diff mbox series

[v3,1/3] iomap: pass blocksize to iomap_truncate_page()

Message ID 20240517111355.233085-2-yi.zhang@huaweicloud.com (mailing list archive)
State Superseded, archived
Headers show
Series iomap/xfs: fix stale data exposure when truncating realtime inodes | expand

Commit Message

Zhang Yi May 17, 2024, 11:13 a.m. UTC 
From: Zhang Yi <yi.zhang@huawei.com>

iomap_truncate_page() always assumes the block size of the truncating
inode is i_blocksize(), this is not always true for some filesystems,
e.g. XFS does extent size alignment for realtime inodes. Drop this
assumption and pass the block size for zeroing into
iomap_truncate_page(), allow filesystems to indicate the correct block
size.

Suggested-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
 fs/iomap/buffered-io.c | 13 +++++++++----
 fs/xfs/xfs_iomap.c     |  3 ++-
 include/linux/iomap.h  |  4 ++--
 3 files changed, 13 insertions(+), 7 deletions(-)

Comments

Darrick J. Wong May 17, 2024, 5:29 p.m. UTC | #1 
On Fri, May 17, 2024 at 07:13:53PM +0800, Zhang Yi wrote:
> From: Zhang Yi <yi.zhang@huawei.com>
> 
> iomap_truncate_page() always assumes the block size of the truncating
> inode is i_blocksize(), this is not always true for some filesystems,
> e.g. XFS does extent size alignment for realtime inodes. Drop this
> assumption and pass the block size for zeroing into
> iomap_truncate_page(), allow filesystems to indicate the correct block
> size.
> 
> Suggested-by: Dave Chinner <david@fromorbit.com>
> Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
> ---
>  fs/iomap/buffered-io.c | 13 +++++++++----
>  fs/xfs/xfs_iomap.c     |  3 ++-
>  include/linux/iomap.h  |  4 ++--
>  3 files changed, 13 insertions(+), 7 deletions(-)
> 
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 0926d216a5af..a0a0ac2c659c 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -17,6 +17,7 @@
>  #include <linux/bio.h>
>  #include <linux/sched/signal.h>
>  #include <linux/migrate.h>
> +#include <linux/math64.h>
>  #include "trace.h"
>  
>  #include "../internal.h"
> @@ -1445,11 +1446,15 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
>  EXPORT_SYMBOL_GPL(iomap_zero_range);
>  
>  int
> -iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
> -		const struct iomap_ops *ops)
> +iomap_truncate_page(struct inode *inode, loff_t pos, unsigned int blocksize,
> +		bool *did_zero, const struct iomap_ops *ops)
>  {
> -	unsigned int blocksize = i_blocksize(inode);
> -	unsigned int off = pos & (blocksize - 1);
> +	unsigned int off;
> +
> +	if (is_power_of_2(blocksize))
> +		off = pos & (blocksize - 1);
> +	else
> +		div_u64_rem(pos, blocksize, &off);

I wish this was a helper in math64.h somewhere.

static inline u32 rem_u64(u64 dividend, u32 divisor)
{
	if (likely(is_power_of_2(divisor)))
		return dividend & (divisor - 1);

	return dividend % divisor;
}

That way we skip the second division in div_u64_rem entirely, and the
iomap/dax code becomes:

	unsigned int off = rem_u64(pos, blocksize); /* pos in block */

Otherwise this looks like a straightforward mechanical change to me.

--D

>  
>  	/* Block boundary? Nothing to do */
>  	if (!off)
> diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
> index 2857ef1b0272..31ac07bb8425 100644
> --- a/fs/xfs/xfs_iomap.c
> +++ b/fs/xfs/xfs_iomap.c
> @@ -1467,10 +1467,11 @@ xfs_truncate_page(
>  	bool			*did_zero)
>  {
>  	struct inode		*inode = VFS_I(ip);
> +	unsigned int		blocksize = i_blocksize(inode);
>  
>  	if (IS_DAX(inode))
>  		return dax_truncate_page(inode, pos, did_zero,
>  					&xfs_dax_write_iomap_ops);
> -	return iomap_truncate_page(inode, pos, did_zero,
> +	return iomap_truncate_page(inode, pos, blocksize, did_zero,
>  				   &xfs_buffered_write_iomap_ops);
>  }
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 6fc1c858013d..d67bf86ec582 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h
> @@ -273,8 +273,8 @@ int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
>  		const struct iomap_ops *ops);
>  int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
>  		bool *did_zero, const struct iomap_ops *ops);
> -int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
> -		const struct iomap_ops *ops);
> +int iomap_truncate_page(struct inode *inode, loff_t pos, unsigned int blocksize,
> +		bool *did_zero, const struct iomap_ops *ops);
>  vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf,
>  			const struct iomap_ops *ops);
>  int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
> -- 
> 2.39.2
> 
>
Zhang Yi May 18, 2024, 2:01 a.m. UTC | #2 
On 2024/5/18 1:29, Darrick J. Wong wrote:
> On Fri, May 17, 2024 at 07:13:53PM +0800, Zhang Yi wrote:
>> From: Zhang Yi <yi.zhang@huawei.com>
>>
>> iomap_truncate_page() always assumes the block size of the truncating
>> inode is i_blocksize(), this is not always true for some filesystems,
>> e.g. XFS does extent size alignment for realtime inodes. Drop this
>> assumption and pass the block size for zeroing into
>> iomap_truncate_page(), allow filesystems to indicate the correct block
>> size.
>>
>> Suggested-by: Dave Chinner <david@fromorbit.com>
>> Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
>> ---
>>  fs/iomap/buffered-io.c | 13 +++++++++----
>>  fs/xfs/xfs_iomap.c     |  3 ++-
>>  include/linux/iomap.h  |  4 ++--
>>  3 files changed, 13 insertions(+), 7 deletions(-)
>>
>> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
>> index 0926d216a5af..a0a0ac2c659c 100644
>> --- a/fs/iomap/buffered-io.c
>> +++ b/fs/iomap/buffered-io.c
>> @@ -17,6 +17,7 @@
>>  #include <linux/bio.h>
>>  #include <linux/sched/signal.h>
>>  #include <linux/migrate.h>
>> +#include <linux/math64.h>
>>  #include "trace.h"
>>  
>>  #include "../internal.h"
>> @@ -1445,11 +1446,15 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
>>  EXPORT_SYMBOL_GPL(iomap_zero_range);
>>  
>>  int
>> -iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
>> -		const struct iomap_ops *ops)
>> +iomap_truncate_page(struct inode *inode, loff_t pos, unsigned int blocksize,
>> +		bool *did_zero, const struct iomap_ops *ops)
>>  {
>> -	unsigned int blocksize = i_blocksize(inode);
>> -	unsigned int off = pos & (blocksize - 1);
>> +	unsigned int off;
>> +
>> +	if (is_power_of_2(blocksize))
>> +		off = pos & (blocksize - 1);
>> +	else
>> +		div_u64_rem(pos, blocksize, &off);
> 
> I wish this was a helper in math64.h somewhere.
> 
> static inline u32 rem_u64(u64 dividend, u32 divisor)
> {
> 	if (likely(is_power_of_2(divisor)))
> 		return dividend & (divisor - 1);
> 
> 	return dividend % divisor;
> }
> 
> That way we skip the second division in div_u64_rem entirely, and the
> iomap/dax code becomes:
> 
> 	unsigned int off = rem_u64(pos, blocksize); /* pos in block */
> 
> Otherwise this looks like a straightforward mechanical change to me.
> 

Yeah, we do need this helper.

Thanks,
Yi.

> 
>>  
>>  	/* Block boundary? Nothing to do */
>>  	if (!off)
>> diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
>> index 2857ef1b0272..31ac07bb8425 100644
>> --- a/fs/xfs/xfs_iomap.c
>> +++ b/fs/xfs/xfs_iomap.c
>> @@ -1467,10 +1467,11 @@ xfs_truncate_page(
>>  	bool			*did_zero)
>>  {
>>  	struct inode		*inode = VFS_I(ip);
>> +	unsigned int		blocksize = i_blocksize(inode);
>>  
>>  	if (IS_DAX(inode))
>>  		return dax_truncate_page(inode, pos, did_zero,
>>  					&xfs_dax_write_iomap_ops);
>> -	return iomap_truncate_page(inode, pos, did_zero,
>> +	return iomap_truncate_page(inode, pos, blocksize, did_zero,
>>  				   &xfs_buffered_write_iomap_ops);
>>  }
>> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
>> index 6fc1c858013d..d67bf86ec582 100644
>> --- a/include/linux/iomap.h
>> +++ b/include/linux/iomap.h
>> @@ -273,8 +273,8 @@ int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
>>  		const struct iomap_ops *ops);
>>  int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
>>  		bool *did_zero, const struct iomap_ops *ops);
>> -int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
>> -		const struct iomap_ops *ops);
>> +int iomap_truncate_page(struct inode *inode, loff_t pos, unsigned int blocksize,
>> +		bool *did_zero, const struct iomap_ops *ops);
>>  vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf,
>>  			const struct iomap_ops *ops);
>>  int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
>> -- 
>> 2.39.2
>>
>>
diff mbox series

Patch

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 0926d216a5af..a0a0ac2c659c 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -17,6 +17,7 @@ 
 #include <linux/bio.h>
 #include <linux/sched/signal.h>
 #include <linux/migrate.h>
+#include <linux/math64.h>
 #include "trace.h"
 
 #include "../internal.h"
@@ -1445,11 +1446,15 @@  iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 EXPORT_SYMBOL_GPL(iomap_zero_range);
 
 int
-iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
-		const struct iomap_ops *ops)
+iomap_truncate_page(struct inode *inode, loff_t pos, unsigned int blocksize,
+		bool *did_zero, const struct iomap_ops *ops)
 {
-	unsigned int blocksize = i_blocksize(inode);
-	unsigned int off = pos & (blocksize - 1);
+	unsigned int off;
+
+	if (is_power_of_2(blocksize))
+		off = pos & (blocksize - 1);
+	else
+		div_u64_rem(pos, blocksize, &off);
 
 	/* Block boundary? Nothing to do */
 	if (!off)
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 2857ef1b0272..31ac07bb8425 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1467,10 +1467,11 @@  xfs_truncate_page(
 	bool			*did_zero)
 {
 	struct inode		*inode = VFS_I(ip);
+	unsigned int		blocksize = i_blocksize(inode);
 
 	if (IS_DAX(inode))
 		return dax_truncate_page(inode, pos, did_zero,
 					&xfs_dax_write_iomap_ops);
-	return iomap_truncate_page(inode, pos, did_zero,
+	return iomap_truncate_page(inode, pos, blocksize, did_zero,
 				   &xfs_buffered_write_iomap_ops);
 }
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 6fc1c858013d..d67bf86ec582 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -273,8 +273,8 @@  int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
 		bool *did_zero, const struct iomap_ops *ops);
-int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
-		const struct iomap_ops *ops);
+int iomap_truncate_page(struct inode *inode, loff_t pos, unsigned int blocksize,
+		bool *did_zero, const struct iomap_ops *ops);
 vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf,
 			const struct iomap_ops *ops);
 int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,