[PATCH v3 0/2] mm/memory-failure: Poison read receives SIGKILL instead of SIGBUS issue

[PATCH v3 0/2] mm/memory-failure: Poison read receives SIGKILL instead of SIGBUS issue

[Jane Chu]

Changes in v3:
 - move **tk cleanup to its own patch

Changes in v2:
 - move 'tk' allocations internal to add_to_kill(), suggested by Dan;
 - ran checkpatch.pl check, pointed out by Matthew;
 - Noaya pointed out that v1 would have missed the SIGKILL
   if "tk->addr == -EFAULT", since the code returns early.
   Incorporated Noaya's suggestion, also, skip VMAs where
   "tk->size_shift == 0" for zone device page, and deliver SIGBUS
   when "tk->size_shift != 0" so the payload is helpful;
 - added Suggested-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

Jane Chu (2):
  mm/memory-failure.c clean up around tk pre-allocation
  mm/memory-failure: Poison read receives SIGKILL instead of SIGBUS if
    mmaped more than once

 mm/memory-failure.c | 62 ++++++++++++++++++++++-------------------------------
 1 file changed, 26 insertions(+), 36 deletions(-)

-- 
1.8.3.1

[PATCH v3 1/2] mm/memory-failure.c clean up around tk pre-allocation

[Jane Chu]

add_to_kill() expects the first 'tk' to be pre-allocated, it makes
subsequent allocations on need basis, this makes the code a bit
difficult to read. Move all the allocation internal to add_to_kill()
and drop the **tk argument.

Signed-off-by: Jane Chu <jane.chu@oracle.com>
---
 mm/memory-failure.c | 40 +++++++++++++---------------------------
 1 file changed, 13 insertions(+), 27 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index d9cc660..51d5b20 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -304,25 +304,19 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page,
 /*
  * Schedule a process for later kill.
  * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM.
- * TBD would GFP_NOIO be enough?
  */
 static void add_to_kill(struct task_struct *tsk, struct page *p,
 		       struct vm_area_struct *vma,
-		       struct list_head *to_kill,
-		       struct to_kill **tkc)
+		       struct list_head *to_kill)
 {
 	struct to_kill *tk;
 
-	if (*tkc) {
-		tk = *tkc;
-		*tkc = NULL;
-	} else {
-		tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC);
-		if (!tk) {
-			pr_err("Memory failure: Out of memory while machine check handling\n");
-			return;
-		}
+	tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC);
+	if (!tk) {
+		pr_err("Memory failure: Out of memory while machine check handling\n");
+		return;
 	}
+
 	tk->addr = page_address_in_vma(p, vma);
 	tk->addr_valid = 1;
 	if (is_zone_device_page(p))
@@ -341,6 +335,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
 			page_to_pfn(p), tsk->comm);
 		tk->addr_valid = 0;
 	}
+
 	get_task_struct(tsk);
 	tk->tsk = tsk;
 	list_add_tail(&tk->nd, to_kill);
@@ -432,7 +427,7 @@ static struct task_struct *task_early_kill(struct task_struct *tsk,
  * Collect processes when the error hit an anonymous page.
  */
 static void collect_procs_anon(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc, int force_early)
+				int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -457,7 +452,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 			if (!page_mapped_in_vma(page, vma))
 				continue;
 			if (vma->vm_mm == t->mm)
-				add_to_kill(t, page, vma, to_kill, tkc);
+				add_to_kill(t, page, vma, to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -468,7 +463,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
  * Collect processes when the error hit a file mapped page.
  */
 static void collect_procs_file(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc, int force_early)
+				int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -492,7 +487,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 			 * to be informed of all such data corruptions.
 			 */
 			if (vma->vm_mm == t->mm)
-				add_to_kill(t, page, vma, to_kill, tkc);
+				add_to_kill(t, page, vma, to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -501,26 +496,17 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 
 /*
  * Collect the processes who have the corrupted page mapped to kill.
- * This is done in two steps for locking reasons.
- * First preallocate one tokill structure outside the spin locks,
- * so that we can kill at least one process reasonably reliable.
  */
 static void collect_procs(struct page *page, struct list_head *tokill,
 				int force_early)
 {
-	struct to_kill *tk;
-
 	if (!page->mapping)
 		return;
 
-	tk = kmalloc(sizeof(struct to_kill), GFP_NOIO);
-	if (!tk)
-		return;
 	if (PageAnon(page))
-		collect_procs_anon(page, tokill, &tk, force_early);
+		collect_procs_anon(page, tokill, force_early);
 	else
-		collect_procs_file(page, tokill, &tk, force_early);
-	kfree(tk);
+		collect_procs_file(page, tokill, force_early);
 }
 
 static const char *action_name[] = {
-- 
1.8.3.1

[PATCH v3 2/2] mm/memory-failure: Poison read receives SIGKILL instead of SIGBUS if mmaped more than once

[Jane Chu]

Mmap /dev/dax more than once, then read the poison location using address
from one of the mappings. The other mappings due to not having the page
mapped in will cause SIGKILLs delivered to the process. SIGKILL succeeds
over SIGBUS, so user process looses the opportunity to handle the UE.

Although one may add MAP_POPULATE to mmap(2) to work around the issue,
MAP_POPULATE makes mapping 128GB of pmem several magnitudes slower, so
isn't always an option.

Details -

ndctl inject-error --block=10 --count=1 namespace6.0

./read_poison -x dax6.0 -o 5120 -m 2
mmaped address 0x7f5bb6600000
mmaped address 0x7f3cf3600000
doing local read at address 0x7f3cf3601400
Killed

Console messages in instrumented kernel -

mce: Uncorrected hardware memory error in user-access at edbe201400
Memory failure: tk->addr = 7f5bb6601000
Memory failure: address edbe201: call dev_pagemap_mapping_shift
dev_pagemap_mapping_shift: page edbe201: no PUD
Memory failure: tk->size_shift == 0
Memory failure: Unable to find user space address edbe201 in read_poison
Memory failure: tk->addr = 7f3cf3601000
Memory failure: address edbe201: call dev_pagemap_mapping_shift
Memory failure: tk->size_shift = 21
Memory failure: 0xedbe201: forcibly killing read_poison:22434 because of failure to unmap corrupted page
  => to deliver SIGKILL
Memory failure: 0xedbe201: Killing read_poison:22434 due to hardware memory corruption
  => to deliver SIGBUS

Signed-off-by: Jane Chu <jane.chu@oracle.com>
Suggested-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
---
 mm/memory-failure.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 51d5b20..f668c88 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -199,7 +199,6 @@ struct to_kill {
 	struct task_struct *tsk;
 	unsigned long addr;
 	short size_shift;
-	char addr_valid;
 };
 
 /*
@@ -318,22 +317,27 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
 	}
 
 	tk->addr = page_address_in_vma(p, vma);
-	tk->addr_valid = 1;
 	if (is_zone_device_page(p))
 		tk->size_shift = dev_pagemap_mapping_shift(p, vma);
 	else
 		tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT;
 
 	/*
-	 * In theory we don't have to kill when the page was
-	 * munmaped. But it could be also a mremap. Since that's
-	 * likely very rare kill anyways just out of paranoia, but use
-	 * a SIGKILL because the error is not contained anymore.
+	 * Send SIGKILL if "tk->addr == -EFAULT". Also, as
+	 * "tk->size_shift" is always non-zero for !is_zone_device_page(),
+	 * so "tk->size_shift == 0" effectively checks no mapping on
+	 * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times
+	 * to a process' address space, it's possible not all N VMAs
+	 * contain mappings for the page, but at least one VMA does.
+	 * Only deliver SIGBUS with payload derived from the VMA that
+	 * has a mapping for the page.
 	 */
-	if (tk->addr == -EFAULT || tk->size_shift == 0) {
+	if (tk->addr == -EFAULT) { 
 		pr_info("Memory failure: Unable to find user space address %lx in %s\n",
 			page_to_pfn(p), tsk->comm);
-		tk->addr_valid = 0;
+	} else if (tk->size_shift == 0) {
+		kfree(tk);
+		return;
 	}
 
 	get_task_struct(tsk);
@@ -361,7 +365,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
 			 * make sure the process doesn't catch the
 			 * signal and then access the memory. Just kill it.
 			 */
-			if (fail || tk->addr_valid == 0) {
+			if (fail || tk->addr == -EFAULT) {
 				pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
 				       pfn, tk->tsk->comm, tk->tsk->pid);
 				do_send_sig_info(SIGKILL, SEND_SIG_PRIV,
-- 
1.8.3.1

Re: [PATCH v3 2/2] mm/memory-failure: Poison read receives SIGKILL instead of SIGBUS if mmaped more than once

[Naoya Horiguchi]

On Thu, Jul 25, 2019 at 04:01:41PM -0600, Jane Chu wrote:
> Mmap /dev/dax more than once, then read the poison location using address
> from one of the mappings. The other mappings due to not having the page
> mapped in will cause SIGKILLs delivered to the process. SIGKILL succeeds
> over SIGBUS, so user process looses the opportunity to handle the UE.
> 
> Although one may add MAP_POPULATE to mmap(2) to work around the issue,
> MAP_POPULATE makes mapping 128GB of pmem several magnitudes slower, so
> isn't always an option.
> 
> Details -
> 
> ndctl inject-error --block=10 --count=1 namespace6.0
> 
> ./read_poison -x dax6.0 -o 5120 -m 2
> mmaped address 0x7f5bb6600000
> mmaped address 0x7f3cf3600000
> doing local read at address 0x7f3cf3601400
> Killed
> 
> Console messages in instrumented kernel -
> 
> mce: Uncorrected hardware memory error in user-access at edbe201400
> Memory failure: tk->addr = 7f5bb6601000
> Memory failure: address edbe201: call dev_pagemap_mapping_shift
> dev_pagemap_mapping_shift: page edbe201: no PUD
> Memory failure: tk->size_shift == 0
> Memory failure: Unable to find user space address edbe201 in read_poison
> Memory failure: tk->addr = 7f3cf3601000
> Memory failure: address edbe201: call dev_pagemap_mapping_shift
> Memory failure: tk->size_shift = 21
> Memory failure: 0xedbe201: forcibly killing read_poison:22434 because of failure to unmap corrupted page
>   => to deliver SIGKILL
> Memory failure: 0xedbe201: Killing read_poison:22434 due to hardware memory corruption
>   => to deliver SIGBUS
> 
> Signed-off-by: Jane Chu <jane.chu@oracle.com>
> Suggested-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
> ---
>  mm/memory-failure.c | 22 +++++++++++++---------
>  1 file changed, 13 insertions(+), 9 deletions(-)
> 
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index 51d5b20..f668c88 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -199,7 +199,6 @@ struct to_kill {
>  	struct task_struct *tsk;
>  	unsigned long addr;
>  	short size_shift;
> -	char addr_valid;
>  };
>  
>  /*
> @@ -318,22 +317,27 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
>  	}
>  
>  	tk->addr = page_address_in_vma(p, vma);
> -	tk->addr_valid = 1;
>  	if (is_zone_device_page(p))
>  		tk->size_shift = dev_pagemap_mapping_shift(p, vma);
>  	else
>  		tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT;
>  
>  	/*
> -	 * In theory we don't have to kill when the page was
> -	 * munmaped. But it could be also a mremap. Since that's
> -	 * likely very rare kill anyways just out of paranoia, but use
> -	 * a SIGKILL because the error is not contained anymore.
> +	 * Send SIGKILL if "tk->addr == -EFAULT". Also, as
> +	 * "tk->size_shift" is always non-zero for !is_zone_device_page(),
> +	 * so "tk->size_shift == 0" effectively checks no mapping on
> +	 * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times
> +	 * to a process' address space, it's possible not all N VMAs
> +	 * contain mappings for the page, but at least one VMA does.
> +	 * Only deliver SIGBUS with payload derived from the VMA that
> +	 * has a mapping for the page.
>  	 */
> -	if (tk->addr == -EFAULT || tk->size_shift == 0) {
> +	if (tk->addr == -EFAULT) { 
                              ^
(sorry nitpicking...) there's a trailing whitespace.
Otherwise looks good to me.

Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

>  		pr_info("Memory failure: Unable to find user space address %lx in %s\n",
>  			page_to_pfn(p), tsk->comm);
> -		tk->addr_valid = 0;
> +	} else if (tk->size_shift == 0) {
> +		kfree(tk);
> +		return;
>  	}
>  
>  	get_task_struct(tsk);
> @@ -361,7 +365,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
>  			 * make sure the process doesn't catch the
>  			 * signal and then access the memory. Just kill it.
>  			 */
> -			if (fail || tk->addr_valid == 0) {
> +			if (fail || tk->addr == -EFAULT) {
>  				pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
>  				       pfn, tk->tsk->comm, tk->tsk->pid);
>  				do_send_sig_info(SIGKILL, SEND_SIG_PRIV,
> -- 
> 1.8.3.1
> 
> 

Re: [PATCH v3 2/2] mm/memory-failure: Poison read receives SIGKILL instead of SIGBUS if mmaped more than once

[Naoya Horiguchi]

On Thu, Jul 25, 2019 at 04:01:41PM -0600, Jane Chu wrote:
> Mmap /dev/dax more than once, then read the poison location using address
> from one of the mappings. The other mappings due to not having the page
> mapped in will cause SIGKILLs delivered to the process. SIGKILL succeeds
> over SIGBUS, so user process looses the opportunity to handle the UE.
> 
> Although one may add MAP_POPULATE to mmap(2) to work around the issue,
> MAP_POPULATE makes mapping 128GB of pmem several magnitudes slower, so
> isn't always an option.
> 
> Details -
> 
> ndctl inject-error --block=10 --count=1 namespace6.0
> 
> ./read_poison -x dax6.0 -o 5120 -m 2
> mmaped address 0x7f5bb6600000
> mmaped address 0x7f3cf3600000
> doing local read at address 0x7f3cf3601400
> Killed
> 
> Console messages in instrumented kernel -
> 
> mce: Uncorrected hardware memory error in user-access at edbe201400
> Memory failure: tk->addr = 7f5bb6601000
> Memory failure: address edbe201: call dev_pagemap_mapping_shift
> dev_pagemap_mapping_shift: page edbe201: no PUD
> Memory failure: tk->size_shift == 0
> Memory failure: Unable to find user space address edbe201 in read_poison
> Memory failure: tk->addr = 7f3cf3601000
> Memory failure: address edbe201: call dev_pagemap_mapping_shift
> Memory failure: tk->size_shift = 21
> Memory failure: 0xedbe201: forcibly killing read_poison:22434 because of failure to unmap corrupted page
>   => to deliver SIGKILL
> Memory failure: 0xedbe201: Killing read_poison:22434 due to hardware memory corruption
>   => to deliver SIGBUS
> 
> Signed-off-by: Jane Chu <jane.chu@oracle.com>
> Suggested-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

Thanks for the fix.

Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

Re: [PATCH v3 1/2] mm/memory-failure.c clean up around tk pre-allocation

[Naoya Horiguchi]

On Thu, Jul 25, 2019 at 04:01:40PM -0600, Jane Chu wrote:
> add_to_kill() expects the first 'tk' to be pre-allocated, it makes
> subsequent allocations on need basis, this makes the code a bit
> difficult to read. Move all the allocation internal to add_to_kill()
> and drop the **tk argument.
> 
> Signed-off-by: Jane Chu <jane.chu@oracle.com>

Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

# somehow I sent 2 acks to 2/2, sorry about the noise.

Re: [PATCH v3 1/2] mm/memory-failure.c clean up around tk pre-allocation

[Jane Chu]

Hi, Naoya,

Thanks a lot!  v4 on the way. :)

-jane

On 8/1/2019 2:06 AM, Naoya Horiguchi wrote:
> On Thu, Jul 25, 2019 at 04:01:40PM -0600, Jane Chu wrote:
>> add_to_kill() expects the first 'tk' to be pre-allocated, it makes
>> subsequent allocations on need basis, this makes the code a bit
>> difficult to read. Move all the allocation internal to add_to_kill()
>> and drop the **tk argument.
>>
>> Signed-off-by: Jane Chu <jane.chu@oracle.com>
> 
> Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
> 
> # somehow I sent 2 acks to 2/2, sorry about the noise.
>