mm/memunmap: Use the correct start and end pfn when removing pages from zone
diff mbox series

Message ID 20190927103224.15962-1-aneesh.kumar@linux.ibm.com
State New
Headers show
Series
  • mm/memunmap: Use the correct start and end pfn when removing pages from zone
Related show

Commit Message

Aneesh Kumar K.V Sept. 27, 2019, 10:32 a.m. UTC
With altmap, all the resource pfns are not initialized. While initializing
pfn, altmap reserve space is skipped. Hence when removing pfn from zone skip
pfns that were never initialized.

Update memunmap_pages to calculate start and end pfn based on altmap
values. This fixes a kernel crash that is observed when destroying namespace.

[   81.356173] kernel BUG at include/linux/mm.h:1107!
cpu 0x1: Vector: 700 (Program Check) at [c000000274087890]
    pc: c0000000004b9728: memunmap_pages+0x238/0x340
    lr: c0000000004b9724: memunmap_pages+0x234/0x340
...
    pid   = 3669, comm = ndctl
kernel BUG at include/linux/mm.h:1107!
[c000000274087ba0] c0000000009e3500 devm_action_release+0x30/0x50
[c000000274087bc0] c0000000009e4758 release_nodes+0x268/0x2d0
[c000000274087c30] c0000000009dd144 device_release_driver_internal+0x174/0x240
[c000000274087c70] c0000000009d9dfc unbind_store+0x13c/0x190
[c000000274087cb0] c0000000009d8a24 drv_attr_store+0x44/0x60
[c000000274087cd0] c0000000005a7470 sysfs_kf_write+0x70/0xa0
[c000000274087d10] c0000000005a5cac kernfs_fop_write+0x1ac/0x290
[c000000274087d60] c0000000004be45c __vfs_write+0x3c/0x70
[c000000274087d80] c0000000004c26e4 vfs_write+0xe4/0x200
[c000000274087dd0] c0000000004c2a6c ksys_write+0x7c/0x140
[c000000274087e20] c00000000000bbd0 system_call+0x5c/0x68

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
Note:
This patch alone won't fix all the kernel crashes related wrong usage of pfn.
For ndctl destroy-namespace to work correctly we need rest of patches from
the series posted at

https://lore.kernel.org/linux-mm/20190830091428.18399-1-david@redhat.com

 mm/memremap.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

Comments

David Hildenbrand Sept. 27, 2019, 10:38 a.m. UTC | #1
On 27.09.19 12:32, Aneesh Kumar K.V wrote:
> With altmap, all the resource pfns are not initialized. While initializing
> pfn, altmap reserve space is skipped. Hence when removing pfn from zone skip
> pfns that were never initialized.
> 
> Update memunmap_pages to calculate start and end pfn based on altmap
> values. This fixes a kernel crash that is observed when destroying namespace.
> 
> [   81.356173] kernel BUG at include/linux/mm.h:1107!
> cpu 0x1: Vector: 700 (Program Check) at [c000000274087890]
>     pc: c0000000004b9728: memunmap_pages+0x238/0x340
>     lr: c0000000004b9724: memunmap_pages+0x234/0x340
> ...
>     pid   = 3669, comm = ndctl
> kernel BUG at include/linux/mm.h:1107!
> [c000000274087ba0] c0000000009e3500 devm_action_release+0x30/0x50
> [c000000274087bc0] c0000000009e4758 release_nodes+0x268/0x2d0
> [c000000274087c30] c0000000009dd144 device_release_driver_internal+0x174/0x240
> [c000000274087c70] c0000000009d9dfc unbind_store+0x13c/0x190
> [c000000274087cb0] c0000000009d8a24 drv_attr_store+0x44/0x60
> [c000000274087cd0] c0000000005a7470 sysfs_kf_write+0x70/0xa0
> [c000000274087d10] c0000000005a5cac kernfs_fop_write+0x1ac/0x290
> [c000000274087d60] c0000000004be45c __vfs_write+0x3c/0x70
> [c000000274087d80] c0000000004c26e4 vfs_write+0xe4/0x200
> [c000000274087dd0] c0000000004c2a6c ksys_write+0x7c/0x140
> [c000000274087e20] c00000000000bbd0 system_call+0x5c/0x68
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> ---
> Note:
> This patch alone won't fix all the kernel crashes related wrong usage of pfn.
> For ndctl destroy-namespace to work correctly we need rest of patches from
> the series posted at
> 
> https://lore.kernel.org/linux-mm/20190830091428.18399-1-david@redhat.com
> 
>  mm/memremap.c | 14 +++++++++-----
>  1 file changed, 9 insertions(+), 5 deletions(-)
> 
> diff --git a/mm/memremap.c b/mm/memremap.c
> index 32c79b51af86..4b31f0b7c42d 100644
> --- a/mm/memremap.c
> +++ b/mm/memremap.c
> @@ -105,7 +105,8 @@ static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
>  void memunmap_pages(struct dev_pagemap *pgmap)
>  {
>  	struct resource *res = &pgmap->res;
> -	unsigned long pfn;
> +	unsigned long start_pfn, end_pfn;
> +	unsigned long pfn, nr_pages;

pack all into a single line?

>  	int nid;
>  
>  	dev_pagemap_kill(pgmap);
> @@ -113,14 +114,17 @@ void memunmap_pages(struct dev_pagemap *pgmap)
>  		put_page(pfn_to_page(pfn));
>  	dev_pagemap_cleanup(pgmap);
>  
> +	start_pfn = pfn_first(pgmap);
> +	end_pfn = pfn_end(pgmap);
> +	nr_pages = end_pfn - start_pfn;
> +
>  	/* pages are dead and unused, undo the arch mapping */
> -	nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start)));
> +	nid = page_to_nid(pfn_to_page(start_pfn));
>  
>  	mem_hotplug_begin();
>  	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
> -		pfn = PHYS_PFN(res->start);
> -		__remove_pages(page_zone(pfn_to_page(pfn)), pfn,
> -				 PHYS_PFN(resource_size(res)), NULL);
> +		__remove_pages(page_zone(pfn_to_page(start_pfn)), start_pfn,
> +			       nr_pages, NULL);
>  	} else {
>  		arch_remove_memory(nid, res->start, resource_size(res),
>  				pgmap_altmap(pgmap));
> 

I am no expert on the details of the whole pgmap,
what-to-add-what-to-initialize-whatsoever devmem specific stuff, but
this change looks sane to me as far as I can tell.

Patch
diff mbox series

diff --git a/mm/memremap.c b/mm/memremap.c
index 32c79b51af86..4b31f0b7c42d 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -105,7 +105,8 @@  static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
 void memunmap_pages(struct dev_pagemap *pgmap)
 {
 	struct resource *res = &pgmap->res;
-	unsigned long pfn;
+	unsigned long start_pfn, end_pfn;
+	unsigned long pfn, nr_pages;
 	int nid;
 
 	dev_pagemap_kill(pgmap);
@@ -113,14 +114,17 @@  void memunmap_pages(struct dev_pagemap *pgmap)
 		put_page(pfn_to_page(pfn));
 	dev_pagemap_cleanup(pgmap);
 
+	start_pfn = pfn_first(pgmap);
+	end_pfn = pfn_end(pgmap);
+	nr_pages = end_pfn - start_pfn;
+
 	/* pages are dead and unused, undo the arch mapping */
-	nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start)));
+	nid = page_to_nid(pfn_to_page(start_pfn));
 
 	mem_hotplug_begin();
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
-		pfn = PHYS_PFN(res->start);
-		__remove_pages(page_zone(pfn_to_page(pfn)), pfn,
-				 PHYS_PFN(resource_size(res)), NULL);
+		__remove_pages(page_zone(pfn_to_page(start_pfn)), start_pfn,
+			       nr_pages, NULL);
 	} else {
 		arch_remove_memory(nid, res->start, resource_size(res),
 				pgmap_altmap(pgmap));