From: Jan Kara jack@suse.cz

commit ee0ed02ca93ef1ecf8963ad96638795d55af2c14 upstream.

It is possible that unlinked inode enters ext4_setattr() (e.g. if somebody calls ftruncate(2) on unlinked but still open file). In such case we should not delete the inode from the orphan list if truncate fails. Note that this is mostly a theoretical concern as filesystem is corrupted if we reach this path anyway but let's be consistent in our orphan handling.

Reviewed-by: Ira Weiny ira.weiny@intel.com Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ext4/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5596,7 +5596,7 @@ int ext4_setattr(struct dentry *dentry, up_write(&EXT4_I(inode)->i_data_sem); ext4_journal_stop(handle); if (error) { - if (orphan) + if (orphan && inode->i_nlink) ext4_orphan_del(NULL, inode); goto err_out; }

From: Damien Le Moal damien.lemoal@wdc.com

commit 0916878da355650d7e77104a7ac0fa1784eca852 upstream.

For a single device mount using a zoned block device, the zone information for the device is stored in the sbi->devs single entry array and sbi->s_ndevs is set to 1. This differs from a single device mount using a regular block device which does not allocate sbi->devs and sets sbi->s_ndevs to 0.

However, sbi->s_devs == 0 condition is used throughout the code to differentiate a single device mount from a multi-device mount where sbi->s_ndevs is always larger than 1. This results in problems with single zoned block device volumes as these are treated as multi-device mounts but do not have the start_blk and end_blk information set. One of the problem observed is skipping of zone discard issuing resulting in write commands being issued to full zones or unaligned to a zone write pointer.

Fix this problem by simply treating the cases sbi->s_ndevs == 0 (single regular block device mount) and sbi->s_ndevs == 1 (single zoned block device mount) in the same manner. This is done by introducing the helper function f2fs_is_multi_device() and using this helper in place of direct tests of sbi->s_ndevs value, improving code readability.

Fixes: 7bb3a371d199 ("f2fs: Fix zoned block device support") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal damien.lemoal@wdc.com Reviewed-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 08314fb42652..4d02e76b648a 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -197,12 +197,14 @@ struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, struct block_device *bdev = sbi->sb->s_bdev; int i;

- for (i = 0; i < sbi->s_ndevs; i++) { - if (FDEV(i).start_blk <= blk_addr && - FDEV(i).end_blk >= blk_addr) { - blk_addr -= FDEV(i).start_blk; - bdev = FDEV(i).bdev; - break; + if (f2fs_is_multi_device(sbi)) { + for (i = 0; i < sbi->s_ndevs; i++) { + if (FDEV(i).start_blk <= blk_addr && + FDEV(i).end_blk >= blk_addr) { + blk_addr -= FDEV(i).start_blk; + bdev = FDEV(i).bdev; + break; + } } } if (bio) { @@ -216,6 +218,9 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) { int i;

+ if (!f2fs_is_multi_device(sbi)) + return 0; + for (i = 0; i < sbi->s_ndevs; i++) if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr) return i; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 1f5d5f62bb77..a4b6eacf22ea 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1336,6 +1336,17 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) } #endif

+/* + * Test if the mounted volume is a multi-device volume. + * - For a single regular disk volume, sbi->s_ndevs is 0. + * - For a single zoned disk volume, sbi->s_ndevs is 1. + * - For a multi-device volume, sbi->s_ndevs is always 2 or more. + */ +static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) +{ + return sbi->s_ndevs > 1; +} + /* For write statistics. Suppose sector size is 512 bytes, * and the return value is in kbytes. s is of struct f2fs_sb_info. */ @@ -3455,7 +3466,7 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, int rw) { return (f2fs_post_read_required(inode) || (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) || - F2FS_I_SB(inode)->s_ndevs); + f2fs_is_multi_device(F2FS_I_SB(inode))); }

#ifdef CONFIG_F2FS_FAULT_INJECTION diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index b3f46e3bec17..8d1eb8dec605 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2539,7 +2539,7 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) sizeof(range))) return -EFAULT;

- if (sbi->s_ndevs <= 1 || sbi->s_ndevs - 1 <= range.dev_num || + if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num || sbi->segs_per_sec != 1) { f2fs_msg(sbi->sb, KERN_WARNING, "Can't flush %u in %d for segs_per_sec %u != 1\n", diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 5c8d00422237..d44b57a363ff 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1256,7 +1256,7 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi) sbi->gc_pin_file_threshold = DEF_GC_FAILED_PINNED_FILES;

/* give warm/cold data area from slower device */ - if (sbi->s_ndevs && sbi->segs_per_sec == 1) + if (f2fs_is_multi_device(sbi) && sbi->segs_per_sec == 1) SIT_I(sbi)->last_victim[ALLOC_NEXT] = GET_SEGNO(sbi, FDEV(0).end_blk) + 1; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index ac038563273d..03fa2c4d3d79 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -574,7 +574,7 @@ static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino) int ret = 0; int i;

- if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return __submit_flush_wait(sbi, sbi->sb->s_bdev);

for (i = 0; i < sbi->s_ndevs; i++) { @@ -640,7 +640,8 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino) return ret; }

- if (atomic_inc_return(&fcc->issing_flush) == 1 || sbi->s_ndevs > 1) { + if (atomic_inc_return(&fcc->issing_flush) == 1 || + f2fs_is_multi_device(sbi)) { ret = submit_flush_wait(sbi, ino); atomic_dec(&fcc->issing_flush);

@@ -746,7 +747,7 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi) { int ret = 0, i;

- if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return 0;

for (i = 1; i < sbi->s_ndevs; i++) { @@ -1289,7 +1290,7 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi,

trace_f2fs_queue_discard(bdev, blkstart, blklen);

- if (sbi->s_ndevs) { + if (f2fs_is_multi_device(sbi)) { int devi = f2fs_target_device_index(sbi, blkstart);

blkstart -= FDEV(devi).start_blk; @@ -1638,7 +1639,7 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, block_t lblkstart = blkstart; int devi = 0;

- if (sbi->s_ndevs) { + if (f2fs_is_multi_device(sbi)) { devi = f2fs_target_device_index(sbi, blkstart); blkstart -= FDEV(devi).start_blk; } @@ -2971,7 +2972,7 @@ static void update_device_state(struct f2fs_io_info *fio) struct f2fs_sb_info *sbi = fio->sbi; unsigned int devidx;

- if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return;

devidx = f2fs_target_device_index(sbi, fio->new_blkaddr);

From: Andrea Parri andrea.parri@amarulasolutions.com

commit f381c6a4bd0ae0fde2d6340f1b9bb0f58d915de6 upstream.

This barrier only applies to the read-modify-write operations; in particular, it does not apply to the atomic_set() primitive.

Replace the barrier with an smp_mb().

Fixes: dac56212e8127 ("bio: skip atomic inc/dec of ->bi_cnt for most use cases") Cc: stable@vger.kernel.org Reported-by: "Paul E. McKenney" paulmck@linux.ibm.com Reported-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Andrea Parri andrea.parri@amarulasolutions.com Reviewed-by: Ming Lei ming.lei@redhat.com Cc: Jens Axboe axboe@kernel.dk Cc: Ming Lei ming.lei@redhat.com Cc: linux-block@vger.kernel.org Cc: "Paul E. McKenney" paulmck@linux.ibm.com Cc: Peter Zijlstra peterz@infradead.org Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

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

--- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -257,7 +257,7 @@ static inline void bio_cnt_set(struct bi { if (count != 1) { bio->bi_flags |= (1 << BIO_REFFED); - smp_mb__before_atomic(); + smp_mb(); } atomic_set(&bio->__bi_cnt, count); }

From: Martin K. Petersen martin.petersen@oracle.com

commit 8acf608e602f6ec38b7cc37b04c80f1ce9a1a6cc upstream.

This reverts commit 20bd1d026aacc5399464f8328f305985c493cde3.

This patch introduced regressions for devices that come online in read-only state and subsequently switch to read-write.

Given how the partition code is currently implemented it is not possible to persist the read-only flag across a device revalidate call. This may need to get addressed in the future since it is common for user applications to proactively call BLKRRPART.

Reverting this commit will re-introduce a regression where a device-initiated revalidate event will cause the admin state to be forgotten. A separate patch will address this issue.

Fixes: 20bd1d026aac ("scsi: sd: Keep disk read-only when re-reading partition") Cc: stable@vger.kernel.org Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/scsi/sd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2605,7 +2605,6 @@ sd_read_write_protect_flag(struct scsi_d int res; struct scsi_device *sdp = sdkp->device; struct scsi_mode_data data; - int disk_ro = get_disk_ro(sdkp->disk); int old_wp = sdkp->write_prot;

set_disk_ro(sdkp->disk, 0); @@ -2646,7 +2645,7 @@ sd_read_write_protect_flag(struct scsi_d "Test WP failed, assume Write Enabled\n"); } else { sdkp->write_prot = ((data.device_specific & 0x80) != 0); - set_disk_ro(sdkp->disk, sdkp->write_prot || disk_ro); + set_disk_ro(sdkp->disk, sdkp->write_prot); if (sdkp->first_scan || old_wp != sdkp->write_prot) { sd_printk(KERN_NOTICE, sdkp, "Write Protect is %s\n", sdkp->write_prot ? "on" : "off");

From: Trac Hoang trac.hoang@broadcom.com

commit b7dfa695afc40d5396ed84b9f25aa3754de23e39 upstream.

The iproc host eMMC/SD controller hold time does not meet the specification in the HS50 mode. This problem can be mitigated by disabling the HISPD bit; thus forcing the controller output data to be driven on the falling clock edges rather than the rising clock edges.

This change applies only to the Cygnus platform.

Stable tag (v4.12+) chosen to assist stable kernel maintainers so that the change does not produce merge conflicts backporting to older kernel versions. In reality, the timing bug existed since the driver was first introduced but there is no need for this driver to be supported in kernel versions that old.

Cc: stable@vger.kernel.org # v4.12+ Signed-off-by: Trac Hoang trac.hoang@broadcom.com Signed-off-by: Scott Branden scott.branden@broadcom.com Acked-by: Adrian Hunter adrian.hunter@intel.com Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/mmc/host/sdhci-iproc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/mmc/host/sdhci-iproc.c +++ b/drivers/mmc/host/sdhci-iproc.c @@ -185,7 +185,8 @@ static const struct sdhci_ops sdhci_ipro };

static const struct sdhci_pltfm_data sdhci_iproc_cygnus_pltfm_data = { - .quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK, + .quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK | + SDHCI_QUIRK_NO_HISPD_BIT, .quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN | SDHCI_QUIRK2_HOST_OFF_CARD_ON, .ops = &sdhci_iproc_32only_ops, };

From: Suthikulpanit, Suravee Suravee.Suthikulpanit@amd.com

commit c9bcd3e3335d0a29d89fabd2c385e1b989e6f1b0 upstream.

Current logic does not allow VCPU to be loaded onto CPU with APIC ID 255. This should be allowed since the host physical APIC ID field in the AVIC Physical APIC table entry is an 8-bit value, and APIC ID 255 is valid in system with x2APIC enabled. Instead, do not allow VCPU load if the host APIC ID cannot be represented by an 8-bit value.

Also, use the more appropriate AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK instead of AVIC_MAX_PHYSICAL_ID_COUNT.

Signed-off-by: Suravee Suthikulpanit suravee.suthikulpanit@amd.com Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kvm/svm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2022,7 +2022,11 @@ static void avic_vcpu_load(struct kvm_vc if (!kvm_vcpu_apicv_active(vcpu)) return;

- if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT)) + /* + * Since the host physical APIC id is 8 bits, + * we can support host APIC ID upto 255. + */ + if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) return;

entry = READ_ONCE(*(svm->avic_physical_id_cache));

From: Ard Biesheuvel ard.biesheuvel@arm.com

commit b2eed9b58811283d00fa861944cb75797d4e52a7 upstream.

The following commit

7290d5809571 ("module: use relative references for __ksymtab entries")

updated the ksymtab handling of some KASLR capable architectures so that ksymtab entries are emitted as pairs of 32-bit relative references. This reduces the size of the entries, but more importantly, it gets rid of statically assigned absolute addresses, which require fixing up at boot time if the kernel is self relocating (which takes a 24 byte RELA entry for each member of the ksymtab struct).

Since ksymtab entries are always part of the same module as the symbol they export, it was assumed at the time that a 32-bit relative reference is always sufficient to capture the offset between a ksymtab entry and its target symbol.

Unfortunately, this is not always true: in the case of per-CPU variables, a per-CPU variable's base address (which usually differs from the actual address of any of its per-CPU copies) is allocated in the vicinity of the ..data.percpu section in the core kernel (i.e., in the per-CPU reserved region which follows the section containing the core kernel's statically allocated per-CPU variables).

Since we randomize the module space over a 4 GB window covering the core kernel (based on the -/+ 4 GB range of an ADRP/ADD pair), we may end up putting the core kernel out of the -/+ 2 GB range of 32-bit relative references of module ksymtab entries that refer to per-CPU variables.

So reduce the module randomization range a bit further. We lose 1 bit of randomization this way, but this is something we can tolerate.

Cc: stable@vger.kernel.org # v4.19+ Signed-off-by: Ard Biesheuvel ard.biesheuvel@arm.com Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/kernel/kaslr.c | 6 +++--- arch/arm64/kernel/module.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-)

--- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -145,15 +145,15 @@ u64 __init kaslr_early_init(u64 dt_phys)

if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) { /* - * Randomize the module region over a 4 GB window covering the + * Randomize the module region over a 2 GB window covering the * kernel. This reduces the risk of modules leaking information * about the address of the kernel itself, but results in * branches between modules and the core kernel that are * resolved via PLTs. (Branches between modules will be * resolved normally.) */ - module_range = SZ_4G - (u64)(_end - _stext); - module_alloc_base = max((u64)_end + offset - SZ_4G, + module_range = SZ_2G - (u64)(_end - _stext); + module_alloc_base = max((u64)_end + offset - SZ_2G, (u64)MODULES_VADDR); } else { /* --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -56,7 +56,7 @@ void *module_alloc(unsigned long size) * can simply omit this fallback in that case. */ p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base, - module_alloc_base + SZ_4G, GFP_KERNEL, + module_alloc_base + SZ_2G, GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, __builtin_return_address(0));

From: Andreas Gruenbacher agruenba@redhat.com

commit 5a5ec83d6ac974b12085cd99b196795f14079037 upstream.

Commit 4d207133e9c3 changed the types of the statistic values in struct gfs2_lkstats from s64 to u64. Because of that, what should be a signed value in gfs2_update_stats turned into an unsigned value. When shifted right, we end up with a large positive value instead of a small negative value, which results in an incorrect variance estimate.

Fixes: 4d207133e9c3 ("gfs2: Make statistics unsigned, suitable for use with do_div()") Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Cc: stable@vger.kernel.org # v4.4+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/gfs2/lock_dlm.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

--- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -31,9 +31,10 @@ * @delta is the difference between the current rtt sample and the * running average srtt. We add 1/8 of that to the srtt in order to * update the current srtt estimate. The variance estimate is a bit - * more complicated. We subtract the abs value of the @delta from - * the current variance estimate and add 1/4 of that to the running - * total. + * more complicated. We subtract the current variance estimate from + * the abs value of the @delta and add 1/4 of that to the running + * total. That's equivalent to 3/4 of the current variance + * estimate plus 1/4 of the abs of @delta. * * Note that the index points at the array entry containing the smoothed * mean value, and the variance is always in the following entry @@ -49,7 +50,7 @@ static inline void gfs2_update_stats(str s64 delta = sample - s->stats[index]; s->stats[index] += (delta >> 3); index++; - s->stats[index] += ((abs(delta) - s->stats[index]) >> 2); + s->stats[index] += (s64)(abs(delta) - s->stats[index]) >> 2; }

/**

From: Filipe Manana fdmanana@suse.com

commit 72bd2323ec87722c115a5906bc6a1b31d11e8f54 upstream.

Currently when we fail to COW a path at btrfs_update_root() we end up always aborting the transaction. However all the current callers of btrfs_update_root() are able to deal with errors returned from it, many do end up aborting the transaction themselves (directly or not, such as the transaction commit path), other BUG_ON() or just gracefully cancel whatever they were doing.

When syncing the fsync log, we call btrfs_update_root() through tree-log.c:update_log_root(), and if it returns an -ENOSPC error, the log sync code does not abort the transaction, instead it gracefully handles the error and returns -EAGAIN to the fsync handler, so that it falls back to a transaction commit. Any other error different from -ENOSPC, makes the log sync code abort the transaction.

So remove the transaction abort from btrfs_update_log() when we fail to COW a path to update the root item, so that if an -ENOSPC failure happens we avoid aborting the current transaction and have a chance of the fsync succeeding after falling back to a transaction commit.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203413 Fixes: 79787eaab46121 ("btrfs: replace many BUG_ONs with proper error handling") Cc: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana fdmanana@suse.com Reviewed-by: Anand Jain anand.jain@oracle.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/root-tree.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -132,10 +132,8 @@ int btrfs_update_root(struct btrfs_trans return -ENOMEM;

ret = btrfs_search_slot(trans, root, key, path, 0, 1); - if (ret < 0) { - btrfs_abort_transaction(trans, ret); + if (ret < 0) goto out; - }

if (ret != 0) { btrfs_print_leaf(path->nodes[0]);

From: Filipe Manana fdmanana@suse.com

commit 0c713cbab6200b0ab6473b50435e450a6e1de85d upstream.

When we do a full fsync (the bit BTRFS_INODE_NEEDS_FULL_SYNC is set in the inode) that happens to be ranged, which happens during a msync() or writes for files opened with O_SYNC for example, we can end up with a corrupt log, due to different file extent items representing ranges that overlap with each other, or hit some assertion failures.

When doing a ranged fsync we only flush delalloc and wait for ordered exents within that range. If while we are logging items from our inode ordered extents for adjacent ranges complete, we end up in a race that can make us insert the file extent items that overlap with others we logged previously and the assertion failures.

For example, if tree-log.c:copy_items() receives a leaf that has the following file extents items, all with a length of 4K and therefore there is an implicit hole in the range 68K to 72K - 1:

(257 EXTENT_ITEM 64K), (257 EXTENT_ITEM 72K), (257 EXTENT_ITEM 76K), ...

It copies them to the log tree. However due to the need to detect implicit holes, it may release the path, in order to look at the previous leaf to detect an implicit hole, and then later it will search again in the tree for the first file extent item key, with the goal of locking again the leaf (which might have changed due to concurrent changes to other inodes).

However when it locks again the leaf containing the first key, the key corresponding to the extent at offset 72K may not be there anymore since there is an ordered extent for that range that is finishing (that is, somewhere in the middle of btrfs_finish_ordered_io()), and it just removed the file extent item but has not yet replaced it with a new file extent item, so the part of copy_items() that does hole detection will decide that there is a hole in the range starting from 68K to 76K - 1, and therefore insert a file extent item to represent that hole, having a key offset of 68K. After that we now have a log tree with 2 different extent items that have overlapping ranges:

1) The file extent item copied before copy_items() released the path, which has a key offset of 72K and a length of 4K, representing the file range 72K to 76K - 1.

2) And a file extent item representing a hole that has a key offset of 68K and a length of 8K, representing the range 68K to 76K - 1. This item was inserted after releasing the path, and overlaps with the extent item inserted before.

The overlapping extent items can cause all sorts of unpredictable and incorrect behaviour, either when replayed or if a fast (non full) fsync happens later, which can trigger a BUG_ON() when calling btrfs_set_item_key_safe() through __btrfs_drop_extents(), producing a trace like the following:

[61666.783269] ------------[ cut here ]------------ [61666.783943] kernel BUG at fs/btrfs/ctree.c:3182! [61666.784644] invalid opcode: 0000 [#1] PREEMPT SMP (...) [61666.786253] task: ffff880117b88c40 task.stack: ffffc90008168000 [61666.786253] RIP: 0010:btrfs_set_item_key_safe+0x7c/0xd2 [btrfs] [61666.786253] RSP: 0018:ffffc9000816b958 EFLAGS: 00010246 [61666.786253] RAX: 0000000000000000 RBX: 000000000000000f RCX: 0000000000030000 [61666.786253] RDX: 0000000000000000 RSI: ffffc9000816ba4f RDI: ffffc9000816b937 [61666.786253] RBP: ffffc9000816b998 R08: ffff88011dae2428 R09: 0000000000001000 [61666.786253] R10: 0000160000000000 R11: 6db6db6db6db6db7 R12: ffff88011dae2418 [61666.786253] R13: ffffc9000816ba4f R14: ffff8801e10c4118 R15: ffff8801e715c000 [61666.786253] FS: 00007f6060a18700(0000) GS:ffff88023f5c0000(0000) knlGS:0000000000000000 [61666.786253] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [61666.786253] CR2: 00007f6060a28000 CR3: 0000000213e69000 CR4: 00000000000006e0 [61666.786253] Call Trace: [61666.786253] __btrfs_drop_extents+0x5e3/0xaad [btrfs] [61666.786253] ? time_hardirqs_on+0x9/0x14 [61666.786253] btrfs_log_changed_extents+0x294/0x4e0 [btrfs] [61666.786253] ? release_extent_buffer+0x38/0xb4 [btrfs] [61666.786253] btrfs_log_inode+0xb6e/0xcdc [btrfs] [61666.786253] ? lock_acquire+0x131/0x1c5 [61666.786253] ? btrfs_log_inode_parent+0xee/0x659 [btrfs] [61666.786253] ? arch_local_irq_save+0x9/0xc [61666.786253] ? btrfs_log_inode_parent+0x1f5/0x659 [btrfs] [61666.786253] btrfs_log_inode_parent+0x223/0x659 [btrfs] [61666.786253] ? arch_local_irq_save+0x9/0xc [61666.786253] ? lockref_get_not_zero+0x2c/0x34 [61666.786253] ? rcu_read_unlock+0x3e/0x5d [61666.786253] btrfs_log_dentry_safe+0x60/0x7b [btrfs] [61666.786253] btrfs_sync_file+0x317/0x42c [btrfs] [61666.786253] vfs_fsync_range+0x8c/0x9e [61666.786253] SyS_msync+0x13c/0x1c9 [61666.786253] entry_SYSCALL_64_fastpath+0x18/0xad

A sample of a corrupt log tree leaf with overlapping extents I got from running btrfs/072:

item 14 key (295 108 200704) itemoff 2599 itemsize 53 extent data disk bytenr 0 nr 0 extent data offset 0 nr 458752 ram 458752 item 15 key (295 108 659456) itemoff 2546 itemsize 53 extent data disk bytenr 4343541760 nr 770048 extent data offset 606208 nr 163840 ram 770048 item 16 key (295 108 663552) itemoff 2493 itemsize 53 extent data disk bytenr 4343541760 nr 770048 extent data offset 610304 nr 155648 ram 770048 item 17 key (295 108 819200) itemoff 2440 itemsize 53 extent data disk bytenr 4334788608 nr 4096 extent data offset 0 nr 4096 ram 4096

The file extent item at offset 659456 (item 15) ends at offset 823296 (659456 + 163840) while the next file extent item (item 16) starts at offset 663552.

Another different problem that the race can trigger is a failure in the assertions at tree-log.c:copy_items(), which expect that the first file extent item key we found before releasing the path exists after we have released path and that the last key we found before releasing the path also exists after releasing the path:

$ cat -n fs/btrfs/tree-log.c 4080 if (need_find_last_extent) { 4081 /* btrfs_prev_leaf could return 1 without releasing the path */ 4082 btrfs_release_path(src_path); 4083 ret = btrfs_search_slot(NULL, inode->root, &first_key, 4084 src_path, 0, 0); 4085 if (ret < 0) 4086 return ret; 4087 ASSERT(ret == 0); (...) 4103 if (i >= btrfs_header_nritems(src_path->nodes[0])) { 4104 ret = btrfs_next_leaf(inode->root, src_path); 4105 if (ret < 0) 4106 return ret; 4107 ASSERT(ret == 0); 4108 src = src_path->nodes[0]; 4109 i = 0; 4110 need_find_last_extent = true; 4111 } (...)

The second assertion implicitly expects that the last key before the path release still exists, because the surrounding while loop only stops after we have found that key. When this assertion fails it produces a stack like this:

[139590.037075] assertion failed: ret == 0, file: fs/btrfs/tree-log.c, line: 4107 [139590.037406] ------------[ cut here ]------------ [139590.037707] kernel BUG at fs/btrfs/ctree.h:3546! [139590.038034] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC PTI [139590.038340] CPU: 1 PID: 31841 Comm: fsstress Tainted: G W 5.0.0-btrfs-next-46 #1 (...) [139590.039354] RIP: 0010:assfail.constprop.24+0x18/0x1a [btrfs] (...) [139590.040397] RSP: 0018:ffffa27f48f2b9b0 EFLAGS: 00010282 [139590.040730] RAX: 0000000000000041 RBX: ffff897c635d92c8 RCX: 0000000000000000 [139590.041105] RDX: 0000000000000000 RSI: ffff897d36a96868 RDI: ffff897d36a96868 [139590.041470] RBP: ffff897d1b9a0708 R08: 0000000000000000 R09: 0000000000000000 [139590.041815] R10: 0000000000000008 R11: 0000000000000000 R12: 0000000000000013 [139590.042159] R13: 0000000000000227 R14: ffff897cffcbba88 R15: 0000000000000001 [139590.042501] FS: 00007f2efc8dee80(0000) GS:ffff897d36a80000(0000) knlGS:0000000000000000 [139590.042847] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [139590.043199] CR2: 00007f8c064935e0 CR3: 0000000232252002 CR4: 00000000003606e0 [139590.043547] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [139590.043899] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [139590.044250] Call Trace: [139590.044631] copy_items+0xa3f/0x1000 [btrfs] [139590.045009] ? generic_bin_search.constprop.32+0x61/0x200 [btrfs] [139590.045396] btrfs_log_inode+0x7b3/0xd70 [btrfs] [139590.045773] btrfs_log_inode_parent+0x2b3/0xce0 [btrfs] [139590.046143] ? do_raw_spin_unlock+0x49/0xc0 [139590.046510] btrfs_log_dentry_safe+0x4a/0x70 [btrfs] [139590.046872] btrfs_sync_file+0x3b6/0x440 [btrfs] [139590.047243] btrfs_file_write_iter+0x45b/0x5c0 [btrfs] [139590.047592] __vfs_write+0x129/0x1c0 [139590.047932] vfs_write+0xc2/0x1b0 [139590.048270] ksys_write+0x55/0xc0 [139590.048608] do_syscall_64+0x60/0x1b0 [139590.048946] entry_SYSCALL_64_after_hwframe+0x49/0xbe [139590.049287] RIP: 0033:0x7f2efc4be190 (...) [139590.050342] RSP: 002b:00007ffe743243a8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [139590.050701] RAX: ffffffffffffffda RBX: 0000000000008d58 RCX: 00007f2efc4be190 [139590.051067] RDX: 0000000000008d58 RSI: 00005567eca0f370 RDI: 0000000000000003 [139590.051459] RBP: 0000000000000024 R08: 0000000000000003 R09: 0000000000008d60 [139590.051863] R10: 0000000000000078 R11: 0000000000000246 R12: 0000000000000003 [139590.052252] R13: 00000000003d3507 R14: 00005567eca0f370 R15: 0000000000000000 (...) [139590.055128] ---[ end trace 193f35d0215cdeeb ]---

So fix this race between a full ranged fsync and writeback of adjacent ranges by flushing all delalloc and waiting for all ordered extents to complete before logging the inode. This is the simplest way to solve the problem because currently the full fsync path does not deal with ranges at all (it assumes a full range from 0 to LLONG_MAX) and it always needs to look at adjacent ranges for hole detection. For use cases of ranged fsyncs this can make a few fsyncs slower but on the other hand it can make some following fsyncs to other ranges do less work or no need to do anything at all. A full fsync is rare anyway and happens only once after loading/creating an inode and once after less common operations such as a shrinking truncate.

This is an issue that exists for a long time, and was often triggered by generic/127, because it does mmap'ed writes and msync (which triggers a ranged fsync). Adding support for the tree checker to detect overlapping extents (next patch in the series) and trigger a WARN() when such cases are found, and then calling btrfs_check_leaf_full() at the end of btrfs_insert_file_extent() made the issue much easier to detect. Running btrfs/072 with that change to the tree checker and making fsstress open files always with O_SYNC made it much easier to trigger the issue (as triggering it with generic/127 is very rare).

CC: stable@vger.kernel.org # 3.16+ Reviewed-by: Josef Bacik josef@toxicpanda.com Signed-off-by: Filipe Manana fdmanana@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/file.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)

--- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2059,6 +2059,18 @@ int btrfs_sync_file(struct file *file, l u64 len;

/* + * If the inode needs a full sync, make sure we use a full range to + * avoid log tree corruption, due to hole detection racing with ordered + * extent completion for adjacent ranges, and assertion failures during + * hole detection. + */ + if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &BTRFS_I(inode)->runtime_flags)) { + start = 0; + end = LLONG_MAX; + } + + /* * The range length can be represented by u64, we have to do the typecasts * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync() */

From: Tobin C. Harding tobin@kernel.org

commit e32773357d5cc271b1d23550b3ed026eb5c2a468 upstream.

A failed call to kobject_init_and_add() must be followed by a call to kobject_put(). Currently in the error path when adding fs_devices we are missing this call. This could be fixed by calling btrfs_sysfs_remove_fsid() if btrfs_sysfs_add_fsid() returns an error or by adding a call to kobject_put() directly in btrfs_sysfs_add_fsid(). Here we choose the second option because it prevents the slightly unusual error path handling requirements of kobject from leaking out into btrfs functions.

Add a call to kobject_put() in the error path of kobject_add_and_init(). This causes the release method to be called if kobject_init_and_add() fails. open_tree() is the function that calls btrfs_sysfs_add_fsid() and the error code in this function is already written with the assumption that the release method is called during the error path of open_tree() (as seen by the call to btrfs_sysfs_remove_fsid() under the fail_fsdev_sysfs label).

Cc: stable@vger.kernel.org # v4.4+ Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Tobin C. Harding tobin@kernel.org Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/sysfs.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -811,7 +811,12 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs fs_devs->fsid_kobj.kset = btrfs_kset; error = kobject_init_and_add(&fs_devs->fsid_kobj, &btrfs_ktype, parent, "%pU", fs_devs->fsid); - return error; + if (error) { + kobject_put(&fs_devs->fsid_kobj); + return error; + } + + return 0; }

int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info)

From: Shile Zhang shile.zhang@linux.alibaba.com

commit cf84807f6dd0be5214378e66460cfc9187f532f9 upstream.

To fix following divide-by-zero error found by Syzkaller:

divide error: 0000 [#1] SMP PTI CPU: 7 PID: 8447 Comm: test Kdump: loaded Not tainted 4.19.24-8.al7.x86_64 #1 Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS rel-1.12.0-0-ga698c8995f-prebuilt.qemu.org 04/01/2014 RIP: 0010:fb_var_to_videomode+0xae/0xc0 Code: 04 44 03 46 78 03 4e 7c 44 03 46 68 03 4e 70 89 ce d1 ee 69 c0 e8 03 00 00 f6 c2 01 0f 45 ce 83 e2 02 8d 34 09 0f 45 ce 31 d2 <41> f7 f0 31 d2 f7 f1 89 47 08 f3 c3 66 0f 1f 44 00 00 0f 1f 44 00 RSP: 0018:ffffb7e189347bf0 EFLAGS: 00010246 RAX: 00000000e1692410 RBX: ffffb7e189347d60 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffb7e189347c10 RBP: ffff99972a091c00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000100 R13: 0000000000010000 R14: 00007ffd66baf6d0 R15: 0000000000000000 FS: 00007f2054d11740(0000) GS:ffff99972fbc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f205481fd20 CR3: 00000004288a0001 CR4: 00000000001606a0 Call Trace: fb_set_var+0x257/0x390 ? lookup_fast+0xbb/0x2b0 ? fb_open+0xc0/0x140 ? chrdev_open+0xa6/0x1a0 do_fb_ioctl+0x445/0x5a0 do_vfs_ioctl+0x92/0x5f0 ? __alloc_fd+0x3d/0x160 ksys_ioctl+0x60/0x90 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x5b/0x190 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f20548258d7 Code: 44 00 00 48 8b 05 b9 15 2d 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 89 15 2d 00 f7 d8 64 89 01 48

It can be triggered easily with following test code:

#include <linux/fb.h> #include <fcntl.h> #include <sys/ioctl.h> int main(void) { struct fb_var_screeninfo var = {.activate = 0x100, .pixclock = 60}; int fd = open("/dev/fb0", O_RDWR); if (fd < 0) return 1;

if (ioctl(fd, FBIOPUT_VSCREENINFO, &var)) return 1;

return 0; }

Signed-off-by: Shile Zhang shile.zhang@linux.alibaba.com Cc: Fredrik Noring noring@nocrew.org Cc: Daniel Vetter daniel.vetter@ffwll.ch Reviewed-by: Mukesh Ojha mojha@codeaurora.org Signed-off-by: Bartlomiej Zolnierkiewicz b.zolnierkie@samsung.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/video/fbdev/core/modedb.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/video/fbdev/core/modedb.c +++ b/drivers/video/fbdev/core/modedb.c @@ -935,6 +935,9 @@ void fb_var_to_videomode(struct fb_video if (var->vmode & FB_VMODE_DOUBLE) vtotal *= 2;

+ if (!htotal || !vtotal) + return; + hfreq = pixclock/htotal; mode->refresh = hfreq/vtotal; }

From: Olga Kornievskaia kolga@netapp.com

commit 0769663b4f580566ef6cdf366f3073dbe8022c39 upstream.

According to the NFSv4.2 spec if the input and output file is the same file, operation should fail with EINVAL. However, linux copy_file_range() system call has no such restrictions. Therefore, in such case let's return EOPNOTSUPP and allow VFS to fallback to doing do_splice_direct(). Also when copy_file_range is called on an NFSv4.0 or 4.1 mount (ie., a server that doesn't support COPY functionality), we also need to return EOPNOTSUPP and fallback to a regular copy.

Fixes xfstest generic/075, generic/091, generic/112, generic/263 for all NFSv4.x versions.

Signed-off-by: Olga Kornievskaia kolga@netapp.com Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Cc: Yu Xu xuyu@linux.alibaba.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/nfs/nfs42proc.c | 3 --- fs/nfs/nfs4file.c | 4 +++- 2 files changed, 3 insertions(+), 4 deletions(-)

--- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -329,9 +329,6 @@ ssize_t nfs42_proc_copy(struct file *src }; ssize_t err, err2;

- if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY)) - return -EOPNOTSUPP; - src_lock = nfs_get_lock_context(nfs_file_open_context(src)); if (IS_ERR(src_lock)) return PTR_ERR(src_lock); --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -133,8 +133,10 @@ static ssize_t nfs4_copy_file_range(stru struct file *file_out, loff_t pos_out, size_t count, unsigned int flags) { + if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY)) + return -EOPNOTSUPP; if (file_inode(file_in) == file_inode(file_out)) - return -EINVAL; + return -EOPNOTSUPP; return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); }

From: Arend van Spriel arend.vanspriel@broadcom.com

commit 1b5e2423164b3670e8bc9174e4762d297990deff upstream.

The SSID length as received from firmware should not exceed IEEE80211_MAX_SSID_LEN as that would result in heap overflow.

Reviewed-by: Hante Meuleman hante.meuleman@broadcom.com Reviewed-by: Pieter-Paul Giesberts pieter-paul.giesberts@broadcom.com Reviewed-by: Franky Lin franky.lin@broadcom.com Signed-off-by: Arend van Spriel arend.vanspriel@broadcom.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Cc: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -3466,6 +3466,8 @@ brcmf_wowl_nd_results(struct brcmf_if *i }

netinfo = brcmf_get_netinfo_array(pfn_result); + if (netinfo->SSID_len > IEEE80211_MAX_SSID_LEN) + netinfo->SSID_len = IEEE80211_MAX_SSID_LEN; memcpy(cfg->wowl.nd->ssid.ssid, netinfo->SSID, netinfo->SSID_len); cfg->wowl.nd->ssid.ssid_len = netinfo->SSID_len; cfg->wowl.nd->n_channels = 1;

From: Will Deacon will.deacon@arm.com

commit 969f5ea627570e91c9d54403287ee3ed657f58fe upstream.

Revisions of the Cortex-A76 CPU prior to r4p0 are affected by an erratum that can prevent interrupts from being taken when single-stepping.

This patch implements a software workaround to prevent userspace from effectively being able to disable interrupts.

Cc: stable@vger.kernel.org Cc: Marc Zyngier marc.zyngier@arm.com Cc: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- Documentation/arm64/silicon-errata.txt | 1 arch/arm64/Kconfig | 18 ++++++++++++++++ arch/arm64/include/asm/cpucaps.h | 3 +- arch/arm64/include/asm/cputype.h | 2 + arch/arm64/kernel/cpu_errata.c | 24 +++++++++++++++++++++ arch/arm64/kernel/syscall.c | 31 +++++++++++++++++++++++++++ arch/arm64/mm/fault.c | 37 +++++++++++++++++++++++++++++++-- 7 files changed, 113 insertions(+), 3 deletions(-)

--- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -58,6 +58,7 @@ stable kernels. | ARM | Cortex-A72 | #853709 | N/A | | ARM | Cortex-A73 | #858921 | ARM64_ERRATUM_858921 | | ARM | Cortex-A55 | #1024718 | ARM64_ERRATUM_1024718 | +| ARM | Cortex-A76 | #1463225 | ARM64_ERRATUM_1463225 | | ARM | MMU-500 | #841119,#826419 | N/A | | | | | | | Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -479,6 +479,24 @@ config ARM64_ERRATUM_1024718

If unsure, say Y.

+config ARM64_ERRATUM_1463225 + bool "Cortex-A76: Software Step might prevent interrupt recognition" + default y + help + This option adds a workaround for Arm Cortex-A76 erratum 1463225. + + On the affected Cortex-A76 cores (r0p0 to r3p1), software stepping + of a system call instruction (SVC) can prevent recognition of + subsequent interrupts when software stepping is disabled in the + exception handler of the system call and either kernel debugging + is enabled or VHE is in use. + + Work around the erratum by triggering a dummy step exception + when handling a system call from a task that is being stepped + in a VHE configuration of the kernel. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -51,7 +51,8 @@ #define ARM64_SSBD 30 #define ARM64_MISMATCHED_CACHE_TYPE 31 #define ARM64_HAS_STAGE2_FWB 32 +#define ARM64_WORKAROUND_1463225 33

-#define ARM64_NCAPS 33 +#define ARM64_NCAPS 34

#endif /* __ASM_CPUCAPS_H */ --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,6 +86,7 @@ #define ARM_CPU_PART_CORTEX_A75 0xD0A #define ARM_CPU_PART_CORTEX_A35 0xD04 #define ARM_CPU_PART_CORTEX_A55 0xD05 +#define ARM_CPU_PART_CORTEX_A76 0xD0B

#define APM_CPU_PART_POTENZA 0x000

@@ -110,6 +111,7 @@ #define MIDR_CORTEX_A75 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A75) #define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35) #define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55) +#define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -411,6 +411,22 @@ static bool has_ssbd_mitigation(const st } #endif /* CONFIG_ARM64_SSBD */

+#ifdef CONFIG_ARM64_ERRATUM_1463225 +DEFINE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); + +static bool +has_cortex_a76_erratum_1463225(const struct arm64_cpu_capabilities *entry, + int scope) +{ + u32 midr = read_cpuid_id(); + /* Cortex-A76 r0p0 - r3p1 */ + struct midr_range range = MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1); + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + return is_midr_in_range(midr, &range) && is_kernel_in_hyp_mode(); +} +#endif + #define CAP_MIDR_RANGE(model, v_min, r_min, v_max, r_max) \ .matches = is_affected_midr_range, \ .midr_range = MIDR_RANGE(model, v_min, r_min, v_max, r_max) @@ -680,6 +696,14 @@ const struct arm64_cpu_capabilities arm6 .matches = has_ssbd_mitigation, }, #endif +#ifdef CONFIG_ARM64_ERRATUM_1463225 + { + .desc = "ARM erratum 1463225", + .capability = ARM64_WORKAROUND_1463225, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = has_cortex_a76_erratum_1463225, + }, +#endif { } }; --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -8,6 +8,7 @@ #include <linux/syscalls.h>

#include <asm/daifflags.h> +#include <asm/debug-monitors.h> #include <asm/fpsimd.h> #include <asm/syscall.h> #include <asm/thread_info.h> @@ -60,6 +61,35 @@ static inline bool has_syscall_work(unsi int syscall_trace_enter(struct pt_regs *regs); void syscall_trace_exit(struct pt_regs *regs);

+#ifdef CONFIG_ARM64_ERRATUM_1463225 +DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); + +static void cortex_a76_erratum_1463225_svc_handler(void) +{ + u32 reg, val; + + if (!unlikely(test_thread_flag(TIF_SINGLESTEP))) + return; + + if (!unlikely(this_cpu_has_cap(ARM64_WORKAROUND_1463225))) + return; + + __this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 1); + reg = read_sysreg(mdscr_el1); + val = reg | DBG_MDSCR_SS | DBG_MDSCR_KDE; + write_sysreg(val, mdscr_el1); + asm volatile("msr daifclr, #8"); + isb(); + + /* We will have taken a single-step exception by this point */ + + write_sysreg(reg, mdscr_el1); + __this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0); +} +#else +static void cortex_a76_erratum_1463225_svc_handler(void) { } +#endif /* CONFIG_ARM64_ERRATUM_1463225 */ + static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, const syscall_fn_t syscall_table[]) { @@ -68,6 +98,7 @@ static void el0_svc_common(struct pt_reg regs->orig_x0 = regs->regs[0]; regs->syscallno = scno;

+ cortex_a76_erratum_1463225_svc_handler(); local_daif_restore(DAIF_PROCCTX); user_exit();

--- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -827,14 +827,47 @@ void __init hook_debug_fault_code(int nr debug_fault_info[nr].name = name; }

+#ifdef CONFIG_ARM64_ERRATUM_1463225 +DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); + +static int __exception +cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +{ + if (user_mode(regs)) + return 0; + + if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa)) + return 0; + + /* + * We've taken a dummy step exception from the kernel to ensure + * that interrupts are re-enabled on the syscall path. Return back + * to cortex_a76_erratum_1463225_svc_handler() with debug exceptions + * masked so that we can safely restore the mdscr and get on with + * handling the syscall. + */ + regs->pstate |= PSR_D_BIT; + return 1; +} +#else +static int __exception +cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +{ + return 0; +} +#endif /* CONFIG_ARM64_ERRATUM_1463225 */ + asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint, - unsigned int esr, - struct pt_regs *regs) + unsigned int esr, + struct pt_regs *regs) { const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr); unsigned long pc = instruction_pointer(regs); int rv;

+ if (cortex_a76_erratum_1463225_debug_handler(regs)) + return 0; + /* * Tell lockdep we disabled irqs in entry.S. Do nothing if they were * already disabled to preserve the last enabled/disabled addresses.

From: Amir Goldstein amir73il@gmail.com

commit acf3062a7e1ccf67c6f7e7c28671a6708fde63b0 upstream.

This nasty little syzbot repro: https://syzkaller.appspot.com/x/repro.syz?x=12c7a94f400000

Creates overlay mounts where the same directory is both in upper and lower layers. Simplified example:

mkdir foo work mount -t overlay none foo -o"lowerdir=.,upperdir=foo,workdir=work"

The repro runs several threads in parallel that attempt to chdir into foo and attempt to symlink/rename/exec/mkdir the file bar.

The repro hits a WARN_ON() I placed in ovl_instantiate(), which suggests that an overlay inode already exists in cache and is hashed by the pointer of the real upper dentry that ovl_create_real() has just created. At the point of the WARN_ON(), for overlay dir inode lock is held and upper dir inode lock, so at first, I did not see how this was possible.

On a closer look, I see that after ovl_create_real(), because of the overlapping upper and lower layers, a lookup by another thread can find the file foo/bar that was just created in upper layer, at overlay path foo/foo/bar and hash the an overlay inode with the new real dentry as lower dentry. This is possible because the overlay directory foo/foo is not locked and the upper dentry foo/bar is in dcache, so ovl_lookup() can find it without taking upper dir inode shared lock.

Overlapping layers is considered a wrong setup which would result in unexpected behavior, but it shouldn't crash the kernel and it shouldn't trigger WARN_ON() either, so relax this WARN_ON() and leave a pr_warn() instead to cover all cases of failure to get an overlay inode.

The error returned from failure to insert new inode to cache with inode_insert5() was changed to -EEXIST, to distinguish from the error -ENOMEM returned on failure to get/allocate inode with iget5_locked().

Reported-by: syzbot+9c69c282adc4edd2b540@syzkaller.appspotmail.com Fixes: 01b39dcc9568 ("ovl: use inode_insert5() to hash a newly...") Signed-off-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Miklos Szeredi mszeredi@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/overlayfs/dir.c | 2 +- fs/overlayfs/inode.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-)

--- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -260,7 +260,7 @@ static int ovl_instantiate(struct dentry * hashed directory inode aliases. */ inode = ovl_get_inode(dentry->d_sb, &oip); - if (WARN_ON(IS_ERR(inode))) + if (IS_ERR(inode)) return PTR_ERR(inode); } else { WARN_ON(ovl_inode_real(inode) != d_inode(newdentry)); --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -832,7 +832,7 @@ struct inode *ovl_get_inode(struct super int fsid = bylower ? oip->lowerpath->layer->fsid : 0; bool is_dir, metacopy = false; unsigned long ino = 0; - int err = -ENOMEM; + int err = oip->newinode ? -EEXIST : -ENOMEM;

if (!realinode) realinode = d_inode(lowerdentry); @@ -917,6 +917,7 @@ out: return inode;

out_err: + pr_warn_ratelimited("overlayfs: failed to get inode (%i)\n", err); inode = ERR_PTR(err); goto out; }

From: YueHaibing yuehaibing@huawei.com

commit dea37a97265588da604c6ba80160a287b72c7bfd upstream.

Syzkaller report this:

BUG: KASAN: use-after-free in sysfs_remove_file_ns+0x5f/0x70 fs/sysfs/file.c:468 Read of size 8 at addr ffff8881f59a6b70 by task syz-executor.0/8363

CPU: 0 PID: 8363 Comm: syz-executor.0 Not tainted 5.0.0-rc8+ #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xfa/0x1ce lib/dump_stack.c:113 print_address_description+0x65/0x270 mm/kasan/report.c:187 kasan_report+0x149/0x18d mm/kasan/report.c:317 sysfs_remove_file_ns+0x5f/0x70 fs/sysfs/file.c:468 sysfs_remove_file include/linux/sysfs.h:519 [inline] driver_remove_file+0x40/0x50 drivers/base/driver.c:122 usb_remove_newid_files drivers/usb/core/driver.c:212 [inline] usb_deregister+0x12a/0x3b0 drivers/usb/core/driver.c:1005 cpia2_exit+0xa/0x16 [cpia2] __do_sys_delete_module kernel/module.c:1018 [inline] __se_sys_delete_module kernel/module.c:961 [inline] __x64_sys_delete_module+0x3dc/0x5e0 kernel/module.c:961 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x462e99 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f86f3754c58 EFLAGS: 00000246 ORIG_RAX: 00000000000000b0 RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462e99 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000020000300 RBP: 0000000000000002 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f86f37556bc R13: 00000000004bcca9 R14: 00000000006f6b48 R15: 00000000ffffffff

Allocated by task 8363: set_track mm/kasan/common.c:85 [inline] __kasan_kmalloc.constprop.3+0xa0/0xd0 mm/kasan/common.c:495 kmalloc include/linux/slab.h:545 [inline] kzalloc include/linux/slab.h:740 [inline] bus_add_driver+0xc0/0x610 drivers/base/bus.c:651 driver_register+0x1bb/0x3f0 drivers/base/driver.c:170 usb_register_driver+0x267/0x520 drivers/usb/core/driver.c:965 0xffffffffc1b4817c do_one_initcall+0xfa/0x5ca init/main.c:887 do_init_module+0x204/0x5f6 kernel/module.c:3460 load_module+0x66b2/0x8570 kernel/module.c:3808 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 8363: set_track mm/kasan/common.c:85 [inline] __kasan_slab_free+0x130/0x180 mm/kasan/common.c:457 slab_free_hook mm/slub.c:1430 [inline] slab_free_freelist_hook mm/slub.c:1457 [inline] slab_free mm/slub.c:3005 [inline] kfree+0xe1/0x270 mm/slub.c:3957 kobject_cleanup lib/kobject.c:662 [inline] kobject_release lib/kobject.c:691 [inline] kref_put include/linux/kref.h:67 [inline] kobject_put+0x146/0x240 lib/kobject.c:708 bus_remove_driver+0x10e/0x220 drivers/base/bus.c:732 driver_unregister+0x6c/0xa0 drivers/base/driver.c:197 usb_register_driver+0x341/0x520 drivers/usb/core/driver.c:980 0xffffffffc1b4817c do_one_initcall+0xfa/0x5ca init/main.c:887 do_init_module+0x204/0x5f6 kernel/module.c:3460 load_module+0x66b2/0x8570 kernel/module.c:3808 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8881f59a6b40 which belongs to the cache kmalloc-256 of size 256 The buggy address is located 48 bytes inside of 256-byte region [ffff8881f59a6b40, ffff8881f59a6c40) The buggy address belongs to the page: page:ffffea0007d66980 count:1 mapcount:0 mapping:ffff8881f6c02e00 index:0x0 flags: 0x2fffc0000000200(slab) raw: 02fffc0000000200 dead000000000100 dead000000000200 ffff8881f6c02e00 raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff8881f59a6a00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff8881f59a6a80: 00 00 00 00 00 00 00 00 00 00 fc fc fc fc fc fc

ffff8881f59a6b00: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb

^ ffff8881f59a6b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8881f59a6c00: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc

cpia2_init does not check return value of cpia2_init, if it failed in usb_register_driver, there is already cleanup using driver_unregister. No need call cpia2_usb_cleanup on module exit.

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: YueHaibing yuehaibing@huawei.com Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/usb/cpia2/cpia2_v4l.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/media/usb/cpia2/cpia2_v4l.c +++ b/drivers/media/usb/cpia2/cpia2_v4l.c @@ -1244,8 +1244,7 @@ static int __init cpia2_init(void) LOG("%s v%s\n", ABOUT, CPIA_VERSION); check_parameters(); - cpia2_usb_init(); - return 0; + return cpia2_usb_init(); }

From: Hans Verkuil hverkuil@xs4all.nl

commit d65842f7126aa1a87fb44b7c9980c12630ed4f33 upstream.

Calling VIDIOC_DQBUF can release the core serialization lock pointed to by vb2_queue->lock if it has to wait for a new buffer to arrive.

However, if userspace dup()ped the video device filehandle, then it is possible to read or call DQBUF from two filehandles at the same time.

It is also possible to call REQBUFS from one filehandle while the other is waiting for a buffer. This will remove all the buffers and reallocate new ones. Removing all the buffers isn't the problem here (that's already handled correctly by DQBUF), but the reallocating part is: DQBUF isn't aware that the buffers have changed.

This is fixed by setting a flag whenever the lock is released while waiting for a buffer to arrive. And checking the flag where needed so we can return -EBUSY.

Signed-off-by: Hans Verkuil hverkuil@xs4all.nl Reported-by: Syzbot syzbot+4180ff9ca6810b06c1e9@syzkaller.appspotmail.com Reviewed-by: Tomasz Figa tfiga@chromium.org Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/common/videobuf2/videobuf2-core.c | 22 ++++++++++++++++++++++ include/media/videobuf2-core.h | 1 + 2 files changed, 23 insertions(+)

--- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -668,6 +668,11 @@ int vb2_core_reqbufs(struct vb2_queue *q return -EBUSY; }

+ if (q->waiting_in_dqbuf && *count) { + dprintk(1, "another dup()ped fd is waiting for a buffer\n"); + return -EBUSY; + } + if (*count == 0 || q->num_buffers != 0 || (q->memory != VB2_MEMORY_UNKNOWN && q->memory != memory)) { /* @@ -797,6 +802,10 @@ int vb2_core_create_bufs(struct vb2_queu }

if (!q->num_buffers) { + if (q->waiting_in_dqbuf && *count) { + dprintk(1, "another dup()ped fd is waiting for a buffer\n"); + return -EBUSY; + } memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); q->memory = memory; q->waiting_for_buffers = !q->is_output; @@ -1466,6 +1475,11 @@ static int __vb2_wait_for_done_vb(struct for (;;) { int ret;

+ if (q->waiting_in_dqbuf) { + dprintk(1, "another dup()ped fd is waiting for a buffer\n"); + return -EBUSY; + } + if (!q->streaming) { dprintk(1, "streaming off, will not wait for buffers\n"); return -EINVAL; @@ -1493,6 +1507,7 @@ static int __vb2_wait_for_done_vb(struct return -EAGAIN; }

+ q->waiting_in_dqbuf = 1; /* * We are streaming and blocking, wait for another buffer to * become ready or for streamoff. Driver's lock is released to @@ -1513,6 +1528,7 @@ static int __vb2_wait_for_done_vb(struct * the locks or return an error if one occurred. */ call_void_qop(q, wait_finish, q); + q->waiting_in_dqbuf = 0; if (ret) { dprintk(1, "sleep was interrupted\n"); return ret; @@ -2361,6 +2377,12 @@ static size_t __vb2_perform_fileio(struc if (!data) return -EINVAL;

+ if (q->waiting_in_dqbuf) { + dprintk(3, "another dup()ped fd is %s\n", + read ? "reading" : "writing"); + return -EBUSY; + } + /* * Initialize emulator on first call. */ --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -551,6 +551,7 @@ struct vb2_queue { unsigned int start_streaming_called:1; unsigned int error:1; unsigned int waiting_for_buffers:1; + unsigned int waiting_in_dqbuf:1; unsigned int is_multiplanar:1; unsigned int is_output:1; unsigned int copy_timestamp:1;

From: YueHaibing yuehaibing@huawei.com

commit b2c01aab9646ed8ffb7c549afe55d5349c482425 upstream.

Syzkaller report this:

kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN PTI CPU: 0 PID: 4492 Comm: syz-executor.0 Not tainted 5.0.0-rc7+ #45 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 RIP: 0010:sysfs_remove_file_ns+0x27/0x70 fs/sysfs/file.c:468 Code: 00 00 00 41 54 55 48 89 fd 53 49 89 d4 48 89 f3 e8 ee 76 9c ff 48 8d 7d 30 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <80> 3c 02 00 75 2d 48 89 da 48 b8 00 00 00 00 00 fc ff df 48 8b 6d RSP: 0018:ffff8881e9d9fc00 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: ffffffff900367e0 RCX: ffffffff81a95952 RDX: 0000000000000006 RSI: ffffc90001405000 RDI: 0000000000000030 RBP: 0000000000000000 R08: fffffbfff1fa22ed R09: fffffbfff1fa22ed R10: 0000000000000001 R11: fffffbfff1fa22ec R12: 0000000000000000 R13: ffffffffc1abdac0 R14: 1ffff1103d3b3f8b R15: 0000000000000000 FS: 00007fe409dc1700(0000) GS:ffff8881f1200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2d721000 CR3: 00000001e98b6005 CR4: 00000000007606f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: sysfs_remove_file include/linux/sysfs.h:519 [inline] driver_remove_file+0x40/0x50 drivers/base/driver.c:122 pcmcia_remove_newid_file drivers/pcmcia/ds.c:163 [inline] pcmcia_unregister_driver+0x7d/0x2b0 drivers/pcmcia/ds.c:209 ssb_modexit+0xa/0x1b [ssb] __do_sys_delete_module kernel/module.c:1018 [inline] __se_sys_delete_module kernel/module.c:961 [inline] __x64_sys_delete_module+0x3dc/0x5e0 kernel/module.c:961 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x462e99 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fe409dc0c58 EFLAGS: 00000246 ORIG_RAX: 00000000000000b0 RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462e99 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00000000200000c0 RBP: 0000000000000002 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fe409dc16bc R13: 00000000004bccaa R14: 00000000006f6bc8 R15: 00000000ffffffff Modules linked in: ssb(-) 3c59x nvme_core macvlan tap pata_hpt3x3 rt2x00pci null_blk tsc40 pm_notifier_error_inject notifier_error_inject mdio cdc_wdm nf_reject_ipv4 ath9k_common ath9k_hw ath pppox ppp_generic slhc ehci_platform wl12xx wlcore tps6507x_ts ioc4 nf_synproxy_core ide_gd_mod ax25 can_dev iwlwifi can_raw atm tm2_touchkey can_gw can sundance adp5588_keys rt2800mmio rt2800lib rt2x00mmio rt2x00lib eeprom_93cx6 pn533 lru_cache elants_i2c ip_set nfnetlink gameport tipc hampshire nhc_ipv6 nhc_hop nhc_udp nhc_fragment nhc_routing nhc_mobility nhc_dest 6lowpan silead brcmutil nfc mt76_usb mt76 mac80211 iptable_security iptable_raw iptable_mangle iptable_nat nf_nat_ipv4 nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 iptable_filter bpfilter ip6_vti ip_gre sit hsr veth vxcan batman_adv cfg80211 rfkill chnl_net caif nlmon vcan bridge stp llc ip6_gre ip6_tunnel tunnel6 tun joydev mousedev serio_raw ide_pci_generic piix floppy ide_core sch_fq_codel ip_tables x_tables ipv6 [last unloaded: 3c59x] Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace 3913cbf8011e1c05 ]---

In ssb_modinit, it does not fail SSB init when ssb_host_pcmcia_init failed, however in ssb_modexit, ssb_host_pcmcia_exit calls pcmcia_unregister_driver unconditionally, which may tigger a NULL pointer dereference issue as above.

Reported-by: Hulk Robot hulkci@huawei.com Fixes: 399500da18f7 ("ssb: pick PCMCIA host code support from b43 driver") Signed-off-by: YueHaibing yuehaibing@huawei.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/ssb/bridge_pcmcia_80211.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

--- a/drivers/ssb/bridge_pcmcia_80211.c +++ b/drivers/ssb/bridge_pcmcia_80211.c @@ -113,16 +113,21 @@ static struct pcmcia_driver ssb_host_pcm .resume = ssb_host_pcmcia_resume, };

+static int pcmcia_init_failed; + /* * These are not module init/exit functions! * The module_pcmcia_driver() helper cannot be used here. */ int ssb_host_pcmcia_init(void) { - return pcmcia_register_driver(&ssb_host_pcmcia_driver); + pcmcia_init_failed = pcmcia_register_driver(&ssb_host_pcmcia_driver); + + return pcmcia_init_failed; }

void ssb_host_pcmcia_exit(void) { - pcmcia_unregister_driver(&ssb_host_pcmcia_driver); + if (!pcmcia_init_failed) + pcmcia_unregister_driver(&ssb_host_pcmcia_driver); }

From: Linus Lüssing linus.luessing@c0d3.blue

commit a3c7cd0cdf1107f891aff847ad481e34df727055 upstream.

Syzbot has reported some issues with the locking assumptions made for the multicast tt/tvlv worker: It was able to trigger the WARN_ON() in batadv_mcast_mla_tt_retract() and batadv_mcast_mla_tt_add(). While hard/not reproduceable for us so far it seems that the delayed_work_pending() we use might not be quite safe from reordering.

Therefore this patch adds an explicit, new spinlock to protect the update of the mla_list and flags in bat_priv and then removes the WARN_ON(delayed_work_pending()).

Reported-by: syzbot+83f2d54ec6b7e417e13f@syzkaller.appspotmail.com Reported-by: syzbot+050927a651272b145a5d@syzkaller.appspotmail.com Reported-by: syzbot+979ffc89b87309b1b94b@syzkaller.appspotmail.com Reported-by: syzbot+f9f3f388440283da2965@syzkaller.appspotmail.com Fixes: cbebd363b2e9 ("batman-adv: Use own timer for multicast TT and TVLV updates") Signed-off-by: Linus Lüssing linus.luessing@c0d3.blue Signed-off-by: Sven Eckelmann sven@narfation.org Signed-off-by: Simon Wunderlich sw@simonwunderlich.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/batman-adv/main.c | 1 + net/batman-adv/multicast.c | 11 +++-------- net/batman-adv/types.h | 5 +++++ 3 files changed, 9 insertions(+), 8 deletions(-)

--- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -160,6 +160,7 @@ int batadv_mesh_init(struct net_device * spin_lock_init(&bat_priv->tt.commit_lock); spin_lock_init(&bat_priv->gw.list_lock); #ifdef CONFIG_BATMAN_ADV_MCAST + spin_lock_init(&bat_priv->mcast.mla_lock); spin_lock_init(&bat_priv->mcast.want_lists_lock); #endif spin_lock_init(&bat_priv->tvlv.container_list_lock); --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -325,8 +325,6 @@ static void batadv_mcast_mla_list_free(s * translation table except the ones listed in the given mcast_list. * * If mcast_list is NULL then all are retracted. - * - * Do not call outside of the mcast worker! (or cancel mcast worker first) */ static void batadv_mcast_mla_tt_retract(struct batadv_priv *bat_priv, struct hlist_head *mcast_list) @@ -334,8 +332,6 @@ static void batadv_mcast_mla_tt_retract( struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp;

- WARN_ON(delayed_work_pending(&bat_priv->mcast.work)); - hlist_for_each_entry_safe(mcast_entry, tmp, &bat_priv->mcast.mla_list, list) { if (mcast_list && @@ -359,8 +355,6 @@ static void batadv_mcast_mla_tt_retract( * * Adds multicast listener announcements from the given mcast_list to the * translation table if they have not been added yet. - * - * Do not call outside of the mcast worker! (or cancel mcast worker first) */ static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv, struct hlist_head *mcast_list) @@ -368,8 +362,6 @@ static void batadv_mcast_mla_tt_add(stru struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp;

- WARN_ON(delayed_work_pending(&bat_priv->mcast.work)); - if (!mcast_list) return;

@@ -658,7 +650,10 @@ static void batadv_mcast_mla_update(stru priv_mcast = container_of(delayed_work, struct batadv_priv_mcast, work); bat_priv = container_of(priv_mcast, struct batadv_priv, mcast);

+ spin_lock(&bat_priv->mcast.mla_lock); __batadv_mcast_mla_update(bat_priv); + spin_unlock(&bat_priv->mcast.mla_lock); + batadv_mcast_start_timer(bat_priv); }

--- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1216,6 +1216,11 @@ struct batadv_priv_mcast { unsigned char bridged:1;

/** + * @mla_lock: a lock protecting mla_list and mla_flags + */ + spinlock_t mla_lock; + + /** * @num_want_all_unsnoopables: number of nodes wanting unsnoopable IP * traffic */

From: Al Viro viro@zeniv.linux.org.uk

commit 9419a3191dcb27f24478d288abaab697228d28e6 upstream.

What happens there is that we are replacing file->path.mnt of a file we'd just opened with a clone and we need the write count contribution to be transferred from original mount to new one. That's it. We do *NOT* want any kind of freeze protection for the duration of switchover.

IOW, we should just use __mnt_{want,drop}_write() for that switchover; no need to bother with mnt_{want,drop}_write() there.

Tested-by: Amir Goldstein amir73il@gmail.com Reported-by: syzbot+2a73a6ea9507b7112141@syzkaller.appspotmail.com Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/internal.h | 2 -- include/linux/mount.h | 2 ++ kernel/acct.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-)

--- a/fs/internal.h +++ b/fs/internal.h @@ -80,9 +80,7 @@ extern int sb_prepare_remount_readonly(s

extern void __init mnt_init(void);

-extern int __mnt_want_write(struct vfsmount *); extern int __mnt_want_write_file(struct file *); -extern void __mnt_drop_write(struct vfsmount *); extern void __mnt_drop_write_file(struct file *);

/* --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -86,6 +86,8 @@ extern bool mnt_may_suid(struct vfsmount

struct path; extern struct vfsmount *clone_private_mount(const struct path *path); +extern int __mnt_want_write(struct vfsmount *); +extern void __mnt_drop_write(struct vfsmount *);

struct file_system_type; extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, --- a/kernel/acct.c +++ b/kernel/acct.c @@ -227,7 +227,7 @@ static int acct_on(struct filename *path filp_close(file, NULL); return PTR_ERR(internal); } - err = mnt_want_write(internal); + err = __mnt_want_write(internal); if (err) { mntput(internal); kfree(acct); @@ -252,7 +252,7 @@ static int acct_on(struct filename *path old = xchg(&ns->bacct, &acct->pin); mutex_unlock(&acct->lock); pin_kill(old); - mnt_drop_write(mnt); + __mnt_drop_write(mnt); mntput(mnt); return 0; }

[ Upstream commit 7881ef3f33bb80f459ea6020d1e021fc524a6348 ]

Under certain conditions, lru_count may drop below zero resulting in a large amount of log spam like this:

vmscan: shrink_slab: gfs2_dump_glock+0x3b0/0x630 [gfs2] \ negative objects to delete nr=-1

This happens as follows: 1) A glock is moved from lru_list to the dispose list and lru_count is decremented. 2) The dispose function calls cond_resched() and drops the lru lock. 3) Another thread takes the lru lock and tries to add the same glock to lru_list, checking if the glock is on an lru list. 4) It is on a list (actually the dispose list) and so it avoids incrementing lru_count. 5) The glock is moved to lru_list. 5) The original thread doesn't dispose it because it has been re-added to the lru list but the lru_count has still decreased by one.

Fix by checking if the LRU flag is set on the glock rather than checking if the glock is on some list and rearrange the code so that the LRU flag is added/removed precisely when the glock is added/removed from lru_list.

Signed-off-by: Ross Lagerwall ross.lagerwall@citrix.com Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/gfs2/glock.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 9d566e62684c2..775256141e9fb 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -183,15 +183,19 @@ static int demote_ok(const struct gfs2_glock *gl)

void gfs2_glock_add_to_lru(struct gfs2_glock *gl) { + if (!(gl->gl_ops->go_flags & GLOF_LRU)) + return; + spin_lock(&lru_lock);

- if (!list_empty(&gl->gl_lru)) - list_del_init(&gl->gl_lru); - else + list_del(&gl->gl_lru); + list_add_tail(&gl->gl_lru, &lru_list); + + if (!test_bit(GLF_LRU, &gl->gl_flags)) { + set_bit(GLF_LRU, &gl->gl_flags); atomic_inc(&lru_count); + }

- list_add_tail(&gl->gl_lru, &lru_list); - set_bit(GLF_LRU, &gl->gl_flags); spin_unlock(&lru_lock); }

@@ -201,7 +205,7 @@ static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) return;

spin_lock(&lru_lock); - if (!list_empty(&gl->gl_lru)) { + if (test_bit(GLF_LRU, &gl->gl_flags)) { list_del_init(&gl->gl_lru); atomic_dec(&lru_count); clear_bit(GLF_LRU, &gl->gl_flags); @@ -1158,8 +1162,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh) !test_bit(GLF_DEMOTE, &gl->gl_flags)) fast_path = 1; } - if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl) && - (glops->go_flags & GLOF_LRU)) + if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl)) gfs2_glock_add_to_lru(gl);

trace_gfs2_glock_queue(gh, 0); @@ -1455,6 +1458,7 @@ __acquires(&lru_lock) if (!spin_trylock(&gl->gl_lockref.lock)) { add_back_to_lru: list_add(&gl->gl_lru, &lru_list); + set_bit(GLF_LRU, &gl->gl_flags); atomic_inc(&lru_count); continue; } @@ -1462,7 +1466,6 @@ __acquires(&lru_lock) spin_unlock(&gl->gl_lockref.lock); goto add_back_to_lru; } - clear_bit(GLF_LRU, &gl->gl_flags); gl->gl_lockref.count++; if (demote_ok(gl)) handle_callback(gl, LM_ST_UNLOCKED, 0, false); @@ -1497,6 +1500,7 @@ static long gfs2_scan_glock_lru(int nr) if (!test_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); + clear_bit(GLF_LRU, &gl->gl_flags); freed++; continue; }

[ Upstream commit 950a578c6128c2886e295b9c7ecb0b6b22fcc92b ]

Actually we don't do anything with return value from nfs_wait_client_init_complete in nfs_match_client, as a consequence if we get a fatal signal and client is not fully initialised, we'll loop to "again" label

This has been proven to cause soft lockups on some scenarios (no-carrier but configured network interfaces)

Signed-off-by: Roberto Bergantinos Corpas rbergant@redhat.com Reviewed-by: Benjamin Coddington bcodding@redhat.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/client.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 751ca65da8a35..846d45cb1a3c8 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -290,6 +290,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat struct nfs_client *clp; const struct sockaddr *sap = data->addr; struct nfs_net *nn = net_generic(data->net, nfs_net_id); + int error;

again: list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { @@ -302,8 +303,10 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat if (clp->cl_cons_state > NFS_CS_READY) { refcount_inc(&clp->cl_count); spin_unlock(&nn->nfs_client_lock); - nfs_wait_client_init_complete(clp); + error = nfs_wait_client_init_complete(clp); nfs_put_client(clp); + if (error < 0) + return ERR_PTR(error); spin_lock(&nn->nfs_client_lock); goto again; } @@ -413,6 +416,8 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) clp = nfs_match_client(cl_init); if (clp) { spin_unlock(&nn->nfs_client_lock); + if (IS_ERR(clp)) + return clp; if (new) new->rpc_ops->free_client(new); return nfs_found_client(cl_init, clp);

[ Upstream commit 9287c6452d2b1f24ea8e84bd3cf6f3c6f267f712 ]

This patch has to do with the life cycle of glocks and buffers. When gfs2 metadata or journaled data is queued to be written, a gfs2_bufdata object is assigned to track the buffer, and that is queued to various lists, including the glock's gl_ail_list to indicate it's on the active items list. Once the page associated with the buffer has been written, it is removed from the ail list, but its life isn't over until a revoke has been successfully written.

So after the block is written, its bufdata object is moved from the glock's gl_ail_list to a file-system-wide list of pending revokes, sd_log_le_revoke. At that point the glock still needs to track how many revokes it contributed to that list (in gl_revokes) so that things like glock go_sync can ensure all the metadata has been not only written, but also revoked before the glock is granted to a different node. This is to guarantee journal replay doesn't replay the block once the glock has been granted to another node.

Ross Lagerwall recently discovered a race in which an inode could be evicted, and its glock freed after its ail list had been synced, but while it still had unwritten revokes on the sd_log_le_revoke list. The evict decremented the glock reference count to zero, which allowed the glock to be freed. After the revoke was written, function revoke_lo_after_commit tried to adjust the glock's gl_revokes counter and clear its GLF_LFLUSH flag, at which time it referenced the freed glock.

This patch fixes the problem by incrementing the glock reference count in gfs2_add_revoke when the glock's first bufdata object is moved from the glock to the global revokes list. Later, when the glock's last such bufdata object is freed, the reference count is decremented. This guarantees that whichever process finishes last (the revoke writing or the evict) will properly free the glock, and neither will reference the glock after it has been freed.

Reported-by: Ross Lagerwall ross.lagerwall@citrix.com Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Signed-off-by: Bob Peterson rpeterso@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/gfs2/glock.c | 1 + fs/gfs2/log.c | 3 ++- fs/gfs2/lops.c | 6 ++++-- 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 775256141e9fb..ccdd8c821abd7 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -140,6 +140,7 @@ void gfs2_glock_free(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;

+ BUG_ON(atomic_read(&gl->gl_revokes)); rhashtable_remove_fast(&gl_hash_table, &gl->gl_node, ht_parms); smp_mb(); wake_up_glock(gl); diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index ee20ea42e7b59..cd85092723dea 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -604,7 +604,8 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) bd->bd_bh = NULL; bd->bd_ops = &gfs2_revoke_lops; sdp->sd_log_num_revoke++; - atomic_inc(&gl->gl_revokes); + if (atomic_inc_return(&gl->gl_revokes) == 1) + gfs2_glock_hold(gl); set_bit(GLF_LFLUSH, &gl->gl_flags); list_add(&bd->bd_list, &sdp->sd_log_le_revoke); } diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index f2567f958d002..8f99b395d7bf6 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -662,8 +662,10 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) bd = list_entry(head->next, struct gfs2_bufdata, bd_list); list_del_init(&bd->bd_list); gl = bd->bd_gl; - atomic_dec(&gl->gl_revokes); - clear_bit(GLF_LFLUSH, &gl->gl_flags); + if (atomic_dec_return(&gl->gl_revokes) == 0) { + clear_bit(GLF_LFLUSH, &gl->gl_flags); + gfs2_glock_queue_put(gl); + } kmem_cache_free(gfs2_bufdata_cachep, bd); } }

[ Upstream commit ca31ca8247e2d3807ff5fa1d1760616a2292001c ]

When build perf for ARC recently, there was a build failure due to lack of __NR_bpf.

| Auto-detecting system features: | | ... get_cpuid: [ OFF ] | ... bpf: [ on ] | | # error __NR_bpf not defined. libbpf does not support your arch. ^~~~~ | bpf.c: In function 'sys_bpf': | bpf.c:66:17: error: '__NR_bpf' undeclared (first use in this function) | return syscall(__NR_bpf, cmd, attr, size); | ^~~~~~~~ | sys_bpf

Signed-off-by: Vineet Gupta vgupta@synopsys.com Acked-by: Yonghong Song yhs@fb.com Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/lib/bpf/bpf.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 7a0014794bff7..dd0b68d1f4be0 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -53,6 +53,8 @@ # define __NR_bpf 349 # elif defined(__s390__) # define __NR_bpf 351 +# elif defined(__arc__) +# define __NR_bpf 280 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif

[ Upstream commit a7d006714724de4334c5e3548701b33f7b12ca96 ]

tools/bpf/bpftool/.gitignore has the "bpftool" pattern, which is intended to ignore the following build artifact:

tools/bpf/bpftool/bpftool

However, the .gitignore entry is effective not only for the current directory, but also for any sub-directories.

So, from the point of .gitignore grammar, the following check-in file is also considered to be ignored:

tools/bpf/bpftool/bash-completion/bpftool

As the manual gitignore(5) says "Files already tracked by Git are not affected", this is not a problem as far as Git is concerned.

However, Git is not the only program that parses .gitignore because .gitignore is useful to distinguish build artifacts from source files.

For example, tar(1) supports the --exclude-vcs-ignore option. As of writing, this option does not work perfectly, but it intends to create a tarball excluding files specified by .gitignore.

So, I believe it is better to fix this issue.

You can fix it by prefixing the pattern with a slash; the leading slash means the specified pattern is relative to the current directory.

Signed-off-by: Masahiro Yamada yamada.masahiro@socionext.com Reviewed-by: Quentin Monnet quentin.monnet@netronome.com Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/bpf/bpftool/.gitignore | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore index 67167e44b7266..8248b8dd89d4b 100644 --- a/tools/bpf/bpftool/.gitignore +++ b/tools/bpf/bpftool/.gitignore @@ -1,5 +1,5 @@ *.d -bpftool +/bpftool bpftool*.8 bpf-helpers.* FEATURE-DUMP.bpftool

[ Upstream commit f913308879bc6ae437ce64d878c7b05643ddea44 ]

GCC 8 contains a number of new warnings as well as enhancements to existing checkers. The warning - Wstringop-truncation - warns for calls to bounded string manipulation functions such as strncat, strncpy, and stpncpy that may either truncate the copied string or leave the destination unchanged.

In our case the destination string length (32 bytes) is much shorter than the source string (64 bytes) which causes this warning to show up. In general the destination has to be at least a byte larger than the length of the source string with strncpy for this warning not to showup.

This can be easily fixed by using strlcpy instead which already does the truncation to the string. Documentation for this function can be found here:

https://elixir.bootlin.com/linux/latest/source/lib/string.c#L141

Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Sameeh Jubran sameehj@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 1b5f591cf0a23..b5d72815776cb 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2223,7 +2223,7 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev)

host_info->os_type = ENA_ADMIN_OS_LINUX; host_info->kernel_ver = LINUX_VERSION_CODE; - strncpy(host_info->kernel_ver_str, utsname()->version, + strlcpy(host_info->kernel_ver_str, utsname()->version, sizeof(host_info->kernel_ver_str) - 1); host_info->os_dist = 0; strncpy(host_info->os_dist_str, utsname()->release,

[ Upstream commit f80c5dad7b6467b884c445ffea45985793b4b2d0 ]

This commit makes the kernel not send the next queued HCI command until a command complete arrives for the last HCI command sent to the controller. This change avoids a problem with some buggy controllers (seen on two SKUs of QCA9377) that send an extra command complete event for the previous command after the kernel had already sent a new HCI command to the controller.

The problem was reproduced when starting an active scanning procedure, where an extra command complete event arrives for the LE_SET_RANDOM_ADDR command. When this happends the kernel ends up not processing the command complete for the following commmand, LE_SET_SCAN_PARAM, and ultimately behaving as if a passive scanning procedure was being performed, when in fact controller is performing an active scanning procedure. This makes it impossible to discover BLE devices as no device found events are sent to userspace.

This problem is reproducible on 100% of the attempts on the affected controllers. The extra command complete event can be seen at timestamp 27.420131 on the btmon logs bellow.

Bluetooth monitor ver 5.50 = Note: Linux version 5.0.0+ (x86_64) 0.352340 = Note: Bluetooth subsystem version 2.22 0.352343 = New Index: 80:C5:F2:8F:87:84 (Primary,USB,hci0) [hci0] 0.352344 = Open Index: 80:C5:F2:8F:87:84 [hci0] 0.352345 = Index Info: 80:C5:F2:8F:87:84 (Qualcomm) [hci0] 0.352346 @ MGMT Open: bluetoothd (privileged) version 1.14 {0x0001} 0.352347 @ MGMT Open: btmon (privileged) version 1.14 {0x0002} 0.352366 @ MGMT Open: btmgmt (privileged) version 1.14 {0x0003} 27.302164 @ MGMT Command: Start Discovery (0x0023) plen 1 {0x0003} [hci0] 27.302310 Address type: 0x06 LE Public LE Random < HCI Command: LE Set Random Address (0x08|0x0005) plen 6 #1 [hci0] 27.302496 Address: 15:60:F2:91:B2:24 (Non-Resolvable)

HCI Event: Command Complete (0x0e) plen 4 #2 [hci0] 27.419117

LE Set Random Address (0x08|0x0005) ncmd 1 Status: Success (0x00) < HCI Command: LE Set Scan Parameters (0x08|0x000b) plen 7 #3 [hci0] 27.419244 Type: Active (0x01) Interval: 11.250 msec (0x0012) Window: 11.250 msec (0x0012) Own address type: Random (0x01) Filter policy: Accept all advertisement (0x00)

HCI Event: Command Complete (0x0e) plen 4 #4 [hci0] 27.420131

LE Set Random Address (0x08|0x0005) ncmd 1 Status: Success (0x00) < HCI Command: LE Set Scan Enable (0x08|0x000c) plen 2 #5 [hci0] 27.420259 Scanning: Enabled (0x01) Filter duplicates: Enabled (0x01)

HCI Event: Command Complete (0x0e) plen 4 #6 [hci0] 27.420969

LE Set Scan Parameters (0x08|0x000b) ncmd 1 Status: Success (0x00)

HCI Event: Command Complete (0x0e) plen 4 #7 [hci0] 27.421983

LE Set Scan Enable (0x08|0x000c) ncmd 1 Status: Success (0x00) @ MGMT Event: Command Complete (0x0001) plen 4 {0x0003} [hci0] 27.422059 Start Discovery (0x0023) plen 1 Status: Success (0x00) Address type: 0x06 LE Public LE Random @ MGMT Event: Discovering (0x0013) plen 2 {0x0003} [hci0] 27.422067 Address type: 0x06 LE Public LE Random Discovery: Enabled (0x01) @ MGMT Event: Discovering (0x0013) plen 2 {0x0002} [hci0] 27.422067 Address type: 0x06 LE Public LE Random Discovery: Enabled (0x01) @ MGMT Event: Discovering (0x0013) plen 2 {0x0001} [hci0] 27.422067 Address type: 0x06 LE Public LE Random Discovery: Enabled (0x01)

Signed-off-by: João Paulo Rechi Vita jprvita@endlessm.com Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/bluetooth/hci.h | 1 + net/bluetooth/hci_core.c | 5 +++++ net/bluetooth/hci_event.c | 12 ++++++++++++ net/bluetooth/hci_request.c | 5 +++++ net/bluetooth/hci_request.h | 1 + 5 files changed, 24 insertions(+)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index cdd9f1fe7cfa9..845d947dbae82 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -270,6 +270,7 @@ enum { HCI_FORCE_BREDR_SMP, HCI_FORCE_STATIC_ADDR, HCI_LL_RPA_RESOLUTION, + HCI_CMD_PENDING,

__HCI_NUM_FLAGS, }; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index a06f030477173..5afd67ef797a6 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -4274,6 +4274,9 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, return; }

+ /* If we reach this point this event matches the last command sent */ + hci_dev_clear_flag(hdev, HCI_CMD_PENDING); + /* If the command succeeded and there's still more commands in * this request the request is not yet complete. */ @@ -4384,6 +4387,8 @@ static void hci_cmd_work(struct work_struct *work)

hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); if (hdev->sent_cmd) { + if (hci_req_status_pend(hdev)) + hci_dev_set_flag(hdev, HCI_CMD_PENDING); atomic_dec(&hdev->cmd_cnt); hci_send_frame(hdev, skb); if (test_bit(HCI_RESET, &hdev->flags)) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 7f800c3480f7a..3e7badb3ac2d5 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3357,6 +3357,12 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_req_cmd_complete(hdev, *opcode, *status, req_complete, req_complete_skb);

+ if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) { + bt_dev_err(hdev, + "unexpected event for opcode 0x%4.4x", *opcode); + return; + } + if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q)) queue_work(hdev->workqueue, &hdev->cmd_work); } @@ -3464,6 +3470,12 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_req_cmd_complete(hdev, *opcode, ev->status, req_complete, req_complete_skb);

+ if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) { + bt_dev_err(hdev, + "unexpected event for opcode 0x%4.4x", *opcode); + return; + } + if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q)) queue_work(hdev->workqueue, &hdev->cmd_work); } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index e8c9ef1e19227..9448ebd3780a3 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -46,6 +46,11 @@ void hci_req_purge(struct hci_request *req) skb_queue_purge(&req->cmd_q); }

+bool hci_req_status_pend(struct hci_dev *hdev) +{ + return hdev->req_status == HCI_REQ_PEND; +} + static int req_run(struct hci_request *req, hci_req_complete_t complete, hci_req_complete_skb_t complete_skb) { diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index 692cc8b133682..55b2050cc9ff0 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -37,6 +37,7 @@ struct hci_request {

void hci_req_init(struct hci_request *req, struct hci_dev *hdev); void hci_req_purge(struct hci_request *req); +bool hci_req_status_pend(struct hci_dev *hdev); int hci_req_run(struct hci_request *req, hci_req_complete_t complete); int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete); void hci_req_add(struct hci_request *req, u16 opcode, u32 plen,

[ Upstream commit 16ec5dfe0327ddcf279957bffe4c8fe527088c63 ]

On kbl_rt5663_max98927, commit 38a5882e4292 ("ASoC: Intel: kbl_rt5663_max98927: Map BTN_0 to KEY_PLAYPAUSE") This key pair mapping to play/pause when playing Youtube

The Android 3.5mm Headset jack specification mentions that BTN_0 should be mapped to KEY_MEDIA, but this is less logical than KEY_PLAYPAUSE, which has much broader userspace support.

For example, the Chrome OS userspace now supports KEY_PLAYPAUSE to toggle play/pause of videos and audio, but does not handle KEY_MEDIA.

Furthermore, Android itself now supports KEY_PLAYPAUSE equivalently, as the new USB headset spec requires KEY_PLAYPAUSE for BTN_0. https://source.android.com/devices/accessories/headset/usb-headset-spec

The same fix is required on Chrome kbl_da7219_max98357a.

Signed-off-by: Mac Chiang mac.chiang@intel.com Reviewed-by: Benson Leung bleung@chromium.org Acked-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/intel/boards/kbl_da7219_max98357a.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/intel/boards/kbl_da7219_max98357a.c b/sound/soc/intel/boards/kbl_da7219_max98357a.c index 38f6ab74709d0..07491a0f8fb8b 100644 --- a/sound/soc/intel/boards/kbl_da7219_max98357a.c +++ b/sound/soc/intel/boards/kbl_da7219_max98357a.c @@ -188,7 +188,7 @@ static int kabylake_da7219_codec_init(struct snd_soc_pcm_runtime *rtd)

jack = &ctx->kabylake_headset;

- snd_jack_set_key(jack->jack, SND_JACK_BTN_0, KEY_MEDIA); + snd_jack_set_key(jack->jack, SND_JACK_BTN_0, KEY_PLAYPAUSE); snd_jack_set_key(jack->jack, SND_JACK_BTN_1, KEY_VOLUMEUP); snd_jack_set_key(jack->jack, SND_JACK_BTN_2, KEY_VOLUMEDOWN); snd_jack_set_key(jack->jack, SND_JACK_BTN_3, KEY_VOICECOMMAND);

[ Upstream commit 41a91c606e7d2b74358a944525267cc451c271e8 ]

dwc3_gadget_suspend() is called under dwc->lock spinlock. In such context calling synchronize_irq() is not allowed. Move the problematic call out of the protected block to fix the following kernel BUG during system suspend:

BUG: sleeping function called from invalid context at kernel/irq/manage.c:112 in_atomic(): 1, irqs_disabled(): 128, pid: 1601, name: rtcwake 6 locks held by rtcwake/1601: #0: f70ac2a2 (sb_writers#7){.+.+}, at: vfs_write+0x130/0x16c #1: b5fe1270 (&of->mutex){+.+.}, at: kernfs_fop_write+0xc0/0x1e4 #2: 7e597705 (kn->count#60){.+.+}, at: kernfs_fop_write+0xc8/0x1e4 #3: 8b3527d0 (system_transition_mutex){+.+.}, at: pm_suspend+0xc4/0xc04 #4: fc7f1c42 (&dev->mutex){....}, at: __device_suspend+0xd8/0x74c #5: 4b36507e (&(&dwc->lock)->rlock){....}, at: dwc3_gadget_suspend+0x24/0x3c irq event stamp: 11252 hardirqs last enabled at (11251): [<c09c54a4>] _raw_spin_unlock_irqrestore+0x6c/0x74 hardirqs last disabled at (11252): [<c09c4d44>] _raw_spin_lock_irqsave+0x1c/0x5c softirqs last enabled at (9744): [<c0102564>] __do_softirq+0x3a4/0x66c softirqs last disabled at (9737): [<c0128528>] irq_exit+0x140/0x168 Preemption disabled at: [<00000000>] (null) CPU: 7 PID: 1601 Comm: rtcwake Not tainted 5.0.0-rc3-next-20190122-00039-ga3f4ee4f8a52 #5252 Hardware name: SAMSUNG EXYNOS (Flattened Device Tree) [<c01110f0>] (unwind_backtrace) from [<c010d120>] (show_stack+0x10/0x14) [<c010d120>] (show_stack) from [<c09a4d04>] (dump_stack+0x90/0xc8) [<c09a4d04>] (dump_stack) from [<c014c700>] (___might_sleep+0x22c/0x2c8) [<c014c700>] (___might_sleep) from [<c0189d68>] (synchronize_irq+0x28/0x84) [<c0189d68>] (synchronize_irq) from [<c05cbbf8>] (dwc3_gadget_suspend+0x34/0x3c) [<c05cbbf8>] (dwc3_gadget_suspend) from [<c05bd020>] (dwc3_suspend_common+0x154/0x410) [<c05bd020>] (dwc3_suspend_common) from [<c05bd34c>] (dwc3_suspend+0x14/0x2c) [<c05bd34c>] (dwc3_suspend) from [<c051c730>] (platform_pm_suspend+0x2c/0x54) [<c051c730>] (platform_pm_suspend) from [<c05285d4>] (dpm_run_callback+0xa4/0x3dc) [<c05285d4>] (dpm_run_callback) from [<c0528a40>] (__device_suspend+0x134/0x74c) [<c0528a40>] (__device_suspend) from [<c052c508>] (dpm_suspend+0x174/0x588) [<c052c508>] (dpm_suspend) from [<c0182134>] (suspend_devices_and_enter+0xc0/0xe74) [<c0182134>] (suspend_devices_and_enter) from [<c0183658>] (pm_suspend+0x770/0xc04) [<c0183658>] (pm_suspend) from [<c0180ddc>] (state_store+0x6c/0xcc) [<c0180ddc>] (state_store) from [<c09a9a70>] (kobj_attr_store+0x14/0x20) [<c09a9a70>] (kobj_attr_store) from [<c02d6800>] (sysfs_kf_write+0x4c/0x50) [<c02d6800>] (sysfs_kf_write) from [<c02d594c>] (kernfs_fop_write+0xfc/0x1e4) [<c02d594c>] (kernfs_fop_write) from [<c02593d8>] (__vfs_write+0x2c/0x160) [<c02593d8>] (__vfs_write) from [<c0259694>] (vfs_write+0xa4/0x16c) [<c0259694>] (vfs_write) from [<c0259870>] (ksys_write+0x40/0x8c) [<c0259870>] (ksys_write) from [<c0101000>] (ret_fast_syscall+0x0/0x28) Exception stack(0xed55ffa8 to 0xed55fff0) ...

Fixes: 01c10880d242 ("usb: dwc3: gadget: synchronize_irq dwc irq in suspend") Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Signed-off-by: Felipe Balbi felipe.balbi@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/dwc3/core.c | 2 ++ drivers/usb/dwc3/gadget.c | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 4d5c7dda8f54d..05b9ccff7447a 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1591,6 +1591,7 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg) spin_lock_irqsave(&dwc->lock, flags); dwc3_gadget_suspend(dwc); spin_unlock_irqrestore(&dwc->lock, flags); + synchronize_irq(dwc->irq_gadget); dwc3_core_exit(dwc); break; case DWC3_GCTL_PRTCAP_HOST: @@ -1623,6 +1624,7 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg) spin_lock_irqsave(&dwc->lock, flags); dwc3_gadget_suspend(dwc); spin_unlock_irqrestore(&dwc->lock, flags); + synchronize_irq(dwc->irq_gadget); }

dwc3_otg_exit(dwc); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 524104eed8a71..65ba1038b1111 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -3277,8 +3277,6 @@ int dwc3_gadget_suspend(struct dwc3 *dwc) dwc3_disconnect_gadget(dwc); __dwc3_gadget_stop(dwc);

- synchronize_irq(dwc->irq_gadget); - return 0; }

[ Upstream commit a913e5e8b43be1d3897a141ce61c1ec071cad89c ]

Nest hardware counter memory resides in a per-chip reserve-memory. During nest_imc_event_init(), chip-id of the event-cpu is considered to calculate the base memory addresss for that cpu. Return, proper error condition if the chip_id calculated is invalid.

Reported-by: Dan Carpenter dan.carpenter@oracle.com Fixes: 885dcd709ba91 ("powerpc/perf: Add nest IMC PMU support") Reviewed-by: Madhavan Srinivasan maddy@linux.vnet.ibm.com Signed-off-by: Anju T Sudhakar anju@linux.vnet.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/perf/imc-pmu.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 1fafc32b12a0f..3cebfdf362116 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -496,6 +496,11 @@ static int nest_imc_event_init(struct perf_event *event) * Get the base memory addresss for this cpu. */ chip_id = cpu_to_chip_id(event->cpu); + + /* Return, if chip_id is not valid */ + if (chip_id < 0) + return -ENODEV; + pcni = pmu->mem_info; do { if (pcni->id == chip_id) {

[ Upstream commit 860b7d2286236170a36f94946d03ca9888d32571 ]

The data structure (i.e struct imc_mem_info) to hold the memory address information for nest imc units is allocated based on the number of nodes in the system.

nest_imc_event_init() traverse this struct array to calculate the memory base address for the event-cpu. If we fail to find a match for the event cpu's chip-id in imc_mem_info struct array, then the do-while loop will iterate until we crash.

Fix this by changing the loop exit condition based on the number of non zero vbase elements in the array, since the allocation is done for nr_chips + 1.

Reported-by: Dan Carpenter dan.carpenter@oracle.com Fixes: 885dcd709ba91 ("powerpc/perf: Add nest IMC PMU support") Signed-off-by: Anju T Sudhakar anju@linux.vnet.ibm.com Reviewed-by: Madhavan Srinivasan maddy@linux.vnet.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/perf/imc-pmu.c | 2 +- arch/powerpc/platforms/powernv/opal-imc.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 3cebfdf362116..5553226770748 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -508,7 +508,7 @@ static int nest_imc_event_init(struct perf_event *event) break; } pcni++; - } while (pcni); + } while (pcni->vbase != 0);

if (!flag) return -ENODEV; diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index 58a07948c76e7..3d27f02695e41 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -127,7 +127,7 @@ static int imc_get_mem_addr_nest(struct device_node *node, nr_chips)) goto error;

- pmu_ptr->mem_info = kcalloc(nr_chips, sizeof(*pmu_ptr->mem_info), + pmu_ptr->mem_info = kcalloc(nr_chips + 1, sizeof(*pmu_ptr->mem_info), GFP_KERNEL); if (!pmu_ptr->mem_info) goto error;

[ Upstream commit 29f2133717c527f492933b0622a4aafe0b3cbe9e ]

Calculate the divisor for the SCR (Serial Clock Rate), avoiding that the SSP transmission rate can be greater than the device rate.

When the division between the SSP clock and the device rate generates a reminder, we have to increment by one the divisor. In this way the resulting SSP clock will never be greater than the device SPI max frequency.

For example, with:

- ssp_clk = 50 MHz - dev freq = 15 MHz

without this patch the SSP clock will be greater than 15 MHz:

- 25 MHz for PXA25x_SSP and CE4100_SSP - 16,56 MHz for the others

Instead, with this patch, we have in both case an SSP clock of 12.5MHz, so the max rate of the SPI device clock is respected.

Signed-off-by: Flavio Suligoi f.suligoi@asem.it Reviewed-by: Jarkko Nikula jarkko.nikula@linux.intel.com Reviewed-by: Jarkko Nikula jarkko.nikula@linux.intel.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-pxa2xx.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index b624f6fb04ce5..729be74621e37 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -876,10 +876,14 @@ static unsigned int ssp_get_clk_div(struct driver_data *drv_data, int rate)

rate = min_t(int, ssp_clk, rate);

+ /* + * Calculate the divisor for the SCR (Serial Clock Rate), avoiding + * that the SSP transmission rate can be greater than the device rate + */ if (ssp->type == PXA25x_SSP || ssp->type == CE4100_SSP) - return (ssp_clk / (2 * rate) - 1) & 0xff; + return (DIV_ROUND_UP(ssp_clk, 2 * rate) - 1) & 0xff; else - return (ssp_clk / rate - 1) & 0xfff; + return (DIV_ROUND_UP(ssp_clk, rate) - 1) & 0xfff; }

static unsigned int pxa2xx_ssp_get_clk_div(struct driver_data *drv_data,

[ Upstream commit 23583f7795025e3c783b680d906509366b0906ad ]

When the DSDT tables expose devices with subdevices and a set of hierarchical _DSD properties, the data returned by acpi_get_next_subnode() is incorrect, with the results suggesting a bad pointer assignment. The parser works fine with device_nodes or data_nodes, but not with a combination of the two.

The problem is traced to an invalid pointer used when jumping from handling device_nodes to data nodes. The existing code looks for data nodes below the last subdevice found instead of the common root. Fix by forcing the acpi_device pointer to be derived from the same fwnode for the two types of subnodes.

This same problem of handling device and data nodes was already fixed in a similar way by 'commit bf4703fdd166 ("ACPI / property: fix data node parsing in acpi_get_next_subnode()")' but broken later by 'commit 34055190b19 ("ACPI / property: Add fwnode_get_next_child_node()")', so this should probably go to linux-stable all the way to 4.12

Signed-off-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/property.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 693cf05b0cc44..288673cff85ea 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -975,6 +975,14 @@ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, const struct acpi_data_node *data = to_acpi_data_node(fwnode); struct acpi_data_node *dn;

+ /* + * We can have a combination of device and data nodes, e.g. with + * hierarchical _DSD properties. Make sure the adev pointer is + * restored before going through data nodes, otherwise we will + * be looking for data_nodes below the last device found instead + * of the common fwnode shared by device_nodes and data_nodes. + */ + adev = to_acpi_device_node(fwnode); if (adev) head = &adev->data.subnodes; else if (data)

[ Upstream commit b5b5a27bee5884860798ffd0f08e611a3942064b ]

During probe, return the provided errors value instead of -ENODEV. This allows the driver to be deferred probed if needed.

Signed-off-by: Fabien Dessenne fabien.dessenne@st.com Acked-by: Hugues Fruchet hugues.fruchet@st.com Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/platform/stm32/stm32-dcmi.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c index 721564176d8c0..100a5922d75fd 100644 --- a/drivers/media/platform/stm32/stm32-dcmi.c +++ b/drivers/media/platform/stm32/stm32-dcmi.c @@ -1645,7 +1645,7 @@ static int dcmi_probe(struct platform_device *pdev) dcmi->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); if (IS_ERR(dcmi->rstc)) { dev_err(&pdev->dev, "Could not get reset control\n"); - return -ENODEV; + return PTR_ERR(dcmi->rstc); }

/* Get bus characteristics from devicetree */ @@ -1660,7 +1660,7 @@ static int dcmi_probe(struct platform_device *pdev) of_node_put(np); if (ret) { dev_err(&pdev->dev, "Could not parse the endpoint\n"); - return -ENODEV; + return ret; }

if (ep.bus_type == V4L2_MBUS_CSI2) { @@ -1673,8 +1673,9 @@ static int dcmi_probe(struct platform_device *pdev)

irq = platform_get_irq(pdev, 0); if (irq <= 0) { - dev_err(&pdev->dev, "Could not get irq\n"); - return -ENODEV; + if (irq != -EPROBE_DEFER) + dev_err(&pdev->dev, "Could not get irq\n"); + return irq; }

dcmi->res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1694,12 +1695,13 @@ static int dcmi_probe(struct platform_device *pdev) dev_name(&pdev->dev), dcmi); if (ret) { dev_err(&pdev->dev, "Unable to request irq %d\n", irq); - return -ENODEV; + return ret; }

mclk = devm_clk_get(&pdev->dev, "mclk"); if (IS_ERR(mclk)) { - dev_err(&pdev->dev, "Unable to get mclk\n"); + if (PTR_ERR(mclk) != -EPROBE_DEFER) + dev_err(&pdev->dev, "Unable to get mclk\n"); return PTR_ERR(mclk); }

[ Upstream commit 1f5b62f09f6b314c8d70b9de5182dae4de1f94da ]

The VDSO code uses the kernel helper that was originally designed to abstract the access between 32 and 64bit systems. It worked so far because this function is declared as 'inline'.

As we're about to revamp that part of the code, the VDSO would break. Let's fix it by doing what should have been done from the start, a proper system register access.

Reviewed-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Marc Zyngier marc.zyngier@arm.com Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/include/asm/cp15.h | 2 ++ arch/arm/vdso/vgettimeofday.c | 5 +++-- 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h index 07e27f212dc75..d2453e2d3f1f3 100644 --- a/arch/arm/include/asm/cp15.h +++ b/arch/arm/include/asm/cp15.h @@ -68,6 +68,8 @@ #define BPIALL __ACCESS_CP15(c7, 0, c5, 6) #define ICIALLU __ACCESS_CP15(c7, 0, c5, 0)

+#define CNTVCT __ACCESS_CP15_64(1, c14) + extern unsigned long cr_alignment; /* defined in entry-armv.S */

static inline unsigned long get_cr(void) diff --git a/arch/arm/vdso/vgettimeofday.c b/arch/arm/vdso/vgettimeofday.c index a9dd619c6c290..7bdbf5d5c47d3 100644 --- a/arch/arm/vdso/vgettimeofday.c +++ b/arch/arm/vdso/vgettimeofday.c @@ -18,9 +18,9 @@ #include <linux/compiler.h> #include <linux/hrtimer.h> #include <linux/time.h> -#include <asm/arch_timer.h> #include <asm/barrier.h> #include <asm/bug.h> +#include <asm/cp15.h> #include <asm/page.h> #include <asm/unistd.h> #include <asm/vdso_datapage.h> @@ -123,7 +123,8 @@ static notrace u64 get_ns(struct vdso_data *vdata) u64 cycle_now; u64 nsec;

- cycle_now = arch_counter_get_cntvct(); + isb(); + cycle_now = read_sysreg(CNTVCT);

cycle_delta = (cycle_now - vdata->cs_cycle_last) & vdata->cs_mask;

[ Upstream commit 7ae3f6e130e8dc6188b59e3b4ebc2f16e9c8d053 ]

Using a jiffies timer creates a dependency on the tick_do_timer_cpu incrementing jiffies. If that CPU has locked up and jiffies is not incrementing, the watchdog heartbeat timer for all CPUs stops and creates false positives and confusing warnings on local CPUs, and also causes the SMP detector to stop, so the root cause is never detected.

Fix this by using hrtimer based timers for the watchdog heartbeat, like the generic kernel hardlockup detector.

Cc: Gautham R. Shenoy ego@linux.vnet.ibm.com Reported-by: Ravikumar Bangoria ravi.bangoria@in.ibm.com Signed-off-by: Nicholas Piggin npiggin@gmail.com Tested-by: Ravi Bangoria ravi.bangoria@linux.ibm.com Reported-by: Ravi Bangoria ravi.bangoria@linux.ibm.com Reviewed-by: Gautham R. Shenoy ego@linux.vnet.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/kernel/watchdog.c | 81 +++++++++++++++++----------------- 1 file changed, 40 insertions(+), 41 deletions(-)

diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 3c6ab22a0c4e3..af3c15a1d41eb 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -77,7 +77,7 @@ static u64 wd_smp_panic_timeout_tb __read_mostly; /* panic other CPUs */

static u64 wd_timer_period_ms __read_mostly; /* interval between heartbeat */

-static DEFINE_PER_CPU(struct timer_list, wd_timer); +static DEFINE_PER_CPU(struct hrtimer, wd_hrtimer); static DEFINE_PER_CPU(u64, wd_timer_tb);

/* SMP checker bits */ @@ -293,21 +293,21 @@ void soft_nmi_interrupt(struct pt_regs *regs) nmi_exit(); }

-static void wd_timer_reset(unsigned int cpu, struct timer_list *t) -{ - t->expires = jiffies + msecs_to_jiffies(wd_timer_period_ms); - if (wd_timer_period_ms > 1000) - t->expires = __round_jiffies_up(t->expires, cpu); - add_timer_on(t, cpu); -} - -static void wd_timer_fn(struct timer_list *t) +static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { int cpu = smp_processor_id();

+ if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + return HRTIMER_NORESTART; + + if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) + return HRTIMER_NORESTART; + watchdog_timer_interrupt(cpu);

- wd_timer_reset(cpu, t); + hrtimer_forward_now(hrtimer, ms_to_ktime(wd_timer_period_ms)); + + return HRTIMER_RESTART; }

void arch_touch_nmi_watchdog(void) @@ -323,37 +323,22 @@ void arch_touch_nmi_watchdog(void) } EXPORT_SYMBOL(arch_touch_nmi_watchdog);

-static void start_watchdog_timer_on(unsigned int cpu) -{ - struct timer_list *t = per_cpu_ptr(&wd_timer, cpu); - - per_cpu(wd_timer_tb, cpu) = get_tb(); - - timer_setup(t, wd_timer_fn, TIMER_PINNED); - wd_timer_reset(cpu, t); -} - -static void stop_watchdog_timer_on(unsigned int cpu) -{ - struct timer_list *t = per_cpu_ptr(&wd_timer, cpu); - - del_timer_sync(t); -} - -static int start_wd_on_cpu(unsigned int cpu) +static void start_watchdog(void *arg) { + struct hrtimer *hrtimer = this_cpu_ptr(&wd_hrtimer); + int cpu = smp_processor_id(); unsigned long flags;

if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) { WARN_ON(1); - return 0; + return; }

if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - return 0; + return;

if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) - return 0; + return;

wd_smp_lock(&flags); cpumask_set_cpu(cpu, &wd_cpus_enabled); @@ -363,27 +348,40 @@ static int start_wd_on_cpu(unsigned int cpu) } wd_smp_unlock(&flags);

- start_watchdog_timer_on(cpu); + *this_cpu_ptr(&wd_timer_tb) = get_tb();

- return 0; + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; + hrtimer_start(hrtimer, ms_to_ktime(wd_timer_period_ms), + HRTIMER_MODE_REL_PINNED); }

-static int stop_wd_on_cpu(unsigned int cpu) +static int start_watchdog_on_cpu(unsigned int cpu) { + return smp_call_function_single(cpu, start_watchdog, NULL, true); +} + +static void stop_watchdog(void *arg) +{ + struct hrtimer *hrtimer = this_cpu_ptr(&wd_hrtimer); + int cpu = smp_processor_id(); unsigned long flags;

if (!cpumask_test_cpu(cpu, &wd_cpus_enabled)) - return 0; /* Can happen in CPU unplug case */ + return; /* Can happen in CPU unplug case */

- stop_watchdog_timer_on(cpu); + hrtimer_cancel(hrtimer);

wd_smp_lock(&flags); cpumask_clear_cpu(cpu, &wd_cpus_enabled); wd_smp_unlock(&flags);

wd_smp_clear_cpu_pending(cpu, get_tb()); +}

- return 0; +static int stop_watchdog_on_cpu(unsigned int cpu) +{ + return smp_call_function_single(cpu, stop_watchdog, NULL, true); }

static void watchdog_calc_timeouts(void) @@ -402,7 +400,7 @@ void watchdog_nmi_stop(void) int cpu;

for_each_cpu(cpu, &wd_cpus_enabled) - stop_wd_on_cpu(cpu); + stop_watchdog_on_cpu(cpu); }

void watchdog_nmi_start(void) @@ -411,7 +409,7 @@ void watchdog_nmi_start(void)

watchdog_calc_timeouts(); for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) - start_wd_on_cpu(cpu); + start_watchdog_on_cpu(cpu); }

/* @@ -423,7 +421,8 @@ int __init watchdog_nmi_probe(void)

err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "powerpc/watchdog:online", - start_wd_on_cpu, stop_wd_on_cpu); + start_watchdog_on_cpu, + stop_watchdog_on_cpu); if (err < 0) { pr_warn("could not be initialized"); return err;

[ Upstream commit 24afabdbd0b3553963a2bbf465895492b14d1107 ]

Make sure that the allocated interrupts are freed if allocating memory for the msix_entries array fails.

Cc: Himanshu Madhani hmadhani@marvell.com Cc: Giridhar Malavali gmalavali@marvell.com Signed-off-by: Bart Van Assche bvanassche@acm.org Acked-by: Himanshu Madhani hmadhani@marvell.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qla2xxx/qla_isr.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 36cbb29c84f63..88d8acf86a2a4 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -3449,7 +3449,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp) ql_log(ql_log_fatal, vha, 0x00c8, "Failed to allocate memory for ha->msix_entries.\n"); ret = -ENOMEM; - goto msix_out; + goto free_irqs; } ha->flags.msix_enabled = 1;

@@ -3532,6 +3532,10 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)

msix_out: return ret; + +free_irqs: + pci_free_irq_vectors(ha->pdev); + goto msix_out; }

int

[ Upstream commit d4023db71108375e4194e92730ba0d32d7f07813 ]

This patch avoids that lockdep reports the following warning:

===================================================== WARNING: HARDIRQ-safe -> HARDIRQ-unsafe lock order detected 5.1.0-rc1-dbg+ #11 Tainted: G W ----------------------------------------------------- rmdir/1478 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire: 00000000e7ac4607 (&(&k->k_lock)->rlock){+.+.}, at: klist_next+0x43/0x1d0

and this task is already holding: 00000000cf0baf5e (&(&ha->tgt.sess_lock)->rlock){-...}, at: tcm_qla2xxx_close_session+0x57/0xb0 [tcm_qla2xxx] which would create a new lock dependency: (&(&ha->tgt.sess_lock)->rlock){-...} -> (&(&k->k_lock)->rlock){+.+.}

but this new dependency connects a HARDIRQ-irq-safe lock: (&(&ha->tgt.sess_lock)->rlock){-...}

... which became HARDIRQ-irq-safe at: lock_acquire+0xe3/0x200 _raw_spin_lock_irqsave+0x3d/0x60 qla2x00_fcport_event_handler+0x1f3d/0x22b0 [qla2xxx] qla2x00_async_login_sp_done+0x1dc/0x1f0 [qla2xxx] qla24xx_process_response_queue+0xa37/0x10e0 [qla2xxx] qla24xx_msix_rsp_q+0x79/0xf0 [qla2xxx] __handle_irq_event_percpu+0x79/0x3c0 handle_irq_event_percpu+0x70/0xf0 handle_irq_event+0x5a/0x8b handle_edge_irq+0x12c/0x310 handle_irq+0x192/0x20a do_IRQ+0x73/0x160 ret_from_intr+0x0/0x1d default_idle+0x23/0x1f0 arch_cpu_idle+0x15/0x20 default_idle_call+0x35/0x40 do_idle+0x2bb/0x2e0 cpu_startup_entry+0x1d/0x20 start_secondary+0x24d/0x2d0 secondary_startup_64+0xa4/0xb0

to a HARDIRQ-irq-unsafe lock: (&(&k->k_lock)->rlock){+.+.}

... which became HARDIRQ-irq-unsafe at: ... lock_acquire+0xe3/0x200 _raw_spin_lock+0x32/0x50 klist_add_tail+0x33/0xb0 device_add+0x7f4/0xb60 device_create_groups_vargs+0x11c/0x150 device_create_with_groups+0x89/0xb0 vtconsole_class_init+0xb2/0x124 do_one_initcall+0xc5/0x3ce kernel_init_freeable+0x295/0x32e kernel_init+0x11/0x11b ret_from_fork+0x3a/0x50

other info that might help us debug this:

Possible interrupt unsafe locking scenario:

CPU0 CPU1 ---- ---- lock(&(&k->k_lock)->rlock); local_irq_disable(); lock(&(&ha->tgt.sess_lock)->rlock); lock(&(&k->k_lock)->rlock); <Interrupt> lock(&(&ha->tgt.sess_lock)->rlock);

*** DEADLOCK ***

4 locks held by rmdir/1478: #0: 000000002c7f1ba4 (sb_writers#10){.+.+}, at: mnt_want_write+0x32/0x70 #1: 00000000c85eb147 (&default_group_class[depth - 1]#2/1){+.+.}, at: do_rmdir+0x217/0x2d0 #2: 000000002b164d6f (&sb->s_type->i_mutex_key#13){++++}, at: vfs_rmdir+0x7e/0x1d0 #3: 00000000cf0baf5e (&(&ha->tgt.sess_lock)->rlock){-...}, at: tcm_qla2xxx_close_session+0x57/0xb0 [tcm_qla2xxx]

the dependencies between HARDIRQ-irq-safe lock and the holding lock: -> (&(&ha->tgt.sess_lock)->rlock){-...} ops: 127 { IN-HARDIRQ-W at: lock_acquire+0xe3/0x200 _raw_spin_lock_irqsave+0x3d/0x60 qla2x00_fcport_event_handler+0x1f3d/0x22b0 [qla2xxx] qla2x00_async_login_sp_done+0x1dc/0x1f0 [qla2xxx] qla24xx_process_response_queue+0xa37/0x10e0 [qla2xxx] qla24xx_msix_rsp_q+0x79/0xf0 [qla2xxx] __handle_irq_event_percpu+0x79/0x3c0 handle_irq_event_percpu+0x70/0xf0 handle_irq_event+0x5a/0x8b handle_edge_irq+0x12c/0x310 handle_irq+0x192/0x20a do_IRQ+0x73/0x160 ret_from_intr+0x0/0x1d default_idle+0x23/0x1f0 arch_cpu_idle+0x15/0x20 default_idle_call+0x35/0x40 do_idle+0x2bb/0x2e0 cpu_startup_entry+0x1d/0x20 start_secondary+0x24d/0x2d0 secondary_startup_64+0xa4/0xb0 INITIAL USE at: lock_acquire+0xe3/0x200 _raw_spin_lock_irqsave+0x3d/0x60 qla2x00_loop_resync+0xb3d/0x2690 [qla2xxx] qla2x00_do_dpc+0xcee/0xf30 [qla2xxx] kthread+0x1d2/0x1f0 ret_from_fork+0x3a/0x50 } ... key at: [<ffffffffa125f700>] __key.62804+0x0/0xfffffffffff7e900 [qla2xxx] ... acquired at: __lock_acquire+0x11ed/0x1b60 lock_acquire+0xe3/0x200 _raw_spin_lock_irqsave+0x3d/0x60 klist_next+0x43/0x1d0 device_for_each_child+0x96/0x110 scsi_target_block+0x3c/0x40 [scsi_mod] fc_remote_port_delete+0xe7/0x1c0 [scsi_transport_fc] qla2x00_mark_device_lost+0x4d3/0x500 [qla2xxx] qlt_unreg_sess+0x104/0x2c0 [qla2xxx] tcm_qla2xxx_close_session+0xa2/0xb0 [tcm_qla2xxx] target_shutdown_sessions+0x17b/0x190 [target_core_mod] core_tpg_del_initiator_node_acl+0xf3/0x1f0 [target_core_mod] target_fabric_nacl_base_release+0x25/0x30 [target_core_mod] config_item_release+0x9f/0x120 [configfs] config_item_put+0x29/0x2b [configfs] configfs_rmdir+0x3d2/0x520 [configfs] vfs_rmdir+0xb3/0x1d0 do_rmdir+0x25c/0x2d0 __x64_sys_rmdir+0x24/0x30 do_syscall_64+0x77/0x220 entry_SYSCALL_64_after_hwframe+0x49/0xbe

the dependencies between the lock to be acquired and HARDIRQ-irq-unsafe lock: -> (&(&k->k_lock)->rlock){+.+.} ops: 14568 { HARDIRQ-ON-W at: lock_acquire+0xe3/0x200 _raw_spin_lock+0x32/0x50 klist_add_tail+0x33/0xb0 device_add+0x7f4/0xb60 device_create_groups_vargs+0x11c/0x150 device_create_with_groups+0x89/0xb0 vtconsole_class_init+0xb2/0x124 do_one_initcall+0xc5/0x3ce kernel_init_freeable+0x295/0x32e kernel_init+0x11/0x11b ret_from_fork+0x3a/0x50 SOFTIRQ-ON-W at: lock_acquire+0xe3/0x200 _raw_spin_lock+0x32/0x50 klist_add_tail+0x33/0xb0 device_add+0x7f4/0xb60 device_create_groups_vargs+0x11c/0x150 device_create_with_groups+0x89/0xb0 vtconsole_class_init+0xb2/0x124 do_one_initcall+0xc5/0x3ce kernel_init_freeable+0x295/0x32e kernel_init+0x11/0x11b ret_from_fork+0x3a/0x50 INITIAL USE at: lock_acquire+0xe3/0x200 _raw_spin_lock+0x32/0x50 klist_add_tail+0x33/0xb0 device_add+0x7f4/0xb60 device_create_groups_vargs+0x11c/0x150 device_create_with_groups+0x89/0xb0 vtconsole_class_init+0xb2/0x124 do_one_initcall+0xc5/0x3ce kernel_init_freeable+0x295/0x32e kernel_init+0x11/0x11b ret_from_fork+0x3a/0x50 } ... key at: [<ffffffff83f3d900>] __key.15805+0x0/0x40 ... acquired at: __lock_acquire+0x11ed/0x1b60 lock_acquire+0xe3/0x200 _raw_spin_lock_irqsave+0x3d/0x60 klist_next+0x43/0x1d0 device_for_each_child+0x96/0x110 scsi_target_block+0x3c/0x40 [scsi_mod] fc_remote_port_delete+0xe7/0x1c0 [scsi_transport_fc] qla2x00_mark_device_lost+0x4d3/0x500 [qla2xxx] qlt_unreg_sess+0x104/0x2c0 [qla2xxx] tcm_qla2xxx_close_session+0xa2/0xb0 [tcm_qla2xxx] target_shutdown_sessions+0x17b/0x190 [target_core_mod] core_tpg_del_initiator_node_acl+0xf3/0x1f0 [target_core_mod] target_fabric_nacl_base_release+0x25/0x30 [target_core_mod] config_item_release+0x9f/0x120 [configfs] config_item_put+0x29/0x2b [configfs] configfs_rmdir+0x3d2/0x520 [configfs] vfs_rmdir+0xb3/0x1d0 do_rmdir+0x25c/0x2d0 __x64_sys_rmdir+0x24/0x30 do_syscall_64+0x77/0x220 entry_SYSCALL_64_after_hwframe+0x49/0xbe

stack backtrace: CPU: 7 PID: 1478 Comm: rmdir Tainted: G W 5.1.0-rc1-dbg+ #11 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x86/0xca check_usage.cold.59+0x473/0x563 check_prev_add.constprop.43+0x1f1/0x1170 __lock_acquire+0x11ed/0x1b60 lock_acquire+0xe3/0x200 _raw_spin_lock_irqsave+0x3d/0x60 klist_next+0x43/0x1d0 device_for_each_child+0x96/0x110 scsi_target_block+0x3c/0x40 [scsi_mod] fc_remote_port_delete+0xe7/0x1c0 [scsi_transport_fc] qla2x00_mark_device_lost+0x4d3/0x500 [qla2xxx] qlt_unreg_sess+0x104/0x2c0 [qla2xxx] tcm_qla2xxx_close_session+0xa2/0xb0 [tcm_qla2xxx] target_shutdown_sessions+0x17b/0x190 [target_core_mod] core_tpg_del_initiator_node_acl+0xf3/0x1f0 [target_core_mod] target_fabric_nacl_base_release+0x25/0x30 [target_core_mod] config_item_release+0x9f/0x120 [configfs] config_item_put+0x29/0x2b [configfs] configfs_rmdir+0x3d2/0x520 [configfs] vfs_rmdir+0xb3/0x1d0 do_rmdir+0x25c/0x2d0 __x64_sys_rmdir+0x24/0x30 do_syscall_64+0x77/0x220 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Cc: Himanshu Madhani hmadhani@marvell.com Cc: Giridhar Malavali gmalavali@marvell.com Signed-off-by: Bart Van Assche bvanassche@acm.org Acked-by: Himanshu Madhani hmadhani@marvell.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qla2xxx/tcm_qla2xxx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 7ef549903124d..f425a9e5056bf 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -365,8 +365,9 @@ static void tcm_qla2xxx_close_session(struct se_session *se_sess)

spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); target_sess_cmd_list_set_waiting(se_sess); - tcm_qla2xxx_put_sess(sess); spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + + tcm_qla2xxx_put_sess(sess); }

static u32 tcm_qla2xxx_sess_get_index(struct se_session *se_sess)

[ Upstream commit f2c65fb3221adc6b73b0549fc7ba892022db9797 ]

When modules and BPF filters are loaded, there is a time window in which some memory is both writable and executable. An attacker that has already found another vulnerability (e.g., a dangling pointer) might be able to exploit this behavior to overwrite kernel code. Prevent having writable executable PTEs in this stage.

In addition, avoiding having W+X mappings can also slightly simplify the patching of modules code on initialization (e.g., by alternatives and static-key), as would be done in the next patch. This was actually the main motivation for this patch.

To avoid having W+X mappings, set them initially as RW (NX) and after they are set as RO set them as X as well. Setting them as executable is done as a separate step to avoid one core in which the old PTE is cached (hence writable), and another which sees the updated PTE (executable), which would break the W^X protection.

Suggested-by: Thomas Gleixner tglx@linutronix.de Suggested-by: Andy Lutomirski luto@amacapital.net Signed-off-by: Nadav Amit namit@vmware.com Signed-off-by: Rick Edgecombe rick.p.edgecombe@intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: akpm@linux-foundation.org Cc: ard.biesheuvel@linaro.org Cc: deneen.t.dock@intel.com Cc: kernel-hardening@lists.openwall.com Cc: kristen@linux.intel.com Cc: linux_dti@icloud.com Cc: will.deacon@arm.com Cc: Andy Lutomirski luto@kernel.org Cc: Borislav Petkov bp@alien8.de Cc: Dave Hansen dave.hansen@intel.com Cc: H. Peter Anvin hpa@zytor.com Cc: Jessica Yu jeyu@kernel.org Cc: Kees Cook keescook@chromium.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Masami Hiramatsu mhiramat@kernel.org Cc: Rik van Riel riel@surriel.com Link: https://lkml.kernel.org/r/20190426001143.4983-12-namit@vmware.com Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/alternative.c | 28 +++++++++++++++++++++------- arch/x86/kernel/module.c | 2 +- include/linux/filter.h | 1 + kernel/module.c | 5 +++++ 4 files changed, 28 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index b9d5e7c9ef43e..918a23704c0c5 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -662,15 +662,29 @@ void __init alternative_instructions(void) * handlers seeing an inconsistent instruction while you patch. */ void *__init_or_module text_poke_early(void *addr, const void *opcode, - size_t len) + size_t len) { unsigned long flags; - local_irq_save(flags); - memcpy(addr, opcode, len); - local_irq_restore(flags); - sync_core(); - /* Could also do a CLFLUSH here to speed up CPU recovery; but - that causes hangs on some VIA CPUs. */ + + if (boot_cpu_has(X86_FEATURE_NX) && + is_module_text_address((unsigned long)addr)) { + /* + * Modules text is marked initially as non-executable, so the + * code cannot be running and speculative code-fetches are + * prevented. Just change the code. + */ + memcpy(addr, opcode, len); + } else { + local_irq_save(flags); + memcpy(addr, opcode, len); + local_irq_restore(flags); + sync_core(); + + /* + * Could also do a CLFLUSH here to speed up CPU recovery; but + * that causes hangs on some VIA CPUs. + */ + } return addr; }

diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index f58336af095c9..6645f123419c6 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -87,7 +87,7 @@ void *module_alloc(unsigned long size) p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR + get_module_load_offset(), MODULES_END, GFP_KERNEL, - PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); if (p && (kasan_module_alloc(p, size) < 0)) { vfree(p); diff --git a/include/linux/filter.h b/include/linux/filter.h index 6ecef32fd8bcd..d52a7484aeb2d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -684,6 +684,7 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_memory_ro((unsigned long)hdr, hdr->pages); + set_memory_x((unsigned long)hdr, hdr->pages); }

static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) diff --git a/kernel/module.c b/kernel/module.c index 38bf28b5cc202..f797c6ace7121 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1949,8 +1949,13 @@ void module_enable_ro(const struct module *mod, bool after_init) return;

frob_text(&mod->core_layout, set_memory_ro); + frob_text(&mod->core_layout, set_memory_x); + frob_rodata(&mod->core_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_x); + frob_rodata(&mod->init_layout, set_memory_ro);

if (after_init)

[ Upstream commit ff612ba7849964b1898fd3ccd1f56941129c6aab ]

We've been seeing the following sporadically throughout our fleet

panic: kernel BUG at fs/btrfs/relocation.c:4584! netversion: 5.0-0 Backtrace: #0 [ffffc90003adb880] machine_kexec at ffffffff81041da8 #1 [ffffc90003adb8c8] __crash_kexec at ffffffff8110396c #2 [ffffc90003adb988] crash_kexec at ffffffff811048ad #3 [ffffc90003adb9a0] oops_end at ffffffff8101c19a #4 [ffffc90003adb9c0] do_trap at ffffffff81019114 #5 [ffffc90003adba00] do_error_trap at ffffffff810195d0 #6 [ffffc90003adbab0] invalid_op at ffffffff81a00a9b [exception RIP: btrfs_reloc_cow_block+692] RIP: ffffffff8143b614 RSP: ffffc90003adbb68 RFLAGS: 00010246 RAX: fffffffffffffff7 RBX: ffff8806b9c32000 RCX: ffff8806aad00690 RDX: ffff880850b295e0 RSI: ffff8806b9c32000 RDI: ffff88084f205bd0 RBP: ffff880849415000 R8: ffffc90003adbbe0 R9: ffff88085ac90000 R10: ffff8805f7369140 R11: 0000000000000000 R12: ffff880850b295e0 R13: ffff88084f205bd0 R14: 0000000000000000 R15: 0000000000000000 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #7 [ffffc90003adbbb0] __btrfs_cow_block at ffffffff813bf1cd #8 [ffffc90003adbc28] btrfs_cow_block at ffffffff813bf4b3 #9 [ffffc90003adbc78] btrfs_search_slot at ffffffff813c2e6c

The way relocation moves data extents is by creating a reloc inode and preallocating extents in this inode and then copying the data into these preallocated extents. Once we've done this for all of our extents, we'll write out these dirty pages, which marks the extent written, and goes into btrfs_reloc_cow_block(). From here we get our current reloc_control, which _should_ match the reloc_control for the current block group we're relocating.

However if we get an ENOSPC in this path at some point we'll bail out, never initiating writeback on this inode. Not a huge deal, unless we happen to be doing relocation on a different block group, and this block group is now rc->stage == UPDATE_DATA_PTRS. This trips the BUG_ON() in btrfs_reloc_cow_block(), because we expect to be done modifying the data inode. We are in fact done modifying the metadata for the data inode we're currently using, but not the one from the failed block group, and thus we BUG_ON().

(This happens when writeback finishes for extents from the previous group, when we are at btrfs_finish_ordered_io() which updates the data reloc tree (inode item, drops/adds extent items, etc).)

Fix this by writing out the reloc data inode always, and then breaking out of the loop after that point to keep from tripping this BUG_ON() later.

Signed-off-by: Josef Bacik josef@toxicpanda.com Reviewed-by: Filipe Manana fdmanana@suse.com [ add note from Filipe ] Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/relocation.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 0526b6c473c79..5d57ed6293455 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4289,27 +4289,36 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) mutex_lock(&fs_info->cleaner_mutex); ret = relocate_block_group(rc); mutex_unlock(&fs_info->cleaner_mutex); - if (ret < 0) { + if (ret < 0) err = ret; - goto out; - } - - if (rc->extents_found == 0) - break; - - btrfs_info(fs_info, "found %llu extents", rc->extents_found);

+ /* + * We may have gotten ENOSPC after we already dirtied some + * extents. If writeout happens while we're relocating a + * different block group we could end up hitting the + * BUG_ON(rc->stage == UPDATE_DATA_PTRS) in + * btrfs_reloc_cow_block. Make sure we write everything out + * properly so we don't trip over this problem, and then break + * out of the loop if we hit an error. + */ if (rc->stage == MOVE_DATA_EXTENTS && rc->found_file_extent) { ret = btrfs_wait_ordered_range(rc->data_inode, 0, (u64)-1); - if (ret) { + if (ret) err = ret; - goto out; - } invalidate_mapping_pages(rc->data_inode->i_mapping, 0, -1); rc->stage = UPDATE_DATA_PTRS; } + + if (err < 0) + goto out; + + if (rc->extents_found == 0) + break; + + btrfs_info(fs_info, "found %llu extents", rc->extents_found); + }

WARN_ON(rc->block_group->pinned > 0);

[ Upstream commit 30f24eabab8cd801064c5c37589d803cb4341929 ]

If for some reason the device gives us an RX interrupt before we're ready for it, perhaps during device power-on with misconfigured IRQ causes mapping or so, we can crash trying to access the queues.

Prevent that by checking that we actually have RXQs and that they were properly allocated.

Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/pcie/rx.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index b2905f01b7df3..6dcd5374d9b4d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1388,10 +1388,15 @@ static struct iwl_rx_mem_buffer *iwl_pcie_get_rxb(struct iwl_trans *trans, static void iwl_pcie_rx_handle(struct iwl_trans *trans, int queue) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); - struct iwl_rxq *rxq = &trans_pcie->rxq[queue]; + struct iwl_rxq *rxq; u32 r, i, count = 0; bool emergency = false;

+ if (WARN_ON_ONCE(!trans_pcie->rxq || !trans_pcie->rxq[queue].bd)) + return; + + rxq = &trans_pcie->rxq[queue]; + restart: spin_lock(&rxq->lock); /* uCode's read index (stored in shared DRAM) indicates the last Rx

[ Upstream commit cf612c5949aca2bd81a1e28688957c8149ea2693 ]

Manage the -EPROBE_DEFER error case for the wake IRQ.

Signed-off-by: Fabien Dessenne fabien.dessenne@st.com Acked-by: Amelie Delaunay amelie.delaunay@st.com Signed-off-by: Alexandre Belloni alexandre.belloni@bootlin.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/rtc/rtc-stm32.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c index c5908cfea2340..8e6c9b3bcc29a 100644 --- a/drivers/rtc/rtc-stm32.c +++ b/drivers/rtc/rtc-stm32.c @@ -788,11 +788,14 @@ static int stm32_rtc_probe(struct platform_device *pdev) ret = device_init_wakeup(&pdev->dev, true); if (rtc->data->has_wakeirq) { rtc->wakeirq_alarm = platform_get_irq(pdev, 1); - if (rtc->wakeirq_alarm <= 0) - ret = rtc->wakeirq_alarm; - else + if (rtc->wakeirq_alarm > 0) { ret = dev_pm_set_dedicated_wake_irq(&pdev->dev, rtc->wakeirq_alarm); + } else { + ret = rtc->wakeirq_alarm; + if (rtc->wakeirq_alarm == -EPROBE_DEFER) + goto err; + } } if (ret) dev_warn(&pdev->dev, "alarm can't wake up the system: %d", ret);

[ Upstream commit 729829d775c9a5217abc784b2f16087d79c4eec8 ]

To register data for the next kernel (command line, oldmem_base, etc.) the current kernel needs to find the ELF segment that contains head.S. This is currently done by checking ifor 'phdr->p_paddr == 0'. This works fine for the current kernel build but in theory the first few pages could be skipped. Make the detection more robust by checking if the entry point lies within the segment.

Signed-off-by: Philipp Rudo prudo@linux.ibm.com Signed-off-by: Martin Schwidefsky schwidefsky@de.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/kernel/kexec_elf.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c index 5a286b012043b..602e7cc26d118 100644 --- a/arch/s390/kernel/kexec_elf.c +++ b/arch/s390/kernel/kexec_elf.c @@ -19,10 +19,15 @@ static int kexec_file_add_elf_kernel(struct kimage *image, struct kexec_buf buf; const Elf_Ehdr *ehdr; const Elf_Phdr *phdr; + Elf_Addr entry; int i, ret;

ehdr = (Elf_Ehdr *)kernel; buf.image = image; + if (image->type == KEXEC_TYPE_CRASH) + entry = STARTUP_KDUMP_OFFSET; + else + entry = ehdr->e_entry;

phdr = (void *)ehdr + ehdr->e_phoff; for (i = 0; i < ehdr->e_phnum; i++, phdr++) { @@ -35,7 +40,7 @@ static int kexec_file_add_elf_kernel(struct kimage *image, buf.mem = ALIGN(phdr->p_paddr, phdr->p_align); buf.memsz = phdr->p_memsz;

- if (phdr->p_paddr == 0) { + if (entry - phdr->p_paddr < phdr->p_memsz) { data->kernel_buf = buf.buffer; data->memsz += STARTUP_NORMAL_OFFSET;

[ Upstream commit 62909da8aca048ecf9fbd7e484e5100608f40a63 ]

From the DS2408 datasheet [1]:

"Resume Command function checks the status of the RC flag and, if it is set, directly transfers control to the control functions, similar to a Skip ROM command. The only way to set the RC flag is through successfully executing the Match ROM, Search ROM, Conditional Search ROM, or Overdrive-Match ROM command"

The function currently works perfectly fine in a multidrop bus, but when we have only a single slave connected, then only a Skip ROM is used and Match ROM is not called at all. This is leading to problems e.g. with single one DS2408 connected, as the Resume Command is not working properly and the device is responding with failing results after the Resume Command.

This commit is fixing this by using a Skip ROM instead in those cases. The bandwidth / performance advantage is exactly the same.

Refs: [1] https://datasheets.maximintegrated.com/en/ds/DS2408.pdf

Signed-off-by: Mariusz Bialonczyk manio@skyboo.net Reviewed-by: Jean-Francois Dagenais jeff.dagenais@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/w1/w1_io.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/w1/w1_io.c b/drivers/w1/w1_io.c index 0364d3329c526..3516ce6718d94 100644 --- a/drivers/w1/w1_io.c +++ b/drivers/w1/w1_io.c @@ -432,8 +432,7 @@ int w1_reset_resume_command(struct w1_master *dev) if (w1_reset_bus(dev)) return -1;

- /* This will make only the last matched slave perform a skip ROM. */ - w1_write_8(dev, W1_RESUME_CMD); + w1_write_8(dev, dev->slave_count > 1 ? W1_RESUME_CMD : W1_SKIP_ROM); return 0; } EXPORT_SYMBOL_GPL(w1_reset_resume_command);

[ Upstream commit 2da254cc7908105a60a6bb219d18e8dced03dcb9 ]

This patch kill instructs the DMAC to immediately terminate execution of a thread. and then clear the interrupt status, at last, stop generating interrupts for DMA_SEV. to guarantee the next dma start is clean. otherwise, one interrupt maybe leave to next start and make some mistake.

we can reporduce the problem as follows:

DMASEV: modify the event-interrupt resource, and if the INTEN sets function as interrupt, the DMAC will set irq<event_num> HIGH to generate interrupt. write INTCLR to clear interrupt.

DMA EXECUTING INSTRUCTS DMA TERMINATE | | | | ... _stop | | | spin_lock_irqsave DMASEV | | | | mask INTEN | | | DMAKILL | | | spin_unlock_irqrestore

in above case, a interrupt was left, and if we unmask INTEN, the DMAC will set irq<event_num> HIGH to generate interrupt.

to fix this, do as follows:

DMA EXECUTING INSTRUCTS DMA TERMINATE | | | | ... _stop | | | spin_lock_irqsave DMASEV | | | | DMAKILL | | | clear INTCLR | mask INTEN | | | spin_unlock_irqrestore

Signed-off-by: Sugar Zhang sugar.zhang@rock-chips.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/pl330.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 88750a34e8598..bc8050c025b7b 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -961,6 +961,7 @@ static void _stop(struct pl330_thread *thrd) { void __iomem *regs = thrd->dmac->base; u8 insn[6] = {0, 0, 0, 0, 0, 0}; + u32 inten = readl(regs + INTEN);

if (_state(thrd) == PL330_STATE_FAULT_COMPLETING) UNTIL(thrd, PL330_STATE_FAULTING | PL330_STATE_KILLING); @@ -973,10 +974,13 @@ static void _stop(struct pl330_thread *thrd)

_emit_KILL(0, insn);

- /* Stop generating interrupts for SEV */ - writel(readl(regs + INTEN) & ~(1 << thrd->ev), regs + INTEN); - _execute_DBGINSN(thrd, insn, is_manager(thrd)); + + /* clear the event */ + if (inten & (1 << thrd->ev)) + writel(1 << thrd->ev, regs + INTCLR); + /* Stop generating interrupts for SEV */ + writel(inten & ~(1 << thrd->ev), regs + INTEN); }

/* Start doing req 'idx' of thread 'thrd' */

[ Upstream commit 32e621e55496a0009f44fe4914cd4a23cade4984 ]

Currently, building bpf samples will cause the following error.

./tools/lib/bpf/bpf.h:132:27: error: 'UINT32_MAX' undeclared here (not in a function) .. #define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */ ^ ./samples/bpf/bpf_load.h:31:25: note: in expansion of macro 'BPF_LOG_BUF_SIZE' extern char bpf_log_buf[BPF_LOG_BUF_SIZE]; ^~~~~~~~~~~~~~~~

Due to commit 4519efa6f8ea ("libbpf: fix BPF_LOG_BUF_SIZE off-by-one error") hard-coded size of BPF_LOG_BUF_SIZE has been replaced with UINT32_MAX which is defined in <stdint.h> header.

Even with this change, bpf selftests are running fine since these are built with clang and it includes header(-idirafter) from clang/6.0.0/include. (it has <stdint.h>)

clang -I. -I./include/uapi -I../../../include/uapi -idirafter /usr/local/include -idirafter /usr/include \ -idirafter /usr/lib/llvm-6.0/lib/clang/6.0.0/include -idirafter /usr/include/x86_64-linux-gnu \ -Wno-compare-distinct-pointer-types -O2 -target bpf -emit-llvm -c progs/test_sysctl_prog.c -o - | \ llc -march=bpf -mcpu=generic -filetype=obj -o /linux/tools/testing/selftests/bpf/test_sysctl_prog.o

But bpf samples are compiled with GCC, and it only searches and includes headers declared at the target file. As '#include <stdint.h>' hasn't been declared in tools/lib/bpf/bpf.h, it causes build failure of bpf samples.

gcc -Wp,-MD,./samples/bpf/.sockex3_user.o.d -Wall -Wmissing-prototypes -Wstrict-prototypes \ -O2 -fomit-frame-pointer -std=gnu89 -I./usr/include -I./tools/lib/ -I./tools/testing/selftests/bpf/ \ -I./tools/ lib/ -I./tools/include -I./tools/perf -c -o ./samples/bpf/sockex3_user.o ./samples/bpf/sockex3_user.c;

This commit add declaration of '#include <stdint.h>' to tools/lib/bpf/bpf.h to fix this problem.

Signed-off-by: Daniel T. Lee danieltimlee@gmail.com Acked-by: Yonghong Song yhs@fb.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: Sasha Levin sashal@kernel.org --- tools/lib/bpf/bpf.h | 1 + 1 file changed, 1 insertion(+)

diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 6f38164b26181..c3145ab3bdcac 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -26,6 +26,7 @@ #include <linux/bpf.h> #include <stdbool.h> #include <stddef.h> +#include <stdint.h>

struct bpf_create_map_attr { const char *name;

[ Upstream commit ddb351145a967ee791a0fb0156852ec2fcb746ba ]

is_slave_mode defaults to false because sai structure that contains it is kzalloc'ed.

Anyhow, if we decide to set the following configuration SAI slave -> SAI master, is_slave_mode will remain set on true although SAI being master it should be set to false.

Fix this by updating is_slave_mode for each call of fsl_sai_set_dai_fmt.

Signed-off-by: Daniel Baluta daniel.baluta@nxp.com Acked-by: Nicolin Chen nicoleotsuka@gmail.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/fsl/fsl_sai.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 4163f2cfc06fc..bfc5b21d0c3f9 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -268,12 +268,14 @@ static int fsl_sai_set_dai_fmt_tr(struct snd_soc_dai *cpu_dai, case SND_SOC_DAIFMT_CBS_CFS: val_cr2 |= FSL_SAI_CR2_BCD_MSTR; val_cr4 |= FSL_SAI_CR4_FSD_MSTR; + sai->is_slave_mode = false; break; case SND_SOC_DAIFMT_CBM_CFM: sai->is_slave_mode = true; break; case SND_SOC_DAIFMT_CBS_CFM: val_cr2 |= FSL_SAI_CR2_BCD_MSTR; + sai->is_slave_mode = false; break; case SND_SOC_DAIFMT_CBM_CFS: val_cr4 |= FSL_SAI_CR4_FSD_MSTR;

[ Upstream commit d5414c2355b20ea8201156d2e874265f1cb0d775 ]

kmalloc can fail in rsi_register_rates_channels but memcpy still attempts to write to channels. The patch replaces these calls with kmemdup and passes the error upstream.

Signed-off-by: Aditya Pakki pakki001@umn.edu Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/rsi/rsi_91x_mac80211.c | 30 ++++++++++++--------- 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index 4e510cbe0a89f..be59d66585d6d 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -188,27 +188,27 @@ bool rsi_is_cipher_wep(struct rsi_common *common) * @adapter: Pointer to the adapter structure. * @band: Operating band to be set. * - * Return: None. + * Return: int - 0 on success, negative error on failure. */ -static void rsi_register_rates_channels(struct rsi_hw *adapter, int band) +static int rsi_register_rates_channels(struct rsi_hw *adapter, int band) { struct ieee80211_supported_band *sbands = &adapter->sbands[band]; void *channels = NULL;

if (band == NL80211_BAND_2GHZ) { - channels = kmalloc(sizeof(rsi_2ghz_channels), GFP_KERNEL); - memcpy(channels, - rsi_2ghz_channels, - sizeof(rsi_2ghz_channels)); + channels = kmemdup(rsi_2ghz_channels, sizeof(rsi_2ghz_channels), + GFP_KERNEL); + if (!channels) + return -ENOMEM; sbands->band = NL80211_BAND_2GHZ; sbands->n_channels = ARRAY_SIZE(rsi_2ghz_channels); sbands->bitrates = rsi_rates; sbands->n_bitrates = ARRAY_SIZE(rsi_rates); } else { - channels = kmalloc(sizeof(rsi_5ghz_channels), GFP_KERNEL); - memcpy(channels, - rsi_5ghz_channels, - sizeof(rsi_5ghz_channels)); + channels = kmemdup(rsi_5ghz_channels, sizeof(rsi_5ghz_channels), + GFP_KERNEL); + if (!channels) + return -ENOMEM; sbands->band = NL80211_BAND_5GHZ; sbands->n_channels = ARRAY_SIZE(rsi_5ghz_channels); sbands->bitrates = &rsi_rates[4]; @@ -227,6 +227,7 @@ static void rsi_register_rates_channels(struct rsi_hw *adapter, int band) sbands->ht_cap.mcs.rx_mask[0] = 0xff; sbands->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED; /* sbands->ht_cap.mcs.rx_highest = 0x82; */ + return 0; }

/** @@ -1985,11 +1986,16 @@ int rsi_mac80211_attach(struct rsi_common *common) wiphy->available_antennas_rx = 1; wiphy->available_antennas_tx = 1;

- rsi_register_rates_channels(adapter, NL80211_BAND_2GHZ); + status = rsi_register_rates_channels(adapter, NL80211_BAND_2GHZ); + if (status) + return status; wiphy->bands[NL80211_BAND_2GHZ] = &adapter->sbands[NL80211_BAND_2GHZ]; if (common->num_supp_bands > 1) { - rsi_register_rates_channels(adapter, NL80211_BAND_5GHZ); + status = rsi_register_rates_channels(adapter, + NL80211_BAND_5GHZ); + if (status) + return status; wiphy->bands[NL80211_BAND_5GHZ] = &adapter->sbands[NL80211_BAND_5GHZ]; }

[ Upstream commit 01fa017484ad98fccdeaab32db0077c574b6bd6f ]

If our target exposed a namespace with a block size that is greater than PAGE_SIZE, set 0 capacity on the namespace as we do not support it.

This issue encountered when the nvmet namespace was backed by a tempfile.

Signed-off-by: Sagi Grimberg sagi@grimberg.me Reviewed-by: Keith Busch keith.busch@intel.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 2cdb3032ca0fc..abfb46378cc13 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1480,6 +1480,10 @@ static void nvme_update_disk_info(struct gendisk *disk, sector_t capacity = le64_to_cpup(&id->nsze) << (ns->lba_shift - 9); unsigned short bs = 1 << ns->lba_shift;

+ if (ns->lba_shift > PAGE_SHIFT) { + /* unsupported block size, set capacity to 0 later */ + bs = (1 << 9); + } blk_mq_freeze_queue(disk->queue); blk_integrity_unregister(disk);

@@ -1490,7 +1494,8 @@ static void nvme_update_disk_info(struct gendisk *disk, if (ns->ms && !ns->ext && (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)) nvme_init_integrity(disk, ns->ms, ns->pi_type); - if (ns->ms && !nvme_ns_has_pi(ns) && !blk_get_integrity(disk)) + if ((ns->ms && !nvme_ns_has_pi(ns) && !blk_get_integrity(disk)) || + ns->lba_shift > PAGE_SHIFT) capacity = 0;

set_capacity(disk, capacity);

[ Upstream commit f87391558acf816b48f325a493d81d45dec40da0 ]

When nbytes < 4, end is wronlgy set to a negative value which, due to uint, is then interpreted to a large value leading to a deadlock in the following code.

This patch fix this problem.

Fixes: 6298e948215f ("crypto: sunxi-ss - Add Allwinner Security System crypto accelerator") Signed-off-by: Corentin Labbe clabbe.montjoie@gmail.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/crypto/sunxi-ss/sun4i-ss-hash.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c index a4b5ff2b72f87..f6936bb3b7be4 100644 --- a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c +++ b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c @@ -240,7 +240,10 @@ static int sun4i_hash(struct ahash_request *areq) } } else { /* Since we have the flag final, we can go up to modulo 4 */ - end = ((areq->nbytes + op->len) / 4) * 4 - op->len; + if (areq->nbytes < 4) + end = 0; + else + end = ((areq->nbytes + op->len) / 4) * 4 - op->len; }

/* TODO if SGlen % 4 and !op->len then DMA */

[ Upstream commit 68d10e6979a3b59e3cd2e90bfcafed79c4cf180a ]

When failure happens inside bch_journal_replay(), calling cache_set_err_on() and handling the failure in async way is not a good idea. Because after bch_journal_replay() returns, registering code will continue to execute following steps, and unregistering code triggered by cache_set_err_on() is running in same time. First it is unnecessary to handle failure and unregister cache set in an async way, second there might be potential race condition to run register and unregister code for same cache set.

So in this patch, if failure happens in bch_journal_replay(), we don't call cache_set_err_on(), and just print out the same error message to kernel message buffer, then return -EIO immediately caller. Then caller can detect such failure and handle it in synchrnozied way.

Signed-off-by: Coly Li colyli@suse.de Reviewed-by: Hannes Reinecke hare@suse.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/bcache/journal.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 772258ee1f517..07da39ac2d110 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -330,9 +330,12 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list) list_for_each_entry(i, list, list) { BUG_ON(i->pin && atomic_read(i->pin) != 1);

- cache_set_err_on(n != i->j.seq, s, -"bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)", - n, i->j.seq - 1, start, end); + if (n != i->j.seq) { + pr_err("bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)", + n, i->j.seq - 1, start, end); + ret = -EIO; + goto err; + }

for (k = i->j.start; k < bset_bkey_last(&i->j);

[ Upstream commit ce3e4cfb59cb382f8e5ce359238aa580d4ae7778 ]

Currently run_cache_set() has no return value, if there is failure in bch_journal_replay(), the caller of run_cache_set() has no idea about such failure and just continue to execute following code after run_cache_set(). The internal failure is triggered inside bch_journal_replay() and being handled in async way. This behavior is inefficient, while failure handling inside bch_journal_replay(), cache register code is still running to start the cache set. Registering and unregistering code running as same time may introduce some rare race condition, and make the code to be more hard to be understood.

This patch adds return value to run_cache_set(), and returns -EIO if bch_journal_rreplay() fails. Then caller of run_cache_set() may detect such failure and stop registering code flow immedidately inside register_cache_set().

If journal replay fails, run_cache_set() can report error immediately to register_cache_set(). This patch makes the failure handling for bch_journal_replay() be in synchronized way, easier to understand and debug, and avoid poetential race condition for register-and-unregister in same time.

Signed-off-by: Coly Li colyli@suse.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/bcache/super.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index d8190804aee9b..2409507d7bff8 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1770,7 +1770,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) return NULL; }

-static void run_cache_set(struct cache_set *c) +static int run_cache_set(struct cache_set *c) { const char *err = "cannot allocate memory"; struct cached_dev *dc, *t; @@ -1866,7 +1866,9 @@ static void run_cache_set(struct cache_set *c) if (j->version < BCACHE_JSET_VERSION_UUID) __uuid_write(c);

- bch_journal_replay(c, &journal); + err = "bcache: replay journal failed"; + if (bch_journal_replay(c, &journal)) + goto err; } else { pr_notice("invalidating existing data");

@@ -1934,7 +1936,7 @@ static void run_cache_set(struct cache_set *c) flash_devs_run(c);

set_bit(CACHE_SET_RUNNING, &c->flags); - return; + return 0; err: while (!list_empty(&journal)) { l = list_first_entry(&journal, struct journal_replay, list); @@ -1945,6 +1947,8 @@ static void run_cache_set(struct cache_set *c) closure_sync(&cl); /* XXX: test this, it's broken */ bch_cache_set_error(c, "%s", err); + + return -EIO; }

static bool can_attach_cache(struct cache *ca, struct cache_set *c) @@ -2008,8 +2012,11 @@ static const char *register_cache_set(struct cache *ca) ca->set->cache[ca->sb.nr_this_dev] = ca; c->cache_by_alloc[c->caches_loaded++] = ca;

- if (c->caches_loaded == c->sb.nr_in_set) - run_cache_set(c); + if (c->caches_loaded == c->sb.nr_in_set) { + err = "failed to run cache set"; + if (run_cache_set(c) < 0) + goto err; + }

return NULL; err:

[ Upstream commit 5d7ed2f27bbd482fd29e6b2e204b1a1ee8a0b268 ]

When two netdev have same link local addresses (such as vlan and non vlan), two rdma cm listen id should be able to bind to following different addresses.

listener-1: addr=lla, scope_id=A, port=X listener-2: addr=lla, scope_id=B, port=X

However while comparing the addresses only addr and port are considered, due to which 2nd listener fails to listen.

In below example of two listeners, 2nd listener is failing with address in use error.

$ rping -sv -a fe80::268a:7ff:feb3:d113%ens2f1 -p 4545&

$ rping -sv -a fe80::268a:7ff:feb3:d113%ens2f1.200 -p 4545 rdma_bind_addr: Address already in use

To overcome this, consider the scope_ids as well which forms the accurate IPv6 link local address.

Signed-off-by: Parav Pandit parav@mellanox.com Reviewed-by: Daniel Jurgens danielj@mellanox.com Signed-off-by: Leon Romanovsky leonro@mellanox.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/cma.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 6f5be78024762..39dc7be56884a 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1078,18 +1078,31 @@ static inline bool cma_any_addr(const struct sockaddr *addr) return cma_zero_addr(addr) || cma_loopback_addr(addr); }

-static int cma_addr_cmp(struct sockaddr *src, struct sockaddr *dst) +static int cma_addr_cmp(const struct sockaddr *src, const struct sockaddr *dst) { if (src->sa_family != dst->sa_family) return -1;

switch (src->sa_family) { case AF_INET: - return ((struct sockaddr_in *) src)->sin_addr.s_addr != - ((struct sockaddr_in *) dst)->sin_addr.s_addr; - case AF_INET6: - return ipv6_addr_cmp(&((struct sockaddr_in6 *) src)->sin6_addr, - &((struct sockaddr_in6 *) dst)->sin6_addr); + return ((struct sockaddr_in *)src)->sin_addr.s_addr != + ((struct sockaddr_in *)dst)->sin_addr.s_addr; + case AF_INET6: { + struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *)src; + struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *)dst; + bool link_local; + + if (ipv6_addr_cmp(&src_addr6->sin6_addr, + &dst_addr6->sin6_addr)) + return 1; + link_local = ipv6_addr_type(&dst_addr6->sin6_addr) & + IPV6_ADDR_LINKLOCAL; + /* Link local must match their scope_ids */ + return link_local ? (src_addr6->sin6_scope_id != + dst_addr6->sin6_scope_id) : + 0; + } + default: return ib_addr_cmp(&((struct sockaddr_ib *) src)->sib_addr, &((struct sockaddr_ib *) dst)->sib_addr);

[ Upstream commit b49bdc8602b7c9c7a977758bee4125683f73e59f ]

When releasing the vfio-ccw mdev, we currently do not release any existing channel program and its pinned pages. This can lead to the following warning:

[1038876.561565] WARNING: CPU: 2 PID: 144727 at drivers/vfio/vfio_iommu_type1.c:1494 vfio_sanity_check_pfn_list+0x40/0x70 [vfio_iommu_type1]

....

1038876.561921] Call Trace: [1038876.561935] ([<00000009897fb870>] 0x9897fb870) [1038876.561949] [<000003ff8013bf62>] vfio_iommu_type1_detach_group+0xda/0x2f0 [vfio_iommu_type1] [1038876.561965] [<000003ff8007b634>] __vfio_group_unset_container+0x64/0x190 [vfio] [1038876.561978] [<000003ff8007b87e>] vfio_group_put_external_user+0x26/0x38 [vfio] [1038876.562024] [<000003ff806fc608>] kvm_vfio_group_put_external_user+0x40/0x60 [kvm] [1038876.562045] [<000003ff806fcb9e>] kvm_vfio_destroy+0x5e/0xd0 [kvm] [1038876.562065] [<000003ff806f63fc>] kvm_put_kvm+0x2a4/0x3d0 [kvm] [1038876.562083] [<000003ff806f655e>] kvm_vm_release+0x36/0x48 [kvm] [1038876.562098] [<00000000003c2dc4>] __fput+0x144/0x228 [1038876.562113] [<000000000016ee82>] task_work_run+0x8a/0xd8 [1038876.562125] [<000000000014c7a8>] do_exit+0x5d8/0xd90 [1038876.562140] [<000000000014d084>] do_group_exit+0xc4/0xc8 [1038876.562155] [<000000000015c046>] get_signal+0x9ae/0xa68 [1038876.562169] [<0000000000108d66>] do_signal+0x66/0x768 [1038876.562185] [<0000000000b9e37e>] system_call+0x1ea/0x2d8 [1038876.562195] 2 locks held by qemu-system-s39/144727: [1038876.562205] #0: 00000000537abaf9 (&container->group_lock){++++}, at: __vfio_group_unset_container+0x3c/0x190 [vfio] [1038876.562230] #1: 00000000670008b5 (&iommu->lock){+.+.}, at: vfio_iommu_type1_detach_group+0x36/0x2f0 [vfio_iommu_type1] [1038876.562250] Last Breaking-Event-Address: [1038876.562262] [<000003ff8013aa24>] vfio_sanity_check_pfn_list+0x3c/0x70 [vfio_iommu_type1] [1038876.562272] irq event stamp: 4236481 [1038876.562287] hardirqs last enabled at (4236489): [<00000000001cee7a>] console_unlock+0x6d2/0x740 [1038876.562299] hardirqs last disabled at (4236496): [<00000000001ce87e>] console_unlock+0xd6/0x740 [1038876.562311] softirqs last enabled at (4234162): [<0000000000b9fa1e>] __do_softirq+0x556/0x598 [1038876.562325] softirqs last disabled at (4234153): [<000000000014e4cc>] irq_exit+0xac/0x108 [1038876.562337] ---[ end trace 6c96d467b1c3ca06 ]---

Similarly we do not free the channel program when we are removing the vfio-ccw device. Let's fix this by resetting the device and freeing the channel program and pinned pages in the release path. For the remove path we can just quiesce the device, since in the remove path the mediated device is going away for good and so we don't need to do a full reset.

Signed-off-by: Farhan Ali alifm@linux.ibm.com Message-Id: ae9f20dc8873f2027f7b3c5d2aaa0bdfe06850b8.1554756534.git.alifm@linux.ibm.com Acked-by: Eric Farman farman@linux.ibm.com Signed-off-by: Cornelia Huck cohuck@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/s390/cio/vfio_ccw_ops.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index f673e106c0415..dc5ff47de3fee 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -130,11 +130,12 @@ static int vfio_ccw_mdev_remove(struct mdev_device *mdev)

if ((private->state != VFIO_CCW_STATE_NOT_OPER) && (private->state != VFIO_CCW_STATE_STANDBY)) { - if (!vfio_ccw_mdev_reset(mdev)) + if (!vfio_ccw_sch_quiesce(private->sch)) private->state = VFIO_CCW_STATE_STANDBY; /* The state will be NOT_OPER on error. */ }

+ cp_free(&private->cp); private->mdev = NULL; atomic_inc(&private->avail);

@@ -158,6 +159,14 @@ static void vfio_ccw_mdev_release(struct mdev_device *mdev) struct vfio_ccw_private *private = dev_get_drvdata(mdev_parent_dev(mdev));

+ if ((private->state != VFIO_CCW_STATE_NOT_OPER) && + (private->state != VFIO_CCW_STATE_STANDBY)) { + if (!vfio_ccw_mdev_reset(mdev)) + private->state = VFIO_CCW_STATE_STANDBY; + /* The state will be NOT_OPER on error. */ + } + + cp_free(&private->cp); vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, &private->nb); }

[ Upstream commit d4645d30b50d1691c26ff0f8fa4e718b08f8d3bb ]

The test robot reported a wrong assignment of a per-CPU variable which it detected by using sparse and sent a report. The assignment itself is correct. The annotation for sparse was wrong and hence the report. The first pointer is a "normal" pointer and points to the per-CPU memory area. That means that the __percpu annotation has to be moved.

Move the __percpu annotation to pointer which points to the per-CPU area. This change affects only the sparse tool (and is ignored by the compiler).

Reported-by: kbuild test robot lkp@intel.com Signed-off-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Paul E. McKenney paulmck@linux.ibm.com Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Fixes: f97f8f06a49fe ("smpboot: Provide infrastructure for percpu hotplug threads") Link: http://lkml.kernel.org/r/20190424085253.12178-1-bigeasy@linutronix.de Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/smpboot.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index d0884b5250010..9d1bc65d226cc 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -29,7 +29,7 @@ struct smpboot_thread_data; * @thread_comm: The base name of the thread */ struct smp_hotplug_thread { - struct task_struct __percpu **store; + struct task_struct * __percpu *store; struct list_head list; int (*thread_should_run)(unsigned int cpu); void (*thread_fn)(unsigned int cpu);

[ Upstream commit 29da93fea3ea39ab9b12270cc6be1b70ef201c9e ]

Randy reported objtool triggered on his (GCC-7.4) build:

lib/strncpy_from_user.o: warning: objtool: strncpy_from_user()+0x315: call to __ubsan_handle_add_overflow() with UACCESS enabled lib/strnlen_user.o: warning: objtool: strnlen_user()+0x337: call to __ubsan_handle_sub_overflow() with UACCESS enabled

This is due to UBSAN generating signed-overflow-UB warnings where it should not. Prior to GCC-8 UBSAN ignored -fwrapv (which the kernel uses through -fno-strict-overflow).

Make the functions use 'unsigned long' throughout.

Reported-by: Randy Dunlap rdunlap@infradead.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Acked-by: Randy Dunlap rdunlap@infradead.org # build-tested Acked-by: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: luto@kernel.org Link: http://lkml.kernel.org/r/20190424072208.754094071@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- lib/strncpy_from_user.c | 5 +++-- lib/strnlen_user.c | 4 ++-- 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index b53e1b5d80f42..e304b54c9c7dd 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -23,10 +23,11 @@ * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ -static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max) +static inline long do_strncpy_from_user(char *dst, const char __user *src, + unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; - long res = 0; + unsigned long res = 0;

/* * Truncate 'max' to the user-specified limit, so that diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index 60d0bbda8f5e5..184f80f7bacfa 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -28,7 +28,7 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; - long align, res = 0; + unsigned long align, res = 0; unsigned long c;

/* @@ -42,7 +42,7 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, * Do everything aligned. But that means that we * need to also expand the maximum.. */ - align = (sizeof(long) - 1) & (unsigned long)src; + align = (sizeof(unsigned long) - 1) & (unsigned long)src; src -= align; max += align;

[ Upstream commit 096377525cdb8251e4656085efc988bdf733fb4c ]

According to the logitech_hidpp_2.0_specification_draft_2012-06-04.pdf doc: https://lekensteyn.nl/files/logitech/logitech_hidpp_2.0_specification_draft_...

We should use a register-access-protocol request using the short input / output report ids. This is necessary because 27MHz HID++ receivers have a max-packetsize on their HIP++ endpoint of 8, so they cannot support long reports. Using a feature-access-protocol request (which is always long or very-long) with these will cause a timeout error, followed by the hidpp driver treating the device as not being HID++ capable.

This commit fixes this by switching to using a rap request to get the protocol version.

Besides being tested with a (046d:c517) 27MHz receiver with various 27MHz keyboards and mice, this has also been tested to not cause regressions on a non-unifying dual-HID++ nano receiver (046d:c534) with k270 and m185 HID++-2.0 devices connected and on a unifying/dj receiver (046d:c52b) with a HID++-2.0 Logitech Rechargeable Touchpad T650.

Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Benjamin Tissoires benjamin.tissoires@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/hid-logitech-hidpp.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 8425d3548a414..edf224ad13369 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -725,13 +725,16 @@ static int hidpp_root_get_feature(struct hidpp_device *hidpp, u16 feature,

static int hidpp_root_get_protocol_version(struct hidpp_device *hidpp) { + const u8 ping_byte = 0x5a; + u8 ping_data[3] = { 0, 0, ping_byte }; struct hidpp_report response; int ret;

- ret = hidpp_send_fap_command_sync(hidpp, + ret = hidpp_send_rap_command_sync(hidpp, + REPORT_ID_HIDPP_SHORT, HIDPP_PAGE_ROOT_IDX, CMD_ROOT_GET_PROTOCOL_VERSION, - NULL, 0, &response); + ping_data, sizeof(ping_data), &response);

if (ret == HIDPP_ERROR_INVALID_SUBID) { hidpp->protocol_major = 1; @@ -751,8 +754,14 @@ static int hidpp_root_get_protocol_version(struct hidpp_device *hidpp) if (ret) return ret;

- hidpp->protocol_major = response.fap.params[0]; - hidpp->protocol_minor = response.fap.params[1]; + if (response.rap.params[2] != ping_byte) { + hid_err(hidpp->hid_dev, "%s: ping mismatch 0x%02x != 0x%02x\n", + __func__, response.rap.params[2], ping_byte); + return -EPROTO; + } + + hidpp->protocol_major = response.rap.params[0]; + hidpp->protocol_minor = response.rap.params[1];

return ret; }

[ Upstream commit 44b9f86cd41db6c522effa5aec251d664a52fbc0 ]

The call to of_find_compatible_node returns a node pointer with refcount incremented thus it must be explicitly decremented after the last usage.

Detected by coccinelle with the following warnings: ./drivers/pinctrl/samsung/pinctrl-exynos-arm.c:76:2-8: ERROR: missing of_node_put; acquired a node pointer with refcount incremented on line 66, but without a corresponding object release within this function. ./drivers/pinctrl/samsung/pinctrl-exynos-arm.c:82:1-7: ERROR: missing of_node_put; acquired a node pointer with refcount incremented on line 66, but without a corresponding object release within this function.

Signed-off-by: Wen Yang wen.yang99@zte.com.cn Cc: Linus Walleij linus.walleij@linaro.org Cc: Tomasz Figa tomasz.figa@gmail.com Cc: Sylwester Nawrocki s.nawrocki@samsung.com Cc: Kukjin Kim kgene@kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-gpio@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reviewed-by: Krzysztof Kozlowski krzk@kernel.org Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pinctrl/samsung/pinctrl-exynos-arm.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm.c index 44c6b753f692a..85ddf49a51885 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos-arm.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm.c @@ -71,6 +71,7 @@ s5pv210_retention_init(struct samsung_pinctrl_drv_data *drvdata, }

clk_base = of_iomap(np, 0); + of_node_put(np); if (!clk_base) { pr_err("%s: failed to map clock registers\n", __func__); return ERR_PTR(-EINVAL);

[ Upstream commit 0d2e2a82d4de298d006bf8eddc86829e3c7da820 ]

Uncore PMU drivers face an awkward cyclic dependency wherein:

- They have to pick a valid online CPU to associate with before registering the PMU device, since it will get exposed to userspace immediately. - The PMU registration has to be be at least partly complete before hotplug events can be handled, since trying to migrate an uninitialised context would be bad. - The hotplug handler has to be ready as soon as a CPU is chosen, lest it go offline without the user-visible cpumask value getting updated.

The arm-cci driver has tried to solve this by using get_cpu() to pick the current CPU and prevent it from disappearing while both registrations are performed, but that results in taking mutexes with preemption disabled, which makes certain configurations very unhappy:

[ 1.983337] BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:2004 [ 1.983340] in_atomic(): 1, irqs_disabled(): 0, pid: 1, name: swapper/0 [ 1.983342] Preemption disabled at: [ 1.983353] [<ffffff80089801f4>] cci_pmu_probe+0x1dc/0x488 [ 1.983360] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.18.20-rt8-yocto-preempt-rt #1 [ 1.983362] Hardware name: ZynqMP ZCU102 Rev1.0 (DT) [ 1.983364] Call trace: [ 1.983369] dump_backtrace+0x0/0x158 [ 1.983372] show_stack+0x24/0x30 [ 1.983378] dump_stack+0x80/0xa4 [ 1.983383] ___might_sleep+0x138/0x160 [ 1.983386] __might_sleep+0x58/0x90 [ 1.983391] __rt_mutex_lock_state+0x30/0xc0 [ 1.983395] _mutex_lock+0x24/0x30 [ 1.983400] perf_pmu_register+0x2c/0x388 [ 1.983404] cci_pmu_probe+0x2bc/0x488 [ 1.983409] platform_drv_probe+0x58/0xa8

It is not feasible to resolve all the possible races outside of the perf core itself, so address the immediate bug by following the example of nearly every other PMU driver and not even trying to do so. Registering the hotplug notifier first should minimise the window in which things can go wrong, so that's about as much as we can reasonably do here. This also revealed an additional race in assigning the global pointer too late relative to the hotplug notifier, which gets fixed in the process.

Reported-by: Li, Meng Meng.Li@windriver.com Tested-by: Corentin Labbe clabbe.montjoie@gmail.com Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com Signed-off-by: Robin Murphy robin.murphy@arm.com Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/perf/arm-cci.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c index 1bfeb160c5b16..14a541c453e58 100644 --- a/drivers/perf/arm-cci.c +++ b/drivers/perf/arm-cci.c @@ -1692,21 +1692,24 @@ static int cci_pmu_probe(struct platform_device *pdev) raw_spin_lock_init(&cci_pmu->hw_events.pmu_lock); mutex_init(&cci_pmu->reserve_mutex); atomic_set(&cci_pmu->active_events, 0); - cci_pmu->cpu = get_cpu(); - - ret = cci_pmu_init(cci_pmu, pdev); - if (ret) { - put_cpu(); - return ret; - }

+ cci_pmu->cpu = raw_smp_processor_id(); + g_cci_pmu = cci_pmu; cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_CCI_ONLINE, "perf/arm/cci:online", NULL, cci_pmu_offline_cpu); - put_cpu(); - g_cci_pmu = cci_pmu; + + ret = cci_pmu_init(cci_pmu, pdev); + if (ret) + goto error_pmu_init; + pr_info("ARM %s PMU driver probed", cci_pmu->model->name); return 0; + +error_pmu_init: + cpuhp_remove_state(CPUHP_AP_PERF_ARM_CCI_ONLINE); + g_cci_pmu = NULL; + return ret; }

static int cci_pmu_remove(struct platform_device *pdev)

[ Upstream commit bbeefa7357a648afe70e7183914c87c3878d528d ]

The error return value is not written by some firmware codecs, such as MPEG-2 decode on CodaHx4. Clear the error return value before starting the picture run to avoid misinterpreting unrelated values returned by sequence initialization as error return value.

Signed-off-by: Philipp Zabel p.zabel@pengutronix.de Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/platform/coda/coda-bit.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c index d20d3df5778bc..a3cfefdbee127 100644 --- a/drivers/media/platform/coda/coda-bit.c +++ b/drivers/media/platform/coda/coda-bit.c @@ -1999,6 +1999,9 @@ static int coda_prepare_decode(struct coda_ctx *ctx) /* Clear decode success flag */ coda_write(dev, 0, CODA_RET_DEC_PIC_SUCCESS);

+ /* Clear error return value */ + coda_write(dev, 0, CODA_RET_DEC_PIC_ERR_MB); + trace_coda_dec_pic_run(ctx, meta);

coda_command_async(ctx, CODA_COMMAND_PIC_RUN);

[ Upstream commit f604f0f5afb88045944567f604409951b5eb6af8 ]

If the application was streaming from both videoX and vbiX, and streaming from videoX was stopped, then the vbi streaming also stopped.

The cause being that stop_streaming for video stopped the subdevs as well, instead of only doing that if dev->streaming_users reached 0.

au0828_stop_vbi_streaming was also wrong since it didn't stop the subdevs at all when dev->streaming_users reached 0.

Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Tested-by: Shuah Khan shuah@kernel.org Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/au0828/au0828-video.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c index 62b45062b1e68..72095465856a2 100644 --- a/drivers/media/usb/au0828/au0828-video.c +++ b/drivers/media/usb/au0828/au0828-video.c @@ -839,9 +839,9 @@ int au0828_start_analog_streaming(struct vb2_queue *vq, unsigned int count) return rc; }

+ v4l2_device_call_all(&dev->v4l2_dev, 0, video, s_stream, 1); + if (vq->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) { - v4l2_device_call_all(&dev->v4l2_dev, 0, video, - s_stream, 1); dev->vid_timeout_running = 1; mod_timer(&dev->vid_timeout, jiffies + (HZ / 10)); } else if (vq->type == V4L2_BUF_TYPE_VBI_CAPTURE) { @@ -861,10 +861,11 @@ static void au0828_stop_streaming(struct vb2_queue *vq)

dprintk(1, "au0828_stop_streaming called %d\n", dev->streaming_users);

- if (dev->streaming_users-- == 1) + if (dev->streaming_users-- == 1) { au0828_uninit_isoc(dev); + v4l2_device_call_all(&dev->v4l2_dev, 0, video, s_stream, 0); + }

- v4l2_device_call_all(&dev->v4l2_dev, 0, video, s_stream, 0); dev->vid_timeout_running = 0; del_timer_sync(&dev->vid_timeout);

@@ -893,8 +894,10 @@ void au0828_stop_vbi_streaming(struct vb2_queue *vq) dprintk(1, "au0828_stop_vbi_streaming called %d\n", dev->streaming_users);

- if (dev->streaming_users-- == 1) + if (dev->streaming_users-- == 1) { au0828_uninit_isoc(dev); + v4l2_device_call_all(&dev->v4l2_dev, 0, video, s_stream, 0); + }

spin_lock_irqsave(&dev->slock, flags); if (dev->isoc_ctl.vbi_buf != NULL) {

[ Upstream commit 70c4cf17e445264453bc5323db3e50aa0ac9e81f ]

In audit_rule_change(), audit_data_to_entry() is firstly invoked to translate the payload data to the kernel's rule representation. In audit_data_to_entry(), depending on the audit field type, an audit tree may be created in audit_make_tree(), which eventually invokes kmalloc() to allocate the tree. Since this tree is a temporary tree, it will be then freed in the following execution, e.g., audit_add_rule() if the message type is AUDIT_ADD_RULE or audit_del_rule() if the message type is AUDIT_DEL_RULE. However, if the message type is neither AUDIT_ADD_RULE nor AUDIT_DEL_RULE, i.e., the default case of the switch statement, this temporary tree is not freed.

To fix this issue, only allocate the tree when the type is AUDIT_ADD_RULE or AUDIT_DEL_RULE.

Signed-off-by: Wenwen Wang wang6495@umn.edu Reviewed-by: Richard Guy Briggs rgb@redhat.com Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/auditfilter.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index bf309f2592c46..425c67e4f5681 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1114,22 +1114,24 @@ int audit_rule_change(int type, int seq, void *data, size_t datasz) int err = 0; struct audit_entry *entry;

- entry = audit_data_to_entry(data, datasz); - if (IS_ERR(entry)) - return PTR_ERR(entry); - switch (type) { case AUDIT_ADD_RULE: + entry = audit_data_to_entry(data, datasz); + if (IS_ERR(entry)) + return PTR_ERR(entry); err = audit_add_rule(entry); audit_log_rule_change("add_rule", &entry->rule, !err); break; case AUDIT_DEL_RULE: + entry = audit_data_to_entry(data, datasz); + if (IS_ERR(entry)) + return PTR_ERR(entry); err = audit_del_rule(entry); audit_log_rule_change("remove_rule", &entry->rule, !err); break; default: - err = -EINVAL; WARN_ON(1); + return -EINVAL; }

if (err || type == AUDIT_DEL_RULE) {

[ Upstream commit 898bc40bfcc26abb6e06e960d6d4754c36c58b50 ]

Fix au0828_analog_stream_enable() to check if device is in the right state first. When unbind happens while bind is in progress, usbdev pointer could be invalid in au0828_analog_stream_enable() and a call to usb_ifnum_to_if() will result in the null pointer dereference.

This problem is found with the new media_dev_allocator.sh test.

kernel: [ 590.359623] BUG: unable to handle kernel NULL pointer dereference at 00000000000004e8 kernel: [ 590.359627] #PF error: [normal kernel read fault] kernel: [ 590.359629] PGD 0 P4D 0 kernel: [ 590.359632] Oops: 0000 [#1] SMP PTI kernel: [ 590.359634] CPU: 3 PID: 1458 Comm: v4l_id Not tainted 5.1.0-rc2+ #30 kernel: [ 590.359636] Hardware name: Dell Inc. OptiPlex 7 90/0HY9JP, BIOS A18 09/24/2013 kernel: [ 590.359641] RIP: 0010:usb_ifnum_to_if+0x6/0x60 kernel: [ 590.359643] Code: 5d 41 5e 41 5f 5d c3 48 83 c4 10 b8 fa ff ff ff 5b 41 5c 41 5d 41 5e 41 5f 5d c3 b8 fa ff ff ff c3 0f 1f 00 6 6 66 66 66 90 55 <48> 8b 97 e8 04 00 00 48 89 e5 48 85 d2 74 41 0f b6 4a 04 84 c 9 74 kernel: [ 590.359645] RSP: 0018:ffffad3cc3c1fc00 EFLAGS: 00010246 kernel: [ 590.359646] RAX: 0000000000000000 RBX: ffff8ded b1f3c000 RCX: 1f377e4500000000 kernel: [ 590.359648] RDX: ffff8dedfa3a6b50 RSI: 00000000 00000000 RDI: 0000000000000000 kernel: [ 590.359649] RBP: ffffad3cc3c1fc28 R08: 00000000 8574acc2 R09: ffff8dedfa3a6b50 kernel: [ 590.359650] R10: 0000000000000001 R11: 00000000 00000000 R12: 0000000000000000 kernel: [ 590.359652] R13: ffff8dedb1f3f0f0 R14: ffffffff adcf7ec0 R15: 0000000000000000 kernel: [ 590.359654] FS: 00007f7917198540(0000) GS:ffff 8dee258c0000(0000) knlGS:0000000000000000 kernel: [ 590.359655] CS: 0010 DS: 0000 ES: 0000 CR0: 00 00000080050033 kernel: [ 590.359657] CR2: 00000000000004e8 CR3: 00000001 a388e002 CR4: 00000000000606e0 kernel: [ 590.359658] Call Trace: kernel: [ 590.359664] ? au0828_analog_stream_enable+0x2c/0x180 kernel: [ 590.359666] au0828_v4l2_open+0xa4/0x110 kernel: [ 590.359670] v4l2_open+0x8b/0x120 kernel: [ 590.359674] chrdev_open+0xa6/0x1c0 kernel: [ 590.359676] ? cdev_put.part.3+0x20/0x20 kernel: [ 590.359678] do_dentry_open+0x1f6/0x360 kernel: [ 590.359681] vfs_open+0x2f/0x40 kernel: [ 590.359684] path_openat+0x299/0xc20 kernel: [ 590.359688] do_filp_open+0x9b/0x110 kernel: [ 590.359695] ? _raw_spin_unlock+0x27/0x40 kernel: [ 590.359697] ? __alloc_fd+0xb2/0x160 kernel: [ 590.359700] do_sys_open+0x1ba/0x260 kernel: [ 590.359702] ? do_sys_open+0x1ba/0x260 kernel: [ 590.359712] __x64_sys_openat+0x20/0x30 kernel: [ 590.359715] do_syscall_64+0x5a/0x120 kernel: [ 590.359718] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Signed-off-by: Shuah Khan shuah@kernel.org Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/au0828/au0828-video.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c index 72095465856a2..3e111f7f56dfe 100644 --- a/drivers/media/usb/au0828/au0828-video.c +++ b/drivers/media/usb/au0828/au0828-video.c @@ -758,6 +758,9 @@ static int au0828_analog_stream_enable(struct au0828_dev *d)

dprintk(1, "au0828_analog_stream_enable called\n");

+ if (test_bit(DEV_DISCONNECTED, &d->dev_state)) + return -ENODEV; + iface = usb_ifnum_to_if(d->usbdev, 0); if (iface && iface->cur_altsetting->desc.bAlternateSetting != 5) { dprintk(1, "Changing intf#0 to alt 5\n");

[ Upstream commit ba7ecfe43d6bf12e2aa76705c45f7d187ae3d7c0 ]

This fixes unmet direct dependencies seen when CONFIG_STM32_DFSDM_ADC is selected:

WARNING: unmet direct dependencies detected for IIO_BUFFER_HW_CONSUMER Depends on [n]: IIO [=y] && IIO_BUFFER [=n] Selected by [y]: - STM32_DFSDM_ADC [=y] && IIO [=y] && (ARCH_STM32 [=y] && OF [=y] || COMPILE_TEST [=n])

Fixes: e2e6771c6462 ("IIO: ADC: add STM32 DFSDM sigma delta ADC support")

Signed-off-by: Fabrice Gasnier fabrice.gasnier@st.com Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iio/adc/Kconfig | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index 4a754921fb6f9..9421c1ec86f73 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -696,6 +696,7 @@ config STM32_DFSDM_ADC depends on (ARCH_STM32 && OF) || COMPILE_TEST select STM32_DFSDM_CORE select REGMAP_MMIO + select IIO_BUFFER select IIO_BUFFER_HW_CONSUMER help Select this option to support ADCSigma delta modulator for

[ Upstream commit 2d4d9b308f8f8dec68f6dbbff18c68ec7c6bd26f ]

When booted with "topology_updates=no", or when "off" is written to /proc/powerpc/topology_updates, NUMA reassignments are inhibited for PRRN and VPHN events. However, migration and suspend unconditionally re-enable reassignments via start_topology_update(). This is incoherent.

Check the topology_updates_enabled flag in start/stop_topology_update() so that callers of those APIs need not be aware of whether reassignments are enabled. This allows the administrative decision on reassignments to remain in force across migrations and suspensions.

Signed-off-by: Nathan Lynch nathanl@linux.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/mm/numa.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 10fb43efef508..f473c05e96497 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1495,6 +1495,9 @@ int start_topology_update(void) { int rc = 0;

+ if (!topology_updates_enabled) + return 0; + if (firmware_has_feature(FW_FEATURE_PRRN)) { if (!prrn_enabled) { prrn_enabled = 1; @@ -1524,6 +1527,9 @@ int stop_topology_update(void) { int rc = 0;

+ if (!topology_updates_enabled) + return 0; + if (prrn_enabled) { prrn_enabled = 0; #ifdef CONFIG_SMP @@ -1579,11 +1585,13 @@ static ssize_t topology_write(struct file *file, const char __user *buf,

kbuf[read_len] = '\0';

- if (!strncmp(kbuf, "on", 2)) + if (!strncmp(kbuf, "on", 2)) { + topology_updates_enabled = true; start_topology_update(); - else if (!strncmp(kbuf, "off", 3)) + } else if (!strncmp(kbuf, "off", 3)) { stop_topology_update(); - else + topology_updates_enabled = false; + } else return -EINVAL;

return count; @@ -1598,9 +1606,7 @@ static const struct file_operations topology_ops = {

static int topology_update_init(void) { - /* Do not poll for changes if disabled at boot */ - if (topology_updates_enabled) - start_topology_update(); + start_topology_update();

if (vphn_enabled) topology_schedule_update();

[ Upstream commit fe6f1a6a8eedc1aa538fee0baa612b6a59639cf8 ]

When the system boots with random.trust_cpu=1 it doesn't initialize the per-NUMA CRNGs because it skips the rest of the CRNG startup code. This means that the code from 1e7f583af67b ("random: make /dev/urandom scalable for silly userspace programs") is not used when random.trust_cpu=1.

crash> dmesg | grep random: [ 0.000000] random: get_random_bytes called from start_kernel+0x94/0x530 with crng_init=0 [ 0.314029] random: crng done (trusting CPU's manufacturer) crash> print crng_node_pool $6 = (struct crng_state **) 0x0

After adding the missing call to numa_crng_init() the per-NUMA CRNGs are initialized again:

crash> dmesg | grep random: [ 0.000000] random: get_random_bytes called from start_kernel+0x94/0x530 with crng_init=0 [ 0.314031] random: crng done (trusting CPU's manufacturer) crash> print crng_node_pool $1 = (struct crng_state **) 0xffff9a915f4014a0

The call to invalidate_batched_entropy() was also missing. This is important for architectures like PPC and S390 which only have the arch_get_random_seed_* functions.

Fixes: 39a8883a2b98 ("random: add a config option to trust the CPU's hwrng") Signed-off-by: Jon DeVree nuxi@vault24.org Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/char/random.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c index c75b6cdf00533..a4515703cfcdd 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -778,6 +778,7 @@ static struct crng_state **crng_node_pool __read_mostly; #endif

static void invalidate_batched_entropy(void); +static void numa_crng_init(void);

static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU); static int __init parse_trust_cpu(char *arg) @@ -806,7 +807,9 @@ static void crng_initialize(struct crng_state *crng) } crng->state[i] ^= rv; } - if (trust_cpu && arch_init) { + if (trust_cpu && arch_init && crng == &primary_crng) { + invalidate_batched_entropy(); + numa_crng_init(); crng_init = 2; pr_notice("random: crng done (trusting CPU's manufacturer)\n"); }

[ Upstream commit 4dcabece4c3a9f9522127be12cc12cc120399b2f ]

The number of descendant cgroups and the number of dying descendant cgroups are currently synchronized using the cgroup_mutex.

The number of descendant cgroups will be required by the cgroup v2 freezer, which will use it to determine if a cgroup is frozen (depending on total number of descendants and number of frozen descendants). It's not always acceptable to grab the cgroup_mutex, especially from quite hot paths (e.g. exit()).

To avoid this, let's additionally synchronize these counters using the css_set_lock.

So, it's safe to read these counters with either cgroup_mutex or css_set_lock locked, and for changing both locks should be acquired.

Signed-off-by: Roman Gushchin guro@fb.com Signed-off-by: Tejun Heo tj@kernel.org Cc: kernel-team@fb.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/cgroup-defs.h | 5 +++++ kernel/cgroup/cgroup.c | 6 ++++++ 2 files changed, 11 insertions(+)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 6002275937f55..a6090154b2ab7 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -346,6 +346,11 @@ struct cgroup { * Dying cgroups are cgroups which were deleted by a user, * but are still existing because someone else is holding a reference. * max_descendants is a maximum allowed number of descent cgroups. + * + * nr_descendants and nr_dying_descendants are protected + * by cgroup_mutex and css_set_lock. It's fine to read them holding + * any of cgroup_mutex and css_set_lock; for writing both locks + * should be held. */ int nr_descendants; int nr_dying_descendants; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 63dae7e0ccae7..81441117f6114 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4659,9 +4659,11 @@ static void css_release_work_fn(struct work_struct *work) if (cgroup_on_dfl(cgrp)) cgroup_rstat_flush(cgrp);

+ spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) tcgrp->nr_dying_descendants--; + spin_unlock_irq(&css_set_lock);

cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id); cgrp->id = -1; @@ -4874,12 +4876,14 @@ static struct cgroup *cgroup_create(struct cgroup *parent) if (ret) goto out_idr_free;

+ spin_lock_irq(&css_set_lock); for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;

if (tcgrp != cgrp) tcgrp->nr_descendants++; } + spin_unlock_irq(&css_set_lock);

if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); @@ -5162,10 +5166,12 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) if (parent && cgroup_is_threaded(cgrp)) parent->nr_threaded_children--;

+ spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) { tcgrp->nr_descendants--; tcgrp->nr_dying_descendants++; } + spin_unlock_irq(&css_set_lock);

cgroup1_check_for_release(parent);

[ Upstream commit 1a010e29cfa00fee2888fd2fd4983f848cbafb58 ]

Example of unhandled overflows:

# echo 18446744073709651 > cpu.rt_runtime_us # cat cpu.rt_runtime_us 99

# echo 18446744073709900 > cpu.rt_period_us # cat cpu.rt_period_us 348

After this patch they will fail with -EINVAL.

Signed-off-by: Konstantin Khlebnikov khlebnikov@yandex-team.ru Acked-by: Peter Zijlstra a.p.zijlstra@chello.nl Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Link: http://lkml.kernel.org/r/155125501739.293431.5252197504404771496.stgit@buzz Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/rt.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 2e2955a8cf8fe..b980cc96604fa 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2559,6 +2559,8 @@ int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; if (rt_runtime_us < 0) rt_runtime = RUNTIME_INF; + else if ((u64)rt_runtime_us > U64_MAX / NSEC_PER_USEC) + return -EINVAL;

return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); } @@ -2579,6 +2581,9 @@ int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us) { u64 rt_runtime, rt_period;

+ if (rt_period_us > U64_MAX / NSEC_PER_USEC) + return -EINVAL; + rt_period = rt_period_us * NSEC_PER_USEC; rt_runtime = tg->rt_bandwidth.rt_runtime;

[ Upstream commit a5112277872a56017b777770e2fd4324d4a6c866 ]

The kzalloc here was being used without checking the return - if the kzalloc fails return VCHIQ_ERROR. The call-site of vchiq_platform_init_state() vchiq_init_state() was not responding to an allocation failure so checks for != VCHIQ_SUCCESS and pass VCHIQ_ERROR up to vchiq_platform_init() which then will fail with -EINVAL.

Signed-off-by: Nicholas Mc Guire hofrat@osadl.org Reported-by: kbuild test robot lkp@intel.com Acked-By: Stefan Wahren stefan.wahren@i2se.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- .../staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c | 3 +++ drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c | 2 ++ 2 files changed, 5 insertions(+)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c index e767209030642..c7c8ef67b67fa 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c @@ -208,6 +208,9 @@ vchiq_platform_init_state(VCHIQ_STATE_T *state) struct vchiq_2835_state *platform_state;

state->platform_state = kzalloc(sizeof(*platform_state), GFP_KERNEL); + if (!state->platform_state) + return VCHIQ_ERROR; + platform_state = (struct vchiq_2835_state *)state->platform_state;

platform_state->inited = 1; diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c index 7642ced314364..63ce567eb6b75 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c @@ -2537,6 +2537,8 @@ vchiq_init_state(VCHIQ_STATE_T *state, VCHIQ_SLOT_ZERO_T *slot_zero, local->debug[DEBUG_ENTRIES] = DEBUG_MAX;

status = vchiq_platform_init_state(state); + if (status != VCHIQ_SUCCESS) + return VCHIQ_ERROR;

/* bring up slot handler thread

[ Upstream commit 471ba0e686cb13752bc1ff3216c54b69a2d250ea ]

The QEMU PowerPC/PSeries machine model was not expecting a self-IPI, and it may be a bit surprising thing to do, so have irq_work_queue_on do local queueing when target is the current CPU.

Suggested-by: Steven Rostedt rostedt@goodmis.org Reported-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Tested-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Signed-off-by: Nicholas Piggin npiggin@gmail.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Frederic Weisbecker frederic@kernel.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= clg@kaod.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Paul Mackerras paulus@samba.org Cc: Peter Zijlstra peterz@infradead.org Cc: Suraj Jitindar Singh sjitindarsingh@gmail.com Cc: Thomas Gleixner tglx@linutronix.de Link: https://lkml.kernel.org/r/20190409093403.20994-1-npiggin@gmail.com [ Simplified the preprocessor comments. Fixed unbalanced curly brackets pointed out by Thomas. ] Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/irq_work.c | 75 ++++++++++++++++++++++++++--------------------- 1 file changed, 42 insertions(+), 33 deletions(-)

diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 6b7cdf17ccf89..73288914ed5e7 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -56,61 +56,70 @@ void __weak arch_irq_work_raise(void) */ }

-/* - * Enqueue the irq_work @work on @cpu unless it's already pending - * somewhere. - * - * Can be re-enqueued while the callback is still in progress. - */ -bool irq_work_queue_on(struct irq_work *work, int cpu) +/* Enqueue on current CPU, work must already be claimed and preempt disabled */ +static void __irq_work_queue_local(struct irq_work *work) { - /* All work should have been flushed before going offline */ - WARN_ON_ONCE(cpu_is_offline(cpu)); - -#ifdef CONFIG_SMP - - /* Arch remote IPI send/receive backend aren't NMI safe */ - WARN_ON_ONCE(in_nmi()); + /* If the work is "lazy", handle it from next tick if any */ + if (work->flags & IRQ_WORK_LAZY) { + if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && + tick_nohz_tick_stopped()) + arch_irq_work_raise(); + } else { + if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) + arch_irq_work_raise(); + } +}

+/* Enqueue the irq work @work on the current CPU */ +bool irq_work_queue(struct irq_work *work) +{ /* Only queue if not already pending */ if (!irq_work_claim(work)) return false;

- if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) - arch_send_call_function_single_ipi(cpu); - -#else /* #ifdef CONFIG_SMP */ - irq_work_queue(work); -#endif /* #else #ifdef CONFIG_SMP */ + /* Queue the entry and raise the IPI if needed. */ + preempt_disable(); + __irq_work_queue_local(work); + preempt_enable();

return true; } +EXPORT_SYMBOL_GPL(irq_work_queue);

-/* Enqueue the irq work @work on the current CPU */ -bool irq_work_queue(struct irq_work *work) +/* + * Enqueue the irq_work @work on @cpu unless it's already pending + * somewhere. + * + * Can be re-enqueued while the callback is still in progress. + */ +bool irq_work_queue_on(struct irq_work *work, int cpu) { +#ifndef CONFIG_SMP + return irq_work_queue(work); + +#else /* CONFIG_SMP: */ + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(cpu)); + /* Only queue if not already pending */ if (!irq_work_claim(work)) return false;

- /* Queue the entry and raise the IPI if needed. */ preempt_disable(); - - /* If the work is "lazy", handle it from next tick if any */ - if (work->flags & IRQ_WORK_LAZY) { - if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && - tick_nohz_tick_stopped()) - arch_irq_work_raise(); + if (cpu != smp_processor_id()) { + /* Arch remote IPI send/receive backend aren't NMI safe */ + WARN_ON_ONCE(in_nmi()); + if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) + arch_send_call_function_single_ipi(cpu); } else { - if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) - arch_irq_work_raise(); + __irq_work_queue_local(work); } - preempt_enable();

return true; +#endif /* CONFIG_SMP */ } -EXPORT_SYMBOL_GPL(irq_work_queue); +

bool irq_work_needs_cpu(void) {

[ Upstream commit a4cdc9baee0740748f16e50cd70c2607510df492 ]

Subsequent code relies on the values that qeth_update_from_chp_desc() reads from the CHP descriptor. Rather than dealing with weird errors later on, just handle it properly here.

Signed-off-by: Julian Wiedmann jwi@linux.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/s390/net/qeth_core_main.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 56aacf32f71b0..461afc276db72 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -1370,7 +1370,7 @@ static void qeth_set_multiple_write_queues(struct qeth_card *card) card->qdio.no_out_queues = 4; }

-static void qeth_update_from_chp_desc(struct qeth_card *card) +static int qeth_update_from_chp_desc(struct qeth_card *card) { struct ccw_device *ccwdev; struct channel_path_desc_fmt0 *chp_dsc; @@ -1380,7 +1380,7 @@ static void qeth_update_from_chp_desc(struct qeth_card *card) ccwdev = card->data.ccwdev; chp_dsc = ccw_device_get_chp_desc(ccwdev, 0); if (!chp_dsc) - goto out; + return -ENOMEM;

card->info.func_level = 0x4100 + chp_dsc->desc; if (card->info.type == QETH_CARD_TYPE_IQD) @@ -1395,6 +1395,7 @@ static void qeth_update_from_chp_desc(struct qeth_card *card) kfree(chp_dsc); QETH_DBF_TEXT_(SETUP, 2, "nr:%x", card->qdio.no_out_queues); QETH_DBF_TEXT_(SETUP, 2, "lvl:%02x", card->info.func_level); + return 0; }

static void qeth_init_qdio_info(struct qeth_card *card) @@ -5090,7 +5091,9 @@ int qeth_core_hardsetup_card(struct qeth_card *card)

QETH_DBF_TEXT(SETUP, 2, "hrdsetup"); atomic_set(&card->force_alloc_skb, 0); - qeth_update_from_chp_desc(card); + rc = qeth_update_from_chp_desc(card); + if (rc) + return rc; retry: if (retries < 3) QETH_DBF_MESSAGE(2, "%s Retrying to do IDX activates.\n", @@ -5768,7 +5771,9 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) gdev->cdev[2]->handler = qeth_irq;

qeth_setup_card(card); - qeth_update_from_chp_desc(card); + rc = qeth_update_from_chp_desc(card); + if (rc) + goto err_chp_desc;

card->dev = qeth_alloc_netdev(card); if (!card->dev) { @@ -5806,6 +5811,7 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) qeth_core_free_discipline(card); err_load: free_netdev(card->dev); +err_chp_desc: err_card: qeth_core_free_card(card); err_dev:

[ Upstream commit 7dbcf2b0b770eeb803a416ee8dcbef78e6389d40 ]

Commit

37fe6a42b343 ("x86: Check stack overflow in detail")

added a broad check for the full exception stack area, i.e. it considers the full exception stack area as valid.

That's wrong in two aspects:

1) It does not check the individual areas one by one

2) #DF, NMI and #MCE are not enabling interrupts which means that a regular device interrupt cannot happen in their context. In fact if a device interrupt hits one of those IST stacks that's a bug because some code path enabled interrupts while handling the exception.

Limit the check to the #DB stack and consider all other IST stacks as 'overflow' or invalid.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Borislav Petkov bp@suse.de Cc: Andy Lutomirski luto@kernel.org Cc: "H. Peter Anvin" hpa@zytor.com Cc: Ingo Molnar mingo@redhat.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Mitsuo Hayasaka mitsuo.hayasaka.hu@hitachi.com Cc: Nicolai Stange nstange@suse.de Cc: Sean Christopherson sean.j.christopherson@intel.com Cc: x86-ml x86@kernel.org Link: https://lkml.kernel.org/r/20190414160143.682135110@linutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/irq_64.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 0469cd078db15..b50ac9c7397bb 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -26,9 +26,18 @@ int sysctl_panic_on_stackoverflow; /* * Probabilistic stack overflow check: * - * Only check the stack in process context, because everything else - * runs on the big interrupt stacks. Checking reliably is too expensive, - * so we just check from interrupts. + * Regular device interrupts can enter on the following stacks: + * + * - User stack + * + * - Kernel task stack + * + * - Interrupt stack if a device driver reenables interrupts + * which should only happen in really old drivers. + * + * - Debug IST stack + * + * All other contexts are invalid. */ static inline void stack_overflow_check(struct pt_regs *regs) { @@ -53,8 +62,8 @@ static inline void stack_overflow_check(struct pt_regs *regs) return;

oist = this_cpu_ptr(&orig_ist); - estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN; - estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1]; + estack_bottom = (u64)oist->ist[DEBUG_STACK]; + estack_top = estack_bottom - DEBUG_STKSZ + STACK_TOP_MARGIN; if (regs->sp >= estack_top && regs->sp <= estack_bottom) return;

[ Upstream commit e6f32efb1b128344a2c7df9875bc1a1abaa1d395 ]

On platforms where the MUSB and HCI controllers share PHY0, PHY passby is required when using the HCI controller with the PHY, but it must be disabled when the MUSB controller is used instead.

Without this, PHY0 passby is always enabled, which results in broken peripheral mode on such platforms (e.g. H3/H5).

Fixes: ba4bdc9e1dc0 ("PHY: sunxi: Add driver for sunxi usb phy")

Signed-off-by: Paul Kocialkowski paul.kocialkowski@bootlin.com Signed-off-by: Kishon Vijay Abraham I kishon@ti.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/phy/allwinner/phy-sun4i-usb.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c index 15c8fc2abf01f..1f8809bab002c 100644 --- a/drivers/phy/allwinner/phy-sun4i-usb.c +++ b/drivers/phy/allwinner/phy-sun4i-usb.c @@ -550,6 +550,7 @@ static void sun4i_usb_phy0_id_vbus_det_scan(struct work_struct *work) struct sun4i_usb_phy_data *data = container_of(work, struct sun4i_usb_phy_data, detect.work); struct phy *phy0 = data->phys[0].phy; + struct sun4i_usb_phy *phy = phy_get_drvdata(phy0); bool force_session_end, id_notify = false, vbus_notify = false; int id_det, vbus_det;

@@ -606,6 +607,9 @@ static void sun4i_usb_phy0_id_vbus_det_scan(struct work_struct *work) mutex_unlock(&phy0->mutex); }

+ /* Enable PHY0 passby for host mode only. */ + sun4i_usb_phy_passby(phy, !id_det); + /* Re-route PHY0 if necessary */ if (data->cfg->phy0_dual_route) sun4i_usb_phy0_reroute(data, id_det);

[ Upstream commit 06b6e2a2333eb3581567a7ac43ca465ef45f4daa ]

This patch fixes the problem with the driver being able to add only 7 multicast MAC address filters instead of 16. The problem is fixed by changing the maximum number of MAC address filters to 16+1+1 (two extra are needed because the driver uses 1 for unicast MAC address and 1 for broadcast).

Signed-off-by: Adam Ludkiewicz adam.ludkiewicz@intel.com Tested-by: Andrew Bowers andrewx.bowers@intel.com Signed-off-by: Jeff Kirsher jeffrey.t.kirsher@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index c6d24eaede184..d86f3fa7aa6a4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2399,8 +2399,10 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) (u8 *)&stats, sizeof(stats)); }

-/* If the VF is not trusted restrict the number of MAC/VLAN it can program */ -#define I40E_VC_MAX_MAC_ADDR_PER_VF 12 +/* If the VF is not trusted restrict the number of MAC/VLAN it can program + * MAC filters: 16 for multicast, 1 for MAC, 1 for broadcast + */ +#define I40E_VC_MAX_MAC_ADDR_PER_VF (16 + 1 + 1) #define I40E_VC_MAX_VLAN_PER_VF 8

/**