| 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
| ||
|
Message-ID: <lui7hffmc35dfzwxu3xyybf5pion74fbfxszfopsp6tgyt2ajq@bmpeieroavro>
Date: Mon, 13 Jan 2025 11:47:41 +1100
From: Alistair Popple <apopple@...dia.com>
To: "Darrick J. Wong" <djwong@...nel.org>
Cc: akpm@...ux-foundation.org, dan.j.williams@...el.com,
linux-mm@...ck.org, alison.schofield@...el.com, lina@...hilina.net,
zhang.lyra@...il.com, gerald.schaefer@...ux.ibm.com, vishal.l.verma@...el.com,
dave.jiang@...el.com, logang@...tatee.com, bhelgaas@...gle.com, jack@...e.cz,
jgg@...pe.ca, catalin.marinas@....com, will@...nel.org, mpe@...erman.id.au,
npiggin@...il.com, dave.hansen@...ux.intel.com, ira.weiny@...el.com,
willy@...radead.org, tytso@....edu, linmiaohe@...wei.com, david@...hat.com,
peterx@...hat.com, linux-doc@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-arm-kernel@...ts.infradead.org, linuxppc-dev@...ts.ozlabs.org, nvdimm@...ts.linux.dev,
linux-cxl@...r.kernel.org, linux-fsdevel@...r.kernel.org, linux-ext4@...r.kernel.org,
linux-xfs@...r.kernel.org, jhubbard@...dia.com, hch@....de, david@...morbit.com,
chenhuacai@...nel.org, kernel@...0n.name, loongarch@...ts.linux.dev
Subject: Re: [PATCH v6 05/26] fs/dax: Create a common implementation to break
DAX layouts
On Fri, Jan 10, 2025 at 08:44:38AM -0800, Darrick J. Wong wrote:
> On Fri, Jan 10, 2025 at 05:00:33PM +1100, Alistair Popple wrote:
> > Prior to freeing a block file systems supporting FS DAX must check
> > that the associated pages are both unmapped from user-space and not
> > undergoing DMA or other access from eg. get_user_pages(). This is
> > achieved by unmapping the file range and scanning the FS DAX
> > page-cache to see if any pages within the mapping have an elevated
> > refcount.
> >
> > This is done using two functions - dax_layout_busy_page_range() which
> > returns a page to wait for the refcount to become idle on. Rather than
> > open-code this introduce a common implementation to both unmap and
> > wait for the page to become idle.
> >
> > Signed-off-by: Alistair Popple <apopple@...dia.com>
>
> So now that Dan Carpenter has complained, I guess I should look at
> this...
>
> > ---
> >
> > Changes for v5:
> >
> > - Don't wait for idle pages on non-DAX mappings
> >
> > Changes for v4:
> >
> > - Fixed some build breakage due to missing symbol exports reported by
> > John Hubbard (thanks!).
> > ---
> > fs/dax.c | 33 +++++++++++++++++++++++++++++++++
> > fs/ext4/inode.c | 10 +---------
> > fs/fuse/dax.c | 27 +++------------------------
> > fs/xfs/xfs_inode.c | 23 +++++------------------
> > fs/xfs/xfs_inode.h | 2 +-
> > include/linux/dax.h | 21 +++++++++++++++++++++
> > mm/madvise.c | 8 ++++----
> > 7 files changed, 68 insertions(+), 56 deletions(-)
> >
> > diff --git a/fs/dax.c b/fs/dax.c
> > index d010c10..9c3bd07 100644
> > --- a/fs/dax.c
> > +++ b/fs/dax.c
> > @@ -845,6 +845,39 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
> > return ret;
> > }
> >
> > +static int wait_page_idle(struct page *page,
> > + void (cb)(struct inode *),
> > + struct inode *inode)
> > +{
> > + return ___wait_var_event(page, page_ref_count(page) == 1,
> > + TASK_INTERRUPTIBLE, 0, 0, cb(inode));
> > +}
> > +
> > +/*
> > + * Unmaps the inode and waits for any DMA to complete prior to deleting the
> > + * DAX mapping entries for the range.
> > + */
> > +int dax_break_mapping(struct inode *inode, loff_t start, loff_t end,
> > + void (cb)(struct inode *))
> > +{
> > + struct page *page;
> > + int error;
> > +
> > + if (!dax_mapping(inode->i_mapping))
> > + return 0;
> > +
> > + do {
> > + page = dax_layout_busy_page_range(inode->i_mapping, start, end);
> > + if (!page)
> > + break;
> > +
> > + error = wait_page_idle(page, cb, inode);
> > + } while (error == 0);
>
> You didn't initialize error to 0, so it could be any value. What if
> dax_layout_busy_page_range returns null the first time through the loop?
Yes. I went down the rabbit hole of figuring out why this didn't produce a
compiler warning and forgot to go back and fix it. Thanks.
> > +
> > + return error;
> > +}
> > +EXPORT_SYMBOL_GPL(dax_break_mapping);
> > +
> > /*
> > * Invalidate DAX entry if it is clean.
> > */
>
> <I'm no expert, skipping to xfs>
>
> > diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> > index 42ea203..295730a 100644
> > --- a/fs/xfs/xfs_inode.c
> > +++ b/fs/xfs/xfs_inode.c
> > @@ -2715,21 +2715,17 @@ xfs_mmaplock_two_inodes_and_break_dax_layout(
> > struct xfs_inode *ip2)
> > {
> > int error;
> > - bool retry;
> > struct page *page;
> >
> > if (ip1->i_ino > ip2->i_ino)
> > swap(ip1, ip2);
> >
> > again:
> > - retry = false;
> > /* Lock the first inode */
> > xfs_ilock(ip1, XFS_MMAPLOCK_EXCL);
> > - error = xfs_break_dax_layouts(VFS_I(ip1), &retry);
> > - if (error || retry) {
> > + error = xfs_break_dax_layouts(VFS_I(ip1));
> > + if (error) {
> > xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
> > - if (error == 0 && retry)
> > - goto again;
>
> Hmm, so the retry loop has moved into xfs_break_dax_layouts, which means
> that we no longer cycle the MMAPLOCK. Why was the lock cycling
> unnecessary?
Because the lock cycling is already happening in the xfs_wait_dax_page()
callback which is called as part of the retry loop in dax_break_mapping().
> > return error;
> > }
> >
> > @@ -2988,19 +2984,11 @@ xfs_wait_dax_page(
> >
> > int
> > xfs_break_dax_layouts(
> > - struct inode *inode,
> > - bool *retry)
> > + struct inode *inode)
> > {
> > - struct page *page;
> > -
> > xfs_assert_ilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL);
> >
> > - page = dax_layout_busy_page(inode->i_mapping);
> > - if (!page)
> > - return 0;
> > -
> > - *retry = true;
> > - return dax_wait_page_idle(page, xfs_wait_dax_page, inode);
> > + return dax_break_mapping_inode(inode, xfs_wait_dax_page);
> > }
> >
> > int
> > @@ -3018,8 +3006,7 @@ xfs_break_layouts(
> > retry = false;
> > switch (reason) {
> > case BREAK_UNMAP:
> > - error = xfs_break_dax_layouts(inode, &retry);
> > - if (error || retry)
> > + if (xfs_break_dax_layouts(inode))
>
> dax_break_mapping can return -ERESTARTSYS, right? So doesn't this need
> to be:
> error = xfs_break_dax_layouts(inode);
> if (error)
> break;
>
> Hm?
Right. Thanks for the review, have fixed for the next respin.
- Alistair
> --D
>
> > break;
> > fallthrough;
> > case BREAK_WRITE:
> > diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
> > index 1648dc5..c4f03f6 100644
> > --- a/fs/xfs/xfs_inode.h
> > +++ b/fs/xfs/xfs_inode.h
> > @@ -593,7 +593,7 @@ xfs_itruncate_extents(
> > return xfs_itruncate_extents_flags(tpp, ip, whichfork, new_size, 0);
> > }
> >
> > -int xfs_break_dax_layouts(struct inode *inode, bool *retry);
> > +int xfs_break_dax_layouts(struct inode *inode);
> > int xfs_break_layouts(struct inode *inode, uint *iolock,
> > enum layout_break_reason reason);
> >
> > diff --git a/include/linux/dax.h b/include/linux/dax.h
> > index 9b1ce98..f6583d3 100644
> > --- a/include/linux/dax.h
> > +++ b/include/linux/dax.h
> > @@ -228,6 +228,20 @@ static inline void dax_read_unlock(int id)
> > {
> > }
> > #endif /* CONFIG_DAX */
> > +
> > +#if !IS_ENABLED(CONFIG_FS_DAX)
> > +static inline int __must_check dax_break_mapping(struct inode *inode,
> > + loff_t start, loff_t end, void (cb)(struct inode *))
> > +{
> > + return 0;
> > +}
> > +
> > +static inline void dax_break_mapping_uninterruptible(struct inode *inode,
> > + void (cb)(struct inode *))
> > +{
> > +}
> > +#endif
> > +
> > bool dax_alive(struct dax_device *dax_dev);
> > void *dax_get_private(struct dax_device *dax_dev);
> > long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
> > @@ -251,6 +265,13 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
> > int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
> > int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
> > pgoff_t index);
> > +int __must_check dax_break_mapping(struct inode *inode, loff_t start,
> > + loff_t end, void (cb)(struct inode *));
> > +static inline int __must_check dax_break_mapping_inode(struct inode *inode,
> > + void (cb)(struct inode *))
> > +{
> > + return dax_break_mapping(inode, 0, LLONG_MAX, cb);
> > +}
> > int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
> > struct inode *dest, loff_t destoff,
> > loff_t len, bool *is_same,
> > diff --git a/mm/madvise.c b/mm/madvise.c
> > index 49f3a75..1f4c99e 100644
> > --- a/mm/madvise.c
> > +++ b/mm/madvise.c
> > @@ -1063,7 +1063,7 @@ static int guard_install_pud_entry(pud_t *pud, unsigned long addr,
> > pud_t pudval = pudp_get(pud);
> >
> > /* If huge return >0 so we abort the operation + zap. */
> > - return pud_trans_huge(pudval) || pud_devmap(pudval);
> > + return pud_trans_huge(pudval);
> > }
> >
> > static int guard_install_pmd_entry(pmd_t *pmd, unsigned long addr,
> > @@ -1072,7 +1072,7 @@ static int guard_install_pmd_entry(pmd_t *pmd, unsigned long addr,
> > pmd_t pmdval = pmdp_get(pmd);
> >
> > /* If huge return >0 so we abort the operation + zap. */
> > - return pmd_trans_huge(pmdval) || pmd_devmap(pmdval);
> > + return pmd_trans_huge(pmdval);
> > }
> >
> > static int guard_install_pte_entry(pte_t *pte, unsigned long addr,
> > @@ -1183,7 +1183,7 @@ static int guard_remove_pud_entry(pud_t *pud, unsigned long addr,
> > pud_t pudval = pudp_get(pud);
> >
> > /* If huge, cannot have guard pages present, so no-op - skip. */
> > - if (pud_trans_huge(pudval) || pud_devmap(pudval))
> > + if (pud_trans_huge(pudval))
> > walk->action = ACTION_CONTINUE;
> >
> > return 0;
> > @@ -1195,7 +1195,7 @@ static int guard_remove_pmd_entry(pmd_t *pmd, unsigned long addr,
> > pmd_t pmdval = pmdp_get(pmd);
> >
> > /* If huge, cannot have guard pages present, so no-op - skip. */
> > - if (pmd_trans_huge(pmdval) || pmd_devmap(pmdval))
> > + if (pmd_trans_huge(pmdval))
> > walk->action = ACTION_CONTINUE;
> >
> > return 0;
> > --
> > git-series 0.9.1
> >
Powered by blists - more mailing lists