[PATCH openEuler-5.10 1/6] Revert "xfrm: rate limit SA mapping change message to user space"
hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I531X9
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
This reverts commit 71022a70c75395d2edbd2bf83101794f65719a69.
Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- include/net/xfrm.h | 5 ----- include/uapi/linux/xfrm.h | 1 - net/xfrm/xfrm_compat.c | 6 ++---- net/xfrm/xfrm_state.c | 23 +---------------------- net/xfrm/xfrm_user.c | 18 +----------------- 5 files changed, 4 insertions(+), 49 deletions(-)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c3437ae77e7d..f2875c629d06 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -199,11 +199,6 @@ struct xfrm_state { struct xfrm_algo_aead *aead; const char *geniv;
- /* mapping change rate limiting */ - __be16 new_mapping_sport; - u32 new_mapping; /* seconds */ - u32 mapping_maxage; /* seconds for input SA */ - /* Data for encapsulator */ struct xfrm_encap_tmpl *encap; struct sock __rcu *encap_sk; diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 2290c98b47cf..ffc6a5391bb7 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -308,7 +308,6 @@ enum xfrm_attr_type_t { XFRMA_SET_MARK, /* __u32 */ XFRMA_SET_MARK_MASK, /* __u32 */ XFRMA_IF_ID, /* __u32 */ - XFRMA_MTIMER_THRESH, /* __u32 in seconds for input SA */ __XFRMA_MAX
#define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index a0f62fa02e06..2bf269390163 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -127,7 +127,6 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_SET_MARK] = { .type = NLA_U32 }, [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, - [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, };
static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, @@ -275,10 +274,9 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) case XFRMA_SET_MARK: case XFRMA_SET_MARK_MASK: case XFRMA_IF_ID: - case XFRMA_MTIMER_THRESH: return xfrm_nla_cpy(dst, src, nla_len(src)); default: - BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID); pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } @@ -433,7 +431,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, int err;
if (type > XFRMA_MAX) { - BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID); NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 65e2805fa113..c158e70e8ae1 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1557,9 +1557,6 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->km.seq = orig->km.seq; x->replay = orig->replay; x->preplay = orig->preplay; - x->mapping_maxage = orig->mapping_maxage; - x->new_mapping = 0; - x->new_mapping_sport = 0;
return x;
@@ -2211,7 +2208,7 @@ int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) } EXPORT_SYMBOL(km_query);
-static int __km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) +int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { int err = -EINVAL; struct xfrm_mgr *km; @@ -2226,24 +2223,6 @@ static int __km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 rcu_read_unlock(); return err; } - -int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) -{ - int ret = 0; - - if (x->mapping_maxage) { - if ((jiffies / HZ - x->new_mapping) > x->mapping_maxage || - x->new_mapping_sport != sport) { - x->new_mapping_sport = sport; - x->new_mapping = jiffies / HZ; - ret = __km_new_mapping(x, ipaddr, sport); - } - } else { - ret = __km_new_mapping(x, ipaddr, sport); - } - - return ret; -} EXPORT_SYMBOL(km_new_mapping);
void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index d0fdfbf4c5f7..ddf1b3a5f7c1 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -282,10 +282,6 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
err = 0;
- if (attrs[XFRMA_MTIMER_THRESH]) - if (!attrs[XFRMA_ENCAP]) - err = -EINVAL; - out: return err; } @@ -525,7 +521,6 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, struct nlattr *lt = attrs[XFRMA_LTIME_VAL]; struct nlattr *et = attrs[XFRMA_ETIMER_THRESH]; struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; - struct nlattr *mt = attrs[XFRMA_MTIMER_THRESH];
if (re) { struct xfrm_replay_state_esn *replay_esn; @@ -557,9 +552,6 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs,
if (rt) x->replay_maxdiff = nla_get_u32(rt); - - if (mt) - x->mapping_maxage = nla_get_u32(mt); }
static void xfrm_smark_init(struct nlattr **attrs, struct xfrm_mark *m) @@ -977,13 +969,8 @@ static int copy_to_user_state_extra(struct xfrm_state *x, if (ret) goto out; } - if (x->security) { + if (x->security) ret = copy_sec_ctx(x->security, skb); - if (ret) - goto out; - } - if (x->mapping_maxage) - ret = nla_put_u32(skb, XFRMA_MTIMER_THRESH, x->mapping_maxage); out: return ret; } @@ -2937,9 +2924,6 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) /* Must count x->lastused as it may become non-zero behind our back. */ l += nla_total_size_64bit(sizeof(u64));
- if (x->mapping_maxage) - l += nla_total_size(sizeof(x->mapping_maxage)); - return l; }
hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I531X9
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
This reverts commit d99e6e1c12d838dfcfc67421c293e972214b9eed.
Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- kernel/time/clocksource.c | 50 +++++++-------------------------------- 1 file changed, 9 insertions(+), 41 deletions(-)
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index e34ceb91f4c5..d0803a69a200 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -105,7 +105,7 @@ static u64 suspend_start; * This delay could be due to SMIs, NMIs, or to VCPU preemptions. Used as * a lower bound for cs->uncertainty_margin values when registering clocks. */ -#define WATCHDOG_MAX_SKEW (100 * NSEC_PER_USEC) +#define WATCHDOG_MAX_SKEW (50 * NSEC_PER_USEC)
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); @@ -200,24 +200,17 @@ void clocksource_mark_unstable(struct clocksource *cs) static ulong max_cswd_read_retries = 3; module_param(max_cswd_read_retries, ulong, 0644);
-enum wd_read_status { - WD_READ_SUCCESS, - WD_READ_UNSTABLE, - WD_READ_SKIP -}; - -static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) +static bool cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { unsigned int nretries; - u64 wd_end, wd_end2, wd_delta; - int64_t wd_delay, wd_seq_delay; + u64 wd_end, wd_delta; + int64_t wd_delay;
for (nretries = 0; nretries <= max_cswd_read_retries; nretries++) { local_irq_disable(); *wdnow = watchdog->read(watchdog); *csnow = cs->read(cs); wd_end = watchdog->read(watchdog); - wd_end2 = watchdog->read(watchdog); local_irq_enable();
wd_delta = clocksource_delta(wd_end, *wdnow, watchdog->mask); @@ -228,34 +221,13 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", smp_processor_id(), watchdog->name, nretries); } - return WD_READ_SUCCESS; + return true; } - - /* - * Now compute delay in consecutive watchdog read to see if - * there is too much external interferences that cause - * significant delay in reading both clocksource and watchdog. - * - * If consecutive WD read-back delay > WATCHDOG_MAX_SKEW/2, - * report system busy, reinit the watchdog and skip the current - * watchdog test. - */ - wd_delta = clocksource_delta(wd_end2, wd_end, watchdog->mask); - wd_seq_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, watchdog->shift); - if (wd_seq_delay > WATCHDOG_MAX_SKEW/2) - goto skip_test; }
pr_warn("timekeeping watchdog on CPU%d: %s read-back delay of %lldns, attempt %d, marking unstable\n", smp_processor_id(), watchdog->name, wd_delay, nretries); - return WD_READ_UNSTABLE; - -skip_test: - pr_info("timekeeping watchdog on CPU%d: %s wd-wd read-back delay of %lldns\n", - smp_processor_id(), watchdog->name, wd_seq_delay); - pr_info("wd-%s-wd read-back delay of %lldns, clock-skew test skipped!\n", - cs->name, wd_delay); - return WD_READ_SKIP; + return false; }
static u64 csnow_mid; @@ -318,7 +290,6 @@ static void clocksource_watchdog(struct timer_list *unused) int next_cpu, reset_pending; int64_t wd_nsec, cs_nsec; struct clocksource *cs; - enum wd_read_status read_ret; u32 md;
spin_lock(&watchdog_lock); @@ -336,12 +307,9 @@ static void clocksource_watchdog(struct timer_list *unused) continue; }
- read_ret = cs_watchdog_read(cs, &csnow, &wdnow); - - if (read_ret != WD_READ_SUCCESS) { - if (read_ret == WD_READ_UNSTABLE) - /* Clock readout unreliable, so give it up. */ - __clocksource_unstable(cs); + if (!cs_watchdog_read(cs, &csnow, &wdnow)) { + /* Clock readout unreliable, so give it up. */ + __clocksource_unstable(cs); continue; }
hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I531X9
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
This reverts commit 270507d879d1c4c343603cb299423576e1fb96a1.
Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- arch/x86/kernel/tsc.c | 1 - include/linux/clocksource.h | 3 --- kernel/time/clocksource.c | 48 ++++++++----------------------------- kernel/time/jiffies.c | 15 ++++++------ 4 files changed, 17 insertions(+), 50 deletions(-)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 13d1a0ac8916..f9f1b45e5ddc 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1127,7 +1127,6 @@ static int tsc_cs_enable(struct clocksource *cs) static struct clocksource clocksource_tsc_early = { .name = "tsc-early", .rating = 299, - .uncertainty_margin = 32 * NSEC_PER_MSEC, .read = read_tsc, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 5eed1e196900..4c3ecccc44ed 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -42,8 +42,6 @@ struct module; * @shift: Cycle to nanosecond divisor (power of two) * @max_idle_ns: Maximum idle time permitted by the clocksource (nsecs) * @maxadj: Maximum adjustment value to mult (~11%) - * @uncertainty_margin: Maximum uncertainty in nanoseconds per half second. - * Zero says to use default WATCHDOG_THRESHOLD. * @archdata: Optional arch-specific data * @max_cycles: Maximum safe cycle value which won't overflow on * multiplication @@ -95,7 +93,6 @@ struct clocksource { u32 shift; u64 max_idle_ns; u32 maxadj; - u32 uncertainty_margin; #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA struct arch_clocksource_data archdata; #endif diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index d0803a69a200..74492f08660c 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -93,20 +93,6 @@ static char override_name[CS_NAME_LEN]; static int finished_booting; static u64 suspend_start;
-/* - * Threshold: 0.0312s, when doubled: 0.0625s. - * Also a default for cs->uncertainty_margin when registering clocks. - */ -#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 5) - -/* - * Maximum permissible delay between two readouts of the watchdog - * clocksource surrounding a read of the clocksource being validated. - * This delay could be due to SMIs, NMIs, or to VCPU preemptions. Used as - * a lower bound for cs->uncertainty_margin values when registering clocks. - */ -#define WATCHDOG_MAX_SKEW (50 * NSEC_PER_USEC) - #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); static void clocksource_select(void); @@ -133,9 +119,17 @@ static int clocksource_watchdog_kthread(void *data); static void __clocksource_change_rating(struct clocksource *cs, int rating);
/* - * Interval: 0.5sec. + * Interval: 0.5sec Threshold: 0.0625s */ #define WATCHDOG_INTERVAL (HZ >> 1) +#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4) + +/* + * Maximum permissible delay between two readouts of the watchdog + * clocksource surrounding a read of the clocksource being validated. + * This delay could be due to SMIs, NMIs, or to VCPU preemptions. + */ +#define WATCHDOG_MAX_SKEW (100 * NSEC_PER_USEC)
static void clocksource_watchdog_work(struct work_struct *work) { @@ -290,7 +284,6 @@ static void clocksource_watchdog(struct timer_list *unused) int next_cpu, reset_pending; int64_t wd_nsec, cs_nsec; struct clocksource *cs; - u32 md;
spin_lock(&watchdog_lock); if (!watchdog_running) @@ -337,8 +330,7 @@ static void clocksource_watchdog(struct timer_list *unused) continue;
/* Check the deviation from the watchdog clocksource. */ - md = cs->uncertainty_margin + watchdog->uncertainty_margin; - if (abs(cs_nsec - wd_nsec) > md) { + if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { pr_warn("timekeeping watchdog on CPU%d: Marking clocksource '%s' as unstable because the skew is too large:\n", smp_processor_id(), cs->name); pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n", @@ -993,26 +985,6 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, NSEC_PER_SEC / scale, sec * scale); } - - /* - * If the uncertainty margin is not specified, calculate it. - * If both scale and freq are non-zero, calculate the clock - * period, but bound below at 2*WATCHDOG_MAX_SKEW. However, - * if either of scale or freq is zero, be very conservative and - * take the tens-of-milliseconds WATCHDOG_THRESHOLD value for the - * uncertainty margin. Allow stupidly small uncertainty margins - * to be specified by the caller for testing purposes, but warn - * to discourage production use of this capability. - */ - if (scale && freq && !cs->uncertainty_margin) { - cs->uncertainty_margin = NSEC_PER_SEC / (scale * freq); - if (cs->uncertainty_margin < 2 * WATCHDOG_MAX_SKEW) - cs->uncertainty_margin = 2 * WATCHDOG_MAX_SKEW; - } else if (!cs->uncertainty_margin) { - cs->uncertainty_margin = WATCHDOG_THRESHOLD; - } - WARN_ON_ONCE(cs->uncertainty_margin < 2 * WATCHDOG_MAX_SKEW); - /* * Ensure clocksources that have large 'mult' values don't overflow * when adjusted. diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 65409abcca8e..eddcf4970444 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -49,14 +49,13 @@ static u64 jiffies_read(struct clocksource *cs) * for "tick-less" systems. */ static struct clocksource clocksource_jiffies = { - .name = "jiffies", - .rating = 1, /* lowest valid rating*/ - .uncertainty_margin = 32 * NSEC_PER_MSEC, - .read = jiffies_read, - .mask = CLOCKSOURCE_MASK(32), - .mult = TICK_NSEC << JIFFIES_SHIFT, /* details above */ - .shift = JIFFIES_SHIFT, - .max_cycles = 10, + .name = "jiffies", + .rating = 1, /* lowest valid rating*/ + .read = jiffies_read, + .mask = CLOCKSOURCE_MASK(32), + .mult = TICK_NSEC << JIFFIES_SHIFT, /* details above */ + .shift = JIFFIES_SHIFT, + .max_cycles = 10, };
__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock);
From: Eric Dumazet edumazet@google.com
stable inclusion from stable-v5.10.109 commit 571df3393f523b59cba87e2f3e80a3a624030f9c bugzilla: https://gitee.com/src-openeuler/kernel/issues/I51YBN CVE: CVE-2022-28356
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
commit 764f4eb6846f5475f1244767d24d25dd86528a4a upstream.
Whenever llc_ui_bind() and/or llc_ui_autobind() took a reference on a netdevice but subsequently fail, they must properly release their reference or risk the infamous message from unregister_netdevice() at device dismantle.
unregister_netdevice: waiting for eth0 to become free. Usage count = 3
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: 赵子轩 beraphin@gmail.com Reported-by: Stoyan Manolov smanolov@suse.de Link: https://lore.kernel.org/r/20220323004147.1990845-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Huang Guobin huangguobin4@huawei.com Reviewed-by: Wei Yongjun weiyongjun1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- net/llc/af_llc.c | 8 ++++++++ 1 file changed, 8 insertions(+)
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index ac5cadd02cfa..2fdb72a26fa8 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -311,6 +311,10 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) sock_reset_flag(sk, SOCK_ZAPPED); rc = 0; out: + if (rc) { + dev_put(llc->dev); + llc->dev = NULL; + } return rc; }
@@ -409,6 +413,10 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) out_put: llc_sap_put(sap); out: + if (rc) { + dev_put(llc->dev); + llc->dev = NULL; + } release_sock(sk); return rc; }
From: Yajun Deng yajun.deng@linux.dev
stable inclusion from stable-v5.10.110 commit ff919a7ad90c361634f0bc5c58120252d87b887a bugzilla: https://gitee.com/src-openeuler/kernel/issues/I51YBN CVE: CVE-2022-28356
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?ff9...
--------------------------------
commit b37a466837393af72fe8bcb8f1436410f3f173f3 upstream.
Add the case if dev is NULL in dev_{put, hold}, so the caller doesn't need to care whether dev is NULL or not.
Signed-off-by: Yajun Deng yajun.deng@linux.dev Signed-off-by: David S. Miller davem@davemloft.net Cc: Pavel Machek pavel@denx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Huang Guobin huangguobin4@huawei.com Reviewed-by: Wei Yongjun weiyongjun1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- include/linux/netdevice.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 41b991fc3a4b..051a8b2edf13 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4033,7 +4033,8 @@ void netdev_run_todo(void); */ static inline void dev_put(struct net_device *dev) { - this_cpu_dec(*dev->pcpu_refcnt); + if (dev) + this_cpu_dec(*dev->pcpu_refcnt); }
/** @@ -4044,7 +4045,8 @@ static inline void dev_put(struct net_device *dev) */ static inline void dev_hold(struct net_device *dev) { - this_cpu_inc(*dev->pcpu_refcnt); + if (dev) + this_cpu_inc(*dev->pcpu_refcnt); }
/* Carrier loss detection, dial on demand. The functions netif_carrier_on
From: Eric Dumazet edumazet@google.com
stable inclusion from stable-v5.10.109 commit 163960a7de1333514c9352deb7c80c6b9fd9abf2 bugzilla: https://gitee.com/src-openeuler/kernel/issues/I51YBN CVE: CVE-2022-28356
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
commit 2d327a79ee176930dc72c131a970c891d367c1dc upstream.
My latest patch, attempting to fix the refcount leak in a minimal way turned out to add a new bug.
Whenever the bind operation fails before we attempt to grab a reference count on a device, we might release the device refcount of a prior successful bind() operation.
syzbot was not happy about this [1].
Note to stable teams:
Make sure commit b37a46683739 ("netdevice: add the case if dev is NULL") is already present in your trees.
[1] general protection fault, probably for non-canonical address 0xdffffc0000000070: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000380-0x0000000000000387] CPU: 1 PID: 3590 Comm: syz-executor361 Tainted: G W 5.17.0-syzkaller-04796-g169e77764adc #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:llc_ui_connect+0x400/0xcb0 net/llc/af_llc.c:500 Code: 80 3c 02 00 0f 85 fc 07 00 00 4c 8b a5 38 05 00 00 48 b8 00 00 00 00 00 fc ff df 49 8d bc 24 80 03 00 00 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 a9 07 00 00 49 8b b4 24 80 03 00 00 4c 89 f2 48 RSP: 0018:ffffc900038cfcc0 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff8880756eb600 RCX: 0000000000000000 RDX: 0000000000000070 RSI: ffffc900038cfe3e RDI: 0000000000000380 RBP: ffff888015ee5000 R08: 0000000000000001 R09: ffff888015ee5535 R10: ffffed1002bdcaa6 R11: 0000000000000000 R12: 0000000000000000 R13: ffffc900038cfe37 R14: ffffc900038cfe38 R15: ffff888015ee5012 FS: 0000555555acd300(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000280 CR3: 0000000077db6000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> __sys_connect_file+0x155/0x1a0 net/socket.c:1900 __sys_connect+0x161/0x190 net/socket.c:1917 __do_sys_connect net/socket.c:1927 [inline] __se_sys_connect net/socket.c:1924 [inline] __x64_sys_connect+0x6f/0xb0 net/socket.c:1924 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f016acb90b9 Code: 28 c3 e8 2a 14 00 00 66 2e 0f 1f 84 00 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffd417947f8 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f016acb90b9 RDX: 0000000000000010 RSI: 0000000020000140 RDI: 0000000000000003 RBP: 00007f016ac7d0a0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f016ac7d130 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- RIP: 0010:llc_ui_connect+0x400/0xcb0 net/llc/af_llc.c:500
Fixes: 764f4eb6846f ("llc: fix netdevice reference leaks in llc_ui_bind()") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Cc: 赵子轩 beraphin@gmail.com Cc: Stoyan Manolov smanolov@suse.de Link: https://lore.kernel.org/r/20220325035827.360418-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Huang Guobin huangguobin4@huawei.com Reviewed-by: Wei Yongjun weiyongjun1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- net/llc/af_llc.c | 57 +++++++++++++++++++++++++++--------------------- 1 file changed, 32 insertions(+), 25 deletions(-)
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 2fdb72a26fa8..99a37c411323 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -276,6 +276,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); + struct net_device *dev = NULL; struct llc_sap *sap; int rc = -EINVAL;
@@ -287,14 +288,14 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) goto out; rc = -ENODEV; if (sk->sk_bound_dev_if) { - llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); - if (llc->dev && addr->sllc_arphrd != llc->dev->type) { - dev_put(llc->dev); - llc->dev = NULL; + dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); + if (dev && addr->sllc_arphrd != dev->type) { + dev_put(dev); + dev = NULL; } } else - llc->dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd); - if (!llc->dev) + dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd); + if (!dev) goto out; rc = -EUSERS; llc->laddr.lsap = llc_ui_autoport(); @@ -304,6 +305,11 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) sap = llc_sap_open(llc->laddr.lsap, NULL); if (!sap) goto out; + + /* Note: We do not expect errors from this point. */ + llc->dev = dev; + dev = NULL; + memcpy(llc->laddr.mac, llc->dev->dev_addr, IFHWADDRLEN); memcpy(&llc->addr, addr, sizeof(llc->addr)); /* assign new connection to its SAP */ @@ -311,10 +317,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) sock_reset_flag(sk, SOCK_ZAPPED); rc = 0; out: - if (rc) { - dev_put(llc->dev); - llc->dev = NULL; - } + dev_put(dev); return rc; }
@@ -337,6 +340,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) struct sockaddr_llc *addr = (struct sockaddr_llc *)uaddr; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); + struct net_device *dev = NULL; struct llc_sap *sap; int rc = -EINVAL;
@@ -352,25 +356,26 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) rc = -ENODEV; rcu_read_lock(); if (sk->sk_bound_dev_if) { - llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); - if (llc->dev) { + dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); + if (dev) { if (is_zero_ether_addr(addr->sllc_mac)) - memcpy(addr->sllc_mac, llc->dev->dev_addr, + memcpy(addr->sllc_mac, dev->dev_addr, IFHWADDRLEN); - if (addr->sllc_arphrd != llc->dev->type || + if (addr->sllc_arphrd != dev->type || !ether_addr_equal(addr->sllc_mac, - llc->dev->dev_addr)) { + dev->dev_addr)) { rc = -EINVAL; - llc->dev = NULL; + dev = NULL; } } - } else - llc->dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd, + } else { + dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd, addr->sllc_mac); - if (llc->dev) - dev_hold(llc->dev); + } + if (dev) + dev_hold(dev); rcu_read_unlock(); - if (!llc->dev) + if (!dev) goto out; if (!addr->sllc_sap) { rc = -EUSERS; @@ -403,6 +408,11 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) goto out_put; } } + + /* Note: We do not expect errors from this point. */ + llc->dev = dev; + dev = NULL; + llc->laddr.lsap = addr->sllc_sap; memcpy(llc->laddr.mac, addr->sllc_mac, IFHWADDRLEN); memcpy(&llc->addr, addr, sizeof(llc->addr)); @@ -413,10 +423,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) out_put: llc_sap_put(sap); out: - if (rc) { - dev_put(llc->dev); - llc->dev = NULL; - } + dev_put(dev); release_sock(sk); return rc; }
-
Zheng Zengkai