* [PATCH v7 5/6] syncookies: use SipHash in place of SHA1
From: Jason A. Donenfeld @ 2016-12-21 23:02 UTC (permalink / raw)
To: Netdev, kernel-hardening, LKML, linux-crypto, David Laight,
Ted Tso, Hannes Frederic Sowa, edumazet, Linus Torvalds,
Eric Biggers, Tom Herbert, ak, davem, luto,
Jean-Philippe Aumasson
Cc: Jason A. Donenfeld, Eric Dumazet
In-Reply-To: <20161221230216.25341-1-Jason@zx2c4.com>
SHA1 is slower and less secure than SipHash, and so replacing syncookie
generation with SipHash makes natural sense. Some BSDs have been doing
this for several years in fact.
The speedup should be similar -- and even more impressive -- to the
speedup from the sequence number fix in this series.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David Miller <davem@davemloft.net>
---
net/ipv4/syncookies.c | 20 ++++----------------
net/ipv6/syncookies.c | 37 ++++++++++++++++---------------------
2 files changed, 20 insertions(+), 37 deletions(-)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 3e88467d70ee..03bb068f8888 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -13,13 +13,13 @@
#include <linux/tcp.h>
#include <linux/slab.h>
#include <linux/random.h>
-#include <linux/cryptohash.h>
+#include <linux/siphash.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <net/tcp.h>
#include <net/route.h>
-static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
+static siphash_key_t syncookie_secret[2] __read_mostly;
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
@@ -48,24 +48,12 @@ static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
#define TSBITS 6
#define TSMASK (((__u32)1 << TSBITS) - 1)
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv4_cookie_scratch);
-
static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
u32 count, int c)
{
- __u32 *tmp;
-
net_get_random_once(syncookie_secret, sizeof(syncookie_secret));
-
- tmp = this_cpu_ptr(ipv4_cookie_scratch);
- memcpy(tmp + 4, syncookie_secret[c], sizeof(syncookie_secret[c]));
- tmp[0] = (__force u32)saddr;
- tmp[1] = (__force u32)daddr;
- tmp[2] = ((__force u32)sport << 16) + (__force u32)dport;
- tmp[3] = count;
- sha_transform(tmp + 16, (__u8 *)tmp, tmp + 16 + 5);
-
- return tmp[17];
+ return siphash_4u32(saddr, daddr, (u32)sport << 16 | dport, count,
+ syncookie_secret[c]);
}
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index a4d49760bf43..be51fc0d99ad 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -16,7 +16,7 @@
#include <linux/tcp.h>
#include <linux/random.h>
-#include <linux/cryptohash.h>
+#include <linux/siphash.h>
#include <linux/kernel.h>
#include <net/ipv6.h>
#include <net/tcp.h>
@@ -24,7 +24,7 @@
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
-static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
+static siphash_key_t syncookie6_secret[2] __read_mostly;
/* RFC 2460, Section 8.3:
* [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
@@ -41,30 +41,25 @@ static __u16 const msstab[] = {
9000 - 60,
};
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv6_cookie_scratch);
-
static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr,
__be16 sport, __be16 dport, u32 count, int c)
{
- __u32 *tmp;
+ const struct {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ u32 count;
+ u16 sport;
+ u16 dport;
+ } __aligned(SIPHASH_ALIGNMENT) combined = {
+ .saddr = *saddr,
+ .daddr = *daddr,
+ .count = count,
+ .sport = sport,
+ .dport = dport
+ };
net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret));
-
- tmp = this_cpu_ptr(ipv6_cookie_scratch);
-
- /*
- * we have 320 bits of information to hash, copy in the remaining
- * 192 bits required for sha_transform, from the syncookie6_secret
- * and overwrite the digest with the secret
- */
- memcpy(tmp + 10, syncookie6_secret[c], 44);
- memcpy(tmp, saddr, 16);
- memcpy(tmp + 4, daddr, 16);
- tmp[8] = ((__force u32)sport << 16) + (__force u32)dport;
- tmp[9] = count;
- sha_transform(tmp + 16, (__u8 *)tmp, tmp + 16 + 5);
-
- return tmp[17];
+ return siphash(&combined, offsetofend(typeof(combined), dport), syncookie6_secret[c]);
}
static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
--
2.11.0
^ permalink raw reply related
* [PATCH v7 4/6] md5: remove from lib and only live in crypto
From: Jason A. Donenfeld @ 2016-12-21 23:02 UTC (permalink / raw)
To: Netdev, kernel-hardening, LKML, linux-crypto, David Laight,
Ted Tso, Hannes Frederic Sowa, edumazet, Linus Torvalds,
Eric Biggers, Tom Herbert, ak, davem, luto,
Jean-Philippe Aumasson
Cc: Jason A. Donenfeld
In-Reply-To: <20161221230216.25341-1-Jason@zx2c4.com>
The md5_transform function is no longer used any where in the tree,
except for the crypto api's actual implementation of md5, so we can drop
the function from lib and put it as a static function of the crypto
file, where it belongs. There should be no new users of md5_transform,
anyway, since there are more modern ways of doing what it once achieved.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
crypto/md5.c | 95 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
lib/Makefile | 2 +-
lib/md5.c | 95 ------------------------------------------------------------
3 files changed, 95 insertions(+), 97 deletions(-)
delete mode 100644 lib/md5.c
diff --git a/crypto/md5.c b/crypto/md5.c
index 2355a7c25c45..f7ae1a48225b 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -21,9 +21,11 @@
#include <linux/module.h>
#include <linux/string.h>
#include <linux/types.h>
-#include <linux/cryptohash.h>
#include <asm/byteorder.h>
+#define MD5_DIGEST_WORDS 4
+#define MD5_MESSAGE_BYTES 64
+
const u8 md5_zero_message_hash[MD5_DIGEST_SIZE] = {
0xd4, 0x1d, 0x8c, 0xd9, 0x8f, 0x00, 0xb2, 0x04,
0xe9, 0x80, 0x09, 0x98, 0xec, 0xf8, 0x42, 0x7e,
@@ -47,6 +49,97 @@ static inline void cpu_to_le32_array(u32 *buf, unsigned int words)
}
}
+#define F1(x, y, z) (z ^ (x & (y ^ z)))
+#define F2(x, y, z) F1(z, x, y)
+#define F3(x, y, z) (x ^ y ^ z)
+#define F4(x, y, z) (y ^ (x | ~z))
+
+#define MD5STEP(f, w, x, y, z, in, s) \
+ (w += f(x, y, z) + in, w = (w<<s | w>>(32-s)) + x)
+
+static void md5_transform(__u32 *hash, __u32 const *in)
+{
+ u32 a, b, c, d;
+
+ a = hash[0];
+ b = hash[1];
+ c = hash[2];
+ d = hash[3];
+
+ MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
+ MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
+ MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
+ MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
+ MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
+ MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
+ MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
+ MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
+ MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
+ MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
+ MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
+ MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
+ MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
+ MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
+ MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
+ MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
+
+ MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
+ MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
+ MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
+ MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
+ MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
+ MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
+ MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
+ MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
+ MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
+ MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
+ MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
+ MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
+ MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
+ MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
+ MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
+ MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
+
+ MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
+ MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
+ MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
+ MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
+ MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
+ MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
+ MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
+ MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
+ MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
+ MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
+ MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
+ MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
+ MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
+ MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
+ MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
+ MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
+
+ MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
+ MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
+ MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
+ MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
+ MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
+ MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
+ MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
+ MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
+ MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
+ MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
+ MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
+ MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
+ MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
+ MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
+ MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
+ MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
+
+ hash[0] += a;
+ hash[1] += b;
+ hash[2] += c;
+ hash[3] += d;
+}
+
static inline void md5_transform_helper(struct md5_state *ctx)
{
le32_to_cpu_array(ctx->block, sizeof(ctx->block) / sizeof(u32));
diff --git a/lib/Makefile b/lib/Makefile
index 71d398b04a74..1079152607e0 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -19,7 +19,7 @@ KCOV_INSTRUMENT_dynamic_debug.o := n
lib-y := ctype.o string.o vsprintf.o cmdline.o \
rbtree.o radix-tree.o dump_stack.o timerqueue.o\
idr.o int_sqrt.o extable.o \
- sha1.o chacha20.o md5.o irq_regs.o argv_split.o \
+ sha1.o chacha20.o irq_regs.o argv_split.o \
flex_proportions.o ratelimit.o show_mem.o \
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
earlycpio.o seq_buf.o siphash.o \
diff --git a/lib/md5.c b/lib/md5.c
deleted file mode 100644
index bb0cd01d356d..000000000000
--- a/lib/md5.c
+++ /dev/null
@@ -1,95 +0,0 @@
-#include <linux/compiler.h>
-#include <linux/export.h>
-#include <linux/cryptohash.h>
-
-#define F1(x, y, z) (z ^ (x & (y ^ z)))
-#define F2(x, y, z) F1(z, x, y)
-#define F3(x, y, z) (x ^ y ^ z)
-#define F4(x, y, z) (y ^ (x | ~z))
-
-#define MD5STEP(f, w, x, y, z, in, s) \
- (w += f(x, y, z) + in, w = (w<<s | w>>(32-s)) + x)
-
-void md5_transform(__u32 *hash, __u32 const *in)
-{
- u32 a, b, c, d;
-
- a = hash[0];
- b = hash[1];
- c = hash[2];
- d = hash[3];
-
- MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
- MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
- MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
- MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
- MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
- MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
- MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
- MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
- MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
- MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
- MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
- MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
- MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
- MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
- MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
- MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
-
- MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
- MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
- MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
- MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
- MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
- MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
- MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
- MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
- MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
- MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
- MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
- MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
- MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
- MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
- MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
- MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
-
- MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
- MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
- MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
- MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
- MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
- MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
- MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
- MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
- MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
- MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
- MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
- MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
- MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
- MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
- MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
- MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
-
- MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
- MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
- MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
- MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
- MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
- MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
- MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
- MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
- MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
- MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
- MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
- MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
- MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
- MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
- MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
- MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
-
- hash[0] += a;
- hash[1] += b;
- hash[2] += c;
- hash[3] += d;
-}
-EXPORT_SYMBOL(md5_transform);
--
2.11.0
^ permalink raw reply related
* [PATCH v7 3/6] random: use SipHash in place of MD5
From: Jason A. Donenfeld @ 2016-12-21 23:02 UTC (permalink / raw)
To: Netdev, kernel-hardening, LKML, linux-crypto, David Laight,
Ted Tso, Hannes Frederic Sowa, edumazet, Linus Torvalds,
Eric Biggers, Tom Herbert, ak, davem, luto,
Jean-Philippe Aumasson
Cc: Jason A. Donenfeld
In-Reply-To: <20161221230216.25341-1-Jason@zx2c4.com>
This duplicates the current algorithm for get_random_int/long, but uses
siphash instead. This comes with several benefits. It's certainly
faster and more cryptographically secure than MD5. This patch also
separates hashed fields into three values instead of one, in order to
increase diffusion.
The previous MD5 algorithm used a per-cpu MD5 state, which caused
successive calls to the function to chain upon each other. While it's
not entirely clear that this kind of chaining is absolutely necessary
when using a secure PRF like siphash, it can't hurt, and the timing of
the call chain does add a degree of natural entropy. So, in keeping with
this design, instead of the massive per-cpu 64-byte MD5 state, there is
instead a per-cpu previously returned value for chaining.
The speed benefits are substantial:
| siphash | md5 | speedup |
------------------------------
get_random_long | 137130 | 415983 | 3.03x |
get_random_int | 86384 | 343323 | 3.97x |
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com>
Cc: Ted Tso <tytso@mit.edu>
---
drivers/char/random.c | 84 +++++++++++++++++++++++++++++---------------------
include/linux/random.h | 1 -
init/main.c | 1 -
3 files changed, 49 insertions(+), 37 deletions(-)
diff --git a/drivers/char/random.c b/drivers/char/random.c
index d6876d506220..ea9858d9d8b4 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -262,6 +262,7 @@
#include <linux/syscalls.h>
#include <linux/completion.h>
#include <linux/uuid.h>
+#include <linux/siphash.h>
#include <crypto/chacha20.h>
#include <asm/processor.h>
@@ -2042,17 +2043,31 @@ struct ctl_table random_table[] = {
};
#endif /* CONFIG_SYSCTL */
-static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
-int random_int_secret_init(void)
+struct random_int_secret {
+ siphash_key_t secret;
+ u64 chaining;
+ unsigned long birthdate;
+ bool initialized;
+};
+static DEFINE_PER_CPU(struct random_int_secret, random_int_secret);
+
+enum {
+ SECRET_ROTATION_TIME = HZ * 60 * 5
+};
+
+static struct random_int_secret *get_random_int_secret(void)
{
- get_random_bytes(random_int_secret, sizeof(random_int_secret));
- return 0;
+ struct random_int_secret *secret = &get_cpu_var(random_int_secret);
+ if (unlikely(!secret->initialized ||
+ !time_is_after_jiffies(secret->birthdate + SECRET_ROTATION_TIME))) {
+ secret->initialized = true;
+ secret->birthdate = jiffies;
+ get_random_bytes(secret->secret, sizeof(secret->secret));
+ }
+ return secret;
}
-static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
- __aligned(sizeof(unsigned long));
-
/*
* Get a random word for internal kernel use only. Similar to urandom but
* with the goal of minimal entropy pool depletion. As a result, the random
@@ -2061,20 +2076,20 @@ static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
*/
unsigned int get_random_int(void)
{
- __u32 *hash;
- unsigned int ret;
-
- if (arch_get_random_int(&ret))
- return ret;
-
- hash = get_cpu_var(get_random_int_hash);
-
- hash[0] += current->pid + jiffies + random_get_entropy();
- md5_transform(hash, random_int_secret);
- ret = hash[0];
- put_cpu_var(get_random_int_hash);
-
- return ret;
+ unsigned int arch_result;
+ u64 result;
+ struct random_int_secret *secret;
+
+ if (arch_get_random_int(&arch_result))
+ return arch_result;
+
+ secret = get_random_int_secret();
+ result = siphash_3u64(secret->chaining, jiffies,
+ (u64)random_get_entropy() + current->pid,
+ secret->secret);
+ secret->chaining += result;
+ put_cpu_var(secret);
+ return result;
}
EXPORT_SYMBOL(get_random_int);
@@ -2083,20 +2098,19 @@ EXPORT_SYMBOL(get_random_int);
*/
unsigned long get_random_long(void)
{
- __u32 *hash;
- unsigned long ret;
-
- if (arch_get_random_long(&ret))
- return ret;
-
- hash = get_cpu_var(get_random_int_hash);
-
- hash[0] += current->pid + jiffies + random_get_entropy();
- md5_transform(hash, random_int_secret);
- ret = *(unsigned long *)hash;
- put_cpu_var(get_random_int_hash);
-
- return ret;
+ unsigned long arch_result;
+ u64 result;
+ struct random_int_secret *secret;
+
+ if (arch_get_random_long(&arch_result))
+ return arch_result;
+
+ secret = get_random_int_secret();
+ result = siphash_3u64(secret->chaining, jiffies, random_get_entropy() +
+ current->pid, secret->secret);
+ secret->chaining += result;
+ put_cpu_var(secret);
+ return result;
}
EXPORT_SYMBOL(get_random_long);
diff --git a/include/linux/random.h b/include/linux/random.h
index 7bd2403e4fef..16ab429735a7 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -37,7 +37,6 @@ extern void get_random_bytes(void *buf, int nbytes);
extern int add_random_ready_callback(struct random_ready_callback *rdy);
extern void del_random_ready_callback(struct random_ready_callback *rdy);
extern void get_random_bytes_arch(void *buf, int nbytes);
-extern int random_int_secret_init(void);
#ifndef MODULE
extern const struct file_operations random_fops, urandom_fops;
diff --git a/init/main.c b/init/main.c
index 23c275cca73a..a3af9296cafd 100644
--- a/init/main.c
+++ b/init/main.c
@@ -879,7 +879,6 @@ static void __init do_basic_setup(void)
do_ctors();
usermodehelper_enable();
do_initcalls();
- random_int_secret_init();
}
static void __init do_pre_smp_initcalls(void)
--
2.11.0
^ permalink raw reply related
* [PATCH v7 2/6] secure_seq: use SipHash in place of MD5
From: Jason A. Donenfeld @ 2016-12-21 23:02 UTC (permalink / raw)
To: Netdev, kernel-hardening, LKML, linux-crypto, David Laight,
Ted Tso, Hannes Frederic Sowa, edumazet, Linus Torvalds,
Eric Biggers, Tom Herbert, ak, davem, luto,
Jean-Philippe Aumasson
Cc: Jason A. Donenfeld, Eric Dumazet
In-Reply-To: <20161221230216.25341-1-Jason@zx2c4.com>
This gives a clear speed and security improvement. Siphash is both
faster and is more solid crypto than the aging MD5.
Rather than manually filling MD5 buffers, for IPv6, we simply create
a layout by a simple anonymous struct, for which gcc generates
rather efficient code. For IPv4, we pass the values directly to the
short input convenience functions.
64-bit x86_64:
[ 1.683628] secure_tcpv6_sequence_number_md5# cycles: 99563527
[ 1.717350] secure_tcp_sequence_number_md5# cycles: 92890502
[ 1.741968] secure_tcpv6_sequence_number_siphash# cycles: 67825362
[ 1.762048] secure_tcp_sequence_number_siphash# cycles: 67485526
32-bit x86:
[ 1.600012] secure_tcpv6_sequence_number_md5# cycles: 103227892
[ 1.634219] secure_tcp_sequence_number_md5# cycles: 94732544
[ 1.669102] secure_tcpv6_sequence_number_siphash# cycles: 96299384
[ 1.700165] secure_tcp_sequence_number_siphash# cycles: 86015473
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Miller <davem@davemloft.net>
Cc: David Laight <David.Laight@aculab.com>
Cc: Tom Herbert <tom@herbertland.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
---
net/core/secure_seq.c | 135 ++++++++++++++++++++------------------------------
1 file changed, 54 insertions(+), 81 deletions(-)
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 88a8e429fc3e..3dc2689bcc64 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -1,3 +1,5 @@
+/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */
+
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/cryptohash.h>
@@ -8,14 +10,14 @@
#include <linux/ktime.h>
#include <linux/string.h>
#include <linux/net.h>
-
+#include <linux/siphash.h>
#include <net/secure_seq.h>
#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET)
+#include <linux/in6.h>
#include <net/tcp.h>
-#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
-static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
+static siphash_key_t net_secret;
static __always_inline void net_secret_init(void)
{
@@ -44,80 +46,65 @@ static u32 seq_scale(u32 seq)
u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
__be16 sport, __be16 dport, u32 *tsoff)
{
- u32 secret[MD5_MESSAGE_BYTES / 4];
- u32 hash[MD5_DIGEST_WORDS];
- u32 i;
-
+ const struct {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ __be16 sport;
+ __be16 dport;
+ } __aligned(SIPHASH_ALIGNMENT) combined = {
+ .saddr = *(struct in6_addr *)saddr,
+ .daddr = *(struct in6_addr *)daddr,
+ .sport = sport,
+ .dport = dport
+ };
+ u64 hash;
net_secret_init();
- memcpy(hash, saddr, 16);
- for (i = 0; i < 4; i++)
- secret[i] = net_secret[i] + (__force u32)daddr[i];
- secret[4] = net_secret[4] +
- (((__force u16)sport << 16) + (__force u16)dport);
- for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
- secret[i] = net_secret[i];
-
- md5_transform(hash, secret);
-
- *tsoff = sysctl_tcp_timestamps == 1 ? hash[1] : 0;
- return seq_scale(hash[0]);
+ hash = siphash(&combined, offsetofend(typeof(combined), dport), net_secret);
+ *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+ return seq_scale(hash);
}
EXPORT_SYMBOL(secure_tcpv6_sequence_number);
u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
__be16 dport)
{
- u32 secret[MD5_MESSAGE_BYTES / 4];
- u32 hash[MD5_DIGEST_WORDS];
- u32 i;
-
+ const struct {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ __be16 dport;
+ } __aligned(SIPHASH_ALIGNMENT) combined = {
+ .saddr = *(struct in6_addr *)saddr,
+ .daddr = *(struct in6_addr *)daddr,
+ .dport = dport
+ };
net_secret_init();
- memcpy(hash, saddr, 16);
- for (i = 0; i < 4; i++)
- secret[i] = net_secret[i] + (__force u32) daddr[i];
- secret[4] = net_secret[4] + (__force u32)dport;
- for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
- secret[i] = net_secret[i];
-
- md5_transform(hash, secret);
-
- return hash[0];
+ return siphash(&combined, offsetofend(typeof(combined), dport), net_secret);
}
EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
#endif
#ifdef CONFIG_INET
+/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
+ * but fortunately, `sport' cannot be 0 in any circumstances. If this changes,
+ * it would be easy enough to have the former function use siphash_4u32, passing
+ * the arguments as separate u32.
+ */
+
u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
__be16 sport, __be16 dport, u32 *tsoff)
{
- u32 hash[MD5_DIGEST_WORDS];
-
+ u64 hash;
net_secret_init();
- hash[0] = (__force u32)saddr;
- hash[1] = (__force u32)daddr;
- hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
- hash[3] = net_secret[15];
-
- md5_transform(hash, net_secret);
-
- *tsoff = sysctl_tcp_timestamps == 1 ? hash[1] : 0;
- return seq_scale(hash[0]);
+ hash = siphash_3u32(saddr, daddr, (u32)sport << 16 | dport, net_secret);
+ *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+ return seq_scale(hash);
}
u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
{
- u32 hash[MD5_DIGEST_WORDS];
-
net_secret_init();
- hash[0] = (__force u32)saddr;
- hash[1] = (__force u32)daddr;
- hash[2] = (__force u32)dport ^ net_secret[14];
- hash[3] = net_secret[15];
-
- md5_transform(hash, net_secret);
-
- return hash[0];
+ return siphash_3u32(saddr, daddr, dport, net_secret);
}
EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
#endif
@@ -126,21 +113,11 @@ EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
__be16 sport, __be16 dport)
{
- u32 hash[MD5_DIGEST_WORDS];
u64 seq;
-
net_secret_init();
- hash[0] = (__force u32)saddr;
- hash[1] = (__force u32)daddr;
- hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
- hash[3] = net_secret[15];
-
- md5_transform(hash, net_secret);
-
- seq = hash[0] | (((u64)hash[1]) << 32);
+ seq = siphash_3u32(saddr, daddr, (u32)sport << 16 | dport, net_secret);
seq += ktime_get_real_ns();
seq &= (1ull << 48) - 1;
-
return seq;
}
EXPORT_SYMBOL(secure_dccp_sequence_number);
@@ -149,26 +126,22 @@ EXPORT_SYMBOL(secure_dccp_sequence_number);
u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
__be16 sport, __be16 dport)
{
- u32 secret[MD5_MESSAGE_BYTES / 4];
- u32 hash[MD5_DIGEST_WORDS];
+ const struct {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ __be16 sport;
+ __be16 dport;
+ } __aligned(SIPHASH_ALIGNMENT) combined = {
+ .saddr = *(struct in6_addr *)saddr,
+ .daddr = *(struct in6_addr *)daddr,
+ .sport = sport,
+ .dport = dport
+ };
u64 seq;
- u32 i;
-
net_secret_init();
- memcpy(hash, saddr, 16);
- for (i = 0; i < 4; i++)
- secret[i] = net_secret[i] + (__force u32)daddr[i];
- secret[4] = net_secret[4] +
- (((__force u16)sport << 16) + (__force u16)dport);
- for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
- secret[i] = net_secret[i];
-
- md5_transform(hash, secret);
-
- seq = hash[0] | (((u64)hash[1]) << 32);
+ seq = siphash(&combined, offsetofend(typeof(combined), dport), net_secret);
seq += ktime_get_real_ns();
seq &= (1ull << 48) - 1;
-
return seq;
}
EXPORT_SYMBOL(secure_dccpv6_sequence_number);
--
2.11.0
^ permalink raw reply related
* [PATCH v7 1/6] siphash: add cryptographically secure PRF
From: Jason A. Donenfeld @ 2016-12-21 23:02 UTC (permalink / raw)
To: Netdev, kernel-hardening, LKML, linux-crypto, David Laight,
Ted Tso, Hannes Frederic Sowa, edumazet, Linus Torvalds,
Eric Biggers, Tom Herbert, ak, davem, luto,
Jean-Philippe Aumasson
Cc: Jason A. Donenfeld, Eric Dumazet
In-Reply-To: <20161221230216.25341-1-Jason@zx2c4.com>
SipHash is a 64-bit keyed hash function that is actually a
cryptographically secure PRF, like HMAC. Except SipHash is super fast,
and is meant to be used as a hashtable keyed lookup function, or as a
general PRF for short input use cases, such as sequence numbers or RNG
chaining.
For the first usage:
There are a variety of attacks known as "hashtable poisoning" in which an
attacker forms some data such that the hash of that data will be the
same, and then preceeds to fill up all entries of a hashbucket. This is
a realistic and well-known denial-of-service vector. Currently
hashtables use jhash, which is fast but not secure, and some kind of
rotating key scheme (or none at all, which isn't good). SipHash is meant
as a replacement for jhash in these cases.
There are a modicum of places in the kernel that are vulnerable to
hashtable poisoning attacks, either via userspace vectors or network
vectors, and there's not a reliable mechanism inside the kernel at the
moment to fix it. The first step toward fixing these issues is actually
getting a secure primitive into the kernel for developers to use. Then
we can, bit by bit, port things over to it as deemed appropriate.
While SipHash is extremely fast for a cryptographically secure function,
it is likely a bit slower than the insecure jhash, and so replacements
will be evaluated on a case-by-case basis based on whether or not the
difference in speed is negligible and whether or not the current jhash usage
poses a real security risk.
For the second usage:
A few places in the kernel are using MD5 or SHA1 for creating secure
sequence numbers, syn cookies, port numbers, or fast random numbers.
SipHash is a faster and more fitting, and more secure replacement for MD5
in those situations. Replacing MD5 and SHA1 with SipHash for these uses is
obvious and straight-forward, and so is submitted along with this patch
series. There shouldn't be much of a debate over its efficacy.
Dozens of languages are already using this internally for their hash
tables and PRFs. Some of the BSDs already use this in their kernels.
SipHash is a widely known high-speed solution to a widely known set of
problems, and it's time we catch-up.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Eric Biggers <ebiggers3@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
---
Documentation/siphash.txt | 79 ++++++++++++++++
MAINTAINERS | 7 ++
include/linux/siphash.h | 79 ++++++++++++++++
lib/Kconfig.debug | 6 +-
lib/Makefile | 5 +-
lib/siphash.c | 232 ++++++++++++++++++++++++++++++++++++++++++++++
lib/test_siphash.c | 119 ++++++++++++++++++++++++
7 files changed, 522 insertions(+), 5 deletions(-)
create mode 100644 Documentation/siphash.txt
create mode 100644 include/linux/siphash.h
create mode 100644 lib/siphash.c
create mode 100644 lib/test_siphash.c
diff --git a/Documentation/siphash.txt b/Documentation/siphash.txt
new file mode 100644
index 000000000000..39ff7f0438e7
--- /dev/null
+++ b/Documentation/siphash.txt
@@ -0,0 +1,79 @@
+ SipHash - a short input PRF
+-----------------------------------------------
+Written by Jason A. Donenfeld <jason@zx2c4.com>
+
+SipHash is a cryptographically secure PRF -- a keyed hash function -- that
+performs very well for short inputs, hence the name. It was designed by
+cryptographers Daniel J. Bernstein and Jean-Philippe Aumasson. It is intended
+as a replacement for some uses of: `jhash`, `md5_transform`, `sha_transform`,
+and so forth.
+
+SipHash takes a secret key filled with randomly generated numbers and either
+an input buffer or several input integers. It spits out an integer that is
+indistinguishable from random. You may then use that integer as part of secure
+sequence numbers, secure cookies, or mask it off for use in a hash table.
+
+1. Generating a key
+
+Keys should always be generated from a cryptographically secure source of
+random numbers, either using get_random_bytes or get_random_once:
+
+siphash_key_t key;
+get_random_bytes(key, sizeof(key));
+
+If you're not deriving your key from here, you're doing it wrong.
+
+2. Using the functions
+
+There are two variants of the function, one that takes a list of integers, and
+one that takes a buffer:
+
+u64 siphash(const void *data, size_t len, siphash_key_t key);
+
+And:
+
+u64 siphash_1u64(u64, siphash_key_t key);
+u64 siphash_2u64(u64, u64, siphash_key_t key);
+u64 siphash_3u64(u64, u64, u64, siphash_key_t key);
+u64 siphash_4u64(u64, u64, u64, u64, siphash_key_t key);
+u64 siphash_1u32(u32, siphash_key_t key);
+u64 siphash_2u32(u32, u32, siphash_key_t key);
+u64 siphash_3u32(u32, u32, u32, siphash_key_t key);
+u64 siphash_4u32(u32, u32, u32, u32, siphash_key_t key);
+
+If you pass the generic siphash function something of a constant length, it
+will constant fold at compile-time and automatically choose one of the
+optimized functions.
+
+3. Hashtable key function usage:
+
+struct some_hashtable {
+ DECLARE_HASHTABLE(hashtable, 8);
+ siphash_key_t key;
+};
+
+void init_hashtable(struct some_hashtable *table)
+{
+ get_random_bytes(table->key, sizeof(table->key));
+}
+
+static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input)
+{
+ return &table->hashtable[siphash(input, sizeof(*input), table->key) & (HASH_SIZE(table->hashtable) - 1)];
+}
+
+You may then iterate like usual over the returned hash bucket.
+
+4. Security
+
+SipHash has a very high security margin, with its 128-bit key. So long as the
+key is kept secret, it is impossible for an attacker to guess the outputs of
+the function, even if being able to observe many outputs, since 2^128 outputs
+is significant.
+
+Linux implements the "2-4" variant of SipHash.
+
+5. Resources
+
+Read the SipHash paper if you're interested in learning more:
+https://131002.net/siphash/siphash.pdf
diff --git a/MAINTAINERS b/MAINTAINERS
index 59c9895d73d5..5d87a8c1056a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11231,6 +11231,13 @@ F: arch/arm/mach-s3c24xx/mach-bast.c
F: arch/arm/mach-s3c24xx/bast-ide.c
F: arch/arm/mach-s3c24xx/bast-irq.c
+SIPHASH PRF ROUTINES
+M: Jason A. Donenfeld <Jason@zx2c4.com>
+S: Maintained
+F: lib/siphash.c
+F: lib/test_siphash.c
+F: include/linux/siphash.h
+
TI DAVINCI MACHINE SUPPORT
M: Sekhar Nori <nsekhar@ti.com>
M: Kevin Hilman <khilman@kernel.org>
diff --git a/include/linux/siphash.h b/include/linux/siphash.h
new file mode 100644
index 000000000000..7aa666eb00d9
--- /dev/null
+++ b/include/linux/siphash.h
@@ -0,0 +1,79 @@
+/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.
+ *
+ * SipHash: a fast short-input PRF
+ * https://131002.net/siphash/
+ *
+ * This implementation is specifically for SipHash2-4.
+ */
+
+#ifndef _LINUX_SIPHASH_H
+#define _LINUX_SIPHASH_H
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+
+#define SIPHASH_ALIGNMENT __alignof__(u64)
+typedef u64 siphash_key_t[2];
+
+u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t key);
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t key);
+#endif
+
+u64 siphash_1u64(const u64 a, const siphash_key_t key);
+u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t key);
+u64 siphash_3u64(const u64 a, const u64 b, const u64 c,
+ const siphash_key_t key);
+u64 siphash_4u64(const u64 a, const u64 b, const u64 c, const u64 d,
+ const siphash_key_t key);
+u64 siphash_1u32(const u32 a, const siphash_key_t key);
+u64 siphash_3u32(const u32 a, const u32 b, const u32 c, const siphash_key_t key);
+
+static inline u64 siphash_2u32(const u32 a, const u32 b, const siphash_key_t key)
+{
+ return siphash_1u64((u64)b << 32 | a, key);
+}
+static inline u64 siphash_4u32(const u32 a, const u32 b, const u32 c, const u32 d,
+ const siphash_key_t key)
+{
+ return siphash_2u64((u64)b << 32 | a, (u64)d << 32 | c, key);
+}
+
+
+static inline u64 ___siphash_aligned(const __le64 *data, size_t len, const siphash_key_t key)
+{
+ if (__builtin_constant_p(len) && len == 4)
+ return siphash_1u32(le32_to_cpu(data[0]), key);
+ if (__builtin_constant_p(len) && len == 8)
+ return siphash_1u64(le64_to_cpu(data[0]), key);
+ if (__builtin_constant_p(len) && len == 16)
+ return siphash_2u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]),
+ key);
+ if (__builtin_constant_p(len) && len == 24)
+ return siphash_3u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]),
+ le64_to_cpu(data[2]), key);
+ if (__builtin_constant_p(len) && len == 32)
+ return siphash_4u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]),
+ le64_to_cpu(data[2]), le64_to_cpu(data[3]),
+ key);
+ return __siphash_aligned(data, len, key);
+}
+
+/**
+ * siphash - compute 64-bit siphash PRF value
+ * @data: buffer to hash
+ * @size: size of @data
+ * @key: the siphash key
+ */
+static inline u64 siphash(const void *data, size_t len, const siphash_key_t key)
+{
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
+ return __siphash_unaligned(data, len, key);
+#endif
+ return ___siphash_aligned(data, len, key);
+}
+
+#endif /* _LINUX_SIPHASH_H */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7446097f72bd..86254ea99b45 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1843,9 +1843,9 @@ config TEST_HASH
tristate "Perform selftest on hash functions"
default n
help
- Enable this option to test the kernel's integer (<linux/hash,h>)
- and string (<linux/stringhash.h>) hash functions on boot
- (or module load).
+ Enable this option to test the kernel's integer (<linux/hash.h>),
+ string (<linux/stringhash.h>), and siphash (<linux/siphash.h>)
+ hash functions on boot (or module load).
This is intended to help people writing architecture-specific
optimized versions. If unsure, say N.
diff --git a/lib/Makefile b/lib/Makefile
index 50144a3aeebd..71d398b04a74 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -22,7 +22,8 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
sha1.o chacha20.o md5.o irq_regs.o argv_split.o \
flex_proportions.o ratelimit.o show_mem.o \
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
- earlycpio.o seq_buf.o nmi_backtrace.o nodemask.o win_minmax.o
+ earlycpio.o seq_buf.o siphash.o \
+ nmi_backtrace.o nodemask.o win_minmax.o
lib-$(CONFIG_MMU) += ioremap.o
lib-$(CONFIG_SMP) += cpumask.o
@@ -44,7 +45,7 @@ obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o
obj-y += kstrtox.o
obj-$(CONFIG_TEST_BPF) += test_bpf.o
obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
-obj-$(CONFIG_TEST_HASH) += test_hash.o
+obj-$(CONFIG_TEST_HASH) += test_hash.o test_siphash.o
obj-$(CONFIG_TEST_KASAN) += test_kasan.o
obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
obj-$(CONFIG_TEST_LKM) += test_module.o
diff --git a/lib/siphash.c b/lib/siphash.c
new file mode 100644
index 000000000000..ff2151313667
--- /dev/null
+++ b/lib/siphash.c
@@ -0,0 +1,232 @@
+/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.
+ *
+ * SipHash: a fast short-input PRF
+ * https://131002.net/siphash/
+ *
+ * This implementation is specifically for SipHash2-4.
+ */
+
+#include <linux/siphash.h>
+#include <asm/unaligned.h>
+
+#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
+#include <linux/dcache.h>
+#include <asm/word-at-a-time.h>
+#endif
+
+#define SIPROUND \
+ do { \
+ v0 += v1; v1 = rol64(v1, 13); v1 ^= v0; v0 = rol64(v0, 32); \
+ v2 += v3; v3 = rol64(v3, 16); v3 ^= v2; \
+ v0 += v3; v3 = rol64(v3, 21); v3 ^= v0; \
+ v2 += v1; v1 = rol64(v1, 17); v1 ^= v2; v2 = rol64(v2, 32); \
+ } while(0)
+
+#define PREAMBLE(len) \
+ u64 v0 = 0x736f6d6570736575ULL; \
+ u64 v1 = 0x646f72616e646f6dULL; \
+ u64 v2 = 0x6c7967656e657261ULL; \
+ u64 v3 = 0x7465646279746573ULL; \
+ u64 b = ((u64)len) << 56; \
+ v3 ^= key[1]; \
+ v2 ^= key[0]; \
+ v1 ^= key[1]; \
+ v0 ^= key[0];
+
+#define POSTAMBLE \
+ v3 ^= b; \
+ SIPROUND; \
+ SIPROUND; \
+ v0 ^= b; \
+ v2 ^= 0xff; \
+ SIPROUND; \
+ SIPROUND; \
+ SIPROUND; \
+ SIPROUND; \
+ return (v0 ^ v1) ^ (v2 ^ v3);
+
+u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t key)
+{
+ const u8 *end = data + len - (len % sizeof(u64));
+ const u8 left = len & (sizeof(u64) - 1);
+ u64 m;
+ PREAMBLE(len)
+ for (; data != end; data += sizeof(u64)) {
+ m = le64_to_cpup(data);
+ v3 ^= m;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= m;
+ }
+#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
+ if (left)
+ b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
+ bytemask_from_count(left)));
+#else
+ switch (left) {
+ case 7: b |= ((u64)end[6]) << 48;
+ case 6: b |= ((u64)end[5]) << 40;
+ case 5: b |= ((u64)end[4]) << 32;
+ case 4: b |= le32_to_cpup(data); break;
+ case 3: b |= ((u64)end[2]) << 16;
+ case 2: b |= le16_to_cpup(data); break;
+ case 1: b |= end[0];
+ }
+#endif
+ POSTAMBLE
+}
+EXPORT_SYMBOL(__siphash_aligned);
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t key)
+{
+ const u8 *end = data + len - (len % sizeof(u64));
+ const u8 left = len & (sizeof(u64) - 1);
+ u64 m;
+ PREAMBLE(len)
+ for (; data != end; data += sizeof(u64)) {
+ m = get_unaligned_le64(data);
+ v3 ^= m;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= m;
+ }
+#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
+ if (left)
+ b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
+ bytemask_from_count(left)));
+#else
+ switch (left) {
+ case 7: b |= ((u64)end[6]) << 48;
+ case 6: b |= ((u64)end[5]) << 40;
+ case 5: b |= ((u64)end[4]) << 32;
+ case 4: b |= get_unaligned_le32(end); break;
+ case 3: b |= ((u64)end[2]) << 16;
+ case 2: b |= get_unaligned_le16(end); break;
+ case 1: b |= end[0];
+ }
+#endif
+ POSTAMBLE
+}
+EXPORT_SYMBOL(__siphash_unaligned);
+#endif
+
+/**
+ * siphash_1u64 - compute 64-bit siphash PRF value of a u64
+ * @first: first u64
+ * @key: the siphash key
+ */
+u64 siphash_1u64(const u64 first, const siphash_key_t key)
+{
+ PREAMBLE(8)
+ v3 ^= first;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= first;
+ POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_1u64);
+
+/**
+ * siphash_2u64 - compute 64-bit siphash PRF value of 2 u64
+ * @first: first u64
+ * @second: second u64
+ * @key: the siphash key
+ */
+u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t key)
+{
+ PREAMBLE(16)
+ v3 ^= first;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= first;
+ v3 ^= second;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= second;
+ POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_2u64);
+
+/**
+ * siphash_3u64 - compute 64-bit siphash PRF value of 3 u64
+ * @first: first u64
+ * @second: second u64
+ * @third: third u64
+ * @key: the siphash key
+ */
+u64 siphash_3u64(const u64 first, const u64 second, const u64 third,
+ const siphash_key_t key)
+{
+ PREAMBLE(24)
+ v3 ^= first;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= first;
+ v3 ^= second;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= second;
+ v3 ^= third;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= third;
+ POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_3u64);
+
+/**
+ * siphash_4u64 - compute 64-bit siphash PRF value of 4 u64
+ * @first: first u64
+ * @second: second u64
+ * @third: third u64
+ * @forth: forth u64
+ * @key: the siphash key
+ */
+u64 siphash_4u64(const u64 first, const u64 second, const u64 third,
+ const u64 forth, const siphash_key_t key)
+{
+ PREAMBLE(32)
+ v3 ^= first;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= first;
+ v3 ^= second;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= second;
+ v3 ^= third;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= third;
+ v3 ^= forth;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= forth;
+ POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_4u64);
+
+u64 siphash_1u32(const u32 first, const siphash_key_t key)
+{
+ PREAMBLE(4)
+ b |= first;
+ POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_1u32);
+
+u64 siphash_3u32(const u32 first, const u32 second, const u32 third,
+ const siphash_key_t key)
+{
+ u64 combined = (u64)second << 32 | first;
+ PREAMBLE(12)
+ v3 ^= combined;
+ SIPROUND;
+ SIPROUND;
+ v0 ^= combined;
+ b |= third;
+ POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_3u32);
diff --git a/lib/test_siphash.c b/lib/test_siphash.c
new file mode 100644
index 000000000000..e0ba2cf8dc67
--- /dev/null
+++ b/lib/test_siphash.c
@@ -0,0 +1,119 @@
+/* Test cases for siphash.c
+ *
+ * Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.
+ *
+ * SipHash: a fast short-input PRF
+ * https://131002.net/siphash/
+ *
+ * This implementation is specifically for SipHash2-4.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/siphash.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+
+/* Test vectors taken from official reference source available at:
+ * https://131002.net/siphash/siphash24.c
+ */
+static const u64 test_vectors[64] = {
+ 0x726fdb47dd0e0e31ULL, 0x74f839c593dc67fdULL, 0x0d6c8009d9a94f5aULL,
+ 0x85676696d7fb7e2dULL, 0xcf2794e0277187b7ULL, 0x18765564cd99a68dULL,
+ 0xcbc9466e58fee3ceULL, 0xab0200f58b01d137ULL, 0x93f5f5799a932462ULL,
+ 0x9e0082df0ba9e4b0ULL, 0x7a5dbbc594ddb9f3ULL, 0xf4b32f46226bada7ULL,
+ 0x751e8fbc860ee5fbULL, 0x14ea5627c0843d90ULL, 0xf723ca908e7af2eeULL,
+ 0xa129ca6149be45e5ULL, 0x3f2acc7f57c29bdbULL, 0x699ae9f52cbe4794ULL,
+ 0x4bc1b3f0968dd39cULL, 0xbb6dc91da77961bdULL, 0xbed65cf21aa2ee98ULL,
+ 0xd0f2cbb02e3b67c7ULL, 0x93536795e3a33e88ULL, 0xa80c038ccd5ccec8ULL,
+ 0xb8ad50c6f649af94ULL, 0xbce192de8a85b8eaULL, 0x17d835b85bbb15f3ULL,
+ 0x2f2e6163076bcfadULL, 0xde4daaaca71dc9a5ULL, 0xa6a2506687956571ULL,
+ 0xad87a3535c49ef28ULL, 0x32d892fad841c342ULL, 0x7127512f72f27cceULL,
+ 0xa7f32346f95978e3ULL, 0x12e0b01abb051238ULL, 0x15e034d40fa197aeULL,
+ 0x314dffbe0815a3b4ULL, 0x027990f029623981ULL, 0xcadcd4e59ef40c4dULL,
+ 0x9abfd8766a33735cULL, 0x0e3ea96b5304a7d0ULL, 0xad0c42d6fc585992ULL,
+ 0x187306c89bc215a9ULL, 0xd4a60abcf3792b95ULL, 0xf935451de4f21df2ULL,
+ 0xa9538f0419755787ULL, 0xdb9acddff56ca510ULL, 0xd06c98cd5c0975ebULL,
+ 0xe612a3cb9ecba951ULL, 0xc766e62cfcadaf96ULL, 0xee64435a9752fe72ULL,
+ 0xa192d576b245165aULL, 0x0a8787bf8ecb74b2ULL, 0x81b3e73d20b49b6fULL,
+ 0x7fa8220ba3b2eceaULL, 0x245731c13ca42499ULL, 0xb78dbfaf3a8d83bdULL,
+ 0xea1ad565322a1a0bULL, 0x60e61c23a3795013ULL, 0x6606d7e446282b93ULL,
+ 0x6ca4ecb15c5f91e1ULL, 0x9f626da15c9625f3ULL, 0xe51b38608ef25f57ULL,
+ 0x958a324ceb064572ULL
+};
+static const siphash_key_t test_key =
+ { 0x0706050403020100ULL , 0x0f0e0d0c0b0a0908ULL };
+
+static int __init siphash_test_init(void)
+{
+ u8 in[64] __aligned(SIPHASH_ALIGNMENT);
+ u8 in_unaligned[65];
+ u8 i;
+ int ret = 0;
+
+ for (i = 0; i < 64; ++i) {
+ in[i] = i;
+ in_unaligned[i + 1] = i;
+ if (siphash(in, i, test_key) != test_vectors[i]) {
+ pr_info("self-test aligned %u: FAIL\n", i + 1);
+ ret = -EINVAL;
+ }
+ if (siphash(in_unaligned + 1, i, test_key) != test_vectors[i]) {
+ pr_info("self-test unaligned %u: FAIL\n", i + 1);
+ ret = -EINVAL;
+ }
+ }
+ if (siphash_1u64(0x0706050403020100ULL, test_key) != test_vectors[8]) {
+ pr_info("self-test 1u64: FAIL\n");
+ ret = -EINVAL;
+ }
+ if (siphash_2u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL, test_key) != test_vectors[16]) {
+ pr_info("self-test 2u64: FAIL\n");
+ ret = -EINVAL;
+ }
+ if (siphash_3u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL,
+ 0x1716151413121110ULL, test_key) != test_vectors[24]) {
+ pr_info("self-test 3u64: FAIL\n");
+ ret = -EINVAL;
+ }
+ if (siphash_4u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL,
+ 0x1716151413121110ULL, 0x1f1e1d1c1b1a1918ULL, test_key) != test_vectors[32]) {
+ pr_info("self-test 4u64: FAIL\n");
+ ret = -EINVAL;
+ }
+ if (siphash_1u32(0x03020100U, test_key) != test_vectors[4]) {
+ pr_info("self-test 1u32: FAIL\n");
+ ret = -EINVAL;
+ }
+ if (siphash_2u32(0x03020100U, 0x07060504U, test_key) != test_vectors[8]) {
+ pr_info("self-test 2u32: FAIL\n");
+ ret = -EINVAL;
+ }
+ if (siphash_3u32(0x03020100U, 0x07060504U,
+ 0x0b0a0908U, test_key) != test_vectors[12]) {
+ pr_info("self-test 3u32: FAIL\n");
+ ret = -EINVAL;
+ }
+ if (siphash_4u32(0x03020100U, 0x07060504U,
+ 0x0b0a0908U, 0x0f0e0d0cU, test_key) != test_vectors[16]) {
+ pr_info("self-test 4u32: FAIL\n");
+ ret = -EINVAL;
+ }
+ if (!ret)
+ pr_info("self-tests: pass\n");
+ return ret;
+}
+
+static void __exit siphash_test_exit(void)
+{
+}
+
+module_init(siphash_test_init);
+module_exit(siphash_test_exit);
+
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
+MODULE_LICENSE("Dual BSD/GPL");
--
2.11.0
^ permalink raw reply related
* [PATCH v7 0/6] The SipHash Patchset
From: Jason A. Donenfeld @ 2016-12-21 23:02 UTC (permalink / raw)
To: Netdev, kernel-hardening, LKML, linux-crypto, David Laight,
Ted Tso, Hannes Frederic Sowa, edumazet, Linus Torvalds,
Eric Biggers, Tom Herbert, ak, davem, luto,
Jean-Philippe Aumasson
Cc: Jason A. Donenfeld
In-Reply-To: <20161216030328.11602-1-Jason@zx2c4.com>
Hey folks,
Again we've made huge progress, with this latest version now shipping
Jean-Phillipe Aumasson's HalfSipHash, which should be much more competitive
with jhash (in addition to being more secure, of course).
There are dozens of little cleanups and improvements right and left throughout
this series, so I urge you to take a look at the whole thing. I've tried to
take into consideration lots of concerns and suggestions from many of you
over the last week.
There is also now documentation! And the test suite now has full coverage of
all functions.
Finally, there's been some significant benchmarking, and now a few commit
messages have some performance numbers.
Please send your Reviewed-by lines as you see fit.
Regards,
Jason
Jason A. Donenfeld (6):
siphash: add cryptographically secure PRF
secure_seq: use SipHash in place of MD5
random: use SipHash in place of MD5
md5: remove from lib and only live in crypto
syncookies: use SipHash in place of SHA1
siphash: implement HalfSipHash1-3 for hash tables
Documentation/siphash.txt | 154 +++++++++++++
MAINTAINERS | 7 +
crypto/md5.c | 95 +++++++-
drivers/char/random.c | 84 ++++---
include/linux/random.h | 1 -
include/linux/siphash.h | 133 +++++++++++
init/main.c | 1 -
lib/Kconfig.debug | 6 +-
lib/Makefile | 7 +-
lib/md5.c | 95 --------
lib/siphash.c | 548 ++++++++++++++++++++++++++++++++++++++++++++++
lib/test_siphash.c | 208 ++++++++++++++++++
net/core/secure_seq.c | 135 +++++-------
net/ipv4/syncookies.c | 20 +-
net/ipv6/syncookies.c | 37 ++--
15 files changed, 1274 insertions(+), 257 deletions(-)
create mode 100644 Documentation/siphash.txt
create mode 100644 include/linux/siphash.h
delete mode 100644 lib/md5.c
create mode 100644 lib/siphash.c
create mode 100644 lib/test_siphash.c
--
2.11.0
^ permalink raw reply
* Re: [PATCH 2/2] net: wireless: fix to uses struct
From: Ozgur Karatas @ 2016-12-21 23:01 UTC (permalink / raw)
To: Paul Bolle, johannes, David Miller
Cc: Thomas Gleixner, linux-wireless, netdev, linux-kernel
In-Reply-To: <601101482360611@web25o.yandex.ru>
My previous patch is invalid, I'm sorry.
The last patc will be fellow because "regulatory_request" is defined as a "static struct".
Signed-off-by: Ozgur Karatas <okaratas@member.fsf.org>
---
net/wireless/reg.c | 10 +++++-----
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 5dbac37..5b70970 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -490,7 +490,7 @@ static int reg_query_builtin(const char *alpha2)
if (!regdom)
return -ENODATA;
- request = kzalloc(sizeof(struct reg_regdb_apply_request), GFP_KERNEL);
+ request = kzalloc(sizeof(*reg_regdb_apply_request), GFP_KERNEL);
if (!request)
return -ENOMEM;
@@ -2661,7 +2661,7 @@ int regulatory_hint_found_beacon(struct wiphy *wiphy,
if (processing)
return 0;
- reg_beacon = kzalloc(sizeof(struct reg_beacon), gfp);
+ reg_beacon = kzalloc(sizeof(*reg_beacon), gfp);
if (!reg_beacon)
return -ENOMEM;
--
2.1.4
^ permalink raw reply related
* Re: [PATCH 2/2] net: wireless: fix to uses struct
From: Ozgur Karatas @ 2016-12-21 22:50 UTC (permalink / raw)
To: Paul Bolle, johannes, David Miller
Cc: Thomas Gleixner, linux-wireless, netdev, linux-kernel
In-Reply-To: <1482359625.28171.2.camel@tiscali.nl>
22.12.2016, 00:34, "Paul Bolle" <pebolle@tiscali.nl>:
> On Thu, 2016-12-22 at 00:23 +0200, Ozgur Karatas wrote:
>> I compiled and didn't to errors.
>
> Really?
I'm very sorry. The "regulatory_request" is defined a static struct. I missed.
line: static struct regulatory_request core_request_world = {
I send to wrong line please can ignore last message and should be fix to as follows:
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 5dbac37..5b70970 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -490,7 +490,7 @@ static int reg_query_builtin(const char *alpha2)
if (!regdom)
return -ENODATA;
- request = kzalloc(sizeof(struct reg_regdb_apply_request), GFP_KERNEL);
+ request = kzalloc(sizeof(*reg_regdb_apply_request), GFP_KERNEL);
if (!request)
return -ENOMEM;
@@ -2291,7 +2291,7 @@ static int regulatory_hint_core(const char *alpha2)
{
struct regulatory_request *request;
- request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
+ request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
if (!request)
return -ENOMEM;
@@ -2313,7 +2313,7 @@ int regulatory_hint_user(const char *alpha2,
if (WARN_ON(!alpha2))
return -EINVAL;
- request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
+ request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
if (!request)
return -ENOMEM;
@@ -2385,7 +2385,7 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2)
wiphy->regulatory_flags &= ~REGULATORY_CUSTOM_REG;
- request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
+ request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
if (!request)
return -ENOMEM;
@@ -2661,7 +2661,7 @@ int regulatory_hint_found_beacon(struct wiphy *wiphy,
if (processing)
return 0;
- reg_beacon = kzalloc(sizeof(struct reg_beacon), gfp);
+ reg_beacon = kzalloc(sizeof(*reg_beacon), gfp);
if (!reg_beacon)
return -ENOMEM;
--
2.1.4
> $ make net/wireless/reg.o
> CHK include/config/kernel.release
> CHK include/generated/uapi/linux/version.h
> CHK include/generated/utsrelease.h
> CHK include/generated/bounds.h
> CHK include/generated/timeconst.h
> CHK include/generated/asm-offsets.h
> CALL scripts/checksyscalls.sh
> CC net/wireless/reg.o
> net/wireless/reg.c: In function ‘regulatory_hint_core’:
> net/wireless/reg.c:2294:28: error: ‘regulatory_request’ undeclared (first use in this function)
> request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
> ^~~~~~~~~~~~~~~~~~
> net/wireless/reg.c:2294:28: note: each undeclared identifier is reported only once for each function it appears in
> net/wireless/reg.c: In function ‘regulatory_hint_user’:
> net/wireless/reg.c:2316:28: error: ‘regulatory_request’ undeclared (first use in this function)
> request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
> ^~~~~~~~~~~~~~~~~~
> net/wireless/reg.c: In function ‘regulatory_hint’:
> net/wireless/reg.c:2388:28: error: ‘regulatory_request’ undeclared (first use in this function)
> request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
> ^~~~~~~~~~~~~~~~~~
> scripts/Makefile.build:293: recipe for target 'net/wireless/reg.o' failed
> make[1]: *** [net/wireless/reg.o] Error 1
> Makefile:1640: recipe for target 'net/wireless/reg.o' failed
> make: *** [net/wireless/reg.o] Error 2
$ make M=net/wireless/
CC net/wireless//core.o
CC net/wireless//sysfs.o
CC net/wireless//radiotap.o
CC net/wireless//util.o
CC net/wireless//reg.o
CC net/wireless//scan.o
CC net/wireless//nl80211.o
CC net/wireless//mlme.o
CC net/wireless//ibss.o
CC net/wireless//sme.o
CC net/wireless//chan.o
CC net/wireless//ethtool.o
CC net/wireless//mesh.o
CC net/wireless//ap.o
CC net/wireless//trace.o
CC net/wireless//ocb.o
LD net/wireless//cfg80211.o
LD net/wireless//built-in.o
Building modules, stage 2.
MODPOST 0 modules
$ make net/wireless/reg.o
scripts/kconfig/conf --silentoldconfig Kconfig
*
* Restart config...
*
*
* Memory power savings
*
> Didn't Thomas Gleixner suggest that you do a basic C course just yesterday?
I don't have a problem with C programming, So only I'm learning the kernel.
Also, this is a lie if say "I'm expert to C".
I think be re-learned every day. wrong?
> Paul Bolle
Regards,
~ Ozgur
^ permalink raw reply related
* Re: [PATCH 2/2] net: wireless: fix to uses struct
From: Paul Bolle @ 2016-12-21 22:33 UTC (permalink / raw)
To: Ozgur Karatas, johannes, David Miller
Cc: Thomas Gleixner, linux-wireless, netdev, linux-kernel
In-Reply-To: <608881482358981@web17g.yandex.ru>
On Thu, 2016-12-22 at 00:23 +0200, Ozgur Karatas wrote:
> I compiled and didn't to errors.
Really?
$ make net/wireless/reg.o
CHK include/config/kernel.release
CHK include/generated/uapi/linux/version.h
CHK include/generated/utsrelease.h
CHK include/generated/bounds.h
CHK include/generated/timeconst.h
CHK include/generated/asm-offsets.h
CALL scripts/checksyscalls.sh
CC net/wireless/reg.o
net/wireless/reg.c: In function ‘regulatory_hint_core’:
net/wireless/reg.c:2294:28: error: ‘regulatory_request’ undeclared (first use in this function)
request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
^~~~~~~~~~~~~~~~~~
net/wireless/reg.c:2294:28: note: each undeclared identifier is reported only once for each function it appears in
net/wireless/reg.c: In function ‘regulatory_hint_user’:
net/wireless/reg.c:2316:28: error: ‘regulatory_request’ undeclared (first use in this function)
request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
^~~~~~~~~~~~~~~~~~
net/wireless/reg.c: In function ‘regulatory_hint’:
net/wireless/reg.c:2388:28: error: ‘regulatory_request’ undeclared (first use in this function)
request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
^~~~~~~~~~~~~~~~~~
scripts/Makefile.build:293: recipe for target 'net/wireless/reg.o' failed
make[1]: *** [net/wireless/reg.o] Error 1
Makefile:1640: recipe for target 'net/wireless/reg.o' failed
make: *** [net/wireless/reg.o] Error 2
Didn't Thomas Gleixner suggest that you do a basic C course just yesterday?
Paul Bolle
^ permalink raw reply
* Re: [kernel-hardening] Re: HalfSipHash Acceptable Usage
From: Jason A. Donenfeld @ 2016-12-21 22:29 UTC (permalink / raw)
To: kernel-hardening, Theodore Ts'o, George Spelvin, Eric Dumazet,
Jason, Andi Kleen, David Miller, David Laight,
Daniel J . Bernstein, Eric Biggers, Hannes Frederic Sowa,
Jean-Philippe Aumasson, Linux Crypto Mailing List, LKML,
Andy Lutomirski, Netdev, Tom Herbert, Linus Torvalds,
Vegard Nossum
On Wed, Dec 21, 2016 at 11:27 PM, Theodore Ts'o <tytso@mit.edu> wrote:
> And "with enough registers" includes ARM and MIPS, right? So the only
> real problem is 32-bit x86, and you're right, at that point, only
> people who might care are people who are using a space-radiation
> hardened 386 --- and they're not likely to be doing high throughput
> TCP connections. :-)
Plus the benchmark was bogus anyway, and when I built a more specific
harness -- actually comparing the TCP sequence number functions --
SipHash was faster than MD5, even on register starved x86. So I think
we're fine and this chapter of the discussion can come to a close, in
order to move on to more interesting things.
^ permalink raw reply
* Re: HalfSipHash Acceptable Usage
From: Theodore Ts'o @ 2016-12-21 22:27 UTC (permalink / raw)
To: George Spelvin
Cc: eric.dumazet, Jason, ak, davem, David.Laight, djb, ebiggers3,
hannes, jeanphilippe.aumasson, kernel-hardening, linux-crypto,
linux-kernel, luto, netdev, tom, torvalds, vegard.nossum
In-Reply-To: <20161221183751.1123.qmail@ns.sciencehorizons.net>
On Wed, Dec 21, 2016 at 01:37:51PM -0500, George Spelvin wrote:
> SipHash annihilates the competition on 64-bit superscalar hardware.
> SipHash dominates the field on 64-bit in-order hardware.
> SipHash wins easily on 32-bit hardware *with enough registers*.
> On register-starved 32-bit machines, it really struggles.
And "with enough registers" includes ARM and MIPS, right? So the only
real problem is 32-bit x86, and you're right, at that point, only
people who might care are people who are using a space-radiation
hardened 386 --- and they're not likely to be doing high throughput
TCP connections. :-)
- Ted
^ permalink raw reply
* [PATCH 2/2] net: wireless: fix to uses struct
From: Ozgur Karatas @ 2016-12-21 22:23 UTC (permalink / raw)
To: johannes, David Miller; +Cc: linux-wireless, netdev, linux-kernel
The patch fixed to struct uses in reg.c, I think doesn't need to be use to "struct".
There is dataype not have to logical link and each is different definitons.
I'm undecided on this patch. I compiled and didn't to errors.
Signed-off-by: Ozgur Karatas <okaratas@member.fsf.org>
---
net/wireless/reg.c | 10 +++++-----
1 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 5dbac37..5b70970 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -490,7 +490,7 @@ static int reg_query_builtin(const char *alpha2)
if (!regdom)
return -ENODATA;
- request = kzalloc(sizeof(struct reg_regdb_apply_request), GFP_KERNEL);
+ request = kzalloc(sizeof(*reg_regdb_apply_request), GFP_KERNEL);
if (!request)
return -ENOMEM;
@@ -2291,7 +2291,7 @@ static int regulatory_hint_core(const char *alpha2)
{
struct regulatory_request *request;
- request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
+ request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
if (!request)
return -ENOMEM;
@@ -2313,7 +2313,7 @@ int regulatory_hint_user(const char *alpha2,
if (WARN_ON(!alpha2))
return -EINVAL;
- request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
+ request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
if (!request)
return -ENOMEM;
@@ -2385,7 +2385,7 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2)
wiphy->regulatory_flags &= ~REGULATORY_CUSTOM_REG;
- request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
+ request = kzalloc(sizeof(*regulatory_request), GFP_KERNEL);
if (!request)
return -ENOMEM;
@@ -2661,7 +2661,7 @@ int regulatory_hint_found_beacon(struct wiphy *wiphy,
if (processing)
return 0;
- reg_beacon = kzalloc(sizeof(struct reg_beacon), gfp);
+ reg_beacon = kzalloc(sizeof(*reg_beacon), gfp);
if (!reg_beacon)
return -ENOMEM;
--
2.1.4
^ permalink raw reply related
* Re: [PATCH net] ipvlan: fix various issues in ipvlan_process_multicast()
From: Mahesh Bandewar (महेश बंडेवार) @ 2016-12-21 22:21 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David Miller, netdev
In-Reply-To: <1482355800.8944.75.camel@edumazet-glaptop3.roam.corp.google.com>
On Wed, Dec 21, 2016 at 1:30 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> From: Eric Dumazet <edumazet@google.com>
>
> 1) netif_rx() / dev_forward_skb() should not be called from process
> context.
>
> 2) ipvlan_count_rx() should be called with preemption disabled.
>
> 3) We should check if ipvlan->dev is up before feeding packets
> to netif_rx()
>
> 4) We need to prevent device from disappearing if some packets
> are in the multicast backlog.
>
> 5) One kfree_skb() should be a consume_skb() eventually
>
Thank you Eric for all these fixes.
> Fixes: ba35f8588f47 ("ipvlan: Defer multicast / broadcast processing to a work-queue")
> Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
> Cc: Mahesh Bandewar <maheshb@google.com>
> ---
> drivers/net/ipvlan/ipvlan_core.c | 38 +++++++++++++++++++----------
> 1 file changed, 25 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
> index b4e990743e1da0cb3a946f5473d02cce7447bd1a..ea6bc1e12cdf6827a69d8d54d96b4b59106ede96 100644
> --- a/drivers/net/ipvlan/ipvlan_core.c
> +++ b/drivers/net/ipvlan/ipvlan_core.c
> @@ -207,6 +207,9 @@ void ipvlan_process_multicast(struct work_struct *work)
> spin_unlock_bh(&port->backlog.lock);
>
> while ((skb = __skb_dequeue(&list)) != NULL) {
> + struct net_device *dev = skb->dev;
> + bool consumed = false;
> +
> ethh = eth_hdr(skb);
> hlocal = ether_addr_equal(ethh->h_source, port->dev->dev_addr);
> mac_hash = ipvlan_mac_hash(ethh->h_dest);
> @@ -219,27 +222,29 @@ void ipvlan_process_multicast(struct work_struct *work)
> dlocal = false;
> rcu_read_lock();
> list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
> - if (hlocal && (ipvlan->dev == skb->dev)) {
> + if (hlocal && (ipvlan->dev == dev)) {
> dlocal = true;
> continue;
> }
> if (!test_bit(mac_hash, ipvlan->mac_filters))
> continue;
> -
> + if (!(ipvlan->dev->flags & IFF_UP))
> + continue;
> ret = NET_RX_DROP;
> len = skb->len + ETH_HLEN;
> nskb = skb_clone(skb, GFP_ATOMIC);
> - if (!nskb)
> - goto acct;
> -
> - nskb->pkt_type = pkt_type;
> - nskb->dev = ipvlan->dev;
> - if (hlocal)
> - ret = dev_forward_skb(ipvlan->dev, nskb);
> - else
> - ret = netif_rx(nskb);
> -acct:
> + local_bh_disable();
> + if (nskb) {
> + consumed = true;
> + nskb->pkt_type = pkt_type;
> + nskb->dev = ipvlan->dev;
> + if (hlocal)
> + ret = dev_forward_skb(ipvlan->dev, nskb);
> + else
> + ret = netif_rx(nskb);
> + }
> ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
> + local_bh_enable();
> }
> rcu_read_unlock();
>
> @@ -249,8 +254,13 @@ void ipvlan_process_multicast(struct work_struct *work)
> skb->pkt_type = pkt_type;
> dev_queue_xmit(skb);
> } else {
> - kfree_skb(skb);
> + if (consumed)
> + consume_skb(skb);
> + else
> + kfree_skb(skb);
> }
> + if (dev)
> + dev_put(dev);
> }
> }
>
> @@ -479,6 +489,8 @@ static void ipvlan_multicast_enqueue(struct ipvl_port *port,
>
> spin_lock(&port->backlog.lock);
> if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) {
> + if (skb->dev)
> + dev_hold(skb->dev);
> __skb_queue_tail(&port->backlog, skb);
> spin_unlock(&port->backlog.lock);
> schedule_work(&port->wq);
>
>
^ permalink raw reply
* [PATCH 1/2] net: wireless: fixed to checkpatch errors
From: Ozgur Karatas @ 2016-12-21 22:13 UTC (permalink / raw)
To: johannes, David Miller; +Cc: linux-wireless, netdev, linux-kernel
Fixed to checkpatch errors, Normally, comment's */ had to be finish on the next line.
The patch fix to readability and Coding Style.
Sİgned-off-by: Ozgur Karatas <okaratas@member.fsf.org>
---
net/wireless/chan.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 5497d022..8c7ac7f 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -891,7 +891,8 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
: CHAN_MODE_EXCLUSIVE;
/* consider worst-case - IBSS can try to return to the
- * original user-specified channel as creator */
+ * original user-specified channel as creator
+ */
if (wdev->ibss_dfs_possible)
*radar_detect |= BIT(wdev->chandef.width);
return;
--
2.1.4
^ permalink raw reply related
* Re: ipv6: handle -EFAULT from skb_copy_bits
From: Hannes Frederic Sowa @ 2016-12-21 21:33 UTC (permalink / raw)
To: David Miller; +Cc: xiyou.wangcong, davej, netdev
In-Reply-To: <20161221.140431.1651188849352763159.davem@davemloft.net>
On Wed, 2016-12-21 at 14:04 -0500, David Miller wrote:
> From: Hannes Frederic Sowa <hannes@stressinduktion.org>
> Date: Wed, 21 Dec 2016 13:41:13 +0100
>
> > On Wed, 2016-12-21 at 13:27 +0100, Hannes Frederic Sowa wrote:
> >> @@ -555,8 +566,8 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
> >> goto out;
> >>
> >> offset = rp->offset;
> >> - total_len = inet_sk(sk)->cork.base.length;
> >> - if (offset >= total_len - 1) {
> >> + transport_len = raw6_corked_transport_len(sk);
> >> + if (offset >= transport_len - 1) {
> >> err = -EINVAL;
> >> ip6_flush_pending_frames(sk);
> >> goto out;
> >> @@ -598,7 +609,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
> >> tmp_csum = csum_sub(tmp_csum, csum_unfold(csum));
> >>
> >> csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr,
> >> - total_len, fl6->flowi6_proto, tmp_csum);
> >> + transport_len, fl6->flowi6_proto, tmp_csum);
> >>
> >>
> >
> > Ops, here we need actually the total_len plus the opt->opt_nflen to
> > always calculate the correct checksum.
>
> It's a real shame we can't just use skb_transport_offset(). This value
> has essentially been calculated for us already.
This code path is called when we want to send out the socket write
queue. Because of MSG_MORE we might have multiple skbs in there, but
only the first one actually carries the true header, the others are
optimized for the ipv6 fragmentation fast path, thus we need to use
skb_transport_offset to find the correct offset but we must not
touch/read the data area before, as it is undefined data at that point.
Basically total_len so far accumulated all the payload length written
to the socket from the syscall argument from the user, but
unfortunately it also accounts for the first sendmsg's synthesized
extension header length in the write queue. We need to reverse this
calculation at this point in time.
So total_len is independent from the loop we do below and the length
should always reflect the length of all skbs stored in the write queue.
The loop adjusts the offset of the checksum in case the checksum offset
points to data in one of the later skbs, but we know before if that can
happen or not because of the cork length.
> Also, if we iterate over multiple SKBs in the write queue, don't you have
> to redo this calculation for every SKB we iterate over?
All the skb's payload length are summed up in the cork's length field,
so we don't need to sum it up again but just can use that value as is
minus the extension header adjustment.
> Furthermore, what if the user queued up some SKBs in the raw socket
> with MSG_MORE, and then changed some of the options for a subsequent
> sendmsg() call?
We only refresh the extension headers the next time we prepare an ipv6
header, which is the first sendmsg after one without MSG_MORE. We are
protected in this situation and don't change header lengths later
during further MSG_MORE sendmsgs.
> Given all of this, I think the best thing to do is validate the offset
> after the queue walks, which is pretty much what Dave Jones's original
> patch was doing.
I think both approaches protect against the bug reasonably well, but
Dave's patch has a bug: we must either call ip6_flush_pending_frames to
clear the socket write queue with the buggy send request.
> Sigh... well, at least we now understand what's going on here.
Yep, the code is more than a bit complex. :/
Bye,
Hannes
^ permalink raw reply
* [PATCH net] ipvlan: fix various issues in ipvlan_process_multicast()
From: Eric Dumazet @ 2016-12-21 21:30 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Mahesh Bandewar
From: Eric Dumazet <edumazet@google.com>
1) netif_rx() / dev_forward_skb() should not be called from process
context.
2) ipvlan_count_rx() should be called with preemption disabled.
3) We should check if ipvlan->dev is up before feeding packets
to netif_rx()
4) We need to prevent device from disappearing if some packets
are in the multicast backlog.
5) One kfree_skb() should be a consume_skb() eventually
Fixes: ba35f8588f47 ("ipvlan: Defer multicast / broadcast processing to a work-queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
---
drivers/net/ipvlan/ipvlan_core.c | 38 +++++++++++++++++++----------
1 file changed, 25 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index b4e990743e1da0cb3a946f5473d02cce7447bd1a..ea6bc1e12cdf6827a69d8d54d96b4b59106ede96 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -207,6 +207,9 @@ void ipvlan_process_multicast(struct work_struct *work)
spin_unlock_bh(&port->backlog.lock);
while ((skb = __skb_dequeue(&list)) != NULL) {
+ struct net_device *dev = skb->dev;
+ bool consumed = false;
+
ethh = eth_hdr(skb);
hlocal = ether_addr_equal(ethh->h_source, port->dev->dev_addr);
mac_hash = ipvlan_mac_hash(ethh->h_dest);
@@ -219,27 +222,29 @@ void ipvlan_process_multicast(struct work_struct *work)
dlocal = false;
rcu_read_lock();
list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
- if (hlocal && (ipvlan->dev == skb->dev)) {
+ if (hlocal && (ipvlan->dev == dev)) {
dlocal = true;
continue;
}
if (!test_bit(mac_hash, ipvlan->mac_filters))
continue;
-
+ if (!(ipvlan->dev->flags & IFF_UP))
+ continue;
ret = NET_RX_DROP;
len = skb->len + ETH_HLEN;
nskb = skb_clone(skb, GFP_ATOMIC);
- if (!nskb)
- goto acct;
-
- nskb->pkt_type = pkt_type;
- nskb->dev = ipvlan->dev;
- if (hlocal)
- ret = dev_forward_skb(ipvlan->dev, nskb);
- else
- ret = netif_rx(nskb);
-acct:
+ local_bh_disable();
+ if (nskb) {
+ consumed = true;
+ nskb->pkt_type = pkt_type;
+ nskb->dev = ipvlan->dev;
+ if (hlocal)
+ ret = dev_forward_skb(ipvlan->dev, nskb);
+ else
+ ret = netif_rx(nskb);
+ }
ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
+ local_bh_enable();
}
rcu_read_unlock();
@@ -249,8 +254,13 @@ void ipvlan_process_multicast(struct work_struct *work)
skb->pkt_type = pkt_type;
dev_queue_xmit(skb);
} else {
- kfree_skb(skb);
+ if (consumed)
+ consume_skb(skb);
+ else
+ kfree_skb(skb);
}
+ if (dev)
+ dev_put(dev);
}
}
@@ -479,6 +489,8 @@ static void ipvlan_multicast_enqueue(struct ipvl_port *port,
spin_lock(&port->backlog.lock);
if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) {
+ if (skb->dev)
+ dev_hold(skb->dev);
__skb_queue_tail(&port->backlog, skb);
spin_unlock(&port->backlog.lock);
schedule_work(&port->wq);
^ permalink raw reply related
* Re: [PATCH net] net, sched: fix soft lockup in tc_classify
From: Daniel Borkmann @ 2016-12-21 21:07 UTC (permalink / raw)
To: Cong Wang
Cc: David Miller, Shahar Klein, Or Gerlitz, Roi Dayan, Jiri Pirko,
John Fastabend, Linux Kernel Network Developers
In-Reply-To: <CAM_iQpUEUmJpjQYV7HV+4NVtGe6D-yZs6=YizcDtf7dogkNR0Q@mail.gmail.com>
On 12/21/2016 09:47 PM, Cong Wang wrote:
> On Wed, Dec 21, 2016 at 12:02 PM, Daniel Borkmann <daniel@iogearbox.net> wrote:
>> On 12/21/2016 08:10 PM, Cong Wang wrote:
>>> On Wed, Dec 21, 2016 at 10:51 AM, Cong Wang <xiyou.wangcong@gmail.com>
>>> wrote:
>>>> On Wed, Dec 21, 2016 at 9:04 AM, Daniel Borkmann <daniel@iogearbox.net>
>>>> wrote:
>>>>>
>>>>> What happens is that in tc_ctl_tfilter(), thread A allocates a new
>>>>> tp, initializes it, sets tp_created to 1, and calls into
>>>>> tp->ops->change()
>>>>> with it. In that classifier callback we had to unlock/lock the rtnl
>>>>> mutex and returned with -EAGAIN. One reason why we need to drop there
>>>>> is, for example, that we need to request an action module to be loaded.
>>>>
>>>> Excellent catch!
>>>>
>>>> But why do we have to replay the request here? Shouldn't we just return
>>>> EAGAIN to user-space and let user-space decide to retry or not?
>>>> Replaying is the root of the evil here.
>>>
>>> Answer myself: probably due to historical reasons, but still replaying
>>> inside such a big function is just error-prone, we should promote it
>>> out:
>>
>> Have no strong opinion, I guess it could be done as a simplification
>> for net-next, why not, along with moving out the netlink_ns_capable()
>> check or possibly other things after careful analysis that don't need
>> to be redone in that circumstance.
>
> It is only slightly bigger than your current one so could fit for -stable too.
> Also, it could fix all potential problems like this one. Let compiler do the
> work, not human. ;)
Ok, you mean for net. In that case I prefer the smaller sized fix to be
honest. It also covers everything from the point where we fetch the chain
via cops->tcf_chain() to the end of the function, which is where most of
the complexity resides, and only the two mentioned commits do the relock,
so as a fix I think it's fine as-is. As mentioned, if there's need to
refactor tc_ctl_tfilter() net-next would be better, imho.
Thanks,
Daniel
^ permalink raw reply
* Re: [PATCH] at86rf230: Allow slow GPIO pins for "rstn"
From: Stefan Schmidt @ 2016-12-21 21:01 UTC (permalink / raw)
To: Chris Healy
Cc: Alexander Aring, Andrey Smirnov, linux-kernel, netdev, linux-wpan
In-Reply-To: <CAFXsbZpgiTM2qngYERVpfXHvePW8M8DN91YnZwc-voKO=FDUUA@mail.gmail.com>
Hello.
On 21/12/16 19:30, Chris Healy wrote:
>
>
> On Dec 21, 2016 5:11 AM, "Stefan Schmidt" <stefan@osg.samsung.com
> <mailto:stefan@osg.samsung.com>> wrote:
>
> Hello.
>
>
> On 19/12/16 00:25, Andrey Smirnov wrote:
>
> Driver code never touches "rstn" signal in atomic context, so
> there's
> no need to implicitly put such restriction on it by using
> gpio_set_value
> to manipulate it. Replace gpio_set_value to
> gpio_set_value_cansleep to
> fix that.
>
>
> We need to make sure we are not assuming it can be called in such a
> context in the future now. But that is something we can worry about
> if it comes up.
>
>
> As a an example of where such restriction might be inconvenient,
> consider a hardware design where "rstn" is connected to a pin of
> I2C/SPI
> GPIO expander chip.
>
>
> Is this a real life issue you run into?
>
>
> I have a platform with this configuration. The DTS for the platform is
> in the process of being mainlined right now.
Thanks for letting us know. What platform is that? I'm always interested
in hearing about devices that use the Linux ieee802154 subsystem. :)
regards
Stefan Schmidt
^ permalink raw reply
* Re: [PATCH net] net, sched: fix soft lockup in tc_classify
From: Cong Wang @ 2016-12-21 20:47 UTC (permalink / raw)
To: Daniel Borkmann
Cc: David Miller, Shahar Klein, Or Gerlitz, Roi Dayan, Jiri Pirko,
John Fastabend, Linux Kernel Network Developers
In-Reply-To: <585ADFEB.3030206@iogearbox.net>
On Wed, Dec 21, 2016 at 12:02 PM, Daniel Borkmann <daniel@iogearbox.net> wrote:
> On 12/21/2016 08:10 PM, Cong Wang wrote:
>>
>> On Wed, Dec 21, 2016 at 10:51 AM, Cong Wang <xiyou.wangcong@gmail.com>
>> wrote:
>>>
>>> On Wed, Dec 21, 2016 at 9:04 AM, Daniel Borkmann <daniel@iogearbox.net>
>>> wrote:
>>>>
>>>> What happens is that in tc_ctl_tfilter(), thread A allocates a new
>>>> tp, initializes it, sets tp_created to 1, and calls into
>>>> tp->ops->change()
>>>> with it. In that classifier callback we had to unlock/lock the rtnl
>>>> mutex and returned with -EAGAIN. One reason why we need to drop there
>>>> is, for example, that we need to request an action module to be loaded.
>>>
>>>
>>> Excellent catch!
>>>
>>> But why do we have to replay the request here? Shouldn't we just return
>>> EAGAIN to user-space and let user-space decide to retry or not?
>>> Replaying is the root of the evil here.
>>
>>
>> Answer myself: probably due to historical reasons, but still replaying
>> inside such a big function is just error-prone, we should promote it
>> out:
>
>
> Have no strong opinion, I guess it could be done as a simplification
> for net-next, why not, along with moving out the netlink_ns_capable()
> check or possibly other things after careful analysis that don't need
> to be redone in that circumstance.
It is only slightly bigger than your current one so could fit for -stable too.
Also, it could fix all potential problems like this one. Let compiler do the
work, not human. ;)
^ permalink raw reply
* Re: [PATCH] net: fddi: skfp: use %p format specifier for addresses rather than %x
From: David Miller @ 2016-12-21 20:35 UTC (permalink / raw)
To: colin.king; +Cc: netdev, linux-kernel
In-Reply-To: <20161221160323.27780-1-colin.king@canonical.com>
From: Colin King <colin.king@canonical.com>
Date: Wed, 21 Dec 2016 16:03:23 +0000
> From: Colin Ian King <colin.king@canonical.com>
>
> Trivial fix: Addresses should be printed using the %p format specifier
> rather than using %x.
>
> Signed-off-by: Colin Ian King <colin.king@canonical.com>
Applied.
^ permalink raw reply
* [PATCH v4 3/3] Bluetooth: btusb: Configure Marvell to use one of the pins for oob wakeup
From: Rajat Jain @ 2016-12-21 20:33 UTC (permalink / raw)
To: Rob Herring, Mark Rutland, Marcel Holtmann, Gustavo Padovan,
Johan Hedberg, Amitkumar Karwar, Wei-Ning Huang, Xinming Hu,
netdev, devicetree, linux-bluetooth, Brian Norris, linux-kernel
Cc: Rajat Jain, rajatxjain
In-Reply-To: <1482352432-38302-1-git-send-email-rajatja@google.com>
The Marvell devices may have many gpio pins, and hence for wakeup
on these out-of-band pins, the chip needs to be told which pin is
to be used for wakeup, using an hci command.
Thus, we read the pin number etc from the device tree node and send
a command to the chip.
Signed-off-by: Rajat Jain <rajatja@google.com>
Reviewed-by: Brian Norris <briannorris@chromium.org>
Acked-by: Rob Herring <robh@kernel.org>
---
v4: same as v3
v3: * remove the Marvell specific id table and check
* Add reference to marvell-bt-8xxx.txt in btusb.txt
* Add "Reviewed-by" and "Acked-by"
v2: Fix the binding document to specify to use "wakeup" interrupt-name
Documentation/devicetree/bindings/net/btusb.txt | 3 ++
.../{marvell-bt-sd8xxx.txt => marvell-bt-8xxx.txt} | 46 +++++++++++++++----
drivers/bluetooth/btusb.c | 51 ++++++++++++++++++++++
3 files changed, 92 insertions(+), 8 deletions(-)
rename Documentation/devicetree/bindings/net/{marvell-bt-sd8xxx.txt => marvell-bt-8xxx.txt} (50%)
diff --git a/Documentation/devicetree/bindings/net/btusb.txt b/Documentation/devicetree/bindings/net/btusb.txt
index 2c0355c..01fa2d4 100644
--- a/Documentation/devicetree/bindings/net/btusb.txt
+++ b/Documentation/devicetree/bindings/net/btusb.txt
@@ -10,6 +10,9 @@ Required properties:
"usb1286,204e" (Marvell 8997)
+Also, vendors that use btusb may have device additional properties, e.g:
+Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
+
Optional properties:
- interrupt-parent: phandle of the parent interrupt controller
diff --git a/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt b/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
similarity index 50%
rename from Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt
rename to Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
index 6a9a63c..9be1059 100644
--- a/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt
+++ b/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
@@ -1,16 +1,21 @@
-Marvell 8897/8997 (sd8897/sd8997) bluetooth SDIO devices
+Marvell 8897/8997 (sd8897/sd8997) bluetooth devices (SDIO or USB based)
------
+The 8997 devices supports multiple interfaces. When used on SDIO interfaces,
+the btmrvl driver is used and when used on USB interface, the btusb driver is
+used.
Required properties:
- compatible : should be one of the following:
- * "marvell,sd8897-bt"
- * "marvell,sd8997-bt"
+ * "marvell,sd8897-bt" (for SDIO)
+ * "marvell,sd8997-bt" (for SDIO)
+ * "usb1286,204e" (for USB)
Optional properties:
- marvell,cal-data: Calibration data downloaded to the device during
initialization. This is an array of 28 values(u8).
+ This is only applicable to SDIO devices.
- marvell,wakeup-pin: It represents wakeup pin number of the bluetooth chip.
firmware will use the pin to wakeup host system (u16).
@@ -18,10 +23,15 @@ Optional properties:
platform. The value will be configured to firmware. This
is needed to work chip's sleep feature as expected (u16).
- interrupt-parent: phandle of the parent interrupt controller
- - interrupts : interrupt pin number to the cpu. Driver will request an irq based
- on this interrupt number. During system suspend, the irq will be
- enabled so that the bluetooth chip can wakeup host platform under
- certain condition. During system resume, the irq will be disabled
+ - interrupt-names: Used only for USB based devices (See below)
+ - interrupts : specifies the interrupt pin number to the cpu. For SDIO, the
+ driver will use the first interrupt specified in the interrupt
+ array. For USB based devices, the driver will use the interrupt
+ named "wakeup" from the interrupt-names and interrupt arrays.
+ The driver will request an irq based on this interrupt number.
+ During system suspend, the irq will be enabled so that the
+ bluetooth chip can wakeup host platform under certain
+ conditions. During system resume, the irq will be disabled
to make sure unnecessary interrupt is not received.
Example:
@@ -29,7 +39,9 @@ Example:
IRQ pin 119 is used as system wakeup source interrupt.
wakeup pin 13 and gap 100ms are configured so that firmware can wakeup host
using this device side pin and wakeup latency.
-calibration data is also available in below example.
+
+Example for SDIO device follows (calibration data is also available in
+below example).
&mmc3 {
status = "okay";
@@ -54,3 +66,21 @@ calibration data is also available in below example.
marvell,wakeup-gap-ms = /bits/ 16 <0x64>;
};
};
+
+Example for USB device:
+
+&usb_host1_ohci {
+ status = "okay";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ mvl_bt1: bt@1 {
+ compatible = "usb1286,204e";
+ reg = <1>;
+ interrupt-parent = <&gpio0>;
+ interrupt-names = "wakeup";
+ interrupts = <119 IRQ_TYPE_LEVEL_LOW>;
+ marvell,wakeup-pin = /bits/ 16 <0x0d>;
+ marvell,wakeup-gap-ms = /bits/ 16 <0x64>;
+ };
+};
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 2b45f1c..91dcd8a 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2343,6 +2343,50 @@ static int btusb_shutdown_intel(struct hci_dev *hdev)
return 0;
}
+#ifdef CONFIG_PM
+/* Configure an out-of-band gpio as wake-up pin, if specified in device tree */
+static int marvell_config_oob_wake(struct hci_dev *hdev)
+{
+ struct sk_buff *skb;
+ struct btusb_data *data = hci_get_drvdata(hdev);
+ struct device *dev = &data->udev->dev;
+ u16 pin, gap, opcode;
+ int ret;
+ u8 cmd[5];
+
+ /* Move on if no wakeup pin specified */
+ if (of_property_read_u16(dev->of_node, "marvell,wakeup-pin", &pin) ||
+ of_property_read_u16(dev->of_node, "marvell,wakeup-gap-ms", &gap))
+ return 0;
+
+ /* Vendor specific command to configure a GPIO as wake-up pin */
+ opcode = hci_opcode_pack(0x3F, 0x59);
+ cmd[0] = opcode & 0xFF;
+ cmd[1] = opcode >> 8;
+ cmd[2] = 2; /* length of parameters that follow */
+ cmd[3] = pin;
+ cmd[4] = gap; /* time in ms, for which wakeup pin should be asserted */
+
+ skb = bt_skb_alloc(sizeof(cmd), GFP_KERNEL);
+ if (!skb) {
+ bt_dev_err(hdev, "%s: No memory\n", __func__);
+ return -ENOMEM;
+ }
+
+ memcpy(skb_put(skb, sizeof(cmd)), cmd, sizeof(cmd));
+ hci_skb_pkt_type(skb) = HCI_COMMAND_PKT;
+
+ ret = btusb_send_frame(hdev, skb);
+ if (ret) {
+ bt_dev_err(hdev, "%s: configuration failed\n", __func__);
+ kfree_skb(skb);
+ return ret;
+ }
+
+ return 0;
+}
+#endif
+
static int btusb_set_bdaddr_marvell(struct hci_dev *hdev,
const bdaddr_t *bdaddr)
{
@@ -2917,6 +2961,13 @@ static int btusb_probe(struct usb_interface *intf,
err = btusb_config_oob_wake(hdev);
if (err)
goto out_free_dev;
+
+ /* Marvell devices may need a specific chip configuration */
+ if (id->driver_info & BTUSB_MARVELL && data->oob_wake_irq) {
+ err = marvell_config_oob_wake(hdev);
+ if (err)
+ goto out_free_dev;
+ }
#endif
if (id->driver_info & BTUSB_CW6622)
set_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks);
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* [PATCH v4 2/3] Bluetooth: btusb: Add out-of-band wakeup support
From: Rajat Jain @ 2016-12-21 20:33 UTC (permalink / raw)
To: Rob Herring, Mark Rutland, Marcel Holtmann, Gustavo Padovan,
Johan Hedberg, Amitkumar Karwar, Wei-Ning Huang, Xinming Hu,
netdev-u79uwXL29TY76Z2rM5mHXA, devicetree-u79uwXL29TY76Z2rM5mHXA,
linux-bluetooth-u79uwXL29TY76Z2rM5mHXA, Brian Norris,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
Cc: Rajat Jain, rajatxjain-Re5JQEeQqe8AvxtiuMwx3w
In-Reply-To: <1482352432-38302-1-git-send-email-rajatja-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Some onboard BT chips (e.g. Marvell 8997) contain a wakeup pin that
can be connected to a gpio on the CPU side, and can be used to wakeup
the host out-of-band. This can be useful in situations where the
in-band wakeup is not possible or not preferable (e.g. the in-band
wakeup may require the USB host controller to remain active, and
hence consuming more system power during system sleep).
The oob gpio interrupt to be used for wakeup on the CPU side, is
read from the device tree node, (using standard interrupt descriptors).
A devcie tree binding document is also added for the driver. The
compatible string is in compliance with
Documentation/devicetree/bindings/usb/usb-device.txt
Signed-off-by: Rajat Jain <rajatja-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Reviewed-by: Brian Norris <briannorris-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
---
v4: Move the set_bit(BTUSB_OOB_WAKE_DISABLED,..) call to the beginning of
btusb_config_oob_wake() - caught by Brian.
v3: Add Brian's "Reviewed-by"
v2: * Use interrupt-names ("wakeup") instead of assuming first interrupt.
* Leave it on device tree to specify IRQ flags (level /edge triggered)
* Mark the device as non wakeable on exit.
Documentation/devicetree/bindings/net/btusb.txt | 40 ++++++++++++
drivers/bluetooth/btusb.c | 84 +++++++++++++++++++++++++
2 files changed, 124 insertions(+)
create mode 100644 Documentation/devicetree/bindings/net/btusb.txt
diff --git a/Documentation/devicetree/bindings/net/btusb.txt b/Documentation/devicetree/bindings/net/btusb.txt
new file mode 100644
index 0000000..2c0355c
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/btusb.txt
@@ -0,0 +1,40 @@
+Generic Bluetooth controller over USB (btusb driver)
+---------------------------------------------------
+
+Required properties:
+
+ - compatible : should comply with the format "usbVID,PID" specified in
+ Documentation/devicetree/bindings/usb/usb-device.txt
+ At the time of writing, the only OF supported devices
+ (more may be added later) are:
+
+ "usb1286,204e" (Marvell 8997)
+
+Optional properties:
+
+ - interrupt-parent: phandle of the parent interrupt controller
+ - interrupt-names: (see below)
+ - interrupts : The interrupt specified by the name "wakeup" is the interrupt
+ that shall be used for out-of-band wake-on-bt. Driver will
+ request this interrupt for wakeup. During system suspend, the
+ irq will be enabled so that the bluetooth chip can wakeup host
+ platform out of band. During system resume, the irq will be
+ disabled to make sure unnecessary interrupt is not received.
+
+Example:
+
+Following example uses irq pin number 3 of gpio0 for out of band wake-on-bt:
+
+&usb_host1_ehci {
+ status = "okay";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ mvl_bt1: bt@1 {
+ compatible = "usb1286,204e";
+ reg = <1>;
+ interrupt-parent = <&gpio0>;
+ interrupt-name = "wakeup";
+ interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
+ };
+};
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index ce22cef..2b45f1c 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -24,6 +24,8 @@
#include <linux/module.h>
#include <linux/usb.h>
#include <linux/firmware.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
#include <asm/unaligned.h>
#include <net/bluetooth/bluetooth.h>
@@ -369,6 +371,7 @@ static const struct usb_device_id blacklist_table[] = {
#define BTUSB_BOOTING 9
#define BTUSB_RESET_RESUME 10
#define BTUSB_DIAG_RUNNING 11
+#define BTUSB_OOB_WAKE_DISABLED 12
struct btusb_data {
struct hci_dev *hdev;
@@ -416,6 +419,8 @@ struct btusb_data {
int (*recv_bulk)(struct btusb_data *data, void *buffer, int count);
int (*setup_on_usb)(struct hci_dev *hdev);
+
+ int oob_wake_irq; /* irq for out-of-band wake-on-bt */
};
static inline void btusb_free_frags(struct btusb_data *data)
@@ -2728,6 +2733,65 @@ static int btusb_bcm_set_diag(struct hci_dev *hdev, bool enable)
}
#endif
+#ifdef CONFIG_PM
+static irqreturn_t btusb_oob_wake_handler(int irq, void *priv)
+{
+ struct btusb_data *data = priv;
+
+ /* Disable only if not already disabled (keep it balanced) */
+ if (!test_and_set_bit(BTUSB_OOB_WAKE_DISABLED, &data->flags)) {
+ disable_irq_nosync(irq);
+ disable_irq_wake(irq);
+ }
+ pm_wakeup_event(&data->udev->dev, 0);
+ return IRQ_HANDLED;
+}
+
+static const struct of_device_id btusb_match_table[] = {
+ { .compatible = "usb1286,204e" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, btusb_match_table);
+
+/* Use an oob wakeup pin? */
+static int btusb_config_oob_wake(struct hci_dev *hdev)
+{
+ struct btusb_data *data = hci_get_drvdata(hdev);
+ struct device *dev = &data->udev->dev;
+ int irq, ret;
+
+ set_bit(BTUSB_OOB_WAKE_DISABLED, &data->flags);
+
+ if (!of_match_device(btusb_match_table, dev))
+ return 0;
+
+ /* Move on if no IRQ specified */
+ irq = of_irq_get_byname(dev->of_node, "wakeup");
+ if (irq <= 0) {
+ bt_dev_dbg(hdev, "%s: no OOB Wakeup IRQ in DT", __func__);
+ return 0;
+ }
+
+ ret = devm_request_irq(&hdev->dev, irq, btusb_oob_wake_handler,
+ 0, "OOB Wake-on-BT", data);
+ if (ret) {
+ bt_dev_err(hdev, "%s: IRQ request failed", __func__);
+ return ret;
+ }
+
+ ret = device_init_wakeup(dev, true);
+ if (ret) {
+ bt_dev_err(hdev, "%s: failed to init_wakeup\n", __func__);
+ return ret;
+ }
+
+ data->oob_wake_irq = irq;
+ disable_irq(irq);
+ bt_dev_info(hdev, "OOB Wake-on-BT configured at IRQ %u\n", irq);
+ return 0;
+}
+#endif
+
static int btusb_probe(struct usb_interface *intf,
const struct usb_device_id *id)
{
@@ -2849,6 +2913,11 @@ static int btusb_probe(struct usb_interface *intf,
hdev->send = btusb_send_frame;
hdev->notify = btusb_notify;
+#ifdef CONFIG_PM
+ err = btusb_config_oob_wake(hdev);
+ if (err)
+ goto out_free_dev;
+#endif
if (id->driver_info & BTUSB_CW6622)
set_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks);
@@ -3061,6 +3130,9 @@ static void btusb_disconnect(struct usb_interface *intf)
usb_driver_release_interface(&btusb_driver, data->isoc);
}
+ if (data->oob_wake_irq)
+ device_init_wakeup(&data->udev->dev, false);
+
hci_free_dev(hdev);
}
@@ -3089,6 +3161,12 @@ static int btusb_suspend(struct usb_interface *intf, pm_message_t message)
btusb_stop_traffic(data);
usb_kill_anchored_urbs(&data->tx_anchor);
+ if (data->oob_wake_irq && device_may_wakeup(&data->udev->dev)) {
+ clear_bit(BTUSB_OOB_WAKE_DISABLED, &data->flags);
+ enable_irq_wake(data->oob_wake_irq);
+ enable_irq(data->oob_wake_irq);
+ }
+
/* Optionally request a device reset on resume, but only when
* wakeups are disabled. If wakeups are enabled we assume the
* device will stay powered up throughout suspend.
@@ -3126,6 +3204,12 @@ static int btusb_resume(struct usb_interface *intf)
if (--data->suspend_count)
return 0;
+ /* Disable only if not already disabled (keep it balanced) */
+ if (!test_and_set_bit(BTUSB_OOB_WAKE_DISABLED, &data->flags)) {
+ disable_irq(data->oob_wake_irq);
+ disable_irq_wake(data->oob_wake_irq);
+ }
+
if (!test_bit(HCI_RUNNING, &hdev->flags))
goto done;
--
2.8.0.rc3.226.g39d4020
--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH v4 1/3] Bluetooth: btusb: Use an error label for error paths
From: Rajat Jain @ 2016-12-21 20:33 UTC (permalink / raw)
To: Rob Herring, Mark Rutland, Marcel Holtmann, Gustavo Padovan,
Johan Hedberg, Amitkumar Karwar, Wei-Ning Huang, Xinming Hu,
netdev-u79uwXL29TY76Z2rM5mHXA, devicetree-u79uwXL29TY76Z2rM5mHXA,
linux-bluetooth-u79uwXL29TY76Z2rM5mHXA, Brian Norris,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
Cc: Rajat Jain, rajatxjain-Re5JQEeQqe8AvxtiuMwx3w
Use a label to remove the repetetive cleanup, for error cases.
Signed-off-by: Rajat Jain <rajatja-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Reviewed-by: Brian Norris <briannorris-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
---
v4: same as v3
v3: Added Brian's "Reviewed-by"
v2: same as v1
drivers/bluetooth/btusb.c | 19 +++++++++----------
1 file changed, 9 insertions(+), 10 deletions(-)
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 2f633df..ce22cef 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2991,18 +2991,15 @@ static int btusb_probe(struct usb_interface *intf,
err = usb_set_interface(data->udev, 0, 0);
if (err < 0) {
BT_ERR("failed to set interface 0, alt 0 %d", err);
- hci_free_dev(hdev);
- return err;
+ goto out_free_dev;
}
}
if (data->isoc) {
err = usb_driver_claim_interface(&btusb_driver,
data->isoc, data);
- if (err < 0) {
- hci_free_dev(hdev);
- return err;
- }
+ if (err < 0)
+ goto out_free_dev;
}
#ifdef CONFIG_BT_HCIBTUSB_BCM
@@ -3016,14 +3013,16 @@ static int btusb_probe(struct usb_interface *intf,
#endif
err = hci_register_dev(hdev);
- if (err < 0) {
- hci_free_dev(hdev);
- return err;
- }
+ if (err < 0)
+ goto out_free_dev;
usb_set_intfdata(intf, data);
return 0;
+
+out_free_dev:
+ hci_free_dev(hdev);
+ return err;
}
static void btusb_disconnect(struct usb_interface *intf)
--
2.8.0.rc3.226.g39d4020
--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* Re: [PATCH net] tcp: add a missing barrier in tcp_tasklet_func()
From: David Miller @ 2016-12-21 20:31 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev, edumazet, madalin.bucur
In-Reply-To: <1482327763.8944.26.camel@edumazet-glaptop3.roam.corp.google.com>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Wed, 21 Dec 2016 05:42:43 -0800
> From: Eric Dumazet <edumazet@google.com>
>
> Madalin reported crashes happening in tcp_tasklet_func() on powerpc64
>
> Before TSQ_QUEUED bit is cleared, we must ensure the changes done
> by list_del(&tp->tsq_node); are committed to memory, otherwise
> corruption might happen, as an other cpu could catch TSQ_QUEUED
> clearance too soon.
>
> We can notice that old kernels were immune to this bug, because
> TSQ_QUEUED was cleared after a bh_lock_sock(sk)/bh_unlock_sock(sk)
> section, but they could have missed a kick to write additional bytes,
> when NIC interrupts for a given flow are spread to multiple cpus.
>
> Affected TCP flows would need an incoming ACK or RTO timer to add more
> packets to the pipe. So overall situation should be better now.
>
> Fixes: b223feb9de2a ("tcp: tsq: add shortcut in tcp_tasklet_func()")
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Reported-by: Madalin Bucur <madalin.bucur@nxp.com>
> Tested-by: Madalin Bucur <madalin.bucur@nxp.com>
Applied, thanks Eric.
^ permalink raw reply
* BUG/panic in ctnetlink_conntrack_event in 4.8.11
From: Chris Boot @ 2016-12-21 20:20 UTC (permalink / raw)
To: Netfilter Development Mailing list
Cc: Linux Kernel Network Developers, coreteam, linux-kernel
Hi all,
I've encountered this BUG three times in the last few days, though I
must admit I've only captured the trace once so far so I can't be
completely certain it was exactly this the last few times. I did not
experience this with a 4.7 kernel; it only seemed to start with 4.8.
For some background: I use conntrackd (this is an "HA" firewall pair),
plenty of IPv6, IPsec with vti6 interfaces, conntrack, some NAT on IPv4
but definitely not with IPv6.
Without further ado, here is my crash:
[147965.209318] BUG: unable to handle kernel NULL pointer dereference at 0000000000000018
[147965.217347] IP: [<ffffffffb4bb8b19>] icmp6_send+0x229/0x9f0
[147965.223051] PGD 0
[147965.225184] Oops: 0000 [#1] SMP
[147965.228424] Modules linked in: sch_fq_codel sch_htb pppoe pppox ppp_generic slhc ip6_vti ip6_tunnel tunnel6 drbg ansi_cprng seqiv esp6 xfrm4_mode_tunnel xfrm6_mode_tunnel ghash_generic gcm twofish_generic twofish_x86_64_3way twofish_x86_64 twofish_common serpent_sse2_x86_64 serpent_generic blowfish_generic blowfish_x86_64 blowfish_common cast5_generic cast_common ctr des_generic cbc algif_skcipher camellia_generic camellia_x86_64 xts xcbc sha512_ssse3 sha512_generic md4 algif_hash af_alg xfrm_user xfrm4_tunnel tunnel4 ipcomp xfrm_ipcomp esp4 ah4 af_key xfrm_algo tun hmac xt_nat xt_policy xt_statistic xt_helper xt_CLASSIFY xt_recent ip6table_nat xt_dscp xt_length binfmt_misc ip6t_REJECT xt_hashlimit nf_reject_ipv6 ip6table_mangle xt_comment iptable_nat ipt_REJECT nf_reject_ipv4 xt_addrtype xt_set ip_set_hash_ip ip_set xt_connmark xt_mark iptable_mangle xt_tcpudp iptable_raw xt_CT ip6table_raw xt_multiport xt_conntrack nf_log_ipv4 nf_nat_tftp nf_nat_snmp_basic nf_conntrack_snmp xt_NFLOG nf_nat_sip xt_LOG nf_log_ipv6 nf_nat_pptp nf_log_common nf_nat_proto_gre nf_nat_irc nf_nat_h323 nf_nat_ftp nf_nat_amanda ts_kmp nf_conntrack_amanda nf_conntrack_sane nf_conntrack_tftp nf_conntrack_sip nf_conntrack_proto_udplite nf_conntrack_proto_sctp nf_conntrack_pptp nf_conntrack_proto_gre nf_conntrack_netlink nf_conntrack_netbios_ns nf_conntrack_broadcast nf_conntrack_irc nf_conntrack_h323 nf_conntrack_ftp ip6table_filter ip6_tables iptable_filter openvswitch nf_conntrack_ipv6 nf_nat_ipv6 nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_defrag_ipv6 nf_nat nf_conntrack 8021q garp mrp stp llc dummy nfnetlink_log nfnetlink evdev kvm_amd kvm irqbypass pcspkr k10temp sp5100_tco i2c_piix4 sg shpchp acpi_cpufreq tpm_tis tpm_tis_core tpm button drbd lru_cache libcrc32c ip_tables x_tables autofs4 ext4 crc16 jbd2 crc32c_generic fscrypto ecb glue_helper lrw gf128mul ablk_helper cryptd aes_x86_64 mbcache dm_mod sd_mod uas usb_storage ohci_pci ehci_pci ohci_hcd ehci_hcd usbcore ahci libahci libata scsi_mod usb_common r8169 mii
[147965.409769] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.8.0-2-amd64 #1 Debian 4.8.11-1
[147965.417773] Hardware name: PC Engines APU, BIOS SageBios_PCEngines_APU-45 04/05/2014
[147965.425607] task: ffff96d2d940aec0 task.stack: ffff96d2d9410000
[147965.431622] RIP: 0010:[<ffffffffb4bb8b19>] [<ffffffffb4bb8b19>] icmp6_send+0x229/0x9f0
[147965.439742] RSP: 0018:ffff96d2ded03d30 EFLAGS: 00010246
[147965.445150] RAX: 0000000000000000 RBX: ffff96d2861e1700 RCX: 0000000000000020
[147965.452377] RDX: 0000000000000001 RSI: 0000000000000200 RDI: ffff96d1cb42799e
[147965.459597] RBP: ffff96d2ded03e60 R08: 0000000000000000 R09: ffff96d299832000
[147965.466823] R10: 0000000000000001 R11: 0000000000000000 R12: ffff96d1cb427996
[147965.474042] R13: ffffffffb50da680 R14: 0000000000000000 R15: 0000000000000003
[147965.481263] FS: 0000000000000000(0000) GS:ffff96d2ded00000(0000) knlGS:0000000000000000
[147965.489444] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[147965.495283] CR2: 0000000000000018 CR3: 0000000116d59000 CR4: 00000000000006e0
[147965.502501] Stack:
[147965.504607] ffff96d291d14880 0000000000000000 ffff96d289288400 0000000000000000
[147965.512189] 0000000000000000 0000000000000000 ffff96d1cb42799e 0000000000000000
[147965.519772] 0000000000000001 ffff96d200000001 ffff96d1cb4279ae ffff96d280fb2900
[147965.527356] Call Trace:
[147965.529895] <IRQ>
[147965.531932] [<ffffffffc07330df>] ? ctnetlink_conntrack_event+0x3ff/0x620 [nf_conntrack_netlink]
[147965.541005] [<ffffffffc068e94a>] ? nf_nat_cleanup_conntrack+0xea/0x1a0 [nf_nat]
[147965.548492] [<ffffffffb4b74653>] ? get_frag_bucket_locked+0x43/0x70
[147965.554939] [<ffffffffc0696330>] ? nf_ct_net_init+0x130/0x130 [nf_defrag_ipv6]
[147965.562338] [<ffffffffb4bbff78>] ? ip6_expire_frag_queue+0xf8/0x100
[147965.568787] [<ffffffffb46e6e80>] ? call_timer_fn+0x30/0x120
[147965.574539] [<ffffffffb46e7406>] ? run_timer_softirq+0x216/0x4b0
[147965.580728] [<ffffffffb46f7ac0>] ? tick_sched_handle.isra.12+0x20/0x50
[147965.587434] [<ffffffffb46f7b28>] ? tick_sched_timer+0x38/0x70
[147965.593363] [<ffffffffb4bf2598>] ? __do_softirq+0xf8/0x290
[147965.599030] [<ffffffffb4681abb>] ? irq_exit+0x9b/0xa0
[147965.604266] [<ffffffffb4bf23ae>] ? smp_apic_timer_interrupt+0x3e/0x50
[147965.610884] [<ffffffffb4bf16c2>] ? apic_timer_interrupt+0x82/0x90
[147965.617155] <EOI>
[147965.619184] [<ffffffffb4ab0f06>] ? cpuidle_enter_state+0x126/0x2d0
[147965.625740] [<ffffffffb4ab0ef3>] ? cpuidle_enter_state+0x113/0x2d0
[147965.632100] [<ffffffffb46bd742>] ? cpu_startup_entry+0x2a2/0x350
[147965.638291] [<ffffffffb464eddd>] ? start_secondary+0x14d/0x190
[147965.644299] Code: 8b 44 24 38 75 46 f6 c2 02 74 05 f6 c2 30 75 3c 48 8b 43 58 4c 89 44 24 20 44 89 5c 24 38 44 89 54 24 40 89 54 24 48 48 83 e0 fe <48> 8b 78 18 e8 8e 88 02 00 8b 54 24 48 41 89 c1 44 8b 54 24 40
[147965.664907] RIP [<ffffffffb4bb8b19>] icmp6_send+0x229/0x9f0
[147965.670686] RSP <ffff96d2ded03d30>
[147965.674267] CR2: 0000000000000018
[147965.677683] ---[ end trace d5725bb00a2f3d6b ]---
[147965.682396] Kernel panic - not syncing: Fatal exception in interrupt
[147965.688898] Kernel Offset: 0x33600000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[147965.699764] ---[ end Kernel panic - not syncing: Fatal exception in interrupt
[147965.707009] ------------[ cut here ]------------
[147965.711730] WARNING: CPU: 1 PID: 0 at /build/linux-lIgGMF/linux-4.8.11/arch/x86/kernel/smp.c:125 check_preempt_curr+0x50/0x90
[147965.723108] Modules linked in: sch_fq_codel sch_htb pppoe pppox ppp_generic slhc ip6_vti ip6_tunnel tunnel6 drbg ansi_cprng seqiv esp6 xfrm4_mode_tunnel xfrm6_mode_tunnel ghash_generic gcm twofish_generic twofish_x86_64_3way twofish_x86_64 twofish_common serpent_sse2_x86_64 serpent_generic blowfish_generic blowfish_x86_64 blowfish_common cast5_generic cast_common ctr des_generic cbc algif_skcipher camellia_generic camellia_x86_64 xts xcbc sha512_ssse3 sha512_generic md4 algif_hash af_alg xfrm_user xfrm4_tunnel tunnel4 ipcomp xfrm_ipcomp esp4 ah4 af_key xfrm_algo tun hmac xt_nat xt_policy xt_statistic xt_helper xt_CLASSIFY xt_recent ip6table_nat xt_dscp xt_length binfmt_misc ip6t_REJECT xt_hashlimit nf_reject_ipv6 ip6table_mangle xt_comment iptable_nat ipt_REJECT nf_reject_ipv4 xt_addrtype xt_set ip_set_hash_ip ip_set xt_connmark xt_mark iptable_mangle xt_tcpudp iptable_raw xt_CT ip6table_raw xt_multiport xt_conntrack nf_log_ipv4 nf_nat_tftp nf_nat_snmp_basic nf_conntrack_snmp xt_NFLOG nf_nat_sip xt_LOG nf_log_ipv6 nf_nat_pptp nf_log_common nf_nat_proto_gre nf_nat_irc nf_nat_h323 nf_nat_ftp nf_nat_amanda ts_kmp nf_conntrack_amanda nf_conntrack_sane nf_conntrack_tftp nf_conntrack_sip nf_conntrack_proto_udplite nf_conntrack_proto_sctp nf_conntrack_pptp nf_conntrack_proto_gre nf_conntrack_netlink nf_conntrack_netbios_ns nf_conntrack_broadcast nf_conntrack_irc nf_conntrack_h323 nf_conntrack_ftp ip6table_filter ip6_tables iptable_filter openvswitch nf_conntrack_ipv6 nf_nat_ipv6 nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_defrag_ipv6 nf_nat nf_conntrack 8021q garp mrp stp llc dummy nfnetlink_log nfnetlink evdev kvm_amd kvm irqbypass pcspkr k10temp sp5100_tco i2c_piix4 sg shpchp acpi_cpufreq tpm_tis tpm_tis_core tpm button drbd lru_cache libcrc32c ip_tables x_tables autofs4 ext4 crc16 jbd2 crc32c_generic fscrypto ecb glue_helper lrw gf128mul ablk_helper cryptd aes_x86_64 mbcache dm_mod sd_mod uas usb_storage ohci_pci ehci_pci ohci_hcd ehci_hcd usbcore ahci libahci libata scsi_mod usb_common r8169 mii
[147965.904454] CPU: 1 PID: 0 Comm: swapper/1 Tainted: G D 4.8.0-2-amd64 #1 Debian 4.8.11-1
[147965.913671] Hardware name: PC Engines APU, BIOS SageBios_PCEngines_APU-45 04/05/2014
[147965.921496] 0000000000000086 2c0493b5e5995666 ffffffffb49269f5 0000000000000000
[147965.929080] 0000000000000000 ffffffffb467c16e ffff96d2dec18180 ffff96d2c17fee40
[147965.936662] ffff96d2dec18180 0000000000000004 0000000000000046 ffff96d2dec18180
[147965.944244] Call Trace:
[147965.946786] <IRQ> [<ffffffffb49269f5>] ? dump_stack+0x5c/0x77
[147965.952830] [<ffffffffb467c16e>] ? __warn+0xbe/0xe0
[147965.957893] [<ffffffffb46a4720>] ? check_preempt_curr+0x50/0x90
[147965.963993] [<ffffffffb46a4774>] ? ttwu_do_wakeup+0x14/0xe0
[147965.969745] [<ffffffffb46a5441>] ? try_to_wake_up+0x191/0x3a0
[147965.975675] [<ffffffffb46bce93>] ? autoremove_wake_function+0x13/0x40
[147965.982293] [<ffffffffb46bc76e>] ? __wake_up_common+0x4e/0x90
[147965.988221] [<ffffffffb46bc7e4>] ? __wake_up+0x34/0x50
[147965.993545] [<ffffffffb475b943>] ? irq_work_run_list+0x43/0x70
[147965.999557] [<ffffffffb46318da>] ? smp_irq_work_interrupt+0x2a/0x30
[147966.006005] [<ffffffffb4bf2202>] ? irq_work_interrupt+0x82/0x90
[147966.012108] [<ffffffffb477a7b4>] ? panic+0x1e6/0x226
[147966.017254] [<ffffffffb477a7ad>] ? panic+0x1df/0x226
[147966.022404] [<ffffffffb462fa42>] ? oops_end+0xc2/0xd0
[147966.027635] [<ffffffffb46651e8>] ? no_context+0x128/0x370
[147966.033217] [<ffffffffb46a56d0>] ? wake_up_q+0x60/0x60
[147966.038538] [<ffffffffb4bf0e58>] ? page_fault+0x28/0x30
[147966.043948] [<ffffffffb4bb8b19>] ? icmp6_send+0x229/0x9f0
[147966.049532] [<ffffffffc07330df>] ? ctnetlink_conntrack_event+0x3ff/0x620 [nf_conntrack_netlink]
[147966.058404] [<ffffffffc068e94a>] ? nf_nat_cleanup_conntrack+0xea/0x1a0 [nf_nat]
[147966.065888] [<ffffffffb4b74653>] ? get_frag_bucket_locked+0x43/0x70
[147966.072340] [<ffffffffc0696330>] ? nf_ct_net_init+0x130/0x130 [nf_defrag_ipv6]
[147966.079738] [<ffffffffb4bbff78>] ? ip6_expire_frag_queue+0xf8/0x100
[147966.086186] [<ffffffffb46e6e80>] ? call_timer_fn+0x30/0x120
[147966.091941] [<ffffffffb46e7406>] ? run_timer_softirq+0x216/0x4b0
[147966.098127] [<ffffffffb46f7ac0>] ? tick_sched_handle.isra.12+0x20/0x50
[147966.104835] [<ffffffffb46f7b28>] ? tick_sched_timer+0x38/0x70
[147966.110764] [<ffffffffb4bf2598>] ? __do_softirq+0xf8/0x290
[147966.116431] [<ffffffffb4681abb>] ? irq_exit+0x9b/0xa0
[147966.121664] [<ffffffffb4bf23ae>] ? smp_apic_timer_interrupt+0x3e/0x50
[147966.128285] [<ffffffffb4bf16c2>] ? apic_timer_interrupt+0x82/0x90
[147966.134557] <EOI> [<ffffffffb4ab0f06>] ? cpuidle_enter_state+0x126/0x2d0
[147966.141555] [<ffffffffb4ab0ef3>] ? cpuidle_enter_state+0x113/0x2d0
[147966.147916] [<ffffffffb46bd742>] ? cpu_startup_entry+0x2a2/0x350
[147966.154103] [<ffffffffb464eddd>] ? start_secondary+0x14d/0x190
[147966.160117] ---[ end trace d5725bb00a2f3d6c ]---
Regards,
Chris
--
Chris Boot
bootc@bootc.net
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox