From: Dmitry Monakhov dmonakhov@gmail.com

commit 4068664e3cd2312610ceac05b74c4cf1853b8325 upstream.

Extents are cached in read_extent_tree_block(); as a result, extents are not cached for inodes with depth == 0 when we try to find the extent using ext4_find_extent(). The result of the lookup is cached in ext4_map_blocks() but is only a subset of the extent on disk. As a result, the contents of extents status cache can get very badly fragmented for certain workloads, such as a random 4k read workload.

File size of /mnt/test is 33554432 (8192 blocks of 4096 bytes) ext: logical_offset: physical_offset: length: expected: flags: 0: 0.. 8191: 40960.. 49151: 8192: last,eof

$ perf record -e 'ext4:ext4_es_*' /root/bin/fio --name=t --direct=0 --rw=randread --bs=4k --filesize=32M --size=32M --filename=/mnt/test $ perf script | grep ext4_es_insert_extent | head -n 10 fio 131 [000] 13.975421: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [494/1) mapped 41454 status W fio 131 [000] 13.975939: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [6064/1) mapped 47024 status W fio 131 [000] 13.976467: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [6907/1) mapped 47867 status W fio 131 [000] 13.976937: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [3850/1) mapped 44810 status W fio 131 [000] 13.977440: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [3292/1) mapped 44252 status W fio 131 [000] 13.977931: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [6882/1) mapped 47842 status W fio 131 [000] 13.978376: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [3117/1) mapped 44077 status W fio 131 [000] 13.978957: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [2896/1) mapped 43856 status W fio 131 [000] 13.979474: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [7479/1) mapped 48439 status W

Fix this by caching the extents for inodes with depth == 0 in ext4_find_extent().

[ Renamed ext4_es_cache_extents() to ext4_cache_extents() since this newly added function is not in extents_cache.c, and to avoid potential visual confusion with ext4_es_cache_extent(). -TYT ]

Signed-off-by: Dmitry Monakhov dmonakhov@gmail.com Link: https://lore.kernel.org/r/20191106122502.19986-1-dmonakhov@gmail.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ext4/extents.c | 47 +++++++++++++++++++++++++++-------------------- 1 file changed, 27 insertions(+), 20 deletions(-)

--- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -510,6 +510,30 @@ int ext4_ext_check_inode(struct inode *i return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0); }

+static void ext4_cache_extents(struct inode *inode, + struct ext4_extent_header *eh) +{ + struct ext4_extent *ex = EXT_FIRST_EXTENT(eh); + ext4_lblk_t prev = 0; + int i; + + for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) { + unsigned int status = EXTENT_STATUS_WRITTEN; + ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); + int len = ext4_ext_get_actual_len(ex); + + if (prev && (prev != lblk)) + ext4_es_cache_extent(inode, prev, lblk - prev, ~0, + EXTENT_STATUS_HOLE); + + if (ext4_ext_is_unwritten(ex)) + status = EXTENT_STATUS_UNWRITTEN; + ext4_es_cache_extent(inode, lblk, len, + ext4_ext_pblock(ex), status); + prev = lblk + len; + } +} + static struct buffer_head * __read_extent_tree_block(const char *function, unsigned int line, struct inode *inode, ext4_fsblk_t pblk, int depth, @@ -540,26 +564,7 @@ __read_extent_tree_block(const char *fun */ if (!(flags & EXT4_EX_NOCACHE) && depth == 0) { struct ext4_extent_header *eh = ext_block_hdr(bh); - struct ext4_extent *ex = EXT_FIRST_EXTENT(eh); - ext4_lblk_t prev = 0; - int i; - - for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) { - unsigned int status = EXTENT_STATUS_WRITTEN; - ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); - int len = ext4_ext_get_actual_len(ex); - - if (prev && (prev != lblk)) - ext4_es_cache_extent(inode, prev, - lblk - prev, ~0, - EXTENT_STATUS_HOLE); - - if (ext4_ext_is_unwritten(ex)) - status = EXTENT_STATUS_UNWRITTEN; - ext4_es_cache_extent(inode, lblk, len, - ext4_ext_pblock(ex), status); - prev = lblk + len; - } + ext4_cache_extents(inode, eh); } return bh; errout: @@ -907,6 +912,8 @@ ext4_find_extent(struct inode *inode, ex path[0].p_bh = NULL;

i = depth; + if (!(flags & EXT4_EX_NOCACHE) && depth == 0) + ext4_cache_extents(inode, eh); /* walk through the tree */ while (i) { ext_debug("depth %d: num %d, max %d\n",

From: Arnd Bergmann arnd@arndb.de

commit 773daa3caf5d3f87fdb1ab43e9c1b367a38fa394 upstream.

The newly introudced ip_min_valid_pmtu variable is only used when CONFIG_SYSCTL is set:

net/ipv4/route.c:135:12: error: 'ip_min_valid_pmtu' defined but not used [-Werror=unused-variable]

This moves it to the other variables like it, to avoid the harmless warning.

Fixes: c7272c2f1229 ("net: ipv4: don't allow setting net.ipv4.route.min_pmtu below 68") Signed-off-by: Arnd Bergmann arnd@arndb.de Acked-by: Sabrina Dubroca sd@queasysnail.net Signed-off-by: David S. Miller davem@davemloft.net Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/ipv4/route.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -133,8 +133,6 @@ static int ip_rt_min_advmss __read_mostl

static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;

-static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; - /* * Interface to generic destination cache. */ @@ -2869,6 +2867,7 @@ void ip_rt_multicast_event(struct in_dev static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; +static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU;

static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write, void __user *buffer,

From: Rob Clark robdclark@chromium.org

commit 9f614197c744002f9968e82c649fdf7fe778e1e7 upstream.

Looks like the dma_sync calls don't do what we want on armv7 either. Fixes:

Unable to handle kernel paging request at virtual address 50001000 pgd = (ptrval) [50001000] *pgd=00000000 Internal error: Oops: 805 [#1] SMP ARM Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.3.0-rc6-00271-g9f159ae07f07 #4 Hardware name: Freescale i.MX53 (Device Tree Support) PC is at v7_dma_clean_range+0x20/0x38 LR is at __dma_page_cpu_to_dev+0x28/0x90 pc : [<c011c76c>] lr : [<c01181c4>] psr: 20000013 sp : d80b5a88 ip : de96c000 fp : d840ce6c r10: 00000000 r9 : 00000001 r8 : d843e010 r7 : 00000000 r6 : 00008000 r5 : ddb6c000 r4 : 00000000 r3 : 0000003f r2 : 00000040 r1 : 50008000 r0 : 50001000 Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 10c5387d Table: 70004019 DAC: 00000051 Process swapper/0 (pid: 1, stack limit = 0x(ptrval))

Signed-off-by: Rob Clark robdclark@chromium.org Fixes: 3de433c5b38a ("drm/msm: Use the correct dma_sync calls in msm_gem") Tested-by: Fabio Estevam festevam@gmail.com Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpu/drm/msm/msm_gem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -61,7 +61,7 @@ static void sync_for_device(struct msm_g { struct device *dev = msm_obj->base.dev->dev;

- if (get_dma_ops(dev)) { + if (get_dma_ops(dev) && IS_ENABLED(CONFIG_ARM64)) { dma_sync_sg_for_device(dev, msm_obj->sgt->sgl, msm_obj->sgt->nents, DMA_BIDIRECTIONAL); } else { @@ -74,7 +74,7 @@ static void sync_for_cpu(struct msm_gem_ { struct device *dev = msm_obj->base.dev->dev;

- if (get_dma_ops(dev)) { + if (get_dma_ops(dev) && IS_ENABLED(CONFIG_ARM64)) { dma_sync_sg_for_cpu(dev, msm_obj->sgt->sgl, msm_obj->sgt->nents, DMA_BIDIRECTIONAL); } else {

From: Jeremy Sowden jeremy@azazel.net

commit 01ce31c57b3f07c91c9d45bbaf126124cce83a5d upstream.

Removed info log-message if ipip tunnel registration fails during module-initialization: it adds nothing to the error message that is written on all failures.

Fixes: dd9ee3444014e ("vti4: Fix a ipip packet processing bug in 'IPCOMP' virtual tunnel") Signed-off-by: Jeremy Sowden jeremy@azazel.net Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/ipv4/ip_vti.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -681,10 +681,8 @@ static int __init vti_init(void)

msg = "ipip tunnel"; err = xfrm4_tunnel_register(&ipip_handler, AF_INET); - if (err < 0) { - pr_info("%s: cant't register tunnel\n",__func__); + if (err < 0) goto xfrm_tunnel_failed; - }

msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops);

From: James Smart jsmart2021@gmail.com

[ Upstream commit 38503943c89f0bafd9e3742f63f872301d44cbea ]

The following kasan bug was called out:

BUG: KASAN: slab-out-of-bounds in lpfc_unreg_login+0x7c/0xc0 [lpfc] Read of size 2 at addr ffff889fc7c50a22 by task lpfc_worker_3/6676 ... Call Trace: dump_stack+0x96/0xe0 ? lpfc_unreg_login+0x7c/0xc0 [lpfc] print_address_description.constprop.6+0x1b/0x220 ? lpfc_unreg_login+0x7c/0xc0 [lpfc] ? lpfc_unreg_login+0x7c/0xc0 [lpfc] __kasan_report.cold.9+0x37/0x7c ? lpfc_unreg_login+0x7c/0xc0 [lpfc] kasan_report+0xe/0x20 lpfc_unreg_login+0x7c/0xc0 [lpfc] lpfc_sli_def_mbox_cmpl+0x334/0x430 [lpfc] ...

When processing the completion of a "Reg Rpi" login mailbox command in lpfc_sli_def_mbox_cmpl, a call may be made to lpfc_unreg_login. The vpi is extracted from the completing mailbox context and passed as an input for the next. However, the vpi stored in the mailbox command context is an absolute vpi, which for SLI4 represents both base + offset. When used with a non-zero base component, (function id > 0) this results in an out-of-range access beyond the allocated phba->vpi_ids array.

Fix by subtracting the function's base value to get an accurate vpi number.

Link: https://lore.kernel.org/r/20200322181304.37655-2-jsmart2021@gmail.com Signed-off-by: James Smart jsmart2021@gmail.com Signed-off-by: Dick Kennedy dick.kennedy@broadcom.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/lpfc/lpfc_sli.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index d8e0ba68879c3..480d2d467f7a6 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -2271,6 +2271,8 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) !pmb->u.mb.mbxStatus) { rpi = pmb->u.mb.un.varWords[0]; vpi = pmb->u.mb.un.varRegLogin.vpi; + if (phba->sli_rev == LPFC_SLI_REV4) + vpi -= phba->sli4_hba.max_cfg_param.vpi_base; lpfc_unreg_login(phba, vpi, rpi, pmb); pmb->vport = vport; pmb->mbox_cmpl = lpfc_sli_def_mbox_cmpl;

From: Yan, Zheng zyan@redhat.com

[ Upstream commit 0aa971b6fd3f92afef6afe24ef78d9bb14471519 ]

1. try_get_cap_refs() fails to get caps and finds that mds_wanted does not include what it wants. It returns -ESTALE. 2. ceph_get_caps() calls ceph_renew_caps(). ceph_renew_caps() finds that inode has cap, so it calls ceph_check_caps(). 3. ceph_check_caps() finds that issued caps (without checking if it's stale) already includes caps wanted by open file, so it skips updating wanted caps.

Above events can cause an infinite loop inside ceph_get_caps().

Signed-off-by: "Yan, Zheng" zyan@redhat.com Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ceph/caps.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index c3a3ee74e2d84..1b5a50848b5be 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1863,8 +1863,12 @@ retry_locked: }

/* want more caps from mds? */ - if (want & ~(cap->mds_wanted | cap->issued)) - goto ack; + if (want & ~cap->mds_wanted) { + if (want & ~(cap->mds_wanted | cap->issued)) + goto ack; + if (!__cap_is_valid(cap)) + goto ack; + }

/* things we might delay */ if ((cap->issued & ~retain) == 0 &&

From: Wu Bo wubo40@huawei.com

[ Upstream commit 13e60d3ba287d96eeaf1deaadba51f71578119a3 ]

If the daemon is restarted or crashes while logging out of a session, the unbind session event sent by the kernel is not processed and is lost. When the daemon starts again, the session can't be unbound because the daemon is waiting for the event message. However, the kernel has already logged out and the event will not be resent.

When iscsid restart is complete, logout session reports error:

Logging out of session [sid: 6, target: iqn.xxxxx, portal: xx.xx.xx.xx,3260] iscsiadm: Could not logout of [sid: 6, target: iscsiadm -m node iqn.xxxxx, portal: xx.xx.xx.xx,3260]. iscsiadm: initiator reported error (9 - internal error) iscsiadm: Could not logout of all requested sessions

Make sure the unbind event is emitted.

[mkp: commit desc and applied by hand since patch was mangled]

Link: https://lore.kernel.org/r/4eab1771-2cb3-8e79-b31c-923652340e99@huawei.com Reviewed-by: Lee Duncan lduncan@suse.com Signed-off-by: Wu Bo wubo40@huawei.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/scsi_transport_iscsi.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index aecb563a2b4e3..9589015234693 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2010,7 +2010,7 @@ static void __iscsi_unbind_session(struct work_struct *work) if (session->target_id == ISCSI_MAX_TARGET) { spin_unlock_irqrestore(&session->lock, flags); mutex_unlock(&ihost->mutex); - return; + goto unbind_session_exit; }

target_id = session->target_id; @@ -2022,6 +2022,8 @@ static void __iscsi_unbind_session(struct work_struct *work) ida_simple_remove(&iscsi_sess_ida, target_id);

scsi_remove_target(&session->dev); + +unbind_session_exit: iscsi_session_event(session, ISCSI_KEVENT_UNBIND_SESSION); ISCSI_DBG_TRANS_SESSION(session, "Completed target removal\n"); }

From: Vasily Averin vvs@virtuozzo.com

[ Upstream commit f4d74ef6220c1eda0875da30457bef5c7111ab06 ]

If seq_file .next function does not change position index, read after some lseek can generate unexpected output.

https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin vvs@virtuozzo.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Acked-by: Peter Oberparleiter oberpar@linux.ibm.com Cc: Al Viro viro@zeniv.linux.org.uk Cc: Davidlohr Bueso dave@stgolabs.net Cc: Ingo Molnar mingo@redhat.com Cc: Manfred Spraul manfred@colorfullife.com Cc: NeilBrown neilb@suse.com Cc: Steven Rostedt rostedt@goodmis.org Cc: Waiman Long longman@redhat.com Link: http://lkml.kernel.org/r/f65c6ee7-bd00-f910-2f8a-37cc67e4ff88@virtuozzo.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/gcov/fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c index 6e40ff6be083d..291e0797125b6 100644 --- a/kernel/gcov/fs.c +++ b/kernel/gcov/fs.c @@ -109,9 +109,9 @@ static void *gcov_seq_next(struct seq_file *seq, void *data, loff_t *pos) { struct gcov_iterator *iter = data;

+ (*pos)++; if (gcov_iter_next(iter)) return NULL; - (*pos)++;

return iter; }

From: Vasily Averin vvs@virtuozzo.com

[ Upstream commit 89163f93c6f969da5811af5377cc10173583123b ]

If seq_file .next function does not change position index, read after some lseek can generate unexpected output.

https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin vvs@virtuozzo.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Acked-by: Waiman Long longman@redhat.com Cc: Davidlohr Bueso dave@stgolabs.net Cc: Manfred Spraul manfred@colorfullife.com Cc: Al Viro viro@zeniv.linux.org.uk Cc: Ingo Molnar mingo@redhat.com Cc: NeilBrown neilb@suse.com Cc: Peter Oberparleiter oberpar@linux.ibm.com Cc: Steven Rostedt rostedt@goodmis.org Link: http://lkml.kernel.org/r/b7a20945-e315-8bb0-21e6-3875c14a8494@virtuozzo.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- ipc/util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ipc/util.c b/ipc/util.c index 79b30eee32cd8..7989f5e532198 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -750,13 +750,13 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos, total++; }

+ *new_pos = pos + 1; if (total >= ids->in_use) return NULL;

for (; pos < IPCMNI; pos++) { ipc = idr_find(&ids->ipcs_idr, pos); if (ipc != NULL) { - *new_pos = pos + 1; rcu_read_lock(); ipc_lock_object(ipc); return ipc;

From: Geert Uytterhoeven geert+renesas@glider.be

[ Upstream commit d5a3c7a4536e1329a758e14340efd0e65252bd3d ]

Runtime PM should be enabled before calling pwmchip_add(), as PWM users can appear immediately after the PWM chip has been added. Likewise, Runtime PM should always be disabled after the removal of the PWM chip, even if the latter failed.

Fixes: 99b82abb0a35b073 ("pwm: Add Renesas TPU PWM driver") Signed-off-by: Geert Uytterhoeven geert+renesas@glider.be Signed-off-by: Thierry Reding thierry.reding@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pwm/pwm-renesas-tpu.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/pwm/pwm-renesas-tpu.c b/drivers/pwm/pwm-renesas-tpu.c index 29267d12fb4c9..9c7962f2f0aa4 100644 --- a/drivers/pwm/pwm-renesas-tpu.c +++ b/drivers/pwm/pwm-renesas-tpu.c @@ -423,16 +423,17 @@ static int tpu_probe(struct platform_device *pdev) tpu->chip.base = -1; tpu->chip.npwm = TPU_CHANNEL_MAX;

+ pm_runtime_enable(&pdev->dev); + ret = pwmchip_add(&tpu->chip); if (ret < 0) { dev_err(&pdev->dev, "failed to register PWM chip\n"); + pm_runtime_disable(&pdev->dev); return ret; }

dev_info(&pdev->dev, "TPU PWM %d registered\n", tpu->pdev->id);

- pm_runtime_enable(&pdev->dev); - return 0; }

@@ -442,12 +443,10 @@ static int tpu_remove(struct platform_device *pdev) int ret;

ret = pwmchip_remove(&tpu->chip); - if (ret) - return ret;

pm_runtime_disable(&pdev->dev);

- return 0; + return ret; }

#ifdef CONFIG_OF

From: Jiri Olsa jolsa@kernel.org

[ Upstream commit d3296fb372bf7497b0e5d0478c4e7a677ec6f6e9 ]

We hit following warning when running tests on kernel compiled with CONFIG_DEBUG_ATOMIC_SLEEP=y:

WARNING: CPU: 19 PID: 4472 at mm/gup.c:2381 __get_user_pages_fast+0x1a4/0x200 CPU: 19 PID: 4472 Comm: dummy Not tainted 5.6.0-rc6+ #3 RIP: 0010:__get_user_pages_fast+0x1a4/0x200 ... Call Trace: perf_prepare_sample+0xff1/0x1d90 perf_event_output_forward+0xe8/0x210 __perf_event_overflow+0x11a/0x310 __intel_pmu_pebs_event+0x657/0x850 intel_pmu_drain_pebs_nhm+0x7de/0x11d0 handle_pmi_common+0x1b2/0x650 intel_pmu_handle_irq+0x17b/0x370 perf_event_nmi_handler+0x40/0x60 nmi_handle+0x192/0x590 default_do_nmi+0x6d/0x150 do_nmi+0x2f9/0x3c0 nmi+0x8e/0xd7

While __get_user_pages_fast() is IRQ-safe, it calls access_ok(), which warns on:

WARN_ON_ONCE(!in_task() && !pagefault_disabled())

Peter suggested disabling page faults around __get_user_pages_fast(), which gets rid of the warning in access_ok() call.

Suggested-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Jiri Olsa jolsa@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lkml.kernel.org/r/20200407141427.3184722-1-jolsa@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/events/core.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c index 845c8a1a9d30a..c16ce11049de3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6119,9 +6119,12 @@ static u64 perf_virt_to_phys(u64 virt) * Try IRQ-safe __get_user_pages_fast first. * If failed, leave phys_addr as 0. */ - if ((current->mm != NULL) && - (__get_user_pages_fast(virt, 1, 0, &p) == 1)) - phys_addr = page_to_phys(p) + virt % PAGE_SIZE; + if (current->mm != NULL) { + pagefault_disable(); + if (__get_user_pages_fast(virt, 1, 0, &p) == 1) + phys_addr = page_to_phys(p) + virt % PAGE_SIZE; + pagefault_enable(); + }

if (p) put_page(p);

From: Vlastimil Babka vbabka@suse.cz

commit 0882ff9190e3bc51e2d78c3aadd7c690eeaa91d5 upstream.

In SLUB, prefetch_freepointer() is used when allocating an object from cache's freelist, to make sure the next object in the list is cache-hot, since it's probable it will be allocated soon.

Commit 2482ddec670f ("mm: add SLUB free list pointer obfuscation") has unintentionally changed the prefetch in a way where the prefetch is turned to a real fetch, and only the next->next pointer is prefetched. In case there is not a stream of allocations that would benefit from prefetching, the extra real fetch might add a useless cache miss to the allocation. Restore the previous behavior.

Link: http://lkml.kernel.org/r/20180809085245.22448-1-vbabka@suse.cz Fixes: 2482ddec670f ("mm: add SLUB free list pointer obfuscation") Signed-off-by: Vlastimil Babka vbabka@suse.cz Acked-by: Kees Cook keescook@chromium.org Cc: Daniel Micay danielmicay@gmail.com Cc: Eric Dumazet edumazet@google.com Cc: Christoph Lameter cl@linux.com Cc: Pekka Enberg penberg@kernel.org Cc: David Rientjes rientjes@google.com Cc: Joonsoo Kim iamjoonsoo.kim@lge.com Cc: Matthias Schiffer mschiffer@universe-factory.net Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sven Eckelmann sven@narfation.org Signed-off-by: Sasha Levin sashal@kernel.org --- mm/slub.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c index 3c1a16f03b2bd..481518c3f61a9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -269,8 +269,7 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object)

static void prefetch_freepointer(const struct kmem_cache *s, void *object) { - if (object) - prefetch(freelist_dereference(s, object + s->offset)); + prefetch(object + s->offset); }

static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)

From: John Haxby john.haxby@oracle.com

[ Upstream commit 82c9ae440857840c56e05d4fb1427ee032531346 ]

Commit b6f6118901d1 ("ipv6: restrict IPV6_ADDRFORM operation") fixed a problem found by syzbot an unfortunate logic error meant that it also broke IPV6_ADDRFORM.

Rearrange the checks so that the earlier test is just one of the series of checks made before moving the socket from IPv6 to IPv4.

Fixes: b6f6118901d1 ("ipv6: restrict IPV6_ADDRFORM operation") Signed-off-by: John Haxby john.haxby@oracle.com Cc: stable@vger.kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/ipv6_sockglue.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-)

--- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -185,15 +185,14 @@ static int do_ipv6_setsockopt(struct soc retv = -EBUSY; break; } - } else if (sk->sk_protocol == IPPROTO_TCP) { - if (sk->sk_prot != &tcpv6_prot) { - retv = -EBUSY; - break; - } - break; - } else { + } + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_prot != &tcpv6_prot) { + retv = -EBUSY; break; } + if (sk->sk_protocol != IPPROTO_TCP) + break; if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; break;

From: Taehee Yoo ap420073@gmail.com

[ Upstream commit 4dee15b4fd0d61ec6bbd179238191e959d34cf7a ]

In the macvlan_device_event(), the list_first_entry_or_null() is used. This function could return null pointer if there is no node. But, the macvlan module doesn't check the null pointer. So, null-ptr-deref would occur.

bond0 | +----+-----+ | | macvlan0 macvlan1 | | dummy0 dummy1

The problem scenario. If dummy1 is removed, 1. ->dellink() of dummy1 is called. 2. NETDEV_UNREGISTER of dummy1 notification is sent to macvlan module. 3. ->dellink() of macvlan1 is called. 4. NETDEV_UNREGISTER of macvlan1 notification is sent to bond module. 5. __bond_release_one() is called and it internally calls dev_set_mac_address(). 6. dev_set_mac_address() calls the ->ndo_set_mac_address() of macvlan1, which is macvlan_set_mac_address(). 7. macvlan_set_mac_address() calls the dev_set_mac_address() with dummy1. 8. NETDEV_CHANGEADDR of dummy1 is sent to macvlan module. 9. In the macvlan_device_event(), it calls list_first_entry_or_null(). At this point, dummy1 and macvlan1 were removed. So, list_first_entry_or_null() will return NULL.

Test commands: ip netns add nst ip netns exec nst ip link add bond0 type bond for i in {0..10} do ip netns exec nst ip link add dummy$i type dummy ip netns exec nst ip link add macvlan$i link dummy$i \ type macvlan mode passthru ip netns exec nst ip link set macvlan$i master bond0 done ip netns del nst

Splat looks like: [ 40.585687][ T146] general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP DEI [ 40.587249][ T146] KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] [ 40.588342][ T146] CPU: 1 PID: 146 Comm: kworker/u8:2 Not tainted 5.7.0-rc1+ #532 [ 40.589299][ T146] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 40.590469][ T146] Workqueue: netns cleanup_net [ 40.591045][ T146] RIP: 0010:macvlan_device_event+0x4e2/0x900 [macvlan] [ 40.591905][ T146] Code: 00 00 00 00 00 fc ff df 80 3c 06 00 0f 85 45 02 00 00 48 89 da 48 b8 00 00 00 00 00 fc ff d2 [ 40.594126][ T146] RSP: 0018:ffff88806116f4a0 EFLAGS: 00010246 [ 40.594783][ T146] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 40.595653][ T146] RDX: 0000000000000000 RSI: ffff88806547ddd8 RDI: ffff8880540f1360 [ 40.596495][ T146] RBP: ffff88804011a808 R08: fffffbfff4fb8421 R09: fffffbfff4fb8421 [ 40.597377][ T146] R10: ffffffffa7dc2107 R11: 0000000000000000 R12: 0000000000000008 [ 40.598186][ T146] R13: ffff88804011a000 R14: ffff8880540f1000 R15: 1ffff1100c22de9a [ 40.599012][ T146] FS: 0000000000000000(0000) GS:ffff888067800000(0000) knlGS:0000000000000000 [ 40.600004][ T146] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 40.600665][ T146] CR2: 00005572d3a807b8 CR3: 000000005fcf4003 CR4: 00000000000606e0 [ 40.601485][ T146] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 40.602461][ T146] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 40.603443][ T146] Call Trace: [ 40.603871][ T146] ? nf_tables_dump_setelem+0xa0/0xa0 [nf_tables] [ 40.604587][ T146] ? macvlan_uninit+0x100/0x100 [macvlan] [ 40.605212][ T146] ? __module_text_address+0x13/0x140 [ 40.605842][ T146] notifier_call_chain+0x90/0x160 [ 40.606477][ T146] dev_set_mac_address+0x28e/0x3f0 [ 40.607117][ T146] ? netdev_notify_peers+0xc0/0xc0 [ 40.607762][ T146] ? __module_text_address+0x13/0x140 [ 40.608440][ T146] ? notifier_call_chain+0x90/0x160 [ 40.609097][ T146] ? dev_set_mac_address+0x1f0/0x3f0 [ 40.609758][ T146] dev_set_mac_address+0x1f0/0x3f0 [ 40.610402][ T146] ? __local_bh_enable_ip+0xe9/0x1b0 [ 40.611071][ T146] ? bond_hw_addr_flush+0x77/0x100 [bonding] [ 40.611823][ T146] ? netdev_notify_peers+0xc0/0xc0 [ 40.612461][ T146] ? bond_hw_addr_flush+0x77/0x100 [bonding] [ 40.613213][ T146] ? bond_hw_addr_flush+0x77/0x100 [bonding] [ 40.613963][ T146] ? __local_bh_enable_ip+0xe9/0x1b0 [ 40.614631][ T146] ? bond_time_in_interval.isra.31+0x90/0x90 [bonding] [ 40.615484][ T146] ? __bond_release_one+0x9f0/0x12c0 [bonding] [ 40.616230][ T146] __bond_release_one+0x9f0/0x12c0 [bonding] [ 40.616949][ T146] ? bond_enslave+0x47c0/0x47c0 [bonding] [ 40.617642][ T146] ? lock_downgrade+0x730/0x730 [ 40.618218][ T146] ? check_flags.part.42+0x450/0x450 [ 40.618850][ T146] ? __mutex_unlock_slowpath+0xd0/0x670 [ 40.619519][ T146] ? trace_hardirqs_on+0x30/0x180 [ 40.620117][ T146] ? wait_for_completion+0x250/0x250 [ 40.620754][ T146] bond_netdev_event+0x822/0x970 [bonding] [ 40.621460][ T146] ? __module_text_address+0x13/0x140 [ 40.622097][ T146] notifier_call_chain+0x90/0x160 [ 40.622806][ T146] rollback_registered_many+0x660/0xcf0 [ 40.623522][ T146] ? netif_set_real_num_tx_queues+0x780/0x780 [ 40.624290][ T146] ? notifier_call_chain+0x90/0x160 [ 40.624957][ T146] ? netdev_upper_dev_unlink+0x114/0x180 [ 40.625686][ T146] ? __netdev_adjacent_dev_unlink_neighbour+0x30/0x30 [ 40.626421][ T146] ? mutex_is_locked+0x13/0x50 [ 40.627016][ T146] ? unregister_netdevice_queue+0xf2/0x240 [ 40.627663][ T146] unregister_netdevice_many.part.134+0x13/0x1b0 [ 40.628362][ T146] default_device_exit_batch+0x2d9/0x390 [ 40.628987][ T146] ? unregister_netdevice_many+0x40/0x40 [ 40.629615][ T146] ? dev_change_net_namespace+0xcb0/0xcb0 [ 40.630279][ T146] ? prepare_to_wait_exclusive+0x2e0/0x2e0 [ 40.630943][ T146] ? ops_exit_list.isra.9+0x97/0x140 [ 40.631554][ T146] cleanup_net+0x441/0x890 [ ... ]

Fixes: e289fd28176b ("macvlan: fix the problem when mac address changes for passthru mode") Reported-by: syzbot+5035b1f9dc7ea4558d5a@syzkaller.appspotmail.com Signed-off-by: Taehee Yoo ap420073@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/macvlan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1673,7 +1673,7 @@ static int macvlan_device_event(struct n struct macvlan_dev, list);

- if (macvlan_sync_address(vlan->dev, dev->dev_addr)) + if (vlan && macvlan_sync_address(vlan->dev, dev->dev_addr)) return NOTIFY_BAD;

break;

From: Xiyu Yang xiyuyang19@fudan.edu.cn

[ Upstream commit d03f228470a8c0a22b774d1f8d47071e0de4f6dd ]

nr_add_node() invokes nr_neigh_get_dev(), which returns a local reference of the nr_neigh object to "nr_neigh" with increased refcnt.

When nr_add_node() returns, "nr_neigh" becomes invalid, so the refcount should be decreased to keep refcount balanced.

The issue happens in one normal path of nr_add_node(), which forgets to decrease the refcnt increased by nr_neigh_get_dev() and causes a refcnt leak. It should decrease the refcnt before the function returns like other normal paths do.

Fix this issue by calling nr_neigh_put() before the nr_add_node() returns.

Signed-off-by: Xiyu Yang xiyuyang19@fudan.edu.cn Signed-off-by: Xin Tan tanxin.ctf@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/netrom/nr_route.c | 1 + 1 file changed, 1 insertion(+)

--- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -199,6 +199,7 @@ static int __must_check nr_add_node(ax25 /* refcount initialized at 1 */ spin_unlock_bh(&nr_node_list_lock);

+ nr_neigh_put(nr_neigh); return 0; } nr_node_lock(nr_node);

From: Eric Dumazet edumazet@google.com

[ Upstream commit 9bacd256f1354883d3c1402655153367982bba49 ]

TCP stack is dumb in how it cooks its output packets.

Depending on MAX_HEADER value, we might chose a bad ending point for the headers.

If we align the end of TCP headers to cache line boundary, we make sure to always use the smallest number of cache lines, which always help.

Signed-off-by: Eric Dumazet edumazet@google.com Cc: Soheil Hassas Yeganeh soheil@google.com Acked-by: Soheil Hassas Yeganeh soheil@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -55,7 +55,7 @@ extern struct inet_hashinfo tcp_hashinfo extern struct percpu_counter tcp_orphan_count; void tcp_time_wait(struct sock *sk, int state, int timeo);

-#define MAX_TCP_HEADER (128 + MAX_HEADER) +#define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) #define MAX_TCP_OPTION_SPACE 40 #define TCP_MIN_SND_MSS 48 #define TCP_MIN_GSO_SIZE (TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE)

From: Florian Fainelli f.fainelli@gmail.com

[ Upstream commit c2e77a18a7ed65eb48f6e389b6a59a0fd753646a ]

The ARL {MAC,VID} tuple and the forward entry were off by 0x10 bytes, which means that when we read/wrote from/to ARL bin index 0, we were actually accessing the ARLA_RWCTRL register.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations") Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/b53/b53_regs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -294,7 +294,7 @@ * * BCM5325 and BCM5365 share most definitions below */ -#define B53_ARLTBL_MAC_VID_ENTRY(n) (0x10 * (n)) +#define B53_ARLTBL_MAC_VID_ENTRY(n) ((0x10 * (n)) + 0x10) #define ARLTBL_MAC_MASK 0xffffffffffffULL #define ARLTBL_VID_S 48 #define ARLTBL_VID_MASK_25 0xff @@ -306,7 +306,7 @@ #define ARLTBL_VALID_25 BIT(63)

/* ARL Table Data Entry N Registers (32 bit) */ -#define B53_ARLTBL_DATA_ENTRY(n) ((0x10 * (n)) + 0x08) +#define B53_ARLTBL_DATA_ENTRY(n) ((0x10 * (n)) + 0x18) #define ARLTBL_DATA_PORT_ID_MASK 0x1ff #define ARLTBL_TC(tc) ((3 & tc) << 11) #define ARLTBL_AGE BIT(14)

From: David Ahern dsahern@gmail.com

[ Upstream commit 16b9db1ce34ff00d6c18e82825125cfef0cdfb13 ]

To avoid a loop with qdiscs and xfrms, check if the skb has already gone through the qdisc attached to the VRF device and then to the xfrm layer. If so, no need for a second redirect.

Fixes: 193125dbd8eb ("net: Introduce VRF device driver") Reported-by: Trev Larock trev@larock.ca Signed-off-by: David Ahern dsahern@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/vrf.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -476,7 +476,8 @@ static struct sk_buff *vrf_ip6_out(struc if (rt6_need_strict(&ipv6_hdr(skb)->daddr)) return skb;

- if (qdisc_tx_is_default(vrf_dev)) + if (qdisc_tx_is_default(vrf_dev) || + IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return vrf_ip6_out_direct(vrf_dev, sk, skb);

return vrf_ip6_out_redirect(vrf_dev, skb); @@ -692,7 +693,8 @@ static struct sk_buff *vrf_ip_out(struct ipv4_is_lbcast(ip_hdr(skb)->daddr)) return skb;

- if (qdisc_tx_is_default(vrf_dev)) + if (qdisc_tx_is_default(vrf_dev) || + IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return vrf_ip_out_direct(vrf_dev, sk, skb);

return vrf_ip_out_redirect(vrf_dev, skb);

From: Takashi Iwai tiwai@suse.de

[ Upstream commit a8cf44f085ac12c0b5b8750ebb3b436c7f455419 ]

The commit 3c6fd1f07ed0 ("ALSA: hda: Add driver blacklist") added a new blacklist for the devices that are known to have empty codecs, and one of the entries was ASUS ROG Zenith II (PCI SSID 1043:874f). However, it turned out that the very same PCI SSID is used for the previous model that does have the valid HD-audio codecs and the change broke the sound on it.

This patch reverts the corresponding entry as a temporary solution. Although Zenith II and co will see get the empty HD-audio bus again, it'd be merely resource wastes and won't affect the functionality, so it's no end of the world. We'll need to address this later, e.g. by either switching to DMI string matching or using PCI ID & SSID pairs.

Fixes: 3c6fd1f07ed0 ("ALSA: hda: Add driver blacklist") Reported-by: Johnathan Smithinovic johnathan.smithinovic@gmx.at Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200419071926.22683-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/hda/hda_intel.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index d392c1ec0b282..46670da047074 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2173,7 +2173,6 @@ static const struct hdac_io_ops pci_hda_io_ops = { * should be ignored from the beginning. */ static const struct snd_pci_quirk driver_blacklist[] = { - SND_PCI_QUIRK(0x1043, 0x874f, "ASUS ROG Zenith II / Strix", 0), SND_PCI_QUIRK(0x1462, 0xcb59, "MSI TRX40 Creator", 0), SND_PCI_QUIRK(0x1462, 0xcb60, "MSI TRX40", 0), {}

From: Lars-Peter Clausen lars@metafoo.de

commit e44ec7794d88f918805d700240211a9ec05ed89d upstream.

The check for shutting down the second ADC is inverted. This causes it to be powered down when it should be enabled. As a result channels that are supposed to be handled by the second ADC return invalid conversion results.

Signed-off-by: Lars-Peter Clausen lars@metafoo.de Fixes: bdc8cda1d010 ("iio:adc: Add Xilinx XADC driver") Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/iio/adc/xilinx-xadc-core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/drivers/iio/adc/xilinx-xadc-core.c +++ b/drivers/iio/adc/xilinx-xadc-core.c @@ -709,13 +709,14 @@ static int xadc_power_adc_b(struct xadc { uint16_t val;

+ /* Powerdown the ADC-B when it is not needed. */ switch (seq_mode) { case XADC_CONF1_SEQ_SIMULTANEOUS: case XADC_CONF1_SEQ_INDEPENDENT: - val = XADC_CONF2_PD_ADC_B; + val = 0; break; default: - val = 0; + val = XADC_CONF2_PD_ADC_B; break; }

From: Lars-Peter Clausen lars@metafoo.de

commit 8bef455c8b1694547ee59e8b1939205ed9d901a6 upstream.

The XADC has two internal ADCs. Depending on the mode it is operating in either one or both of them are used. The device manual calls this continuous (one ADC) and simultaneous (both ADCs) mode.

The meaning of the sequencing register for the aux channels changes depending on the mode.

In continuous mode each bit corresponds to one of the 16 aux channels. And the single ADC will convert them one by one in order.

In simultaneous mode the aux channels are split into two groups the first 8 channels are assigned to the first ADC and the other 8 channels to the second ADC. The upper 8 bits of the sequencing register are unused and the lower 8 bits control both ADCs. This means a bit needs to be set if either the corresponding channel from the first group or the second group (or both) are set.

Currently the driver does not have the special handling required for simultaneous mode. Add it.

Signed-off-by: Lars-Peter Clausen lars@metafoo.de Fixes: bdc8cda1d010 ("iio:adc: Add Xilinx XADC driver") Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/iio/adc/xilinx-xadc-core.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

--- a/drivers/iio/adc/xilinx-xadc-core.c +++ b/drivers/iio/adc/xilinx-xadc-core.c @@ -785,6 +785,16 @@ static int xadc_preenable(struct iio_dev if (ret) goto err;

+ /* + * In simultaneous mode the upper and lower aux channels are samples at + * the same time. In this mode the upper 8 bits in the sequencer + * register are don't care and the lower 8 bits control two channels + * each. As such we must set the bit if either the channel in the lower + * group or the upper group is enabled. + */ + if (seq_mode == XADC_CONF1_SEQ_SIMULTANEOUS) + scan_mask = ((scan_mask >> 8) | scan_mask) & 0xff0000; + ret = xadc_write_adc_reg(xadc, XADC_REG_SEQ(1), scan_mask >> 16); if (ret) goto err;

From: Changming Liu liu.changm@northeastern.edu

commit 2df7405f79ce1674d73c2786fe1a8727c905d65b upstream.

Change a bunch of arguments of wrapper functions which pass signed integer to an unsigned integer which might cause undefined behaviors when sign integer overflow.

Signed-off-by: Changming Liu liu.changm@northeastern.edu Cc: stable stable@vger.kernel.org Link: https://lore.kernel.org/r/BL0PR06MB45482D71EA822D75A0E60A2EE5D50@BL0PR06MB45... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/misc/sisusbvga/sisusb.c | 20 ++++++++++---------- drivers/usb/misc/sisusbvga/sisusb_init.h | 14 +++++++------- 2 files changed, 17 insertions(+), 17 deletions(-)

--- a/drivers/usb/misc/sisusbvga/sisusb.c +++ b/drivers/usb/misc/sisusbvga/sisusb.c @@ -1198,18 +1198,18 @@ static int sisusb_read_mem_bulk(struct s /* High level: Gfx (indexed) register access */

#ifdef INCL_SISUSB_CON -int sisusb_setreg(struct sisusb_usb_data *sisusb, int port, u8 data) +int sisusb_setreg(struct sisusb_usb_data *sisusb, u32 port, u8 data) { return sisusb_write_memio_byte(sisusb, SISUSB_TYPE_IO, port, data); }

-int sisusb_getreg(struct sisusb_usb_data *sisusb, int port, u8 *data) +int sisusb_getreg(struct sisusb_usb_data *sisusb, u32 port, u8 *data) { return sisusb_read_memio_byte(sisusb, SISUSB_TYPE_IO, port, data); } #endif

-int sisusb_setidxreg(struct sisusb_usb_data *sisusb, int port, +int sisusb_setidxreg(struct sisusb_usb_data *sisusb, u32 port, u8 index, u8 data) { int ret; @@ -1219,7 +1219,7 @@ int sisusb_setidxreg(struct sisusb_usb_d return ret; }

-int sisusb_getidxreg(struct sisusb_usb_data *sisusb, int port, +int sisusb_getidxreg(struct sisusb_usb_data *sisusb, u32 port, u8 index, u8 *data) { int ret; @@ -1229,7 +1229,7 @@ int sisusb_getidxreg(struct sisusb_usb_d return ret; }

-int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, int port, u8 idx, +int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, u32 port, u8 idx, u8 myand, u8 myor) { int ret; @@ -1244,7 +1244,7 @@ int sisusb_setidxregandor(struct sisusb_ }

static int sisusb_setidxregmask(struct sisusb_usb_data *sisusb, - int port, u8 idx, u8 data, u8 mask) + u32 port, u8 idx, u8 data, u8 mask) { int ret; u8 tmp; @@ -1257,13 +1257,13 @@ static int sisusb_setidxregmask(struct s return ret; }

-int sisusb_setidxregor(struct sisusb_usb_data *sisusb, int port, +int sisusb_setidxregor(struct sisusb_usb_data *sisusb, u32 port, u8 index, u8 myor) { return sisusb_setidxregandor(sisusb, port, index, 0xff, myor); }

-int sisusb_setidxregand(struct sisusb_usb_data *sisusb, int port, +int sisusb_setidxregand(struct sisusb_usb_data *sisusb, u32 port, u8 idx, u8 myand) { return sisusb_setidxregandor(sisusb, port, idx, myand, 0x00); @@ -2786,8 +2786,8 @@ static loff_t sisusb_lseek(struct file * static int sisusb_handle_command(struct sisusb_usb_data *sisusb, struct sisusb_command *y, unsigned long arg) { - int retval, port, length; - u32 address; + int retval, length; + u32 port, address;

/* All our commands require the device * to be initialized. --- a/drivers/usb/misc/sisusbvga/sisusb_init.h +++ b/drivers/usb/misc/sisusbvga/sisusb_init.h @@ -811,17 +811,17 @@ static const struct SiS_VCLKData SiSUSB_ int SiSUSBSetMode(struct SiS_Private *SiS_Pr, unsigned short ModeNo); int SiSUSBSetVESAMode(struct SiS_Private *SiS_Pr, unsigned short VModeNo);

-extern int sisusb_setreg(struct sisusb_usb_data *sisusb, int port, u8 data); -extern int sisusb_getreg(struct sisusb_usb_data *sisusb, int port, u8 * data); -extern int sisusb_setidxreg(struct sisusb_usb_data *sisusb, int port, +extern int sisusb_setreg(struct sisusb_usb_data *sisusb, u32 port, u8 data); +extern int sisusb_getreg(struct sisusb_usb_data *sisusb, u32 port, u8 * data); +extern int sisusb_setidxreg(struct sisusb_usb_data *sisusb, u32 port, u8 index, u8 data); -extern int sisusb_getidxreg(struct sisusb_usb_data *sisusb, int port, +extern int sisusb_getidxreg(struct sisusb_usb_data *sisusb, u32 port, u8 index, u8 * data); -extern int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, int port, +extern int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, u32 port, u8 idx, u8 myand, u8 myor); -extern int sisusb_setidxregor(struct sisusb_usb_data *sisusb, int port, +extern int sisusb_setidxregor(struct sisusb_usb_data *sisusb, u32 port, u8 index, u8 myor); -extern int sisusb_setidxregand(struct sisusb_usb_data *sisusb, int port, +extern int sisusb_setidxregand(struct sisusb_usb_data *sisusb, u32 port, u8 idx, u8 myand);

void sisusb_delete(struct kref *kref);

From: Jann Horn jannh@google.com

commit 7dbdb53d72a51cea9b921d9dbba54be00752212a upstream.

This fixes a bug that causes the USB3 early console to freeze after printing a single line on AMD machines because it can't parse the Transfer TRB properly.

The spec at https://www.intel.com/content/dam/www/public/us/en/documents/technical-speci... says in section "4.5.1 Device Context Index" that the Context Index, also known as Endpoint ID according to section "1.6 Terms and Abbreviations", is normally computed as `DCI = (Endpoint Number * 2) + Direction`, which matches the current definitions of XDBC_EPID_OUT and XDBC_EPID_IN.

However, the numbering in a Debug Capability Context data structure is supposed to be different: Section "7.6.3.2 Endpoint Contexts and Transfer Rings" explains that a Debug Capability Context data structure has the endpoints mapped to indices 0 and 1.

Change XDBC_EPID_OUT/XDBC_EPID_IN to the spec-compliant values, add XDBC_EPID_OUT_INTEL/XDBC_EPID_IN_INTEL with Intel's incorrect values, and let xdbc_handle_tx_event() handle both.

I have verified that with this patch applied, the USB3 early console works on both an Intel and an AMD machine.

Fixes: aeb9dd1de98c ("usb/early: Add driver for xhci debug capability") Cc: stable@vger.kernel.org Signed-off-by: Jann Horn jannh@google.com Link: https://lore.kernel.org/r/20200401074619.8024-1-jannh@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/early/xhci-dbc.c | 8 ++++---- drivers/usb/early/xhci-dbc.h | 18 ++++++++++++++++-- 2 files changed, 20 insertions(+), 6 deletions(-)

--- a/drivers/usb/early/xhci-dbc.c +++ b/drivers/usb/early/xhci-dbc.c @@ -738,19 +738,19 @@ static void xdbc_handle_tx_event(struct case COMP_USB_TRANSACTION_ERROR: case COMP_STALL_ERROR: default: - if (ep_id == XDBC_EPID_OUT) + if (ep_id == XDBC_EPID_OUT || ep_id == XDBC_EPID_OUT_INTEL) xdbc.flags |= XDBC_FLAGS_OUT_STALL; - if (ep_id == XDBC_EPID_IN) + if (ep_id == XDBC_EPID_IN || ep_id == XDBC_EPID_IN_INTEL) xdbc.flags |= XDBC_FLAGS_IN_STALL;

xdbc_trace("endpoint %d stalled\n", ep_id); break; }

- if (ep_id == XDBC_EPID_IN) { + if (ep_id == XDBC_EPID_IN || ep_id == XDBC_EPID_IN_INTEL) { xdbc.flags &= ~XDBC_FLAGS_IN_PROCESS; xdbc_bulk_transfer(NULL, XDBC_MAX_PACKET, true); - } else if (ep_id == XDBC_EPID_OUT) { + } else if (ep_id == XDBC_EPID_OUT || ep_id == XDBC_EPID_OUT_INTEL) { xdbc.flags &= ~XDBC_FLAGS_OUT_PROCESS; } else { xdbc_trace("invalid endpoint id %d\n", ep_id); --- a/drivers/usb/early/xhci-dbc.h +++ b/drivers/usb/early/xhci-dbc.h @@ -123,8 +123,22 @@ struct xdbc_ring { u32 cycle_state; };

-#define XDBC_EPID_OUT 2 -#define XDBC_EPID_IN 3 +/* + * These are the "Endpoint ID" (also known as "Context Index") values for the + * OUT Transfer Ring and the IN Transfer Ring of a Debug Capability Context data + * structure. + * According to the "eXtensible Host Controller Interface for Universal Serial + * Bus (xHCI)" specification, section "7.6.3.2 Endpoint Contexts and Transfer + * Rings", these should be 0 and 1, and those are the values AMD machines give + * you; but Intel machines seem to use the formula from section "4.5.1 Device + * Context Index", which is supposed to be used for the Device Context only. + * Luckily the values from Intel don't overlap with those from AMD, so we can + * just test for both. + */ +#define XDBC_EPID_OUT 0 +#define XDBC_EPID_IN 1 +#define XDBC_EPID_OUT_INTEL 2 +#define XDBC_EPID_IN_INTEL 3

struct xdbc_state { u16 vendor;

From: Alan Stern stern@rowland.harvard.edu

commit 9f952e26295d977dbfc6fedeaf8c4f112c818d37 upstream.

Commit 8099f58f1ecd ("USB: hub: Don't record a connect-change event during reset-resume") wasn't very well conceived. The problem it tried to fix was that if a connect-change event occurred while the system was asleep (such as a device disconnecting itself from the bus when it is suspended and then reconnecting when it resumes) requiring a reset-resume during the system wakeup transition, the hub port's change_bit entry would remain set afterward. This would cause the hub driver to believe another connect-change event had occurred after the reset-resume, which was wrong and would lead the driver to send unnecessary requests to the device (which could interfere with a firmware update).

The commit tried to fix this by not setting the change_bit during the wakeup. But this was the wrong thing to do; it means that when a device is unplugged while the system is asleep, the hub driver doesn't realize anything has happened: The change_bit flag which would tell it to handle the disconnect event is clear.

The commit needs to be reverted and the problem fixed in a different way. Fortunately an alternative solution was noted in the commit's Changelog: We can continue to set the change_bit entry in hub_activate() but then clear it when a reset-resume occurs. That way the the hub driver will see the change_bit when a device is disconnected but won't see it when the device is still present.

That's what this patch does.

Reported-and-tested-by: Peter Chen peter.chen@nxp.com Signed-off-by: Alan Stern stern@rowland.harvard.edu Fixes: 8099f58f1ecd ("USB: hub: Don't record a connect-change event during reset-resume") Tested-by: Paul Zimmerman pauldzim@gmail.com CC: stable@vger.kernel.org Link: https://lore.kernel.org/r/Pine.LNX.4.44L0.2004221602480.11262-100000@iolanth... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/core/hub.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

--- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1195,6 +1195,11 @@ static void hub_activate(struct usb_hub #ifdef CONFIG_PM udev->reset_resume = 1; #endif + /* Don't set the change_bits when the device + * was powered off. + */ + if (test_bit(port1, hub->power_bits)) + set_bit(port1, hub->change_bits);

} else { /* The power session is gone; tell hub_wq */ @@ -3008,6 +3013,15 @@ static int check_port_resume_type(struct if (portchange & USB_PORT_STAT_C_ENABLE) usb_clear_port_feature(hub->hdev, port1, USB_PORT_FEAT_C_ENABLE); + + /* + * Whatever made this reset-resume necessary may have + * turned on the port1 bit in hub->change_bits. But after + * a successful reset-resume we want the bit to be clear; + * if it was on it would indicate that something happened + * following the reset-resume. + */ + clear_bit(port1, hub->change_bits); }

return status;

From: Jann Horn jannh@google.com

commit bdebd6a2831b6fab69eb85cee74a8ba77f1a1cc2 upstream.

remap_vmalloc_range() has had various issues with the bounds checks it promises to perform ("This function checks that addr is a valid vmalloc'ed area, and that it is big enough to cover the vma") over time, e.g.:

- not detecting pgoff<<PAGE_SHIFT overflow

- not detecting (pgoff<<PAGE_SHIFT)+usize overflow

- not checking whether addr and addr+(pgoff<<PAGE_SHIFT) are the same vmalloc allocation

- comparing a potentially wildly out-of-bounds pointer with the end of the vmalloc region

In particular, since commit fc9702273e2e ("bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY"), unprivileged users can cause kernel null pointer dereferences by calling mmap() on a BPF map with a size that is bigger than the distance from the start of the BPF map to the end of the address space.

This could theoretically be used as a kernel ASLR bypass, by using whether mmap() with a given offset oopses or returns an error code to perform a binary search over the possible address range.

To allow remap_vmalloc_range_partial() to verify that addr and addr+(pgoff<<PAGE_SHIFT) are in the same vmalloc region, pass the offset to remap_vmalloc_range_partial() instead of adding it to the pointer in remap_vmalloc_range().

In remap_vmalloc_range_partial(), fix the check against get_vm_area_size() by using size comparisons instead of pointer comparisons, and add checks for pgoff.

Fixes: 833423143c3a ("[PATCH] mm: introduce remap_vmalloc_range()") Signed-off-by: Jann Horn jannh@google.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Cc: stable@vger.kernel.org Cc: Alexei Starovoitov ast@kernel.org Cc: Daniel Borkmann daniel@iogearbox.net Cc: Martin KaFai Lau kafai@fb.com Cc: Song Liu songliubraving@fb.com Cc: Yonghong Song yhs@fb.com Cc: Andrii Nakryiko andriin@fb.com Cc: John Fastabend john.fastabend@gmail.com Cc: KP Singh kpsingh@chromium.org Link: http://lkml.kernel.org/r/20200415222312.236431-1-jannh@google.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/proc/vmcore.c | 2 +- include/linux/vmalloc.h | 2 +- mm/vmalloc.c | 16 +++++++++++++--- 3 files changed, 15 insertions(+), 5 deletions(-)

--- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -459,7 +459,7 @@ static int mmap_vmcore(struct file *file tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size); kaddr = elfnotes_buf + start - elfcorebuf_sz; if (remap_vmalloc_range_partial(vma, vma->vm_start + len, - kaddr, tsz)) + kaddr, 0, tsz)) goto fail; size -= tsz; start += tsz; --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -102,7 +102,7 @@ extern void vunmap(const void *addr);

extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, - unsigned long size); + unsigned long pgoff, unsigned long size);

extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -31,6 +31,7 @@ #include <linux/compiler.h> #include <linux/llist.h> #include <linux/bitops.h> +#include <linux/overflow.h>

#include <linux/uaccess.h> #include <asm/tlbflush.h> @@ -2246,6 +2247,7 @@ finished: * @vma: vma to cover * @uaddr: target user address to start at * @kaddr: virtual address of vmalloc kernel memory + * @pgoff: offset from @kaddr to start at * @size: size of map area * * Returns: 0 for success, -Exxx on failure @@ -2258,9 +2260,15 @@ finished: * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, - void *kaddr, unsigned long size) + void *kaddr, unsigned long pgoff, + unsigned long size) { struct vm_struct *area; + unsigned long off; + unsigned long end_index; + + if (check_shl_overflow(pgoff, PAGE_SHIFT, &off)) + return -EINVAL;

size = PAGE_ALIGN(size);

@@ -2274,8 +2282,10 @@ int remap_vmalloc_range_partial(struct v if (!(area->flags & VM_USERMAP)) return -EINVAL;

- if (kaddr + size > area->addr + get_vm_area_size(area)) + if (check_add_overflow(size, off, &end_index) || + end_index > get_vm_area_size(area)) return -EINVAL; + kaddr += off;

do { struct page *page = vmalloc_to_page(kaddr); @@ -2314,7 +2324,7 @@ int remap_vmalloc_range(struct vm_area_s unsigned long pgoff) { return remap_vmalloc_range_partial(vma, vma->vm_start, - addr + (pgoff << PAGE_SHIFT), + addr, pgoff, vma->vm_end - vma->vm_start); } EXPORT_SYMBOL(remap_vmalloc_range);

From: Muchun Song songmuchun@bytedance.com

commit 56df70a63ed5d989c1d36deee94cae14342be6e9 upstream.

find_mergeable_vma() can return NULL. In this case, it leads to a crash when we access vm_mm(its offset is 0x40) later in write_protect_page. And this case did happen on our server. The following call trace is captured in kernel 4.19 with the following patch applied and KSM zero page enabled on our server.

commit e86c59b1b12d ("mm/ksm: improve deduplication of zero pages with colouring")

So add a vma check to fix it.

BUG: unable to handle kernel NULL pointer dereference at 0000000000000040 Oops: 0000 [#1] SMP NOPTI CPU: 9 PID: 510 Comm: ksmd Kdump: loaded Tainted: G OE 4.19.36.bsk.9-amd64 #4.19.36.bsk.9 RIP: try_to_merge_one_page+0xc7/0x760 Code: 24 58 65 48 33 34 25 28 00 00 00 89 e8 0f 85 a3 06 00 00 48 83 c4 60 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 8b 46 08 a8 01 75 b8 <49> 8b 44 24 40 4c 8d 7c 24 20 b9 07 00 00 00 4c 89 e6 4c 89 ff 48 RSP: 0018:ffffadbdd9fffdb0 EFLAGS: 00010246 RAX: ffffda83ffd4be08 RBX: ffffda83ffd4be40 RCX: 0000002c6e800000 RDX: 0000000000000000 RSI: ffffda83ffd4be40 RDI: 0000000000000000 RBP: ffffa11939f02ec0 R08: 0000000094e1a447 R09: 00000000abe76577 R10: 0000000000000962 R11: 0000000000004e6a R12: 0000000000000000 R13: ffffda83b1e06380 R14: ffffa18f31f072c0 R15: ffffda83ffd4be40 FS: 0000000000000000(0000) GS:ffffa0da43b80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000040 CR3: 0000002c77c0a003 CR4: 00000000007626e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: ksm_scan_thread+0x115e/0x1960 kthread+0xf5/0x130 ret_from_fork+0x1f/0x30

[songmuchun@bytedance.com: if the vma is out of date, just exit] Link: http://lkml.kernel.org/r/20200416025034.29780-1-songmuchun@bytedance.com [akpm@linux-foundation.org: add the conventional braces, replace /** with /*] Fixes: e86c59b1b12d ("mm/ksm: improve deduplication of zero pages with colouring") Co-developed-by: Xiongchun Duan duanxiongchun@bytedance.com Signed-off-by: Muchun Song songmuchun@bytedance.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Reviewed-by: David Hildenbrand david@redhat.com Reviewed-by: Kirill Tkhai ktkhai@virtuozzo.com Cc: Hugh Dickins hughd@google.com Cc: Yang Shi yang.shi@linux.alibaba.com Cc: Claudio Imbrenda imbrenda@linux.vnet.ibm.com Cc: Markus Elfring Markus.Elfring@web.de Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20200416025034.29780-1-songmuchun@bytedance.com Link: http://lkml.kernel.org/r/20200414132905.83819-1-songmuchun@bytedance.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- mm/ksm.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)

--- a/mm/ksm.c +++ b/mm/ksm.c @@ -2074,8 +2074,16 @@ static void cmp_and_merge_page(struct pa

down_read(&mm->mmap_sem); vma = find_mergeable_vma(mm, rmap_item->address); - err = try_to_merge_one_page(vma, page, - ZERO_PAGE(rmap_item->address)); + if (vma) { + err = try_to_merge_one_page(vma, page, + ZERO_PAGE(rmap_item->address)); + } else { + /* + * If the vma is out of date, we do not need to + * continue. + */ + err = 0; + } up_read(&mm->mmap_sem); /* * In case of failure, the page was not really empty, so we

From: Takashi Iwai tiwai@suse.de

commit 7686e3485253635c529cdd5f416fc640abaf076f upstream.

The error handling code in usX2Y_rate_set() may hit a potential NULL dereference when an error occurs before allocating all us->urb[]. Add a proper NULL check for fixing the corner case.

Reported-by: Lin Yi teroincn@gmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200420075529.27203-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/usb/usx2y/usbusx2yaudio.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/sound/usb/usx2y/usbusx2yaudio.c +++ b/sound/usb/usx2y/usbusx2yaudio.c @@ -689,6 +689,8 @@ static int usX2Y_rate_set(struct usX2Yde us->submitted = 2*NOOF_SETRATE_URBS; for (i = 0; i < NOOF_SETRATE_URBS; ++i) { struct urb *urb = us->urb[i]; + if (!urb) + continue; if (urb->status) { if (!err) err = -ENODEV;

From: Xiyu Yang xiyuyang19@fudan.edu.cn

commit 59e1947ca09ebd1cae147c08c7c41f3141233c84 upstream.

snd_microii_spdif_default_get() invokes snd_usb_lock_shutdown(), which increases the refcount of the snd_usb_audio object "chip".

When snd_microii_spdif_default_get() returns, local variable "chip" becomes invalid, so the refcount should be decreased to keep refcount balanced.

The reference counting issue happens in several exception handling paths of snd_microii_spdif_default_get(). When those error scenarios occur such as usb_ifnum_to_if() returns NULL, the function forgets to decrease the refcnt increased by snd_usb_lock_shutdown(), causing a refcnt leak.

Fix this issue by jumping to "end" label when those error scenarios occur.

Fixes: 447d6275f0c2 ("ALSA: usb-audio: Add sanity checks for endpoint accesses") Signed-off-by: Xiyu Yang xiyuyang19@fudan.edu.cn Signed-off-by: Xin Tan tanxin.ctf@gmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1587617711-13200-1-git-send-email-xiyuyang19@fudan... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/usb/mixer_quirks.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

--- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -1520,11 +1520,15 @@ static int snd_microii_spdif_default_get

/* use known values for that card: interface#1 altsetting#1 */ iface = usb_ifnum_to_if(chip->dev, 1); - if (!iface || iface->num_altsetting < 2) - return -EINVAL; + if (!iface || iface->num_altsetting < 2) { + err = -EINVAL; + goto end; + } alts = &iface->altsetting[1]; - if (get_iface_desc(alts)->bNumEndpoints < 1) - return -EINVAL; + if (get_iface_desc(alts)->bNumEndpoints < 1) { + err = -EINVAL; + goto end; + } ep = get_endpoint(alts, 0)->bEndpointAddress;

err = snd_usb_ctl_msg(chip->dev,

From: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com

commit b160c94be5d2816b62c8ac338605668304242959 upstream.

Call disable_interrupts() if we have to revert to polling in order not to unnecessarily reserve the IRQ for the life-cycle of the driver.

Cc: stable@vger.kernel.org # 4.5.x Reported-by: Hans de Goede hdegoede@redhat.com Fixes: e3837e74a06d ("tpm_tis: Refactor the interrupt setup") Signed-off-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/char/tpm/tpm_tis_core.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

--- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -331,6 +331,9 @@ static void disable_interrupts(struct tp u32 intmask; int rc;

+ if (priv->irq == 0) + return; + rc = tpm_tis_read32(priv, TPM_INT_ENABLE(priv->locality), &intmask); if (rc < 0) intmask = 0; @@ -874,9 +877,12 @@ int tpm_tis_core_init(struct device *dev if (irq) { tpm_tis_probe_irq_single(chip, intmask, IRQF_SHARED, irq); - if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) + if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) { dev_err(&chip->dev, FW_BUG "TPM interrupt not working, polling instead\n"); + + disable_interrupts(chip); + } } else { tpm_tis_probe_irq(chip, intmask); }

From: Sean Christopherson sean.j.christopherson@intel.com

commit b6467ab142b708dd076f6186ca274f14af379c72 upstream.

Check that the resolved slot (somewhat confusingly named 'start') is a valid/allocated slot before doing the final comparison to see if the specified gfn resides in the associated slot. The resolved slot can be invalid if the binary search loop terminated because the search index was incremented beyond the number of used slots.

This bug has existed since the binary search algorithm was introduced, but went unnoticed because KVM statically allocated memory for the max number of slots, i.e. the access would only be truly out-of-bounds if all possible slots were allocated and the specified gfn was less than the base of the lowest memslot. Commit 36947254e5f98 ("KVM: Dynamically size memslot array based on number of used slots") eliminated the "all possible slots allocated" condition and made the bug embarrasingly easy to hit.

Fixes: 9c1a5d38780e6 ("kvm: optimize GFN to memslot lookup with large slots amount") Reported-by: syzbot+d889b59b2bb87d4047a2@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Message-Id: 20200408064059.8957-2-sean.j.christopherson@intel.com Reviewed-by: Cornelia Huck cohuck@redhat.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -945,7 +945,7 @@ search_memslots(struct kvm_memslots *slo start = slot + 1; }

- if (gfn >= memslots[start].base_gfn && + if (start < slots->used_slots && gfn >= memslots[start].base_gfn && gfn < memslots[start].base_gfn + memslots[start].npages) { atomic_set(&slots->lru_slot, start); return &memslots[start];

From: Andrew Melnychenko andrew@daynix.com

commit 9a9fc42b86c06120744555fea43fdcabe297c656 upstream.

If there is a lot(more then 16) of virtio-console devices or virtio_console module is reloaded - buffers 'vtermnos' and 'cons_ops' are overflowed. In older kernels it overruns spinlock which leads to kernel freezing: https://bugzilla.redhat.com/show_bug.cgi?id=1786239

To reproduce the issue, you can try simple script that loads/unloads module. Something like this: while [ 1 ] do modprobe virtio_console sleep 2 modprobe -r virtio_console sleep 2 done

Description of problem: Guest get 'Call Trace' when loading module "virtio_console" and unloading it frequently - clearly reproduced on kernel-4.18.0:

[ 81.498208] ------------[ cut here ]------------ [ 81.499263] pvqspinlock: lock 0xffffffff92080020 has corrupted value 0xc0774ca0! [ 81.501000] WARNING: CPU: 0 PID: 785 at kernel/locking/qspinlock_paravirt.h:500 __pv_queued_spin_unlock_slowpath+0xc0/0xd0 [ 81.503173] Modules linked in: virtio_console fuse xt_CHECKSUM ipt_MASQUERADE xt_conntrack ipt_REJECT nft_counter nf_nat_tftp nft_objref nf_conntrack_tftp tun bridge stp llc nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nf_tables_set nft_chain_nat_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 nft_chain_route_ipv6 nft_chain_nat_ipv4 nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack nft_chain_route_ipv4 ip6_tables nft_compat ip_set nf_tables nfnetlink sunrpc bochs_drm drm_vram_helper ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm i2c_piix4 pcspkr crct10dif_pclmul crc32_pclmul joydev ghash_clmulni_intel ip_tables xfs libcrc32c sd_mod sg ata_generic ata_piix virtio_net libata crc32c_intel net_failover failover serio_raw virtio_scsi dm_mirror dm_region_hash dm_log dm_mod [last unloaded: virtio_console] [ 81.517019] CPU: 0 PID: 785 Comm: kworker/0:2 Kdump: loaded Not tainted 4.18.0-167.el8.x86_64 #1 [ 81.518639] Hardware name: Red Hat KVM, BIOS 1.12.0-5.scrmod+el8.2.0+5159+d8aa4d83 04/01/2014 [ 81.520205] Workqueue: events control_work_handler [virtio_console] [ 81.521354] RIP: 0010:__pv_queued_spin_unlock_slowpath+0xc0/0xd0 [ 81.522450] Code: 07 00 48 63 7a 10 e8 bf 64 f5 ff 66 90 c3 8b 05 e6 cf d6 01 85 c0 74 01 c3 8b 17 48 89 fe 48 c7 c7 38 4b 29 91 e8 3a 6c fa ff <0f> 0b c3 0f 0b 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 48 [ 81.525830] RSP: 0018:ffffb51a01ffbd70 EFLAGS: 00010282 [ 81.526798] RAX: 0000000000000000 RBX: 0000000000000010 RCX: 0000000000000000 [ 81.528110] RDX: ffff9e66f1826480 RSI: ffff9e66f1816a08 RDI: ffff9e66f1816a08 [ 81.529437] RBP: ffffffff9153ff10 R08: 000000000000026c R09: 0000000000000053 [ 81.530732] R10: 0000000000000000 R11: ffffb51a01ffbc18 R12: ffff9e66cd682200 [ 81.532133] R13: ffffffff9153ff10 R14: ffff9e6685569500 R15: ffff9e66cd682000 [ 81.533442] FS: 0000000000000000(0000) GS:ffff9e66f1800000(0000) knlGS:0000000000000000 [ 81.534914] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 81.535971] CR2: 00005624c55b14d0 CR3: 00000003a023c000 CR4: 00000000003406f0 [ 81.537283] Call Trace: [ 81.537763] __raw_callee_save___pv_queued_spin_unlock_slowpath+0x11/0x20 [ 81.539011] .slowpath+0x9/0xe [ 81.539585] hvc_alloc+0x25e/0x300 [ 81.540237] init_port_console+0x28/0x100 [virtio_console] [ 81.541251] handle_control_message.constprop.27+0x1c4/0x310 [virtio_console] [ 81.542546] control_work_handler+0x70/0x10c [virtio_console] [ 81.543601] process_one_work+0x1a7/0x3b0 [ 81.544356] worker_thread+0x30/0x390 [ 81.545025] ? create_worker+0x1a0/0x1a0 [ 81.545749] kthread+0x112/0x130 [ 81.546358] ? kthread_flush_work_fn+0x10/0x10 [ 81.547183] ret_from_fork+0x22/0x40 [ 81.547842] ---[ end trace aa97649bd16c8655 ]--- [ 83.546539] general protection fault: 0000 [#1] SMP NOPTI [ 83.547422] CPU: 5 PID: 3225 Comm: modprobe Kdump: loaded Tainted: G W --------- - - 4.18.0-167.el8.x86_64 #1 [ 83.549191] Hardware name: Red Hat KVM, BIOS 1.12.0-5.scrmod+el8.2.0+5159+d8aa4d83 04/01/2014 [ 83.550544] RIP: 0010:__pv_queued_spin_lock_slowpath+0x19a/0x2a0 [ 83.551504] Code: c4 c1 ea 12 41 be 01 00 00 00 4c 8d 6d 14 41 83 e4 03 8d 42 ff 49 c1 e4 05 48 98 49 81 c4 40 a5 02 00 4c 03 24 c5 60 48 34 91 <49> 89 2c 24 b8 00 80 00 00 eb 15 84 c0 75 0a 41 0f b6 54 24 14 84 [ 83.554449] RSP: 0018:ffffb51a0323fdb0 EFLAGS: 00010202 [ 83.555290] RAX: 000000000000301c RBX: ffffffff92080020 RCX: 0000000000000001 [ 83.556426] RDX: 000000000000301d RSI: 0000000000000000 RDI: 0000000000000000 [ 83.557556] RBP: ffff9e66f196a540 R08: 000000000000028a R09: ffff9e66d2757788 [ 83.558688] R10: 0000000000000000 R11: 0000000000000000 R12: 646e61725f770b07 [ 83.559821] R13: ffff9e66f196a554 R14: 0000000000000001 R15: 0000000000180000 [ 83.560958] FS: 00007fd5032e8740(0000) GS:ffff9e66f1940000(0000) knlGS:0000000000000000 [ 83.562233] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 83.563149] CR2: 00007fd5022b0da0 CR3: 000000038c334000 CR4: 00000000003406e0

Signed-off-by: Andrew Melnychenko andrew@daynix.com Cc: stable stable@vger.kernel.org Link: https://lore.kernel.org/r/20200414191503.3471783-1-andrew@daynix.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/tty/hvc/hvc_console.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-)

--- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -288,10 +288,6 @@ int hvc_instantiate(uint32_t vtermno, in vtermnos[index] = vtermno; cons_ops[index] = ops;

- /* reserve all indices up to and including this index */ - if (last_hvc < index) - last_hvc = index; - /* check if we need to re-register the kernel console */ hvc_check_console(index);

@@ -895,13 +891,22 @@ struct hvc_struct *hvc_alloc(uint32_t vt cons_ops[i] == hp->ops) break;

- /* no matching slot, just use a counter */ - if (i >= MAX_NR_HVC_CONSOLES) - i = ++last_hvc; + if (i >= MAX_NR_HVC_CONSOLES) { + + /* find 'empty' slot for console */ + for (i = 0; i < MAX_NR_HVC_CONSOLES && vtermnos[i] != -1; i++) { + } + + /* no matching slot, just use a counter */ + if (i == MAX_NR_HVC_CONSOLES) + i = ++last_hvc + MAX_NR_HVC_CONSOLES; + }

hp->index = i; - cons_ops[i] = ops; - vtermnos[i] = vtermno; + if (i < MAX_NR_HVC_CONSOLES) { + cons_ops[i] = ops; + vtermnos[i] = vtermno; + }

list_add_tail(&(hp->next), &hvc_structs); spin_unlock(&hvc_structs_lock);

From: Alan Stern stern@rowland.harvard.edu

commit 94f9c8c3c404ee1f7aaff81ad4f24aec4e34a78b upstream.

Cyril Roelandt reports that his JMicron JMS566 USB-SATA bridge fails to handle WRITE commands with the FUA bit set, even though it claims to support FUA. (Oddly enough, a later version of the same bridge, version 2.03 as opposed to 1.14, doesn't claim to support FUA. Also oddly, the bridge _does_ support FUA when using the UAS transport instead of the Bulk-Only transport -- but this device was blacklisted for uas in commit bc3bdb12bbb3 ("usb-storage: Disable UAS on JMicron SATA enclosure") for apparently unrelated reasons.)

This patch adds a usb-storage unusual_devs entry with the BROKEN_FUA flag. This allows the bridge to work properly with usb-storage.

Reported-and-tested-by: Cyril Roelandt tipecaml@gmail.com Signed-off-by: Alan Stern stern@rowland.harvard.edu CC: stable@vger.kernel.org Link: https://lore.kernel.org/r/Pine.LNX.4.44L0.2004221613110.11262-100000@iolanth... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/storage/unusual_devs.h | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2342,6 +2342,13 @@ UNUSUAL_DEV( 0x3340, 0xffff, 0x0000, 0x USB_SC_DEVICE,USB_PR_DEVICE,NULL, US_FL_MAX_SECTORS_64 ),

+/* Reported by Cyril Roelandt tipecaml@gmail.com */ +UNUSUAL_DEV( 0x357d, 0x7788, 0x0114, 0x0114, + "JMicron", + "USB to ATA/ATAPI Bridge", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_BROKEN_FUA ), + /* Reported by Andrey Rahmatullin wrar@altlinux.org */ UNUSUAL_DEV( 0x4102, 0x1020, 0x0100, 0x0100, "iRiver",

From: Gyeongtaek Lee gt82.lee@samsung.com

commit ebf1474745b4373fdde0fcf32d9d1f369b50b212 upstream.

snd_soc_dapm_kcontrol widget which is created by autodisable control should contain correct on_val, mask and shift because it is set when the widget is powered and changed value is applied on registers by following code in dapm_seq_run_coalesced().

mask |= w->mask << w->shift; if (w->power) value |= w->on_val << w->shift; else value |= w->off_val << w->shift;

Shift on the mask in dapm_kcontrol_data_alloc() is removed to prevent double shift. And, on_val in dapm_kcontrol_set_value() is modified to get correct value in the dapm_seq_run_coalesced().

Signed-off-by: Gyeongtaek Lee gt82.lee@samsung.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/000001d61537%24b212f620%241638e260%24@samsung.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/soc/soc-dapm.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-)

--- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -413,7 +413,7 @@ static int dapm_kcontrol_data_alloc(stru

memset(&template, 0, sizeof(template)); template.reg = e->reg; - template.mask = e->mask << e->shift_l; + template.mask = e->mask; template.shift = e->shift_l; template.off_val = snd_soc_enum_item_to_val(e, 0); template.on_val = template.off_val; @@ -539,8 +539,22 @@ static bool dapm_kcontrol_set_value(cons if (data->value == value) return false;

- if (data->widget) - data->widget->on_val = value; + if (data->widget) { + switch (dapm_kcontrol_get_wlist(kcontrol)->widgets[0]->id) { + case snd_soc_dapm_switch: + case snd_soc_dapm_mixer: + case snd_soc_dapm_mixer_named_ctl: + data->widget->on_val = value & data->widget->mask; + break; + case snd_soc_dapm_demux: + case snd_soc_dapm_mux: + data->widget->on_val = value >> data->widget->shift; + break; + default: + data->widget->on_val = value; + break; + } + }

data->value = value;

From: Ahmad Fatoum a.fatoum@pengutronix.de

commit f1baca8896ae18e12c45552a4c4ae2086aa7e02c upstream.

512a928affd5 ("ARM: imx: build v7_cpu_resume() unconditionally") introduced an unintended linker error for i.MX6 configurations that have ARM_CPU_SUSPEND=n which can happen if neither CONFIG_PM, CONFIG_CPU_IDLE, nor ARM_PSCI_FW are selected.

Fix this by having v7_cpu_resume() compiled only when cpu_resume() it calls is available as well.

The C declaration for the function remains unguarded to avoid future code inadvertently using a stub and introducing a regression to the bug the original commit fixed.

Cc: stable@vger.kernel.org Fixes: 512a928affd5 ("ARM: imx: build v7_cpu_resume() unconditionally") Reported-by: Clemens Gruber clemens.gruber@pqgruber.com Signed-off-by: Ahmad Fatoum a.fatoum@pengutronix.de Tested-by: Roland Hieber rhi@pengutronix.de Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/mach-imx/Makefile | 2 ++ 1 file changed, 2 insertions(+)

--- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -87,8 +87,10 @@ AFLAGS_suspend-imx6.o :=-Wa,-march=armv7 obj-$(CONFIG_SOC_IMX6) += suspend-imx6.o obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o endif +ifeq ($(CONFIG_ARM_CPU_SUSPEND),y) AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a obj-$(CONFIG_SOC_IMX6) += resume-imx6.o +endif obj-$(CONFIG_SOC_IMX6) += pm-imx6.o

obj-$(CONFIG_SOC_IMX1) += mach-imx1.o

From: Ian Abbott abbotti@mev.co.uk

commit ed87d33ddbcd9a1c3b5ae87995da34e6f51a862c upstream.

The DT2815 analog output command is 16 bits wide, consisting of the 12-bit sample value in bits 15 to 4, the channel number in bits 3 to 1, and a voltage or current selector in bit 0. Both bytes of the 16-bit command need to be written in turn to a single 8-bit data register. However, the driver currently only writes the low 8-bits. It is broken and appears to have always been broken.

Electronic copies of the DT2815 User's Manual seem impossible to find online, but looking at the source code, a best guess for the sequence the driver intended to use to write the analog output command is as follows:

1. Wait for the status register to read 0x00. 2. Write the low byte of the command to the data register. 3. Wait for the status register to read 0x80. 4. Write the high byte of the command to the data register.

Step 4 is missing from the driver. Add step 4 to (hopefully) fix the driver.

Also add a "FIXME" comment about setting bit 0 of the low byte of the command. Supposedly, it is used to choose between voltage output and current output, but the current driver always sets it to 1.

Signed-off-by: Ian Abbott abbotti@mev.co.uk Cc: stable stable@vger.kernel.org Link: https://lore.kernel.org/r/20200406142015.126982-1-abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/staging/comedi/drivers/dt2815.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/staging/comedi/drivers/dt2815.c +++ b/drivers/staging/comedi/drivers/dt2815.c @@ -101,6 +101,7 @@ static int dt2815_ao_insn(struct comedi_ int ret;

for (i = 0; i < insn->n; i++) { + /* FIXME: lo bit 0 chooses voltage output or current output */ lo = ((data[i] & 0x0f) << 4) | (chan << 1) | 0x01; hi = (data[i] & 0xff0) >> 4;

@@ -114,6 +115,8 @@ static int dt2815_ao_insn(struct comedi_ if (ret) return ret;

+ outb(hi, dev->iobase + DT2815_DATA); + devpriv->ao_readback[chan] = data[i]; } return i;

From: Nicolas Pitre nico@fluxnic.net

commit 2717769e204e83e65b8819c5e2ef3e5b6639b270 upstream.

The code in vc_do_resize() bounds the memory allocation size to avoid exceeding MAX_ORDER down the kzalloc() call chain and generating a runtime warning triggerable from user space. However, not only is it unwise to use a literal value here, but MAX_ORDER may also be configurable based on CONFIG_FORCE_MAX_ZONEORDER. Let's use KMALLOC_MAX_SIZE instead.

Note that prior commit bb1107f7c605 ("mm, slab: make sure that KMALLOC_MAX_SIZE will fit into MAX_ORDER") the KMALLOC_MAX_SIZE value could not be relied upon.

Signed-off-by: Nicolas Pitre nico@fluxnic.net Cc: stable@vger.kernel.org # v4.10+ Link: https://lore.kernel.org/r/nycvar.YSQ.7.76.2003281702410.2671@knanqh.ubzr Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/tty/vt/vt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -880,7 +880,7 @@ static int vc_do_resize(struct tty_struc if (new_cols == vc->vc_cols && new_rows == vc->vc_rows) return 0;

- if (new_screen_size > (4 << 20)) + if (new_screen_size > KMALLOC_MAX_SIZE) return -EINVAL; newscreen = kzalloc(new_screen_size, GFP_USER); if (!newscreen)

From: Malcolm Priestley tvboxspy@gmail.com

commit 664ba5180234593b4b8517530e8198bf2f7359e2 upstream.

vnt_set_bss_mode needs to be called on all changes to BSS_CHANGED_BASIC_RATES, BSS_CHANGED_ERP_PREAMBLE and BSS_CHANGED_ERP_SLOT

Remove all other calls and vnt_update_ifs which is called in vnt_set_bss_mode.

Fixes an issue that preamble mode is not being updated correctly.

Fixes: c12603576e06 ("staging: vt6656: Only call vnt_set_bss_mode on basic rates change.") Cc: stable stable@vger.kernel.org Signed-off-by: Malcolm Priestley tvboxspy@gmail.com Link: https://lore.kernel.org/r/44110801-6234-50d8-c583-9388f04b486c@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/staging/vt6656/main_usb.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/staging/vt6656/main_usb.c +++ b/drivers/staging/vt6656/main_usb.c @@ -594,8 +594,6 @@ static int vnt_add_interface(struct ieee

priv->op_mode = vif->type;

- vnt_set_bss_mode(priv); - /* LED blink on TX */ vnt_mac_set_led(priv, LEDSTS_STS, LEDSTS_INTER);

@@ -682,7 +680,6 @@ static void vnt_bss_info_changed(struct priv->basic_rates = conf->basic_rates;

vnt_update_top_rates(priv); - vnt_set_bss_mode(priv);

dev_dbg(&priv->usb->dev, "basic rates %x\n", conf->basic_rates); } @@ -711,11 +708,14 @@ static void vnt_bss_info_changed(struct priv->short_slot_time = false;

vnt_set_short_slot_time(priv); - vnt_update_ifs(priv); vnt_set_vga_gain_offset(priv, priv->bb_vga[0]); vnt_update_pre_ed_threshold(priv, false); }

+ if (changed & (BSS_CHANGED_BASIC_RATES | BSS_CHANGED_ERP_PREAMBLE | + BSS_CHANGED_ERP_SLOT)) + vnt_set_bss_mode(priv); + if (changed & BSS_CHANGED_TXPOWER) vnt_rf_setpower(priv, priv->current_rate, conf->chandef.chan->hw_value);

From: Malcolm Priestley tvboxspy@gmail.com

commit 0b59f10b1d8fe8d50944f21f5d403df9303095a8 upstream.

The problem is that the group key was saved as VNT_KEY_DEFAULTKEY was over written by the VNT_KEY_GROUP_ADDRESS index.

mac80211 could not clear the mac_addr in the default key.

The VNT_KEY_DEFAULTKEY is not necesscary so remove it and set as VNT_KEY_GROUP_ADDRESS.

mac80211 can clear any key using vnt_mac_disable_keyentry.

Fixes: f9ef05ce13e4 ("staging: vt6656: Fix pairwise key for non station modes") Cc: stable stable@vger.kernel.org Signed-off-by: Malcolm Priestley tvboxspy@gmail.com Link: https://lore.kernel.org/r/da2f7e7f-1658-1320-6eee-0f55770ca391@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/staging/vt6656/key.c | 14 +++----------- drivers/staging/vt6656/main_usb.c | 6 +++++- 2 files changed, 8 insertions(+), 12 deletions(-)

--- a/drivers/staging/vt6656/key.c +++ b/drivers/staging/vt6656/key.c @@ -91,9 +91,6 @@ static int vnt_set_keymode(struct ieee80 case VNT_KEY_PAIRWISE: key_mode |= mode; key_inx = 4; - /* Don't save entry for pairwise key for station mode */ - if (priv->op_mode == NL80211_IFTYPE_STATION) - clear_bit(entry, &priv->key_entry_inuse); break; default: return -EINVAL; @@ -117,7 +114,6 @@ static int vnt_set_keymode(struct ieee80 int vnt_set_keys(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct ieee80211_vif *vif, struct ieee80211_key_conf *key) { - struct ieee80211_bss_conf *conf = &vif->bss_conf; struct vnt_private *priv = hw->priv; u8 *mac_addr = NULL; u8 key_dec_mode = 0; @@ -159,16 +155,12 @@ int vnt_set_keys(struct ieee80211_hw *hw key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV; }

- if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) { + if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) vnt_set_keymode(hw, mac_addr, key, VNT_KEY_PAIRWISE, key_dec_mode, true); - } else { - vnt_set_keymode(hw, mac_addr, key, VNT_KEY_DEFAULTKEY, + else + vnt_set_keymode(hw, mac_addr, key, VNT_KEY_GROUP_ADDRESS, key_dec_mode, true);

- vnt_set_keymode(hw, (u8 *)conf->bssid, key, - VNT_KEY_GROUP_ADDRESS, key_dec_mode, true); - } - return 0; } --- a/drivers/staging/vt6656/main_usb.c +++ b/drivers/staging/vt6656/main_usb.c @@ -827,8 +827,12 @@ static int vnt_set_key(struct ieee80211_ return -EOPNOTSUPP; break; case DISABLE_KEY: - if (test_bit(key->hw_key_idx, &priv->key_entry_inuse)) + if (test_bit(key->hw_key_idx, &priv->key_entry_inuse)) { clear_bit(key->hw_key_idx, &priv->key_entry_inuse); + + vnt_mac_disable_keyentry(priv, key->hw_key_idx); + } + default: break; }

From: Oliver Neukum oneukum@suse.com

commit 0afccd7601514c4b83d8cc58c740089cc447051d upstream.

Suspend increments a counter, then kills the URBs, then kills the scheduled work. The scheduled work, however, may reschedule the URBs. Fix this by having the work check the counter.

Signed-off-by: Oliver Neukum oneukum@suse.com Cc: stable stable@vger.kernel.org Tested-by: Jonas Karlsson jonas.karlsson@actia.se Link: https://lore.kernel.org/r/20200415151358.32664-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/class/cdc-acm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -575,14 +575,14 @@ static void acm_softint(struct work_stru struct acm *acm = container_of(work, struct acm, work);

if (test_bit(EVENT_RX_STALL, &acm->flags)) { - if (!(usb_autopm_get_interface(acm->data))) { + smp_mb(); /* against acm_suspend() */ + if (!acm->susp_count) { for (i = 0; i < acm->rx_buflimit; i++) usb_kill_urb(acm->read_urbs[i]); usb_clear_halt(acm->dev, acm->in); acm_submit_read_urbs(acm, GFP_KERNEL); - usb_autopm_put_interface(acm->data); + clear_bit(EVENT_RX_STALL, &acm->flags); } - clear_bit(EVENT_RX_STALL, &acm->flags); }

if (test_and_clear_bit(EVENT_TTY_WAKEUP, &acm->flags))

From: Oliver Neukum oneukum@suse.com

commit 5963dec98dc52d52476390485f07a29c30c6a582 upstream.

Once a device is gone, the internal state does not matter anymore. There is no need to spam the logs.

Signed-off-by: Oliver Neukum oneukum@suse.com Cc: stable stable@vger.kernel.org Fixes: 326349f824619 ("uas: add dead request list") Link: https://lore.kernel.org/r/20200415141750.811-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/storage/uas.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -191,6 +191,9 @@ static void uas_log_cmd_state(struct scs struct uas_cmd_info *ci = (void *)&cmnd->SCp; struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;

+ if (status == -ENODEV) /* too late */ + return; + scmd_printk(KERN_INFO, cmnd, "%s %d uas-tag %d inflight:%s%s%s%s%s%s%s%s%s%s%s%s ", prefix, status, cmdinfo->uas_tag,

From: Udipto Goswami ugoswami@codeaurora.org

commit 1c2e54fbf1da5e5445a0ab132c862b02ccd8d230 upstream.

For userspace functions using OS Descriptors, if a function also supplies Extended Property descriptors currently the counts and lengths stored in the ms_os_descs_ext_prop_{count,name_len,data_len} variables are not getting reset to 0 during an unbind or when the epfiles are closed. If the same function is re-bound and the descriptors are re-written, this results in those count/length variables to monotonically increase causing the VLA allocation in _ffs_func_bind() to grow larger and larger at each bind/unbind cycle and eventually fail to allocate.

Fix this by clearing the ms_os_descs_ext_prop count & lengths to 0 in ffs_data_reset().

Fixes: f0175ab51993 ("usb: gadget: f_fs: OS descriptors support") Cc: stable@vger.kernel.org Signed-off-by: Udipto Goswami ugoswami@codeaurora.org Signed-off-by: Sriharsha Allenki sallenki@codeaurora.org Reviewed-by: Manu Gautam mgautam@codeaurora.org Link: https://lore.kernel.org/r/20200402044521.9312-1-sallenki@codeaurora.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/gadget/function/f_fs.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1727,6 +1727,10 @@ static void ffs_data_reset(struct ffs_da ffs->state = FFS_READ_DESCRIPTORS; ffs->setup_state = FFS_NO_SETUP; ffs->flags = 0; + + ffs->ms_os_descs_ext_prop_count = 0; + ffs->ms_os_descs_ext_prop_name_len = 0; + ffs->ms_os_descs_ext_prop_data_len = 0; }

From: Darrick J. Wong darrick.wong@oracle.com

commit 9c92ee208b1faa0ef2cc899b85fd0607b6fac7fe upstream.

Make sure the log stripe unit is sane before proceeding with mounting. AFAICT this means that logsunit has to be 0, 1, or a multiple of the fs block size. Found this by setting the LSB of logsunit in xfs/350 and watching the system crash as soon as we try to write to the log.

Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by: Brian Foster bfoster@redhat.com Signed-off-by: Suraj Jitindar Singh surajjs@amazon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/xfs_log.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)

--- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -608,6 +608,7 @@ xfs_log_mount( xfs_daddr_t blk_offset, int num_bblks) { + bool fatal = xfs_sb_version_hascrc(&mp->m_sb); int error = 0; int min_logfsbs;

@@ -659,9 +660,20 @@ xfs_log_mount( XFS_FSB_TO_B(mp, mp->m_sb.sb_logblocks), XFS_MAX_LOG_BYTES); error = -EINVAL; + } else if (mp->m_sb.sb_logsunit > 1 && + mp->m_sb.sb_logsunit % mp->m_sb.sb_blocksize) { + xfs_warn(mp, + "log stripe unit %u bytes must be a multiple of block size", + mp->m_sb.sb_logsunit); + error = -EINVAL; + fatal = true; } if (error) { - if (xfs_sb_version_hascrc(&mp->m_sb)) { + /* + * Log check errors are always fatal on v5; or whenever bad + * metadata leads to a crash. + */ + if (fatal) { xfs_crit(mp, "AAIEEE! Log failed size checks. Abort!"); ASSERT(0); goto out_free_log;

From: Clement Leger cleger@kalray.eu

commit 00a0eec59ddbb1ce966b19097d8a8d2f777e726a upstream.

Index of rvring is computed using pointer arithmetic. However, since rvring->rvdev->vring is the base of the vring array, computation of rvring idx should be reversed. It previously lead to writing at negative indices in the resource table.

Signed-off-by: Clement Leger cleger@kalray.eu Link: https://lore.kernel.org/r/20191004073736.8327-1-cleger@kalray.eu Signed-off-by: Bjorn Andersson bjorn.andersson@linaro.org Cc: Doug Anderson dianders@chromium.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/remoteproc/remoteproc_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -288,7 +288,7 @@ void rproc_free_vring(struct rproc_vring { int size = PAGE_ALIGN(vring_size(rvring->len, rvring->align)); struct rproc *rproc = rvring->rvdev->rproc; - int idx = rvring->rvdev->vring - rvring; + int idx = rvring - rvring->rvdev->vring; struct fw_rsc_vdev *rsc;

dma_free_coherent(rproc->dev.parent, size, rvring->va, rvring->dma);

From: Christian Borntraeger borntraeger@de.ibm.com

commit 467d12f5c7842896d2de3ced74e4147ee29e97c8 upstream.

QEMU has a funny new build error message when I use the upstream kernel headers:

CC block/file-posix.o In file included from /home/cborntra/REPOS/qemu/include/qemu/timer.h:4, from /home/cborntra/REPOS/qemu/include/qemu/timed-average.h:29, from /home/cborntra/REPOS/qemu/include/block/accounting.h:28, from /home/cborntra/REPOS/qemu/include/block/block_int.h:27, from /home/cborntra/REPOS/qemu/block/file-posix.c:30: /usr/include/linux/swab.h: In function `__swab': /home/cborntra/REPOS/qemu/include/qemu/bitops.h:20:34: error: "sizeof" is not defined, evaluates to 0 [-Werror=undef] 20 | #define BITS_PER_LONG (sizeof (unsigned long) * BITS_PER_BYTE) | ^~~~~~ /home/cborntra/REPOS/qemu/include/qemu/bitops.h:20:41: error: missing binary operator before token "(" 20 | #define BITS_PER_LONG (sizeof (unsigned long) * BITS_PER_BYTE) | ^ cc1: all warnings being treated as errors make: *** [/home/cborntra/REPOS/qemu/rules.mak:69: block/file-posix.o] Error 1 rm tests/qemu-iotests/socket_scm_helper.o

This was triggered by commit d5767057c9a ("uapi: rename ext2_swab() to swab() and share globally in swab.h"). That patch is doing

#include <asm/bitsperlong.h>

but it uses BITS_PER_LONG.

The kernel file asm/bitsperlong.h provide only __BITS_PER_LONG.

Let us use the __ variant in swap.h

Link: http://lkml.kernel.org/r/20200213142147.17604-1-borntraeger@de.ibm.com Fixes: d5767057c9a ("uapi: rename ext2_swab() to swab() and share globally in swab.h") Signed-off-by: Christian Borntraeger borntraeger@de.ibm.com Cc: Yury Norov yury.norov@gmail.com Cc: Allison Randal allison@lohutok.net Cc: Joe Perches joe@perches.com Cc: Thomas Gleixner tglx@linutronix.de Cc: William Breathitt Gray vilhelm.gray@gmail.com Cc: Torsten Hilbrich torsten.hilbrich@secunet.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/uapi/linux/swab.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/include/uapi/linux/swab.h +++ b/include/uapi/linux/swab.h @@ -135,9 +135,9 @@ static inline __attribute_const__ __u32

static __always_inline unsigned long __swab(const unsigned long y) { -#if BITS_PER_LONG == 64 +#if __BITS_PER_LONG == 64 return __swab64(y); -#else /* BITS_PER_LONG == 32 */ +#else /* __BITS_PER_LONG == 32 */ return __swab32(y); #endif }

From: Thinh Nguyen Thinh.Nguyen@synopsys.com

commit d0550cd20e52558ecf6847a0f96ebd5d944c17e4 upstream.

The controller always supports link recovery for device in SS and SSP. Remove the speed limit check. Also, when the device is in RESUME or RESET state, it means the controller received the resume/reset request. The driver must send the link recovery to acknowledge the request. They are valid states for the driver to send link recovery.

Fixes: 72246da40f37 ("usb: Introduce DesignWare USB3 DRD Driver") Fixes: ee5cd41c9117 ("usb: dwc3: Update speed checks for SuperSpeedPlus") Signed-off-by: Thinh Nguyen thinhn@synopsys.com Signed-off-by: Felipe Balbi balbi@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/dwc3/gadget.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-)

--- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1641,7 +1641,6 @@ static int __dwc3_gadget_wakeup(struct d u32 reg;

u8 link_state; - u8 speed;

/* * According to the Databook Remote wakeup request should @@ -1651,16 +1650,13 @@ static int __dwc3_gadget_wakeup(struct d */ reg = dwc3_readl(dwc->regs, DWC3_DSTS);

- speed = reg & DWC3_DSTS_CONNECTSPD; - if ((speed == DWC3_DSTS_SUPERSPEED) || - (speed == DWC3_DSTS_SUPERSPEED_PLUS)) - return 0; - link_state = DWC3_DSTS_USBLNKST(reg);

switch (link_state) { + case DWC3_LINK_STATE_RESET: case DWC3_LINK_STATE_RX_DET: /* in HS, means Early Suspend */ case DWC3_LINK_STATE_U3: /* in HS, means SUSPEND */ + case DWC3_LINK_STATE_RESUME: break; default: return -EINVAL;

From: YueHaibing yuehaibing@huawei.com

commit 28535877ac5b2b84f0d394fd67a5ec71c0c48b10 upstream.

It should use ad7797_attribute_group in ad7797_info, according to commit ("iio:ad7793: Add support for the ad7796 and ad7797").

Scale is fixed for the ad7796 and not programmable, hence should not have the scale_available attribute.

Fixes: fd1a8b912841 ("iio:ad7793: Add support for the ad7796 and ad7797") Signed-off-by: YueHaibing yuehaibing@huawei.com Reviewed-by: Lars-Peter Clausen lars@metafoo.de Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/iio/adc/ad7793.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/iio/adc/ad7793.c +++ b/drivers/iio/adc/ad7793.c @@ -543,7 +543,7 @@ static const struct iio_info ad7797_info .read_raw = &ad7793_read_raw, .write_raw = &ad7793_write_raw, .write_raw_get_fmt = &ad7793_write_raw_get_fmt, - .attrs = &ad7793_attribute_group, + .attrs = &ad7797_attribute_group, .validate_trigger = ad_sd_validate_trigger, .driver_module = THIS_MODULE, };

From: Wolfram Sang wsa+renesas@sang-engineering.com

commit edb2c9dd3948738ef030c32b948543e84f4d3f81 upstream.

device_property_read_u32() returns errno or 0, so we should use the integer variable 'ret' and not the u32 'val' to hold the retval.

Fixes: 0560ad576268 ("i2c: altera: Add Altera I2C Controller driver") Signed-off-by: Wolfram Sang wsa+renesas@sang-engineering.com Reviewed-by: Thor Thayer thor.thayer@linux.intel.com Signed-off-by: Wolfram Sang wsa@the-dreams.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/i2c/busses/i2c-altera.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

--- a/drivers/i2c/busses/i2c-altera.c +++ b/drivers/i2c/busses/i2c-altera.c @@ -395,7 +395,6 @@ static int altr_i2c_probe(struct platfor struct altr_i2c_dev *idev = NULL; struct resource *res; int irq, ret; - u32 val;

idev = devm_kzalloc(&pdev->dev, sizeof(*idev), GFP_KERNEL); if (!idev) @@ -422,17 +421,17 @@ static int altr_i2c_probe(struct platfor init_completion(&idev->msg_complete); spin_lock_init(&idev->lock);

- val = device_property_read_u32(idev->dev, "fifo-size", + ret = device_property_read_u32(idev->dev, "fifo-size", &idev->fifo_size); - if (val) { + if (ret) { dev_err(&pdev->dev, "FIFO size set to default of %d\n", ALTR_I2C_DFLT_FIFO_SZ); idev->fifo_size = ALTR_I2C_DFLT_FIFO_SZ; }

- val = device_property_read_u32(idev->dev, "clock-frequency", + ret = device_property_read_u32(idev->dev, "clock-frequency", &idev->bus_clk_rate); - if (val) { + if (ret) { dev_err(&pdev->dev, "Default to 100kHz\n"); idev->bus_clk_rate = 100000; /* default clock rate */ }

From: Nicolas Saenz Julienne nsaenzjulienne@suse.de

commit 90444b958461a5f8fc299ece0fe17eab15cba1e1 upstream.

Since its inception the module was meant to be disabled by default, but the original commit failed to add the relevant property.

Fixes: 4aba4cf82054 ("ARM: dts: bcm2835: Add the DSI module nodes and clocks") Signed-off-by: Nicolas Saenz Julienne nsaenzjulienne@suse.de Reviewed-by: Eric Anholt eric@anholt.net Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/boot/dts/bcm283x.dtsi | 1 + 1 file changed, 1 insertion(+)

--- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -454,6 +454,7 @@ "dsi0_ddr2", "dsi0_ddr";

+ status = "disabled"; };

thermal: thermal@7e212000 {

From: Yang Shi yang.shi@linux.alibaba.com

commit 94b7cc01da5a3cc4f3da5e0ff492ef008bb555d6 upstream.

Syzbot reported the below lockdep splat:

WARNING: possible irq lock inversion dependency detected 5.6.0-rc7-syzkaller #0 Not tainted -------------------------------------------------------- syz-executor.0/10317 just changed the state of lock: ffff888021d16568 (&(&info->lock)->rlock){+.+.}, at: spin_lock include/linux/spinlock.h:338 [inline] ffff888021d16568 (&(&info->lock)->rlock){+.+.}, at: shmem_mfill_atomic_pte+0x1012/0x21c0 mm/shmem.c:2407 but this lock was taken by another, SOFTIRQ-safe lock in the past: (&(&xa->xa_lock)->rlock#5){..-.}

and interrupts could create inverse lock ordering between them.

other info that might help us debug this: Possible interrupt unsafe locking scenario:

CPU0 CPU1 ---- ---- lock(&(&info->lock)->rlock); local_irq_disable(); lock(&(&xa->xa_lock)->rlock#5); lock(&(&info->lock)->rlock); <Interrupt> lock(&(&xa->xa_lock)->rlock#5);

*** DEADLOCK ***

The full report is quite lengthy, please see:

https://lore.kernel.org/linux-mm/alpine.LSU.2.11.2004152007370.13597@eggly.a...

It is because CPU 0 held info->lock with IRQ enabled in userfaultfd_copy path, then CPU 1 is splitting a THP which held xa_lock and info->lock in IRQ disabled context at the same time. If softirq comes in to acquire xa_lock, the deadlock would be triggered.

The fix is to acquire/release info->lock with *_irq version instead of plain spin_{lock,unlock} to make it softirq safe.

Fixes: 4c27fe4c4c84 ("userfaultfd: shmem: add shmem_mcopy_atomic_pte for userfaultfd support") Reported-by: syzbot+e27980339d305f2dbfd9@syzkaller.appspotmail.com Signed-off-by: Yang Shi yang.shi@linux.alibaba.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Tested-by: syzbot+e27980339d305f2dbfd9@syzkaller.appspotmail.com Acked-by: Hugh Dickins hughd@google.com Cc: Andrea Arcangeli aarcange@redhat.com Link: http://lkml.kernel.org/r/1587061357-122619-1-git-send-email-yang.shi@linux.a... Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- mm/shmem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/mm/shmem.c +++ b/mm/shmem.c @@ -2330,11 +2330,11 @@ static int shmem_mfill_atomic_pte(struct

lru_cache_add_anon(page);

- spin_lock(&info->lock); + spin_lock_irq(&info->lock); info->alloced++; inode->i_blocks += BLOCKS_PER_PAGE; shmem_recalc_inode(inode); - spin_unlock(&info->lock); + spin_unlock_irq(&info->lock);

inc_mm_counter(dst_mm, mm_counter_file(page)); page_add_file_rmap(page, false);

From: Olaf Hering olaf@aepfle.de

[ Upstream commit 97d9f1c43bedd400301d6f1eff54d46e8c636e47 ]

A few kernel features depend on ms_hyperv.misc_features, but unlike its siblings ->features and ->hints, the value was never reported during boot.

Signed-off-by: Olaf Hering olaf@aepfle.de Link: https://lore.kernel.org/r/20200407172739.31371-1-olaf@aepfle.de Signed-off-by: Wei Liu wei.liu@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/cpu/mshyperv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index c0201b11e9e2a..a6b323a3a6304 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -178,8 +178,8 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);

- pr_info("Hyper-V: features 0x%x, hints 0x%x\n", - ms_hyperv.features, ms_hyperv.hints); + pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n", + ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features);

ms_hyperv.max_vp_index = cpuid_eax(HVCPUID_IMPLEMENTATION_LIMITS); ms_hyperv.max_lp_index = cpuid_ebx(HVCPUID_IMPLEMENTATION_LIMITS);

From: Bodo Stroesser bstroesser@ts.fujitsu.com

[ Upstream commit 8fed04eb79a74cbf471dfaa755900a51b37273ab ]

Creation of the response to READ FULL STATUS fails for FC based reservations. Reason is the too high loop limit (< 24) in fc_get_pr_transport_id(). The string representation of FC WWPN is 23 chars long only ("11:22:33:44:55:66:77:88"). So when i is 23, the loop body is executed a last time for the ending '\0' of the string and thus hex2bin() reports an error.

Link: https://lore.kernel.org/r/20200408132610.14623-3-bstroesser@ts.fujitsu.com Signed-off-by: Bodo Stroesser bstroesser@ts.fujitsu.com Reviewed-by: Mike Christie mchristi@redhat.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/target/target_core_fabric_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c index 95aa47ac4dcd2..f8621fe673767 100644 --- a/drivers/target/target_core_fabric_lib.c +++ b/drivers/target/target_core_fabric_lib.c @@ -76,7 +76,7 @@ static int fc_get_pr_transport_id( * encoded TransportID. */ ptr = &se_nacl->initiatorname[0]; - for (i = 0; i < 24; ) { + for (i = 0; i < 23; ) { if (!strncmp(&ptr[i], ":", 1)) { i++; continue;

From: Josh Poimboeuf jpoimboe@redhat.com

[ Upstream commit 8782e7cab51b6bf01a5a86471dd82228af1ac185 ]

Historically, the relocation symbols for ORC entries have only been section symbols:

.text+0: sp:sp+8 bp:(und) type:call end:0

However, the Clang assembler is aggressive about stripping section symbols. In that case we will need to use function symbols:

freezing_slow_path+0: sp:sp+8 bp:(und) type:call end:0

In preparation for the generation of such entries in "objtool orc generate", add support for reading them in "objtool orc dump".

Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Miroslav Benes mbenes@suse.cz Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/b811b5eb1a42602c3b523576dc5efab9ad1c174d.158576102... Signed-off-by: Sasha Levin sashal@kernel.org --- tools/objtool/orc_dump.c | 44 ++++++++++++++++++++++++---------------- 1 file changed, 27 insertions(+), 17 deletions(-)

diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index c3343820916a6..7cbbbdd932f1d 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -78,7 +78,7 @@ int orc_dump(const char *_objname) char *name; size_t nr_sections; Elf64_Addr orc_ip_addr = 0; - size_t shstrtab_idx; + size_t shstrtab_idx, strtab_idx = 0; Elf *elf; Elf_Scn *scn; GElf_Shdr sh; @@ -139,6 +139,8 @@ int orc_dump(const char *_objname)

if (!strcmp(name, ".symtab")) { symtab = data; + } else if (!strcmp(name, ".strtab")) { + strtab_idx = i; } else if (!strcmp(name, ".orc_unwind")) { orc = data->d_buf; orc_size = sh.sh_size; @@ -150,7 +152,7 @@ int orc_dump(const char *_objname) } }

- if (!symtab || !orc || !orc_ip) + if (!symtab || !strtab_idx || !orc || !orc_ip) return 0;

if (orc_size % sizeof(*orc) != 0) { @@ -171,21 +173,29 @@ int orc_dump(const char *_objname) return -1; }

- scn = elf_getscn(elf, sym.st_shndx); - if (!scn) { - WARN_ELF("elf_getscn"); - return -1; - } - - if (!gelf_getshdr(scn, &sh)) { - WARN_ELF("gelf_getshdr"); - return -1; - } - - name = elf_strptr(elf, shstrtab_idx, sh.sh_name); - if (!name || !*name) { - WARN_ELF("elf_strptr"); - return -1; + if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) { + scn = elf_getscn(elf, sym.st_shndx); + if (!scn) { + WARN_ELF("elf_getscn"); + return -1; + } + + if (!gelf_getshdr(scn, &sh)) { + WARN_ELF("gelf_getshdr"); + return -1; + } + + name = elf_strptr(elf, shstrtab_idx, sh.sh_name); + if (!name) { + WARN_ELF("elf_strptr"); + return -1; + } + } else { + name = elf_strptr(elf, strtab_idx, sym.st_name); + if (!name) { + WARN_ELF("elf_strptr"); + return -1; + } }

printf("%s+%llx:", name, (unsigned long long)rela.r_addend);

From: Fangrui Song maskray@google.com

[ Upstream commit c9a4ef66450145a356a626c833d3d7b1668b3ded ]

In assembly, many instances of __emit_inst(x) expand to a directive. In a few places __emit_inst(x) is used as an assembler macro argument. For example, in arch/arm64/kvm/hyp/entry.S

ALTERNATIVE(nop, SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)

expands to the following by the C preprocessor:

alternative_insn nop, .inst (0xd500401f | ((0) << 16 | (4) << 5) | ((!!1) << 8)), 4, 1

Both comma and space are separators, with an exception that content inside a pair of parentheses/quotes is not split, so the clang integrated assembler splits the arguments to:

nop, .inst, (0xd500401f | ((0) << 16 | (4) << 5) | ((!!1) << 8)), 4, 1

GNU as preprocesses the input with do_scrub_chars(). Its arm64 backend (along with many other non-x86 backends) sees:

alternative_insn nop,.inst(0xd500401f|((0)<<16|(4)<<5)|((!!1)<<8)),4,1 # .inst(...) is parsed as one argument

while its x86 backend sees:

alternative_insn nop,.inst (0xd500401f|((0)<<16|(4)<<5)|((!!1)<<8)),4,1 # The extra space before '(' makes the whole .inst (...) parsed as two arguments

The non-x86 backend's behavior is considered unintentional (https://sourceware.org/bugzilla/show_bug.cgi?id=25750). So drop the space separator inside `.inst (...)` to make the clang integrated assembler work.

Suggested-by: Ilie Halip ilie.halip@gmail.com Signed-off-by: Fangrui Song maskray@google.com Reviewed-by: Mark Rutland mark.rutland@arm.com Link: https://github.com/ClangBuiltLinux/linux/issues/939 Signed-off-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/include/asm/sysreg.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 50a89bcf9072e..2564dd429ab68 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -60,7 +60,9 @@ #ifndef CONFIG_BROKEN_GAS_INST

#ifdef __ASSEMBLY__ -#define __emit_inst(x) .inst (x) +// The space separator is omitted so that __emit_inst(x) can be parsed as +// either an assembler directive or an assembler macro argument. +#define __emit_inst(x) .inst(x) #else #define __emit_inst(x) ".inst " __stringify((x)) "\n\t" #endif

From: Theodore Ts'o tytso@mit.edu

[ Upstream commit a17a9d935dc4a50acefaf319d58030f1da7f115a ]

Current wait times have proven to be too short to protect against inode reuses that lead to metadata inconsistencies.

Now that we will retry the inode allocation if we can't find any recently deleted inodes, it's a lot safer to increase the recently deleted time from 5 seconds to a minute.

Link: https://lore.kernel.org/r/20200414023925.273867-1-tytso@mit.edu Google-Bug-Id: 36602237 Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/ialloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 2a480c0ef1bc1..96efe53855a0b 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -673,7 +673,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent, * block has been written back to disk. (Yes, these values are * somewhat arbitrary...) */ -#define RECENTCY_MIN 5 +#define RECENTCY_MIN 60 #define RECENTCY_DIRTY 300

static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)

From: Frank Rowand frank.rowand@sony.com

[ Upstream commit b3fb36ed694b05738d45218ea72cf7feb10ce2b1 ]

kmemleak reports several memory leaks from devicetree unittest. This is the fix for problem 1 of 5.

of_unittest_changeset() reaches deeply into the dynamic devicetree functions. Several nodes were left with an elevated reference count and thus were not properly cleaned up. Fix the reference counts so that the memory will be freed.

Fixes: 201c910bd689 ("of: Transactional DT support.") Reported-by: Erhard F. erhard_f@mailbox.org Signed-off-by: Frank Rowand frank.rowand@sony.com Signed-off-by: Rob Herring robh@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/of/unittest.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 55c98f119df22..e7e6dd07f2150 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -605,6 +605,10 @@ static void __init of_unittest_changeset(void) unittest(!of_changeset_revert(&chgset), "revert failed\n");

of_changeset_destroy(&chgset); + + of_node_put(n1); + of_node_put(n2); + of_node_put(n21); #endif }

From: Theodore Ts'o tytso@mit.edu

commit 8a363970d1dc38c4ec4ad575c862f776f468d057 upstream.

If we receive a file handle, either from NFS or open_by_handle_at(2), and it points at an inode which has not been initialized, and the file system has metadata checksums enabled, we shouldn't try to get the inode, discover the checksum is invalid, and then declare the file system as being inconsistent.

This can be reproduced by creating a test file system via "mke2fs -t ext4 -O metadata_csum /tmp/foo.img 8M", mounting it, cd'ing into that directory, and then running the following program.

#define _GNU_SOURCE #include <fcntl.h>

struct handle { struct file_handle fh; unsigned char fid[MAX_HANDLE_SZ]; };

int main(int argc, char **argv) { struct handle h = {{8, 1 }, { 12, }};

open_by_handle_at(AT_FDCWD, &h.fh, O_RDONLY); return 0; }

Google-Bug-Id: 120690101 Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Ashwin H ashwinh@vmware.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ext4/ext4.h | 15 +++++++++++++-- fs/ext4/ialloc.c | 2 +- fs/ext4/inode.c | 49 ++++++++++++++++++++++++++++++++++--------------- fs/ext4/ioctl.c | 2 +- fs/ext4/namei.c | 4 ++-- fs/ext4/resize.c | 5 +++-- fs/ext4/super.c | 19 +++++-------------- fs/ext4/xattr.c | 5 +++-- 8 files changed, 62 insertions(+), 39 deletions(-)

--- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2509,8 +2509,19 @@ int do_journal_get_write_access(handle_t #define FALL_BACK_TO_NONDELALLOC 1 #define CONVERT_INLINE_DATA 2

-extern struct inode *ext4_iget(struct super_block *, unsigned long); -extern struct inode *ext4_iget_normal(struct super_block *, unsigned long); +typedef enum { + EXT4_IGET_NORMAL = 0, + EXT4_IGET_SPECIAL = 0x0001, /* OK to iget a system inode */ + EXT4_IGET_HANDLE = 0x0002 /* Inode # is from a handle */ +} ext4_iget_flags; + +extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, + ext4_iget_flags flags, const char *function, + unsigned int line); + +#define ext4_iget(sb, ino, flags) \ + __ext4_iget((sb), (ino), (flags), __func__, __LINE__) + extern int ext4_write_inode(struct inode *, struct writeback_control *); extern int ext4_setattr(struct dentry *, struct iattr *); extern int ext4_getattr(const struct path *, struct kstat *, u32, unsigned int); --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1239,7 +1239,7 @@ struct inode *ext4_orphan_get(struct sup if (!ext4_test_bit(bit, bitmap_bh->b_data)) goto bad_orphan;

- inode = ext4_iget(sb, ino); + inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error(sb, "couldn't read orphan inode %lu (err %d)", --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4695,7 +4695,9 @@ int ext4_get_projid(struct inode *inode, return 0; }

-struct inode *ext4_iget(struct super_block *sb, unsigned long ino) +struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, + ext4_iget_flags flags, const char *function, + unsigned int line) { struct ext4_iloc iloc; struct ext4_inode *raw_inode; @@ -4709,6 +4711,18 @@ struct inode *ext4_iget(struct super_blo gid_t i_gid; projid_t i_projid;

+ if (((flags & EXT4_IGET_NORMAL) && + (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)) || + (ino < EXT4_ROOT_INO) || + (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))) { + if (flags & EXT4_IGET_HANDLE) + return ERR_PTR(-ESTALE); + __ext4_error(sb, function, line, + "inode #%lu: comm %s: iget: illegal inode #", + ino, current->comm); + return ERR_PTR(-EFSCORRUPTED); + } + inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); @@ -4724,18 +4738,26 @@ struct inode *ext4_iget(struct super_blo raw_inode = ext4_raw_inode(&iloc);

if ((ino == EXT4_ROOT_INO) && (raw_inode->i_links_count == 0)) { - EXT4_ERROR_INODE(inode, "root inode unallocated"); + ext4_error_inode(inode, function, line, 0, + "iget: root inode unallocated"); ret = -EFSCORRUPTED; goto bad_inode; }

+ if ((flags & EXT4_IGET_HANDLE) && + (raw_inode->i_links_count == 0) && (raw_inode->i_mode == 0)) { + ret = -ESTALE; + goto bad_inode; + } + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > EXT4_INODE_SIZE(inode->i_sb) || (ei->i_extra_isize & 3)) { - EXT4_ERROR_INODE(inode, - "bad extra_isize %u (inode size %u)", + ext4_error_inode(inode, function, line, 0, + "iget: bad extra_isize %u " + "(inode size %u)", ei->i_extra_isize, EXT4_INODE_SIZE(inode->i_sb)); ret = -EFSCORRUPTED; @@ -4757,7 +4779,8 @@ struct inode *ext4_iget(struct super_blo }

if (!ext4_inode_csum_verify(inode, raw_inode, ei)) { - EXT4_ERROR_INODE(inode, "checksum invalid"); + ext4_error_inode(inode, function, line, 0, + "iget: checksum invalid"); ret = -EFSBADCRC; goto bad_inode; } @@ -4813,7 +4836,8 @@ struct inode *ext4_iget(struct super_blo ((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32; inode->i_size = ext4_isize(sb, raw_inode); if ((size = i_size_read(inode)) < 0) { - EXT4_ERROR_INODE(inode, "bad i_size value: %lld", size); + ext4_error_inode(inode, function, line, 0, + "iget: bad i_size value: %lld", size); ret = -EFSCORRUPTED; goto bad_inode; } @@ -4899,7 +4923,8 @@ struct inode *ext4_iget(struct super_blo ret = 0; if (ei->i_file_acl && !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) { - EXT4_ERROR_INODE(inode, "bad extended attribute block %llu", + ext4_error_inode(inode, function, line, 0, + "iget: bad extended attribute block %llu", ei->i_file_acl); ret = -EFSCORRUPTED; goto bad_inode; @@ -4954,7 +4979,8 @@ struct inode *ext4_iget(struct super_blo make_bad_inode(inode); } else { ret = -EFSCORRUPTED; - EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode); + ext4_error_inode(inode, function, line, 0, + "iget: bogus i_mode (%o)", inode->i_mode); goto bad_inode; } brelse(iloc.bh); @@ -4969,13 +4995,6 @@ bad_inode: return ERR_PTR(ret); }

-struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino) -{ - if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) - return ERR_PTR(-EFSCORRUPTED); - return ext4_iget(sb, ino); -} - static int ext4_inode_blocks_set(handle_t *handle, struct ext4_inode *raw_inode, struct ext4_inode_info *ei) --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -111,7 +111,7 @@ static long swap_inode_boot_loader(struc if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) return -EPERM;

- inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO); + inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL); if (IS_ERR(inode_bl)) return PTR_ERR(inode_bl); ei_bl = EXT4_I(inode_bl); --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1597,7 +1597,7 @@ static struct dentry *ext4_lookup(struct dentry); return ERR_PTR(-EFSCORRUPTED); } - inode = ext4_iget_normal(dir->i_sb, ino); + inode = ext4_iget(dir->i_sb, ino, EXT4_IGET_NORMAL); if (inode == ERR_PTR(-ESTALE)) { EXT4_ERROR_INODE(dir, "deleted inode referenced: %u", @@ -1639,7 +1639,7 @@ struct dentry *ext4_get_parent(struct de return ERR_PTR(-EFSCORRUPTED); }

- return d_obtain_alias(ext4_iget_normal(child->d_sb, ino)); + return d_obtain_alias(ext4_iget(child->d_sb, ino, EXT4_IGET_NORMAL)); }

/* --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1652,7 +1652,7 @@ int ext4_group_add(struct super_block *s "No reserved GDT blocks, can't resize"); return -EPERM; } - inode = ext4_iget(sb, EXT4_RESIZE_INO); + inode = ext4_iget(sb, EXT4_RESIZE_INO, EXT4_IGET_SPECIAL); if (IS_ERR(inode)) { ext4_warning(sb, "Error opening resize inode"); return PTR_ERR(inode); @@ -1980,7 +1980,8 @@ retry: }

if (!resize_inode) - resize_inode = ext4_iget(sb, EXT4_RESIZE_INO); + resize_inode = ext4_iget(sb, EXT4_RESIZE_INO, + EXT4_IGET_SPECIAL); if (IS_ERR(resize_inode)) { ext4_warning(sb, "Error opening resize inode"); return PTR_ERR(resize_inode); --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1126,20 +1126,11 @@ static struct inode *ext4_nfs_get_inode( { struct inode *inode;

- if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) - return ERR_PTR(-ESTALE); - if (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)) - return ERR_PTR(-ESTALE); - - /* iget isn't really right if the inode is currently unallocated!! - * - * ext4_read_inode will return a bad_inode if the inode had been - * deleted, so we should be safe. - * + /* * Currently we don't know the generation for parent directory, so * a generation of 0 means "accept any" */ - inode = ext4_iget_normal(sb, ino); + inode = ext4_iget(sb, ino, EXT4_IGET_HANDLE); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation && inode->i_generation != generation) { @@ -4370,7 +4361,7 @@ no_journal: * so we can safely mount the rest of the filesystem now. */

- root = ext4_iget(sb, EXT4_ROOT_INO); + root = ext4_iget(sb, EXT4_ROOT_INO, EXT4_IGET_SPECIAL); if (IS_ERR(root)) { ext4_msg(sb, KERN_ERR, "get root inode failed"); ret = PTR_ERR(root); @@ -4620,7 +4611,7 @@ static struct inode *ext4_get_journal_in * happen if we iget() an unused inode, as the subsequent iput() * will try to delete it. */ - journal_inode = ext4_iget(sb, journal_inum); + journal_inode = ext4_iget(sb, journal_inum, EXT4_IGET_SPECIAL); if (IS_ERR(journal_inode)) { ext4_msg(sb, KERN_ERR, "no journal found"); return NULL; @@ -5693,7 +5684,7 @@ static int ext4_quota_enable(struct supe if (!qf_inums[type]) return -EPERM;

- qf_inode = ext4_iget(sb, qf_inums[type]); + qf_inode = ext4_iget(sb, qf_inums[type], EXT4_IGET_SPECIAL); if (IS_ERR(qf_inode)) { ext4_error(sb, "Bad quota inode # %lu", qf_inums[type]); return PTR_ERR(qf_inode); --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -383,7 +383,7 @@ static int ext4_xattr_inode_iget(struct struct inode *inode; int err;

- inode = ext4_iget(parent->i_sb, ea_ino); + inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error(parent->i_sb, @@ -1486,7 +1486,8 @@ ext4_xattr_inode_cache_find(struct inode }

while (ce) { - ea_inode = ext4_iget(inode->i_sb, ce->e_value); + ea_inode = ext4_iget(inode->i_sb, ce->e_value, + EXT4_IGET_NORMAL); if (!IS_ERR(ea_inode) && !is_bad_inode(ea_inode) && (EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) &&

From: Theodore Ts'o tytso@mit.edu

commit 0a944e8a6c66ca04c7afbaa17e22bf208a8b37f0 upstream.

Since the journal inode is already checked when we added it to the block validity's system zone, if we check it again, we'll just trigger a failure.

This was causing failures like this:

[ 53.897001] EXT4-fs error (device sda): ext4_find_extent:909: inode #8: comm jbd2/sda-8: pblk 121667583 bad header/extent: invalid extent entries - magic f30a, entries 8, max 340(340), depth 0(0) [ 53.931430] jbd2_journal_bmap: journal block not found at offset 49 on sda-8 [ 53.938480] Aborting journal on device sda-8.

... but only if the system was under enough memory pressure that logical->physical mapping for the journal inode gets pushed out of the extent cache. (This is why it wasn't noticed earlier.)

Fixes: 345c0dbf3a30 ("ext4: protect journal inode's blocks using block_validity") Reported-by: Dan Rue dan.rue@linaro.org Signed-off-by: Theodore Ts'o tytso@mit.edu Tested-by: Naresh Kamboju naresh.kamboju@linaro.org Signed-off-by: Ashwin H ashwinh@vmware.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ext4/extents.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

--- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -554,10 +554,14 @@ __read_extent_tree_block(const char *fun } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; - err = __ext4_ext_check(function, line, inode, - ext_block_hdr(bh), depth, pblk); - if (err) - goto errout; + if (!ext4_has_feature_journal(inode->i_sb) || + (inode->i_ino != + le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) { + err = __ext4_ext_check(function, line, inode, + ext_block_hdr(bh), depth, pblk); + if (err) + goto errout; + } set_buffer_verified(bh); /* * If this is a leaf block, cache all of its entries

From: Colin Ian King colin.king@canonical.com

commit fbbbbd2f28aec991f3fbc248df211550fbdfd58c upstream.

There are two cases where u32 variables n and err are being checked for less than zero error values, the checks is always false because the variables are not signed. Fix this by making the variables ints.

Addresses-Coverity: ("Unsigned compared against 0") Fixes: 345c0dbf3a30 ("ext4: protect journal inode's blocks using block_validity") Signed-off-by: Colin Ian King colin.king@canonical.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Ashwin H ashwinh@vmware.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ext4/block_validity.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -142,7 +142,8 @@ static int ext4_protect_reserved_inode(s struct inode *inode; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_map_blocks map; - u32 i = 0, err = 0, num, n; + u32 i = 0, num; + int err = 0, n;

if ((ino < EXT4_ROOT_INO) || (ino > le32_to_cpu(sbi->s_es->s_inodes_count)))

From: Ritesh Harjani riteshh@linux.ibm.com

commit f1eec3b0d0a849996ebee733b053efa71803dad5 upstream.

While calculating overhead for internal journal, also check that j_inum shouldn't be 0. Otherwise we get below error with xfstests generic/050 with external journal (XXX_LOGDEV config) enabled.

It could be simply reproduced with loop device with an external journal and marking blockdev as RO before mounting.

[ 3337.146838] EXT4-fs error (device pmem1p2): ext4_get_journal_inode:4634: comm mount: inode #0: comm mount: iget: illegal inode # ------------[ cut here ]------------ generic_make_request: Trying to write to read-only block-device pmem1p2 (partno 2) WARNING: CPU: 107 PID: 115347 at block/blk-core.c:788 generic_make_request_checks+0x6b4/0x7d0 CPU: 107 PID: 115347 Comm: mount Tainted: G L --------- -t - 4.18.0-167.el8.ppc64le #1 NIP: c0000000006f6d44 LR: c0000000006f6d40 CTR: 0000000030041dd4 <...> NIP [c0000000006f6d44] generic_make_request_checks+0x6b4/0x7d0 LR [c0000000006f6d40] generic_make_request_checks+0x6b0/0x7d0 <...> Call Trace: generic_make_request_checks+0x6b0/0x7d0 (unreliable) generic_make_request+0x3c/0x420 submit_bio+0xd8/0x200 submit_bh_wbc+0x1e8/0x250 __sync_dirty_buffer+0xd0/0x210 ext4_commit_super+0x310/0x420 [ext4] __ext4_error+0xa4/0x1e0 [ext4] __ext4_iget+0x388/0xe10 [ext4] ext4_get_journal_inode+0x40/0x150 [ext4] ext4_calculate_overhead+0x5a8/0x610 [ext4] ext4_fill_super+0x3188/0x3260 [ext4] mount_bdev+0x778/0x8f0 ext4_mount+0x28/0x50 [ext4] mount_fs+0x74/0x230 vfs_kern_mount.part.6+0x6c/0x250 do_mount+0x2fc/0x1280 sys_mount+0x158/0x180 system_call+0x5c/0x70 EXT4-fs (pmem1p2): no journal found EXT4-fs (pmem1p2): can't get journal size EXT4-fs (pmem1p2): mounted filesystem without journal. Opts: dax,norecovery

Fixes: 3c816ded78bb ("ext4: use journal inode to determine journal overhead") Reported-by: Harish Sriram harish@linux.ibm.com Signed-off-by: Ritesh Harjani riteshh@linux.ibm.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20200316093038.25485-1-riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ext4/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3456,7 +3456,8 @@ int ext4_calculate_overhead(struct super */ if (sbi->s_journal && !sbi->journal_bdev) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen); - else if (ext4_has_feature_journal(sb) && !sbi->s_journal) { + else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { + /* j_inum for internal journal is non-zero */ j_inode = ext4_get_journal_inode(sb, j_inum); if (j_inode) { j_blocks = j_inode->i_size >> sb->s_blocksize_bits;