[v9,1/4] unicode: Add utf8_casefold_hash
diff mbox series

Message ID 20200624043341.33364-2-drosen@google.com
State Superseded
Headers show
Series
  • Prepare for upcoming Casefolding/Encryption patches
Related show

Commit Message

Daniel Rosenberg June 24, 2020, 4:33 a.m. UTC
This adds a case insensitive hash function to allow taking the hash
without needing to allocate a casefolded copy of the string.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
---
 fs/unicode/utf8-core.c  | 23 ++++++++++++++++++++++-
 include/linux/unicode.h |  3 +++
 2 files changed, 25 insertions(+), 1 deletion(-)

Comments

Gabriel Krisman Bertazi June 24, 2020, 5:13 a.m. UTC | #1
Daniel Rosenberg <drosen@google.com> writes:

> This adds a case insensitive hash function to allow taking the hash
> without needing to allocate a casefolded copy of the string.
>
> Signed-off-by: Daniel Rosenberg <drosen@google.com>
> ---
>  fs/unicode/utf8-core.c  | 23 ++++++++++++++++++++++-
>  include/linux/unicode.h |  3 +++
>  2 files changed, 25 insertions(+), 1 deletion(-)
>
> diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
> index 2a878b739115d..90656b9980720 100644
> --- a/fs/unicode/utf8-core.c
> +++ b/fs/unicode/utf8-core.c
> @@ -6,6 +6,7 @@
>  #include <linux/parser.h>
>  #include <linux/errno.h>
>  #include <linux/unicode.h>
> +#include <linux/stringhash.h>
>  
>  #include "utf8n.h"
>  
> @@ -122,9 +123,29 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
>  	}
>  	return -EINVAL;
>  }
> -
>  EXPORT_SYMBOL(utf8_casefold);
>  
> +int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
> +		       struct qstr *str)
> +{
> +	const struct utf8data *data = utf8nfdicf(um->version);
> +	struct utf8cursor cur;
> +	int c;
> +	unsigned long hash = init_name_hash(salt);
> +
> +	if (utf8ncursor(&cur, data, str->name, str->len) < 0)
> +		return -EINVAL;
> +
> +	while ((c = utf8byte(&cur))) {
> +		if (c < 0)
> +			return c;

Return -EINVAL here to match other unicode functions, since utf8byte
will return -1 on a binary blob, which doesn't make sense for this.

Other than that, looks good to me.

Reviewed-by: Gabriel Krisman Bertazi <krisman@collabora.com>

> +		hash = partial_name_hash((unsigned char)c, hash);
> +	}
> +	str->hash = end_name_hash(hash);
> +	return 0;
> +}
> +EXPORT_SYMBOL(utf8_casefold_hash);
> +
>  int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
>  		   unsigned char *dest, size_t dlen)
>  {
> diff --git a/include/linux/unicode.h b/include/linux/unicode.h
> index 990aa97d80496..74484d44c7554 100644
> --- a/include/linux/unicode.h
> +++ b/include/linux/unicode.h
> @@ -27,6 +27,9 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
>  int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
>  		  unsigned char *dest, size_t dlen);
>  
> +int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
> +		       struct qstr *str);
> +
>  struct unicode_map *utf8_load(const char *version);
>  void utf8_unload(struct unicode_map *um);
Eric Biggers June 24, 2020, 5:37 a.m. UTC | #2
On Tue, Jun 23, 2020 at 09:33:38PM -0700, Daniel Rosenberg wrote:
> This adds a case insensitive hash function to allow taking the hash
> without needing to allocate a casefolded copy of the string.

It would be helpful to add a few more details in this commit message.
Somewhat along the lines of: ->d_hash() for casefolding currently allocates
memory, it needs to use GFP_ATOMIC due to ->d_hash() being called in rcu-walk
mode, this is unreliable and inefficient, and this patch allows solving that
problem by removing the need to allocate memory.

- Eric

Patch
diff mbox series

diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
index 2a878b739115d..90656b9980720 100644
--- a/fs/unicode/utf8-core.c
+++ b/fs/unicode/utf8-core.c
@@ -6,6 +6,7 @@ 
 #include <linux/parser.h>
 #include <linux/errno.h>
 #include <linux/unicode.h>
+#include <linux/stringhash.h>
 
 #include "utf8n.h"
 
@@ -122,9 +123,29 @@  int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 	}
 	return -EINVAL;
 }
-
 EXPORT_SYMBOL(utf8_casefold);
 
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+		       struct qstr *str)
+{
+	const struct utf8data *data = utf8nfdicf(um->version);
+	struct utf8cursor cur;
+	int c;
+	unsigned long hash = init_name_hash(salt);
+
+	if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+		return -EINVAL;
+
+	while ((c = utf8byte(&cur))) {
+		if (c < 0)
+			return c;
+		hash = partial_name_hash((unsigned char)c, hash);
+	}
+	str->hash = end_name_hash(hash);
+	return 0;
+}
+EXPORT_SYMBOL(utf8_casefold_hash);
+
 int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 		   unsigned char *dest, size_t dlen)
 {
diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index 990aa97d80496..74484d44c7554 100644
--- a/include/linux/unicode.h
+++ b/include/linux/unicode.h
@@ -27,6 +27,9 @@  int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 		  unsigned char *dest, size_t dlen);
 
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+		       struct qstr *str);
+
 struct unicode_map *utf8_load(const char *version);
 void utf8_unload(struct unicode_map *um);