From: Takashi Iwai tiwai@suse.de

[ Upstream commit 2eabc5ec8ab4d4748a82050dfcb994119b983750 ]

The snd_seq_ioctl_get_subscription() retrieves the port subscriber information as a pointer, while the object isn't protected, hence it may be deleted before the actual reference. This race was spotted by syzkaller and may lead to a UAF.

The fix is simply copying the data in the lookup function that performs in the rwsem to protect against the deletion.

Reported-by: syzbot+9437020c82413d00222d@syzkaller.appspotmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/core/seq/seq_clientmgr.c | 10 ++-------- sound/core/seq/seq_ports.c | 13 ++++++++----- sound/core/seq/seq_ports.h | 5 +++-- 3 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 3b1b2e9fb33e..881c965555c5 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1905,20 +1905,14 @@ static int snd_seq_ioctl_get_subscription(struct snd_seq_client *client, int result; struct snd_seq_client *sender = NULL; struct snd_seq_client_port *sport = NULL; - struct snd_seq_subscribers *p;

result = -EINVAL; if ((sender = snd_seq_client_use_ptr(subs->sender.client)) == NULL) goto __end; if ((sport = snd_seq_port_use_ptr(sender, subs->sender.port)) == NULL) goto __end; - p = snd_seq_port_get_subscription(&sport->c_src, &subs->dest); - if (p) { - result = 0; - *subs = p->info; - } else - result = -ENOENT; - + result = snd_seq_port_get_subscription(&sport->c_src, &subs->dest, + subs); __end: if (sport) snd_seq_port_unlock(sport); diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index f04714d70bf7..faf7ceffbeca 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -635,20 +635,23 @@ int snd_seq_port_disconnect(struct snd_seq_client *connector,

/* get matched subscriber */ -struct snd_seq_subscribers *snd_seq_port_get_subscription(struct snd_seq_port_subs_info *src_grp, - struct snd_seq_addr *dest_addr) +int snd_seq_port_get_subscription(struct snd_seq_port_subs_info *src_grp, + struct snd_seq_addr *dest_addr, + struct snd_seq_port_subscribe *subs) { - struct snd_seq_subscribers *s, *found = NULL; + struct snd_seq_subscribers *s; + int err = -ENOENT;

down_read(&src_grp->list_mutex); list_for_each_entry(s, &src_grp->list_head, src_list) { if (addr_match(dest_addr, &s->info.dest)) { - found = s; + *subs = s->info; + err = 0; break; } } up_read(&src_grp->list_mutex); - return found; + return err; }

/* diff --git a/sound/core/seq/seq_ports.h b/sound/core/seq/seq_ports.h index 26bd71f36c41..06003b36652e 100644 --- a/sound/core/seq/seq_ports.h +++ b/sound/core/seq/seq_ports.h @@ -135,7 +135,8 @@ int snd_seq_port_subscribe(struct snd_seq_client_port *port, struct snd_seq_port_subscribe *info);

/* get matched subscriber */ -struct snd_seq_subscribers *snd_seq_port_get_subscription(struct snd_seq_port_subs_info *src_grp, - struct snd_seq_addr *dest_addr); +int snd_seq_port_get_subscription(struct snd_seq_port_subs_info *src_grp, + struct snd_seq_addr *dest_addr, + struct snd_seq_port_subscribe *subs);

#endif

From: Takashi Iwai tiwai@suse.de

[ Upstream commit 7c32ae35fbf9cffb7aa3736f44dec10c944ca18e ]

The call of unsubscribe_port() which manages the group count and module refcount from delete_and_unsubscribe_port() looks racy; it's not covered by the group list lock, and it's likely a cause of the reported unbalance at port deletion. Let's move the call inside the group list_mutex to plug the hole.

Reported-by: syzbot+e4c8abb920efa77bace9@syzkaller.appspotmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/core/seq/seq_ports.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index faf7ceffbeca..9cfe4fcee9a5 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -550,10 +550,10 @@ static void delete_and_unsubscribe_port(struct snd_seq_client *client, list_del_init(list); grp->exclusive = 0; write_unlock_irq(&grp->list_lock); - up_write(&grp->list_mutex);

if (!empty) unsubscribe_port(client, port, grp, &subs->info, ack); + up_write(&grp->list_mutex); }

/* connect two ports */

From: Young Xiao YangX92@hotmail.com

[ Upstream commit b281218ad4311a0342a40cb02fb17a363df08b48 ]

There is an out-of-bounds access to "config[len - 1]" array when the variable "len" is zero.

See commit dada6a43b040 ("kgdboc: fix KASAN global-out-of-bounds bug in param_set_kgdboc_var()") for details.

Signed-off-by: Young Xiao YangX92@hotmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/misc/kgdbts.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c index 99635dd9dbac..bb3a76ad80da 100644 --- a/drivers/misc/kgdbts.c +++ b/drivers/misc/kgdbts.c @@ -1132,7 +1132,7 @@ static void kgdbts_put_char(u8 chr)

static int param_set_kgdbts_var(const char *kmessage, struct kernel_param *kp) { - int len = strlen(kmessage); + size_t len = strlen(kmessage);

if (len >= MAX_CONFIG_LEN) { printk(KERN_ERR "kgdbts: config string too long\n"); @@ -1152,7 +1152,7 @@ static int param_set_kgdbts_var(const char *kmessage, struct kernel_param *kp)

strcpy(config, kmessage); /* Chop out \n char as a result of echo */ - if (config[len - 1] == '\n') + if (len && config[len - 1] == '\n') config[len - 1] = '\0';

/* Go and configure with the new params. */

From: Li Rongqing lirongqing@baidu.com

[ Upstream commit d6a2946a88f524a47cc9b79279667137899db807 ]

msgctl10 of ltp triggers the following lockup When CONFIG_KASAN is enabled on large memory SMP systems, the pages initialization can take a long time, if msgctl10 requests a huge block memory, and it will block rcu scheduler, so release cpu actively.

After adding schedule() in free_msg, free_msg can not be called when holding spinlock, so adding msg to a tmp list, and free it out of spinlock

rcu: INFO: rcu_preempt detected stalls on CPUs/tasks: rcu: Tasks blocked on level-1 rcu_node (CPUs 16-31): P32505 rcu: Tasks blocked on level-1 rcu_node (CPUs 48-63): P34978 rcu: (detected by 11, t=35024 jiffies, g=44237529, q=16542267) msgctl10 R running task 21608 32505 2794 0x00000082 Call Trace: preempt_schedule_irq+0x4c/0xb0 retint_kernel+0x1b/0x2d RIP: 0010:__is_insn_slot_addr+0xfb/0x250 Code: 82 1d 00 48 8b 9b 90 00 00 00 4c 89 f7 49 c1 ee 03 e8 59 83 1d 00 48 b8 00 00 00 00 00 fc ff df 4c 39 eb 48 89 9d 58 ff ff ff <41> c6 04 06 f8 74 66 4c 8d 75 98 4c 89 f1 48 c1 e9 03 48 01 c8 48 RSP: 0018:ffff88bce041f758 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: dffffc0000000000 RBX: ffffffff8471bc50 RCX: ffffffff828a2a57 RDX: dffffc0000000000 RSI: dffffc0000000000 RDI: ffff88bce041f780 RBP: ffff88bce041f828 R08: ffffed15f3f4c5b3 R09: ffffed15f3f4c5b3 R10: 0000000000000001 R11: ffffed15f3f4c5b2 R12: 000000318aee9b73 R13: ffffffff8471bc50 R14: 1ffff1179c083ef0 R15: 1ffff1179c083eec kernel_text_address+0xc1/0x100 __kernel_text_address+0xe/0x30 unwind_get_return_address+0x2f/0x50 __save_stack_trace+0x92/0x100 create_object+0x380/0x650 __kmalloc+0x14c/0x2b0 load_msg+0x38/0x1a0 do_msgsnd+0x19e/0xcf0 do_syscall_64+0x117/0x400 entry_SYSCALL_64_after_hwframe+0x49/0xbe

rcu: INFO: rcu_preempt detected stalls on CPUs/tasks: rcu: Tasks blocked on level-1 rcu_node (CPUs 0-15): P32170 rcu: (detected by 14, t=35016 jiffies, g=44237525, q=12423063) msgctl10 R running task 21608 32170 32155 0x00000082 Call Trace: preempt_schedule_irq+0x4c/0xb0 retint_kernel+0x1b/0x2d RIP: 0010:lock_acquire+0x4d/0x340 Code: 48 81 ec c0 00 00 00 45 89 c6 4d 89 cf 48 8d 6c 24 20 48 89 3c 24 48 8d bb e4 0c 00 00 89 74 24 0c 48 c7 44 24 20 b3 8a b5 41 <48> c1 ed 03 48 c7 44 24 28 b4 25 18 84 48 c7 44 24 30 d0 54 7a 82 RSP: 0018:ffff88af83417738 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13 RAX: dffffc0000000000 RBX: ffff88bd335f3080 RCX: 0000000000000002 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88bd335f3d64 RBP: ffff88af83417758 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: ffffed13f3f745b2 R12: 0000000000000000 R13: 0000000000000002 R14: 0000000000000000 R15: 0000000000000000 is_bpf_text_address+0x32/0xe0 kernel_text_address+0xec/0x100 __kernel_text_address+0xe/0x30 unwind_get_return_address+0x2f/0x50 __save_stack_trace+0x92/0x100 save_stack+0x32/0xb0 __kasan_slab_free+0x130/0x180 kfree+0xfa/0x2d0 free_msg+0x24/0x50 do_msgrcv+0x508/0xe60 do_syscall_64+0x117/0x400 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Davidlohr said: "So after releasing the lock, the msg rbtree/list is empty and new calls will not see those in the newly populated tmp_msg list, and therefore they cannot access the delayed msg freeing pointers, which is good. Also the fact that the node_cache is now freed before the actual messages seems to be harmless as this is wanted for msg_insert() avoiding GFP_ATOMIC allocations, and after releasing the info->lock the thing is freed anyway so it should not change things"

Link: http://lkml.kernel.org/r/1552029161-4957-1-git-send-email-lirongqing@baidu.c... Signed-off-by: Li RongQing lirongqing@baidu.com Signed-off-by: Zhang Yu zhangyu31@baidu.com Reviewed-by: Davidlohr Bueso dbueso@suse.de Cc: Manfred Spraul manfred@colorfullife.com Cc: Arnd Bergmann arnd@arndb.de Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- ipc/mqueue.c | 10 ++++++++-- ipc/msgutil.c | 6 ++++++ 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 28a142f1be36..d5491a880751 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -371,7 +371,8 @@ static void mqueue_evict_inode(struct inode *inode) struct user_struct *user; unsigned long mq_bytes, mq_treesize; struct ipc_namespace *ipc_ns; - struct msg_msg *msg; + struct msg_msg *msg, *nmsg; + LIST_HEAD(tmp_msg);

clear_inode(inode);

@@ -382,10 +383,15 @@ static void mqueue_evict_inode(struct inode *inode) info = MQUEUE_I(inode); spin_lock(&info->lock); while ((msg = msg_get(info)) != NULL) - free_msg(msg); + list_add_tail(&msg->m_list, &tmp_msg); kfree(info->node_cache); spin_unlock(&info->lock);

+ list_for_each_entry_safe(msg, nmsg, &tmp_msg, m_list) { + list_del(&msg->m_list); + free_msg(msg); + } + /* Total amount of bytes accounted for the mqueue */ mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) + min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) * diff --git a/ipc/msgutil.c b/ipc/msgutil.c index bf74eaa5c39f..6d90b191c638 100644 --- a/ipc/msgutil.c +++ b/ipc/msgutil.c @@ -18,6 +18,7 @@ #include <linux/utsname.h> #include <linux/proc_ns.h> #include <linux/uaccess.h> +#include <linux/sched.h>

#include "util.h"

@@ -64,6 +65,9 @@ static struct msg_msg *alloc_msg(size_t len) pseg = &msg->next; while (len > 0) { struct msg_msgseg *seg; + + cond_resched(); + alen = min(len, DATALEN_SEG); seg = kmalloc(sizeof(*seg) + alen, GFP_KERNEL_ACCOUNT); if (seg == NULL) @@ -176,6 +180,8 @@ void free_msg(struct msg_msg *msg) kfree(msg); while (seg != NULL) { struct msg_msgseg *tmp = seg->next; + + cond_resched(); kfree(seg); seg = tmp; }

From: Mark Rutland mark.rutland@arm.com

[ Upstream commit 7ba36eccb3f83983a651efd570b4f933ecad1b5c ]

The arm64 ptdump code can race with concurrent modification of the kernel page tables. At the time this was added, this was sound as:

* Modifications to leaf entries could result in stale information being logged, but would not result in a functional problem.

* Boot time modifications to non-leaf entries (e.g. freeing of initmem) were performed when the ptdump code cannot be invoked.

* At runtime, modifications to non-leaf entries only occurred in the vmalloc region, and these were strictly additive, as intermediate entries were never freed.

However, since commit:

commit 324420bf91f6 ("arm64: add support for ioremap() block mappings")

... it has been possible to create huge mappings in the vmalloc area at runtime, and as part of this existing intermediate levels of table my be removed and freed.

It's possible for the ptdump code to race with this, and continue to walk tables which have been freed (and potentially poisoned or reallocated). As a result of this, the ptdump code may dereference bogus addresses, which could be fatal.

Since huge-vmap is a TLB and memory optimization, we can disable it when the runtime ptdump code is in use to avoid this problem.

Cc: Catalin Marinas catalin.marinas@arm.com Fixes: 324420bf91f60582 ("arm64: add support for ioremap() block mappings") Acked-by: Ard Biesheuvel ard.biesheuvel@arm.com Signed-off-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Anshuman Khandual anshuman.khandual@arm.com Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/mm/mmu.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 0a56898f8410..efd65fc85238 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -765,13 +765,18 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys)

int __init arch_ioremap_pud_supported(void) { - /* only 4k granule supports level 1 block mappings */ - return IS_ENABLED(CONFIG_ARM64_4K_PAGES); + /* + * Only 4k granule supports level 1 block mappings. + * SW table walks can't handle removal of intermediate entries. + */ + return IS_ENABLED(CONFIG_ARM64_4K_PAGES) && + !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); }

int __init arch_ioremap_pmd_supported(void) { - return 1; + /* See arch_ioremap_pud_supported() */ + return !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); }

int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)

From: Kees Cook keescook@chromium.org

[ Upstream commit fe48319243a626c860fd666ca032daacc2ba84a5 ]

When running under a pipe, some timer tests would not report output in real-time because stdout flushes were missing after printf()s that lacked a newline. This adds them to restore real-time status output that humans can enjoy.

Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/timers/adjtick.c | 1 + tools/testing/selftests/timers/leapcrash.c | 1 + tools/testing/selftests/timers/mqueue-lat.c | 1 + tools/testing/selftests/timers/nanosleep.c | 1 + tools/testing/selftests/timers/nsleep-lat.c | 1 + tools/testing/selftests/timers/raw_skew.c | 1 + tools/testing/selftests/timers/set-tai.c | 1 + tools/testing/selftests/timers/set-tz.c | 2 ++ tools/testing/selftests/timers/threadtest.c | 1 + tools/testing/selftests/timers/valid-adjtimex.c | 2 ++ 10 files changed, 12 insertions(+)

diff --git a/tools/testing/selftests/timers/adjtick.c b/tools/testing/selftests/timers/adjtick.c index 9887fd538fec..91316ab4b041 100644 --- a/tools/testing/selftests/timers/adjtick.c +++ b/tools/testing/selftests/timers/adjtick.c @@ -147,6 +147,7 @@ int check_tick_adj(long tickval)

eppm = get_ppm_drift(); printf("%lld usec, %lld ppm", systick + (systick * eppm / MILLION), eppm); + fflush(stdout);

tx1.modes = 0; adjtimex(&tx1); diff --git a/tools/testing/selftests/timers/leapcrash.c b/tools/testing/selftests/timers/leapcrash.c index a1071bdbdeb7..a77c70b47495 100644 --- a/tools/testing/selftests/timers/leapcrash.c +++ b/tools/testing/selftests/timers/leapcrash.c @@ -114,6 +114,7 @@ int main(void) } clear_time_state(); printf("."); + fflush(stdout); } printf("[OK]\n"); return ksft_exit_pass(); diff --git a/tools/testing/selftests/timers/mqueue-lat.c b/tools/testing/selftests/timers/mqueue-lat.c index a2a3924d0b41..efdb62470052 100644 --- a/tools/testing/selftests/timers/mqueue-lat.c +++ b/tools/testing/selftests/timers/mqueue-lat.c @@ -113,6 +113,7 @@ int main(int argc, char **argv) int ret;

printf("Mqueue latency : "); + fflush(stdout);

ret = mqueue_lat_test(); if (ret < 0) { diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c index ff942ff7c9b3..2e6e94c02a33 100644 --- a/tools/testing/selftests/timers/nanosleep.c +++ b/tools/testing/selftests/timers/nanosleep.c @@ -153,6 +153,7 @@ int main(int argc, char **argv) continue;

printf("Nanosleep %-31s ", clockstring(clockid)); + fflush(stdout);

length = 10; while (length <= (NSEC_PER_SEC * 10)) { diff --git a/tools/testing/selftests/timers/nsleep-lat.c b/tools/testing/selftests/timers/nsleep-lat.c index 2d7898fda0f1..ac06cf10a5c2 100644 --- a/tools/testing/selftests/timers/nsleep-lat.c +++ b/tools/testing/selftests/timers/nsleep-lat.c @@ -166,6 +166,7 @@ int main(int argc, char **argv) continue;

printf("nsleep latency %-26s ", clockstring(clockid)); + fflush(stdout);

length = 10; while (length <= (NSEC_PER_SEC * 10)) { diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c index 0ab937a17ebb..4e631da7f956 100644 --- a/tools/testing/selftests/timers/raw_skew.c +++ b/tools/testing/selftests/timers/raw_skew.c @@ -124,6 +124,7 @@ int main(int argv, char **argc) printf("WARNING: ADJ_OFFSET in progress, this will cause inaccurate results\n");

printf("Estimating clock drift: "); + fflush(stdout); sleep(120);

get_monotonic_and_raw(&mon, &raw); diff --git a/tools/testing/selftests/timers/set-tai.c b/tools/testing/selftests/timers/set-tai.c index dc88dbc8831f..3ae76ab483de 100644 --- a/tools/testing/selftests/timers/set-tai.c +++ b/tools/testing/selftests/timers/set-tai.c @@ -66,6 +66,7 @@ int main(int argc, char **argv) printf("tai offset started at %i\n", ret);

printf("Checking tai offsets can be properly set: "); + fflush(stdout); for (i = 1; i <= 60; i++) { ret = set_tai(i); ret = get_tai(); diff --git a/tools/testing/selftests/timers/set-tz.c b/tools/testing/selftests/timers/set-tz.c index f4184928b16b..b038131c9682 100644 --- a/tools/testing/selftests/timers/set-tz.c +++ b/tools/testing/selftests/timers/set-tz.c @@ -76,6 +76,7 @@ int main(int argc, char **argv) printf("tz_minuteswest started at %i, dst at %i\n", min, dst);

printf("Checking tz_minuteswest can be properly set: "); + fflush(stdout); for (i = -15*60; i < 15*60; i += 30) { ret = set_tz(i, dst); ret = get_tz_min(); @@ -87,6 +88,7 @@ int main(int argc, char **argv) printf("[OK]\n");

printf("Checking invalid tz_minuteswest values are caught: "); + fflush(stdout);

if (!set_tz(-15*60-1, dst)) { printf("[FAILED] %i didn't return failure!\n", -15*60-1); diff --git a/tools/testing/selftests/timers/threadtest.c b/tools/testing/selftests/timers/threadtest.c index e632e116f05e..a4bf736dd842 100644 --- a/tools/testing/selftests/timers/threadtest.c +++ b/tools/testing/selftests/timers/threadtest.c @@ -175,6 +175,7 @@ int main(int argc, char **argv) strftime(buf, 255, "%a, %d %b %Y %T %z", localtime(&start)); printf("%s\n", buf); printf("Testing consistency with %i threads for %ld seconds: ", thread_count, runtime); + fflush(stdout);

/* spawn */ for (i = 0; i < thread_count; i++) diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index 60fe3c569bd9..a747645d79f4 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -134,6 +134,7 @@ int validate_freq(void) /* Set the leap second insert flag */

printf("Testing ADJ_FREQ... "); + fflush(stdout); for (i = 0; i < NUM_FREQ_VALID; i++) { tx.modes = ADJ_FREQUENCY; tx.freq = valid_freq[i]; @@ -261,6 +262,7 @@ int set_bad_offset(long sec, long usec, int use_nano) int validate_set_offset(void) { printf("Testing ADJ_SETOFFSET... "); + fflush(stdout);

/* Test valid values */ if (set_offset(NSEC_PER_SEC - 1, 1))

From: Kloetzke Jan Jan.Kloetzke@preh.de

[ Upstream commit ad70411a978d1e6e97b1e341a7bde9a79af0c93d ]

When disconnecting cdc_ncm the kernel sporadically crashes shortly after the disconnect:

[ 57.868812] Unable to handle kernel NULL pointer dereference at virtual address 00000000 ... [ 58.006653] PC is at 0x0 [ 58.009202] LR is at call_timer_fn+0xec/0x1b4 [ 58.013567] pc : [<0000000000000000>] lr : [<ffffff80080f5130>] pstate: 00000145 [ 58.020976] sp : ffffff8008003da0 [ 58.024295] x29: ffffff8008003da0 x28: 0000000000000001 [ 58.029618] x27: 000000000000000a x26: 0000000000000100 [ 58.034941] x25: 0000000000000000 x24: ffffff8008003e68 [ 58.040263] x23: 0000000000000000 x22: 0000000000000000 [ 58.045587] x21: 0000000000000000 x20: ffffffc68fac1808 [ 58.050910] x19: 0000000000000100 x18: 0000000000000000 [ 58.056232] x17: 0000007f885aff8c x16: 0000007f883a9f10 [ 58.061556] x15: 0000000000000001 x14: 000000000000006e [ 58.066878] x13: 0000000000000000 x12: 00000000000000ba [ 58.072201] x11: ffffffc69ff1db30 x10: 0000000000000020 [ 58.077524] x9 : 8000100008001000 x8 : 0000000000000001 [ 58.082847] x7 : 0000000000000800 x6 : ffffff8008003e70 [ 58.088169] x5 : ffffffc69ff17a28 x4 : 00000000ffff138b [ 58.093492] x3 : 0000000000000000 x2 : 0000000000000000 [ 58.098814] x1 : 0000000000000000 x0 : 0000000000000000 ... [ 58.205800] [< (null)>] (null) [ 58.210521] [<ffffff80080f5298>] expire_timers+0xa0/0x14c [ 58.215937] [<ffffff80080f542c>] run_timer_softirq+0xe8/0x128 [ 58.221702] [<ffffff8008081120>] __do_softirq+0x298/0x348 [ 58.227118] [<ffffff80080a6304>] irq_exit+0x74/0xbc [ 58.232009] [<ffffff80080e17dc>] __handle_domain_irq+0x78/0xac [ 58.237857] [<ffffff8008080cf4>] gic_handle_irq+0x80/0xac ...

The crash happens roughly 125..130ms after the disconnect. This correlates with the 'delay' timer that is started on certain USB tx/rx errors in the URB completion handler.

The problem is a race of usbnet_stop() with usbnet_start_xmit(). In usbnet_stop() we call usbnet_terminate_urbs() to cancel all URBs in flight. This only makes sense if no new URBs are submitted concurrently, though. But the usbnet_start_xmit() can run at the same time on another CPU which almost unconditionally submits an URB. The error callback of the new URB will then schedule the timer after it was already stopped.

The fix adds a check if the tx queue is stopped after the tx list lock has been taken. This should reliably prevent the submission of new URBs while usbnet_terminate_urbs() does its job. The same thing is done on the rx side even though it might be safe due to other flags that are checked there.

Signed-off-by: Jan Klötzke Jan.Kloetzke@preh.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/usbnet.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 4ab82b998a0f..a5acbcb3c044 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -508,6 +508,7 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)

if (netif_running (dev->net) && netif_device_present (dev->net) && + test_bit(EVENT_DEV_OPEN, &dev->flags) && !test_bit (EVENT_RX_HALT, &dev->flags) && !test_bit (EVENT_DEV_ASLEEP, &dev->flags)) { switch (retval = usb_submit_urb (urb, GFP_ATOMIC)) { @@ -1394,6 +1395,11 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, spin_unlock_irqrestore(&dev->txq.lock, flags); goto drop; } + if (netif_queue_stopped(net)) { + usb_autopm_put_interface_async(dev->intf); + spin_unlock_irqrestore(&dev->txq.lock, flags); + goto drop; + }

#ifdef CONFIG_PM /* if this triggers the device is still a sleep */

From: Christian Borntraeger borntraeger@de.ibm.com

[ Upstream commit 19ec166c3f39fe1d3789888a74cc95544ac266d4 ]

kselftests exposed a problem in the s390 handling for memory slots. Right now we only do proper memory slot handling for creation of new memory slots. Neither MOVE, nor DELETION are handled properly. Let us implement those.

Signed-off-by: Christian Borntraeger borntraeger@de.ibm.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/kvm/kvm-s390.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-)

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 2032ab81b2d7..07f571900676 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3288,21 +3288,28 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - int rc; - - /* If the basics of the memslot do not change, we do not want - * to update the gmap. Every update causes several unnecessary - * segment translation exceptions. This is usually handled just - * fine by the normal fault handler + gmap, but it will also - * cause faults on the prefix page of running guest CPUs. - */ - if (old->userspace_addr == mem->userspace_addr && - old->base_gfn * PAGE_SIZE == mem->guest_phys_addr && - old->npages * PAGE_SIZE == mem->memory_size) - return; + int rc = 0;

- rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, - mem->guest_phys_addr, mem->memory_size); + switch (change) { + case KVM_MR_DELETE: + rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE, + old->npages * PAGE_SIZE); + break; + case KVM_MR_MOVE: + rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE, + old->npages * PAGE_SIZE); + if (rc) + break; + /* FALLTHROUGH */ + case KVM_MR_CREATE: + rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, + mem->guest_phys_addr, mem->memory_size); + break; + case KVM_MR_FLAGS_ONLY: + break; + default: + WARN(1, "Unknown KVM MR CHANGE: %d\n", change); + } if (rc) pr_warn("failed to commit memory region\n"); return;