[ Upstream commit edb64bca50cd736c6894cc6081d5263c007ce005 ]

In case of devboards we really often disable bootloader and load Linux image in memory via JTAG. Even if kernel tries to verify uboot_tag and uboot_arg there is sill a chance that we treat some garbage in registers as valid u-boot arguments in JTAG case. E.g. it is enough to have '1' in r0 to treat any value in r2 as a boot command line.

So check that magic number passed from u-boot is correct and drop u-boot arguments otherwise. That helps to reduce the possibility of using garbage as u-boot arguments in JTAG case.

We can safely check U-boot magic value (0x0) in linux passed via r1 register as U-boot pass it from the beginning. So there is no backward-compatibility issues.

Signed-off-by: Eugeniy Paltsev Eugeniy.Paltsev@synopsys.com Signed-off-by: Vineet Gupta vgupta@synopsys.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arc/kernel/head.S | 1 + arch/arc/kernel/setup.c | 8 ++++++++ 2 files changed, 9 insertions(+)

diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 1f945d0f40da..208bf2c9e7b0 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -107,6 +107,7 @@ ENTRY(stext) ; r2 = pointer to uboot provided cmdline or external DTB in mem ; These are handled later in handle_uboot_args() st r0, [@uboot_tag] + st r1, [@uboot_magic] st r2, [@uboot_arg] #endif

diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 3320ca2fe20f..a1218937abd6 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -35,6 +35,7 @@ unsigned int intr_to_DE_cnt;

/* Part of U-boot ABI: see head.S */ int __initdata uboot_tag; +int __initdata uboot_magic; char __initdata *uboot_arg;

const struct machine_desc *machine_desc; @@ -484,6 +485,8 @@ static inline bool uboot_arg_invalid(unsigned long addr) #define UBOOT_TAG_NONE 0 #define UBOOT_TAG_CMDLINE 1 #define UBOOT_TAG_DTB 2 +/* We always pass 0 as magic from U-boot */ +#define UBOOT_MAGIC_VALUE 0

void __init handle_uboot_args(void) { @@ -499,6 +502,11 @@ void __init handle_uboot_args(void) goto ignore_uboot_args; }

+ if (uboot_magic != UBOOT_MAGIC_VALUE) { + pr_warn(IGNORE_ARGS "non zero uboot magic\n"); + goto ignore_uboot_args; + } + if (uboot_tag != UBOOT_TAG_NONE && uboot_arg_invalid((unsigned long)uboot_arg)) { pr_warn(IGNORE_ARGS "invalid uboot arg: '%px'\n", uboot_arg);

[ Upstream commit 62c9d2674b31d4c8a674bee86b7edc6da2803aea ]

Commit 4d97f7d53da7dc83 ("inotify: Add flag IN_MASK_CREATE for inotify_add_watch()") forgot to call fsnotify_put_mark() with IN_MASK_CREATE after fsnotify_find_mark()

Fixes: 4d97f7d53da7dc83 ("inotify: Add flag IN_MASK_CREATE for inotify_add_watch()") Signed-off-by: ZhangXiaoxu zhangxiaoxu5@huawei.com Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- fs/notify/inotify/inotify_user.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 780bba695453..97a51690338e 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -519,8 +519,10 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group); if (!fsn_mark) return -ENOENT; - else if (create) - return -EEXIST; + else if (create) { + ret = -EEXIST; + goto out; + }

i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);

@@ -548,6 +550,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, /* return the wd */ ret = i_mark->wd;

+out: /* match the get from fsnotify_find_mark() */ fsnotify_put_mark(fsn_mark);

[ Upstream commit cd3dd8dd8ff62374d90cb3f2e54b8c94106c7810 ]

We can't store the auxtrace index when we store into multiple files, because we keep only offset for it, not the file.

The auxtrace data will be processed correctly in the 'pipe' mode.

Signed-off-by: Jiri Olsa jolsa@kernel.org Cc: Adrian Hunter adrian.hunter@intel.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Alexey Budankov alexey.budankov@linux.intel.com Cc: Andi Kleen ak@linux.intel.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Link: http://lkml.kernel.org/r/20190308134745.5057-3-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/builtin-record.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 22ebeb92ac51..f5b438486a64 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -178,7 +178,7 @@ static int record__process_auxtrace(struct perf_tool *tool, size_t padding; u8 pad[8] = {0};

- if (!perf_data__is_pipe(data)) { + if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) { off_t file_offset; int fd = perf_data__fd(data); int err;

[ Upstream commit 1dc1097ff60e4105216da7cd0aa99032b039a994 ]

When admin calls "reboot -f" - i.e., does a hard system reboot by directly calling reboot(2) - ext4 filesystem mounted with errors=panic can panic the system. This happens because the underlying device gets disabled without unmounting the filesystem and thus some syscall running in parallel to reboot(2) can result in the filesystem getting IO errors.

This is somewhat surprising to the users so try improve the behavior by switching to errors=remount-ro behavior when the system is running reboot(2).

Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/super.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a1cf7d68b4f0..abba7ece78e9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -430,6 +430,12 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) spin_unlock(&sbi->s_md_lock); }

+static bool system_going_down(void) +{ + return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF + || system_state == SYSTEM_RESTART; +} + /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * @@ -460,7 +466,12 @@ static void ext4_handle_error(struct super_block *sb) if (journal) jbd2_journal_abort(journal, -EIO); } - if (test_opt(sb, ERRORS_RO)) { + /* + * We force ERRORS_RO behavior when system is rebooting. Otherwise we + * could panic during 'reboot -f' as the underlying device got already + * disabled. + */ + if (test_opt(sb, ERRORS_RO) || system_going_down()) { ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); /* * Make sure updated value of ->s_mount_flags will be visible @@ -468,8 +479,7 @@ static void ext4_handle_error(struct super_block *sb) */ smp_wmb(); sb->s_flags |= SB_RDONLY; - } - if (test_opt(sb, ERRORS_PANIC)) { + } else if (test_opt(sb, ERRORS_PANIC)) { if (EXT4_SB(sb)->s_journal && !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) return;

[ Upstream commit 6c7328400e0488f7d49e19e02290ba343b6811b2 ]

Currently when the file system resize using ext4_resize_fs() fails it will report into log that "resized filesystem to <requested block count>". However this may not be true in the case of failure. Use the current block count as returned by ext4_blocks_count() to report the block count.

Additionally, report a warning that "error occurred during file system resize"

Signed-off-by: Lukas Czerner lczerner@redhat.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/resize.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 90061c3d048b..e7ae26e36c9c 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -2080,6 +2080,10 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) free_flex_gd(flex_gd); if (resize_inode != NULL) iput(resize_inode); - ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", n_blocks_count); + if (err) + ext4_warning(sb, "error (%d) occurred during " + "file system resize", err); + ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", + ext4_blocks_count(es)); return err; }

[ Upstream commit dcd0feac9bab901d5739de51b3f69840851f8919 ]

In case request_region fails, the fix returns an error code to avoid NULL pointer dereference.

Signed-off-by: Kangjie Lu kjlu@umn.edu Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/isa/sb/sb8.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/sound/isa/sb/sb8.c b/sound/isa/sb/sb8.c index d77dcba276b5..1eb8b61a185b 100644 --- a/sound/isa/sb/sb8.c +++ b/sound/isa/sb/sb8.c @@ -111,6 +111,10 @@ static int snd_sb8_probe(struct device *pdev, unsigned int dev)

/* block the 0x388 port to avoid PnP conflicts */ acard->fm_res = request_region(0x388, 4, "SoundBlaster FM"); + if (!acard->fm_res) { + err = -EBUSY; + goto _err; + }

if (port[dev] != SNDRV_AUTO_PORT) { if ((err = snd_sbdsp_create(card, port[dev], irq[dev],

[ Upstream commit 8f3b487685b2acf71b42bb30d68fd9271bec8695 ]

When Daniel removed struct_mutex he didn't fix this call to the unlocked variant which is required since we no longer use struct mutex.

This fixes a bunch of: WARNING: CPU: 4 PID: 1370 at drivers/gpu/drm/drm_gem.c:931 drm_gem_object_put+0x2b/0x30 [drm] Modules linked in: udl xt_CHECKSUM ipt_MASQUERADE tun bridge stp llc nf_conntrack_netbios_ns nf_conntrack_broadcast xt_CT ip6t> CPU: 4 PID: 1370 Comm: Xorg Not tainted 5.0.0+ #2

backtraces when you plug in a udl device.

Fixes: ae358dacd217 (drm/udl: Get rid of dev->struct_mutex usage) Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch Cc: Sean Paul seanpaul@chromium.org Signed-off-by: Dave Airlie airlied@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/udl/udl_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c index d5a23295dd80..bb7b58407039 100644 --- a/drivers/gpu/drm/udl/udl_gem.c +++ b/drivers/gpu/drm/udl/udl_gem.c @@ -224,7 +224,7 @@ int udl_gem_mmap(struct drm_file *file, struct drm_device *dev, *offset = drm_vma_node_offset_addr(&gobj->base.vma_node);

out: - drm_gem_object_put(&gobj->base); + drm_gem_object_put_unlocked(&gobj->base); unlock: mutex_unlock(&udl->gem_lock); return ret;

[ Upstream commit ec4fe4bcc584b55e24e8d1768f5510a62c0fd619 ]

There is a panic reported that on a system with x722 ethernet, when doing the operations like:

# ip link add br0 type bridge # ip link set eno1 master br0 # systemctl restart systemd-networkd

The system will panic "BUG: unable to handle kernel null pointer dereference at 0000000000000034", with call chain:

i40iw_inetaddr_event notifier_call_chain blocking_notifier_call_chain notifier_call_chain __inet_del_ifa inet_rtm_deladdr rtnetlink_rcv_msg netlink_rcv_skb rtnetlink_rcv netlink_unicast netlink_sendmsg sock_sendmsg __sys_sendto

It is caused by "local_ipaddr = ntohl(in->ifa_list->ifa_address)", while the in->ifa_list is NULL.

So add a check for the "in->ifa_list == NULL" case, and skip the ARP operation accordingly.

Signed-off-by: Feng Tang feng.tang@intel.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/i40iw/i40iw_utils.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c index a9ea966877f2..dda8e79d4b27 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_utils.c +++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c @@ -173,7 +173,12 @@ int i40iw_inetaddr_event(struct notifier_block *notifier,

rcu_read_lock(); in = __in_dev_get_rcu(upper_dev); - local_ipaddr = ntohl(in->ifa_list->ifa_address); + + if (!in->ifa_list) + local_ipaddr = 0; + else + local_ipaddr = ntohl(in->ifa_list->ifa_address); + rcu_read_unlock(); } else { local_ipaddr = ntohl(ifa->ifa_address); @@ -185,6 +190,11 @@ int i40iw_inetaddr_event(struct notifier_block *notifier, case NETDEV_UP: /* Fall through */ case NETDEV_CHANGEADDR: + + /* Just skip if no need to handle ARP cache */ + if (!local_ipaddr) + break; + i40iw_manage_arp_cache(iwdev, netdev->dev_addr, &local_ipaddr,

[ Upstream commit b4748e7ab731e436cf5db4786358ada5dd2db6dd ]

The function snd_opl3_drum_switch declaration in the header file has the order of the two arguments on_off and vel swapped when compared to the definition arguments of vel and on_off. Fix this by swapping them around to match the definition.

This error predates the git history, so no idea when this error was introduced.

Signed-off-by: Colin Ian King colin.king@canonical.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/drivers/opl3/opl3_voice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/drivers/opl3/opl3_voice.h b/sound/drivers/opl3/opl3_voice.h index 5b02bd49fde4..4e4ecc21760b 100644 --- a/sound/drivers/opl3/opl3_voice.h +++ b/sound/drivers/opl3/opl3_voice.h @@ -41,7 +41,7 @@ void snd_opl3_timer_func(struct timer_list *t);

/* Prototypes for opl3_drums.c */ void snd_opl3_load_drums(struct snd_opl3 *opl3); -void snd_opl3_drum_switch(struct snd_opl3 *opl3, int note, int on_off, int vel, struct snd_midi_channel *chan); +void snd_opl3_drum_switch(struct snd_opl3 *opl3, int note, int vel, int on_off, struct snd_midi_channel *chan);

/* Prototypes for opl3_oss.c */ #if IS_ENABLED(CONFIG_SND_SEQUENCER_OSS)

[ Upstream commit 3b5236cc5d086dd3ddd01113ee9255421aab9fab ]

Merge commit 19785cf93b6c ("Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal") broke the code introduced by commit ffe6e16f14fa ("thermal: exynos: Reduce severity of too early temperature read"). Restore the original code from the mentioned commit to finally fix the warning message during boot:

thermal thermal_zone0: failed to read out thermal zone (-22)

Reported-by: Marian Mihailescu mihailescu2m@gmail.com Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Fixes: 19785cf93b6c ("Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal") Reviewed-by: Krzysztof Kozlowski krzk@kernel.org Signed-off-by: Zhang Rui rui.zhang@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/thermal/samsung/exynos_tmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c index 48eef552cba4..fc9399d9c082 100644 --- a/drivers/thermal/samsung/exynos_tmu.c +++ b/drivers/thermal/samsung/exynos_tmu.c @@ -666,7 +666,7 @@ static int exynos_get_temp(void *p, int *temp) struct exynos_tmu_data *data = p; int value, ret = 0;

- if (!data || !data->tmu_read || !data->enabled) + if (!data || !data->tmu_read) return -EINVAL; else if (!data->enabled) /*

[ Upstream commit 16fc8eca1975358111dbd7ce65e4ce42d1a848fb ]

Add more supported DPTF policies than the driver currently exposes.

Signed-off-by: Matthew Garrett mjg59@google.com Cc: Nisha Aram nisha.aram@intel.com Signed-off-by: Zhang Rui rui.zhang@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/thermal/int340x_thermal/int3400_thermal.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

diff --git a/drivers/thermal/int340x_thermal/int3400_thermal.c b/drivers/thermal/int340x_thermal/int3400_thermal.c index e26b01c05e82..51c9097eaf7a 100644 --- a/drivers/thermal/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/int340x_thermal/int3400_thermal.c @@ -22,6 +22,13 @@ enum int3400_thermal_uuid { INT3400_THERMAL_PASSIVE_1, INT3400_THERMAL_ACTIVE, INT3400_THERMAL_CRITICAL, + INT3400_THERMAL_ADAPTIVE_PERFORMANCE, + INT3400_THERMAL_EMERGENCY_CALL_MODE, + INT3400_THERMAL_PASSIVE_2, + INT3400_THERMAL_POWER_BOSS, + INT3400_THERMAL_VIRTUAL_SENSOR, + INT3400_THERMAL_COOLING_MODE, + INT3400_THERMAL_HARDWARE_DUTY_CYCLING, INT3400_THERMAL_MAXIMUM_UUID, };

@@ -29,6 +36,13 @@ static char *int3400_thermal_uuids[INT3400_THERMAL_MAXIMUM_UUID] = { "42A441D6-AE6A-462b-A84B-4A8CE79027D3", "3A95C389-E4B8-4629-A526-C52C88626BAE", "97C68AE7-15FA-499c-B8C9-5DA81D606E0A", + "63BE270F-1C11-48FD-A6F7-3AF253FF3E2D", + "5349962F-71E6-431D-9AE8-0A635B710AEE", + "9E04115A-AE87-4D1C-9500-0F3E340BFE75", + "F5A35014-C209-46A4-993A-EB56DE7530A1", + "6ED722A7-9240-48A5-B479-31EEF723D7CF", + "16CAF1B7-DD38-40ED-B1C1-1B8A1913D531", + "BE84BABF-C4D4-403D-B495-3128FD44dAC1", };

struct int3400_thermal_priv {

[ Upstream commit e925b5be5751f6a7286bbd9a4cbbc4ac90cc5fa6 ]

kthread name only allows 15 characters (TASK_COMMON_LEN is 16). Thus rename the kthreads created by intel_powerclamp driver from "kidle_inject/ + decimal cpuid" to "kidle_inj/ + decimal cpuid" to avoid truncated kthead name for cpu 100 and later.

Signed-off-by: Zhang Rui rui.zhang@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/thermal/intel_powerclamp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c index ea1aa7dbe42c..8e8328347c0e 100644 --- a/drivers/thermal/intel_powerclamp.c +++ b/drivers/thermal/intel_powerclamp.c @@ -494,7 +494,7 @@ static void start_power_clamp_worker(unsigned long cpu) struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu); struct kthread_worker *worker;

- worker = kthread_create_worker_on_cpu(cpu, 0, "kidle_inject/%ld", cpu); + worker = kthread_create_worker_on_cpu(cpu, 0, "kidle_inj/%ld", cpu); if (IS_ERR(worker)) return;

[ Upstream commit a23314e9d88d89d49e69db08f60b7caa470f04e1 ]

Vincent Wang reported that get_next_freq() has a mult overflow bug on 32-bit platforms in the IOWAIT boost case, since in that case {util,max} are in freq units instead of capacity units.

Solve this by moving the IOWAIT boost to capacity units. And since this means @max is constant; simplify the code.

Reported-by: Vincent Wang vincent.wang@unisoc.com Tested-by: Vincent Wang vincent.wang@unisoc.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Acked-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Cc: Andy Lutomirski luto@kernel.org Cc: Borislav Petkov bp@alien8.de Cc: Chunyan Zhang zhang.lyra@gmail.com Cc: Dave Hansen dave.hansen@linux.intel.com Cc: H. Peter Anvin hpa@zytor.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Quentin Perret quentin.perret@arm.com Cc: Rafael J. Wysocki rjw@rjwysocki.net Cc: Rik van Riel riel@surriel.com Cc: Thomas Gleixner tglx@linutronix.de Link: https://lkml.kernel.org/r/20190305083202.GU32494@hirez.programming.kicks-ass... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/cpufreq_schedutil.c | 59 ++++++++++++++------------------ 1 file changed, 25 insertions(+), 34 deletions(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 3fffad3bc8a8..217f81ecae17 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -50,10 +50,10 @@ struct sugov_cpu {

bool iowait_boost_pending; unsigned int iowait_boost; - unsigned int iowait_boost_max; u64 last_update;

unsigned long bw_dl; + unsigned long min; unsigned long max;

/* The field below is for single-CPU policies only: */ @@ -283,8 +283,7 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time, if (delta_ns <= TICK_NSEC) return false;

- sg_cpu->iowait_boost = set_iowait_boost - ? sg_cpu->sg_policy->policy->min : 0; + sg_cpu->iowait_boost = set_iowait_boost ? sg_cpu->min : 0; sg_cpu->iowait_boost_pending = set_iowait_boost;

return true; @@ -324,14 +323,13 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,

/* Double the boost at each request */ if (sg_cpu->iowait_boost) { - sg_cpu->iowait_boost <<= 1; - if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max) - sg_cpu->iowait_boost = sg_cpu->iowait_boost_max; + sg_cpu->iowait_boost = + min_t(unsigned int, sg_cpu->iowait_boost << 1, SCHED_CAPACITY_SCALE); return; }

/* First wakeup after IO: start with minimum boost */ - sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min; + sg_cpu->iowait_boost = sg_cpu->min; }

/** @@ -353,47 +351,38 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, * This mechanism is designed to boost high frequently IO waiting tasks, while * being more conservative on tasks which does sporadic IO operations. */ -static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, - unsigned long *util, unsigned long *max) +static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, + unsigned long util, unsigned long max) { - unsigned int boost_util, boost_max; + unsigned long boost;

/* No boost currently required */ if (!sg_cpu->iowait_boost) - return; + return util;

/* Reset boost if the CPU appears to have been idle enough */ if (sugov_iowait_reset(sg_cpu, time, false)) - return; + return util;

- /* - * An IO waiting task has just woken up: - * allow to further double the boost value - */ - if (sg_cpu->iowait_boost_pending) { - sg_cpu->iowait_boost_pending = false; - } else { + if (!sg_cpu->iowait_boost_pending) { /* - * Otherwise: reduce the boost value and disable it when we - * reach the minimum. + * No boost pending; reduce the boost value. */ sg_cpu->iowait_boost >>= 1; - if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) { + if (sg_cpu->iowait_boost < sg_cpu->min) { sg_cpu->iowait_boost = 0; - return; + return util; } }

+ sg_cpu->iowait_boost_pending = false; + /* - * Apply the current boost value: a CPU is boosted only if its current - * utilization is smaller then the current IO boost level. + * @util is already in capacity scale; convert iowait_boost + * into the same scale so we can compare. */ - boost_util = sg_cpu->iowait_boost; - boost_max = sg_cpu->iowait_boost_max; - if (*util * boost_max < *max * boost_util) { - *util = boost_util; - *max = boost_max; - } + boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT; + return max(boost, util); }

#ifdef CONFIG_NO_HZ_COMMON @@ -440,7 +429,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,

util = sugov_get_util(sg_cpu); max = sg_cpu->max; - sugov_iowait_apply(sg_cpu, time, &util, &max); + util = sugov_iowait_apply(sg_cpu, time, util, max); next_f = get_next_freq(sg_policy, util, max); /* * Do not reduce the frequency if the CPU has not been idle @@ -480,7 +469,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)

j_util = sugov_get_util(j_sg_cpu); j_max = j_sg_cpu->max; - sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max); + j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max);

if (j_util * max > j_max * util) { util = j_util; @@ -817,7 +806,9 @@ static int sugov_start(struct cpufreq_policy *policy) memset(sg_cpu, 0, sizeof(*sg_cpu)); sg_cpu->cpu = cpu; sg_cpu->sg_policy = sg_policy; - sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; + sg_cpu->min = + (SCHED_CAPACITY_SCALE * policy->cpuinfo.min_freq) / + policy->cpuinfo.max_freq; }

for_each_cpu(cpu, policy->cpus) {

[ Upstream commit a3151724437f54076cc10bc02b1c4f0003ae36cd ]

Since commit:

ad67b74d2469d9b8 ("printk: hash addresses printed with %p")

at boot "____ptrval____" is printed instead of actual addresses:

found SMP MP-table at [mem 0x000f5cc0-0x000f5ccf] mapped at [(____ptrval____)]

Instead of changing the print to "%px", and leaking a kernel addresses, just remove the print completely, like in:

071929dbdd865f77 ("arm64: Stop printing the virtual memory layout").

Signed-off-by: Matteo Croce mcroce@redhat.com Cc: Borislav Petkov bp@alien8.de Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/mpparse.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index f1c5eb99d445..ddb1ca6923b1 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -599,8 +599,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) mpf_base = base; mpf_found = true;

- pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n", - base, base + sizeof(*mpf) - 1, mpf); + pr_info("found SMP MP-table at [mem %#010lx-%#010lx]\n", + base, base + sizeof(*mpf) - 1);

memblock_reserve(base, sizeof(*mpf)); if (mpf->physptr)

[ Upstream commit 39df730b09774bd860e39ea208a48d15078236cb ]

Detected via gcc's ASan:

Direct leak of 2048 byte(s) in 64 object(s) allocated from: 6 #0 0x7f606512e370 in __interceptor_realloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xee370) 7 #1 0x556b0f1d7ddd in thread_map__realloc util/thread_map.c:43 8 #2 0x556b0f1d84c7 in thread_map__new_by_tid util/thread_map.c:85 9 #3 0x556b0f0e045e in is_event_supported util/parse-events.c:2250 10 #4 0x556b0f0e1aa1 in print_hwcache_events util/parse-events.c:2382 11 #5 0x556b0f0e3231 in print_events util/parse-events.c:2514 12 #6 0x556b0ee0a66e in cmd_list /home/changbin/work/linux/tools/perf/builtin-list.c:58 13 #7 0x556b0f01e0ae in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 14 #8 0x556b0f01e859 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 15 #9 0x556b0f01edc8 in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 16 #10 0x556b0f01f71f in main /home/changbin/work/linux/tools/perf/perf.c:520 17 #11 0x7f6062ccf09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a)

Signed-off-by: Changbin Du changbin.du@gmail.com Reviewed-by: Jiri Olsa jolsa@kernel.org Cc: Alexei Starovoitov ast@kernel.org Cc: Daniel Borkmann daniel@iogearbox.net Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Steven Rostedt (VMware) rostedt@goodmis.org Fixes: 89896051f8da ("perf tools: Do not put a variable sized type not at the end of a struct") Link: http://lkml.kernel.org/r/20190316080556.3075-3-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/parse-events.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index ebb18a9bc460..85977cebf87c 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2263,6 +2263,7 @@ static bool is_event_supported(u8 type, unsigned config) perf_evsel__delete(evsel); }

+ thread_map__put(tmap); return ret; }

[ Upstream commit 54569ba4b06d5baedae4614bde33a25a191473ba ]

Detected with gcc's ASan:

Direct leak of 66 byte(s) in 5 object(s) allocated from: #0 0x7ff3b1f32070 in __interceptor_strdup (/usr/lib/x86_64-linux-gnu/libasan.so.5+0x3b070) #1 0x560c8761034d in collect_config util/config.c:597 #2 0x560c8760d9cb in get_value util/config.c:169 #3 0x560c8760dfd7 in perf_parse_file util/config.c:285 #4 0x560c8760e0d2 in perf_config_from_file util/config.c:476 #5 0x560c876108fd in perf_config_set__init util/config.c:661 #6 0x560c87610c72 in perf_config_set__new util/config.c:709 #7 0x560c87610d2f in perf_config__init util/config.c:718 #8 0x560c87610e5d in perf_config util/config.c:730 #9 0x560c875ddea0 in main /home/changbin/work/linux/tools/perf/perf.c:442 #10 0x7ff3afb8609a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a)

Signed-off-by: Changbin Du changbin.du@gmail.com Reviewed-by: Jiri Olsa jolsa@kernel.org Cc: Alexei Starovoitov ast@kernel.org Cc: Daniel Borkmann daniel@iogearbox.net Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Steven Rostedt (VMware) rostedt@goodmis.org Cc: Taeung Song treeze.taeung@gmail.com Fixes: 20105ca1240c ("perf config: Introduce perf_config_set class") Link: http://lkml.kernel.org/r/20190316080556.3075-6-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/config.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 5ac157056cdf..9bb742accfa5 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -628,11 +628,10 @@ static int collect_config(const char *var, const char *value, }

ret = set_value(item, value); - return ret;

out_free: free(key); - return -1; + return ret; }

int perf_config_set__collect(struct perf_config_set *set, const char *file_name,

[ Upstream commit 70c819e4bf1c5f492768b399d898d458ccdad2b6 ]

We should go to the cleanup path, to avoid leaks, detected using gcc's ASan.

Signed-off-by: Changbin Du changbin.du@gmail.com Reviewed-by: Jiri Olsa jolsa@kernel.org Cc: Alexei Starovoitov ast@kernel.org Cc: Daniel Borkmann daniel@iogearbox.net Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Steven Rostedt (VMware) rostedt@goodmis.org Link: http://lkml.kernel.org/r/20190316080556.3075-9-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/builtin-top.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index d21d8751e749..33eefc33e0ea 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1491,8 +1491,9 @@ int cmd_top(int argc, const char **argv) annotation_config__init();

symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); - if (symbol__init(NULL) < 0) - return -1; + status = symbol__init(NULL); + if (status < 0) + goto out_delete_evlist;

sort__setup_elide(stdout);

[ Upstream commit 42dfa451d825a2ad15793c476f73e7bbc0f9d312 ]

Using gcc's ASan, Changbin reports:

================================================================= ==7494==ERROR: LeakSanitizer: detected memory leaks

Direct leak of 48 byte(s) in 1 object(s) allocated from: #0 0x7f0333a89138 in calloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xee138) #1 0x5625e5330a5e in zalloc util/util.h:23 #2 0x5625e5330a9b in perf_counts__new util/counts.c:10 #3 0x5625e5330ca0 in perf_evsel__alloc_counts util/counts.c:47 #4 0x5625e520d8e5 in __perf_evsel__read_on_cpu util/evsel.c:1505 #5 0x5625e517a985 in perf_evsel__read_on_cpu /home/work/linux/tools/perf/util/evsel.h:347 #6 0x5625e517ad1a in test__openat_syscall_event tests/openat-syscall.c:47 #7 0x5625e51528e6 in run_test tests/builtin-test.c:358 #8 0x5625e5152baf in test_and_print tests/builtin-test.c:388 #9 0x5625e51543fe in __cmd_test tests/builtin-test.c:583 #10 0x5625e515572f in cmd_test tests/builtin-test.c:722 #11 0x5625e51c3fb8 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #12 0x5625e51c44f7 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #13 0x5625e51c48fb in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #14 0x5625e51c5069 in main /home/changbin/work/linux/tools/perf/perf.c:520 #15 0x7f033214d09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a)

Indirect leak of 72 byte(s) in 1 object(s) allocated from: #0 0x7f0333a89138 in calloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xee138) #1 0x5625e532560d in zalloc util/util.h:23 #2 0x5625e532566b in xyarray__new util/xyarray.c:10 #3 0x5625e5330aba in perf_counts__new util/counts.c:15 #4 0x5625e5330ca0 in perf_evsel__alloc_counts util/counts.c:47 #5 0x5625e520d8e5 in __perf_evsel__read_on_cpu util/evsel.c:1505 #6 0x5625e517a985 in perf_evsel__read_on_cpu /home/work/linux/tools/perf/util/evsel.h:347 #7 0x5625e517ad1a in test__openat_syscall_event tests/openat-syscall.c:47 #8 0x5625e51528e6 in run_test tests/builtin-test.c:358 #9 0x5625e5152baf in test_and_print tests/builtin-test.c:388 #10 0x5625e51543fe in __cmd_test tests/builtin-test.c:583 #11 0x5625e515572f in cmd_test tests/builtin-test.c:722 #12 0x5625e51c3fb8 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #13 0x5625e51c44f7 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #14 0x5625e51c48fb in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #15 0x5625e51c5069 in main /home/changbin/work/linux/tools/perf/perf.c:520 #16 0x7f033214d09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a)

His patch took care of evsel->prev_raw_counts, but the above backtraces are about evsel->counts, so fix that instead.

Reported-by: Changbin Du changbin.du@gmail.com Cc: Alexei Starovoitov ast@kernel.org Cc: Daniel Borkmann daniel@iogearbox.net Cc: Jiri Olsa jolsa@kernel.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Steven Rostedt (VMware) rostedt@goodmis.org Link: https://lkml.kernel.org/n/tip-hd1x13g59f0nuhe4anxhsmfp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/evsel.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index e7dbdcc8d465..b65ad5a273eb 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1274,6 +1274,7 @@ void perf_evsel__exit(struct perf_evsel *evsel) { assert(list_empty(&evsel->node)); assert(evsel->evlist == NULL); + perf_evsel__free_counts(evsel); perf_evsel__free_fd(evsel); perf_evsel__free_id(evsel); perf_evsel__free_config_terms(evsel);

[ Upstream commit f97a8991d3b998e518f56794d879f645964de649 ]

================================================================= ==7506==ERROR: LeakSanitizer: detected memory leaks

Direct leak of 13 byte(s) in 3 object(s) allocated from: #0 0x7f03339d6070 in __interceptor_strdup (/usr/lib/x86_64-linux-gnu/libasan.so.5+0x3b070) #1 0x5625e53aaef0 in expr__find_other util/expr.y:221 #2 0x5625e51bcd3f in test__expr tests/expr.c:52 #3 0x5625e51528e6 in run_test tests/builtin-test.c:358 #4 0x5625e5152baf in test_and_print tests/builtin-test.c:388 #5 0x5625e51543fe in __cmd_test tests/builtin-test.c:583 #6 0x5625e515572f in cmd_test tests/builtin-test.c:722 #7 0x5625e51c3fb8 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #8 0x5625e51c44f7 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #9 0x5625e51c48fb in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #10 0x5625e51c5069 in main /home/changbin/work/linux/tools/perf/perf.c:520 #11 0x7f033214d09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a)

Signed-off-by: Changbin Du changbin.du@gmail.com Cc: Alexei Starovoitov ast@kernel.org Cc: Andi Kleen ak@linux.intel.com Cc: Daniel Borkmann daniel@iogearbox.net Cc: Jiri Olsa jolsa@kernel.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Steven Rostedt (VMware) rostedt@goodmis.org Fixes: 075167363f8b ("perf tools: Add a simple expression parser for JSON") Link: http://lkml.kernel.org/r/20190316080556.3075-16-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/tests/expr.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 01f0706995a9..9acc1e80b936 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -19,7 +19,7 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) const char *p; const char **other; double val; - int ret; + int i, ret; struct parse_ctx ctx; int num_other;

@@ -56,6 +56,9 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ")); TEST_ASSERT_VAL("find other", !strcmp(other[2], "BOZO")); TEST_ASSERT_VAL("find other", other[3] == NULL); + + for (i = 0; i < num_other; i++) + free((void *)other[i]); free((void *)other);

return 0;

[ Upstream commit 54e3aca84e571559915998aa6cc05e5ac37c043b ]

When commit 8661423eea1a ("ACPI / utils: Add new acpi_dev_present helper") introduced acpi_dev_present(), it missed the fact that bus_find_device() took a reference on the device found by it and the callers of acpi_dev_present() don't drop that reference.

Drop the reference on the device in acpi_dev_present().

Fixes: 8661423eea1a ("ACPI / utils: Add new acpi_dev_present helper") Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/utils.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index 78db97687f26..c4b06cc075f9 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -800,6 +800,7 @@ bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) match.hrv = hrv;

dev = bus_find_device(&acpi_bus_type, NULL, &match, acpi_dev_match_cb); + put_device(dev); return !!dev; } EXPORT_SYMBOL(acpi_dev_present);

[ Upstream commit 373e915cd8e84544609eced57a44fbc084f8d60f ]

This patch avoids that the following warning is reported when building with W=1:

block/blk-iolatency.c:734:5: warning: no previous prototype for 'blk_iolatency_init' [-Wmissing-prototypes]

Cc: Josef Bacik jbacik@fb.com Fixes: d70675121546 ("block: introduce blk-iolatency io controller") # v4.19 Signed-off-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-iolatency.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index b154e057ca67..6b8396ccb5c4 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -75,6 +75,7 @@ #include <linux/blk-mq.h> #include "blk-rq-qos.h" #include "blk-stat.h" +#include "blk.h"

#define DEFAULT_SCALE_COOKIE 1000000U

[ Upstream commit 0dda09666f50eae9c5b794dd89b1fd8a8d89d714 ]

Falling and rising configuration and status registers are not banked. As they are shared with M4 co-processor, they should not be cleared at probe time, else M4 co-processor configuration will be lost.

Fixes: f9fc1745501e ("irqchip/stm32: Add host and driver data structures") Signed-off-by: Loic Pallardy loic.pallardy@st.com Signed-off-by: Fabien Dessenne fabien.dessenne@st.com Signed-off-by: Marc Zyngier marc.zyngier@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/irqchip/irq-stm32-exti.c | 5 ----- 1 file changed, 5 deletions(-)

diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index 0a2088e12d96..97b27f338c30 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -650,11 +650,6 @@ stm32_exti_chip_data *stm32_exti_chip_init(struct stm32_exti_host_data *h_data, */ writel_relaxed(0, base + stm32_bank->imr_ofst); writel_relaxed(0, base + stm32_bank->emr_ofst); - writel_relaxed(0, base + stm32_bank->rtsr_ofst); - writel_relaxed(0, base + stm32_bank->ftsr_ofst); - writel_relaxed(~0UL, base + stm32_bank->rpr_ofst); - if (stm32_bank->fpr_ofst != UNDEF_REG) - writel_relaxed(~0UL, base + stm32_bank->fpr_ofst);

pr_info("%s: bank%d, External IRQs available:%#x\n", node->full_name, bank_idx, irqs_mask);

[ Upstream commit 2e84f116afca3719c9d0a1a78b47b48f75fd5724 ]

hpet_virt_address may be NULL when ioremap_nocache fail, but the code lacks a check.

Add a check to prevent NULL pointer dereference.

Signed-off-by: Aditya Pakki pakki001@umn.edu Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: kjlu@umn.edu Cc: Borislav Petkov bp@alien8.de Cc: "H. Peter Anvin" hpa@zytor.com Cc: Kees Cook keescook@chromium.org Cc: Joe Perches joe@perches.com Cc: Nicolai Stange nstange@suse.de Cc: Roland Dreier roland@purestorage.com Link: https://lkml.kernel.org/r/20190319021958.17275-1-pakki001@umn.edu Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/hpet.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index b0acb22e5a46..1e3f1f140ffb 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -909,6 +909,8 @@ int __init hpet_enable(void) return 0;

hpet_set_mapping(); + if (!hpet_virt_address) + return 0;

/* * Read the period and check for a sane value:

[ Upstream commit 18fb053f9b827bd98cfc64f2a35df8ab19745a1d ]

There are comments in processor-cyrix.h advising you to _not_ make calls using the deprecated macros in this style:

setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x80);

This is because it expands the macro into a non-functioning calling sequence. The calling order must be:

outb(CX86_CCR2, 0x22); inb(0x23);

From the comments:

* When using the old macros a line like * setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88); * gets expanded to: * do { * outb((CX86_CCR2), 0x22); * outb((({ * outb((CX86_CCR2), 0x22); * inb(0x23); * }) | 0x88), 0x23); * } while (0);

The new macros fix this problem, so use them instead. Tested on an actual Geode processor.

Signed-off-by: Matthew Whitehead tedheadster@gmail.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: luto@kernel.org Link: https://lkml.kernel.org/r/1552596361-8967-2-git-send-email-tedheadster@gmail... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/cpu/cyrix.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 8949b7ae6d92..fa61c870ada9 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -124,7 +124,7 @@ static void set_cx86_reorder(void) setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */

/* Load/Store Serialize to mem access disable (=reorder it) */ - setCx86_old(CX86_PCR0, getCx86_old(CX86_PCR0) & ~0x80); + setCx86(CX86_PCR0, getCx86(CX86_PCR0) & ~0x80); /* set load/store serialize from 1GB to 4GB */ ccr3 |= 0xe0; setCx86(CX86_CCR3, ccr3); @@ -135,11 +135,11 @@ static void set_cx86_memwb(void) pr_info("Enable Memory-Write-back mode on Cyrix/NSC processor.\n");

/* CCR2 bit 2: unlock NW bit */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) & ~0x04); /* set 'Not Write-through' */ write_cr0(read_cr0() | X86_CR0_NW); /* CCR2 bit 2: lock NW bit and set WT1 */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x14); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14); }

/* @@ -153,14 +153,14 @@ static void geode_configure(void) local_irq_save(flags);

/* Suspend on halt power saving and enable #SUSP pin */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x88); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);

ccr3 = getCx86(CX86_CCR3); setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */

/* FPU fast, DTE cache, Mem bypass */ - setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x38); + setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38); setCx86(CX86_CCR3, ccr3); /* disable MAPEN */

set_cx86_memwb(); @@ -296,7 +296,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) /* GXm supports extended cpuid levels 'ala' AMD */ if (c->cpuid_level == 2) { /* Enable cxMMX extensions (GX1 Datasheet 54) */ - setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7) | 1); + setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1);

/* * GXm : 0x30 ... 0x5f GXm datasheet 51 @@ -319,7 +319,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) if (dir1 > 7) { dir0_msn++; /* M II */ /* Enable MMX extensions (App note 108) */ - setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1); + setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1); } else { /* A 6x86MX - it has the bug. */ set_cpu_bug(c, X86_BUG_COMA);

[ Upstream commit 5bb71fc790a88d063507dc5d445ab8b14e845591 ]

The spec states in 10.4.16 that the Protected Memory Enable Register should be treated as read-only for implementations not supporting protected memory regions (PLMR and PHMR fields reported as Clear in the Capability register).

Cc: Jacob Pan jacob.jun.pan@linux.intel.com Cc: mark gross mgross@intel.com Suggested-by: Ashok Raj ashok.raj@intel.com Fixes: f8bab73515ca5 ("intel-iommu: PMEN support") Signed-off-by: Lu Baolu baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/intel-iommu.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 2b8f5ebae821..603bf5233a99 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1624,6 +1624,9 @@ static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu) u32 pmen; unsigned long flags;

+ if (!cap_plmr(iommu->cap) && !cap_phmr(iommu->cap)) + return; + raw_spin_lock_irqsave(&iommu->register_lock, flags); pmen = readl(iommu->reg + DMAR_PMEN_REG); pmen &= ~DMA_PMEN_EPM;

[ Upstream commit 85f9987b236cf46e06ffdb5c225cf1f3c0acb789 ]

It was mapped to EIO which can be confusing when user space queries for an object GUID for an object for which the server file system doesn't support (or hasn't saved one).

As Amir Goldstein suggested this is similar to ENOATTR (equivalently ENODATA in Linux errno definitions) so changing NT STATUS code mapping for OBJECTID_NOT_FOUND to ENODATA.

Signed-off-by: Steve French stfrench@microsoft.com CC: Amir Goldstein amir73il@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cifs/smb2maperror.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index c3ae8c1d6089..18814f1d67d9 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -1036,7 +1036,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_UNFINISHED_CONTEXT_DELETED, -EIO, "STATUS_UNFINISHED_CONTEXT_DELETED"}, {STATUS_NO_TGT_REPLY, -EIO, "STATUS_NO_TGT_REPLY"}, - {STATUS_OBJECTID_NOT_FOUND, -EIO, "STATUS_OBJECTID_NOT_FOUND"}, + /* Note that ENOATTTR and ENODATA are the same errno */ + {STATUS_OBJECTID_NOT_FOUND, -ENODATA, "STATUS_OBJECTID_NOT_FOUND"}, {STATUS_NO_IP_ADDRESSES, -EIO, "STATUS_NO_IP_ADDRESSES"}, {STATUS_WRONG_CREDENTIAL_HANDLE, -EIO, "STATUS_WRONG_CREDENTIAL_HANDLE"},

[ Upstream commit 18915b5873f07e5030e6fb108a050fa7c71c59fb ]

The ext4 fstrim implementation uses the block bitmaps to find free space that can be discarded. If we haven't replayed the journal, the bitmaps will be stale and we absolutely *cannot* use stale metadata to zap the underlying storage.

Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/ioctl.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 2e76fb55d94a..5f24fdc140ad 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -999,6 +999,13 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (!blk_queue_discard(q)) return -EOPNOTSUPP;

+ /* + * We haven't replayed the journal, so we cannot use our + * block-bitmap-guided storage zapping commands. + */ + if (test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) + return -EROFS; + if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT;

[ Upstream commit 9ce3ebe973bf4073426f35f282c6b955ed802765 ]

In the corner case where the gpio driver probe fails, for whatever reason, the suspend and resume handlers will still be called as they have to be registered as syscore operations. This applies as well when no probe was called while the driver has been built in the kernel.

Nicolas tracked this in : https://bugzilla.kernel.org/show_bug.cgi?id=200905

Therefore, add a failsafe in these function, and test if a proper probe succeeded and the driver is functional.

Signed-off-by: Robert Jarzmik robert.jarzmik@free.fr Reported-by: Nicolas Chauvet kwizart@gmail.com Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/gpio-pxa.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c index eb27fa76e8fc..bcc6be4a5cb2 100644 --- a/drivers/gpio/gpio-pxa.c +++ b/drivers/gpio/gpio-pxa.c @@ -777,6 +777,9 @@ static int pxa_gpio_suspend(void) struct pxa_gpio_bank *c; int gpio;

+ if (!pchip) + return 0; + for_each_gpio_bank(gpio, c, pchip) { c->saved_gplr = readl_relaxed(c->regbase + GPLR_OFFSET); c->saved_gpdr = readl_relaxed(c->regbase + GPDR_OFFSET); @@ -795,6 +798,9 @@ static void pxa_gpio_resume(void) struct pxa_gpio_bank *c; int gpio;

+ if (!pchip) + return; + for_each_gpio_bank(gpio, c, pchip) { /* restore level with set/clear */ writel_relaxed(c->saved_gplr, c->regbase + GPSR_OFFSET);

[ Upstream commit 7d20c8abb2edcf962ca857d51f4d0f9cd4b19053 ]

https://bugzilla.kernel.org/show_bug.cgi?id=200951

These is a NULL pointer dereference issue reported in bugzilla:

Hi, in the setup there is a SATA SSD connected to a SATA-to-USB bridge.

The disc is "Samsung SSD 850 PRO 256G" which supports TRIM. There are four partitions: sda1: FAT /boot sda2: F2FS / sda3: F2FS /home sda4: F2FS

The bridge is ASMT1153e which uses the "uas" driver. There is no TRIM pass-through, so, when mounting it reports: mounting with "discard" option, but the device does not support discard

The USB host is USB3.0 and UASP capable. It is the one on RK3399.

Given this everything works fine, except there is no TRIM support.

In order to enable TRIM a new UDEV rule is added [1]: /etc/udev/rules.d/10-sata-bridge-trim.rules: ACTION=="add|change", ATTRS{idVendor}=="174c", ATTRS{idProduct}=="55aa", SUBSYSTEM=="scsi_disk", ATTR{provisioning_mode}="unmap" After reboot any F2FS write hangs forever and dmesg reports: Unable to handle kernel NULL pointer dereference

Also tested on a x86_64 system: works fine even with TRIM enabled. same disc same bridge different usb host controller different cpu architecture not root filesystem

Regards, Vicenç.

[1] Post #5 in https://bbs.archlinux.org/viewtopic.php?id=236280

Unable to handle kernel NULL pointer dereference at virtual address 000000000000003e Mem abort info: ESR = 0x96000004 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgdp = 00000000626e3122 [000000000000003e] pgd=0000000000000000 Internal error: Oops: 96000004 [#1] SMP Modules linked in: overlay snd_soc_hdmi_codec rc_cec dw_hdmi_i2s_audio dw_hdmi_cec snd_soc_simple_card snd_soc_simple_card_utils snd_soc_rockchip_i2s rockchip_rga snd_soc_rockchip_pcm rockchipdrm videobuf2_dma_sg v4l2_mem2mem rtc_rk808 videobuf2_memops analogix_dp videobuf2_v4l2 videobuf2_common dw_hdmi dw_wdt cec rc_core videodev drm_kms_helper media drm rockchip_thermal rockchip_saradc realtek drm_panel_orientation_quirks syscopyarea sysfillrect sysimgblt fb_sys_fops dwmac_rk stmmac_platform stmmac pwm_bl squashfs loop crypto_user gpio_keys hid_kensington CPU: 5 PID: 957 Comm: nvim Not tainted 4.19.0-rc1-1-ARCH #1 Hardware name: Sapphire-RK3399 Board (DT) pstate: 00000005 (nzcv daif -PAN -UAO) pc : update_sit_entry+0x304/0x4b0 lr : update_sit_entry+0x108/0x4b0 sp : ffff00000ca13bd0 x29: ffff00000ca13bd0 x28: 000000000000003e x27: 0000000000000020 x26: 0000000000080000 x25: 0000000000000048 x24: ffff8000ebb85cf8 x23: 0000000000000253 x22: 00000000ffffffff x21: 00000000000535f2 x20: 00000000ffffffdf x19: ffff8000eb9e6800 x18: ffff8000eb9e6be8 x17: 0000000007ce6926 x16: 000000001c83ffa8 x15: 0000000000000000 x14: ffff8000f602df90 x13: 0000000000000006 x12: 0000000000000040 x11: 0000000000000228 x10: 0000000000000000 x9 : 0000000000000000 x8 : 0000000000000000 x7 : 00000000000535f2 x6 : ffff8000ebff3440 x5 : ffff8000ebff3440 x4 : ffff8000ebe3a6c8 x3 : 00000000ffffffff x2 : 0000000000000020 x1 : 0000000000000000 x0 : ffff8000eb9e5800 Process nvim (pid: 957, stack limit = 0x0000000063a78320) Call trace: update_sit_entry+0x304/0x4b0 f2fs_invalidate_blocks+0x98/0x140 truncate_node+0x90/0x400 f2fs_remove_inode_page+0xe8/0x340 f2fs_evict_inode+0x2b0/0x408 evict+0xe0/0x1e0 iput+0x160/0x260 do_unlinkat+0x214/0x298 __arm64_sys_unlinkat+0x3c/0x68 el0_svc_handler+0x94/0x118 el0_svc+0x8/0xc Code: f9400800 b9488400 36080140 f9400f01 (387c4820) ---[ end trace a0f21a307118c477 ]---

The reason is it is possible to enable discard flag on block queue via UDEV, but during mount, f2fs will initialize se->discard_map only if this flag is set, once the flag is set after mount, f2fs may dereference NULL pointer on se->discard_map.

So this patch does below changes to fix this issue: - initialize and update se->discard_map all the time. - don't clear DISCARD option if device has no QUEUE_FLAG_DISCARD flag during mount. - don't issue small discard on zoned block device. - introduce some functions to enhance the readability.

Signed-off-by: Chao Yu yuchao0@huawei.com Tested-by: Vicente Bergas vicencb@gmail.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/f2fs/debug.c | 3 +-- fs/f2fs/f2fs.h | 15 ++++++++--- fs/f2fs/file.c | 2 +- fs/f2fs/segment.c | 65 ++++++++++++++++++++--------------------------- fs/f2fs/super.c | 16 +++--------- 5 files changed, 46 insertions(+), 55 deletions(-)

diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 214a968962a1..ebe649d9793c 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -190,8 +190,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry); si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi)); si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); - if (f2fs_discard_en(sbi)) - si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); + si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); si->base_mem += SIT_VBLOCK_MAP_SIZE; if (sbi->segs_per_sec > 1) si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index a3ba20e5946f..1f5d5f62bb77 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3409,11 +3409,20 @@ static inline int get_blkz_type(struct f2fs_sb_info *sbi, } #endif

-static inline bool f2fs_discard_en(struct f2fs_sb_info *sbi) +static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi) { - struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev); + return f2fs_sb_has_blkzoned(sbi->sb); +}

- return blk_queue_discard(q) || f2fs_sb_has_blkzoned(sbi->sb); +static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi) +{ + return blk_queue_discard(bdev_get_queue(sbi->sb->s_bdev)); +} + +static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi) +{ + return (test_opt(sbi, DISCARD) && f2fs_hw_support_discard(sbi)) || + f2fs_hw_should_discard(sbi); }

static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 81c1dd635a8d..9fc076ca002d 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1983,7 +1983,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM;

- if (!blk_queue_discard(q)) + if (!f2fs_hw_support_discard(F2FS_SB(sb))) return -EOPNOTSUPP;

if (copy_from_user(&range, (struct fstrim_range __user *)arg, diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 1fa6f8185766..ac038563273d 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1744,11 +1744,11 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, struct list_head *head = &SM_I(sbi)->dcc_info->entry_list; int i;

- if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi)) + if (se->valid_blocks == max_blocks || !f2fs_hw_support_discard(sbi)) return false;

if (!force) { - if (!test_opt(sbi, DISCARD) || !se->valid_blocks || + if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks || SM_I(sbi)->dcc_info->nr_discards >= SM_I(sbi)->dcc_info->max_discards) return false; @@ -1854,7 +1854,7 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, dirty_i->nr_dirty[PRE]--; }

- if (!test_opt(sbi, DISCARD)) + if (!f2fs_realtime_discard_enable(sbi)) continue;

if (force && start >= cpc->trim_start && @@ -2044,8 +2044,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) del = 0; }

- if (f2fs_discard_en(sbi) && - !f2fs_test_and_set_bit(offset, se->discard_map)) + if (!f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--;

/* don't overwrite by SSR to keep node chain */ @@ -2073,8 +2072,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) del = 0; }

- if (f2fs_discard_en(sbi) && - f2fs_test_and_clear_bit(offset, se->discard_map)) + if (f2fs_test_and_clear_bit(offset, se->discard_map)) sbi->discard_blks++; } if (!f2fs_test_bit(offset, se->ckpt_valid_map)) @@ -2690,7 +2688,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) * discard option. User configuration looks like using runtime discard * or periodic fstrim instead of it. */ - if (test_opt(sbi, DISCARD)) + if (f2fs_realtime_discard_enable(sbi)) goto out;

start_block = START_BLOCK(sbi, start_segno); @@ -3781,13 +3779,11 @@ static int build_sit_info(struct f2fs_sb_info *sbi) return -ENOMEM; #endif

- if (f2fs_discard_en(sbi)) { - sit_i->sentries[start].discard_map - = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, - GFP_KERNEL); - if (!sit_i->sentries[start].discard_map) - return -ENOMEM; - } + sit_i->sentries[start].discard_map + = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, + GFP_KERNEL); + if (!sit_i->sentries[start].discard_map) + return -ENOMEM; }

sit_i->tmp_map = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); @@ -3935,18 +3931,16 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) total_node_blocks += se->valid_blocks;

/* build discard map only one time */ - if (f2fs_discard_en(sbi)) { - if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { - memset(se->discard_map, 0xff, - SIT_VBLOCK_MAP_SIZE); - } else { - memcpy(se->discard_map, - se->cur_valid_map, - SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += - sbi->blocks_per_seg - - se->valid_blocks; - } + if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { + memset(se->discard_map, 0xff, + SIT_VBLOCK_MAP_SIZE); + } else { + memcpy(se->discard_map, + se->cur_valid_map, + SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += + sbi->blocks_per_seg - + se->valid_blocks; }

if (sbi->segs_per_sec > 1) @@ -3984,16 +3978,13 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) if (IS_NODESEG(se->type)) total_node_blocks += se->valid_blocks;

- if (f2fs_discard_en(sbi)) { - if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { - memset(se->discard_map, 0xff, - SIT_VBLOCK_MAP_SIZE); - } else { - memcpy(se->discard_map, se->cur_valid_map, - SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += old_valid_blocks; - sbi->discard_blks -= se->valid_blocks; - } + if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { + memset(se->discard_map, 0xff, SIT_VBLOCK_MAP_SIZE); + } else { + memcpy(se->discard_map, se->cur_valid_map, + SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += old_valid_blocks; + sbi->discard_blks -= se->valid_blocks; }

if (sbi->segs_per_sec > 1) { diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 79370b7fa9d2..6539969a1c7f 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -360,7 +360,6 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) static int parse_options(struct super_block *sb, char *options) { struct f2fs_sb_info *sbi = F2FS_SB(sb); - struct request_queue *q; substring_t args[MAX_OPT_ARGS]; char *p, *name; int arg = 0; @@ -415,14 +414,7 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; break; case Opt_discard: - q = bdev_get_queue(sb->s_bdev); - if (blk_queue_discard(q)) { - set_opt(sbi, DISCARD); - } else if (!f2fs_sb_has_blkzoned(sb)) { - f2fs_msg(sb, KERN_WARNING, - "mounting with "discard" option, but " - "the device does not support discard"); - } + set_opt(sbi, DISCARD); break; case Opt_nodiscard: if (f2fs_sb_has_blkzoned(sb)) { @@ -1033,7 +1025,8 @@ static void f2fs_put_super(struct super_block *sb) /* be sure to wait for any on-going discard commands */ dropped = f2fs_wait_discard_bios(sbi);

- if (f2fs_discard_en(sbi) && !sbi->discard_blks && !dropped) { + if ((f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) && + !sbi->discard_blks && !dropped) { struct cp_control cpc = { .reason = CP_UMOUNT | CP_TRIMMED, }; @@ -1403,8 +1396,7 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, NOHEAP); sbi->sb->s_flags |= SB_LAZYTIME; set_opt(sbi, FLUSH_MERGE); - if (blk_queue_discard(bdev_get_queue(sbi->sb->s_bdev))) - set_opt(sbi, DISCARD); + set_opt(sbi, DISCARD); if (f2fs_sb_has_blkzoned(sbi->sb)) set_opt_mode(sbi, F2FS_MOUNT_LFS); else

[ Upstream commit 5e172f75e51e3de1b4274146d9b990f803cb5c2a ]

The default P9_LOCK_TIMEOUT can be too long for some users exporting a local file system to a guest VM (30s), make this configurable at mount time.

Link: http://lkml.kernel.org/r/1536295827-3181-1-git-send-email-asmadeus@codewreck... Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=195727 Signed-off-by: Dinu-Razvan Chis-Serban justcsdr@gmail.com Signed-off-by: Dominique Martinet dominique.martinet@cea.fr Signed-off-by: Sasha Levin sashal@kernel.org --- fs/9p/v9fs.c | 21 +++++++++++++++++++++ fs/9p/v9fs.h | 1 + fs/9p/vfs_file.c | 6 +++++- 3 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 89bac3d2f05b..619128b55837 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -61,6 +61,8 @@ enum { Opt_cache_loose, Opt_fscache, Opt_mmap, /* Access options */ Opt_access, Opt_posixacl, + /* Lock timeout option */ + Opt_locktimeout, /* Error token */ Opt_err }; @@ -80,6 +82,7 @@ static const match_table_t tokens = { {Opt_cachetag, "cachetag=%s"}, {Opt_access, "access=%s"}, {Opt_posixacl, "posixacl"}, + {Opt_locktimeout, "locktimeout=%u"}, {Opt_err, NULL} };

@@ -187,6 +190,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) #ifdef CONFIG_9P_FSCACHE v9ses->cachetag = NULL; #endif + v9ses->session_lock_timeout = P9_LOCK_TIMEOUT;

if (!opts) return 0; @@ -359,6 +363,23 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) #endif break;

+ case Opt_locktimeout: + r = match_int(&args[0], &option); + if (r < 0) { + p9_debug(P9_DEBUG_ERROR, + "integer field, but no integer?\n"); + ret = r; + continue; + } + if (option < 1) { + p9_debug(P9_DEBUG_ERROR, + "locktimeout must be a greater than zero integer.\n"); + ret = -EINVAL; + continue; + } + v9ses->session_lock_timeout = (long)option * HZ; + break; + default: continue; } diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 982e017acadb..129e5243a6bf 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -116,6 +116,7 @@ struct v9fs_session_info { struct p9_client *clnt; /* 9p client */ struct list_head slist; /* list of sessions registered with v9fs */ struct rw_semaphore rename_sem; + long session_lock_timeout; /* retry interval for blocking locks */ };

/* cache_validity flags */ diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index c87e6d6ec069..05454a7e22dc 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -154,6 +154,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) uint8_t status = P9_LOCK_ERROR; int res = 0; unsigned char fl_type; + struct v9fs_session_info *v9ses;

fid = filp->private_data; BUG_ON(fid == NULL); @@ -189,6 +190,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) if (IS_SETLKW(cmd)) flock.flags = P9_LOCK_FLAGS_BLOCK;

+ v9ses = v9fs_inode2v9ses(file_inode(filp)); + /* * if its a blocked request and we get P9_LOCK_BLOCKED as the status * for lock request, keep on trying @@ -202,7 +205,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) break; if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd)) break; - if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0) + if (schedule_timeout_interruptible(v9ses->session_lock_timeout) + != 0) break; /* * p9_client_lock_dotl overwrites flock.client_id with the

[ Upstream commit 042be0f849e5fc24116d0afecfaf926eed5cac63 ]

https://bugzilla.kernel.org/show_bug.cgi?id=200219

Reproduction way: - mount image - run poc code - umount image

F2FS-fs (loop1): Bitmap was wrongly set, blk:15364 ------------[ cut here ]------------ kernel BUG at /home/yuchao/git/devf2fs/segment.c:2061! invalid opcode: 0000 [#1] PREEMPT SMP CPU: 2 PID: 17686 Comm: umount Tainted: G W O 4.18.0-rc2+ #39 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 EIP: update_sit_entry+0x459/0x4e0 [f2fs] Code: e8 1c b5 fd ff 0f 0b 0f 0b 8b 45 e4 c7 44 24 08 9c 7a 6c f8 c7 44 24 04 bc 4a 6c f8 89 44 24 0c 8b 06 89 04 24 e8 f7 b4 fd ff <0f> 0b 8b 45 e4 0f b6 d2 89 54 24 10 c7 44 24 08 60 7a 6c f8 c7 44 EAX: 00000032 EBX: 000000f8 ECX: 00000002 EDX: 00000001 ESI: d7177000 EDI: f520fe68 EBP: d6477c6c ESP: d6477c34 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010282 CR0: 80050033 CR2: b7fbe000 CR3: 2a99b3c0 CR4: 000406f0 Call Trace: f2fs_allocate_data_block+0x124/0x580 [f2fs] do_write_page+0x78/0x150 [f2fs] f2fs_do_write_node_page+0x25/0xa0 [f2fs] __write_node_page+0x2bf/0x550 [f2fs] f2fs_sync_node_pages+0x60e/0x6d0 [f2fs] ? sync_inode_metadata+0x2f/0x40 ? f2fs_write_checkpoint+0x28f/0x7d0 [f2fs] ? up_write+0x1e/0x80 f2fs_write_checkpoint+0x2a9/0x7d0 [f2fs] ? mark_held_locks+0x5d/0x80 ? _raw_spin_unlock_irq+0x27/0x50 kill_f2fs_super+0x68/0x90 [f2fs] deactivate_locked_super+0x3d/0x70 deactivate_super+0x40/0x60 cleanup_mnt+0x39/0x70 __cleanup_mnt+0x10/0x20 task_work_run+0x81/0xa0 exit_to_usermode_loop+0x59/0xa7 do_fast_syscall_32+0x1f5/0x22c entry_SYSENTER_32+0x53/0x86 EIP: 0xb7f95c51 Code: c1 1e f7 ff ff 89 e5 8b 55 08 85 d2 8b 81 64 cd ff ff 74 02 89 02 5d c3 8b 0c 24 c3 8b 1c 24 c3 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: 00000000 EBX: 0871ab90 ECX: bfb2cd00 EDX: 00000000 ESI: 00000000 EDI: 0871ab90 EBP: 0871ab90 ESP: bfb2cd7c DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000246 Modules linked in: f2fs(O) crc32_generic bnep rfcomm bluetooth ecdh_generic snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq pcbc joydev aesni_intel snd_seq_device aes_i586 snd_timer crypto_simd snd cryptd soundcore mac_hid serio_raw video i2c_piix4 parport_pc ppdev lp parport hid_generic psmouse usbhid hid e1000 [last unloaded: f2fs] ---[ end trace d423f83982cfcdc5 ]---

The reason is, different log headers using the same segment, once one log's next block address is used by another log, it will cause panic as above.

Main area: 24 segs, 24 secs 24 zones - COLD data: 0, 0, 0 - WARM data: 1, 1, 1 - HOT data: 20, 20, 20 - Dir dnode: 22, 22, 22 - File dnode: 22, 22, 22 - Indir nodes: 21, 21, 21

So this patch adds sanity check to detect such condition to avoid this issue.

Signed-off-by: Chao Yu yuchao0@huawei.com

Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org

Signed-off-by: Sasha Levin sashal@kernel.org --- fs/f2fs/super.c | 34 +++++++++++++++++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 6539969a1c7f..06017138eab0 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2329,7 +2329,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) unsigned int segment_count_main; unsigned int cp_pack_start_sum, cp_payload; block_t user_block_count; - int i; + int i, j;

total = le32_to_cpu(raw_super->segment_count); fsmeta = le32_to_cpu(raw_super->segment_count_ckpt); @@ -2370,11 +2370,43 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg) return 1; + for (j = i + 1; j < NR_CURSEG_NODE_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) == + le32_to_cpu(ckpt->cur_node_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Node segment (%u, %u) has the same " + "segno: %u", i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); + return 1; + } + } } for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) { if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg) return 1; + for (j = i + 1; j < NR_CURSEG_DATA_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_data_segno[i]) == + le32_to_cpu(ckpt->cur_data_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Data segment (%u, %u) has the same " + "segno: %u", i, j, + le32_to_cpu(ckpt->cur_data_segno[i])); + return 1; + } + } + } + for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { + for (j = i; j < NR_CURSEG_DATA_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) == + le32_to_cpu(ckpt->cur_data_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Data segment (%u) and Data segment (%u)" + " has the same segno: %u", i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); + return 1; + } + } }

sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);

[ Upstream commit 4bb1ce2350a598502b23088b169e16b43d4bc639 ]

When console device is rebinded, console_setup() is called again. But marking it as __init means that function will be clear after boot is complete. If console device is binded again console_setup() is not found and error "Unable to handle kernel paging request at virtual address" is reported.

Signed-off-by: Michal Simek michal.simek@xilinx.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/tty/serial/xilinx_uartps.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index 0e3627289047..77efa0a43fe7 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1223,7 +1223,7 @@ static void cdns_uart_console_write(struct console *co, const char *s, * * Return: 0 on success, negative errno otherwise. */ -static int __init cdns_uart_console_setup(struct console *co, char *options) +static int cdns_uart_console_setup(struct console *co, char *options) { struct uart_port *port = console_port;

[ Upstream commit 4add7104919f9e94e0db03e234caeadbfcc02ea9 ]

If au0828_analog_register fails, the dev is kfree'd and then flow jumps to done, which can call au0828_usb_disconnect. Since all USB error codes are negative, au0828_usb_disconnect will be called. The problem is au0828_usb_disconnect uses dev, if dev is NULL then there is immediate oops encountered.

[ 7.454307] au0828: au0828_usb_probe() au0282_dev_register failed to register on V4L2 [ 7.454323] BUG: unable to handle kernel NULL pointer dereference at 0000000000000050 [ 7.454421] PGD 0 P4D 0 [ 7.454457] Oops: 0002 [#1] SMP PTI [ 7.454500] CPU: 1 PID: 262 Comm: systemd-udevd Tainted: P O 4.18.3 #1 [ 7.454584] Hardware name: Google Panther/Panther, BIOS MattDevo 04/27/2015 [ 7.454670] RIP: 0010:_raw_spin_lock_irqsave+0x2c/0x50 [ 7.454725] Code: 44 00 00 55 48 89 e5 41 54 53 48 89 fb 9c 58 0f 1f 44 00 00 49 89 c4 fa 66 0f 1f 44 00 00 e8 db 23 1b ff 31 c0 ba 01 00 00 00 <f0> 0f b1 13 85 c0 75 08 4c 89 e0 5b 41 5c 5d c3 89 c6 48 89 df e8 [ 7.455004] RSP: 0018:ffff9130f53ef988 EFLAGS: 00010046 [ 7.455063] RAX: 0000000000000000 RBX: 0000000000000050 RCX: 0000000000000000 [ 7.455139] RDX: 0000000000000001 RSI: 0000000000000003 RDI: 0000000000000050 [ 7.455216] RBP: ffff9130f53ef998 R08: 0000000000000018 R09: 0000000000000090 [ 7.455292] R10: ffffed4cc53cb000 R11: ffffed4cc53cb108 R12: 0000000000000082 [ 7.455369] R13: ffff9130cf2c6188 R14: 0000000000000000 R15: 0000000000000018 [ 7.455447] FS: 00007f2ff8514cc0(0000) GS:ffff9130fcb00000(0000) knlGS:0000000000000000 [ 7.455535] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7.455597] CR2: 0000000000000050 CR3: 00000001753f0002 CR4: 00000000000606a0 [ 7.455675] Call Trace: [ 7.455713] __wake_up_common_lock+0x65/0xc0 [ 7.455764] __wake_up+0x13/0x20 [ 7.455808] ir_lirc_unregister+0x57/0xe0 [rc_core] [ 7.455865] rc_unregister_device+0xa0/0xc0 [rc_core] [ 7.455935] au0828_rc_unregister+0x25/0x40 [au0828] [ 7.455999] au0828_usb_disconnect+0x33/0x80 [au0828] [ 7.456064] au0828_usb_probe.cold.16+0x8d/0x2aa [au0828] [ 7.456130] usb_probe_interface+0xf1/0x300 [ 7.456184] driver_probe_device+0x2e3/0x460 [ 7.456235] __driver_attach+0xe4/0x110 [ 7.456282] ? driver_probe_device+0x460/0x460 [ 7.456335] bus_for_each_dev+0x74/0xb0 [ 7.456385] ? kmem_cache_alloc_trace+0x15d/0x1d0 [ 7.456441] driver_attach+0x1e/0x20 [ 7.456485] bus_add_driver+0x159/0x230 [ 7.456532] driver_register+0x70/0xc0 [ 7.456578] usb_register_driver+0x7f/0x140 [ 7.456626] ? 0xffffffffc0474000 [ 7.456674] au0828_init+0xbc/0x1000 [au0828] [ 7.456725] do_one_initcall+0x4a/0x1c9 [ 7.456771] ? _cond_resched+0x19/0x30 [ 7.456817] ? kmem_cache_alloc_trace+0x15d/0x1d0 [ 7.456873] do_init_module+0x60/0x210 [ 7.456918] load_module+0x221b/0x2710 [ 7.456966] ? vfs_read+0xf5/0x120 [ 7.457010] __do_sys_finit_module+0xbd/0x120 [ 7.457061] ? __do_sys_finit_module+0xbd/0x120 [ 7.457115] __x64_sys_finit_module+0x1a/0x20 [ 7.457166] do_syscall_64+0x5b/0x110 [ 7.457210] entry_SYSCALL_64_after_hwframe+0x49/0xbe

Signed-off-by: Brad Love brad@nextdimension.cc Signed-off-by: Hans Verkuil hans.verkuil@cisco.com Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/au0828/au0828-core.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/drivers/media/usb/au0828/au0828-core.c b/drivers/media/usb/au0828/au0828-core.c index cd363a2100d4..257ae0d8cfe2 100644 --- a/drivers/media/usb/au0828/au0828-core.c +++ b/drivers/media/usb/au0828/au0828-core.c @@ -629,7 +629,6 @@ static int au0828_usb_probe(struct usb_interface *interface, pr_err("%s() au0282_dev_register failed to register on V4L2\n", __func__); mutex_unlock(&dev->lock); - kfree(dev); goto done; }

[ Upstream commit 9ee3e06610fdb8a601cde59c92089fb6c1deb4aa ]

A particular touchpad (SIPODEV SP1064) refuses to supply the HID descriptors. This patch provides the framework for overriding these descriptors based on DMI data. It also includes the descriptors for said touchpad, which were extracted by listening to the traffic of the windows filter driver, as well as the DMI data for the laptops known to use this device.

Relevant Bug: https://bugzilla.redhat.com/show_bug.cgi?id=1526312

Cc: Hans de Goede hdegoede@redhat.com Reported-and-tested-by: ahormann@gmx.net Reported-and-tested-by: Bruno Jesus bruno.fl.jesus@gmail.com Reported-and-tested-by: Dietrich enaut.w@googlemail.com Reported-and-tested-by: kloxdami@yahoo.com Signed-off-by: Julian Sax jsbc@gmx.de Reviewed-by: Benjamin Tissoires benjamin.tissoires@redhat.com Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/i2c-hid/Makefile | 3 + .../hid/i2c-hid/{i2c-hid.c => i2c-hid-core.c} | 56 ++- drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c | 376 ++++++++++++++++++ drivers/hid/i2c-hid/i2c-hid.h | 20 + 4 files changed, 437 insertions(+), 18 deletions(-) rename drivers/hid/i2c-hid/{i2c-hid.c => i2c-hid-core.c} (96%) create mode 100644 drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c create mode 100644 drivers/hid/i2c-hid/i2c-hid.h

diff --git a/drivers/hid/i2c-hid/Makefile b/drivers/hid/i2c-hid/Makefile index 832d8f9aaba2..099e1ce2f234 100644 --- a/drivers/hid/i2c-hid/Makefile +++ b/drivers/hid/i2c-hid/Makefile @@ -3,3 +3,6 @@ #

obj-$(CONFIG_I2C_HID) += i2c-hid.o + +i2c-hid-objs = i2c-hid-core.o +i2c-hid-$(CONFIG_DMI) += i2c-hid-dmi-quirks.o diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid-core.c similarity index 96% rename from drivers/hid/i2c-hid/i2c-hid.c rename to drivers/hid/i2c-hid/i2c-hid-core.c index 88daa388e1f6..3cde7c1b9c33 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -43,6 +43,7 @@ #include <linux/platform_data/i2c-hid.h>

#include "../hid-ids.h" +#include "i2c-hid.h"

/* quirks to control the device */ #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV BIT(0) @@ -687,6 +688,7 @@ static int i2c_hid_parse(struct hid_device *hid) char *rdesc; int ret; int tries = 3; + char *use_override;

i2c_hid_dbg(ihid, "entering %s\n", __func__);

@@ -705,26 +707,37 @@ static int i2c_hid_parse(struct hid_device *hid) if (ret) return ret;

- rdesc = kzalloc(rsize, GFP_KERNEL); + use_override = i2c_hid_get_dmi_hid_report_desc_override(client->name, + &rsize);

- if (!rdesc) { - dbg_hid("couldn't allocate rdesc memory\n"); - return -ENOMEM; - } + if (use_override) { + rdesc = use_override; + i2c_hid_dbg(ihid, "Using a HID report descriptor override\n"); + } else { + rdesc = kzalloc(rsize, GFP_KERNEL); + + if (!rdesc) { + dbg_hid("couldn't allocate rdesc memory\n"); + return -ENOMEM; + }

- i2c_hid_dbg(ihid, "asking HID report descriptor\n"); + i2c_hid_dbg(ihid, "asking HID report descriptor\n");

- ret = i2c_hid_command(client, &hid_report_descr_cmd, rdesc, rsize); - if (ret) { - hid_err(hid, "reading report descriptor failed\n"); - kfree(rdesc); - return -EIO; + ret = i2c_hid_command(client, &hid_report_descr_cmd, + rdesc, rsize); + if (ret) { + hid_err(hid, "reading report descriptor failed\n"); + kfree(rdesc); + return -EIO; + } }

i2c_hid_dbg(ihid, "Report Descriptor: %*ph\n", rsize, rdesc);

ret = hid_parse_report(hid, rdesc, rsize); - kfree(rdesc); + if (!use_override) + kfree(rdesc); + if (ret) { dbg_hid("parsing report descriptor failed\n"); return ret; @@ -851,12 +864,19 @@ static int i2c_hid_fetch_hid_descriptor(struct i2c_hid *ihid) int ret;

/* i2c hid fetch using a fixed descriptor size (30 bytes) */ - i2c_hid_dbg(ihid, "Fetching the HID descriptor\n"); - ret = i2c_hid_command(client, &hid_descr_cmd, ihid->hdesc_buffer, - sizeof(struct i2c_hid_desc)); - if (ret) { - dev_err(&client->dev, "hid_descr_cmd failed\n"); - return -ENODEV; + if (i2c_hid_get_dmi_i2c_hid_desc_override(client->name)) { + i2c_hid_dbg(ihid, "Using a HID descriptor override\n"); + ihid->hdesc = + *i2c_hid_get_dmi_i2c_hid_desc_override(client->name); + } else { + i2c_hid_dbg(ihid, "Fetching the HID descriptor\n"); + ret = i2c_hid_command(client, &hid_descr_cmd, + ihid->hdesc_buffer, + sizeof(struct i2c_hid_desc)); + if (ret) { + dev_err(&client->dev, "hid_descr_cmd failed\n"); + return -ENODEV; + } }

/* Validate the length of HID descriptor, the 4 first bytes: diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c new file mode 100644 index 000000000000..1d645c9ab417 --- /dev/null +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Quirks for I2C-HID devices that do not supply proper descriptors + * + * Copyright (c) 2018 Julian Sax jsbc@gmx.de + * + */ + +#include <linux/types.h> +#include <linux/dmi.h> +#include <linux/mod_devicetable.h> + +#include "i2c-hid.h" + + +struct i2c_hid_desc_override { + union { + struct i2c_hid_desc *i2c_hid_desc; + uint8_t *i2c_hid_desc_buffer; + }; + uint8_t *hid_report_desc; + unsigned int hid_report_desc_size; + uint8_t *i2c_name; +}; + + +/* + * descriptors for the SIPODEV SP1064 touchpad + * + * This device does not supply any descriptors and on windows a filter + * driver operates between the i2c-hid layer and the device and injects + * these descriptors when the device is prompted. The descriptors were + * extracted by listening to the i2c-hid traffic that occurs between the + * windows filter driver and the windows i2c-hid driver. + */ + +static const struct i2c_hid_desc_override sipodev_desc = { + .i2c_hid_desc_buffer = (uint8_t []) + {0x1e, 0x00, /* Length of descriptor */ + 0x00, 0x01, /* Version of descriptor */ + 0xdb, 0x01, /* Length of report descriptor */ + 0x21, 0x00, /* Location of report descriptor */ + 0x24, 0x00, /* Location of input report */ + 0x1b, 0x00, /* Max input report length */ + 0x25, 0x00, /* Location of output report */ + 0x11, 0x00, /* Max output report length */ + 0x22, 0x00, /* Location of command register */ + 0x23, 0x00, /* Location of data register */ + 0x11, 0x09, /* Vendor ID */ + 0x88, 0x52, /* Product ID */ + 0x06, 0x00, /* Version ID */ + 0x00, 0x00, 0x00, 0x00 /* Reserved */ + }, + + .hid_report_desc = (uint8_t []) + {0x05, 0x01, /* Usage Page (Desktop), */ + 0x09, 0x02, /* Usage (Mouse), */ + 0xA1, 0x01, /* Collection (Application), */ + 0x85, 0x01, /* Report ID (1), */ + 0x09, 0x01, /* Usage (Pointer), */ + 0xA1, 0x00, /* Collection (Physical), */ + 0x05, 0x09, /* Usage Page (Button), */ + 0x19, 0x01, /* Usage Minimum (01h), */ + 0x29, 0x02, /* Usage Maximum (02h), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x02, /* Report Count (2), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x06, /* Report Count (6), */ + 0x81, 0x01, /* Input (Constant), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x09, 0x30, /* Usage (X), */ + 0x09, 0x31, /* Usage (Y), */ + 0x15, 0x81, /* Logical Minimum (-127), */ + 0x25, 0x7F, /* Logical Maximum (127), */ + 0x75, 0x08, /* Report Size (8), */ + 0x95, 0x02, /* Report Count (2), */ + 0x81, 0x06, /* Input (Variable, Relative), */ + 0xC0, /* End Collection, */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x05, /* Usage (Touchpad), */ + 0xA1, 0x01, /* Collection (Application), */ + 0x85, 0x04, /* Report ID (4), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x02, /* Collection (Logical), */ + 0x15, 0x00, /* Logical Minimum (0), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x09, 0x47, /* Usage (Touch Valid), */ + 0x09, 0x42, /* Usage (Tip Switch), */ + 0x95, 0x02, /* Report Count (2), */ + 0x75, 0x01, /* Report Size (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x01, /* Report Count (1), */ + 0x75, 0x03, /* Report Size (3), */ + 0x25, 0x05, /* Logical Maximum (5), */ + 0x09, 0x51, /* Usage (Contact Identifier), */ + 0x81, 0x02, /* Input (Variable), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x03, /* Report Count (3), */ + 0x81, 0x03, /* Input (Constant, Variable), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x26, 0x44, 0x0A, /* Logical Maximum (2628), */ + 0x75, 0x10, /* Report Size (16), */ + 0x55, 0x0E, /* Unit Exponent (14), */ + 0x65, 0x11, /* Unit (Centimeter), */ + 0x09, 0x30, /* Usage (X), */ + 0x46, 0x1A, 0x04, /* Physical Maximum (1050), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x46, 0xBC, 0x02, /* Physical Maximum (700), */ + 0x26, 0x34, 0x05, /* Logical Maximum (1332), */ + 0x09, 0x31, /* Usage (Y), */ + 0x81, 0x02, /* Input (Variable), */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x02, /* Collection (Logical), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x09, 0x47, /* Usage (Touch Valid), */ + 0x09, 0x42, /* Usage (Tip Switch), */ + 0x95, 0x02, /* Report Count (2), */ + 0x75, 0x01, /* Report Size (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x01, /* Report Count (1), */ + 0x75, 0x03, /* Report Size (3), */ + 0x25, 0x05, /* Logical Maximum (5), */ + 0x09, 0x51, /* Usage (Contact Identifier), */ + 0x81, 0x02, /* Input (Variable), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x03, /* Report Count (3), */ + 0x81, 0x03, /* Input (Constant, Variable), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x26, 0x44, 0x0A, /* Logical Maximum (2628), */ + 0x75, 0x10, /* Report Size (16), */ + 0x09, 0x30, /* Usage (X), */ + 0x46, 0x1A, 0x04, /* Physical Maximum (1050), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x46, 0xBC, 0x02, /* Physical Maximum (700), */ + 0x26, 0x34, 0x05, /* Logical Maximum (1332), */ + 0x09, 0x31, /* Usage (Y), */ + 0x81, 0x02, /* Input (Variable), */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x02, /* Collection (Logical), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x09, 0x47, /* Usage (Touch Valid), */ + 0x09, 0x42, /* Usage (Tip Switch), */ + 0x95, 0x02, /* Report Count (2), */ + 0x75, 0x01, /* Report Size (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x01, /* Report Count (1), */ + 0x75, 0x03, /* Report Size (3), */ + 0x25, 0x05, /* Logical Maximum (5), */ + 0x09, 0x51, /* Usage (Contact Identifier), */ + 0x81, 0x02, /* Input (Variable), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x03, /* Report Count (3), */ + 0x81, 0x03, /* Input (Constant, Variable), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x26, 0x44, 0x0A, /* Logical Maximum (2628), */ + 0x75, 0x10, /* Report Size (16), */ + 0x09, 0x30, /* Usage (X), */ + 0x46, 0x1A, 0x04, /* Physical Maximum (1050), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x46, 0xBC, 0x02, /* Physical Maximum (700), */ + 0x26, 0x34, 0x05, /* Logical Maximum (1332), */ + 0x09, 0x31, /* Usage (Y), */ + 0x81, 0x02, /* Input (Variable), */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x02, /* Collection (Logical), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x09, 0x47, /* Usage (Touch Valid), */ + 0x09, 0x42, /* Usage (Tip Switch), */ + 0x95, 0x02, /* Report Count (2), */ + 0x75, 0x01, /* Report Size (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x01, /* Report Count (1), */ + 0x75, 0x03, /* Report Size (3), */ + 0x25, 0x05, /* Logical Maximum (5), */ + 0x09, 0x51, /* Usage (Contact Identifier), */ + 0x81, 0x02, /* Input (Variable), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x03, /* Report Count (3), */ + 0x81, 0x03, /* Input (Constant, Variable), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x26, 0x44, 0x0A, /* Logical Maximum (2628), */ + 0x75, 0x10, /* Report Size (16), */ + 0x09, 0x30, /* Usage (X), */ + 0x46, 0x1A, 0x04, /* Physical Maximum (1050), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x46, 0xBC, 0x02, /* Physical Maximum (700), */ + 0x26, 0x34, 0x05, /* Logical Maximum (1332), */ + 0x09, 0x31, /* Usage (Y), */ + 0x81, 0x02, /* Input (Variable), */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x55, 0x0C, /* Unit Exponent (12), */ + 0x66, 0x01, 0x10, /* Unit (Seconds), */ + 0x47, 0xFF, 0xFF, 0x00, 0x00,/* Physical Maximum (65535), */ + 0x27, 0xFF, 0xFF, 0x00, 0x00,/* Logical Maximum (65535), */ + 0x75, 0x10, /* Report Size (16), */ + 0x95, 0x01, /* Report Count (1), */ + 0x09, 0x56, /* Usage (Scan Time), */ + 0x81, 0x02, /* Input (Variable), */ + 0x09, 0x54, /* Usage (Contact Count), */ + 0x25, 0x7F, /* Logical Maximum (127), */ + 0x75, 0x08, /* Report Size (8), */ + 0x81, 0x02, /* Input (Variable), */ + 0x05, 0x09, /* Usage Page (Button), */ + 0x09, 0x01, /* Usage (01h), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x07, /* Report Count (7), */ + 0x81, 0x03, /* Input (Constant, Variable), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x85, 0x02, /* Report ID (2), */ + 0x09, 0x55, /* Usage (Contact Count Maximum), */ + 0x09, 0x59, /* Usage (59h), */ + 0x75, 0x04, /* Report Size (4), */ + 0x95, 0x02, /* Report Count (2), */ + 0x25, 0x0F, /* Logical Maximum (15), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x85, 0x07, /* Report ID (7), */ + 0x09, 0x60, /* Usage (60h), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x01, /* Report Count (1), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0x95, 0x07, /* Report Count (7), */ + 0xB1, 0x03, /* Feature (Constant, Variable), */ + 0x85, 0x06, /* Report ID (6), */ + 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */ + 0x09, 0xC5, /* Usage (C5h), */ + 0x26, 0xFF, 0x00, /* Logical Maximum (255), */ + 0x75, 0x08, /* Report Size (8), */ + 0x96, 0x00, 0x01, /* Report Count (256), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0xC0, /* End Collection, */ + 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */ + 0x09, 0x01, /* Usage (01h), */ + 0xA1, 0x01, /* Collection (Application), */ + 0x85, 0x0D, /* Report ID (13), */ + 0x26, 0xFF, 0x00, /* Logical Maximum (255), */ + 0x19, 0x01, /* Usage Minimum (01h), */ + 0x29, 0x02, /* Usage Maximum (02h), */ + 0x75, 0x08, /* Report Size (8), */ + 0x95, 0x02, /* Report Count (2), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x0E, /* Usage (Configuration), */ + 0xA1, 0x01, /* Collection (Application), */ + 0x85, 0x03, /* Report ID (3), */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x02, /* Collection (Logical), */ + 0x09, 0x52, /* Usage (Device Mode), */ + 0x25, 0x0A, /* Logical Maximum (10), */ + 0x95, 0x01, /* Report Count (1), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0xC0, /* End Collection, */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x00, /* Collection (Physical), */ + 0x85, 0x05, /* Report ID (5), */ + 0x09, 0x57, /* Usage (57h), */ + 0x09, 0x58, /* Usage (58h), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x02, /* Report Count (2), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0x95, 0x06, /* Report Count (6), */ + 0xB1, 0x03, /* Feature (Constant, Variable),*/ + 0xC0, /* End Collection, */ + 0xC0 /* End Collection */ + }, + .hid_report_desc_size = 475, + .i2c_name = "SYNA3602:00" +}; + + +static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { + { + .ident = "Teclast F6 Pro", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TECLAST"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "F6 Pro"), + }, + .driver_data = (void *)&sipodev_desc + }, + { + .ident = "Teclast F7", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TECLAST"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "F7"), + }, + .driver_data = (void *)&sipodev_desc + }, + { + .ident = "Trekstor Primebook C13", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Primebook C13"), + }, + .driver_data = (void *)&sipodev_desc + }, + { + .ident = "Trekstor Primebook C11", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Primebook C11"), + }, + .driver_data = (void *)&sipodev_desc + }, + { + .ident = "Direkt-Tek DTLAPY116-2", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "DTLAPY116-2"), + }, + .driver_data = (void *)&sipodev_desc + }, + { + .ident = "Mediacom Flexbook Edge 11", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "MEDIACOM"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "FlexBook edge11 - M-FBE11"), + }, + .driver_data = (void *)&sipodev_desc + } +}; + + +struct i2c_hid_desc *i2c_hid_get_dmi_i2c_hid_desc_override(uint8_t *i2c_name) +{ + struct i2c_hid_desc_override *override; + const struct dmi_system_id *system_id; + + system_id = dmi_first_match(i2c_hid_dmi_desc_override_table); + if (!system_id) + return NULL; + + override = system_id->driver_data; + if (strcmp(override->i2c_name, i2c_name)) + return NULL; + + return override->i2c_hid_desc; +} + +char *i2c_hid_get_dmi_hid_report_desc_override(uint8_t *i2c_name, + unsigned int *size) +{ + struct i2c_hid_desc_override *override; + const struct dmi_system_id *system_id; + + system_id = dmi_first_match(i2c_hid_dmi_desc_override_table); + if (!system_id) + return NULL; + + override = system_id->driver_data; + if (strcmp(override->i2c_name, i2c_name)) + return NULL; + + *size = override->hid_report_desc_size; + return override->hid_report_desc; +} diff --git a/drivers/hid/i2c-hid/i2c-hid.h b/drivers/hid/i2c-hid/i2c-hid.h new file mode 100644 index 000000000000..a8c19aef5824 --- /dev/null +++ b/drivers/hid/i2c-hid/i2c-hid.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef I2C_HID_H +#define I2C_HID_H + + +#ifdef CONFIG_DMI +struct i2c_hid_desc *i2c_hid_get_dmi_i2c_hid_desc_override(uint8_t *i2c_name); +char *i2c_hid_get_dmi_hid_report_desc_override(uint8_t *i2c_name, + unsigned int *size); +#else +static inline struct i2c_hid_desc + *i2c_hid_get_dmi_i2c_hid_desc_override(uint8_t *i2c_name) +{ return NULL; } +static inline char *i2c_hid_get_dmi_hid_report_desc_override(uint8_t *i2c_name, + unsigned int *size) +{ return NULL; } +#endif + +#endif

[ Upstream commit 6862fdf2201ab67cd962dbf0643d37db909f4860 ]

"S3C2410 PM Suspend Memory CRC" feature (controlled by SAMSUNG_PM_CHECK config option) is incompatible with highmem (uses phys_to_virt() instead of proper mapping) which is used by the majority of Exynos boards. The issue manifests itself in OOPS on affected boards, i.e. on Odroid-U3 I got the following one:

Unable to handle kernel paging request at virtual address f0000000 pgd = 1c0f9bb4 [f0000000] *pgd=00000000 Internal error: Oops: 5 [#1] PREEMPT SMP ARM [<c0458034>] (crc32_le) from [<c0121f8c>] (s3c_pm_makecheck+0x34/0x54) [<c0121f8c>] (s3c_pm_makecheck) from [<c0121efc>] (s3c_pm_run_res+0x74/0x8c) [<c0121efc>] (s3c_pm_run_res) from [<c0121ecc>] (s3c_pm_run_res+0x44/0x8c) [<c0121ecc>] (s3c_pm_run_res) from [<c01210b8>] (exynos_suspend_enter+0x64/0x148) [<c01210b8>] (exynos_suspend_enter) from [<c018893c>] (suspend_devices_and_enter+0x9ec/0xe74) [<c018893c>] (suspend_devices_and_enter) from [<c0189534>] (pm_suspend+0x770/0xc04) [<c0189534>] (pm_suspend) from [<c0186ce8>] (state_store+0x6c/0xcc) [<c0186ce8>] (state_store) from [<c09db434>] (kobj_attr_store+0x14/0x20) [<c09db434>] (kobj_attr_store) from [<c02fa63c>] (sysfs_kf_write+0x4c/0x50) [<c02fa63c>] (sysfs_kf_write) from [<c02f97a4>] (kernfs_fop_write+0xfc/0x1e4) [<c02f97a4>] (kernfs_fop_write) from [<c027b198>] (__vfs_write+0x2c/0x140) [<c027b198>] (__vfs_write) from [<c027b418>] (vfs_write+0xa4/0x160) [<c027b418>] (vfs_write) from [<c027b5d8>] (ksys_write+0x40/0x8c) [<c027b5d8>] (ksys_write) from [<c0101000>] (ret_fast_syscall+0x0/0x28)

Add PLAT_S3C24XX, ARCH_S3C64XX and ARCH_S5PV210 dependencies to SAMSUNG_PM_CHECK config option to hide it on Exynos platforms.

Signed-off-by: Bartlomiej Zolnierkiewicz b.zolnierkie@samsung.com Signed-off-by: Krzysztof Kozlowski krzk@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/plat-samsung/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig index b600e38364eb..377ff9cda667 100644 --- a/arch/arm/plat-samsung/Kconfig +++ b/arch/arm/plat-samsung/Kconfig @@ -256,7 +256,7 @@ config S3C_PM_DEBUG_LED_SMDK

config SAMSUNG_PM_CHECK bool "S3C2410 PM Suspend Memory CRC" - depends on PM + depends on PM && (PLAT_S3C24XX || ARCH_S3C64XX || ARCH_S5PV210) select CRC32 help Enable the PM code's memory area checksum over sleep. This option

[ Upstream commit ca1721c5bee77105829cbd7baab8ee0eab85b06d ]

On Apple machines, plugging-in or unplugging the power triggers a GPE for the EC. Since these machines expose an SBS device, this GPE ends up triggering the acpi_sbs_callback(). This in turn tries to get the status of the SBS charger. However, on MBP13,* and MBP14,* machines, performing the smbus-read operation to get the charger's status triggers the EC's GPE again. The result is an endless re-triggering and handling of that GPE, consuming significant CPU resources (> 50% in irq).

In the end this is quite similar to commit 3031cddea633 (ACPI / SBS: Don't assume the existence of an SBS charger), except that on the above machines a status of all 1's is returned. And like there, we just want ignore the charger here.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=198169 Signed-off-by: Ronald Tschalär ronald@innovation.ch Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/sbs.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index 295b59271189..96c5e27967f4 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -441,9 +441,13 @@ static int acpi_ac_get_present(struct acpi_sbs *sbs)

/* * The spec requires that bit 4 always be 1. If it's not set, assume - * that the implementation doesn't support an SBS charger + * that the implementation doesn't support an SBS charger. + * + * And on some MacBooks a status of 0xffff is always returned, no + * matter whether the charger is plugged in or not, which is also + * wrong, so ignore the SBS charger for those too. */ - if (!((status >> 4) & 0x1)) + if (!((status >> 4) & 0x1) || status == 0xffff) return -ENODEV;

sbs->charger_present = (status >> 15) & 0x1;

[ Upstream commit bd18bffca35397214ae68d85cf7203aca25c3c1d ]

A VMEnter that VMFails (as opposed to VMExits) does not touch host state beyond registers that are explicitly noted in the VMFail path, e.g. EFLAGS. Host state does not need to be loaded because VMFail is only signaled for consistency checks that occur before the CPU starts to load guest state, i.e. there is no need to restore any state as nothing has been modified. But in the case where a VMFail is detected by hardware and not by KVM (due to deferring consistency checks to hardware), KVM has already loaded some amount of guest state. Luckily, "loaded" only means loaded to KVM's software model, i.e. vmcs01 has not been modified. So, unwind our software model to the pre-VMEntry host state.

Not restoring host state in this VMFail path leads to a variety of failures because we end up with stale data in vcpu->arch, e.g. CR0, CR4, EFER, etc... will all be out of sync relative to vmcs01. Any significant delta in the stale data is all but guaranteed to crash L1, e.g. emulation of SMEP, SMAP, UMIP, WP, etc... will be wrong.

An alternative to this "soft" reload would be to load host state from vmcs12 as if we triggered a VMExit (as opposed to VMFail), but that is wildly inconsistent with respect to the VMX architecture, e.g. an L1 VMM with separate VMExit and VMFail paths would explode.

Note that this approach does not mean KVM is 100% accurate with respect to VMX hardware behavior, even at an architectural level (the exact order of consistency checks is microarchitecture specific). But 100% emulation accuracy isn't the goal (with this patch), rather the goal is to be consistent in the information delivered to L1, e.g. a VMExit should not fall-through VMENTER, and a VMFail should not jump to HOST_RIP.

This technically reverts commit "5af4157388ad (KVM: nVMX: Fix mmu context after VMLAUNCH/VMRESUME failure)", but retains the core aspects of that patch, just in an open coded form due to the need to pull state from vmcs01 instead of vmcs12. Restoring host state resolves a variety of issues introduced by commit "4f350c6dbcb9 (kvm: nVMX: Handle deferred early VMLAUNCH/VMRESUME failure properly)", which remedied the incorrect behavior of treating VMFail like VMExit but in doing so neglected to restore arch state that had been modified prior to attempting nested VMEnter.

A sample failure that occurs due to stale vcpu.arch state is a fault of some form while emulating an LGDT (due to emulated UMIP) from L1 after a failed VMEntry to L3, in this case when running the KVM unit test test_tpr_threshold_values in L1. L0 also hits a WARN in this case due to a stale arch.cr4.UMIP.

L1: BUG: unable to handle kernel paging request at ffffc90000663b9e PGD 276512067 P4D 276512067 PUD 276513067 PMD 274efa067 PTE 8000000271de2163 Oops: 0009 [#1] SMP CPU: 5 PID: 12495 Comm: qemu-system-x86 Tainted: G W 4.18.0-rc2+ #2 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:native_load_gdt+0x0/0x10

...

Call Trace: load_fixmap_gdt+0x22/0x30 __vmx_load_host_state+0x10e/0x1c0 [kvm_intel] vmx_switch_vmcs+0x2d/0x50 [kvm_intel] nested_vmx_vmexit+0x222/0x9c0 [kvm_intel] vmx_handle_exit+0x246/0x15a0 [kvm_intel] kvm_arch_vcpu_ioctl_run+0x850/0x1830 [kvm] kvm_vcpu_ioctl+0x3a1/0x5c0 [kvm] do_vfs_ioctl+0x9f/0x600 ksys_ioctl+0x66/0x70 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x4f/0x100 entry_SYSCALL_64_after_hwframe+0x44/0xa9

L0: WARNING: CPU: 2 PID: 3529 at arch/x86/kvm/vmx.c:6618 handle_desc+0x28/0x30 [kvm_intel] ... CPU: 2 PID: 3529 Comm: qemu-system-x86 Not tainted 4.17.2-coffee+ #76 Hardware name: Intel Corporation Kabylake Client platform/KBL S RIP: 0010:handle_desc+0x28/0x30 [kvm_intel]

...

Call Trace: kvm_arch_vcpu_ioctl_run+0x863/0x1840 [kvm] kvm_vcpu_ioctl+0x3a1/0x5c0 [kvm] do_vfs_ioctl+0x9f/0x5e0 ksys_ioctl+0x66/0x70 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x49/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 5af4157388ad (KVM: nVMX: Fix mmu context after VMLAUNCH/VMRESUME failure) Fixes: 4f350c6dbcb9 (kvm: nVMX: Handle deferred early VMLAUNCH/VMRESUME failure properly) Cc: Jim Mattson jmattson@google.com Cc: Krish Sadhukhan krish.sadhukhan@oracle.com Cc: Paolo Bonzini pbonzini@redhat.com Cc: Radim KrÄmář rkrcmar@redhat.com Cc: Wanpeng Li wanpeng.li@hotmail.com Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/vmx.c | 173 +++++++++++++++++++++++++++++++++++++++------ 1 file changed, 153 insertions(+), 20 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 6b6bcafd1d2c..3380a312d186 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -13181,24 +13181,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, kvm_clear_interrupt_queue(vcpu); }

-static void load_vmcs12_mmu_host_state(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) -{ - u32 entry_failure_code; - - nested_ept_uninit_mmu_context(vcpu); - - /* - * Only PDPTE load can fail as the value of cr3 was checked on entry and - * couldn't have changed. - */ - if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code)) - nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); - - if (!enable_ept) - vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; -} - /* * A part of what we need to when the nested L2 guest exits and we want to * run its L1 parent, is to reset L1's guest state to the host state specified @@ -13212,6 +13194,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct kvm_segment seg; + u32 entry_failure_code;

if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->host_ia32_efer; @@ -13238,7 +13221,17 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); vmx_set_cr4(vcpu, vmcs12->host_cr4);

- load_vmcs12_mmu_host_state(vcpu, vmcs12); + nested_ept_uninit_mmu_context(vcpu); + + /* + * Only PDPTE load can fail as the value of cr3 was checked on entry and + * couldn't have changed. + */ + if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code)) + nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); + + if (!enable_ept) + vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;

/* * If vmcs01 don't use VPID, CPU flushes TLB on every @@ -13334,6 +13327,140 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); }

+static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) +{ + struct shared_msr_entry *efer_msr; + unsigned int i; + + if (vm_entry_controls_get(vmx) & VM_ENTRY_LOAD_IA32_EFER) + return vmcs_read64(GUEST_IA32_EFER); + + if (cpu_has_load_ia32_efer) + return host_efer; + + for (i = 0; i < vmx->msr_autoload.guest.nr; ++i) { + if (vmx->msr_autoload.guest.val[i].index == MSR_EFER) + return vmx->msr_autoload.guest.val[i].value; + } + + efer_msr = find_msr_entry(vmx, MSR_EFER); + if (efer_msr) + return efer_msr->data; + + return host_efer; +} + +static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmx_msr_entry g, h; + struct msr_data msr; + gpa_t gpa; + u32 i, j; + + vcpu->arch.pat = vmcs_read64(GUEST_IA32_PAT); + + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) { + /* + * L1's host DR7 is lost if KVM_GUESTDBG_USE_HW_BP is set + * as vmcs01.GUEST_DR7 contains a userspace defined value + * and vcpu->arch.dr7 is not squirreled away before the + * nested VMENTER (not worth adding a variable in nested_vmx). + */ + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + kvm_set_dr(vcpu, 7, DR7_FIXED_1); + else + WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7))); + } + + /* + * Note that calling vmx_set_{efer,cr0,cr4} is important as they + * handle a variety of side effects to KVM's software model. + */ + vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx)); + + vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; + vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW)); + + vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); + vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW)); + + nested_ept_uninit_mmu_context(vcpu); + vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + + /* + * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs + * from vmcs01 (if necessary). The PDPTRs are not loaded on + * VMFail, like everything else we just need to ensure our + * software model is up-to-date. + */ + ept_save_pdptrs(vcpu); + + kvm_mmu_reset_context(vcpu); + + if (cpu_has_vmx_msr_bitmap()) + vmx_update_msr_bitmap(vcpu); + + /* + * This nasty bit of open coding is a compromise between blindly + * loading L1's MSRs using the exit load lists (incorrect emulation + * of VMFail), leaving the nested VM's MSRs in the software model + * (incorrect behavior) and snapshotting the modified MSRs (too + * expensive since the lists are unbound by hardware). For each + * MSR that was (prematurely) loaded from the nested VMEntry load + * list, reload it from the exit load list if it exists and differs + * from the guest value. The intent is to stuff host state as + * silently as possible, not to fully process the exit load list. + */ + msr.host_initiated = false; + for (i = 0; i < vmcs12->vm_entry_msr_load_count; i++) { + gpa = vmcs12->vm_entry_msr_load_addr + (i * sizeof(g)); + if (kvm_vcpu_read_guest(vcpu, gpa, &g, sizeof(g))) { + pr_debug_ratelimited( + "%s read MSR index failed (%u, 0x%08llx)\n", + __func__, i, gpa); + goto vmabort; + } + + for (j = 0; j < vmcs12->vm_exit_msr_load_count; j++) { + gpa = vmcs12->vm_exit_msr_load_addr + (j * sizeof(h)); + if (kvm_vcpu_read_guest(vcpu, gpa, &h, sizeof(h))) { + pr_debug_ratelimited( + "%s read MSR failed (%u, 0x%08llx)\n", + __func__, j, gpa); + goto vmabort; + } + if (h.index != g.index) + continue; + if (h.value == g.value) + break; + + if (nested_vmx_load_msr_check(vcpu, &h)) { + pr_debug_ratelimited( + "%s check failed (%u, 0x%x, 0x%x)\n", + __func__, j, h.index, h.reserved); + goto vmabort; + } + + msr.index = h.index; + msr.data = h.value; + if (kvm_set_msr(vcpu, &msr)) { + pr_debug_ratelimited( + "%s WRMSR failed (%u, 0x%x, 0x%llx)\n", + __func__, j, h.index, h.value); + goto vmabort; + } + } + } + + return; + +vmabort: + nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); +} + /* * Emulate an exit from nested guest (L2) to L1, i.e., prepare to run L1 * and modify vmcs12 to make it see what it would expect to see there if @@ -13478,7 +13605,13 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, */ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);

- load_vmcs12_mmu_host_state(vcpu, vmcs12); + /* + * Restore L1's host state to KVM's software model. We're here + * because a consistency check was caught by hardware, which + * means some amount of guest state has been propagated to KVM's + * model and needs to be unwound to the host's state. + */ + nested_vmx_restore_host_state(vcpu);

/* * The emulated instruction was already skipped in

[ Upstream commit b7f1a16d29b2e28d3dcbb070511bd703e306281b ]

When device is unregistered, flowtable flush routine is called by notifier_call(nf_tables_flowtable_event). and exit callback of nftables pernet_operation(nf_tables_exit_net) also has flowtable flush routine. but when network namespace is destroyed, both notifier_call and pernet_operation are called. hence flowtable flush routine in pernet_operation is unnecessary.

test commands: %ip netns add vm1 %ip netns exec vm1 nft add table ip filter %ip netns exec vm1 nft add flowtable ip filter w \ { hook ingress priority 0; devices = { lo }; } %ip netns del vm1

splat looks like: [ 265.187019] WARNING: CPU: 0 PID: 87 at net/netfilter/core.c:309 nf_hook_entry_head+0xc7/0xf0 [ 265.187112] Modules linked in: nf_flow_table_ipv4 nf_flow_table nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables nfnetlink ip_tables x_tables [ 265.187390] CPU: 0 PID: 87 Comm: kworker/u4:2 Not tainted 4.19.0-rc3+ #5 [ 265.187453] Workqueue: netns cleanup_net [ 265.187514] RIP: 0010:nf_hook_entry_head+0xc7/0xf0 [ 265.187546] Code: 8d 81 68 03 00 00 5b c3 89 d0 83 fa 04 48 8d 84 c7 e8 11 00 00 76 81 0f 0b 31 c0 e9 78 ff ff ff 0f 0b 48 83 c4 08 31 c0 5b c3 <0f> 0b 31 c0 e9 65 ff ff ff 0f 0b 31 c0 e9 5c ff ff ff 48 89 0c 24 [ 265.187573] RSP: 0018:ffff88011546f098 EFLAGS: 00010246 [ 265.187624] RAX: ffffffff8d90e135 RBX: 1ffff10022a8de1c RCX: 0000000000000000 [ 265.187645] RDX: 0000000000000000 RSI: 0000000000000005 RDI: ffff880116298040 [ 265.187645] RBP: ffff88010ea4c1a8 R08: 0000000000000000 R09: 0000000000000000 [ 265.187645] R10: ffff88011546f1d8 R11: ffffed0022c532c1 R12: ffff88010ea4c1d0 [ 265.187645] R13: 0000000000000005 R14: dffffc0000000000 R15: ffff88010ea4c1c4 [ 265.187645] FS: 0000000000000000(0000) GS:ffff88011b200000(0000) knlGS:0000000000000000 [ 265.187645] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 265.187645] CR2: 00007fdfb8d00000 CR3: 0000000057a16000 CR4: 00000000001006f0 [ 265.187645] Call Trace: [ 265.187645] __nf_unregister_net_hook+0xca/0x5d0 [ 265.187645] ? nf_hook_entries_free.part.3+0x80/0x80 [ 265.187645] ? save_trace+0x300/0x300 [ 265.187645] nf_unregister_net_hooks+0x2e/0x40 [ 265.187645] nf_tables_exit_net+0x479/0x1340 [nf_tables] [ 265.187645] ? find_held_lock+0x39/0x1c0 [ 265.187645] ? nf_tables_abort+0x30/0x30 [nf_tables] [ 265.187645] ? inet_frag_destroy_rcu+0xd0/0xd0 [ 265.187645] ? trace_hardirqs_on+0x93/0x210 [ 265.187645] ? __bpf_trace_preemptirq_template+0x10/0x10 [ 265.187645] ? inet_frag_destroy_rcu+0xd0/0xd0 [ 265.187645] ? inet_frag_destroy_rcu+0xd0/0xd0 [ 265.187645] ? __mutex_unlock_slowpath+0x17f/0x740 [ 265.187645] ? wait_for_completion+0x710/0x710 [ 265.187645] ? bucket_table_free+0xb2/0x1f0 [ 265.187645] ? nested_table_free+0x130/0x130 [ 265.187645] ? __lock_is_held+0xb4/0x140 [ 265.187645] ops_exit_list.isra.10+0x94/0x140 [ 265.187645] cleanup_net+0x45b/0x900 [ ... ]

This WARNING means that hook unregisteration is failed because all flowtables hooks are already unregistered by notifier_call.

Network namespace exit routine guarantees that all devices will be unregistered first. then, other exit callbacks of pernet_operations are called. so that removing flowtable flush routine in exit callback of pernet_operation(nf_tables_exit_net) doesn't make flowtable leak.

Signed-off-by: Taehee Yoo ap420073@gmail.com Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 3 --- 1 file changed, 3 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7d424fd27025..c06393fc716d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7203,9 +7203,6 @@ static void __nft_release_tables(struct net *net)

list_for_each_entry(chain, &table->chains, list) nf_tables_unregister_hook(net, table, chain); - list_for_each_entry(flowtable, &table->flowtables, list) - nf_unregister_net_hooks(net, flowtable->ops, - flowtable->ops_len); /* No packets are walking on these chains anymore. */ ctx.table = table; list_for_each_entry(chain, &table->chains, list) {

[ Upstream commit 487e2e22ab7968f2c0c82f37b5ca5883efd1a354 ]

Ping with Jumbo packet does not reply and get a watchdog timeout

[ 46.059616] ------------[ cut here ]------------ [ 46.064268] NETDEV WATCHDOG: eth0 (socfpga-dwmac): transmit queue 0 timed out [ 46.071471] WARNING: CPU: 1 PID: 0 at net/sched/sch_generic.c:461 dev_watchdog+0x2cc/0x2d8 [ 46.079708] Modules linked in: [ 46.082761] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.18.0-00115-gc262be665854-dirty #264 [ 46.091082] Hardware name: SoCFPGA Stratix 10 SoCDK (DT) [ 46.096377] pstate: 20000005 (nzCv daif -PAN -UAO) [ 46.101152] pc : dev_watchdog+0x2cc/0x2d8 [ 46.105149] lr : dev_watchdog+0x2cc/0x2d8 [ 46.109144] sp : ffff00000800bd80 [ 46.112447] x29: ffff00000800bd80 x28: ffff80007a9b4940 [ 46.117744] x27: 00000000ffffffff x26: ffff80007aa183b0 [ 46.123040] x25: 0000000000000001 x24: 0000000000000140 [ 46.128336] x23: ffff80007aa1839c x22: ffff80007aa17fb0 [ 46.133632] x21: ffff80007aa18000 x20: ffff0000091a7000 [ 46.138927] x19: 0000000000000000 x18: ffffffffffffffff [ 46.144223] x17: 0000000000000000 x16: 0000000000000000 [ 46.149519] x15: ffff0000091a96c8 x14: 07740775076f0720 [ 46.154814] x13: 07640765076d0769 x12: 0774072007300720 [ 46.160110] x11: 0765077507650775 x10: 0771072007740769 [ 46.165406] x9 : 076d0773076e0761 x8 : 077207740720073a [ 46.170702] x7 : 072907630761076d x6 : ffff80007ff9a0c0 [ 46.175997] x5 : ffff80007ff9a0c0 x4 : 0000000000000002 [ 46.181293] x3 : 0000000000000000 x2 : ffff0000091ac180 [ 46.186589] x1 : e6a742ebe628e800 x0 : 0000000000000000 [ 46.191885] Call trace: [ 46.194326] dev_watchdog+0x2cc/0x2d8 [ 46.197980] call_timer_fn+0x20/0x78 [ 46.201544] expire_timers+0xa4/0xb0 [ 46.205108] run_timer_softirq+0xe4/0x198 [ 46.209107] __do_softirq+0x114/0x210 [ 46.212760] irq_exit+0xd0/0xd8 [ 46.215895] __handle_domain_irq+0x60/0xb0 [ 46.219977] gic_handle_irq+0x58/0xa8 [ 46.223628] el1_irq+0xb0/0x128 [ 46.226761] arch_cpu_idle+0x10/0x18 [ 46.230326] do_idle+0x1d4/0x288 [ 46.233544] cpu_startup_entry+0x24/0x28 [ 46.237457] secondary_start_kernel+0x17c/0x1c0 [ 46.241971] ---[ end trace 57048cd1372cd828 ]---

Inspection of queue showed Jumbo packets were not sent out. The ring Jumbo packet function needs to set the OWN bit so the packet is sent.

Signed-off-by: Thor Thayer thor.thayer@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/stmicro/stmmac/ring_mode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index afed0f0f4027..c0c75c111abb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -59,7 +59,7 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum)

desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); stmmac_prepare_tx_desc(priv, desc, 1, bmax, csum, - STMMAC_RING_MODE, 0, false, skb->len); + STMMAC_RING_MODE, 1, false, skb->len); tx_q->tx_skbuff[entry] = NULL; entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);

@@ -91,7 +91,7 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum) tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); stmmac_prepare_tx_desc(priv, desc, 1, nopaged_len, csum, - STMMAC_RING_MODE, 0, true, skb->len); + STMMAC_RING_MODE, 1, true, skb->len); }

tx_q->cur_tx = entry;

[ Upstream commit a1c6ca3c6de763459a6e93b644ec6518c890ba1c ]

It is possible to observe hung_task complaints when system goes to suspend-to-idle state:

# echo freeze > /sys/power/state

PM: Syncing filesystems ... done. Freezing user space processes ... (elapsed 0.001 seconds) done. OOM killer disabled. Freezing remaining freezable tasks ... (elapsed 0.002 seconds) done. sd 0:0:0:0: [sda] Synchronizing SCSI cache INFO: task bash:1569 blocked for more than 120 seconds. Not tainted 4.19.0-rc3_+ #687 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. bash D 0 1569 604 0x00000000 Call Trace: ? __schedule+0x1fe/0x7e0 schedule+0x28/0x80 suspend_devices_and_enter+0x4ac/0x750 pm_suspend+0x2c0/0x310

Register a PM notifier to disable the detector on suspend and re-enable back on wakeup.

Signed-off-by: Vitaly Kuznetsov vkuznets@redhat.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/hung_task.c | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 9eca2371f189..4a9191617076 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -15,6 +15,7 @@ #include <linux/lockdep.h> #include <linux/export.h> #include <linux/sysctl.h> +#include <linux/suspend.h> #include <linux/utsname.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> @@ -240,6 +241,28 @@ void reset_hung_task_detector(void) } EXPORT_SYMBOL_GPL(reset_hung_task_detector);

+static bool hung_detector_suspended; + +static int hungtask_pm_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + switch (action) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + case PM_RESTORE_PREPARE: + hung_detector_suspended = true; + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + case PM_POST_RESTORE: + hung_detector_suspended = false; + break; + default: + break; + } + return NOTIFY_OK; +} + /* * kthread which checks for tasks stuck in D state */ @@ -259,7 +282,8 @@ static int watchdog(void *dummy) interval = min_t(unsigned long, interval, timeout); t = hung_timeout_jiffies(hung_last_checked, interval); if (t <= 0) { - if (!atomic_xchg(&reset_hung_task, 0)) + if (!atomic_xchg(&reset_hung_task, 0) && + !hung_detector_suspended) check_hung_uninterruptible_tasks(timeout); hung_last_checked = jiffies; continue; @@ -273,6 +297,10 @@ static int watchdog(void *dummy) static int __init hung_task_init(void) { atomic_notifier_chain_register(&panic_notifier_list, &panic_block); + + /* Disable hung task detector on suspend */ + pm_notifier(hungtask_pm_notify, 0); + watchdog_task = kthread_run(watchdog, NULL, "khungtaskd");

return 0;

[ Upstream commit 30f33126feca0fe16df9e9302ffc28a953e2eb37 ]

ttm_bo_glob and ttm_mem_glob are defined as structure instance, while not allocated by kzalloc, so kfree should not be invoked to release them anymore. Otherwise, it will cause the following kernel BUG when unloading amdgpu module

[ 48.419294] kernel BUG at /build/linux-5s7Xkn/linux-4.15.0/mm/slub.c:3894! [ 48.419352] invalid opcode: 0000 [#1] SMP PTI [ 48.419387] Modules linked in: amdgpu(OE-) amdchash(OE) amdttm(OE) amd_sched(OE) amdkcl(OE) amd_iommu_v2 drm_kms_helper drm i2c_algo_bit fb_sys_fops syscopyarea sysfillrect sysimgblt snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi pcbc snd_seq snd_seq_device snd_timer aesni_intel snd soundcore joydev aes_x86_64 crypto_simd glue_helper cryptd input_leds mac_hid serio_raw binfmt_misc nfsd auth_rpcgss nfs_acl lockd grace sunrpc sch_fq_codel parport_pc ppdev lp parport ip_tables x_tables autofs4 8139too psmouse i2c_piix4 8139cp mii floppy pata_acpi [ 48.419782] CPU: 1 PID: 1281 Comm: modprobe Tainted: G OE 4.15.0-20-generic #21-Ubuntu [ 48.419838] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 48.419901] RIP: 0010:kfree+0x137/0x180 [ 48.419934] RSP: 0018:ffffb02101273bf8 EFLAGS: 00010246 [ 48.419974] RAX: ffffeee1418ad7e0 RBX: ffffffffc075f100 RCX: ffff8fed7fca7ed0 [ 48.420025] RDX: 0000000000000000 RSI: 000000000003440e RDI: 0000000022400000 [ 48.420073] RBP: ffffb02101273c10 R08: 0000000000000010 R09: ffff8fed7ffd3680 [ 48.420121] R10: ffffeee1418ad7c0 R11: ffff8fed7ffd3000 R12: ffffffffc075e2c0 [ 48.420169] R13: ffffffffc074ec10 R14: ffff8fed73063900 R15: ffff8fed737428e8 [ 48.420216] FS: 00007fdc912ec540(0000) GS:ffff8fed7fc80000(0000) knlGS:0000000000000000 [ 48.420267] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 48.420308] CR2: 000055fa40c30060 CR3: 000000023470a006 CR4: 00000000003606e0 [ 48.420358] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 48.420405] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 48.420452] Call Trace: [ 48.420485] ttm_bo_global_kobj_release+0x20/0x30 [amdttm] [ 48.420528] kobject_release+0x6a/0x180 [ 48.420562] kobject_put+0x28/0x50 [ 48.420595] ttm_bo_global_release+0x36/0x50 [amdttm] [ 48.420636] amdttm_bo_device_release+0x119/0x180 [amdttm] [ 48.420678] ? amdttm_bo_clean_mm+0xa6/0xf0 [amdttm] [ 48.420760] amdgpu_ttm_fini+0xc9/0x180 [amdgpu] [ 48.420821] amdgpu_bo_fini+0x12/0x40 [amdgpu] [ 48.420889] gmc_v9_0_sw_fini+0x40/0x50 [amdgpu] [ 48.420947] amdgpu_device_fini+0x36f/0x4c0 [amdgpu] [ 48.421007] amdgpu_driver_unload_kms+0xb4/0x150 [amdgpu] [ 48.421058] drm_dev_unregister+0x46/0xf0 [drm] [ 48.421102] drm_dev_unplug+0x12/0x70 [drm]

Signed-off-by: Trigger Huang Trigger.Huang@amd.com Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/ttm/ttm_bo.c | 1 - drivers/gpu/drm/ttm/ttm_memory.c | 9 --------- 2 files changed, 10 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 7c484729f9b2..268f5a3b3122 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1445,7 +1445,6 @@ static void ttm_bo_global_kobj_release(struct kobject *kobj) container_of(kobj, struct ttm_bo_global, kobj);

__free_page(glob->dummy_read_page); - kfree(glob); }

void ttm_bo_global_release(struct drm_global_reference *ref) diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c index 450387c92b63..df73d5ff84a8 100644 --- a/drivers/gpu/drm/ttm/ttm_memory.c +++ b/drivers/gpu/drm/ttm/ttm_memory.c @@ -216,14 +216,6 @@ static ssize_t ttm_mem_global_store(struct kobject *kobj, return size; }

-static void ttm_mem_global_kobj_release(struct kobject *kobj) -{ - struct ttm_mem_global *glob = - container_of(kobj, struct ttm_mem_global, kobj); - - kfree(glob); -} - static struct attribute *ttm_mem_global_attrs[] = { &ttm_mem_global_lower_mem_limit, NULL @@ -235,7 +227,6 @@ static const struct sysfs_ops ttm_mem_global_ops = { };

static struct kobj_type ttm_mem_glob_kobj_type = { - .release = &ttm_mem_global_kobj_release, .sysfs_ops = &ttm_mem_global_ops, .default_attrs = ttm_mem_global_attrs, };

[ Upstream commit f941d3e41da7f86bdb9dcc1977c2bcc6b89bfe47 ]

There are systems in which non-wakeup GPEs fire during the "noirq" suspend stage of suspending devices and that effectively prevents the system that tries to suspend to idle from entering any low-power state at all. If the offending GPE fires regularly and often enough, the system appears to be suspended, but in fact it is in a tight loop over "noirq" suspend and "noirq" resume of devices all the time.

To prevent that from happening, disable all non-wakeup GPEs except for the EC GPE for suspend-to-idle (the EC GPE is special, because on some systems it has to be enabled for power button wakeup events to be generated as expected).

Fixes: 147a7d9d25ca (ACPI / PM: Do not reconfigure GPEs for suspend-to-idle) Link: https://bugzilla.kernel.org/show_bug.cgi?id=201987 Reported-by: Zhang Rui rui.zhang@intel.com Tested-by: Mika Westerberg mika.westerberg@linux.intel.com Tested-by: Zhang Rui rui.zhang@intel.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/ec.c | 12 ++++++++++++ drivers/acpi/internal.h | 2 ++ drivers/acpi/sleep.c | 11 +++++++++++ 3 files changed, 25 insertions(+)

diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index d4e5610e09c5..9d66a47d32fb 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1034,6 +1034,18 @@ void acpi_ec_unblock_transactions(void) acpi_ec_start(first_ec, true); }

+void acpi_ec_mark_gpe_for_wake(void) +{ + if (first_ec && !ec_no_wakeup) + acpi_mark_gpe_for_wake(NULL, first_ec->gpe); +} + +void acpi_ec_set_gpe_wake_mask(u8 action) +{ + if (first_ec && !ec_no_wakeup) + acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action); +} + void acpi_ec_dispatch_gpe(void) { if (first_ec) diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 530a3f675490..f59d0b9e2683 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -188,6 +188,8 @@ int acpi_ec_ecdt_probe(void); int acpi_ec_dsdt_probe(void); void acpi_ec_block_transactions(void); void acpi_ec_unblock_transactions(void); +void acpi_ec_mark_gpe_for_wake(void); +void acpi_ec_set_gpe_wake_mask(u8 action); void acpi_ec_dispatch_gpe(void); int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, acpi_handle handle, acpi_ec_query_func func, diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 754d59f95500..74c489047f57 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -940,6 +940,8 @@ static int lps0_device_attach(struct acpi_device *adev,

acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n", bitmask); + + acpi_ec_mark_gpe_for_wake(); } else { acpi_handle_debug(adev->handle, "_DSM function 0 evaluation failed\n"); @@ -968,11 +970,16 @@ static int acpi_s2idle_prepare(void) if (lps0_device_handle) { acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF); acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY); + + acpi_ec_set_gpe_wake_mask(ACPI_GPE_ENABLE); }

if (acpi_sci_irq_valid()) enable_irq_wake(acpi_sci_irq);

+ /* Change the configuration of GPEs to avoid spurious wakeup. */ + acpi_enable_all_wakeup_gpes(); + acpi_os_wait_events_complete(); return 0; }

@@ -1017,10 +1024,14 @@ static void acpi_s2idle_sync(void)

static void acpi_s2idle_restore(void) { + acpi_enable_all_runtime_gpes(); + if (acpi_sci_irq_valid()) disable_irq_wake(acpi_sci_irq);

if (lps0_device_handle) { + acpi_ec_set_gpe_wake_mask(ACPI_GPE_DISABLE); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT); acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON); }

[ Upstream commit f75a2804da391571563c4b6b29e7797787332673 ]

xfrm_state_put() moves struct xfrm_state to the GC list and schedules the GC work to clean it up. On net exit call path, xfrm_state_flush() is called to clean up and xfrm_flush_gc() is called to wait for the GC work to complete before exit.

However, this doesn't work because one of the ->destructor(), ipcomp_destroy(), schedules the same GC work again inside the GC work. It is hard to wait for such a nested async callback. This is also why syzbot still reports the following warning:

WARNING: CPU: 1 PID: 33 at net/ipv6/xfrm6_tunnel.c:351 xfrm6_tunnel_net_exit+0x2cb/0x500 net/ipv6/xfrm6_tunnel.c:351 ... ops_exit_list.isra.0+0xb0/0x160 net/core/net_namespace.c:153 cleanup_net+0x51d/0xb10 net/core/net_namespace.c:551 process_one_work+0xd0c/0x1ce0 kernel/workqueue.c:2153 worker_thread+0x143/0x14a0 kernel/workqueue.c:2296 kthread+0x357/0x430 kernel/kthread.c:246 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352

In fact, it is perfectly fine to bypass GC and destroy xfrm_state synchronously on net exit call path, because it is in process context and doesn't need a work struct to do any blocking work.

This patch introduces xfrm_state_put_sync() which simply bypasses GC, and lets its callers to decide whether to use this synchronous version. On net exit path, xfrm_state_fini() and xfrm6_tunnel_net_exit() use it. And, as ipcomp_destroy() itself is blocking, it can use xfrm_state_put_sync() directly too.

Also rename xfrm_state_gc_destroy() to ___xfrm_state_destroy() to reflect this change.

Fixes: b48c05ab5d32 ("xfrm: Fix warning in xfrm6_tunnel_net_exit.") Reported-and-tested-by: syzbot+e9aebef558e3ed673934@syzkaller.appspotmail.com Cc: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/xfrm.h | 12 +++++++++--- net/ipv6/xfrm6_tunnel.c | 2 +- net/key/af_key.c | 2 +- net/xfrm/xfrm_state.c | 30 +++++++++++++++++++----------- net/xfrm/xfrm_user.c | 2 +- 5 files changed, 31 insertions(+), 17 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h index da588def3c61..5e3daf53b3d1 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -850,7 +850,7 @@ static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) xfrm_pol_put(pols[i]); }

-void __xfrm_state_destroy(struct xfrm_state *); +void __xfrm_state_destroy(struct xfrm_state *, bool);

static inline void __xfrm_state_put(struct xfrm_state *x) { @@ -860,7 +860,13 @@ static inline void __xfrm_state_put(struct xfrm_state *x) static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x); + __xfrm_state_destroy(x, false); +} + +static inline void xfrm_state_put_sync(struct xfrm_state *x) +{ + if (refcount_dec_and_test(&x->refcnt)) + __xfrm_state_destroy(x, true); }

static inline void xfrm_state_hold(struct xfrm_state *x) @@ -1616,7 +1622,7 @@ struct xfrmk_spdinfo {

struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq); int xfrm_state_delete(struct xfrm_state *x); -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f5b4febeaa25..bc65db782bfb 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -344,8 +344,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i;

- xfrm_state_flush(net, IPSEC_PROTO_ANY, false); xfrm_flush_gc(); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);

for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); diff --git a/net/key/af_key.c b/net/key/af_key.c index 7da629d59717..7d4bed955060 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1773,7 +1773,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m if (proto == 0) return -EINVAL;

- err = xfrm_state_flush(net, proto, true); + err = xfrm_state_flush(net, proto, true, false); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index cc0203efb584..3f729cd512af 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -432,7 +432,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free);

-static void xfrm_state_gc_destroy(struct xfrm_state *x) +static void ___xfrm_state_destroy(struct xfrm_state *x) { tasklet_hrtimer_cancel(&x->mtimer); del_timer_sync(&x->rtimer); @@ -474,7 +474,7 @@ static void xfrm_state_gc_task(struct work_struct *work) synchronize_rcu();

hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) - xfrm_state_gc_destroy(x); + ___xfrm_state_destroy(x); }

static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) @@ -598,14 +598,19 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) } EXPORT_SYMBOL(xfrm_state_alloc);

-void __xfrm_state_destroy(struct xfrm_state *x) +void __xfrm_state_destroy(struct xfrm_state *x, bool sync) { WARN_ON(x->km.state != XFRM_STATE_DEAD);

- spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &xfrm_state_gc_list); - spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); + if (sync) { + synchronize_rcu(); + ___xfrm_state_destroy(x); + } else { + spin_lock_bh(&xfrm_state_gc_lock); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); + spin_unlock_bh(&xfrm_state_gc_lock); + schedule_work(&xfrm_state_gc_work); + } } EXPORT_SYMBOL(__xfrm_state_destroy);

@@ -708,7 +713,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool } #endif

-int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) { int i, err = 0, cnt = 0;

@@ -730,7 +735,10 @@ int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); - xfrm_state_put(x); + if (sync) + xfrm_state_put_sync(x); + else + xfrm_state_put(x); if (!err) cnt++;

@@ -2217,7 +2225,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x) if (atomic_read(&t->tunnel_users) == 2) xfrm_state_delete(t); atomic_dec(&t->tunnel_users); - xfrm_state_put(t); + xfrm_state_put_sync(t); x->tunnel = NULL; } } @@ -2377,8 +2385,8 @@ void xfrm_state_fini(struct net *net) unsigned int sz;

flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&xfrm_state_gc_work); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);

WARN_ON(!list_empty(&net->xfrm.state_all));

diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ab557827aac0..7e4904b93004 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1932,7 +1932,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err;

- err = xfrm_state_flush(net, p->proto, true); + err = xfrm_state_flush(net, p->proto, true, false); if (err) { if (err == -ESRCH) /* empty table */ return 0;

[ Upstream commit c64316502008064c158fa40cc250665e461b0f2a ]

The SHA512 code we adopted from the OpenSSL project uses a rather peculiar way to take the address of the round constant table: it takes the address of the sha256_block_data_order() routine, and substracts a constant known quantity to arrive at the base of the table, which is emitted by the same assembler code right before the routine's entry point.

However, recent versions of binutils have helpfully changed the behavior of references emitted via an ADR instruction when running in Thumb2 mode: it now takes the Thumb execution mode bit into account, which is bit 0 af the address. This means the produced table address also has bit 0 set, and so we end up with an address value pointing 1 byte past the start of the table, which results in crashes such as

Unable to handle kernel paging request at virtual address bf825000 pgd = 42f44b11 [bf825000] *pgd=80000040206003, *pmd=5f1bd003, *pte=00000000 Internal error: Oops: 207 [#1] PREEMPT SMP THUMB2 Modules linked in: sha256_arm(+) sha1_arm_ce sha1_arm ... CPU: 7 PID: 396 Comm: cryptomgr_test Not tainted 5.0.0-rc6+ #144 Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 PC is at sha256_block_data_order+0xaaa/0xb30 [sha256_arm] LR is at __this_module+0x17fd/0xffffe800 [sha256_arm] pc : [<bf820bca>] lr : [<bf824ffd>] psr: 800b0033 sp : ebc8bbe8 ip : faaabe1c fp : 2fdd3433 r10: 4c5f1692 r9 : e43037df r8 : b04b0a5a r7 : c369d722 r6 : 39c3693e r5 : 7a013189 r4 : 1580d26b r3 : 8762a9b0 r2 : eea9c2cd r1 : 3e9ab536 r0 : 1dea4ae7 Flags: Nzcv IRQs on FIQs on Mode SVC_32 ISA Thumb Segment user Control: 70c5383d Table: 6b8467c0 DAC: dbadc0de Process cryptomgr_test (pid: 396, stack limit = 0x69e1fe23) Stack: (0xebc8bbe8 to 0xebc8c000) ... unwind: Unknown symbol address bf820bca unwind: Index not found bf820bca Code: 441a ea80 40f9 440a (f85e) 3b04 ---[ end trace e560cce92700ef8a ]---

Given that this affects older kernels as well, in case they are built with a recent toolchain, apply a minimal backportable fix, which is to emit another non-code label at the start of the routine, and reference that instead. (This is similar to the current upstream state of this file in OpenSSL)

Signed-off-by: Ard Biesheuvel ard.biesheuvel@linaro.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/crypto/sha512-armv4.pl | 3 ++- arch/arm/crypto/sha512-core.S_shipped | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl index fb5d15048c0b..788c17b56ecc 100644 --- a/arch/arm/crypto/sha512-armv4.pl +++ b/arch/arm/crypto/sha512-armv4.pl @@ -274,10 +274,11 @@ WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817) .global sha512_block_data_order .type sha512_block_data_order,%function sha512_block_data_order: +.Lsha512_block_data_order: #if __ARM_ARCH__<7 sub r3,pc,#8 @ sha512_block_data_order #else - adr r3,sha512_block_data_order + adr r3,.Lsha512_block_data_order #endif #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) ldr r12,.LOPENSSL_armcap diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped index b1c334a49cda..710ea309769e 100644 --- a/arch/arm/crypto/sha512-core.S_shipped +++ b/arch/arm/crypto/sha512-core.S_shipped @@ -141,10 +141,11 @@ WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817) .global sha512_block_data_order .type sha512_block_data_order,%function sha512_block_data_order: +.Lsha512_block_data_order: #if __ARM_ARCH__<7 sub r3,pc,#8 @ sha512_block_data_order #else - adr r3,sha512_block_data_order + adr r3,.Lsha512_block_data_order #endif #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) ldr r12,.LOPENSSL_armcap

[ Upstream commit cffaaf0c816238c45cd2d06913476c83eb50f682 ]

Commit 57384592c433 ("iommu/vt-d: Store bus information in RMRR PCI device path") changed the type of the path data, however, the change in path type was not reflected in size calculations. Update to use the correct type and prevent a buffer overflow.

This bug manifests in systems with deep PCI hierarchies, and can lead to an overflow of the static allocated buffer (dmar_pci_notify_info_buf), or can lead to overflow of slab-allocated data.

BUG: KASAN: global-out-of-bounds in dmar_alloc_pci_notify_info+0x1d5/0x2e0 Write of size 1 at addr ffffffff90445d80 by task swapper/0/1 CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 4.14.87-rt49-02406-gd0a0e96 #1 Call Trace: ? dump_stack+0x46/0x59 ? print_address_description+0x1df/0x290 ? dmar_alloc_pci_notify_info+0x1d5/0x2e0 ? kasan_report+0x256/0x340 ? dmar_alloc_pci_notify_info+0x1d5/0x2e0 ? e820__memblock_setup+0xb0/0xb0 ? dmar_dev_scope_init+0x424/0x48f ? __down_write_common+0x1ec/0x230 ? dmar_dev_scope_init+0x48f/0x48f ? dmar_free_unused_resources+0x109/0x109 ? cpumask_next+0x16/0x20 ? __kmem_cache_create+0x392/0x430 ? kmem_cache_create+0x135/0x2f0 ? e820__memblock_setup+0xb0/0xb0 ? intel_iommu_init+0x170/0x1848 ? _raw_spin_unlock_irqrestore+0x32/0x60 ? migrate_enable+0x27a/0x5b0 ? sched_setattr+0x20/0x20 ? migrate_disable+0x1fc/0x380 ? task_rq_lock+0x170/0x170 ? try_to_run_init_process+0x40/0x40 ? locks_remove_file+0x85/0x2f0 ? dev_prepare_static_identity_mapping+0x78/0x78 ? rt_spin_unlock+0x39/0x50 ? lockref_put_or_lock+0x2a/0x40 ? dput+0x128/0x2f0 ? __rcu_read_unlock+0x66/0x80 ? __fput+0x250/0x300 ? __rcu_read_lock+0x1b/0x30 ? mntput_no_expire+0x38/0x290 ? e820__memblock_setup+0xb0/0xb0 ? pci_iommu_init+0x25/0x63 ? pci_iommu_init+0x25/0x63 ? do_one_initcall+0x7e/0x1c0 ? initcall_blacklisted+0x120/0x120 ? kernel_init_freeable+0x27b/0x307 ? rest_init+0xd0/0xd0 ? kernel_init+0xf/0x120 ? rest_init+0xd0/0xd0 ? ret_from_fork+0x1f/0x40 The buggy address belongs to the variable: dmar_pci_notify_info_buf+0x40/0x60

Fixes: 57384592c433 ("iommu/vt-d: Store bus information in RMRR PCI device path") Signed-off-by: Julia Cartwright julia@ni.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/dmar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index d9c748b6f9e4..7f9824b0609e 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -144,7 +144,7 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event) for (tmp = dev; tmp; tmp = tmp->bus->self) level++;

- size = sizeof(*info) + level * sizeof(struct acpi_dmar_pci_path); + size = sizeof(*info) + level * sizeof(info->path[0]); if (size <= sizeof(dmar_pci_notify_info_buf)) { info = (struct dmar_pci_notify_info *)dmar_pci_notify_info_buf; } else {

[ Upstream commit b6e1fd17a38bd1d97c11d69fd3207b3ef9bfa4b3 ]

This fixes splats like the one below if CONFIG_DEBUG_ATOMIC_SLEEP=y and machine (Tegra30) booted with SMP=n or all secondary CPU's are put offline. Locking isn't needed because it protects atomic operation.

BUG: sleeping function called from invalid context at kernel/locking/mutex.c:254 in_atomic(): 1, irqs_disabled(): 128, pid: 0, name: swapper/0 CPU: 0 PID: 0 Comm: swapper/0 Tainted: G C 4.18.0-next-20180821-00180-gc3ebb6544e44-dirty #823 Hardware name: NVIDIA Tegra SoC (Flattened Device Tree) [<c01134f4>] (unwind_backtrace) from [<c010db2c>] (show_stack+0x20/0x24) [<c010db2c>] (show_stack) from [<c0bd0f3c>] (dump_stack+0x94/0xa8) [<c0bd0f3c>] (dump_stack) from [<c0151df8>] (___might_sleep+0x13c/0x174) [<c0151df8>] (___might_sleep) from [<c0151ea0>] (__might_sleep+0x70/0xa8) [<c0151ea0>] (__might_sleep) from [<c0bec2b8>] (mutex_lock+0x2c/0x70) [<c0bec2b8>] (mutex_lock) from [<c0589844>] (tegra_powergate_is_powered+0x44/0xa8) [<c0589844>] (tegra_powergate_is_powered) from [<c0581a60>] (tegra30_cpu_rail_off_ready+0x30/0x74) [<c0581a60>] (tegra30_cpu_rail_off_ready) from [<c0122244>] (tegra30_idle_lp2+0xa0/0x108) [<c0122244>] (tegra30_idle_lp2) from [<c0853438>] (cpuidle_enter_state+0x140/0x540) [<c0853438>] (cpuidle_enter_state) from [<c08538a4>] (cpuidle_enter+0x40/0x4c) [<c08538a4>] (cpuidle_enter) from [<c01595e0>] (call_cpuidle+0x30/0x48) [<c01595e0>] (call_cpuidle) from [<c01599f8>] (do_idle+0x238/0x28c) [<c01599f8>] (do_idle) from [<c0159d28>] (cpu_startup_entry+0x28/0x2c) [<c0159d28>] (cpu_startup_entry) from [<c0be76c8>] (rest_init+0xd8/0xdc) [<c0be76c8>] (rest_init) from [<c1200f50>] (start_kernel+0x41c/0x430)

Signed-off-by: Dmitry Osipenko digetx@gmail.com Acked-by: Jon Hunter jonathanh@nvidia.com Signed-off-by: Thierry Reding treding@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/soc/tegra/pmc.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c index ed71a4c9c8b2..4b452f36f054 100644 --- a/drivers/soc/tegra/pmc.c +++ b/drivers/soc/tegra/pmc.c @@ -524,16 +524,10 @@ EXPORT_SYMBOL(tegra_powergate_power_off); */ int tegra_powergate_is_powered(unsigned int id) { - int status; - if (!tegra_powergate_is_valid(id)) return -EINVAL;

- mutex_lock(&pmc->powergates_lock); - status = tegra_powergate_state(id); - mutex_unlock(&pmc->powergates_lock); - - return status; + return tegra_powergate_state(id); }

/**

[ Upstream commit 59a12205d3c32aee4c13ca36889fdf7cfed31126 ]

Introduce lkdtm tests for NULL pointer dereference: check access or exec at NULL address, since these errors tend to be reported differently from the general fault error text. For example from x86:

pr_alert("BUG: unable to handle kernel %s at %px\n", address < PAGE_SIZE ? "NULL pointer dereference" : "paging request", (void *)address);

Signed-off-by: Christophe Leroy christophe.leroy@c-s.fr Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/misc/lkdtm/core.c | 2 ++ drivers/misc/lkdtm/lkdtm.h | 2 ++ drivers/misc/lkdtm/perms.c | 18 ++++++++++++++++++ 3 files changed, 22 insertions(+)

diff --git a/drivers/misc/lkdtm/core.c b/drivers/misc/lkdtm/core.c index 2154d1bfd18b..07caaa2cfe1e 100644 --- a/drivers/misc/lkdtm/core.c +++ b/drivers/misc/lkdtm/core.c @@ -152,7 +152,9 @@ static const struct crashtype crashtypes[] = { CRASHTYPE(EXEC_VMALLOC), CRASHTYPE(EXEC_RODATA), CRASHTYPE(EXEC_USERSPACE), + CRASHTYPE(EXEC_NULL), CRASHTYPE(ACCESS_USERSPACE), + CRASHTYPE(ACCESS_NULL), CRASHTYPE(WRITE_RO), CRASHTYPE(WRITE_RO_AFTER_INIT), CRASHTYPE(WRITE_KERN), diff --git a/drivers/misc/lkdtm/lkdtm.h b/drivers/misc/lkdtm/lkdtm.h index 9e513dcfd809..8c3f2e6af256 100644 --- a/drivers/misc/lkdtm/lkdtm.h +++ b/drivers/misc/lkdtm/lkdtm.h @@ -45,7 +45,9 @@ void lkdtm_EXEC_KMALLOC(void); void lkdtm_EXEC_VMALLOC(void); void lkdtm_EXEC_RODATA(void); void lkdtm_EXEC_USERSPACE(void); +void lkdtm_EXEC_NULL(void); void lkdtm_ACCESS_USERSPACE(void); +void lkdtm_ACCESS_NULL(void);

/* lkdtm_refcount.c */ void lkdtm_REFCOUNT_INC_OVERFLOW(void); diff --git a/drivers/misc/lkdtm/perms.c b/drivers/misc/lkdtm/perms.c index fa54add6375a..62f76d506f04 100644 --- a/drivers/misc/lkdtm/perms.c +++ b/drivers/misc/lkdtm/perms.c @@ -164,6 +164,11 @@ void lkdtm_EXEC_USERSPACE(void) vm_munmap(user_addr, PAGE_SIZE); }

+void lkdtm_EXEC_NULL(void) +{ + execute_location(NULL, CODE_AS_IS); +} + void lkdtm_ACCESS_USERSPACE(void) { unsigned long user_addr, tmp = 0; @@ -195,6 +200,19 @@ void lkdtm_ACCESS_USERSPACE(void) vm_munmap(user_addr, PAGE_SIZE); }

+void lkdtm_ACCESS_NULL(void) +{ + unsigned long tmp; + unsigned long *ptr = (unsigned long *)NULL; + + pr_info("attempting bad read at %px\n", ptr); + tmp = *ptr; + tmp += 0xc0dec0de; + + pr_info("attempting bad write at %px\n", ptr); + *ptr = tmp; +} + void __init lkdtm_perms_init(void) { /* Make sure we can write to __ro_after_init values during __init */

[ Upstream commit c34a83820f59bb275e5f2d55cd5ea99c64f6ef23 ]

Clients may submit a new requests from the completion callback context. The driver was not prepared to receive a request in this state because it already held the request queue lock and a recursive lock error is triggered.

Now all completions are queued up until we are ready to drop the queue lock and then delivered.

The fault was triggered by TCP over an IPsec connection in the LTP test suite: LTP: starting tcp4_ipsec02 (tcp_ipsec.sh -p ah -m transport -s "100 1000 65535") BUG: spinlock recursion on CPU#1, genload/943 lock: 0xbf3c3094, .magic: dead4ead, .owner: genload/943, .owner_cpu: 1 CPU: 1 PID: 943 Comm: genload Tainted: G O 4.9.62-axis5-devel #6 Hardware name: Axis ARTPEC-6 Platform (unwind_backtrace) from [<8010d134>] (show_stack+0x18/0x1c) (show_stack) from [<803a289c>] (dump_stack+0x84/0x98) (dump_stack) from [<8016e164>] (do_raw_spin_lock+0x124/0x128) (do_raw_spin_lock) from [<804de1a4>] (artpec6_crypto_submit+0x2c/0xa0) (artpec6_crypto_submit) from [<804def38>] (artpec6_crypto_prepare_submit_hash+0xd0/0x54c) (artpec6_crypto_prepare_submit_hash) from [<7f3165f0>] (ah_output+0x2a4/0x3dc [ah4]) (ah_output [ah4]) from [<805df9bc>] (xfrm_output_resume+0x178/0x4a4) (xfrm_output_resume) from [<805d283c>] (xfrm4_output+0xac/0xbc) (xfrm4_output) from [<80587928>] (ip_queue_xmit+0x140/0x3b4) (ip_queue_xmit) from [<805a13b4>] (tcp_transmit_skb+0x4c4/0x95c) (tcp_transmit_skb) from [<8059f218>] (tcp_rcv_state_process+0xdf4/0xdfc) (tcp_rcv_state_process) from [<805a7530>] (tcp_v4_do_rcv+0x64/0x1ac) (tcp_v4_do_rcv) from [<805a9724>] (tcp_v4_rcv+0xa34/0xb74) (tcp_v4_rcv) from [<80581d34>] (ip_local_deliver_finish+0x78/0x2b0) (ip_local_deliver_finish) from [<8058259c>] (ip_local_deliver+0xe4/0x104) (ip_local_deliver) from [<805d23ec>] (xfrm4_transport_finish+0xf4/0x144) (xfrm4_transport_finish) from [<805df564>] (xfrm_input+0x4f4/0x74c) (xfrm_input) from [<804de420>] (artpec6_crypto_task+0x208/0x38c) (artpec6_crypto_task) from [<801271b0>] (tasklet_action+0x60/0xec) (tasklet_action) from [<801266d4>] (__do_softirq+0xcc/0x3a4) (__do_softirq) from [<80126d20>] (irq_exit+0xf4/0x15c) (irq_exit) from [<801741e8>] (__handle_domain_irq+0x68/0xbc) (__handle_domain_irq) from [<801014f0>] (gic_handle_irq+0x50/0x94) (gic_handle_irq) from [<80657370>] (__irq_usr+0x50/0x80)

Signed-off-by: Lars Persson larper@axis.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/crypto/axis/artpec6_crypto.c | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c index 7f07a5085e9b..fdcdc751d03b 100644 --- a/drivers/crypto/axis/artpec6_crypto.c +++ b/drivers/crypto/axis/artpec6_crypto.c @@ -284,6 +284,7 @@ enum artpec6_crypto_hash_flags {

struct artpec6_crypto_req_common { struct list_head list; + struct list_head complete_in_progress; struct artpec6_crypto_dma_descriptors *dma; struct crypto_async_request *req; void (*complete)(struct crypto_async_request *req); @@ -2046,7 +2047,8 @@ static int artpec6_crypto_prepare_aead(struct aead_request *areq) return artpec6_crypto_dma_map_descs(common); }

-static void artpec6_crypto_process_queue(struct artpec6_crypto *ac) +static void artpec6_crypto_process_queue(struct artpec6_crypto *ac, + struct list_head *completions) { struct artpec6_crypto_req_common *req;

@@ -2057,7 +2059,7 @@ static void artpec6_crypto_process_queue(struct artpec6_crypto *ac) list_move_tail(&req->list, &ac->pending); artpec6_crypto_start_dma(req);

- req->req->complete(req->req, -EINPROGRESS); + list_add_tail(&req->complete_in_progress, completions); }

/* @@ -2087,6 +2089,11 @@ static void artpec6_crypto_task(unsigned long data) struct artpec6_crypto *ac = (struct artpec6_crypto *)data; struct artpec6_crypto_req_common *req; struct artpec6_crypto_req_common *n; + struct list_head complete_done; + struct list_head complete_in_progress; + + INIT_LIST_HEAD(&complete_done); + INIT_LIST_HEAD(&complete_in_progress);

if (list_empty(&ac->pending)) { pr_debug("Spurious IRQ\n"); @@ -2120,19 +2127,30 @@ static void artpec6_crypto_task(unsigned long data)

pr_debug("Completing request %p\n", req);

- list_del(&req->list); + list_move_tail(&req->list, &complete_done);

artpec6_crypto_dma_unmap_all(req); artpec6_crypto_copy_bounce_buffers(req);

ac->pending_count--; artpec6_crypto_common_destroy(req); - req->complete(req->req); }

- artpec6_crypto_process_queue(ac); + artpec6_crypto_process_queue(ac, &complete_in_progress);

spin_unlock_bh(&ac->queue_lock); + + /* Perform the completion callbacks without holding the queue lock + * to allow new request submissions from the callbacks. + */ + list_for_each_entry_safe(req, n, &complete_done, list) { + req->complete(req->req); + } + + list_for_each_entry_safe(req, n, &complete_in_progress, + complete_in_progress) { + req->req->complete(req->req, -EINPROGRESS); + } }

static void artpec6_crypto_complete_crypto(struct crypto_async_request *req)

[ Upstream commit a0f890aba2be33377f4eb24e13633c4a76a68f38 ]

This patch is to add the AMBA device ID for CA73 CPU, so that CPU debug module can be initialized successfully when a SoC contain CA73 CPUs.

This patch has been verified on 96boards Hikey960.

Signed-off-by: Leo Yan leo.yan@linaro.org Signed-off-by: Mathieu Poirier mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwtracing/coresight/coresight-cpu-debug.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/hwtracing/coresight/coresight-cpu-debug.c b/drivers/hwtracing/coresight/coresight-cpu-debug.c index 45b2460f3166..e8819d750938 100644 --- a/drivers/hwtracing/coresight/coresight-cpu-debug.c +++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c @@ -668,6 +668,10 @@ static const struct amba_id debug_ids[] = { .id = 0x000bbd08, .mask = 0x000fffff, }, + { /* Debug for Cortex-A73 */ + .id = 0x000bbd09, + .mask = 0x000fffff, + }, { 0, 0 }, };

[ Upstream commit fc782242749fa4235592854fafe1a1297583c1fb ]

GF117 appears to use the same register as GK104 (but still with the general Fermi readout mechanism).

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108980 Signed-off-by: Ilia Mirkin imirkin@alum.mit.edu Signed-off-by: Ben Skeggs bskeggs@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../drm/nouveau/include/nvkm/subdev/volt.h | 1 + .../gpu/drm/nouveau/nvkm/engine/device/base.c | 2 +- .../gpu/drm/nouveau/nvkm/subdev/volt/Kbuild | 1 + .../gpu/drm/nouveau/nvkm/subdev/volt/gf117.c | 60 +++++++++++++++++++ 4 files changed, 63 insertions(+), 1 deletion(-) create mode 100644 drivers/gpu/drm/nouveau/nvkm/subdev/volt/gf117.c

diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/volt.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/volt.h index 8a0f85f5fc1a..6a765682fbfa 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/volt.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/volt.h @@ -38,6 +38,7 @@ int nvkm_volt_set_id(struct nvkm_volt *, u8 id, u8 min_id, u8 temp,

int nv40_volt_new(struct nvkm_device *, int, struct nvkm_volt **); int gf100_volt_new(struct nvkm_device *, int, struct nvkm_volt **); +int gf117_volt_new(struct nvkm_device *, int, struct nvkm_volt **); int gk104_volt_new(struct nvkm_device *, int, struct nvkm_volt **); int gk20a_volt_new(struct nvkm_device *, int, struct nvkm_volt **); int gm20b_volt_new(struct nvkm_device *, int, struct nvkm_volt **); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index e294013426ce..347a6a4cb339 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -1613,7 +1613,7 @@ nvd7_chipset = { .pci = gf106_pci_new, .therm = gf119_therm_new, .timer = nv41_timer_new, - .volt = gf100_volt_new, + .volt = gf117_volt_new, .ce[0] = gf100_ce_new, .disp = gf119_disp_new, .dma = gf119_dma_new, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/Kbuild index bcd179ba11d0..146adcdd316a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/Kbuild +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/Kbuild @@ -2,6 +2,7 @@ nvkm-y += nvkm/subdev/volt/base.o nvkm-y += nvkm/subdev/volt/gpio.o nvkm-y += nvkm/subdev/volt/nv40.o nvkm-y += nvkm/subdev/volt/gf100.o +nvkm-y += nvkm/subdev/volt/gf117.o nvkm-y += nvkm/subdev/volt/gk104.o nvkm-y += nvkm/subdev/volt/gk20a.o nvkm-y += nvkm/subdev/volt/gm20b.o diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gf117.c b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gf117.c new file mode 100644 index 000000000000..547a58f0aeac --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gf117.c @@ -0,0 +1,60 @@ +/* + * Copyright 2019 Ilia Mirkin + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Ilia Mirkin + */ +#include "priv.h" + +#include <subdev/fuse.h> + +static int +gf117_volt_speedo_read(struct nvkm_volt *volt) +{ + struct nvkm_device *device = volt->subdev.device; + struct nvkm_fuse *fuse = device->fuse; + + if (!fuse) + return -EINVAL; + + return nvkm_fuse_read(fuse, 0x3a8); +} + +static const struct nvkm_volt_func +gf117_volt = { + .oneinit = gf100_volt_oneinit, + .vid_get = nvkm_voltgpio_get, + .vid_set = nvkm_voltgpio_set, + .speedo_read = gf117_volt_speedo_read, +}; + +int +gf117_volt_new(struct nvkm_device *device, int index, struct nvkm_volt **pvolt) +{ + struct nvkm_volt *volt; + int ret; + + ret = nvkm_volt_new_(&gf117_volt, device, index, &volt); + *pvolt = volt; + if (ret) + return ret; + + return nvkm_voltgpio_init(volt); +}

[ Upstream commit cac734c2dbd2514f14c8c6a17caba1990d83bf1d ]

if use the legacy method to allocate object, when mqd_hiq need to run uninit code, it will be cause WARNING call trace.

eg: (s3 suspend test) [ 34.918944] Call Trace: [ 34.918948] [<ffffffff92961dc1>] dump_stack+0x19/0x1b [ 34.918950] [<ffffffff92297648>] __warn+0xd8/0x100 [ 34.918951] [<ffffffff9229778d>] warn_slowpath_null+0x1d/0x20 [ 34.918991] [<ffffffffc03ce1fe>] uninit_mqd_hiq_sdma+0x4e/0x50 [amdgpu] [ 34.919028] [<ffffffffc03d0ef7>] uninitialize+0x37/0xe0 [amdgpu] [ 34.919064] [<ffffffffc03d15a6>] kernel_queue_uninit+0x16/0x30 [amdgpu] [ 34.919086] [<ffffffffc03d26c2>] pm_uninit+0x12/0x20 [amdgpu] [ 34.919107] [<ffffffffc03d4915>] stop_nocpsch+0x15/0x20 [amdgpu] [ 34.919129] [<ffffffffc03c1dce>] kgd2kfd_suspend.part.4+0x2e/0x50 [amdgpu] [ 34.919150] [<ffffffffc03c2667>] kgd2kfd_suspend+0x17/0x20 [amdgpu] [ 34.919171] [<ffffffffc03c103a>] amdgpu_amdkfd_suspend+0x1a/0x20 [amdgpu] [ 34.919187] [<ffffffffc02ec428>] amdgpu_device_suspend+0x88/0x3a0 [amdgpu] [ 34.919189] [<ffffffff922e22cf>] ? enqueue_entity+0x2ef/0xbe0 [ 34.919205] [<ffffffffc02e8220>] amdgpu_pmops_suspend+0x20/0x30 [amdgpu] [ 34.919207] [<ffffffff925c56ff>] pci_pm_suspend+0x6f/0x150 [ 34.919208] [<ffffffff925c5690>] ? pci_pm_freeze+0xf0/0xf0 [ 34.919210] [<ffffffff926b45c6>] dpm_run_callback+0x46/0x90 [ 34.919212] [<ffffffff926b49db>] __device_suspend+0xfb/0x2a0 [ 34.919213] [<ffffffff926b4b9f>] async_suspend+0x1f/0xa0 [ 34.919214] [<ffffffff922c918f>] async_run_entry_fn+0x3f/0x130 [ 34.919216] [<ffffffff922b9d4f>] process_one_work+0x17f/0x440 [ 34.919217] [<ffffffff922bade6>] worker_thread+0x126/0x3c0 [ 34.919218] [<ffffffff922bacc0>] ? manage_workers.isra.25+0x2a0/0x2a0 [ 34.919220] [<ffffffff922c1c31>] kthread+0xd1/0xe0 [ 34.919221] [<ffffffff922c1b60>] ? insert_kthread_work+0x40/0x40 [ 34.919222] [<ffffffff92974c1d>] ret_from_fork_nospec_begin+0x7/0x21 [ 34.919224] [<ffffffff922c1b60>] ? insert_kthread_work+0x40/0x40 [ 34.919224] ---[ end trace 38cd9f65c963adad ]---

Signed-off-by: Kevin Wang kevin1.wang@amd.com Reviewed-by: Oak Zeng Oak.Zeng@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c | 52 +------------------ 1 file changed, 1 insertion(+), 51 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c index 47243165a082..ae90a99909ef 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c @@ -323,57 +323,7 @@ static int init_mqd_hiq(struct mqd_manager *mm, void **mqd, struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr, struct queue_properties *q) { - uint64_t addr; - struct cik_mqd *m; - int retval; - - retval = kfd_gtt_sa_allocate(mm->dev, sizeof(struct cik_mqd), - mqd_mem_obj); - - if (retval != 0) - return -ENOMEM; - - m = (struct cik_mqd *) (*mqd_mem_obj)->cpu_ptr; - addr = (*mqd_mem_obj)->gpu_addr; - - memset(m, 0, ALIGN(sizeof(struct cik_mqd), 256)); - - m->header = 0xC0310800; - m->compute_pipelinestat_enable = 1; - m->compute_static_thread_mgmt_se0 = 0xFFFFFFFF; - m->compute_static_thread_mgmt_se1 = 0xFFFFFFFF; - m->compute_static_thread_mgmt_se2 = 0xFFFFFFFF; - m->compute_static_thread_mgmt_se3 = 0xFFFFFFFF; - - m->cp_hqd_persistent_state = DEFAULT_CP_HQD_PERSISTENT_STATE | - PRELOAD_REQ; - m->cp_hqd_quantum = QUANTUM_EN | QUANTUM_SCALE_1MS | - QUANTUM_DURATION(10); - - m->cp_mqd_control = MQD_CONTROL_PRIV_STATE_EN; - m->cp_mqd_base_addr_lo = lower_32_bits(addr); - m->cp_mqd_base_addr_hi = upper_32_bits(addr); - - m->cp_hqd_ib_control = DEFAULT_MIN_IB_AVAIL_SIZE; - - /* - * Pipe Priority - * Identifies the pipe relative priority when this queue is connected - * to the pipeline. The pipe priority is against the GFX pipe and HP3D. - * In KFD we are using a fixed pipe priority set to CS_MEDIUM. - * 0 = CS_LOW (typically below GFX) - * 1 = CS_MEDIUM (typically between HP3D and GFX - * 2 = CS_HIGH (typically above HP3D) - */ - m->cp_hqd_pipe_priority = 1; - m->cp_hqd_queue_priority = 15; - - *mqd = m; - if (gart_addr) - *gart_addr = addr; - retval = mm->update_mqd(mm, m, q); - - return retval; + return init_mqd(mm, mqd, mqd_mem_obj, gart_addr, q); }

static int update_mqd_hiq(struct mqd_manager *mm, void *mqd,

[ Upstream commit cdc94a37493135e355dfc0b0e086d84e3eadb50d ]

fls counts bits starting from 1 to 32 (returns 0 for zero argument). If we add 1 we shift right one bit more and loose precision from divisor, what cause function incorect results with some numbers.

Corrected code was tested in user-space, see bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202391

Link: http://lkml.kernel.org/r/1548686944-11891-1-git-send-email-sgruszka@redhat.c... Fixes: 658716d19f8f ("div64_u64(): improve precision on 32bit platforms") Signed-off-by: Stanislaw Gruszka sgruszka@redhat.com Reported-by: Siarhei Volkau lis8215@gmail.com Tested-by: Siarhei Volkau lis8215@gmail.com Acked-by: Oleg Nesterov oleg@redhat.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- lib/div64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/div64.c b/lib/div64.c index 01c8602bb6ff..ee146bb4c558 100644 --- a/lib/div64.c +++ b/lib/div64.c @@ -109,7 +109,7 @@ u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) quot = div_u64_rem(dividend, divisor, &rem32); *remainder = rem32; } else { - int n = 1 + fls(high); + int n = fls(high); quot = div_u64(dividend >> n, divisor >> n);

if (quot != 0) @@ -147,7 +147,7 @@ u64 div64_u64(u64 dividend, u64 divisor) if (high == 0) { quot = div_u64(dividend, divisor); } else { - int n = 1 + fls(high); + int n = fls(high); quot = div_u64(dividend >> n, divisor >> n);

if (quot != 0)

[ Upstream commit ca597bddedd94906cd761d8be6a3ad21292725de ]

As Seulbae Kim reported in bugzilla:

https://bugzilla.kernel.org/show_bug.cgi?id=202637

We didn't recover permission field correctly after sudden power-cut, the reason is in setattr we didn't add inode into global dirty list once i_mode is changed, so latter checkpoint triggered by fsync will not flush last i_mode into disk, result in this problem, fix it.

Reported-by: Seulbae Kim seulbae@gatech.edu Signed-off-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/f2fs/file.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 9fc076ca002d..b3f46e3bec17 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -770,7 +770,6 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int err; - bool size_changed = false;

if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; @@ -830,8 +829,6 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) down_write(&F2FS_I(inode)->i_sem); F2FS_I(inode)->last_disk_size = i_size_read(inode); up_write(&F2FS_I(inode)->i_sem); - - size_changed = true; }

__setattr_copy(inode, attr); @@ -845,7 +842,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) }

/* file size may changed here */ - f2fs_mark_inode_dirty_sync(inode, size_changed); + f2fs_mark_inode_dirty_sync(inode, true);

/* inode change will produce dirty node pages flushed by checkpoint */ f2fs_balance_fs(F2FS_I_SB(inode), true);

[ Upstream commit 1da6c4d9140cb7c13e87667dc4e1488d6c8fc10f ]

syzkaller was able to generate the following UAF in bpf:

BUG: KASAN: use-after-free in lookup_last fs/namei.c:2269 [inline] BUG: KASAN: use-after-free in path_lookupat.isra.43+0x9f8/0xc00 fs/namei.c:2318 Read of size 1 at addr ffff8801c4865c47 by task syz-executor2/9423

CPU: 0 PID: 9423 Comm: syz-executor2 Not tainted 4.20.0-rc1-next-20181109+ #110 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x244/0x39d lib/dump_stack.c:113 print_address_description.cold.7+0x9/0x1ff mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.8+0x242/0x309 mm/kasan/report.c:412 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:430 lookup_last fs/namei.c:2269 [inline] path_lookupat.isra.43+0x9f8/0xc00 fs/namei.c:2318 filename_lookup+0x26a/0x520 fs/namei.c:2348 user_path_at_empty+0x40/0x50 fs/namei.c:2608 user_path include/linux/namei.h:62 [inline] do_mount+0x180/0x1ff0 fs/namespace.c:2980 ksys_mount+0x12d/0x140 fs/namespace.c:3258 __do_sys_mount fs/namespace.c:3272 [inline] __se_sys_mount fs/namespace.c:3269 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3269 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457569 Code: fd b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fde6ed96c78 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 0000000000457569 RDX: 0000000020000040 RSI: 0000000020000000 RDI: 0000000000000000 RBP: 000000000072bf00 R08: 0000000020000340 R09: 0000000000000000 R10: 0000000000200000 R11: 0000000000000246 R12: 00007fde6ed976d4 R13: 00000000004c2c24 R14: 00000000004d4990 R15: 00000000ffffffff

Allocated by task 9424: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] kasan_kmalloc+0xc7/0xe0 mm/kasan/kasan.c:553 __do_kmalloc mm/slab.c:3722 [inline] __kmalloc_track_caller+0x157/0x760 mm/slab.c:3737 kstrdup+0x39/0x70 mm/util.c:49 bpf_symlink+0x26/0x140 kernel/bpf/inode.c:356 vfs_symlink+0x37a/0x5d0 fs/namei.c:4127 do_symlinkat+0x242/0x2d0 fs/namei.c:4154 __do_sys_symlink fs/namei.c:4173 [inline] __se_sys_symlink fs/namei.c:4171 [inline] __x64_sys_symlink+0x59/0x80 fs/namei.c:4171 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 9425: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/kasan.c:521 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528 __cache_free mm/slab.c:3498 [inline] kfree+0xcf/0x230 mm/slab.c:3817 bpf_evict_inode+0x11f/0x150 kernel/bpf/inode.c:565 evict+0x4b9/0x980 fs/inode.c:558 iput_final fs/inode.c:1550 [inline] iput+0x674/0xa90 fs/inode.c:1576 do_unlinkat+0x733/0xa30 fs/namei.c:4069 __do_sys_unlink fs/namei.c:4110 [inline] __se_sys_unlink fs/namei.c:4108 [inline] __x64_sys_unlink+0x42/0x50 fs/namei.c:4108 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe

In this scenario path lookup under RCU is racing with the final unlink in case of symlinks. As Linus puts it in his analysis:

[...] We actually RCU-delay the inode freeing itself, but when we do the final iput(), the "evict()" function is called synchronously. Now, the simple fix would seem to just RCU-delay the kfree() of the symlink data in bpf_evict_inode(). Maybe that's the right thing to do. [...]

Al suggested to piggy-back on the ->destroy_inode() callback in order to implement RCU deferral there which can then kfree() the inode->i_link eventually right before putting inode back into inode cache. By reusing free_inode_nonrcu() from there we can avoid the need for our own inode cache and just reuse generic one as we currently do.

And in-fact on top of all this we should just get rid of the bpf_evict_inode() entirely. This means truncate_inode_pages_final() and clear_inode() will then simply be called by the fs core via evict(). Dropping the reference should really only be done when inode is unhashed and nothing reachable anymore, so it's better also moved into the final ->destroy_inode() callback.

Fixes: 0f98621bef5d ("bpf, inode: add support for symlinks and fix mtime/ctime") Reported-by: syzbot+fb731ca573367b7f6564@syzkaller.appspotmail.com Reported-by: syzbot+a13e5ead792d6df37818@syzkaller.appspotmail.com Reported-by: syzbot+7a8ba368b47fdefca61e@syzkaller.appspotmail.com Suggested-by: Al Viro viro@zeniv.linux.org.uk Analyzed-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: Alexei Starovoitov ast@kernel.org Acked-by: Linus Torvalds torvalds@linux-foundation.org Acked-by: Al Viro viro@zeniv.linux.org.uk Link: https://lore.kernel.org/lkml/0000000000006946d2057bbd0eef@google.com/T/ Signed-off-by: Sasha Levin (Microsoft) sashal@kernel.org --- kernel/bpf/inode.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 2ada5e21dfa6..4a8f390a2b82 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -554,19 +554,6 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ } EXPORT_SYMBOL(bpf_prog_get_type_path);

-static void bpf_evict_inode(struct inode *inode) -{ - enum bpf_type type; - - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); - - if (S_ISLNK(inode->i_mode)) - kfree(inode->i_link); - if (!bpf_inode_type(inode, &type)) - bpf_any_put(inode->i_private, type); -} - /* * Display the mount options in /proc/mounts. */ @@ -579,11 +566,28 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) return 0; }

+static void bpf_destroy_inode_deferred(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + enum bpf_type type; + + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_link); + if (!bpf_inode_type(inode, &type)) + bpf_any_put(inode->i_private, type); + free_inode_nonrcu(inode); +} + +static void bpf_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, bpf_destroy_inode_deferred); +} + static const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, - .evict_inode = bpf_evict_inode, + .destroy_inode = bpf_destroy_inode, };

enum {

From: Kaike Wan kaike.wan@intel.com

commit 662d66466637862ef955f7f6e78a286d8cf0ebef upstream.

When a QP is put into error state, all pending requests in the send work queue should be drained. The following sequence of events could lead to a failure, causing a request to hang:

(1) The QP builds a packet and tries to send through SDMA engine. However, PIO engine is still busy. Consequently, this packet is put on the QP's tx list and the QP is put on the PIO waiting list. The field qp->s_flags is set with HFI1_S_WAIT_PIO_DRAIN;

(2) The QP is put into error state by the user application and notify_error_qp() is called, which removes the QP from the PIO waiting list and the packet from the QP's tx list. In addition, qp->s_flags is cleared of RVT_S_ANY_WAIT_IO bits, which does not include HFI1_S_WAIT_PIO_DRAIN bit;

(3) The hfi1_schdule_send() function is called to drain the QP's send queue. Subsequently, hfi1_do_send() is called. Since the flag bit HFI1_S_WAIT_PIO_DRAIN is set in qp->s_flags, hfi1_send_ok() fails. As a result, hfi1_do_send() bails out without draining any request from the send queue;

(4) The PIO engine completes the sending and tries to wake up any QP on its waiting list. But the QP has been removed from the PIO waiting list and therefore is kept in sleep forever.

The fix is to clear qp->s_flags of HFI1_S_ANY_WAIT_IO bits in step (2). HFI1_S_ANY_WAIT_IO includes RVT_S_ANY_WAIT_IO and HFI1_S_WAIT_PIO_DRAIN.

Fixes: 2e2ba09e48b7 ("IB/rdmavt, IB/hfi1: Create device dependent s_flags") Cc: stable@vger.kernel.org # 4.19.x+ Reviewed-by: Mike Marciniszyn mike.marciniszyn@intel.com Reviewed-by: Alex Estrin alex.estrin@intel.com Signed-off-by: Kaike Wan kaike.wan@intel.com Signed-off-by: Dennis Dalessandro dennis.dalessandro@intel.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/infiniband/hw/hfi1/qp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -784,7 +784,7 @@ void notify_error_qp(struct rvt_qp *qp) write_seqlock(lock); if (!list_empty(&priv->s_iowait.list) && !(qp->s_flags & RVT_S_BUSY)) { - qp->s_flags &= ~RVT_S_ANY_WAIT_IO; + qp->s_flags &= ~HFI1_S_ANY_WAIT_IO; list_del_init(&priv->s_iowait.list); priv->s_iowait.lock = NULL; rvt_put_qp(qp);

From: Konstantin Khlebnikov khlebnikov@yandex-team.ru

In upstream branch this fixed by commit b29940c1abd7 ("mm: rename and change semantics of nr_indirectly_reclaimable_bytes").

This fixes /sys/devices/system/node/node*/vmstat format:

... nr_dirtied 6613155 nr_written 5796802 11089216 ...

Cc: stable@vger.kernel.org # 4.19.y Fixes: 7aaf77272358 ("mm: don't show nr_indirectly_reclaimable in /proc/vmstat") Signed-off-by: Konstantin Khlebnikov khlebnikov@yandex-team.ru Cc: Roman Gushchin guro@fb.com Cc: Vlastimil Babka vbabka@suse.cz Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/base/node.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -197,11 +197,16 @@ static ssize_t node_read_vmstat(struct d sum_zone_numa_state(nid, i)); #endif

- for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { + /* Skip hidden vmstat items. */ + if (*vmstat_text[i + NR_VM_ZONE_STAT_ITEMS + + NR_VM_NUMA_STAT_ITEMS] == '\0') + continue; n += sprintf(buf+n, "%s %lu\n", vmstat_text[i + NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_STAT_ITEMS], node_page_state(pgdat, i)); + }

return n; }