July 2025 - Linux-stable-mirror

FAILED: patch "[PATCH] Revert "xfrm: destroy xfrm_state synchronously on net exit" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 2a198bbec6913ae1c90ec963750003c6213668c7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025072925-hardware-hatching-15cf@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2a198bbec6913ae1c90ec963750003c6213668c7 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca <sd(a)queasysnail.net> Date: Fri, 4 Jul 2025 16:54:34 +0200 Subject: [PATCH] Revert "xfrm: destroy xfrm_state synchronously on net exit path" This reverts commit f75a2804da391571563c4b6b29e7797787332673. With all states (whether user or kern) removed from the hashtables during deletion, there's no need for synchronous destruction of states. xfrm6_tunnel states still need to have been destroyed (which will be the case when its last user is deleted (not destroyed)) so that xfrm6_tunnel_free_spi removes it from the per-netns hashtable before the netns is destroyed. This has the benefit of skipping one synchronize_rcu per state (in __xfrm_state_destroy(sync=true)) when we exit a netns. Signed-off-by: Sabrina Dubroca <sd(a)queasysnail.net> Signed-off-by: Steffen Klassert <steffen.klassert(a)secunet.com> diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 91d52a380e37..f3014e4f54fc 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -915,7 +915,7 @@ static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) xfrm_pol_put(pols[i]); } -void __xfrm_state_destroy(struct xfrm_state *, bool); +void __xfrm_state_destroy(struct xfrm_state *); static inline void __xfrm_state_put(struct xfrm_state *x) { @@ -925,13 +925,7 @@ static inline void __xfrm_state_put(struct xfrm_state *x) static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, false); -} - -static inline void xfrm_state_put_sync(struct xfrm_state *x) -{ - if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, true); + __xfrm_state_destroy(x); } static inline void xfrm_state_hold(struct xfrm_state *x) @@ -1769,7 +1763,7 @@ struct xfrmk_spdinfo { struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_delete(struct xfrm_state *x); -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, bool task_valid); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 7fd8bc08e6eb..5120a763da0d 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -334,7 +334,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, 0, false, true); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); xfrm_flush_gc(); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) diff --git a/net/key/af_key.c b/net/key/af_key.c index efc2a91f4c48..b5d761700776 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1766,7 +1766,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m if (proto == 0) return -EINVAL; - err = xfrm_state_flush(net, proto, true, false); + err = xfrm_state_flush(net, proto, true); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f7110a658897..327a1a6f892c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -592,7 +592,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); -static void ___xfrm_state_destroy(struct xfrm_state *x) +static void xfrm_state_gc_destroy(struct xfrm_state *x) { if (x->mode_cbs && x->mode_cbs->destroy_state) x->mode_cbs->destroy_state(x); @@ -631,7 +631,7 @@ static void xfrm_state_gc_task(struct work_struct *work) synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) - ___xfrm_state_destroy(x); + xfrm_state_gc_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) @@ -795,19 +795,14 @@ void xfrm_dev_state_free(struct xfrm_state *x) } #endif -void __xfrm_state_destroy(struct xfrm_state *x, bool sync) +void __xfrm_state_destroy(struct xfrm_state *x) { WARN_ON(x->km.state != XFRM_STATE_DEAD); - if (sync) { - synchronize_rcu(); - ___xfrm_state_destroy(x); - } else { - spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &xfrm_state_gc_list); - spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); - } + spin_lock_bh(&xfrm_state_gc_lock); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); + spin_unlock_bh(&xfrm_state_gc_lock); + schedule_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(__xfrm_state_destroy); @@ -922,7 +917,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool } #endif -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) { int i, err = 0, cnt = 0; @@ -3283,7 +3278,7 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, 0, false, true); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&xfrm_state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 1db18f470f42..684239018bec 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2635,7 +2635,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err; - err = xfrm_state_flush(net, p->proto, true, false); + err = xfrm_state_flush(net, p->proto, true); if (err) { if (err == -ESRCH) /* empty table */ return 0;

3 weeks, 4 days

1
0
0 0

FAILED: patch "[PATCH] Revert "xfrm: destroy xfrm_state synchronously on net exit" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 2a198bbec6913ae1c90ec963750003c6213668c7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025072926-chill-nylon-314e@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2a198bbec6913ae1c90ec963750003c6213668c7 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca <sd(a)queasysnail.net> Date: Fri, 4 Jul 2025 16:54:34 +0200 Subject: [PATCH] Revert "xfrm: destroy xfrm_state synchronously on net exit path" This reverts commit f75a2804da391571563c4b6b29e7797787332673. With all states (whether user or kern) removed from the hashtables during deletion, there's no need for synchronous destruction of states. xfrm6_tunnel states still need to have been destroyed (which will be the case when its last user is deleted (not destroyed)) so that xfrm6_tunnel_free_spi removes it from the per-netns hashtable before the netns is destroyed. This has the benefit of skipping one synchronize_rcu per state (in __xfrm_state_destroy(sync=true)) when we exit a netns. Signed-off-by: Sabrina Dubroca <sd(a)queasysnail.net> Signed-off-by: Steffen Klassert <steffen.klassert(a)secunet.com> diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 91d52a380e37..f3014e4f54fc 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -915,7 +915,7 @@ static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) xfrm_pol_put(pols[i]); } -void __xfrm_state_destroy(struct xfrm_state *, bool); +void __xfrm_state_destroy(struct xfrm_state *); static inline void __xfrm_state_put(struct xfrm_state *x) { @@ -925,13 +925,7 @@ static inline void __xfrm_state_put(struct xfrm_state *x) static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, false); -} - -static inline void xfrm_state_put_sync(struct xfrm_state *x) -{ - if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, true); + __xfrm_state_destroy(x); } static inline void xfrm_state_hold(struct xfrm_state *x) @@ -1769,7 +1763,7 @@ struct xfrmk_spdinfo { struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_delete(struct xfrm_state *x); -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, bool task_valid); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 7fd8bc08e6eb..5120a763da0d 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -334,7 +334,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, 0, false, true); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); xfrm_flush_gc(); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) diff --git a/net/key/af_key.c b/net/key/af_key.c index efc2a91f4c48..b5d761700776 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1766,7 +1766,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m if (proto == 0) return -EINVAL; - err = xfrm_state_flush(net, proto, true, false); + err = xfrm_state_flush(net, proto, true); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f7110a658897..327a1a6f892c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -592,7 +592,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); -static void ___xfrm_state_destroy(struct xfrm_state *x) +static void xfrm_state_gc_destroy(struct xfrm_state *x) { if (x->mode_cbs && x->mode_cbs->destroy_state) x->mode_cbs->destroy_state(x); @@ -631,7 +631,7 @@ static void xfrm_state_gc_task(struct work_struct *work) synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) - ___xfrm_state_destroy(x); + xfrm_state_gc_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) @@ -795,19 +795,14 @@ void xfrm_dev_state_free(struct xfrm_state *x) } #endif -void __xfrm_state_destroy(struct xfrm_state *x, bool sync) +void __xfrm_state_destroy(struct xfrm_state *x) { WARN_ON(x->km.state != XFRM_STATE_DEAD); - if (sync) { - synchronize_rcu(); - ___xfrm_state_destroy(x); - } else { - spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &xfrm_state_gc_list); - spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); - } + spin_lock_bh(&xfrm_state_gc_lock); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); + spin_unlock_bh(&xfrm_state_gc_lock); + schedule_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(__xfrm_state_destroy); @@ -922,7 +917,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool } #endif -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) { int i, err = 0, cnt = 0; @@ -3283,7 +3278,7 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, 0, false, true); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&xfrm_state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 1db18f470f42..684239018bec 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2635,7 +2635,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err; - err = xfrm_state_flush(net, p->proto, true, false); + err = xfrm_state_flush(net, p->proto, true); if (err) { if (err == -ESRCH) /* empty table */ return 0;

3 weeks, 4 days

1
0
0 0

FAILED: patch "[PATCH] Revert "xfrm: destroy xfrm_state synchronously on net exit" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 2a198bbec6913ae1c90ec963750003c6213668c7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025072925-swiftly-cheesy-9ad2@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2a198bbec6913ae1c90ec963750003c6213668c7 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca <sd(a)queasysnail.net> Date: Fri, 4 Jul 2025 16:54:34 +0200 Subject: [PATCH] Revert "xfrm: destroy xfrm_state synchronously on net exit path" This reverts commit f75a2804da391571563c4b6b29e7797787332673. With all states (whether user or kern) removed from the hashtables during deletion, there's no need for synchronous destruction of states. xfrm6_tunnel states still need to have been destroyed (which will be the case when its last user is deleted (not destroyed)) so that xfrm6_tunnel_free_spi removes it from the per-netns hashtable before the netns is destroyed. This has the benefit of skipping one synchronize_rcu per state (in __xfrm_state_destroy(sync=true)) when we exit a netns. Signed-off-by: Sabrina Dubroca <sd(a)queasysnail.net> Signed-off-by: Steffen Klassert <steffen.klassert(a)secunet.com> diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 91d52a380e37..f3014e4f54fc 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -915,7 +915,7 @@ static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) xfrm_pol_put(pols[i]); } -void __xfrm_state_destroy(struct xfrm_state *, bool); +void __xfrm_state_destroy(struct xfrm_state *); static inline void __xfrm_state_put(struct xfrm_state *x) { @@ -925,13 +925,7 @@ static inline void __xfrm_state_put(struct xfrm_state *x) static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, false); -} - -static inline void xfrm_state_put_sync(struct xfrm_state *x) -{ - if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, true); + __xfrm_state_destroy(x); } static inline void xfrm_state_hold(struct xfrm_state *x) @@ -1769,7 +1763,7 @@ struct xfrmk_spdinfo { struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_delete(struct xfrm_state *x); -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, bool task_valid); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 7fd8bc08e6eb..5120a763da0d 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -334,7 +334,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, 0, false, true); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); xfrm_flush_gc(); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) diff --git a/net/key/af_key.c b/net/key/af_key.c index efc2a91f4c48..b5d761700776 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1766,7 +1766,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m if (proto == 0) return -EINVAL; - err = xfrm_state_flush(net, proto, true, false); + err = xfrm_state_flush(net, proto, true); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f7110a658897..327a1a6f892c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -592,7 +592,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); -static void ___xfrm_state_destroy(struct xfrm_state *x) +static void xfrm_state_gc_destroy(struct xfrm_state *x) { if (x->mode_cbs && x->mode_cbs->destroy_state) x->mode_cbs->destroy_state(x); @@ -631,7 +631,7 @@ static void xfrm_state_gc_task(struct work_struct *work) synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) - ___xfrm_state_destroy(x); + xfrm_state_gc_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) @@ -795,19 +795,14 @@ void xfrm_dev_state_free(struct xfrm_state *x) } #endif -void __xfrm_state_destroy(struct xfrm_state *x, bool sync) +void __xfrm_state_destroy(struct xfrm_state *x) { WARN_ON(x->km.state != XFRM_STATE_DEAD); - if (sync) { - synchronize_rcu(); - ___xfrm_state_destroy(x); - } else { - spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &xfrm_state_gc_list); - spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); - } + spin_lock_bh(&xfrm_state_gc_lock); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); + spin_unlock_bh(&xfrm_state_gc_lock); + schedule_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(__xfrm_state_destroy); @@ -922,7 +917,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool } #endif -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) { int i, err = 0, cnt = 0; @@ -3283,7 +3278,7 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, 0, false, true); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&xfrm_state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 1db18f470f42..684239018bec 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2635,7 +2635,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err; - err = xfrm_state_flush(net, p->proto, true, false); + err = xfrm_state_flush(net, p->proto, true); if (err) { if (err == -ESRCH) /* empty table */ return 0;

3 weeks, 4 days

1
0
0 0

[PATCH v2 1/1] mm: fix a UAF when vma->mm is freed after vma->vm_refcnt got dropped

by Suren Baghdasaryan

By inducing delays in the right places, Jann Horn created a reproducer for a hard to hit UAF issue that became possible after VMAs were allowed to be recycled by adding SLAB_TYPESAFE_BY_RCU to their cache. Race description is borrowed from Jann's discovery report: lock_vma_under_rcu() looks up a VMA locklessly with mas_walk() under rcu_read_lock(). At that point, the VMA may be concurrently freed, and it can be recycled by another process. vma_start_read() then increments the vma->vm_refcnt (if it is in an acceptable range), and if this succeeds, vma_start_read() can return a recycled VMA. In this scenario where the VMA has been recycled, lock_vma_under_rcu() will then detect the mismatching ->vm_mm pointer and drop the VMA through vma_end_read(), which calls vma_refcount_put(). vma_refcount_put() drops the refcount and then calls rcuwait_wake_up() using a copy of vma->vm_mm. This is wrong: It implicitly assumes that the caller is keeping the VMA's mm alive, but in this scenario the caller has no relation to the VMA's mm, so the rcuwait_wake_up() can cause UAF. The diagram depicting the race: T1 T2 T3 == == == lock_vma_under_rcu mas_walk <VMA gets removed from mm> mmap <the same VMA is reallocated> vma_start_read __refcount_inc_not_zero_limited_acquire munmap __vma_enter_locked refcount_add_not_zero vma_end_read vma_refcount_put __refcount_dec_and_test rcuwait_wait_event <finish operation> rcuwait_wake_up [UAF] Note that rcuwait_wait_event() in T3 does not block because refcount was already dropped by T1. At this point T3 can exit and free the mm causing UAF in T1. To avoid this we move vma->vm_mm verification into vma_start_read() and grab vma->vm_mm to stabilize it before vma_refcount_put() operation. Fixes: 3104138517fc ("mm: make vma cache SLAB_TYPESAFE_BY_RCU") Reported-by: Jann Horn <jannh(a)google.com> Closes: https://lore.kernel.org/all/CAG48ez0-deFbVH=E3jbkWx=X3uVbd8nWeo6kbJPQ0KoUD+… Signed-off-by: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> --- Changes since v1 [1] - Made a copy of vma->mm before using it in vma_start_read(), per Vlastimil Babka Notes: - Applies cleanly over mm-unstable. - Should be applied to 6.15 and 6.16 but these branches do not have lock_next_vma() function, so the change in lock_next_vma() should be skipped when applying to those branches. [1] https://lore.kernel.org/all/20250728170950.2216966-1-surenb@google.com/ include/linux/mmap_lock.h | 23 +++++++++++++++++++++++ mm/mmap_lock.c | 10 +++------- 2 files changed, 26 insertions(+), 7 deletions(-) diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 1f4f44951abe..da34afa2f8ef 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -12,6 +12,7 @@ extern int rcuwait_wake_up(struct rcuwait *w); #include <linux/tracepoint-defs.h> #include <linux/types.h> #include <linux/cleanup.h> +#include <linux/sched/mm.h> #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), @@ -183,6 +184,28 @@ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, } rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); + + /* + * If vma got attached to another mm from under us, that mm is not + * stable and can be freed in the narrow window after vma->vm_refcnt + * is dropped and before rcuwait_wake_up(mm) is called. Grab it before + * releasing vma->vm_refcnt. + */ + if (unlikely(vma->vm_mm != mm)) { + /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */ + struct mm_struct *other_mm = vma->vm_mm; + /* + * __mmdrop() is a heavy operation and we don't need RCU + * protection here. Release RCU lock during these operations. + */ + rcu_read_unlock(); + mmgrab(other_mm); + vma_refcount_put(vma); + mmdrop(other_mm); + rcu_read_lock(); + return NULL; + } + /* * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. * False unlocked result is impossible because we modify and check diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c index 729fb7d0dd59..aa3bc42ecde0 100644 --- a/mm/mmap_lock.c +++ b/mm/mmap_lock.c @@ -164,8 +164,7 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, */ /* Check if the vma we locked is the right one. */ - if (unlikely(vma->vm_mm != mm || - address < vma->vm_start || address >= vma->vm_end)) + if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto inval_end_read; rcu_read_unlock(); @@ -236,11 +235,8 @@ struct vm_area_struct *lock_next_vma(struct mm_struct *mm, goto fallback; } - /* - * Verify the vma we locked belongs to the same address space and it's - * not behind of the last search position. - */ - if (unlikely(vma->vm_mm != mm || from_addr >= vma->vm_end)) + /* Verify the vma is not behind of the last search position. */ + if (unlikely(from_addr >= vma->vm_end)) goto fallback_unlock; /* base-commit: c617a4dd7102e691fa0fb2bc4f6b369e37d7f509 -- 2.50.1.487.gc89ff58d15-goog

3 weeks, 4 days

4
8
0 0

[PATCH v1] ASoC: SOF: amd: acp-loader: Use GFP_KERNEL for DMA allocations in resume context

by Muhammad Usama Anjum

Replace GFP_ATOMIC with GFP_KERNEL for dma_alloc_coherent() calls. This change improves memory allocation reliability during firmware loading, particularly during system resume when memory pressure is high. Because of using GFP_KERNEL, reclaim can happen which can reduce the probability of failure. Fixes memory allocation failures observed during system resume with fragmented memory conditions. snd_sof_amd_vangogh 0000:04:00.5: error: failed to load DSP firmware after resume -12 Fixes: 145d7e5ae8f4e ("ASoC: SOF: amd: add option to use sram for data bin loading") Fixes: 7e51a9e38ab20 ("ASoC: SOF: amd: Add fw loader and renoir dsp ops to load firmware") Cc: stable(a)vger.kernel.org Signed-off-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> --- sound/soc/sof/amd/acp-loader.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/sound/soc/sof/amd/acp-loader.c b/sound/soc/sof/amd/acp-loader.c index 2d5e58846499..5b5d6db74c10 100644 --- a/sound/soc/sof/amd/acp-loader.c +++ b/sound/soc/sof/amd/acp-loader.c @@ -65,7 +65,7 @@ int acp_dsp_block_write(struct snd_sof_dev *sdev, enum snd_sof_fw_blk_type blk_t dma_size = page_count * ACP_PAGE_SIZE; adata->bin_buf = dma_alloc_coherent(&pci->dev, dma_size, &adata->sha_dma_addr, - GFP_ATOMIC); + GFP_KERNEL); if (!adata->bin_buf) return -ENOMEM; } @@ -77,7 +77,7 @@ int acp_dsp_block_write(struct snd_sof_dev *sdev, enum snd_sof_fw_blk_type blk_t adata->data_buf = dma_alloc_coherent(&pci->dev, ACP_DEFAULT_DRAM_LENGTH, &adata->dma_addr, - GFP_ATOMIC); + GFP_KERNEL); if (!adata->data_buf) return -ENOMEM; } @@ -90,7 +90,7 @@ int acp_dsp_block_write(struct snd_sof_dev *sdev, enum snd_sof_fw_blk_type blk_t adata->sram_data_buf = dma_alloc_coherent(&pci->dev, ACP_DEFAULT_SRAM_LENGTH, &adata->sram_dma_addr, - GFP_ATOMIC); + GFP_KERNEL); if (!adata->sram_data_buf) return -ENOMEM; } -- 2.39.5

3 weeks, 4 days

2
1
0 0

[PATCH v2] kbuild: userprogs: use correct linker when mixing clang and GNU ld

by Thomas Weißschuh

The userprogs infrastructure does not expect clang being used with GNU ld and in that case uses /usr/bin/ld for linking, not the configured $(LD). This fallback is problematic as it will break when cross-compiling. Mixing clang and GNU ld is used for example when building for SPARC64, as ld.lld is not sufficient; see Documentation/kbuild/llvm.rst. Relax the check around --ld-path so it gets used for all linkers. Fixes: dfc1b168a8c4 ("kbuild: userprogs: use correct lld when linking through clang") Cc: stable(a)vger.kernel.org Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> Reviewed-by: Nathan Chancellor <nathan(a)kernel.org> --- Changes in v2: - Use plain ifdef instead of ifneq - Rebase onto v6.16 - Pick up review tag from Nathan - Link to v1: https://lore.kernel.org/r/20250724-userprogs-clang-gnu-ld-v1-1-3d3d071e53a7… --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 478f2004602da03c9039044e3288f24a13833cc7..7d24245d118c0e903119263b871d2e5c2759f48a 100644 --- a/Makefile +++ b/Makefile @@ -1134,7 +1134,7 @@ KBUILD_USERCFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS)) # userspace programs are linked via the compiler, use the correct linker -ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_LD_IS_LLD),yy) +ifdef CONFIG_CC_IS_CLANG KBUILD_USERLDFLAGS += --ld-path=$(LD) endif --- base-commit: 038d61fd642278bab63ee8ef722c50d10ab01e8f change-id: 20250723-userprogs-clang-gnu-ld-7a1c16fc852d Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

3 weeks, 4 days

2
1
0 0

[PATCH v2 0/2] scsi: ufs: core: interrupt handling optimisations

by André Draszik

UFS performance for < v4 controllers has reduced quite a bit in 6.16. This series addresses this regression and brings numbers more or less back to the previous level. See patch 2 for some benchmark (fio) results. Signed-off-by: André Draszik <andre.draszik(a)linaro.org> --- Changes in v2: - patch 1: new patch as suggested by Bart during v1 review - patch 2: update commit message and some inline & kerneldoc comments - patch 2: add missing jiffies.h include - Link to v1: https://lore.kernel.org/r/20250724-ufshcd-hardirq-v1-1-6398a52f8f02@linaro.… --- André Draszik (2): scsi: ufs: core: complete polled requests also from interrupt context scsi: ufs: core: move some irq handling back to hardirq (with time limit) drivers/ufs/core/ufshcd.c | 211 +++++++++++++++++++++++++++++++++------------- 1 file changed, 152 insertions(+), 59 deletions(-) --- base-commit: 58ba80c4740212c29a1cf9b48f588e60a7612209 change-id: 20250723-ufshcd-hardirq-c7326f642e56 Best regards, -- André Draszik <andre.draszik(a)linaro.org>

3 weeks, 4 days

3
7
0 0

[PATCH] media: rc: fix races with imon_disconnect()

by Larshin Sergey

Syzbot reports a KASAN issue as below: BUG: KASAN: use-after-free in __create_pipe include/linux/usb.h:1945 [inline] BUG: KASAN: use-after-free in send_packet+0xa2d/0xbc0 drivers/media/rc/imon.c:627 Read of size 4 at addr ffff8880256fb000 by task syz-executor314/4465 CPU: 2 PID: 4465 Comm: syz-executor314 Not tainted 6.0.0-rc1-syzkaller #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.14.0-2 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:317 [inline] print_report.cold+0x2ba/0x6e9 mm/kasan/report.c:433 kasan_report+0xb1/0x1e0 mm/kasan/report.c:495 __create_pipe include/linux/usb.h:1945 [inline] send_packet+0xa2d/0xbc0 drivers/media/rc/imon.c:627 vfd_write+0x2d9/0x550 drivers/media/rc/imon.c:991 vfs_write+0x2d7/0xdd0 fs/read_write.c:576 ksys_write+0x127/0x250 fs/read_write.c:631 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+0x63/0xcd The iMON driver improperly releases the usb_device reference in imon_disconnect without coordinating with active users of the device. Specifically, the fields usbdev_intf0 and usbdev_intf1 are not protected by the users counter (ictx->users). During probe, imon_init_intf0 or imon_init_intf1 increments the usb_device reference count depending on the interface. However, during disconnect, usb_put_dev is called unconditionally, regardless of actual usage. As a result, if vfd_write or other operations are still in progress after disconnect, this can lead to a use-after-free of the usb_device pointer. Thread 1 vfd_write Thread 2 imon_disconnect ... if usb_put_dev(ictx->usbdev_intf0) else usb_put_dev(ictx->usbdev_intf1) ... while send_packet if pipe = usb_sndintpipe( ictx->usbdev_intf0) UAF else pipe = usb_sndctrlpipe( ictx->usbdev_intf0, 0) UAF Guard access to usbdev_intf0 and usbdev_intf1 after disconnect by checking ictx->disconnected in all writer paths. Add early return with -ENODEV in send_packet(), vfd_write(), lcd_write() and display_open() if the device is no longer present. Set and read ictx->disconnected under ictx->lock to ensure memory synchronization. Acquire the lock in imon_disconnect() before setting the flag to synchronize with any ongoing operations. Ensure writers exit early and safely after disconnect before the USB core proceeds with cleanup. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Reported-by: syzbot+f1a69784f6efe748c3bf(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=f1a69784f6efe748c3bf Fixes: 21677cfc562a ("V4L/DVB: ir-core: add imon driver") Cc: stable(a)vger.kernel.org Signed-off-by: Larshin Sergey <Sergey.Larshin(a)kaspersky.com> --- drivers/media/rc/imon.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c index f5221b018808..cf3e6e43c0c7 100644 --- a/drivers/media/rc/imon.c +++ b/drivers/media/rc/imon.c @@ -536,7 +536,9 @@ static int display_open(struct inode *inode, struct file *file) mutex_lock(&ictx->lock); - if (!ictx->display_supported) { + if (ictx->disconnected) { + retval = -ENODEV; + } else if (!ictx->display_supported) { pr_err("display not supported by device\n"); retval = -ENODEV; } else if (ictx->display_isopen) { @@ -598,6 +600,9 @@ static int send_packet(struct imon_context *ictx) int retval = 0; struct usb_ctrlrequest *control_req = NULL; + if (ictx->disconnected) + return -ENODEV; + /* Check if we need to use control or interrupt urb */ if (!ictx->tx_control) { pipe = usb_sndintpipe(ictx->usbdev_intf0, @@ -949,12 +954,14 @@ static ssize_t vfd_write(struct file *file, const char __user *buf, static const unsigned char vfd_packet6[] = { 0x01, 0x00, 0x00, 0x00, 0x00, 0xFF, 0xFF }; - if (ictx->disconnected) - return -ENODEV; - if (mutex_lock_interruptible(&ictx->lock)) return -ERESTARTSYS; + if (ictx->disconnected) { + retval = -ENODEV; + goto exit; + } + if (!ictx->dev_present_intf0) { pr_err_ratelimited("no iMON device present\n"); retval = -ENODEV; @@ -1029,11 +1036,13 @@ static ssize_t lcd_write(struct file *file, const char __user *buf, int retval = 0; struct imon_context *ictx = file->private_data; - if (ictx->disconnected) - return -ENODEV; - mutex_lock(&ictx->lock); + if (ictx->disconnected) { + retval = -ENODEV; + goto exit; + } + if (!ictx->display_supported) { pr_err_ratelimited("no iMON display present\n"); retval = -ENODEV; @@ -2499,7 +2508,11 @@ static void imon_disconnect(struct usb_interface *interface) int ifnum; ictx = usb_get_intfdata(interface); + + mutex_lock(&ictx->lock); ictx->disconnected = true; + mutex_unlock(&ictx->lock); + dev = ictx->dev; ifnum = interface->cur_altsetting->desc.bInterfaceNumber; -- 2.39.5

3 weeks, 4 days

1
0
0 0

FAILED: patch "[PATCH] tools/hv: fcopy: Fix irregularities with size of ring buffer" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x a4131a50d072b369bfed0b41e741c41fd8048641 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025072131-stage-bundle-b616@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a4131a50d072b369bfed0b41e741c41fd8048641 Mon Sep 17 00:00:00 2001 From: Naman Jain <namjain(a)linux.microsoft.com> Date: Fri, 11 Jul 2025 11:38:46 +0530 Subject: [PATCH] tools/hv: fcopy: Fix irregularities with size of ring buffer Size of ring buffer, as defined in uio_hv_generic driver, is no longer fixed to 16 KB. This creates a problem in fcopy, since this size was hardcoded. With the change in place to make ring sysfs node actually reflect the size of underlying ring buffer, it is safe to get the size of ring sysfs file and use it for ring buffer size in fcopy daemon. Fix the issue of disparity in ring buffer size, by making it dynamic in fcopy uio daemon. Cc: stable(a)vger.kernel.org Fixes: 0315fef2aff9 ("uio_hv_generic: Align ring size to system page") Signed-off-by: Naman Jain <namjain(a)linux.microsoft.com> Reviewed-by: Saurabh Sengar <ssengar(a)linux.microsoft.com> Reviewed-by: Long Li <longli(a)microsoft.com> Link: https://lore.kernel.org/r/20250711060846.9168-1-namjain@linux.microsoft.com Signed-off-by: Wei Liu <wei.liu(a)kernel.org> Message-ID: <20250711060846.9168-1-namjain(a)linux.microsoft.com> diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c index 4b09ed6b637a..92e8307b2a46 100644 --- a/tools/hv/hv_fcopy_uio_daemon.c +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -35,7 +35,10 @@ #define WIN8_SRV_MINOR 1 #define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) -#define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio" +#define FCOPY_DEVICE_PATH(subdir) \ + "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/" #subdir +#define FCOPY_UIO_PATH FCOPY_DEVICE_PATH(uio) +#define FCOPY_CHANNELS_PATH FCOPY_DEVICE_PATH(channels) #define FCOPY_VER_COUNT 1 static const int fcopy_versions[] = { @@ -47,9 +50,62 @@ static const int fw_versions[] = { UTIL_FW_VERSION }; -#define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */ +static uint32_t get_ring_buffer_size(void) +{ + char ring_path[PATH_MAX]; + DIR *dir; + struct dirent *entry; + struct stat st; + uint32_t ring_size = 0; + int retry_count = 0; -static unsigned char desc[HV_RING_SIZE]; + /* Find the channel directory */ + dir = opendir(FCOPY_CHANNELS_PATH); + if (!dir) { + usleep(100 * 1000); /* Avoid race with kernel, wait 100ms and retry once */ + dir = opendir(FCOPY_CHANNELS_PATH); + if (!dir) { + syslog(LOG_ERR, "Failed to open channels directory: %s", strerror(errno)); + return 0; + } + } + +retry_once: + while ((entry = readdir(dir)) != NULL) { + if (entry->d_type == DT_DIR && strcmp(entry->d_name, ".") != 0 && + strcmp(entry->d_name, "..") != 0) { + snprintf(ring_path, sizeof(ring_path), "%s/%s/ring", + FCOPY_CHANNELS_PATH, entry->d_name); + + if (stat(ring_path, &st) == 0) { + /* + * stat returns size of Tx, Rx rings combined, + * so take half of it for individual ring size. + */ + ring_size = (uint32_t)st.st_size / 2; + syslog(LOG_INFO, "Ring buffer size from %s: %u bytes", + ring_path, ring_size); + break; + } + } + } + + if (!ring_size && retry_count == 0) { + retry_count = 1; + rewinddir(dir); + usleep(100 * 1000); /* Wait 100ms and retry once */ + goto retry_once; + } + + closedir(dir); + + if (!ring_size) + syslog(LOG_ERR, "Could not determine ring size"); + + return ring_size; +} + +static unsigned char *desc; static int target_fd; static char target_fname[PATH_MAX]; @@ -397,7 +453,7 @@ int main(int argc, char *argv[]) int daemonize = 1, long_index = 0, opt, ret = -EINVAL; struct vmbus_br txbr, rxbr; void *ring; - uint32_t len = HV_RING_SIZE; + uint32_t ring_size, len; char uio_name[NAME_MAX] = {0}; char uio_dev_path[PATH_MAX] = {0}; @@ -428,7 +484,20 @@ int main(int argc, char *argv[]) openlog("HV_UIO_FCOPY", 0, LOG_USER); syslog(LOG_INFO, "starting; pid is:%d", getpid()); - fcopy_get_first_folder(FCOPY_UIO, uio_name); + ring_size = get_ring_buffer_size(); + if (!ring_size) { + ret = -ENODEV; + goto exit; + } + + desc = malloc(ring_size * sizeof(unsigned char)); + if (!desc) { + syslog(LOG_ERR, "malloc failed for desc buffer"); + ret = -ENOMEM; + goto exit; + } + + fcopy_get_first_folder(FCOPY_UIO_PATH, uio_name); snprintf(uio_dev_path, sizeof(uio_dev_path), "/dev/%s", uio_name); fcopy_fd = open(uio_dev_path, O_RDWR); @@ -436,17 +505,17 @@ int main(int argc, char *argv[]) syslog(LOG_ERR, "open %s failed; error: %d %s", uio_dev_path, errno, strerror(errno)); ret = fcopy_fd; - goto exit; + goto free_desc; } - ring = vmbus_uio_map(&fcopy_fd, HV_RING_SIZE); + ring = vmbus_uio_map(&fcopy_fd, ring_size); if (!ring) { ret = errno; syslog(LOG_ERR, "mmap ringbuffer failed; error: %d %s", ret, strerror(ret)); goto close; } - vmbus_br_setup(&txbr, ring, HV_RING_SIZE); - vmbus_br_setup(&rxbr, (char *)ring + HV_RING_SIZE, HV_RING_SIZE); + vmbus_br_setup(&txbr, ring, ring_size); + vmbus_br_setup(&rxbr, (char *)ring + ring_size, ring_size); rxbr.vbr->imask = 0; @@ -463,7 +532,7 @@ int main(int argc, char *argv[]) goto close; } - len = HV_RING_SIZE; + len = ring_size; ret = rte_vmbus_chan_recv_raw(&rxbr, desc, &len); if (unlikely(ret <= 0)) { /* This indicates a failure to communicate (or worse) */ @@ -483,6 +552,8 @@ int main(int argc, char *argv[]) } close: close(fcopy_fd); +free_desc: + free(desc); exit: return ret; }

3 weeks, 4 days

2
1
0 0

[PATCH v3 mm-hotfixes 2/5] mm: introduce and use {pgd,p4d}_populate_kernel()

by Harry Yoo

Introduce and use {pgd,p4d}_populate_kernel() in core MM code when populating PGD and P4D entries for the kernel address space. These helpers ensure proper synchronization of page tables when updating the kernel portion of top-level page tables. Until now, the kernel has relied on each architecture to handle synchronization of top-level page tables in an ad-hoc manner. For example, see commit 9b861528a801 ("x86-64, mem: Update all PGDs for direct mapping and vmemmap mapping changes"). However, this approach has proven fragile for following reasons: 1) It is easy to forget to perform the necessary page table synchronization when introducing new changes. For instance, commit 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps") overlooked the need to synchronize page tables for the vmemmap area. 2) It is also easy to overlook that the vmemmap and direct mapping areas must not be accessed before explicit page table synchronization. For example, commit 8d400913c231 ("x86/vmemmap: handle unpopulated sub-pmd ranges")) caused crashes by accessing the vmemmap area before calling sync_global_pgds(). To address this, as suggested by Dave Hansen, introduce _kernel() variants of the page table population helpers, which invoke architecture-specific hooks to properly synchronize page tables. They reuse existing infrastructure for vmalloc and ioremap. Synchronization requirements are determined by ARCH_PAGE_TABLE_SYNC_MASK, and the actual synchronization is performed by arch_sync_kernel_mappings(). This change currently targets only x86_64, so only PGD and P4D level helpers are introduced. In theory, PUD and PMD level helpers can be added later if needed by other architectures. Currently this is a no-op, since no architecture sets PGTBL_{PGD,P4D}_MODIFIED in ARCH_PAGE_TABLE_SYNC_MASK. Cc: stable(a)vger.kernel.org Suggested-by: Dave Hansen <dave.hansen(a)linux.intel.com> Signed-off-by: Harry Yoo <harry.yoo(a)oracle.com> --- include/asm-generic/pgalloc.h | 16 ++++++++++++++++ include/linux/pgtable.h | 4 ++-- mm/kasan/init.c | 10 +++++----- mm/percpu.c | 4 ++-- mm/sparse-vmemmap.c | 4 ++-- 5 files changed, 27 insertions(+), 11 deletions(-) diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index 3c8ec3bfea44..fc0ab8eed5a6 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -4,6 +4,8 @@ #ifdef CONFIG_MMU +#include <linux/pgtable.h> + #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) @@ -296,6 +298,20 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) } #endif +#define pgd_populate_kernel(addr, pgd, p4d) \ +do { \ + pgd_populate(&init_mm, pgd, p4d); \ + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED) \ + arch_sync_kernel_mappings(addr, addr); \ +} while (0) + +#define p4d_populate_kernel(addr, p4d, pud) \ +do { \ + p4d_populate(&init_mm, p4d, pud); \ + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_P4D_MODIFIED) \ + arch_sync_kernel_mappings(addr, addr); \ +} while (0) + #endif /* CONFIG_MMU */ #endif /* __ASM_GENERIC_PGALLOC_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e564f338c758..2e24514ab6d0 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1332,8 +1332,8 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values - * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() - * needs to be called. + * and let generic vmalloc, ioremap and page table update code know when + * arch_sync_kernel_mappings() needs to be called. */ #ifndef ARCH_PAGE_TABLE_SYNC_MASK #define ARCH_PAGE_TABLE_SYNC_MASK 0 diff --git a/mm/kasan/init.c b/mm/kasan/init.c index ced6b29fcf76..43de820ee282 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -191,7 +191,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, pud_t *pud; pmd_t *pmd; - p4d_populate(&init_mm, p4d, + p4d_populate_kernel(addr, p4d, lm_alias(kasan_early_shadow_pud)); pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, @@ -212,7 +212,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, } else { p = early_alloc(PAGE_SIZE, NUMA_NO_NODE); pud_init(p); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } } zero_pud_populate(p4d, addr, next); @@ -251,10 +251,10 @@ int __ref kasan_populate_early_shadow(const void *shadow_start, * puds,pmds, so pgd_populate(), pud_populate() * is noops. */ - pgd_populate(&init_mm, pgd, + pgd_populate_kernel(addr, pgd, lm_alias(kasan_early_shadow_p4d)); p4d = p4d_offset(pgd, addr); - p4d_populate(&init_mm, p4d, + p4d_populate_kernel(addr, p4d, lm_alias(kasan_early_shadow_pud)); pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, @@ -273,7 +273,7 @@ int __ref kasan_populate_early_shadow(const void *shadow_start, if (!p) return -ENOMEM; } else { - pgd_populate(&init_mm, pgd, + pgd_populate_kernel(addr, pgd, early_alloc(PAGE_SIZE, NUMA_NO_NODE)); } } diff --git a/mm/percpu.c b/mm/percpu.c index b35494c8ede2..1615dc3b3af5 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -3134,13 +3134,13 @@ void __init __weak pcpu_populate_pte(unsigned long addr) if (pgd_none(*pgd)) { p4d = memblock_alloc_or_panic(P4D_TABLE_SIZE, P4D_TABLE_SIZE); - pgd_populate(&init_mm, pgd, p4d); + pgd_populate_kernel(addr, pgd, p4d); } p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { pud = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE); - p4d_populate(&init_mm, p4d, pud); + p4d_populate_kernel(addr, p4d, pud); } pud = pud_offset(p4d, addr); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index fd2ab5118e13..e275310ac708 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -229,7 +229,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) if (!p) return NULL; pud_init(p); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } return p4d; } @@ -241,7 +241,7 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); if (!p) return NULL; - pgd_populate(&init_mm, pgd, p); + pgd_populate_kernel(addr, pgd, p); } return pgd; } -- 2.43.0

3 weeks, 4 days

1
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2025