mm: fix double page fault on arm64 if PTE_AF is cleared
Subsystems (31)
Sasha Levin
maintainerPATCH 20/127 gfs2: clean up iopen glock mess in gfs2_create_inode
In reply to Sasha LevinFrom: Bob Peterson <[email protected]>
[ Upstream commit 2c47c1be51fbded1f7baa2ceaed90f97932f79be ]
Before this patch, gfs2_create_inode had a use-after-free for the iopen glock in some error paths because it did this:
gfs2_glock_put(io_gl); fail_gunlock2: if (io_gl) clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
In some cases, the io_gl was used for create and only had one reference, so the glock might be freed before the clear_bit(). This patch tries to straighten it out by only jumping to the error paths where iopen is properly set, and moving the gfs2_glock_put after the clear_bit.
--- fs/gfs2/inode.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)
fs/gfs2/inode.c +7 -6
@@ -714,7 +714,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error =gfs2_trans_begin (sdp, blocks,0 );if (error) - goto fail_gunlock2; + goto fail_free_inode;if (blocks >1 ) { ip->i_eattr = ip->i_no_addr +1 ;
@@ -725,7 +725,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error =gfs2_glock_get (sdp, ip->i_no_addr, &gfs2_iopen_glops,CREATE , &io_gl);if (error) - goto fail_gunlock2; + goto fail_free_inode;BUG_ON (test_and_set_bit (GLF_INODE_CREATING , &io_gl->gl_flags));
@@ -734,7 +734,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, goto fail_gunlock2;glock_set_object (ip->i_iopen_gh.gh_gl, ip); -gfs2_glock_put (io_gl);gfs2_set_iop (inode);insert_inode_hash (inode);
@@ -767,6 +766,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,mark_inode_dirty (inode);d_instantiate (dentry, inode); +/* After instantiate, errors should result in evict which will destroy +* both inode and iopen glocks properly. */ if (file) { *opened |=FILE_CREATED ; error =finish_open (file, dentry, gfs2_open_common, opened);
@@ -774,15 +775,15 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,gfs2_glock_dq_uninit (ghs);gfs2_glock_dq_uninit (ghs +1 );clear_bit (GLF_INODE_CREATING , &io_gl->gl_flags); +gfs2_glock_put (io_gl);return error; fail_gunlock3:glock_clear_object (io_gl, ip);gfs2_glock_dq_uninit (&ip->i_iopen_gh); -gfs2_glock_put (io_gl); fail_gunlock2: -if (io_gl) -clear_bit (GLF_INODE_CREATING , &io_gl->gl_flags); +clear_bit (GLF_INODE_CREATING , &io_gl->gl_flags); +gfs2_glock_put (io_gl); fail_free_inode:if (ip->i_gl) {glock_clear_object (ip->i_gl, ip);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 72/127 perf cpumap: Fix snprintf overflow check
In reply to Sasha LevinFrom: Christophe JAILLET <[email protected]>
[ Upstream commit d74b181a028bb5a468f0c609553eff6a8fdf4887 ]
'snprintf' returns the number of characters which would be generated for the given input.
If the returned value is *greater than* or equal to the buffer size, it means that the output has been truncated.
Fix the overflow test accordingly.
--- tools/perf/util/cpumap.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
tools/perf/util/cpumap.c +5 -5
@@ -462,7 +462,7 @@ static void set_max_cpu_num(void)/* get the highest possible cpu number for a sparse allocation */ ret =snprintf (path,PATH_MAX ,"%s/devices/system/cpu/possible" , mnt); -if (ret =PATH_MAX ) { +if (ret >=PATH_MAX ) {pr_err ("sysfs path crossed PATH_MAX(%d) size\n" ,PATH_MAX ); goto out; }
@@ -473,7 +473,7 @@ static void set_max_cpu_num(void)/* get the highest present cpu number for a sparse allocation */ ret =snprintf (path,PATH_MAX ,"%s/devices/system/cpu/present" , mnt); -if (ret =PATH_MAX ) { +if (ret >=PATH_MAX ) {pr_err ("sysfs path crossed PATH_MAX(%d) size\n" ,PATH_MAX ); goto out; }
@@ -501,7 +501,7 @@ static void set_max_node_num(void)/* get the highest possible cpu number for a sparse allocation */ ret =snprintf (path,PATH_MAX ,"%s/devices/system/node/possible" , mnt); -if (ret =PATH_MAX ) { +if (ret >=PATH_MAX ) {pr_err ("sysfs path crossed PATH_MAX(%d) size\n" ,PATH_MAX ); goto out; }
@@ -586,7 +586,7 @@ int cpu__setup_cpunode_map(void)return 0 ; n =snprintf (path,PATH_MAX ,"%s/devices/system/node" , mnt); -if (n =PATH_MAX ) { +if (n >=PATH_MAX ) {pr_err ("sysfs path crossed PATH_MAX(%d) size\n" ,PATH_MAX );return -1 ; }
@@ -601,7 +601,7 @@ int cpu__setup_cpunode_map(void)continue ; n =snprintf (buf,PATH_MAX ,"%s/%s" , path, dent1->d_name); -if (n =PATH_MAX ) { +if (n >=PATH_MAX ) {pr_err ("sysfs path crossed PATH_MAX(%d) size\n" ,PATH_MAX );continue ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 106/127 e1000: Do not perform reset in reset_task if we are already down
In reply to Sasha LevinFrom: Alexander Duyck <[email protected]>
[ Upstream commit 49ee3c2ab5234757bfb56a0b3a3cb422f427e3a3 ]
We are seeing a deadlock in e1000 down when NAPI is being disabled. Looking over the kernel function trace of the system it appears that the interface is being closed and then a reset is hitting which deadlocks the interface as the NAPI interface is already disabled.
To prevent this from happening I am disabling the reset task when __E1000_DOWN is already set. In addition code has been added so that we set the __E1000_DOWN while holding the __E1000_RESET flag in e1000_close in order to guarantee that the reset task will not run after we have started the close call.
--- drivers/net/ethernet/intel/e1000/e1000_main.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-)
drivers/net/ethernet/intel/e1000/e1000_main.c +14 -4
@@ -567,8 +567,13 @@ void e1000_reinit_locked(struct e1000_adapter *adapter)WARN_ON (in_interrupt ());while (test_and_set_bit (__E1000_RESETTING, &adapter->flags))msleep (1 ); -e1000_down (adapter); -e1000_up (adapter); + +/* only run the task if not already down */ +if (!test_bit (__E1000_DOWN, &adapter->flags)) { +e1000_down (adapter); +e1000_up (adapter); + } +clear_bit (__E1000_RESETTING, &adapter->flags); }
@@ -1458,10 +1463,15 @@ int e1000_close(struct net_device *netdev)struct e1000_hw *hw = &adapter->hw;int count =E1000_CHECK_RESET_COUNT ; -while (test_bit (__E1000_RESETTING, &adapter->flags) && count--) +while (test_and_set_bit (__E1000_RESETTING, &adapter->flags) && count--)usleep_range (10000 ,20000 ); -WARN_ON (test_bit (__E1000_RESETTING, &adapter->flags)); +WARN_ON (count <0 ); + +/* signal that we're down so that the reset task will no longer run */ +set_bit (__E1000_DOWN, &adapter->flags); +clear_bit (__E1000_RESETTING, &adapter->flags); +e1000_down (adapter);e1000_power_down_phy (adapter);e1000_free_irq (adapter);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 1/127 mm: fix double page fault on arm64 if PTE_AF is cleared
From: Jia He <[email protected]>
[ Upstream commit 83d116c53058d505ddef051e90ab27f57015b025 ]
When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page.
To reproduce the bug, the cmd is as follows after you deployed everything:
make -C src/test/vmmalloc_fork/ TEST_TIME=60m check
Below call trace is from arm64 do_page_fault for debugging purpose:
[ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24
The pte info before __copy_from_user_inatomic is (PTE_AF is cleared):
[ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003,
pmd=000000023d4b3003, pte=360000298607bd3
As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64."
This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page()
Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill).
[1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork
--- mm/memory.c | 104 ++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 89 insertions(+), 15 deletions(-)
mm/memory.c +89 -15
@@ -117,6 +117,18 @@ int randomize_va_space __read_mostly =2 ;#endif +#ifndef arch_faults_on_old_pte +static inline bool arch_faults_on_old_pte (void ) +{ +/* +* Those arches which don't have hw access flag feature need to +* implement their own helper. By default, "true" means pagefault +* will be hit on old pte. +*/ +return true; +} +#endif +static int __init disable_randmaps (char *s) { randomize_va_space =0 ;
@@ -2324,32 +2336,82 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,return same; } -static inline void cow_user_page (struct page *dst,struct page *src,unsigned long va,struct vm_area_struct *vma) +static inline bool cow_user_page (struct page *dst,struct page *src, +struct vm_fault *vmf) { +bool ret; +void *kaddr; +void __user *uaddr; +bool force_mkyoung; +struct vm_area_struct *vma = vmf->vma; +struct mm_struct *mm = vma->vm_mm; +unsigned long addr = vmf->address; +debug_dma_assert_idle (src); +if (likely (src)) { +copy_user_highpage (dst, src, addr, vma); +return true; + } +/* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ -if (unlikely (!src)) { -void *kaddr =kmap_atomic (dst); -void __user *uaddr = (void __user *)(va &PAGE_MASK ); + kaddr =kmap_atomic (dst); + uaddr = (void __user *)(addr &PAGE_MASK ); + +/* +* On architectures with software "accessed" bits, we would +* take a double page fault, so mark it accessed here. +*/ + force_mkyoung =arch_faults_on_old_pte () && !pte_young (vmf->orig_pte); +if (force_mkyoung) { +pte_t entry; + + vmf->pte =pte_offset_map_lock (mm, vmf->pmd, addr, &vmf->ptl); +if (!likely (pte_same (*vmf->pte, vmf->orig_pte))) { +/* +* Other thread has already handled the fault +* and we don't need to do anything. If it's +* not the case, the fault will be triggered +* again on the same address. +*/ + ret = false; + goto pte_unlock; + } + entry =pte_mkyoung (vmf->orig_pte); +if (ptep_set_access_flags (vma, addr, vmf->pte, entry,0 )) +update_mmu_cache (vma, addr, vmf->pte); + } + +/* +* This really shouldn't fail, because the page is there +* in the page tables. But it might just be unreadable, +* in which case we just give up and fill the result with +* zeroes. +*/ +if (__copy_from_user_inatomic (kaddr, uaddr,PAGE_SIZE )) {/* -* This really shouldn't fail, because the page is there -* in the page tables. But it might just be unreadable, -* in which case we just give up and fill the result with -* zeroes. +* Give a warn in case there can be some obscure +* use-case */ -if (__copy_from_user_inatomic (kaddr, uaddr,PAGE_SIZE )) -clear_page (kaddr); -kunmap_atomic (kaddr); -flush_dcache_page (dst); - }else -copy_user_highpage (dst, src, va, vma); +WARN_ON_ONCE (1 ); +clear_page (kaddr); + } + + ret = true; + +pte_unlock: +if (force_mkyoung) +pte_unmap_unlock (vmf->pte, vmf->ptl); +kunmap_atomic (kaddr); +flush_dcache_page (dst); + +return ret; }static gfp_t __get_fault_gfp_mask (struct vm_area_struct *vma)
@@ -2503,7 +2565,19 @@ static int wp_page_copy(struct vm_fault *vmf) vmf->address);if (!new_page) goto oom; -cow_user_page (new_page, old_page, vmf->address, vma); + +if (!cow_user_page (new_page, old_page, vmf)) { +/* +* COW failed, if the fault was solved by other, +* it's fine. If not, userspace would re-fault on +* the same address and we will handle the fault +* from the second attempt. +*/ +put_page (new_page); +if (old_page) +put_page (old_page); +return 0 ; + } }if (mem_cgroup_try_charge (new_page, mm,GFP_KERNEL , &memcg, false))
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 3/127 m68k: q40: Fix info-leak in rtc_ioctl
From: Fuqian Huang <[email protected]>
[ Upstream commit 7cf78b6b12fd5550545e4b73b35dca18bd46b44c ]
When the option is RTC_PLL_GET, pll will be copied to userland via copy_to_user. pll is initialized using mach_get_rtc_pll indirect call and mach_get_rtc_pll is only assigned with function q40_get_rtc_pll in arch/m68k/q40/config.c.
In function q40_get_rtc_pll, the field pll_ctrl is not initialized. This will leak uninitialized stack content to userland. Fix this by zeroing the uninitialized field.
--- arch/m68k/q40/config.c | 1 + 1 file changed, 1 insertion(+)
arch/m68k/q40/config.c +1 -0
@@ -303,6 +303,7 @@ static int q40_get_rtc_pll(struct rtc_pll_info *pll) {int tmp =Q40_RTC_CTRL ; + pll->pll_ctrl =0 ; pll->pll_value = tmp &Q40_RTC_PLL_MASK ;if (tmp &Q40_RTC_PLL_SIGN ) pll->pll_value = -pll->pll_value;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 4/127 gma/gma500: fix a memory disclosure bug due to uninitialized bytes
In reply to Sasha LevinFrom: Kangjie Lu <[email protected]>
[ Upstream commit 57a25a5f754ce27da2cfa6f413cfd366f878db76 ]
best_clock is an object that may be sent out. Object clock contains uninitialized bytes that are copied to best_clock, which leads to memory disclosure and information leak.
--- drivers/gpu/drm/gma500/cdv_intel_display.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/gpu/drm/gma500/cdv_intel_display.c +2 -0
@@ -415,6 +415,8 @@ static bool cdv_intel_find_dp_pll(const struct gma_limit_t *limit,struct gma_crtc *gma_crtc =to_gma_crtc (crtc);struct gma_clock_t clock; +memset (&clock,0 ,sizeof (clock)); +switch (refclk) {case 27000 :if (target <200000 ) {
Signature · 6 lines
2.25.1 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Sasha Levin
maintainerPATCH 2/127 scsi: aacraid: fix illegal IO beyond last LBA
In reply to Sasha LevinFrom: Balsundar P <[email protected]>
[ Upstream commit c86fbe484c10b2cd1e770770db2d6b2c88801c1d ]
The driver fails to handle data when read or written beyond device reported LBA, which triggers kernel panic
--- drivers/scsi/aacraid/aachba.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/scsi/aacraid/aachba.c +4 -4
@@ -2322,13 +2322,13 @@ static int aac_read(struct scsi_cmnd * scsicmd) scsicmd->result =DID_OK <<16 |COMMAND_COMPLETE <<8 |SAM_STAT_CHECK_CONDITION ;set_sense (&dev->fsa_dev[cid].sense_data, -HARDWARE_ERROR ,SENCODE_INTERNAL_TARGET_FAILURE , +ILLEGAL_REQUEST ,SENCODE_LBA_OUT_OF_RANGE ,ASENCODE_INTERNAL_TARGET_FAILURE ,0 ,0 );memcpy (scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data,min_t (size_t,sizeof (dev->fsa_dev[cid].sense_data),SCSI_SENSE_BUFFERSIZE )); scsicmd->scsi_done (scsicmd); -return 1 ; +return 0 ; } dprintk((KERN_DEBUG "aac_read[cpu %d]: lba = %llu, t = %ld.\n",
@@ -2414,13 +2414,13 @@ static int aac_write(struct scsi_cmnd * scsicmd) scsicmd->result =DID_OK <<16 |COMMAND_COMPLETE <<8 |SAM_STAT_CHECK_CONDITION ;set_sense (&dev->fsa_dev[cid].sense_data, -HARDWARE_ERROR ,SENCODE_INTERNAL_TARGET_FAILURE , +ILLEGAL_REQUEST ,SENCODE_LBA_OUT_OF_RANGE ,ASENCODE_INTERNAL_TARGET_FAILURE ,0 ,0 );memcpy (scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data,min_t (size_t,sizeof (dev->fsa_dev[cid].sense_data),SCSI_SENSE_BUFFERSIZE )); scsicmd->scsi_done (scsicmd); -return 1 ; +return 0 ; } dprintk((KERN_DEBUG "aac_write[cpu %d]: lba = %llu, t = %ld.\n",
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 10/127 clk/ti/adpll: allocate room for terminating null
In reply to Sasha LevinFrom: Stephen Kitt <[email protected]>
[ Upstream commit 7f6ac72946b88b89ee44c1c527aa8591ac5ffcbe ]
The buffer allocated in ti_adpll_clk_get_name doesn't account for the terminating null. This patch switches to devm_kasprintf to avoid overflowing.
--- drivers/clk/ti/adpll.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-)
drivers/clk/ti/adpll.c +2 -9
@@ -193,15 +193,8 @@ static const char *ti_adpll_clk_get_name(struct ti_adpll_data *d,if (err)return NULL ; }else { -const char *base_name ="adpll" ; -char *buf; - - buf =devm_kzalloc (d->dev,8 +1 +strlen (base_name) +1 + -strlen (postfix),GFP_KERNEL ); -if (!buf) -return NULL ; -sprintf (buf,"%08lx.%s.%s" , d->pa, base_name, postfix); - name = buf; + name =devm_kasprintf (d->dev,GFP_KERNEL ,"%08lx.adpll.%s" , + d->pa, postfix); }return name;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 15/127 bcache: fix a lost wake-up problem caused by mca_cannibalize_lock
In reply to Sasha LevinFrom: Guoju Fang <[email protected]>
[ Upstream commit 34cf78bf34d48dddddfeeadb44f9841d7864997a ]
This patch fix a lost wake-up problem caused by the race between mca_cannibalize_lock and bch_cannibalize_unlock.
Consider two processes, A and B. Process A is executing mca_cannibalize_lock, while process B takes c->btree_cache_alloc_lock and is executing bch_cannibalize_unlock. The problem happens that after process A executes cmpxchg and will execute prepare_to_wait. In this timeslice process B executes wake_up, but after that process A executes prepare_to_wait and set the state to TASK_INTERRUPTIBLE. Then process A goes to sleep but no one will wake up it. This problem may cause bcache device to dead.
--- drivers/md/bcache/bcache.h | 1 + drivers/md/bcache/btree.c | 12 ++++++++---- drivers/md/bcache/super.c | 1 + 3 files changed, 10 insertions(+), 4 deletions(-)
drivers/md/bcache/bcache.h +1 -0
@@ -548,6 +548,7 @@ struct cache_set {*/ wait_queue_head_t btree_cache_wait;struct task_struct *btree_cache_alloc_lock; +spinlock_t btree_cannibalize_lock;/* * When we free a btree node, we increment the gen of the bucket the
drivers/md/bcache/btree.c +8 -4
@@ -840,15 +840,17 @@ out:static int mca_cannibalize_lock (struct cache_set *c,struct btree_op *op) { -struct task_struct *old; - - old =cmpxchg (&c->btree_cache_alloc_lock,NULL , current); -if (old && old != current) { +spin_lock (&c->btree_cannibalize_lock); +if (likely (c->btree_cache_alloc_lock ==NULL )) { + c->btree_cache_alloc_lock = current; + }else if (c->btree_cache_alloc_lock != current) {if (op)prepare_to_wait (&c->btree_cache_wait, &op->wait,TASK_UNINTERRUPTIBLE ); +spin_unlock (&c->btree_cannibalize_lock);return -EINTR ; } +spin_unlock (&c->btree_cannibalize_lock);return 0 ; }
@@ -883,10 +885,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op,*/ static void bch_cannibalize_unlock (struct cache_set *c) { +spin_lock (&c->btree_cannibalize_lock);if (c->btree_cache_alloc_lock == current) { c->btree_cache_alloc_lock =NULL ;wake_up (&c->btree_cache_wait); } +spin_unlock (&c->btree_cannibalize_lock); } static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op,
drivers/md/bcache/super.c +1 -0
@@ -1510,6 +1510,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)sema_init (&c->sb_write_mutex,1 );mutex_init (&c->bucket_lock);init_waitqueue_head (&c->btree_cache_wait); +spin_lock_init (&c->btree_cannibalize_lock);init_waitqueue_head (&c->bucket_wait);init_waitqueue_head (&c->gc_wait);sema_init (&c->uuid_write_mutex,1 );
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 16/127 RDMA/i40iw: Fix potential use after free
In reply to Sasha LevinFrom: Pan Bian <[email protected]>
[ Upstream commit da046d5f895fca18d63b15ac8faebd5bf784e23a ]
Release variable dst after logging dst->error to avoid possible use after free.
--- drivers/infiniband/hw/i40iw/i40iw_cm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/infiniband/hw/i40iw/i40iw_cm.c +1 -1
@@ -2052,9 +2052,9 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev, dst =i40iw_get_dst_ipv6 (&src_addr, &dst_addr);if (!dst || dst->error) {if (dst) { -dst_release (dst);i40iw_pr_err ("ip6_route_output returned dst->error = %d\n" , dst->error); +dst_release (dst); }return rc; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 22/127 CIFS: Properly process SMB3 lease breaks
In reply to Sasha LevinFrom: Pavel Shilovsky <[email protected]>
[ Upstream commit 9bd4540836684013aaad6070a65d6fcdd9006625 ]
Currenly we doesn't assume that a server may break a lease from RWH to RW which causes us setting a wrong lease state on a file and thus mistakenly flushing data and byte-range locks and purging cached data on the client. This leads to performance degradation because subsequent IOs go directly to the server.
Fix this by propagating new lease state and epoch values to the oplock break handler through cifsFileInfo structure and removing the use of cifsInodeInfo flags for that. It allows to avoid some races of several lease/oplock breaks using those flags in parallel.
--- fs/cifs/cifsglob.h | 9 ++++++--- fs/cifs/file.c | 10 +++++++--- fs/cifs/misc.c | 17 +++-------------- fs/cifs/smb1ops.c | 8 +++----- fs/cifs/smb2misc.c | 32 +++++++------------------------- fs/cifs/smb2ops.c | 44 ++++++++++++++++++++++++++++++-------------- fs/cifs/smb2pdu.h | 2 +- 7 files changed, 57 insertions(+), 65 deletions(-)
fs/cifs/cifsglob.h +6 -3
@@ -246,8 +246,9 @@ struct smb_version_operations {int (*check_message)(char *,unsigned int ,struct TCP_Server_Info *);bool (*is_oplock_break)(char *,struct TCP_Server_Info *);int (*handle_cancelled_mid)(char *,struct TCP_Server_Info *); -void (*downgrade_oplock)(struct TCP_Server_Info *, -struct cifsInodeInfo *,bool ); +void (*downgrade_oplock)(struct TCP_Server_Info *server, +struct cifsInodeInfo *cinode,__u32 oplock, +unsigned int epoch,bool *purge_cache);/* process transaction2 response */ bool (*check_trans2)(struct mid_q_entry *,struct TCP_Server_Info *,char *,int );
@@ -1092,6 +1093,8 @@ struct cifsFileInfo {unsigned int f_flags; bool invalidHandle:1; /* file closed via session abend */ bool oplock_break_cancelled:1; +unsigned int oplock_epoch;/* epoch from the lease break */ +__u32 oplock_level;/* oplock/lease level from the lease break */ int count;spinlock_t file_info_lock;/* protects four flag/count fields above */ struct mutex fh_mutex;/* prevents reopen race after dead ses*/
@@ -1223,7 +1226,7 @@ struct cifsInodeInfo {unsigned int epoch;/* used to track lease state changes */ #define CIFS_INODE_PENDING_OPLOCK_BREAK (0)/* oplock break in progress */ #define CIFS_INODE_PENDING_WRITERS (1)/* Writes in progress */ -#define CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 (2)/* Downgrade oplock to L2 */ +#define CIFS_INODE_FLAG_UNUSED (2)/* Unused flag */ #define CIFS_INO_DELETE_PENDING (3)/* delete pending on server */ #define CIFS_INO_INVALID_MAPPING (4)/* pagecache is invalid */ #define CIFS_INO_LOCK (5)/* lock bit for synchronization */
fs/cifs/file.c +7 -3
@@ -4135,12 +4135,13 @@ void cifs_oplock_break(struct work_struct *work)struct cifs_tcon *tcon =tlink_tcon (cfile->tlink);struct TCP_Server_Info *server = tcon->ses->server;int rc =0 ; +bool purge_cache = false;wait_on_bit (&cinode->flags,CIFS_INODE_PENDING_WRITERS ,TASK_UNINTERRUPTIBLE ); - server->ops->downgrade_oplock (server, cinode, -test_bit (CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 , &cinode->flags)); + server->ops->downgrade_oplock (server, cinode, cfile->oplock_level, + cfile->oplock_epoch, &purge_cache);if (!CIFS_CACHE_WRITE (cinode) &&CIFS_CACHE_READ (cinode) &&cifs_has_mand_locks (cinode)) {
@@ -4155,18 +4156,21 @@ void cifs_oplock_break(struct work_struct *work)else break_lease (inode,O_WRONLY ); rc =filemap_fdatawrite (inode->i_mapping); -if (!CIFS_CACHE_READ (cinode)) { +if (!CIFS_CACHE_READ (cinode) || purge_cache) { rc =filemap_fdatawait (inode->i_mapping);mapping_set_error (inode->i_mapping, rc);cifs_zap_mapping (inode); }cifs_dbg (FYI ,"Oplock flush inode %p rc %d\n" , inode, rc); +if (CIFS_CACHE_WRITE (cinode)) + goto oplock_break_ack; } rc =cifs_push_locks (cfile);if (rc)cifs_dbg (VFS ,"Push locks rc = %d\n" , rc); +oplock_break_ack:/* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do
fs/cifs/misc.c +3 -14
@@ -473,21 +473,10 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)set_bit (CIFS_INODE_PENDING_OPLOCK_BREAK , &pCifsInode->flags); -/* -* Set flag if the server downgrades the oplock -* to L2 else clear. -*/ -if (pSMB->OplockLevel) -set_bit ( -CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 , - &pCifsInode->flags); -else -clear_bit ( -CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 , - &pCifsInode->flags); - -cifs_queue_oplock_break (netfile); + netfile->oplock_epoch =0 ; + netfile->oplock_level = pSMB->OplockLevel; netfile->oplock_break_cancelled = false; +cifs_queue_oplock_break (netfile);spin_unlock (&tcon->open_file_lock);spin_unlock (&cifs_tcp_ses_lock);
fs/cifs/smb1ops.c +3 -5
@@ -379,12 +379,10 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr)static void cifs_downgrade_oplock (struct TCP_Server_Info *server, -struct cifsInodeInfo *cinode,bool set_level2) +struct cifsInodeInfo *cinode,__u32 oplock, +unsigned int epoch,bool *purge_cache) { -if (set_level2) -cifs_set_oplock_level (cinode,OPLOCK_READ ); -else -cifs_set_oplock_level (cinode,0 ); +cifs_set_oplock_level (cinode, oplock); } static bool
fs/cifs/smb2misc.c +7 -25
@@ -496,7 +496,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,cifs_dbg (FYI ,"found in the open list\n" );cifs_dbg (FYI ,"lease key match, lease break 0x%x\n" , -le32_to_cpu (rsp->NewLeaseState)); + lease_state);if (ack_req) cfile->oplock_break_cancelled = false;
@@ -505,17 +505,8 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,set_bit (CIFS_INODE_PENDING_OPLOCK_BREAK , &cinode->flags); -/* -* Set or clear flags depending on the lease state being READ. -* HANDLE caching flag should be added when the client starts -* to defer closing remote file handles with HANDLE leases. -*/ -if (lease_state &SMB2_LEASE_READ_CACHING_HE ) -set_bit (CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 , - &cinode->flags); -else -clear_bit (CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 , - &cinode->flags); + cfile->oplock_epoch =le16_to_cpu (rsp->Epoch); + cfile->oplock_level = lease_state;cifs_queue_oplock_break (cfile);kfree (lw);
@@ -538,7 +529,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,cifs_dbg (FYI ,"found in the pending open list\n" );cifs_dbg (FYI ,"lease key match, lease break 0x%x\n" , -le32_to_cpu (rsp->NewLeaseState)); + lease_state); open->oplock = lease_state; }
@@ -650,18 +641,9 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)set_bit (CIFS_INODE_PENDING_OPLOCK_BREAK , &cinode->flags); -/* -* Set flag if the server downgrades the oplock -* to L2 else clear. -*/ -if (rsp->OplockLevel) -set_bit ( -CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 , - &cinode->flags); -else -clear_bit ( -CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 , - &cinode->flags); + cfile->oplock_epoch =0 ; + cfile->oplock_level = rsp->OplockLevel; +spin_unlock (&cfile->file_info_lock);cifs_queue_oplock_break (cfile);
fs/cifs/smb2ops.c +30 -14
73 lines not on this page · raw message
fs/cifs/smb2pdu.h +1 -1
@@ -1046,7 +1046,7 @@ struct smb2_oplock_break {struct smb2_lease_break {struct smb2_hdr hdr;__le16 StructureSize;/* Must be 44 */ -__le16 Reserved; +__le16 Epoch;__le32 Flags;__u8 LeaseKey[16 ];__le32 CurrentLeaseState;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 23/127 kernel/sys.c: avoid copying possible padding bytes in copy_to_user
In reply to Sasha LevinFrom: Joe Perches <[email protected]>
[ Upstream commit 5e1aada08cd19ea652b2d32a250501d09b02ff2e ]
Initialization is not guaranteed to zero padding bytes so use an explicit memset instead to avoid leaking any kernel content in any possible padding bytes.
--- kernel/sys.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
kernel/sys.c +3 -1
@@ -1217,11 +1217,13 @@ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { -struct oldold_utsname tmp = {}; +struct oldold_utsname tmp;if (!name)return -EFAULT ; +memset (&tmp,0 ,sizeof (tmp)); +down_read (&uts_sem);memcpy (&tmp.sysname, &utsname ()->sysname, __OLD_UTS_LEN);memcpy (&tmp.nodename, &utsname ()->nodename, __OLD_UTS_LEN);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 30/127 dmaengine: zynqmp_dma: fix burst length configuration
In reply to Sasha LevinFrom: Matthias Fend <[email protected]>
[ Upstream commit cc88525ebffc757e00cc5a5d61da6271646c7f5f ]
Since the dma engine expects the burst length register content as power of 2 value, the burst length needs to be converted first. Additionally add a burst length range check to avoid corrupting unrelated register bits.
--- drivers/dma/xilinx/zynqmp_dma.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-)
drivers/dma/xilinx/zynqmp_dma.c +15 -9
@@ -125,10 +125,12 @@/* Max transfer size per descriptor */ #define ZYNQMP_DMA_MAX_TRANS_LEN 0x40000000 +/* Max burst lengths */ +#define ZYNQMP_DMA_MAX_DST_BURST_LEN 32768U +#define ZYNQMP_DMA_MAX_SRC_BURST_LEN 32768U +/* Reset values for data attributes */ #define ZYNQMP_DMA_AXCACHE_VAL 0xF -#define ZYNQMP_DMA_ARLEN_RST_VAL 0xF -#define ZYNQMP_DMA_AWLEN_RST_VAL 0xF#define ZYNQMP_DMA_SRC_ISSUE_RST_VAL 0x1F
@@ -527,17 +529,19 @@ static void zynqmp_dma_handle_ovfl_int(struct zynqmp_dma_chan *chan, u32 status)static void zynqmp_dma_config (struct zynqmp_dma_chan *chan) { -u32 val; +u32 val, burst_val; val =readl (chan->regs +ZYNQMP_DMA_CTRL0 ); val |=ZYNQMP_DMA_POINT_TYPE_SG ;writel (val, chan->regs +ZYNQMP_DMA_CTRL0 ); val =readl (chan->regs +ZYNQMP_DMA_DATA_ATTR ); + burst_val =__ilog2_u32 (chan->src_burst_len); val = (val & ~ZYNQMP_DMA_ARLEN ) | - (chan->src_burst_len <<ZYNQMP_DMA_ARLEN_OFST ); + ((burst_val <<ZYNQMP_DMA_ARLEN_OFST ) &ZYNQMP_DMA_ARLEN ); + burst_val =__ilog2_u32 (chan->dst_burst_len); val = (val & ~ZYNQMP_DMA_AWLEN ) | - (chan->dst_burst_len <<ZYNQMP_DMA_AWLEN_OFST ); + ((burst_val <<ZYNQMP_DMA_AWLEN_OFST ) &ZYNQMP_DMA_AWLEN );writel (val, chan->regs +ZYNQMP_DMA_DATA_ATTR ); }
@@ -551,8 +555,10 @@ static int zynqmp_dma_device_config(struct dma_chan *dchan, {struct zynqmp_dma_chan *chan =to_chan (dchan); - chan->src_burst_len = config->src_maxburst; - chan->dst_burst_len = config->dst_maxburst; + chan->src_burst_len =clamp (config->src_maxburst,1U , +ZYNQMP_DMA_MAX_SRC_BURST_LEN ); + chan->dst_burst_len =clamp (config->dst_maxburst,1U , +ZYNQMP_DMA_MAX_DST_BURST_LEN );return 0 ; }
@@ -873,8 +879,8 @@ static int zynqmp_dma_chan_probe(struct zynqmp_dma_device *zdev,return PTR_ERR (chan->regs); chan->bus_width =ZYNQMP_DMA_BUS_WIDTH_64 ; - chan->dst_burst_len =ZYNQMP_DMA_AWLEN_RST_VAL ; - chan->src_burst_len =ZYNQMP_DMA_ARLEN_RST_VAL ; + chan->dst_burst_len =ZYNQMP_DMA_MAX_DST_BURST_LEN ; + chan->src_burst_len =ZYNQMP_DMA_MAX_SRC_BURST_LEN ; err =of_property_read_u32 (node,"xlnx,bus-width" , &chan->bus_width);if (err <0 ) {dev_err (&pdev->dev,"missing xlnx,bus-width property\n" );
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 31/127 powerpc/eeh: Only dump stack once if an MMIO loop is detected
In reply to Sasha LevinFrom: Oliver O'Halloran <[email protected]>
[ Upstream commit 4e0942c0302b5ad76b228b1a7b8c09f658a1d58a ]
Many drivers don't check for errors when they get a 0xFFs response from an MMIO load. As a result after an EEH event occurs a driver can get stuck in a polling loop unless it some kind of internal timeout logic.
Currently EEH tries to detect and report stuck drivers by dumping a stack trace after eeh_dev_check_failure() is called EEH_MAX_FAILS times on an already frozen PE. The value of EEH_MAX_FAILS was chosen so that a dump would occur every few seconds if the driver was spinning in a loop. This results in a lot of spurious stack traces in the kernel log.
Fix this by limiting it to printing one stack trace for each PE freeze. If the driver is truely stuck the kernel's hung task detector is better suited to reporting the probelm anyway.
--- arch/powerpc/kernel/eeh.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/powerpc/kernel/eeh.c +1 -1
@@ -506,7 +506,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) rc =1 ;if (pe->state &EEH_PE_ISOLATED ) { pe->check_count++; -if (pe->check_count %EEH_MAX_FAILS ==0 ) { +if (pe->check_count ==EEH_MAX_FAILS ) { dn =pci_device_to_OF_node (dev);if (dn) location = of_get_property(dn, "ibm,loc-code",
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 32/127 tracing: Set kernel_stack's caller size properly
In reply to Sasha LevinFrom: Josef Bacik <[email protected]>
[ Upstream commit cbc3b92ce037f5e7536f6db157d185cd8b8f615c ]
I noticed when trying to use the trace-cmd python interface that reading the raw buffer wasn't working for kernel_stack events. This is because it uses a stubbed version of __dynamic_array that doesn't do the __data_loc trick and encode the length of the array into the field. Instead it just shows up as a size of 0. So change this to __array and set the len to FTRACE_STACK_ENTRIES since this is what we actually do in practice and matches how user_stack_trace works.
--- kernel/trace/trace_entries.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/trace/trace_entries.h +1 -1
@@ -179,7 +179,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry,F_STRUCT (__field (int ,size ) - __dynamic_array(unsigned long, caller ) + __array( unsigned long, caller, FTRACE_STACK_ENTRIES ) ), F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 38/127 mm: pagewalk: fix termination condition in walk_pte_range()
In reply to Sasha LevinFrom: Steven Price <[email protected]>
[ Upstream commit c02a98753e0a36ba65a05818626fa6adeb4e7c97 ]
If walk_pte_range() is called with a 'end' argument that is beyond the last page of memory (e.g. ~0UL) then the comparison between 'addr' and 'end' will always fail and the loop will be infinite. Instead change the comparison to >= while accounting for overflow.
--- mm/pagewalk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
mm/pagewalk.c +2 -2
@@ -15,9 +15,9 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, err = walk->pte_entry (pte, addr, addr +PAGE_SIZE , walk);if (err)break ; - addr +=PAGE_SIZE ; -if (addr == end) +if (addr >= end -PAGE_SIZE )break ; + addr +=PAGE_SIZE ; pte++; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 40/127 KVM: fix overflow of zero page refcount with ksm running
In reply to Sasha LevinFrom: Zhuang Yanying <[email protected]>
[ Upstream commit 7df003c85218b5f5b10a7f6418208f31e813f38f ]
We are testing Virtual Machine with KSM on v5.4-rc2 kernel, and found the zero_page refcount overflow.
The cause of refcount overflow is increased in try_async_pf (get_user_page) without being decreased in mmu_set_spte() while handling ept violation.
In kvm_release_pfn_clean(), only unreserved page will call put_page. However, zero page is reserved.
So, as well as creating and destroy vm, the refcount of zero page will continue to increase until it overflows.
step1:
echo 10000 > /sys/kernel/pages_to_scan/pages_to_scan echo 1 > /sys/kernel/pages_to_scan/run
echo 1 > /sys/kernel/pages_to_scan/use_zero_pages
step2:
just create several normal qemu kvm vms.
And destroy it after 10s.
Repeat this action all the time.
After a long period of time, all domains hang because of the refcount of zero page overflow.
Qemu print error log as follow:
…
error: kvm run failed Bad address
EAX=00006cdc EBX=00000008 ECX=80202001 EDX=078bfbfd ESI=ffffffff EDI=00000000 EBP=00000008 ESP=00006cc4 EIP=000efd75 EFL=00010002 [-------] CPL=0 II=0 A20=1 SMM=0 HLT=0
ES =0010 00000000 ffffffff 00c09300 DPL=0 DS [-WA]
CS =0008 00000000 ffffffff 00c09b00 DPL=0 CS32 [-RA]
SS =0010 00000000 ffffffff 00c09300 DPL=0 DS [-WA] DS =0010 00000000 ffffffff 00c09300 DPL=0 DS [-WA] FS =0010 00000000 ffffffff 00c09300 DPL=0 DS [-WA] GS =0010 00000000 ffffffff 00c09300 DPL=0 DS [-WA]
LDT=0000 00000000 0000ffff 00008200 DPL=0 LDT
TR =0000 00000000 0000ffff 00008b00 DPL=0 TSS32-busy
GDT= 000f7070 00000037
IDT= 000f70ae 00000000
CR0=00000011 CR2=00000000 CR3=00000000 CR4=00000000
DR0=0000000000000000 DR1=0000000000000000 DR2=0000000000000000 DR3=0000000000000000
DR6=00000000ffff0ff0 DR7=0000000000000400
EFER=0000000000000000
Code=00 01 00 00 00 e9 e8 00 00 00 c7 05 4c 55 0f 00 01 00 00 00 <8b> 35 00 00 01 00 8b 3d 04 00 01 00 b8 d8 d3 00 00 c1 e0 08 0c ea a3 00 00 01 00 c7 05 04 …
Meanwhile, a kernel warning is departed.
[40914.836375] WARNING: CPU: 3 PID: 82067 at ./include/linux/mm.h:987 try_get_page+0x1f/0x30 [40914.836412] CPU: 3 PID: 82067 Comm: CPU 0/KVM Kdump: loaded Tainted: G OE 5.2.0-rc2 #5 [40914.836415] RIP: 0010:try_get_page+0x1f/0x30 [40914.836417] Code: 40 00 c3 0f 1f 84 00 00 00 00 00 48 8b 47 08 a8 01 75 11 8b 47 34 85 c0 7e 10 f0 ff 47 34 b8 01 00 00 00 c3 48 8d 78 ff eb e9 <0f> 0b 31 c0 c3 66 90 66 2e 0f 1f 84 00 0 0 00 00 00 48 8b 47 08 a8 [40914.836418] RSP: 0018:ffffb4144e523988 EFLAGS: 00010286 [40914.836419] RAX: 0000000080000000 RBX: 0000000000000326 RCX: 0000000000000000 [40914.836420] RDX: 0000000000000000 RSI: 00004ffdeba10000 RDI: ffffdf07093f6440 [40914.836421] RBP: ffffdf07093f6440 R08: 800000424fd91225 R09: 0000000000000000 [40914.836421] R10: ffff9eb41bfeebb8 R11: 0000000000000000 R12: ffffdf06bbd1e8a8 [40914.836422] R13: 0000000000000080 R14: 800000424fd91225 R15: ffffdf07093f6440 [40914.836423] FS: 00007fb60ffff700(0000) GS:ffff9eb4802c0000(0000) knlGS:0000000000000000 [40914.836425] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [40914.836426] CR2: 0000000000000000 CR3: 0000002f220e6002 CR4: 00000000003626e0 [40914.836427] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [40914.836427] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [40914.836428] Call Trace: [40914.836433] follow_page_pte+0x302/0x47b [40914.836437] __get_user_pages+0xf1/0x7d0 [40914.836441] ? irq_work_queue+0x9/0x70 [40914.836443] get_user_pages_unlocked+0x13f/0x1e0 [40914.836469] __gfn_to_pfn_memslot+0x10e/0x400 [kvm] [40914.836486] try_async_pf+0x87/0x240 [kvm] [40914.836503] tdp_page_fault+0x139/0x270 [kvm] [40914.836523] kvm_mmu_page_fault+0x76/0x5e0 [kvm] [40914.836588] vcpu_enter_guest+0xb45/0x1570 [kvm] [40914.836632] kvm_arch_vcpu_ioctl_run+0x35d/0x580 [kvm] [40914.836645] kvm_vcpu_ioctl+0x26e/0x5d0 [kvm] [40914.836650] do_vfs_ioctl+0xa9/0x620 [40914.836653] ksys_ioctl+0x60/0x90 [40914.836654] __x64_sys_ioctl+0x16/0x20 [40914.836658] do_syscall_64+0x5b/0x180 [40914.836664] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [40914.836666] RIP: 0033:0x7fb61cb6bfc7
--- virt/kvm/kvm_main.c | 1 + 1 file changed, 1 insertion(+)
virt/kvm/kvm_main.c +1 -0
@@ -165,6 +165,7 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn)*/ if (pfn_valid (pfn))return PageReserved (pfn_to_page (pfn)) && + !is_zero_pfn (pfn) && !kvm_is_zone_device_pfn (pfn);return true;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 44/127 selinux: sel_avc_get_stat_idx should increase position index
In reply to Sasha LevinFrom: Vasily Averin <[email protected]>
[ Upstream commit 8d269a8e2a8f0bca89022f4ec98de460acb90365 ]
If seq_file .next function does not change position index, read after some lseek can generate unexpected output.
$ dd if=/sys/fs/selinux/avc/cache_stats # usual output lookups hits misses allocations reclaims frees 817223 810034 7189 7189 6992 7037 1934894 1926896 7998 7998 7632 7683 1322812 1317176 5636 5636 5456 5507 1560571 1551548 9023 9023 9056 9115 0+1 records in 0+1 records out 189 bytes copied, 5,1564e-05 s, 3,7 MB/s
$# read after lseek to midle of last line
$ dd if=/sys/fs/selinux/avc/cache_stats bs=180 skip=1 dd: /sys/fs/selinux/avc/cache_stats: cannot skip to specified offset 056 9115 <<<< end of last line 1560571 1551548 9023 9023 9056 9115 <<< whole last line once again 0+1 records in 0+1 records out 45 bytes copied, 8,7221e-05 s, 516 kB/s
$# read after lseek beyond end of of file
$ dd if=/sys/fs/selinux/avc/cache_stats bs=1000 skip=1 dd: /sys/fs/selinux/avc/cache_stats: cannot skip to specified offset 1560571 1551548 9023 9023 9056 9115 <<<< generates whole last line 0+1 records in 0+1 records out 36 bytes copied, 9,0934e-05 s, 396 kB/s
https://bugzilla.kernel.org/show_bug.cgi?id=206283
--- security/selinux/selinuxfs.c | 1 + 1 file changed, 1 insertion(+)
security/selinux/selinuxfs.c +1 -0
@@ -1425,6 +1425,7 @@ static struct avc_cache_stats *sel_avc_get_stat_idx(loff_t *idx) *idx = cpu +1 ;return &per_cpu (avc_cache_stats, cpu); } + (*idx)++;return NULL ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 47/127 drm/omap: fix possible object reference leak
In reply to Sasha LevinFrom: Wen Yang <[email protected]>
[ Upstream commit 47340e46f34a3b1d80e40b43ae3d7a8da34a3541 ]
The call to of_find_matching_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/gpu/drm/omapdrm/dss/omapdss-boot-init.c:212:2-8: ERROR: missing of_node_put; acquired a node pointer with refcount incremented on line 209, but without a corresponding object release within this function. drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c:237:1-7: ERROR: missing of_node_put; acquired a node pointer with refcount incremented on line 209, but without a corresponding object release within this function.
--- drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c +3 -1
@@ -193,7 +193,7 @@ static int __init omapdss_boot_init(void) dss =of_find_matching_node (NULL , omapdss_of_match);if (dss ==NULL || !of_device_is_available (dss)) -return 0 ; + goto put_node;omapdss_walk_device (dss, true);
@@ -218,6 +218,8 @@ static int __init omapdss_boot_init(void)kfree (n); } +put_node: +of_node_put (dss);return 0 ; }
Signature · 6 lines
2.25.1 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Sasha Levin
maintainerPATCH 43/127 audit: CONFIG_CHANGE don't log internal bookkeeping as an event
In reply to Sasha LevinFrom: Steve Grubb <[email protected]>
[ Upstream commit 70b3eeed49e8190d97139806f6fbaf8964306cdb ]
Common Criteria calls out for any action that modifies the audit trail to be recorded. That usually is interpreted to mean insertion or removal of rules. It is not required to log modification of the inode information since the watch is still in effect. Additionally, if the rule is a never rule and the underlying file is one they do not want events for, they get an event for this bookkeeping update against their wishes.
Since no device/inode info is logged at insertion and no device/inode information is logged on update, there is nothing meaningful being communicated to the admin by the CONFIG_CHANGE updated_rules event. One can assume that the rule was not "modified" because it is still watching the intended target. If the device or inode cannot be resolved, then audit_panic is called which is sufficient.
The correct resolution is to drop logging config_update events since the watch is still in effect but just on another unknown inode.
--- kernel/audit_watch.c | 2 -- 1 file changed, 2 deletions(-)
kernel/audit_watch.c +0 -2
@@ -316,8 +316,6 @@ static void audit_update_watch(struct audit_parent *parent,if (oentry->rule.exe)audit_remove_mark (oentry->rule.exe); -audit_watch_log_rule_change (r, owatch,"updated_rules" ); -call_rcu (&oentry->rcu, audit_free_rule_rcu); }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 45/127 scsi: lpfc: Fix RQ buffer leakage when no IOCBs available
In reply to Sasha LevinFrom: James Smart <[email protected]>
[ Upstream commit 39c4f1a965a9244c3ba60695e8ff8da065ec6ac4 ]
The driver is occasionally seeing the following SLI Port error, requiring reset and reinit:
Port Status Event: ... error 1=0x52004a01, error 2=0x218
The failure means an RQ timeout. That is, the adapter had received asynchronous receive frames, ran out of buffer slots to place the frames, and the driver did not replenish the buffer slots before a timeout occurred. The driver should not be so slow in replenishing buffers that a timeout can occur.
When the driver received all the frames of a sequence, it allocates an IOCB to put the frames in. In a situation where there was no IOCB available for the frame of a sequence, the RQ buffer corresponding to the first frame of the sequence was not returned to the FW. Eventually, with enough traffic encountering the situation, the timeout occurred.
Fix by releasing the buffer back to firmware whenever there is no IOCB for the first frame.
[mkp: typo]
--- drivers/scsi/lpfc/lpfc_sli.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/scsi/lpfc/lpfc_sli.c +4 -0
@@ -17038,6 +17038,10 @@ lpfc_prep_seq(struct lpfc_vport *vport, struct hbq_dmabuf *seq_dmabuf)list_add_tail (&iocbq->list, &first_iocbq->list); } } +/* Free the sequence's header buffer */ +if (!first_iocbq) +lpfc_in_buf_free (vport->phba, &seq_dmabuf->dbuf); +return first_iocbq; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 51/127 media: staging/imx: Missing assignment in imx_media_capture_device_register()
In reply to Sasha LevinFrom: Dan Carpenter <[email protected]>
[ Upstream commit ef0ed05dcef8a74178a8b480cce23a377b1de2b8 ]
There was supposed to be a "ret = " assignment here, otherwise the error handling on the next line won't work.
--- drivers/staging/media/imx/imx-media-capture.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/staging/media/imx/imx-media-capture.c +1 -1
@@ -685,7 +685,7 @@ int imx_media_capture_device_register(struct imx_media_video_dev *vdev)/* setup default format */ fmt_src.pad = priv->src_sd_pad; fmt_src.which =V4L2_SUBDEV_FORMAT_ACTIVE ; -v4l2_subdev_call (sd, pad, get_fmt,NULL , &fmt_src); + ret =v4l2_subdev_call (sd, pad, get_fmt,NULL , &fmt_src);if (ret) {v4l2_err (sd,"failed to get src_sd format\n" ); goto unreg;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 54/127 dmaengine: tegra-apb: Prevent race conditions on channel's freeing
In reply to Sasha LevinFrom: Dmitry Osipenko <[email protected]>
[ Upstream commit 8e84172e372bdca20c305d92d51d33640d2da431 ]
It's incorrect to check the channel's "busy" state without taking a lock. That shouldn't cause any real troubles, nevertheless it's always better not to have any race conditions in the code.
--- drivers/dma/tegra20-apb-dma.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/dma/tegra20-apb-dma.c +1 -2
@@ -1208,8 +1208,7 @@ static void tegra_dma_free_chan_resources(struct dma_chan *dc)dev_dbg (tdc2dev (tdc),"Freeing channel %d\n" , tdc->id); -if (tdc->busy) -tegra_dma_terminate_all (dc); +tegra_dma_terminate_all (dc);spin_lock_irqsave (&tdc->lock, flags);list_splice_init (&tdc->pending_sg_req, &sg_req_list);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 52/127 x86/pkeys: Add check for pkey "overflow"
In reply to Sasha LevinFrom: Dave Hansen <[email protected]>
[ Upstream commit 16171bffc829272d5e6014bad48f680cb50943d9 ]
Alex Shi reported the pkey macros above arch_set_user_pkey_access() to be unused. They are unused, and even refer to a nonexistent CONFIG option.
But, they might have served a good use, which was to ensure that the code does not try to set values that would not fit in the PKRU register. As it stands, a too-large 'pkey' value would be likely to silently overflow the u32 new_pkru_bits.
Add a check to look for overflows. Also add a comment to remind any future developer to closely examine the types used to store pkey values if arch_max_pkey() ever changes.
This boots and passes the x86 pkey selftests.
--- arch/x86/include/asm/pkeys.h | 5 +++++ arch/x86/kernel/fpu/xstate.c | 9 +++++++-- 2 files changed, 12 insertions(+), 2 deletions(-)
arch/x86/include/asm/pkeys.h +5 -0
@@ -4,6 +4,11 @@#define ARCH_DEFAULT_PKEY 0 +/* +* If more than 16 keys are ever supported, a thorough audit +* will be necessary to ensure that the types that store key +* numbers and masks have sufficient capacity. +*/ #define arch_max_pkey () (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
arch/x86/kernel/fpu/xstate.c +7 -2
@@ -907,8 +907,6 @@ const void *get_xsave_field_ptr(int xsave_state)#ifdef CONFIG_ARCH_HAS_PKEYS -#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) -#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1)/* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val.
@@ -927,6 +925,13 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,if (!boot_cpu_has (X86_FEATURE_OSPKE ))return -EINVAL ; +/* +* This code should only be called with valid 'pkey' +* values originating from in-kernel users. Complain +* if a bad value is observed. +*/ +WARN_ON_ONCE (pkey >=arch_max_pkey ()); +/* Set the bits we need in PKRU: */ if (init_val &PKEY_DISABLE_ACCESS ) new_pkru_bits |=PKRU_AD_BIT ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 59/127 mm: avoid data corruption on CoW fault into PFN-mapped VMA
In reply to Sasha LevinFrom: "Kirill A. Shutemov" <[email protected]>
[ Upstream commit c3e5ea6ee574ae5e845a40ac8198de1fb63bb3ab ]
Jeff Moyer has reported that one of xfstests triggers a warning when run on DAX-enabled filesystem:
WARNING: CPU: 76 PID: 51024 at mm/memory.c:2317 wp_page_copy+0xc40/0xd50 ... wp_page_copy+0x98c/0xd50 (unreliable) do_wp_page+0xd8/0xad0 __handle_mm_fault+0x748/0x1b90 handle_mm_fault+0x120/0x1f0 __do_page_fault+0x240/0xd70 do_page_fault+0x38/0xd0 handle_page_fault+0x10/0x30
The warning happens on failed __copy_from_user_inatomic() which tries to copy data into a CoW page.
This happens because of race between MADV_DONTNEED and CoW page fault:
CPU0 CPU1
handle_mm_fault()
do_wp_page()
wp_page_copy()
do_wp_page()
madvise(MADV_DONTNEED)
zap_page_range()
zap_pte_range()
ptep_get_and_clear_full()
<TLB flush>
__copy_from_user_inatomic()
sees empty PTE and fails
WARN_ON_ONCE(1)
clear_page()The solution is to re-try __copy_from_user_inatomic() under PTL after checking that PTE is matches the orig_pte.
The second copy attempt can still fail, like due to non-readable PTE, but there's nothing reasonable we can do about, except clearing the CoW page.
--- mm/memory.c | 35 +++++++++++++++++++++++++++-------- 1 file changed, 27 insertions(+), 8 deletions(-)
mm/memory.c +27 -8
@@ -2342,7 +2342,7 @@ static inline bool cow_user_page(struct page *dst, struct page *src,bool ret;void *kaddr;void __user *uaddr; -bool force_mkyoung; +bool locked = false;struct vm_area_struct *vma = vmf->vma;struct mm_struct *mm = vma->vm_mm;unsigned long addr = vmf->address;
@@ -2367,11 +2367,11 @@ static inline bool cow_user_page(struct page *dst, struct page *src,* On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ - force_mkyoung =arch_faults_on_old_pte () && !pte_young (vmf->orig_pte); -if (force_mkyoung) { +if (arch_faults_on_old_pte () && !pte_young (vmf->orig_pte)) {pte_t entry; vmf->pte =pte_offset_map_lock (mm, vmf->pmd, addr, &vmf->ptl); + locked = true;if (!likely (pte_same (*vmf->pte, vmf->orig_pte))) {/* * Other thread has already handled the fault
@@ -2395,18 +2395,37 @@ static inline bool cow_user_page(struct page *dst, struct page *src,* zeroes. */ if (__copy_from_user_inatomic (kaddr, uaddr,PAGE_SIZE )) { +if (locked) + goto warn; + +/* Re-validate under PTL if the page is still mapped */ + vmf->pte =pte_offset_map_lock (mm, vmf->pmd, addr, &vmf->ptl); + locked = true; +if (!likely (pte_same (*vmf->pte, vmf->orig_pte))) { +/* The PTE changed under us. Retry page fault. */ + ret = false; + goto pte_unlock; + } +/* -* Give a warn in case there can be some obscure -* use-case +* The same page can be mapped back since last copy attampt. +* Try to copy again under PTL. */ -WARN_ON_ONCE (1 ); -clear_page (kaddr); +if (__copy_from_user_inatomic (kaddr, uaddr,PAGE_SIZE )) { +/* +* Give a warn in case there can be some obscure +* use-case +*/ +warn: +WARN_ON_ONCE (1 ); +clear_page (kaddr); + } } ret = true; pte_unlock: -if (force_mkyoung) +if (locked)pte_unmap_unlock (vmf->pte, vmf->ptl);kunmap_atomic (kaddr);flush_dcache_page (dst);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 55/127 media: go7007: Fix URB type for interrupt handling
In reply to Sasha LevinFrom: Takashi Iwai <[email protected]>
[ Upstream commit a3ea410cac41b19a5490aad7fe6d9a9a772e646e ]
Josef reported that his old-and-good Plextor ConvertX M402U video converter spews lots of WARNINGs on the recent kernels, and it turned out that the device uses a bulk endpoint for interrupt handling just like 2250 board.
For fixing it, generalize the check with the proper verification of the endpoint instead of hard-coded board type check.
--- drivers/media/usb/go7007/go7007-usb.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/media/usb/go7007/go7007-usb.c +3 -1
@@ -1052,6 +1052,7 @@ static int go7007_usb_probe(struct usb_interface *intf,struct go7007_usb *usb;const struct go7007_usb_board *board;struct usb_device *usbdev =interface_to_usbdev (intf); +struct usb_host_endpoint *ep;unsigned num_i2c_devs;char *name;int video_pipe, i, v_urb_len;
@@ -1147,7 +1148,8 @@ static int go7007_usb_probe(struct usb_interface *intf,if (usb->intr_urb->transfer_buffer ==NULL ) goto allocfail; -if (go->board_id ==GO7007_BOARDID_SENSORAY_2250 ) + ep = usb->usbdev->ep_in[4 ]; +if (usb_endpoint_type (&ep->desc) ==USB_ENDPOINT_XFER_BULK ) usb_fill_bulk_urb(usb->intr_urb, usb->usbdev, usb_rcvbulkpipe(usb->usbdev, 4), usb->intr_urb->transfer_buffer, 2*sizeof(u16),
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 60/127 drm/amdgpu: increase atombios cmd timeout
In reply to Sasha LevinFrom: John Clements <[email protected]>
[ Upstream commit 1b3460a8b19688ad3033b75237d40fa580a5a953 ]
mitigates race condition on BACO reset between GPU bootcode and driver reload
--- drivers/gpu/drm/amd/amdgpu/atom.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/atom.c +2 -2
@@ -742,8 +742,8 @@ static void atom_op_jump(atom_exec_context *ctx, int *ptr, int arg) cjiffies = jiffies;if (time_after (cjiffies, ctx->last_jump_jiffies)) { cjiffies -= ctx->last_jump_jiffies; -if ((jiffies_to_msecs (cjiffies) >5000 )) { -DRM_ERROR ("atombios stuck in loop for more than 5secs aborting\n" ); +if ((jiffies_to_msecs (cjiffies) >10000 )) { +DRM_ERROR ("atombios stuck in loop for more than 10secs aborting\n" ); ctx->abort = true; } }else {
Signature · 6 lines
2.25.1 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Sasha Levin
maintainerPATCH 61/127 ath10k: use kzalloc to read for ath10k_sdio_hif_diag_read
In reply to Sasha LevinFrom: Wen Gong <[email protected]>
[ Upstream commit 402f2992b4d62760cce7c689ff216ea3bf4d6e8a ]
When use command to read values, it crashed.
command:
dd if=/sys/kernel/debug/ieee80211/phy0/ath10k/mem_value count=1 bs=4 skip=$((0x100233))
It will call to ath10k_sdio_hif_diag_read with address = 0x4008cc and buf_len = 4.
Then system crash:
[ 1786.013258] Unable to handle kernel paging request at virtual address ffffffc00bd45000 [ 1786.013273] Mem abort info: [ 1786.013281] ESR = 0x96000045 [ 1786.013291] Exception class = DABT (current EL), IL = 32 bits [ 1786.013299] SET = 0, FnV = 0 [ 1786.013307] EA = 0, S1PTW = 0 [ 1786.013314] Data abort info: [ 1786.013322] ISV = 0, ISS = 0x00000045 [ 1786.013330] CM = 0, WnR = 1 [ 1786.013342] swapper pgtable: 4k pages, 39-bit VAs, pgdp = 000000008542a60e [ 1786.013350] [ffffffc00bd45000] pgd=0000000000000000, pud=0000000000000000 [ 1786.013368] Internal error: Oops: 96000045 [#1] PREEMPT SMP [ 1786.013609] Process swapper/0 (pid: 0, stack limit = 0x0000000084b153c6) [ 1786.013623] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.19.86 #137 [ 1786.013631] Hardware name: MediaTek krane sku176 board (DT) [ 1786.013643] pstate: 80000085 (Nzcv daIf -PAN -UAO) [ 1786.013662] pc : __memcpy+0x94/0x180 [ 1786.013678] lr : swiotlb_tbl_unmap_single+0x84/0x150 [ 1786.013686] sp : ffffff8008003c60 [ 1786.013694] x29: ffffff8008003c90 x28: ffffffae96411f80 [ 1786.013708] x27: ffffffae960d2018 x26: ffffff8019a4b9a8 [ 1786.013721] x25: 0000000000000000 x24: 0000000000000001 [ 1786.013734] x23: ffffffae96567000 x22: 00000000000051d4 [ 1786.013747] x21: 0000000000000000 x20: 00000000fe6e9000 [ 1786.013760] x19: 0000000000000004 x18: 0000000000000020 [ 1786.013773] x17: 0000000000000001 x16: 0000000000000000 [ 1786.013787] x15: 00000000ffffffff x14: 00000000000044c0 [ 1786.013800] x13: 0000000000365ba4 x12: 0000000000000000 [ 1786.013813] x11: 0000000000000001 x10: 00000037be6e9000 [ 1786.013826] x9 : ffffffc940000000 x8 : 000000000bd45000 [ 1786.013839] x7 : 0000000000000000 x6 : ffffffc00bd45000 [ 1786.013852] x5 : 0000000000000000 x4 : 0000000000000000 [ 1786.013865] x3 : 0000000000000c00 x2 : 0000000000000004 [ 1786.013878] x1 : fffffff7be6e9004 x0 : ffffffc00bd45000 [ 1786.013891] Call trace: [ 1786.013903] __memcpy+0x94/0x180 [ 1786.013914] unmap_single+0x6c/0x84 [ 1786.013925] swiotlb_unmap_sg_attrs+0x54/0x80 [ 1786.013938] __swiotlb_unmap_sg_attrs+0x8c/0xa4 [ 1786.013952] msdc_unprepare_data+0x6c/0x84 [ 1786.013963] msdc_request_done+0x58/0x84 [ 1786.013974] msdc_data_xfer_done+0x1a0/0x1c8 [ 1786.013985] msdc_irq+0x12c/0x17c [ 1786.013996] __handle_irq_event_percpu+0xe4/0x250 [ 1786.014006] handle_irq_event_percpu+0x28/0x68 [ 1786.014015] handle_irq_event+0x48/0x78 [ 1786.014026] handle_fasteoi_irq+0xd0/0x1a0 [ 1786.014039] __handle_domain_irq+0x84/0xc4 [ 1786.014050] gic_handle_irq+0x124/0x1a4 [ 1786.014059] el1_irq+0xb0/0x128 [ 1786.014072] cpuidle_enter_state+0x298/0x328 [ 1786.014082] cpuidle_enter+0x30/0x40 [ 1786.014094] do_idle+0x190/0x268 [ 1786.014104] cpu_startup_entry+0x24/0x28 [ 1786.014116] rest_init+0xd4/0xe0 [ 1786.014126] start_kernel+0x30c/0x38c [ 1786.014139] Code: f8408423 f80084c3 36100062 b8404423 (b80044c3) [ 1786.014150] ---[ end trace 3b02ddb698ea69ee ]--- [ 1786.015415] Kernel panic - not syncing: Fatal exception in interrupt [ 1786.015433] SMP: stopping secondary CPUs [ 1786.015447] Kernel Offset: 0x2e8d200000 from 0xffffff8008000000 [ 1786.015458] CPU features: 0x0,2188200c [ 1786.015466] Memory Limit: none
For sdio chip, it need the memory which is kmalloc, if it is vmalloc from ath10k_mem_value_read, then it have a memory error. kzalloc of ath10k_sdio_hif_diag_read32 is the correct type, so add kzalloc in ath10k_sdio_hif_diag_read to replace the buffer which is vmalloc from ath10k_mem_value_read.
This patch only effect sdio chip.
Tested with QCA6174 SDIO with firmware WLAN.RMH.4.4.1-00029.
--- drivers/net/wireless/ath/ath10k/sdio.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-)
drivers/net/wireless/ath/ath10k/sdio.c +14 -4
@@ -1564,23 +1564,33 @@ static int ath10k_sdio_hif_diag_read(struct ath10k *ar, u32 address, void *buf, size_t buf_len) {int ret; +void *mem; + + mem =kzalloc (buf_len,GFP_KERNEL ); +if (!mem) +return -ENOMEM ;/* set window register to start read cycle */ ret =ath10k_sdio_write32 (ar,MBOX_WINDOW_READ_ADDR_ADDRESS , address);if (ret) {ath10k_warn (ar,"failed to set mbox window read address: %d" , ret); -return ret; + goto out; }/* read the data */ - ret =ath10k_sdio_read (ar,MBOX_WINDOW_DATA_ADDRESS , buf, buf_len); + ret =ath10k_sdio_read (ar,MBOX_WINDOW_DATA_ADDRESS , mem, buf_len);if (ret) {ath10k_warn (ar,"failed to read from mbox window data address: %d\n" , ret); -return ret; + goto out; } -return 0 ; +memcpy (buf, mem, buf_len); + +out: +kfree (mem); + +return ret; } static int ath10k_sdio_hif_diag_read32(struct ath10k *ar, u32 address,
Signature · 7 lines
2.25.1 _______________________________________________ ath10k mailing list [email protected] http://lists.infradead.org/mailman/listinfo/ath10k
Sasha Levin
maintainerPATCH 63/127 Bluetooth: L2CAP: handle l2cap config request during open state
In reply to Sasha LevinFrom: Howard Chung <[email protected]>
[ Upstream commit 96298f640104e4cd9a913a6e50b0b981829b94ff ]
According to Core Spec Version 5.2 | Vol 3, Part A 6.1.5, the incoming L2CAP_ConfigReq should be handled during OPEN state.
The section below shows the btmon trace when running L2CAP/COS/CFD/BV-12-C before and after this change.
=== Before ===
...
Quoted 1 line
ACL Data RX: Handle 256 flags
0x02dlen 12 #22
L2CAP: Connection Request (0x02) ident 2 len 4
PSM: 1 (0x0001)
Source CID: 65
< ACL Data TX: Handle 256 flags 0x00 dlen 16 #23
L2CAP: Connection Response (0x03) ident 2 len 8
Destination CID: 64
Source CID: 65
Result: Connection successful (0x0000)
Status: No further information available (0x0000)
< ACL Data TX: Handle 256 flags 0x00 dlen 12 #24
L2CAP: Configure Request (0x04) ident 2 len 4
Destination CID: 65
Flags: 0x0000Quoted 1 line
HCI Event: Number of Completed Packets (
0x13) plen 5 #25
Num handles: 1
Handle: 256
Count: 1
Quoted 1 line
HCI Event: Number of Completed Packets (
0x13) plen 5 #26
Num handles: 1
Handle: 256
Count: 1
Quoted 1 line
ACL Data RX: Handle 256 flags
0x02dlen 16 #27
L2CAP: Configure Request (0x04) ident 3 len 8
Destination CID: 64
Flags: 0x0000
Option: Unknown (0x10) [hint]
01 00 ..
< ACL Data TX: Handle 256 flags 0x00 dlen 18 #28
L2CAP: Configure Response (0x05) ident 3 len 10
Source CID: 65
Flags: 0x0000
Result: Success (0x0000)
Option: Maximum Transmission Unit (0x01) [mandatory]
MTU: 672Quoted 1 line
HCI Event: Number of Completed Packets (
0x13) plen 5 #29
Num handles: 1
Handle: 256
Count: 1
Quoted 1 line
ACL Data RX: Handle 256 flags
0x02dlen 14 #30
L2CAP: Configure Response (0x05) ident 2 len 6
Source CID: 64
Flags: 0x0000
Result: Success (0x0000)Quoted 1 line
ACL Data RX: Handle 256 flags
0x02dlen 20 #31
L2CAP: Configure Request (0x04) ident 3 len 12
Destination CID: 64
Flags: 0x0000
Option: Unknown (0x10) [hint]
01 00 91 02 11 11 ......< ACL Data TX: Handle 256 flags 0x00 dlen 14 #32
L2CAP: Command Reject (0x01) ident 3 len 6
Reason: Invalid CID in request (0x0002) Destination CID: 64
Source CID: 65
Quoted 1 line
HCI Event: Number of Completed Packets (
0x13) plen 5 #33
Num handles: 1
Handle: 256
Count: 1
...
=== After ===
...
Quoted 1 line
ACL Data RX: Handle 256 flags
0x02dlen 12 #22
L2CAP: Connection Request (0x02) ident 2 len 4
PSM: 1 (0x0001)
Source CID: 65
< ACL Data TX: Handle 256 flags 0x00 dlen 16 #23
L2CAP: Connection Response (0x03) ident 2 len 8
Destination CID: 64
Source CID: 65
Result: Connection successful (0x0000)
Status: No further information available (0x0000)
< ACL Data TX: Handle 256 flags 0x00 dlen 12 #24
L2CAP: Configure Request (0x04) ident 2 len 4
Destination CID: 65
Flags: 0x0000Quoted 1 line
HCI Event: Number of Completed Packets (
0x13) plen 5 #25
Num handles: 1
Handle: 256
Count: 1
Quoted 1 line
HCI Event: Number of Completed Packets (
0x13) plen 5 #26
Num handles: 1
Handle: 256
Count: 1
Quoted 1 line
ACL Data RX: Handle 256 flags
0x02dlen 16 #27
L2CAP: Configure Request (0x04) ident 3 len 8
Destination CID: 64
Flags: 0x0000
Option: Unknown (0x10) [hint]
01 00 ..
< ACL Data TX: Handle 256 flags 0x00 dlen 18 #28
L2CAP: Configure Response (0x05) ident 3 len 10
Source CID: 65
Flags: 0x0000
Result: Success (0x0000)
Option: Maximum Transmission Unit (0x01) [mandatory]
MTU: 672Quoted 1 line
HCI Event: Number of Completed Packets (
0x13) plen 5 #29
Num handles: 1
Handle: 256
Count: 1
Quoted 1 line
ACL Data RX: Handle 256 flags
0x02dlen 14 #30
L2CAP: Configure Response (0x05) ident 2 len 6
Source CID: 64
Flags: 0x0000
Result: Success (0x0000)Quoted 1 line
ACL Data RX: Handle 256 flags
0x02dlen 20 #31
L2CAP: Configure Request (0x04) ident 3 len 12
Destination CID: 64
Flags: 0x0000
Option: Unknown (0x10) [hint]
01 00 91 02 11 11 .....
< ACL Data TX: Handle 256 flags 0x00 dlen 18 #32
L2CAP: Configure Response (0x05) ident 3 len 10
Source CID: 65
Flags: 0x0000
Result: Success (0x0000)
Option: Maximum Transmission Unit (0x01) [mandatory]
MTU: 672
< ACL Data TX: Handle 256 flags 0x00 dlen 12 #33
L2CAP: Configure Request (0x04) ident 3 len 4
Destination CID: 65
Flags: 0x0000Quoted 1 line
HCI Event: Number of Completed Packets (
0x13) plen 5 #34
Num handles: 1
Handle: 256
Count: 1
Quoted 1 line
HCI Event: Number of Completed Packets (
0x13) plen 5 #35
Num handles: 1
Handle: 256
Count: 1
...
--- net/bluetooth/l2cap_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
net/bluetooth/l2cap_core.c +2 -1
@@ -4117,7 +4117,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,return 0 ; } -if (chan->state !=BT_CONFIG && chan->state !=BT_CONNECT2 ) { +if (chan->state !=BT_CONFIG && chan->state !=BT_CONNECT2 && + chan->state !=BT_CONNECTED ) {cmd_reject_invalid_cid (conn, cmd->ident, chan->scid, chan->dcid); goto unlock;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 71/127 serial: 8250: 8250_omap: Terminate DMA before pushing data on RX timeout
In reply to Sasha LevinFrom: Vignesh Raghavendra <[email protected]>
[ Upstream commit 7cf4df30a98175033e9849f7f16c46e96ba47f41 ]
Terminate and flush DMA internal buffers, before pushing RX data to higher layer. Otherwise, this will lead to data corruption, as driver would end up pushing stale buffer data to higher layer while actual data is still stuck inside DMA hardware and has yet not arrived at the memory.
While at that, replace deprecated dmaengine_terminate_all() with dmaengine_terminate_async().
--- drivers/tty/serial/8250/8250_omap.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/tty/serial/8250/8250_omap.c +4 -2
@@ -773,7 +773,10 @@ static void __dma_rx_do_complete(struct uart_8250_port *p)dmaengine_tx_status (dma->rxchan, dma->rx_cookie, &state); count = dma->rx_size - state.residue; - +if (count < dma->rx_size) +dmaengine_terminate_async (dma->rxchan); +if (!count) + goto unlock; ret =tty_insert_flip_string (tty_port, dma->rx_buf, count); p->port.icount.rx += ret;
@@ -833,7 +836,6 @@ static void omap_8250_rx_dma_flush(struct uart_8250_port *p)spin_unlock_irqrestore (&priv->rx_dma_lock, flags);__dma_rx_do_complete (p); -dmaengine_terminate_all (dma->rxchan); }static int omap_8250_rx_dma (struct uart_8250_port *p)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 70/127 serial: 8250_omap: Fix sleeping function called from invalid context during probe
In reply to Sasha LevinFrom: Peter Ujfalusi <[email protected]>
[ Upstream commit 4ce35a3617c0ac758c61122b2218b6c8c9ac9398 ]
When booting j721e the following bug is printed:
[ 1.154821] BUG: sleeping function called from invalid context at kernel/sched/completion.c:99
[ 1.154827] in_atomic(): 0, irqs_disabled(): 128, non_block: 0, pid: 12, name: kworker/0:1
[ 1.154832] 3 locks held by kworker/0:1/12:
[ 1.154836] #0: ffff000840030728 ((wq_completion)events){+.+.}, at: process_one_work+0x1d4/0x6e8
[ 1.154852] #1: ffff80001214fdd8 (deferred_probe_work){+.+.}, at: process_one_work+0x1d4/0x6e8
[ 1.154860] #2: ffff00084060b170 (&dev->mutex){....}, at: __device_attach+0x38/0x138
[ 1.154872] irq event stamp: 63096
[ 1.154881] hardirqs last enabled at (63095): [<ffff800010b74318>] _raw_spin_unlock_irqrestore+0x70/0x78
[ 1.154887] hardirqs last disabled at (63096): [<ffff800010b740d8>] _raw_spin_lock_irqsave+0x28/0x80
[ 1.154893] softirqs last enabled at (62254): [<ffff800010080c88>] _stext+0x488/0x564
[ 1.154899] softirqs last disabled at (62247): [<ffff8000100fdb3c>] irq_exit+0x114/0x140
[ 1.154906] CPU: 0 PID: 12 Comm: kworker/0:1 Not tainted 5.6.0-rc6-next-20200318-00094-g45e4089b0bd3 #221
[ 1.154911] Hardware name: Texas Instruments K3 J721E SoC (DT)
[ 1.154917] Workqueue: events deferred_probe_work_func
[ 1.154923] Call trace:
[ 1.154928] dump_backtrace+0x0/0x190
[ 1.154933] show_stack+0x14/0x20
[ 1.154940] dump_stack+0xe0/0x148
[ 1.154946] ___might_sleep+0x150/0x1f0
[ 1.154952] __might_sleep+0x4c/0x80
[ 1.154957] wait_for_completion_timeout+0x40/0x140
[ 1.154964] ti_sci_set_device_state+0xa0/0x158
[ 1.154969] ti_sci_cmd_get_device_exclusive+0x14/0x20
[ 1.154977] ti_sci_dev_start+0x34/0x50
[ 1.154984] genpd_runtime_resume+0x78/0x1f8
[ 1.154991] __rpm_callback+0x3c/0x140
[ 1.154996] rpm_callback+0x20/0x80
[ 1.155001] rpm_resume+0x568/0x758
[ 1.155007] __pm_runtime_resume+0x44/0xb0
[ 1.155013] omap8250_probe+0x2b4/0x508
[ 1.155019] platform_drv_probe+0x50/0xa0
[ 1.155023] really_probe+0xd4/0x318
[ 1.155028] driver_probe_device+0x54/0xe8
[ 1.155033] __device_attach_driver+0x80/0xb8
[ 1.155039] bus_for_each_drv+0x74/0xc0
[ 1.155044] __device_attach+0xdc/0x138
[ 1.155049] device_initial_probe+0x10/0x18
[ 1.155053] bus_probe_device+0x98/0xa0
[ 1.155058] deferred_probe_work_func+0x74/0xb0
[ 1.155063] process_one_work+0x280/0x6e8
[ 1.155068] worker_thread+0x48/0x430
[ 1.155073] kthread+0x108/0x138
[ 1.155079] ret_from_fork+0x10/0x18To fix the bug we need to first call pm_runtime_enable() prior to any pm_runtime calls.
--- drivers/tty/serial/8250/8250_omap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/tty/serial/8250/8250_omap.c +1 -1
@@ -1216,11 +1216,11 @@ static int omap8250_probe(struct platform_device *pdev)spin_lock_init (&priv->rx_dma_lock);device_init_wakeup (&pdev->dev, true); +pm_runtime_enable (&pdev->dev);pm_runtime_use_autosuspend (&pdev->dev);pm_runtime_set_autosuspend_delay (&pdev->dev,-1 );pm_runtime_irq_safe (&pdev->dev); -pm_runtime_enable (&pdev->dev);pm_runtime_get_sync (&pdev->dev);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 81/127 mm/kmemleak.c: use address-of operator on section symbols
In reply to Sasha LevinFrom: Nathan Chancellor <[email protected]>
[ Upstream commit b0d14fc43d39203ae025f20ef4d5d25d9ccf4be1 ]
Clang warns:
mm/kmemleak.c:1955:28: warning: array comparison always evaluates to a constant [-Wtautological-compare]
if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata)
^
mm/kmemleak.c:1955:60: warning: array comparison always evaluates to a constant [-Wtautological-compare]
if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata)These are not true arrays, they are linker defined symbols, which are just addresses. Using the address of operator silences the warning and does not change the resulting assembly with either clang/ld.lld or gcc/ld (tested with diff + objdump -Dr).
--- mm/kmemleak.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
mm/kmemleak.c +1 -1
@@ -2030,7 +2030,7 @@ void __init kmemleak_init(void)create_object ((unsigned long )__bss_start, __bss_stop - __bss_start,KMEMLEAK_GREY ,GFP_ATOMIC );/* only register .data..ro_after_init if not within .data */ -if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata) +if (&__start_ro_after_init < &_sdata || &__end_ro_after_init > &_edata)create_object ((unsigned long )__start_ro_after_init, __end_ro_after_init - __start_ro_after_init,KMEMLEAK_GREY ,GFP_ATOMIC );
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 5/127 ASoC: kirkwood: fix IRQ error handling
In reply to Sasha LevinFrom: Russell King <[email protected]>
[ Upstream commit 175fc928198236037174e5c5c066fe3c4691903e ]
Propagate the error code from request_irq(), rather than returning -EBUSY.
--- sound/soc/kirkwood/kirkwood-dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
sound/soc/kirkwood/kirkwood-dma.c +1 -1
@@ -136,7 +136,7 @@ static int kirkwood_dma_open(struct snd_pcm_substream *substream) err =request_irq (priv->irq, kirkwood_dma_irq,IRQF_SHARED ,"kirkwood-i2s" , priv);if (err) -return -EBUSY ; +return err;/* * Enable Error interrupts. We're only ack'ing them but
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 82/127 mm/filemap.c: clear page error before actual read
In reply to Sasha LevinFrom: Xianting Tian <[email protected]>
[ Upstream commit faffdfa04fa11ccf048cebdde73db41ede0679e0 ]
Mount failure issue happens under the scenario: Application forked dozens of threads to mount the same number of cramfs images separately in docker, but several mounts failed with high probability. Mount failed due to the checking result of the page(read from the superblock of loop dev) is not uptodate after wait_on_page_locked(page) returned in function cramfs_read:
wait_on_page_locked(page);
if (!PageUptodate(page)) {
...
}The reason of the checking result of the page not uptodate: systemd-udevd read the loopX dev before mount, because the status of loopX is Lo_unbound at this time, so loop_make_request directly trigger the calling of io_end handler end_buffer_async_read, which called SetPageError(page). So It caused the page can't be set to uptodate in function end_buffer_async_read:
if(page_uptodate && !PageError(page)) {
SetPageUptodate(page);
}Then mount operation is performed, it used the same page which is just accessed by systemd-udevd above, Because this page is not uptodate, it will launch a actual read via submit_bh, then wait on this page by calling wait_on_page_locked(page). When the I/O of the page done, io_end handler end_buffer_async_read is called, because no one cleared the page error(during the whole read path of mount), which is caused by systemd-udevd reading, so this page is still in "PageError" status, which can't be set to uptodate in function end_buffer_async_read, then caused mount failure.
But sometimes mount succeed even through systemd-udeved read loopX dev just before, The reason is systemd-udevd launched other loopX read just between step 3.1 and 3.2, the steps as below:
1, loopX dev default status is Lo_unbound;
2, systemd-udved read loopX dev (page is set to PageError); 3, mount operation
1) set loopX status to Lo_bound; ==>systemd-udevd read loopX dev<==
2) read loopX dev(page has no error)
3) mount succeed
As the loopX dev status is set to Lo_bound after step 3.1, so the other loopX dev read by systemd-udevd will go through the whole I/O stack, part of the call trace as below:
SYS_read
vfs_read
do_sync_read
blkdev_aio_read
generic_file_aio_read
do_generic_file_read:
ClearPageError(page);
mapping->a_ops->readpage(filp, page);here, mapping->a_ops->readpage() is blkdev_readpage. In latest kernel, some function name changed, the call trace as below:
blkdev_read_iter
generic_file_read_iter
generic_file_buffered_read:
/*
* A previous I/O error may have been due to temporary
* failures, eg. mutipath errors.
* Pg_error will be set again if readpage fails.
*/
ClearPageError(page);
/* Start the actual read. The read will unlock the page*/
error=mapping->a_ops->readpage(flip, page);We can see ClearPageError(page) is called before the actual read, then the read in step 3.2 succeed.
This patch is to add the calling of ClearPageError just before the actual read of read path of cramfs mount. Without the patch, the call trace as below when performing cramfs mount:
do_mount
cramfs_read
cramfs_blkdev_read
read_cache_page
do_read_cache_page:
filler(data, page);
or
mapping->a_ops->readpage(data, page);With the patch, the call trace as below when performing mount:
do_mount
cramfs_read
cramfs_blkdev_read
read_cache_page:
do_read_cache_page:
ClearPageError(page); <== new add
filler(data, page);
or
mapping->a_ops->readpage(data, page);With the patch, mount operation trigger the calling of ClearPageError(page) before the actual read, the page has no error if no additional page error happen when I/O done.
--- mm/filemap.c | 8 ++++++++ 1 file changed, 8 insertions(+)
mm/filemap.c +8 -0
@@ -2774,6 +2774,14 @@ filler:unlock_page (page); goto out; } + +/* +* A previous I/O error may have been due to temporary +* failures. +* Clear page error before actual read, PG_error will be +* set again if read page fails. +*/ +ClearPageError (page); goto filler; out:
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 69/127 serial: 8250_port: Don't service RX FIFO if throttled
In reply to Sasha LevinFrom: Vignesh Raghavendra <[email protected]>
[ Upstream commit f19c3f6c8109b8bab000afd35580929958e087a9 ]
When port's throttle callback is called, it should stop pushing any more data into TTY buffer to avoid buffer overflow. This means driver has to stop HW from receiving more data and assert the HW flow control. For UARTs with auto HW flow control (such as 8250_omap) manual assertion of flow control line is not possible and only way is to allow RX FIFO to fill up, thus trigger auto HW flow control logic.
Therefore make sure that 8250 generic IRQ handler does not drain data when port is stopped (i.e UART_LSR_DR is unset in read_status_mask). Not servicing, RX FIFO would trigger auto HW flow control when FIFO occupancy reaches preset threshold, thus halting RX.
Since, error conditions in UART_LSR register are cleared just by reading the register, data has to be drained in case there are FIFO errors, else error information will lost.
--- drivers/tty/serial/8250/8250_port.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)
drivers/tty/serial/8250/8250_port.c +15 -1
@@ -1865,6 +1865,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)unsigned char status;unsigned long flags;struct uart_8250_port *up =up_to_u8250p (port); +bool skip_rx = false;if (iir &UART_IIR_NO_INT )return 0 ;
@@ -1873,7 +1874,20 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) status =serial_port_in (port,UART_LSR ); -if (status & (UART_LSR_DR |UART_LSR_BI )) { +/* +* If port is stopped and there are no error conditions in the +* FIFO, then don't drain the FIFO, as this may lead to TTY buffer +* overflow. Not servicing, RX FIFO would trigger auto HW flow +* control when FIFO occupancy reaches preset threshold, thus +* halting RX. This only works when auto HW flow control is +* available. +*/ +if (!(status & (UART_LSR_FIFOE |UART_LSR_BRK_ERROR_BITS )) && + (port->status & (UPSTAT_AUTOCTS |UPSTAT_AUTORTS )) && + !(port->read_status_mask &UART_LSR_DR )) + skip_rx = true; + +if (status & (UART_LSR_DR |UART_LSR_BI ) && !skip_rx) {if (!up->dma ||handle_rx_dma (up, iir)) status =serial8250_rx_chars (up, status); }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 83/127 mm/vmscan.c: fix data races using kswapd_classzone_idx
In reply to Sasha LevinFrom: Qian Cai <[email protected]>
[ Upstream commit 5644e1fbbfe15ad06785502bbfe5751223e5841d ]
pgdat->kswapd_classzone_idx could be accessed concurrently in wakeup_kswapd(). Plain writes and reads without any lock protection result in data races. Fix them by adding a pair of READ|WRITE_ONCE() as well as saving a branch (compilers might well optimize the original code in an unintentional way anyway). While at it, also take care of pgdat->kswapd_order and non-kswapd threads in allow_direct_reclaim(). The data races were reported by KCSAN,
BUG: KCSAN: data-race in wakeup_kswapd / wakeup_kswapd
write to 0xffff9f427ffff2dc of 4 bytes by task 7454 on cpu 13:
wakeup_kswapd+0xf1/0x400 wakeup_kswapd at mm/vmscan.c:3967 wake_all_kswapds+0x59/0xc0 wake_all_kswapds at mm/page_alloc.c:4241 __alloc_pages_slowpath+0xdcc/0x1290 __alloc_pages_slowpath at mm/page_alloc.c:4512 __alloc_pages_nodemask+0x3bb/0x450 alloc_pages_vma+0x8a/0x2c0 do_anonymous_page+0x16e/0x6f0 __handle_mm_fault+0xcd5/0xd40 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40
1 lock held by mtest01/7454:
#0: ffff9f425afe8808 (&mm->mmap_sem#2){++++}, at:
do_page_fault+0x143/0x6f9 do_user_addr_fault at arch/x86/mm/fault.c:1405 (inlined by) do_page_fault at arch/x86/mm/fault.c:1539 irq event stamp: 6944085 count_memcg_event_mm+0x1a6/0x270 count_memcg_event_mm+0x119/0x270 __do_softirq+0x34c/0x57c irq_exit+0xa2/0xc0
read to 0xffff9f427ffff2dc of 4 bytes by task 7472 on cpu 38:
wakeup_kswapd+0xc8/0x400 wake_all_kswapds+0x59/0xc0 __alloc_pages_slowpath+0xdcc/0x1290 __alloc_pages_nodemask+0x3bb/0x450 alloc_pages_vma+0x8a/0x2c0 do_anonymous_page+0x16e/0x6f0 __handle_mm_fault+0xcd5/0xd40 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40
1 lock held by mtest01/7472:
#0: ffff9f425a9ac148 (&mm->mmap_sem#2){++++}, at:
do_page_fault+0x143/0x6f9 irq event stamp: 6793561 count_memcg_event_mm+0x1a6/0x270 count_memcg_event_mm+0x119/0x270 __do_softirq+0x34c/0x57c irq_exit+0xa2/0xc0 BUG: KCSAN: data-race in kswapd / wakeup_kswapd
write to 0xffff90973ffff2dc of 4 bytes by task 820 on cpu 6:
kswapd+0x27c/0x8d0 kthread+0x1e0/0x200 ret_from_fork+0x27/0x50
read to 0xffff90973ffff2dc of 4 bytes by task 6299 on cpu 0:
wakeup_kswapd+0xf3/0x450 wake_all_kswapds+0x59/0xc0 __alloc_pages_slowpath+0xdcc/0x1290 __alloc_pages_nodemask+0x3bb/0x450 alloc_pages_vma+0x8a/0x2c0 do_anonymous_page+0x170/0x700 __handle_mm_fault+0xc9f/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40
--- mm/vmscan.c | 45 ++++++++++++++++++++++++++------------------- 1 file changed, 26 insertions(+), 19 deletions(-)
mm/vmscan.c +26 -19
@@ -2950,8 +2950,9 @@ static bool allow_direct_reclaim(pg_data_t *pgdat)/* kswapd must be awake if processes are being throttled */ if (!wmark_ok &&waitqueue_active (&pgdat->kswapd_wait)) { - pgdat->kswapd_classzone_idx =min (pgdat->kswapd_classzone_idx, - (enum zone_type )ZONE_NORMAL ); +if (READ_ONCE (pgdat->kswapd_classzone_idx) >ZONE_NORMAL ) +WRITE_ONCE (pgdat->kswapd_classzone_idx,ZONE_NORMAL ); +wake_up_interruptible (&pgdat->kswapd_wait); }
@@ -3451,9 +3452,9 @@ out:static enum zone_type kswapd_classzone_idx (pg_data_t *pgdat,enum zone_type prev_classzone_idx) { -if (pgdat->kswapd_classzone_idx ==MAX_NR_ZONES ) -return prev_classzone_idx; -return pgdat->kswapd_classzone_idx; +enum zone_type curr_idx =READ_ONCE (pgdat->kswapd_classzone_idx); + +return curr_idx ==MAX_NR_ZONES ? prev_classzone_idx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
@@ -3497,8 +3498,11 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o* the previous request that slept prematurely. */ if (remaining) { - pgdat->kswapd_classzone_idx =kswapd_classzone_idx (pgdat, classzone_idx); - pgdat->kswapd_order =max (pgdat->kswapd_order, reclaim_order); +WRITE_ONCE (pgdat->kswapd_classzone_idx, +kswapd_classzone_idx (pgdat, classzone_idx)); + +if (READ_ONCE (pgdat->kswapd_order) < reclaim_order) +WRITE_ONCE (pgdat->kswapd_order, reclaim_order); }finish_wait (&pgdat->kswapd_wait, &wait);
@@ -3580,12 +3584,12 @@ static int kswapd(void *p) tsk->flags |=PF_MEMALLOC |PF_SWAPWRITE |PF_KSWAPD ;set_freezable (); - pgdat->kswapd_order =0 ; - pgdat->kswapd_classzone_idx =MAX_NR_ZONES ; +WRITE_ONCE (pgdat->kswapd_order,0 ); +WRITE_ONCE (pgdat->kswapd_classzone_idx,MAX_NR_ZONES );for ( ; ; ) {bool ret; - alloc_order = reclaim_order = pgdat->kswapd_order; + alloc_order = reclaim_order =READ_ONCE (pgdat->kswapd_order); classzone_idx =kswapd_classzone_idx (pgdat, classzone_idx); kswapd_try_sleep:
@@ -3593,10 +3597,10 @@ kswapd_try_sleep: classzone_idx);/* Read the new order and classzone_idx */ - alloc_order = reclaim_order = pgdat->kswapd_order; + alloc_order = reclaim_order =READ_ONCE (pgdat->kswapd_order); classzone_idx =kswapd_classzone_idx (pgdat, classzone_idx); - pgdat->kswapd_order =0 ; - pgdat->kswapd_classzone_idx =MAX_NR_ZONES ; +WRITE_ONCE (pgdat->kswapd_order,0 ); +WRITE_ONCE (pgdat->kswapd_classzone_idx,MAX_NR_ZONES ); ret =try_to_freeze ();if (kthread_should_stop ())
@@ -3638,20 +3642,23 @@ kswapd_try_sleep:void wakeup_kswapd (struct zone *zone,int order,enum zone_type classzone_idx) {pg_data_t *pgdat; +enum zone_type curr_idx;if (!managed_zone (zone))return ;if (!cpuset_zone_allowed (zone,GFP_KERNEL | __GFP_HARDWALL))return ; + pgdat = zone->zone_pgdat; + curr_idx =READ_ONCE (pgdat->kswapd_classzone_idx); + +if (curr_idx ==MAX_NR_ZONES || curr_idx < classzone_idx) +WRITE_ONCE (pgdat->kswapd_classzone_idx, classzone_idx); + +if (READ_ONCE (pgdat->kswapd_order) < order) +WRITE_ONCE (pgdat->kswapd_order, order); -if (pgdat->kswapd_classzone_idx ==MAX_NR_ZONES ) - pgdat->kswapd_classzone_idx = classzone_idx; -else - pgdat->kswapd_classzone_idx =max (pgdat->kswapd_classzone_idx, - classzone_idx); - pgdat->kswapd_order =max (pgdat->kswapd_order, order);if (!waitqueue_active (&pgdat->kswapd_wait))return ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 79/127 ALSA: usb-audio: Fix case when USB MIDI interface has more than one extra endpoint descriptor
In reply to Sasha LevinFrom: Andreas Steinmetz <[email protected]>
[ Upstream commit 5c6cd7021a05a02fcf37f360592d7c18d4d807fb ]
The Miditech MIDIFACE 16x16 (USB ID 1290:1749) has more than one extra endpoint descriptor.
The first extra descriptor is: 0x06 0x30 0x00 0x00 0x00 0x00
As the code in snd_usbmidi_get_ms_info() looks only at the first extra descriptor to find USB_DT_CS_ENDPOINT the device as such is recognized but there is neither input nor output configured.
The patch iterates through the extra descriptors to find the proper one. With this patch the device is correctly configured.
--- sound/usb/midi.c | 29 ++++++++++++++++++++++++----- 1 file changed, 24 insertions(+), 5 deletions(-)
sound/usb/midi.c +24 -5
@@ -1805,6 +1805,28 @@ static int snd_usbmidi_create_endpoints(struct snd_usb_midi *umidi,return 0 ; } +static struct usb_ms_endpoint_descriptor *find_usb_ms_endpoint_descriptor ( +struct usb_host_endpoint *hostep) +{ +unsigned char *extra = hostep->extra; +int extralen = hostep->extralen; + +while (extralen >3 ) { +struct usb_ms_endpoint_descriptor *ms_ep = + (struct usb_ms_endpoint_descriptor *)extra; + +if (ms_ep->bLength >3 && + ms_ep->bDescriptorType ==USB_DT_CS_ENDPOINT && + ms_ep->bDescriptorSubtype ==UAC_MS_GENERAL ) +return ms_ep; +if (!extra[0 ]) +break ; + extralen -= extra[0 ]; + extra += extra[0 ]; + } +return NULL ; +} +/* * Returns MIDIStreaming device capabilities. */
@@ -1842,11 +1864,8 @@ static int snd_usbmidi_get_ms_info(struct snd_usb_midi *umidi, ep =get_ep_desc (hostep);if (!usb_endpoint_xfer_bulk (ep) && !usb_endpoint_xfer_int (ep))continue ; - ms_ep = (struct usb_ms_endpoint_descriptor *)hostep->extra; -if (hostep->extralen <4 || - ms_ep->bLength <4 || - ms_ep->bDescriptorType !=USB_DT_CS_ENDPOINT || - ms_ep->bDescriptorSubtype !=UAC_MS_GENERAL ) + ms_ep =find_usb_ms_endpoint_descriptor (hostep); +if (!ms_ep)continue ;if (usb_endpoint_dir_out (ep)) {if (endpoints[epidx].out_ep) {
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 84/127 mm/mmap.c: initialize align_offset explicitly for vm_unmapped_area
In reply to Sasha LevinFrom: Jaewon Kim <[email protected]>
[ Upstream commit 09ef5283fd96ac424ef0e569626f359bf9ab86c9 ]
On passing requirement to vm_unmapped_area, arch_get_unmapped_area and arch_get_unmapped_area_topdown did not set align_offset. Internally on both unmapped_area and unmapped_area_topdown, if info->align_mask is 0, then info->align_offset was meaningless.
But commit df529cabb7a2 ("mm: mmap: add trace point of vm_unmapped_area") always prints info->align_offset even though it is uninitialized.
Fix this uninitialized value issue by setting it to 0 explicitly.
Before:
vm_unmapped_area: addr=0x755b155000 err=0 total_vm=0x15aaf0 flags=0x1 len=0x109000 lo=0x8000 hi=0x75eed48000 mask=0x0 ofs=0x4022
After:
vm_unmapped_area: addr=0x74a4ca1000 err=0 total_vm=0x168ab1 flags=0x1 len=0x9000 lo=0x8000 hi=0x753d94b000 mask=0x0 ofs=0x0
--- mm/mmap.c | 2 ++ 1 file changed, 2 insertions(+)
mm/mmap.c +2 -0
@@ -2034,6 +2034,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, info.low_limit = mm->mmap_base; info.high_limit =TASK_SIZE ; info.align_mask =0 ; + info.align_offset =0 ; return vm_unmapped_area(&info); }#endif
@@ -2075,6 +2076,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.low_limit =max (PAGE_SIZE , mmap_min_addr); info.high_limit = mm->mmap_base; info.align_mask =0 ; + info.align_offset =0 ; addr =vm_unmapped_area (&info);/*
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 77/127 svcrdma: Fix leak of transport addresses
In reply to Sasha LevinFrom: Chuck Lever <[email protected]>
[ Upstream commit 1a33d8a284b1e85e03b8c7b1ea8fb985fccd1d71 ]
Kernel memory leak detected:
unreferenced object 0xffff888849cdf480 (size 8):
comm "kworker/u8:3", pid 2086, jiffies 4297898756 (age 4269.856s) hex dump (first 8 bytes):
30 00 cd 49 88 88 ff ff 0..I....
backtrace:
[<00000000acfc370b>] __kmalloc_track_caller+0x137/0x183
[<00000000a2724354>] kstrdup+0x2b/0x43
[<0000000082964f84>] xprt_rdma_format_addresses+0x114/0x17d [rpcrdma]
[<00000000dfa6ed00>] xprt_setup_rdma_bc+0xc0/0x10c [rpcrdma]
[<0000000073051a83>] xprt_create_transport+0x3f/0x1a0 [sunrpc]
[<0000000053531a8e>] rpc_create+0x118/0x1cd [sunrpc]
[<000000003a51b5f8>] setup_callback_client+0x1a5/0x27d [nfsd]
[<000000001bd410af>] nfsd4_process_cb_update.isra.7+0x16c/0x1ac [nfsd]
[<000000007f4bbd56>] nfsd4_run_cb_work+0x4c/0xbd [nfsd]
[<0000000055c5586b>] process_one_work+0x1b2/0x2fe
[<00000000b1e3e8ef>] worker_thread+0x1a6/0x25a
[<000000005205fb78>] kthread+0xf6/0xfb
[<000000006d2dc057>] ret_from_fork+0x3a/0x50Introduce a call to xprt_rdma_free_addresses() similar to the way that the TCP backchannel releases a transport's peer address strings.
--- net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 1 + 1 file changed, 1 insertion(+)
net/sunrpc/xprtrdma/svc_rdma_backchannel.c +1 -0
@@ -270,6 +270,7 @@ xprt_rdma_bc_put(struct rpc_xprt *xprt) {dprintk ("svcrdma: %s: xprt %p\n" , __func__, xprt); +xprt_rdma_free_addresses (xprt);xprt_free (xprt);module_put (THIS_MODULE ); }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 87/127 KVM: Remove CREATE_IRQCHIP/SET_PIT2 race
In reply to Sasha LevinFrom: Steve Rutherford <[email protected]>
[ Upstream commit 7289fdb5dcdbc5155b5531529c44105868a762f2 ]
Fixes a NULL pointer dereference, caused by the PIT firing an interrupt before the interrupt table has been initialized.
SET_PIT2 can race with the creation of the IRQchip. In particular, if SET_PIT2 is called with a low PIT timer period (after the creation of the IOAPIC, but before the instantiation of the irq routes), the PIT can fire an interrupt at an uninitialized table.
Message-Id: <[email protected]>
--- arch/x86/kvm/x86.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)
arch/x86/kvm/x86.c +8 -2
@@ -4370,10 +4370,13 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT ;if (copy_from_user (&u.ps, argp,sizeof u.ps)) goto out; +mutex_lock (&kvm->lock); r = -ENXIO ;if (!kvm->arch.vpit) - goto out; + goto set_pit_out; r =kvm_vm_ioctl_set_pit (kvm, &u.ps); +set_pit_out: +mutex_unlock (&kvm->lock);break ; }case KVM_GET_PIT2 : {
@@ -4393,10 +4396,13 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT ;if (copy_from_user (&u.ps2, argp,sizeof (u.ps2))) goto out; +mutex_lock (&kvm->lock); r = -ENXIO ;if (!kvm->arch.vpit) - goto out; + goto set_pit2_out; r =kvm_vm_ioctl_set_pit2 (kvm, &u.ps2); +set_pit2_out: +mutex_unlock (&kvm->lock);break ; }case KVM_REINJECT_CONTROL : {
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 86/127 serial: uartps: Wait for tx_empty in console setup
In reply to Sasha LevinFrom: Raviteja Narayanam <[email protected]>
[ Upstream commit 42e11948ddf68b9f799cad8c0ddeab0a39da33e8 ]
On some platforms, the log is corrupted while console is being registered. It is observed that when set_termios is called, there are still some bytes in the FIFO to be transmitted.
So, wait for tx_empty inside cdns_uart_console_setup before calling set_termios.
--- drivers/tty/serial/xilinx_uartps.c | 8 ++++++++ 1 file changed, 8 insertions(+)
drivers/tty/serial/xilinx_uartps.c +8 -0
@@ -1282,6 +1282,7 @@ static int cdns_uart_console_setup(struct console *co, char *options)int bits =8 ;int parity ='n' ;int flow ='n' ; +unsigned long time_out;if (co->index <0 || co->index >=CDNS_UART_NR_PORTS )return -EINVAL ;
@@ -1295,6 +1296,13 @@ static int cdns_uart_console_setup(struct console *co, char *options)if (options)uart_parse_options (options, &baud, &parity, &bits, &flow); +/* Wait for tx_empty before setting up the console */ + time_out = jiffies +usecs_to_jiffies (TX_TIMEOUT ); + +while (time_before (jiffies, time_out) && +cdns_uart_tx_empty (port) !=TIOCSER_TEMT ) +cpu_relax (); +return uart_set_options (port, co, baud, parity, bits, flow); }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 97/127 phy: samsung: s5pv210-usb2: Add delay after reset
In reply to Sasha LevinFrom: Jonathan Bakker <[email protected]>
[ Upstream commit 05942b8c36c7eb5d3fc5e375d4b0d0c49562e85d ]
The USB phy takes some time to reset, so make sure we give it to it. The delay length was taken from the 4x12 phy driver.
This manifested in issues with the DWC2 driver since commit fe369e1826b3 ("usb: dwc2: Make dwc2_readl/writel functions endianness-agnostic.") where the endianness check would read the DWC ID as 0 due to the phy still resetting, resulting in the wrong endian mode being chosen.
--- drivers/phy/samsung/phy-s5pv210-usb2.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/phy/samsung/phy-s5pv210-usb2.c +4 -0
@@ -142,6 +142,10 @@ static void s5pv210_phy_pwr(struct samsung_usb2_phy_instance *inst, bool on)udelay (10 ); rst &= ~rstbits;writel (rst, drv->reg_phy +S5PV210_UPHYRST ); +/* The following delay is necessary for the reset sequence to be +* completed +*/ +udelay (80 ); }else { pwr =readl (drv->reg_phy +S5PV210_UPHYPWR ); pwr |= phypwr;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 41/127 ALSA: hda: Clear RIRB status before reading WP
In reply to Sasha LevinFrom: Mohan Kumar <[email protected]>
[ Upstream commit 6d011d5057ff88ee556c000ac6fe0be23bdfcd72 ]
RIRB interrupt status getting cleared after the write pointer is read causes a race condition, where last response(s) into RIRB may remain unserviced by IRQ, eventually causing azx_rirb_get_response to fall back to polling mode. Clearing the RIRB interrupt status ahead of write pointer access ensures that this condition is avoided.
--- sound/pci/hda/hda_controller.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)
sound/pci/hda/hda_controller.c +9 -2
@@ -1169,16 +1169,23 @@ irqreturn_t azx_interrupt(int irq, void *dev_id)if (snd_hdac_bus_handle_stream_irq (bus, status, stream_update)) active = true; -/* clear rirb int */ status =azx_readb (chip,RIRBSTS );if (status &RIRB_INT_MASK ) { +/* +* Clearing the interrupt status here ensures that no +* interrupt gets masked after the RIRB wp is read in +* snd_hdac_bus_update_rirb. This avoids a possible +* race condition where codec response in RIRB may +* remain unserviced by IRQ, eventually falling back +* to polling mode in azx_rirb_get_response. +*/ +azx_writeb (chip,RIRBSTS ,RIRB_INT_MASK ); active = true;if (status &RIRB_INT_RESPONSE ) {if (chip->driver_caps &AZX_DCAPS_CTX_WORKAROUND )udelay (80 );snd_hdac_bus_update_rirb (bus); } -azx_writeb (chip,RIRBSTS ,RIRB_INT_MASK ); } }while (active && ++repeat <10 );
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 96/127 power: supply: max17040: Correct voltage reading
In reply to Sasha LevinFrom: Jonathan Bakker <[email protected]>
[ Upstream commit 0383024f811aa469df258039807810fc3793a105 ]
According to the datasheet available at (1), the bottom four bits are always zero and the actual voltage is 1.25x this value in mV. Since the kernel API specifies that voltages should be in uV, it should report 1250x the shifted value.
1) https://datasheets.maximintegrated.com/en/ds/MAX17040-MAX17041.pdf
--- drivers/power/supply/max17040_battery.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/power/supply/max17040_battery.c +1 -1
@@ -109,7 +109,7 @@ static void max17040_get_vcell(struct i2c_client *client) vcell =max17040_read_reg (client,MAX17040_VCELL ); - chip->vcell = vcell; + chip->vcell = (vcell >>4 ) *1250 ; }static void max17040_get_soc (struct i2c_client *client)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 95/127 perf parse-events: Fix memory leaks found on parse_events
In reply to Sasha LevinFrom: Ian Rogers <[email protected]>
[ Upstream commit e8dfb81838b14f82521968343884665b996646ef ]
Fix a memory leak found by applying LLVM's libfuzzer on parse_events().
--- tools/perf/util/parse-events.c | 1 + 1 file changed, 1 insertion(+)
tools/perf/util/parse-events.c +1 -0
@@ -1258,6 +1258,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,list_for_each_entry_safe (pos, tmp, &config_terms, list) {list_del_init (&pos->list); +zfree (&pos->val.str);free (pos); }return -EINVAL ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 107/127 drm/nouveau/debugfs: fix runtime pm imbalance on error
In reply to Sasha LevinFrom: Dinghao Liu <[email protected]>
[ Upstream commit 00583fbe8031f69bba8b0a9a861efb75fb7131af ]
pm_runtime_get_sync() increments the runtime PM usage counter even the call returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.
--- drivers/gpu/drm/nouveau/nouveau_debugfs.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/gpu/drm/nouveau/nouveau_debugfs.c +4 -1
@@ -161,8 +161,11 @@ nouveau_debugfs_pstate_set(struct file *file, const char __user *ubuf, } ret =pm_runtime_get_sync (drm->dev); -if (ret <0 && ret != -EACCES ) +if (ret <0 && ret != -EACCES ) { +pm_runtime_put_autosuspend (drm->dev);return ret; + } + ret =nvif_mthd (ctrl,NVIF_CONTROL_PSTATE_USER , &args,sizeof (args));pm_runtime_put_autosuspend (drm->dev);if (ret <0 )
Signature · 6 lines
2.25.1 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Sasha Levin
maintainerPATCH 109/127 usb: dwc3: Increase timeout for CmdAct cleared by device controller
In reply to Sasha LevinFrom: Yu Chen <[email protected]>
[ Upstream commit 1c0e69ae1b9f9004fd72978612ae3463791edc56 ]
If the SS PHY is in P3, there is no pipe_clk, HW may use suspend_clk for function, as suspend_clk is slow so EP command need more time to complete, e.g, imx8M suspend_clk is 32K, set ep configuration will take about 380us per below trace time stamp(44.286278 - 44.285897 = 0.000381):
configfs_acm.sh-822 [000] d..1 44.285896: dwc3_writel: addr000000006d59aae1 value 00000401
configfs_acm.sh-822 [000] d..1 44.285897: dwc3_readl: addr000000006d59aae1 value 00000401
... ...
configfs_acm.sh-822 [000] d..1 44.286278: dwc3_readl: addr000000006d59aae1 value 00000001
configfs_acm.sh-822 [000] d..1 44.286279: dwc3_gadget_ep_cmd:
ep0out: cmd 'Set Endpoint Configuration' [401] params 00001000 00000500 00000000 --> status: Successful
This was originally found on Hisilicon Kirin Soc that need more time for the device controller to clear the CmdAct of DEPCMD.
--- drivers/usb/dwc3/gadget.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/usb/dwc3/gadget.c +1 -1
@@ -276,7 +276,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned cmd, {const struct usb_endpoint_descriptor *desc = dep->endpoint.desc;struct dwc3 *dwc = dep->dwc; -u32 timeout =1000 ; +u32 timeout =5000 ;u32 saved_config =0 ;u32 reg;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 110/127 btrfs: don't force read-only after error in drop snapshot
In reply to Sasha LevinFrom: David Sterba <[email protected]>
[ Upstream commit 7c09c03091ac562ddca2b393e5d65c1d37da79f1 ]
Deleting a subvolume on a full filesystem leads to ENOSPC followed by a forced read-only. This is not a transaction abort and the filesystem is otherwise ok, so the error should be just propagated to the callers.
This is caused by unnecessary call to btrfs_handle_fs_error for all errors, except EAGAIN. This does not make sense as the standard transaction abort mechanism is in btrfs_drop_snapshot so all relevant failures are handled.
Originally in commit cb1b69f4508a ("Btrfs: forced readonly when btrfs_drop_snapshot() fails") there was no return value at all, so the btrfs_std_error made some sense but once the error handling and propagation has been implemented we don't need it anymore.
--- fs/btrfs/extent-tree.c | 2 -- 1 file changed, 2 deletions(-)
fs/btrfs/extent-tree.c +0 -2
@@ -9365,8 +9365,6 @@ out:*/ if (!for_reloc && root_dropped == false)btrfs_add_dead_root (root); -if (err && err != -EAGAIN ) -btrfs_handle_fs_error (fs_info, err,NULL );return err; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 111/127 vfio/pci: fix memory leaks of eventfd ctx
In reply to Sasha LevinFrom: Qian Cai <[email protected]>
[ Upstream commit 1518ac272e789cae8c555d69951b032a275b7602 ]
Finished a qemu-kvm (-device vfio-pci,host=0001:01:00.0) triggers a few memory leaks after a while because vfio_pci_set_ctx_trigger_single() calls eventfd_ctx_fdget() without the matching eventfd_ctx_put() later. Fix it by calling eventfd_ctx_put() for those memory in vfio_pci_release() before vfio_device_release().
unreferenced object 0xebff008981cc2b00 (size 128):
comm "qemu-kvm", pid 4043, jiffies 4294994816 (age 9796.310s) hex dump (first 32 bytes):
01 00 00 00 6b 6b 6b 6b 00 00 00 00 ad 4e ad de ....kkkk.....N.. ff ff ff ff 6b 6b 6b 6b ff ff ff ff ff ff ff ff ....kkkk........
backtrace:
[<00000000917e8f8d>] slab_post_alloc_hook+0x74/0x9c
[<00000000df0f2aa2>] kmem_cache_alloc_trace+0x2b4/0x3d4
[<000000005fcec025>] do_eventfd+0x54/0x1ac
[<0000000082791a69>] __arm64_sys_eventfd2+0x34/0x44
[<00000000b819758c>] do_el0_svc+0x128/0x1dc
[<00000000b244e810>] el0_sync_handler+0xd0/0x268
[<00000000d495ef94>] el0_sync+0x164/0x180unreferenced object 0x29ff008981cc4180 (size 128):
comm "qemu-kvm", pid 4043, jiffies 4294994818 (age 9796.290s) hex dump (first 32 bytes):
01 00 00 00 6b 6b 6b 6b 00 00 00 00 ad 4e ad de ....kkkk.....N.. ff ff ff ff 6b 6b 6b 6b ff ff ff ff ff ff ff ff ....kkkk........
backtrace:
[<00000000917e8f8d>] slab_post_alloc_hook+0x74/0x9c
[<00000000df0f2aa2>] kmem_cache_alloc_trace+0x2b4/0x3d4
[<000000005fcec025>] do_eventfd+0x54/0x1ac
[<0000000082791a69>] __arm64_sys_eventfd2+0x34/0x44
[<00000000b819758c>] do_el0_svc+0x128/0x1dc
[<00000000b244e810>] el0_sync_handler+0xd0/0x268
[<00000000d495ef94>] el0_sync+0x164/0x180--- drivers/vfio/pci/vfio_pci.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/vfio/pci/vfio_pci.c +4 -0
@@ -399,6 +399,10 @@ static void vfio_pci_release(void *device_data)if (!(--vdev->refcnt)) {vfio_spapr_pci_eeh_release (vdev->pdev);vfio_pci_disable (vdev); +if (vdev->err_trigger) +eventfd_ctx_put (vdev->err_trigger); +if (vdev->req_trigger) +eventfd_ctx_put (vdev->req_trigger); }mutex_unlock (&driver_lock);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 114/127 perf kcore_copy: Fix module map when there are no modules loaded
In reply to Sasha LevinFrom: Adrian Hunter <[email protected]>
[ Upstream commit 61f82e3fb697a8e85f22fdec786528af73dc36d1 ]
In the absence of any modules, no "modules" map is created, but there are other executable pages to map, due to eBPF JIT, kprobe or ftrace. Map them by recognizing that the first "module" symbol is not necessarily from a module, and adjust the map accordingly.
--- tools/perf/util/symbol-elf.c | 7 +++++++ 1 file changed, 7 insertions(+)
tools/perf/util/symbol-elf.c +7 -0
@@ -1420,6 +1420,7 @@ struct kcore_copy_info {u64 first_symbol;u64 last_symbol;u64 first_module; +u64 first_module_symbol;u64 last_module_symbol;struct phdr_data kernel_map;struct phdr_data modules_map;
@@ -1434,6 +1435,8 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,return 0 ;if (strchr (name,'[' )) { +if (!kci->first_module_symbol || start < kci->first_module_symbol) + kci->first_module_symbol = start;if (start > kci->last_module_symbol) kci->last_module_symbol = start;return 0 ;
@@ -1558,6 +1561,10 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir, kci->etext += page_size; } +if (kci->first_module_symbol && + (!kci->first_module || kci->first_module_symbol < kci->first_module)) + kci->first_module = kci->first_module_symbol; + kci->first_module =round_down (kci->first_module, page_size);if (kci->last_module_symbol) {
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 120/127 x86/speculation/mds: Mark mds_user_clear_cpu_buffers() __always_inline
In reply to Sasha LevinFrom: Thomas Gleixner <[email protected]>
[ Upstream commit a7ef9ba986b5fae9d80f8a7b31db0423687efe4e ]
Prevent the compiler from uninlining and creating traceable/probable functions as this is invoked _after_ context tracking switched to CONTEXT_USER and rcu idle.
--- arch/x86/include/asm/nospec-branch.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/x86/include/asm/nospec-branch.h +2 -2
@@ -330,7 +330,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear);* combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ -static inline void mds_clear_cpu_buffers (void ) +static __always_inline void mds_clear_cpu_buffers(void) {static const u16 ds = __KERNEL_DS;
@@ -351,7 +351,7 @@ static inline void mds_clear_cpu_buffers(void)* * Clear CPU buffers if the corresponding static key is enabled */ -static inline void mds_user_clear_cpu_buffers (void ) +static __always_inline void mds_user_clear_cpu_buffers(void) {if (static_branch_likely (&mds_user_clear))mds_clear_cpu_buffers ();
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 113/127 perf util: Fix memory leak of prefix_if_not_in
In reply to Sasha LevinFrom: Xie XiuQi <[email protected]>
[ Upstream commit 07e9a6f538cbeecaf5c55b6f2991416f873cdcbd ]
Need to free "str" before return when asprintf() failed to avoid memory leak.
--- tools/perf/util/sort.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/sort.c +1 -1
@@ -2667,7 +2667,7 @@ static char *prefix_if_not_in(const char *pre, char *str)return str;if (asprintf (&n,"%s,%s" , pre, str) <0 ) -return NULL ; + n =NULL ;free (str);return n;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 119/127 mtd: parser: cmdline: Support MTD names containing one or more colons
In reply to Sasha LevinFrom: Boris Brezillon <[email protected]>
[ Upstream commit eb13fa0227417e84aecc3bd9c029d376e33474d3 ]
Looks like some drivers define MTD names with a colon in it, thus making mtdpart= parsing impossible. Let's fix the parser to gracefully handle that case: the last ':' in a partition definition sequence is considered instead of the first one.
--- drivers/mtd/cmdlinepart.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-)
drivers/mtd/cmdlinepart.c +20 -3
@@ -228,12 +228,29 @@ static int mtdpart_setup_real(char *s)struct cmdline_mtd_partition *this_mtd;struct mtd_partition *parts;int mtd_id_len, num_parts; -char *p, *mtd_id; +char *p, *mtd_id, *semicol; + +/* +* Replace the first ';' by a NULL char so strrchr can work +* properly. +*/ + semicol =strchr (s,';' ); +if (semicol) + *semicol ='\0' ; mtd_id = s; -/* fetch <mtd-id> */ - p =strchr (s,':' ); +/* +* fetch <mtd-id>. We use strrchr to ignore all ':' that could +* be present in the MTD name, only the last one is interpreted +* as an <mtd-id>/<part-definition> separator. +*/ + p =strrchr (s,':' ); + +/* Restore the ';' now. */ +if (semicol) + *semicol =';' ; +if (!p) {pr_err ("no mtd-id\n" );return -EINVAL ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 124/127 scsi: libfc: Skip additional kref updating work event
In reply to Sasha LevinFrom: Javed Hasan <[email protected]>
[ Upstream commit 823a65409c8990f64c5693af98ce0e7819975cba ]
When an rport event (RPORT_EV_READY) is updated without work being queued, avoid taking an additional reference.
This issue was leading to memory leak. Trace from KMEMLEAK tool:
unreferenced object 0xffff8888259e8780 (size 512):
comm "kworker/2:1", jiffies 4433237386 (age 113021.971s)
hex dump (first 32 bytes): 58 0a ec cf 83 88 ff ff 00 00 00 00 00 00 00 00 01 00 00 00 08 00 00 00 13 7d f0 1e 0e 00 00 10 backtrace: [<000000006b25760f>] fc_rport_recv_req+0x3c6/0x18f0 [libfc] [<00000000f208d994>] fc_lport_recv_els_req+0x120/0x8a0 [libfc] [<00000000a9c437b8>] fc_lport_recv+0xb9/0x130 [libfc] [<00000000a9c437b8>] fc_lport_recv+0xb9/0x130 [libfc] [<00000000ad5be37b>] qedf_ll2_process_skb+0x73d/0xad0 [qedf] [<00000000e0eb6893>] process_one_work+0x382/0x6c0 [<000000002dfd9e21>] worker_thread+0x57/0x5c0 [<00000000b648204f>] kthread+0x1a0/0x1c0 [<0000000072f5ab20>] ret_from_fork+0x35/0x40 [<000000001d5c05d8>] 0xffffffffffffffff
Below is the log sequence which leads to memory leak. Here we get the RPORT_EV_READY and RPORT_EV_STOP back to back, which lead to overwrite the event RPORT_EV_READY by event RPORT_EV_STOP. Because of this, kref_count gets incremented by 1.
kernel: host0: rport fffce5: Received PLOGI request
kernel: host0: rport fffce5: Received PLOGI in INIT state
kernel: host0: rport fffce5: Port is Ready
kernel: host0: rport fffce5: Received PRLI request while in state Ready
kernel: host0: rport fffce5: PRLI rspp type 8 active 1 passive 0
kernel: host0: rport fffce5: Received LOGO request while in state Ready
kernel: host0: rport fffce5: Delete port
kernel: host0: rport fffce5: Received PLOGI request
kernel: host0: rport fffce5: Received PLOGI in state Delete - send busy
kernel: host0: rport fffce5: work event 3
kernel: host0: rport fffce5: lld callback ev 3
kernel: host0: rport fffce5: work delete
--- drivers/scsi/libfc/fc_rport.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
drivers/scsi/libfc/fc_rport.c +5 -4
@@ -495,10 +495,11 @@ static void fc_rport_enter_delete(struct fc_rport_priv *rdata,fc_rport_state_enter (rdata,RPORT_ST_DELETE ); -kref_get (&rdata->kref); -if (rdata->event ==RPORT_EV_NONE && - !queue_work (rport_event_queue, &rdata->event_work)) -kref_put (&rdata->kref, fc_rport_destroy); +if (rdata->event ==RPORT_EV_NONE ) { +kref_get (&rdata->kref); +if (!queue_work (rport_event_queue, &rdata->event_work)) +kref_put (&rdata->kref, fc_rport_destroy); + } rdata->event = event; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 125/127 selftests/x86/syscall_nt: Clear weird flags after each test
In reply to Sasha LevinFrom: Andy Lutomirski <[email protected]>
[ Upstream commit a61fa2799ef9bf6c4f54cf7295036577cececc72 ]
Clear the weird flags before logging to improve strace output -- logging results while, say, TF is set does no one any favors.
--- tools/testing/selftests/x86/syscall_nt.c | 1 + 1 file changed, 1 insertion(+)
tools/testing/selftests/x86/syscall_nt.c +1 -0
@@ -67,6 +67,7 @@ static void do_it(unsigned long extraflags)set_eflags (get_eflags () | extraflags);syscall (SYS_getpid); flags =get_eflags (); +set_eflags (X86_EFLAGS_IF |X86_EFLAGS_FIXED );if ((flags & extraflags) == extraflags) {printf ("[OK]\tThe syscall worked and flags are still set\n" ); }else {
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 101/127 ALSA: hda: Fix potential race in unsol event handler
In reply to Sasha LevinFrom: Takashi Iwai <[email protected]>
[ Upstream commit c637fa151259c0f74665fde7cba5b7eac1417ae5 ]
The unsol event handling code has a loop retrieving the read/write indices and the arrays without locking while the append to the array may happen concurrently. This may lead to some inconsistency. Although there hasn't been any proof of this bad results, it's still safer to protect the racy accesses.
This patch adds the spinlock protection around the unsol handling loop for addressing it. Here we take bus->reg_lock as the writer side snd_hdac_bus_queue_event() is also protected by that lock.
--- sound/hda/hdac_bus.c | 4 ++++ 1 file changed, 4 insertions(+)
sound/hda/hdac_bus.c +4 -0
@@ -155,6 +155,7 @@ static void process_unsol_events(struct work_struct *work)struct hdac_driver *drv;unsigned int rp, caddr, res; +spin_lock_irq (&bus->reg_lock);while (bus->unsol_rp != bus->unsol_wp) { rp = (bus->unsol_rp +1 ) %HDA_UNSOL_QUEUE_SIZE ; bus->unsol_rp = rp;
@@ -166,10 +167,13 @@ static void process_unsol_events(struct work_struct *work) codec = bus->caddr_tbl[caddr &0x0f ];if (!codec || !codec->dev.driver)continue ; +spin_unlock_irq (&bus->reg_lock); drv =drv_to_hdac_driver (codec->dev.driver);if (drv->unsol_event) drv->unsol_event (codec, res); +spin_lock_irq (&bus->reg_lock); } +spin_unlock_irq (&bus->reg_lock); }/**
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 123/127 scsi: libfc: Handling of extra kref
In reply to Sasha LevinFrom: Javed Hasan <[email protected]>
[ Upstream commit 71f2bf85e90d938d4a9ef9dd9bfa8d9b0b6a03f7 ]
Handling of extra kref which is done by lookup table in case rdata is already present in list.
This issue was leading to memory leak. Trace from KMEMLEAK tool:
unreferenced object 0xffff8888259e8780 (size 512):
comm "kworker/2:1", pid 182614, jiffies 4433237386 (age 113021.971s)
hex dump (first 32 bytes):
58 0a ec cf 83 88 ff ff 00 00 00 00 00 00 00 00
01 00 00 00 08 00 00 00 13 7d f0 1e 0e 00 00 10
backtrace:
[<000000006b25760f>] fc_rport_recv_req+0x3c6/0x18f0 [libfc]
[<00000000f208d994>] fc_lport_recv_els_req+0x120/0x8a0 [libfc]
[<00000000a9c437b8>] fc_lport_recv+0xb9/0x130 [libfc]
[<00000000ad5be37b>] qedf_ll2_process_skb+0x73d/0xad0 [qedf]
[<00000000e0eb6893>] process_one_work+0x382/0x6c0
[<000000002dfd9e21>] worker_thread+0x57/0x5c0
[<00000000b648204f>] kthread+0x1a0/0x1c0
[<0000000072f5ab20>] ret_from_fork+0x35/0x40
[<000000001d5c05d8>] 0xffffffffffffffffBelow is the log sequence which leads to memory leak. Here we get the nested "Received PLOGI request" for same port and this request leads to call the fc_rport_create() twice for the same rport.
kernel: host1: rport fffce5: Received PLOGI request
kernel: host1: rport fffce5: Received PLOGI in INIT state
kernel: host1: rport fffce5: Port is Ready
kernel: host1: rport fffce5: Received PRLI request while in state Ready
kernel: host1: rport fffce5: PRLI rspp type 8 active 1 passive 0
kernel: host1: rport fffce5: Received LOGO request while in state Ready
kernel: host1: rport fffce5: Delete port
kernel: host1: rport fffce5: Received PLOGI request
kernel: host1: rport fffce5: Received PLOGI in state Delete - send busy
--- drivers/scsi/libfc/fc_rport.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/scsi/libfc/fc_rport.c +3 -1
@@ -145,8 +145,10 @@ struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id)size_t rport_priv_size =sizeof (*rdata); rdata =fc_rport_lookup (lport, port_id); -if (rdata) +if (rdata) { +kref_put (&rdata->kref, fc_rport_destroy);return rdata; + }if (lport->rport_priv_size >0 ) rport_priv_size = lport->rport_priv_size;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 126/127 vfio/pci: fix racy on error and request eventfd ctx
In reply to Sasha LevinFrom: Zeng Tao <[email protected]>
[ Upstream commit b872d0640840018669032b20b6375a478ed1f923 ]
The vfio_pci_release call will free and clear the error and request eventfd ctx while these ctx could be in use at the same time in the function like vfio_pci_request, and it's expected to protect them under the vdev->igate mutex, which is missing in vfio_pci_release.
This issue is introduced since commit 1518ac272e78 ("vfio/pci: fix memory leaks of eventfd ctx"),and since commit 5c5866c593bb ("vfio/pci: Clear error and request eventfd ctx after releasing"), it's very easily to trigger the kernel panic like this:
[ 9513.904346] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 [ 9513.913091] Mem abort info: [ 9513.915871] ESR = 0x96000006 [ 9513.918912] EC = 0x25: DABT (current EL), IL = 32 bits [ 9513.924198] SET = 0, FnV = 0 [ 9513.927238] EA = 0, S1PTW = 0 [ 9513.930364] Data abort info: [ 9513.933231] ISV = 0, ISS = 0x00000006 [ 9513.937048] CM = 0, WnR = 0 [ 9513.940003] user pgtable: 4k pages, 48-bit VAs, pgdp=0000007ec7d12000 [ 9513.946414] [0000000000000008] pgd=0000007ec7d13003, p4d=0000007ec7d13003, pud=0000007ec728c003, pmd=0000000000000000 [ 9513.956975] Internal error: Oops: 96000006 [#1] PREEMPT SMP [ 9513.962521] Modules linked in: vfio_pci vfio_virqfd vfio_iommu_type1 vfio hclge hns3 hnae3 [last unloaded: vfio_pci] [ 9513.972998] CPU: 4 PID: 1327 Comm: bash Tainted: G W 5.8.0-rc4+ #3 [ 9513.980443] Hardware name: Huawei TaiShan 2280 V2/BC82AMDC, BIOS 2280-V2 CS V3.B270.01 05/08/2020 [ 9513.989274] pstate: 80400089 (Nzcv daIf +PAN -UAO BTYPE=--) [ 9513.994827] pc : _raw_spin_lock_irqsave+0x48/0x88 [ 9513.999515] lr : eventfd_signal+0x6c/0x1b0 [ 9514.003591] sp : ffff800038a0b960 [ 9514.006889] x29: ffff800038a0b960 x28: ffff007ef7f4da10 [ 9514.012175] x27: ffff207eefbbfc80 x26: ffffbb7903457000 [ 9514.017462] x25: ffffbb7912191000 x24: ffff007ef7f4d400 [ 9514.022747] x23: ffff20be6e0e4c00 x22: 0000000000000008 [ 9514.028033] x21: 0000000000000000 x20: 0000000000000000 [ 9514.033321] x19: 0000000000000008 x18: 0000000000000000 [ 9514.038606] x17: 0000000000000000 x16: ffffbb7910029328 [ 9514.043893] x15: 0000000000000000 x14: 0000000000000001 [ 9514.049179] x13: 0000000000000000 x12: 0000000000000002 [ 9514.054466] x11: 0000000000000000 x10: 0000000000000a00 [ 9514.059752] x9 : ffff800038a0b840 x8 : ffff007ef7f4de60 [ 9514.065038] x7 : ffff007fffc96690 x6 : fffffe01faffb748 [ 9514.070324] x5 : 0000000000000000 x4 : 0000000000000000 [ 9514.075609] x3 : 0000000000000000 x2 : 0000000000000001 [ 9514.080895] x1 : ffff007ef7f4d400 x0 : 0000000000000000 [ 9514.086181] Call trace: [ 9514.088618] _raw_spin_lock_irqsave+0x48/0x88 [ 9514.092954] eventfd_signal+0x6c/0x1b0 [ 9514.096691] vfio_pci_request+0x84/0xd0 [vfio_pci] [ 9514.101464] vfio_del_group_dev+0x150/0x290 [vfio] [ 9514.106234] vfio_pci_remove+0x30/0x128 [vfio_pci] [ 9514.111007] pci_device_remove+0x48/0x108 [ 9514.115001] device_release_driver_internal+0x100/0x1b8 [ 9514.120200] device_release_driver+0x28/0x38 [ 9514.124452] pci_stop_bus_device+0x68/0xa8 [ 9514.128528] pci_stop_and_remove_bus_device+0x20/0x38 [ 9514.133557] pci_iov_remove_virtfn+0xb4/0x128 [ 9514.137893] sriov_disable+0x3c/0x108 [ 9514.141538] pci_disable_sriov+0x28/0x38 [ 9514.145445] hns3_pci_sriov_configure+0x48/0xb8 [hns3] [ 9514.150558] sriov_numvfs_store+0x110/0x198 [ 9514.154724] dev_attr_store+0x44/0x60 [ 9514.158373] sysfs_kf_write+0x5c/0x78 [ 9514.162018] kernfs_fop_write+0x104/0x210 [ 9514.166010] __vfs_write+0x48/0x90 [ 9514.169395] vfs_write+0xbc/0x1c0 [ 9514.172694] ksys_write+0x74/0x100 [ 9514.176079] __arm64_sys_write+0x24/0x30 [ 9514.179987] el0_svc_common.constprop.4+0x110/0x200 [ 9514.184842] do_el0_svc+0x34/0x98 [ 9514.188144] el0_svc+0x14/0x40 [ 9514.191185] el0_sync_handler+0xb0/0x2d0 [ 9514.195088] el0_sync+0x140/0x180 [ 9514.198389] Code: b9001020 d2800000 52800022 f9800271 (885ffe61) [ 9514.204455] ---[ end trace 648de00c8406465f ]--- [ 9514.212308] note: bash[1327] exited with preempt_count 1
--- drivers/vfio/pci/vfio_pci.c | 5 +++++ 1 file changed, 5 insertions(+)
drivers/vfio/pci/vfio_pci.c +5 -0
@@ -399,14 +399,19 @@ static void vfio_pci_release(void *device_data)if (!(--vdev->refcnt)) {vfio_spapr_pci_eeh_release (vdev->pdev);vfio_pci_disable (vdev); +mutex_lock (&vdev->igate);if (vdev->err_trigger) {eventfd_ctx_put (vdev->err_trigger); vdev->err_trigger =NULL ; } +mutex_unlock (&vdev->igate); + +mutex_lock (&vdev->igate);if (vdev->req_trigger) {eventfd_ctx_put (vdev->req_trigger); vdev->req_trigger =NULL ; } +mutex_unlock (&vdev->igate); }mutex_unlock (&driver_lock);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 127/127 btrfs: qgroup: fix data leak caused by race between writeback and truncate
In reply to Sasha LevinFrom: Qu Wenruo <[email protected]>
[ Upstream commit fa91e4aa1716004ea8096d5185ec0451e206aea0 ]
[BUG]
When running tests like generic/013 on test device with btrfs quota enabled, it can normally lead to data leak, detected at unmount time:
BTRFS warning (device dm-3): qgroup 0/5 has unreleased space, type 0 rsv 4096
------------[ cut here ]------------ WARNING: CPU: 11 PID: 16386 at fs/btrfs/disk-io.c:4142 close_ctree+0x1dc/0x323 [btrfs] RIP: 0010:close_ctree+0x1dc/0x323 [btrfs] Call Trace: btrfs_put_super+0x15/0x17 [btrfs] generic_shutdown_super+0x72/0x110 kill_anon_super+0x18/0x30 btrfs_kill_super+0x17/0x30 [btrfs] deactivate_locked_super+0x3b/0xa0 deactivate_super+0x40/0x50 cleanup_mnt+0x135/0x190 __cleanup_mnt+0x12/0x20 task_work_run+0x64/0xb0 __prepare_exit_to_usermode+0x1bc/0x1c0 __syscall_return_slowpath+0x47/0x230 do_syscall_64+0x64/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ---[ end trace caf08beafeca2392 ]--- BTRFS error (device dm-3): qgroup reserved space leaked
[CAUSE]
In the offending case, the offending operations are:
2/6: writev f2X[269 1 0 0 0 0] [1006997,67,288] 0 2/7: truncate f2X[269 1 0 0 48 1026293] 18388 0
The following sequence of events could happen after the writev():
CPU1 (writeback) | CPU2 (truncate)
-----------------------------------------------------------------
btrfs_writepages() |
|- extent_write_cache_pages() |
|- Got page for 1003520 |
| 1003520 is Dirty, no writeback |
| So (!clear_page_dirty_for_io()) |
| gets called for it |
|- Now page 1003520 is Clean. |
| | btrfs_setattr()
| | |- btrfs_setsize()
| | |- truncate_setsize()
| | New i_size is 18388
|- __extent_writepage() |
| |- page_offset() > i_size |
|- btrfs_invalidatepage() |
|- Page is clean, so no qgroup |callback executed
This means, the qgroup reserved data space is not properly released in btrfs_invalidatepage() as the page is Clean.
[FIX]
Instead of checking the dirty bit of a page, call btrfs_qgroup_free_data() unconditionally in btrfs_invalidatepage().
As qgroup rsv are completely bound to the QGROUP_RESERVED bit of io_tree, not bound to page status, thus we won't cause double freeing anyway.
--- fs/btrfs/inode.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-)
fs/btrfs/inode.c +10 -13
@@ -9204,20 +9204,17 @@ again:/* * Qgroup reserved space handler * Page here will be either -* 1) Already written to disk -* In this case, its reserved space is released from data rsv map -* and will be freed by delayed_ref handler finally. -* So even we call qgroup_free_data(), it won't decrease reserved -* space. -* 2) Not written to disk -* This means the reserved space should be freed here. However, -* if a truncate invalidates the page (by clearing PageDirty) -* and the page is accounted for while allocating extent -* in btrfs_check_data_free_space() we let delayed_ref to -* free the entire extent. +* 1) Already written to disk or ordered extent already submitted +* Then its QGROUP_RESERVED bit in io_tree is already cleaned. +* Qgroup will be handled by its qgroup_record then. +* btrfs_qgroup_free_data() call will do nothing here. +* +* 2) Not written to disk yet +* Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED +* bit of its io_tree, and free the qgroup reserved data space. +* Since the IO will never happen for this page. */ -if (PageDirty (page)) -btrfs_qgroup_free_data (inode,NULL , page_start,PAGE_SIZE ); +btrfs_qgroup_free_data (inode,NULL , page_start,PAGE_SIZE );if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DIRTY |
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 121/127 vfio/pci: Clear error and request eventfd ctx after releasing
In reply to Sasha LevinFrom: Alex Williamson <[email protected]>
[ Upstream commit 5c5866c593bbd444d0339ede6a8fb5f14ff66d72 ]
The next use of the device will generate an underflow from the stale reference.
--- drivers/vfio/pci/vfio_pci.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/vfio/pci/vfio_pci.c +6 -2
@@ -399,10 +399,14 @@ static void vfio_pci_release(void *device_data)if (!(--vdev->refcnt)) {vfio_spapr_pci_eeh_release (vdev->pdev);vfio_pci_disable (vdev); -if (vdev->err_trigger) +if (vdev->err_trigger) {eventfd_ctx_put (vdev->err_trigger); -if (vdev->req_trigger) + vdev->err_trigger =NULL ; + } +if (vdev->req_trigger) {eventfd_ctx_put (vdev->req_trigger); + vdev->req_trigger =NULL ; + } }mutex_unlock (&driver_lock);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 122/127 cifs: Fix double add page to memcg when cifs_readpages
In reply to Sasha LevinFrom: Zhang Xiaoxu <[email protected]>
[ Upstream commit 95a3d8f3af9b0d63b43f221b630beaab9739d13a ]
When xfstests generic/451, there is an BUG at mm/memcontrol.c:
page:ffffea000560f2c0 refcount:2 mapcount:0 mapping:000000008544e0ea
index:0xf
mapping->aops:cifs_addr_ops dentry name:"tst-aio-dio-cycle-write.451"
flags: 0x2fffff80000001(locked)
raw: 002fffff80000001 ffffc90002023c50 ffffea0005280088 ffff88815cda0210
raw: 000000000000000f 0000000000000000 00000002ffffffff ffff88817287d000
page dumped because: VM_BUG_ON_PAGE(page->mem_cgroup)
page->mem_cgroup:ffff88817287d000
------------[ cut here ]------------
kernel BUG at mm/memcontrol.c:2659!
invalid opcode: 0000 [#1] SMP
CPU: 2 PID: 2038 Comm: xfs_io Not tainted 5.8.0-rc1 #44
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20190727_
073836-buildvm-ppc64le-16.ppc.4
RIP: 0010:commit_charge+0x35/0x50
Code: 0d 48 83 05 54 b2 02 05 01 48 89 77 38 c3 48 c7
c6 78 4a ea ba 48 83 05 38 b2 02 05 01 e8 63 0d9
RSP: 0018:ffffc90002023a50 EFLAGS: 00010202
RAX: 0000000000000000 RBX: ffff88817287d000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffff88817ac97ea0 RDI: ffff88817ac97ea0
RBP: ffffea000560f2c0 R08: 0000000000000203 R09: 0000000000000005
R10: 0000000000000030 R11: ffffc900020237a8 R12: 0000000000000000
R13: 0000000000000001 R14: 0000000000000001 R15: ffff88815a1272c0
FS: 00007f5071ab0800(0000) GS:ffff88817ac80000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055efcd5ca000 CR3: 000000015d312000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
mem_cgroup_charge+0x166/0x4f0
__add_to_page_cache_locked+0x4a9/0x710
add_to_page_cache_locked+0x15/0x20
cifs_readpages+0x217/0x1270
read_pages+0x29a/0x670
page_cache_readahead_unbounded+0x24f/0x390
__do_page_cache_readahead+0x3f/0x60
ondemand_readahead+0x1f1/0x470
page_cache_async_readahead+0x14c/0x170
generic_file_buffered_read+0x5df/0x1100
generic_file_read_iter+0x10c/0x1d0
cifs_strict_readv+0x139/0x170
new_sync_read+0x164/0x250
__vfs_read+0x39/0x60
vfs_read+0xb5/0x1e0
ksys_pread64+0x85/0xf0
__x64_sys_pread64+0x22/0x30
do_syscall_64+0x69/0x150
entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7f5071fcb1af
Code: Bad RIP value.
RSP: 002b:00007ffde2cdb8e0 EFLAGS: 00000293 ORIG_RAX: 0000000000000011
RAX: ffffffffffffffda RBX: 00007ffde2cdb990 RCX: 00007f5071fcb1af
RDX: 0000000000001000 RSI: 000055efcd5ca000 RDI: 0000000000000003
RBP: 0000000000000003 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000001000 R11: 0000000000000293 R12: 0000000000000001
R13: 000000000009f000 R14: 0000000000000000 R15: 0000000000001000
Modules linked in:
---[ end trace 725fa14a3e1af65c ]---Since commit 3fea5a499d57 ("mm: memcontrol: convert page cache to a new mem_cgroup_charge() API") not cancel the page charge, the pages maybe double add to pagecache:
thread1 | thread2cifs_readpagesreadpages_get_pages
add_to_page_cache_locked(head,index=n)=0
| readpages_get_pages
| add_to_page_cache_locked(head,index=n+1)=0 add_to_page_cache_locked(head, index=n+1)=-EEXIST then, will next loop with list head page's index=n+1 and the page->mapping not NULLreadpages_get_pages add_to_page_cache_locked(head, index=n+1)
commit_charge
VM_BUG_ON_PAGE
So, we should not do the next loop when any page add to page cache failed.
--- fs/cifs/file.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)
fs/cifs/file.c +7 -4
@@ -3753,7 +3753,8 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,break ;__SetPageLocked (page); -if (add_to_page_cache_locked (page, mapping, page->index, gfp)) { + rc =add_to_page_cache_locked (page, mapping, page->index, gfp); +if (rc) {__ClearPageLocked (page);break ; }
@@ -3769,6 +3770,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, struct list_head *page_list, unsigned num_pages) { int rc; +int err =0 ;struct list_head tmplist;struct cifsFileInfo *open_file = file->private_data;struct cifs_sb_info *cifs_sb =CIFS_FILE_SB (file);
@@ -3809,7 +3811,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,* the order of declining indexes. When we put the pages in * the rdata->pages, then we want them in increasing order. */ -while (!list_empty (page_list)) { +while (!list_empty (page_list) && !err) {unsigned int i, nr_pages, bytes, rsize;loff_t offset;struct page *page, *tpage;
@@ -3832,9 +3834,10 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,return 0 ; } - rc =readpages_get_pages (mapping, page_list, rsize, &tmplist, + nr_pages =0 ; + err =readpages_get_pages (mapping, page_list, rsize, &tmplist, &nr_pages, &offset, &bytes); -if (rc) { +if (!nr_pages) {add_credits_and_wake_if (server, credits,0 );break ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 117/127 mm/swap_state: fix a data race in swapin_nr_pages
In reply to Sasha LevinFrom: Qian Cai <[email protected]>
[ Upstream commit d6c1f098f2a7ba62627c9bc17cda28f534ef9e4a ]
"prev_offset" is a static variable in swapin_nr_pages() that can be accessed concurrently with only mmap_sem held in read mode as noticed by KCSAN,
BUG: KCSAN: data-race in swap_cluster_readahead / swap_cluster_readahead
write to 0xffffffff92763830 of 8 bytes by task 14795 on cpu 17:
swap_cluster_readahead+0x2a6/0x5e0 swapin_readahead+0x92/0x8dc do_swap_page+0x49b/0xf20 __handle_mm_fault+0xcfb/0xd70 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x715 page_fault+0x34/0x40
1 lock held by (dnf)/14795:
#0: ffff897bd2e98858 (&mm->mmap_sem#2){++++}-{3:3}, at: do_page_fault+0x143/0x715 do_user_addr_fault at arch/x86/mm/fault.c:1405
(inlined by) do_page_fault at arch/x86/mm/fault.c:1535
irq event stamp: 83493 count_memcg_event_mm+0x1a6/0x270 count_memcg_event_mm+0x119/0x270 __do_softirq+0x365/0x589 irq_exit+0xa2/0xc0
read to 0xffffffff92763830 of 8 bytes by task 1 on cpu 22:
swap_cluster_readahead+0xfd/0x5e0 swapin_readahead+0x92/0x8dc do_swap_page+0x49b/0xf20 __handle_mm_fault+0xcfb/0xd70 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x715 page_fault+0x34/0x40
1 lock held by systemd/1:
#0: ffff897c38f14858 (&mm->mmap_sem#2){++++}-{3:3}, at: do_page_fault+0x143/0x715
irq event stamp: 43530289 count_memcg_event_mm+0x1a6/0x270 count_memcg_event_mm+0x119/0x270 __do_softirq+0x365/0x589 irq_exit+0xa2/0xc0
--- mm/swap_state.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
mm/swap_state.c +3 -2
@@ -524,10 +524,11 @@ static unsigned long swapin_nr_pages(unsigned long offset)return 1 ; hits =atomic_xchg (&swapin_readahead_hits,0 ); - pages =__swapin_nr_pages (prev_offset, offset, hits, max_pages, + pages =__swapin_nr_pages (READ_ONCE (prev_offset), offset, hits, + max_pages,atomic_read (&last_readahead_pages));if (!hits) - prev_offset = offset; +WRITE_ONCE (prev_offset, offset);atomic_set (&last_readahead_pages, pages);return pages;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 118/127 rapidio: avoid data race between file operation callbacks and mport_cdev_add().
In reply to Sasha LevinFrom: Madhuparna Bhowmik <[email protected]>
[ Upstream commit e1c3cdb26ab881b77486dc50370356a349077c74 ]
Fields of md(mport_dev) are set after cdev_device_add(). However, the file operation callbacks can be called after cdev_device_add() and therefore accesses to fields of md in the callbacks can race with the rest of the mport_cdev_add() function.
One such example is INIT_LIST_HEAD(&md->portwrites) in mport_cdev_add(), the list is initialised after cdev_device_add(). This can race with list_add_tail(&pw_filter->md_node,&md->portwrites) in rio_mport_add_pw_filter() which is called by unlocked_ioctl.
To avoid such data races use cdev_device_add() after initializing md.
Found by Linux Driver Verification project (linuxtesting.org).
--- drivers/rapidio/devices/rio_mport_cdev.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)
drivers/rapidio/devices/rio_mport_cdev.c +7 -7
@@ -2464,13 +2464,6 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport)cdev_init (&md->cdev, &mport_fops); md->cdev.owner =THIS_MODULE ; - ret =cdev_device_add (&md->cdev, &md->dev); -if (ret) { -rmcd_error ("Failed to register mport %d (err=%d)" , - mport->id, ret); - goto err_cdev; - } -INIT_LIST_HEAD (&md->doorbells);spin_lock_init (&md->db_lock);INIT_LIST_HEAD (&md->portwrites);
@@ -2490,6 +2483,13 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport)#else md->properties.transfer_mode |=RIO_TRANSFER_MODE_TRANSFER ;#endif + + ret =cdev_device_add (&md->cdev, &md->dev); +if (ret) { +rmcd_error ("Failed to register mport %d (err=%d)" , + mport->id, ret); + goto err_cdev; + } ret =rio_query_mport (mport, &attr);if (!ret) { md->properties.flags = attr.flags;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 116/127 ceph: fix potential race in ceph_check_caps
In reply to Sasha LevinFrom: Jeff Layton <[email protected]>
[ Upstream commit dc3da0461cc4b76f2d0c5b12247fcb3b520edbbf ]
Nothing ensures that session will still be valid by the time we dereference the pointer. Take and put a reference.
In principle, we should always be able to get a reference here, but throw a warning if that's ever not the case.
--- fs/ceph/caps.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)
fs/ceph/caps.c +13 -1
@@ -1906,12 +1906,24 @@ ack:if (mutex_trylock (&session->s_mutex) ==0 ) {dout ("inverting session/ino locks on %p\n" , session); + session =ceph_get_mds_session (session);spin_unlock (&ci->i_ceph_lock);if (took_snap_rwsem) {up_read (&mdsc->snap_rwsem); took_snap_rwsem =0 ; } -mutex_lock (&session->s_mutex); +if (session) { +mutex_lock (&session->s_mutex); +ceph_put_mds_session (session); + }else { +/* +* Because we take the reference while +* holding the i_ceph_lock, it should +* never be NULL. Throw a warning if it +* ever is. +*/ +WARN_ON_ONCE (true); + } goto retry; } }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 115/127 mtd: rawnand: omap_elm: Fix runtime PM imbalance on error
In reply to Sasha LevinFrom: Dinghao Liu <[email protected]>
[ Upstream commit 37f7212148cf1d796135cdf8d0c7fee13067674b ]
pm_runtime_get_sync() increments the runtime PM usage counter even when it returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.
--- drivers/mtd/nand/omap_elm.c | 1 + 1 file changed, 1 insertion(+)
drivers/mtd/nand/omap_elm.c +1 -0
@@ -421,6 +421,7 @@ static int elm_probe(struct platform_device *pdev)pm_runtime_enable (&pdev->dev);if (pm_runtime_get_sync (&pdev->dev) <0 ) { ret = -EINVAL ; +pm_runtime_put_sync (&pdev->dev);pm_runtime_disable (&pdev->dev);dev_err (&pdev->dev,"can't enable clock\n" );return ret;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 112/127 perf parse-events: Fix incorrect conversion of 'if () free()' to 'zfree()'
In reply to Sasha LevinFrom: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 7fcdccd4237724931d9773d1e3039bfe053a6f52 ]
When applying a patch by Ian I incorrectly converted to zfree() an expression that involved testing some other struct member, not the one being freed, which lead to bugs reproduceable by:
$ perf stat -e i/bs,tsc,L2/o sleep 1 WARNING: multiple event parsing errors Segmentation fault (core dumped) $
Fix it by restoring the test for pos->free_str before freeing pos->val.str, but continue using zfree(&pos->val.str) to set that member to NULL after freeing it.
--- tools/perf/util/parse-events.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
tools/perf/util/parse-events.c +2 -1
@@ -1258,7 +1258,8 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,list_for_each_entry_safe (pos, tmp, &config_terms, list) {list_del_init (&pos->list); -zfree (&pos->val.str); +if (pos->free_str) +zfree (&pos->val.str);free (pos); }return -EINVAL ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 108/127 printk: handle blank console arguments passed in.
In reply to Sasha LevinFrom: Shreyas Joshi <[email protected]>
[ Upstream commit 48021f98130880dd74286459a1ef48b5e9bc374f ]
If uboot passes a blank string to console_setup then it results in a trashed memory. Ultimately, the kernel crashes during freeing up the memory.
This fix checks if there is a blank parameter being passed to console_setup from uboot. In case it detects that the console parameter is blank then it doesn't setup the serial device and it gracefully exits.
--- kernel/printk/printk.c | 3 +++ 1 file changed, 3 insertions(+)
kernel/printk/printk.c +3 -0
@@ -2092,6 +2092,9 @@ static int __init console_setup(char *str)char *s, *options, *brl_options =NULL ;int idx; +if (str[0 ] ==0 ) +return 1 ; +if (_braille_console_setup (&str, &brl_options))return 1 ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 105/127 arm64/cpufeature: Drop TraceFilt feature exposure from ID_DFR0 register
In reply to Sasha LevinFrom: Anshuman Khandual <[email protected]>
[ Upstream commit 1ed1b90a0594c8c9d31e8bb8be25a2b37717dc9e ]
ID_DFR0 based TraceFilt feature should not be exposed to guests. Hence lets drop it.
--- arch/arm64/kernel/cpufeature.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm64/kernel/cpufeature.c +1 -1
@@ -272,7 +272,7 @@ static const struct arm64_ftr_bits ftr_id_pfr0[] = { };static const struct arm64_ftr_bits ftr_id_dfr0[] = { -ARM64_FTR_BITS (FTR_HIDDEN ,FTR_STRICT ,FTR_LOWER_SAFE ,28 ,4 ,0 ), +/* [31:28] TraceFilt */ S_ARM64_FTR_BITS (FTR_HIDDEN ,FTR_STRICT ,FTR_LOWER_SAFE ,24 ,4 ,0xf ),/* PerfMon */ ARM64_FTR_BITS (FTR_HIDDEN ,FTR_STRICT ,FTR_LOWER_SAFE ,20 ,4 ,0 ),ARM64_FTR_BITS (FTR_HIDDEN ,FTR_STRICT ,FTR_LOWER_SAFE ,16 ,4 ,0 ),
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 104/127 USB: EHCI: ehci-mv: fix less than zero comparison of an unsigned int
In reply to Sasha LevinFrom: Colin Ian King <[email protected]>
[ Upstream commit a7f40c233a6b0540d28743267560df9cfb571ca9 ]
The comparison of hcd->irq to less than zero for an error check will never be true because hcd->irq is an unsigned int. Fix this by assigning the int retval to the return of platform_get_irq and checking this for the -ve error condition and assigning hcd->irq to retval.
Addresses-Coverity: ("Unsigned compared against 0")
--- drivers/usb/host/ehci-mv.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
drivers/usb/host/ehci-mv.c +3 -4
@@ -196,11 +196,10 @@ static int mv_ehci_probe(struct platform_device *pdev) hcd->rsrc_len =resource_size (r); hcd->regs = ehci_mv->op_regs; - hcd->irq =platform_get_irq (pdev,0 ); -if (hcd->irq <0 ) { - retval = hcd->irq; + retval =platform_get_irq (pdev,0 ); +if (retval <0 ) goto err_disable_clk; - } + hcd->irq = retval; ehci =hcd_to_ehci (hcd); ehci->caps = (struct ehci_caps *) ehci_mv->cap_regs;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 103/127 fuse: don't check refcount after stealing page
In reply to Sasha LevinFrom: Miklos Szeredi <[email protected]>
[ Upstream commit 32f98877c57bee6bc27f443a96f49678a2cd6a50 ]
page_count() is unstable. Unless there has been an RCU grace period between when the page was removed from the page cache and now, a speculative reference may exist from the page cache.
--- fs/fuse/dev.c | 1 - 1 file changed, 1 deletion(-)
fs/fuse/dev.c +0 -1
@@ -824,7 +824,6 @@ static int fuse_check_page(struct page *page) { if (page_mapcount(page) || page->mapping != NULL || - page_count(page) != 1 || (page->flags & PAGE_FLAGS_CHECK_AT_PREP & ~(1 << PG_locked | 1 << PG_referenced |
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 100/127 tty: serial: samsung: Correct clock selection logic
In reply to Sasha LevinFrom: Jonathan Bakker <[email protected]>
[ Upstream commit 7d31676a8d91dd18e08853efd1cb26961a38c6a6 ]
Some variants of the samsung tty driver can pick which clock to use for their baud rate generation. In the DT conversion, a default clock was selected to be used if a specific one wasn't assigned and then a comparison of which clock rate worked better was done. Unfortunately, the comparison was implemented in such a way that only the default clock was ever actually compared. Fix this by iterating through all possible clocks, except when a specific clock has already been picked via clk_sel (which is only possible via board files).
--- drivers/tty/serial/samsung.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/tty/serial/samsung.c +4 -4
@@ -1165,14 +1165,14 @@ static unsigned int s3c24xx_serial_getclk(struct s3c24xx_uart_port *ourport,struct s3c24xx_uart_info *info = ourport->info;struct clk *clk;unsigned long rate; -unsigned int cnt, baud, quot, clk_sel, best_quot =0 ; +unsigned int cnt, baud, quot, best_quot =0 ;char clkname[MAX_CLK_NAME_LENGTH ];int calc_deviation, deviation = (1 <<30 ) -1 ; - clk_sel = (ourport->cfg->clk_sel) ? ourport->cfg->clk_sel : - ourport->info->def_clk_sel;for (cnt =0 ; cnt < info->num_clks; cnt++) { -if (!(clk_sel & (1 << cnt))) +/* Keep selected clock if provided */ +if (ourport->cfg->clk_sel && + !(ourport->cfg->clk_sel & (1 << cnt)))continue ;sprintf (clkname,"clk_uart_baud%d" , cnt);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 102/127 powerpc/traps: Make unrecoverable NMIs die instead of panic
In reply to Sasha LevinFrom: Nicholas Piggin <[email protected]>
[ Upstream commit 265d6e588d87194c2fe2d6c240247f0264e0c19b ]
System Reset and Machine Check interrupts that are not recoverable due to being nested or interrupting when RI=0 currently panic. This is not necessary, and can often just kill the current context and recover.
--- arch/powerpc/kernel/traps.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
arch/powerpc/kernel/traps.c +3 -3
@@ -357,11 +357,11 @@ out:#ifdef CONFIG_PPC_BOOK3S_64 BUG_ON (get_paca ()->in_nmi ==0 );if (get_paca ()->in_nmi >1 ) -nmi_panic (regs,"Unrecoverable nested System Reset" ); +die ("Unrecoverable nested System Reset" , regs,SIGABRT );#endif /* Must die if the interrupt is not recoverable */ if (!(regs->msr &MSR_RI )) -nmi_panic (regs,"Unrecoverable System Reset" ); +die ("Unrecoverable System Reset" , regs,SIGABRT );if (!nested)nmi_exit ();
@@ -701,7 +701,7 @@ void machine_check_exception(struct pt_regs *regs)/* Must die if the interrupt is not recoverable */ if (!(regs->msr &MSR_RI )) -nmi_panic (regs,"Unrecoverable Machine check" ); +die ("Unrecoverable Machine check" , regs,SIGBUS );return ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 99/127 USB: EHCI: ehci-mv: fix error handling in mv_ehci_probe()
In reply to Sasha LevinFrom: Tang Bin <[email protected]>
[ Upstream commit c856b4b0fdb5044bca4c0acf9a66f3b5cc01a37a ]
If the function platform_get_irq() failed, the negative value returned will not be detected here. So fix error handling in mv_ehci_probe(). And when get irq failed, the function platform_get_irq() logs an error message, so remove redundant message here.
--- drivers/usb/host/ehci-mv.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/usb/host/ehci-mv.c +2 -3
@@ -197,9 +197,8 @@ static int mv_ehci_probe(struct platform_device *pdev) hcd->regs = ehci_mv->op_regs; hcd->irq =platform_get_irq (pdev,0 ); -if (!hcd->irq) { -dev_err (&pdev->dev,"Cannot get irq." ); - retval = -ENODEV ; +if (hcd->irq <0 ) { + retval = hcd->irq; goto err_disable_clk; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 98/127 Bluetooth: Handle Inquiry Cancel error after Inquiry Complete
In reply to Sasha LevinFrom: Sonny Sasaka <[email protected]>
[ Upstream commit adf1d6926444029396861413aba8a0f2a805742a ]
After sending Inquiry Cancel command to the controller, it is possible that Inquiry Complete event comes before Inquiry Cancel command complete event. In this case the Inquiry Cancel command will have status of Command Disallowed since there is no Inquiry session to be cancelled. This case should not be treated as error, otherwise we can reach an inconsistent state.
Example of a btmon trace when this happened:
< HCI Command: Inquiry Cancel (0x01|0x0002) plen 0
Quoted 1 line
HCI Event: Inquiry Complete (
0x01) plen 1
Status: Success (0x00)
Quoted 1 line
HCI Event: Command Complete (
0x0e) plen 4
Inquiry Cancel (0x01|0x0002) ncmd 1
Status: Command Disallowed (0x0c)--- net/bluetooth/hci_event.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-)
net/bluetooth/hci_event.c +17 -2
@@ -41,12 +41,27 @@/* Handle HCI Event packets */ -static void hci_cc_inquiry_cancel (struct hci_dev *hdev,struct sk_buff *skb) +static void hci_cc_inquiry_cancel (struct hci_dev *hdev,struct sk_buff *skb, +u8 *new_status) {__u8 status = *((__u8 *) skb->data);BT_DBG ("%s status 0x%2.2x" , hdev->name, status); +/* It is possible that we receive Inquiry Complete event right +* before we receive Inquiry Cancel Command Complete event, in +* which case the latter event should have status of Command +* Disallowed (0x0c). This should not be treated as error, since +* we actually achieve what Inquiry Cancel wants to achieve, +* which is to end the last Inquiry session. +*/ +if (status ==0x0c && !test_bit (HCI_INQUIRY , &hdev->flags)) { +bt_dev_warn (hdev,"Ignoring error of Inquiry Cancel command" ); + status =0x00 ; + } + + *new_status = status; +if (status)return ;
@@ -2772,7 +2787,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,switch (*opcode) {case HCI_OP_INQUIRY_CANCEL : -hci_cc_inquiry_cancel (hdev, skb); +hci_cc_inquiry_cancel (hdev, skb, status);break ;case HCI_OP_PERIODIC_INQ :
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 94/127 atm: fix a memory leak of vcc->user_back
In reply to Sasha LevinFrom: Cong Wang <[email protected]>
[ Upstream commit 8d9f73c0ad2f20e9fed5380de0a3097825859d03 ]
In lec_arp_clear_vccs() only entry->vcc is freed, but vcc could be installed on entry->recv_vcc too in lec_vcc_added().
This fixes the following memory leak:
unreferenced object 0xffff8880d9266b90 (size 16):
comm "atm2", pid 425, jiffies 4294907980 (age 23.488s) hex dump (first 16 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 6b 6b 6b a5 ............kkk.
backtrace:
[<(____ptrval____)>] kmem_cache_alloc_trace+0x10e/0x151
[<(____ptrval____)>] lane_ioctl+0x4b3/0x569
[<(____ptrval____)>] do_vcc_ioctl+0x1ea/0x236
[<(____ptrval____)>] svc_ioctl+0x17d/0x198
[<(____ptrval____)>] sock_do_ioctl+0x47/0x12f
[<(____ptrval____)>] sock_ioctl+0x2f9/0x322
[<(____ptrval____)>] vfs_ioctl+0x1e/0x2b
[<(____ptrval____)>] ksys_ioctl+0x61/0x80
[<(____ptrval____)>] __x64_sys_ioctl+0x16/0x19
[<(____ptrval____)>] do_syscall_64+0x57/0x65
[<(____ptrval____)>] entry_SYSCALL_64_after_hwframe+0x49/0xb3--- net/atm/lec.c | 6 ++++++ 1 file changed, 6 insertions(+)
net/atm/lec.c +6 -0
@@ -1282,6 +1282,12 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry) entry->vcc =NULL ; }if (entry->recv_vcc) { +struct atm_vcc *vcc = entry->recv_vcc; +struct lec_vcc_priv *vpriv =LEC_VCC_PRIV (vcc); + +kfree (vpriv); + vcc->user_back =NULL ; + entry->recv_vcc->push = entry->old_recv_push;vcc_release_async (entry->recv_vcc, -EPIPE ); entry->recv_vcc =NULL ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 90/127 staging:r8188eu: avoid skb_clone for amsdu to msdu conversion
In reply to Sasha LevinFrom: Ivan Safonov <[email protected]>
[ Upstream commit 628cbd971a927abe6388d44320e351c337b331e4 ]
skb clones use same data buffer,
so tail of one skb is corrupted by beginning of next skb.
--- drivers/staging/rtl8188eu/core/rtw_recv.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-)
drivers/staging/rtl8188eu/core/rtw_recv.c +6 -13
@@ -1541,21 +1541,14 @@ static int amsdu_to_msdu(struct adapter *padapter, struct recv_frame *prframe)/* Allocate new skb for releasing to upper layer */ sub_skb =dev_alloc_skb (nSubframe_Length +12 ); -if (sub_skb) { -skb_reserve (sub_skb,12 ); -skb_put_data (sub_skb, pdata, nSubframe_Length); - }else { - sub_skb =skb_clone (prframe->pkt,GFP_ATOMIC ); -if (sub_skb) { - sub_skb->data = pdata; - sub_skb->len = nSubframe_Length; -skb_set_tail_pointer (sub_skb, nSubframe_Length); - }else { -DBG_88E ("skb_clone() Fail!!! , nr_subframes=%d\n" , nr_subframes); -break ; - } +if (!sub_skb) { +DBG_88E ("dev_alloc_skb() Fail!!! , nr_subframes=%d\n" , nr_subframes); +break ; } +skb_reserve (sub_skb,12 ); +skb_put_data (sub_skb, pdata, nSubframe_Length); + subframes[nr_subframes++] = sub_skb;if (nr_subframes >=MAX_SUBFRAME_COUNT ) {
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 91/127 sparc64: vcc: Fix error return code in vcc_probe()
In reply to Sasha LevinFrom: Wei Yongjun <[email protected]>
[ Upstream commit ff62255a2a5c1228a28f2bb063646f948115a309 ]
Fix to return negative error code -ENOMEM from the error handling case instead of 0, as done elsewhere in this function.
--- drivers/tty/vcc.c | 1 + 1 file changed, 1 insertion(+)
drivers/tty/vcc.c +1 -0
@@ -612,6 +612,7 @@ static int vcc_probe(struct vio_dev *vdev, const struct vio_device_id *id) port->index =vcc_table_add (port);if (port->index ==-1 ) {pr_err ("VCC: no more TTY indices left for allocation\n" ); + rv = -ENOMEM ; goto free_ldc; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 92/127 arm64: cpufeature: Relax checks for AArch32 support at EL[0-2]
In reply to Sasha LevinFrom: Will Deacon <[email protected]>
[ Upstream commit 98448cdfe7060dd5491bfbd3f7214ffe1395d58e ]
We don't need to be quite as strict about mismatched AArch32 support, which is good because the friendly hardware folks have been busy mismatching this to their hearts' content.
* We don't care about EL2 or EL3 (there are silly comments concerning the latter, so remove those)
* EL1 support is gated by the ARM64_HAS_32BIT_EL1 capability and handled gracefully when a mismatch occurs
* EL0 support is gated by the ARM64_HAS_32BIT_EL0 capability and handled gracefully when a mismatch occurs
Relax the AArch32 checks to FTR_NONSTRICT.
--- arch/arm64/kernel/cpufeature.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-)
arch/arm64/kernel/cpufeature.c +3 -7
@@ -136,11 +136,10 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {ARM64_FTR_BITS (FTR_HIDDEN ,FTR_STRICT ,FTR_LOWER_SAFE ,ID_AA64PFR0_GIC_SHIFT ,4 ,0 ),S_ARM64_FTR_BITS (FTR_VISIBLE ,FTR_STRICT ,FTR_LOWER_SAFE ,ID_AA64PFR0_ASIMD_SHIFT ,4 ,ID_AA64PFR0_ASIMD_NI ),S_ARM64_FTR_BITS (FTR_VISIBLE ,FTR_STRICT ,FTR_LOWER_SAFE ,ID_AA64PFR0_FP_SHIFT ,4 ,ID_AA64PFR0_FP_NI ), -/* Linux doesn't care about the EL3 */ ARM64_FTR_BITS (FTR_HIDDEN ,FTR_NONSTRICT ,FTR_LOWER_SAFE ,ID_AA64PFR0_EL3_SHIFT ,4 ,0 ), -ARM64_FTR_BITS (FTR_HIDDEN ,FTR_STRICT ,FTR_LOWER_SAFE ,ID_AA64PFR0_EL2_SHIFT ,4 ,0 ), -ARM64_FTR_BITS (FTR_HIDDEN ,FTR_STRICT ,FTR_LOWER_SAFE ,ID_AA64PFR0_EL1_SHIFT ,4 ,ID_AA64PFR0_EL1_64BIT_ONLY ), -ARM64_FTR_BITS (FTR_HIDDEN ,FTR_STRICT ,FTR_LOWER_SAFE ,ID_AA64PFR0_EL0_SHIFT ,4 ,ID_AA64PFR0_EL0_64BIT_ONLY ), +ARM64_FTR_BITS (FTR_HIDDEN ,FTR_NONSTRICT ,FTR_LOWER_SAFE ,ID_AA64PFR0_EL2_SHIFT ,4 ,0 ), +ARM64_FTR_BITS (FTR_HIDDEN ,FTR_NONSTRICT ,FTR_LOWER_SAFE ,ID_AA64PFR0_EL1_SHIFT ,4 ,ID_AA64PFR0_EL1_64BIT_ONLY ), +ARM64_FTR_BITS (FTR_HIDDEN ,FTR_NONSTRICT ,FTR_LOWER_SAFE ,ID_AA64PFR0_EL0_SHIFT ,4 ,ID_AA64PFR0_EL0_64BIT_ONLY ), ARM64_FTR_END, };
@@ -627,9 +626,6 @@ void update_cpu_features(int cpu, taint |=check_update_ftr_reg (SYS_ID_AA64MMFR2_EL1 , cpu, info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2); -/* -* EL3 is not our concern. -*/ taint |=check_update_ftr_reg (SYS_ID_AA64PFR0_EL1 , cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu,
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 93/127 dt-bindings: sound: wm8994: Correct required supplies based on actual implementaion
In reply to Sasha LevinFrom: Krzysztof Kozlowski <[email protected]>
[ Upstream commit 8c149b7d75e53be47648742f40fc90d9fc6fa63a ]
The required supplies in bindings were actually not matching implementation making the bindings incorrect and misleading. The Linux kernel driver requires all supplies to be present. Also for wlf,wm8994 uses just DBVDD-supply instead of DBVDDn-supply (n: <1,3>).
--- .../devicetree/bindings/sound/wm8994.txt | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)
Documentation/devicetree/bindings/sound/wm8994.txt +12 -6
@@ -14,9 +14,15 @@ Required properties: - #gpio-cells : Must be 2. The first cell is the pin number and the second cell is used to specify optional parameters (currently unused). - - AVDD2-supply, DBVDD1-supply, DBVDD2-supply, DBVDD3-supply, CPVDD-supply, - SPKVDD1-supply, SPKVDD2-supply : power supplies for the device, as covered - in Documentation/devicetree/bindings/regulator/regulator.txt + - power supplies for the device, as covered in + Documentation/devicetree/bindings/regulator/regulator.txt, depending + on compatible: + - for wlf,wm1811 and wlf,wm8958: + AVDD1-supply, AVDD2-supply, DBVDD1-supply, DBVDD2-supply, DBVDD3-supply, + DCVDD-supply, CPVDD-supply, SPKVDD1-supply, SPKVDD2-supply + - for wlf,wm8994: + AVDD1-supply, AVDD2-supply, DBVDD-supply, DCVDD-supply, CPVDD-supply, + SPKVDD1-supply, SPKVDD2-supply Optional properties:
@@ -68,11 +74,11 @@ codec: wm8994@1a { lineout1-se; + AVDD1-supply = <®ulator>; AVDD2-supply = <®ulator>; CPVDD-supply = <®ulator>; - DBVDD1-supply = <®ulator>; - DBVDD2-supply = <®ulator>; - DBVDD3-supply = <®ulator>; + DBVDD-supply = <®ulator>; + DCVDD-supply = <®ulator>; SPKVDD1-supply = <®ulator>; SPKVDD2-supply = <®ulator>; };
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 88/127 bdev: Reduce time holding bd_mutex in sync in blkdev_close()
In reply to Sasha LevinFrom: Douglas Anderson <[email protected]>
[ Upstream commit b849dd84b6ccfe32622988b79b7b073861fcf9f7 ]
While trying to "dd" to the block device for a USB stick, I encountered a hung task warning (blocked for > 120 seconds). I managed to come up with an easy way to reproduce this on my system (where /dev/sdb is the block device for my USB stick) with:
while true; do dd if=/dev/zero of=/dev/sdb bs=4M; done
With my reproduction here are the relevant bits from the hung task detector:
INFO: task udevd:294 blocked for more than 122 seconds. ... udevd D 0 294 1 0x00400008 Call trace: ... mutex_lock_nested+0x40/0x50 __blkdev_get+0x7c/0x3d4 blkdev_get+0x118/0x138 blkdev_open+0x94/0xa8 do_dentry_open+0x268/0x3a0 vfs_open+0x34/0x40 path_openat+0x39c/0xdf4 do_filp_open+0x90/0x10c do_sys_open+0x150/0x3c8 ...
...
Showing all locks held in the system:
...
1 lock held by dd/2798:
#0: ffffff814ac1a3b8 (&bdev->bd_mutex){+.+.}, at: __blkdev_put+0x50/0x204
...
dd D 0 2798 2764 0x00400208
Call trace:
...
schedule+0x8c/0xbc
io_schedule+0x1c/0x40
wait_on_page_bit_common+0x238/0x338
__lock_page+0x5c/0x68
write_cache_pages+0x194/0x500
generic_writepages+0x64/0xa4
blkdev_writepages+0x24/0x30
do_writepages+0x48/0xa8
__filemap_fdatawrite_range+0xac/0xd8
filemap_write_and_wait+0x30/0x84
__blkdev_put+0x88/0x204
blkdev_put+0xc4/0xe4
blkdev_close+0x28/0x38
__fput+0xe0/0x238
____fput+0x1c/0x28
task_work_run+0xb0/0xe4
do_notify_resume+0xfc0/0x14bc
work_pending+0x8/0x14The problem appears related to the fact that my USB disk is terribly slow and that I have a lot of RAM in my system to cache things. Specifically my writes seem to be happening at ~15 MB/s and I've got ~4 GB of RAM in my system that can be used for buffering. To write 4 GB of buffer to disk thus takes ~4000 MB / ~15 MB/s = ~267 seconds.
The 267 second number is a problem because in __blkdev_put() we call sync_blockdev() while holding the bd_mutex. Any other callers who want the bd_mutex will be blocked for the whole time.
The problem is made worse because I believe blkdev_put() specifically tells other tasks (namely udev) to go try to access the device at right around the same time we're going to hold the mutex for a long time.
Putting some traces around this (after disabling the hung task detector), I could confirm:
dd: 437.608600: __blkdev_put() right before sync_blockdev() for sdb
udevd: 437.623901: blkdev_open() right before blkdev_get() for sdb
dd: 661.468451: __blkdev_put() right after sync_blockdev() for sdb
udevd: 663.820426: blkdev_open() right after blkdev_get() for sdb
A simple fix for this is to realize that sync_blockdev() works fine if you're not holding the mutex. Also, it's not the end of the world if you sync a little early (though it can have performance impacts). Thus we can make a guess that we're going to need to do the sync and then do it without holding the mutex. We still do one last sync with the mutex but it should be much, much faster.
With this, my hung task warnings for my test case are gone.
--- fs/block_dev.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
fs/block_dev.c +10 -0
@@ -1777,6 +1777,16 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)struct gendisk *disk = bdev->bd_disk;struct block_device *victim =NULL ; +/* +* Sync early if it looks like we're the last one. If someone else +* opens the block device between now and the decrement of bd_openers +* then we did a sync that we didn't need to, but that's not the end +* of the world and we want to avoid long (could be several minute) +* syncs while holding the mutex. +*/ +if (bdev->bd_openers ==1 ) +sync_blockdev (bdev); +mutex_lock_nested (&bdev->bd_mutex, for_part);if (for_part) bdev->bd_part_count--;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 89/127 drivers: char: tlclk.c: Avoid data race between init and interrupt handler
In reply to Sasha LevinFrom: Madhuparna Bhowmik <[email protected]>
[ Upstream commit 44b8fb6eaa7c3fb770bf1e37619cdb3902cca1fc ]
After registering character device the file operation callbacks can be called. The open callback registers interrupt handler. Therefore interrupt handler can execute in parallel with rest of the init function. To avoid such data race initialize telclk_interrupt variable and struct alarm_events before registering character device.
Found by Linux Driver Verification project (linuxtesting.org).
--- drivers/char/tlclk.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-)
drivers/char/tlclk.c +10 -7
@@ -777,17 +777,21 @@ static int __init tlclk_init(void) {int ret; + telclk_interrupt = (inb (TLCLK_REG7 ) &0x0f ); + + alarm_events =kzalloc (sizeof (struct tlclk_alarms ),GFP_KERNEL ); +if (!alarm_events) { + ret = -ENOMEM ; + goto out1; + } + ret =register_chrdev (tlclk_major,"telco_clock" , &tlclk_fops);if (ret <0 ) {printk (KERN_ERR "tlclk: can't get major %d.\n" , tlclk_major); +kfree (alarm_events);return ret; } tlclk_major = ret; - alarm_events =kzalloc (sizeof (struct tlclk_alarms ),GFP_KERNEL ); -if (!alarm_events) { - ret = -ENOMEM ; - goto out1; - }/* Read telecom clock IRQ number (Set by BIOS) */ if (!request_region (TLCLK_BASE ,8 ,"telco_clock" )) {
@@ -796,7 +800,6 @@ static int __init tlclk_init(void) ret = -EBUSY ; goto out2; } - telclk_interrupt = (inb (TLCLK_REG7 ) &0x0f );if (0x0F == telclk_interrupt ) {/* not MCPBL0010 ? */ printk(KERN_ERR "telclk_interrupt = 0x%x non-mcpbl0010 hw.\n",
@@ -837,8 +840,8 @@ out3:release_region (TLCLK_BASE ,8 ); out2:kfree (alarm_events); -out1:unregister_chrdev (tlclk_major,"telco_clock" ); +out1:return ret; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 11/127 mtd: cfi_cmdset_0002: don't free cfi->cfiq in error path of cfi_amdstd_setup()
In reply to Sasha LevinFrom: Hou Tao <[email protected]>
[ Upstream commit 03976af89e3bd9489d542582a325892e6a8cacc0 ]
Else there may be a double-free problem, because cfi->cfiq will be freed by mtd_do_chip_probe() if both the two invocations of check_cmd_set() return failure.
--- drivers/mtd/chips/cfi_cmdset_0002.c | 1 - 1 file changed, 1 deletion(-)
drivers/mtd/chips/cfi_cmdset_0002.c +0 -1
@@ -726,7 +726,6 @@ static struct mtd_info *cfi_amdstd_setup(struct mtd_info *mtd)kfree (mtd->eraseregions);kfree (mtd);kfree (cfi->cmdset_priv); -kfree (cfi->cfiq);return NULL ; }
Signature · 6 lines
2.25.1 ______________________________________________________ Linux MTD discussion mailing list http://lists.infradead.org/mailman/listinfo/linux-mtd/
Sasha Levin
maintainerPATCH 85/127 scsi: qedi: Fix termination timeouts in session logout
In reply to Sasha LevinFrom: Nilesh Javali <[email protected]>
[ Upstream commit b9b97e6903032ec56e6dcbe137a9819b74a17fea ]
The destroy connection ramrod timed out during session logout. Fix the wait delay for graceful vs abortive termination as per the FW requirements.
--- drivers/scsi/qedi/qedi_iscsi.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/scsi/qedi/qedi_iscsi.c +3 -0
@@ -1072,6 +1072,9 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep)break ; } +if (!abrt_conn) + wait_delay += qedi->pf_params.iscsi_pf_params.two_msl_timer; + qedi_ep->state =EP_STATE_DISCONN_START ; ret = qedi_ops->destroy_conn (qedi->cdev, qedi_ep->handle, abrt_conn);if (ret) {
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 80/127 NFS: Fix races nfs_page_group_destroy() vs nfs_destroy_unlinked_subrequests()
In reply to Sasha LevinFrom: Trond Myklebust <[email protected]>
[ Upstream commit 08ca8b21f760c0ed5034a5c122092eec22ccf8f4 ]
When a subrequest is being detached from the subgroup, we want to ensure that it is not holding the group lock, or in the process of waiting for the group lock.
--- fs/nfs/pagelist.c | 67 +++++++++++++++++++++++++++------------- fs/nfs/write.c | 10 ++++-- include/linux/nfs_page.h | 2 ++ 3 files changed, 55 insertions(+), 24 deletions(-)
fs/nfs/pagelist.c +45 -22
@@ -132,47 +132,70 @@ nfs_async_iocounter_wait(struct rpc_task *task, struct nfs_lock_context *l_ctx)EXPORT_SYMBOL_GPL (nfs_async_iocounter_wait);/* -* nfs_page_group_lock - lock the head of the page group -* @req - request in group that is to be locked +* nfs_page_set_headlock - set the request PG_HEADLOCK +* @req: request that is to be locked * -* this lock must be held when traversing or modifying the page -* group list +* this lock must be held when modifying req->wb_head * * return 0 on success, < 0 on error */ int -nfs_page_group_lock (struct nfs_page *req) +nfs_page_set_headlock (struct nfs_page *req) { -struct nfs_page *head = req->wb_head; - -WARN_ON_ONCE (head != head->wb_head); - -if (!test_and_set_bit (PG_HEADLOCK , &head->wb_flags)) +if (!test_and_set_bit (PG_HEADLOCK , &req->wb_flags))return 0 ; -set_bit (PG_CONTENDED1 , &head->wb_flags); +set_bit (PG_CONTENDED1 , &req->wb_flags);smp_mb__after_atomic (); -return wait_on_bit_lock (&head->wb_flags,PG_HEADLOCK , +return wait_on_bit_lock (&req->wb_flags,PG_HEADLOCK ,TASK_UNINTERRUPTIBLE ); }/* -* nfs_page_group_unlock - unlock the head of the page group -* @req - request in group that is to be unlocked +* nfs_page_clear_headlock - clear the request PG_HEADLOCK +* @req: request that is to be locked */ void -nfs_page_group_unlock (struct nfs_page *req) +nfs_page_clear_headlock (struct nfs_page *req) { -struct nfs_page *head = req->wb_head; - -WARN_ON_ONCE (head != head->wb_head); -smp_mb__before_atomic (); -clear_bit (PG_HEADLOCK , &head->wb_flags); +clear_bit (PG_HEADLOCK , &req->wb_flags);smp_mb__after_atomic (); -if (!test_bit (PG_CONTENDED1 , &head->wb_flags)) +if (!test_bit (PG_CONTENDED1 , &req->wb_flags))return ; -wake_up_bit (&head->wb_flags,PG_HEADLOCK ); +wake_up_bit (&req->wb_flags,PG_HEADLOCK ); +} + +/* +* nfs_page_group_lock - lock the head of the page group +* @req: request in group that is to be locked +* +* this lock must be held when traversing or modifying the page +* group list +* +* return 0 on success, < 0 on error +*/ +int +nfs_page_group_lock (struct nfs_page *req) +{ +int ret; + + ret =nfs_page_set_headlock (req); +if (ret || req->wb_head == req) +return ret; +return nfs_page_set_headlock (req->wb_head); +} + +/* +* nfs_page_group_unlock - unlock the head of the page group +* @req: request in group that is to be unlocked +*/ +void +nfs_page_group_unlock (struct nfs_page *req) +{ +if (req != req->wb_head) +nfs_page_clear_headlock (req->wb_head); +nfs_page_clear_headlock (req); }/*
fs/nfs/write.c +8 -2
@@ -406,22 +406,28 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, destroy_list = (subreq->wb_this_page == old_head) ?NULL : subreq->wb_this_page; +/* Note: lock subreq in order to change subreq->wb_head */ +nfs_page_set_headlock (subreq);WARN_ON_ONCE (old_head != subreq->wb_head);/* make sure old group is not used */ subreq->wb_this_page = subreq; + subreq->wb_head = subreq;clear_bit (PG_REMOVE , &subreq->wb_flags);/* Note: races with nfs_page_group_destroy() */ if (!kref_read (&subreq->wb_kref)) {/* Check if we raced with nfs_page_group_destroy() */ -if (test_and_clear_bit (PG_TEARDOWN , &subreq->wb_flags)) +if (test_and_clear_bit (PG_TEARDOWN , &subreq->wb_flags)) { +nfs_page_clear_headlock (subreq);nfs_free_request (subreq); + }else +nfs_page_clear_headlock (subreq);continue ; } +nfs_page_clear_headlock (subreq); - subreq->wb_head = subreq;nfs_release_request (old_head);if (test_and_clear_bit (PG_INODE_REF , &subreq->wb_flags)) {
include/linux/nfs_page.h +2 -0
@@ -142,6 +142,8 @@ extern void nfs_unlock_and_release_request(struct nfs_page *);extern int nfs_page_group_lock (struct nfs_page *);extern void nfs_page_group_unlock (struct nfs_page *);extern bool nfs_page_group_sync_on_bit (struct nfs_page *,unsigned int ); +extern int nfs_page_set_headlock (struct nfs_page *req); +extern void nfs_page_clear_headlock (struct nfs_page *req);extern bool nfs_async_iocounter_wait (struct rpc_task *,struct nfs_lock_context *);/*
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 78/127 ubifs: Fix out-of-bounds memory access caused by abnormal value of node_len
In reply to Sasha LevinFrom: Liu Song <[email protected]>
[ Upstream commit acc5af3efa303d5f36cc8c0f61716161f6ca1384 ]
In “ubifs_check_node”, when the value of "node_len" is abnormal, the code will goto label of "out_len" for execution. Then, in the following "ubifs_dump_node", if inode type is "UBIFS_DATA_NODE", in "print_hex_dump", an out-of-bounds access may occur due to the wrong "ch->len".
Therefore, when the value of "node_len" is abnormal, data length should to be adjusted to a reasonable safe range. At this time, structured data is not credible, so dump the corrupted data directly for analysis.
--- fs/ubifs/io.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)
fs/ubifs/io.c +14 -2
@@ -237,7 +237,7 @@ int ubifs_is_mapped(const struct ubifs_info *c, int lnum)int ubifs_check_node (const struct ubifs_info *c,const void *buf,int lnum,int offs,int quiet,int must_chk_crc) { -int err = -EINVAL , type, node_len; +int err = -EINVAL , type, node_len, dump_node =1 ;uint32_t crc, node_crc, magic;const struct ubifs_ch *ch = buf;
@@ -290,10 +290,22 @@ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, out_len:if (!quiet)ubifs_err (c,"bad node length %d" , node_len); +if (type ==UBIFS_DATA_NODE && node_len >UBIFS_DATA_NODE_SZ ) + dump_node =0 ; out:if (!quiet) {ubifs_err (c,"bad node at LEB %d:%d" , lnum, offs); -ubifs_dump_node (c, buf); +if (dump_node) { +ubifs_dump_node (c, buf); + }else { +int safe_len =min3 (node_len, c->leb_size - offs, + (int )UBIFS_MAX_DATA_NODE_SZ ); +pr_err ("\tprevent out-of-bounds memory access\n" ); +pr_err ("\ttruncated data node length %d\n" , safe_len); +pr_err ("\tcorrupted data node:\n" ); +print_hex_dump (KERN_ERR ,"\t" ,DUMP_PREFIX_OFFSET ,32 ,1 , + buf, safe_len,0 ); + }dump_stack (); }return err;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 76/127 SUNRPC: Fix a potential buffer overflow in 'svc_print_xprts()'
In reply to Sasha LevinFrom: Christophe JAILLET <[email protected]>
[ Upstream commit b25b60d7bfb02a74bc3c2d998e09aab159df8059 ]
'maxlen' is the total size of the destination buffer. There is only one caller and this value is 256.
When we compute the size already used and what we would like to add in the buffer, the trailling NULL character is not taken into account. However, this trailling character will be added by the 'strcat' once we have checked that we have enough place.
So, there is a off-by-one issue and 1 byte of the stack could be erroneously overwridden.
Take into account the trailling NULL, when checking if there is enough place in the destination buffer.
While at it, also replace a 'sprintf' by a safer 'snprintf', check for output truncation and avoid a superfluous 'strlen'.
[ cel: very minor fix to documenting comment
--- net/sunrpc/svc_xprt.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-)
net/sunrpc/svc_xprt.c +14 -5
@@ -103,8 +103,17 @@ void svc_unreg_xprt_class(struct svc_xprt_class *xcl) }EXPORT_SYMBOL_GPL (svc_unreg_xprt_class); -/* -* Format the transport list for printing +/** +* svc_print_xprts - Format the transport list for printing +* @buf: target buffer for formatted address +* @maxlen: length of target buffer +* +* Fills in @buf with a string containing a list of transport names, each name +* terminated with '\n'. If the buffer is too small, some entries may be +* missing, but it is guaranteed that all lines in the output buffer are +* complete. +* +* Returns positive length of the filled-in string. */ int svc_print_xprts (char *buf,int maxlen) {
@@ -117,9 +126,9 @@ int svc_print_xprts(char *buf, int maxlen)list_for_each_entry (xcl, &svc_xprt_class_list, xcl_list) {int slen; -sprintf (tmpstr,"%s %d\n" , xcl->xcl_name, xcl->xcl_max_payload); - slen =strlen (tmpstr); -if (len + slen > maxlen) + slen =snprintf (tmpstr,sizeof (tmpstr),"%s %d\n" , + xcl->xcl_name, xcl->xcl_max_payload); +if (slen >=sizeof (tmpstr) || len + slen >= maxlen)break ; len += slen;strcat (buf, tmpstr);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 75/127 RDMA/rxe: Set sys_image_guid to be aligned with HW IB devices
In reply to Sasha LevinFrom: Zhu Yanjun <[email protected]>
[ Upstream commit d0ca2c35dd15a3d989955caec02beea02f735ee6 ]
The RXE driver doesn't set sys_image_guid and user space applications see zeros. This causes to pyverbs tests to fail with the following traceback, because the IBTA spec requires to have valid sys_image_guid.
Traceback (most recent call last):
File "./tests/test_device.py", line 51, in test_query_device
self.verify_device_attr(attr)
File "./tests/test_device.py", line 74, in verify_device_attr
assert attr.sys_image_guid != 0
In order to fix it, set sys_image_guid to be equal to node_guid.
Before:
5: rxe0: ... node_guid 5054:00ff:feaa:5363 sys_image_guid 0000:0000:0000:0000
After:
5: rxe0: ... node_guid 5054:00ff:feaa:5363 sys_image_guid 5054:00ff:feaa:5363
--- drivers/infiniband/sw/rxe/rxe.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/infiniband/sw/rxe/rxe.c +2 -0
@@ -126,6 +126,8 @@ static int rxe_init_device_param(struct rxe_dev *rxe) rxe->attr.max_fast_reg_page_list_len =RXE_MAX_FMR_PAGE_LIST_LEN ; rxe->attr.max_pkeys =RXE_MAX_PKEYS ; rxe->attr.local_ca_ack_delay =RXE_LOCAL_CA_ACK_DELAY ; +addrconf_addr_eui48 ((unsigned char *)&rxe->attr.sys_image_guid, + rxe->ndev->dev_addr); rxe->max_ucontext =RXE_MAX_UCONTEXT ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 73/127 cpufreq: powernv: Fix frame-size-overflow in powernv_cpufreq_work_fn
In reply to Sasha LevinFrom: Pratik Rajesh Sampat <[email protected]>
[ Upstream commit d95fe371ecd28901f11256c610b988ed44e36ee2 ]
The patch avoids allocating cpufreq_policy on stack hence fixing frame size overflow in 'powernv_cpufreq_work_fn'
--- drivers/cpufreq/powernv-cpufreq.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-)
drivers/cpufreq/powernv-cpufreq.c +8 -5
@@ -864,6 +864,7 @@ static struct notifier_block powernv_cpufreq_reboot_nb = {void powernv_cpufreq_work_fn (struct work_struct *work) { struct chip *chip = container_of(work, struct chip, throttle); +struct cpufreq_policy *policy;unsigned int cpu;cpumask_t mask;
@@ -878,12 +879,14 @@ void powernv_cpufreq_work_fn(struct work_struct *work) chip->restore = false;for_each_cpu (cpu, &mask) {int index; -struct cpufreq_policy policy; -cpufreq_get_policy (&policy, cpu); - index =cpufreq_table_find_index_c (&policy, policy.cur); -powernv_cpufreq_target_index (&policy, index); -cpumask_andnot (&mask, &mask, policy.cpus); + policy =cpufreq_cpu_get (cpu); +if (!policy) +continue ; + index =cpufreq_table_find_index_c (policy, policy->cur); +powernv_cpufreq_target_index (policy, index); +cpumask_andnot (&mask, &mask, policy->cpus); +cpufreq_cpu_put (policy); } out:put_online_cpus ();
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 74/127 tools: gpio-hammer: Avoid potential overflow in main
In reply to Sasha LevinFrom: Gabriel Ravier <[email protected]>
[ Upstream commit d1ee7e1f5c9191afb69ce46cc7752e4257340a31 ]
If '-o' was used more than 64 times in a single invocation of gpio-hammer, this could lead to an overflow of the 'lines' array. This commit fixes this by avoiding the overflow and giving a proper diagnostic back to the user
--- tools/gpio/gpio-hammer.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-)
tools/gpio/gpio-hammer.c +16 -1
@@ -138,7 +138,14 @@ int main(int argc, char **argv) device_name = optarg;break ;case 'o' : - lines[i] =strtoul (optarg,NULL ,10 ); +/* +* Avoid overflow. Do not immediately error, we want to +* be able to accurately report on the amount of times +* '-o' was given to give an accurate error message +*/ +if (i <GPIOHANDLES_MAX ) + lines[i] =strtoul (optarg,NULL ,10 ); + i++;break ;case '?' :
@@ -146,6 +153,14 @@ int main(int argc, char **argv)return -1 ; } } + +if (i >=GPIOHANDLES_MAX ) { +fprintf (stderr, +"Only %d occurences of '-o' are allowed, %d were found\n" , +GPIOHANDLES_MAX , i +1 ); +return -1 ; + } + nlines = i;if (!device_name || !nlines) {
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 68/127 tracing: Use address-of operator on section symbols
In reply to Sasha LevinFrom: Nathan Chancellor <[email protected]>
[ Upstream commit bf2cbe044da275021b2de5917240411a19e5c50d ]
Clang warns:
../kernel/trace/trace.c:9335:33: warning: array comparison always evaluates to true [-Wtautological-compare]
if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt)
^1 warning generated.
These are not true arrays, they are linker defined symbols, which are just addresses. Using the address of operator silences the warning and does not change the runtime result of the check (tested with some print statements compiled in with clang + ld.lld and gcc + ld.bfd in QEMU).
--- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/trace/trace.c +1 -1
@@ -8346,7 +8346,7 @@ __init static int tracer_alloc_buffers(void) goto out_free_buffer_mask;/* Only allocate trace_printk buffers if a trace_printk exists */ -if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt) +if (&__stop___trace_bprintk_fmt != &__start___trace_bprintk_fmt)/* Must be called before global_trace.buffer is allocated */ trace_printk_init_buffers ();
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 67/127 rtc: ds1374: fix possible race condition
In reply to Sasha LevinFrom: Alexandre Belloni <[email protected]>
[ Upstream commit c11af8131a4e7ba1960faed731ee7e84c2c13c94 ]
The RTC IRQ is requested before the struct rtc_device is allocated, this may lead to a NULL pointer dereference in the IRQ handler.
To fix this issue, allocating the rtc_device struct before requesting the RTC IRQ using devm_rtc_allocate_device, and use rtc_register_device to register the RTC device.
--- drivers/rtc/rtc-ds1374.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)
drivers/rtc/rtc-ds1374.c +9 -6
@@ -620,6 +620,10 @@ static int ds1374_probe(struct i2c_client *client,if (!ds1374)return -ENOMEM ; + ds1374->rtc =devm_rtc_allocate_device (&client->dev); +if (IS_ERR (ds1374->rtc)) +return PTR_ERR (ds1374->rtc); + ds1374->client = client;i2c_set_clientdata (client, ds1374);
@@ -641,12 +645,11 @@ static int ds1374_probe(struct i2c_client *client,device_set_wakeup_capable (&client->dev,1 ); } - ds1374->rtc =devm_rtc_device_register (&client->dev, client->name, - &ds1374_rtc_ops,THIS_MODULE ); -if (IS_ERR (ds1374->rtc)) { -dev_err (&client->dev,"unable to register the class device\n" ); -return PTR_ERR (ds1374->rtc); - } + ds1374->rtc->ops = &ds1374_rtc_ops; + + ret =rtc_register_device (ds1374->rtc); +if (ret) +return ret;#ifdef CONFIG_RTC_DRV_DS1374_WDT save_client = client;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 66/127 tpm: ibmvtpm: Wait for buffer to be set before proceeding
In reply to Sasha LevinFrom: Stefan Berger <[email protected]>
[ Upstream commit d8d74ea3c00214aee1e1826ca18e77944812b9b4 ]
Synchronize with the results from the CRQs before continuing with the initialization. This avoids trying to send TPM commands while the rtce buffer has not been allocated, yet.
This patch fixes an existing race condition that may occurr if the hypervisor does not quickly respond to the VTPM_GET_RTCE_BUFFER_SIZE request sent during initialization and therefore the ibmvtpm->rtce_buf has not been allocated at the time the first TPM command is sent.
--- drivers/char/tpm/tpm_ibmvtpm.c | 9 +++++++++ drivers/char/tpm/tpm_ibmvtpm.h | 1 + 2 files changed, 10 insertions(+)
drivers/char/tpm/tpm_ibmvtpm.c +9 -0
@@ -588,6 +588,7 @@ static irqreturn_t ibmvtpm_interrupt(int irq, void *vtpm_instance)*/ while ((crq =ibmvtpm_crq_get_next (ibmvtpm)) !=NULL ) {ibmvtpm_crq_process (crq, ibmvtpm); +wake_up_interruptible (&ibmvtpm->crq_queue.wq); crq->valid =0 ;smp_wmb (); }
@@ -635,6 +636,7 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev, } crq_q->num_entry =CRQ_RES_BUF_SIZE /sizeof (*crq_q->crq_addr); +init_waitqueue_head (&crq_q->wq); ibmvtpm->crq_dma_handle =dma_map_single (dev, crq_q->crq_addr,CRQ_RES_BUF_SIZE ,DMA_BIDIRECTIONAL );
@@ -687,6 +689,13 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev,if (rc) goto init_irq_cleanup; +if (!wait_event_timeout (ibmvtpm->crq_queue.wq, + ibmvtpm->rtce_buf !=NULL , +HZ )) { +dev_err (dev,"CRQ response timed out\n" ); + goto init_irq_cleanup; + } +return tpm_chip_register (chip); init_irq_cleanup: do {
drivers/char/tpm/tpm_ibmvtpm.h +1 -0
@@ -31,6 +31,7 @@ struct ibmvtpm_crq_queue {struct ibmvtpm_crq *crq_addr;u32 index;u32 num_entry; +wait_queue_head_t wq; };struct ibmvtpm_dev {
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 65/127 xfs: don't ever return a stale pointer from __xfs_dir3_free_read
In reply to Sasha LevinFrom: "Darrick J. Wong" <[email protected]>
[ Upstream commit 1cb5deb5bc095c070c09a4540c45f9c9ba24be43 ]
If we decide that a directory free block is corrupt, we must take care not to leak a buffer pointer to the caller. After xfs_trans_brelse returns, the buffer can be freed or reused, which means that we have to set *bpp back to NULL.
Callers are supposed to notice the nonzero return value and not use the buffer pointer, but we should code more defensively, even if all current callers handle this situation correctly.
--- fs/xfs/libxfs/xfs_dir2_node.c | 1 + 1 file changed, 1 insertion(+)
fs/xfs/libxfs/xfs_dir2_node.c +1 -0
@@ -212,6 +212,7 @@ __xfs_dir3_free_read(xfs_buf_ioerror (*bpp, -EFSCORRUPTED );xfs_verifier_error (*bpp);xfs_trans_brelse (tp, *bpp); + *bpp =NULL ;return -EFSCORRUPTED ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 62/127 scsi: aacraid: Disabling TM path and only processing IOP reset
In reply to Sasha LevinFrom: Sagar Biradar <[email protected]>
[ Upstream commit bef18d308a2215eff8c3411a23d7f34604ce56c3 ]
Fixes the occasional adapter panic when sg_reset is issued with -d, -t, -b and -H flags. Removal of command type HBA_IU_TYPE_SCSI_TM_REQ in aac_hba_send since iu_type, request_id and fib_flags are not populated. Device and target reset handlers are made to send TMF commands only when reset_state is 0.
--- drivers/scsi/aacraid/commsup.c | 2 +- drivers/scsi/aacraid/linit.c | 34 +++++++++++++++++++++++++--------- 2 files changed, 26 insertions(+), 10 deletions(-)
drivers/scsi/aacraid/commsup.c +1 -1
@@ -771,7 +771,7 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback, hbacmd->request_id =cpu_to_le32 ((((u32)(fibptr - dev->fibs)) <<2 ) +1 ); fibptr->flags |=FIB_CONTEXT_FLAG_SCSI_CMD ; - }else if (command !=HBA_IU_TYPE_SCSI_TM_REQ ) + }else return -EINVAL ;
drivers/scsi/aacraid/linit.c +25 -9
@@ -736,7 +736,11 @@ static int aac_eh_abort(struct scsi_cmnd* cmd) status =aac_hba_send (HBA_IU_TYPE_SCSI_TM_REQ , fib, (fib_callback ) aac_hba_callback, (void *) cmd); - +if (status != -EINPROGRESS ) { +aac_fib_complete (fib); +aac_fib_free (fib); +return ret; + }/* Wait up to 15 secs for completion */ for (count =0 ; count <15 ; ++count) {if (cmd->SCp.sent_command) {
@@ -915,11 +919,11 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd) info = &aac->hba_map[bus][cid]; -if (info->devtype !=AAC_DEVTYPE_NATIVE_RAW && - info->reset_state >0 ) +if (!(info->devtype ==AAC_DEVTYPE_NATIVE_RAW && + !(info->reset_state >0 )))return FAILED ; -pr_err ("%s: Host adapter reset request. SCSI hang ?\n" , +pr_err ("%s: Host device reset request. SCSI hang ?\n" ,AAC_DRIVERNAME ); fib =aac_fib_alloc (aac);
@@ -934,7 +938,12 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd) status =aac_hba_send (command, fib, (fib_callback ) aac_tmf_callback, (void *) info); - +if (status != -EINPROGRESS ) { + info->reset_state =0 ; +aac_fib_complete (fib); +aac_fib_free (fib); +return ret; + }/* Wait up to 15 seconds for completion */ for (count =0 ; count <15 ; ++count) {if (info->reset_state ==0 ) {
@@ -973,11 +982,11 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd) info = &aac->hba_map[bus][cid]; -if (info->devtype !=AAC_DEVTYPE_NATIVE_RAW && - info->reset_state >0 ) +if (!(info->devtype ==AAC_DEVTYPE_NATIVE_RAW && + !(info->reset_state >0 )))return FAILED ; -pr_err ("%s: Host adapter reset request. SCSI hang ?\n" , +pr_err ("%s: Host target reset request. SCSI hang ?\n" ,AAC_DRIVERNAME ); fib =aac_fib_alloc (aac);
@@ -994,6 +1003,13 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd) (fib_callback ) aac_tmf_callback, (void *) info); +if (status != -EINPROGRESS ) { + info->reset_state =0 ; +aac_fib_complete (fib); +aac_fib_free (fib); +return ret; + } +/* Wait up to 15 seconds for completion */ for (count =0 ; count <15 ; ++count) {if (info->reset_state <=0 ) {
@@ -1046,7 +1062,7 @@ static int aac_eh_bus_reset(struct scsi_cmnd* cmd) } } -pr_err ("%s: Host adapter reset request. SCSI hang ?\n" ,AAC_DRIVERNAME ); +pr_err ("%s: Host bus reset request. SCSI hang ?\n" ,AAC_DRIVERNAME );/* * Check the health of the controller
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 64/127 media: tda10071: fix unsigned sign extension overflow
In reply to Sasha LevinFrom: Colin Ian King <[email protected]>
[ Upstream commit a7463e2dc698075132de9905b89f495df888bb79 ]
The shifting of buf[3] by 24 bits to the left will be promoted to a 32 bit signed int and then sign-extended to an unsigned long. In the unlikely event that the the top bit of buf[3] is set then all then all the upper bits end up as also being set because of the sign-extension and this affect the ev->post_bit_error sum. Fix this by using the temporary u32 variable bit_error to avoid the sign-extension promotion. This also removes the need to do the computation twice.
Addresses-Coverity: ("Unintended sign extension")
--- drivers/media/dvb-frontends/tda10071.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
drivers/media/dvb-frontends/tda10071.c +5 -4
@@ -483,10 +483,11 @@ static int tda10071_read_status(struct dvb_frontend *fe, enum fe_status *status) goto error;if (dev->delivery_system ==SYS_DVBS ) { - dev->dvbv3_ber = buf[0 ] <<24 | buf[1 ] <<16 | - buf[2 ] <<8 | buf[3 ] <<0 ; - dev->post_bit_error += buf[0 ] <<24 | buf[1 ] <<16 | - buf[2 ] <<8 | buf[3 ] <<0 ; +u32 bit_error = buf[0 ] <<24 | buf[1 ] <<16 | + buf[2 ] <<8 | buf[3 ] <<0 ; + + dev->dvbv3_ber = bit_error; + dev->post_bit_error += bit_error; c->post_bit_error.stat[0 ].scale =FE_SCALE_COUNTER ; c->post_bit_error.stat[0 ].uvalue = dev->post_bit_error; dev->block_error += buf[4 ] <<8 | buf[5 ] <<0 ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 53/127 bpf: Remove recursion prevention from rcu free callback
In reply to Sasha LevinFrom: Thomas Gleixner <[email protected]>
[ Upstream commit 8a37963c7ac9ecb7f86f8ebda020e3f8d6d7b8a0 ]
If an element is freed via RCU then recursion into BPF instrumentation functions is not a concern. The element is already detached from the map and the RCU callback does not hold any locks on which a kprobe, perf event or tracepoint attached BPF program could deadlock.
--- kernel/bpf/hashtab.c | 8 -------- 1 file changed, 8 deletions(-)
kernel/bpf/hashtab.c +0 -8
@@ -645,15 +645,7 @@ static void htab_elem_free_rcu(struct rcu_head *head) struct htab_elem *l = container_of(head, struct htab_elem, rcu);struct bpf_htab *htab = l->htab; -/* must increment bpf_prog_active to avoid kprobe+bpf triggering while -* we're calling kfree, otherwise deadlock is possible if kprobes -* are placed somewhere inside of slub -*/ -preempt_disable (); -__this_cpu_inc (bpf_prog_active);htab_elem_free (htab, l); -__this_cpu_dec (bpf_prog_active); -preempt_enable (); }static void htab_put_fd_value (struct bpf_htab *htab,struct htab_elem *l)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 57/127 timekeeping: Prevent 32bit truncation in scale64_check_overflow()
In reply to Sasha LevinFrom: Wen Yang <[email protected]>
[ Upstream commit 4cbbc3a0eeed675449b1a4d080008927121f3da3 ]
While unlikely the divisor in scale64_check_overflow() could be >= 32bit in scale64_check_overflow(). do_div() truncates the divisor to 32bit at least on 32bit platforms.
Use div64_u64() instead to avoid the truncation to 32-bit.
[ tglx: Massaged changelog ]
--- kernel/time/timekeeping.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
kernel/time/timekeeping.c +1 -2
@@ -988,9 +988,8 @@ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; - rem *= mult; -do_div (rem, div); + rem =div64_u64 (rem * mult, div); *base = tmp + rem;return 0 ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 58/127 ext4: fix a data race at inode->i_disksize
In reply to Sasha LevinFrom: Qiujun Huang <[email protected]>
[ Upstream commit dce8e237100f60c28cc66effb526ba65a01d8cb3 ]
KCSAN find inode->i_disksize could be accessed concurrently.
BUG: KCSAN: data-race in ext4_mark_iloc_dirty / ext4_write_end
write (marked) to 0xffff8b8932f40090 of 8 bytes by task 66792 on cpu 0:
ext4_write_end+0x53f/0x5b0 ext4_da_write_end+0x237/0x510 generic_perform_write+0x1c4/0x2a0 ext4_buffered_write_iter+0x13a/0x210 ext4_file_write_iter+0xe2/0x9b0 new_sync_write+0x29c/0x3a0 __vfs_write+0x92/0xa0 vfs_write+0xfc/0x2a0 ksys_write+0xe8/0x140 __x64_sys_write+0x4c/0x60 do_syscall_64+0x8a/0x2a0 entry_SYSCALL_64_after_hwframe+0x44/0xa9
read to 0xffff8b8932f40090 of 8 bytes by task 14414 on cpu 1:
ext4_mark_iloc_dirty+0x716/0x1190 ext4_mark_inode_dirty+0xc9/0x360 ext4_convert_unwritten_extents+0x1bc/0x2a0 ext4_convert_unwritten_io_end_vec+0xc5/0x150 ext4_put_io_end+0x82/0x130 ext4_writepages+0xae7/0x16f0 do_writepages+0x64/0x120 __writeback_single_inode+0x7d/0x650 writeback_sb_inodes+0x3a4/0x860 __writeback_inodes_wb+0xc4/0x150 wb_writeback+0x43f/0x510 wb_workfn+0x3b2/0x8a0 process_one_work+0x39b/0x7e0 worker_thread+0x88/0x650 kthread+0x1d4/0x1f0 ret_from_fork+0x35/0x40
The plain read is outside of inode->i_data_sem critical section which results in a data race. Fix it by adding READ_ONCE().
--- fs/ext4/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/ext4/inode.c +1 -1
@@ -5179,7 +5179,7 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_file_acl_high =cpu_to_le16 (ei->i_file_acl >>32 ); raw_inode->i_file_acl_lo =cpu_to_le32 (ei->i_file_acl); -if (ei->i_disksize !=ext4_isize (inode->i_sb, raw_inode)) { +if (READ_ONCE (ei->i_disksize) !=ext4_isize (inode->i_sb, raw_inode)) {ext4_isize_set (raw_inode, ei->i_disksize); need_datasync =1 ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 56/127 Bluetooth: guard against controllers sending zero'd events
In reply to Sasha LevinFrom: Alain Michaud <[email protected]>
[ Upstream commit 08bb4da90150e2a225f35e0f642cdc463958d696 ]
Some controllers have been observed to send zero'd events under some conditions. This change guards against this condition as well as adding a trace to facilitate diagnosability of this condition.
--- net/bluetooth/hci_event.c | 6 ++++++ 1 file changed, 6 insertions(+)
net/bluetooth/hci_event.c +6 -0
@@ -5257,6 +5257,11 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)u8 status =0 , event = hdr->evt, req_evt =0 ;u16 opcode =HCI_OP_NOP ; +if (!event) { +bt_dev_warn (hdev,"Received unexpected HCI Event 00000000" ); + goto done; + } +if (hdev->sent_cmd &&bt_cb (hdev->sent_cmd)->hci.req_event == event) {struct hci_command_hdr *cmd_hdr = (void *) hdev->sent_cmd->data; opcode =__le16_to_cpu (cmd_hdr->opcode);
@@ -5468,6 +5473,7 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)req_complete_skb (hdev, status, opcode, orig_skb); } +done:kfree_skb (orig_skb);kfree_skb (skb); hdev->stat.evt_rx++;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 50/127 KVM: x86: fix incorrect comparison in trace event
In reply to Sasha LevinFrom: Paolo Bonzini <[email protected]>
[ Upstream commit 147f1a1fe5d7e6b01b8df4d0cbd6f9eaf6b6c73b ]
The "u" field in the event has three states, -1/0/1. Using u8 however means that comparison with -1 will always fail, so change to signed char.
--- arch/x86/kvm/mmutrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kvm/mmutrace.h +1 -1
@@ -339,7 +339,7 @@ TRACE_EVENT(/* These depend on page entry type, so compute them now. */ __field(bool, r) __field(bool, x) -__field (u8, u) + __field(signed char, u) ), TP_fast_assign(
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 49/127 RDMA/rxe: Fix configuration of atomic queue pair attributes
In reply to Sasha LevinFrom: Bart Van Assche <[email protected]>
[ Upstream commit fb3063d31995cc4cf1d47a406bb61d6fb1b1d58d ]
From the comment above the definition of the roundup_pow_of_two() macro:
The result is undefined when n == 0.
Hence only pass positive values to roundup_pow_of_two(). This patch fixes the following UBSAN complaint:
UBSAN: Undefined behaviour in ./include/linux/log2.h:57:13 shift exponent 64 is too large for 64-bit type 'long unsigned int' Call Trace: dump_stack+0xa5/0xe6 ubsan_epilogue+0x9/0x26 __ubsan_handle_shift_out_of_bounds.cold+0x4c/0xf9 rxe_qp_from_attr.cold+0x37/0x5d [rdma_rxe] rxe_modify_qp+0x59/0x70 [rdma_rxe] _ib_modify_qp+0x5aa/0x7c0 [ib_core] ib_modify_qp+0x3b/0x50 [ib_core] cma_modify_qp_rtr+0x234/0x260 [rdma_cm] __rdma_accept+0x1a7/0x650 [rdma_cm] nvmet_rdma_cm_handler+0x1286/0x14cd [nvmet_rdma] cma_cm_event_handler+0x6b/0x330 [rdma_cm] cma_ib_req_handler+0xe60/0x22d0 [rdma_cm] cm_process_work+0x30/0x140 [ib_cm] cm_req_handler+0x11f4/0x1cd0 [ib_cm] cm_work_handler+0xb8/0x344e [ib_cm] process_one_work+0x569/0xb60 worker_thread+0x7a/0x5d0 kthread+0x1e6/0x210 ret_from_fork+0x24/0x30
--- drivers/infiniband/sw/rxe/rxe_qp.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
drivers/infiniband/sw/rxe/rxe_qp.c +4 -3
@@ -593,15 +593,16 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask,struct ib_gid_attr sgid_attr;if (mask &IB_QP_MAX_QP_RD_ATOMIC ) { -int max_rd_atomic =__roundup_pow_of_two (attr->max_rd_atomic); +int max_rd_atomic = attr->max_rd_atomic ? +roundup_pow_of_two (attr->max_rd_atomic) :0 ; qp->attr.max_rd_atomic = max_rd_atomic;atomic_set (&qp->req.rd_atomic, max_rd_atomic); }if (mask &IB_QP_MAX_DEST_RD_ATOMIC ) { -int max_dest_rd_atomic = -__roundup_pow_of_two (attr->max_dest_rd_atomic); +int max_dest_rd_atomic = attr->max_dest_rd_atomic ? +roundup_pow_of_two (attr->max_dest_rd_atomic) :0 ; qp->attr.max_dest_rd_atomic = max_dest_rd_atomic;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 46/127 scsi: lpfc: Fix coverity errors in fmdi attribute handling
In reply to Sasha LevinFrom: James Smart <[email protected]>
[ Upstream commit 4cb9e1ddaa145be9ed67b6a7de98ca705a43f998 ]
Coverity reported a memory corruption error for the fdmi attributes routines:
CID 15768 [Memory Corruption] Out-of-bounds access on FDMI
Sloppy coding of the fmdi structures. In both the lpfc_fdmi_attr_def and lpfc_fdmi_reg_port_list structures, a field was placed at the start of payload that may have variable content. The field was given an arbitrary type (uint32_t). The code then uses the field name to derive an address, which it used in things such as memset and memcpy. The memset sizes or memcpy lengths were larger than the arbitrary type, thus coverity reported an error.
Fix by replacing the arbitrary fields with the real field structures describing the payload.
--- drivers/scsi/lpfc/lpfc_ct.c | 137 ++++++++++++++++++------------------ drivers/scsi/lpfc/lpfc_hw.h | 36 +++++----- 2 files changed, 85 insertions(+), 88 deletions(-)
drivers/scsi/lpfc/lpfc_ct.c +69 -68
@@ -1714,8 +1714,8 @@ lpfc_fdmi_hba_attr_wwnn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_def *ad)struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,sizeof (struct lpfc_name )); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));memcpy (&ae->un.AttrWWN, &vport->fc_sparam.nodeName,sizeof (struct lpfc_name ));
@@ -1731,8 +1731,8 @@ lpfc_fdmi_hba_attr_manufacturer(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));/* This string MUST be consistent with other FC platforms * supported by Broadcom.
@@ -1756,8 +1756,8 @@ lpfc_fdmi_hba_attr_sn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_def *ad)struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));strncpy (ae->un.AttrString, phba->SerialNumber,sizeof (ae->un.AttrString));
@@ -1778,8 +1778,8 @@ lpfc_fdmi_hba_attr_model(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));strncpy (ae->un.AttrString, phba->ModelName,sizeof (ae->un.AttrString));
@@ -1799,8 +1799,8 @@ lpfc_fdmi_hba_attr_description(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));strncpy (ae->un.AttrString, phba->ModelDesc,sizeof (ae->un.AttrString));
@@ -1822,8 +1822,8 @@ lpfc_fdmi_hba_attr_hdw_ver(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t i, j, incr, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));/* Convert JEDEC ID to ascii for hardware version */ incr = vp->rev.biuRev;
@@ -1852,8 +1852,8 @@ lpfc_fdmi_hba_attr_drvr_ver(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));strncpy (ae->un.AttrString, lpfc_release_version,sizeof (ae->un.AttrString));
@@ -1874,8 +1874,8 @@ lpfc_fdmi_hba_attr_rom_ver(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));if (phba->sli_rev ==LPFC_SLI_REV4 )lpfc_decode_firmware_rev (phba, ae->un.AttrString,1 );
@@ -1899,8 +1899,8 @@ lpfc_fdmi_hba_attr_fmw_ver(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));lpfc_decode_firmware_rev (phba, ae->un.AttrString,1 ); len = strnlen(ae->un.AttrString,
@@ -1919,8 +1919,8 @@ lpfc_fdmi_hba_attr_os_ver(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae)); snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s %s %s", init_utsname()->sysname,
@@ -1942,7 +1942,7 @@ lpfc_fdmi_hba_attr_ct_len(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt =cpu_to_be32 (LPFC_MAX_CT_SIZE ); size =FOURBYTES +sizeof (uint32_t );
@@ -1958,8 +1958,8 @@ lpfc_fdmi_hba_attr_symbolic_name(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae)); len =lpfc_vport_symbolic_node_name (vport, ae->un.AttrString,256 );
@@ -1977,7 +1977,7 @@ lpfc_fdmi_hba_attr_vendor_info(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;/* Nothing is defined for this currently */ ae->un.AttrInt =cpu_to_be32 (0 );
@@ -1994,7 +1994,7 @@ lpfc_fdmi_hba_attr_num_ports(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;/* Each driver instance corresponds to a single port */ ae->un.AttrInt =cpu_to_be32 (1 );
@@ -2011,8 +2011,8 @@ lpfc_fdmi_hba_attr_fabric_wwnn(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,sizeof (struct lpfc_name )); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));memcpy (&ae->un.AttrWWN, &vport->fabric_nodename,sizeof (struct lpfc_name ));
@@ -2030,8 +2030,8 @@ lpfc_fdmi_hba_attr_bios_ver(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));lpfc_decode_firmware_rev (phba, ae->un.AttrString,1 ); len = strnlen(ae->un.AttrString,
@@ -2050,7 +2050,7 @@ lpfc_fdmi_hba_attr_bios_state(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;/* Driver doesn't have access to this information */ ae->un.AttrInt =cpu_to_be32 (0 );
@@ -2067,8 +2067,8 @@ lpfc_fdmi_hba_attr_vendor_id(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));strncpy (ae->un.AttrString,"EMULEX" ,sizeof (ae->un.AttrString));
@@ -2089,8 +2089,8 @@ lpfc_fdmi_port_attr_fc4type(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,32 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae)); ae->un.AttrTypes[3 ] =0x02 ;/* Type 0x1 - ELS */ ae->un.AttrTypes[2 ] =0x01 ;/* Type 0x8 - FCP */
@@ -2111,7 +2111,7 @@ lpfc_fdmi_port_attr_support_speed(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt =0 ;if (!(phba->hba_flag &HBA_FCOE_MODE )) {
@@ -2161,7 +2161,7 @@ lpfc_fdmi_port_attr_speed(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;if (!(phba->hba_flag &HBA_FCOE_MODE )) {switch (phba->fc_linkspeed) {
@@ -2225,7 +2225,7 @@ lpfc_fdmi_port_attr_max_frame(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; hsp = (struct serv_parm *)&vport->fc_sparam; ae->un.AttrInt = (((uint32_t) hsp->cmn.bbRcvSizeMsb) << 8) |
@@ -2245,8 +2245,8 @@ lpfc_fdmi_port_attr_os_devname(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));snprintf (ae->un.AttrString,sizeof (ae->un.AttrString),"/sys/class/scsi_host/host%d" , shost->host_no);
@@ -2266,8 +2266,8 @@ lpfc_fdmi_port_attr_host_name(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));snprintf (ae->un.AttrString,sizeof (ae->un.AttrString),"%s" ,init_utsname ()->nodename);
@@ -2287,8 +2287,8 @@ lpfc_fdmi_port_attr_wwnn(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,sizeof (struct lpfc_name )); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));memcpy (&ae->un.AttrWWN, &vport->fc_sparam.nodeName,sizeof (struct lpfc_name ));
@@ -2305,8 +2305,8 @@ lpfc_fdmi_port_attr_wwpn(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,sizeof (struct lpfc_name )); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));memcpy (&ae->un.AttrWWN, &vport->fc_sparam.portName,sizeof (struct lpfc_name ));
@@ -2323,8 +2323,8 @@ lpfc_fdmi_port_attr_symbolic_name(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae)); len =lpfc_vport_symbolic_port_name (vport, ae->un.AttrString,256 ); len += (len &3 ) ? (4 - (len &3 )) :4 ;
@@ -2342,7 +2342,7 @@ lpfc_fdmi_port_attr_port_type(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;if (phba->fc_topology ==LPFC_TOPOLOGY_LOOP ) ae->un.AttrInt =cpu_to_be32 (LPFC_FDMI_PORTTYPE_NLPORT );else
@@ -2360,7 +2360,7 @@ lpfc_fdmi_port_attr_class(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt =cpu_to_be32 (FC_COS_CLASS2 |FC_COS_CLASS3 ); size =FOURBYTES +sizeof (uint32_t ); ad->AttrLen =cpu_to_be16 (size);
@@ -2375,8 +2375,8 @@ lpfc_fdmi_port_attr_fabric_wwpn(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,sizeof (struct lpfc_name )); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));memcpy (&ae->un.AttrWWN, &vport->fabric_portname,sizeof (struct lpfc_name ));
@@ -2393,8 +2393,8 @@ lpfc_fdmi_port_attr_active_fc4type(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,32 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae)); ae->un.AttrTypes[3 ] =0x02 ;/* Type 0x1 - ELS */ ae->un.AttrTypes[2 ] =0x01 ;/* Type 0x8 - FCP */
@@ -2414,7 +2414,7 @@ lpfc_fdmi_port_attr_port_state(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;/* Link Up - operational */ ae->un.AttrInt =cpu_to_be32 (LPFC_FDMI_PORTSTATE_ONLINE ); size =FOURBYTES +sizeof (uint32_t );
@@ -2430,7 +2430,7 @@ lpfc_fdmi_port_attr_num_disc(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; vport->fdmi_num_disc =lpfc_find_map_node (vport); ae->un.AttrInt =cpu_to_be32 (vport->fdmi_num_disc); size =FOURBYTES +sizeof (uint32_t );
@@ -2446,7 +2446,7 @@ lpfc_fdmi_port_attr_nportid(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt =cpu_to_be32 (vport->fc_myDID); size =FOURBYTES +sizeof (uint32_t ); ad->AttrLen =cpu_to_be16 (size);
@@ -2461,8 +2461,8 @@ lpfc_fdmi_smart_attr_service(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));strncpy (ae->un.AttrString,"Smart SAN Initiator" ,sizeof (ae->un.AttrString));
@@ -2482,8 +2482,8 @@ lpfc_fdmi_smart_attr_guid(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));memcpy (&ae->un.AttrString, &vport->fc_sparam.nodeName,sizeof (struct lpfc_name ));
@@ -2503,8 +2503,8 @@ lpfc_fdmi_smart_attr_version(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));strncpy (ae->un.AttrString,"Smart SAN Version 2.0" ,sizeof (ae->un.AttrString));
@@ -2525,8 +2525,8 @@ lpfc_fdmi_smart_attr_model(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; -memset (ae,0 ,256 ); + ae = &ad->AttrValue; +memset (ae,0 ,sizeof (*ae));strncpy (ae->un.AttrString, phba->ModelName,sizeof (ae->un.AttrString));
@@ -2545,7 +2545,7 @@ lpfc_fdmi_smart_attr_port_info(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;/* SRIOV (type 3) is not supported */ if (vport->vpi)
@@ -2565,7 +2565,7 @@ lpfc_fdmi_smart_attr_qos(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt =cpu_to_be32 (0 ); size =FOURBYTES +sizeof (uint32_t ); ad->AttrLen =cpu_to_be16 (size);
@@ -2580,7 +2580,7 @@ lpfc_fdmi_smart_attr_security(struct lpfc_vport *vport,struct lpfc_fdmi_attr_entry *ae;uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt =cpu_to_be32 (1 ); size =FOURBYTES +sizeof (uint32_t ); ad->AttrLen =cpu_to_be16 (size);
@@ -2728,7 +2728,8 @@ lpfc_fdmi_cmd(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,/* Registered Port List */ /* One entry (port) per adapter */ rh->rpl.EntryCnt =cpu_to_be32 (1 ); -memcpy (&rh->rpl.pe, &phba->pport->fc_sparam.portName, +memcpy (&rh->rpl.pe.PortName, + &phba->pport->fc_sparam.portName,sizeof (struct lpfc_name ));/* point to the HBA attribute block */
drivers/scsi/lpfc/lpfc_hw.h +16 -20
@@ -1326,25 +1326,8 @@ struct fc_rdp_res_frame {/* lpfc_sli_ct_request defines the CT_IU preamble for FDMI commands */ #define SLI_CT_FDMI_Subtypes 0x10/* Management Service Subtype */ -/* -* Registered Port List Format -*/ -struct lpfc_fdmi_reg_port_list { -uint32_t EntryCnt; -uint32_t pe;/* Variable-length array */ -}; - -/* Definitions for HBA / Port attribute entries */ -struct lpfc_fdmi_attr_def {/* Defined in TLV format */ -/* Structure is in Big Endian format */ -uint32_t AttrType:16 ; -uint32_t AttrLen:16 ; -uint32_t AttrValue;/* Marks start of Value (ATTRIBUTE_ENTRY) */ -}; - -/* Attribute Entry */ struct lpfc_fdmi_attr_entry { union {
@@ -1355,7 +1338,13 @@ struct lpfc_fdmi_attr_entry { } un; }; -#define LPFC_FDMI_MAX_AE_SIZE sizeof(struct lpfc_fdmi_attr_entry) +struct lpfc_fdmi_attr_def {/* Defined in TLV format */ +/* Structure is in Big Endian format */ +uint32_t AttrType:16 ; +uint32_t AttrLen:16 ; +/* Marks start of Value (ATTRIBUTE_ENTRY) */ +struct lpfc_fdmi_attr_entry AttrValue; +} __packed;/* * HBA Attribute Block
@@ -1379,13 +1368,20 @@ struct lpfc_fdmi_hba_ident {struct lpfc_name PortName; }; +/* +* Registered Port List Format +*/ +struct lpfc_fdmi_reg_port_list { +uint32_t EntryCnt; +struct lpfc_fdmi_port_entry pe; +} __packed; +/* * Register HBA(RHBA) */ struct lpfc_fdmi_reg_hba {struct lpfc_fdmi_hba_ident hi; -struct lpfc_fdmi_reg_port_list rpl;/* variable-length array */ -/* struct lpfc_fdmi_attr_block ab; */ +struct lpfc_fdmi_reg_port_list rpl; };/*
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 48/127 perf test: Fix test trace+probe_vfs_getname.sh on s390
In reply to Sasha LevinFrom: Thomas Richter <[email protected]>
[ Upstream commit 2bbc83537614517730e9f2811195004b712de207 ]
This test places a kprobe to function getname_flags() in the kernel which has the following prototype:
struct filename *getname_flags(const char __user *filename, int flags, int *empty)
The 'filename' argument points to a filename located in user space memory.
Looking at commit 88903c464321c ("tracing/probe: Add ustring type for user-space string") the kprobe should indicate that user space memory is accessed.
Output before:
[root@m35lp76 perf]# ./perf test 66 67
66: Use vfs_getname probe to get syscall args filenames : FAILED!
67: Check open filename arg using perf trace + vfs_getname: FAILED! [root@m35lp76 perf]#
Output after:
[root@m35lp76 perf]# ./perf test 66 67
66: Use vfs_getname probe to get syscall args filenames : Ok
67: Check open filename arg using perf trace + vfs_getname: Ok [root@m35lp76 perf]#
Comments from Masami Hiramatsu:
This bug doesn't happen on x86 or other archs on which user address space and kernel address space is the same. On some arches (ppc64 in this case?) user address space is partially or completely the same as kernel address space.
(Yes, they switch the world when running into the kernel) In this case, we need to use different data access functions for each space.
That is why I introduced the "ustring" type for kprobe events.
As far as I can see, Thomas's patch is sane. Thomas, could you show us your result on your test environment?
Comments from Thomas Richter:
Test results for s/390 included above.
--- tools/perf/tests/shell/lib/probe_vfs_getname.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/tests/shell/lib/probe_vfs_getname.sh +1 -1
@@ -14,7 +14,7 @@ add_probe_vfs_getname() { if [ $had_vfs_getname -eq 1 ] ; then line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/') perf probe -q "vfs_getname=getname_flags:${line} pathname=result->name:string" || \ - perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string" + perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" fi }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 42/127 skbuff: fix a data race in skb_queue_len()
In reply to Sasha LevinFrom: Qian Cai <[email protected]>
[ Upstream commit 86b18aaa2b5b5bb48e609cd591b3d2d0fdbe0442 ]
sk_buff.qlen can be accessed concurrently as noticed by KCSAN,
BUG: KCSAN: data-race in __skb_try_recv_from_queue / unix_dgram_sendmsg
read to 0xffff8a1b1d8a81c0 of 4 bytes by task 5371 on cpu 96:
unix_dgram_sendmsg+0x9a9/0xb70 include/linux/skbuff.h:1821 net/unix/af_unix.c:1761 ____sys_sendmsg+0x33e/0x370 ___sys_sendmsg+0xa6/0xf0 __sys_sendmsg+0x69/0xf0 __x64_sys_sendmsg+0x51/0x70 do_syscall_64+0x91/0xb47 entry_SYSCALL_64_after_hwframe+0x49/0xbe
write to 0xffff8a1b1d8a81c0 of 4 bytes by task 1 on cpu 99:
__skb_try_recv_from_queue+0x327/0x410 include/linux/skbuff.h:2029 __skb_try_recv_datagram+0xbe/0x220 unix_dgram_recvmsg+0xee/0x850 ____sys_recvmsg+0x1fb/0x210 ___sys_recvmsg+0xa2/0xf0 __sys_recvmsg+0x66/0xf0 __x64_sys_recvmsg+0x51/0x70 do_syscall_64+0x91/0xb47 entry_SYSCALL_64_after_hwframe+0x49/0xbe
Since only the read is operating as lockless, it could introduce a logic bug in unix_recvq_full() due to the load tearing. Fix it by adding a lockless variant of skb_queue_len() and unix_recvq_full() where READ_ONCE() is on the read while WRITE_ONCE() is on the write similar to the commit d7d16a89350a ("net: add skb_queue_empty_lockless()").
--- include/linux/skbuff.h | 14 +++++++++++++- net/unix/af_unix.c | 11 +++++++++-- 2 files changed, 22 insertions(+), 3 deletions(-)
include/linux/skbuff.h +13 -1
@@ -1674,6 +1674,18 @@ static inline __u32 skb_queue_len(const struct sk_buff_head *list_)return list_->qlen; } +/** +* skb_queue_len_lockless - get queue length +* @list_: list to measure +* +* Return the length of an &sk_buff queue. +* This variant can be used in lockless contexts. +*/ +static inline __u32 skb_queue_len_lockless (const struct sk_buff_head *list_) +{ +return READ_ONCE (list_->qlen); +} +/** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize
@@ -1881,7 +1893,7 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) {struct sk_buff *next, *prev; - list->qlen--; +WRITE_ONCE (list->qlen, list->qlen -1 ); next = skb->next; prev = skb->prev; skb->next = skb->prev =NULL ;
net/unix/af_unix.c +9 -2
@@ -192,11 +192,17 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk)return unix_peer (osk) ==NULL ||unix_our_peer (sk, osk); } -static inline int unix_recvq_full (struct sock const *sk) +static inline int unix_recvq_full (const struct sock *sk) {return skb_queue_len (&sk->sk_receive_queue) > sk->sk_max_ack_backlog; } +static inline int unix_recvq_full_lockless (const struct sock *sk) +{ +return skb_queue_len_lockless (&sk->sk_receive_queue) > +READ_ONCE (sk->sk_max_ack_backlog); +} +struct sock *unix_peer_get (struct sock *s) {struct sock *peer;
@@ -1792,7 +1798,8 @@ restart_locked:* - unix_peer(sk) == sk by time of get but disconnected before lock */ if (other != sk && -unlikely (unix_peer (other) != sk &&unix_recvq_full (other))) { +unlikely (unix_peer (other) != sk && +unix_recvq_full_lockless (other))) {if (timeo) { timeo =unix_wait_for_peer (other, timeo);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 39/127 Bluetooth: prefetch channel before killing sock
In reply to Sasha LevinFrom: Hillf Danton <[email protected]>
[ Upstream commit 2a154903cec20fb64ff4d7d617ca53c16f8fd53a ]
Prefetch channel before killing sock in order to fix UAF like
BUG: KASAN: use-after-free in l2cap_sock_release+0x24c/0x290 net/bluetooth/l2cap_sock.c:1212 Read of size 8 at addr ffff8880944904a0 by task syz-fuzzer/9751
--- net/bluetooth/l2cap_sock.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
net/bluetooth/l2cap_sock.c +6 -4
@@ -1191,6 +1191,7 @@ static int l2cap_sock_release(struct socket *sock) {struct sock *sk = sock->sk;int err; +struct l2cap_chan *chan;BT_DBG ("sock %p, sk %p" , sock, sk);
@@ -1200,15 +1201,16 @@ static int l2cap_sock_release(struct socket *sock)bt_sock_unlink (&l2cap_sk_list, sk); err =l2cap_sock_shutdown (sock,2 ); + chan =l2cap_pi (sk)->chan; -l2cap_chan_hold (l2cap_pi (sk)->chan); -l2cap_chan_lock (l2cap_pi (sk)->chan); +l2cap_chan_hold (chan); +l2cap_chan_lock (chan);sock_orphan (sk);l2cap_sock_kill (sk); -l2cap_chan_unlock (l2cap_pi (sk)->chan); -l2cap_chan_put (l2cap_pi (sk)->chan); +l2cap_chan_unlock (chan); +l2cap_chan_put (chan);return err; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 36/127 tools/power/x86/intel_pstate_tracer: changes for python 3 compatibility
In reply to Sasha LevinFrom: Doug Smythies <[email protected]>
[ Upstream commit e749e09db30c38f1a275945814b0109e530a07b0 ]
Some syntax needs to be more rigorous for python 3. Backwards compatibility tested with python 2.7
--- .../intel_pstate_tracer.py | 22 +++++++++---------- 1 file changed, 11 insertions(+), 11 deletions(-)
tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py +11 -11
@@ -10,11 +10,11 @@ then this utility enables and collects trace data for a user specified interval and generates performance plots. Prerequisites: - Python version 2.7.x + Python version 2.7.x or higher gnuplot 5.0 or higher - gnuplot-py 1.8 + gnuplot-py 1.8 or higher (Most of the distributions have these required packages. They may be called - gnuplot-py, phython-gnuplot. ) + gnuplot-py, phython-gnuplot or phython3-gnuplot, gnuplot-nox, ... ) HWP (Hardware P-States are disabled) Kernel config for Linux trace is enabled
@@ -178,7 +178,7 @@ def plot_pstate_cpu_with_sample(): g_plot('set xlabel "Samples"') g_plot('set ylabel "P-State"') g_plot('set title "{} : cpu pstate vs. sample : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_SAMPLE, C_TO) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str)
@@ -195,7 +195,7 @@ def plot_pstate_cpu(): # the following command is really cool, but doesn't work with the CPU masking option because it aborts on the first missing file. # plot_str = 'plot for [i=0:*] file=sprintf("cpu%03d.csv",i) title_s=sprintf("cpu%03d",i) file using 16:7 pt 7 ps 1 title title_s' # - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_TO) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str)
@@ -209,7 +209,7 @@ def plot_load_cpu(): g_plot('set ylabel "CPU load (percent)"') g_plot('set title "{} : cpu loads : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_LOAD) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str)
@@ -223,7 +223,7 @@ def plot_frequency_cpu(): g_plot('set ylabel "CPU Frequency (GHz)"') g_plot('set title "{} : cpu frequencies : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_FREQ) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str)
@@ -238,7 +238,7 @@ def plot_duration_cpu(): g_plot('set ylabel "Timer Duration (MilliSeconds)"') g_plot('set title "{} : cpu durations : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_DURATION) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str)
@@ -252,7 +252,7 @@ def plot_scaled_cpu(): g_plot('set ylabel "Scaled Busy (Unitless)"') g_plot('set title "{} : cpu scaled busy : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_SCALED) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str)
@@ -266,7 +266,7 @@ def plot_boost_cpu(): g_plot('set ylabel "CPU IO Boost (percent)"') g_plot('set title "{} : cpu io boost : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_BOOST) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str)
@@ -280,7 +280,7 @@ def plot_ghz_cpu(): g_plot('set ylabel "TSC Frequency (GHz)"') g_plot('set title "{} : cpu TSC Frequencies (Sanity check calculation) : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_GHZ) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 37/127 Bluetooth: Fix refcount use-after-free issue
In reply to Sasha LevinFrom: Manish Mandlik <[email protected]>
[ Upstream commit 6c08fc896b60893c5d673764b0668015d76df462 ]
There is no lock preventing both l2cap_sock_release() and chan->ops->close() from running at the same time.
If we consider Thread A running l2cap_chan_timeout() and Thread B running l2cap_sock_release(), expected behavior is:
A::l2cap_chan_timeout()->l2cap_chan_close()->l2cap_sock_teardown_cb() A::l2cap_chan_timeout()->l2cap_sock_close_cb()->l2cap_sock_kill() B::l2cap_sock_release()->sock_orphan() B::l2cap_sock_release()->l2cap_sock_kill()
where,sock_orphan() clears "sk->sk_socket" and l2cap_sock_teardown_cb() marks socket as SOCK_ZAPPED.
In l2cap_sock_kill(), there is an "if-statement" that checks if both sock_orphan() and sock_teardown() has been run i.e. sk->sk_socket is NULL and socket is marked as SOCK_ZAPPED. Socket is killed if the condition is satisfied.
In the race condition, following occurs:
A::l2cap_chan_timeout()->l2cap_chan_close()->l2cap_sock_teardown_cb() B::l2cap_sock_release()->sock_orphan() B::l2cap_sock_release()->l2cap_sock_kill() A::l2cap_chan_timeout()->l2cap_sock_close_cb()->l2cap_sock_kill()
In this scenario, "if-statement" is true in both B::l2cap_sock_kill() and A::l2cap_sock_kill() and we hit "refcount: underflow; use-after-free" bug.
Similar condition occurs at other places where teardown/sock_kill is happening:
l2cap_disconnect_rsp()->l2cap_chan_del()->l2cap_sock_teardown_cb() l2cap_disconnect_rsp()->l2cap_sock_close_cb()->l2cap_sock_kill()
l2cap_conn_del()->l2cap_chan_del()->l2cap_sock_teardown_cb() l2cap_conn_del()->l2cap_sock_close_cb()->l2cap_sock_kill()
l2cap_disconnect_req()->l2cap_chan_del()->l2cap_sock_teardown_cb() l2cap_disconnect_req()->l2cap_sock_close_cb()->l2cap_sock_kill()
l2cap_sock_cleanup_listen()->l2cap_chan_close()->l2cap_sock_teardown_cb() l2cap_sock_cleanup_listen()->l2cap_sock_kill()
Protect teardown/sock_kill and orphan/sock_kill by adding hold_lock on l2cap channel to ensure that the socket is killed only after marked as zapped and orphan.
--- net/bluetooth/l2cap_core.c | 26 +++++++++++++++----------- net/bluetooth/l2cap_sock.c | 16 +++++++++++++--- 2 files changed, 28 insertions(+), 14 deletions(-)
net/bluetooth/l2cap_core.c +15 -11
@@ -414,6 +414,9 @@ static void l2cap_chan_timeout(struct work_struct *work)BT_DBG ("chan %p state %s" , chan,state_to_string (chan->state));mutex_lock (&conn->chan_lock); +/* __set_chan_timer() calls l2cap_chan_hold(chan) while scheduling +* this work. No need to call l2cap_chan_hold(chan) here again. +*/ l2cap_chan_lock (chan);if (chan->state ==BT_CONNECTED || chan->state ==BT_CONFIG )
@@ -426,12 +429,12 @@ static void l2cap_chan_timeout(struct work_struct *work)l2cap_chan_close (chan, reason); -l2cap_chan_unlock (chan); - chan->ops->close (chan); -mutex_unlock (&conn->chan_lock); +l2cap_chan_unlock (chan);l2cap_chan_put (chan); + +mutex_unlock (&conn->chan_lock); }struct l2cap_chan *l2cap_chan_create (void )
@@ -1725,9 +1728,9 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)l2cap_chan_del (chan, err); -l2cap_chan_unlock (chan); - chan->ops->close (chan); + +l2cap_chan_unlock (chan);l2cap_chan_put (chan); }
@@ -4337,6 +4340,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn,return 0 ; } +l2cap_chan_hold (chan);l2cap_chan_lock (chan); rsp.dcid =cpu_to_le16 (chan->scid);
@@ -4345,12 +4349,11 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, chan->ops->set_shutdown (chan); -l2cap_chan_hold (chan);l2cap_chan_del (chan,ECONNRESET ); -l2cap_chan_unlock (chan); - chan->ops->close (chan); + +l2cap_chan_unlock (chan);l2cap_chan_put (chan);mutex_unlock (&conn->chan_lock);
@@ -4382,20 +4385,21 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn,return 0 ; } +l2cap_chan_hold (chan);l2cap_chan_lock (chan);if (chan->state !=BT_DISCONN ) {l2cap_chan_unlock (chan); +l2cap_chan_put (chan);mutex_unlock (&conn->chan_lock);return 0 ; } -l2cap_chan_hold (chan);l2cap_chan_del (chan,0 ); -l2cap_chan_unlock (chan); - chan->ops->close (chan); + +l2cap_chan_unlock (chan);l2cap_chan_put (chan);mutex_unlock (&conn->chan_lock);
net/bluetooth/l2cap_sock.c +13 -3
@@ -1040,7 +1040,7 @@ done: }/* Kill socket (only if zapped and orphan) -* Must be called on unlocked socket. +* Must be called on unlocked socket, with l2cap channel lock. */ static void l2cap_sock_kill (struct sock *sk) {
@@ -1201,8 +1201,15 @@ static int l2cap_sock_release(struct socket *sock) err =l2cap_sock_shutdown (sock,2 ); +l2cap_chan_hold (l2cap_pi (sk)->chan); +l2cap_chan_lock (l2cap_pi (sk)->chan); +sock_orphan (sk);l2cap_sock_kill (sk); + +l2cap_chan_unlock (l2cap_pi (sk)->chan); +l2cap_chan_put (l2cap_pi (sk)->chan); +return err; }
@@ -1220,12 +1227,15 @@ static void l2cap_sock_cleanup_listen(struct sock *parent)BT_DBG ("child chan %p state %s" , chan,state_to_string (chan->state)); +l2cap_chan_hold (chan);l2cap_chan_lock (chan); +__clear_chan_timer (chan);l2cap_chan_close (chan,ECONNRESET ); -l2cap_chan_unlock (chan); -l2cap_sock_kill (sk); + +l2cap_chan_unlock (chan); +l2cap_chan_put (chan); } }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 34/127 ar5523: Add USB ID of SMCWUSBT-G2 wireless adapter
In reply to Sasha LevinFrom: Mert Dirik <[email protected]>
[ Upstream commit 5b362498a79631f283578b64bf6f4d15ed4cc19a ]
Add the required USB ID for running SMCWUSBT-G2 wireless adapter (SMC "EZ Connect g").
This device uses ar5523 chipset and requires firmware to be loaded. Even though pid of the device is 4507, this patch adds it as 4506 so that AR5523_DEVICE_UG macro can set the AR5523_FLAG_PRE_FIRMWARE flag for pid 4507.
--- drivers/net/wireless/ath/ar5523/ar5523.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/net/wireless/ath/ar5523/ar5523.c +2 -0
@@ -1771,6 +1771,8 @@ static const struct usb_device_id ar5523_id_table[] = {AR5523_DEVICE_UX (0x0846 ,0x4300 ),/* Netgear / WG111U */ AR5523_DEVICE_UG (0x0846 ,0x4250 ),/* Netgear / WG111T */ AR5523_DEVICE_UG (0x0846 ,0x5f00 ),/* Netgear / WPN111 */ +AR5523_DEVICE_UG (0x083a ,0x4506 ),/* SMC / EZ Connect +SMCWUSBT-G2 */ AR5523_DEVICE_UG (0x157e ,0x3006 ),/* Umedia / AR5523_1 */ AR5523_DEVICE_UX (0x157e ,0x3205 ),/* Umedia / AR5523_2 */ AR5523_DEVICE_UG(0x157e, 0x3006), /* Umedia / TEW444UBEU */
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 35/127 selftests/ftrace: fix glob selftest
In reply to Sasha LevinFrom: Sven Schnelle <[email protected]>
[ Upstream commit af4ddd607dff7aabd466a4a878e01b9f592a75ab ]
test.d/ftrace/func-filter-glob.tc is failing on s390 because it has ARCH_INLINE_SPIN_LOCK and friends set to 'y'. So the usual __raw_spin_lock symbol isn't in the ftrace function list. Change '*aw*lock' to '*spin*lock' which would hopefully match some of the locking functions on all platforms.
--- .../testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc +1 -1
@@ -30,7 +30,7 @@ ftrace_filter_check '*schedule*' '^.*schedule.*$' ftrace_filter_check 'schedule*' '^schedule.*$' # filter by *mid*end -ftrace_filter_check '*aw*lock' '.*aw.*lock$' +ftrace_filter_check '*pin*lock' '.*pin.*lock$' # filter by start*mid* ftrace_filter_check 'mutex*try*' '^mutex.*try.*'
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 33/127 ext4: make dioread_nolock the default
In reply to Sasha LevinFrom: Theodore Ts'o <[email protected]>
[ Upstream commit 244adf6426ee31a83f397b700d964cff12a247d3 ]
This fixes the direct I/O versus writeback race which can reveal stale data, and it improves the tail latency of commits on slow devices.
--- fs/ext4/super.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
fs/ext4/super.c +4 -3
@@ -1471,6 +1471,7 @@ static const match_table_t tokens = { {Opt_auto_da_alloc, "auto_da_alloc"}, {Opt_noauto_da_alloc, "noauto_da_alloc"}, {Opt_dioread_nolock, "dioread_nolock"}, + {Opt_dioread_lock, "nodioread_nolock"}, {Opt_dioread_lock, "dioread_lock"}, {Opt_discard, "discard"}, {Opt_nodiscard, "nodiscard"},
@@ -3633,6 +3634,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)set_opt (sb,NO_UID32 );/* xattr user namespace & acls are now defaulted on */ set_opt (sb,XATTR_USER ); +set_opt (sb,DIOREAD_NOLOCK );#ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt (sb,POSIX_ACL );#endif
@@ -3770,9 +3772,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount;if (test_opt (sb,DATA_FLAGS ) ==EXT4_MOUNT_JOURNAL_DATA ) { -printk_once (KERN_WARNING "EXT4-fs: Warning: mounting " -"with data=journal disables delayed " -"allocation and O_DIRECT support!\n" ); +printk_once (KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n" ); +clear_opt (sb,DIOREAD_NOLOCK );if (test_opt2 (sb,EXPLICIT_DELALLOC )) {ext4_msg (sb,KERN_ERR ,"can't mount with " "both data=journal and delalloc" );
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 21/127 debugfs: Fix !DEBUG_FS debugfs_create_automount
In reply to Sasha LevinFrom: Kusanagi Kouichi <[email protected]>
[ Upstream commit 4250b047039d324e0ff65267c8beb5bad5052a86 ]
If DEBUG_FS=n, compile fails with the following error:
kernel/trace/trace.c: In function 'tracing_init_dentry':kernel/trace/trace.c:8658:9: error: passing argument 3 of 'debugfs_create_automount' from incompatible pointer type [-Werror=incompatible-pointer-types]
8658 | trace_automount, NULL);
| ^~~~~~~~~~~~~~~
| |
| struct vfsmount * (*)(struct dentry *, void *)
In file included from kernel/trace/trace.c:24:
./include/linux/debugfs.h:206:25: note: expected 'struct vfsmount * (*)(void *)' but argument is of type 'struct vfsmount * (*)(struct dentry *, void *)'
206 | struct vfsmount *(*f)(void *),
| ~~~~~~~~~~~~~~~~~~~^~~~~~~~~~--- include/linux/debugfs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
include/linux/debugfs.h +3 -2
@@ -77,6 +77,8 @@ static const struct file_operations __fops = { \ .llseek = no_llseek, \ } +typedef struct vfsmount *(*debugfs_automount_t )(struct dentry *,void *); +#if defined(CONFIG_DEBUG_FS )struct dentry *debugfs_lookup (const char *name,struct dentry *parent);
@@ -98,7 +100,6 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent);struct dentry *debugfs_create_symlink (const char *name,struct dentry *parent,const char *dest); -typedef struct vfsmount *(*debugfs_automount_t )(struct dentry *,void *); struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, debugfs_automount_t f,
@@ -227,7 +228,7 @@ static inline struct dentry *debugfs_create_symlink(const char *name,static inline struct dentry *debugfs_create_automount (const char *name,struct dentry *parent, -struct vfsmount *(*f)(void *), +debugfs_automount_t f,void *data) {return ERR_PTR (-ENODEV );
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 29/127 efi/arm: Defer probe of PCIe backed efifb on DT systems
In reply to Sasha LevinFrom: Ard Biesheuvel <[email protected]>
[ Upstream commit 64c8a0cd0a535891d5905c3a1651150f0f141439 ]
The new of_devlink support breaks PCIe probing on ARM platforms booting via UEFI if the firmware exposes a EFI framebuffer that is backed by a PCI device. The reason is that the probing order gets reversed, resulting in a resource conflict on the framebuffer memory window when the PCIe probes last, causing it to give up entirely.
Given that we rely on PCI quirks to deal with EFI framebuffers that get moved around in memory, we cannot simply drop the memory reservation, so instead, let's use the device link infrastructure to register this dependency, and force the probing to occur in the expected order.
--- drivers/firmware/efi/arm-init.c | 107 ++++++++++++++++++++++++++++++-- 1 file changed, 103 insertions(+), 4 deletions(-)
drivers/firmware/efi/arm-init.c +103 -4
@@ -14,10 +14,12 @@#define pr_fmt (fmt) "efi: " fmt#include <linux/efi.h> +#include <linux/fwnode.h> #include <linux/init.h> #include <linux/memblock.h> #include <linux/mm_types.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/of_fdt.h> #include <linux/platform_device.h> #include <linux/screen_info.h>
@@ -271,15 +273,112 @@ void __init efi_init(void)efi_memmap_unmap (); } +static bool efifb_overlaps_pci_range (const struct of_pci_range *range) +{ +u64 fb_base = screen_info.lfb_base; + +if (screen_info.capabilities &VIDEO_CAPABILITY_64BIT_BASE ) + fb_base |= (u64 )(unsigned long )screen_info.ext_lfb_base <<32 ; + +return fb_base >= range->cpu_addr && + fb_base < (range->cpu_addr + range->size); +} + +static struct device_node *find_pci_overlap_node (void ) +{ +struct device_node *np; + +for_each_node_by_type (np,"pci" ) { +struct of_pci_range_parser parser; +struct of_pci_range range; +int err; + + err =of_pci_range_parser_init (&parser, np); +if (err) { +pr_warn ("of_pci_range_parser_init() failed: %d\n" , err); +continue ; + } + +for_each_of_pci_range (&parser, &range) +if (efifb_overlaps_pci_range (&range)) +return np; + } +return NULL ; +} + +/* +* If the efifb framebuffer is backed by a PCI graphics controller, we have +* to ensure that this relation is expressed using a device link when +* running in DT mode, or the probe order may be reversed, resulting in a +* resource reservation conflict on the memory window that the efifb +* framebuffer steals from the PCIe host bridge. +*/ +static int efifb_add_links (const struct fwnode_handle *fwnode, +struct device *dev) +{ +struct device_node *sup_np; +struct device *sup_dev; + + sup_np =find_pci_overlap_node (); + +/* +* If there's no PCI graphics controller backing the efifb, we are +* done here. +*/ +if (!sup_np) +return 0 ; + + sup_dev =get_dev_from_fwnode (&sup_np->fwnode); +of_node_put (sup_np); + +/* +* Return -ENODEV if the PCI graphics controller device hasn't been +* registered yet. This ensures that efifb isn't allowed to probe +* and this function is retried again when new devices are +* registered. +*/ +if (!sup_dev) +return -ENODEV ; + +/* +* If this fails, retrying this function at a later point won't +* change anything. So, don't return an error after this. +*/ +if (!device_link_add (dev, sup_dev,0 )) +dev_warn (dev,"device_link_add() failed\n" ); + +put_device (sup_dev); + +return 0 ; +} + +static const struct fwnode_operations efifb_fwnode_ops = { + .add_links = efifb_add_links, +}; + +static struct fwnode_handle efifb_fwnode = { + .ops = &efifb_fwnode_ops, +}; +static int __init register_gop_device (void ) { -void *pd; +struct platform_device *pd; +int err;if (screen_info.orig_video_isVGA !=VIDEO_TYPE_EFI )return 0 ; - pd =platform_device_register_data (NULL ,"efi-framebuffer" ,0 , - &screen_info,sizeof (screen_info)); -return PTR_ERR_OR_ZERO (pd); + pd =platform_device_alloc ("efi-framebuffer" ,0 ); +if (!pd) +return -ENOMEM ; + +if (IS_ENABLED (CONFIG_PCI )) + pd->dev.fwnode = &efifb_fwnode; + + err =platform_device_add_data (pd, &screen_info,sizeof (screen_info)); +if (err) +return err; + +return platform_device_add (pd); }subsys_initcall (register_gop_device);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 28/127 ACPI: EC: Reference count query handlers under lock
In reply to Sasha LevinFrom: "Rafael J. Wysocki" <[email protected]>
[ Upstream commit 3df663a147fe077a6ee8444ec626738946e65547 ]
There is a race condition in acpi_ec_get_query_handler() theoretically allowing query handlers to go away before refernce counting them.
In order to avoid it, call kref_get() on query handlers under ec->mutex.
Also simplify the code a bit while at it.
--- drivers/acpi/ec.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-)
drivers/acpi/ec.c +4 -12
@@ -1062,29 +1062,21 @@ void acpi_ec_unblock_transactions(void)/* -------------------------------------------------------------------------- Event Management -------------------------------------------------------------------------- */ -static struct acpi_ec_query_handler * -acpi_ec_get_query_handler (struct acpi_ec_query_handler *handler) -{ -if (handler) -kref_get (&handler->kref); -return handler; -} -static struct acpi_ec_query_handler *acpi_ec_get_query_handler_by_value (struct acpi_ec *ec,u8 value) {struct acpi_ec_query_handler *handler; -bool found = false;mutex_lock (&ec->mutex);list_for_each_entry (handler, &ec->list, node) {if (value == handler->query_bit) { - found = true; -break ; +kref_get (&handler->kref); +mutex_unlock (&ec->mutex); +return handler; } }mutex_unlock (&ec->mutex); -return found ?acpi_ec_get_query_handler (handler) :NULL ; +return NULL ; }static void acpi_ec_query_handler_release (struct kref *kref)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 27/127 media: ti-vpe: cal: Restrict DMA to avoid memory corruption
In reply to Sasha LevinFrom: Nikhil Devshatwar <[email protected]>
[ Upstream commit 6e72eab2e7b7a157d554b8f9faed7676047be7c1 ]
When setting DMA for video capture from CSI channel, if the DMA size is not given, it ends up writing as much data as sent by the camera.
This may lead to overwriting the buffers causing memory corruption. Observed green lines on the default framebuffer.
Restrict the DMA to maximum height as specified in the S_FMT ioctl.
--- drivers/media/platform/ti-vpe/cal.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/media/platform/ti-vpe/cal.c +4 -2
@@ -687,12 +687,13 @@ static void pix_proc_config(struct cal_ctx *ctx) }static void cal_wr_dma_config (struct cal_ctx *ctx, -unsigned int width) +unsigned int width,unsigned int height) {u32 val; val =reg_read (ctx->dev,CAL_WR_DMA_CTRL (ctx->csi2_port));set_field (&val, ctx->csi2_port,CAL_WR_DMA_CTRL_CPORT_MASK ); +set_field (&val, height,CAL_WR_DMA_CTRL_YSIZE_MASK );set_field (&val,CAL_WR_DMA_CTRL_DTAG_PIX_DAT ,CAL_WR_DMA_CTRL_DTAG_MASK ); set_field(&val, CAL_WR_DMA_CTRL_MODE_CONST,
@@ -1318,7 +1319,8 @@ static int cal_start_streaming(struct vb2_queue *vq, unsigned int count)csi2_lane_config (ctx);csi2_ctx_config (ctx);pix_proc_config (ctx); -cal_wr_dma_config (ctx, ctx->v_fmt.fmt.pix.bytesperline); +cal_wr_dma_config (ctx, ctx->v_fmt.fmt.pix.bytesperline, + ctx->v_fmt.fmt.pix.height);cal_wr_dma_addr (ctx, addr);csi2_ppi_enable (ctx);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 26/127 seqlock: Require WRITE_ONCE surrounding raw_seqcount_barrier
In reply to Sasha LevinFrom: Marco Elver <[email protected]>
[ Upstream commit bf07132f96d426bcbf2098227fb680915cf44498 ]
This patch proposes to require marked atomic accesses surrounding raw_write_seqcount_barrier. We reason that otherwise there is no way to guarantee propagation nor atomicity of writes before/after the barrier [1]. For example, consider the compiler tears stores either before or after the barrier; in this case, readers may observe a partial value, and because readers are unaware that writes are going on (writes are not in a seq-writer critical section), will complete the seq-reader critical section while having observed some partial state.
[1] https://lwn.net/Articles/793253/
This came up when designing and implementing KCSAN, because KCSAN would flag these accesses as data-races. After careful analysis, our reasoning as above led us to conclude that the best thing to do is to propose an amendment to the raw_seqcount_barrier usage.
--- include/linux/seqlock.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)
include/linux/seqlock.h +9 -2
@@ -243,6 +243,13 @@ static inline void raw_write_seqcount_end(seqcount_t *s)* usual consistency guarantee. It is one wmb cheaper, because we can * collapse the two back-to-back wmb()s. * +* Note that, writes surrounding the barrier should be declared atomic (e.g. +* via WRITE_ONCE): a) to ensure the writes become visible to other threads +* atomically, avoiding compiler optimizations; b) to document which writes are +* meant to propagate to the reader critical section. This is necessary because +* neither writes before and after the barrier are enclosed in a seq-writer +* critical section that would ensure readers are aware of ongoing writes. +* * seqcount_t seq; * bool X = true, Y = false; *
@@ -262,11 +269,11 @@ static inline void raw_write_seqcount_end(seqcount_t *s)* * void write(void) * { -* Y = true; +* WRITE_ONCE(Y, true); * * raw_write_seqcount_barrier(seq); * -* X = false; +* WRITE_ONCE(X, false); * } */ static inline void raw_write_seqcount_barrier (seqcount_t *s)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 25/127 rt_cpu_seq_next should increase position index
In reply to Sasha LevinFrom: Vasily Averin <[email protected]>
[ Upstream commit a3ea86739f1bc7e121d921842f0f4a8ab1af94d9 ]
if seq_file .next fuction does not change position index, read after some lseek can generate unexpected output.
https://bugzilla.kernel.org/show_bug.cgi?id=206283
--- net/ipv4/route.c | 1 + 1 file changed, 1 insertion(+)
net/ipv4/route.c +1 -0
@@ -276,6 +276,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1 ;return &per_cpu (rt_cache_stat, cpu); } + (*pos)++;return NULL ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 24/127 neigh_stat_seq_next() should increase position index
In reply to Sasha LevinFrom: Vasily Averin <[email protected]>
[ Upstream commit 1e3f9f073c47bee7c23e77316b07bc12338c5bba ]
if seq_file .next fuction does not change position index, read after some lseek can generate unexpected output.
https://bugzilla.kernel.org/show_bug.cgi?id=206283
--- net/core/neighbour.c | 1 + 1 file changed, 1 insertion(+)
net/core/neighbour.c +1 -0
@@ -2836,6 +2836,7 @@ static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1 ;return per_cpu_ptr (tbl->stats, cpu); } + (*pos)++;return NULL ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 18/127 RDMA/iw_cgxb4: Fix an error handling path in 'c4iw_connect()'
In reply to Sasha LevinFrom: Christophe JAILLET <[email protected]>
[ Upstream commit 9067f2f0b41d7e817fc8c5259bab1f17512b0147 ]
We should jump to fail3 in order to undo the 'xa_insert_irq()' call.
--- drivers/infiniband/hw/cxgb4/cm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/infiniband/hw/cxgb4/cm.c +2 -2
@@ -3265,7 +3265,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)if (raddr->sin_addr.s_addr ==htonl (INADDR_ANY )) { err =pick_local_ipaddrs (dev, cm_id);if (err) - goto fail2; + goto fail3; }/* find a route */
@@ -3287,7 +3287,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)if (ipv6_addr_type (&raddr6->sin6_addr) ==IPV6_ADDR_ANY ) { err =pick_local_ip6addrs (dev, cm_id);if (err) - goto fail2; + goto fail3; }/* find a route */
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 19/127 mmc: core: Fix size overflow for mmc partitions
In reply to Sasha LevinFrom: Bradley Bolen <[email protected]>
[ Upstream commit f3d7c2292d104519195fdb11192daec13229c219 ]
With large eMMC cards, it is possible to create general purpose partitions that are bigger than 4GB. The size member of the mmc_part struct is only an unsigned int which overflows for gp partitions larger than 4GB. Change this to a u64 to handle the overflow.
--- drivers/mmc/core/mmc.c | 9 ++++----- include/linux/mmc/card.h | 2 +- 2 files changed, 5 insertions(+), 6 deletions(-)
drivers/mmc/core/mmc.c +4 -5
@@ -300,7 +300,7 @@ static void mmc_manage_enhanced_area(struct mmc_card *card, u8 *ext_csd) } } -static void mmc_part_add (struct mmc_card *card,unsigned int size, +static void mmc_part_add (struct mmc_card *card,u64 size,unsigned int part_cfg,char *name,int idx,bool ro,int area_type) {
@@ -316,7 +316,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd) {int idx;u8 hc_erase_grp_sz, hc_wp_grp_sz; -unsigned int part_size; +u64 part_size;/* * General purpose partition feature support --
@@ -346,8 +346,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd) (ext_csd[EXT_CSD_GP_SIZE_MULT + idx *3 +1 ] <<8 ) + ext_csd[EXT_CSD_GP_SIZE_MULT + idx *3 ]; - part_size *= (size_t )(hc_erase_grp_sz * - hc_wp_grp_sz); + part_size *= (hc_erase_grp_sz * hc_wp_grp_sz); mmc_part_add(card, part_size << 19, EXT_CSD_PART_CONFIG_ACC_GP0 + idx, "gp%d", idx, false,
@@ -365,7 +364,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd)static int mmc_decode_ext_csd (struct mmc_card *card,u8 *ext_csd) {int err =0 , idx; -unsigned int part_size; +u64 part_size;struct device_node *np;bool broken_hpi = false;
include/linux/mmc/card.h +1 -1
@@ -226,7 +226,7 @@ struct mmc_queue_req;* MMC Physical partitions */ struct mmc_part { -unsigned int size;/* partition size (in bytes) */ +u64 size;/* partition size (in bytes) */ unsigned int part_cfg;/* partition type */ char name[MAX_MMC_PART_NAME_LEN ];bool force_ro;/* to make boot parts RO by default */
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 17/127 xfs: fix attr leaf header freemap.size underflow
In reply to Sasha LevinFrom: Brian Foster <[email protected]>
[ Upstream commit 2a2b5932db67586bacc560cc065d62faece5b996 ]
The leaf format xattr addition helper xfs_attr3_leaf_add_work() adjusts the block freemap in a couple places. The first update drops the size of the freemap that the caller had already selected to place the xattr name/value data. Before the function returns, it also checks whether the entries array has encroached on a freemap range by virtue of the new entry addition. This is necessary because the entries array grows from the start of the block (but end of the block header) towards the end of the block while the name/value data grows from the end of the block in the opposite direction. If the associated freemap is already empty, however, size is zero and the subtraction underflows the field and causes corruption.
This is reproduced rarely by generic/070. The observed behavior is that a smaller sized freemap is aligned to the end of the entries list, several subsequent xattr additions land in larger freemaps and the entries list expands into the smaller freemap until it is fully consumed and then underflows. Note that it is not otherwise a corruption for the entries array to consume an empty freemap because the nameval list (i.e. the firstused pointer in the xattr header) starts beyond the end of the corrupted freemap.
Update the freemap size modification to account for the fact that the freemap entry can be empty and thus stale.
--- fs/xfs/libxfs/xfs_attr_leaf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
fs/xfs/libxfs/xfs_attr_leaf.c +3 -1
@@ -1335,7 +1335,9 @@ xfs_attr3_leaf_add_work(for (i =0 ; i <XFS_ATTR_LEAF_MAPSIZE ; i++) {if (ichdr->freemap[i].base == tmp) { ichdr->freemap[i].base +=sizeof (xfs_attr_leaf_entry_t); - ichdr->freemap[i].size -=sizeof (xfs_attr_leaf_entry_t); + ichdr->freemap[i].size -= +min_t (uint16_t, ichdr->freemap[i].size, +sizeof (xfs_attr_leaf_entry_t)); } } ichdr->usedbytes +=xfs_attr_leaf_entsize (leaf, args->index);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 14/127 tracing: Adding NULL checks for trace_array descriptor pointer
In reply to Sasha LevinFrom: Divya Indi <[email protected]>
[ Upstream commit 953ae45a0c25e09428d4a03d7654f97ab8a36647 ]
As part of commit f45d1225adb0 ("tracing: Kernel access to Ftrace instances") we exported certain functions. Here, we are adding some additional NULL checks to ensure safe usage by users of these APIs.
--- kernel/trace/trace.c | 3 +++ kernel/trace/trace_events.c | 2 ++ 2 files changed, 5 insertions(+)
kernel/trace/trace.c +3 -0
@@ -3035,6 +3035,9 @@ int trace_array_printk(struct trace_array *tr,if (!(global_trace.trace_flags &TRACE_ITER_PRINTK ))return 0 ; +if (!tr) +return -ENOENT ; +va_start (ap, fmt); ret =trace_array_vprintk (tr, ip, fmt, ap);va_end (ap);
kernel/trace/trace_events.c +2 -0
@@ -799,6 +799,8 @@ static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)char *event =NULL , *sub =NULL , *match;int ret; +if (!tr) +return -ENOENT ;/* * The buf format can be <subsystem>:<event-name> * *:<event-name> means any event by that name.
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 13/127 USB: serial: mos7840: fix probe error handling
In reply to Sasha LevinFrom: Johan Hovold <[email protected]>
[ Upstream commit 960fbd1ca584a5b4cd818255769769d42bfc6dbe ]
The driver would return success and leave the port structures half-initialised if any of the register accesses during probe fails.
This would specifically leave the port control urb unallocated, something which could trigger a NULL pointer dereference on interrupt events.
Fortunately the interrupt implementation is completely broken and has never even been enabled...
Note that the zero-length-enable register write used to set the zle-flag for all ports is moved to attach.
--- drivers/usb/serial/mos7840.c | 48 +++++++++++++++++++++--------------- 1 file changed, 28 insertions(+), 20 deletions(-)
drivers/usb/serial/mos7840.c +28 -20
@@ -2131,6 +2131,23 @@ static int mos7840_calc_num_ports(struct usb_serial *serial,return num_ports; } +static int mos7840_attach (struct usb_serial *serial) +{ +struct device *dev = &serial->interface->dev; +int status; +u16 val; + +/* Zero Length flag enable */ + val =0x0f ; + status =mos7840_set_reg_sync (serial->port[0 ],ZLP_REG5 , val); +if (status <0 ) +dev_dbg (dev,"Writing ZLP_REG5 failed status-0x%x\n" , status); +else +dev_dbg (dev,"ZLP_REG5 Writing success status%d\n" , status); + +return status; +} +static int mos7840_port_probe (struct usb_serial_port *port) {struct usb_serial *serial = port->serial;
@@ -2194,7 +2211,7 @@ static int mos7840_port_probe(struct usb_serial_port *port) mos7840_port->ControlRegOffset, &Data);if (status <0 ) {dev_dbg (&port->dev,"Reading ControlReg failed status-0x%x\n" , status); - goto out; + goto error; }else dev_dbg (&port->dev,"ControlReg Reading success val is %x, status%d\n" , Data, status); Data |=0x08 ;/* setting driver done bit */
@@ -2206,7 +2223,7 @@ static int mos7840_port_probe(struct usb_serial_port *port) mos7840_port->ControlRegOffset, Data);if (status <0 ) {dev_dbg (&port->dev,"Writing ControlReg failed(rx_disable) status-0x%x\n" , status); - goto out; + goto error; }else dev_dbg (&port->dev,"ControlReg Writing success(rx_disable) status%d\n" , status);
@@ -2217,7 +2234,7 @@ static int mos7840_port_probe(struct usb_serial_port *port) (__u16) (mos7840_port->DcrRegOffset + 0), Data);if (status <0 ) {dev_dbg (&port->dev,"Writing DCR0 failed status-0x%x\n" , status); - goto out; + goto error; }else dev_dbg (&port->dev,"DCR0 Writing success status%d\n" , status);
@@ -2226,7 +2243,7 @@ static int mos7840_port_probe(struct usb_serial_port *port) (__u16) (mos7840_port->DcrRegOffset + 1), Data);if (status <0 ) {dev_dbg (&port->dev,"Writing DCR1 failed status-0x%x\n" , status); - goto out; + goto error; }else dev_dbg (&port->dev,"DCR1 Writing success status%d\n" , status);
@@ -2235,7 +2252,7 @@ static int mos7840_port_probe(struct usb_serial_port *port) (__u16) (mos7840_port->DcrRegOffset + 2), Data);if (status <0 ) {dev_dbg (&port->dev,"Writing DCR2 failed status-0x%x\n" , status); - goto out; + goto error; }else dev_dbg (&port->dev,"DCR2 Writing success status%d\n" , status);
@@ -2244,7 +2261,7 @@ static int mos7840_port_probe(struct usb_serial_port *port) status =mos7840_set_reg_sync (port,CLK_START_VALUE_REGISTER , Data);if (status <0 ) {dev_dbg (&port->dev,"Writing CLK_START_VALUE_REGISTER failed status-0x%x\n" , status); - goto out; + goto error; }else dev_dbg (&port->dev,"CLK_START_VALUE_REGISTER Writing success status%d\n" , status);
@@ -2261,7 +2278,7 @@ static int mos7840_port_probe(struct usb_serial_port *port) status =mos7840_set_uart_reg (port,SCRATCH_PAD_REGISTER , Data);if (status <0 ) {dev_dbg (&port->dev,"Writing SCRATCH_PAD_REGISTER failed status-0x%x\n" , status); - goto out; + goto error; }else dev_dbg (&port->dev,"SCRATCH_PAD_REGISTER Writing success status%d\n" , status);
@@ -2275,7 +2292,7 @@ static int mos7840_port_probe(struct usb_serial_port *port) (__u16)(ZLP_REG1 + ((__u16) mos7840_port->port_num)));if (status <0 ) {dev_dbg (&port->dev,"Writing ZLP_REG%d failed status-0x%x\n" , pnum +2 , status); - goto out; + goto error; }else dev_dbg (&port->dev,"ZLP_REG%d Writing success status%d\n" , pnum +2 , status); }else {
@@ -2287,7 +2304,7 @@ static int mos7840_port_probe(struct usb_serial_port *port) (__u16)(ZLP_REG1 + ((__u16) mos7840_port->port_num) - 0x1));if (status <0 ) {dev_dbg (&port->dev,"Writing ZLP_REG%d failed status-0x%x\n" , pnum +1 , status); - goto out; + goto error; }else dev_dbg (&port->dev,"ZLP_REG%d Writing success status%d\n" , pnum +1 , status);
@@ -2328,17 +2345,7 @@ static int mos7840_port_probe(struct usb_serial_port *port)/* Turn off LED */ mos7840_set_led_sync (port,MODEM_CONTROL_REGISTER ,0x0300 ); } -out: -if (pnum == serial->num_ports -1 ) { -/* Zero Length flag enable */ - Data =0x0f ; - status =mos7840_set_reg_sync (serial->port[0 ],ZLP_REG5 , Data); -if (status <0 ) { -dev_dbg (&port->dev,"Writing ZLP_REG5 failed status-0x%x\n" , status); - goto error; - }else -dev_dbg (&port->dev,"ZLP_REG5 Writing success status%d\n" , status); - } +return 0 ; error:kfree (mos7840_port->led_dr);
@@ -2394,6 +2401,7 @@ static struct usb_serial_driver moschip7840_4port_device = { .unthrottle = mos7840_unthrottle, .calc_num_ports = mos7840_calc_num_ports, .probe = mos7840_probe, + .attach = mos7840_attach, .ioctl = mos7840_ioctl, .set_termios = mos7840_set_termios, .break_ctl = mos7840_break,
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 12/127 mfd: mfd-core: Protect against NULL call-back function pointer
In reply to Sasha LevinFrom: Lee Jones <[email protected]>
[ Upstream commit b195e101580db390f50b0d587b7f66f241d2bc88 ]
If a child device calls mfd_cell_{en,dis}able() without an appropriate call-back being set, we are likely to encounter a panic. Avoid this by adding suitable checking.
--- drivers/mfd/mfd-core.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
drivers/mfd/mfd-core.c +10 -0
@@ -32,6 +32,11 @@ int mfd_cell_enable(struct platform_device *pdev)const struct mfd_cell *cell =mfd_get_cell (pdev);int err =0 ; +if (!cell->enable) { +dev_dbg (&pdev->dev,"No .enable() call-back registered\n" ); +return 0 ; + } +/* only call enable hook if the cell wasn't previously enabled */ if (atomic_inc_return (cell->usage_count) ==1 ) err = cell->enable (pdev);
@@ -49,6 +54,11 @@ int mfd_cell_disable(struct platform_device *pdev)const struct mfd_cell *cell =mfd_get_cell (pdev);int err =0 ; +if (!cell->disable) { +dev_dbg (&pdev->dev,"No .disable() call-back registered\n" ); +return 0 ; + } +/* only disable if no other clients are using it */ if (atomic_dec_return (cell->usage_count) ==0 ) err = cell->disable (pdev);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 9/127 scsi: fnic: fix use after free
In reply to Sasha LevinFrom: Pan Bian <[email protected]>
[ Upstream commit ec990306f77fd4c58c3b27cc3b3c53032d6e6670 ]
The memory chunk io_req is released by mempool_free. Accessing io_req->start_time will result in a use after free bug. The variable start_time is a backup of the timestamp. So, use start_time here to avoid use after free.
--- drivers/scsi/fnic/fnic_scsi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/scsi/fnic/fnic_scsi.c +2 -1
@@ -1034,7 +1034,8 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic,atomic64_inc (&fnic_stats->io_stats.io_completions); - io_duration_time =jiffies_to_msecs (jiffies) -jiffies_to_msecs (io_req->start_time); + io_duration_time =jiffies_to_msecs (jiffies) - +jiffies_to_msecs (start_time);if (io_duration_time <=10 )atomic64_inc (&fnic_stats->io_stats.io_btw_0_to_10_msec);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 7/127 ata: sata_mv, avoid trigerrable BUG_ON
In reply to Sasha LevinFrom: Jiri Slaby <[email protected]>
[ Upstream commit e9f691d899188679746eeb96e6cb520459eda9b4 ]
There are several reports that the BUG_ON on unsupported command in mv_qc_prep can be triggered under some circumstances:
https://bugzilla.suse.com/show_bug.cgi?id=1110252
https://serverfault.com/questions/888897/raid-problems-after-power-outage
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1652185
https://bugs.centos.org/view.php?id=14998
Let sata_mv handle the failure gracefully: warn about that incl. the failed command number and return an AC_ERR_INVALID error. We can do that now thanks to the previous patch.
Remove also the long-standing FIXME.
[v2] use %.2x as commands are defined as hexa.
--- drivers/ata/sata_mv.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)
drivers/ata/sata_mv.c +3 -5
@@ -2111,12 +2111,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)* non-NCQ mode are: [RW] STREAM DMA and W DMA FUA EXT, none * of which are defined/used by Linux. If we get here, this * driver needs work. -* -* FIXME: modify libata to give qc_prep a return value and -* return error here. */ -BUG_ON (tf->command); -break ; +ata_port_err (ap,"%s: unsupported command: %.2x\n" , __func__, + tf->command); +return AC_ERR_INVALID ; }mv_crqb_pack_cmd (cw++, tf->nsect,ATA_REG_NSECT ,0 );mv_crqb_pack_cmd (cw++, tf->hob_lbal,ATA_REG_LBAL ,0 );
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 8/127 PM / devfreq: tegra30: Fix integer overflow on CPU's freq max out
In reply to Sasha LevinFrom: Dmitry Osipenko <[email protected]>
[ Upstream commit 53b4b2aeee26f42cde5ff2a16dd0d8590c51a55a ]
There is another kHz-conversion bug in the code, resulting in integer overflow. Although, this time the resulting value is 4294966296 and it's close to ULONG_MAX, which is okay in this case.
--- drivers/devfreq/tegra-devfreq.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/devfreq/tegra-devfreq.c +3 -1
@@ -79,6 +79,8 @@#define KHZ 1000 +#define KHZ_MAX (ULONG_MAX / KHZ) +/* Assume that the bus is saturated if the utilization is 25% */ #define BUS_SATURATION_RATIO 25
@@ -179,7 +181,7 @@ struct tegra_actmon_emc_ratio { };static struct tegra_actmon_emc_ratio actmon_emc_ratios[] = { - {1400000 ,ULONG_MAX }, + {1400000 ,KHZ_MAX }, {1200000 ,750000 }, {1100000 ,600000 }, {1000000 ,500000 },
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 6/127 media: smiapp: Fix error handling at NVM reading
In reply to Sasha LevinFrom: Sakari Ailus <[email protected]>
[ Upstream commit a5b1d5413534607b05fb34470ff62bf395f5c8d0 ]
If NVM reading failed, the device was left powered on. Fix that.
--- drivers/media/i2c/smiapp/smiapp-core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/media/i2c/smiapp/smiapp-core.c +2 -1
@@ -2338,11 +2338,12 @@ smiapp_sysfs_nvm_read(struct device *dev, struct device_attribute *attr,if (rval <0 ) {if (rval != -EBUSY && rval != -EAGAIN )pm_runtime_set_active (&client->dev); -pm_runtime_put (&client->dev); +pm_runtime_put_noidle (&client->dev);return -ENODEV ; }if (smiapp_read_nvm (sensor, sensor->nvm)) { +pm_runtime_put (&client->dev);dev_err (&client->dev,"nvm read failed\n" );return -ENODEV ; }
Signature · 1 line
2.25.1
Re: [PATCH AUTOSEL 4.14 112/127] perf parse-events: Fix incorrect conversion of 'if () free()' to 'zfree()'
In reply to Sasha LevinQuoted 18 lines · Sasha Levin
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit
7fcdccd4237724931d9773d1e3039bfe053a6f52]When applying a patch by Ian I incorrectly converted to
zfree()an expression that involved testing some other struct member, not the one being freed, which lead to bugs reproduceable by:$ perf stat -e i/bs,tsc,L2/o sleep 1 WARNING: multiple event parsing errors Segmentation fault (core dumped) $Fix it by restoring the test for
pos->free_strbefore freeingpos->val.str, but continue usingzfree(&pos->val.str)to set that member to NULL after freeing it.
Quoted 14 lines
Reported-by Ian Rogers <[email protected]>Fixes e8dfb81838b1 ("perf parse-events: Fix memory leaks found on parse_events")Cc Adrian Hunter <[email protected]>Cc Alexander Shishkin <[email protected]>Cc Andi Kleen <[email protected]>Cc Jiri Olsa <[email protected]>Cc Leo Yan <[email protected]>Cc Mark Rutland <[email protected]>Cc Namhyung Kim <[email protected]>Cc Peter Zijlstra <[email protected]>Cc Stephane Eranian <[email protected]>Signed-off-by Arnaldo Carvalho de Melo <[email protected]>Signed-off-by Sasha Levin <[email protected]>
stable rc 4.14 perf build broken.
Quoted 9 lines
--- tools/perf/util/parse-events.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)tools/perf/util/parse-events.c +0
-0
tools/perf/util/parse-events.c static int __parse_events_add_pmu(struct parse_events_state *parse_state, · line 1265
Quoted 9 lines
tools/perf/util/parse-events.c +2
-1@@ -1258,7 +1258,8 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,list_for_each_entry_safe (pos, tmp, &config_terms, list) {list_del_init (&pos->list); -zfree (&pos->val.str); +if (pos->free_str) +zfree (&pos->val.str);free (pos); }return -EINVAL ;
util/parse-events.c: In function '__parse_events_add_pmu':util/parse-events.c:1261:11: error: 'struct perf_evsel_config_term' has no member named 'free_str'
if (pos->free_str)
^~In file included from util/evlist.h:14:0,
from util/parse-events.c:10:util/parse-events.c:1262:20: error: 'union <anonymous>' has no member named 'str'
zfree(&pos->val.str);
^
util/util.h:27:29: note: in definition of macro 'zfree'
#define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
^~~
util/parse-events.c:1262:20: error: 'union <anonymous>' has no member
named 'str'
zfree(&pos->val.str);
^
util/util.h:27:36: note: in definition of macro 'zfree'
#define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
^~~full build link,
https://ci.linaro.org/view/lkft/job/openembedded-lkft-linux-stable-rc-4.14/DISTRO=lkft,MACHINE=intel-corei7-64,label=docker-lkft/938/consoleText
Signature · 2 lines
Linaro LKFT https://lkft.linaro.org
Quoted 3 lines
--
2.25.1
Sasha Levin
maintainerRe: [PATCH AUTOSEL 4.14 112/127] perf parse-events: Fix incorrect conversion of 'if () free()' to 'zfree()'
Quoted 34 lines · Naresh Kamboju
Quoted 18 lines · Sasha Levin
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit
7fcdccd4237724931d9773d1e3039bfe053a6f52]When applying a patch by Ian I incorrectly converted to
zfree()an expression that involved testing some other struct member, not the one being freed, which lead to bugs reproduceable by:$ perf stat -e i/bs,tsc,L2/o sleep 1 WARNING: multiple event parsing errors Segmentation fault (core dumped) $Fix it by restoring the test for
pos->free_strbefore freeingpos->val.str, but continue usingzfree(&pos->val.str)to set that member to NULL after freeing it.Quoted 14 lines
Reported-by Ian Rogers <[email protected]>Fixes e8dfb81838b1 ("perf parse-events: Fix memory leaks found on parse_events")Cc Adrian Hunter <[email protected]>Cc Alexander Shishkin <[email protected]>Cc Andi Kleen <[email protected]>Cc Jiri Olsa <[email protected]>Cc Leo Yan <[email protected]>Cc Mark Rutland <[email protected]>Cc Namhyung Kim <[email protected]>Cc Peter Zijlstra <[email protected]>Cc Stephane Eranian <[email protected]>Signed-off-by Arnaldo Carvalho de Melo <[email protected]>Signed-off-by Sasha Levin <[email protected]>
Quoted 1 line
stable rc 4.14 perf build broken.
Dropped, thanks!
Signature · 2 lines
Thanks, Sasha