diff mbox series

[3/3] fs/ufs: Replace kmap() with kmap_local_page()

Message ID 20221211213111.30085-4-fmdefrancesco@gmail.com (mailing list archive)
State Not Applicable
Headers show
Series fs/ufs: replace kmap() with kmap_local_page() | expand

Checks

Context Check Description
netdev/tree_selection success Not a local patch

Commit Message

Fabio M. De Francesco Dec. 11, 2022, 9:31 p.m. UTC
kmap() is being deprecated in favor of kmap_local_page().

There are two main problems with kmap(): (1) It comes with an overhead as
the mapping space is restricted and protected by a global lock for
synchronization and (2) it also requires global TLB invalidation when the
kmap’s pool wraps and it might block when the mapping space is fully
utilized until a slot becomes available.

With kmap_local_page() the mappings are per thread, CPU local, can take
page faults, and can be called from any context (including interrupts).
It is faster than kmap() in kernels with HIGHMEM enabled. Furthermore,
the tasks can be preempted and, when they are scheduled to run again, the
kernel virtual addresses are restored and still valid.

Since its use in fs/ufs is safe everywhere, it should be preferred.

Therefore, replace kmap() with kmap_local_page() in fs/ufs. kunmap_local()
requires the mapping address, so return that address from ufs_get_page()
to be used in ufs_put_page().

Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Suggested-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Fabio M. De Francesco <fmdefrancesco@gmail.com>
---
 fs/ufs/dir.c | 76 ++++++++++++++++++++++++++++++++--------------------
 1 file changed, 47 insertions(+), 29 deletions(-)

Comments

Al Viro Dec. 11, 2022, 10:39 p.m. UTC | #1
On Sun, Dec 11, 2022 at 10:31:11PM +0100, Fabio M. De Francesco wrote:

> +/*
> + * Calls to ufs_get_page()/ufs_put_page() must be nested according to the
> + * rules documented in kmap_local_page()/kunmap_local().
> + *
> + * NOTE: ufs_find_entry() and ufs_dotdot() act as calls to ufs_get_page()
> + * and must be treated accordingly for nesting purposes.
> + */
>  static void *ufs_get_page(struct inode *dir, unsigned long n, struct page **page)
>  {
> +	char *kaddr;
> +
>  	struct address_space *mapping = dir->i_mapping;
>  	*page = read_mapping_page(mapping, n, NULL);
>  	if (!IS_ERR(*page)) {
> -		kmap(*page);
> +		kmap_local_page(*page);
>  		if (unlikely(!PageChecked(*page))) {
> -			if (!ufs_check_page(*page))
> +			if (!ufs_check_page(*page, kaddr))

	Er...  Building the patched tree is occasionally useful.
Here kaddr is obviously uninitialized and compiler would've
probably caught that.

	And return value of kmap_local_page() is lost, which
is related to the previous issue ;-)


>  				goto fail;
>  		}
>  	}
> -	return page;
> +	return *page;

Hell, no.  Callers expect the pointer to the first byte of
your page.  What it should return is kaddr.

> @@ -388,7 +406,8 @@ int ufs_add_link(struct dentry *dentry, struct inode *inode)
>  	mark_inode_dirty(dir);
>  	/* OFFSET_CACHE */
>  out_put:
> -	ufs_put_page(page);
> +	ufs_put_page(page, kaddr);
> +	return 0;
>  out_unlock:
>  	unlock_page(page);
>  	goto out_put;

That can't be right.  Places like
        if (err)
		goto out_unlock;
do not expect err to be lost.  You end up returning 0 now.  Something strange
happened here (in the previous commit, perhaps?)
Fabio M. De Francesco Dec. 12, 2022, 12:14 a.m. UTC | #2
On domenica 11 dicembre 2022 23:39:44 CET Al Viro wrote:
> On Sun, Dec 11, 2022 at 10:31:11PM +0100, Fabio M. De Francesco wrote:
> > +/*
> > + * Calls to ufs_get_page()/ufs_put_page() must be nested according to the
> > + * rules documented in kmap_local_page()/kunmap_local().
> > + *
> > + * NOTE: ufs_find_entry() and ufs_dotdot() act as calls to ufs_get_page()
> > + * and must be treated accordingly for nesting purposes.
> > + */
> > 
> >  static void *ufs_get_page(struct inode *dir, unsigned long n, struct page
> >  **page) {
> > 
> > +	char *kaddr;
> > +
> > 
> >  	struct address_space *mapping = dir->i_mapping;
> >  	*page = read_mapping_page(mapping, n, NULL);
> >  	if (!IS_ERR(*page)) {
> > 
> > -		kmap(*page);
> > +		kmap_local_page(*page);
> > 
> >  		if (unlikely(!PageChecked(*page))) {
> > 
> > -			if (!ufs_check_page(*page))
> > +			if (!ufs_check_page(*page, kaddr))
> 
> 	Er...  Building the patched tree is occasionally useful.
>
I don't know why gcc didn't catch this (gcc version 12.2.1 20221020 [revision 
0aaef83351473e8f4eb774f8f999bbe87a4866d7] (SUSE Linux)):

setarch i686
make ARCH=i386 O=../build-linux-x86_32-debug/ -j12
make[1]: Entering directory '/usr/src/git/kernels/build-linux-x86_32-debug'
  GEN     Makefile
  DESCEND bpf/resolve_btfids
  CALL    /usr/src/git/kernels/linux/scripts/checksyscalls.sh
  CC [M]  fs/ufs/dir.o
  LD [M]  fs/ufs/ufs.o
  MODPOST Module.symvers
Kernel: arch/x86/boot/bzImage is ready  (#3)
  LD [M]  fs/ufs/ufs.ko
  BTF [M] fs/ufs/ufs.ko
make[1]: Leaving directory '/usr/src/git/kernels/build-linux-x86_32-debug'

> Here kaddr is obviously uninitialized and compiler would've
> probably caught that.
>
I'd better use option W=1 next time.
>
> 	And return value of kmap_local_page() is lost, which
> is related to the previous issue ;-)
> 
> >  				goto fail;
> >  		
> >  		}
> >  	
> >  	}
> > 
> > -	return page;
> > +	return *page;
> 
> Hell, no.  Callers expect the pointer to the first byte of
> your page.  What it should return is kaddr.
>
I'm sorry that I entirely missed this :-(
> 
> > @@ -388,7 +406,8 @@ int ufs_add_link(struct dentry *dentry, struct inode
> > *inode)> 
> >  	mark_inode_dirty(dir);
> >  	/* OFFSET_CACHE */
> >  
> >  out_put:
> > -	ufs_put_page(page);
> > +	ufs_put_page(page, kaddr);
> > +	return 0;
> > 
> >  out_unlock:
> >  	unlock_page(page);
> >  	goto out_put;
> 
> That can't be right.  Places like
>         if (err)
> 		goto out_unlock;
> do not expect err to be lost.  You end up returning 0 now.  Something 
strange
> happened here (in the previous commit, perhaps?)
>
I don't yet know. Maybe that it is related to a copy-paste error or something 
like that...

As said, I'll send next version ASAP.

Again thanks for your kind help,

Fabio
Al Viro Dec. 12, 2022, 1:07 a.m. UTC | #3
On Mon, Dec 12, 2022 at 08:52:47AM +0800, kernel test robot wrote:

> >> fs/ufs/dir.c:210:22: warning: variable 'kaddr' is uninitialized when used here [-Wuninitialized]
>            ufs_put_page(*page, kaddr);
>                                ^~~~~
>    fs/ufs/dir.c:196:13: note: initialize the variable 'kaddr' to silence this warning
>            char *kaddr;
>                       ^
>                        = NULL
>    1 warning generated.

Warning is right, suggestion - worse than useless...
diff mbox series

Patch

diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index bb6b29ce1d3a..fd57d8171c88 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -61,9 +61,9 @@  static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len)
 	return err;
 }
 
-static inline void ufs_put_page(struct page *page)
+static inline void ufs_put_page(struct page *page, void *page_addr)
 {
-	kunmap(page);
+	kunmap((void *)((unsigned long)page_addr & PAGE_MASK));
 	put_page(page);
 }
 
@@ -76,7 +76,7 @@  ino_t ufs_inode_by_name(struct inode *dir, const struct qstr *qstr)
 	de = ufs_find_entry(dir, qstr, &page);
 	if (de) {
 		res = fs32_to_cpu(dir->i_sb, de->d_ino);
-		ufs_put_page(page);
+		ufs_put_page(page, de);
 	}
 	return res;
 }
@@ -99,18 +99,17 @@  void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
 	ufs_set_de_type(dir->i_sb, de, inode->i_mode);
 
 	err = ufs_commit_chunk(page, pos, len);
-	ufs_put_page(page);
+	ufs_put_page(page, de);
 	if (update_times)
 		dir->i_mtime = dir->i_ctime = current_time(dir);
 	mark_inode_dirty(dir);
 }
 
 
-static bool ufs_check_page(struct page *page)
+static bool ufs_check_page(struct page *page, char *kaddr)
 {
 	struct inode *dir = page->mapping->host;
 	struct super_block *sb = dir->i_sb;
-	char *kaddr = page_address(page);
 	unsigned offs, rec_len;
 	unsigned limit = PAGE_SIZE;
 	const unsigned chunk_mask = UFS_SB(sb)->s_uspi->s_dirblksize - 1;
@@ -185,21 +184,30 @@  static bool ufs_check_page(struct page *page)
 	return false;
 }
 
+/*
+ * Calls to ufs_get_page()/ufs_put_page() must be nested according to the
+ * rules documented in kmap_local_page()/kunmap_local().
+ *
+ * NOTE: ufs_find_entry() and ufs_dotdot() act as calls to ufs_get_page()
+ * and must be treated accordingly for nesting purposes.
+ */
 static void *ufs_get_page(struct inode *dir, unsigned long n, struct page **page)
 {
+	char *kaddr;
+
 	struct address_space *mapping = dir->i_mapping;
 	*page = read_mapping_page(mapping, n, NULL);
 	if (!IS_ERR(*page)) {
-		kmap(*page);
+		kmap_local_page(*page);
 		if (unlikely(!PageChecked(*page))) {
-			if (!ufs_check_page(*page))
+			if (!ufs_check_page(*page, kaddr))
 				goto fail;
 		}
 	}
-	return page;
+	return *page;
 
 fail:
-	ufs_put_page(*page);
+	ufs_put_page(*page, kaddr);
 	return ERR_PTR(-EIO);
 }
 
@@ -225,6 +233,13 @@  ufs_next_entry(struct super_block *sb, struct ufs_dir_entry *p)
 					fs16_to_cpu(sb, p->d_reclen));
 }
 
+/*
+ * Calls to ufs_get_page()/ufs_put_page() must be nested according to the
+ * rules documented in kmap_local_page()/kunmap_local().
+ *
+ * ufs_dotdot() acts as a call to ufs_get_page() and must be treated
+ * accordingly for nesting purposes.
+ */
 struct ufs_dir_entry *ufs_dotdot(struct inode *dir, struct page **p)
 {
 	struct ufs_dir_entry *de = ufs_get_page(dir, 0, p);
@@ -236,12 +251,15 @@  struct ufs_dir_entry *ufs_dotdot(struct inode *dir, struct page **p)
 }
 
 /*
- *	ufs_find_entry()
+ * Finds an entry in the specified directory with the wanted name. It returns a
+ * pointer to the directory's entry. The page in which the entry was found is
+ * in the res_page out parameter. The page is returned mapped and unlocked.
+ * The entry is guaranteed to be valid.
+ *
+ * On Success ufs_put_page() should be called on *res_page.
  *
- * finds an entry in the specified directory with the wanted name. It
- * returns the page in which the entry was found, and the entry itself
- * (as a parameter - res_dir). Page is returned mapped and unlocked.
- * Entry is guaranteed to be valid.
+ * ufs_find_entry() acts as a call to ufs_get_page() and must be treated
+ * accordingly for nesting purposes.
  */
 struct ufs_dir_entry *ufs_find_entry(struct inode *dir, const struct qstr *qstr,
 				     struct page **res_page)
@@ -280,7 +298,7 @@  struct ufs_dir_entry *ufs_find_entry(struct inode *dir, const struct qstr *qstr,
 					goto found;
 				de = ufs_next_entry(sb, de);
 			}
-			ufs_put_page(page);
+			ufs_put_page(page, kaddr);
 		}
 		if (++n >= npages)
 			n = 0;
@@ -358,7 +376,7 @@  int ufs_add_link(struct dentry *dentry, struct inode *inode)
 			de = (struct ufs_dir_entry *) ((char *) de + rec_len);
 		}
 		unlock_page(page);
-		ufs_put_page(page);
+		ufs_put_page(page, kaddr);
 	}
 	BUG();
 	return -EINVAL;
@@ -388,7 +406,8 @@  int ufs_add_link(struct dentry *dentry, struct inode *inode)
 	mark_inode_dirty(dir);
 	/* OFFSET_CACHE */
 out_put:
-	ufs_put_page(page);
+	ufs_put_page(page, kaddr);
+	return 0;
 out_unlock:
 	unlock_page(page);
 	goto out_put;
@@ -465,13 +484,13 @@  ufs_readdir(struct file *file, struct dir_context *ctx)
 					       ufs_get_de_namlen(sb, de),
 					       fs32_to_cpu(sb, de->d_ino),
 					       d_type)) {
-					ufs_put_page(page);
+					ufs_put_page(page, kaddr);
 					return 0;
 				}
 			}
 			ctx->pos += fs16_to_cpu(sb, de->d_reclen);
 		}
-		ufs_put_page(page);
+		ufs_put_page(page, kaddr);
 	}
 	return 0;
 }
@@ -482,10 +501,10 @@  ufs_readdir(struct file *file, struct dir_context *ctx)
  * previous entry.
  */
 int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir,
-		     struct page * page)
+		     struct page *page)
 {
 	struct super_block *sb = inode->i_sb;
-	char *kaddr = page_address(page);
+	char *kaddr = (char *)((unsigned long)dir & PAGE_MASK);
 	unsigned int from = offset_in_page(dir) & ~(UFS_SB(sb)->s_uspi->s_dirblksize - 1);
 	unsigned int to = offset_in_page(dir) + fs16_to_cpu(sb, dir->d_reclen);
 	loff_t pos;
@@ -524,7 +543,7 @@  int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir,
 	inode->i_ctime = inode->i_mtime = current_time(inode);
 	mark_inode_dirty(inode);
 out:
-	ufs_put_page(page);
+	ufs_put_page(page, kaddr);
 	UFSD("EXIT\n");
 	return err;
 }
@@ -548,8 +567,7 @@  int ufs_make_empty(struct inode * inode, struct inode *dir)
 		goto fail;
 	}
 
-	kmap(page);
-	base = (char*)page_address(page);
+	base = kmap_local_page(page);
 	memset(base, 0, PAGE_SIZE);
 
 	de = (struct ufs_dir_entry *) base;
@@ -566,7 +584,7 @@  int ufs_make_empty(struct inode * inode, struct inode *dir)
 	de->d_reclen = cpu_to_fs16(sb, chunk_size - UFS_DIR_REC_LEN(1));
 	ufs_set_de_namlen(sb, de, 2);
 	strcpy (de->d_name, "..");
-	kunmap(page);
+	kunmap_local(base);
 
 	err = ufs_commit_chunk(page, 0, chunk_size);
 fail:
@@ -582,9 +600,9 @@  int ufs_empty_dir(struct inode * inode)
 	struct super_block *sb = inode->i_sb;
 	struct page *page = NULL;
 	unsigned long i, npages = dir_pages(inode);
+	char *kaddr;
 
 	for (i = 0; i < npages; i++) {
-		char *kaddr;
 		struct ufs_dir_entry *de;
 
 		kaddr = ufs_get_page(inode, i, &page);
@@ -617,12 +635,12 @@  int ufs_empty_dir(struct inode * inode)
 			}
 			de = ufs_next_entry(sb, de);
 		}
-		ufs_put_page(page);
+		ufs_put_page(page, kaddr);
 	}
 	return 1;
 
 not_empty:
-	ufs_put_page(page);
+	ufs_put_page(page, kaddr);
 	return 0;
 }