phys_segments just as with * the read case. */ - plugged = mddev_check_plugged(mddev); r10_bio->read_slot = -1; /* make sure repl_bio gets freed */ raid10_find_phys(conf, r10_bio); @@ -1396,6 +1394,8 @@ retry_write: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev, 0, 0)) + md_wakeup_thread(mddev->thread); if (!r10_bio->devs[i].repl_bio) continue; @@ -1423,6 +1423,8 @@ retry_write: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev)) + md_wakeup_thread(mddev->thread); } /* Don't remove the bias on 'remaining' (one_write_done) until @@ -1448,9 +1450,6 @@ retry_write: /* In case raid10d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - - if (do_sync || !mddev->bitmap || !plugged) - md_wakeup_thread(mddev->thread); } static void status(struct seq_file *seq, struct mddev *mddev) @@ -2310,7 +2309,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 if (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s<<9, conf->tmppage, WRITE) + s, conf->tmppage, WRITE) == 0) { /* Well, this device is dead */ printk(KERN_NOTICE @@ -2349,7 +2348,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 switch (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s<<9, conf->tmppage, + s, conf->tmppage, READ)) { case 0: /* Well, this device is dead */ @@ -2512,7 +2511,7 @@ read_more: slot = r10_bio->read_slot; printk_ratelimited( KERN_ERR - "md/raid10:%s: %s: redirecting" + "md/raid10:%s: %s: redirecting " "sector %llu to another mirror\n", mdname(mddev), bdevname(rdev->bdev, b), @@ -2661,7 +2660,8 @@ static void raid10d(struct mddev *mddev) blk_start_plug(&plug); for (;;) { - flush_pending_writes(conf); + if (atomic_read(&mddev->plug_cnt) == 0) + flush_pending_writes(conf); spin_lock_irqsave(&conf->device_lock, flags); if (list_empty(head)) { @@ -2890,6 +2890,12 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, /* want to reconstruct this device */ rb2 = r10_bio; sect = raid10_find_virt(conf, sector_nr, i); + if (sect >= mddev->resync_max_sectors) { + /* last stripe is not complete - don't + * try to recover this sector. + */ + continue; + } /* Unless we are doing a full sync, or a replacement * we only need to recover the block if it is set in * the bitmap @@ -3421,7 +3427,7 @@ static struct r10conf *setup_conf(struct mddev *mddev) spin_lock_init(&conf->resync_lock); init_waitqueue_head(&conf->wait_barrier); - conf->thread = md_register_thread(raid10d, mddev, NULL); + conf->thread = md_register_thread(raid10d, mddev, "raid10"); if (!conf->thread) goto out; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index d26767246d26..04348d76bb30 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -196,12 +196,14 @@ static void __release_stripe(struct r5conf *conf, struct stripe_head *sh) BUG_ON(!list_empty(&sh->lru)); BUG_ON(atomic_read(&conf->active_stripes)==0); if (test_bit(STRIPE_HANDLE, &sh->state)) { - if (test_bit(STRIPE_DELAYED, &sh->state)) + if (test_bit(STRIPE_DELAYED, &sh->state) && + !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) list_add_tail(&sh->lru, &conf->delayed_list); else if (test_bit(STRIPE_BIT_DELAY, &sh->state) && sh->bm_seq - conf->seq_write > 0) list_add_tail(&sh->lru, &conf->bitmap_list); else { + clear_bit(STRIPE_DELAYED, &sh->state); clear_bit(STRIPE_BIT_DELAY, &sh->state); list_add_tail(&sh->lru, &conf->handle_list); } @@ -606,6 +608,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) * a chance*/ md_check_recovery(conf->mddev); } + /* + * Because md_wait_for_blocked_rdev + * will dec nr_pending, we must + * increment it first. + */ + atomic_inc(&rdev->nr_pending); md_wait_for_blocked_rdev(rdev, conf->mddev); } else { /* Acknowledged bad block - skip the write */ @@ -1737,6 +1745,7 @@ static void raid5_end_read_request(struct bio * bi, int error) } else { const char *bdn = bdevname(rdev->bdev, b); int retry = 0; + int set_bad = 0; clear_bit(R5_UPTODATE, &sh->dev[i].flags); atomic_inc(&rdev->read_errors); @@ -1748,7 +1757,8 @@ static void raid5_end_read_request(struct bio * bi, int error) mdname(conf->mddev), (unsigned long long)s, bdn); - else if (conf->mddev->degraded >= conf->max_degraded) + else if (conf->mddev->degraded >= conf->max_degraded) { + set_bad = 1; printk_ratelimited( KERN_WARNING "md/raid:%s: read error not correctable " @@ -1756,8 +1766,9 @@ static void raid5_end_read_request(struct bio * bi, int error) mdname(conf->mddev), (unsigned long long)s, bdn); - else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) + } else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) { /* Oh, no!!! */ + set_bad = 1; printk_ratelimited( KERN_WARNING "md/raid:%s: read error NOT corrected!! " @@ -1765,7 +1776,7 @@ static void raid5_end_read_request(struct bio * bi, int error) mdname(conf->mddev), (unsigned long long)s, bdn); - else if (atomic_read(&rdev->read_errors) + } else if (atomic_read(&rdev->read_errors) > conf->max_nr_stripes) printk(KERN_WARNING "md/raid:%s: Too many read errors, failing device %s.\n", @@ -1777,7 +1788,11 @@ static void raid5_end_read_request(struct bio * bi, int error) else { clear_bit(R5_ReadError, &sh->dev[i].flags); clear_bit(R5_ReWrite, &sh->dev[i].flags); - md_error(conf->mddev, rdev); + if (!(set_bad + && test_bit(In_sync, &rdev->flags) + && rdev_set_badblocks( + rdev, sh->sector, STRIPE_SECTORS, 0))) + md_error(conf->mddev, rdev); } } rdev_dec_pending(rdev, conf->mddev); @@ -3582,8 +3597,18 @@ static void handle_stripe(struct stripe_head *sh) finish: /* wait for this device to become unblocked */ - if (conf->mddev->external && unlikely(s.blocked_rdev)) - md_wait_for_blocked_rdev(s.blocked_rdev, conf->mddev); + if (unlikely(s.blocked_rdev)) { + if (conf->mddev->external) + md_wait_for_blocked_rdev(s.blocked_rdev, + conf->mddev); + else + /* Internal metadata will immediately + * be written by raid5d, so we don't + * need to wait here. + */ + rdev_dec_pending(s.blocked_rdev, + conf->mddev); + } if (s.handle_bad_blocks) for (i = disks; i--; ) { @@ -3881,8 +3906,6 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) raid_bio->bi_next = (void*)rdev; align_bi->bi_bdev = rdev->bdev; align_bi->bi_flags &= ~(1 << BIO_SEG_VALID); - /* No reshape active, so we can trust rdev->data_offset */ - align_bi->bi_sector += rdev->data_offset; if (!bio_fits_rdev(align_bi) || is_badblock(rdev, align_bi->bi_sector, align_bi->bi_size>>9, @@ -3893,6 +3916,9 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) return 0; } + /* No reshape active, so we can trust rdev->data_offset */ + align_bi->bi_sector += rdev->data_offset; + spin_lock_irq(&conf->device_lock); wait_event_lock_irq(conf->wait_for_stripe, conf->quiesce == 0, @@ -3971,7 +3997,6 @@ static void make_request(struct mddev *mddev, struct bio * bi) struct stripe_head *sh; const int rw = bio_data_dir(bi); int remaining; - int plugged; if (unlikely(bi->bi_rw & REQ_FLUSH)) { md_flush_request(mddev, bi); @@ -3990,7 +4015,6 @@ static void make_request(struct mddev *mddev, struct bio * bi) bi->bi_next = NULL; bi->bi_phys_segments = 1; /* over-loaded to count active stripes */ - plugged = mddev_check_plugged(mddev); for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) { DEFINE_WAIT(w); int previous; @@ -4092,6 +4116,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) if ((bi->bi_rw & REQ_SYNC) && !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); + mddev_check_plugged(mddev); release_stripe(sh); } else { /* cannot get stripe for read-ahead, just give-up */ @@ -4099,10 +4124,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) finish_wait(&conf->wait_for_overlap, &w); break; } - } - if (!plugged) - md_wakeup_thread(mddev->thread); spin_lock_irq(&conf->device_lock); remaining = raid5_dec_bi_phys_segments(bi); @@ -4823,6 +4845,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) int raid_disk, memory, max_disks; struct md_rdev *rdev; struct disk_info *disk; + char pers_name[6]; if (mddev->new_level != 5 && mddev->new_level != 4 @@ -4946,7 +4969,8 @@ static struct r5conf *setup_conf(struct mddev *mddev) printk(KERN_INFO "md/raid:%s: allocated %dkB\n", mdname(mddev), memory); - conf->thread = md_register_thread(raid5d, mddev, NULL); + sprintf(pers_name, "raid%d", mddev->new_level); + conf->thread = md_register_thread(raid5d, mddev, pers_name); if (!conf->thread) { printk(KERN_ERR "md/raid:%s: couldn't allocate thread.\n", @@ -5465,10 +5489,9 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk >= 0 && rdev->saved_raid_disk >= first && conf->disks[rdev->saved_raid_disk].rdev == NULL) - disk = rdev->saved_raid_disk; - else - disk = first; - for ( ; disk <= last ; disk++) { + first = rdev->saved_raid_disk; + + for (disk = first; disk <= last; disk++) { p = conf->disks + disk; if (p->rdev == NULL) { clear_bit(In_sync, &rdev->flags); @@ -5477,8 +5500,11 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk != disk) conf->fullsync = 1; rcu_assign_pointer(p->rdev, rdev); - break; + goto out; } + } + for (disk = first; disk <= last; disk++) { + p = conf->disks + disk; if (test_bit(WantReplacement, &p->rdev->flags) && p->replacement == NULL) { clear_bit(In_sync, &rdev->flags); @@ -5490,6 +5516,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } } +out: print_raid5_conf(conf); return err; } diff --git a/security/security.c b/security/security.c index 3efc9b12aef4..860aeb349cb3 100644 --- a/security/security.c +++ b/security/security.c @@ -23,6 +23,7 @@ #include <linux/mman.h> #include <linux/mount.h> #include <linux/personality.h> +#include <linux/backing-dev.h> #include <net/flow.h> #define MAX_LSM_EVM_XATTR 2 |