| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 8 Apr 2021 03:21:53 +0000
From: "ruansy.fnst@...itsu.com" <ruansy.fnst@...itsu.com>
To: Ritesh Harjani <ritesh.list@...il.com>
CC: "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-xfs@...r.kernel.org" <linux-xfs@...r.kernel.org>,
"linux-nvdimm@...ts.01.org" <linux-nvdimm@...ts.01.org>,
"linux-fsdevel@...r.kernel.org" <linux-fsdevel@...r.kernel.org>,
"darrick.wong@...cle.com" <darrick.wong@...cle.com>,
"dan.j.williams@...el.com" <dan.j.williams@...el.com>,
"willy@...radead.org" <willy@...radead.org>,
"jack@...e.cz" <jack@...e.cz>,
"viro@...iv.linux.org.uk" <viro@...iv.linux.org.uk>,
"linux-btrfs@...r.kernel.org" <linux-btrfs@...r.kernel.org>,
"ocfs2-devel@....oracle.com" <ocfs2-devel@....oracle.com>,
"david@...morbit.com" <david@...morbit.com>,
"hch@....de" <hch@....de>, "rgoldwyn@...e.de" <rgoldwyn@...e.de>,
Goldwyn Rodrigues <rgoldwyn@...e.com>
Subject: RE: [PATCH v3 08/10] fsdax: Dedup file range to use a compare
function
> -----Original Message-----
> From: Ritesh Harjani <ritesh.list@...il.com>
> Subject: Re: [PATCH v3 08/10] fsdax: Dedup file range to use a compare function
>
> On 21/03/19 09:52AM, Shiyang Ruan wrote:
> > With dax we cannot deal with readpage() etc. So, we create a dax
> > comparison funciton which is similar with
> > vfs_dedupe_file_range_compare().
> > And introduce dax_remap_file_range_prep() for filesystem use.
> >
> > Signed-off-by: Goldwyn Rodrigues <rgoldwyn@...e.com>
> > Signed-off-by: Shiyang Ruan <ruansy.fnst@...itsu.com>
> > ---
> > fs/dax.c | 56
> ++++++++++++++++++++++++++++++++++++++++++++
> > fs/remap_range.c | 45 ++++++++++++++++++++++++++++-------
> > fs/xfs/xfs_reflink.c | 9 +++++--
> > include/linux/dax.h | 4 ++++
> > include/linux/fs.h | 15 ++++++++----
> > 5 files changed, 115 insertions(+), 14 deletions(-)
> >
> > diff --git a/fs/dax.c b/fs/dax.c
> > index 348297b38f76..76f81f1d76ec 100644
> > --- a/fs/dax.c
> > +++ b/fs/dax.c
> > @@ -1833,3 +1833,59 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault
> *vmf,
> > return dax_insert_pfn_mkwrite(vmf, pfn, order); }
> > EXPORT_SYMBOL_GPL(dax_finish_sync_fault);
> > +
> > +static loff_t dax_range_compare_actor(struct inode *ino1, loff_t pos1,
> > + struct inode *ino2, loff_t pos2, loff_t len, void *data,
> > + struct iomap *smap, struct iomap *dmap) {
> > + void *saddr, *daddr;
> > + bool *same = data;
> > + int ret;
> > +
> > + if (smap->type == IOMAP_HOLE && dmap->type == IOMAP_HOLE) {
> > + *same = true;
> > + return len;
> > + }
> > +
> > + if (smap->type == IOMAP_HOLE || dmap->type == IOMAP_HOLE) {
> > + *same = false;
> > + return 0;
> > + }
> > +
> > + ret = dax_iomap_direct_access(smap, pos1, ALIGN(pos1 + len, PAGE_SIZE),
> > + &saddr, NULL);
>
> shouldn't it take len as the second argument?
The second argument of dax_iomap_direct_access() means offset, and the third one means length. So, I think this is right.
>
> > + if (ret < 0)
> > + return -EIO;
> > +
> > + ret = dax_iomap_direct_access(dmap, pos2, ALIGN(pos2 + len, PAGE_SIZE),
> > + &daddr, NULL);
>
> ditto.
> > + if (ret < 0)
> > + return -EIO;
> > +
> > + *same = !memcmp(saddr, daddr, len);
> > + return len;
> > +}
> > +
> > +int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
> > + struct inode *dest, loff_t destoff, loff_t len, bool *is_same,
> > + const struct iomap_ops *ops)
> > +{
> > + int id, ret = 0;
> > +
> > + id = dax_read_lock();
> > + while (len) {
> > + ret = iomap_apply2(src, srcoff, dest, destoff, len, 0, ops,
> > + is_same, dax_range_compare_actor);
> > + if (ret < 0 || !*is_same)
> > + goto out;
> > +
> > + len -= ret;
> > + srcoff += ret;
> > + destoff += ret;
> > + }
> > + ret = 0;
> > +out:
> > + dax_read_unlock(id);
> > + return ret;
> > +}
> > +EXPORT_SYMBOL_GPL(dax_dedupe_file_range_compare);
> > diff --git a/fs/remap_range.c b/fs/remap_range.c index
> > 77dba3a49e65..9079390edaf3 100644
> > --- a/fs/remap_range.c
> > +++ b/fs/remap_range.c
> > @@ -14,6 +14,7 @@
> > #include <linux/compat.h>
> > #include <linux/mount.h>
> > #include <linux/fs.h>
> > +#include <linux/dax.h>
> > #include "internal.h"
> >
> > #include <linux/uaccess.h>
> > @@ -199,9 +200,9 @@ static void vfs_unlock_two_pages(struct page *page1,
> struct page *page2)
> > * Compare extents of two files to see if they are the same.
> > * Caller must have locked both inodes to prevent write races.
> > */
> > -static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
> > - struct inode *dest, loff_t destoff,
> > - loff_t len, bool *is_same)
> > +int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
> > + struct inode *dest, loff_t destoff,
> > + loff_t len, bool *is_same)
> > {
> > loff_t src_poff;
> > loff_t dest_poff;
> > @@ -280,6 +281,7 @@ static int vfs_dedupe_file_range_compare(struct
> > inode *src, loff_t srcoff,
> > out_error:
> > return error;
> > }
> > +EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
> >
> > /*
> > * Check that the two inodes are eligible for cloning, the ranges
> > make @@ -289,9 +291,11 @@ static int
> vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
> > * If there's an error, then the usual negative error code is returned.
> > * Otherwise returns 0 with *len set to the request length.
> > */
> > -int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> > - struct file *file_out, loff_t pos_out,
> > - loff_t *len, unsigned int remap_flags)
> > +static int
> > +__generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> > + struct file *file_out, loff_t pos_out,
> > + loff_t *len, unsigned int remap_flags,
> > + const struct iomap_ops *ops)
> > {
> > struct inode *inode_in = file_inode(file_in);
> > struct inode *inode_out = file_inode(file_out); @@ -351,8 +355,15 @@
> > int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> > if (remap_flags & REMAP_FILE_DEDUP) {
> > bool is_same = false;
> >
> > - ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
> > - inode_out, pos_out, *len, &is_same);
> > + if (!IS_DAX(inode_in) && !IS_DAX(inode_out))
> > + ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
> > + inode_out, pos_out, *len, &is_same);
> > + else if (IS_DAX(inode_in) && IS_DAX(inode_out) && ops)
> > + ret = dax_dedupe_file_range_compare(inode_in, pos_in,
> > + inode_out, pos_out, *len, &is_same,
> > + ops);
> > + else
> > + return -EINVAL;
> > if (ret)
> > return ret;
> > if (!is_same)
>
> should we consider to check !is_same check b4?
> you should maybe relook at this error handling side of code.
> we still return len from actor function but is_same is set to false.
> So we are essentially returning ret (positive value), instead should be returning
> -EBADE because of !memcmp
The ret from compare function will not be positive, it will always be 0 or negative.
In addition, if something wrong happens, is_same will always be false. The caller could not get correct errno if check !is_same firstly.
>
> > @@ -370,6 +381,24 @@ int generic_remap_file_range_prep(struct file
> > *file_in, loff_t pos_in,
> >
> > return ret;
> > }
> > +
> > +int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> > + struct file *file_out, loff_t pos_out,
> > + loff_t *len, unsigned int remap_flags,
> > + const struct iomap_ops *ops) {
> > + return __generic_remap_file_range_prep(file_in, pos_in, file_out,
> > + pos_out, len, remap_flags, ops); }
> > +EXPORT_SYMBOL(dax_remap_file_range_prep);
> > +
> > +int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> > + struct file *file_out, loff_t pos_out,
> > + loff_t *len, unsigned int remap_flags) {
> > + return __generic_remap_file_range_prep(file_in, pos_in, file_out,
> > + pos_out, len, remap_flags, NULL); }
> > EXPORT_SYMBOL(generic_remap_file_range_prep);
> >
> > loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, diff
> > --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index
> > 6fa05fb78189..f5b3a3da36b7 100644
> > --- a/fs/xfs/xfs_reflink.c
> > +++ b/fs/xfs/xfs_reflink.c
> > @@ -1308,8 +1308,13 @@ xfs_reflink_remap_prep(
> > if (IS_DAX(inode_in) || IS_DAX(inode_out))
> > goto out_unlock;
> >
> > - ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
> > - len, remap_flags);
> > + if (IS_DAX(inode_in))
>
> if (!IS_DAX(inode_in)) no?
My mistake...
>
> > + ret = generic_remap_file_range_prep(file_in, pos_in, file_out,
> > + pos_out, len, remap_flags);
> > + else
> > + ret = dax_remap_file_range_prep(file_in, pos_in, file_out,
> > + pos_out, len, remap_flags,
> > + &xfs_read_iomap_ops);
> > if (ret || *len == 0)
> > goto out_unlock;
> >
> > diff --git a/include/linux/dax.h b/include/linux/dax.h index
> > 3275e01ed33d..32e1c34349f2 100644
> > --- a/include/linux/dax.h
> > +++ b/include/linux/dax.h
> > @@ -239,6 +239,10 @@ int dax_invalidate_mapping_entry_sync(struct
> address_space *mapping,
> > pgoff_t index);
> > s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap,
> > struct iomap *srcmap);
> > +int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
> > + struct inode *dest, loff_t destoff,
> > + loff_t len, bool *is_same,
> > + const struct iomap_ops *ops);
> > static inline bool dax_mapping(struct address_space *mapping) {
> > return mapping->host && IS_DAX(mapping->host); diff --git
> > a/include/linux/fs.h b/include/linux/fs.h index
> > fd47deea7c17..2e6ec5bdf82a 100644
> > --- a/include/linux/fs.h
> > +++ b/include/linux/fs.h
> > @@ -68,6 +68,7 @@ struct fsverity_info; struct fsverity_operations;
> > struct fs_context; struct fs_parameter_spec;
> > +struct iomap_ops;
> >
> > extern void __init inode_init(void);
> > extern void __init inode_init_early(void); @@ -1910,13 +1911,19 @@
> > extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t
> > *); extern ssize_t vfs_write(struct file *, const char __user *,
> > size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct
> file *,
> > loff_t, size_t, unsigned int);
> > +typedef int (*compare_range_t)(struct inode *src, loff_t srcpos,
> > + struct inode *dest, loff_t destpos,
> > + loff_t len, bool *is_same);
>
> Is this used anywhere?
No, I forgot to remove it...
--
Thanks,
Ruan Shiyang.
>
> > extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
> > struct file *file_out, loff_t pos_out,
> > size_t len, unsigned int flags); -extern int
> > generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> > - struct file *file_out, loff_t pos_out,
> > - loff_t *count,
> > - unsigned int remap_flags);
> > +int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> > + struct file *file_out, loff_t pos_out,
> > + loff_t *count, unsigned int remap_flags); int
> > +dax_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> > + struct file *file_out, loff_t pos_out,
> > + loff_t *len, unsigned int remap_flags,
> > + const struct iomap_ops *ops);
> > extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
> > struct file *file_out, loff_t pos_out,
> > loff_t len, unsigned int remap_flags);
> > --
> > 2.30.1
> >
> >
> >
Powered by blists - more mailing lists