From: Sasha Levin Date: Wed, 23 Jan 2019 15:53:12 +0000 (-0500) Subject: autosel patches for 3.18 X-Git-Tag: v4.20.5~15 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=b8e531bd5c9a95ef827a52bdb8d429ba4f46eb72;p=thirdparty%2Fkernel%2Fstable-queue.git autosel patches for 3.18 Signed-off-by: Sasha Levin --- diff --git a/queue-3.18/alsa-bebob-fix-model-id-of-unit-for-apogee-ensemble.patch b/queue-3.18/alsa-bebob-fix-model-id-of-unit-for-apogee-ensemble.patch new file mode 100644 index 00000000000..466e15c65ce --- /dev/null +++ b/queue-3.18/alsa-bebob-fix-model-id-of-unit-for-apogee-ensemble.patch @@ -0,0 +1,93 @@ +From 945234064f76457aa40f208a4e1bed3f4c61408c Mon Sep 17 00:00:00 2001 +From: Takashi Sakamoto +Date: Wed, 19 Dec 2018 20:00:42 +0900 +Subject: ALSA: bebob: fix model-id of unit for Apogee Ensemble + +[ Upstream commit 644b2e97405b0b74845e1d3c2b4fe4c34858062b ] + +This commit fixes hard-coded model-id for an unit of Apogee Ensemble with +a correct value. This unit uses DM1500 ASIC produced ArchWave AG (formerly +known as BridgeCo AG). + +I note that this model supports three modes in the number of data channels +in tx/rx streams; 8 ch pairs, 10 ch pairs, 18 ch pairs. The mode is +switched by Vendor-dependent AV/C command, like: + +$ cd linux-firewire-utils +$ ./firewire-request /dev/fw1 fcp 0x00ff000003dbeb0600000000 (8ch pairs) +$ ./firewire-request /dev/fw1 fcp 0x00ff000003dbeb0601000000 (10ch pairs) +$ ./firewire-request /dev/fw1 fcp 0x00ff000003dbeb0602000000 (18ch pairs) + +When switching between different mode, the unit disappears from IEEE 1394 +bus, then appears on the bus with different combination of stream formats. +In a mode of 18 ch pairs, available sampling rate is up to 96.0 kHz, else +up to 192.0 kHz. + +$ ./hinawa-config-rom-printer /dev/fw1 +{ 'bus-info': { 'adj': False, + 'bmc': True, + 'chip_ID': 21474898341, + 'cmc': True, + 'cyc_clk_acc': 100, + 'generation': 2, + 'imc': True, + 'isc': True, + 'link_spd': 2, + 'max_ROM': 1, + 'max_rec': 512, + 'name': '1394', + 'node_vendor_ID': 987, + 'pmc': False}, + 'root-directory': [ ['HARDWARE_VERSION', 19], + [ 'NODE_CAPABILITIES', + { 'addressing': {'64': True, 'fix': True, 'prv': False}, + 'misc': {'int': False, 'ms': False, 'spt': True}, + 'state': { 'atn': False, + 'ded': False, + 'drq': True, + 'elo': False, + 'init': False, + 'lst': True, + 'off': False}, + 'testing': {'bas': False, 'ext': False}}], + ['VENDOR', 987], + ['DESCRIPTOR', 'Apogee Electronics'], + ['MODEL', 126702], + ['DESCRIPTOR', 'Ensemble'], + ['VERSION', 5297], + [ 'UNIT', + [ ['SPECIFIER_ID', 41005], + ['VERSION', 65537], + ['MODEL', 126702], + ['DESCRIPTOR', 'Ensemble']]], + [ 'DEPENDENT_INFO', + [ ['SPECIFIER_ID', 2037], + ['VERSION', 1], + [(58, 'IMMEDIATE'), 16777159], + [(59, 'IMMEDIATE'), 1048576], + [(60, 'IMMEDIATE'), 16777159], + [(61, 'IMMEDIATE'), 6291456]]]]} + +Signed-off-by: Takashi Sakamoto +Signed-off-by: Takashi Iwai +Signed-off-by: Sasha Levin +--- + sound/firewire/bebob/bebob.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/sound/firewire/bebob/bebob.c b/sound/firewire/bebob/bebob.c +index fc19c99654aa..e4312afe2ce5 100644 +--- a/sound/firewire/bebob/bebob.c ++++ b/sound/firewire/bebob/bebob.c +@@ -356,7 +356,7 @@ static const struct ieee1394_device_id bebob_id_table[] = { + /* Apogee Electronics, DA/AD/DD-16X (X-FireWire card) */ + SND_BEBOB_DEV_ENTRY(VEN_APOGEE, 0x00010048, &spec_normal), + /* Apogee Electronics, Ensemble */ +- SND_BEBOB_DEV_ENTRY(VEN_APOGEE, 0x00001eee, &spec_normal), ++ SND_BEBOB_DEV_ENTRY(VEN_APOGEE, 0x01eeee, &spec_normal), + /* ESI, Quatafire610 */ + SND_BEBOB_DEV_ENTRY(VEN_ESI, 0x00010064, &spec_normal), + /* AcousticReality, eARMasterOne */ +-- +2.19.1 + diff --git a/queue-3.18/clk-imx6q-reset-exclusive-gates-on-init.patch b/queue-3.18/clk-imx6q-reset-exclusive-gates-on-init.patch new file mode 100644 index 00000000000..c99dd52ae68 --- /dev/null +++ b/queue-3.18/clk-imx6q-reset-exclusive-gates-on-init.patch @@ -0,0 +1,44 @@ +From 722323376df5fae098dd33210a1b1e581c4d8dbd Mon Sep 17 00:00:00 2001 +From: Lucas Stach +Date: Thu, 15 Nov 2018 15:30:26 +0100 +Subject: clk: imx6q: reset exclusive gates on init + +[ Upstream commit f7542d817733f461258fd3a47d77da35b2d9fc81 ] + +The exclusive gates may be set up in the wrong way by software running +before the clock driver comes up. In that case the exclusive setup is +locked in its initial state, as the complementary function can't be +activated without disabling the initial setup first. + +To avoid this lock situation, reset the exclusive gates to the off +state and allow the kernel to provide the proper setup. + +Signed-off-by: Lucas Stach +Reviewed-by: Dong Aisheng +Signed-off-by: Stephen Boyd +Signed-off-by: Sasha Levin +--- + arch/arm/mach-imx/clk-imx6q.c | 6 +++++- + 1 file changed, 5 insertions(+), 1 deletion(-) + +diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c +index 5474a76803f0..936ed9bae595 100644 +--- a/arch/arm/mach-imx/clk-imx6q.c ++++ b/arch/arm/mach-imx/clk-imx6q.c +@@ -222,8 +222,12 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) + * lvds1_gate and lvds2_gate are pseudo-gates. Both can be + * independently configured as clock inputs or outputs. We treat + * the "output_enable" bit as a gate, even though it's really just +- * enabling clock output. ++ * enabling clock output. Initially the gate bits are cleared, as ++ * otherwise the exclusive configuration gets locked in the setup done ++ * by software running before the clock driver, with no way to change ++ * it. + */ ++ writel(readl(base + 0x160) & ~0x3c00, base + 0x160); + clk[IMX6QDL_CLK_LVDS1_GATE] = imx_clk_gate_exclusive("lvds1_gate", "lvds1_sel", base + 0x160, 10, BIT(12)); + clk[IMX6QDL_CLK_LVDS2_GATE] = imx_clk_gate_exclusive("lvds2_gate", "lvds2_sel", base + 0x160, 11, BIT(13)); + +-- +2.19.1 + diff --git a/queue-3.18/dm-kcopyd-fix-bug-causing-workqueue-stalls.patch b/queue-3.18/dm-kcopyd-fix-bug-causing-workqueue-stalls.patch new file mode 100644 index 00000000000..3151dbd75ec --- /dev/null +++ b/queue-3.18/dm-kcopyd-fix-bug-causing-workqueue-stalls.patch @@ -0,0 +1,159 @@ +From cff72847b45975c4e57040d23aae3cf222554705 Mon Sep 17 00:00:00 2001 +From: Nikos Tsironis +Date: Wed, 31 Oct 2018 17:53:09 -0400 +Subject: dm kcopyd: Fix bug causing workqueue stalls + +[ Upstream commit d7e6b8dfc7bcb3f4f3a18313581f67486a725b52 ] + +When using kcopyd to run callbacks through dm_kcopyd_do_callback() or +submitting copy jobs with a source size of 0, the jobs are pushed +directly to the complete_jobs list, which could be under processing by +the kcopyd thread. As a result, the kcopyd thread can continue running +completed jobs indefinitely, without releasing the CPU, as long as +someone keeps submitting new completed jobs through the aforementioned +paths. Processing of work items, queued for execution on the same CPU as +the currently running kcopyd thread, is thus stalled for excessive +amounts of time, hurting performance. + +Running the following test, from the device mapper test suite [1], + + dmtest run --suite snapshot -n parallel_io_to_many_snaps_N + +, with 8 active snapshots, we get, in dmesg, messages like the +following: + +[68899.948523] BUG: workqueue lockup - pool cpus=0 node=0 flags=0x0 nice=0 stuck for 95s! +[68899.949282] Showing busy workqueues and worker pools: +[68899.949288] workqueue events: flags=0x0 +[68899.949295] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=2/256 +[68899.949306] pending: vmstat_shepherd, cache_reap +[68899.949331] workqueue mm_percpu_wq: flags=0x8 +[68899.949337] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256 +[68899.949345] pending: vmstat_update +[68899.949387] workqueue dm_bufio_cache: flags=0x8 +[68899.949392] pwq 4: cpus=2 node=0 flags=0x0 nice=0 active=1/256 +[68899.949400] pending: work_fn [dm_bufio] +[68899.949423] workqueue kcopyd: flags=0x8 +[68899.949429] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256 +[68899.949437] pending: do_work [dm_mod] +[68899.949452] workqueue kcopyd: flags=0x8 +[68899.949458] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=2/256 +[68899.949466] in-flight: 13:do_work [dm_mod] +[68899.949474] pending: do_work [dm_mod] +[68899.949487] workqueue kcopyd: flags=0x8 +[68899.949493] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256 +[68899.949501] pending: do_work [dm_mod] +[68899.949515] workqueue kcopyd: flags=0x8 +[68899.949521] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256 +[68899.949529] pending: do_work [dm_mod] +[68899.949541] workqueue kcopyd: flags=0x8 +[68899.949547] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256 +[68899.949555] pending: do_work [dm_mod] +[68899.949568] pool 0: cpus=0 node=0 flags=0x0 nice=0 hung=95s workers=4 idle: 27130 27223 1084 + +Fix this by splitting the complete_jobs list into two parts: A user +facing part, named callback_jobs, and one used internally by kcopyd, +retaining the name complete_jobs. dm_kcopyd_do_callback() and +dispatch_job() now push their jobs to the callback_jobs list, which is +spliced to the complete_jobs list once, every time the kcopyd thread +wakes up. This prevents kcopyd from hogging the CPU indefinitely and +causing workqueue stalls. + +Re-running the aforementioned test: + + * Workqueue stalls are eliminated + * The maximum writing time among all targets is reduced from 09m37.10s + to 06m04.85s and the total run time of the test is reduced from + 10m43.591s to 7m19.199s + +[1] https://github.com/jthornber/device-mapper-test-suite + +Signed-off-by: Nikos Tsironis +Signed-off-by: Ilias Tsitsimpis +Signed-off-by: Mike Snitzer +Signed-off-by: Sasha Levin +--- + drivers/md/dm-kcopyd.c | 19 ++++++++++++++----- + 1 file changed, 14 insertions(+), 5 deletions(-) + +diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c +index 77833b65e01e..9e626e5df2f6 100644 +--- a/drivers/md/dm-kcopyd.c ++++ b/drivers/md/dm-kcopyd.c +@@ -55,15 +55,17 @@ struct dm_kcopyd_client { + struct dm_kcopyd_throttle *throttle; + + /* +- * We maintain three lists of jobs: ++ * We maintain four lists of jobs: + * + * i) jobs waiting for pages + * ii) jobs that have pages, and are waiting for the io to be issued. +- * iii) jobs that have completed. ++ * iii) jobs that don't need to do any IO and just run a callback ++ * iv) jobs that have completed. + * +- * All three of these are protected by job_lock. ++ * All four of these are protected by job_lock. + */ + spinlock_t job_lock; ++ struct list_head callback_jobs; + struct list_head complete_jobs; + struct list_head io_jobs; + struct list_head pages_jobs; +@@ -583,6 +585,7 @@ static void do_work(struct work_struct *work) + struct dm_kcopyd_client *kc = container_of(work, + struct dm_kcopyd_client, kcopyd_work); + struct blk_plug plug; ++ unsigned long flags; + + /* + * The order that these are called is *very* important. +@@ -591,6 +594,10 @@ static void do_work(struct work_struct *work) + * list. io jobs call wake when they complete and it all + * starts again. + */ ++ spin_lock_irqsave(&kc->job_lock, flags); ++ list_splice_tail_init(&kc->callback_jobs, &kc->complete_jobs); ++ spin_unlock_irqrestore(&kc->job_lock, flags); ++ + blk_start_plug(&plug); + process_jobs(&kc->complete_jobs, kc, run_complete_job); + process_jobs(&kc->pages_jobs, kc, run_pages_job); +@@ -608,7 +615,7 @@ static void dispatch_job(struct kcopyd_job *job) + struct dm_kcopyd_client *kc = job->kc; + atomic_inc(&kc->nr_jobs); + if (unlikely(!job->source.count)) +- push(&kc->complete_jobs, job); ++ push(&kc->callback_jobs, job); + else if (job->pages == &zero_page_list) + push(&kc->io_jobs, job); + else +@@ -795,7 +802,7 @@ void dm_kcopyd_do_callback(void *j, int read_err, unsigned long write_err) + job->read_err = read_err; + job->write_err = write_err; + +- push(&kc->complete_jobs, job); ++ push(&kc->callback_jobs, job); + wake(kc); + } + EXPORT_SYMBOL(dm_kcopyd_do_callback); +@@ -825,6 +832,7 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *thro + return ERR_PTR(-ENOMEM); + + spin_lock_init(&kc->job_lock); ++ INIT_LIST_HEAD(&kc->callback_jobs); + INIT_LIST_HEAD(&kc->complete_jobs); + INIT_LIST_HEAD(&kc->io_jobs); + INIT_LIST_HEAD(&kc->pages_jobs); +@@ -874,6 +882,7 @@ void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc) + /* Wait for completion of all jobs submitted by this client. */ + wait_event(kc->destroyq, !atomic_read(&kc->nr_jobs)); + ++ BUG_ON(!list_empty(&kc->callback_jobs)); + BUG_ON(!list_empty(&kc->complete_jobs)); + BUG_ON(!list_empty(&kc->io_jobs)); + BUG_ON(!list_empty(&kc->pages_jobs)); +-- +2.19.1 + diff --git a/queue-3.18/dm-snapshot-fix-excessive-memory-usage-and-workqueue.patch b/queue-3.18/dm-snapshot-fix-excessive-memory-usage-and-workqueue.patch new file mode 100644 index 00000000000..7e87558464f --- /dev/null +++ b/queue-3.18/dm-snapshot-fix-excessive-memory-usage-and-workqueue.patch @@ -0,0 +1,225 @@ +From e00926630d886be2e48b37ec8d52e2c1dd4cc947 Mon Sep 17 00:00:00 2001 +From: Nikos Tsironis +Date: Wed, 31 Oct 2018 17:53:08 -0400 +Subject: dm snapshot: Fix excessive memory usage and workqueue stalls + +[ Upstream commit 721b1d98fb517ae99ab3b757021cf81db41e67be ] + +kcopyd has no upper limit to the number of jobs one can allocate and +issue. Under certain workloads this can lead to excessive memory usage +and workqueue stalls. For example, when creating multiple dm-snapshot +targets with a 4K chunk size and then writing to the origin through the +page cache. Syncing the page cache causes a large number of BIOs to be +issued to the dm-snapshot origin target, which itself issues an even +larger (because of the BIO splitting taking place) number of kcopyd +jobs. + +Running the following test, from the device mapper test suite [1], + + dmtest run --suite snapshot -n many_snapshots_of_same_volume_N + +, with 8 active snapshots, results in the kcopyd job slab cache growing +to 10G. Depending on the available system RAM this can lead to the OOM +killer killing user processes: + +[463.492878] kthreadd invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), + nodemask=(null), order=1, oom_score_adj=0 +[463.492894] kthreadd cpuset=/ mems_allowed=0 +[463.492948] CPU: 7 PID: 2 Comm: kthreadd Not tainted 4.19.0-rc7 #3 +[463.492950] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 +[463.492952] Call Trace: +[463.492964] dump_stack+0x7d/0xbb +[463.492973] dump_header+0x6b/0x2fc +[463.492987] ? lockdep_hardirqs_on+0xee/0x190 +[463.493012] oom_kill_process+0x302/0x370 +[463.493021] out_of_memory+0x113/0x560 +[463.493030] __alloc_pages_slowpath+0xf40/0x1020 +[463.493055] __alloc_pages_nodemask+0x348/0x3c0 +[463.493067] cache_grow_begin+0x81/0x8b0 +[463.493072] ? cache_grow_begin+0x874/0x8b0 +[463.493078] fallback_alloc+0x1e4/0x280 +[463.493092] kmem_cache_alloc_node+0xd6/0x370 +[463.493098] ? copy_process.part.31+0x1c5/0x20d0 +[463.493105] copy_process.part.31+0x1c5/0x20d0 +[463.493115] ? __lock_acquire+0x3cc/0x1550 +[463.493121] ? __switch_to_asm+0x34/0x70 +[463.493129] ? kthread_create_worker_on_cpu+0x70/0x70 +[463.493135] ? finish_task_switch+0x90/0x280 +[463.493165] _do_fork+0xe0/0x6d0 +[463.493191] ? kthreadd+0x19f/0x220 +[463.493233] kernel_thread+0x25/0x30 +[463.493235] kthreadd+0x1bf/0x220 +[463.493242] ? kthread_create_on_cpu+0x90/0x90 +[463.493248] ret_from_fork+0x3a/0x50 +[463.493279] Mem-Info: +[463.493285] active_anon:20631 inactive_anon:4831 isolated_anon:0 +[463.493285] active_file:80216 inactive_file:80107 isolated_file:435 +[463.493285] unevictable:0 dirty:51266 writeback:109372 unstable:0 +[463.493285] slab_reclaimable:31191 slab_unreclaimable:3483521 +[463.493285] mapped:526 shmem:4903 pagetables:1759 bounce:0 +[463.493285] free:33623 free_pcp:2392 free_cma:0 +... +[463.493489] Unreclaimable slab info: +[463.493513] Name Used Total +[463.493522] bio-6 1028KB 1028KB +[463.493525] bio-5 1028KB 1028KB +[463.493528] dm_snap_pending_exception 236783KB 243789KB +[463.493531] dm_exception 41KB 42KB +[463.493534] bio-4 1216KB 1216KB +[463.493537] bio-3 439396KB 439396KB +[463.493539] kcopyd_job 6973427KB 6973427KB +... +[463.494340] Out of memory: Kill process 1298 (ruby2.3) score 1 or sacrifice child +[463.494673] Killed process 1298 (ruby2.3) total-vm:435740kB, anon-rss:20180kB, file-rss:4kB, shmem-rss:0kB +[463.506437] oom_reaper: reaped process 1298 (ruby2.3), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB + +Moreover, issuing a large number of kcopyd jobs results in kcopyd +hogging the CPU, while processing them. As a result, processing of work +items, queued for execution on the same CPU as the currently running +kcopyd thread, is stalled for long periods of time, hurting performance. +Running the aforementioned test we get, in dmesg, messages like the +following: + +[67501.194592] BUG: workqueue lockup - pool cpus=4 node=0 flags=0x0 nice=0 stuck for 27s! +[67501.195586] Showing busy workqueues and worker pools: +[67501.195591] workqueue events: flags=0x0 +[67501.195597] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 +[67501.195611] pending: cache_reap +[67501.195641] workqueue mm_percpu_wq: flags=0x8 +[67501.195645] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 +[67501.195656] pending: vmstat_update +[67501.195682] workqueue kblockd: flags=0x18 +[67501.195687] pwq 5: cpus=2 node=0 flags=0x0 nice=-20 active=1/256 +[67501.195698] pending: blk_timeout_work +[67501.195753] workqueue kcopyd: flags=0x8 +[67501.195757] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 +[67501.195768] pending: do_work [dm_mod] +[67501.195802] workqueue kcopyd: flags=0x8 +[67501.195806] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 +[67501.195817] pending: do_work [dm_mod] +[67501.195834] workqueue kcopyd: flags=0x8 +[67501.195838] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 +[67501.195848] pending: do_work [dm_mod] +[67501.195881] workqueue kcopyd: flags=0x8 +[67501.195885] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=1/256 +[67501.195896] pending: do_work [dm_mod] +[67501.195920] workqueue kcopyd: flags=0x8 +[67501.195924] pwq 8: cpus=4 node=0 flags=0x0 nice=0 active=2/256 +[67501.195935] in-flight: 67:do_work [dm_mod] +[67501.195945] pending: do_work [dm_mod] +[67501.195961] pool 8: cpus=4 node=0 flags=0x0 nice=0 hung=27s workers=3 idle: 129 23765 + +The root cause for these issues is the way dm-snapshot uses kcopyd. In +particular, the lack of an explicit or implicit limit to the maximum +number of in-flight COW jobs. The merging path is not affected because +it implicitly limits the in-flight kcopyd jobs to one. + +Fix these issues by using a semaphore to limit the maximum number of +in-flight kcopyd jobs. We grab the semaphore before allocating a new +kcopyd job in start_copy() and start_full_bio() and release it after the +job finishes in copy_callback(). + +The initial semaphore value is configurable through a module parameter, +to allow fine tuning the maximum number of in-flight COW jobs. Setting +this parameter to zero initializes the semaphore to INT_MAX. + +A default value of 2048 maximum in-flight kcopyd jobs was chosen. This +value was decided experimentally as a trade-off between memory +consumption, stalling the kernel's workqueues and maintaining a high +enough throughput. + +Re-running the aforementioned test: + + * Workqueue stalls are eliminated + * kcopyd's job slab cache uses a maximum of 130MB + * The time taken by the test to write to the snapshot-origin target is + reduced from 05m20.48s to 03m26.38s + +[1] https://github.com/jthornber/device-mapper-test-suite + +Signed-off-by: Nikos Tsironis +Signed-off-by: Ilias Tsitsimpis +Signed-off-by: Mike Snitzer +Signed-off-by: Sasha Levin +--- + drivers/md/dm-snap.c | 22 ++++++++++++++++++++++ + 1 file changed, 22 insertions(+) + +diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c +index b91b39caf7a9..0a304e7de260 100644 +--- a/drivers/md/dm-snap.c ++++ b/drivers/md/dm-snap.c +@@ -19,6 +19,7 @@ + #include + #include + #include ++#include + + #include "dm.h" + +@@ -98,6 +99,9 @@ struct dm_snapshot { + /* The on disk metadata handler */ + struct dm_exception_store *store; + ++ /* Maximum number of in-flight COW jobs. */ ++ struct semaphore cow_count; ++ + struct dm_kcopyd_client *kcopyd_client; + + /* Wait for events based on state_bits */ +@@ -138,6 +142,19 @@ struct dm_snapshot { + #define RUNNING_MERGE 0 + #define SHUTDOWN_MERGE 1 + ++/* ++ * Maximum number of chunks being copied on write. ++ * ++ * The value was decided experimentally as a trade-off between memory ++ * consumption, stalling the kernel's workqueues and maintaining a high enough ++ * throughput. ++ */ ++#define DEFAULT_COW_THRESHOLD 2048 ++ ++static int cow_threshold = DEFAULT_COW_THRESHOLD; ++module_param_named(snapshot_cow_threshold, cow_threshold, int, 0644); ++MODULE_PARM_DESC(snapshot_cow_threshold, "Maximum number of chunks being copied on write"); ++ + DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle, + "A percentage of time allocated for copy on write"); + +@@ -1173,6 +1190,8 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) + goto bad_hash_tables; + } + ++ sema_init(&s->cow_count, (cow_threshold > 0) ? cow_threshold : INT_MAX); ++ + s->kcopyd_client = dm_kcopyd_client_create(&dm_kcopyd_throttle); + if (IS_ERR(s->kcopyd_client)) { + r = PTR_ERR(s->kcopyd_client); +@@ -1545,6 +1564,7 @@ static void copy_callback(int read_err, unsigned long write_err, void *context) + } + list_add(&pe->out_of_order_entry, lh); + } ++ up(&s->cow_count); + } + + /* +@@ -1568,6 +1588,7 @@ static void start_copy(struct dm_snap_pending_exception *pe) + dest.count = src.count; + + /* Hand over to kcopyd */ ++ down(&s->cow_count); + dm_kcopyd_copy(s->kcopyd_client, &src, 1, &dest, 0, copy_callback, pe); + } + +@@ -1588,6 +1609,7 @@ static void start_full_bio(struct dm_snap_pending_exception *pe, + pe->full_bio_end_io = bio->bi_end_io; + pe->full_bio_private = bio->bi_private; + ++ down(&s->cow_count); + callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client, + copy_callback, pe); + +-- +2.19.1 + diff --git a/queue-3.18/jffs2-fix-use-of-uninitialized-delayed_work-lockdep-.patch b/queue-3.18/jffs2-fix-use-of-uninitialized-delayed_work-lockdep-.patch new file mode 100644 index 00000000000..4edcbfdf263 --- /dev/null +++ b/queue-3.18/jffs2-fix-use-of-uninitialized-delayed_work-lockdep-.patch @@ -0,0 +1,69 @@ +From f4d0380e61d23cc96d42410a6676bb37105c7f1c Mon Sep 17 00:00:00 2001 +From: Daniel Santos +Date: Fri, 19 Oct 2018 03:30:20 -0500 +Subject: jffs2: Fix use of uninitialized delayed_work, lockdep breakage + +[ Upstream commit a788c5272769ddbcdbab297cf386413eeac04463 ] + +jffs2_sync_fs makes the assumption that if CONFIG_JFFS2_FS_WRITEBUFFER +is defined then a write buffer is available and has been initialized. +However, this does is not the case when the mtd device has no +out-of-band buffer: + +int jffs2_nand_flash_setup(struct jffs2_sb_info *c) +{ + if (!c->mtd->oobsize) + return 0; +... + +The resulting call to cancel_delayed_work_sync passing a uninitialized +(but zeroed) delayed_work struct forces lockdep to become disabled. + +[ 90.050639] overlayfs: upper fs does not support tmpfile. +[ 90.652264] INFO: trying to register non-static key. +[ 90.662171] the code is fine but needs lockdep annotation. +[ 90.673090] turning off the locking correctness validator. +[ 90.684021] CPU: 0 PID: 1762 Comm: mount_root Not tainted 4.14.63 #0 +[ 90.696672] Stack : 00000000 00000000 80d8f6a2 00000038 805f0000 80444600 8fe364f4 805dfbe7 +[ 90.713349] 80563a30 000006e2 8068370c 00000001 00000000 00000001 8e2fdc48 ffffffff +[ 90.730020] 00000000 00000000 80d90000 00000000 00000106 00000000 6465746e 312e3420 +[ 90.746690] 6b636f6c 03bf0000 f8000000 20676e69 00000000 80000000 00000000 8e2c2a90 +[ 90.763362] 80d90000 00000001 00000000 8e2c2a90 00000003 80260dc0 08052098 80680000 +[ 90.780033] ... +[ 90.784902] Call Trace: +[ 90.789793] [<8000f0d8>] show_stack+0xb8/0x148 +[ 90.798659] [<8005a000>] register_lock_class+0x270/0x55c +[ 90.809247] [<8005cb64>] __lock_acquire+0x13c/0xf7c +[ 90.818964] [<8005e314>] lock_acquire+0x194/0x1dc +[ 90.828345] [<8003f27c>] flush_work+0x200/0x24c +[ 90.837374] [<80041dfc>] __cancel_work_timer+0x158/0x210 +[ 90.847958] [<801a8770>] jffs2_sync_fs+0x20/0x54 +[ 90.857173] [<80125cf4>] iterate_supers+0xf4/0x120 +[ 90.866729] [<80158fc4>] sys_sync+0x44/0x9c +[ 90.875067] [<80014424>] syscall_common+0x34/0x58 + +Signed-off-by: Daniel Santos +Reviewed-by: Hou Tao +Signed-off-by: Boris Brezillon +Signed-off-by: Sasha Levin +--- + fs/jffs2/super.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c +index f3194e5147fd..0bbc31d10857 100644 +--- a/fs/jffs2/super.c ++++ b/fs/jffs2/super.c +@@ -101,7 +101,8 @@ static int jffs2_sync_fs(struct super_block *sb, int wait) + struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); + + #ifdef CONFIG_JFFS2_FS_WRITEBUFFER +- cancel_delayed_work_sync(&c->wbuf_dwork); ++ if (jffs2_is_writebuffered(c)) ++ cancel_delayed_work_sync(&c->wbuf_dwork); + #endif + + mutex_lock(&c->alloc_sem); +-- +2.19.1 + diff --git a/queue-3.18/kconfig-fix-memory-leak-when-eof-is-encountered-in-q.patch b/queue-3.18/kconfig-fix-memory-leak-when-eof-is-encountered-in-q.patch new file mode 100644 index 00000000000..f30b3441003 --- /dev/null +++ b/queue-3.18/kconfig-fix-memory-leak-when-eof-is-encountered-in-q.patch @@ -0,0 +1,67 @@ +From 74b09b671ea76ce1d9ecef2cc5b71756f29be8e9 Mon Sep 17 00:00:00 2001 +From: Masahiro Yamada +Date: Tue, 11 Dec 2018 20:00:45 +0900 +Subject: kconfig: fix memory leak when EOF is encountered in quotation + +[ Upstream commit fbac5977d81cb2b2b7e37b11c459055d9585273c ] + +An unterminated string literal followed by new line is passed to the +parser (with "multi-line strings not supported" warning shown), then +handled properly there. + +On the other hand, an unterminated string literal at end of file is +never passed to the parser, then results in memory leak. + +[Test Code] + + ----------(Kconfig begin)---------- + source "Kconfig.inc" + + config A + bool "a" + -----------(Kconfig end)----------- + + --------(Kconfig.inc begin)-------- + config B + bool "b\No new line at end of file + ---------(Kconfig.inc end)--------- + +[Summary from Valgrind] + + Before the fix: + + LEAK SUMMARY: + definitely lost: 16 bytes in 1 blocks + ... + + After the fix: + + LEAK SUMMARY: + definitely lost: 0 bytes in 0 blocks + ... + +Eliminate the memory leak path by handling this case. Of course, such +a Kconfig file is wrong already, so I will add an error message later. + +Signed-off-by: Masahiro Yamada +Signed-off-by: Sasha Levin +--- + scripts/kconfig/zconf.l | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/scripts/kconfig/zconf.l b/scripts/kconfig/zconf.l +index 6c62d93b4ffb..485b19a461f8 100644 +--- a/scripts/kconfig/zconf.l ++++ b/scripts/kconfig/zconf.l +@@ -180,6 +180,8 @@ n [A-Za-z0-9_] + } + <> { + BEGIN(INITIAL); ++ yylval.string = text; ++ return T_WORD_QUOTE; + } + } + +-- +2.19.1 + diff --git a/queue-3.18/media-firewire-fix-app_info-parameter-type-in-avc_ca.patch b/queue-3.18/media-firewire-fix-app_info-parameter-type-in-avc_ca.patch new file mode 100644 index 00000000000..7df8988a6bb --- /dev/null +++ b/queue-3.18/media-firewire-fix-app_info-parameter-type-in-avc_ca.patch @@ -0,0 +1,89 @@ +From 8ea42c25ed3ab5519e7ab03b04b57968841436cb Mon Sep 17 00:00:00 2001 +From: Nathan Chancellor +Date: Thu, 18 Oct 2018 16:03:06 -0400 +Subject: media: firewire: Fix app_info parameter type in avc_ca{,_app}_info + +[ Upstream commit b2e9a4eda11fd2cb1e6714e9ad3f455c402568ff ] + +Clang warns: + +drivers/media/firewire/firedtv-avc.c:999:45: warning: implicit +conversion from 'int' to 'char' changes value from 159 to -97 +[-Wconstant-conversion] + app_info[0] = (EN50221_TAG_APP_INFO >> 16) & 0xff; + ~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~ +drivers/media/firewire/firedtv-avc.c:1000:45: warning: implicit +conversion from 'int' to 'char' changes value from 128 to -128 +[-Wconstant-conversion] + app_info[1] = (EN50221_TAG_APP_INFO >> 8) & 0xff; + ~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~ +drivers/media/firewire/firedtv-avc.c:1040:44: warning: implicit +conversion from 'int' to 'char' changes value from 159 to -97 +[-Wconstant-conversion] + app_info[0] = (EN50221_TAG_CA_INFO >> 16) & 0xff; + ~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~ +drivers/media/firewire/firedtv-avc.c:1041:44: warning: implicit +conversion from 'int' to 'char' changes value from 128 to -128 +[-Wconstant-conversion] + app_info[1] = (EN50221_TAG_CA_INFO >> 8) & 0xff; + ~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~ +4 warnings generated. + +Change app_info's type to unsigned char to match the type of the +member msg in struct ca_msg, which is the only thing passed into the +app_info parameter in this function. + +Link: https://github.com/ClangBuiltLinux/linux/issues/105 + +Signed-off-by: Nathan Chancellor +Signed-off-by: Mauro Carvalho Chehab +Signed-off-by: Sasha Levin +--- + drivers/media/firewire/firedtv-avc.c | 6 ++++-- + drivers/media/firewire/firedtv.h | 6 ++++-- + 2 files changed, 8 insertions(+), 4 deletions(-) + +diff --git a/drivers/media/firewire/firedtv-avc.c b/drivers/media/firewire/firedtv-avc.c +index 251a556112a9..280b5ffea592 100644 +--- a/drivers/media/firewire/firedtv-avc.c ++++ b/drivers/media/firewire/firedtv-avc.c +@@ -968,7 +968,8 @@ static int get_ca_object_length(struct avc_response_frame *r) + return r->operand[7]; + } + +-int avc_ca_app_info(struct firedtv *fdtv, char *app_info, unsigned int *len) ++int avc_ca_app_info(struct firedtv *fdtv, unsigned char *app_info, ++ unsigned int *len) + { + struct avc_command_frame *c = (void *)fdtv->avc_data; + struct avc_response_frame *r = (void *)fdtv->avc_data; +@@ -1009,7 +1010,8 @@ out: + return ret; + } + +-int avc_ca_info(struct firedtv *fdtv, char *app_info, unsigned int *len) ++int avc_ca_info(struct firedtv *fdtv, unsigned char *app_info, ++ unsigned int *len) + { + struct avc_command_frame *c = (void *)fdtv->avc_data; + struct avc_response_frame *r = (void *)fdtv->avc_data; +diff --git a/drivers/media/firewire/firedtv.h b/drivers/media/firewire/firedtv.h +index c2ba085e0d20..54853159482e 100644 +--- a/drivers/media/firewire/firedtv.h ++++ b/drivers/media/firewire/firedtv.h +@@ -124,8 +124,10 @@ int avc_lnb_control(struct firedtv *fdtv, char voltage, char burst, + struct dvb_diseqc_master_cmd *diseqcmd); + void avc_remote_ctrl_work(struct work_struct *work); + int avc_register_remote_control(struct firedtv *fdtv); +-int avc_ca_app_info(struct firedtv *fdtv, char *app_info, unsigned int *len); +-int avc_ca_info(struct firedtv *fdtv, char *app_info, unsigned int *len); ++int avc_ca_app_info(struct firedtv *fdtv, unsigned char *app_info, ++ unsigned int *len); ++int avc_ca_info(struct firedtv *fdtv, unsigned char *app_info, ++ unsigned int *len); + int avc_ca_reset(struct firedtv *fdtv); + int avc_ca_pmt(struct firedtv *fdtv, char *app_info, int length); + int avc_ca_get_time_date(struct firedtv *fdtv, int *interval); +-- +2.19.1 + diff --git a/queue-3.18/mips-sibyte-enable-swiotlb-for-swarm-littlesur-and-b.patch b/queue-3.18/mips-sibyte-enable-swiotlb-for-swarm-littlesur-and-b.patch new file mode 100644 index 00000000000..8f71c87a82b --- /dev/null +++ b/queue-3.18/mips-sibyte-enable-swiotlb-for-swarm-littlesur-and-b.patch @@ -0,0 +1,155 @@ +From a667b7548a8f960b8edaabcc40c4013686cdd1ac Mon Sep 17 00:00:00 2001 +From: "Maciej W. Rozycki" +Date: Tue, 13 Nov 2018 22:42:44 +0000 +Subject: MIPS: SiByte: Enable swiotlb for SWARM, LittleSur and BigSur + +[ Upstream commit e4849aff1e169b86c561738daf8ff020e9de1011 ] + +The Broadcom SiByte BCM1250, BCM1125, and BCM1125H SOCs have an onchip +DRAM controller that supports memory amounts of up to 16GiB, and due to +how the address decoder has been wired in the SOC any memory beyond 1GiB +is actually mapped starting from 4GiB physical up, that is beyond the +32-bit addressable limit[1]. Consequently if the maximum amount of +memory has been installed, then it will span up to 19GiB. + +Many of the evaluation boards we support that are based on one of these +SOCs have their memory soldered and the amount present fits in the +32-bit address range. The BCM91250A SWARM board however has actual DIMM +slots and accepts, depending on the peripherals revision of the SOC, up +to 4GiB or 8GiB of memory in commercially available JEDEC modules[2]. +I believe this is also the case with the BCM91250C2 LittleSur board. +This means that up to either 3GiB or 7GiB of memory requires 64-bit +addressing to access. + +I believe the BCM91480B BigSur board, which has the BCM1480 SOC instead, +accepts at least as much memory, although I have no documentation or +actual hardware available to verify that. + +Both systems have PCI slots installed for use by any PCI option boards, +including ones that only support 32-bit addressing (additionally the +32-bit PCI host bridge of the BCM1250, BCM1125, and BCM1125H SOCs limits +addressing to 32-bits), and there is no IOMMU available. Therefore for +PCI DMA to work in the presence of memory beyond enable swiotlb for the +affected systems. + +All the other SOC onchip DMA devices use 40-bit addressing and therefore +can address the whole memory, so only enable swiotlb if PCI support and +support for DMA beyond 4GiB have been both enabled in the configuration +of the kernel. + +This shows up as follows: + +Broadcom SiByte BCM1250 B2 @ 800 MHz (SB1 rev 2) +Board type: SiByte BCM91250A (SWARM) +Determined physical RAM map: + memory: 000000000fe7fe00 @ 0000000000000000 (usable) + memory: 000000001ffffe00 @ 0000000080000000 (usable) + memory: 000000000ffffe00 @ 00000000c0000000 (usable) + memory: 0000000087fffe00 @ 0000000100000000 (usable) +software IO TLB: mapped [mem 0xcbffc000-0xcfffc000] (64MB) + +in the bootstrap log and removes failures like these: + +defxx 0000:02:00.0: dma_direct_map_page: overflow 0x0000000185bc6080+4608 of device mask ffffffff bus mask 0 +fddi0: Receive buffer allocation failed +fddi0: Adapter open failed! +IP-Config: Failed to open fddi0 +defxx 0000:09:08.0: dma_direct_map_page: overflow 0x0000000185bc6080+4608 of device mask ffffffff bus mask 0 +fddi1: Receive buffer allocation failed +fddi1: Adapter open failed! +IP-Config: Failed to open fddi1 + +when memory beyond 4GiB is handed out to devices that can only do 32-bit +addressing. + +This updates commit cce335ae47e2 ("[MIPS] 64-bit Sibyte kernels need +DMA32."). + +References: + +[1] "BCM1250/BCM1125/BCM1125H User Manual", Revision 1250_1125-UM100-R, + Broadcom Corporation, 21 Oct 2002, Section 3: "System Overview", + "Memory Map", pp. 34-38 + +[2] "BCM91250A User Manual", Revision 91250A-UM100-R, Broadcom + Corporation, 18 May 2004, Section 3: "Physical Description", + "Supported DRAM", p. 23 + +Signed-off-by: Maciej W. Rozycki +[paul.burton@mips.com: Remove GPL text from dma.c; SPDX tag covers it] +Signed-off-by: Paul Burton +Reviewed-by: Christoph Hellwig +Patchwork: https://patchwork.linux-mips.org/patch/21108/ +References: cce335ae47e2 ("[MIPS] 64-bit Sibyte kernels need DMA32.") +Cc: Ralf Baechle +Cc: linux-mips@linux-mips.org +Cc: linux-kernel@vger.kernel.org +Signed-off-by: Sasha Levin +--- + arch/mips/Kconfig | 3 +++ + arch/mips/sibyte/common/Makefile | 1 + + arch/mips/sibyte/common/dma.c | 14 ++++++++++++++ + 3 files changed, 18 insertions(+) + create mode 100644 arch/mips/sibyte/common/dma.c + +diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig +index 9536ef912f59..077ae203e8f9 100644 +--- a/arch/mips/Kconfig ++++ b/arch/mips/Kconfig +@@ -627,6 +627,7 @@ config SIBYTE_SWARM + select SYS_SUPPORTS_HIGHMEM + select SYS_SUPPORTS_LITTLE_ENDIAN + select ZONE_DMA32 if 64BIT ++ select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI + + config SIBYTE_LITTLESUR + bool "Sibyte BCM91250C2-LittleSur" +@@ -649,6 +650,7 @@ config SIBYTE_SENTOSA + select SYS_HAS_CPU_SB1 + select SYS_SUPPORTS_BIG_ENDIAN + select SYS_SUPPORTS_LITTLE_ENDIAN ++ select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI + + config SIBYTE_BIGSUR + bool "Sibyte BCM91480B-BigSur" +@@ -662,6 +664,7 @@ config SIBYTE_BIGSUR + select SYS_SUPPORTS_HIGHMEM + select SYS_SUPPORTS_LITTLE_ENDIAN + select ZONE_DMA32 if 64BIT ++ select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI + + config SNI_RM + bool "SNI RM200/300/400" +diff --git a/arch/mips/sibyte/common/Makefile b/arch/mips/sibyte/common/Makefile +index b3d6bf23a662..3ef3fb658136 100644 +--- a/arch/mips/sibyte/common/Makefile ++++ b/arch/mips/sibyte/common/Makefile +@@ -1,4 +1,5 @@ + obj-y := cfe.o ++obj-$(CONFIG_SWIOTLB) += dma.o + obj-$(CONFIG_SIBYTE_BUS_WATCHER) += bus_watcher.o + obj-$(CONFIG_SIBYTE_CFE_CONSOLE) += cfe_console.o + obj-$(CONFIG_SIBYTE_TBPROF) += sb_tbprof.o +diff --git a/arch/mips/sibyte/common/dma.c b/arch/mips/sibyte/common/dma.c +new file mode 100644 +index 000000000000..eb47a94f3583 +--- /dev/null ++++ b/arch/mips/sibyte/common/dma.c +@@ -0,0 +1,14 @@ ++// SPDX-License-Identifier: GPL-2.0+ ++/* ++ * DMA support for Broadcom SiByte platforms. ++ * ++ * Copyright (c) 2018 Maciej W. Rozycki ++ */ ++ ++#include ++#include ++ ++void __init plat_swiotlb_setup(void) ++{ ++ swiotlb_init(1); ++} +-- +2.19.1 + diff --git a/queue-3.18/mm-proc-be-more-verbose-about-unstable-vma-flags-in-.patch b/queue-3.18/mm-proc-be-more-verbose-about-unstable-vma-flags-in-.patch new file mode 100644 index 00000000000..e48d954e7c0 --- /dev/null +++ b/queue-3.18/mm-proc-be-more-verbose-about-unstable-vma-flags-in-.patch @@ -0,0 +1,107 @@ +From cd817dd3465b503a0cff79801753ecb2a436fb18 Mon Sep 17 00:00:00 2001 +From: Michal Hocko +Date: Fri, 28 Dec 2018 00:38:17 -0800 +Subject: mm, proc: be more verbose about unstable VMA flags in + /proc//smaps + +[ Upstream commit 7550c6079846a24f30d15ac75a941c8515dbedfb ] + +Patch series "THP eligibility reporting via proc". + +This series of three patches aims at making THP eligibility reporting much +more robust and long term sustainable. The trigger for the change is a +regression report [2] and the long follow up discussion. In short the +specific application didn't have good API to query whether a particular +mapping can be backed by THP so it has used VMA flags to workaround that. +These flags represent a deep internal state of VMAs and as such they +should be used by userspace with a great deal of caution. + +A similar has happened for [3] when users complained that VM_MIXEDMAP is +no longer set on DAX mappings. Again a lack of a proper API led to an +abuse. + +The first patch in the series tries to emphasise that that the semantic of +flags might change and any application consuming those should be really +careful. + +The remaining two patches provide a more suitable interface to address [2] +and provide a consistent API to query the THP status both for each VMA and +process wide as well. [1] + +http://lkml.kernel.org/r/20181120103515.25280-1-mhocko@kernel.org [2] +http://lkml.kernel.org/r/http://lkml.kernel.org/r/alpine.DEB.2.21.1809241054050.224429@chino.kir.corp.google.com +[3] http://lkml.kernel.org/r/20181002100531.GC4135@quack2.suse.cz + +This patch (of 3): + +Even though vma flags exported via /proc//smaps are explicitly +documented to be not guaranteed for future compatibility the warning +doesn't go far enough because it doesn't mention semantic changes to those +flags. And they are important as well because these flags are a deep +implementation internal to the MM code and the semantic might change at +any time. + +Let's consider two recent examples: +http://lkml.kernel.org/r/20181002100531.GC4135@quack2.suse.cz +: commit e1fb4a086495 "dax: remove VM_MIXEDMAP for fsdax and device dax" has +: removed VM_MIXEDMAP flag from DAX VMAs. Now our testing shows that in the +: mean time certain customer of ours started poking into /proc//smaps +: and looks at VMA flags there and if VM_MIXEDMAP is missing among the VMA +: flags, the application just fails to start complaining that DAX support is +: missing in the kernel. + +http://lkml.kernel.org/r/alpine.DEB.2.21.1809241054050.224429@chino.kir.corp.google.com +: Commit 1860033237d4 ("mm: make PR_SET_THP_DISABLE immediately active") +: introduced a regression in that userspace cannot always determine the set +: of vmas where thp is ineligible. +: Userspace relies on the "nh" flag being emitted as part of /proc/pid/smaps +: to determine if a vma is eligible to be backed by hugepages. +: Previous to this commit, prctl(PR_SET_THP_DISABLE, 1) would cause thp to +: be disabled and emit "nh" as a flag for the corresponding vmas as part of +: /proc/pid/smaps. After the commit, thp is disabled by means of an mm +: flag and "nh" is not emitted. +: This causes smaps parsing libraries to assume a vma is eligible for thp +: and ends up puzzling the user on why its memory is not backed by thp. + +In both cases userspace was relying on a semantic of a specific VMA flag. +The primary reason why that happened is a lack of a proper interface. +While this has been worked on and it will be fixed properly, it seems that +our wording could see some refinement and be more vocal about semantic +aspect of these flags as well. + +Link: http://lkml.kernel.org/r/20181211143641.3503-2-mhocko@kernel.org +Signed-off-by: Michal Hocko +Acked-by: Jan Kara +Acked-by: Dan Williams +Acked-by: David Rientjes +Acked-by: Mike Rapoport +Acked-by: Vlastimil Babka +Cc: Dan Williams +Cc: David Rientjes +Cc: Paul Oppenheimer +Cc: William Kucharski +Signed-off-by: Andrew Morton +Signed-off-by: Linus Torvalds +Signed-off-by: Sasha Levin +--- + Documentation/filesystems/proc.txt | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt +index 04b23a83ce68..3172a2465ff2 100644 +--- a/Documentation/filesystems/proc.txt ++++ b/Documentation/filesystems/proc.txt +@@ -439,7 +439,9 @@ manner. The codes are the following: + + Note that there is no guarantee that every flag and associated mnemonic will + be present in all further kernel releases. Things get changed, the flags may +-be vanished or the reverse -- new added. ++be vanished or the reverse -- new added. Interpretation of their meaning ++might change in future as well. So each consumer of these flags has to ++follow each specific kernel version for the exact semantic. + + This file is only present if the CONFIG_MMU kernel configuration option is + enabled. +-- +2.19.1 + diff --git a/queue-3.18/mmc-atmel-mci-do-not-assume-idle-after-atmci_request.patch b/queue-3.18/mmc-atmel-mci-do-not-assume-idle-after-atmci_request.patch new file mode 100644 index 00000000000..03567d5883a --- /dev/null +++ b/queue-3.18/mmc-atmel-mci-do-not-assume-idle-after-atmci_request.patch @@ -0,0 +1,68 @@ +From 448b8ad7eaec7858f84db86fd4a286d89437533a Mon Sep 17 00:00:00 2001 +From: Jonas Danielsson +Date: Fri, 19 Oct 2018 16:40:05 +0200 +Subject: mmc: atmel-mci: do not assume idle after atmci_request_end + +[ Upstream commit ae460c115b7aa50c9a36cf78fced07b27962c9d0 ] + +On our AT91SAM9260 board we use the same sdio bus for wifi and for the +sd card slot. This caused the atmel-mci to give the following splat on +the serial console: + + ------------[ cut here ]------------ + WARNING: CPU: 0 PID: 538 at drivers/mmc/host/atmel-mci.c:859 atmci_send_command+0x24/0x44 + Modules linked in: + CPU: 0 PID: 538 Comm: mmcqd/0 Not tainted 4.14.76 #14 + Hardware name: Atmel AT91SAM9 + [] (unwind_backtrace) from [] (show_stack+0x10/0x14) + [] (show_stack) from [] (__warn+0xd8/0xf4) + [] (__warn) from [] (warn_slowpath_null+0x1c/0x24) + [] (warn_slowpath_null) from [] (atmci_send_command+0x24/0x44) + [] (atmci_send_command) from [] (atmci_start_request+0x1f4/0x2dc) + [] (atmci_start_request) from [] (atmci_request+0xf0/0x164) + [] (atmci_request) from [] (mmc_start_request+0x280/0x2d0) + [] (mmc_start_request) from [] (mmc_start_areq+0x230/0x330) + [] (mmc_start_areq) from [] (mmc_blk_issue_rw_rq+0xc4/0x310) + [] (mmc_blk_issue_rw_rq) from [] (mmc_blk_issue_rq+0x118/0x5ac) + [] (mmc_blk_issue_rq) from [] (mmc_queue_thread+0xc4/0x118) + [] (mmc_queue_thread) from [] (kthread+0x100/0x118) + [] (kthread) from [] (ret_from_fork+0x14/0x34) + ---[ end trace 594371ddfa284bd6 ]--- + +This is: + WARN_ON(host->cmd); + +This was fixed on our board by letting atmci_request_end determine what +state we are in. Instead of unconditionally setting it to STATE_IDLE on +STATE_END_REQUEST. + +Signed-off-by: Jonas Danielsson +Signed-off-by: Ulf Hansson +Signed-off-by: Sasha Levin +--- + drivers/mmc/host/atmel-mci.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c +index 6423083c5238..bacc0368db6b 100644 +--- a/drivers/mmc/host/atmel-mci.c ++++ b/drivers/mmc/host/atmel-mci.c +@@ -1838,13 +1838,14 @@ static void atmci_tasklet_func(unsigned long priv) + } + + atmci_request_end(host, host->mrq); +- state = STATE_IDLE; ++ goto unlock; /* atmci_request_end() sets host->state */ + break; + } + } while (state != prev_state); + + host->state = state; + ++unlock: + spin_unlock(&host->lock); + } + +-- +2.19.1 + diff --git a/queue-3.18/net-call-sk_dst_reset-when-set-so_dontroute.patch b/queue-3.18/net-call-sk_dst_reset-when-set-so_dontroute.patch new file mode 100644 index 00000000000..3a9e0a904b9 --- /dev/null +++ b/queue-3.18/net-call-sk_dst_reset-when-set-so_dontroute.patch @@ -0,0 +1,65 @@ +From c6a5e6907e1d133f83ce8483e958f0f4fe43453d Mon Sep 17 00:00:00 2001 +From: yupeng +Date: Wed, 5 Dec 2018 18:56:28 -0800 +Subject: net: call sk_dst_reset when set SO_DONTROUTE + +[ Upstream commit 0fbe82e628c817e292ff588cd5847fc935e025f2 ] + +after set SO_DONTROUTE to 1, the IP layer should not route packets if +the dest IP address is not in link scope. But if the socket has cached +the dst_entry, such packets would be routed until the sk_dst_cache +expires. So we should clean the sk_dst_cache when a user set +SO_DONTROUTE option. Below are server/client python scripts which +could reprodue this issue: + +server side code: + +========================================================================== +import socket +import struct +import time + +s = socket.socket(socket.AF_INET, socket.SOCK_STREAM) +s.bind(('0.0.0.0', 9000)) +s.listen(1) +sock, addr = s.accept() +sock.setsockopt(socket.SOL_SOCKET, socket.SO_DONTROUTE, struct.pack('i', 1)) +while True: + sock.send(b'foo') + time.sleep(1) +========================================================================== + +client side code: +========================================================================== +import socket +import time + +s = socket.socket(socket.AF_INET, socket.SOCK_STREAM) +s.connect(('server_address', 9000)) +while True: + data = s.recv(1024) + print(data) +========================================================================== + +Signed-off-by: yupeng +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/core/sock.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/net/core/sock.c b/net/core/sock.c +index 91ee0eb70fcf..039f101e7807 100644 +--- a/net/core/sock.c ++++ b/net/core/sock.c +@@ -720,6 +720,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, + break; + case SO_DONTROUTE: + sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); ++ sk_dst_reset(sk); + break; + case SO_BROADCAST: + sock_valbool_flag(sk, SOCK_BROADCAST, valbool); +-- +2.19.1 + diff --git a/queue-3.18/ocfs2-fix-panic-due-to-unrecovered-local-alloc.patch b/queue-3.18/ocfs2-fix-panic-due-to-unrecovered-local-alloc.patch new file mode 100644 index 00000000000..45fb2e31b62 --- /dev/null +++ b/queue-3.18/ocfs2-fix-panic-due-to-unrecovered-local-alloc.patch @@ -0,0 +1,105 @@ +From fabcc4ccb617fa1d2efcb1792badc7ec7d2126ad Mon Sep 17 00:00:00 2001 +From: Junxiao Bi +Date: Fri, 28 Dec 2018 00:32:50 -0800 +Subject: ocfs2: fix panic due to unrecovered local alloc + +[ Upstream commit 532e1e54c8140188e192348c790317921cb2dc1c ] + +mount.ocfs2 ignore the inconsistent error that journal is clean but +local alloc is unrecovered. After mount, local alloc not empty, then +reserver cluster didn't alloc a new local alloc window, reserveration +map is empty(ocfs2_reservation_map.m_bitmap_len = 0), that triggered the +following panic. + +This issue was reported at + + https://oss.oracle.com/pipermail/ocfs2-devel/2015-May/010854.html + +and was advised to fixed during mount. But this is a very unusual +inconsistent state, usually journal dirty flag should be cleared at the +last stage of umount until every other things go right. We may need do +further debug to check that. Any way to avoid possible futher +corruption, mount should be abort and fsck should be run. + + (mount.ocfs2,1765,1):ocfs2_load_local_alloc:353 ERROR: Local alloc hasn't been recovered! + found = 6518, set = 6518, taken = 8192, off = 15912372 + ocfs2: Mounting device (202,64) on (node 0, slot 3) with ordered data mode. + o2dlm: Joining domain 89CEAC63CC4F4D03AC185B44E0EE0F3F ( 0 1 2 3 4 5 6 8 ) 8 nodes + ocfs2: Mounting device (202,80) on (node 0, slot 3) with ordered data mode. + o2hb: Region 89CEAC63CC4F4D03AC185B44E0EE0F3F (xvdf) is now a quorum device + o2net: Accepted connection from node yvwsoa17p (num 7) at 172.22.77.88:7777 + o2dlm: Node 7 joins domain 64FE421C8C984E6D96ED12C55FEE2435 ( 0 1 2 3 4 5 6 7 8 ) 9 nodes + o2dlm: Node 7 joins domain 89CEAC63CC4F4D03AC185B44E0EE0F3F ( 0 1 2 3 4 5 6 7 8 ) 9 nodes + ------------[ cut here ]------------ + kernel BUG at fs/ocfs2/reservations.c:507! + invalid opcode: 0000 [#1] SMP + Modules linked in: ocfs2 rpcsec_gss_krb5 auth_rpcgss nfsv4 nfs fscache lockd grace ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue configfs sunrpc ipt_REJECT nf_reject_ipv4 nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_reject_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm ib_sa ib_mad ib_core ib_addr ipv6 ovmapi ppdev parport_pc parport xen_netfront fb_sys_fops sysimgblt sysfillrect syscopyarea acpi_cpufreq pcspkr i2c_piix4 i2c_core sg ext4 jbd2 mbcache2 sr_mod cdrom xen_blkfront pata_acpi ata_generic ata_piix floppy dm_mirror dm_region_hash dm_log dm_mod + CPU: 0 PID: 4349 Comm: startWebLogic.s Not tainted 4.1.12-124.19.2.el6uek.x86_64 #2 + Hardware name: Xen HVM domU, BIOS 4.4.4OVM 09/06/2018 + task: ffff8803fb04e200 ti: ffff8800ea4d8000 task.ti: ffff8800ea4d8000 + RIP: 0010:[] [] __ocfs2_resv_find_window+0x498/0x760 [ocfs2] + Call Trace: + ocfs2_resmap_resv_bits+0x10d/0x400 [ocfs2] + ocfs2_claim_local_alloc_bits+0xd0/0x640 [ocfs2] + __ocfs2_claim_clusters+0x178/0x360 [ocfs2] + ocfs2_claim_clusters+0x1f/0x30 [ocfs2] + ocfs2_convert_inline_data_to_extents+0x634/0xa60 [ocfs2] + ocfs2_write_begin_nolock+0x1c6/0x1da0 [ocfs2] + ocfs2_write_begin+0x13e/0x230 [ocfs2] + generic_perform_write+0xbf/0x1c0 + __generic_file_write_iter+0x19c/0x1d0 + ocfs2_file_write_iter+0x589/0x1360 [ocfs2] + __vfs_write+0xb8/0x110 + vfs_write+0xa9/0x1b0 + SyS_write+0x46/0xb0 + system_call_fastpath+0x18/0xd7 + Code: ff ff 8b 75 b8 39 75 b0 8b 45 c8 89 45 98 0f 84 e5 fe ff ff 45 8b 74 24 18 41 8b 54 24 1c e9 56 fc ff ff 85 c0 0f 85 48 ff ff ff <0f> 0b 48 8b 05 cf c3 de ff 48 ba 00 00 00 00 00 00 00 10 48 85 + RIP __ocfs2_resv_find_window+0x498/0x760 [ocfs2] + RSP + ---[ end trace 566f07529f2edf3c ]--- + Kernel panic - not syncing: Fatal exception + Kernel Offset: disabled + +Link: http://lkml.kernel.org/r/20181121020023.3034-2-junxiao.bi@oracle.com +Signed-off-by: Junxiao Bi +Reviewed-by: Yiwen Jiang +Acked-by: Joseph Qi +Cc: Jun Piao +Cc: Mark Fasheh +Cc: Joel Becker +Cc: Changwei Ge +Signed-off-by: Andrew Morton +Signed-off-by: Linus Torvalds +Signed-off-by: Sasha Levin +--- + fs/ocfs2/localalloc.c | 9 +++++++-- + 1 file changed, 7 insertions(+), 2 deletions(-) + +diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c +index 044013455621..12675bb5304a 100644 +--- a/fs/ocfs2/localalloc.c ++++ b/fs/ocfs2/localalloc.c +@@ -345,13 +345,18 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb) + if (num_used + || alloc->id1.bitmap1.i_used + || alloc->id1.bitmap1.i_total +- || la->la_bm_off) +- mlog(ML_ERROR, "Local alloc hasn't been recovered!\n" ++ || la->la_bm_off) { ++ mlog(ML_ERROR, "inconsistent detected, clean journal with" ++ " unrecovered local alloc, please run fsck.ocfs2!\n" + "found = %u, set = %u, taken = %u, off = %u\n", + num_used, le32_to_cpu(alloc->id1.bitmap1.i_used), + le32_to_cpu(alloc->id1.bitmap1.i_total), + OCFS2_LOCAL_ALLOC(alloc)->la_bm_off); + ++ status = -EINVAL; ++ goto bail; ++ } ++ + osb->local_alloc_bh = alloc_bh; + osb->local_alloc_state = OCFS2_LA_ENABLED; + +-- +2.19.1 + diff --git a/queue-3.18/perf-parse-events-fix-unchecked-usage-of-strncpy.patch b/queue-3.18/perf-parse-events-fix-unchecked-usage-of-strncpy.patch new file mode 100644 index 00000000000..52d91e92651 --- /dev/null +++ b/queue-3.18/perf-parse-events-fix-unchecked-usage-of-strncpy.patch @@ -0,0 +1,56 @@ +From 77a58a00aa765d316f243d0ff7ddd7e91c55a111 Mon Sep 17 00:00:00 2001 +From: Arnaldo Carvalho de Melo +Date: Thu, 6 Dec 2018 13:52:13 -0300 +Subject: perf parse-events: Fix unchecked usage of strncpy() + +[ Upstream commit bd8d57fb7e25e9fcf67a9eef5fa13aabe2016e07 ] + +The strncpy() function may leave the destination string buffer +unterminated, better use strlcpy() that we have a __weak fallback +implementation for systems without it. + +This fixes this warning on an Alpine Linux Edge system with gcc 8.2: + + util/parse-events.c: In function 'print_symbol_events': + util/parse-events.c:2465:4: error: 'strncpy' specified bound 100 equals destination size [-Werror=stringop-truncation] + strncpy(name, syms->symbol, MAX_NAME_LEN); + ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + In function 'print_symbol_events.constprop', + inlined from 'print_events' at util/parse-events.c:2508:2: + util/parse-events.c:2465:4: error: 'strncpy' specified bound 100 equals destination size [-Werror=stringop-truncation] + strncpy(name, syms->symbol, MAX_NAME_LEN); + ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + In function 'print_symbol_events.constprop', + inlined from 'print_events' at util/parse-events.c:2511:2: + util/parse-events.c:2465:4: error: 'strncpy' specified bound 100 equals destination size [-Werror=stringop-truncation] + strncpy(name, syms->symbol, MAX_NAME_LEN); + ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + cc1: all warnings being treated as errors + +Cc: Adrian Hunter +Cc: Jiri Olsa +Cc: Namhyung Kim +Fixes: 947b4ad1d198 ("perf list: Fix max event string size") +Link: https://lkml.kernel.org/n/tip-b663e33bm6x8hrkie4uxh7u2@git.kernel.org +Signed-off-by: Arnaldo Carvalho de Melo +Signed-off-by: Sasha Levin +--- + tools/perf/util/parse-events.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c +index c659a3ca1283..78b452421375 100644 +--- a/tools/perf/util/parse-events.c ++++ b/tools/perf/util/parse-events.c +@@ -1319,7 +1319,7 @@ static void print_symbol_events(const char *event_glob, unsigned type, + if (strlen(syms->alias)) + snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias); + else +- strncpy(name, syms->symbol, MAX_NAME_LEN); ++ strlcpy(name, syms->symbol, MAX_NAME_LEN); + + printf(" %-50s [%s]\n", name, event_type_descriptors[type]); + +-- +2.19.1 + diff --git a/queue-3.18/perf-svghelper-fix-unchecked-usage-of-strncpy.patch b/queue-3.18/perf-svghelper-fix-unchecked-usage-of-strncpy.patch new file mode 100644 index 00000000000..0fb1fc5c378 --- /dev/null +++ b/queue-3.18/perf-svghelper-fix-unchecked-usage-of-strncpy.patch @@ -0,0 +1,55 @@ +From 0dcc456be195f11e054f69b6d2c4c4bcb0865156 Mon Sep 17 00:00:00 2001 +From: Arnaldo Carvalho de Melo +Date: Thu, 6 Dec 2018 11:29:48 -0300 +Subject: perf svghelper: Fix unchecked usage of strncpy() + +[ Upstream commit 2f5302533f306d5ee87bd375aef9ca35b91762cb ] + +The strncpy() function may leave the destination string buffer +unterminated, better use strlcpy() that we have a __weak fallback +implementation for systems without it. + +In this specific case this would only happen if fgets() was buggy, as +its man page states that it should read one less byte than the size of +the destination buffer, so that it can put the nul byte at the end of +it, so it would never copy 255 non-nul chars, as fgets reads into the +orig buffer at most 254 non-nul chars and terminates it. But lets just +switch to strlcpy to keep the original intent and silence the gcc 8.2 +warning. + +This fixes this warning on an Alpine Linux Edge system with gcc 8.2: + + In function 'cpu_model', + inlined from 'svg_cpu_box' at util/svghelper.c:378:2: + util/svghelper.c:337:5: error: 'strncpy' output may be truncated copying 255 bytes from a string of length 255 [-Werror=stringop-truncation] + strncpy(cpu_m, &buf[13], 255); + ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Cc: Adrian Hunter +Cc: Jiri Olsa +Cc: Namhyung Kim +Cc: Arjan van de Ven +Fixes: f48d55ce7871 ("perf: Add a SVG helper library file") +Link: https://lkml.kernel.org/n/tip-xzkoo0gyr56gej39ltivuh9g@git.kernel.org +Signed-off-by: Arnaldo Carvalho de Melo +Signed-off-by: Sasha Levin +--- + tools/perf/util/svghelper.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c +index 283d3e73e2f2..48a841462536 100644 +--- a/tools/perf/util/svghelper.c ++++ b/tools/perf/util/svghelper.c +@@ -333,7 +333,7 @@ static char *cpu_model(void) + if (file) { + while (fgets(buf, 255, file)) { + if (strstr(buf, "model name")) { +- strncpy(cpu_m, &buf[13], 255); ++ strlcpy(cpu_m, &buf[13], 255); + break; + } + } +-- +2.19.1 + diff --git a/queue-3.18/powerpc-pseries-cpuidle-fix-preempt-warning.patch b/queue-3.18/powerpc-pseries-cpuidle-fix-preempt-warning.patch new file mode 100644 index 00000000000..14bd91c47e7 --- /dev/null +++ b/queue-3.18/powerpc-pseries-cpuidle-fix-preempt-warning.patch @@ -0,0 +1,68 @@ +From f42eb4e52536e370a61e69435cbcb26ea87f2950 Mon Sep 17 00:00:00 2001 +From: Breno Leitao +Date: Fri, 23 Nov 2018 14:30:11 -0200 +Subject: powerpc/pseries/cpuidle: Fix preempt warning + +[ Upstream commit 2b038cbc5fcf12a7ee1cc9bfd5da1e46dacdee87 ] + +When booting a pseries kernel with PREEMPT enabled, it dumps the +following warning: + + BUG: using smp_processor_id() in preemptible [00000000] code: swapper/0/1 + caller is pseries_processor_idle_init+0x5c/0x22c + CPU: 13 PID: 1 Comm: swapper/0 Not tainted 4.20.0-rc3-00090-g12201a0128bc-dirty #828 + Call Trace: + [c000000429437ab0] [c0000000009c8878] dump_stack+0xec/0x164 (unreliable) + [c000000429437b00] [c0000000005f2f24] check_preemption_disabled+0x154/0x160 + [c000000429437b90] [c000000000cab8e8] pseries_processor_idle_init+0x5c/0x22c + [c000000429437c10] [c000000000010ed4] do_one_initcall+0x64/0x300 + [c000000429437ce0] [c000000000c54500] kernel_init_freeable+0x3f0/0x500 + [c000000429437db0] [c0000000000112dc] kernel_init+0x2c/0x160 + [c000000429437e20] [c00000000000c1d0] ret_from_kernel_thread+0x5c/0x6c + +This happens because the code calls get_lppaca() which calls +get_paca() and it checks if preemption is disabled through +check_preemption_disabled(). + +Preemption should be disabled because the per CPU variable may make no +sense if there is a preemption (and a CPU switch) after it reads the +per CPU data and when it is used. + +In this device driver specifically, it is not a problem, because this +code just needs to have access to one lppaca struct, and it does not +matter if it is the current per CPU lppaca struct or not (i.e. when +there is a preemption and a CPU migration). + +That said, the most appropriate fix seems to be related to avoiding +the debug_smp_processor_id() call at get_paca(), instead of calling +preempt_disable() before get_paca(). + +Signed-off-by: Breno Leitao +Signed-off-by: Michael Ellerman +Signed-off-by: Sasha Levin +--- + drivers/cpuidle/cpuidle-pseries.c | 8 +++++++- + 1 file changed, 7 insertions(+), 1 deletion(-) + +diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c +index 6f7b01956885..b755d3a54e3c 100644 +--- a/drivers/cpuidle/cpuidle-pseries.c ++++ b/drivers/cpuidle/cpuidle-pseries.c +@@ -237,7 +237,13 @@ static int pseries_idle_probe(void) + return -ENODEV; + + if (firmware_has_feature(FW_FEATURE_SPLPAR)) { +- if (lppaca_shared_proc(get_lppaca())) { ++ /* ++ * Use local_paca instead of get_lppaca() since ++ * preemption is not disabled, and it is not required in ++ * fact, since lppaca_ptr does not need to be the value ++ * associated to the current CPU, it can be from any CPU. ++ */ ++ if (lppaca_shared_proc(local_paca->lppaca_ptr)) { + cpuidle_state_table = shared_states; + max_idle_state = ARRAY_SIZE(shared_states); + } else { +-- +2.19.1 + diff --git a/queue-3.18/pstore-ram-do-not-treat-empty-buffers-as-valid.patch b/queue-3.18/pstore-ram-do-not-treat-empty-buffers-as-valid.patch new file mode 100644 index 00000000000..72d60872603 --- /dev/null +++ b/queue-3.18/pstore-ram-do-not-treat-empty-buffers-as-valid.patch @@ -0,0 +1,51 @@ +From 4e4e4cb6de9190e48206f648e28bb91397970617 Mon Sep 17 00:00:00 2001 +From: "Joel Fernandes (Google)" +Date: Sat, 3 Nov 2018 16:38:18 -0700 +Subject: pstore/ram: Do not treat empty buffers as valid + +[ Upstream commit 30696378f68a9e3dad6bfe55938b112e72af00c2 ] + +The ramoops backend currently calls persistent_ram_save_old() even +if a buffer is empty. While this appears to work, it is does not seem +like the right thing to do and could lead to future bugs so lets avoid +that. It also prevents misleading prints in the logs which claim the +buffer is valid. + +I got something like: + + found existing buffer, size 0, start 0 + +When I was expecting: + + no valid data in buffer (sig = ...) + +This bails out early (and reports with pr_debug()), since it's an +acceptable state. + +Signed-off-by: Joel Fernandes (Google) +Co-developed-by: Kees Cook +Signed-off-by: Kees Cook +Signed-off-by: Sasha Levin +--- + fs/pstore/ram_core.c | 5 +++++ + 1 file changed, 5 insertions(+) + +diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c +index 288ce45f613e..5ffbf60f5c88 100644 +--- a/fs/pstore/ram_core.c ++++ b/fs/pstore/ram_core.c +@@ -484,6 +484,11 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, + sig ^= PERSISTENT_RAM_SIG; + + if (prz->buffer->sig == sig) { ++ if (buffer_size(prz) == 0) { ++ pr_debug("found existing empty buffer\n"); ++ return 0; ++ } ++ + if (buffer_size(prz) > prz->buffer_size || + buffer_start(prz) > buffer_size(prz)) + pr_info("found existing invalid buffer, size %zu, start %zu\n", +-- +2.19.1 + diff --git a/queue-3.18/scsi-target-use-consistent-left-aligned-ascii-inquir.patch b/queue-3.18/scsi-target-use-consistent-left-aligned-ascii-inquir.patch new file mode 100644 index 00000000000..378eb91162a --- /dev/null +++ b/queue-3.18/scsi-target-use-consistent-left-aligned-ascii-inquir.patch @@ -0,0 +1,77 @@ +From 3a6dc699cd9a436feb631e1500bcbd11662d5e85 Mon Sep 17 00:00:00 2001 +From: David Disseldorp +Date: Wed, 5 Dec 2018 13:18:34 +0100 +Subject: scsi: target: use consistent left-aligned ASCII INQUIRY data + +[ Upstream commit 0de263577de5d5e052be5f4f93334e63cc8a7f0b ] + +spc5r17.pdf specifies: + + 4.3.1 ASCII data field requirements + ASCII data fields shall contain only ASCII printable characters (i.e., + code values 20h to 7Eh) and may be terminated with one or more ASCII null + (00h) characters. ASCII data fields described as being left-aligned + shall have any unused bytes at the end of the field (i.e., highest + offset) and the unused bytes shall be filled with ASCII space characters + (20h). + +LIO currently space-pads the T10 VENDOR IDENTIFICATION and PRODUCT +IDENTIFICATION fields in the standard INQUIRY data. However, the PRODUCT +REVISION LEVEL field in the standard INQUIRY data as well as the T10 VENDOR +IDENTIFICATION field in the INQUIRY Device Identification VPD Page are +zero-terminated/zero-padded. + +Fix this inconsistency by using space-padding for all of the above fields. + +Signed-off-by: David Disseldorp +Reviewed-by: Christoph Hellwig +Reviewed-by: Bryant G. Ly +Reviewed-by: Lee Duncan +Reviewed-by: Hannes Reinecke +Reviewed-by: Roman Bolshakov +Signed-off-by: Martin K. Petersen +Signed-off-by: Sasha Levin +--- + drivers/target/target_core_spc.c | 17 ++++++++++++----- + 1 file changed, 12 insertions(+), 5 deletions(-) + +diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c +index 614005b6b08b..3ab264d4fb1f 100644 +--- a/drivers/target/target_core_spc.c ++++ b/drivers/target/target_core_spc.c +@@ -112,12 +112,17 @@ spc_emulate_inquiry_std(struct se_cmd *cmd, unsigned char *buf) + + buf[7] = 0x2; /* CmdQue=1 */ + +- memcpy(&buf[8], "LIO-ORG ", 8); +- memset(&buf[16], 0x20, 16); ++ /* ++ * ASCII data fields described as being left-aligned shall have any ++ * unused bytes at the end of the field (i.e., highest offset) and the ++ * unused bytes shall be filled with ASCII space characters (20h). ++ */ ++ memset(&buf[8], 0x20, 8 + 16 + 4); ++ memcpy(&buf[8], "LIO-ORG", sizeof("LIO-ORG") - 1); + memcpy(&buf[16], dev->t10_wwn.model, +- min_t(size_t, strlen(dev->t10_wwn.model), 16)); ++ strnlen(dev->t10_wwn.model, 16)); + memcpy(&buf[32], dev->t10_wwn.revision, +- min_t(size_t, strlen(dev->t10_wwn.revision), 4)); ++ strnlen(dev->t10_wwn.revision, 4)); + buf[4] = 31; /* Set additional length to 31 */ + + return 0; +@@ -257,7 +262,9 @@ check_t10_vend_desc: + buf[off] = 0x2; /* ASCII */ + buf[off+1] = 0x1; /* T10 Vendor ID */ + buf[off+2] = 0x0; +- memcpy(&buf[off+4], "LIO-ORG", 8); ++ /* left align Vendor ID and pad with spaces */ ++ memset(&buf[off+4], 0x20, 8); ++ memcpy(&buf[off+4], "LIO-ORG", sizeof("LIO-ORG") - 1); + /* Extra Byte for NULL Terminator */ + id_len++; + /* Identifier Length */ +-- +2.19.1 + diff --git a/queue-3.18/series b/queue-3.18/series index 06bfd53ae7f..c16e5a7d2e4 100644 --- a/queue-3.18/series +++ b/queue-3.18/series @@ -32,3 +32,21 @@ block-loop-use-global-lock-for-ioctl-operation.patch drm-fb-helper-ignore-the-value-of-fb_var_screeninfo.pixclock.patch media-vb2-be-sure-to-unlock-mutex-on-errors.patch r8169-add-support-for-new-realtek-ethernet.patch +mips-sibyte-enable-swiotlb-for-swarm-littlesur-and-b.patch +jffs2-fix-use-of-uninitialized-delayed_work-lockdep-.patch +pstore-ram-do-not-treat-empty-buffers-as-valid.patch +powerpc-pseries-cpuidle-fix-preempt-warning.patch +media-firewire-fix-app_info-parameter-type-in-avc_ca.patch +net-call-sk_dst_reset-when-set-so_dontroute.patch +scsi-target-use-consistent-left-aligned-ascii-inquir.patch +clk-imx6q-reset-exclusive-gates-on-init.patch +kconfig-fix-memory-leak-when-eof-is-encountered-in-q.patch +mmc-atmel-mci-do-not-assume-idle-after-atmci_request.patch +perf-svghelper-fix-unchecked-usage-of-strncpy.patch +perf-parse-events-fix-unchecked-usage-of-strncpy.patch +dm-kcopyd-fix-bug-causing-workqueue-stalls.patch +dm-snapshot-fix-excessive-memory-usage-and-workqueue.patch +alsa-bebob-fix-model-id-of-unit-for-apogee-ensemble.patch +sysfs-disable-lockdep-for-driver-bind-unbind-files.patch +ocfs2-fix-panic-due-to-unrecovered-local-alloc.patch +mm-proc-be-more-verbose-about-unstable-vma-flags-in-.patch diff --git a/queue-3.18/sysfs-disable-lockdep-for-driver-bind-unbind-files.patch b/queue-3.18/sysfs-disable-lockdep-for-driver-bind-unbind-files.patch new file mode 100644 index 00000000000..2a241ed54a7 --- /dev/null +++ b/queue-3.18/sysfs-disable-lockdep-for-driver-bind-unbind-files.patch @@ -0,0 +1,174 @@ +From 69b2df0d73dc8ecc115f5508d2141a70ddd45552 Mon Sep 17 00:00:00 2001 +From: Daniel Vetter +Date: Wed, 19 Dec 2018 13:39:09 +0100 +Subject: sysfs: Disable lockdep for driver bind/unbind files + +[ Upstream commit 4f4b374332ec0ae9c738ff8ec9bed5cd97ff9adc ] + +This is the much more correct fix for my earlier attempt at: + +https://lkml.org/lkml/2018/12/10/118 + +Short recap: + +- There's not actually a locking issue, it's just lockdep being a bit + too eager to complain about a possible deadlock. + +- Contrary to what I claimed the real problem is recursion on + kn->count. Greg pointed me at sysfs_break_active_protection(), used + by the scsi subsystem to allow a sysfs file to unbind itself. That + would be a real deadlock, which isn't what's happening here. Also, + breaking the active protection means we'd need to manually handle + all the lifetime fun. + +- With Rafael we discussed the task_work approach, which kinda works, + but has two downsides: It's a functional change for a lockdep + annotation issue, and it won't work for the bind file (which needs + to get the errno from the driver load function back to userspace). + +- Greg also asked why this never showed up: To hit this you need to + unregister a 2nd driver from the unload code of your first driver. I + guess only gpus do that. The bug has always been there, but only + with a recent patch series did we add more locks so that lockdep + built a chain from unbinding the snd-hda driver to the + acpi_video_unregister call. + +Full lockdep splat: + +[12301.898799] ============================================ +[12301.898805] WARNING: possible recursive locking detected +[12301.898811] 4.20.0-rc7+ #84 Not tainted +[12301.898815] -------------------------------------------- +[12301.898821] bash/5297 is trying to acquire lock: +[12301.898826] 00000000f61c6093 (kn->count#39){++++}, at: kernfs_remove_by_name_ns+0x3b/0x80 +[12301.898841] but task is already holding lock: +[12301.898847] 000000005f634021 (kn->count#39){++++}, at: kernfs_fop_write+0xdc/0x190 +[12301.898856] other info that might help us debug this: +[12301.898862] Possible unsafe locking scenario: +[12301.898867] CPU0 +[12301.898870] ---- +[12301.898874] lock(kn->count#39); +[12301.898879] lock(kn->count#39); +[12301.898883] *** DEADLOCK *** +[12301.898891] May be due to missing lock nesting notation +[12301.898899] 5 locks held by bash/5297: +[12301.898903] #0: 00000000cd800e54 (sb_writers#4){.+.+}, at: vfs_write+0x17f/0x1b0 +[12301.898915] #1: 000000000465e7c2 (&of->mutex){+.+.}, at: kernfs_fop_write+0xd3/0x190 +[12301.898925] #2: 000000005f634021 (kn->count#39){++++}, at: kernfs_fop_write+0xdc/0x190 +[12301.898936] #3: 00000000414ef7ac (&dev->mutex){....}, at: device_release_driver_internal+0x34/0x240 +[12301.898950] #4: 000000003218fbdf (register_count_mutex){+.+.}, at: acpi_video_unregister+0xe/0x40 +[12301.898960] stack backtrace: +[12301.898968] CPU: 1 PID: 5297 Comm: bash Not tainted 4.20.0-rc7+ #84 +[12301.898974] Hardware name: Hewlett-Packard HP EliteBook 8460p/161C, BIOS 68SCF Ver. F.01 03/11/2011 +[12301.898982] Call Trace: +[12301.898989] dump_stack+0x67/0x9b +[12301.898997] __lock_acquire+0x6ad/0x1410 +[12301.899003] ? kernfs_remove_by_name_ns+0x3b/0x80 +[12301.899010] ? find_held_lock+0x2d/0x90 +[12301.899017] ? mutex_spin_on_owner+0xe4/0x150 +[12301.899023] ? find_held_lock+0x2d/0x90 +[12301.899030] ? lock_acquire+0x90/0x180 +[12301.899036] lock_acquire+0x90/0x180 +[12301.899042] ? kernfs_remove_by_name_ns+0x3b/0x80 +[12301.899049] __kernfs_remove+0x296/0x310 +[12301.899055] ? kernfs_remove_by_name_ns+0x3b/0x80 +[12301.899060] ? kernfs_name_hash+0xd/0x80 +[12301.899066] ? kernfs_find_ns+0x6c/0x100 +[12301.899073] kernfs_remove_by_name_ns+0x3b/0x80 +[12301.899080] bus_remove_driver+0x92/0xa0 +[12301.899085] acpi_video_unregister+0x24/0x40 +[12301.899127] i915_driver_unload+0x42/0x130 [i915] +[12301.899160] i915_pci_remove+0x19/0x30 [i915] +[12301.899169] pci_device_remove+0x36/0xb0 +[12301.899176] device_release_driver_internal+0x185/0x240 +[12301.899183] unbind_store+0xaf/0x180 +[12301.899189] kernfs_fop_write+0x104/0x190 +[12301.899195] __vfs_write+0x31/0x180 +[12301.899203] ? rcu_read_lock_sched_held+0x6f/0x80 +[12301.899209] ? rcu_sync_lockdep_assert+0x29/0x50 +[12301.899216] ? __sb_start_write+0x13c/0x1a0 +[12301.899221] ? vfs_write+0x17f/0x1b0 +[12301.899227] vfs_write+0xb9/0x1b0 +[12301.899233] ksys_write+0x50/0xc0 +[12301.899239] do_syscall_64+0x4b/0x180 +[12301.899247] entry_SYSCALL_64_after_hwframe+0x49/0xbe +[12301.899253] RIP: 0033:0x7f452ac7f7a4 +[12301.899259] Code: 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 80 00 00 00 00 8b 05 aa f0 2c 00 48 63 ff 85 c0 75 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 f3 c3 66 90 55 53 48 89 d5 48 89 f3 48 83 +[12301.899273] RSP: 002b:00007ffceafa6918 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 +[12301.899282] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f452ac7f7a4 +[12301.899288] RDX: 000000000000000d RSI: 00005612a1abf7c0 RDI: 0000000000000001 +[12301.899295] RBP: 00005612a1abf7c0 R08: 000000000000000a R09: 00005612a1c46730 +[12301.899301] R10: 000000000000000a R11: 0000000000000246 R12: 000000000000000d +[12301.899308] R13: 0000000000000001 R14: 00007f452af4a740 R15: 000000000000000d + +Looking around I've noticed that usb and i2c already handle similar +recursion problems, where a sysfs file can unbind the same type of +sysfs somewhere else in the hierarchy. Relevant commits are: + +commit 356c05d58af05d582e634b54b40050c73609617b +Author: Alan Stern +Date: Mon May 14 13:30:03 2012 -0400 + + sysfs: get rid of some lockdep false positives + +commit e9b526fe704812364bca07edd15eadeba163ebfb +Author: Alexander Sverdlin +Date: Fri May 17 14:56:35 2013 +0200 + + i2c: suppress lockdep warning on delete_device + +Implement the same trick for driver bind/unbind. + +v2: Put the macro into bus.c (Greg). + +Reviewed-by: Rafael J. Wysocki +Cc: Ramalingam C +Cc: Arend van Spriel +Cc: Andy Shevchenko +Cc: Geert Uytterhoeven +Cc: Bartosz Golaszewski +Cc: Heikki Krogerus +Cc: Vivek Gautam +Cc: Joe Perches +Signed-off-by: Daniel Vetter +Signed-off-by: Greg Kroah-Hartman +Signed-off-by: Sasha Levin +--- + drivers/base/bus.c | 7 +++++-- + 1 file changed, 5 insertions(+), 2 deletions(-) + +diff --git a/drivers/base/bus.c b/drivers/base/bus.c +index 07ea8608fb0b..c05561e26d85 100644 +--- a/drivers/base/bus.c ++++ b/drivers/base/bus.c +@@ -32,6 +32,9 @@ static struct kset *system_kset; + + #define to_drv_attr(_attr) container_of(_attr, struct driver_attribute, attr) + ++#define DRIVER_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ ++ struct driver_attribute driver_attr_##_name = \ ++ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) + + static int __must_check bus_rescan_devices_helper(struct device *dev, + void *data); +@@ -197,7 +200,7 @@ static ssize_t unbind_store(struct device_driver *drv, const char *buf, + bus_put(bus); + return err; + } +-static DRIVER_ATTR_WO(unbind); ++static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, S_IWUSR, NULL, unbind_store); + + /* + * Manually attach a device to a driver. +@@ -233,7 +236,7 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf, + bus_put(bus); + return err; + } +-static DRIVER_ATTR_WO(bind); ++static DRIVER_ATTR_IGNORE_LOCKDEP(bind, S_IWUSR, NULL, bind_store); + + static ssize_t show_drivers_autoprobe(struct bus_type *bus, char *buf) + { +-- +2.19.1 +