July 2018 - Linux-stable-mirror

[PATCH] powerpc/fadump: handle crash memory ranges array overflow

by Hari Bathini

Crash memory ranges is an array of memory ranges of the crashing kernel to be exported as a dump via /proc/vmcore file. The size of the array is set based on INIT_MEMBLOCK_REGIONS, which works alright in most cases where memblock memory regions count is less than INIT_MEMBLOCK_REGIONS value. But this count can grow beyond INIT_MEMBLOCK_REGIONS value since commit 142b45a72e22 ("memblock: Add array resizing support"). On large memory systems with a few DLPAR operations, the memblock memory regions count could be larger than INIT_MEMBLOCK_REGIONS value. On such systems, registering fadump results in crash or other system failures like below: task: c00007f39a290010 ti: c00000000b738000 task.ti: c00000000b738000 NIP: c000000000047df4 LR: c0000000000f9e58 CTR: c00000000010f180 REGS: c00000000b73b570 TRAP: 0300 Tainted: G L X (4.4.140+) MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 22004484 XER: 20000000 CFAR: c000000000008500 DAR: 000007a450000000 DSISR: 40000000 SOFTE: 0 GPR00: c0000000000f9e58 c00000000b73b7f0 c000000000f09a00 000000000000001a GPR04: c00007f3bf774c90 0000000000000004 c000000000eb9a00 0000000000000800 GPR08: 0000000000000804 000007a450000000 c000000000fa9a00 c00007ffb169ca20 GPR12: 0000000022004482 c00000000fa12c00 c00007f3a0ea97a8 0000000000000000 GPR16: c00007f3a0ea9a50 c00000000b73bd60 0000000000000118 000000000001fe80 GPR20: 0000000000000118 0000000000000000 c000000000b8c980 00000000000000d0 GPR24: 000007ffb0b10000 c00007ffb169c980 0000000000000000 c000000000b8c980 GPR28: 0000000000000004 c00007ffb169c980 000000000000001a c00007ffb169c980 NIP [c000000000047df4] smp_send_reschedule+0x24/0x80 LR [c0000000000f9e58] resched_curr+0x138/0x160 Call Trace: [c00000000b73b7f0] [c0000000000f9e58] resched_curr+0x138/0x160 (unreliable) [c00000000b73b820] [c0000000000fb538] check_preempt_curr+0xc8/0xf0 [c00000000b73b850] [c0000000000fb598] ttwu_do_wakeup+0x38/0x150 [c00000000b73b890] [c0000000000fc9c4] try_to_wake_up+0x224/0x4d0 [c00000000b73b900] [c00000000011ef34] __wake_up_common+0x94/0x100 [c00000000b73b960] [c00000000034a78c] ep_poll_callback+0xac/0x1c0 [c00000000b73b9b0] [c00000000011ef34] __wake_up_common+0x94/0x100 [c00000000b73ba10] [c00000000011f810] __wake_up_sync_key+0x70/0xa0 [c00000000b73ba60] [c00000000067c3e8] sock_def_readable+0x58/0xa0 [c00000000b73ba90] [c0000000007848ac] unix_stream_sendmsg+0x2dc/0x4c0 [c00000000b73bb70] [c000000000675a38] sock_sendmsg+0x68/0xa0 [c00000000b73bba0] [c00000000067673c] ___sys_sendmsg+0x2cc/0x2e0 [c00000000b73bd30] [c000000000677dbc] __sys_sendmsg+0x5c/0xc0 [c00000000b73bdd0] [c0000000006789bc] SyS_socketcall+0x36c/0x3f0 [c00000000b73be30] [c000000000009488] system_call+0x3c/0x100 Instruction dump: 4e800020 60000000 60420000 3c4c00ec 38421c30 7c0802a6 f8010010 60000000 3d42000a e92ab420 2fa90000 4dde0020 <e9290000> 2fa90000 419e0044 7c0802a6 ---[ end trace a6d1dd4bab5f8253 ]--- as array index overflow is not checked for while setting up crash memory ranges causing memory corruption. To resolve this issue, resize crash memory ranges array on hitting array size limit. But without a hard limit on the number of crash memory ranges, there is a possibility of program headers count overflow in the /proc/vmcore ELF file while exporting each of this memory ranges as PT_LOAD segments. To reduce the likelihood of such scenario, fold adjacent memory ranges to minimize the total number of crash memory ranges. Fixes: 2df173d9e85d ("fadump: Initialize elfcore header and add PT_LOAD program headers.") Cc: stable(a)vger.kernel.org Cc: Mahesh Salgaonkar <mahesh(a)linux.vnet.ibm.com> Signed-off-by: Hari Bathini <hbathini(a)linux.ibm.com> --- arch/powerpc/include/asm/fadump.h | 2 + arch/powerpc/kernel/fadump.c | 63 ++++++++++++++++++++++++++++++++++--- 2 files changed, 59 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h index 5a23010..ff708b3 100644 --- a/arch/powerpc/include/asm/fadump.h +++ b/arch/powerpc/include/asm/fadump.h @@ -196,7 +196,7 @@ struct fadump_crash_info_header { }; /* Crash memory ranges */ -#define INIT_CRASHMEM_RANGES (INIT_MEMBLOCK_REGIONS + 2) +#define INIT_CRASHMEM_RANGES INIT_MEMBLOCK_REGIONS struct fad_crash_memory_ranges { unsigned long long base; diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 07e8396..1c1df4f 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -47,7 +47,9 @@ static struct fadump_mem_struct fdm; static const struct fadump_mem_struct *fdm_active; static DEFINE_MUTEX(fadump_mutex); -struct fad_crash_memory_ranges crash_memory_ranges[INIT_CRASHMEM_RANGES]; +struct fad_crash_memory_ranges init_crash_memory_ranges[INIT_CRASHMEM_RANGES]; +int max_crash_mem_ranges = INIT_CRASHMEM_RANGES; +struct fad_crash_memory_ranges *crash_memory_ranges = init_crash_memory_ranges; int crash_mem_ranges; /* Scan the Firmware Assisted dump configuration details. */ @@ -871,14 +873,65 @@ static int __init process_fadump(const struct fadump_mem_struct *fdm_active) static inline void fadump_add_crash_memory(unsigned long long base, unsigned long long end) { + u64 start, size; + bool is_adjacent = false; + if (base == end) return; + /* + * Fold adjacent memory ranges to bring down the memory ranges/ + * PT_LOAD segments count. + */ + if (crash_mem_ranges) { + start = crash_memory_ranges[crash_mem_ranges-1].base; + size = crash_memory_ranges[crash_mem_ranges-1].size; + + if ((start + size) == base) + is_adjacent = true; + } + + if (!is_adjacent) { + /* resize the array on reaching the limit */ + if (crash_mem_ranges == max_crash_mem_ranges) { + u64 old_size, new_max; + struct fad_crash_memory_ranges *new_array; + + old_size = max_crash_mem_ranges; + old_size *= sizeof(struct fad_crash_memory_ranges); + + new_max = max_crash_mem_ranges + INIT_CRASHMEM_RANGES; + size = new_max * sizeof(struct fad_crash_memory_ranges); + + pr_debug("Resizing crash memory ranges count from %d to %d\n", + max_crash_mem_ranges, new_max); + + new_array = kmalloc(size, GFP_KERNEL); + if (new_array == NULL) { + pr_warn("Insufficient memory for setting up crash memory ranges\n"); + return; + } + + /* + * Copy the old memory ranges into the new array before + * free'ing it. + */ + memcpy(new_array, crash_memory_ranges, old_size); + if (crash_memory_ranges != init_crash_memory_ranges) + kfree(crash_memory_ranges); + + crash_memory_ranges = new_array; + max_crash_mem_ranges = new_max; + } + start = base; + crash_memory_ranges[crash_mem_ranges].base = start; + crash_mem_ranges++; + } + + crash_memory_ranges[crash_mem_ranges-1].size = (end - start); + pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n", - crash_mem_ranges, base, end - 1, (end - base)); - crash_memory_ranges[crash_mem_ranges].base = base; - crash_memory_ranges[crash_mem_ranges].size = end - base; - crash_mem_ranges++; + (crash_mem_ranges - 1), start, end - 1, (end - start)); } static void fadump_exclude_reserved_area(unsigned long long start,

6 years, 6 months

4
3
0 0

[PATCH] drm/vc4: Fix the "no scaling" case on multi-planar YUV formats

by Boris Brezillon

When there's no scaling requested ->is_unity should be true no matter the format. Also, when no scaling is requested and we have a multi-planar YUV format, we should leave ->y_scaling[0] to VC4_SCALING_NONE and only set ->x_scaling[0] to VC4_SCALING_PPF. Doing this fixes an hardly visible artifact (seen when using modetest and a rather big overlay plane in YUV420). Fixes: fc04023fafec ("drm/vc4: Add support for YUV planes.") Cc: <stable(a)vger.kernel.org> Signed-off-by: Boris Brezillon <boris.brezillon(a)bootlin.com> --- drivers/gpu/drm/vc4/vc4_plane.c | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index cfb50fedfa2b..a3275fa66b7b 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -297,6 +297,9 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) vc4_state->y_scaling[0] = vc4_get_scaling_mode(vc4_state->src_h[0], vc4_state->crtc_h); + vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE && + vc4_state->y_scaling[0] == VC4_SCALING_NONE); + if (num_planes > 1) { vc4_state->is_yuv = true; @@ -312,24 +315,17 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) vc4_get_scaling_mode(vc4_state->src_h[1], vc4_state->crtc_h); - /* YUV conversion requires that scaling be enabled, - * even on a plane that's otherwise 1:1. Choose TPZ - * for simplicity. + /* YUV conversion requires that horizontal scaling be enabled, + * even on a plane that's otherwise 1:1. Looks like only PPF + * works in that case, so let's pick that one. */ - if (vc4_state->x_scaling[0] == VC4_SCALING_NONE) - vc4_state->x_scaling[0] = VC4_SCALING_TPZ; - if (vc4_state->y_scaling[0] == VC4_SCALING_NONE) - vc4_state->y_scaling[0] = VC4_SCALING_TPZ; + if (vc4_state->is_unity) + vc4_state->x_scaling[0] = VC4_SCALING_PPF; } else { vc4_state->x_scaling[1] = VC4_SCALING_NONE; vc4_state->y_scaling[1] = VC4_SCALING_NONE; } - vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE && - vc4_state->y_scaling[0] == VC4_SCALING_NONE && - vc4_state->x_scaling[1] == VC4_SCALING_NONE && - vc4_state->y_scaling[1] == VC4_SCALING_NONE); - /* No configuring scaling on the cursor plane, since it gets non-vblank-synced updates, and scaling requires requires LBM changes which have to be vblank-synced. @@ -672,7 +668,10 @@ static int vc4_plane_mode_set(struct drm_plane *plane, vc4_dlist_write(vc4_state, SCALER_CSC2_ITR_R_601_5); } - if (!vc4_state->is_unity) { + if (vc4_state->x_scaling[0] != VC4_SCALING_NONE || + vc4_state->x_scaling[1] != VC4_SCALING_NONE || + vc4_state->y_scaling[0] != VC4_SCALING_NONE || + vc4_state->y_scaling[1] != VC4_SCALING_NONE) { /* LBM Base Address. */ if (vc4_state->y_scaling[0] != VC4_SCALING_NONE || vc4_state->y_scaling[1] != VC4_SCALING_NONE) { -- 2.14.1

6 years, 6 months

2
2
0 0

[PATCH 2/2] Avoid that SCSI device removal through sysfs triggers a deadlock

by Bart Van Assche

A long time ago the unfortunate decision was taken to add a self- deletion attribute to the sysfs SCSI device directory. That decision was unfortunate because self-deletion is really tricky. We can't drop that attribute because widely used user space software depends on it, namely the rescan-scsi-bus.sh script. Hence this patch that avoids that writing into that attribute triggers a deadlock. See also commit 7973cbd9fbd9 ("[PATCH] add sysfs attributes to scan and delete scsi_devices"). This patch avoids that self-removal triggers the following deadlock: ====================================================== WARNING: possible circular locking dependency detected 4.18.0-rc2-dbg+ #5 Not tainted ------------------------------------------------------ modprobe/6539 is trying to acquire lock: 000000008323c4cd (kn->count#202){++++}, at: kernfs_remove_by_name_ns+0x45/0x90 but task is already holding lock: 00000000a6ec2c69 (&shost->scan_mutex){+.+.}, at: scsi_remove_host+0x21/0x150 [scsi_mod] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&shost->scan_mutex){+.+.}: __mutex_lock+0xfe/0xc70 mutex_lock_nested+0x1b/0x20 scsi_remove_device+0x26/0x40 [scsi_mod] sdev_store_delete+0x27/0x30 [scsi_mod] dev_attr_store+0x3e/0x50 sysfs_kf_write+0x87/0xa0 kernfs_fop_write+0x190/0x230 __vfs_write+0xd2/0x3b0 vfs_write+0x101/0x270 ksys_write+0xab/0x120 __x64_sys_write+0x43/0x50 do_syscall_64+0x77/0x230 entry_SYSCALL_64_after_hwframe+0x49/0xbe -> #0 (kn->count#202){++++}: lock_acquire+0xd2/0x260 __kernfs_remove+0x424/0x4a0 kernfs_remove_by_name_ns+0x45/0x90 remove_files.isra.1+0x3a/0x90 sysfs_remove_group+0x5c/0xc0 sysfs_remove_groups+0x39/0x60 device_remove_attrs+0x82/0xb0 device_del+0x251/0x580 __scsi_remove_device+0x19f/0x1d0 [scsi_mod] scsi_forget_host+0x37/0xb0 [scsi_mod] scsi_remove_host+0x9b/0x150 [scsi_mod] sdebug_driver_remove+0x4b/0x150 [scsi_debug] device_release_driver_internal+0x241/0x360 device_release_driver+0x12/0x20 bus_remove_device+0x1bc/0x290 device_del+0x259/0x580 device_unregister+0x1a/0x70 sdebug_remove_adapter+0x8b/0xf0 [scsi_debug] scsi_debug_exit+0x76/0xe8 [scsi_debug] __x64_sys_delete_module+0x1c1/0x280 do_syscall_64+0x77/0x230 entry_SYSCALL_64_after_hwframe+0x49/0xbe other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&shost->scan_mutex); lock(kn->count#202); lock(&shost->scan_mutex); lock(kn->count#202); *** DEADLOCK *** 2 locks held by modprobe/6539: #0: 00000000efaf9298 (&dev->mutex){....}, at: device_release_driver_internal+0x68/0x360 #1: 00000000a6ec2c69 (&shost->scan_mutex){+.+.}, at: scsi_remove_host+0x21/0x150 [scsi_mod] stack backtrace: CPU: 10 PID: 6539 Comm: modprobe Not tainted 4.18.0-rc2-dbg+ #5 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0xa4/0xf5 print_circular_bug.isra.34+0x213/0x221 __lock_acquire+0x1a7e/0x1b50 lock_acquire+0xd2/0x260 __kernfs_remove+0x424/0x4a0 kernfs_remove_by_name_ns+0x45/0x90 remove_files.isra.1+0x3a/0x90 sysfs_remove_group+0x5c/0xc0 sysfs_remove_groups+0x39/0x60 device_remove_attrs+0x82/0xb0 device_del+0x251/0x580 __scsi_remove_device+0x19f/0x1d0 [scsi_mod] scsi_forget_host+0x37/0xb0 [scsi_mod] scsi_remove_host+0x9b/0x150 [scsi_mod] sdebug_driver_remove+0x4b/0x150 [scsi_debug] device_release_driver_internal+0x241/0x360 device_release_driver+0x12/0x20 bus_remove_device+0x1bc/0x290 device_del+0x259/0x580 device_unregister+0x1a/0x70 sdebug_remove_adapter+0x8b/0xf0 [scsi_debug] scsi_debug_exit+0x76/0xe8 [scsi_debug] __x64_sys_delete_module+0x1c1/0x280 do_syscall_64+0x77/0x230 entry_SYSCALL_64_after_hwframe+0x49/0xbe See also https://www.mail-archive.com/linux-scsi@vger.kernel.org/msg54525.html. Fixes: ac0ece9174ac ("scsi: use device_remove_file_self() instead of device_schedule_callback()") Signed-off-by: Bart Van Assche <bart.vanassche(a)wdc.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Tejun Heo <tj(a)kernel.org> Cc: Johannes Thumshirn <jthumshirn(a)suse.de> Cc: <stable(a)vger.kernel.org> --- drivers/scsi/scsi_sysfs.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index de122354d09a..3aee9464a7bf 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -722,8 +722,24 @@ static ssize_t sdev_store_delete(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - if (device_remove_file_self(dev, attr)) - scsi_remove_device(to_scsi_device(dev)); + struct kernfs_node *kn; + + kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); + WARN_ON_ONCE(!kn); + /* + * Concurrent writes into the "delete" sysfs attribute may trigger + * concurrent calls to device_remove_file() and scsi_remove_device(). + * device_remove_file() handles concurrent removal calls by + * serializing these and by ignoring the second and later removal + * attempts. Concurrent calls of scsi_remove_device() are + * serialized. The second and later calls of scsi_remove_device() are + * ignored because the first call of that function changes the device + * state into SDEV_DEL. + */ + device_remove_file(dev, attr); + scsi_remove_device(to_scsi_device(dev)); + if (kn) + sysfs_unbreak_active_protection(kn); return count; }; static DEVICE_ATTR(delete, S_IWUSR, NULL, sdev_store_delete); -- 2.18.0

6 years, 6 months

3
4
0 0

[PATCH] block: really disable runtime-pm for blk-mq

by Ming Lei

Runtime PM isn't ready for blk-mq yet, and commit 765e40b675a9 ("block: disable runtime-pm for blk-mq") tried to disable it. Unfortunately, it can't take effect in that way since user space still can switch it on via 'echo auto > /sys/block/sdN/device/power/control'. This patch disables runtime-pm for blk-mq really by pm_runtime_disable() and fixes all kinds of PM related kernel crash. Cc: Christoph Hellwig <hch(a)lst.de> Cc: Patrick Steinhardt <ps(a)pks.im> Cc: Bart Van Assche <Bart.VanAssche(a)wdc.com> Cc: Tomas Janousek <tomi(a)nomi.cz> Cc: Przemek Socha <soprwa(a)gmail.com> Cc: Alan Stern <stern(a)rowland.harvard.edu> Cc: <stable(a)vger.kernel.org> Signed-off-by: Ming Lei <ming.lei(a)redhat.com> --- block/blk-core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 03a4ea93a5f3..090b782df129 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -3769,9 +3769,11 @@ EXPORT_SYMBOL(blk_finish_plug); */ void blk_pm_runtime_init(struct request_queue *q, struct device *dev) { - /* not support for RQF_PM and ->rpm_status in blk-mq yet */ - if (q->mq_ops) + /* Don't enable runtime PM for blk-mq until it is ready */ + if (q->mq_ops) { + pm_runtime_disable(dev); return; + } q->dev = dev; q->rpm_status = RPM_ACTIVE; -- 2.9.5

6 years, 6 months

6
5
0 0

[PATCH 1/2] sysfs: Introduce sysfs_{un,}break_active_protection()

by Bart Van Assche

Introduce these two functions and export them such that the next patch can add calls to these functions from the SCSI core. Signed-off-by: Bart Van Assche <bart.vanassche(a)wdc.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Tejun Heo <tj(a)kernel.org> Cc: <stable(a)vger.kernel.org> --- fs/sysfs/file.c | 44 +++++++++++++++++++++++++++++++++++++++++++ include/linux/sysfs.h | 14 ++++++++++++++ 2 files changed, 58 insertions(+) diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 5c13f29bfcdb..118fa197a35f 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -405,6 +405,50 @@ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, } EXPORT_SYMBOL_GPL(sysfs_chmod_file); +/** + * sysfs_break_active_protection - break "active" protection + * @kobj: The kernel object @attr is associated with. + * @attr: The attribute to break the "active" protection for. + * + * With sysfs, just like kernfs, deletion of an attribute is postponed until + * all active .show() and .store() callbacks have finished unless this function + * is called. Hence this function is useful in methods that implement self + * deletion. + */ +struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, + const struct attribute *attr) +{ + struct kernfs_node *kn; + + kobject_get(kobj); + kn = kernfs_find_and_get(kobj->sd, attr->name); + if (kn) + kernfs_break_active_protection(kn); + return kn; +} +EXPORT_SYMBOL_GPL(sysfs_break_active_protection); + +/** + * sysfs_unbreak_active_protection - restore "active" protection + * @kn: Pointer returned by sysfs_break_active_protection(). + * + * Undo the effects of sysfs_break_active_protection(). Since this function + * calls kernfs_put() on the kernfs node that corresponds to the 'attr' + * argument passed to sysfs_break_active_protection() that attribute may have + * been removed between the sysfs_break_active_protection() and + * sysfs_unbreak_active_protection() calls, it is not safe to access @kn after + * this function has returned. + */ +void sysfs_unbreak_active_protection(struct kernfs_node *kn) +{ + struct kobject *kobj = kn->parent->priv; + + kernfs_unbreak_active_protection(kn); + kernfs_put(kn); + kobject_put(kobj); +} +EXPORT_SYMBOL_GPL(sysfs_unbreak_active_protection); + /** * sysfs_remove_file_ns - remove an object attribute with a custom ns tag * @kobj: object we're acting for diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index b8bfdc173ec0..3c12198c0103 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -237,6 +237,9 @@ int __must_check sysfs_create_files(struct kobject *kobj, const struct attribute **attr); int __must_check sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, umode_t mode); +struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, + const struct attribute *attr); +void sysfs_unbreak_active_protection(struct kernfs_node *kn); void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns); bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr); @@ -350,6 +353,17 @@ static inline int sysfs_chmod_file(struct kobject *kobj, return 0; } +static inline struct kernfs_node * +sysfs_break_active_protection(struct kobject *kobj, + const struct attribute *attr) +{ + return NULL; +} + +static inline void sysfs_unbreak_active_protection(struct kernfs_node *kn) +{ +} + static inline void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns) -- 2.18.0

6 years, 6 months

3
2
0 0

[PATCH v2] ext4: mballoc: Fix spectre gadget in ext4_mb_regular_allocator

by Jeremy Cline

'ac->ac_g_ex.fe_len' is a user-controlled value which is used in the derivation of 'ac->ac_2order'. 'ac->ac_2order', in turn, is used to index arrays which makes it a potential spectre gadget. Fix this by sanitizing the value assigned to 'ac->ac2_order'. This covers the following accesses found with the help of smatch: * fs/ext4/mballoc.c:1896 ext4_mb_simple_scan_group() warn: potential spectre issue 'grp->bb_counters' [w] (local cap) * fs/ext4/mballoc.c:445 mb_find_buddy() warn: potential spectre issue 'EXT4_SB(e4b->bd_sb)->s_mb_offsets' [r] (local cap) * fs/ext4/mballoc.c:446 mb_find_buddy() warn: potential spectre issue 'EXT4_SB(e4b->bd_sb)->s_mb_maxs' [r] (local cap) Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: stable(a)vger.kernel.org Suggested-by: Josh Poimboeuf <jpoimboe(a)redhat.com> Signed-off-by: Jeremy Cline <jcline(a)redhat.com> --- I broke this out of the "ext4: fix spectre v1 gadgets" patch set since the other patches in that series could, as Josh noted, be replaced with one fix in do_quotactl. I'll send that fix to the disk quota folks separately. Changes from v1: - Sanitize ac_2order on assignment, rather than down the call chain in ext4_mb_simple_scan_group. fs/ext4/mballoc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index f7ab34088162..8b24d3d42cb3 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -14,6 +14,7 @@ #include <linux/log2.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/nospec.h> #include <linux/backing-dev.h> #include <trace/events/ext4.h> @@ -2140,7 +2141,8 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) * This should tell if fe_len is exactly power of 2 */ if ((ac->ac_g_ex.fe_len & (~(1 << (i - 1)))) == 0) - ac->ac_2order = i - 1; + ac->ac_2order = array_index_nospec(i - 1, + sb->s_blocksize_bits + 2); } /* if stream allocation is enabled, use global goal */ -- 2.17.1

6 years, 6 months

3
5
0 0

[PATCH] sched/deadline: Update rq_clock of later_rq when pushing a task

by Daniel Bristot de Oliveira

Daniel Casini got this warn while running a DL task here at RetisLab: [ 461.137582] ------------[ cut here ]------------ [ 461.137583] rq->clock_update_flags < RQCF_ACT_SKIP [ 461.137599] WARNING: CPU: 4 PID: 2354 at kernel/sched/sched.h:967 assert_clock_updated.isra.32.part.33+0x17/0x20 [a ton of modules] [ 461.137646] CPU: 4 PID: 2354 Comm: label_image Not tainted 4.18.0-rc4+ #3 [ 461.137647] Hardware name: ASUS All Series/Z87-K, BIOS 0801 09/02/2013 [ 461.137649] RIP: 0010:assert_clock_updated.isra.32.part.33+0x17/0x20 [ 461.137649] Code: ff 48 89 83 08 09 00 00 eb c6 66 0f 1f 84 00 00 00 00 00 55 48 c7 c7 98 7a 6c a5 c6 05 bc 0d 54 01 01 48 89 e5 e8 a9 84 fb ff <0f> 0b 5d c3 0f 1f 44 00 00 0f 1f 44 00 00 83 7e 60 01 74 0a 48 3b [ 461.137673] RSP: 0018:ffffa77e08cafc68 EFLAGS: 00010082 [ 461.137674] RAX: 0000000000000000 RBX: ffff8b3fc1702d80 RCX: 0000000000000006 [ 461.137674] RDX: 0000000000000007 RSI: 0000000000000096 RDI: ffff8b3fded164b0 [ 461.137675] RBP: ffffa77e08cafc68 R08: 0000000000000026 R09: 0000000000000339 [ 461.137676] R10: ffff8b3fd060d410 R11: 0000000000000026 R12: ffffffffa4e14e20 [ 461.137677] R13: ffff8b3fdec22940 R14: ffff8b3fc1702da0 R15: ffff8b3fdec22940 [ 461.137678] FS: 00007efe43ee5700(0000) GS:ffff8b3fded00000(0000) knlGS:0000000000000000 [ 461.137679] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 461.137680] CR2: 00007efe30000010 CR3: 0000000301744003 CR4: 00000000001606e0 [ 461.137680] Call Trace: [ 461.137684] push_dl_task.part.46+0x3bc/0x460 [ 461.137686] task_woken_dl+0x60/0x80 [ 461.137689] ttwu_do_wakeup+0x4f/0x150 [ 461.137690] ttwu_do_activate+0x77/0x80 [ 461.137692] try_to_wake_up+0x1d6/0x4c0 [ 461.137693] wake_up_q+0x32/0x70 [ 461.137696] do_futex+0x7e7/0xb50 [ 461.137698] __x64_sys_futex+0x8b/0x180 [ 461.137701] do_syscall_64+0x5a/0x110 [ 461.137703] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 461.137705] RIP: 0033:0x7efe4918ca26 [ 461.137705] Code: 00 00 00 74 17 49 8b 48 20 44 8b 59 10 41 83 e3 30 41 83 fb 20 74 1e be 85 00 00 00 41 ba 01 00 00 00 41 b9 01 00 00 04 0f 05 <48> 3d 01 f0 ff ff 73 1f 31 c0 c3 be 8c 00 00 00 49 89 c8 4d 31 d2 [ 461.137738] RSP: 002b:00007efe43ee4928 EFLAGS: 00000283 ORIG_RAX: 00000000000000ca [ 461.137739] RAX: ffffffffffffffda RBX: 0000000005094df0 RCX: 00007efe4918ca26 [ 461.137740] RDX: 0000000000000001 RSI: 0000000000000085 RDI: 0000000005094e24 [ 461.137741] RBP: 00007efe43ee49c0 R08: 0000000005094e20 R09: 0000000004000001 [ 461.137741] R10: 0000000000000001 R11: 0000000000000283 R12: 0000000000000000 [ 461.137742] R13: 0000000005094df8 R14: 0000000000000001 R15: 0000000000448a10 [ 461.137743] ---[ end trace 187df4cad2bf7649 ]--- This warning was caused in the push_dl_task(), because the rq_clock of the later_rq was used by cpufreq_update_util() inside __add_running_bw(), before its update at activate_task(). The fix then is to update the clock before calling add_running_bw. To avoid double rq_clock_update(), we set ENQUEUE_NOCLOCK flag to activate_task(). Reported-by: Daniel Casini <daniel.casini(a)santannapisa.it> Signed-off-by: Daniel Bristot de Oliveira <bristot(a)redhat.com> Cc: Juri Lelli <juri.lelli(a)arm.com> Cc: Luca Abeni <luca.abeni(a)santannapisa.it> Cc: Tommaso Cucinotta <tommaso.cucinotta(a)sssup.it> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Ingo Molnar <mingo(a)kernel.org> Cc: linux-kernel(a)vger.kernel.org Cc: <stable(a)vger.kernel.org> # 4.16+ Fixes: e0367b12674b sched/deadline: Move CPU frequency selection triggering points --- kernel/sched/deadline.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fbfc3f1d368a..e733c15b7695 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2090,8 +2090,16 @@ static int push_dl_task(struct rq *rq) sub_rq_bw(&next_task->dl, &rq->dl); set_task_cpu(next_task, later_rq->cpu); add_rq_bw(&next_task->dl, &later_rq->dl); + + /* + * Update the later_rq clock here, because the clock is used + * by the cpufreq_update_util() inside __add_running_bw(). + * Then, set ENQUEUE_NOCLOCK flag to avoid updating the rq_clock + * again in the activate_task()->enqueue_task(). + */ + update_rq_clock(later_rq); add_running_bw(&next_task->dl, &later_rq->dl); - activate_task(later_rq, next_task, 0); + activate_task(later_rq, next_task, ENQUEUE_NOCLOCK); ret = 1; resched_curr(later_rq); -- 2.17.1

6 years, 6 months

4
4
0 0

Re: [PATCH] pinctrl: freescale: off by one in imx1_pinconf_group_dbg_show()

by Uwe Kleine-König

Hello, On Mon, Jul 30, 2018 at 05:43:43PM +0200, Linus Walleij wrote: > On Fri, Jul 13, 2018 at 4:55 PM Dan Carpenter <dan.carpenter(a)oracle.com> wrote: > > > The info->groups[] array is allocated in imx1_pinctrl_parse_dt(). It > > has info->ngroups elements. Thus the > here should be >= to prevent > > reading one element beyond the end of the array. > > > > Fixes: 30612cd90005 ("pinctrl: imx1 core driver") > > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > > Patch applied. > > I am not tagging for stable as it is debug code and does not > affect end users. Not sure this is a valid reason. Distro kernels usually enable debugfs. I'd say an out-of-bounds access that can only be triggered by root should still be fixed. I won't argue but added stable to the addressees of this mail to at least raise awareness. Best regards Uwe -- Pengutronix e.K. | Uwe Kleine-König | Industrial Linux Solutions | http://www.pengutronix.de/ |

6 years, 6 months

2
1
0 0

[PATCH] drm/i915/gvt: move intel_runtime_pm_get out of spin_lock in stop_schedule

by hang.yuan＠linux.intel.com

From: Hang Yuan <hang.yuan(a)linux.intel.com> pm_runtime_get_sync in intel_runtime_pm_get might sleep if i915 device is not active. When stop vgpu schedule, the device may be inactive. So need to move runtime_pm_get out of spin_lock/unlock. Fixes: b24881e0b0b6("drm/i915/gvt: Add runtime_pm_get/put into gvt_switch_mmio Signed-off-by: Hang Yuan <hang.yuan(a)linux.intel.com> Signed-off-by: Xiong Zhang <xiong.y.zhang(a)intel.com> --- drivers/gpu/drm/i915/gvt/mmio_context.c | 2 -- drivers/gpu/drm/i915/gvt/sched_policy.c | 3 +++ 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 7e702c6..10e63ee 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -549,11 +549,9 @@ void intel_gvt_switch_mmio(struct intel_vgpu *pre, * performace for batch mmio read/write, so we need * handle forcewake mannually. */ - intel_runtime_pm_get(dev_priv); intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); switch_mmio(pre, next, ring_id); intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); - intel_runtime_pm_put(dev_priv); } /** diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c index 09d7bb7..985fe81 100644 --- a/drivers/gpu/drm/i915/gvt/sched_policy.c +++ b/drivers/gpu/drm/i915/gvt/sched_policy.c @@ -426,6 +426,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) &vgpu->gvt->scheduler; int ring_id; struct vgpu_sched_data *vgpu_data = vgpu->sched_data; + struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; if (!vgpu_data->active) return; @@ -444,6 +445,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) scheduler->current_vgpu = NULL; } + intel_runtime_pm_get(dev_priv); spin_lock_bh(&scheduler->mmio_context_lock); for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) { if (scheduler->engine_owner[ring_id] == vgpu) { @@ -452,5 +454,6 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) } } spin_unlock_bh(&scheduler->mmio_context_lock); + intel_runtime_pm_put(dev_priv); mutex_unlock(&vgpu->gvt->sched_lock); } -- 2.7.4

6 years, 6 months

3
2
0 0

+ userfaultfd-remove-uffd-flags-from-vma-vm_flags-if-uffd_event_fork-fails.patch added to -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: userfaultfd: remove uffd flags from vma->vm_flags if UFFD_EVENT_FORK fails has been added to the -mm tree. Its filename is userfaultfd-remove-uffd-flags-from-vma-vm_flags-if-uffd_event_fork-fails.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/userfaultfd-remove-uffd-flags-from… and later at http://ozlabs.org/~akpm/mmotm/broken-out/userfaultfd-remove-uffd-flags-from… Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Mike Rapoport <rppt(a)linux.vnet.ibm.com> Subject: userfaultfd: remove uffd flags from vma->vm_flags if UFFD_EVENT_FORK fails The fix in 0cbb4b4f4c44 ("userfaultfd: clear the vma->vm_userfaultfd_ctx if UFFD_EVENT_FORK fails") cleared the vma->vm_userfaultfd_ctx but kept userfaultfd flags in vma->vm_flags that were copied from the parent process VMA. As the result, there is an inconsistency between the values of vma->vm_userfaultfd_ctx.ctx and vma->vm_flags which triggers BUG_ON in userfaultfd_release(). Clearing the uffd flags from vma->vm_flags in case of UFFD_EVENT_FORK failure resolves the issue. Link: http://lkml.kernel.org/r/1532931975-25473-1-git-send-email-rppt@linux.vnet.… Fixes: 0cbb4b4f4c44 ("userfaultfd: clear the vma->vm_userfaultfd_ctx if UFFD_EVENT_FORK fails") Signed-off-by: Mike Rapoport <rppt(a)linux.vnet.ibm.com> Reported-by: syzbot+121be635a7a35ddb7dcb(a)syzkaller.appspotmail.com Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Eric Biggers <ebiggers3(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- diff -puN fs/userfaultfd.c~userfaultfd-remove-uffd-flags-from-vma-vm_flags-if-uffd_event_fork-fails fs/userfaultfd.c --- a/fs/userfaultfd.c~userfaultfd-remove-uffd-flags-from-vma-vm_flags-if-uffd_event_fork-fails +++ a/fs/userfaultfd.c @@ -633,8 +633,10 @@ static void userfaultfd_event_wait_compl /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) - if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) + if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + } up_write(&mm->mmap_sem); userfaultfd_ctx_put(release_new_ctx); _ Patches currently in -mm which might be from rppt(a)linux.vnet.ibm.com are userfaultfd-remove-uffd-flags-from-vma-vm_flags-if-uffd_event_fork-fails.patch mm-make-deferred_struct_page_init-explicitly-depend-on-sparsemem.patch mm-memblock-replace-u64-with-phys_addr_t-where-appropriate.patch mm-mempool-add-missing-parameter-description.patch mm-util-make-strndup_user-description-a-kernel-doc-comment.patch mm-util-add-kernel-doc-for-kvfree.patch docs-core-api-kill-trailing-whitespace-in-kernel-apirst.patch docs-core-api-move-strmemdup-to-string-manipulation.patch docs-core-api-split-memory-management-api-to-a-separate-file.patch docs-mm-make-gfp-flags-descriptions-usable-as-kernel-doc.patch docs-core-api-mm-api-add-section-about-gfp-flags.patch

6 years, 6 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2018