From f61ae5f525bf55f7ad87777963d0ecaf130cfd12 Mon Sep 17 00:00:00 2001 From: Nathan Rebello Date: Tue, 7 Apr 2026 02:39:58 -0400 Subject: [PATCH 01/85] usb: typec: ucsi: skip connector validation before init commit 5a1140404cbf7ba40137dfb1fb96893aa9a67d68 upstream. Notifications can arrive before ucsi_init() has populated ucsi->cap.num_connectors via GET_CAPABILITY. At that point num_connectors is still 0, causing all valid connector numbers to be incorrectly rejected as bogus. Skip the bounds check when num_connectors is 0 (not yet initialized). Pre-init notifications are already handled safely by the early-event guard in ucsi_connector_change(). Reported-by: Takashi Iwai Fixes: d2d8c17ac01a ("usb: typec: ucsi: validate connector number in ucsi_notify_common()") Cc: stable@vger.kernel.org Signed-off-by: Nathan Rebello Tested-by: Takashi Iwai Link: https://patch.msgid.link/20260407063958.863-1-nathan.c.rebello@gmail.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit f4786c34216a702d108e53fc890bd21e547aabc9) Signed-off-by: Wentao Guan --- drivers/usb/typec/ucsi/ucsi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 31c809eeac40..47f9a8046109 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -43,7 +43,8 @@ void ucsi_notify_common(struct ucsi *ucsi, u32 cci) return; if (UCSI_CCI_CONNECTOR(cci)) { - if (UCSI_CCI_CONNECTOR(cci) <= ucsi->cap.num_connectors) + if (!ucsi->cap.num_connectors || + UCSI_CCI_CONNECTOR(cci) <= ucsi->cap.num_connectors) ucsi_connector_change(ucsi, UCSI_CCI_CONNECTOR(cci)); else dev_err(ucsi->dev, "bogus connector number in CCI: %lu\n", From e59d75a958c8fce088fb5eee8d449f976abfdd4f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 27 Mar 2026 12:32:19 +0100 Subject: [PATCH 02/85] wifi: rt2x00usb: fix devres lifetime commit 25369b22223d1c56e42a0cd4ac9137349d5a898e upstream. USB drivers bind to USB interfaces and any device managed resources should have their lifetime tied to the interface rather than parent USB device. This avoids issues like memory leaks when drivers are unbound without their devices being physically disconnected (e.g. on probe deferral or configuration changes). Fix the USB anchor lifetime so that it is released on driver unbind. Fixes: 8b4c0009313f ("rt2x00usb: Use usb anchor to manage URB") Cc: stable@vger.kernel.org # 4.7 Cc: Vishal Thanki Signed-off-by: Johan Hovold Acked-by: Stanislaw Gruszka Reviewed-by: Greg Kroah-Hartman Link: https://patch.msgid.link/20260327113219.1313748-1-johan@kernel.org Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman (cherry picked from commit e360d15fcb1e819eef49e3d4434d8050542eed16) Signed-off-by: Wentao Guan --- drivers/net/wireless/ralink/rt2x00/rt2x00usb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c index a6d50149e0c3..1275bd8232d2 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c @@ -828,7 +828,7 @@ int rt2x00usb_probe(struct usb_interface *usb_intf, if (retval) goto exit_free_device; - rt2x00dev->anchor = devm_kmalloc(&usb_dev->dev, + rt2x00dev->anchor = devm_kmalloc(&usb_intf->dev, sizeof(struct usb_anchor), GFP_KERNEL); if (!rt2x00dev->anchor) { From 3cc63c9bd02a9e145d529c13dae075be8e00e501 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 6 Apr 2026 17:34:22 +0200 Subject: [PATCH 03/85] xfrm_user: fix info leak in build_report() commit d10119968d0e1f2b669604baf2a8b5fdb72fa6b4 upstream. struct xfrm_user_report is a __u8 proto field followed by a struct xfrm_selector which means there is three "empty" bytes of padding, but the padding is never zeroed before copying to userspace. Fix that up by zeroing the structure before setting individual member variables. Cc: stable Cc: Steffen Klassert Cc: Herbert Xu Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Simon Horman Assisted-by: gregkh_clanker_t1000 Signed-off-by: Greg Kroah-Hartman Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 6c55714c931051cd7f4839c19ce0867179fd22fe) Signed-off-by: Wentao Guan --- net/xfrm/xfrm_user.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4dd8341225bc..c44bc4bf4cdf 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -4108,6 +4108,7 @@ static int build_report(struct sk_buff *skb, u8 proto, return -EMSGSIZE; ur = nlmsg_data(nlh); + memset(ur, 0, sizeof(*ur)); ur->proto = proto; memcpy(&ur->sel, sel, sizeof(ur->sel)); From 50435857278e2e5a5fefc5e974f2b4ab31b0ef7d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 30 Mar 2026 11:14:13 +0200 Subject: [PATCH 04/85] net: rfkill: prevent unlimited numbers of rfkill events from being created commit ea245d78dec594372e27d8c79616baf49e98a4a1 upstream. Userspace can create an unlimited number of rfkill events if the system is so configured, while not consuming them from the rfkill file descriptor, causing a potential out of memory situation. Prevent this from bounding the number of pending rfkill events at a "large" number (i.e. 1000) to prevent abuses like this. Cc: Johannes Berg Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Cc: stable Signed-off-by: Greg Kroah-Hartman Link: https://patch.msgid.link/2026033013-disfigure-scroll-e25e@gregkh Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman (cherry picked from commit a8c26800e0220e1550af012f5a20e50f5c78864d) Signed-off-by: Wentao Guan --- net/rfkill/core.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 7d3e82e4c2fc..868a8586dc17 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -73,11 +73,14 @@ struct rfkill_int_event { struct rfkill_event_ext ev; }; +/* Max rfkill events that can be "in-flight" for one data source */ +#define MAX_RFKILL_EVENT 1000 struct rfkill_data { struct list_head list; struct list_head events; struct mutex mtx; wait_queue_head_t read_wait; + u32 event_count; bool input_handler; u8 max_size; }; @@ -255,10 +258,12 @@ static void rfkill_global_led_trigger_unregister(void) } #endif /* CONFIG_RFKILL_LEDS */ -static void rfkill_fill_event(struct rfkill_event_ext *ev, - struct rfkill *rfkill, - enum rfkill_operation op) +static int rfkill_fill_event(struct rfkill_int_event *int_ev, + struct rfkill *rfkill, + struct rfkill_data *data, + enum rfkill_operation op) { + struct rfkill_event_ext *ev = &int_ev->ev; unsigned long flags; ev->idx = rfkill->idx; @@ -271,6 +276,15 @@ static void rfkill_fill_event(struct rfkill_event_ext *ev, RFKILL_BLOCK_SW_PREV)); ev->hard_block_reasons = rfkill->hard_block_reasons; spin_unlock_irqrestore(&rfkill->lock, flags); + + scoped_guard(mutex, &data->mtx) { + if (data->event_count++ > MAX_RFKILL_EVENT) { + data->event_count--; + return -ENOSPC; + } + list_add_tail(&int_ev->list, &data->events); + } + return 0; } static void rfkill_send_events(struct rfkill *rfkill, enum rfkill_operation op) @@ -282,10 +296,10 @@ static void rfkill_send_events(struct rfkill *rfkill, enum rfkill_operation op) ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) continue; - rfkill_fill_event(&ev->ev, rfkill, op); - mutex_lock(&data->mtx); - list_add_tail(&ev->list, &data->events); - mutex_unlock(&data->mtx); + if (rfkill_fill_event(ev, rfkill, data, op)) { + kfree(ev); + continue; + } wake_up_interruptible(&data->read_wait); } } @@ -1186,10 +1200,8 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) if (!ev) goto free; rfkill_sync(rfkill); - rfkill_fill_event(&ev->ev, rfkill, RFKILL_OP_ADD); - mutex_lock(&data->mtx); - list_add_tail(&ev->list, &data->events); - mutex_unlock(&data->mtx); + if (rfkill_fill_event(ev, rfkill, data, RFKILL_OP_ADD)) + kfree(ev); } list_add(&data->list, &rfkill_fds); mutex_unlock(&rfkill_global_mutex); @@ -1259,6 +1271,7 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf, ret = -EFAULT; list_del(&ev->list); + data->event_count--; kfree(ev); out: mutex_unlock(&data->mtx); From 641de1a257aeb95721dde89c9f94768807b22356 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 7 Apr 2026 14:33:17 +0200 Subject: [PATCH 05/85] Revert "ALSA: hda/realtek: Add quirk for Gigabyte Technology to fix headphone" commit 8508e9118649f13f7b857e9e10147b241db615d7 upstream. This reverts commit 56fbbe096a89ff4b52af78a21a4afd9d94bdcc80. It caused regressions on other Gigabyte models, and looking at the bugzilla entry again, the suggested change appears rather dubious, as incorrectly setting the front mic pin as the headphone. Fixes: 56fbbe096a89 ("ALSA: hda/realtek: Add quirk for Gigabyte Technology to fix headphone") Cc: Reported-by: Marcin Krycki Reported-by: Theodoros Orfanidis Closes: https://lore.kernel.org/CAEfRphPU_ABuVFzaHhspxgp2WAqi7kKNGo4yOOt0zeVFPSj8+Q@mail.gmail.com Link: https://patch.msgid.link/20260407123333.171130-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 130c991e6aad032f8c1449afa97dcdde91e722fb) Signed-off-by: Wentao Guan --- sound/hda/codecs/realtek/alc662.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/sound/hda/codecs/realtek/alc662.c b/sound/hda/codecs/realtek/alc662.c index 3a943adf9087..5073165d1f3c 100644 --- a/sound/hda/codecs/realtek/alc662.c +++ b/sound/hda/codecs/realtek/alc662.c @@ -313,7 +313,6 @@ enum { ALC897_FIXUP_HEADSET_MIC_PIN2, ALC897_FIXUP_UNIS_H3C_X500S, ALC897_FIXUP_HEADSET_MIC_PIN3, - ALC897_FIXUP_H610M_HP_PIN, }; static const struct hda_fixup alc662_fixups[] = { @@ -767,13 +766,6 @@ static const struct hda_fixup alc662_fixups[] = { { } }, }, - [ALC897_FIXUP_H610M_HP_PIN] = { - .type = HDA_FIXUP_PINS, - .v.pins = (const struct hda_pintbl[]) { - { 0x19, 0x0321403f }, /* HP out */ - { } - }, - }, }; static const struct hda_quirk alc662_fixup_tbl[] = { @@ -823,7 +815,6 @@ static const struct hda_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT), SND_PCI_QUIRK(0x105b, 0x0cd6, "Foxconn", ALC662_FIXUP_ASUS_MODE2), SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD), - SND_PCI_QUIRK(0x1458, 0xa194, "H610M H V2 DDR4", ALC897_FIXUP_H610M_HP_PIN), SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS), SND_PCI_QUIRK(0x17aa, 0x1057, "Lenovo P360", ALC897_FIXUP_HEADSET_MIC_PIN), From b87f52572fabe72daf8069a9527f685fbe3e4a84 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Tue, 7 Apr 2026 10:41:41 +0200 Subject: [PATCH 06/85] Revert "mptcp: add needs_id for netlink appending addr" commit 8e2760eaab778494fc1fa257031e0e1799647f46 upstream. This commit was originally adding the ability to add MPTCP endpoints with ID 0 by accident. The in-kernel PM, handling MPTCP endpoints at the net namespace level, is not supposed to handle endpoints with such ID, because this ID 0 is reserved to the initial subflow, as mentioned in the MPTCPv1 protocol [1], a per-connection setting. Note that 'ip mptcp endpoint add id 0' stops early with an error, but other tools might still request the in-kernel PM to create MPTCP endpoints with this restricted ID 0. In other words, it was wrong to call the mptcp_pm_has_addr_attr_id helper to check whether the address ID attribute is set: if it was set to 0, a new MPTCP endpoint would be created with ID 0, which is not expected, and might cause various issues later. Fixes: 584f38942626 ("mptcp: add needs_id for netlink appending addr") Cc: stable@vger.kernel.org Link: https://datatracker.ietf.org/doc/html/rfc8684#section-3.2-9 [1] Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260407-net-mptcp-revert-pm-needs-id-v2-1-7a25cbc324f8@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 96a95b6d9e6dca5d338e58991e02e9c1efdaf2fe) Signed-off-by: Wentao Guan --- net/mptcp/pm_kernel.c | 24 +++++------------------- 1 file changed, 5 insertions(+), 19 deletions(-) diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index 52d15df12f58..4494cf4c3828 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -710,7 +710,7 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, struct mptcp_pm_addr_entry *entry, - bool needs_id, bool replace) + bool replace) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; int ret = -EINVAL; @@ -769,7 +769,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id && needs_id) { + if (!entry->addr.id) { find_next: entry->addr.id = find_next_zero_bit(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, @@ -780,7 +780,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id && needs_id) + if (!entry->addr.id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); @@ -909,7 +909,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, return -ENOMEM; entry->addr.port = 0; - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, false); if (ret < 0) kfree(entry); @@ -963,18 +963,6 @@ static int mptcp_nl_add_subflow_or_signal_addr(struct net *net, return 0; } -static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr, - struct genl_info *info) -{ - struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; - - if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, - mptcp_pm_address_nl_policy, info->extack) && - tb[MPTCP_PM_ADDR_ATTR_ID]) - return true; - return false; -} - /* Add an MPTCP endpoint */ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) { @@ -1023,9 +1011,7 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) goto out_free; } } - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, - !mptcp_pm_has_addr_attr_id(attr, info), - true); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true); if (ret < 0) { GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret); goto out_free; From 694981e3a914b761258df439bc4f117568f2087b Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Mon, 6 Apr 2026 11:15:10 +0800 Subject: [PATCH 07/85] mptcp: fix slab-use-after-free in __inet_lookup_established commit 9b55b253907e7431210483519c5ad711a37dafa1 upstream. The ehash table lookups are lockless and rely on SLAB_TYPESAFE_BY_RCU to guarantee socket memory stability during RCU read-side critical sections. Both tcp_prot and tcpv6_prot have their slab caches created with this flag via proto_register(). However, MPTCP's mptcp_subflow_init() copies tcpv6_prot into tcpv6_prot_override during inet_init() (fs_initcall, level 5), before inet6_init() (module_init/device_initcall, level 6) has called proto_register(&tcpv6_prot). At that point, tcpv6_prot.slab is still NULL, so tcpv6_prot_override.slab remains NULL permanently. This causes MPTCP v6 subflow child sockets to be allocated via kmalloc (falling into kmalloc-4k) instead of the TCPv6 slab cache. The kmalloc-4k cache lacks SLAB_TYPESAFE_BY_RCU, so when these sockets are freed without SOCK_RCU_FREE (which is cleared for child sockets by design), the memory can be immediately reused. Concurrent ehash lookups under rcu_read_lock can then access freed memory, triggering a slab-use-after-free in __inet_lookup_established. Fix this by splitting the IPv6-specific initialization out of mptcp_subflow_init() into a new mptcp_subflow_v6_init(), called from mptcp_proto_v6_init() before protocol registration. This ensures tcpv6_prot_override.slab correctly inherits the SLAB_TYPESAFE_BY_RCU slab cache. Fixes: b19bc2945b40 ("mptcp: implement delegated actions") Cc: stable@vger.kernel.org Signed-off-by: Jiayuan Chen Reviewed-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260406031512.189159-1-jiayuan.chen@linux.dev Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 15fa9ead4d5e6b6b9c794e84144146c917f2cb62) Signed-off-by: Wentao Guan --- net/mptcp/protocol.c | 2 ++ net/mptcp/protocol.h | 1 + net/mptcp/subflow.c | 15 +++++++++------ 3 files changed, 12 insertions(+), 6 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7b92da6e49d6..09e1a93b7daa 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -4271,6 +4271,8 @@ int __init mptcp_proto_v6_init(void) { int err; + mptcp_subflow_v6_init(); + mptcp_v6_prot = mptcp_prot; strscpy(mptcp_v6_prot.name, "MPTCPv6", sizeof(mptcp_v6_prot.name)); mptcp_v6_prot.slab = NULL; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 27b1698c5aa2..5a03c8824ab6 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -830,6 +830,7 @@ static inline void mptcp_subflow_tcp_fallback(struct sock *sk, void __init mptcp_proto_init(void); #if IS_ENABLED(CONFIG_MPTCP_IPV6) int __init mptcp_proto_v6_init(void); +void __init mptcp_subflow_v6_init(void); #endif struct sock *mptcp_sk_clone_init(const struct sock *sk, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 838203e2740e..90927f6cad26 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -2145,7 +2145,15 @@ void __init mptcp_subflow_init(void) tcp_prot_override.psock_update_sk_prot = NULL; #endif + mptcp_diag_subflow_init(&subflow_ulp_ops); + + if (tcp_register_ulp(&subflow_ulp_ops) != 0) + panic("MPTCP: failed to register subflows to ULP\n"); +} + #if IS_ENABLED(CONFIG_MPTCP_IPV6) +void __init mptcp_subflow_v6_init(void) +{ /* In struct mptcp_subflow_request_sock, we assume the TCP request sock * structures for v4 and v6 have the same size. It should not changed in * the future but better to make sure to be warned if it is no longer @@ -2184,10 +2192,5 @@ void __init mptcp_subflow_init(void) /* Disable sockmap processing for subflows */ tcpv6_prot_override.psock_update_sk_prot = NULL; #endif -#endif - - mptcp_diag_subflow_init(&subflow_ulp_ops); - - if (tcp_register_ulp(&subflow_ulp_ops) != 0) - panic("MPTCP: failed to register subflows to ULP\n"); } +#endif From 2c2070f8f6bb0a40cc86c9941520a29d95258c4c Mon Sep 17 00:00:00 2001 From: Andrea Mayer Date: Sat, 4 Apr 2026 02:44:04 +0200 Subject: [PATCH 08/85] seg6: separate dst_cache for input and output paths in seg6 lwtunnel commit c3812651b522fe8437ebb7063b75ddb95b571643 upstream. The seg6 lwtunnel uses a single dst_cache per encap route, shared between seg6_input_core() and seg6_output_core(). These two paths can perform the post-encap SID lookup in different routing contexts (e.g., ip rules matching on the ingress interface, or VRF table separation). Whichever path runs first populates the cache, and the other reuses it blindly, bypassing its own lookup. Fix this by splitting the cache into cache_input and cache_output, so each path maintains its own cached dst independently. Fixes: 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels") Cc: stable@vger.kernel.org Signed-off-by: Andrea Mayer Reviewed-by: Nicolas Dichtel Reviewed-by: Justin Iurman Link: https://patch.msgid.link/20260404004405.4057-2-andrea.mayer@uniroma2.it Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit fb56de5d99218de49d5d43ef3a99e062ecd0f9a1) Signed-off-by: Wentao Guan --- net/ipv6/seg6_iptunnel.c | 34 +++++++++++++++++++++++----------- 1 file changed, 23 insertions(+), 11 deletions(-) diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 3e1b9991131a..d6a0f7df9080 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -48,7 +48,8 @@ static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) } struct seg6_lwt { - struct dst_cache cache; + struct dst_cache cache_input; + struct dst_cache cache_output; struct seg6_iptunnel_encap tuninfo[]; }; @@ -488,7 +489,7 @@ static int seg6_input_core(struct net *net, struct sock *sk, slwt = seg6_lwt_lwtunnel(lwtst); local_bh_disable(); - dst = dst_cache_get(&slwt->cache); + dst = dst_cache_get(&slwt->cache_input); local_bh_enable(); err = seg6_do_srh(skb, dst); @@ -504,7 +505,7 @@ static int seg6_input_core(struct net *net, struct sock *sk, /* cache only if we don't create a dst reference loop */ if (!dst->error && lwtst != dst->lwtstate) { local_bh_disable(); - dst_cache_set_ip6(&slwt->cache, dst, + dst_cache_set_ip6(&slwt->cache_input, dst, &ipv6_hdr(skb)->saddr); local_bh_enable(); } @@ -564,7 +565,7 @@ static int seg6_output_core(struct net *net, struct sock *sk, slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); local_bh_disable(); - dst = dst_cache_get(&slwt->cache); + dst = dst_cache_get(&slwt->cache_output); local_bh_enable(); err = seg6_do_srh(skb, dst); @@ -591,7 +592,7 @@ static int seg6_output_core(struct net *net, struct sock *sk, /* cache only if we don't create a dst reference loop */ if (orig_dst->lwtstate != dst->lwtstate) { local_bh_disable(); - dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); + dst_cache_set_ip6(&slwt->cache_output, dst, &fl6.saddr); local_bh_enable(); } @@ -701,11 +702,13 @@ static int seg6_build_state(struct net *net, struct nlattr *nla, slwt = seg6_lwt_lwtunnel(newts); - err = dst_cache_init(&slwt->cache, GFP_ATOMIC); - if (err) { - kfree(newts); - return err; - } + err = dst_cache_init(&slwt->cache_input, GFP_ATOMIC); + if (err) + goto err_free_newts; + + err = dst_cache_init(&slwt->cache_output, GFP_ATOMIC); + if (err) + goto err_destroy_input; memcpy(&slwt->tuninfo, tuninfo, tuninfo_len); @@ -720,11 +723,20 @@ static int seg6_build_state(struct net *net, struct nlattr *nla, *ts = newts; return 0; + +err_destroy_input: + dst_cache_destroy(&slwt->cache_input); +err_free_newts: + kfree(newts); + return err; } static void seg6_destroy_state(struct lwtunnel_state *lwt) { - dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache); + struct seg6_lwt *slwt = seg6_lwt_lwtunnel(lwt); + + dst_cache_destroy(&slwt->cache_input); + dst_cache_destroy(&slwt->cache_output); } static int seg6_fill_encap_info(struct sk_buff *skb, From 81e7d75190240a806a6bbf77503300001504c401 Mon Sep 17 00:00:00 2001 From: Mikhail Gavrilov Date: Tue, 7 Apr 2026 12:50:31 +0500 Subject: [PATCH 09/85] Input: uinput - fix circular locking dependency with ff-core commit 4cda78d6f8bf2b700529f2fbccb994c3e826d7c2 upstream. A lockdep circular locking dependency warning can be triggered reproducibly when using a force-feedback gamepad with uinput (for example, playing ELDEN RING under Wine with a Flydigi Vader 5 controller): ff->mutex -> udev->mutex -> input_mutex -> dev->mutex -> ff->mutex The cycle is caused by four lock acquisition paths: 1. ff upload: input_ff_upload() holds ff->mutex and calls uinput_dev_upload_effect() -> uinput_request_submit() -> uinput_request_send(), which acquires udev->mutex. 2. device create: uinput_ioctl_handler() holds udev->mutex and calls uinput_create_device() -> input_register_device(), which acquires input_mutex. 3. device register: input_register_device() holds input_mutex and calls kbd_connect() -> input_register_handle(), which acquires dev->mutex. 4. evdev release: evdev_release() calls input_flush_device() under dev->mutex, which calls input_ff_flush() acquiring ff->mutex. Fix this by introducing a new state_lock spinlock to protect udev->state and udev->dev access in uinput_request_send() instead of acquiring udev->mutex. The function only needs to atomically check device state and queue an input event into the ring buffer via uinput_dev_event() -- both operations are safe under a spinlock (ktime_get_ts64() and wake_up_interruptible() do not sleep). This breaks the ff->mutex -> udev->mutex link since a spinlock is a leaf in the lock ordering and cannot form cycles with mutexes. To keep state transitions visible to uinput_request_send(), protect writes to udev->state in uinput_create_device() and uinput_destroy_device() with the same state_lock spinlock. Additionally, move init_completion(&request->done) from uinput_request_send() to uinput_request_submit() before uinput_request_reserve_slot(). Once the slot is allocated, uinput_flush_requests() may call complete() on it at any time from the destroy path, so the completion must be initialised before the request becomes visible. Lock ordering after the fix: ff->mutex -> state_lock (spinlock, leaf) udev->mutex -> state_lock (spinlock, leaf) udev->mutex -> input_mutex -> dev->mutex -> ff->mutex (no back-edge) Fixes: ff462551235d ("Input: uinput - switch to the new FF interface") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/CABXGCsMoxag+kEwHhb7KqhuyxfmGGd0P=tHZyb1uKE0pLr8Hkg@mail.gmail.com/ Signed-off-by: Mikhail Gavrilov Link: https://patch.msgid.link/20260407075031.38351-1-mikhail.v.gavrilov@gmail.com Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 1e09dfbb4f5d20ee111f92325a00f85778a5f328) Signed-off-by: Wentao Guan --- drivers/input/misc/uinput.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index 13336a2fd49c..a973e82205b5 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -57,6 +57,7 @@ struct uinput_device { struct input_dev *dev; struct mutex mutex; enum uinput_state state; + spinlock_t state_lock; wait_queue_head_t waitq; unsigned char ready; unsigned char head; @@ -146,19 +147,15 @@ static void uinput_request_release_slot(struct uinput_device *udev, static int uinput_request_send(struct uinput_device *udev, struct uinput_request *request) { - int retval; + int retval = 0; - retval = mutex_lock_interruptible(&udev->mutex); - if (retval) - return retval; + spin_lock(&udev->state_lock); if (udev->state != UIST_CREATED) { retval = -ENODEV; goto out; } - init_completion(&request->done); - /* * Tell our userspace application about this new request * by queueing an input event. @@ -166,7 +163,7 @@ static int uinput_request_send(struct uinput_device *udev, uinput_dev_event(udev->dev, EV_UINPUT, request->code, request->id); out: - mutex_unlock(&udev->mutex); + spin_unlock(&udev->state_lock); return retval; } @@ -175,6 +172,13 @@ static int uinput_request_submit(struct uinput_device *udev, { int retval; + /* + * Initialize completion before allocating the request slot. + * Once the slot is allocated, uinput_flush_requests() may + * complete it at any time, so it must be initialized first. + */ + init_completion(&request->done); + retval = uinput_request_reserve_slot(udev, request); if (retval) return retval; @@ -289,7 +293,14 @@ static void uinput_destroy_device(struct uinput_device *udev) struct input_dev *dev = udev->dev; enum uinput_state old_state = udev->state; + /* + * Update state under state_lock so that concurrent + * uinput_request_send() sees the state change before we + * flush pending requests and tear down the device. + */ + spin_lock(&udev->state_lock); udev->state = UIST_NEW_DEVICE; + spin_unlock(&udev->state_lock); if (dev) { name = dev->name; @@ -366,7 +377,9 @@ static int uinput_create_device(struct uinput_device *udev) if (error) goto fail2; + spin_lock(&udev->state_lock); udev->state = UIST_CREATED; + spin_unlock(&udev->state_lock); return 0; @@ -384,6 +397,7 @@ static int uinput_open(struct inode *inode, struct file *file) return -ENOMEM; mutex_init(&newdev->mutex); + spin_lock_init(&newdev->state_lock); spin_lock_init(&newdev->requests_lock); init_waitqueue_head(&newdev->requests_waitq); init_waitqueue_head(&newdev->waitq); From f661d0a73c6781e28cac3b6e5a62193340139396 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 7 Apr 2026 22:16:27 -0700 Subject: [PATCH 10/85] Input: uinput - take event lock when submitting FF request "event" commit ff14dafde15c11403fac61367a34fea08926e9ee upstream. To avoid racing with FF playback events and corrupting device's event queue take event_lock spinlock when calling uinput_dev_event() when submitting a FF upload or erase "event". Tested-by: Mikhail Gavrilov Link: https://patch.msgid.link/adXkf6MWzlB8LA_s@google.com Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 6c098142b37015610ad9de403e670b5956f7eb13) Signed-off-by: Wentao Guan --- drivers/input/misc/uinput.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index a973e82205b5..0e9544a98e67 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -25,8 +25,10 @@ #include #include #include +#include #include #include +#include #include #include "../input-compat.h" @@ -76,6 +78,8 @@ static int uinput_dev_event(struct input_dev *dev, struct uinput_device *udev = input_get_drvdata(dev); struct timespec64 ts; + lockdep_assert_held(&dev->event_lock); + ktime_get_ts64(&ts); udev->buff[udev->head] = (struct input_event) { @@ -147,6 +151,7 @@ static void uinput_request_release_slot(struct uinput_device *udev, static int uinput_request_send(struct uinput_device *udev, struct uinput_request *request) { + unsigned long flags; int retval = 0; spin_lock(&udev->state_lock); @@ -160,7 +165,9 @@ static int uinput_request_send(struct uinput_device *udev, * Tell our userspace application about this new request * by queueing an input event. */ + spin_lock_irqsave(&udev->dev->event_lock, flags); uinput_dev_event(udev->dev, EV_UINPUT, request->code, request->id); + spin_unlock_irqrestore(&udev->dev->event_lock, flags); out: spin_unlock(&udev->state_lock); From 345ff202f1b6444f14010a24678072c8aa2962b4 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 10 Apr 2026 01:49:58 +0100 Subject: [PATCH 11/85] MIPS: Always record SEGBITS in cpu_data.vmbits commit 8374c2cb83b95b3c92f129fd56527225c20a058c upstream. With a 32-bit kernel running on 64-bit MIPS hardware the hardcoded value of `cpu_vmbits' only records the size of compatibility useg and does not reflect the size of native xuseg or the complete range of values allowed in the VPN2 field of TLB entries. An upcoming change will need the actual VPN2 value range permitted even in 32-bit kernel configurations, so always include the `vmbits' member in `struct cpuinfo_mips' and probe for SEGBITS when running on 64-bit hardware and resorting to the currently hardcoded value of 31 on 32-bit processors. No functional change for users of `cpu_vmbits'. Signed-off-by: Maciej W. Rozycki Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin (cherry picked from commit 6c600fc0e99180c7a1b91c93e359009be8b4cfc2) Signed-off-by: Wentao Guan --- arch/mips/include/asm/cpu-features.h | 1 - arch/mips/include/asm/cpu-info.h | 2 -- arch/mips/include/asm/mipsregs.h | 2 ++ arch/mips/kernel/cpu-probe.c | 13 ++++++++----- arch/mips/kernel/cpu-r3k-probe.c | 2 ++ 5 files changed, 12 insertions(+), 8 deletions(-) diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index 404390bb87ea..3f11e5218e6c 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -484,7 +484,6 @@ # endif # ifndef cpu_vmbits # define cpu_vmbits cpu_data[0].vmbits -# define __NEED_VMBITS_PROBE # endif #endif diff --git a/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h index fd60837ce50b..211b578af6aa 100644 --- a/arch/mips/include/asm/cpu-info.h +++ b/arch/mips/include/asm/cpu-info.h @@ -80,9 +80,7 @@ struct cpuinfo_mips { int srsets; /* Shadow register sets */ int package;/* physical package number */ unsigned int globalnumber; -#ifdef CONFIG_64BIT int vmbits; /* Virtual memory size in bits */ -#endif void *data; /* Additional data */ unsigned int watch_reg_count; /* Number that exist */ unsigned int watch_reg_use_cnt; /* Usable by ptrace */ diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index f799c0d723da..12a095dbf9e2 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -1871,6 +1871,8 @@ do { \ #define read_c0_entryhi() __read_ulong_c0_register($10, 0) #define write_c0_entryhi(val) __write_ulong_c0_register($10, 0, val) +#define read_c0_entryhi_64() __read_64bit_c0_register($10, 0) +#define write_c0_entryhi_64(val) __write_64bit_c0_register($10, 0, val) #define read_c0_guestctl1() __read_32bit_c0_register($10, 4) #define write_c0_guestctl1(val) __write_32bit_c0_register($10, 4, val) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 1e49e05ac8b1..489612ed9d49 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -210,11 +210,14 @@ static inline void set_elf_base_platform(const char *plat) static inline void cpu_probe_vmbits(struct cpuinfo_mips *c) { -#ifdef __NEED_VMBITS_PROBE - write_c0_entryhi(0x3fffffffffffe000ULL); - back_to_back_c0_hazard(); - c->vmbits = fls64(read_c0_entryhi() & 0x3fffffffffffe000ULL); -#endif + int vmbits = 31; + + if (cpu_has_64bits) { + write_c0_entryhi_64(0x3fffffffffffe000ULL); + back_to_back_c0_hazard(); + vmbits = fls64(read_c0_entryhi_64() & 0x3fffffffffffe000ULL); + } + c->vmbits = vmbits; } static void set_isa(struct cpuinfo_mips *c, unsigned int isa) diff --git a/arch/mips/kernel/cpu-r3k-probe.c b/arch/mips/kernel/cpu-r3k-probe.c index 0c826f729f75..edcf04de0a6f 100644 --- a/arch/mips/kernel/cpu-r3k-probe.c +++ b/arch/mips/kernel/cpu-r3k-probe.c @@ -137,6 +137,8 @@ void cpu_probe(void) else cpu_set_nofpu_opts(c); + c->vmbits = 31; + reserve_exception_space(0, 0x400); } From 3637edc20ed28c32815cc601f161e434bf8b2d12 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 10 Apr 2026 01:49:59 +0100 Subject: [PATCH 12/85] MIPS: mm: Suppress TLB uniquification on EHINV hardware commit 74283cfe216392c7b776ebf6045b5b15ed9dffcd upstream. Hardware that supports the EHINV feature, mandatory for R6 ISA and FTLB implementation, lets software mark TLB entries invalid, which eliminates the need to ensure no duplicate matching entries are ever created. This feature is already used by local_flush_tlb_all(), via the UNIQUE_ENTRYHI macro, making the preceding call to r4k_tlb_uniquify() superfluous. The next change will also modify uniquification code such that it'll become incompatible with the FTLB and MMID features, as well as MIPSr6 CPUs that do not implement 4KiB pages. Therefore prevent r4k_tlb_uniquify() from being used on EHINV hardware, as denoted by `cpu_has_tlbinv'. Signed-off-by: Maciej W. Rozycki Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin (cherry picked from commit ccc6a2241a49f68d8656ab1e10df377acfe2c5b4) Signed-off-by: Wentao Guan --- arch/mips/mm/tlb-r4k.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 645f77e09d5b..65f0357958fc 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -640,7 +640,8 @@ static void r4k_tlb_configure(void) temp_tlb_entry = current_cpu_data.tlbsize - 1; /* From this point on the ARC firmware is dead. */ - r4k_tlb_uniquify(); + if (!cpu_has_tlbinv) + r4k_tlb_uniquify(); local_flush_tlb_all(); /* Did I tell you that ARC SUCKS? */ From a90847132e93b93253c3f3c7946dd8ef012f8fab Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 10 Apr 2026 01:50:00 +0100 Subject: [PATCH 13/85] MIPS: mm: Rewrite TLB uniquification for the hidden bit feature commit 540760b77b8fc49d39d1b2b76196e5ec57711a32 upstream. Before the introduction of the EHINV feature, which lets software mark TLB entries invalid, certain older implementations of the MIPS ISA were equipped with an analogous bit, as a vendor extension, which however is hidden from software and only ever set at reset, and then any software write clears it, making the intended TLB entry valid. This feature makes it unsafe to read a TLB entry with TLBR, modify the page mask, and write the entry back with TLBWI, because this operation will implicitly clear the hidden bit and this may create a duplicate entry, as with the presence of the hidden bit there is no guarantee all the entries across the TLB are unique each. Usually the firmware has already uniquified TLB entries before handing control over, in which case we only need to guarantee at bootstrap no clash will happen with the VPN2 values chosen in local_flush_tlb_all(). However with systems such as Mikrotik RB532 we get handed the TLB as at reset, with the hidden bit set across the entries and possibly duplicate entries present. This then causes a machine check exception when page sizes are reset in r4k_tlb_uniquify() and prevents the system from booting. Rewrite the algorithm used in r4k_tlb_uniquify() then such as to avoid the reuse of ASID/VPN values across the TLB. Get rid of global entries first as they may be blocking the entire address space, e.g. 16 256MiB pages will exhaust the whole address space of a 32-bit CPU and a single big page can exhaust the 32-bit compatibility space on a 64-bit CPU. Details of the algorithm chosen are given across the code itself. Fixes: 9f048fa48740 ("MIPS: mm: Prevent a TLB shutdown on initial uniquification") Signed-off-by: Maciej W. Rozycki Cc: stable@vger.kernel.org # v6.18+ Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin (cherry picked from commit d8b281165a86041bb40e055eb79f735826d0df1b) Signed-off-by: Wentao Guan --- arch/mips/mm/tlb-r4k.c | 282 +++++++++++++++++++++++++++++++++-------- 1 file changed, 228 insertions(+), 54 deletions(-) diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 65f0357958fc..24fe85fa169d 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -24,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -511,87 +513,259 @@ static int __init set_ntlb(char *str) __setup("ntlb=", set_ntlb); -/* Comparison function for EntryHi VPN fields. */ -static int r4k_vpn_cmp(const void *a, const void *b) +/* The start bit position of VPN2 and Mask in EntryHi/PageMask registers. */ +#define VPN2_SHIFT 13 + +/* Read full EntryHi even with CONFIG_32BIT. */ +static inline unsigned long long read_c0_entryhi_native(void) +{ + return cpu_has_64bits ? read_c0_entryhi_64() : read_c0_entryhi(); +} + +/* Write full EntryHi even with CONFIG_32BIT. */ +static inline void write_c0_entryhi_native(unsigned long long v) { - long v = *(unsigned long *)a - *(unsigned long *)b; - int s = sizeof(long) > sizeof(int) ? sizeof(long) * 8 - 1: 0; - return s ? (v != 0) | v >> s : v; + if (cpu_has_64bits) + write_c0_entryhi_64(v); + else + write_c0_entryhi(v); } +/* TLB entry state for uniquification. */ +struct tlbent { + unsigned long long wired:1; + unsigned long long global:1; + unsigned long long asid:10; + unsigned long long vpn:51; + unsigned long long pagesz:5; + unsigned long long index:14; +}; + /* - * Initialise all TLB entries with unique values that do not clash with - * what we have been handed over and what we'll be using ourselves. + * Comparison function for TLB entry sorting. Place wired entries first, + * then global entries, then order by the increasing VPN/ASID and the + * decreasing page size. This lets us avoid clashes with wired entries + * easily and get entries for larger pages out of the way first. + * + * We could group bits so as to reduce the number of comparisons, but this + * is seldom executed and not performance-critical, so prefer legibility. */ -static void __ref r4k_tlb_uniquify(void) +static int r4k_entry_cmp(const void *a, const void *b) { - int tlbsize = current_cpu_data.tlbsize; - bool use_slab = slab_is_available(); - int start = num_wired_entries(); - phys_addr_t tlb_vpn_size; - unsigned long *tlb_vpns; - unsigned long vpn_mask; - int cnt, ent, idx, i; - - vpn_mask = GENMASK(cpu_vmbits - 1, 13); - vpn_mask |= IS_ENABLED(CONFIG_64BIT) ? 3ULL << 62 : 1 << 31; + struct tlbent ea = *(struct tlbent *)a, eb = *(struct tlbent *)b; + + if (ea.wired > eb.wired) + return -1; + else if (ea.wired < eb.wired) + return 1; + else if (ea.global > eb.global) + return -1; + else if (ea.global < eb.global) + return 1; + else if (ea.vpn < eb.vpn) + return -1; + else if (ea.vpn > eb.vpn) + return 1; + else if (ea.asid < eb.asid) + return -1; + else if (ea.asid > eb.asid) + return 1; + else if (ea.pagesz > eb.pagesz) + return -1; + else if (ea.pagesz < eb.pagesz) + return 1; + else + return 0; +} - tlb_vpn_size = tlbsize * sizeof(*tlb_vpns); - tlb_vpns = (use_slab ? - kmalloc(tlb_vpn_size, GFP_ATOMIC) : - memblock_alloc_raw(tlb_vpn_size, sizeof(*tlb_vpns))); - if (WARN_ON(!tlb_vpns)) - return; /* Pray local_flush_tlb_all() is good enough. */ +/* + * Fetch all the TLB entries. Mask individual VPN values retrieved with + * the corresponding page mask and ignoring any 1KiB extension as we'll + * be using 4KiB pages for uniquification. + */ +static void __ref r4k_tlb_uniquify_read(struct tlbent *tlb_vpns, int tlbsize) +{ + int start = num_wired_entries(); + unsigned long long vpn_mask; + bool global; + int i; - htw_stop(); + vpn_mask = GENMASK(current_cpu_data.vmbits - 1, VPN2_SHIFT); + vpn_mask |= cpu_has_64bits ? 3ULL << 62 : 1 << 31; - for (i = start, cnt = 0; i < tlbsize; i++, cnt++) { - unsigned long vpn; + for (i = 0; i < tlbsize; i++) { + unsigned long long entryhi, vpn, mask, asid; + unsigned int pagesz; write_c0_index(i); mtc0_tlbr_hazard(); tlb_read(); tlb_read_hazard(); - vpn = read_c0_entryhi(); - vpn &= vpn_mask & PAGE_MASK; - tlb_vpns[cnt] = vpn; - /* Prevent any large pages from overlapping regular ones. */ - write_c0_pagemask(read_c0_pagemask() & PM_DEFAULT_MASK); - mtc0_tlbw_hazard(); - tlb_write_indexed(); - tlbw_use_hazard(); + global = !!(read_c0_entrylo0() & ENTRYLO_G); + entryhi = read_c0_entryhi_native(); + mask = read_c0_pagemask(); + + asid = entryhi & cpu_asid_mask(¤t_cpu_data); + vpn = (entryhi & vpn_mask & ~mask) >> VPN2_SHIFT; + pagesz = ilog2((mask >> VPN2_SHIFT) + 1); + + tlb_vpns[i].global = global; + tlb_vpns[i].asid = global ? 0 : asid; + tlb_vpns[i].vpn = vpn; + tlb_vpns[i].pagesz = pagesz; + tlb_vpns[i].wired = i < start; + tlb_vpns[i].index = i; } +} - sort(tlb_vpns, cnt, sizeof(tlb_vpns[0]), r4k_vpn_cmp, NULL); +/* + * Write unique values to all but the wired TLB entries each, using + * the 4KiB page size. This size might not be supported with R6, but + * EHINV is mandatory for R6, so we won't ever be called in that case. + * + * A sorted table is supplied with any wired entries at the beginning, + * followed by any global entries, and then finally regular entries. + * We start at the VPN and ASID values of zero and only assign user + * addresses, therefore guaranteeing no clash with addresses produced + * by UNIQUE_ENTRYHI. We avoid any VPN values used by wired or global + * entries, by increasing the VPN value beyond the span of such entry. + * + * When a VPN/ASID clash is found with a regular entry we increment the + * ASID instead until no VPN/ASID clash has been found or the ASID space + * has been exhausted, in which case we increase the VPN value beyond + * the span of the largest clashing entry. + * + * We do not need to be concerned about FTLB or MMID configurations as + * those are required to implement the EHINV feature. + */ +static void __ref r4k_tlb_uniquify_write(struct tlbent *tlb_vpns, int tlbsize) +{ + unsigned long long asid, vpn, vpn_size, pagesz; + int widx, gidx, idx, sidx, lidx, i; - write_c0_pagemask(PM_DEFAULT_MASK); + vpn_size = 1ULL << (current_cpu_data.vmbits - VPN2_SHIFT); + pagesz = ilog2((PM_4K >> VPN2_SHIFT) + 1); + + write_c0_pagemask(PM_4K); write_c0_entrylo0(0); write_c0_entrylo1(0); - idx = 0; - ent = tlbsize; - for (i = start; i < tlbsize; i++) - while (1) { - unsigned long entryhi, vpn; + asid = 0; + vpn = 0; + widx = 0; + gidx = 0; + for (sidx = 0; sidx < tlbsize && tlb_vpns[sidx].wired; sidx++) + ; + for (lidx = sidx; lidx < tlbsize && tlb_vpns[lidx].global; lidx++) + ; + idx = gidx = sidx + 1; + for (i = sidx; i < tlbsize; i++) { + unsigned long long entryhi, vpn_pagesz = 0; - entryhi = UNIQUE_ENTRYHI(ent); - vpn = entryhi & vpn_mask & PAGE_MASK; + while (1) { + if (WARN_ON(vpn >= vpn_size)) { + dump_tlb_all(); + /* Pray local_flush_tlb_all() will cope. */ + return; + } - if (idx >= cnt || vpn < tlb_vpns[idx]) { - write_c0_entryhi(entryhi); - write_c0_index(i); - mtc0_tlbw_hazard(); - tlb_write_indexed(); - ent++; - break; - } else if (vpn == tlb_vpns[idx]) { - ent++; - } else { + /* VPN must be below the next wired entry. */ + if (widx < sidx && vpn >= tlb_vpns[widx].vpn) { + vpn = max(vpn, + (tlb_vpns[widx].vpn + + (1ULL << tlb_vpns[widx].pagesz))); + asid = 0; + widx++; + continue; + } + /* VPN must be below the next global entry. */ + if (gidx < lidx && vpn >= tlb_vpns[gidx].vpn) { + vpn = max(vpn, + (tlb_vpns[gidx].vpn + + (1ULL << tlb_vpns[gidx].pagesz))); + asid = 0; + gidx++; + continue; + } + /* Try to find a free ASID so as to conserve VPNs. */ + if (idx < tlbsize && vpn == tlb_vpns[idx].vpn && + asid == tlb_vpns[idx].asid) { + unsigned long long idx_pagesz; + + idx_pagesz = tlb_vpns[idx].pagesz; + vpn_pagesz = max(vpn_pagesz, idx_pagesz); + do + idx++; + while (idx < tlbsize && + vpn == tlb_vpns[idx].vpn && + asid == tlb_vpns[idx].asid); + asid++; + if (asid > cpu_asid_mask(¤t_cpu_data)) { + vpn += vpn_pagesz; + asid = 0; + vpn_pagesz = 0; + } + continue; + } + /* VPN mustn't be above the next regular entry. */ + if (idx < tlbsize && vpn > tlb_vpns[idx].vpn) { + vpn = max(vpn, + (tlb_vpns[idx].vpn + + (1ULL << tlb_vpns[idx].pagesz))); + asid = 0; idx++; + continue; } + break; } + entryhi = (vpn << VPN2_SHIFT) | asid; + write_c0_entryhi_native(entryhi); + write_c0_index(tlb_vpns[i].index); + mtc0_tlbw_hazard(); + tlb_write_indexed(); + + tlb_vpns[i].asid = asid; + tlb_vpns[i].vpn = vpn; + tlb_vpns[i].pagesz = pagesz; + + asid++; + if (asid > cpu_asid_mask(¤t_cpu_data)) { + vpn += 1ULL << pagesz; + asid = 0; + } + } +} + +/* + * Initialise all TLB entries with unique values that do not clash with + * what we have been handed over and what we'll be using ourselves. + */ +static void __ref r4k_tlb_uniquify(void) +{ + int tlbsize = current_cpu_data.tlbsize; + bool use_slab = slab_is_available(); + phys_addr_t tlb_vpn_size; + struct tlbent *tlb_vpns; + + tlb_vpn_size = tlbsize * sizeof(*tlb_vpns); + tlb_vpns = (use_slab ? + kmalloc(tlb_vpn_size, GFP_ATOMIC) : + memblock_alloc_raw(tlb_vpn_size, sizeof(*tlb_vpns))); + if (WARN_ON(!tlb_vpns)) + return; /* Pray local_flush_tlb_all() is good enough. */ + + htw_stop(); + + r4k_tlb_uniquify_read(tlb_vpns, tlbsize); + + sort(tlb_vpns, tlbsize, sizeof(*tlb_vpns), r4k_entry_cmp, NULL); + + r4k_tlb_uniquify_write(tlb_vpns, tlbsize); + + write_c0_pagemask(PM_DEFAULT_MASK); + tlbw_use_hazard(); htw_start(); flush_micro_tlb(); From 5d9577b0e3ce0aeae16940a1566136407c94bc4b Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 20 Jan 2026 19:52:10 +0000 Subject: [PATCH 14/85] btrfs: remove pointless out labels from extent-tree.c [ Upstream commit ea8f9210050136bdd14f5e32b04cd01c8bd5c0ca ] Some functions (lookup_extent_data_ref(), __btrfs_mod_ref() and btrfs_free_tree_block()) have an 'out' label that does nothing but return, making it pointless. Simplify this by removing the label and returning instead of gotos plus setting the 'ret' variable. Reviewed-by: Johannes Thumshirn Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Stable-dep-of: 316fb1b3169e ("btrfs: fix incorrect return value after changing leaf in lookup_extent_data_ref()") Signed-off-by: Sasha Levin (cherry picked from commit 2124a61e6e2b0359ad27d782e23abb699b2f26e0) Signed-off-by: Wentao Guan --- fs/btrfs/extent-tree.c | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 08b710929947..fa83a3d8286c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -476,7 +476,7 @@ static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans, btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != bytenr || key.type != BTRFS_EXTENT_DATA_REF_KEY) - goto fail; + return ret; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_data_ref); @@ -487,12 +487,11 @@ static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans, btrfs_release_path(path); goto again; } - ret = 0; - break; + return 0; } path->slots[0]++; } -fail: + return ret; } @@ -2470,7 +2469,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, int i; int action; int level; - int ret = 0; + int ret; if (btrfs_is_testing(fs_info)) return 0; @@ -2522,7 +2521,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, else ret = btrfs_free_extent(trans, &ref); if (ret) - goto fail; + return ret; } else { /* We don't know the owning_root, leave as 0. */ ref.bytenr = btrfs_node_blockptr(buf, i); @@ -2535,12 +2534,10 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, else ret = btrfs_free_extent(trans, &ref); if (ret) - goto fail; + return ret; } } return 0; -fail: - return ret; } int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -3473,12 +3470,12 @@ int btrfs_free_tree_block(struct btrfs_trans_handle *trans, return 0; if (btrfs_header_generation(buf) != trans->transid) - goto out; + return 0; if (root_id != BTRFS_TREE_LOG_OBJECTID) { ret = check_ref_cleanup(trans, buf->start); if (!ret) - goto out; + return 0; } bg = btrfs_lookup_block_group(fs_info, buf->start); @@ -3486,7 +3483,7 @@ int btrfs_free_tree_block(struct btrfs_trans_handle *trans, if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) { pin_down_extent(trans, bg, buf->start, buf->len, 1); btrfs_put_block_group(bg); - goto out; + return 0; } /* @@ -3510,7 +3507,7 @@ int btrfs_free_tree_block(struct btrfs_trans_handle *trans, || btrfs_is_zoned(fs_info)) { pin_down_extent(trans, bg, buf->start, buf->len, 1); btrfs_put_block_group(bg); - goto out; + return 0; } WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)); @@ -3520,7 +3517,6 @@ int btrfs_free_tree_block(struct btrfs_trans_handle *trans, btrfs_put_block_group(bg); trace_btrfs_reserved_extent_free(fs_info, buf->start, buf->len); -out: return 0; } From b8388bb1807e78791428b53160e99a7c6582bfa9 Mon Sep 17 00:00:00 2001 From: robbieko Date: Wed, 25 Mar 2026 18:18:15 +0800 Subject: [PATCH 15/85] btrfs: fix incorrect return value after changing leaf in lookup_extent_data_ref() [ Upstream commit 316fb1b3169efb081d2db910cbbfef445afa03b9 ] After commit 1618aa3c2e01 ("btrfs: simplify return variables in lookup_extent_data_ref()"), the err and ret variables were merged into a single ret variable. However, when btrfs_next_leaf() returns 0 (success), ret is overwritten from -ENOENT to 0. If the first key in the next leaf does not match (different objectid or type), the function returns 0 instead of -ENOENT, making the caller believe the lookup succeeded when it did not. This can lead to operations on the wrong extent tree item, potentially causing extent tree corruption. Fix this by returning -ENOENT directly when the key does not match, instead of relying on the ret variable. Fixes: 1618aa3c2e01 ("btrfs: simplify return variables in lookup_extent_data_ref()") CC: stable@vger.kernel.org # 6.12+ Reviewed-by: Filipe Manana Signed-off-by: robbieko Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin (cherry picked from commit 450e6a685d0cad95b15f8af152057bd0bf79f50b) Signed-off-by: Wentao Guan --- fs/btrfs/extent-tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index fa83a3d8286c..863b45092a19 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -476,7 +476,7 @@ static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans, btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != bytenr || key.type != BTRFS_EXTENT_DATA_REF_KEY) - return ret; + return -ENOENT; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_data_ref); From 76c516ce58b116049a8b3485adb47eeaa34bcd00 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Sat, 15 Nov 2025 02:08:32 +0000 Subject: [PATCH 16/85] af_unix: Count cyclic SCC. [ Upstream commit 58b47c713711b8afbf68e3158d4d5acdead00e9b ] __unix_walk_scc() and unix_walk_scc_fast() call unix_scc_cyclic() for each SCC to check if it forms a cyclic reference, so that we can skip GC at the following invocations in case all SCCs do not have any cycles. If we count the number of cyclic SCCs in __unix_walk_scc(), we can simplify unix_walk_scc_fast() because the number of cyclic SCCs only changes when it garbage-collects a SCC. So, let's count cyclic SCC in __unix_walk_scc() and decrement it in unix_walk_scc_fast() when performing garbage collection. Note that we will use this counter in a later patch to check if a cycle existed in the previous GC run. Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20251115020935.2643121-2-kuniyu@google.com Signed-off-by: Jakub Kicinski Stable-dep-of: e5b31d988a41 ("af_unix: Give up GC if MSG_PEEK intervened.") Signed-off-by: Sasha Levin (cherry picked from commit 1e211179f1d9273b6cfd0b30d6983dc1d626736b) Signed-off-by: Wentao Guan --- net/unix/garbage.c | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-) diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 65396a4e1b07..9f62d5097973 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -404,9 +404,11 @@ static bool unix_scc_cyclic(struct list_head *scc) static LIST_HEAD(unix_visited_vertices); static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2; -static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_index, - struct sk_buff_head *hitlist) +static unsigned long __unix_walk_scc(struct unix_vertex *vertex, + unsigned long *last_index, + struct sk_buff_head *hitlist) { + unsigned long cyclic_sccs = 0; LIST_HEAD(vertex_stack); struct unix_edge *edge; LIST_HEAD(edge_stack); @@ -497,8 +499,8 @@ static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_inde if (unix_vertex_max_scc_index < vertex->scc_index) unix_vertex_max_scc_index = vertex->scc_index; - if (!unix_graph_maybe_cyclic) - unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + if (unix_scc_cyclic(&scc)) + cyclic_sccs++; } list_del(&scc); @@ -507,13 +509,17 @@ static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_inde /* Need backtracking ? */ if (!list_empty(&edge_stack)) goto prev_vertex; + + return cyclic_sccs; } +static unsigned long unix_graph_cyclic_sccs; + static void unix_walk_scc(struct sk_buff_head *hitlist) { unsigned long last_index = UNIX_VERTEX_INDEX_START; + unsigned long cyclic_sccs = 0; - unix_graph_maybe_cyclic = false; unix_vertex_max_scc_index = UNIX_VERTEX_INDEX_START; /* Visit every vertex exactly once. @@ -523,18 +529,20 @@ static void unix_walk_scc(struct sk_buff_head *hitlist) struct unix_vertex *vertex; vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); - __unix_walk_scc(vertex, &last_index, hitlist); + cyclic_sccs += __unix_walk_scc(vertex, &last_index, hitlist); } list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); swap(unix_vertex_unvisited_index, unix_vertex_grouped_index); + unix_graph_cyclic_sccs = cyclic_sccs; + unix_graph_maybe_cyclic = !!unix_graph_cyclic_sccs; unix_graph_grouped = true; } static void unix_walk_scc_fast(struct sk_buff_head *hitlist) { - unix_graph_maybe_cyclic = false; + unsigned long cyclic_sccs = unix_graph_cyclic_sccs; while (!list_empty(&unix_unvisited_vertices)) { struct unix_vertex *vertex; @@ -551,15 +559,18 @@ static void unix_walk_scc_fast(struct sk_buff_head *hitlist) scc_dead = unix_vertex_dead(vertex); } - if (scc_dead) + if (scc_dead) { + cyclic_sccs--; unix_collect_skb(&scc, hitlist); - else if (!unix_graph_maybe_cyclic) - unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + } list_del(&scc); } list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); + + unix_graph_cyclic_sccs = cyclic_sccs; + unix_graph_maybe_cyclic = !!unix_graph_cyclic_sccs; } static bool gc_in_progress; From d9d9812115c88a47c62c2e0327e6f805ec45ed6a Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Sat, 15 Nov 2025 02:08:33 +0000 Subject: [PATCH 17/85] af_unix: Simplify GC state. [ Upstream commit 6b6f3c71fe568aa8ed3e16e9135d88a5f4fd3e84 ] GC manages its state by two variables, unix_graph_maybe_cyclic and unix_graph_grouped, both of which are set to false in the initial state. When an AF_UNIX socket is passed to an in-flight AF_UNIX socket, unix_update_graph() sets unix_graph_maybe_cyclic to true and unix_graph_grouped to false, making the next GC invocation call unix_walk_scc() to group SCCs. Once unix_walk_scc() finishes, sockets in the same SCC are linked via vertex->scc_entry. Then, unix_graph_grouped is set to true so that the following GC invocations can skip Tarjan's algorithm and simply iterate through the list in unix_walk_scc_fast(). In addition, if we know there is at least one cyclic reference, we set unix_graph_maybe_cyclic to true so that we do not skip GC. So the state transitions as follows: (unix_graph_maybe_cyclic, unix_graph_grouped) = (false, false) -> (true, false) -> (true, true) or (false, true) ^.______________/________________/ There is no transition to the initial state where both variables are false. If we consider the initial state as grouped, we can see that the GC actually has a tristate. Let's consolidate two variables into one enum. Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20251115020935.2643121-3-kuniyu@google.com Signed-off-by: Jakub Kicinski Stable-dep-of: e5b31d988a41 ("af_unix: Give up GC if MSG_PEEK intervened.") Signed-off-by: Sasha Levin (cherry picked from commit 33120558237c7e13db3c39f09fd712431e455005) Signed-off-by: Wentao Guan --- net/unix/garbage.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 9f62d5097973..7528e2db1293 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -121,8 +121,13 @@ static struct unix_vertex *unix_edge_successor(struct unix_edge *edge) return edge->successor->vertex; } -static bool unix_graph_maybe_cyclic; -static bool unix_graph_grouped; +enum { + UNIX_GRAPH_NOT_CYCLIC, + UNIX_GRAPH_MAYBE_CYCLIC, + UNIX_GRAPH_CYCLIC, +}; + +static unsigned char unix_graph_state; static void unix_update_graph(struct unix_vertex *vertex) { @@ -132,8 +137,7 @@ static void unix_update_graph(struct unix_vertex *vertex) if (!vertex) return; - unix_graph_maybe_cyclic = true; - unix_graph_grouped = false; + unix_graph_state = UNIX_GRAPH_MAYBE_CYCLIC; } static LIST_HEAD(unix_unvisited_vertices); @@ -536,8 +540,7 @@ static void unix_walk_scc(struct sk_buff_head *hitlist) swap(unix_vertex_unvisited_index, unix_vertex_grouped_index); unix_graph_cyclic_sccs = cyclic_sccs; - unix_graph_maybe_cyclic = !!unix_graph_cyclic_sccs; - unix_graph_grouped = true; + unix_graph_state = cyclic_sccs ? UNIX_GRAPH_CYCLIC : UNIX_GRAPH_NOT_CYCLIC; } static void unix_walk_scc_fast(struct sk_buff_head *hitlist) @@ -570,7 +573,7 @@ static void unix_walk_scc_fast(struct sk_buff_head *hitlist) list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); unix_graph_cyclic_sccs = cyclic_sccs; - unix_graph_maybe_cyclic = !!unix_graph_cyclic_sccs; + unix_graph_state = cyclic_sccs ? UNIX_GRAPH_CYCLIC : UNIX_GRAPH_NOT_CYCLIC; } static bool gc_in_progress; @@ -582,14 +585,14 @@ static void __unix_gc(struct work_struct *work) spin_lock(&unix_gc_lock); - if (!unix_graph_maybe_cyclic) { + if (unix_graph_state == UNIX_GRAPH_NOT_CYCLIC) { spin_unlock(&unix_gc_lock); goto skip_gc; } __skb_queue_head_init(&hitlist); - if (unix_graph_grouped) + if (unix_graph_state == UNIX_GRAPH_CYCLIC) unix_walk_scc_fast(&hitlist); else unix_walk_scc(&hitlist); From 3c2fb82c34d96126025407bc01836ad542790acb Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 11 Mar 2026 05:40:40 +0000 Subject: [PATCH 18/85] af_unix: Give up GC if MSG_PEEK intervened. [ Upstream commit e5b31d988a41549037b8d8721a3c3cae893d8670 ] Igor Ushakov reported that GC purged the receive queue of an alive socket due to a race with MSG_PEEK with a nice repro. This is the exact same issue previously fixed by commit cbcf01128d0a ("af_unix: fix garbage collect vs MSG_PEEK"). After GC was replaced with the current algorithm, the cited commit removed the locking dance in unix_peek_fds() and reintroduced the same issue. The problem is that MSG_PEEK bumps a file refcount without interacting with GC. Consider an SCC containing sk-A and sk-B, where sk-A is close()d but can be recv()ed via sk-B. The bad thing happens if sk-A is recv()ed with MSG_PEEK from sk-B and sk-B is close()d while GC is checking unix_vertex_dead() for sk-A and sk-B. GC thread User thread --------- ----------- unix_vertex_dead(sk-A) -> true <------. \ `------ recv(sk-B, MSG_PEEK) invalidate !! -> sk-A's file refcount : 1 -> 2 close(sk-B) -> sk-B's file refcount : 2 -> 1 unix_vertex_dead(sk-B) -> true Initially, sk-A's file refcount is 1 by the inflight fd in sk-B recvq. GC thinks sk-A is dead because the file refcount is the same as the number of its inflight fds. However, sk-A's file refcount is bumped silently by MSG_PEEK, which invalidates the previous evaluation. At this moment, sk-B's file refcount is 2; one by the open fd, and one by the inflight fd in sk-A. The subsequent close() releases one refcount by the former. Finally, GC incorrectly concludes that both sk-A and sk-B are dead. One option is to restore the locking dance in unix_peek_fds(), but we can resolve this more elegantly thanks to the new algorithm. The point is that the issue does not occur without the subsequent close() and we actually do not need to synchronise MSG_PEEK with the dead SCC detection. When the issue occurs, close() and GC touch the same file refcount. If GC sees the refcount being decremented by close(), it can just give up garbage-collecting the SCC. Therefore, we only need to signal the race during MSG_PEEK with a proper memory barrier to make it visible to the GC. Let's use seqcount_t to notify GC when MSG_PEEK occurs and let it defer the SCC to the next run. This way no locking is needed on the MSG_PEEK side, and we can avoid imposing a penalty on every MSG_PEEK unnecessarily. Note that we can retry within unix_scc_dead() if MSG_PEEK is detected, but we do not do so to avoid hung task splat from abusive MSG_PEEK calls. Fixes: 118f457da9ed ("af_unix: Remove lock dance in unix_peek_fds().") Reported-by: Igor Ushakov Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260311054043.1231316-1-kuniyu@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin (cherry picked from commit 72cf49ad50c16270b52bc512d9c2df5743922968) Signed-off-by: Wentao Guan --- net/unix/af_unix.c | 2 ++ net/unix/af_unix.h | 1 + net/unix/garbage.c | 79 ++++++++++++++++++++++++++++++---------------- 3 files changed, 54 insertions(+), 28 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 79943fb34806..6b251c76f6be 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1979,6 +1979,8 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) { scm->fp = scm_fp_dup(UNIXCB(skb).fp); + + unix_peek_fpl(scm->fp); } static void unix_destruct_scm(struct sk_buff *skb) diff --git a/net/unix/af_unix.h b/net/unix/af_unix.h index 59db179df9bb..6b96c1007aec 100644 --- a/net/unix/af_unix.h +++ b/net/unix/af_unix.h @@ -30,6 +30,7 @@ void unix_del_edges(struct scm_fp_list *fpl); void unix_update_edges(struct unix_sock *receiver); int unix_prepare_fpl(struct scm_fp_list *fpl); void unix_destroy_fpl(struct scm_fp_list *fpl); +void unix_peek_fpl(struct scm_fp_list *fpl); void unix_gc(void); void wait_for_unix_gc(struct scm_fp_list *fpl); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 7528e2db1293..529b21d043d9 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -319,6 +319,25 @@ void unix_destroy_fpl(struct scm_fp_list *fpl) unix_free_vertices(fpl); } +static bool gc_in_progress; +static seqcount_t unix_peek_seq = SEQCNT_ZERO(unix_peek_seq); + +void unix_peek_fpl(struct scm_fp_list *fpl) +{ + static DEFINE_SPINLOCK(unix_peek_lock); + + if (!fpl || !fpl->count_unix) + return; + + if (!READ_ONCE(gc_in_progress)) + return; + + /* Invalidate the final refcnt check in unix_vertex_dead(). */ + spin_lock(&unix_peek_lock); + raw_write_seqcount_barrier(&unix_peek_seq); + spin_unlock(&unix_peek_lock); +} + static bool unix_vertex_dead(struct unix_vertex *vertex) { struct unix_edge *edge; @@ -352,6 +371,36 @@ static bool unix_vertex_dead(struct unix_vertex *vertex) return true; } +static LIST_HEAD(unix_visited_vertices); +static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2; + +static bool unix_scc_dead(struct list_head *scc, bool fast) +{ + struct unix_vertex *vertex; + bool scc_dead = true; + unsigned int seq; + + seq = read_seqcount_begin(&unix_peek_seq); + + list_for_each_entry_reverse(vertex, scc, scc_entry) { + /* Don't restart DFS from this vertex. */ + list_move_tail(&vertex->entry, &unix_visited_vertices); + + /* Mark vertex as off-stack for __unix_walk_scc(). */ + if (!fast) + vertex->index = unix_vertex_grouped_index; + + if (scc_dead) + scc_dead = unix_vertex_dead(vertex); + } + + /* If MSG_PEEK intervened, defer this SCC to the next round. */ + if (read_seqcount_retry(&unix_peek_seq, seq)) + return false; + + return scc_dead; +} + static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist) { struct unix_vertex *vertex; @@ -405,9 +454,6 @@ static bool unix_scc_cyclic(struct list_head *scc) return false; } -static LIST_HEAD(unix_visited_vertices); -static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2; - static unsigned long __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_index, struct sk_buff_head *hitlist) @@ -475,9 +521,7 @@ static unsigned long __unix_walk_scc(struct unix_vertex *vertex, } if (vertex->index == vertex->scc_index) { - struct unix_vertex *v; struct list_head scc; - bool scc_dead = true; /* SCC finalised. * @@ -486,18 +530,7 @@ static unsigned long __unix_walk_scc(struct unix_vertex *vertex, */ __list_cut_position(&scc, &vertex_stack, &vertex->scc_entry); - list_for_each_entry_reverse(v, &scc, scc_entry) { - /* Don't restart DFS from this vertex in unix_walk_scc(). */ - list_move_tail(&v->entry, &unix_visited_vertices); - - /* Mark vertex as off-stack. */ - v->index = unix_vertex_grouped_index; - - if (scc_dead) - scc_dead = unix_vertex_dead(v); - } - - if (scc_dead) { + if (unix_scc_dead(&scc, false)) { unix_collect_skb(&scc, hitlist); } else { if (unix_vertex_max_scc_index < vertex->scc_index) @@ -550,19 +583,11 @@ static void unix_walk_scc_fast(struct sk_buff_head *hitlist) while (!list_empty(&unix_unvisited_vertices)) { struct unix_vertex *vertex; struct list_head scc; - bool scc_dead = true; vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); list_add(&scc, &vertex->scc_entry); - list_for_each_entry_reverse(vertex, &scc, scc_entry) { - list_move_tail(&vertex->entry, &unix_visited_vertices); - - if (scc_dead) - scc_dead = unix_vertex_dead(vertex); - } - - if (scc_dead) { + if (unix_scc_dead(&scc, true)) { cyclic_sccs--; unix_collect_skb(&scc, hitlist); } @@ -576,8 +601,6 @@ static void unix_walk_scc_fast(struct sk_buff_head *hitlist) unix_graph_state = cyclic_sccs ? UNIX_GRAPH_CYCLIC : UNIX_GRAPH_NOT_CYCLIC; } -static bool gc_in_progress; - static void __unix_gc(struct work_struct *work) { struct sk_buff_head hitlist; From f29eb9423cbe067f59995527ebe94f9ae55aaf9d Mon Sep 17 00:00:00 2001 From: Anthony Pighin Date: Tue, 31 Mar 2026 14:26:32 -0400 Subject: [PATCH 19/85] i2c: imx: zero-initialize dma_slave_config for eDMA commit 39ed7d89b973329cc5c764b65ba6302b17b1907e upstream. commit 66d88e16f204 ("dmaengine: fsl-edma: read/write multiple registers in cyclic transactions") causes fsl_edma_fill_tcd() to read dst_port_window_size and src_port_window_size when building transfer control descriptors. Initialize the structure so unset fields are explicitly zero. Fixes: 66d88e16f204 ("dmaengine: fsl-edma: read/write multiple registers in cyclic transactions") Signed-off-by: Anthony Pighin Cc: # v6.14+ Signed-off-by: Andi Shyti Link: https://lore.kernel.org/r/20260331182632.888110-1-anthony.pighin@nokia.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 2802ba3981f15ed8e89fe86544aad2f43acd17b7) Signed-off-by: Wentao Guan --- drivers/i2c/busses/i2c-imx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 452d120a210b..a208fefd3c3b 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -401,7 +401,7 @@ static void i2c_imx_reset_regs(struct imx_i2c_struct *i2c_imx) static int i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx, dma_addr_t phy_addr) { struct imx_i2c_dma *dma; - struct dma_slave_config dma_sconfig; + struct dma_slave_config dma_sconfig = {}; struct device *dev = i2c_imx->adapter.dev.parent; int ret; From 4c5a7a62710e455de57f83d0cb09ec6c07dbb23e Mon Sep 17 00:00:00 2001 From: Tuan Do Date: Fri, 3 Apr 2026 00:33:17 -0700 Subject: [PATCH 20/85] netfilter: nft_ct: fix use-after-free in timeout object destroy commit f8dca15a1b190787bbd03285304b569631160eda upstream. nft_ct_timeout_obj_destroy() frees the timeout object with kfree() immediately after nf_ct_untimeout(), without waiting for an RCU grace period. Concurrent packet processing on other CPUs may still hold RCU-protected references to the timeout object obtained via rcu_dereference() in nf_ct_timeout_data(). Add an rcu_head to struct nf_ct_timeout and use kfree_rcu() to defer freeing until after an RCU grace period, matching the approach already used in nfnetlink_cttimeout.c. KASAN report: BUG: KASAN: slab-use-after-free in nf_conntrack_tcp_packet+0x1381/0x29d0 Read of size 4 at addr ffff8881035fe19c by task exploit/80 Call Trace: nf_conntrack_tcp_packet+0x1381/0x29d0 nf_conntrack_in+0x612/0x8b0 nf_hook_slow+0x70/0x100 __ip_local_out+0x1b2/0x210 tcp_sendmsg_locked+0x722/0x1580 __sys_sendto+0x2d8/0x320 Allocated by task 75: nft_ct_timeout_obj_init+0xf6/0x290 nft_obj_init+0x107/0x1b0 nf_tables_newobj+0x680/0x9c0 nfnetlink_rcv_batch+0xc29/0xe00 Freed by task 26: nft_obj_destroy+0x3f/0xa0 nf_tables_trans_destroy_work+0x51c/0x5c0 process_one_work+0x2c4/0x5a0 Fixes: 7e0b2b57f01d ("netfilter: nft_ct: add ct timeout support") Cc: stable@vger.kernel.org Signed-off-by: Tuan Do Signed-off-by: Florian Westphal Signed-off-by: Greg Kroah-Hartman (cherry picked from commit b42aca3660dc2627a29a38131597ca610dc451f9) Signed-off-by: Wentao Guan --- include/net/netfilter/nf_conntrack_timeout.h | 1 + net/netfilter/nft_ct.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 9fdaba911de6..3a66d4abb6d6 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -14,6 +14,7 @@ struct nf_ct_timeout { __u16 l3num; const struct nf_conntrack_l4proto *l4proto; + struct rcu_head rcu; char data[]; }; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index db1bf69f8775..4f52ca4c48d5 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1021,7 +1021,7 @@ static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx, nf_queue_nf_hook_drop(ctx->net); nf_ct_untimeout(ctx->net, timeout); nf_ct_netns_put(ctx->net, ctx->family); - kfree(priv->timeout); + kfree_rcu(priv->timeout, rcu); } static int nft_ct_timeout_obj_dump(struct sk_buff *skb, From 9f81794c027dbac7421b6a17bf3cfb62e69fca9c Mon Sep 17 00:00:00 2001 From: Michal Wilczynski Date: Thu, 3 Apr 2025 15:10:51 +0200 Subject: [PATCH 21/85] firmware: thead: Fix buffer overflow and use standard endian macros commit 88c4bd90725557796c15878b7cb70066e9e6b5ab upstream. Addresses two issues in the TH1520 AON firmware protocol driver: 1. Fix a potential buffer overflow where the code used unsafe pointer arithmetic to access the 'mode' field through the 'resource' pointer with an offset. This was flagged by Smatch static checker as: "buffer overflow 'data' 2 <= 3" 2. Replace custom RPC_SET_BE* and RPC_GET_BE* macros with standard kernel endianness conversion macros (cpu_to_be16, etc.) for better portability and maintainability. The functionality was re-tested with the GPU power-up sequence, confirming the GPU powers up correctly and the driver probes successfully. [ 12.702370] powervr ffef400000.gpu: [drm] loaded firmware powervr/rogue_36.52.104.182_v1.fw [ 12.711043] powervr ffef400000.gpu: [drm] FW version v1.0 (build 6645434 OS) [ 12.719787] [drm] Initialized powervr 1.0.0 for ffef400000.gpu on minor 0 Fixes: e4b3cbd840e5 ("firmware: thead: Add AON firmware protocol driver") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/all/17a0ccce-060b-4b9d-a3c4-8d5d5823b1c9@stanley.mountain/ Signed-off-by: Michal Wilczynski Reviewed-by: Dan Carpenter Acked-by: Drew Fustini Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman (cherry picked from commit fbdb43f6bb2a15ed382d6eb0ef82c8b07b0d47bb) Signed-off-by: Wentao Guan --- drivers/firmware/thead,th1520-aon.c | 7 +- .../linux/firmware/thead/thead,th1520-aon.h | 74 ------------------- 2 files changed, 3 insertions(+), 78 deletions(-) diff --git a/drivers/firmware/thead,th1520-aon.c b/drivers/firmware/thead,th1520-aon.c index 38f812ac9920..b87d4e8235b1 100644 --- a/drivers/firmware/thead,th1520-aon.c +++ b/drivers/firmware/thead,th1520-aon.c @@ -170,10 +170,9 @@ int th1520_aon_power_update(struct th1520_aon_chan *aon_chan, u16 rsrc, hdr->func = TH1520_AON_PM_FUNC_SET_RESOURCE_POWER_MODE; hdr->size = TH1520_AON_RPC_MSG_NUM; - RPC_SET_BE16(&msg.resource, 0, rsrc); - RPC_SET_BE16(&msg.resource, 2, - (power_on ? TH1520_AON_PM_PW_MODE_ON : - TH1520_AON_PM_PW_MODE_OFF)); + msg.resource = cpu_to_be16(rsrc); + msg.mode = cpu_to_be16(power_on ? TH1520_AON_PM_PW_MODE_ON : + TH1520_AON_PM_PW_MODE_OFF); ret = th1520_aon_call_rpc(aon_chan, &msg); if (ret) diff --git a/include/linux/firmware/thead/thead,th1520-aon.h b/include/linux/firmware/thead/thead,th1520-aon.h index dae132b66873..d81f5f6f5b90 100644 --- a/include/linux/firmware/thead/thead,th1520-aon.h +++ b/include/linux/firmware/thead/thead,th1520-aon.h @@ -97,80 +97,6 @@ struct th1520_aon_rpc_ack_common { #define RPC_GET_SVC_FLAG_ACK_TYPE(MESG) (((MESG)->svc & 0x40) >> 6) #define RPC_SET_SVC_FLAG_ACK_TYPE(MESG, ACK) ((MESG)->svc |= (ACK) << 6) -#define RPC_SET_BE64(MESG, OFFSET, SET_DATA) \ - do { \ - u8 *data = (u8 *)(MESG); \ - u64 _offset = (OFFSET); \ - u64 _set_data = (SET_DATA); \ - data[_offset + 7] = _set_data & 0xFF; \ - data[_offset + 6] = (_set_data & 0xFF00) >> 8; \ - data[_offset + 5] = (_set_data & 0xFF0000) >> 16; \ - data[_offset + 4] = (_set_data & 0xFF000000) >> 24; \ - data[_offset + 3] = (_set_data & 0xFF00000000) >> 32; \ - data[_offset + 2] = (_set_data & 0xFF0000000000) >> 40; \ - data[_offset + 1] = (_set_data & 0xFF000000000000) >> 48; \ - data[_offset + 0] = (_set_data & 0xFF00000000000000) >> 56; \ - } while (0) - -#define RPC_SET_BE32(MESG, OFFSET, SET_DATA) \ - do { \ - u8 *data = (u8 *)(MESG); \ - u64 _offset = (OFFSET); \ - u64 _set_data = (SET_DATA); \ - data[_offset + 3] = (_set_data) & 0xFF; \ - data[_offset + 2] = (_set_data & 0xFF00) >> 8; \ - data[_offset + 1] = (_set_data & 0xFF0000) >> 16; \ - data[_offset + 0] = (_set_data & 0xFF000000) >> 24; \ - } while (0) - -#define RPC_SET_BE16(MESG, OFFSET, SET_DATA) \ - do { \ - u8 *data = (u8 *)(MESG); \ - u64 _offset = (OFFSET); \ - u64 _set_data = (SET_DATA); \ - data[_offset + 1] = (_set_data) & 0xFF; \ - data[_offset + 0] = (_set_data & 0xFF00) >> 8; \ - } while (0) - -#define RPC_SET_U8(MESG, OFFSET, SET_DATA) \ - do { \ - u8 *data = (u8 *)(MESG); \ - data[OFFSET] = (SET_DATA) & 0xFF; \ - } while (0) - -#define RPC_GET_BE64(MESG, OFFSET, PTR) \ - do { \ - u8 *data = (u8 *)(MESG); \ - u64 _offset = (OFFSET); \ - *(u32 *)(PTR) = \ - (data[_offset + 7] | data[_offset + 6] << 8 | \ - data[_offset + 5] << 16 | data[_offset + 4] << 24 | \ - data[_offset + 3] << 32 | data[_offset + 2] << 40 | \ - data[_offset + 1] << 48 | data[_offset + 0] << 56); \ - } while (0) - -#define RPC_GET_BE32(MESG, OFFSET, PTR) \ - do { \ - u8 *data = (u8 *)(MESG); \ - u64 _offset = (OFFSET); \ - *(u32 *)(PTR) = \ - (data[_offset + 3] | data[_offset + 2] << 8 | \ - data[_offset + 1] << 16 | data[_offset + 0] << 24); \ - } while (0) - -#define RPC_GET_BE16(MESG, OFFSET, PTR) \ - do { \ - u8 *data = (u8 *)(MESG); \ - u64 _offset = (OFFSET); \ - *(u16 *)(PTR) = (data[_offset + 1] | data[_offset + 0] << 8); \ - } while (0) - -#define RPC_GET_U8(MESG, OFFSET, PTR) \ - do { \ - u8 *data = (u8 *)(MESG); \ - *(u8 *)(PTR) = (data[OFFSET]); \ - } while (0) - /* * Defines for SC PM Power Mode */ From 66fef7528ac33b3ba547abd7fabb1259a3167a47 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Tue, 31 Mar 2026 18:07:39 -0700 Subject: [PATCH 22/85] workqueue: Add pool_workqueue to pending_pwqs list when unplugging multiple inactive works MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 703ccb63ae9f7444d6ff876d024e17f628103c69 upstream. In unplug_oldest_pwq(), the first inactive work item on the pool_workqueue is activated correctly. However, if multiple inactive works exist on the same pool_workqueue, subsequent works fail to activate because wq_node_nr_active.pending_pwqs is empty — the list insertion is skipped when the pool_workqueue is plugged. Fix this by checking for additional inactive works in unplug_oldest_pwq() and updating wq_node_nr_active.pending_pwqs accordingly. Fixes: 4c065dbce1e8 ("workqueue: Enable unbound cpumask update on ordered workqueues") Cc: stable@vger.kernel.org Cc: Carlos Santa Cc: Ryan Neph Cc: Lai Jiangshan Cc: Waiman Long Cc: linux-kernel@vger.kernel.org Signed-off-by: Matthew Brost Signed-off-by: Tejun Heo Acked-by: Waiman Long Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 0133aa1a28af222d124f7c289ac9abdcea5220ac) Signed-off-by: Wentao Guan --- kernel/workqueue.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 9111ef6ccfe6..751b8cba52fc 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1855,8 +1855,20 @@ static void unplug_oldest_pwq(struct workqueue_struct *wq) raw_spin_lock_irq(&pwq->pool->lock); if (pwq->plugged) { pwq->plugged = false; - if (pwq_activate_first_inactive(pwq, true)) + if (pwq_activate_first_inactive(pwq, true)) { + /* + * While plugged, queueing skips activation which + * includes bumping the nr_active count and adding the + * pwq to nna->pending_pwqs if the count can't be + * obtained. We need to restore both for the pwq being + * unplugged. The first call activates the first + * inactive work item and the second, if there are more + * inactive, puts the pwq on pending_pwqs. + */ + pwq_activate_first_inactive(pwq, false); + kick_pool(pwq->pool); + } } raw_spin_unlock_irq(&pwq->pool->lock); } From 9872a26eb65e3523fd8921702de377888afd75aa Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 25 Mar 2026 18:20:30 -0700 Subject: [PATCH 23/85] modpost: Declare extra_warn with unused attribute commit deb4605671cfae3b2803cfbbf4739e7245248398 upstream. A recent strengthening of -Wunused-but-set-variable (enabled with -Wall) in clang under a new subwarning, -Wunused-but-set-global, points out an unused static global variable in scripts/mod/modpost.c: scripts/mod/modpost.c:59:13: error: variable 'extra_warn' set but not used [-Werror,-Wunused-but-set-global] 59 | static bool extra_warn; | ^ This variable has been unused since commit 6c6c1fc09de3 ("modpost: require a MODULE_DESCRIPTION()") but that is expected, as there are currently no extra warnings at W=1 right now. Declare the variable with the unused attribute to make it clear to the compiler that this variable may be unused. Cc: stable@vger.kernel.org Fixes: 6c6c1fc09de3 ("modpost: require a MODULE_DESCRIPTION()") Link: https://patch.msgid.link/20260325-modpost-extra_warn-unused-but-set-global-v1-1-2e84003b7e81@kernel.org Reviewed-by: Nicolas Schier Signed-off-by: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 688c1b491c35d43fac013d5aa5490ae4c04a76a3) Signed-off-by: Wentao Guan --- scripts/mod/modpost.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 133dfa16308a..010c398f6a70 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -56,7 +56,7 @@ static bool allow_missing_ns_imports; static bool error_occurred; -static bool extra_warn; +static bool extra_warn __attribute__((unused)); bool target_is_big_endian; bool host_is_big_endian; From c79cf6804a0aaa2645b2a26731d0143d0aa311ae Mon Sep 17 00:00:00 2001 From: Yasuaki Torimaru Date: Thu, 26 Mar 2026 14:58:00 +0900 Subject: [PATCH 24/85] xfrm: clear trailing padding in build_polexpire() commit 71a98248c63c535eaa4d4c22f099b68d902006d0 upstream. build_expire() clears the trailing padding bytes of struct xfrm_user_expire after setting the hard field via memset_after(), but the analogous function build_polexpire() does not do this for struct xfrm_user_polexpire. The padding bytes after the __u8 hard field are left uninitialized from the heap allocation, and are then sent to userspace via netlink multicast to XFRMNLGRP_EXPIRE listeners, leaking kernel heap memory contents. Add the missing memset_after() call, matching build_expire(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Yasuaki Torimaru Reviewed-by: Simon Horman Reviewed-by: Breno Leitao Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman (cherry picked from commit b1dfd6b27df35ef4f87825aa5f607378d23ff0f2) Signed-off-by: Wentao Guan --- net/xfrm/xfrm_user.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c44bc4bf4cdf..306e4f65ce26 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -3951,6 +3951,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, return err; } upe->hard = !!hard; + /* clear the padding bytes */ + memset_after(upe, 0, hard); nlmsg_end(skb, nlh); return 0; From 1406e1e8ac831f9ea1352a6d1f3ade83e8b30987 Mon Sep 17 00:00:00 2001 From: Qi Tang Date: Thu, 2 Apr 2026 19:44:01 +0800 Subject: [PATCH 25/85] xfrm: hold dev ref until after transport_finish NF_HOOK commit 1c428b03840094410c5fb6a5db30640486bbbfcb upstream. After async crypto completes, xfrm_input_resume() calls dev_put() immediately on re-entry before the skb reaches transport_finish. The skb->dev pointer is then used inside NF_HOOK and its okfn, which can race with device teardown. Remove the dev_put from the async resumption entry and instead drop the reference after the NF_HOOK call in transport_finish, using a saved device pointer since NF_HOOK may consume the skb. This covers NF_DROP, NF_QUEUE and NF_STOLEN paths that skip the okfn. For non-transport exits (decaps, gro, drop) and secondary async return points, release the reference inline when async is set. Suggested-by: Florian Westphal Fixes: acf568ee859f ("xfrm: Reinject transport-mode packets through tasklet") Cc: stable@vger.kernel.org Signed-off-by: Qi Tang Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 0f451b43c88bf2b9c038b414be580efee42e031b) Signed-off-by: Wentao Guan --- net/ipv4/xfrm4_input.c | 5 ++++- net/ipv6/xfrm6_input.c | 5 ++++- net/xfrm/xfrm_input.c | 18 ++++++++++++++---- 3 files changed, 22 insertions(+), 6 deletions(-) diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index f28cfd88eaf5..c2eac844bcdb 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -50,6 +50,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) { struct xfrm_offload *xo = xfrm_offload(skb); struct iphdr *iph = ip_hdr(skb); + struct net_device *dev = skb->dev; iph->protocol = XFRM_MODE_SKB_CB(skb)->protocol; @@ -73,8 +74,10 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) } NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, skb->dev, NULL, + dev_net(dev), NULL, skb, dev, NULL, xfrm4_rcv_encap_finish); + if (async) + dev_put(dev); return 0; } diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 9005fc156a20..699a001ac166 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -43,6 +43,7 @@ static int xfrm6_transport_finish2(struct net *net, struct sock *sk, int xfrm6_transport_finish(struct sk_buff *skb, int async) { struct xfrm_offload *xo = xfrm_offload(skb); + struct net_device *dev = skb->dev; int nhlen = -skb_network_offset(skb); skb_network_header(skb)[IP6CB(skb)->nhoff] = @@ -68,8 +69,10 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) } NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, skb->dev, NULL, + dev_net(dev), NULL, skb, dev, NULL, xfrm6_transport_finish2); + if (async) + dev_put(dev); return 0; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index c9ddef869aa5..3d80c5210e04 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -503,7 +503,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) /* An encap_type of -1 indicates async resumption. */ if (encap_type == -1) { async = 1; - dev_put(skb->dev); seq = XFRM_SKB_CB(skb)->seq.input.low; goto resume; } @@ -656,8 +655,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) dev_hold(skb->dev); nexthdr = x->type->input(x, skb); - if (nexthdr == -EINPROGRESS) + if (nexthdr == -EINPROGRESS) { + if (async) + dev_put(skb->dev); return 0; + } dev_put(skb->dev); } @@ -692,9 +694,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_MODE_SKB_CB(skb)->protocol = nexthdr; err = xfrm_inner_mode_input(x, skb); - if (err == -EINPROGRESS) + if (err == -EINPROGRESS) { + if (async) + dev_put(skb->dev); return 0; - else if (err) { + } else if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } @@ -731,6 +735,8 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) sp->olen = 0; if (skb_valid_dst(skb)) skb_dst_drop(skb); + if (async) + dev_put(skb->dev); gro_cells_receive(&gro_cells, skb); return 0; } else { @@ -750,6 +756,8 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) sp->olen = 0; if (skb_valid_dst(skb)) skb_dst_drop(skb); + if (async) + dev_put(skb->dev); gro_cells_receive(&gro_cells, skb); return err; } @@ -760,6 +768,8 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) drop_unlock: spin_unlock(&x->lock); drop: + if (async) + dev_put(skb->dev); xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1); kfree_skb(skb); return 0; From de0cd98234e4c852d5567dc768f406ecf885519e Mon Sep 17 00:00:00 2001 From: Oleh Konko Date: Thu, 2 Apr 2026 09:48:57 +0000 Subject: [PATCH 26/85] tipc: fix bc_ackers underflow on duplicate GRP_ACK_MSG commit 48a5fe38772b6f039522469ee6131a67838221a8 upstream. The GRP_ACK_MSG handler in tipc_group_proto_rcv() currently decrements bc_ackers on every inbound group ACK, even when the same member has already acknowledged the current broadcast round. Because bc_ackers is a u16, a duplicate ACK received after the last legitimate ACK wraps the counter to 65535. Once wrapped, tipc_group_bc_cong() keeps reporting congestion and later group broadcasts on the affected socket stay blocked until the group is recreated. Fix this by ignoring duplicate or stale ACKs before touching bc_acked or bc_ackers. This makes repeated GRP_ACK_MSG handling idempotent and prevents the underflow path. Fixes: 2f487712b893 ("tipc: guarantee that group broadcast doesn't bypass group unicast") Cc: stable@vger.kernel.org Signed-off-by: Oleh Konko Reviewed-by: Tung Nguyen Reviewed-by: Simon Horman Link: https://patch.msgid.link/41a4833f368641218e444fdcff822039.security@1seal.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 1b6f13f626665cac67ba5a012765427680518711) Signed-off-by: Wentao Guan --- net/tipc/group.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/tipc/group.c b/net/tipc/group.c index 3e137d8c9d2f..215f2a7d8458 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -746,6 +746,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, u32 port = msg_origport(hdr); struct tipc_member *m, *pm; u16 remitted, in_flight; + u16 acked; if (!grp) return; @@ -798,7 +799,10 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, case GRP_ACK_MSG: if (!m) return; - m->bc_acked = msg_grp_bc_acked(hdr); + acked = msg_grp_bc_acked(hdr); + if (less_eq(acked, m->bc_acked)) + return; + m->bc_acked = acked; if (--grp->bc_ackers) return; list_del_init(&m->small_win); From b2eb96cac9abae9e6bd70c9193454cc55e5627f5 Mon Sep 17 00:00:00 2001 From: Thomas Fourier Date: Wed, 18 Feb 2026 14:07:37 +0100 Subject: [PATCH 27/85] wifi: brcmsmac: Fix dma_free_coherent() size commit 12cd7632757a54ce586e36040210b1a738a0fc53 upstream. dma_alloc_consistent() may change the size to align it. The new size is saved in alloced. Change the free size to match the allocation size. Fixes: 5b435de0d786 ("net: wireless: add brcm80211 drivers") Cc: Signed-off-by: Thomas Fourier Acked-by: Arend van Spriel Link: https://patch.msgid.link/20260218130741.46566-3-fourier.thomas@gmail.com Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman (cherry picked from commit b27fa888e4a426a3bcf6f6ab24701d888d9bf5aa) Signed-off-by: Wentao Guan --- drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c index c739bf7463b3..13d0d6b68238 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c @@ -483,7 +483,7 @@ static void *dma_ringalloc(struct dma_info *di, u32 boundary, uint size, if (((desc_strtaddr + size - 1) & boundary) != (desc_strtaddr & boundary)) { *alignbits = dma_align_sizetobits(size); - dma_free_coherent(di->dmadev, size, va, *descpa); + dma_free_coherent(di->dmadev, *alloced, va, *descpa); va = dma_alloc_consistent(di, size, *alignbits, alloced, descpa); } From 218691bd45f22cf28db4f61a464c8aa40276385b Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 25 Mar 2026 12:26:38 -0700 Subject: [PATCH 28/85] platform/x86: ISST: Reset core count to 0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit e1415b9418eb22b4a7a1ef4b4aec9dd0a49e3fa7 upstream. Based on feature revision, number of buckets can be less than the TRL_MAX_BUCKETS. In that case core counts in the remaining buckets can be set to some invalid values. Hence reset core count to 0 for all buckets before assigning correct values. Fixes: 885d1c2a30b7 ("platform/x86: ISST: Support SST-TF revision 2") Signed-off-by: Srinivas Pandruvada Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260325192638.3417281-1-srinivas.pandruvada@linux.intel.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Greg Kroah-Hartman (cherry picked from commit c4e1eff4606c7bf8c3289051f63f08ca65653ae2) Signed-off-by: Wentao Guan --- drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c index 77ecf9f26480..c8de8688daed 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c @@ -1460,6 +1460,8 @@ static int isst_if_get_turbo_freq_info(void __user *argp) SST_MUL_FACTOR_FREQ) } + memset(turbo_freq.bucket_core_counts, 0, sizeof(turbo_freq.bucket_core_counts)); + if (feature_rev >= 2) { bool has_tf_info_8 = false; From 275bd238435a57c6016f643d2a40900268386af8 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 25 Mar 2026 12:29:09 -0700 Subject: [PATCH 29/85] platform/x86/intel-uncore-freq: Handle autonomous UFS status bit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 4ab604b3f3aa8dcccc7505f5d310016682a99d5f upstream. When the AUTONOMOUS_UFS_DISABLED bit is set in the header, the ELC (Efficiency Latency Control) feature is non-functional. Hence, return error for read or write to ELC attributes. Fixes: bb516dc79c4a ("platform/x86/intel-uncore-freq: Add support for efficiency latency control") Signed-off-by: Srinivas Pandruvada Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260325192909.3417322-1-srinivas.pandruvada@linux.intel.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Greg Kroah-Hartman (cherry picked from commit fecceacbaf48219519c50d692d05de00e4689b7b) Signed-off-by: Wentao Guan --- .../x86/intel/uncore-frequency/uncore-frequency-tpmi.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c index 1237d9570886..4c7e64db478c 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c @@ -537,6 +537,7 @@ static void set_cdie_id(int domain_id, struct tpmi_uncore_cluster_info *cluster_ #define UNCORE_VERSION_MASK GENMASK_ULL(7, 0) #define UNCORE_LOCAL_FABRIC_CLUSTER_ID_MASK GENMASK_ULL(15, 8) #define UNCORE_CLUSTER_OFF_MASK GENMASK_ULL(7, 0) +#define UNCORE_AUTONOMOUS_UFS_DISABLED BIT(32) #define UNCORE_MAX_CLUSTER_PER_DOMAIN 8 static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id) @@ -598,6 +599,7 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_ for (i = 0; i < num_resources; ++i) { struct tpmi_uncore_power_domain_info *pd_info; + bool auto_ufs_enabled; struct resource *res; u64 cluster_offset; u8 cluster_mask; @@ -647,6 +649,8 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_ continue; } + auto_ufs_enabled = !(header & UNCORE_AUTONOMOUS_UFS_DISABLED); + /* Find out number of clusters in this resource */ pd_info->cluster_count = hweight8(cluster_mask); @@ -689,7 +693,9 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_ cluster_info->uncore_root = tpmi_uncore; - if (TPMI_MINOR_VERSION(pd_info->ufs_header_ver) >= UNCORE_ELC_SUPPORTED_VERSION) + if ((TPMI_MINOR_VERSION(pd_info->ufs_header_ver) >= + UNCORE_ELC_SUPPORTED_VERSION) && + auto_ufs_enabled) cluster_info->elc_supported = true; ret = uncore_freq_add_entry(&cluster_info->uncore_data, 0); From 5fb1a90022f137ce5afabf2075f261d4245ac1b9 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Tue, 10 Feb 2026 13:01:42 +0100 Subject: [PATCH 30/85] Revert "arm64: dts: rockchip: Further describe the WiFi for the Pinebook Pro" commit 29d1f56c4f3001b7f547123e0a307c009ac717f8 upstream. This reverts commit 6d54d935062e2d4a7d3f779ceb9eeff108d0535d. It seems there are different variants of the Wifi chipset in use on the Pinebook Pro. And according to the reported regression - see Closes below, the reverted change causes issues with one Wifi chipset. The original commit message indicates a "further description" only and does not indicate this would fix an actual problem, so a revert should not cause further problems. Fixes: 6d54d935062e ("arm64: dts: rockchip: Further describe the WiFi for the Pinebook Pro") Cc: Jan Palus Cc: Peter Robinson Cc: Thorsten Leemhuis Cc: stable@vger.kernel.org Closes: https://lore.kernel.org/r/aUKOlj-RvTYlrpiS@rock.grzadka/ Tested-by: Jan Palus Reviewed-by: Dragan Simic Signed-off-by: Heiko Stuebner Link: https://patch.msgid.link/20260210120142.698512-1-heiko@sntech.de Signed-off-by: Heiko Stuebner Signed-off-by: Greg Kroah-Hartman (cherry picked from commit aee881c21b576159c7a814f39604308895affcaa) Signed-off-by: Wentao Guan --- .../boot/dts/rockchip/rk3399-pinebook-pro.dts | 18 ------------------ 1 file changed, 18 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index a6ac89567baf..54abe0585ec5 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -879,12 +879,6 @@ }; }; - wifi { - wifi_host_wake_l: wifi-host-wake-l { - rockchip,pins = <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_none>; - }; - }; - wireless-bluetooth { bt_wake_pin: bt-wake-pin { rockchip,pins = <2 RK_PD3 RK_FUNC_GPIO &pcfg_pull_none>; @@ -942,19 +936,7 @@ pinctrl-names = "default"; pinctrl-0 = <&sdio0_bus4 &sdio0_cmd &sdio0_clk>; sd-uhs-sdr104; - #address-cells = <1>; - #size-cells = <0>; status = "okay"; - - brcmf: wifi@1 { - compatible = "brcm,bcm4329-fmac"; - reg = <1>; - interrupt-parent = <&gpio0>; - interrupts = ; - interrupt-names = "host-wake"; - pinctrl-names = "default"; - pinctrl-0 = <&wifi_host_wake_l>; - }; }; &sdhci { From 845d068de06e02c3de345f80d07baf9fb8fab3d1 Mon Sep 17 00:00:00 2001 From: Sebastian Krzyszkowiak Date: Sat, 21 Feb 2026 19:15:18 +0100 Subject: [PATCH 31/85] Revert "arm64: dts: imx8mq-librem5: Set the DVS voltages lower" commit 4cd46ea0eb4504f7f4fea92cb4601c5c9a3e545e upstream. This reverts commit c24a9b698fb02cd0723fa8375abab07f94b97b10. It's been found that there's a significant per-unit variance in accepted supply voltages and the current set still makes some units unstable. Revert back to nominal values. Cc: stable@vger.kernel.org Fixes: c24a9b698fb0 ("arm64: dts: imx8mq-librem5: Set the DVS voltages lower") Signed-off-by: Sebastian Krzyszkowiak Signed-off-by: Frank Li Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 3b31b15230b01f77d52760add62c4c6b7f7a8504) Signed-off-by: Wentao Guan --- .../boot/dts/freescale/imx8mq-librem5-r3.dts | 2 +- .../boot/dts/freescale/imx8mq-librem5.dtsi | 22 +++++-------------- 2 files changed, 7 insertions(+), 17 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5-r3.dts b/arch/arm64/boot/dts/freescale/imx8mq-librem5-r3.dts index 077c5cd2586f..4533a84fb0b9 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-librem5-r3.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5-r3.dts @@ -7,7 +7,7 @@ &a53_opp_table { opp-1000000000 { - opp-microvolt = <950000>; + opp-microvolt = <1000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi index 9e0e2d7271ef..2c481ad419c9 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi @@ -844,8 +844,8 @@ regulator-max-microvolt = <1300000>; regulator-boot-on; regulator-ramp-delay = <1250>; - rohm,dvs-run-voltage = <880000>; - rohm,dvs-idle-voltage = <820000>; + rohm,dvs-run-voltage = <900000>; + rohm,dvs-idle-voltage = <850000>; rohm,dvs-suspend-voltage = <810000>; regulator-always-on; }; @@ -856,8 +856,8 @@ regulator-max-microvolt = <1300000>; regulator-boot-on; regulator-ramp-delay = <1250>; - rohm,dvs-run-voltage = <950000>; - rohm,dvs-idle-voltage = <850000>; + rohm,dvs-run-voltage = <1000000>; + rohm,dvs-idle-voltage = <900000>; regulator-always-on; }; @@ -866,14 +866,14 @@ regulator-min-microvolt = <700000>; regulator-max-microvolt = <1300000>; regulator-boot-on; - rohm,dvs-run-voltage = <850000>; + rohm,dvs-run-voltage = <900000>; }; buck4_reg: BUCK4 { regulator-name = "buck4"; regulator-min-microvolt = <700000>; regulator-max-microvolt = <1300000>; - rohm,dvs-run-voltage = <930000>; + rohm,dvs-run-voltage = <1000000>; }; buck5_reg: BUCK5 { @@ -1407,13 +1407,3 @@ fsl,ext-reset-output; status = "okay"; }; - -&a53_opp_table { - opp-1000000000 { - opp-microvolt = <850000>; - }; - - opp-1500000000 { - opp-microvolt = <950000>; - }; -}; From 559c4b0bbac43e552f52f4dc3b1b56f2f59a0ff3 Mon Sep 17 00:00:00 2001 From: Sebastian Krzyszkowiak Date: Sat, 21 Feb 2026 19:15:19 +0100 Subject: [PATCH 32/85] arm64: dts: imx8mq-librem5: Bump BUCK1 suspend voltage up to 0.85V MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 511f76bf1dce5acf8907b65a7d1bc8f7e7c0d637 upstream. The minimal voltage of VDD_SOC sourced from BUCK1 is 0.81V, which is the currently set value. However, BD71837 only guarantees accuracy of ±0.01V, and this still doesn't factor other reasons for actual voltage to slightly drop in, resulting in the possibility of running out of the operational range. Bump the voltage up to 0.85V, which should give enough headroom. Cc: stable@vger.kernel.org Fixes: 8f0216b006e5 ("arm64: dts: Add a device tree for the Librem 5 phone") Signed-off-by: Sebastian Krzyszkowiak Signed-off-by: Frank Li Signed-off-by: Greg Kroah-Hartman (cherry picked from commit a4115c2abab3677d5ed81ea7738ead89fb6ccd9f) Signed-off-by: Wentao Guan --- arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi index 2c481ad419c9..e5f228517b6d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi @@ -846,7 +846,7 @@ regulator-ramp-delay = <1250>; rohm,dvs-run-voltage = <900000>; rohm,dvs-idle-voltage = <850000>; - rohm,dvs-suspend-voltage = <810000>; + rohm,dvs-suspend-voltage = <850000>; regulator-always-on; }; From 07f476959158124b76d78a802c552c3618ae5417 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Tue, 24 Mar 2026 15:33:28 +0100 Subject: [PATCH 33/85] arm64: dts: renesas: sparrow-hawk: Reserve first 128 MiB of DRAM commit ed8444006df9863ffa682e315352c44a49d9f4cb upstream. Mark the first 128 MiB of DRAM as reserved. The first 128 MiB of DRAM may optionally be used by TFA and other firmware for its own purposes, and in such case, Linux must not use this memory. On this platform, U-Boot runs in EL3 and starts TFA BL31 and Linux from a single combined fitImage. U-Boot has full access to all memory in the 0x40000000..0xbfffffff range, as well memory in the memory banks in the 64-bit address ranges, and therefore U-Boot patches this full complete view of platform memory layout into the DT that is passed to the next stage. The next stage is TFA BL31 and then the Linux kernel. The TFA BL31 does not modify the DT passed from U-Boot to TFA BL31 and then to Linux with any new reserved-memory {} node to reserve memory areas used by the TFA BL31 to prevent the next stage from using those areas, which lets Linux to use all of the available DRAM as described in the DT that was passed in by U-Boot, including the areas that are newly utilized by TFA BL31. In case of high DRAM utilization, for example in case of four instances of "memtester 3900M" running in parallel, unless the memory used by TFA BL31 is properly reserved, Linux may use and corrupt the memory used by TFA BL31, which would often lead to system becoming unresponsive. Until TFA BL31 can properly fill its own reserved-memory node into the DT, and to assure older versions of TFA BL31 do not cause problems, add explicitly reserved-memory {} node which prevents Linux from using the first 128 MiB of DRAM. Note that TFA BL31 can be adjusted to use different memory areas, this newly added reserved-memory {} node follows longer-term practice on the R-Car SoCs where the first 128 MiB of DRAM is reserved for firmware use. In case user does modify TFA BL31 to use different memory ranges, they must either use a future version of TFA BL31 which properly patches a reserved-memory {} node into the DT, or they must adjust the address ranges of this reserved-memory {} node accordingly. Fixes: a719915e76f2 ("arm64: dts: renesas: r8a779g3: Add Retronix R-Car V4H Sparrow Hawk board support") Cc: stable@vger.kernel.org Signed-off-by: Marek Vasut Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20260324143342.17872-1-marek.vasut+renesas@mailbox.org Signed-off-by: Geert Uytterhoeven Signed-off-by: Greg Kroah-Hartman (cherry picked from commit c82a3c9d9fb30ef0956391a605235c0e27120b66) Signed-off-by: Wentao Guan --- arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts b/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts index ff07d984cbf2..812b133cf29e 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts +++ b/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts @@ -118,6 +118,17 @@ reg = <0x6 0x00000000 0x1 0x00000000>; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + tfa@40000000 { + reg = <0x0 0x40000000 0x0 0x8000000>; + no-map; + }; + }; + /* Page 27 / DSI to Display */ dp-con { compatible = "dp-connector"; From 118986fdbc6eb2acc6e17e6b78eedaee1e7397ff Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Fri, 27 Feb 2026 15:19:58 +0800 Subject: [PATCH 34/85] arm64: dts: hisilicon: poplar: Correct PCIe reset GPIO polarity commit c1f2b0f2b5e37b2c27540a175aea2755a3799433 upstream. The PCIe reset GPIO on Poplar is actually active low. The active high worked before because kernel driver didn't respect the setting from DT. This is changed since commit 1d26a55fbeb9 ("PCI: histb: Switch to using gpiod API"), and thus PCIe on Poplar got brken since then. Fix the problem by correcting the polarity. Fixes: 32fa01761bd9 ("arm64: dts: hi3798cv200: enable PCIe support for poplar board") Cc: stable@vger.kernel.org Signed-off-by: Shawn Guo Signed-off-by: Wei Xu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit f0a0a6a8c1cc20353d018a6220701074f0dea24e) Signed-off-by: Wentao Guan --- arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts b/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts index 7d370dac4c85..579d55daa7d0 100644 --- a/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts +++ b/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts @@ -179,7 +179,7 @@ }; &pcie { - reset-gpios = <&gpio4 4 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio4 4 GPIO_ACTIVE_LOW>; vpcie-supply = <®_pcie>; status = "okay"; }; From 5c77c5f4b9dcd650457532c5207e2fb2130901a0 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Fri, 27 Feb 2026 15:22:10 +0800 Subject: [PATCH 35/85] arm64: dts: hisilicon: hi3798cv200: Add missing dma-ranges commit 1af997cad473d505248df6d9577183bb91f69670 upstream. Reboot starts failing on Poplar since commit 8424ecdde7df ("arm64: mm: Set ZONE_DMA size based on devicetree's dma-ranges"), which effectively changes zone_dma_bits from 30 to 32 for arm64 platforms that do not properly define dma-ranges in device tree. It's unclear how Poplar reboot gets broken by this change exactly, but a dma-ranges limiting zone_dma to the first 1 GB fixes the regression. Fixes: 2f20182ed670 ("arm64: dts: hisilicon: add dts files for hi3798cv200-poplar board") Cc: stable@vger.kernel.org Signed-off-by: Shawn Guo Signed-off-by: Wei Xu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 083c5a417dee0a60e793809e5be2387a0cfdbaf6) Signed-off-by: Wentao Guan --- arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi b/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi index f6bc001c3832..2f4ad5da5e33 100644 --- a/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi @@ -122,6 +122,7 @@ #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x0 0xf0000000 0x10000000>; + dma-ranges = <0x0 0x0 0x0 0x40000000>; crg: clock-reset-controller@8a22000 { compatible = "hisilicon,hi3798cv200-crg", "syscon", "simple-mfd"; From ff6a3b24e49418b3e1d2ff3de2ee6de3451a5832 Mon Sep 17 00:00:00 2001 From: Pengpeng Hou Date: Sun, 5 Apr 2026 08:40:00 +0800 Subject: [PATCH 36/85] nfc: pn533: allocate rx skb before consuming bytes commit c71ba669b570c7b3f86ec875be222ea11dacb352 upstream. pn532_receive_buf() reports the number of accepted bytes to the serdev core. The current code consumes bytes into recv_skb and may already hand a complete frame to pn533_recv_frame() before allocating a fresh receive buffer. If that alloc_skb() fails, the callback returns 0 even though it has already consumed bytes, and it leaves recv_skb as NULL for the next receive callback. That breaks the receive_buf() accounting contract and can also lead to a NULL dereference on the next skb_put_u8(). Allocate the receive skb lazily before consuming the next byte instead. If allocation fails, return the number of bytes already accepted. Fixes: c656aa4c27b1 ("nfc: pn533: add UART phy driver") Cc: stable@vger.kernel.org Signed-off-by: Pengpeng Hou Link: https://patch.msgid.link/20260405094003.3-pn533-v2-pengpeng@iscas.ac.cn Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 21ae2cda66a55c759607bbf1d23cbaa42019d2de) Signed-off-by: Wentao Guan --- drivers/nfc/pn533/uart.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c index 49c399a57175..3aacfc79fa72 100644 --- a/drivers/nfc/pn533/uart.c +++ b/drivers/nfc/pn533/uart.c @@ -211,6 +211,13 @@ static size_t pn532_receive_buf(struct serdev_device *serdev, timer_delete(&dev->cmd_timeout); for (i = 0; i < count; i++) { + if (!dev->recv_skb) { + dev->recv_skb = alloc_skb(PN532_UART_SKB_BUFF_LEN, + GFP_KERNEL); + if (!dev->recv_skb) + return i; + } + if (unlikely(!skb_tailroom(dev->recv_skb))) skb_trim(dev->recv_skb, 0); @@ -219,9 +226,7 @@ static size_t pn532_receive_buf(struct serdev_device *serdev, continue; pn533_recv_frame(dev->priv, dev->recv_skb, 0); - dev->recv_skb = alloc_skb(PN532_UART_SKB_BUFF_LEN, GFP_KERNEL); - if (!dev->recv_skb) - return 0; + dev->recv_skb = NULL; } return i; From 9797e6eaf97658e83948c33318ef0397bfad3540 Mon Sep 17 00:00:00 2001 From: Ruide Cao Date: Thu, 2 Apr 2026 23:12:31 +0800 Subject: [PATCH 37/85] batman-adv: reject oversized global TT response buffers commit 3a359bf5c61d52e7f09754108309d637532164a6 upstream. batadv_tt_prepare_tvlv_global_data() builds the allocation length for a global TT response in 16-bit temporaries. When a remote originator advertises a large enough global TT, the TT payload length plus the VLAN header offset can exceed 65535 and wrap before kmalloc(). The full-table response path still uses the original TT payload length when it fills tt_change, so the wrapped allocation is too small and batadv_tt_prepare_tvlv_global_data() writes past the end of the heap object before the later packet-size check runs. Fix this by rejecting TT responses whose TVLV value length cannot fit in the 16-bit TVLV payload length field. Fixes: 7ea7b4a14275 ("batman-adv: make the TT CRC logic VLAN specific") Cc: stable@vger.kernel.org Reported-by: Yifan Wu Reported-by: Juefei Pu Co-developed-by: Yuan Tan Signed-off-by: Yuan Tan Suggested-by: Xin Liu Tested-by: Ren Wei Signed-off-by: Ruide Cao Signed-off-by: Ren Wei Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Greg Kroah-Hartman (cherry picked from commit de6c1dc3c7d01a152607e6fcecee4d5288283f10) Signed-off-by: Wentao Guan --- net/batman-adv/translation-table.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 6e95e883c2bf..05cddcf994f6 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -798,8 +798,8 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, { u16 num_vlan = 0; u16 num_entries = 0; - u16 change_offset; - u16 tvlv_len; + u16 tvlv_len = 0; + unsigned int change_offset; struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_orig_node_vlan *vlan; u8 *tt_change_ptr; @@ -816,6 +816,11 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, if (*tt_len < 0) *tt_len = batadv_tt_len(num_entries); + if (change_offset > U16_MAX || *tt_len > U16_MAX - change_offset) { + *tt_len = 0; + goto out; + } + tvlv_len = *tt_len; tvlv_len += change_offset; From 207923ca3539cf99194a81a22e1c7a0554e68581 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Tue, 7 Apr 2026 12:58:18 +0200 Subject: [PATCH 38/85] X.509: Fix out-of-bounds access when parsing extensions commit d702c3408213bb12bd570bb97204d8340d141c51 upstream. Leo reports an out-of-bounds access when parsing a certificate with empty Basic Constraints or Key Usage extension because the first byte of the extension is read before checking its length. Fix it. The bug can be triggered by an unprivileged user by submitting a specially crafted certificate to the kernel through the keyrings(7) API. Leo has demonstrated this with a proof-of-concept program responsibly disclosed off-list. Fixes: 30eae2b037af ("KEYS: X.509: Parse Basic Constraints for CA") Fixes: 567671281a75 ("KEYS: X.509: Parse Key Usage") Reported-by: Leo Lin # off-list Signed-off-by: Lukas Wunner Reviewed-by: Ignat Korchagin Cc: stable@vger.kernel.org # v6.4+ Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 206121294b9cf27f0589857f80d64f87e496ffb2) Signed-off-by: Wentao Guan --- crypto/asymmetric_keys/x509_cert_parser.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c index 8df3fa60a44f..b56b0d3c443b 100644 --- a/crypto/asymmetric_keys/x509_cert_parser.c +++ b/crypto/asymmetric_keys/x509_cert_parser.c @@ -584,10 +584,10 @@ int x509_process_extension(void *context, size_t hdrlen, * 0x04 is where keyCertSign lands in this bit string * 0x80 is where digitalSignature lands in this bit string */ - if (v[0] != ASN1_BTS) - return -EBADMSG; if (vlen < 4) return -EBADMSG; + if (v[0] != ASN1_BTS) + return -EBADMSG; if (v[2] >= 8) return -EBADMSG; if (v[3] & 0x80) @@ -620,10 +620,10 @@ int x509_process_extension(void *context, size_t hdrlen, * (Expect 0xFF if the CA is TRUE) * vlen should match the entire extension size */ - if (v[0] != (ASN1_CONS_BIT | ASN1_SEQ)) - return -EBADMSG; if (vlen < 2) return -EBADMSG; + if (v[0] != (ASN1_CONS_BIT | ASN1_SEQ)) + return -EBADMSG; if (v[1] != vlen - 2) return -EBADMSG; /* Empty SEQUENCE means CA:FALSE (default value omitted per DER) */ From 940dc849e5e06007df9fb530eb9954d659ca705a Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Tue, 31 Mar 2026 14:16:23 +0200 Subject: [PATCH 39/85] EDAC/mc: Fix error path ordering in edac_mc_alloc() commit 51520e03e70d6c73e33ee7cbe0319767d05764fe upstream. When the mci->pvt_info allocation in edac_mc_alloc() fails, the error path will call put_device() which will end up calling the device's release function. However, the init ordering is wrong such that device_initialize() happens *after* the failed allocation and thus the device itself and the release function pointer are not initialized yet when they're called: MCE: In-kernel MCE decoding enabled. ------------[ cut here ]------------ kobject: '(null)': is not initialized, yet kobject_put() is being called. WARNING: lib/kobject.c:734 at kobject_put, CPU#22: systemd-udevd CPU: 22 UID: 0 PID: 538 Comm: systemd-udevd Not tainted 7.0.0-rc1+ #2 PREEMPT(full) RIP: 0010:kobject_put Call Trace: edac_mc_alloc+0xbe/0xe0 [edac_core] amd64_edac_init+0x7a4/0xff0 [amd64_edac] ? __pfx_amd64_edac_init+0x10/0x10 [amd64_edac] do_one_initcall ... Reorder the calling sequence so that the device is initialized and thus the release function pointer is properly set before it can be used. This was found by Claude while reviewing another EDAC patch. Fixes: 0bbb265f7089 ("EDAC/mc: Get rid of silly one-shot struct allocation in edac_mc_alloc()") Reported-by: Claude Code:claude-opus-4.5 Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Qiuxu Zhuo Cc: stable@kernel.org Link: https://patch.msgid.link/20260331121623.4871-1-bp@kernel.org Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 87ce8ae511962e105bcb3534944208c6a9471ed9) Signed-off-by: Wentao Guan --- drivers/edac/edac_mc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 0959320fe51c..b510919e49c0 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -370,13 +370,13 @@ struct mem_ctl_info *edac_mc_alloc(unsigned int mc_num, if (!mci->layers) goto error; + mci->dev.release = mci_release; + device_initialize(&mci->dev); + mci->pvt_info = kzalloc(sz_pvt, GFP_KERNEL); if (!mci->pvt_info) goto error; - mci->dev.release = mci_release; - device_initialize(&mci->dev); - /* setup index and various internal pointers */ mci->mc_idx = mc_num; mci->tot_dimms = tot_dimms; From 23faca188d72e9060f86378d159e953f404f41a6 Mon Sep 17 00:00:00 2001 From: Muhammad Alifa Ramdhan Date: Fri, 3 Apr 2026 09:36:17 +0800 Subject: [PATCH 40/85] net/tls: fix use-after-free in -EBUSY error path of tls_do_encryption commit a9b8b18364fffce4c451e6f6fd218fa4ab646705 upstream. The -EBUSY handling in tls_do_encryption(), introduced by commit 859054147318 ("net: tls: handle backlogging of crypto requests"), has a use-after-free due to double cleanup of encrypt_pending and the scatterlist entry. When crypto_aead_encrypt() returns -EBUSY, the request is enqueued to the cryptd backlog and the async callback tls_encrypt_done() will be invoked upon completion. That callback unconditionally restores the scatterlist entry (sge->offset, sge->length) and decrements ctx->encrypt_pending. However, if tls_encrypt_async_wait() returns an error, the synchronous error path in tls_do_encryption() performs the same cleanup again, double-decrementing encrypt_pending and double-restoring the scatterlist. The double-decrement corrupts the encrypt_pending sentinel (initialized to 1), making tls_encrypt_async_wait() permanently skip the wait for pending async callbacks. A subsequent sendmsg can then free the tls_rec via bpf_exec_tx_verdict() while a cryptd callback is still pending, resulting in a use-after-free when the callback fires on the freed record. Fix this by skipping the synchronous cleanup when the -EBUSY async wait returns an error, since the callback has already handled encrypt_pending and sge restoration. Fixes: 859054147318 ("net: tls: handle backlogging of crypto requests") Cc: stable@vger.kernel.org Signed-off-by: Muhammad Alifa Ramdhan Reviewed-by: Sabrina Dubroca Link: https://patch.msgid.link/20260403013617.2838875-1-ramdhan@starlabs.sg Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 5d70eb25b41e9b010828cd12818b06a0c3b04412) Signed-off-by: Wentao Guan --- net/tls/tls_sw.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index eecf1146c34f..16aaf41a8cc0 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -584,6 +584,16 @@ static int tls_do_encryption(struct sock *sk, if (rc == -EBUSY) { rc = tls_encrypt_async_wait(ctx); rc = rc ?: -EINPROGRESS; + /* + * The async callback tls_encrypt_done() has already + * decremented encrypt_pending and restored the sge on + * both success and error. Skip the synchronous cleanup + * below on error, just remove the record and return. + */ + if (rc != -EINPROGRESS) { + list_del(&rec->list); + return rc; + } } if (!rc || rc != -EINPROGRESS) { atomic_dec(&ctx->encrypt_pending); From 87c84f3fd213795e6ec121642e03c26dd1e240d7 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Wed, 1 Apr 2026 22:12:18 +0100 Subject: [PATCH 41/85] net: altera-tse: fix skb leak on DMA mapping error in tse_start_xmit() commit 6dede3967619b5944003227a5d09fdc21ed57d10 upstream. When dma_map_single() fails in tse_start_xmit(), the function returns NETDEV_TX_OK without freeing the skb. Since NETDEV_TX_OK tells the stack the packet was consumed, the skb is never freed, leaking memory on every DMA mapping failure. Add dev_kfree_skb_any() before returning to properly free the skb. Fixes: bbd2190ce96d ("Altera TSE: Add main and header file for Altera Ethernet Driver") Cc: stable@vger.kernel.org Signed-off-by: David Carlier Link: https://patch.msgid.link/20260401211218.279185-1-devnexen@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 60f462cd2716d86bd2174f9d5e035c9278f30480) Signed-off-by: Wentao Guan --- drivers/net/ethernet/altera/altera_tse_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 3f6204de9e6b..a5d61a9a225a 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -572,6 +572,7 @@ static netdev_tx_t tse_start_xmit(struct sk_buff *skb, struct net_device *dev) DMA_TO_DEVICE); if (dma_mapping_error(priv->device, dma_addr)) { netdev_err(priv->dev, "%s: DMA mapping error\n", __func__); + dev_kfree_skb_any(skb); ret = NETDEV_TX_OK; goto out; } From 7c2c12c6d2d267c228dbf507e5382aadf66a73af Mon Sep 17 00:00:00 2001 From: Haoze Xie Date: Mon, 6 Apr 2026 21:17:28 +0800 Subject: [PATCH 42/85] batman-adv: hold claim backbone gateways by reference commit 82d8701b2c930d0e96b0dbc9115a218d791cb0d2 upstream. batadv_bla_add_claim() can replace claim->backbone_gw and drop the old gateway's last reference while readers still follow the pointer. The netlink claim dump path dereferences claim->backbone_gw->orig and takes claim->backbone_gw->crc_lock without pinning the underlying backbone gateway. batadv_bla_check_claim() still has the same naked pointer access pattern. Reuse batadv_bla_claim_get_backbone_gw() in both readers so they operate on a stable gateway reference until the read-side work is complete. This keeps the dump and claim-check paths aligned with the lifetime rules introduced for the other BLA claim readers. Fixes: 23721387c409 ("batman-adv: add basic bridge loop avoidance code") Fixes: 04f3f5bf1883 ("batman-adv: add B.A.T.M.A.N. Dump BLA claims via netlink") Cc: stable@vger.kernel.org Reported-by: Yifan Wu Reported-by: Juefei Pu Co-developed-by: Yuan Tan Signed-off-by: Yuan Tan Suggested-by: Xin Liu Signed-off-by: Haoze Xie Signed-off-by: Ao Zhou Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 4dee4c0688443aaf5bbec74aa203c851d1d53c35) Signed-off-by: Wentao Guan --- net/batman-adv/bridge_loop_avoidance.c | 27 +++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index b992ba12aa24..d4f4e97a27f1 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -2165,6 +2165,7 @@ batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid, struct batadv_bla_claim *claim) { const u8 *primary_addr = primary_if->net_dev->dev_addr; + struct batadv_bla_backbone_gw *backbone_gw; u16 backbone_crc; bool is_own; void *hdr; @@ -2180,32 +2181,35 @@ batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid, genl_dump_check_consistent(cb, hdr); - is_own = batadv_compare_eth(claim->backbone_gw->orig, - primary_addr); + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); + + is_own = batadv_compare_eth(backbone_gw->orig, primary_addr); - spin_lock_bh(&claim->backbone_gw->crc_lock); - backbone_crc = claim->backbone_gw->crc; - spin_unlock_bh(&claim->backbone_gw->crc_lock); + spin_lock_bh(&backbone_gw->crc_lock); + backbone_crc = backbone_gw->crc; + spin_unlock_bh(&backbone_gw->crc_lock); if (is_own) if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) { genlmsg_cancel(msg, hdr); - goto out; + goto put_backbone_gw; } if (nla_put(msg, BATADV_ATTR_BLA_ADDRESS, ETH_ALEN, claim->addr) || nla_put_u16(msg, BATADV_ATTR_BLA_VID, claim->vid) || nla_put(msg, BATADV_ATTR_BLA_BACKBONE, ETH_ALEN, - claim->backbone_gw->orig) || + backbone_gw->orig) || nla_put_u16(msg, BATADV_ATTR_BLA_CRC, backbone_crc)) { genlmsg_cancel(msg, hdr); - goto out; + goto put_backbone_gw; } genlmsg_end(msg, hdr); ret = 0; +put_backbone_gw: + batadv_backbone_gw_put(backbone_gw); out: return ret; } @@ -2483,6 +2487,7 @@ int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb) bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr, unsigned short vid) { + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_bla_claim search_claim; struct batadv_bla_claim *claim = NULL; struct batadv_hard_iface *primary_if = NULL; @@ -2505,9 +2510,13 @@ bool batadv_bla_check_claim(struct batadv_priv *bat_priv, * return false. */ if (claim) { - if (!batadv_compare_eth(claim->backbone_gw->orig, + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); + + if (!batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr)) ret = false; + + batadv_backbone_gw_put(backbone_gw); batadv_claim_put(claim); } From 76e0efa54d0f491520dab5351bfff3c1fcfc5082 Mon Sep 17 00:00:00 2001 From: Sebastian Brzezinka Date: Wed, 1 Apr 2026 12:10:07 +0200 Subject: [PATCH 43/85] drm/i915/gt: fix refcount underflow in intel_engine_park_heartbeat commit 4c71fd099513bfa8acab529b626e1f0097b76061 upstream. A use-after-free / refcount underflow is possible when the heartbeat worker and intel_engine_park_heartbeat() race to release the same engine->heartbeat.systole request. The heartbeat worker reads engine->heartbeat.systole and calls i915_request_put() on it when the request is complete, but clears the pointer in a separate, non-atomic step. Concurrently, a request retirement on another CPU can drop the engine wakeref to zero, triggering __engine_park() -> intel_engine_park_heartbeat(). If the heartbeat timer is pending at that point, cancel_delayed_work() returns true and intel_engine_park_heartbeat() reads the stale non-NULL systole pointer and calls i915_request_put() on it again, causing a refcount underflow: ``` <4> [487.221889] Workqueue: i915-unordered engine_retire [i915] <4> [487.222640] RIP: 0010:refcount_warn_saturate+0x68/0xb0 ... <4> [487.222707] Call Trace: <4> [487.222711] <4> [487.222716] intel_engine_park_heartbeat.part.0+0x6f/0x80 [i915] <4> [487.223115] intel_engine_park_heartbeat+0x25/0x40 [i915] <4> [487.223566] __engine_park+0xb9/0x650 [i915] <4> [487.223973] ____intel_wakeref_put_last+0x2e/0xb0 [i915] <4> [487.224408] __intel_wakeref_put_last+0x72/0x90 [i915] <4> [487.224797] intel_context_exit_engine+0x7c/0x80 [i915] <4> [487.225238] intel_context_exit+0xf1/0x1b0 [i915] <4> [487.225695] i915_request_retire.part.0+0x1b9/0x530 [i915] <4> [487.226178] i915_request_retire+0x1c/0x40 [i915] <4> [487.226625] engine_retire+0x122/0x180 [i915] <4> [487.227037] process_one_work+0x239/0x760 <4> [487.227060] worker_thread+0x200/0x3f0 <4> [487.227068] ? __pfx_worker_thread+0x10/0x10 <4> [487.227075] kthread+0x10d/0x150 <4> [487.227083] ? __pfx_kthread+0x10/0x10 <4> [487.227092] ret_from_fork+0x3d4/0x480 <4> [487.227099] ? __pfx_kthread+0x10/0x10 <4> [487.227107] ret_from_fork_asm+0x1a/0x30 <4> [487.227141] ``` Fix this by replacing the non-atomic pointer read + separate clear with xchg() in both racing paths. xchg() is a single indivisible hardware instruction that atomically reads the old pointer and writes NULL. This guarantees only one of the two concurrent callers obtains the non-NULL pointer and performs the put, the other gets NULL and skips it. Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/work_items/15880 Fixes: 058179e72e09 ("drm/i915/gt: Replace hangcheck by heartbeats") Cc: # v5.5+ Signed-off-by: Sebastian Brzezinka Reviewed-by: Krzysztof Karas Reviewed-by: Andi Shyti Signed-off-by: Andi Shyti Link: https://lore.kernel.org/r/d4c1c14255688dd07cc8044973c4f032a8d1559e.1775038106.git.sebastian.brzezinka@intel.com (cherry picked from commit 13238dc0ee4f9ab8dafa2cca7295736191ae2f42) Signed-off-by: Joonas Lahtinen Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 2af8b200cae3fdd0e917ecc2753b28bb40c876c1) Signed-off-by: Wentao Guan --- .../gpu/drm/i915/gt/intel_engine_heartbeat.c | 26 +++++++++++++------ 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c index 8d4bb95f8424..cad81592c848 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c @@ -145,10 +145,12 @@ static void heartbeat(struct work_struct *wrk) /* Just in case everything has gone horribly wrong, give it a kick */ intel_engine_flush_submission(engine); - rq = engine->heartbeat.systole; - if (rq && i915_request_completed(rq)) { - i915_request_put(rq); - engine->heartbeat.systole = NULL; + rq = xchg(&engine->heartbeat.systole, NULL); + if (rq) { + if (i915_request_completed(rq)) + i915_request_put(rq); + else + engine->heartbeat.systole = rq; } if (!intel_engine_pm_get_if_awake(engine)) @@ -229,8 +231,11 @@ static void heartbeat(struct work_struct *wrk) unlock: mutex_unlock(&ce->timeline->mutex); out: - if (!engine->i915->params.enable_hangcheck || !next_heartbeat(engine)) - i915_request_put(fetch_and_zero(&engine->heartbeat.systole)); + if (!engine->i915->params.enable_hangcheck || !next_heartbeat(engine)) { + rq = xchg(&engine->heartbeat.systole, NULL); + if (rq) + i915_request_put(rq); + } intel_engine_pm_put(engine); } @@ -244,8 +249,13 @@ void intel_engine_unpark_heartbeat(struct intel_engine_cs *engine) void intel_engine_park_heartbeat(struct intel_engine_cs *engine) { - if (cancel_delayed_work(&engine->heartbeat.work)) - i915_request_put(fetch_and_zero(&engine->heartbeat.systole)); + if (cancel_delayed_work(&engine->heartbeat.work)) { + struct i915_request *rq; + + rq = xchg(&engine->heartbeat.systole, NULL); + if (rq) + i915_request_put(rq); + } } void intel_gt_unpark_heartbeats(struct intel_gt *gt) From fe5aecf207e7bec31df150c59de5f0e3e9c6fab1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jouni=20H=C3=B6gander?= Date: Fri, 27 Mar 2026 13:45:53 +0200 Subject: [PATCH 44/85] drm/i915/psr: Do not use pipe_src as borders for SU area MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 75519f5df2a9b23f7bf305e12dc9a6e3e65c24b7 upstream. This far using crtc_state->pipe_src as borders for Selective Update area haven't caused visible problems as drm_rect_width(crtc_state->pipe_src) == crtc_state->hw.adjusted_mode.crtc_hdisplay and drm_rect_height(crtc_state->pipe_src) == crtc_state->hw.adjusted_mode.crtc_vdisplay when pipe scaling is not used. On the other hand using pipe scaling is forcing full frame updates and all the Selective Update area calculations are skipped. Now this improper usage of crtc_state->pipe_src is causing following warnings: <4> [7771.978166] xe 0000:00:02.0: [drm] drm_WARN_ON_ONCE(su_lines % vdsc_cfg->slice_height) after WARN_ON_ONCE was added by commit: "drm/i915/dsc: Add helper for writing DSC Selective Update ET parameters" These warnings are seen when DSC and pipe scaling are enabled simultaneously. This is because on full frame update SU area is improperly set as pipe_src which is not aligned with DSC slice height. Fix these by creating local rectangle using crtc_state->hw.adjusted_mode.crtc_hdisplay and crtc_state->hw.adjusted_mode.crtc_vdisplay. Use this local rectangle as borders for SU area. Fixes: d6774b8c3c58 ("drm/i915: Ensure damage clip area is within pipe area") Cc: # v6.0+ Signed-off-by: Jouni Högander Reviewed-by: Mika Kahola Link: https://patch.msgid.link/20260327114553.195285-1-jouni.hogander@intel.com (cherry picked from commit da0cdc1c329dd2ff09c41fbbe9fbd9c92c5d2c6e) Signed-off-by: Joonas Lahtinen Signed-off-by: Greg Kroah-Hartman (cherry picked from commit de9aa7e89b98157d2650f25691e40711b8404151) Signed-off-by: Wentao Guan --- drivers/gpu/drm/i915/display/intel_psr.c | 30 +++++++++++++++--------- 1 file changed, 19 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 83299fd50ef0..504f6228bf35 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -2549,9 +2549,9 @@ static u32 psr2_pipe_srcsz_early_tpt_calc(struct intel_crtc_state *crtc_state, static void clip_area_update(struct drm_rect *overlap_damage_area, struct drm_rect *damage_area, - struct drm_rect *pipe_src) + struct drm_rect *display_area) { - if (!drm_rect_intersect(damage_area, pipe_src)) + if (!drm_rect_intersect(damage_area, display_area)) return; if (overlap_damage_area->y1 == -1) { @@ -2602,6 +2602,7 @@ static bool intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_st static void intel_psr2_sel_fetch_et_alignment(struct intel_atomic_state *state, struct intel_crtc *crtc, + struct drm_rect *display_area, bool *cursor_in_su_area) { struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); @@ -2629,7 +2630,7 @@ intel_psr2_sel_fetch_et_alignment(struct intel_atomic_state *state, continue; clip_area_update(&crtc_state->psr2_su_area, &new_plane_state->uapi.dst, - &crtc_state->pipe_src); + display_area); *cursor_in_su_area = true; } } @@ -2725,6 +2726,12 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct intel_plane_state *new_plane_state, *old_plane_state; struct intel_plane *plane; + struct drm_rect display_area = { + .x1 = 0, + .y1 = 0, + .x2 = crtc_state->hw.adjusted_mode.crtc_hdisplay, + .y2 = crtc_state->hw.adjusted_mode.crtc_vdisplay, + }; bool full_update = false, su_area_changed; int i, ret; @@ -2738,7 +2745,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, crtc_state->psr2_su_area.x1 = 0; crtc_state->psr2_su_area.y1 = -1; - crtc_state->psr2_su_area.x2 = drm_rect_width(&crtc_state->pipe_src); + crtc_state->psr2_su_area.x2 = drm_rect_width(&display_area); crtc_state->psr2_su_area.y2 = -1; /* @@ -2776,14 +2783,14 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, damaged_area.y1 = old_plane_state->uapi.dst.y1; damaged_area.y2 = old_plane_state->uapi.dst.y2; clip_area_update(&crtc_state->psr2_su_area, &damaged_area, - &crtc_state->pipe_src); + &display_area); } if (new_plane_state->uapi.visible) { damaged_area.y1 = new_plane_state->uapi.dst.y1; damaged_area.y2 = new_plane_state->uapi.dst.y2; clip_area_update(&crtc_state->psr2_su_area, &damaged_area, - &crtc_state->pipe_src); + &display_area); } continue; } else if (new_plane_state->uapi.alpha != old_plane_state->uapi.alpha) { @@ -2791,7 +2798,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, damaged_area.y1 = new_plane_state->uapi.dst.y1; damaged_area.y2 = new_plane_state->uapi.dst.y2; clip_area_update(&crtc_state->psr2_su_area, &damaged_area, - &crtc_state->pipe_src); + &display_area); continue; } @@ -2807,7 +2814,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, damaged_area.x1 += new_plane_state->uapi.dst.x1 - src.x1; damaged_area.x2 += new_plane_state->uapi.dst.x1 - src.x1; - clip_area_update(&crtc_state->psr2_su_area, &damaged_area, &crtc_state->pipe_src); + clip_area_update(&crtc_state->psr2_su_area, &damaged_area, &display_area); } /* @@ -2842,7 +2849,8 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, * cursor is added into affected planes even when * cursor is not updated by itself. */ - intel_psr2_sel_fetch_et_alignment(state, crtc, &cursor_in_su_area); + intel_psr2_sel_fetch_et_alignment(state, crtc, &display_area, + &cursor_in_su_area); su_area_changed = intel_psr2_sel_fetch_pipe_alignment(crtc_state); @@ -2918,8 +2926,8 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, skip_sel_fetch_set_loop: if (full_update) - clip_area_update(&crtc_state->psr2_su_area, &crtc_state->pipe_src, - &crtc_state->pipe_src); + clip_area_update(&crtc_state->psr2_su_area, &display_area, + &display_area); psr2_man_trk_ctl_calc(crtc_state, full_update); crtc_state->pipe_srcsz_early_tpt = From 4de2379319c9de7846618b0da3a6ee7758719dc7 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Fri, 3 Apr 2026 12:17:56 +0300 Subject: [PATCH 45/85] net/mlx5: Update the list of the PCI supported devices commit a9d4f4f6e65e0bf9bbddedecc84d67249991979c upstream. Add the upcoming ConnectX-10 NVLink-C2C device ID to the table of supported PCI device IDs. Cc: stable@vger.kernel.org Signed-off-by: Michael Guralnik Reviewed-by: Patrisious Haddad Signed-off-by: Tariq Toukan Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260403091756.139583-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 82e8174d1d0e5a6be49d33aedfa83327097f20b9) Signed-off-by: Wentao Guan --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index acba430a94da..5903a4af9173 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -2238,6 +2238,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1023) }, /* ConnectX-8 */ { PCI_VDEVICE(MELLANOX, 0x1025) }, /* ConnectX-9 */ { PCI_VDEVICE(MELLANOX, 0x1027) }, /* ConnectX-10 */ + { PCI_VDEVICE(MELLANOX, 0x2101) }, /* ConnectX-10 NVLink-C2C */ { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */ From fa2473028881632eb82b5c92459c77369684de41 Mon Sep 17 00:00:00 2001 From: Jacky Bai Date: Fri, 20 Mar 2026 16:43:46 +0800 Subject: [PATCH 46/85] pmdomain: imx8mp-blk-ctrl: Keep the NOC_HDCP clock enabled commit e91d5f94acf68618ea3ad9c92ac28614e791ae7d upstream. Keep the NOC_HDCP clock always enabled to fix the potential hang caused by the NoC ADB400 port power down handshake. Fixes: 77b0ddb42add ("soc: imx: add i.MX8MP HDMI blk ctrl HDCP/HRV_MWR") Signed-off-by: Jacky Bai Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman (cherry picked from commit e44919669f07b8f113ad49a248b44ca4f119bc94) Signed-off-by: Wentao Guan --- drivers/pmdomain/imx/imx8mp-blk-ctrl.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c index 8fc79f9723f0..3f5b9499d30a 100644 --- a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c +++ b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c @@ -352,9 +352,6 @@ static void imx8mp_hdmi_blk_ctrl_power_on(struct imx8mp_blk_ctrl *bc, regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(12)); regmap_clear_bits(bc->regmap, HDMI_TX_CONTROL0, BIT(3)); break; - case IMX8MP_HDMIBLK_PD_HDCP: - regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(11)); - break; case IMX8MP_HDMIBLK_PD_HRV: regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(3) | BIT(4) | BIT(5)); regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(15)); @@ -408,9 +405,6 @@ static void imx8mp_hdmi_blk_ctrl_power_off(struct imx8mp_blk_ctrl *bc, regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(7)); regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(22) | BIT(24)); break; - case IMX8MP_HDMIBLK_PD_HDCP: - regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(11)); - break; case IMX8MP_HDMIBLK_PD_HRV: regmap_clear_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(15)); regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(3) | BIT(4) | BIT(5)); @@ -439,7 +433,7 @@ static int imx8mp_hdmi_power_notifier(struct notifier_block *nb, regmap_write(bc->regmap, HDMI_RTX_CLK_CTL0, 0x0); regmap_write(bc->regmap, HDMI_RTX_CLK_CTL1, 0x0); regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL0, - BIT(0) | BIT(1) | BIT(10)); + BIT(0) | BIT(1) | BIT(10) | BIT(11)); regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(0)); /* From 54f881e2bffac2429b15a3cd156b4f8de867cea7 Mon Sep 17 00:00:00 2001 From: Alex Dvoretsky Date: Thu, 12 Mar 2026 14:52:55 +0100 Subject: [PATCH 47/85] igb: remove napi_synchronize() in igb_down() commit b1e067240379f950a0022208e0685f3465c211cb upstream. When an AF_XDP zero-copy application terminates abruptly (e.g., kill -9), the XSK buffer pool is destroyed but NAPI polling continues. igb_clean_rx_irq_zc() repeatedly returns the full budget, preventing napi_complete_done() from clearing NAPI_STATE_SCHED. igb_down() calls napi_synchronize() before napi_disable() for each queue vector. napi_synchronize() spins waiting for NAPI_STATE_SCHED to clear, which never happens. igb_down() blocks indefinitely, the TX watchdog fires, and the TX queue remains permanently stalled. napi_disable() already handles this correctly: it sets NAPI_STATE_DISABLE. After a full-budget poll, __napi_poll() checks napi_disable_pending(). If set, it forces completion and clears NAPI_STATE_SCHED, breaking the loop that napi_synchronize() cannot. napi_synchronize() was added in commit 41f149a285da ("igb: Fix possible panic caused by Rx traffic arrival while interface is down"). napi_disable() provides stronger guarantees: it prevents further scheduling and waits for any active poll to exit. Other Intel drivers (ixgbe, ice, i40e) use napi_disable() without a preceding napi_synchronize() in their down paths. Remove redundant napi_synchronize() call and reorder napi_disable() before igb_set_queue_napi() so the queue-to-NAPI mapping is only cleared after polling has fully stopped. Fixes: 2c6196013f84 ("igb: Add AF_XDP zero-copy Rx support") Cc: stable@vger.kernel.org Suggested-by: Maciej Fijalkowski Reviewed-by: Aleksandr Loktionov Signed-off-by: Alex Dvoretsky Reviewed-by: Maciej Fijalkowski Tested-by: Patryk Holda Signed-off-by: Tony Nguyen Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 4700471775746058c962ded6e659bf908fd76e13) Signed-off-by: Wentao Guan --- drivers/net/ethernet/intel/igb/igb_main.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index dbea37269d2c..33c6d61ef518 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2203,9 +2203,8 @@ void igb_down(struct igb_adapter *adapter) for (i = 0; i < adapter->num_q_vectors; i++) { if (adapter->q_vector[i]) { - napi_synchronize(&adapter->q_vector[i]->napi); - igb_set_queue_napi(adapter, i, NULL); napi_disable(&adapter->q_vector[i]->napi); + igb_set_queue_napi(adapter, i, NULL); } } From 73c776ff1af612172ae283ff85ee5832da823e1d Mon Sep 17 00:00:00 2001 From: Hao Li Date: Mon, 30 Mar 2026 11:57:49 +0800 Subject: [PATCH 48/85] mm/memory_hotplug: maintain N_NORMAL_MEMORY during hotplug commit 2ecbe06abf9bfb2261cd6464a6bc3a3615625402 upstream. N_NORMAL_MEMORY is initialized from zone population at boot, but memory hotplug currently only updates N_MEMORY. As a result, a node that gains normal memory via hotplug can remain invisible to users iterating over N_NORMAL_MEMORY, while a node that loses its last normal memory can stay incorrectly marked as such. The most visible effect is that /sys/devices/system/node/has_normal_memory does not report a node even after that node has gained normal memory via hotplug. Also, list_lru-based shrinkers can undercount objects on such a node and may skip reclaim on that node entirely, which can lead to a higher memory footprint than expected. Restore N_NORMAL_MEMORY maintenance directly in online_pages() and offline_pages(). Set the bit when a node that currently lacks normal memory onlines pages into a zone <= ZONE_NORMAL, and clear it when offlining removes the last present pages from zones <= ZONE_NORMAL. This restores the intended semantics without bringing back the old status_change_nid_normal notifier plumbing which was removed in 8d2882a8edb8. Current users that benefit include list_lru, zswap, nfsd filecache, hugetlb_cgroup, and has_normal_memory sysfs reporting. Link: https://lkml.kernel.org/r/20260330035941.518186-1-hao.li@linux.dev Fixes: 8d2882a8edb8 ("mm,memory_hotplug: remove status_change_nid_normal and update documentation") Signed-off-by: Hao Li Reviewed-by: Harry Yoo (Oracle) Acked-by: Vlastimil Babka (SUSE) Reviewed-by: Joshua Hahn Acked-by: David Hildenbrand (Arm) Cc: Oscar Salvador Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 49c00ae87230708cc4b39e718fab05013593b8ed) Signed-off-by: Wentao Guan --- mm/memory_hotplug.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0be83039c3b5..aa1f74414307 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1218,6 +1218,13 @@ int online_pages(unsigned long pfn, unsigned long nr_pages, if (node_arg.nid >= 0) node_set_state(nid, N_MEMORY); + /* + * Check whether we are adding normal memory to the node for the first + * time. + */ + if (!node_state(nid, N_NORMAL_MEMORY) && zone_idx(zone) <= ZONE_NORMAL) + node_set_state(nid, N_NORMAL_MEMORY); + if (need_zonelists_rebuild) build_all_zonelists(NULL); @@ -1919,6 +1926,8 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages, unsigned long flags; char *reason; int ret; + unsigned long normal_pages = 0; + enum zone_type zt; /* * {on,off}lining is constrained to full memory sections (or more @@ -2066,6 +2075,17 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages, /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); + /* + * Check whether this operation removes the last normal memory from + * the node. We do this before clearing N_MEMORY to avoid the possible + * transient "!N_MEMORY && N_NORMAL_MEMORY" state. + */ + if (zone_idx(zone) <= ZONE_NORMAL) { + for (zt = 0; zt <= ZONE_NORMAL; zt++) + normal_pages += pgdat->node_zones[zt].present_pages; + if (!normal_pages) + node_clear_state(node, N_NORMAL_MEMORY); + } /* * Make sure to mark the node as memory-less before rebuilding the zone * list. Otherwise this node would still appear in the fallback lists. From 8a1e9d3313170b9095e789b8539741d1967f4d41 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Thu, 26 Mar 2026 17:32:22 -0700 Subject: [PATCH 49/85] mm/damon/sysfs: dealloc repeat_call_control if damon_call() fails commit 0199390a6b92fc21860e1b858abf525c7e73b956 upstream. damon_call() for repeat_call_control of DAMON_SYSFS could fail if somehow the kdamond is stopped before the damon_call(). It could happen, for example, when te damon context was made for monitroing of a virtual address processes, and the process is terminated immediately, before the damon_call() invocation. In the case, the dyanmically allocated repeat_call_control is not deallocated and leaked. Fix the leak by deallocating the repeat_call_control under the damon_call() failure. This issue is discovered by sashiko [1]. Link: https://lkml.kernel.org/r/20260327003224.55752-1-sj@kernel.org Link: https://lore.kernel.org/20260320020630.962-1-sj@kernel.org [1] Fixes: 04a06b139ec0 ("mm/damon/sysfs: use dynamically allocated repeat mode damon_call_control") Signed-off-by: SeongJae Park Cc: [6.17+] Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman (cherry picked from commit b9dadf026a9fb681ed32a0646adc10ab485bf3b1) Signed-off-by: Wentao Guan --- mm/damon/sysfs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 4c0c8fdf450f..a6c3e83a3dad 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1623,7 +1623,8 @@ static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond) repeat_call_control->data = kdamond; repeat_call_control->repeat = true; repeat_call_control->dealloc_on_cancel = true; - damon_call(ctx, repeat_call_control); + if (damon_call(ctx, repeat_call_control)) + kfree(repeat_call_control); return err; } From 29aeaf5bbd1c6f2ef0294d60869a9539c144621b Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Thu, 2 Apr 2026 06:44:17 -0700 Subject: [PATCH 50/85] mm/damon/stat: deallocate damon_call() failure leaking damon_ctx MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 4c04c6b47c361612b1d70cec8f7a60b1482d1400 upstream. damon_stat_start() always allocates the module's damon_ctx object (damon_stat_context). Meanwhile, if damon_call() in the function fails, the damon_ctx object is not deallocated. Hence, if the damon_call() is failed, and the user writes Y to “enabled” again, the previously allocated damon_ctx object is leaked. This cannot simply be fixed by deallocating the damon_ctx object when damon_call() fails. That's because damon_call() failure doesn't guarantee the kdamond main function, which accesses the damon_ctx object, is completely finished. In other words, if damon_stat_start() deallocates the damon_ctx object after damon_call() failure, the not-yet-terminated kdamond could access the freed memory (use-after-free). Fix the leak while avoiding the use-after-free by keeping returning damon_stat_start() without deallocating the damon_ctx object after damon_call() failure, but deallocating it when the function is invoked again and the kdamond is completely terminated. If the kdamond is not yet terminated, simply return -EAGAIN, as the kdamond will soon be terminated. The issue was discovered [1] by sashiko. Link: https://lkml.kernel.org/r/20260402134418.74121-1-sj@kernel.org Link: https://lore.kernel.org/20260401012428.86694-1-sj@kernel.org [1] Fixes: 405f61996d9d ("mm/damon/stat: use damon_call() repeat mode instead of damon_callback") Signed-off-by: SeongJae Park Cc: # 6.17.x Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 447f8870b484f6596d7a7130e72bd0a3f1e037bb) Signed-off-by: Wentao Guan --- mm/damon/stat.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/mm/damon/stat.c b/mm/damon/stat.c index a8d6a3049830..3a55f6e41dc4 100644 --- a/mm/damon/stat.c +++ b/mm/damon/stat.c @@ -237,6 +237,12 @@ static int damon_stat_start(void) { int err; + if (damon_stat_context) { + if (damon_is_running(damon_stat_context)) + return -EAGAIN; + damon_destroy_ctx(damon_stat_context); + } + damon_stat_context = damon_stat_build_ctx(); if (!damon_stat_context) return -ENOMEM; @@ -253,6 +259,7 @@ static void damon_stat_stop(void) { damon_stop(&damon_stat_context, 1); damon_destroy_ctx(damon_stat_context); + damon_stat_context = NULL; } static int damon_stat_enabled_store( From de52e69f14ebf60baba8cbe553861d020b384fe5 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 27 Mar 2026 11:52:05 +0100 Subject: [PATCH 51/85] mmc: vub300: fix NULL-deref on disconnect commit dff34ef879c5e73298443956a8b391311ba78d57 upstream. Make sure to deregister the controller before dropping the reference to the driver data on disconnect to avoid NULL-pointer dereferences or use-after-free. Fixes: 88095e7b473a ("mmc: Add new VUB300 USB-to-SD/SDIO/MMC driver") Cc: stable@vger.kernel.org # 3.0+ Signed-off-by: Johan Hovold Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman (cherry picked from commit c83a282615d8f7ba28cebddd54600b419d562d82) Signed-off-by: Wentao Guan --- drivers/mmc/host/vub300.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index ff49d0770506..f173c7cf4e1a 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -2365,8 +2365,8 @@ static void vub300_disconnect(struct usb_interface *interface) usb_set_intfdata(interface, NULL); /* prevent more I/O from starting */ vub300->interface = NULL; - kref_put(&vub300->kref, vub300_delete); mmc_remove_host(mmc); + kref_put(&vub300->kref, vub300_delete); pr_info("USB vub300 remote SDIO host controller[%d]" " now disconnected", ifnum); return; From 975d1b72e12d9a66f82d5cc87469c8271dfaee50 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 27 Mar 2026 11:52:06 +0100 Subject: [PATCH 52/85] mmc: vub300: fix use-after-free on disconnect commit 8f4d20a710225ec7a565f6a0459862d3b1f32330 upstream. The vub300 driver maintains an explicit reference count for the controller and its driver data and the last reference can in theory be dropped after the driver has been unbound. This specifically means that the controller allocation must not be device managed as that can lead to use-after-free. Note that the lifetime is currently also incorrectly tied the parent USB device rather than interface, which can lead to memory leaks if the driver is unbound without its device being physically disconnected (e.g. on probe deferral). Fix both issues by reverting to non-managed allocation of the controller. Fixes: dcfdd698dc52 ("mmc: vub300: Use devm_mmc_alloc_host() helper") Cc: stable@vger.kernel.org # 6.17+ Cc: Binbin Zhou Signed-off-by: Johan Hovold Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman (cherry picked from commit ea7468f61be033f4e18b95f2912010ed1d175d75) Signed-off-by: Wentao Guan --- drivers/mmc/host/vub300.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index f173c7cf4e1a..3c9df27f9fa7 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -369,11 +369,14 @@ struct vub300_mmc_host { static void vub300_delete(struct kref *kref) { /* kref callback - softirq */ struct vub300_mmc_host *vub300 = kref_to_vub300_mmc_host(kref); + struct mmc_host *mmc = vub300->mmc; + usb_free_urb(vub300->command_out_urb); vub300->command_out_urb = NULL; usb_free_urb(vub300->command_res_urb); vub300->command_res_urb = NULL; usb_put_dev(vub300->udev); + mmc_free_host(mmc); /* * and hence also frees vub300 * which is contained at the end of struct mmc @@ -2112,7 +2115,7 @@ static int vub300_probe(struct usb_interface *interface, goto error1; } /* this also allocates memory for our VUB300 mmc host device */ - mmc = devm_mmc_alloc_host(&udev->dev, sizeof(*vub300)); + mmc = mmc_alloc_host(sizeof(*vub300), &udev->dev); if (!mmc) { retval = -ENOMEM; dev_err(&udev->dev, "not enough memory for the mmc_host\n"); @@ -2269,7 +2272,7 @@ static int vub300_probe(struct usb_interface *interface, dev_err(&vub300->udev->dev, "Could not find two sets of bulk-in/out endpoint pairs\n"); retval = -EINVAL; - goto error4; + goto err_free_host; } retval = usb_control_msg(vub300->udev, usb_rcvctrlpipe(vub300->udev, 0), @@ -2278,14 +2281,14 @@ static int vub300_probe(struct usb_interface *interface, 0x0000, 0x0000, &vub300->hc_info, sizeof(vub300->hc_info), 1000); if (retval < 0) - goto error4; + goto err_free_host; retval = usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0), SET_ROM_WAIT_STATES, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, firmware_rom_wait_states, 0x0000, NULL, 0, 1000); if (retval < 0) - goto error4; + goto err_free_host; dev_info(&vub300->udev->dev, "operating_mode = %s %s %d MHz %s %d byte USB packets\n", (mmc->caps & MMC_CAP_SDIO_IRQ) ? "IRQs" : "POLL", @@ -2300,7 +2303,7 @@ static int vub300_probe(struct usb_interface *interface, 0x0000, 0x0000, &vub300->system_port_status, sizeof(vub300->system_port_status), 1000); if (retval < 0) { - goto error4; + goto err_free_host; } else if (sizeof(vub300->system_port_status) == retval) { vub300->card_present = (0x0001 & vub300->system_port_status.port_flags) ? 1 : 0; @@ -2308,7 +2311,7 @@ static int vub300_probe(struct usb_interface *interface, (0x0010 & vub300->system_port_status.port_flags) ? 1 : 0; } else { retval = -EINVAL; - goto error4; + goto err_free_host; } usb_set_intfdata(interface, vub300); INIT_DELAYED_WORK(&vub300->pollwork, vub300_pollwork_thread); @@ -2338,6 +2341,8 @@ static int vub300_probe(struct usb_interface *interface, return 0; error6: timer_delete_sync(&vub300->inactivity_timer); +err_free_host: + mmc_free_host(mmc); /* * and hence also frees vub300 * which is contained at the end of struct mmc From c4e852c4a25ced6440b59436e41937d1f3d8ce70 Mon Sep 17 00:00:00 2001 From: Pengpeng Hou Date: Thu, 2 Apr 2026 15:12:07 +0800 Subject: [PATCH 53/85] net: qualcomm: qca_uart: report the consumed byte on RX skb allocation failure commit b76254c55dc8f23edc089027dd3f8792554c69fb upstream. qca_tty_receive() consumes each input byte before checking whether a completed frame needs a fresh receive skb. When the current byte completes a frame, the driver delivers that frame and then allocates a new skb for the next one. If that allocation fails, the current code returns i even though data[i] has already been consumed and may already have completed the delivered frame. Since serdev interprets the return value as the number of accepted bytes, this under-reports progress by one byte and can replay the final byte of the completed frame into a fresh parser state on the next call. Return i + 1 in that failure path so the accepted-byte count matches the actual receive-state progress. Fixes: dfc768fbe618 ("net: qualcomm: add QCA7000 UART driver") Cc: stable@vger.kernel.org Signed-off-by: Pengpeng Hou Reviewed-by: Stefan Wahren Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260402071207.4036-1-pengpeng@iscas.ac.cn Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 9fdece45f6e097eaea0e721057ad7ee5c01fc2b2) Signed-off-by: Wentao Guan --- drivers/net/ethernet/qualcomm/qca_uart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c index 37efb1ea9fcd..847a5f928e41 100644 --- a/drivers/net/ethernet/qualcomm/qca_uart.c +++ b/drivers/net/ethernet/qualcomm/qca_uart.c @@ -100,7 +100,7 @@ qca_tty_receive(struct serdev_device *serdev, const u8 *data, size_t count) if (!qca->rx_skb) { netdev_dbg(netdev, "recv: out of RX resources\n"); n_stats->rx_errors++; - return i; + return i + 1; } } } From 68c767408dc780d9930062884f5bdd433356fe34 Mon Sep 17 00:00:00 2001 From: Tyllis Xu Date: Tue, 31 Mar 2026 23:47:07 -0500 Subject: [PATCH 54/85] net: stmmac: fix integer underflow in chain mode commit 51f4e090b9f87b40c21b6daadb5c06e6c0a07b67 upstream. The jumbo_frm() chain-mode implementation unconditionally computes len = nopaged_len - bmax; where nopaged_len = skb_headlen(skb) (linear bytes only) and bmax is BUF_SIZE_8KiB or BUF_SIZE_2KiB. However, the caller stmmac_xmit() decides to invoke jumbo_frm() based on skb->len (total length including page fragments): is_jumbo = stmmac_is_jumbo_frm(priv, skb->len, enh_desc); When a packet has a small linear portion (nopaged_len <= bmax) but a large total length due to page fragments (skb->len > bmax), the subtraction wraps as an unsigned integer, producing a huge len value (~0xFFFFxxxx). This causes the while (len != 0) loop to execute hundreds of thousands of iterations, passing skb->data + bmax * i pointers far beyond the skb buffer to dma_map_single(). On IOMMU-less SoCs (the typical deployment for stmmac), this maps arbitrary kernel memory to the DMA engine, constituting a kernel memory disclosure and potential memory corruption from hardware. Fix this by introducing a buf_len local variable clamped to min(nopaged_len, bmax). Computing len = nopaged_len - buf_len is then always safe: it is zero when the linear portion fits within a single descriptor, causing the while (len != 0) loop to be skipped naturally, and the fragment loop in stmmac_xmit() handles page fragments afterward. Fixes: 286a83721720 ("stmmac: add CHAINED descriptor mode support (V4)") Cc: stable@vger.kernel.org Signed-off-by: Tyllis Xu Link: https://patch.msgid.link/20260401044708.1386919-1-LivelyCarpet87@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 6fca757c20396dc2e604dcc61922264e9e3dc803) Signed-off-by: Wentao Guan --- drivers/net/ethernet/stmicro/stmmac/chain_mode.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c index fb55efd52240..1c01e3c640ce 100644 --- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c @@ -20,7 +20,7 @@ static int jumbo_frm(struct stmmac_tx_queue *tx_q, struct sk_buff *skb, unsigned int nopaged_len = skb_headlen(skb); struct stmmac_priv *priv = tx_q->priv_data; unsigned int entry = tx_q->cur_tx; - unsigned int bmax, des2; + unsigned int bmax, buf_len, des2; unsigned int i = 1, len; struct dma_desc *desc; @@ -31,17 +31,18 @@ static int jumbo_frm(struct stmmac_tx_queue *tx_q, struct sk_buff *skb, else bmax = BUF_SIZE_2KiB; - len = nopaged_len - bmax; + buf_len = min_t(unsigned int, nopaged_len, bmax); + len = nopaged_len - buf_len; des2 = dma_map_single(priv->device, skb->data, - bmax, DMA_TO_DEVICE); + buf_len, DMA_TO_DEVICE); desc->des2 = cpu_to_le32(des2); if (dma_mapping_error(priv->device, des2)) return -1; tx_q->tx_skbuff_dma[entry].buf = des2; - tx_q->tx_skbuff_dma[entry].len = bmax; + tx_q->tx_skbuff_dma[entry].len = buf_len; /* do not close the descriptor and do not set own bit */ - stmmac_prepare_tx_desc(priv, desc, 1, bmax, csum, STMMAC_CHAIN_MODE, + stmmac_prepare_tx_desc(priv, desc, 1, buf_len, csum, STMMAC_CHAIN_MODE, 0, false, skb->len); while (len != 0) { From 370e76599e592e9c76811cdf6f102e62d8a1e276 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Tue, 17 Mar 2026 17:29:55 +0800 Subject: [PATCH 55/85] mm: filemap: fix nr_pages calculation overflow in filemap_map_pages() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f58df566524ebcdfa394329c64f47e3c9257516e upstream. When running stress-ng on my Arm64 machine with v7.0-rc3 kernel, I encountered some very strange crash issues showing up as "Bad page state": " [ 734.496287] BUG: Bad page state in process stress-ng-env pfn:415735fb [ 734.496427] page: refcount:0 mapcount:1 mapping:0000000000000000 index:0x4cf316 pfn:0x415735fb [ 734.496434] flags: 0x57fffe000000800(owner_2|node=1|zone=2|lastcpupid=0x3ffff) [ 734.496439] raw: 057fffe000000800 0000000000000000 dead000000000122 0000000000000000 [ 734.496440] raw: 00000000004cf316 0000000000000000 0000000000000000 0000000000000000 [ 734.496442] page dumped because: nonzero mapcount " After analyzing this page’s state, it is hard to understand why the mapcount is not 0 while the refcount is 0, since this page is not where the issue first occurred. By enabling the CONFIG_DEBUG_VM config, I can reproduce the crash as well and captured the first warning where the issue appears: " [ 734.469226] page: refcount:33 mapcount:0 mapping:00000000bef2d187 index:0x81a0 pfn:0x415735c0 [ 734.469304] head: order:5 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ 734.469315] memcg:ffff000807a8ec00 [ 734.469320] aops:ext4_da_aops ino:100b6f dentry name(?):"stress-ng-mmaptorture-9397-0-2736200540" [ 734.469335] flags: 0x57fffe400000069(locked|uptodate|lru|head|node=1|zone=2|lastcpupid=0x3ffff) ...... [ 734.469364] page dumped because: VM_WARN_ON_FOLIO((_Generic((page + nr_pages - 1), const struct page *: (const struct folio *)_compound_head(page + nr_pages - 1), struct page *: (struct folio *)_compound_head(page + nr_pages - 1))) != folio) [ 734.469390] ------------[ cut here ]------------ [ 734.469393] WARNING: ./include/linux/rmap.h:351 at folio_add_file_rmap_ptes+0x3b8/0x468, CPU#90: stress-ng-mlock/9430 [ 734.469551] folio_add_file_rmap_ptes+0x3b8/0x468 (P) [ 734.469555] set_pte_range+0xd8/0x2f8 [ 734.469566] filemap_map_folio_range+0x190/0x400 [ 734.469579] filemap_map_pages+0x348/0x638 [ 734.469583] do_fault_around+0x140/0x198 ...... [ 734.469640] el0t_64_sync+0x184/0x188 " The code that triggers the warning is: "VM_WARN_ON_FOLIO(page_folio(page + nr_pages - 1) != folio, folio)", which indicates that set_pte_range() tried to map beyond the large folio’s size. By adding more debug information, I found that 'nr_pages' had overflowed in filemap_map_pages(), causing set_pte_range() to establish mappings for a range exceeding the folio size, potentially corrupting fields of pages that do not belong to this folio (e.g., page->_mapcount). After above analysis, I think the possible race is as follows: CPU 0 CPU 1 filemap_map_pages() ext4_setattr() //get and lock folio with old inode->i_size next_uptodate_folio() ....... //shrink the inode->i_size i_size_write(inode, attr->ia_size); //calculate the end_pgoff with the new inode->i_size file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; end_pgoff = min(end_pgoff, file_end); ...... //nr_pages can be overflowed, cause xas.xa_index > end_pgoff end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; ...... //map large folio filemap_map_folio_range() ...... //truncate folios truncate_pagecache(inode, inode->i_size); To fix this issue, move the 'end_pgoff' calculation before next_uptodate_folio(), so the retrieved folio stays consistent with the file end to avoid 'nr_pages' calculation overflow. After this patch, the crash issue is gone. Link: https://lkml.kernel.org/r/1cf1ac59018fc647a87b0dad605d4056a71c14e4.1773739704.git.baolin.wang@linux.alibaba.com Fixes: 743a2753a02e ("filemap: cap PTE range to be created to allowed zero fill in folio_map_range()") Signed-off-by: Baolin Wang Reported-by: Yuanhe Shu Tested-by: Yuanhe Shu Acked-by: Kiryl Shutsemau (Meta) Acked-by: David Hildenbrand (Arm) Cc: Christian Brauner Cc: Daniel Gomez Cc: "Darrick J. Wong" Cc: Dave Chinner Cc: David Howells Cc: Hannes Reinecke Cc: Lorenzo Stoakes (Oracle) Cc: Luis Chamberalin Cc: Matthew Wilcox (Oracle) Cc: Pankaj Raghav Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 576543bedd616254032d4ebe54a90076f9e31740) Signed-off-by: Wentao Guan --- mm/filemap.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index 8a7f4ce69aff..91dcfe14a67b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3823,14 +3823,19 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, unsigned int nr_pages = 0, folio_type; unsigned short mmap_miss = 0, mmap_miss_saved; + /* + * Recalculate end_pgoff based on file_end before calling + * next_uptodate_folio() to avoid races with concurrent + * truncation. + */ + file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; + end_pgoff = min(end_pgoff, file_end); + rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); if (!folio) goto out; - file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; - end_pgoff = min(end_pgoff, file_end); - /* * Do not allow to map with PMD across i_size to preserve * SIGBUS semantics. From e49ee6840a0d18d5318b5a4160cdc2731fe7b38b Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Thu, 19 Mar 2026 14:13:33 -0700 Subject: [PATCH 56/85] idpf: fix PREEMPT_RT raw/bh spinlock nesting for async VC handling commit 591478118293c1bd628de330a99eb1eb2ef8d76b upstream. Switch from using the completion's raw spinlock to a local lock in the idpf_vc_xn struct. The conversion is safe because complete/_all() are called outside the lock and there is no reason to share the completion lock in the current logic. This avoids invalid wait context reported by the kernel due to the async handler taking BH spinlock: [ 805.726977] ============================= [ 805.726991] [ BUG: Invalid wait context ] [ 805.727006] 7.0.0-rc2-net-devq-031026+ #28 Tainted: G S OE [ 805.727026] ----------------------------- [ 805.727038] kworker/u261:0/572 is trying to lock: [ 805.727051] ff190da6a8dbb6a0 (&vport_config->mac_filter_list_lock){+...}-{3:3}, at: idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727099] other info that might help us debug this: [ 805.727111] context-{5:5} [ 805.727119] 3 locks held by kworker/u261:0/572: [ 805.727132] #0: ff190da6db3e6148 ((wq_completion)idpf-0000:83:00.0-mbx){+.+.}-{0:0}, at: process_one_work+0x4b5/0x730 [ 805.727163] #1: ff3c6f0a6131fe50 ((work_completion)(&(&adapter->mbx_task)->work)){+.+.}-{0:0}, at: process_one_work+0x1e5/0x730 [ 805.727191] #2: ff190da765190020 (&x->wait#34){+.+.}-{2:2}, at: idpf_recv_mb_msg+0xc8/0x710 [idpf] [ 805.727218] stack backtrace: ... [ 805.727238] Workqueue: idpf-0000:83:00.0-mbx idpf_mbx_task [idpf] [ 805.727247] Call Trace: [ 805.727249] [ 805.727251] dump_stack_lvl+0x77/0xb0 [ 805.727259] __lock_acquire+0xb3b/0x2290 [ 805.727268] ? __irq_work_queue_local+0x59/0x130 [ 805.727275] lock_acquire+0xc6/0x2f0 [ 805.727277] ? idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727284] ? _printk+0x5b/0x80 [ 805.727290] _raw_spin_lock_bh+0x38/0x50 [ 805.727298] ? idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727303] idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727310] idpf_recv_mb_msg+0x1c8/0x710 [idpf] [ 805.727317] process_one_work+0x226/0x730 [ 805.727322] worker_thread+0x19e/0x340 [ 805.727325] ? __pfx_worker_thread+0x10/0x10 [ 805.727328] kthread+0xf4/0x130 [ 805.727333] ? __pfx_kthread+0x10/0x10 [ 805.727336] ret_from_fork+0x32c/0x410 [ 805.727345] ? __pfx_kthread+0x10/0x10 [ 805.727347] ret_from_fork_asm+0x1a/0x30 [ 805.727354] Fixes: 34c21fa894a1 ("idpf: implement virtchnl transaction manager") Cc: stable@vger.kernel.org Suggested-by: Sebastian Andrzej Siewior Reported-by: Ray Zhang Signed-off-by: Emil Tantilov Reviewed-by: Aleksandr Loktionov Acked-by: Sebastian Andrzej Siewior Tested-by: Samuel Salin Signed-off-by: Tony Nguyen Signed-off-by: Greg Kroah-Hartman (cherry picked from commit e02c974fc331f04b5ba2007d4bc6862df8a43148) Signed-off-by: Wentao Guan --- drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 14 +++++--------- drivers/net/ethernet/intel/idpf/idpf_virtchnl.h | 5 +++-- 2 files changed, 8 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index cb702eac86c8..aebc1f6fb77e 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -284,26 +284,21 @@ int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op, return err; } -/* API for virtchnl "transaction" support ("xn" for short). - * - * We are reusing the completion lock to serialize the accesses to the - * transaction state for simplicity, but it could be its own separate synchro - * as well. For now, this API is only used from within a workqueue context; - * raw_spin_lock() is enough. - */ +/* API for virtchnl "transaction" support ("xn" for short). */ + /** * idpf_vc_xn_lock - Request exclusive access to vc transaction * @xn: struct idpf_vc_xn* to access */ #define idpf_vc_xn_lock(xn) \ - raw_spin_lock(&(xn)->completed.wait.lock) + spin_lock(&(xn)->lock) /** * idpf_vc_xn_unlock - Release exclusive access to vc transaction * @xn: struct idpf_vc_xn* to access */ #define idpf_vc_xn_unlock(xn) \ - raw_spin_unlock(&(xn)->completed.wait.lock) + spin_unlock(&(xn)->lock) /** * idpf_vc_xn_release_bufs - Release reference to reply buffer(s) and @@ -335,6 +330,7 @@ static void idpf_vc_xn_init(struct idpf_vc_xn_manager *vcxn_mngr) xn->state = IDPF_VC_XN_IDLE; xn->idx = i; idpf_vc_xn_release_bufs(xn); + spin_lock_init(&xn->lock); init_completion(&xn->completed); } diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h index eac3d15daa42..0a50a08eb9af 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h @@ -42,8 +42,8 @@ typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *, * struct idpf_vc_xn - Data structure representing virtchnl transactions * @completed: virtchnl event loop uses that to signal when a reply is * available, uses kernel completion API - * @state: virtchnl event loop stores the data below, protected by the - * completion's lock. + * @lock: protects the transaction state fields below + * @state: virtchnl event loop stores the data below, protected by @lock * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be * truncated on its way to the receiver thread according to * reply_buf.iov_len. @@ -58,6 +58,7 @@ typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *, */ struct idpf_vc_xn { struct completion completed; + spinlock_t lock; enum idpf_vc_xn_state state; size_t reply_sz; struct kvec reply; From ef5f6806ded6bf5228a317ef052be27a86fd77db Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Thu, 19 Mar 2026 14:13:34 -0700 Subject: [PATCH 57/85] idpf: improve locking around idpf_vc_xn_push_free() commit d086fae65006368618104ba4c57779440eab2217 upstream. Protect the set_bit() operation for the free_xn bitmask in idpf_vc_xn_push_free(), to make the locking consistent with rest of the code and avoid potential races in that logic. Fixes: 34c21fa894a1 ("idpf: implement virtchnl transaction manager") Cc: stable@vger.kernel.org Reported-by: Ray Zhang Signed-off-by: Emil Tantilov Reviewed-by: Aleksandr Loktionov Acked-by: Sebastian Andrzej Siewior Tested-by: Samuel Salin Signed-off-by: Tony Nguyen Signed-off-by: Greg Kroah-Hartman (cherry picked from commit d6e9bef3313a3bff4d964a0408a8ec7e8d0b6c3f) Signed-off-by: Wentao Guan --- drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index aebc1f6fb77e..0af93bc3e6bd 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -399,7 +399,9 @@ static void idpf_vc_xn_push_free(struct idpf_vc_xn_manager *vcxn_mngr, struct idpf_vc_xn *xn) { idpf_vc_xn_release_bufs(xn); + spin_lock_bh(&vcxn_mngr->xn_bm_lock); set_bit(xn->idx, vcxn_mngr->free_xn_bm); + spin_unlock_bh(&vcxn_mngr->xn_bm_lock); } /** From 91be3ef1585721c179eb346407b96c01a018f45c Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Thu, 19 Mar 2026 14:13:35 -0700 Subject: [PATCH 58/85] idpf: set the payload size before calling the async handler commit 8e2a2420e267a515f6db56a6e9570b5cacd92919 upstream. Set the payload size before forwarding the reply to the async handler. Without this, xn->reply_sz will be 0 and idpf_mac_filter_async_handler() will never get past the size check. Fixes: 34c21fa894a1 ("idpf: implement virtchnl transaction manager") Cc: stable@vger.kernel.org Signed-off-by: Emil Tantilov Reviewed-by: Aleksandr Loktionov Reviewed-by: Li Li Acked-by: Sebastian Andrzej Siewior Tested-by: Samuel Salin Signed-off-by: Tony Nguyen Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 214ceaa8a3a24e2d9bcc343e3f20f4244124b9ec) Signed-off-by: Wentao Guan --- drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index 0af93bc3e6bd..3c8ceff0e669 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -612,6 +612,10 @@ idpf_vc_xn_forward_reply(struct idpf_adapter *adapter, err = -ENXIO; goto out_unlock; case IDPF_VC_XN_ASYNC: + /* Set reply_sz from the actual payload so that async_handler + * can evaluate the response. + */ + xn->reply_sz = ctlq_msg->data_len; err = idpf_vc_xn_forward_async(adapter, xn, ctlq_msg); idpf_vc_xn_unlock(xn); return err; From 3357edf9df42dea96d53d24a38e978a2cc3c5a77 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Sun, 5 Apr 2026 06:52:39 +0100 Subject: [PATCH 59/85] net: lan966x: fix page_pool error handling in lan966x_fdma_rx_alloc_page_pool() commit 3fd0da4fd8851a7e62d009b7db6c4a05b092bc19 upstream. page_pool_create() can return an ERR_PTR on failure. The return value is used unconditionally in the loop that follows, passing the error pointer through xdp_rxq_info_reg_mem_model() into page_pool_use_xdp_mem(), which dereferences it, causing a kernel oops. Add an IS_ERR check after page_pool_create() to return early on failure. Fixes: 11871aba1974 ("net: lan96x: Use page_pool API") Cc: stable@vger.kernel.org Signed-off-by: David Carlier Link: https://patch.msgid.link/20260405055241.35767-2-devnexen@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman (cherry picked from commit b5dcb41ba891b55157006cac79825c78a32b409e) Signed-off-by: Wentao Guan --- drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c index 502670718104..1b898f57ec7b 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c @@ -91,6 +91,8 @@ static int lan966x_fdma_rx_alloc_page_pool(struct lan966x_rx *rx) pp_params.dma_dir = DMA_BIDIRECTIONAL; rx->page_pool = page_pool_create(&pp_params); + if (unlikely(IS_ERR(rx->page_pool))) + return PTR_ERR(rx->page_pool); for (int i = 0; i < lan966x->num_phys_ports; ++i) { struct lan966x_port *port; From e7817c0b58adb20ab007182e2247e88ebc3119eb Mon Sep 17 00:00:00 2001 From: David Carlier Date: Sun, 5 Apr 2026 06:52:40 +0100 Subject: [PATCH 60/85] net: lan966x: fix page pool leak in error paths commit 076344a6ad9d1308faaed1402fdcfdda68b604ab upstream. lan966x_fdma_rx_alloc() creates a page pool but does not destroy it if the subsequent fdma_alloc_coherent() call fails, leaking the pool. Similarly, lan966x_fdma_init() frees the coherent DMA memory when lan966x_fdma_tx_alloc() fails but does not destroy the page pool that was successfully created by lan966x_fdma_rx_alloc(), leaking it. Add the missing page_pool_destroy() calls in both error paths. Fixes: 11871aba1974 ("net: lan96x: Use page_pool API") Cc: stable@vger.kernel.org Signed-off-by: David Carlier Link: https://patch.msgid.link/20260405055241.35767-3-devnexen@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 22e1ee9f22b5c3bb702bb6d4167d770002a85b2b) Signed-off-by: Wentao Guan --- drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c index 1b898f57ec7b..e5d88e098fbb 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c @@ -119,8 +119,10 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx) return PTR_ERR(rx->page_pool); err = fdma_alloc_coherent(lan966x->dev, fdma); - if (err) + if (err) { + page_pool_destroy(rx->page_pool); return err; + } fdma_dcbs_init(fdma, FDMA_DCB_INFO_DATAL(fdma->db_size), FDMA_DCB_STATUS_INTR); @@ -958,6 +960,7 @@ int lan966x_fdma_init(struct lan966x *lan966x) err = lan966x_fdma_tx_alloc(&lan966x->tx); if (err) { fdma_free_coherent(lan966x->dev, &lan966x->rx.fdma); + page_pool_destroy(lan966x->rx.page_pool); return err; } From db349b270171e46ece5934ab1e46b504b92c21f1 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Sun, 5 Apr 2026 06:52:41 +0100 Subject: [PATCH 61/85] net: lan966x: fix use-after-free and leak in lan966x_fdma_reload() commit 59c3d55a946cacdb4181600723c20ac4f4c20c84 upstream. When lan966x_fdma_reload() fails to allocate new RX buffers, the restore path restarts DMA using old descriptors whose pages were already freed via lan966x_fdma_rx_free_pages(). Since page_pool_put_full_page() can release pages back to the buddy allocator, the hardware may DMA into memory now owned by other kernel subsystems. Additionally, on the restore path, the newly created page pool (if allocation partially succeeded) is overwritten without being destroyed, leaking it. Fix both issues by deferring the release of old pages until after the new allocation succeeds. Save the old page array before the allocation so old pages can be freed on the success path. On the failure path, the old descriptors, pages and page pool are all still valid, making the restore safe. Also ensure the restore path re-enables NAPI and wakes the netdev, matching the success path. Fixes: 89ba464fcf54 ("net: lan966x: refactor buffer reload function") Cc: stable@vger.kernel.org Signed-off-by: David Carlier Link: https://patch.msgid.link/20260405055241.35767-4-devnexen@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 92a673019943770930e2a8bfd52e1aad47a1fc1f) Signed-off-by: Wentao Guan --- .../ethernet/microchip/lan966x/lan966x_fdma.c | 21 ++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c index e5d88e098fbb..646f3d65274e 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c @@ -813,9 +813,15 @@ static int lan966x_qsys_sw_status(struct lan966x *lan966x) static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) { + struct page *(*old_pages)[FDMA_RX_DCB_MAX_DBS]; struct page_pool *page_pool; struct fdma fdma_rx_old; - int err; + int err, i, j; + + old_pages = kmemdup(lan966x->rx.page, sizeof(lan966x->rx.page), + GFP_KERNEL); + if (!old_pages) + return -ENOMEM; /* Store these for later to free them */ memcpy(&fdma_rx_old, &lan966x->rx.fdma, sizeof(struct fdma)); @@ -826,7 +832,6 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) lan966x_fdma_stop_netdev(lan966x); lan966x_fdma_rx_disable(&lan966x->rx); - lan966x_fdma_rx_free_pages(&lan966x->rx); lan966x->rx.page_order = round_up(new_mtu, PAGE_SIZE) / PAGE_SIZE - 1; lan966x->rx.max_mtu = new_mtu; err = lan966x_fdma_rx_alloc(&lan966x->rx); @@ -834,6 +839,11 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) goto restore; lan966x_fdma_rx_start(&lan966x->rx); + for (i = 0; i < fdma_rx_old.n_dcbs; ++i) + for (j = 0; j < fdma_rx_old.n_dbs; ++j) + page_pool_put_full_page(page_pool, + old_pages[i][j], false); + fdma_free_coherent(lan966x->dev, &fdma_rx_old); page_pool_destroy(page_pool); @@ -841,12 +851,17 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) lan966x_fdma_wakeup_netdev(lan966x); napi_enable(&lan966x->napi); - return err; + kfree(old_pages); + return 0; restore: lan966x->rx.page_pool = page_pool; memcpy(&lan966x->rx.fdma, &fdma_rx_old, sizeof(struct fdma)); lan966x_fdma_rx_start(&lan966x->rx); + lan966x_fdma_wakeup_netdev(lan966x); + napi_enable(&lan966x->napi); + + kfree(old_pages); return err; } From e6426f6be1f52a39a7d7c782da117e290b6a5497 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 8 Apr 2026 13:12:29 +0100 Subject: [PATCH 62/85] rxrpc: Fix key quota calculation for multitoken keys commit bdbfead6d38979475df0c2f4bad2b19394fe9bdc upstream. In the rxrpc key preparsing, every token extracted sets the proposed quota value, but for multitoken keys, this will overwrite the previous proposed quota, losing it. Fix this by adding to the proposed quota instead. Fixes: 8a7a3eb4ddbe ("KEYS: RxRPC: Use key preparsing") Closes: https://sashiko.dev/#/patchset/20260319150150.4189381-1-dhowells%40redhat.com Signed-off-by: David Howells cc: Marc Dionne cc: Jeffrey Altman cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-2-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 862cb78fb2c984af7ed94aea90bbc115d8ebd815) Signed-off-by: Wentao Guan --- net/rxrpc/key.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index 9fdc1f031c9d..bac2afdb3548 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -72,7 +72,7 @@ static int rxrpc_preparse_xdr_rxkad(struct key_preparsed_payload *prep, return -EKEYREJECTED; plen = sizeof(*token) + sizeof(*token->kad) + tktlen; - prep->quotalen = datalen + plen; + prep->quotalen += datalen + plen; plen -= sizeof(*token); token = kzalloc(sizeof(*token), GFP_KERNEL); @@ -199,7 +199,7 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep, } plen = sizeof(*token) + sizeof(*token->rxgk) + tktlen + keylen; - prep->quotalen = datalen + plen; + prep->quotalen += datalen + plen; plen -= sizeof(*token); token = kzalloc(sizeof(*token), GFP_KERNEL); @@ -460,6 +460,7 @@ static int rxrpc_preparse(struct key_preparsed_payload *prep) memcpy(&kver, prep->data, sizeof(kver)); prep->data += sizeof(kver); prep->datalen -= sizeof(kver); + prep->quotalen = 0; _debug("KEY I/F VERSION: %u", kver); @@ -497,7 +498,7 @@ static int rxrpc_preparse(struct key_preparsed_payload *prep) goto error; plen = sizeof(*token->kad) + v1->ticket_length; - prep->quotalen = plen + sizeof(*token); + prep->quotalen += plen + sizeof(*token); ret = -ENOMEM; token = kzalloc(sizeof(*token), GFP_KERNEL); From c248f46169e7f0b4402e85a973c4a770eb8d3c7f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 8 Apr 2026 13:12:30 +0100 Subject: [PATCH 63/85] rxrpc: Fix key parsing memleak commit b555912b9b21075e8298015f888ffe3ff60b1a97 upstream. In rxrpc_preparse_xdr_yfs_rxgk(), the memory attached to token->rxgk can be leaked in a few error paths after it's allocated. Fix this by freeing it in the "reject_token:" case. Fixes: 0ca100ff4df6 ("rxrpc: Add YFS RxGK (GSSAPI) security class") Closes: https://sashiko.dev/#/patchset/20260319150150.4189381-1-dhowells%40redhat.com Signed-off-by: David Howells cc: Marc Dionne cc: Jeffrey Altman cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-3-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit d5f76f812d2c0ea6dd651b0586be49e85ecca085) Signed-off-by: Wentao Guan --- net/rxrpc/key.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index bac2afdb3548..c35acfaa9eab 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -274,6 +274,7 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep, nomem: return -ENOMEM; reject_token: + kfree(token->rxgk); kfree(token); reject: return -EKEYREJECTED; From bd04cbe67d7e3ad5f652192c2252511200087081 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 8 Apr 2026 13:12:31 +0100 Subject: [PATCH 64/85] rxrpc: Fix anonymous key handling commit 6a59d84b4fc2f27f7b40e348506cc686712e260b upstream. In rxrpc_new_client_call_for_sendmsg(), a key with no payload is meant to be substituted for a NULL key pointer, but the variable this is done with is subsequently not used. Fix this by using "key" rather than "rx->key" when filling in the connection parameters. Note that this only affects direct use of AF_RXRPC; the kAFS filesystem doesn't use sendmsg() directly and so bypasses the issue. Further, AF_RXRPC passes a NULL key in if no key is set, so using an anonymous key in that manner works. Since this hasn't been noticed to this point, it might be better just to remove the "key" variable and the code that sets it - and, arguably, rxrpc_init_client_call_security() would be a better place to handle it. Fixes: 19ffa01c9c45 ("rxrpc: Use structs to hold connection params and protocol info") Closes: https://sashiko.dev/#/patchset/20260319150150.4189381-1-dhowells%40redhat.com Signed-off-by: David Howells cc: Marc Dionne cc: Jeffrey Altman cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-4-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 3bb18ed3b2f6a9659c5cf05809dbde3225944cba) Signed-off-by: Wentao Guan --- net/rxrpc/sendmsg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index ebbb78b842de..39a6b21d6b8f 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -637,7 +637,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, memset(&cp, 0, sizeof(cp)); cp.local = rx->local; cp.peer = peer; - cp.key = rx->key; + cp.key = key; cp.security_level = rx->min_sec_level; cp.exclusive = rx->exclusive | p->exclusive; cp.upgrade = p->upgrade; From d96016f86ed141e47ecfdc70e4901b1d896f5276 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 8 Apr 2026 13:12:32 +0100 Subject: [PATCH 65/85] rxrpc: Fix call removal to use RCU safe deletion commit 146d4ab94cf129ee06cd467cb5c71368a6b5bad6 upstream. Fix rxrpc call removal from the rxnet->calls list to use list_del_rcu() rather than list_del_init() to prevent stuffing up reading /proc/net/rxrpc/calls from potentially getting into an infinite loop. This, however, means that list_empty() no longer works on an entry that's been deleted from the list, making it harder to detect prior deletion. Fix this by: Firstly, make rxrpc_destroy_all_calls() only dump the first ten calls that are unexpectedly still on the list. Limiting the number of steps means there's no need to call cond_resched() or to remove calls from the list here, thereby eliminating the need for rxrpc_put_call() to check for that. rxrpc_put_call() can then be fixed to unconditionally delete the call from the list as it is the only place that the deletion occurs. Fixes: 2baec2c3f854 ("rxrpc: Support network namespacing") Closes: https://sashiko.dev/#/patchset/20260319150150.4189381-1-dhowells%40redhat.com Signed-off-by: David Howells cc: Marc Dionne cc: Jeffrey Altman cc: Linus Torvalds cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-5-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 3be718f659683ad89fad6f1eb66bee99727cae64) Signed-off-by: Wentao Guan --- include/trace/events/rxrpc.h | 2 +- net/rxrpc/call_object.c | 24 +++++++++--------------- 2 files changed, 10 insertions(+), 16 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 869f97c9bf73..a826cd80007b 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -347,7 +347,7 @@ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ - E_(rxrpc_call_see_zap, "SEE zap ") + E_(rxrpc_call_see_still_live, "SEE !still-l") #define rxrpc_txqueue_traces \ EM(rxrpc_txqueue_await_reply, "AWR") \ diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 918f41d97a2f..59329cfe1532 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -654,11 +654,9 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace why) if (dead) { ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE); - if (!list_empty(&call->link)) { - spin_lock(&rxnet->call_lock); - list_del_init(&call->link); - spin_unlock(&rxnet->call_lock); - } + spin_lock(&rxnet->call_lock); + list_del_rcu(&call->link); + spin_unlock(&rxnet->call_lock); rxrpc_cleanup_call(call); } @@ -730,24 +728,20 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet) _enter(""); if (!list_empty(&rxnet->calls)) { - spin_lock(&rxnet->call_lock); + int shown = 0; - while (!list_empty(&rxnet->calls)) { - call = list_entry(rxnet->calls.next, - struct rxrpc_call, link); - _debug("Zapping call %p", call); + spin_lock(&rxnet->call_lock); - rxrpc_see_call(call, rxrpc_call_see_zap); - list_del_init(&call->link); + list_for_each_entry(call, &rxnet->calls, link) { + rxrpc_see_call(call, rxrpc_call_see_still_live); pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n", call, refcount_read(&call->ref), rxrpc_call_states[__rxrpc_call_state(call)], call->flags, call->events); - spin_unlock(&rxnet->call_lock); - cond_resched(); - spin_lock(&rxnet->call_lock); + if (++shown >= 10) + break; } spin_unlock(&rxnet->call_lock); From 75fb80f8f9da4b6f9fdcfd03ab81a423eb3b0cb9 Mon Sep 17 00:00:00 2001 From: Oleh Konko Date: Wed, 8 Apr 2026 13:12:33 +0100 Subject: [PATCH 66/85] rxrpc: Fix RxGK token loading to check bounds commit d179a868dd755b0cfcf7582e00943d702b9943b8 upstream. rxrpc_preparse_xdr_yfs_rxgk() reads the raw key length and ticket length from the XDR token as u32 values and passes each through round_up(x, 4) before using the rounded value for validation and allocation. When the raw length is >= 0xfffffffd, round_up() wraps to 0, so the bounds check and kzalloc both use 0 while the subsequent memcpy still copies the original ~4 GiB value, producing a heap buffer overflow reachable from an unprivileged add_key() call. Fix this by: (1) Rejecting raw key lengths above AFSTOKEN_GK_KEY_MAX and raw ticket lengths above AFSTOKEN_GK_TOKEN_MAX before rounding, consistent with the caps that the RxKAD path already enforces via AFSTOKEN_RK_TIX_MAX. (2) Sizing the flexible-array allocation from the validated raw key length via struct_size_t() instead of the rounded value. (3) Caching the raw lengths so that the later field assignments and memcpy calls do not re-read from the token, eliminating a class of TOCTOU re-parse. The control path (valid token with lengths within bounds) is unaffected. Fixes: 0ca100ff4df6 ("rxrpc: Add YFS RxGK (GSSAPI) security class") Signed-off-by: Oleh Konko Signed-off-by: David Howells Reviewed-by: Jeffrey Altman cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-6-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 3e04596cba8a86cbff9c3f4bf0a524a3a488773c) Signed-off-by: Wentao Guan --- net/rxrpc/key.c | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index c35acfaa9eab..ac992d62b476 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -171,7 +172,7 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep, size_t plen; const __be32 *ticket, *key; s64 tmp; - u32 tktlen, keylen; + size_t raw_keylen, raw_tktlen, keylen, tktlen; _enter(",{%x,%x,%x,%x},%x", ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]), @@ -181,18 +182,22 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep, goto reject; key = xdr + (6 * 2 + 1); - keylen = ntohl(key[-1]); - _debug("keylen: %x", keylen); - keylen = round_up(keylen, 4); + raw_keylen = ntohl(key[-1]); + _debug("keylen: %zx", raw_keylen); + if (raw_keylen > AFSTOKEN_GK_KEY_MAX) + goto reject; + keylen = round_up(raw_keylen, 4); if ((6 * 2 + 2) * 4 + keylen > toklen) goto reject; ticket = xdr + (6 * 2 + 1 + (keylen / 4) + 1); - tktlen = ntohl(ticket[-1]); - _debug("tktlen: %x", tktlen); - tktlen = round_up(tktlen, 4); + raw_tktlen = ntohl(ticket[-1]); + _debug("tktlen: %zx", raw_tktlen); + if (raw_tktlen > AFSTOKEN_GK_TOKEN_MAX) + goto reject; + tktlen = round_up(raw_tktlen, 4); if ((6 * 2 + 2) * 4 + keylen + tktlen != toklen) { - kleave(" = -EKEYREJECTED [%x!=%x, %x,%x]", + kleave(" = -EKEYREJECTED [%zx!=%x, %zx,%zx]", (6 * 2 + 2) * 4 + keylen + tktlen, toklen, keylen, tktlen); goto reject; @@ -206,7 +211,7 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep, if (!token) goto nomem; - token->rxgk = kzalloc(sizeof(*token->rxgk) + keylen, GFP_KERNEL); + token->rxgk = kzalloc(struct_size_t(struct rxgk_key, _key, raw_keylen), GFP_KERNEL); if (!token->rxgk) goto nomem_token; @@ -221,9 +226,9 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep, token->rxgk->enctype = tmp = xdr_dec64(xdr + 5 * 2); if (tmp < 0 || tmp > UINT_MAX) goto reject_token; - token->rxgk->key.len = ntohl(key[-1]); + token->rxgk->key.len = raw_keylen; token->rxgk->key.data = token->rxgk->_key; - token->rxgk->ticket.len = ntohl(ticket[-1]); + token->rxgk->ticket.len = raw_tktlen; if (token->rxgk->endtime != 0) { expiry = rxrpc_s64_to_time64(token->rxgk->endtime); @@ -236,8 +241,7 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep, memcpy(token->rxgk->key.data, key, token->rxgk->key.len); /* Pad the ticket so that we can use it directly in XDR */ - token->rxgk->ticket.data = kzalloc(round_up(token->rxgk->ticket.len, 4), - GFP_KERNEL); + token->rxgk->ticket.data = kzalloc(tktlen, GFP_KERNEL); if (!token->rxgk->ticket.data) goto nomem_yrxgk; memcpy(token->rxgk->ticket.data, ticket, token->rxgk->ticket.len); From fbdb0afe8c6b47cd97d888b21f3f9cdc6e31fefb Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Wed, 8 Apr 2026 13:12:34 +0100 Subject: [PATCH 67/85] rxrpc: Fix use of wrong skb when comparing queued RESP challenge serial commit b33f5741bb187db8ff32e8f5b96def77cc94dfca upstream. In rxrpc_post_response(), the code should be comparing the challenge serial number from the cached response before deciding to switch to a newer response, but looks at the newer packet private data instead, rendering the comparison always false. Fix this by switching to look at the older packet. Fix further[1] to substitute the new packet in place of the old one if newer and also to release whichever we don't use. Fixes: 5800b1cf3fd8 ("rxrpc: Allow CHALLENGEs to the passed to the app for a RESPONSE") Signed-off-by: Alok Tiwari Signed-off-by: David Howells Reviewed-by: Jeffrey Altman cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://sashiko.dev/#/patchset/20260319150150.4189381-1-dhowells%40redhat.com [1] Link: https://patch.msgid.link/20260408121252.2249051-7-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 9132b1a7bf83b4a8042fffbc99d075b727a16742) Signed-off-by: Wentao Guan --- include/trace/events/rxrpc.h | 1 + net/rxrpc/conn_event.c | 5 +++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index a826cd80007b..f7f559204b87 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -185,6 +185,7 @@ EM(rxrpc_skb_put_input, "PUT input ") \ EM(rxrpc_skb_put_jumbo_subpacket, "PUT jumbo-sub") \ EM(rxrpc_skb_put_oob, "PUT oob ") \ + EM(rxrpc_skb_put_old_response, "PUT old-resp ") \ EM(rxrpc_skb_put_purge, "PUT purge ") \ EM(rxrpc_skb_put_purge_oob, "PUT purge-oob") \ EM(rxrpc_skb_put_response, "PUT response ") \ diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 98ad9b51ca2c..c50cbfc5a313 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -557,11 +557,11 @@ void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb) spin_lock_irq(&local->lock); old = conn->tx_response; if (old) { - struct rxrpc_skb_priv *osp = rxrpc_skb(skb); + struct rxrpc_skb_priv *osp = rxrpc_skb(old); /* Always go with the response to the most recent challenge. */ if (after(sp->resp.challenge_serial, osp->resp.challenge_serial)) - conn->tx_response = old; + conn->tx_response = skb; else old = skb; } else { @@ -569,4 +569,5 @@ void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb) } spin_unlock_irq(&local->lock); rxrpc_poke_conn(conn, rxrpc_conn_get_poke_response); + rxrpc_free_skb(old, rxrpc_skb_put_old_response); } From 076989b6af233b403cdb89d6c2f8e3334989312f Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Wed, 8 Apr 2026 13:12:35 +0100 Subject: [PATCH 68/85] rxrpc: Fix rack timer warning to report unexpected mode commit 65b3ffe0972ed023acc3981a0f7e1ae5d0208bd3 upstream. rxrpc_rack_timer_expired() clears call->rack_timer_mode to OFF before the switch. The default case warning therefore always prints OFF and doesn't identify the unexpected timer mode. Log the saved mode value instead so the warning reports the actual unexpected rack timer mode. Fixes: 7c482665931b ("rxrpc: Implement RACK/TLP to deal with transmission stalls [RFC8985]") Signed-off-by: Alok Tiwari Signed-off-by: David Howells Reviewed-by: Simon Horman Reviewed-by: Jeffrey Altman cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-8-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 86303a1da93f6ecdd0792330a71c71e20aeef718) Signed-off-by: Wentao Guan --- net/rxrpc/input_rack.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/rxrpc/input_rack.c b/net/rxrpc/input_rack.c index 13c371261e0a..9eb109ffba56 100644 --- a/net/rxrpc/input_rack.c +++ b/net/rxrpc/input_rack.c @@ -413,6 +413,6 @@ void rxrpc_rack_timer_expired(struct rxrpc_call *call, ktime_t overran_by) break; //case RXRPC_CALL_RACKTIMER_ZEROWIN: default: - pr_warn("Unexpected rack timer %u", call->rack_timer_mode); + pr_warn("Unexpected rack timer %u", mode); } } From 77a86943caa60ad468858ebdfcb4ac504d7a1135 Mon Sep 17 00:00:00 2001 From: Anderson Nascimento Date: Wed, 8 Apr 2026 13:12:36 +0100 Subject: [PATCH 69/85] rxrpc: Fix key reference count leak from call->key commit d666540d217e8d420544ebdfbadeedd623562733 upstream. When creating a client call in rxrpc_alloc_client_call(), the code obtains a reference to the key. This is never cleaned up and gets leaked when the call is destroyed. Fix this by freeing call->key in rxrpc_destroy_call(). Before the patch, it shows the key reference counter elevated: $ cat /proc/keys | grep afs@54321 1bffe9cd I--Q--i 8053480 4169w 3b010000 1000 1000 rxrpc afs@54321: ka $ After the patch, the invalidated key is removed when the code exits: $ cat /proc/keys | grep afs@54321 $ Fixes: f3441d4125fc ("rxrpc: Copy client call parameters into rxrpc_call earlier") Signed-off-by: Anderson Nascimento Co-developed-by: David Howells Signed-off-by: David Howells Reviewed-by: Jeffrey Altman cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-9-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 2e6ef713b1598f6acd7f302fa6b12b6731c89914) Signed-off-by: Wentao Guan --- net/rxrpc/call_object.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 59329cfe1532..f035f486c139 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -692,6 +692,7 @@ static void rxrpc_destroy_call(struct work_struct *work) rxrpc_put_bundle(call->bundle, rxrpc_bundle_put_call); rxrpc_put_peer(call->peer, rxrpc_peer_put_call); rxrpc_put_local(call->local, rxrpc_local_put_call); + key_put(call->key); call_rcu(&call->rcu, rxrpc_rcu_free_call); } From 79c82180e7bef68be5fadea11b837dfccf000045 Mon Sep 17 00:00:00 2001 From: Marc Dionne Date: Wed, 8 Apr 2026 13:12:37 +0100 Subject: [PATCH 70/85] rxrpc: Fix to request an ack if window is limited commit 0cd3e3f3f2ec1a45aa559e2c0f3d57fac5eb3c25 upstream. Peers may only send immediate acks for every 2 UDP packets received. When sending a jumbogram, it is important to check that there is sufficient window space to send another same sized jumbogram following the current one, and request an ack if there isn't. Failure to do so may cause the call to stall waiting for an ack until the resend timer fires. Where jumbograms are in use this causes a very significant drop in performance. Fixes: fe24a5494390 ("rxrpc: Send jumbo DATA packets") Signed-off-by: Marc Dionne Signed-off-by: David Howells cc: Jeffrey Altman cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-10-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 8b353f5f138573b50dd50bdaf1d822c77b0c4cfe) Signed-off-by: Wentao Guan --- include/trace/events/rxrpc.h | 1 + net/rxrpc/ar-internal.h | 2 +- net/rxrpc/output.c | 2 ++ net/rxrpc/proc.c | 5 +++-- 4 files changed, 7 insertions(+), 3 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index f7f559204b87..578b8038b211 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -521,6 +521,7 @@ #define rxrpc_req_ack_traces \ EM(rxrpc_reqack_ack_lost, "ACK-LOST ") \ EM(rxrpc_reqack_app_stall, "APP-STALL ") \ + EM(rxrpc_reqack_jumbo_win, "JUMBO-WIN ") \ EM(rxrpc_reqack_more_rtt, "MORE-RTT ") \ EM(rxrpc_reqack_no_srv_last, "NO-SRVLAST") \ EM(rxrpc_reqack_old_rtt, "OLD-RTT ") \ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 36d6ca0d1089..96ecb83c9071 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -117,7 +117,7 @@ struct rxrpc_net { atomic_t stat_tx_jumbo[10]; atomic_t stat_rx_jumbo[10]; - atomic_t stat_why_req_ack[8]; + atomic_t stat_why_req_ack[9]; atomic_t stat_io_loop; }; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index d70db367e358..870e59bf06af 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -479,6 +479,8 @@ static size_t rxrpc_prepare_data_subpacket(struct rxrpc_call *call, why = rxrpc_reqack_old_rtt; else if (!last && !after(READ_ONCE(call->send_top), txb->seq)) why = rxrpc_reqack_app_stall; + else if (call->tx_winsize <= (2 * req->n) || call->cong_cwnd <= (2 * req->n)) + why = rxrpc_reqack_jumbo_win; else goto dont_set_request_ack; diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 59292f7f9205..7755fca5beb8 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -518,11 +518,12 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_IDLE]), atomic_read(&rxnet->stat_rx_acks[0])); seq_printf(seq, - "Why-Req-A: acklost=%u mrtt=%u ortt=%u stall=%u\n", + "Why-Req-A: acklost=%u mrtt=%u ortt=%u stall=%u jwin=%u\n", atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_ack_lost]), atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_more_rtt]), atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_old_rtt]), - atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_app_stall])); + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_app_stall]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_jumbo_win])); seq_printf(seq, "Why-Req-A: nolast=%u retx=%u slows=%u smtxw=%u\n", atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_no_srv_last]), From 9ffbcf8db76351dd7d9169b369751c92b21f93b1 Mon Sep 17 00:00:00 2001 From: Douya Le Date: Wed, 8 Apr 2026 13:12:38 +0100 Subject: [PATCH 71/85] rxrpc: Only put the call ref if one was acquired commit 6331f1b24a3e85465f6454e003a3e6c22005a5c5 upstream. rxrpc_input_packet_on_conn() can process a to-client packet after the current client call on the channel has already been torn down. In that case chan->call is NULL, rxrpc_try_get_call() returns NULL and there is no reference to drop. The client-side implicit-end error path does not account for that and unconditionally calls rxrpc_put_call(). This turns a protocol error path into a kernel crash instead of rejecting the packet. Only drop the call reference if one was actually acquired. Keep the existing protocol error handling unchanged. Fixes: 5e6ef4f1017c ("rxrpc: Make the I/O thread take over the call and local processor work") Reported-by: Yifan Wu Reported-by: Juefei Pu Signed-off-by: Douya Le Co-developed-by: Yuan Tan Signed-off-by: Yuan Tan Suggested-by: Xin Liu Signed-off-by: Ao Zhou Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-11-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 8299ca146489664e3c0c90a3b8900d8335b1ede4) Signed-off-by: Wentao Guan --- net/rxrpc/io_thread.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index e939ecf417c4..697956931925 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -419,7 +419,8 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, if (sp->hdr.callNumber > chan->call_id) { if (rxrpc_to_client(sp)) { - rxrpc_put_call(call, rxrpc_call_put_input); + if (call) + rxrpc_put_call(call, rxrpc_call_put_input); return rxrpc_protocol_error(skb, rxrpc_eproto_unexpected_implicit_end); } From b3b09378f5984ca0125b91cf0e05db2b6ba4c2f1 Mon Sep 17 00:00:00 2001 From: Yuqi Xu Date: Wed, 8 Apr 2026 13:12:39 +0100 Subject: [PATCH 72/85] rxrpc: reject undecryptable rxkad response tickets commit fe4447cd95623b1cfacc15f280aab73a6d7340b2 upstream. rxkad_decrypt_ticket() decrypts the RXKAD response ticket and then parses the buffer as plaintext without checking whether crypto_skcipher_decrypt() succeeded. A malformed RESPONSE can therefore use a non-block-aligned ticket length, make the decrypt operation fail, and still drive the ticket parser with attacker-controlled bytes. Check the decrypt result and abort the connection with RXKADBADTICKET when ticket decryption fails. Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both") Reported-by: Yifan Wu Reported-by: Juefei Pu Co-developed-by: Yuan Tan Signed-off-by: Yuan Tan Suggested-by: Xin Liu Tested-by: Ren Wei Signed-off-by: Yuqi Xu Signed-off-by: Ren Wei Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-12-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 22f6258e7b31dba9bf88dce4e3ee7f0f20072e60) Signed-off-by: Wentao Guan --- net/rxrpc/rxkad.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index a756855a0a62..a8b8176de8a4 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -958,6 +958,7 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, struct in_addr addr; unsigned int life; time64_t issue, now; + int ret; bool little_endian; u8 *p, *q, *name, *end; @@ -977,8 +978,11 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, sg_init_one(&sg[0], ticket, ticket_len); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, ticket_len, iv.x); - crypto_skcipher_decrypt(req); + ret = crypto_skcipher_decrypt(req); skcipher_request_free(req); + if (ret < 0) + return rxrpc_abort_conn(conn, skb, RXKADBADTICKET, -EPROTO, + rxkad_abort_resp_tkt_short); p = ticket; end = p + ticket_len; From 6d0c8eb5f7510b2aec11a1e2e8c040020caf4d80 Mon Sep 17 00:00:00 2001 From: Keenan Dong Date: Wed, 8 Apr 2026 13:12:40 +0100 Subject: [PATCH 73/85] rxrpc: fix RESPONSE authenticator parser OOB read commit 3e3138007887504ee9206d0bfb5acb062c600025 upstream. rxgk_verify_authenticator() copies auth_len bytes into a temporary buffer and then passes p + auth_len as the parser limit to rxgk_do_verify_authenticator(). Since p is a __be32 *, that inflates the parser end pointer by a factor of four and lets malformed RESPONSE authenticators read past the kmalloc() buffer. Decoded from the original latest-net reproduction logs with scripts/decode_stacktrace.sh: BUG: KASAN: slab-out-of-bounds in rxgk_verify_response() Call Trace: dump_stack_lvl() [lib/dump_stack.c:123] print_report() [mm/kasan/report.c:379 mm/kasan/report.c:482] kasan_report() [mm/kasan/report.c:597] rxgk_verify_response() [net/rxrpc/rxgk.c:1103 net/rxrpc/rxgk.c:1167 net/rxrpc/rxgk.c:1274] rxrpc_process_connection() [net/rxrpc/conn_event.c:266 net/rxrpc/conn_event.c:364 net/rxrpc/conn_event.c:386] process_one_work() [kernel/workqueue.c:3281] worker_thread() [kernel/workqueue.c:3353 kernel/workqueue.c:3440] kthread() [kernel/kthread.c:436] ret_from_fork() [arch/x86/kernel/process.c:164] Allocated by task 54: rxgk_verify_response() [include/linux/slab.h:954 net/rxrpc/rxgk.c:1155 net/rxrpc/rxgk.c:1274] rxrpc_process_connection() [net/rxrpc/conn_event.c:266 net/rxrpc/conn_event.c:364 net/rxrpc/conn_event.c:386] Convert the byte count to __be32 units before constructing the parser limit. Fixes: 9d1d2b59341f ("rxrpc: rxgk: Implement the yfs-rxgk security class (GSSAPI)") Signed-off-by: Keenan Dong Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: Willy Tarreau cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-13-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 7875f3d9777bd4e9892c4db830571ab8ac2044c0) Signed-off-by: Wentao Guan --- net/rxrpc/rxgk.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index 43cbf9efd89f..aedcadb4466f 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -1164,7 +1164,8 @@ static int rxgk_verify_authenticator(struct rxrpc_connection *conn, } p = auth; - ret = rxgk_do_verify_authenticator(conn, krb5, skb, p, p + auth_len); + ret = rxgk_do_verify_authenticator(conn, krb5, skb, p, + p + auth_len / sizeof(*p)); error: kfree(auth); return ret; From 58a7062695391f578e5e66a4e793f1ade697f5e3 Mon Sep 17 00:00:00 2001 From: Keenan Dong Date: Wed, 8 Apr 2026 13:12:41 +0100 Subject: [PATCH 74/85] rxrpc: fix oversized RESPONSE authenticator length check commit a2567217ade970ecc458144b6be469bc015b23e5 upstream. rxgk_verify_response() decodes auth_len from the packet and is supposed to verify that it fits in the remaining bytes. The existing check is inverted, so oversized RESPONSE authenticators are accepted and passed to rxgk_decrypt_skb(), which can later reach skb_to_sgvec() with an impossible length and hit BUG_ON(len). Decoded from the original latest-net reproduction logs with scripts/decode_stacktrace.sh: RIP: __skb_to_sgvec() [net/core/skbuff.c:5285 (discriminator 1)] Call Trace: skb_to_sgvec() [net/core/skbuff.c:5305] rxgk_decrypt_skb() [net/rxrpc/rxgk_common.h:81] rxgk_verify_response() [net/rxrpc/rxgk.c:1268] rxrpc_process_connection() [net/rxrpc/conn_event.c:266 net/rxrpc/conn_event.c:364 net/rxrpc/conn_event.c:386] process_one_work() [kernel/workqueue.c:3281] worker_thread() [kernel/workqueue.c:3353 kernel/workqueue.c:3440] kthread() [kernel/kthread.c:436] ret_from_fork() [arch/x86/kernel/process.c:164] Reject authenticator lengths that exceed the remaining packet payload. Fixes: 9d1d2b59341f ("rxrpc: rxgk: Implement the yfs-rxgk security class (GSSAPI)") Signed-off-by: Keenan Dong Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: Willy Tarreau cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-14-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit beee051f259acd286fed64c32c2b31e6f5097eb5) Signed-off-by: Wentao Guan --- net/rxrpc/rxgk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index aedcadb4466f..13ffdc9352b0 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -1224,7 +1224,7 @@ static int rxgk_verify_response(struct rxrpc_connection *conn, auth_offset = offset; auth_len = ntohl(xauth_len); - if (auth_len < len) + if (auth_len > len) goto short_packet; if (auth_len & 3) goto inconsistent; From 6700e1dc5b3a0ba9a6eee31f476d9d4a89531da5 Mon Sep 17 00:00:00 2001 From: Luxiao Xu Date: Wed, 8 Apr 2026 13:12:42 +0100 Subject: [PATCH 75/85] rxrpc: fix reference count leak in rxrpc_server_keyring() commit f125846ee79fcae537a964ce66494e96fa54a6de upstream. This patch fixes a reference count leak in rxrpc_server_keyring() by checking if rx->securities is already set. Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both") Reported-by: Yifan Wu Reported-by: Juefei Pu Co-developed-by: Yuan Tan Signed-off-by: Yuan Tan Suggested-by: Xin Liu Tested-by: Ren Wei Signed-off-by: Luxiao Xu Signed-off-by: Ren Wei Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-15-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 8ee931c3cd97f1c42b4fbf057f04b9dae45dfb7a) Signed-off-by: Wentao Guan --- net/rxrpc/server_key.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/rxrpc/server_key.c b/net/rxrpc/server_key.c index 36b05fd842a7..27491f1e1273 100644 --- a/net/rxrpc/server_key.c +++ b/net/rxrpc/server_key.c @@ -125,6 +125,9 @@ int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen) _enter(""); + if (rx->securities) + return -EINVAL; + if (optlen <= 0 || optlen > PAGE_SIZE - 1) return -EINVAL; From 842b74c94b63491beab68bcd646adc2fee1a3faa Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 8 Apr 2026 13:12:43 +0100 Subject: [PATCH 76/85] rxrpc: Fix key/keyring checks in setsockopt(RXRPC_SECURITY_KEY/KEYRING) commit 2afd86ccbb2082a3c4258aea8c07e5bb6267bc2f upstream. An AF_RXRPC socket can be both client and server at the same time. When sending new calls (ie. it's acting as a client), it uses rx->key to set the security, and when accepting incoming calls (ie. it's acting as a server), it uses rx->securities. setsockopt(RXRPC_SECURITY_KEY) sets rx->key to point to an rxrpc-type key and setsockopt(RXRPC_SECURITY_KEYRING) sets rx->securities to point to a keyring of rxrpc_s-type keys. Now, it should be possible to use both rx->key and rx->securities on the same socket - but for userspace AF_RXRPC sockets rxrpc_setsockopt() prevents that. Fix this by: (1) Remove the incorrect check rxrpc_setsockopt(RXRPC_SECURITY_KEYRING) makes on rx->key. (2) Move the check that rxrpc_setsockopt(RXRPC_SECURITY_KEY) makes on rx->key down into rxrpc_request_key(). (3) Remove rxrpc_request_key()'s check on rx->securities. This (in combination with a previous patch) pushes the checks down into the functions that set those pointers and removes the cross-checks that prevent both key and keyring being set. Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both") Closes: https://sashiko.dev/#/patchset/20260401105614.1696001-10-dhowells@redhat.com Signed-off-by: David Howells cc: Marc Dionne cc: Anderson Nascimento cc: Luxiao Xu cc: Yuan Tan cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-16-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 03d1c51decaeb8700746ef79c50f4ebb6f1d8139) Signed-off-by: Wentao Guan --- net/rxrpc/af_rxrpc.c | 6 ------ net/rxrpc/key.c | 2 +- 2 files changed, 1 insertion(+), 7 deletions(-) diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index d369e3752538..885a28e3afc5 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -654,9 +654,6 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, goto success; case RXRPC_SECURITY_KEY: - ret = -EINVAL; - if (rx->key) - goto error; ret = -EISCONN; if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; @@ -664,9 +661,6 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, goto error; case RXRPC_SECURITY_KEYRING: - ret = -EINVAL; - if (rx->key) - goto error; ret = -EISCONN; if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index ac992d62b476..e0c29ebe6b6d 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -622,7 +622,7 @@ int rxrpc_request_key(struct rxrpc_sock *rx, sockptr_t optval, int optlen) _enter(""); - if (optlen <= 0 || optlen > PAGE_SIZE - 1 || rx->securities) + if (optlen <= 0 || optlen > PAGE_SIZE - 1 || rx->key) return -EINVAL; description = memdup_sockptr_nul(optval, optlen); From 327c09d770fd313912506c7a0f14f9c1193c3aa5 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 8 Apr 2026 13:12:44 +0100 Subject: [PATCH 77/85] rxrpc: Fix missing error checks for rxkad encryption/decryption failure commit f93af41b9f5f798823d0d0fb8765c2a936d76270 upstream. Add error checking for failure of crypto_skcipher_en/decrypt() to various rxkad function as the crypto functions can fail with ENOMEM at least. Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both") Closes: https://sashiko.dev/#/patchset/20260401105614.1696001-10-dhowells@redhat.com Signed-off-by: David Howells cc: Marc Dionne cc: Jeffrey Altman cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-17-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit bf4d6e4a6856eedeb7f66eb91224115bfff4e2cb) Signed-off-by: Wentao Guan --- net/rxrpc/rxkad.c | 57 +++++++++++++++++++++++++++++++---------------- 1 file changed, 38 insertions(+), 19 deletions(-) diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index a8b8176de8a4..4a3c63094149 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -197,6 +197,7 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn, struct rxrpc_crypt iv; __be32 *tmpbuf; size_t tmpsize = 4 * sizeof(__be32); + int ret; _enter(""); @@ -225,13 +226,13 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn, skcipher_request_set_sync_tfm(req, ci); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, tmpsize, iv.x); - crypto_skcipher_encrypt(req); + ret = crypto_skcipher_encrypt(req); skcipher_request_free(req); memcpy(&conn->rxkad.csum_iv, tmpbuf + 2, sizeof(conn->rxkad.csum_iv)); kfree(tmpbuf); - _leave(" = 0"); - return 0; + _leave(" = %d", ret); + return ret; } /* @@ -264,6 +265,7 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, struct scatterlist sg; size_t pad; u16 check; + int ret; _enter(""); @@ -286,11 +288,11 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); - crypto_skcipher_encrypt(req); + ret = crypto_skcipher_encrypt(req); skcipher_request_zero(req); - _leave(" = 0"); - return 0; + _leave(" = %d", ret); + return ret; } /* @@ -345,7 +347,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) union { __be32 buf[2]; } crypto __aligned(8); - u32 x, y; + u32 x, y = 0; int ret; _enter("{%d{%x}},{#%u},%u,", @@ -376,8 +378,10 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); - crypto_skcipher_encrypt(req); + ret = crypto_skcipher_encrypt(req); skcipher_request_zero(req); + if (ret < 0) + goto out; y = ntohl(crypto.buf[1]); y = (y >> 16) & 0xffff; @@ -413,6 +417,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) memset(p + txb->pkt_len, 0, gap); } +out: skcipher_request_free(req); _leave(" = %d [set %x]", ret, y); return ret; @@ -453,8 +458,10 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, 8, iv.x); - crypto_skcipher_decrypt(req); + ret = crypto_skcipher_decrypt(req); skcipher_request_zero(req); + if (ret < 0) + return ret; /* Extract the decrypted packet length */ if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) @@ -531,10 +538,14 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, sp->len, iv.x); - crypto_skcipher_decrypt(req); + ret = crypto_skcipher_decrypt(req); skcipher_request_zero(req); if (sg != _sg) kfree(sg); + if (ret < 0) { + WARN_ON_ONCE(ret != -ENOMEM); + return ret; + } /* Extract the decrypted packet length */ if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) @@ -602,8 +613,10 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); - crypto_skcipher_encrypt(req); + ret = crypto_skcipher_encrypt(req); skcipher_request_zero(req); + if (ret < 0) + goto out; y = ntohl(crypto.buf[1]); cksum = (y >> 16) & 0xffff; @@ -1077,21 +1090,23 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, /* * decrypt the response packet */ -static void rxkad_decrypt_response(struct rxrpc_connection *conn, - struct rxkad_response *resp, - const struct rxrpc_crypt *session_key) +static int rxkad_decrypt_response(struct rxrpc_connection *conn, + struct rxkad_response *resp, + const struct rxrpc_crypt *session_key) { struct skcipher_request *req = rxkad_ci_req; struct scatterlist sg[1]; struct rxrpc_crypt iv; + int ret; _enter(",,%08x%08x", ntohl(session_key->n[0]), ntohl(session_key->n[1])); mutex_lock(&rxkad_ci_mutex); - if (crypto_sync_skcipher_setkey(rxkad_ci, session_key->x, - sizeof(*session_key)) < 0) - BUG(); + ret = crypto_sync_skcipher_setkey(rxkad_ci, session_key->x, + sizeof(*session_key)); + if (ret < 0) + goto unlock; memcpy(&iv, session_key, sizeof(iv)); @@ -1100,12 +1115,14 @@ static void rxkad_decrypt_response(struct rxrpc_connection *conn, skcipher_request_set_sync_tfm(req, rxkad_ci); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x); - crypto_skcipher_decrypt(req); + ret = crypto_skcipher_decrypt(req); skcipher_request_zero(req); +unlock: mutex_unlock(&rxkad_ci_mutex); _leave(""); + return ret; } /* @@ -1198,7 +1215,9 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, /* use the session key from inside the ticket to decrypt the * response */ - rxkad_decrypt_response(conn, response, &session_key); + ret = rxkad_decrypt_response(conn, response, &session_key); + if (ret < 0) + goto temporary_error_free_ticket; if (ntohl(response->encrypted.epoch) != conn->proto.epoch || ntohl(response->encrypted.cid) != conn->proto.cid || From ba4b2c6153794a11cbb99641145f55909ae5781d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 8 Apr 2026 13:12:45 +0100 Subject: [PATCH 78/85] rxrpc: Fix integer overflow in rxgk_verify_response() commit 699e52180f4231c257821c037ed5c99d5eb0edb8 upstream. In rxgk_verify_response(), there's a potential integer overflow due to rounding up token_len before checking it, thereby allowing the length check to be bypassed. Fix this by checking the unrounded value against len too (len is limited as the response must fit in a single UDP packet). Fixes: 9d1d2b59341f ("rxrpc: rxgk: Implement the yfs-rxgk security class (GSSAPI)") Closes: https://sashiko.dev/#/patchset/20260401105614.1696001-10-dhowells@redhat.com Signed-off-by: David Howells cc: Marc Dionne cc: Jeffrey Altman cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-18-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 1f864d9daaf622aeaa774404fd51e7d6a435b046) Signed-off-by: Wentao Guan --- net/rxrpc/rxgk.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index 13ffdc9352b0..cd16e8e275d2 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -1209,7 +1209,8 @@ static int rxgk_verify_response(struct rxrpc_connection *conn, token_offset = offset; token_len = ntohl(rhdr.token_len); - if (xdr_round_up(token_len) + sizeof(__be32) > len) + if (token_len > len || + xdr_round_up(token_len) + sizeof(__be32) > len) goto short_packet; trace_rxrpc_rx_response(conn, sp->hdr.serial, 0, sp->hdr.cksum, token_len); From 71336307049af1d4d78a3502881bc1439ff6da78 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 8 Apr 2026 13:12:46 +0100 Subject: [PATCH 79/85] rxrpc: Fix leak of rxgk context in rxgk_verify_response() commit 7e1876caa8363056f58a21d3b31b82c2daf7e608 upstream. Fix rxgk_verify_response() to clean up the rxgk context it creates. Fixes: 9d1d2b59341f ("rxrpc: rxgk: Implement the yfs-rxgk security class (GSSAPI)") Closes: https://sashiko.dev/#/patchset/20260401105614.1696001-10-dhowells@redhat.com Signed-off-by: David Howells cc: Marc Dionne cc: Jeffrey Altman cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-19-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 4b5e8365515f4409de7d3b92a439154ee4f90f6d) Signed-off-by: Wentao Guan --- net/rxrpc/rxgk.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index cd16e8e275d2..c7a3d485da68 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -1270,16 +1270,18 @@ static int rxgk_verify_response(struct rxrpc_connection *conn, if (ret < 0) { rxrpc_abort_conn(conn, skb, RXGK_SEALEDINCON, ret, rxgk_abort_resp_auth_dec); - goto out; + goto out_gk; } ret = rxgk_verify_authenticator(conn, krb5, skb, auth_offset, auth_len); if (ret < 0) - goto out; + goto out_gk; conn->key = key; key = NULL; ret = 0; +out_gk: + rxgk_put(gk); out: key_put(key); _leave(" = %d", ret); From a7dff2fd4612775d3af18d96d9daf999aa1e3f6d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 8 Apr 2026 13:12:47 +0100 Subject: [PATCH 80/85] rxrpc: Fix buffer overread in rxgk_do_verify_authenticator() commit f564af387c8c28238f8ebc13314c589d7ba8475d upstream. Fix rxgk_do_verify_authenticator() to check the buffer size before checking the nonce. Fixes: 9d1d2b59341f ("rxrpc: rxgk: Implement the yfs-rxgk security class (GSSAPI)") Closes: https://sashiko.dev/#/patchset/20260401105614.1696001-10-dhowells@redhat.com Signed-off-by: David Howells cc: Marc Dionne cc: Jeffrey Altman cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-20-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 794586789800b16dcbe235452494f4223ac80413) Signed-off-by: Wentao Guan --- net/rxrpc/rxgk.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index c7a3d485da68..c39f5066d8e8 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -1085,6 +1085,9 @@ static int rxgk_do_verify_authenticator(struct rxrpc_connection *conn, _enter(""); + if ((end - p) * sizeof(__be32) < 24) + return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO, + rxgk_abort_resp_short_auth); if (memcmp(p, conn->rxgk.nonce, 20) != 0) return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO, rxgk_abort_resp_bad_nonce); @@ -1098,7 +1101,7 @@ static int rxgk_do_verify_authenticator(struct rxrpc_connection *conn, p += xdr_round_up(app_len) / sizeof(__be32); if (end - p < 4) return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO, - rxgk_abort_resp_short_applen); + rxgk_abort_resp_short_auth); level = ntohl(*p++); epoch = ntohl(*p++); From 71cbc1cf4ac36ef3a66bf3b6b6ef5cd0ae8e5289 Mon Sep 17 00:00:00 2001 From: Wang Jie Date: Wed, 8 Apr 2026 13:12:48 +0100 Subject: [PATCH 81/85] rxrpc: only handle RESPONSE during service challenge commit c43ffdcfdbb5567b1f143556df8a04b4eeea041c upstream. Only process RESPONSE packets while the service connection is still in RXRPC_CONN_SERVICE_CHALLENGING. Check that state under state_lock before running response verification and security initialization, then use a local secured flag to decide whether to queue the secured-connection work after the state transition. This keeps duplicate or late RESPONSE packets from re-running the setup path and removes the unlocked post-transition state test. Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both") Reported-by: Yifan Wu Reported-by: Juefei Pu Co-developed-by: Yuan Tan Signed-off-by: Yuan Tan Suggested-by: Xin Liu Signed-off-by: Jie Wang Signed-off-by: Yang Yang Signed-off-by: David Howells cc: Marc Dionne cc: Jeffrey Altman cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-21-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit d0035e634dae83237ab7f5681eb52b2f65d0ceb8) Signed-off-by: Wentao Guan --- net/rxrpc/conn_event.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index c50cbfc5a313..9a41ec708aeb 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -247,6 +247,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + bool secured = false; int ret; if (conn->state == RXRPC_CONN_ABORTED) @@ -262,6 +263,13 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return ret; case RXRPC_PACKET_TYPE_RESPONSE: + spin_lock_irq(&conn->state_lock); + if (conn->state != RXRPC_CONN_SERVICE_CHALLENGING) { + spin_unlock_irq(&conn->state_lock); + return 0; + } + spin_unlock_irq(&conn->state_lock); + ret = conn->security->verify_response(conn, skb); if (ret < 0) return ret; @@ -272,11 +280,13 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return ret; spin_lock_irq(&conn->state_lock); - if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) + if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) { conn->state = RXRPC_CONN_SERVICE; + secured = true; + } spin_unlock_irq(&conn->state_lock); - if (conn->state == RXRPC_CONN_SERVICE) { + if (secured) { /* Offload call state flipping to the I/O thread. As * we've already received the packet, put it on the * front of the queue. From b6ba44c6795b3e538cc2b82f5c89204fe942e4db Mon Sep 17 00:00:00 2001 From: Pengpeng Hou Date: Wed, 8 Apr 2026 13:12:49 +0100 Subject: [PATCH 82/85] rxrpc: proc: size address buffers for %pISpc output commit a44ce6aa2efb61fe44f2cfab72bb01544bbca272 upstream. The AF_RXRPC procfs helpers format local and remote socket addresses into fixed 50-byte stack buffers with "%pISpc". That is too small for the longest current-tree IPv6-with-port form the formatter can produce. In lib/vsprintf.c, the compressed IPv6 path uses a dotted-quad tail not only for v4mapped addresses, but also for ISATAP addresses via ipv6_addr_is_isatap(). As a result, a case such as [ffff:ffff:ffff:ffff:0:5efe:255.255.255.255]:65535 is possible with the current formatter. That is 50 visible characters, so 51 bytes including the trailing NUL, which does not fit in the existing char[50] buffers used by net/rxrpc/proc.c. Size the buffers from the formatter's maximum textual form and switch the call sites to scnprintf(). Changes since v1: - correct the changelog to cite the actual maximum current-tree case explicitly - frame the proof around the ISATAP formatting path instead of the earlier mapped-v4 example Fixes: 75b54cb57ca3 ("rxrpc: Add IPv6 support") Signed-off-by: Pengpeng Hou Signed-off-by: David Howells cc: Marc Dionne cc: Anderson Nascimento cc: Simon Horman cc: linux-afs@lists.infradead.org cc: stable@kernel.org Link: https://patch.msgid.link/20260408121252.2249051-22-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit db297c78ce537c9ac96f0eda9b25ad72c8caefa9) Signed-off-by: Wentao Guan --- net/rxrpc/proc.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 7755fca5beb8..e9a27fa7b25d 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -10,6 +10,10 @@ #include #include "ar-internal.h" +#define RXRPC_PROC_ADDRBUF_SIZE \ + (sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + \ + sizeof(":12345")) + static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = { [RXRPC_CONN_UNUSED] = "Unused ", [RXRPC_CONN_CLIENT_UNSECURED] = "ClUnsec ", @@ -53,7 +57,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); enum rxrpc_call_state state; rxrpc_seq_t tx_bottom; - char lbuff[50], rbuff[50]; + char lbuff[RXRPC_PROC_ADDRBUF_SIZE], rbuff[RXRPC_PROC_ADDRBUF_SIZE]; long timeout = 0; if (v == &rxnet->calls) { @@ -69,11 +73,11 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) local = call->local; if (local) - sprintf(lbuff, "%pISpc", &local->srx.transport); + scnprintf(lbuff, sizeof(lbuff), "%pISpc", &local->srx.transport); else strcpy(lbuff, "no_local"); - sprintf(rbuff, "%pISpc", &call->dest_srx.transport); + scnprintf(rbuff, sizeof(rbuff), "%pISpc", &call->dest_srx.transport); state = rxrpc_call_state(call); if (state != RXRPC_CALL_SERVER_PREALLOC) @@ -142,7 +146,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) struct rxrpc_connection *conn; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); const char *state; - char lbuff[50], rbuff[50]; + char lbuff[RXRPC_PROC_ADDRBUF_SIZE], rbuff[RXRPC_PROC_ADDRBUF_SIZE]; if (v == &rxnet->conn_proc_list) { seq_puts(seq, @@ -161,8 +165,8 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) goto print; } - sprintf(lbuff, "%pISpc", &conn->local->srx.transport); - sprintf(rbuff, "%pISpc", &conn->peer->srx.transport); + scnprintf(lbuff, sizeof(lbuff), "%pISpc", &conn->local->srx.transport); + scnprintf(rbuff, sizeof(rbuff), "%pISpc", &conn->peer->srx.transport); print: state = rxrpc_is_conn_aborted(conn) ? rxrpc_call_completions[conn->completion] : @@ -228,7 +232,7 @@ static int rxrpc_bundle_seq_show(struct seq_file *seq, void *v) { struct rxrpc_bundle *bundle; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); - char lbuff[50], rbuff[50]; + char lbuff[RXRPC_PROC_ADDRBUF_SIZE], rbuff[RXRPC_PROC_ADDRBUF_SIZE]; if (v == &rxnet->bundle_proc_list) { seq_puts(seq, @@ -242,8 +246,8 @@ static int rxrpc_bundle_seq_show(struct seq_file *seq, void *v) bundle = list_entry(v, struct rxrpc_bundle, proc_link); - sprintf(lbuff, "%pISpc", &bundle->local->srx.transport); - sprintf(rbuff, "%pISpc", &bundle->peer->srx.transport); + scnprintf(lbuff, sizeof(lbuff), "%pISpc", &bundle->local->srx.transport); + scnprintf(rbuff, sizeof(rbuff), "%pISpc", &bundle->peer->srx.transport); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %3u %3d" " %c%c%c %08x | %08x %08x %08x %08x %08x\n", @@ -279,7 +283,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) { struct rxrpc_peer *peer; time64_t now; - char lbuff[50], rbuff[50]; + char lbuff[RXRPC_PROC_ADDRBUF_SIZE], rbuff[RXRPC_PROC_ADDRBUF_SIZE]; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -290,9 +294,9 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) peer = list_entry(v, struct rxrpc_peer, hash_link); - sprintf(lbuff, "%pISpc", &peer->local->srx.transport); + scnprintf(lbuff, sizeof(lbuff), "%pISpc", &peer->local->srx.transport); - sprintf(rbuff, "%pISpc", &peer->srx.transport); + scnprintf(rbuff, sizeof(rbuff), "%pISpc", &peer->srx.transport); now = ktime_get_seconds(); seq_printf(seq, @@ -401,7 +405,7 @@ const struct seq_operations rxrpc_peer_seq_ops = { static int rxrpc_local_seq_show(struct seq_file *seq, void *v) { struct rxrpc_local *local; - char lbuff[50]; + char lbuff[RXRPC_PROC_ADDRBUF_SIZE]; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -412,7 +416,7 @@ static int rxrpc_local_seq_show(struct seq_file *seq, void *v) local = hlist_entry(v, struct rxrpc_local, link); - sprintf(lbuff, "%pISpc", &local->srx.transport); + scnprintf(lbuff, sizeof(lbuff), "%pISpc", &local->srx.transport); seq_printf(seq, "UDP %-47.47s %3u %3u %3u\n", From c315094f91b38e0b82e0a3e4f7fbeaadc366adc1 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Fri, 3 Apr 2026 09:45:12 +0800 Subject: [PATCH 83/85] net: skb: fix cross-cache free of KFENCE-allocated skb head commit 0f42e3f4fe2a58394e37241d02d9ca6ab7b7d516 upstream. SKB_SMALL_HEAD_CACHE_SIZE is intentionally set to a non-power-of-2 value (e.g. 704 on x86_64) to avoid collisions with generic kmalloc bucket sizes. This ensures that skb_kfree_head() can reliably use skb_end_offset to distinguish skb heads allocated from skb_small_head_cache vs. generic kmalloc caches. However, when KFENCE is enabled, kfence_ksize() returns the exact requested allocation size instead of the slab bucket size. If a caller (e.g. bpf_test_init) allocates skb head data via kzalloc() and the requested size happens to equal SKB_SMALL_HEAD_CACHE_SIZE, then slab_build_skb() -> ksize() returns that exact value. After subtracting skb_shared_info overhead, skb_end_offset ends up matching SKB_SMALL_HEAD_HEADROOM, causing skb_kfree_head() to incorrectly free the object to skb_small_head_cache instead of back to the original kmalloc cache, resulting in a slab cross-cache free: kmem_cache_free(skbuff_small_head): Wrong slab cache. Expected skbuff_small_head but got kmalloc-1k Fix this by always calling kfree(head) in skb_kfree_head(). This keeps the free path generic and avoids allocator-specific misclassification for KFENCE objects. Fixes: bf9f1baa279f ("net: add dedicated kmem_cache for typical/small skb->head") Reported-by: Antonius Closes: https://lore.kernel.org/netdev/CAK8a0jxC5L5N7hq-DT2_NhUyjBxrPocoiDazzsBk4TGgT1r4-A@mail.gmail.com/ Signed-off-by: Jiayuan Chen Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260403014517.142550-1-jiayuan.chen@linux.dev Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 2d64618ea846d8d033477311f805ca487d6a6696) Signed-off-by: Wentao Guan --- net/core/skbuff.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 60d89899fdb9..a4695882d1c4 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1042,10 +1042,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb) static void skb_kfree_head(void *head, unsigned int end_offset) { - if (end_offset == SKB_SMALL_HEAD_HEADROOM) - kmem_cache_free(net_hotdata.skb_small_head_cache, head); - else - kfree(head); + kfree(head); } static void skb_free_head(struct sk_buff *skb) From 7d459b4712c6bc6ee1bf5c56d58c98d0feec94fe Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Tue, 7 Apr 2026 11:40:03 +0200 Subject: [PATCH 84/85] x86/CPU: Fix FPDSS on Zen1 commit e55d98e7756135f32150b9b8f75d580d0d4b2dd3 upstream. Zen1's hardware divider can leave, under certain circumstances, partial results from previous operations. Those results can be leaked by another, attacker thread. Fix that with a chicken bit. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman (cherry picked from commit ad17f07e95e6e8505e2153e5b391f0d27eacce25) Signed-off-by: Wentao Guan --- arch/x86/include/asm/msr-index.h | 3 +++ arch/x86/kernel/cpu/amd.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d9e03c6d1d5c..66ddea295c26 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -645,6 +645,9 @@ #define MSR_AMD64_DC_CFG 0xc0011022 #define MSR_AMD64_TW_CFG 0xc0011023 +#define MSR_AMD64_FP_CFG 0xc0011028 +#define MSR_AMD64_FP_CFG_ZEN1_DENORM_FIX_BIT 9 + #define MSR_AMD64_DE_CFG 0xc0011029 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT 1 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 0ffd7ca1902f..d293ebb4a7ef 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -950,6 +950,9 @@ static void init_amd_zen1(struct cpuinfo_x86 *c) msr_clear_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); clear_cpu_cap(c, X86_FEATURE_IRPERF); } + + pr_notice_once("AMD Zen1 FPDSS bug detected, enabling mitigation.\n"); + msr_set_bit(MSR_AMD64_FP_CFG, MSR_AMD64_FP_CFG_ZEN1_DENORM_FIX_BIT); } static const struct x86_cpu_id amd_zenbleed_microcode[] = { From 153ec0dce4c54663bf0dbfc96b61929e5bd4cd98 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 18 Apr 2026 10:45:02 +0200 Subject: [PATCH 85/85] Linux 6.18.23 Link: https://lore.kernel.org/r/20260413155731.019638460@linuxfoundation.org Tested-by: Brett A C Sheffield Tested-by: Florian Fainelli Tested-by: Wentao Guan Tested-by: Jon Hunter Tested-by: Pavel Machek (CIP) Tested-by: Ron Economos Tested-by: Shuah Khan Tested-by: Miguel Ojeda Tested-by: Peter Schneider Tested-by: Barry K. Nathan Tested-by: Shung-Hsi Yu Tested-by: Mark Brown Tested-by: Dileep Malepu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 47a33eea6d5145d53e42315381ef28286c2218fb) Signed-off-by: Wentao Guan --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 3ceba736eecf..df10145ce27c 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 18 -SUBLEVEL = 22 +SUBLEVEL = 23 EXTRAVERSION = NAME = Baby Opossum Posse