--- /dev/null
+From d8f74a367f3dd9380aa3c562ee78bb4d192cc419 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 15 Apr 2024 05:21:55 +0100
+Subject: ARM: 9381/1: kasan: clear stale stack poison
+
+From: Boy.Wu <boy.wu@mediatek.com>
+
+[ Upstream commit c4238686f9093b98bd6245a348bcf059cdce23af ]
+
+We found below OOB crash:
+
+[ 33.452494] ==================================================================
+[ 33.453513] BUG: KASAN: stack-out-of-bounds in refresh_cpu_vm_stats.constprop.0+0xcc/0x2ec
+[ 33.454660] Write of size 164 at addr c1d03d30 by task swapper/0/0
+[ 33.455515]
+[ 33.455767] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G O 6.1.25-mainline #1
+[ 33.456880] Hardware name: Generic DT based system
+[ 33.457555] unwind_backtrace from show_stack+0x18/0x1c
+[ 33.458326] show_stack from dump_stack_lvl+0x40/0x4c
+[ 33.459072] dump_stack_lvl from print_report+0x158/0x4a4
+[ 33.459863] print_report from kasan_report+0x9c/0x148
+[ 33.460616] kasan_report from kasan_check_range+0x94/0x1a0
+[ 33.461424] kasan_check_range from memset+0x20/0x3c
+[ 33.462157] memset from refresh_cpu_vm_stats.constprop.0+0xcc/0x2ec
+[ 33.463064] refresh_cpu_vm_stats.constprop.0 from tick_nohz_idle_stop_tick+0x180/0x53c
+[ 33.464181] tick_nohz_idle_stop_tick from do_idle+0x264/0x354
+[ 33.465029] do_idle from cpu_startup_entry+0x20/0x24
+[ 33.465769] cpu_startup_entry from rest_init+0xf0/0xf4
+[ 33.466528] rest_init from arch_post_acpi_subsys_init+0x0/0x18
+[ 33.467397]
+[ 33.467644] The buggy address belongs to stack of task swapper/0/0
+[ 33.468493] and is located at offset 112 in frame:
+[ 33.469172] refresh_cpu_vm_stats.constprop.0+0x0/0x2ec
+[ 33.469917]
+[ 33.470165] This frame has 2 objects:
+[ 33.470696] [32, 76) 'global_zone_diff'
+[ 33.470729] [112, 276) 'global_node_diff'
+[ 33.471294]
+[ 33.472095] The buggy address belongs to the physical page:
+[ 33.472862] page:3cd72da8 refcount:1 mapcount:0 mapping:00000000 index:0x0 pfn:0x41d03
+[ 33.473944] flags: 0x1000(reserved|zone=0)
+[ 33.474565] raw: 00001000 ed741470 ed741470 00000000 00000000 00000000 ffffffff 00000001
+[ 33.475656] raw: 00000000
+[ 33.476050] page dumped because: kasan: bad access detected
+[ 33.476816]
+[ 33.477061] Memory state around the buggy address:
+[ 33.477732] c1d03c00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
+[ 33.478630] c1d03c80: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 00 00
+[ 33.479526] >c1d03d00: 00 04 f2 f2 f2 f2 00 00 00 00 00 00 f1 f1 f1 f1
+[ 33.480415] ^
+[ 33.481195] c1d03d80: 00 00 00 00 00 00 00 00 00 00 04 f3 f3 f3 f3 f3
+[ 33.482088] c1d03e00: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00
+[ 33.482978] ==================================================================
+
+We find the root cause of this OOB is that arm does not clear stale stack
+poison in the case of cpuidle.
+
+This patch refer to arch/arm64/kernel/sleep.S to resolve this issue.
+
+From cited commit [1] that explain the problem
+
+Functions which the compiler has instrumented for KASAN place poison on
+the stack shadow upon entry and remove this poison prior to returning.
+
+In the case of cpuidle, CPUs exit the kernel a number of levels deep in
+C code. Any instrumented functions on this critical path will leave
+portions of the stack shadow poisoned.
+
+If CPUs lose context and return to the kernel via a cold path, we
+restore a prior context saved in __cpu_suspend_enter are forgotten, and
+we never remove the poison they placed in the stack shadow area by
+functions calls between this and the actual exit of the kernel.
+
+Thus, (depending on stackframe layout) subsequent calls to instrumented
+functions may hit this stale poison, resulting in (spurious) KASAN
+splats to the console.
+
+To avoid this, clear any stale poison from the idle thread for a CPU
+prior to bringing a CPU online.
+
+From cited commit [2]
+
+Extend to check for CONFIG_KASAN_STACK
+
+[1] commit 0d97e6d8024c ("arm64: kasan: clear stale stack poison")
+[2] commit d56a9ef84bd0 ("kasan, arm64: unpoison stack only with CONFIG_KASAN_STACK")
+
+Signed-off-by: Boy Wu <boy.wu@mediatek.com>
+Reviewed-by: Mark Rutland <mark.rutland@arm.com>
+Acked-by: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
+Fixes: 5615f69bc209 ("ARM: 9016/2: Initialize the mapping of KASan shadow memory")
+Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/arm/kernel/sleep.S | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
+index a86a1d4f34618..93afd1005b43c 100644
+--- a/arch/arm/kernel/sleep.S
++++ b/arch/arm/kernel/sleep.S
+@@ -127,6 +127,10 @@ cpu_resume_after_mmu:
+ instr_sync
+ #endif
+ bl cpu_init @ restore the und/abt/irq banked regs
++#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
++ mov r0, sp
++ bl kasan_unpoison_task_stack_below
++#endif
+ mov r0, #0 @ return zero on success
+ ldmfd sp!, {r4 - r11, pc}
+ ENDPROC(cpu_resume_after_mmu)
+--
+2.43.0
+
--- /dev/null
+From 280cd1b1c1b6e36dcda0e6dcbe4deff73404acf2 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 25 Apr 2024 22:23:45 +0800
+Subject: Bluetooth: Fix use-after-free bugs caused by sco_sock_timeout
+
+From: Duoming Zhou <duoming@zju.edu.cn>
+
+[ Upstream commit 483bc08181827fc475643272ffb69c533007e546 ]
+
+When the sco connection is established and then, the sco socket
+is releasing, timeout_work will be scheduled to judge whether
+the sco disconnection is timeout. The sock will be deallocated
+later, but it is dereferenced again in sco_sock_timeout. As a
+result, the use-after-free bugs will happen. The root cause is
+shown below:
+
+ Cleanup Thread | Worker Thread
+sco_sock_release |
+ sco_sock_close |
+ __sco_sock_close |
+ sco_sock_set_timer |
+ schedule_delayed_work |
+ sco_sock_kill | (wait a time)
+ sock_put(sk) //FREE | sco_sock_timeout
+ | sock_hold(sk) //USE
+
+The KASAN report triggered by POC is shown below:
+
+[ 95.890016] ==================================================================
+[ 95.890496] BUG: KASAN: slab-use-after-free in sco_sock_timeout+0x5e/0x1c0
+[ 95.890755] Write of size 4 at addr ffff88800c388080 by task kworker/0:0/7
+...
+[ 95.890755] Workqueue: events sco_sock_timeout
+[ 95.890755] Call Trace:
+[ 95.890755] <TASK>
+[ 95.890755] dump_stack_lvl+0x45/0x110
+[ 95.890755] print_address_description+0x78/0x390
+[ 95.890755] print_report+0x11b/0x250
+[ 95.890755] ? __virt_addr_valid+0xbe/0xf0
+[ 95.890755] ? sco_sock_timeout+0x5e/0x1c0
+[ 95.890755] kasan_report+0x139/0x170
+[ 95.890755] ? update_load_avg+0xe5/0x9f0
+[ 95.890755] ? sco_sock_timeout+0x5e/0x1c0
+[ 95.890755] kasan_check_range+0x2c3/0x2e0
+[ 95.890755] sco_sock_timeout+0x5e/0x1c0
+[ 95.890755] process_one_work+0x561/0xc50
+[ 95.890755] worker_thread+0xab2/0x13c0
+[ 95.890755] ? pr_cont_work+0x490/0x490
+[ 95.890755] kthread+0x279/0x300
+[ 95.890755] ? pr_cont_work+0x490/0x490
+[ 95.890755] ? kthread_blkcg+0xa0/0xa0
+[ 95.890755] ret_from_fork+0x34/0x60
+[ 95.890755] ? kthread_blkcg+0xa0/0xa0
+[ 95.890755] ret_from_fork_asm+0x11/0x20
+[ 95.890755] </TASK>
+[ 95.890755]
+[ 95.890755] Allocated by task 506:
+[ 95.890755] kasan_save_track+0x3f/0x70
+[ 95.890755] __kasan_kmalloc+0x86/0x90
+[ 95.890755] __kmalloc+0x17f/0x360
+[ 95.890755] sk_prot_alloc+0xe1/0x1a0
+[ 95.890755] sk_alloc+0x31/0x4e0
+[ 95.890755] bt_sock_alloc+0x2b/0x2a0
+[ 95.890755] sco_sock_create+0xad/0x320
+[ 95.890755] bt_sock_create+0x145/0x320
+[ 95.890755] __sock_create+0x2e1/0x650
+[ 95.890755] __sys_socket+0xd0/0x280
+[ 95.890755] __x64_sys_socket+0x75/0x80
+[ 95.890755] do_syscall_64+0xc4/0x1b0
+[ 95.890755] entry_SYSCALL_64_after_hwframe+0x67/0x6f
+[ 95.890755]
+[ 95.890755] Freed by task 506:
+[ 95.890755] kasan_save_track+0x3f/0x70
+[ 95.890755] kasan_save_free_info+0x40/0x50
+[ 95.890755] poison_slab_object+0x118/0x180
+[ 95.890755] __kasan_slab_free+0x12/0x30
+[ 95.890755] kfree+0xb2/0x240
+[ 95.890755] __sk_destruct+0x317/0x410
+[ 95.890755] sco_sock_release+0x232/0x280
+[ 95.890755] sock_close+0xb2/0x210
+[ 95.890755] __fput+0x37f/0x770
+[ 95.890755] task_work_run+0x1ae/0x210
+[ 95.890755] get_signal+0xe17/0xf70
+[ 95.890755] arch_do_signal_or_restart+0x3f/0x520
+[ 95.890755] syscall_exit_to_user_mode+0x55/0x120
+[ 95.890755] do_syscall_64+0xd1/0x1b0
+[ 95.890755] entry_SYSCALL_64_after_hwframe+0x67/0x6f
+[ 95.890755]
+[ 95.890755] The buggy address belongs to the object at ffff88800c388000
+[ 95.890755] which belongs to the cache kmalloc-1k of size 1024
+[ 95.890755] The buggy address is located 128 bytes inside of
+[ 95.890755] freed 1024-byte region [ffff88800c388000, ffff88800c388400)
+[ 95.890755]
+[ 95.890755] The buggy address belongs to the physical page:
+[ 95.890755] page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88800c38a800 pfn:0xc388
+[ 95.890755] head: order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0
+[ 95.890755] anon flags: 0x100000000000840(slab|head|node=0|zone=1)
+[ 95.890755] page_type: 0xffffffff()
+[ 95.890755] raw: 0100000000000840 ffff888006842dc0 0000000000000000 0000000000000001
+[ 95.890755] raw: ffff88800c38a800 000000000010000a 00000001ffffffff 0000000000000000
+[ 95.890755] head: 0100000000000840 ffff888006842dc0 0000000000000000 0000000000000001
+[ 95.890755] head: ffff88800c38a800 000000000010000a 00000001ffffffff 0000000000000000
+[ 95.890755] head: 0100000000000003 ffffea000030e201 ffffea000030e248 00000000ffffffff
+[ 95.890755] head: 0000000800000000 0000000000000000 00000000ffffffff 0000000000000000
+[ 95.890755] page dumped because: kasan: bad access detected
+[ 95.890755]
+[ 95.890755] Memory state around the buggy address:
+[ 95.890755] ffff88800c387f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
+[ 95.890755] ffff88800c388000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
+[ 95.890755] >ffff88800c388080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
+[ 95.890755] ^
+[ 95.890755] ffff88800c388100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
+[ 95.890755] ffff88800c388180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
+[ 95.890755] ==================================================================
+
+Fix this problem by adding a check protected by sco_conn_lock to judget
+whether the conn->hcon is null. Because the conn->hcon will be set to null,
+when the sock is releasing.
+
+Fixes: ba316be1b6a0 ("Bluetooth: schedule SCO timeouts with delayed_work")
+Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
+Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/bluetooth/sco.c | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
+index 3cc9fab8e8384..ede7391f3aa98 100644
+--- a/net/bluetooth/sco.c
++++ b/net/bluetooth/sco.c
+@@ -83,6 +83,10 @@ static void sco_sock_timeout(struct work_struct *work)
+ struct sock *sk;
+
+ sco_conn_lock(conn);
++ if (!conn->hcon) {
++ sco_conn_unlock(conn);
++ return;
++ }
+ sk = conn->sk;
+ if (sk)
+ sock_hold(sk);
+--
+2.43.0
+
--- /dev/null
+From d8d08a047a623f742ec824ba376191733e17c407 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 2 May 2024 12:09:31 -0400
+Subject: Bluetooth: HCI: Fix potential null-ptr-deref
+
+From: Sungwoo Kim <iam@sung-woo.kim>
+
+[ Upstream commit d2706004a1b8b526592e823d7e52551b518a7941 ]
+
+Fix potential null-ptr-deref in hci_le_big_sync_established_evt().
+
+Fixes: f777d8827817 (Bluetooth: ISO: Notify user space about failed bis connections)
+Signed-off-by: Sungwoo Kim <iam@sung-woo.kim>
+Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/bluetooth/hci_event.c | 2 ++
+ 1 file changed, 2 insertions(+)
+
+diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
+index 1b4abf8e90f6b..9274d32550493 100644
+--- a/net/bluetooth/hci_event.c
++++ b/net/bluetooth/hci_event.c
+@@ -7200,6 +7200,8 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
+ u16 handle = le16_to_cpu(ev->bis[i]);
+
+ bis = hci_conn_hash_lookup_handle(hdev, handle);
++ if (!bis)
++ continue;
+
+ set_bit(HCI_CONN_BIG_SYNC_FAILED, &bis->flags);
+ hci_connect_cfm(bis, ev->status);
+--
+2.43.0
+
--- /dev/null
+From f7873cb93c327c6daf33ba3b389f8ddeef601600 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 2 May 2024 20:57:36 +0800
+Subject: Bluetooth: l2cap: fix null-ptr-deref in l2cap_chan_timeout
+
+From: Duoming Zhou <duoming@zju.edu.cn>
+
+[ Upstream commit adf0398cee86643b8eacde95f17d073d022f782c ]
+
+There is a race condition between l2cap_chan_timeout() and
+l2cap_chan_del(). When we use l2cap_chan_del() to delete the
+channel, the chan->conn will be set to null. But the conn could
+be dereferenced again in the mutex_lock() of l2cap_chan_timeout().
+As a result the null pointer dereference bug will happen. The
+KASAN report triggered by POC is shown below:
+
+[ 472.074580] ==================================================================
+[ 472.075284] BUG: KASAN: null-ptr-deref in mutex_lock+0x68/0xc0
+[ 472.075308] Write of size 8 at addr 0000000000000158 by task kworker/0:0/7
+[ 472.075308]
+[ 472.075308] CPU: 0 PID: 7 Comm: kworker/0:0 Not tainted 6.9.0-rc5-00356-g78c0094a146b #36
+[ 472.075308] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu4
+[ 472.075308] Workqueue: events l2cap_chan_timeout
+[ 472.075308] Call Trace:
+[ 472.075308] <TASK>
+[ 472.075308] dump_stack_lvl+0x137/0x1a0
+[ 472.075308] print_report+0x101/0x250
+[ 472.075308] ? __virt_addr_valid+0x77/0x160
+[ 472.075308] ? mutex_lock+0x68/0xc0
+[ 472.075308] kasan_report+0x139/0x170
+[ 472.075308] ? mutex_lock+0x68/0xc0
+[ 472.075308] kasan_check_range+0x2c3/0x2e0
+[ 472.075308] mutex_lock+0x68/0xc0
+[ 472.075308] l2cap_chan_timeout+0x181/0x300
+[ 472.075308] process_one_work+0x5d2/0xe00
+[ 472.075308] worker_thread+0xe1d/0x1660
+[ 472.075308] ? pr_cont_work+0x5e0/0x5e0
+[ 472.075308] kthread+0x2b7/0x350
+[ 472.075308] ? pr_cont_work+0x5e0/0x5e0
+[ 472.075308] ? kthread_blkcg+0xd0/0xd0
+[ 472.075308] ret_from_fork+0x4d/0x80
+[ 472.075308] ? kthread_blkcg+0xd0/0xd0
+[ 472.075308] ret_from_fork_asm+0x11/0x20
+[ 472.075308] </TASK>
+[ 472.075308] ==================================================================
+[ 472.094860] Disabling lock debugging due to kernel taint
+[ 472.096136] BUG: kernel NULL pointer dereference, address: 0000000000000158
+[ 472.096136] #PF: supervisor write access in kernel mode
+[ 472.096136] #PF: error_code(0x0002) - not-present page
+[ 472.096136] PGD 0 P4D 0
+[ 472.096136] Oops: 0002 [#1] PREEMPT SMP KASAN NOPTI
+[ 472.096136] CPU: 0 PID: 7 Comm: kworker/0:0 Tainted: G B 6.9.0-rc5-00356-g78c0094a146b #36
+[ 472.096136] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu4
+[ 472.096136] Workqueue: events l2cap_chan_timeout
+[ 472.096136] RIP: 0010:mutex_lock+0x88/0xc0
+[ 472.096136] Code: be 08 00 00 00 e8 f8 23 1f fd 4c 89 f7 be 08 00 00 00 e8 eb 23 1f fd 42 80 3c 23 00 74 08 48 88
+[ 472.096136] RSP: 0018:ffff88800744fc78 EFLAGS: 00000246
+[ 472.096136] RAX: 0000000000000000 RBX: 1ffff11000e89f8f RCX: ffffffff8457c865
+[ 472.096136] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff88800744fc78
+[ 472.096136] RBP: 0000000000000158 R08: ffff88800744fc7f R09: 1ffff11000e89f8f
+[ 472.096136] R10: dffffc0000000000 R11: ffffed1000e89f90 R12: dffffc0000000000
+[ 472.096136] R13: 0000000000000158 R14: ffff88800744fc78 R15: ffff888007405a00
+[ 472.096136] FS: 0000000000000000(0000) GS:ffff88806d200000(0000) knlGS:0000000000000000
+[ 472.096136] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+[ 472.096136] CR2: 0000000000000158 CR3: 000000000da32000 CR4: 00000000000006f0
+[ 472.096136] Call Trace:
+[ 472.096136] <TASK>
+[ 472.096136] ? __die_body+0x8d/0xe0
+[ 472.096136] ? page_fault_oops+0x6b8/0x9a0
+[ 472.096136] ? kernelmode_fixup_or_oops+0x20c/0x2a0
+[ 472.096136] ? do_user_addr_fault+0x1027/0x1340
+[ 472.096136] ? _printk+0x7a/0xa0
+[ 472.096136] ? mutex_lock+0x68/0xc0
+[ 472.096136] ? add_taint+0x42/0xd0
+[ 472.096136] ? exc_page_fault+0x6a/0x1b0
+[ 472.096136] ? asm_exc_page_fault+0x26/0x30
+[ 472.096136] ? mutex_lock+0x75/0xc0
+[ 472.096136] ? mutex_lock+0x88/0xc0
+[ 472.096136] ? mutex_lock+0x75/0xc0
+[ 472.096136] l2cap_chan_timeout+0x181/0x300
+[ 472.096136] process_one_work+0x5d2/0xe00
+[ 472.096136] worker_thread+0xe1d/0x1660
+[ 472.096136] ? pr_cont_work+0x5e0/0x5e0
+[ 472.096136] kthread+0x2b7/0x350
+[ 472.096136] ? pr_cont_work+0x5e0/0x5e0
+[ 472.096136] ? kthread_blkcg+0xd0/0xd0
+[ 472.096136] ret_from_fork+0x4d/0x80
+[ 472.096136] ? kthread_blkcg+0xd0/0xd0
+[ 472.096136] ret_from_fork_asm+0x11/0x20
+[ 472.096136] </TASK>
+[ 472.096136] Modules linked in:
+[ 472.096136] CR2: 0000000000000158
+[ 472.096136] ---[ end trace 0000000000000000 ]---
+[ 472.096136] RIP: 0010:mutex_lock+0x88/0xc0
+[ 472.096136] Code: be 08 00 00 00 e8 f8 23 1f fd 4c 89 f7 be 08 00 00 00 e8 eb 23 1f fd 42 80 3c 23 00 74 08 48 88
+[ 472.096136] RSP: 0018:ffff88800744fc78 EFLAGS: 00000246
+[ 472.096136] RAX: 0000000000000000 RBX: 1ffff11000e89f8f RCX: ffffffff8457c865
+[ 472.096136] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff88800744fc78
+[ 472.096136] RBP: 0000000000000158 R08: ffff88800744fc7f R09: 1ffff11000e89f8f
+[ 472.132932] R10: dffffc0000000000 R11: ffffed1000e89f90 R12: dffffc0000000000
+[ 472.132932] R13: 0000000000000158 R14: ffff88800744fc78 R15: ffff888007405a00
+[ 472.132932] FS: 0000000000000000(0000) GS:ffff88806d200000(0000) knlGS:0000000000000000
+[ 472.132932] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+[ 472.132932] CR2: 0000000000000158 CR3: 000000000da32000 CR4: 00000000000006f0
+[ 472.132932] Kernel panic - not syncing: Fatal exception
+[ 472.132932] Kernel Offset: disabled
+[ 472.132932] ---[ end Kernel panic - not syncing: Fatal exception ]---
+
+Add a check to judge whether the conn is null in l2cap_chan_timeout()
+in order to mitigate the bug.
+
+Fixes: 3df91ea20e74 ("Bluetooth: Revert to mutexes from RCU list")
+Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
+Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/bluetooth/l2cap_core.c | 3 +++
+ 1 file changed, 3 insertions(+)
+
+diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
+index 706d2478ddb33..1e961cfaa07b3 100644
+--- a/net/bluetooth/l2cap_core.c
++++ b/net/bluetooth/l2cap_core.c
+@@ -415,6 +415,9 @@ static void l2cap_chan_timeout(struct work_struct *work)
+
+ BT_DBG("chan %p state %s", chan, state_to_string(chan->state));
+
++ if (!conn)
++ return;
++
+ mutex_lock(&conn->chan_lock);
+ /* __set_chan_timer() calls l2cap_chan_hold(chan) while scheduling
+ * this work. No need to call l2cap_chan_hold(chan) here again.
+--
+2.43.0
+
--- /dev/null
+From 113dd84b598520e89d6de3ddb7fd219230f087d4 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 30 Apr 2024 12:20:51 -0400
+Subject: Bluetooth: msft: fix slab-use-after-free in msft_do_close()
+
+From: Sungwoo Kim <iam@sung-woo.kim>
+
+[ Upstream commit 10f9f426ac6e752c8d87bf4346930ba347aaabac ]
+
+Tying the msft->data lifetime to hdev by freeing it in
+hci_release_dev() to fix the following case:
+
+[use]
+msft_do_close()
+ msft = hdev->msft_data;
+ if (!msft) ...(1) <- passed.
+ return;
+ mutex_lock(&msft->filter_lock); ...(4) <- used after freed.
+
+[free]
+msft_unregister()
+ msft = hdev->msft_data;
+ hdev->msft_data = NULL; ...(2)
+ kfree(msft); ...(3) <- msft is freed.
+
+==================================================================
+BUG: KASAN: slab-use-after-free in __mutex_lock_common
+kernel/locking/mutex.c:587 [inline]
+BUG: KASAN: slab-use-after-free in __mutex_lock+0x8f/0xc30
+kernel/locking/mutex.c:752
+Read of size 8 at addr ffff888106cbbca8 by task kworker/u5:2/309
+
+Fixes: bf6a4e30ffbd ("Bluetooth: disable advertisement filters during suspend")
+Signed-off-by: Sungwoo Kim <iam@sung-woo.kim>
+Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/bluetooth/hci_core.c | 3 +--
+ net/bluetooth/msft.c | 2 +-
+ net/bluetooth/msft.h | 4 ++--
+ 3 files changed, 4 insertions(+), 5 deletions(-)
+
+diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
+index 0592369579ab2..befe645d3f9bf 100644
+--- a/net/bluetooth/hci_core.c
++++ b/net/bluetooth/hci_core.c
+@@ -2736,8 +2736,6 @@ void hci_unregister_dev(struct hci_dev *hdev)
+
+ hci_unregister_suspend_notifier(hdev);
+
+- msft_unregister(hdev);
+-
+ hci_dev_do_close(hdev);
+
+ if (!test_bit(HCI_INIT, &hdev->flags) &&
+@@ -2791,6 +2789,7 @@ void hci_release_dev(struct hci_dev *hdev)
+ hci_discovery_filter_clear(hdev);
+ hci_blocked_keys_clear(hdev);
+ hci_codec_list_clear(&hdev->local_codecs);
++ msft_release(hdev);
+ hci_dev_unlock(hdev);
+
+ ida_destroy(&hdev->unset_handle_ida);
+diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c
+index 9612c5d1b13f6..d039683d3bdd4 100644
+--- a/net/bluetooth/msft.c
++++ b/net/bluetooth/msft.c
+@@ -769,7 +769,7 @@ void msft_register(struct hci_dev *hdev)
+ mutex_init(&msft->filter_lock);
+ }
+
+-void msft_unregister(struct hci_dev *hdev)
++void msft_release(struct hci_dev *hdev)
+ {
+ struct msft_data *msft = hdev->msft_data;
+
+diff --git a/net/bluetooth/msft.h b/net/bluetooth/msft.h
+index 2a63205b377b7..fe538e9c91c01 100644
+--- a/net/bluetooth/msft.h
++++ b/net/bluetooth/msft.h
+@@ -14,7 +14,7 @@
+
+ bool msft_monitor_supported(struct hci_dev *hdev);
+ void msft_register(struct hci_dev *hdev);
+-void msft_unregister(struct hci_dev *hdev);
++void msft_release(struct hci_dev *hdev);
+ void msft_do_open(struct hci_dev *hdev);
+ void msft_do_close(struct hci_dev *hdev);
+ void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb);
+@@ -35,7 +35,7 @@ static inline bool msft_monitor_supported(struct hci_dev *hdev)
+ }
+
+ static inline void msft_register(struct hci_dev *hdev) {}
+-static inline void msft_unregister(struct hci_dev *hdev) {}
++static inline void msft_release(struct hci_dev *hdev) {}
+ static inline void msft_do_open(struct hci_dev *hdev) {}
+ static inline void msft_do_close(struct hci_dev *hdev) {}
+ static inline void msft_vendor_evt(struct hci_dev *hdev, void *data,
+--
+2.43.0
+
--- /dev/null
+From 283ae1731095a4fd1d1f3249a452879332d7cbf8 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 13:20:43 +0100
+Subject: dt-bindings: net: mediatek: remove wrongly added clocks and SerDes
+
+From: Daniel Golle <daniel@makrotopia.org>
+
+[ Upstream commit cc349b0771dccebf0fa9f5e1822ac444aef11448 ]
+
+Several clocks as well as both sgmiisys phandles were added by mistake
+to the Ethernet bindings for MT7988. Also, the total number of clocks
+didn't match with the actual number of items listed.
+
+This happened because the vendor driver which served as a reference uses
+a high number of syscon phandles to access various parts of the SoC
+which wasn't acceptable upstream. Hence several parts which have never
+previously been supported (such SerDes PHY and USXGMII PCS) are going to
+be implemented by separate drivers. As a result the device tree will
+look much more sane.
+
+Quickly align the bindings with the upcoming reality of the drivers
+actually adding support for the remaining Ethernet-related features of
+the MT7988 SoC.
+
+Fixes: c94a9aabec36 ("dt-bindings: net: mediatek,net: add mt7988-eth binding")
+Signed-off-by: Daniel Golle <daniel@makrotopia.org>
+Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+Link: https://lore.kernel.org/r/1569290b21cc787a424469ed74456a7e976b102d.1715084326.git.daniel@makrotopia.org
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ .../devicetree/bindings/net/mediatek,net.yaml | 22 ++-----------------
+ 1 file changed, 2 insertions(+), 20 deletions(-)
+
+diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml
+index e74502a0afe86..3202dc7967c5b 100644
+--- a/Documentation/devicetree/bindings/net/mediatek,net.yaml
++++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml
+@@ -337,8 +337,8 @@ allOf:
+ minItems: 4
+
+ clocks:
+- minItems: 34
+- maxItems: 34
++ minItems: 24
++ maxItems: 24
+
+ clock-names:
+ items:
+@@ -351,18 +351,6 @@ allOf:
+ - const: ethwarp_wocpu1
+ - const: ethwarp_wocpu0
+ - const: esw
+- - const: netsys0
+- - const: netsys1
+- - const: sgmii_tx250m
+- - const: sgmii_rx250m
+- - const: sgmii2_tx250m
+- - const: sgmii2_rx250m
+- - const: top_usxgmii0_sel
+- - const: top_usxgmii1_sel
+- - const: top_sgm0_sel
+- - const: top_sgm1_sel
+- - const: top_xfi_phy0_xtal_sel
+- - const: top_xfi_phy1_xtal_sel
+ - const: top_eth_gmii_sel
+ - const: top_eth_refck_50m_sel
+ - const: top_eth_sys_200m_sel
+@@ -375,16 +363,10 @@ allOf:
+ - const: top_netsys_sync_250m_sel
+ - const: top_netsys_ppefb_250m_sel
+ - const: top_netsys_warp_sel
+- - const: wocpu1
+- - const: wocpu0
+ - const: xgp1
+ - const: xgp2
+ - const: xgp3
+
+- mediatek,sgmiisys:
+- minItems: 2
+- maxItems: 2
+-
+ patternProperties:
+ "^mac@[0-1]$":
+ type: object
+--
+2.43.0
+
--- /dev/null
+From 4b3de9cf37e652cbcc45e72b46b7dec27aac9f62 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 13:12:14 +0200
+Subject: hsr: Simplify code for announcing HSR nodes timer setup
+
+From: Lukasz Majewski <lukma@denx.de>
+
+[ Upstream commit 4893b8b3ef8db2b182d1a1bebf6c7acf91405000 ]
+
+Up till now the code to start HSR announce timer, which triggers sending
+supervisory frames, was assuming that hsr_netdev_notify() would be called
+at least twice for hsrX interface. This was required to have different
+values for old and current values of network device's operstate.
+
+This is problematic for a case where hsrX interface is already in the
+operational state when hsr_netdev_notify() is called, so timer is not
+configured to trigger and as a result the hsrX is not sending supervisory
+frames to HSR ring.
+
+This error has been discovered when hsr_ping.sh script was run. To be
+more specific - for the hsr1 and hsr2 the hsr_netdev_notify() was
+called at least twice with different IF_OPER_{LOWERDOWN|DOWN|UP} states
+assigned in hsr_check_carrier_and_operstate(hsr). As a result there was
+no issue with sending supervisory frames.
+However, with hsr3, the notify function was called only once with
+operstate set to IF_OPER_UP and timer responsible for triggering
+supervisory frames was not fired.
+
+The solution is to use netif_oper_up() and netif_running() helper
+functions to assess if network hsrX device is up.
+Only then, when the timer is not already pending, it is started.
+Otherwise it is deactivated.
+
+Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
+Signed-off-by: Lukasz Majewski <lukma@denx.de>
+Reviewed-by: Simon Horman <horms@kernel.org>
+Link: https://lore.kernel.org/r/20240507111214.3519800-1-lukma@denx.de
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/hsr/hsr_device.c | 27 ++++++++++++---------------
+ 1 file changed, 12 insertions(+), 15 deletions(-)
+
+diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
+index cd337385e8592..c5f7bd01379ce 100644
+--- a/net/hsr/hsr_device.c
++++ b/net/hsr/hsr_device.c
+@@ -71,39 +71,36 @@ static bool hsr_check_carrier(struct hsr_port *master)
+ return false;
+ }
+
+-static void hsr_check_announce(struct net_device *hsr_dev,
+- unsigned char old_operstate)
++static void hsr_check_announce(struct net_device *hsr_dev)
+ {
+ struct hsr_priv *hsr;
+
+ hsr = netdev_priv(hsr_dev);
+-
+- if (READ_ONCE(hsr_dev->operstate) == IF_OPER_UP && old_operstate != IF_OPER_UP) {
+- /* Went up */
+- hsr->announce_count = 0;
+- mod_timer(&hsr->announce_timer,
+- jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL));
++ if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) {
++ /* Enable announce timer and start sending supervisory frames */
++ if (!timer_pending(&hsr->announce_timer)) {
++ hsr->announce_count = 0;
++ mod_timer(&hsr->announce_timer, jiffies +
++ msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL));
++ }
++ } else {
++ /* Deactivate the announce timer */
++ timer_delete(&hsr->announce_timer);
+ }
+-
+- if (READ_ONCE(hsr_dev->operstate) != IF_OPER_UP && old_operstate == IF_OPER_UP)
+- /* Went down */
+- del_timer(&hsr->announce_timer);
+ }
+
+ void hsr_check_carrier_and_operstate(struct hsr_priv *hsr)
+ {
+ struct hsr_port *master;
+- unsigned char old_operstate;
+ bool has_carrier;
+
+ master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
+ /* netif_stacked_transfer_operstate() cannot be used here since
+ * it doesn't set IF_OPER_LOWERLAYERDOWN (?)
+ */
+- old_operstate = READ_ONCE(master->dev->operstate);
+ has_carrier = hsr_check_carrier(master);
+ hsr_set_operstate(master, has_carrier);
+- hsr_check_announce(master->dev, old_operstate);
++ hsr_check_announce(master->dev);
+ }
+
+ int hsr_get_max_mtu(struct hsr_priv *hsr)
+--
+2.43.0
+
--- /dev/null
+From f1e95bc50846fc48a85b7fcd2fde8783a106e102 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sat, 4 May 2024 11:25:03 +0200
+Subject: hwmon: (corsair-cpro) Protect ccp->wait_input_report with a spinlock
+
+From: Aleksa Savic <savicaleksa83@gmail.com>
+
+[ Upstream commit d02abd57e79469a026213f7f5827a98d909f236a ]
+
+Through hidraw, userspace can cause a status report to be sent
+from the device. The parsing in ccp_raw_event() may happen in
+parallel to a send_usb_cmd() call (which resets the completion
+for tracking the report) if it's running on a different CPU where
+bottom half interrupts are not disabled.
+
+Add a spinlock around the complete_all() in ccp_raw_event() and
+reinit_completion() in send_usb_cmd() to prevent race issues.
+
+Fixes: 40c3a4454225 ("hwmon: add Corsair Commander Pro driver")
+Signed-off-by: Aleksa Savic <savicaleksa83@gmail.com>
+Acked-by: Marius Zachmann <mail@mariuszachmann.de>
+Link: https://lore.kernel.org/r/20240504092504.24158-4-savicaleksa83@gmail.com
+Signed-off-by: Guenter Roeck <linux@roeck-us.net>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/hwmon/corsair-cpro.c | 24 +++++++++++++++++++-----
+ 1 file changed, 19 insertions(+), 5 deletions(-)
+
+diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c
+index e65e3825af974..280b90646a873 100644
+--- a/drivers/hwmon/corsair-cpro.c
++++ b/drivers/hwmon/corsair-cpro.c
+@@ -16,6 +16,7 @@
+ #include <linux/module.h>
+ #include <linux/mutex.h>
+ #include <linux/slab.h>
++#include <linux/spinlock.h>
+ #include <linux/types.h>
+
+ #define USB_VENDOR_ID_CORSAIR 0x1b1c
+@@ -77,6 +78,8 @@
+ struct ccp_device {
+ struct hid_device *hdev;
+ struct device *hwmon_dev;
++ /* For reinitializing the completion below */
++ spinlock_t wait_input_report_lock;
+ struct completion wait_input_report;
+ struct mutex mutex; /* whenever buffer is used, lock before send_usb_cmd */
+ u8 *cmd_buffer;
+@@ -118,7 +121,15 @@ static int send_usb_cmd(struct ccp_device *ccp, u8 command, u8 byte1, u8 byte2,
+ ccp->cmd_buffer[2] = byte2;
+ ccp->cmd_buffer[3] = byte3;
+
++ /*
++ * Disable raw event parsing for a moment to safely reinitialize the
++ * completion. Reinit is done because hidraw could have triggered
++ * the raw event parsing and marked the ccp->wait_input_report
++ * completion as done.
++ */
++ spin_lock_bh(&ccp->wait_input_report_lock);
+ reinit_completion(&ccp->wait_input_report);
++ spin_unlock_bh(&ccp->wait_input_report_lock);
+
+ ret = hid_hw_output_report(ccp->hdev, ccp->cmd_buffer, OUT_BUFFER_SIZE);
+ if (ret < 0)
+@@ -136,11 +147,12 @@ static int ccp_raw_event(struct hid_device *hdev, struct hid_report *report, u8
+ struct ccp_device *ccp = hid_get_drvdata(hdev);
+
+ /* only copy buffer when requested */
+- if (completion_done(&ccp->wait_input_report))
+- return 0;
+-
+- memcpy(ccp->buffer, data, min(IN_BUFFER_SIZE, size));
+- complete_all(&ccp->wait_input_report);
++ spin_lock(&ccp->wait_input_report_lock);
++ if (!completion_done(&ccp->wait_input_report)) {
++ memcpy(ccp->buffer, data, min(IN_BUFFER_SIZE, size));
++ complete_all(&ccp->wait_input_report);
++ }
++ spin_unlock(&ccp->wait_input_report_lock);
+
+ return 0;
+ }
+@@ -515,7 +527,9 @@ static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id)
+
+ ccp->hdev = hdev;
+ hid_set_drvdata(hdev, ccp);
++
+ mutex_init(&ccp->mutex);
++ spin_lock_init(&ccp->wait_input_report_lock);
+ init_completion(&ccp->wait_input_report);
+
+ hid_device_io_start(hdev);
+--
+2.43.0
+
--- /dev/null
+From f9f9cbd3b01dfabfef2869292e594a630f8f4e8d Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sat, 4 May 2024 11:25:01 +0200
+Subject: hwmon: (corsair-cpro) Use a separate buffer for sending commands
+
+From: Aleksa Savic <savicaleksa83@gmail.com>
+
+[ Upstream commit e0cd85dc666cb08e1bd313d560cb4eff4d04219e ]
+
+Introduce cmd_buffer, a separate buffer for storing only
+the command that is sent to the device. Before this separation,
+the existing buffer was shared for both the command and the
+report received in ccp_raw_event(), which was copied into it.
+
+However, because of hidraw, the raw event parsing may be triggered
+in the middle of sending a command, resulting in outputting gibberish
+to the device. Using a separate buffer resolves this.
+
+Fixes: 40c3a4454225 ("hwmon: add Corsair Commander Pro driver")
+Signed-off-by: Aleksa Savic <savicaleksa83@gmail.com>
+Acked-by: Marius Zachmann <mail@mariuszachmann.de>
+Link: https://lore.kernel.org/r/20240504092504.24158-2-savicaleksa83@gmail.com
+Signed-off-by: Guenter Roeck <linux@roeck-us.net>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/hwmon/corsair-cpro.c | 19 ++++++++++++-------
+ 1 file changed, 12 insertions(+), 7 deletions(-)
+
+diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c
+index 463ab4296ede5..34136d1b04764 100644
+--- a/drivers/hwmon/corsair-cpro.c
++++ b/drivers/hwmon/corsair-cpro.c
+@@ -79,6 +79,7 @@ struct ccp_device {
+ struct device *hwmon_dev;
+ struct completion wait_input_report;
+ struct mutex mutex; /* whenever buffer is used, lock before send_usb_cmd */
++ u8 *cmd_buffer;
+ u8 *buffer;
+ int target[6];
+ DECLARE_BITMAP(temp_cnct, NUM_TEMP_SENSORS);
+@@ -111,15 +112,15 @@ static int send_usb_cmd(struct ccp_device *ccp, u8 command, u8 byte1, u8 byte2,
+ unsigned long t;
+ int ret;
+
+- memset(ccp->buffer, 0x00, OUT_BUFFER_SIZE);
+- ccp->buffer[0] = command;
+- ccp->buffer[1] = byte1;
+- ccp->buffer[2] = byte2;
+- ccp->buffer[3] = byte3;
++ memset(ccp->cmd_buffer, 0x00, OUT_BUFFER_SIZE);
++ ccp->cmd_buffer[0] = command;
++ ccp->cmd_buffer[1] = byte1;
++ ccp->cmd_buffer[2] = byte2;
++ ccp->cmd_buffer[3] = byte3;
+
+ reinit_completion(&ccp->wait_input_report);
+
+- ret = hid_hw_output_report(ccp->hdev, ccp->buffer, OUT_BUFFER_SIZE);
++ ret = hid_hw_output_report(ccp->hdev, ccp->cmd_buffer, OUT_BUFFER_SIZE);
+ if (ret < 0)
+ return ret;
+
+@@ -492,7 +493,11 @@ static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id)
+ if (!ccp)
+ return -ENOMEM;
+
+- ccp->buffer = devm_kmalloc(&hdev->dev, OUT_BUFFER_SIZE, GFP_KERNEL);
++ ccp->cmd_buffer = devm_kmalloc(&hdev->dev, OUT_BUFFER_SIZE, GFP_KERNEL);
++ if (!ccp->cmd_buffer)
++ return -ENOMEM;
++
++ ccp->buffer = devm_kmalloc(&hdev->dev, IN_BUFFER_SIZE, GFP_KERNEL);
+ if (!ccp->buffer)
+ return -ENOMEM;
+
+--
+2.43.0
+
--- /dev/null
+From 5aecb0dc016093a3d43e11812deaa32cdeb9cfdf Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sat, 4 May 2024 11:25:02 +0200
+Subject: hwmon: (corsair-cpro) Use complete_all() instead of complete() in
+ ccp_raw_event()
+
+From: Aleksa Savic <savicaleksa83@gmail.com>
+
+[ Upstream commit 3a034a7b0715eb51124a5263890b1ed39978ed3a ]
+
+In ccp_raw_event(), the ccp->wait_input_report completion is
+completed once. Since we're waiting for exactly one report in
+send_usb_cmd(), use complete_all() instead of complete()
+to mark the completion as spent.
+
+Fixes: 40c3a4454225 ("hwmon: add Corsair Commander Pro driver")
+Signed-off-by: Aleksa Savic <savicaleksa83@gmail.com>
+Acked-by: Marius Zachmann <mail@mariuszachmann.de>
+Link: https://lore.kernel.org/r/20240504092504.24158-3-savicaleksa83@gmail.com
+Signed-off-by: Guenter Roeck <linux@roeck-us.net>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/hwmon/corsair-cpro.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c
+index 34136d1b04764..e65e3825af974 100644
+--- a/drivers/hwmon/corsair-cpro.c
++++ b/drivers/hwmon/corsair-cpro.c
+@@ -140,7 +140,7 @@ static int ccp_raw_event(struct hid_device *hdev, struct hid_report *report, u8
+ return 0;
+
+ memcpy(ccp->buffer, data, min(IN_BUFFER_SIZE, size));
+- complete(&ccp->wait_input_report);
++ complete_all(&ccp->wait_input_report);
+
+ return 0;
+ }
+--
+2.43.0
+
--- /dev/null
+From ec7ec84ba83132644f6e0419c94fd5e9e196a399 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 28 Feb 2024 13:54:26 +0000
+Subject: ipv6: annotate data-races around cnf.disable_ipv6
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit d289ab65b89c1d4d88417cb6c03e923f21f95fae ]
+
+disable_ipv6 is read locklessly, add appropriate READ_ONCE()
+and WRITE_ONCE() annotations.
+
+v2: do not preload net before rtnl_trylock() in
+ addrconf_disable_ipv6() (Jiri)
+
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Reviewed-by: Jiri Pirko <jiri@nvidia.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Stable-dep-of: 4db783d68b9b ("ipv6: prevent NULL dereference in ip6_output()")
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/ipv6/addrconf.c | 9 +++++----
+ net/ipv6/ip6_input.c | 4 ++--
+ net/ipv6/ip6_output.c | 2 +-
+ 3 files changed, 8 insertions(+), 7 deletions(-)
+
+diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
+index 01f4502916a12..9dfbda164e8c1 100644
+--- a/net/ipv6/addrconf.c
++++ b/net/ipv6/addrconf.c
+@@ -4160,7 +4160,7 @@ static void addrconf_dad_work(struct work_struct *w)
+ if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) &&
+ ipv6_addr_equal(&ifp->addr, &addr)) {
+ /* DAD failed for link-local based on MAC */
+- idev->cnf.disable_ipv6 = 1;
++ WRITE_ONCE(idev->cnf.disable_ipv6, 1);
+
+ pr_info("%s: IPv6 being disabled!\n",
+ ifp->idev->dev->name);
+@@ -6321,7 +6321,8 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
+ idev = __in6_dev_get(dev);
+ if (idev) {
+ int changed = (!idev->cnf.disable_ipv6) ^ (!newf);
+- idev->cnf.disable_ipv6 = newf;
++
++ WRITE_ONCE(idev->cnf.disable_ipv6, newf);
+ if (changed)
+ dev_disable_change(idev);
+ }
+@@ -6338,7 +6339,7 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
+
+ net = (struct net *)table->extra2;
+ old = *p;
+- *p = newf;
++ WRITE_ONCE(*p, newf);
+
+ if (p == &net->ipv6.devconf_dflt->disable_ipv6) {
+ rtnl_unlock();
+@@ -6346,7 +6347,7 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
+ }
+
+ if (p == &net->ipv6.devconf_all->disable_ipv6) {
+- net->ipv6.devconf_dflt->disable_ipv6 = newf;
++ WRITE_ONCE(net->ipv6.devconf_dflt->disable_ipv6, newf);
+ addrconf_disable_change(net, newf);
+ } else if ((!newf) ^ (!old))
+ dev_disable_change((struct inet6_dev *)table->extra1);
+diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
+index b8378814532ce..1ba97933c74fb 100644
+--- a/net/ipv6/ip6_input.c
++++ b/net/ipv6/ip6_input.c
+@@ -168,9 +168,9 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
+
+ SKB_DR_SET(reason, NOT_SPECIFIED);
+ if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
+- !idev || unlikely(idev->cnf.disable_ipv6)) {
++ !idev || unlikely(READ_ONCE(idev->cnf.disable_ipv6))) {
+ __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
+- if (idev && unlikely(idev->cnf.disable_ipv6))
++ if (idev && unlikely(READ_ONCE(idev->cnf.disable_ipv6)))
+ SKB_DR_SET(reason, IPV6DISABLED);
+ goto drop;
+ }
+diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
+index fba789cbd215c..b6cc557abb942 100644
+--- a/net/ipv6/ip6_output.c
++++ b/net/ipv6/ip6_output.c
+@@ -227,7 +227,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+ skb->protocol = htons(ETH_P_IPV6);
+ skb->dev = dev;
+
+- if (unlikely(idev->cnf.disable_ipv6)) {
++ if (unlikely(READ_ONCE(idev->cnf.disable_ipv6))) {
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+ kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED);
+ return 0;
+--
+2.43.0
+
--- /dev/null
+From 07170beb5924f2cf06a64ff3eb22843b66582256 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 16:31:45 +0000
+Subject: ipv6: fib6_rules: avoid possible NULL dereference in
+ fib6_rule_action()
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit d101291b2681e5ab938554e3e323f7a7ee33e3aa ]
+
+syzbot is able to trigger the following crash [1],
+caused by unsafe ip6_dst_idev() use.
+
+Indeed ip6_dst_idev() can return NULL, and must always be checked.
+
+[1]
+
+Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN PTI
+KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
+CPU: 0 PID: 31648 Comm: syz-executor.0 Not tainted 6.9.0-rc4-next-20240417-syzkaller #0
+Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024
+ RIP: 0010:__fib6_rule_action net/ipv6/fib6_rules.c:237 [inline]
+ RIP: 0010:fib6_rule_action+0x241/0x7b0 net/ipv6/fib6_rules.c:267
+Code: 02 00 00 49 8d 9f d8 00 00 00 48 89 d8 48 c1 e8 03 42 80 3c 20 00 74 08 48 89 df e8 f9 32 bf f7 48 8b 1b 48 89 d8 48 c1 e8 03 <42> 80 3c 20 00 74 08 48 89 df e8 e0 32 bf f7 4c 8b 03 48 89 ef 4c
+RSP: 0018:ffffc9000fc1f2f0 EFLAGS: 00010246
+RAX: 0000000000000000 RBX: 0000000000000000 RCX: 1a772f98c8186700
+RDX: 0000000000000003 RSI: ffffffff8bcac4e0 RDI: ffffffff8c1f9760
+RBP: ffff8880673fb980 R08: ffffffff8fac15ef R09: 1ffffffff1f582bd
+R10: dffffc0000000000 R11: fffffbfff1f582be R12: dffffc0000000000
+R13: 0000000000000080 R14: ffff888076509000 R15: ffff88807a029a00
+FS: 00007f55e82ca6c0(0000) GS:ffff8880b9400000(0000) knlGS:0000000000000000
+CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+CR2: 0000001b31d23000 CR3: 0000000022b66000 CR4: 00000000003506f0
+DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
+DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
+Call Trace:
+ <TASK>
+ fib_rules_lookup+0x62c/0xdb0 net/core/fib_rules.c:317
+ fib6_rule_lookup+0x1fd/0x790 net/ipv6/fib6_rules.c:108
+ ip6_route_output_flags_noref net/ipv6/route.c:2637 [inline]
+ ip6_route_output_flags+0x38e/0x610 net/ipv6/route.c:2649
+ ip6_route_output include/net/ip6_route.h:93 [inline]
+ ip6_dst_lookup_tail+0x189/0x11a0 net/ipv6/ip6_output.c:1120
+ ip6_dst_lookup_flow+0xb9/0x180 net/ipv6/ip6_output.c:1250
+ sctp_v6_get_dst+0x792/0x1e20 net/sctp/ipv6.c:326
+ sctp_transport_route+0x12c/0x2e0 net/sctp/transport.c:455
+ sctp_assoc_add_peer+0x614/0x15c0 net/sctp/associola.c:662
+ sctp_connect_new_asoc+0x31d/0x6c0 net/sctp/socket.c:1099
+ __sctp_connect+0x66d/0xe30 net/sctp/socket.c:1197
+ sctp_connect net/sctp/socket.c:4819 [inline]
+ sctp_inet_connect+0x149/0x1f0 net/sctp/socket.c:4834
+ __sys_connect_file net/socket.c:2048 [inline]
+ __sys_connect+0x2df/0x310 net/socket.c:2065
+ __do_sys_connect net/socket.c:2075 [inline]
+ __se_sys_connect net/socket.c:2072 [inline]
+ __x64_sys_connect+0x7a/0x90 net/socket.c:2072
+ do_syscall_x64 arch/x86/entry/common.c:52 [inline]
+ do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83
+ entry_SYSCALL_64_after_hwframe+0x77/0x7f
+
+Fixes: 5e5f3f0f8013 ("[IPV6] ADDRCONF: Convert ipv6_get_saddr() to ipv6_dev_get_saddr().")
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Reviewed-by: Simon Horman <horms@kernel.org>
+Reviewed-by: David Ahern <dsahern@kernel.org>
+Link: https://lore.kernel.org/r/20240507163145.835254-1-edumazet@google.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/ipv6/fib6_rules.c | 6 +++++-
+ 1 file changed, 5 insertions(+), 1 deletion(-)
+
+diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
+index be52b18e08a6b..6eeab21512ba9 100644
+--- a/net/ipv6/fib6_rules.c
++++ b/net/ipv6/fib6_rules.c
+@@ -233,8 +233,12 @@ static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
+ rt = pol_lookup_func(lookup,
+ net, table, flp6, arg->lookup_data, flags);
+ if (rt != net->ipv6.ip6_null_entry) {
++ struct inet6_dev *idev = ip6_dst_idev(&rt->dst);
++
++ if (!idev)
++ goto again;
+ err = fib6_rule_saddr(net, rule, flags, flp6,
+- ip6_dst_idev(&rt->dst)->dev);
++ idev->dev);
+
+ if (err == -EAGAIN)
+ goto again;
+--
+2.43.0
+
--- /dev/null
+From b803daae2bc4a6b7207c65307eb347dd2c33b7a6 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 6 May 2024 23:11:29 +0900
+Subject: ipv6: Fix potential uninit-value access in __ip6_make_skb()
+
+From: Shigeru Yoshida <syoshida@redhat.com>
+
+[ Upstream commit 4e13d3a9c25b7080f8a619f961e943fe08c2672c ]
+
+As it was done in commit fc1092f51567 ("ipv4: Fix uninit-value access in
+__ip_make_skb()") for IPv4, check FLOWI_FLAG_KNOWN_NH on fl6->flowi6_flags
+instead of testing HDRINCL on the socket to avoid a race condition which
+causes uninit-value access.
+
+Fixes: ea30388baebc ("ipv6: Fix an uninit variable access bug in __ip6_make_skb()")
+Signed-off-by: Shigeru Yoshida <syoshida@redhat.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/ipv6/ip6_output.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
+index 53fe1375b147c..fba789cbd215c 100644
+--- a/net/ipv6/ip6_output.c
++++ b/net/ipv6/ip6_output.c
+@@ -2003,7 +2003,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
+ u8 icmp6_type;
+
+ if (sk->sk_socket->type == SOCK_RAW &&
+- !inet_test_bit(HDRINCL, sk))
++ !(fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH))
+ icmp6_type = fl6->fl6_icmp_type;
+ else
+ icmp6_type = icmp6_hdr(skb)->icmp6_type;
+--
+2.43.0
+
--- /dev/null
+From 0e07369f6ae4b05196d851c78566fb6afc89e7d6 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 16:18:42 +0000
+Subject: ipv6: prevent NULL dereference in ip6_output()
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit 4db783d68b9b39a411a96096c10828ff5dfada7a ]
+
+According to syzbot, there is a chance that ip6_dst_idev()
+returns NULL in ip6_output(). Most places in IPv6 stack
+deal with a NULL idev just fine, but not here.
+
+syzbot reported:
+
+general protection fault, probably for non-canonical address 0xdffffc00000000bc: 0000 [#1] PREEMPT SMP KASAN PTI
+KASAN: null-ptr-deref in range [0x00000000000005e0-0x00000000000005e7]
+CPU: 0 PID: 9775 Comm: syz-executor.4 Not tainted 6.9.0-rc5-syzkaller-00157-g6a30653b604a #0
+Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024
+ RIP: 0010:ip6_output+0x231/0x3f0 net/ipv6/ip6_output.c:237
+Code: 3c 1e 00 49 89 df 74 08 4c 89 ef e8 19 58 db f7 48 8b 44 24 20 49 89 45 00 49 89 c5 48 8d 9d e0 05 00 00 48 89 d8 48 c1 e8 03 <42> 0f b6 04 38 84 c0 4c 8b 74 24 28 0f 85 61 01 00 00 8b 1b 31 ff
+RSP: 0018:ffffc9000927f0d8 EFLAGS: 00010202
+RAX: 00000000000000bc RBX: 00000000000005e0 RCX: 0000000000040000
+RDX: ffffc900131f9000 RSI: 0000000000004f47 RDI: 0000000000004f48
+RBP: 0000000000000000 R08: ffffffff8a1f0b9a R09: 1ffffffff1f51fad
+R10: dffffc0000000000 R11: fffffbfff1f51fae R12: ffff8880293ec8c0
+R13: ffff88805d7fc000 R14: 1ffff1100527d91a R15: dffffc0000000000
+FS: 00007f135c6856c0(0000) GS:ffff8880b9400000(0000) knlGS:0000000000000000
+CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+CR2: 0000000020000080 CR3: 0000000064096000 CR4: 00000000003506f0
+DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
+DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
+Call Trace:
+ <TASK>
+ NF_HOOK include/linux/netfilter.h:314 [inline]
+ ip6_xmit+0xefe/0x17f0 net/ipv6/ip6_output.c:358
+ sctp_v6_xmit+0x9f2/0x13f0 net/sctp/ipv6.c:248
+ sctp_packet_transmit+0x26ad/0x2ca0 net/sctp/output.c:653
+ sctp_packet_singleton+0x22c/0x320 net/sctp/outqueue.c:783
+ sctp_outq_flush_ctrl net/sctp/outqueue.c:914 [inline]
+ sctp_outq_flush+0x6d5/0x3e20 net/sctp/outqueue.c:1212
+ sctp_side_effects net/sctp/sm_sideeffect.c:1198 [inline]
+ sctp_do_sm+0x59cc/0x60c0 net/sctp/sm_sideeffect.c:1169
+ sctp_primitive_ASSOCIATE+0x95/0xc0 net/sctp/primitive.c:73
+ __sctp_connect+0x9cd/0xe30 net/sctp/socket.c:1234
+ sctp_connect net/sctp/socket.c:4819 [inline]
+ sctp_inet_connect+0x149/0x1f0 net/sctp/socket.c:4834
+ __sys_connect_file net/socket.c:2048 [inline]
+ __sys_connect+0x2df/0x310 net/socket.c:2065
+ __do_sys_connect net/socket.c:2075 [inline]
+ __se_sys_connect net/socket.c:2072 [inline]
+ __x64_sys_connect+0x7a/0x90 net/socket.c:2072
+ do_syscall_x64 arch/x86/entry/common.c:52 [inline]
+ do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83
+ entry_SYSCALL_64_after_hwframe+0x77/0x7f
+
+Fixes: 778d80be5269 ("ipv6: Add disable_ipv6 sysctl to disable IPv6 operaion on specific interface.")
+Reported-by: syzbot <syzkaller@googlegroups.com>
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
+Link: https://lore.kernel.org/r/20240507161842.773961-1-edumazet@google.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/ipv6/ip6_output.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
+index b6cc557abb942..f97cb368e5a81 100644
+--- a/net/ipv6/ip6_output.c
++++ b/net/ipv6/ip6_output.c
+@@ -227,7 +227,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+ skb->protocol = htons(ETH_P_IPV6);
+ skb->dev = dev;
+
+- if (unlikely(READ_ONCE(idev->cnf.disable_ipv6))) {
++ if (unlikely(!idev || READ_ONCE(idev->cnf.disable_ipv6))) {
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+ kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED);
+ return 0;
+--
+2.43.0
+
--- /dev/null
+From 5cf825eac226ee669c6357c1c349d2545aba178e Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sun, 5 May 2024 20:42:38 +0200
+Subject: net: bridge: fix corrupted ethernet header on multicast-to-unicast
+
+From: Felix Fietkau <nbd@nbd.name>
+
+[ Upstream commit 86b29d830ad69eecff25b22dc96c14c6573718e6 ]
+
+The change from skb_copy to pskb_copy unfortunately changed the data
+copying to omit the ethernet header, since it was pulled before reaching
+this point. Fix this by calling __skb_push/pull around pskb_copy.
+
+Fixes: 59c878cbcdd8 ("net: bridge: fix multicast-to-unicast with fraglist GSO")
+Signed-off-by: Felix Fietkau <nbd@nbd.name>
+Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/bridge/br_forward.c | 9 +++++++--
+ 1 file changed, 7 insertions(+), 2 deletions(-)
+
+diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
+index d7c35f55bd69f..d97064d460dc7 100644
+--- a/net/bridge/br_forward.c
++++ b/net/bridge/br_forward.c
+@@ -258,6 +258,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb,
+ {
+ struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
+ const unsigned char *src = eth_hdr(skb)->h_source;
++ struct sk_buff *nskb;
+
+ if (!should_deliver(p, skb))
+ return;
+@@ -266,12 +267,16 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb,
+ if (skb->dev == p->dev && ether_addr_equal(src, addr))
+ return;
+
+- skb = pskb_copy(skb, GFP_ATOMIC);
+- if (!skb) {
++ __skb_push(skb, ETH_HLEN);
++ nskb = pskb_copy(skb, GFP_ATOMIC);
++ __skb_pull(skb, ETH_HLEN);
++ if (!nskb) {
+ DEV_STATS_INC(dev, tx_dropped);
+ return;
+ }
+
++ skb = nskb;
++ __skb_pull(skb, ETH_HLEN);
+ if (!is_broadcast_ether_addr(addr))
+ memcpy(eth_hdr(skb)->h_dest, addr, ETH_ALEN);
+
+--
+2.43.0
+
--- /dev/null
+From 481f521086f6ef8097f922ad827e148436c48d5a Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 8 May 2024 09:29:43 +0200
+Subject: net: dsa: mv88e6xxx: add phylink_get_caps for the mv88e6320/21 family
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Steffen Bätz <steffen@innosonix.de>
+
+[ Upstream commit f39bf3cf08a49e7d20c44bc8bc8e390fea69959a ]
+
+As of commit de5c9bf40c45 ("net: phylink: require supported_interfaces to
+be filled")
+Marvell 88e6320/21 switches fail to be probed:
+
+...
+mv88e6085 30be0000.ethernet-1:00: phylink: error: empty supported_interfaces
+error creating PHYLINK: -22
+...
+
+The problem stems from the use of mv88e6185_phylink_get_caps() to get
+the device capabilities.
+Since there are serdes only ports 0/1 included, create a new dedicated
+phylink_get_caps for the 6320 and 6321 to properly support their
+set of capabilities.
+
+Fixes: de5c9bf40c45 ("net: phylink: require supported_interfaces to be filled")
+Signed-off-by: Steffen Bätz <steffen@innosonix.de>
+Reviewed-by: Andrew Lunn <andrew@lunn.ch>
+Reviewed-by: Fabio Estevam <festevam@gmail.com>
+Link: https://lore.kernel.org/r/20240508072944.54880-2-steffen@innosonix.de
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/net/dsa/mv88e6xxx/chip.c | 16 ++++++++++++++--
+ 1 file changed, 14 insertions(+), 2 deletions(-)
+
+diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
+index db1d9df7d47fe..e5bac87941f61 100644
+--- a/drivers/net/dsa/mv88e6xxx/chip.c
++++ b/drivers/net/dsa/mv88e6xxx/chip.c
+@@ -697,6 +697,18 @@ static void mv88e6352_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
+ }
+ }
+
++static void mv88e632x_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
++ struct phylink_config *config)
++{
++ unsigned long *supported = config->supported_interfaces;
++
++ /* Translate the default cmode */
++ mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported);
++
++ config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 |
++ MAC_1000FD;
++}
++
+ static void mv88e6341_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_config *config)
+ {
+@@ -4976,7 +4988,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
+ .gpio_ops = &mv88e6352_gpio_ops,
+ .avb_ops = &mv88e6352_avb_ops,
+ .ptp_ops = &mv88e6352_ptp_ops,
+- .phylink_get_caps = mv88e6185_phylink_get_caps,
++ .phylink_get_caps = mv88e632x_phylink_get_caps,
+ };
+
+ static const struct mv88e6xxx_ops mv88e6321_ops = {
+@@ -5022,7 +5034,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
+ .gpio_ops = &mv88e6352_gpio_ops,
+ .avb_ops = &mv88e6352_avb_ops,
+ .ptp_ops = &mv88e6352_ptp_ops,
+- .phylink_get_caps = mv88e6185_phylink_get_caps,
++ .phylink_get_caps = mv88e632x_phylink_get_caps,
+ };
+
+ static const struct mv88e6xxx_ops mv88e6341_ops = {
+--
+2.43.0
+
--- /dev/null
+From 4af3b5fbf0066639cff49c06f333a173cce35b9e Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 21:42:20 +0800
+Subject: net: hns3: change type of numa_node_mask as nodemask_t
+
+From: Peiyang Wang <wangpeiyang1@huawei.com>
+
+[ Upstream commit 6639a7b953212ac51aa4baa7d7fb855bf736cf56 ]
+
+It provides nodemask_t to describe the numa node mask in kernel. To
+improve transportability, change the type of numa_node_mask as nodemask_t.
+
+Fixes: 38caee9d3ee8 ("net: hns3: Add support of the HNAE3 framework")
+Signed-off-by: Peiyang Wang <wangpeiyang1@huawei.com>
+Signed-off-by: Jijie Shao <shaojijie@huawei.com>
+Reviewed-by: Simon Horman <horms@kernel.org>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/net/ethernet/hisilicon/hns3/hnae3.h | 2 +-
+ drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 6 ++++--
+ drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 2 +-
+ drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 7 ++++---
+ drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h | 2 +-
+ 5 files changed, 11 insertions(+), 8 deletions(-)
+
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+index aaf1f42624a79..57787c380fa07 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
++++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+@@ -890,7 +890,7 @@ struct hnae3_handle {
+ struct hnae3_roce_private_info rinfo;
+ };
+
+- u32 numa_node_mask; /* for multi-chip support */
++ nodemask_t numa_node_mask; /* for multi-chip support */
+
+ enum hnae3_port_base_vlan_state port_base_vlan_state;
+
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+index 4398de42c9157..b02b96bd93b7a 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+@@ -1758,7 +1758,8 @@ static int hclge_vport_setup(struct hclge_vport *vport, u16 num_tqps)
+
+ nic->pdev = hdev->pdev;
+ nic->ae_algo = &ae_algo;
+- nic->numa_node_mask = hdev->numa_node_mask;
++ bitmap_copy(nic->numa_node_mask.bits, hdev->numa_node_mask.bits,
++ MAX_NUMNODES);
+ nic->kinfo.io_base = hdev->hw.hw.io_base;
+
+ ret = hclge_knic_setup(vport, num_tqps,
+@@ -2450,7 +2451,8 @@ static int hclge_init_roce_base_info(struct hclge_vport *vport)
+
+ roce->pdev = nic->pdev;
+ roce->ae_algo = nic->ae_algo;
+- roce->numa_node_mask = nic->numa_node_mask;
++ bitmap_copy(roce->numa_node_mask.bits, nic->numa_node_mask.bits,
++ MAX_NUMNODES);
+
+ return 0;
+ }
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+index 6a6b41ef08baf..76a5edfe7d2e5 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+@@ -878,7 +878,7 @@ struct hclge_dev {
+
+ u16 fdir_pf_filter_count; /* Num of guaranteed filters for this PF */
+ u16 num_alloc_vport; /* Num vports this driver supports */
+- u32 numa_node_mask;
++ nodemask_t numa_node_mask;
+ u16 rx_buf_len;
+ u16 num_tx_desc; /* desc num of per tx queue */
+ u16 num_rx_desc; /* desc num of per rx queue */
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+index 0aa9beefd1c7e..b57111252d071 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+@@ -412,7 +412,8 @@ static int hclgevf_set_handle_info(struct hclgevf_dev *hdev)
+
+ nic->ae_algo = &ae_algovf;
+ nic->pdev = hdev->pdev;
+- nic->numa_node_mask = hdev->numa_node_mask;
++ bitmap_copy(nic->numa_node_mask.bits, hdev->numa_node_mask.bits,
++ MAX_NUMNODES);
+ nic->flags |= HNAE3_SUPPORT_VF;
+ nic->kinfo.io_base = hdev->hw.hw.io_base;
+
+@@ -2082,8 +2083,8 @@ static int hclgevf_init_roce_base_info(struct hclgevf_dev *hdev)
+
+ roce->pdev = nic->pdev;
+ roce->ae_algo = nic->ae_algo;
+- roce->numa_node_mask = nic->numa_node_mask;
+-
++ bitmap_copy(roce->numa_node_mask.bits, nic->numa_node_mask.bits,
++ MAX_NUMNODES);
+ return 0;
+ }
+
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+index a73f2bf3a56a6..cccef32284616 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+@@ -236,7 +236,7 @@ struct hclgevf_dev {
+ u16 rss_size_max; /* HW defined max RSS task queue */
+
+ u16 num_alloc_vport; /* num vports this driver supports */
+- u32 numa_node_mask;
++ nodemask_t numa_node_mask;
+ u16 rx_buf_len;
+ u16 num_tx_desc; /* desc num of per tx queue */
+ u16 num_rx_desc; /* desc num of per rx queue */
+--
+2.43.0
+
--- /dev/null
+From dade656315a1b7c9b285af55917198aa0a08c5ec Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 21:42:19 +0800
+Subject: net: hns3: direct return when receive a unknown mailbox message
+
+From: Jian Shen <shenjian15@huawei.com>
+
+[ Upstream commit 669554c512d2107e2f21616f38e050d40655101f ]
+
+Currently, the driver didn't return when receive a unknown
+mailbox message, and continue checking whether need to
+generate a response. It's unnecessary and may be incorrect.
+
+Fixes: bb5790b71bad ("net: hns3: refactor mailbox response scheme between PF and VF")
+Signed-off-by: Jian Shen <shenjian15@huawei.com>
+Signed-off-by: Jijie Shao <shaojijie@huawei.com>
+Reviewed-by: Simon Horman <horms@kernel.org>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 7 ++++---
+ 1 file changed, 4 insertions(+), 3 deletions(-)
+
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+index 04ff9bf121853..877feee53804f 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+@@ -1077,12 +1077,13 @@ static void hclge_mbx_request_handling(struct hclge_mbx_ops_param *param)
+
+ hdev = param->vport->back;
+ cmd_func = hclge_mbx_ops_list[param->req->msg.code];
+- if (cmd_func)
+- ret = cmd_func(param);
+- else
++ if (!cmd_func) {
+ dev_err(&hdev->pdev->dev,
+ "un-supported mailbox message, code = %u\n",
+ param->req->msg.code);
++ return;
++ }
++ ret = cmd_func(param);
+
+ /* PF driver should not reply IMP */
+ if (hnae3_get_bit(param->req->mbx_need_resp, HCLGE_MBX_NEED_RESP_B) &&
+--
+2.43.0
+
--- /dev/null
+From d4f1c79de77804804a1a3f43ab52f056d8b7f04b Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 21:42:24 +0800
+Subject: net: hns3: fix kernel crash when devlink reload during initialization
+
+From: Yonglong Liu <liuyonglong@huawei.com>
+
+[ Upstream commit 35d92abfbad88cf947c010baf34b075e40566095 ]
+
+The devlink reload process will access the hardware resources,
+but the register operation is done before the hardware is initialized.
+So, processing the devlink reload during initialization may lead to kernel
+crash.
+
+This patch fixes this by registering the devlink after
+hardware initialization.
+
+Fixes: cd6242991d2e ("net: hns3: add support for registering devlink for VF")
+Fixes: 93305b77ffcb ("net: hns3: fix kernel crash when devlink reload during pf initialization")
+Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
+Signed-off-by: Jijie Shao <shaojijie@huawei.com>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 17 +++++------------
+ .../hisilicon/hns3/hns3vf/hclgevf_main.c | 10 ++++------
+ 2 files changed, 9 insertions(+), 18 deletions(-)
+
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+index 3b74cce46ac65..14713454e0d82 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+@@ -11619,16 +11619,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
+ if (ret)
+ goto out;
+
+- ret = hclge_devlink_init(hdev);
+- if (ret)
+- goto err_pci_uninit;
+-
+- devl_lock(hdev->devlink);
+-
+ /* Firmware command queue initialize */
+ ret = hclge_comm_cmd_queue_init(hdev->pdev, &hdev->hw.hw);
+ if (ret)
+- goto err_devlink_uninit;
++ goto err_pci_uninit;
+
+ /* Firmware command initialize */
+ ret = hclge_comm_cmd_init(hdev->ae_dev, &hdev->hw.hw, &hdev->fw_version,
+@@ -11796,6 +11790,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
+ dev_warn(&pdev->dev,
+ "failed to wake on lan init, ret = %d\n", ret);
+
++ ret = hclge_devlink_init(hdev);
++ if (ret)
++ goto err_ptp_uninit;
++
+ hclge_state_init(hdev);
+ hdev->last_reset_time = jiffies;
+
+@@ -11803,8 +11801,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
+ HCLGE_DRIVER_NAME);
+
+ hclge_task_schedule(hdev, round_jiffies_relative(HZ));
+-
+- devl_unlock(hdev->devlink);
+ return 0;
+
+ err_ptp_uninit:
+@@ -11818,9 +11814,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
+ pci_free_irq_vectors(pdev);
+ err_cmd_uninit:
+ hclge_comm_cmd_uninit(hdev->ae_dev, &hdev->hw.hw);
+-err_devlink_uninit:
+- devl_unlock(hdev->devlink);
+- hclge_devlink_uninit(hdev);
+ err_pci_uninit:
+ pcim_iounmap(pdev, hdev->hw.hw.io_base);
+ pci_release_regions(pdev);
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+index 08db8e84be4ed..43ee20eb03d1f 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+@@ -2845,10 +2845,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
+ if (ret)
+ return ret;
+
+- ret = hclgevf_devlink_init(hdev);
+- if (ret)
+- goto err_devlink_init;
+-
+ ret = hclge_comm_cmd_queue_init(hdev->pdev, &hdev->hw.hw);
+ if (ret)
+ goto err_cmd_queue_init;
+@@ -2941,6 +2937,10 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
+
+ hclgevf_init_rxd_adv_layout(hdev);
+
++ ret = hclgevf_devlink_init(hdev);
++ if (ret)
++ goto err_config;
++
+ set_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state);
+
+ hdev->last_reset_time = jiffies;
+@@ -2960,8 +2960,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
+ err_cmd_init:
+ hclge_comm_cmd_uninit(hdev->ae_dev, &hdev->hw.hw);
+ err_cmd_queue_init:
+- hclgevf_devlink_uninit(hdev);
+-err_devlink_init:
+ hclgevf_pci_uninit(hdev);
+ clear_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state);
+ return ret;
+--
+2.43.0
+
--- /dev/null
+From e73fda585e29ee9b8d9b8478150817303669c882 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 21:42:23 +0800
+Subject: net: hns3: fix port vlan filter not disabled issue
+
+From: Yonglong Liu <liuyonglong@huawei.com>
+
+[ Upstream commit f5db7a3b65c84d723ca5e2bb6e83115180ab6336 ]
+
+According to hardware limitation, for device support modify
+VLAN filter state but not support bypass port VLAN filter,
+it should always disable the port VLAN filter. but the driver
+enables port VLAN filter when initializing, if there is no
+VLAN(except VLAN 0) id added, the driver will disable it
+in service task. In most time, it works fine. But there is
+a time window before the service task shceduled and net device
+being registered. So if user adds VLAN at this time, the driver
+will not update the VLAN filter state, and the port VLAN filter
+remains enabled.
+
+To fix the problem, if support modify VLAN filter state but not
+support bypass port VLAN filter, set the port vlan filter to "off".
+
+Fixes: 184cd221a863 ("net: hns3: disable port VLAN filter when support function level VLAN filter control")
+Fixes: 2ba306627f59 ("net: hns3: add support for modify VLAN filter state")
+Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
+Signed-off-by: Jijie Shao <shaojijie@huawei.com>
+Reviewed-by: Simon Horman <horms@kernel.org>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 7 ++++++-
+ 1 file changed, 6 insertions(+), 1 deletion(-)
+
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+index 9858124665aa6..3b74cce46ac65 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+@@ -9898,6 +9898,7 @@ static int hclge_set_vlan_protocol_type(struct hclge_dev *hdev)
+ static int hclge_init_vlan_filter(struct hclge_dev *hdev)
+ {
+ struct hclge_vport *vport;
++ bool enable = true;
+ int ret;
+ int i;
+
+@@ -9917,8 +9918,12 @@ static int hclge_init_vlan_filter(struct hclge_dev *hdev)
+ vport->cur_vlan_fltr_en = true;
+ }
+
++ if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, hdev->ae_dev->caps) &&
++ !test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, hdev->ae_dev->caps))
++ enable = false;
++
+ return hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
+- HCLGE_FILTER_FE_INGRESS, true, 0);
++ HCLGE_FILTER_FE_INGRESS, enable, 0);
+ }
+
+ static int hclge_init_vlan_type(struct hclge_dev *hdev)
+--
+2.43.0
+
--- /dev/null
+From 2d7bcc2a8f574dab5ead5b3ea79b402cfcaa43a4 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 21:42:21 +0800
+Subject: net: hns3: release PTP resources if pf initialization failed
+
+From: Peiyang Wang <wangpeiyang1@huawei.com>
+
+[ Upstream commit 950aa42399893a170d9b57eda0e4a3ff91fd8b70 ]
+
+During the PF initialization process, hclge_update_port_info may return an
+error code for some reason. At this point, the ptp initialization has been
+completed. To void memory leaks, the resources that are applied by ptp
+should be released. Therefore, when hclge_update_port_info returns an error
+code, hclge_ptp_uninit is called to release the corresponding resources.
+
+Fixes: eaf83ae59e18 ("net: hns3: add querying fec ability from firmware")
+Signed-off-by: Peiyang Wang <wangpeiyang1@huawei.com>
+Signed-off-by: Jijie Shao <shaojijie@huawei.com>
+Reviewed-by: Hariprasad Kelam <hkelam@marvell.com>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 +++-
+ 1 file changed, 3 insertions(+), 1 deletion(-)
+
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+index b02b96bd93b7a..7f2bb0e708896 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+@@ -11752,7 +11752,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
+
+ ret = hclge_update_port_info(hdev);
+ if (ret)
+- goto err_mdiobus_unreg;
++ goto err_ptp_uninit;
+
+ INIT_KFIFO(hdev->mac_tnl_log);
+
+@@ -11803,6 +11803,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
+ devl_unlock(hdev->devlink);
+ return 0;
+
++err_ptp_uninit:
++ hclge_ptp_uninit(hdev);
+ err_mdiobus_unreg:
+ if (hdev->hw.mac.phydev)
+ mdiobus_unregister(hdev->hw.mac.mdio_bus);
+--
+2.43.0
+
--- /dev/null
+From 4cb6a010521196e2f0a45434ff81916daa1f2fac Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 21:42:22 +0800
+Subject: net: hns3: use appropriate barrier function after setting a bit value
+
+From: Peiyang Wang <wangpeiyang1@huawei.com>
+
+[ Upstream commit 094c281228529d333458208fd02fcac3b139d93b ]
+
+There is a memory barrier in followed case. When set the port down,
+hclgevf_set_timmer will set DOWN in state. Meanwhile, the service task has
+different behaviour based on whether the state is DOWN. Thus, to make sure
+service task see DOWN, use smp_mb__after_atomic after calling set_bit().
+
+ CPU0 CPU1
+========================== ===================================
+hclgevf_set_timer_task() hclgevf_periodic_service_task()
+ set_bit(DOWN,state) test_bit(DOWN,state)
+
+pf also has this issue.
+
+Fixes: ff200099d271 ("net: hns3: remove unnecessary work in hclgevf_main")
+Fixes: 1c6dfe6fc6f7 ("net: hns3: remove mailbox and reset work in hclge_main")
+Signed-off-by: Peiyang Wang <wangpeiyang1@huawei.com>
+Signed-off-by: Jijie Shao <shaojijie@huawei.com>
+Reviewed-by: Simon Horman <horms@kernel.org>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 +--
+ drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 3 +--
+ 2 files changed, 2 insertions(+), 4 deletions(-)
+
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+index 7f2bb0e708896..9858124665aa6 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+@@ -7945,8 +7945,7 @@ static void hclge_set_timer_task(struct hnae3_handle *handle, bool enable)
+ /* Set the DOWN flag here to disable link updating */
+ set_bit(HCLGE_STATE_DOWN, &hdev->state);
+
+- /* flush memory to make sure DOWN is seen by service task */
+- smp_mb__before_atomic();
++ smp_mb__after_atomic(); /* flush memory to make sure DOWN is seen by service task */
+ hclge_flush_link_update(hdev);
+ }
+ }
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+index b57111252d071..08db8e84be4ed 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+@@ -2181,8 +2181,7 @@ static void hclgevf_set_timer_task(struct hnae3_handle *handle, bool enable)
+ } else {
+ set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
+
+- /* flush memory to make sure DOWN is seen by service task */
+- smp_mb__before_atomic();
++ smp_mb__after_atomic(); /* flush memory to make sure DOWN is seen by service task */
+ hclgevf_flush_link_update(hdev);
+ }
+ }
+--
+2.43.0
+
--- /dev/null
+From 7b6941f7507a8e8f8f5fcbd64d72441e403a6ac9 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 21:42:18 +0800
+Subject: net: hns3: using user configure after hardware reset
+
+From: Peiyang Wang <wangpeiyang1@huawei.com>
+
+[ Upstream commit 05eb60e9648cca0beeebdbcd263b599fb58aee48 ]
+
+When a reset occurring, it's supposed to recover user's configuration.
+Currently, the port info(speed, duplex and autoneg) is stored in hclge_mac
+and will be scheduled updated. Consider the case that reset was happened
+consecutively. During the first reset, the port info is configured with
+a temporary value cause the PHY is reset and looking for best link config.
+Second reset start and use pervious configuration which is not the user's.
+The specific process is as follows:
+
++------+ +----+ +----+
+| USER | | PF | | HW |
++---+--+ +-+--+ +-+--+
+ | ethtool --reset | |
+ +------------------->| reset command |
+ | ethtool --reset +-------------------->|
+ +------------------->| +---+
+ | +---+ | |
+ | | |reset currently | | HW RESET
+ | | |and wait to do | |
+ | |<--+ | |
+ | | send pervious cfg |<--+
+ | | (1000M FULL AN_ON) |
+ | +-------------------->|
+ | | read cfg(time task) |
+ | | (10M HALF AN_OFF) +---+
+ | |<--------------------+ | cfg take effect
+ | | reset command |<--+
+ | +-------------------->|
+ | | +---+
+ | | send pervious cfg | | HW RESET
+ | | (10M HALF AN_OFF) |<--+
+ | +-------------------->|
+ | | read cfg(time task) |
+ | | (10M HALF AN_OFF) +---+
+ | |<--------------------+ | cfg take effect
+ | | | |
+ | | read cfg(time task) |<--+
+ | | (10M HALF AN_OFF) |
+ | |<--------------------+
+ | | |
+ v v v
+
+To avoid aboved situation, this patch introduced req_speed, req_duplex,
+req_autoneg to store user's configuration and it only be used after
+hardware reset and to recover user's configuration
+
+Fixes: f5f2b3e4dcc0 ("net: hns3: add support for imp-controlled PHYs")
+Signed-off-by: Peiyang Wang <wangpeiyang1@huawei.com>
+Signed-off-by: Jijie Shao <shaojijie@huawei.com>
+Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
+Reviewed-by: Simon Horman <horms@kernel.org>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 15 +++++++++------
+ .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 3 +++
+ 2 files changed, 12 insertions(+), 6 deletions(-)
+
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+index dfd0c5f4cb9f5..4398de42c9157 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+@@ -1526,6 +1526,9 @@ static int hclge_configure(struct hclge_dev *hdev)
+ cfg.default_speed, ret);
+ return ret;
+ }
++ hdev->hw.mac.req_speed = hdev->hw.mac.speed;
++ hdev->hw.mac.req_autoneg = AUTONEG_ENABLE;
++ hdev->hw.mac.req_duplex = DUPLEX_FULL;
+
+ hclge_parse_link_mode(hdev, cfg.speed_ability);
+
+@@ -3331,9 +3334,9 @@ hclge_set_phy_link_ksettings(struct hnae3_handle *handle,
+ return ret;
+ }
+
+- hdev->hw.mac.autoneg = cmd->base.autoneg;
+- hdev->hw.mac.speed = cmd->base.speed;
+- hdev->hw.mac.duplex = cmd->base.duplex;
++ hdev->hw.mac.req_autoneg = cmd->base.autoneg;
++ hdev->hw.mac.req_speed = cmd->base.speed;
++ hdev->hw.mac.req_duplex = cmd->base.duplex;
+ linkmode_copy(hdev->hw.mac.advertising, cmd->link_modes.advertising);
+
+ return 0;
+@@ -3366,9 +3369,9 @@ static int hclge_tp_port_init(struct hclge_dev *hdev)
+ if (!hnae3_dev_phy_imp_supported(hdev))
+ return 0;
+
+- cmd.base.autoneg = hdev->hw.mac.autoneg;
+- cmd.base.speed = hdev->hw.mac.speed;
+- cmd.base.duplex = hdev->hw.mac.duplex;
++ cmd.base.autoneg = hdev->hw.mac.req_autoneg;
++ cmd.base.speed = hdev->hw.mac.req_speed;
++ cmd.base.duplex = hdev->hw.mac.req_duplex;
+ linkmode_copy(cmd.link_modes.advertising, hdev->hw.mac.advertising);
+
+ return hclge_set_phy_link_ksettings(&hdev->vport->nic, &cmd);
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+index 7bc2049b723da..6a6b41ef08baf 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+@@ -263,11 +263,14 @@ struct hclge_mac {
+ u8 media_type; /* port media type, e.g. fibre/copper/backplane */
+ u8 mac_addr[ETH_ALEN];
+ u8 autoneg;
++ u8 req_autoneg;
+ u8 duplex;
++ u8 req_duplex;
+ u8 support_autoneg;
+ u8 speed_type; /* 0: sfp speed, 1: active speed */
+ u8 lane_num;
+ u32 speed;
++ u32 req_speed;
+ u32 max_speed;
+ u32 speed_ability; /* speed ability supported by current media */
+ u32 module_type; /* sub media type, e.g. kr/cr/sr/lr */
+--
+2.43.0
+
--- /dev/null
+From 240a4ce864cb45adfbac392ae45374b9a58d5d33 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 2 May 2024 20:32:59 +0200
+Subject: net: ks8851: Queue RX packets in IRQ handler instead of disabling BHs
+
+From: Marek Vasut <marex@denx.de>
+
+[ Upstream commit e0863634bf9f7cf36291ebb5bfa2d16632f79c49 ]
+
+Currently the driver uses local_bh_disable()/local_bh_enable() in its
+IRQ handler to avoid triggering net_rx_action() softirq on exit from
+netif_rx(). The net_rx_action() could trigger this driver .start_xmit
+callback, which is protected by the same lock as the IRQ handler, so
+calling the .start_xmit from netif_rx() from the IRQ handler critical
+section protected by the lock could lead to an attempt to claim the
+already claimed lock, and a hang.
+
+The local_bh_disable()/local_bh_enable() approach works only in case
+the IRQ handler is protected by a spinlock, but does not work if the
+IRQ handler is protected by mutex, i.e. this works for KS8851 with
+Parallel bus interface, but not for KS8851 with SPI bus interface.
+
+Remove the BH manipulation and instead of calling netif_rx() inside
+the IRQ handler code protected by the lock, queue all the received
+SKBs in the IRQ handler into a queue first, and once the IRQ handler
+exits the critical section protected by the lock, dequeue all the
+queued SKBs and push them all into netif_rx(). At this point, it is
+safe to trigger the net_rx_action() softirq, since the netif_rx()
+call is outside of the lock that protects the IRQ handler.
+
+Fixes: be0384bf599c ("net: ks8851: Handle softirqs at the end of IRQ thread to fix hang")
+Tested-by: Ronald Wahl <ronald.wahl@raritan.com> # KS8851 SPI
+Signed-off-by: Marek Vasut <marex@denx.de>
+Reviewed-by: Eric Dumazet <edumazet@google.com>
+Link: https://lore.kernel.org/r/20240502183436.117117-1-marex@denx.de
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/net/ethernet/micrel/ks8851_common.c | 16 ++++++++++------
+ 1 file changed, 10 insertions(+), 6 deletions(-)
+
+diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c
+index d4cdf3d4f5525..502518cdb4618 100644
+--- a/drivers/net/ethernet/micrel/ks8851_common.c
++++ b/drivers/net/ethernet/micrel/ks8851_common.c
+@@ -234,12 +234,13 @@ static void ks8851_dbg_dumpkkt(struct ks8851_net *ks, u8 *rxpkt)
+ /**
+ * ks8851_rx_pkts - receive packets from the host
+ * @ks: The device information.
++ * @rxq: Queue of packets received in this function.
+ *
+ * This is called from the IRQ work queue when the system detects that there
+ * are packets in the receive queue. Find out how many packets there are and
+ * read them from the FIFO.
+ */
+-static void ks8851_rx_pkts(struct ks8851_net *ks)
++static void ks8851_rx_pkts(struct ks8851_net *ks, struct sk_buff_head *rxq)
+ {
+ struct sk_buff *skb;
+ unsigned rxfc;
+@@ -299,7 +300,7 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
+ ks8851_dbg_dumpkkt(ks, rxpkt);
+
+ skb->protocol = eth_type_trans(skb, ks->netdev);
+- __netif_rx(skb);
++ __skb_queue_tail(rxq, skb);
+
+ ks->netdev->stats.rx_packets++;
+ ks->netdev->stats.rx_bytes += rxlen;
+@@ -326,11 +327,11 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
+ static irqreturn_t ks8851_irq(int irq, void *_ks)
+ {
+ struct ks8851_net *ks = _ks;
++ struct sk_buff_head rxq;
+ unsigned handled = 0;
+ unsigned long flags;
+ unsigned int status;
+-
+- local_bh_disable();
++ struct sk_buff *skb;
+
+ ks8851_lock(ks, &flags);
+
+@@ -384,7 +385,8 @@ static irqreturn_t ks8851_irq(int irq, void *_ks)
+ * from the device so do not bother masking just the RX
+ * from the device. */
+
+- ks8851_rx_pkts(ks);
++ __skb_queue_head_init(&rxq);
++ ks8851_rx_pkts(ks, &rxq);
+ }
+
+ /* if something stopped the rx process, probably due to wanting
+@@ -408,7 +410,9 @@ static irqreturn_t ks8851_irq(int irq, void *_ks)
+ if (status & IRQ_LCI)
+ mii_check_link(&ks->mii);
+
+- local_bh_enable();
++ if (status & IRQ_RXI)
++ while ((skb = __skb_dequeue(&rxq)))
++ netif_rx(skb);
+
+ return IRQ_HANDLED;
+ }
+--
+2.43.0
+
--- /dev/null
+From 932f4c9031631f3904a70c9da994c129e47bf838 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 20:53:31 +0800
+Subject: net/smc: fix neighbour and rtable leak in smc_ib_find_route()
+
+From: Wen Gu <guwen@linux.alibaba.com>
+
+[ Upstream commit 2ddc0dd7fec86ee53b8928a5cca5fbddd4fc7c06 ]
+
+In smc_ib_find_route(), the neighbour found by neigh_lookup() and rtable
+resolved by ip_route_output_flow() are not released or put before return.
+It may cause the refcount leak, so fix it.
+
+Link: https://lore.kernel.org/r/20240506015439.108739-1-guwen@linux.alibaba.com
+Fixes: e5c4744cfb59 ("net/smc: add SMC-Rv2 connection establishment")
+Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
+Link: https://lore.kernel.org/r/20240507125331.2808-1-guwen@linux.alibaba.com
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/smc/smc_ib.c | 19 ++++++++++++-------
+ 1 file changed, 12 insertions(+), 7 deletions(-)
+
+diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
+index 89981dbe46c94..598ac9ead64b7 100644
+--- a/net/smc/smc_ib.c
++++ b/net/smc/smc_ib.c
+@@ -209,13 +209,18 @@ int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr,
+ if (IS_ERR(rt))
+ goto out;
+ if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET)
+- goto out;
+- neigh = rt->dst.ops->neigh_lookup(&rt->dst, NULL, &fl4.daddr);
+- if (neigh) {
+- memcpy(nexthop_mac, neigh->ha, ETH_ALEN);
+- *uses_gateway = rt->rt_uses_gateway;
+- return 0;
+- }
++ goto out_rt;
++ neigh = dst_neigh_lookup(&rt->dst, &fl4.daddr);
++ if (!neigh)
++ goto out_rt;
++ memcpy(nexthop_mac, neigh->ha, ETH_ALEN);
++ *uses_gateway = rt->rt_uses_gateway;
++ neigh_release(neigh);
++ ip_rt_put(rt);
++ return 0;
++
++out_rt:
++ ip_rt_put(rt);
+ out:
+ return -ENOENT;
+ }
+--
+2.43.0
+
--- /dev/null
+From 8e764166b66f5e8f9dbb7d5189cf663defac1536 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 13 Feb 2024 06:32:39 +0000
+Subject: net-sysfs: convert dev->operstate reads to lockless ones
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit 004d138364fd10dd5ff8ceb54cfdc2d792a7b338 ]
+
+operstate_show() can omit dev_base_lock acquisition only
+to read dev->operstate.
+
+Annotate accesses to dev->operstate.
+
+Writers still acquire dev_base_lock for mutual exclusion.
+
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Stable-dep-of: 4893b8b3ef8d ("hsr: Simplify code for announcing HSR nodes timer setup")
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/bridge/br_netlink.c | 3 ++-
+ net/core/link_watch.c | 4 ++--
+ net/core/net-sysfs.c | 4 +---
+ net/core/rtnetlink.c | 4 ++--
+ net/hsr/hsr_device.c | 10 +++++-----
+ net/ipv6/addrconf.c | 2 +-
+ 6 files changed, 13 insertions(+), 14 deletions(-)
+
+diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
+index 65e9ed3851425..4488faf059a36 100644
+--- a/net/bridge/br_netlink.c
++++ b/net/bridge/br_netlink.c
+@@ -455,7 +455,8 @@ static int br_fill_ifinfo(struct sk_buff *skb,
+ u32 filter_mask, const struct net_device *dev,
+ bool getlink)
+ {
+- u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
++ u8 operstate = netif_running(dev) ? READ_ONCE(dev->operstate) :
++ IF_OPER_DOWN;
+ struct nlattr *af = NULL;
+ struct net_bridge *br;
+ struct ifinfomsg *hdr;
+diff --git a/net/core/link_watch.c b/net/core/link_watch.c
+index c469d1c4db5d7..cb43f5aebfbcc 100644
+--- a/net/core/link_watch.c
++++ b/net/core/link_watch.c
+@@ -67,7 +67,7 @@ static void rfc2863_policy(struct net_device *dev)
+ {
+ unsigned char operstate = default_operstate(dev);
+
+- if (operstate == dev->operstate)
++ if (operstate == READ_ONCE(dev->operstate))
+ return;
+
+ write_lock(&dev_base_lock);
+@@ -87,7 +87,7 @@ static void rfc2863_policy(struct net_device *dev)
+ break;
+ }
+
+- dev->operstate = operstate;
++ WRITE_ONCE(dev->operstate, operstate);
+
+ write_unlock(&dev_base_lock);
+ }
+diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
+index fccaa5bac0ed0..5a9487af44e00 100644
+--- a/net/core/net-sysfs.c
++++ b/net/core/net-sysfs.c
+@@ -307,11 +307,9 @@ static ssize_t operstate_show(struct device *dev,
+ const struct net_device *netdev = to_net_dev(dev);
+ unsigned char operstate;
+
+- read_lock(&dev_base_lock);
+- operstate = netdev->operstate;
++ operstate = READ_ONCE(netdev->operstate);
+ if (!netif_running(netdev))
+ operstate = IF_OPER_DOWN;
+- read_unlock(&dev_base_lock);
+
+ if (operstate >= ARRAY_SIZE(operstates))
+ return -EINVAL; /* should not happen */
+diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
+index 89964270cf27f..7ea66de1442cc 100644
+--- a/net/core/rtnetlink.c
++++ b/net/core/rtnetlink.c
+@@ -880,9 +880,9 @@ static void set_operstate(struct net_device *dev, unsigned char transition)
+ break;
+ }
+
+- if (dev->operstate != operstate) {
++ if (READ_ONCE(dev->operstate) != operstate) {
+ write_lock(&dev_base_lock);
+- dev->operstate = operstate;
++ WRITE_ONCE(dev->operstate, operstate);
+ write_unlock(&dev_base_lock);
+ netdev_state_change(dev);
+ }
+diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
+index dd4b5f0aa1318..cd337385e8592 100644
+--- a/net/hsr/hsr_device.c
++++ b/net/hsr/hsr_device.c
+@@ -31,8 +31,8 @@ static bool is_slave_up(struct net_device *dev)
+ static void __hsr_set_operstate(struct net_device *dev, int transition)
+ {
+ write_lock(&dev_base_lock);
+- if (dev->operstate != transition) {
+- dev->operstate = transition;
++ if (READ_ONCE(dev->operstate) != transition) {
++ WRITE_ONCE(dev->operstate, transition);
+ write_unlock(&dev_base_lock);
+ netdev_state_change(dev);
+ } else {
+@@ -78,14 +78,14 @@ static void hsr_check_announce(struct net_device *hsr_dev,
+
+ hsr = netdev_priv(hsr_dev);
+
+- if (hsr_dev->operstate == IF_OPER_UP && old_operstate != IF_OPER_UP) {
++ if (READ_ONCE(hsr_dev->operstate) == IF_OPER_UP && old_operstate != IF_OPER_UP) {
+ /* Went up */
+ hsr->announce_count = 0;
+ mod_timer(&hsr->announce_timer,
+ jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL));
+ }
+
+- if (hsr_dev->operstate != IF_OPER_UP && old_operstate == IF_OPER_UP)
++ if (READ_ONCE(hsr_dev->operstate) != IF_OPER_UP && old_operstate == IF_OPER_UP)
+ /* Went down */
+ del_timer(&hsr->announce_timer);
+ }
+@@ -100,7 +100,7 @@ void hsr_check_carrier_and_operstate(struct hsr_priv *hsr)
+ /* netif_stacked_transfer_operstate() cannot be used here since
+ * it doesn't set IF_OPER_LOWERLAYERDOWN (?)
+ */
+- old_operstate = master->dev->operstate;
++ old_operstate = READ_ONCE(master->dev->operstate);
+ has_carrier = hsr_check_carrier(master);
+ hsr_set_operstate(master, has_carrier);
+ hsr_check_announce(master->dev, old_operstate);
+diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
+index d1806eee1687d..01f4502916a12 100644
+--- a/net/ipv6/addrconf.c
++++ b/net/ipv6/addrconf.c
+@@ -6011,7 +6011,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
+ (dev->ifindex != dev_get_iflink(dev) &&
+ nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) ||
+ nla_put_u8(skb, IFLA_OPERSTATE,
+- netif_running(dev) ? dev->operstate : IF_OPER_DOWN))
++ netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN))
+ goto nla_put_failure;
+ protoinfo = nla_nest_start_noflag(skb, IFLA_PROTINFO);
+ if (!protoinfo)
+--
+2.43.0
+
--- /dev/null
+From e07a45cf8dfcc21b5144d9132a343a7a3fc878fc Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sun, 5 May 2024 19:36:49 +0900
+Subject: nfc: nci: Fix kcov check in nci_rx_work()
+
+From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
+
+[ Upstream commit 19e35f24750ddf860c51e51c68cf07ea181b4881 ]
+
+Commit 7e8cdc97148c ("nfc: Add KCOV annotations") added
+kcov_remote_start_common()/kcov_remote_stop() pair into nci_rx_work(),
+with an assumption that kcov_remote_stop() is called upon continue of
+the for loop. But commit d24b03535e5e ("nfc: nci: Fix uninit-value in
+nci_dev_up and nci_ntf_packet") forgot to call kcov_remote_stop() before
+break of the for loop.
+
+Reported-by: syzbot <syzbot+0438378d6f157baae1a2@syzkaller.appspotmail.com>
+Closes: https://syzkaller.appspot.com/bug?extid=0438378d6f157baae1a2
+Fixes: d24b03535e5e ("nfc: nci: Fix uninit-value in nci_dev_up and nci_ntf_packet")
+Suggested-by: Andrey Konovalov <andreyknvl@gmail.com>
+Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
+Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+Link: https://lore.kernel.org/r/6d10f829-5a0c-405a-b39a-d7266f3a1a0b@I-love.SAKURA.ne.jp
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/nfc/nci/core.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
+index 772ddb5824d9e..5d708af0fcfd3 100644
+--- a/net/nfc/nci/core.c
++++ b/net/nfc/nci/core.c
+@@ -1518,6 +1518,7 @@ static void nci_rx_work(struct work_struct *work)
+
+ if (!nci_plen(skb->data)) {
+ kfree_skb(skb);
++ kcov_remote_stop();
+ break;
+ }
+
+--
+2.43.0
+
--- /dev/null
+From 8f307c4f63fa2328b138f3d46f8367c38c6768f7 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 2 May 2024 16:17:00 +0000
+Subject: phonet: fix rtm_phonet_notify() skb allocation
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit d8cac8568618dcb8a51af3db1103e8d4cc4aeea7 ]
+
+fill_route() stores three components in the skb:
+
+- struct rtmsg
+- RTA_DST (u8)
+- RTA_OIF (u32)
+
+Therefore, rtm_phonet_notify() should use
+
+NLMSG_ALIGN(sizeof(struct rtmsg)) +
+nla_total_size(1) +
+nla_total_size(4)
+
+Fixes: f062f41d0657 ("Phonet: routing table Netlink interface")
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Acked-by: Rémi Denis-Courmont <courmisch@gmail.com>
+Link: https://lore.kernel.org/r/20240502161700.1804476-1-edumazet@google.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/phonet/pn_netlink.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
+index 59aebe2968907..dd4c7e9a634fb 100644
+--- a/net/phonet/pn_netlink.c
++++ b/net/phonet/pn_netlink.c
+@@ -193,7 +193,7 @@ void rtm_phonet_notify(int event, struct net_device *dev, u8 dst)
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+- skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) +
++ skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct rtmsg)) +
+ nla_total_size(1) + nla_total_size(4), GFP_KERNEL);
+ if (skb == NULL)
+ goto errout;
+--
+2.43.0
+
--- /dev/null
+From bcd1225d1bc0341816567f3f9d0b8a319a4fb815 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sun, 25 Feb 2024 23:58:42 -0500
+Subject: qibfs: fix dentry leak
+
+From: Al Viro <viro@zeniv.linux.org.uk>
+
+[ Upstream commit aa23317d0268b309bb3f0801ddd0d61813ff5afb ]
+
+simple_recursive_removal() drops the pinning references to all positives
+in subtree. For the cases when its argument has been kept alive by
+the pinning alone that's exactly the right thing to do, but here
+the argument comes from dcache lookup, that needs to be balanced by
+explicit dput().
+
+Fixes: e41d237818598 "qib_fs: switch to simple_recursive_removal()"
+Fucked-up-by: Al Viro <viro@zeniv.linux.org.uk>
+Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/infiniband/hw/qib/qib_fs.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c
+index ed7d4b02f45a6..11155e0fb8395 100644
+--- a/drivers/infiniband/hw/qib/qib_fs.c
++++ b/drivers/infiniband/hw/qib/qib_fs.c
+@@ -439,6 +439,7 @@ static int remove_device_files(struct super_block *sb,
+ return PTR_ERR(dir);
+ }
+ simple_recursive_removal(dir, NULL);
++ dput(dir);
+ return 0;
+ }
+
+--
+2.43.0
+
--- /dev/null
+From 36fb6c0b49f496ee4412fdc15a055c0a8f12194b Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 2 May 2024 18:57:51 +0300
+Subject: rtnetlink: Correct nested IFLA_VF_VLAN_LIST attribute validation
+
+From: Roded Zats <rzats@paloaltonetworks.com>
+
+[ Upstream commit 1aec77b2bb2ed1db0f5efc61c4c1ca3813307489 ]
+
+Each attribute inside a nested IFLA_VF_VLAN_LIST is assumed to be a
+struct ifla_vf_vlan_info so the size of such attribute needs to be at least
+of sizeof(struct ifla_vf_vlan_info) which is 14 bytes.
+The current size validation in do_setvfinfo is against NLA_HDRLEN (4 bytes)
+which is less than sizeof(struct ifla_vf_vlan_info) so this validation
+is not enough and a too small attribute might be cast to a
+struct ifla_vf_vlan_info, this might result in an out of bands
+read access when accessing the saved (casted) entry in ivvl.
+
+Fixes: 79aab093a0b5 ("net: Update API for VF vlan protocol 802.1ad support")
+Signed-off-by: Roded Zats <rzats@paloaltonetworks.com>
+Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
+Link: https://lore.kernel.org/r/20240502155751.75705-1-rzats@paloaltonetworks.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/core/rtnetlink.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
+index e8bf481e80f72..89964270cf27f 100644
+--- a/net/core/rtnetlink.c
++++ b/net/core/rtnetlink.c
+@@ -2519,7 +2519,7 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
+
+ nla_for_each_nested(attr, tb[IFLA_VF_VLAN_LIST], rem) {
+ if (nla_type(attr) != IFLA_VF_VLAN_INFO ||
+- nla_len(attr) < NLA_HDRLEN) {
++ nla_len(attr) < sizeof(struct ifla_vf_vlan_info)) {
+ return -EINVAL;
+ }
+ if (len >= MAX_VLAN_LIST_LEN)
+--
+2.43.0
+
--- /dev/null
+From 1201f32065f27e93bd4e9cee21fd61caf8c17481 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 3 May 2024 16:07:39 +0100
+Subject: rxrpc: Fix congestion control algorithm
+
+From: David Howells <dhowells@redhat.com>
+
+[ Upstream commit ba4e103848d3a2a28a0445e39f4a9564187efe54 ]
+
+Make the following fixes to the congestion control algorithm:
+
+ (1) Don't vary the cwnd starting value by the size of RXRPC_TX_SMSS since
+ that's currently held constant - set to the size of a jumbo subpacket
+ payload so that we can create jumbo packets on the fly. The current
+ code invariably picks 3 as the starting value.
+
+ Further, the starting cwnd needs to be an even number because we ack
+ every other packet, so set it to 4.
+
+ (2) Don't cut ssthresh when we see an ACK come from the peer with a
+ receive window (rwind) less than ssthresh. ssthresh keeps track of
+ characteristics of the connection whereas rwind may be reduced by the
+ peer for any reason - and may be reduced to 0.
+
+Fixes: 1fc4fa2ac93d ("rxrpc: Fix congestion management")
+Fixes: 0851115090a3 ("rxrpc: Reduce ssthresh to peer's receive window")
+Signed-off-by: David Howells <dhowells@redhat.com>
+Suggested-by: Simon Wilkinson <sxw@auristor.com>
+cc: Marc Dionne <marc.dionne@auristor.com>
+cc: linux-afs@lists.infradead.org
+Reviewed-by: Jeffrey Altman <jaltman@auristor.com <mailto:jaltman@auristor.com>>
+Link: https://lore.kernel.org/r/20240503150749.1001323-2-dhowells@redhat.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/rxrpc/ar-internal.h | 2 +-
+ net/rxrpc/call_object.c | 7 +------
+ net/rxrpc/input.c | 3 ---
+ 3 files changed, 2 insertions(+), 10 deletions(-)
+
+diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
+index bda3f6690b321..d431376bb120a 100644
+--- a/net/rxrpc/ar-internal.h
++++ b/net/rxrpc/ar-internal.h
+@@ -688,7 +688,7 @@ struct rxrpc_call {
+ * packets) rather than bytes.
+ */
+ #define RXRPC_TX_SMSS RXRPC_JUMBO_DATALEN
+-#define RXRPC_MIN_CWND (RXRPC_TX_SMSS > 2190 ? 2 : RXRPC_TX_SMSS > 1095 ? 3 : 4)
++#define RXRPC_MIN_CWND 4
+ u8 cong_cwnd; /* Congestion window size */
+ u8 cong_extra; /* Extra to send for congestion management */
+ u8 cong_ssthresh; /* Slow-start threshold */
+diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
+index 0a50341d920af..29385908099ef 100644
+--- a/net/rxrpc/call_object.c
++++ b/net/rxrpc/call_object.c
+@@ -175,12 +175,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
+ call->rx_winsize = rxrpc_rx_window_size;
+ call->tx_winsize = 16;
+
+- if (RXRPC_TX_SMSS > 2190)
+- call->cong_cwnd = 2;
+- else if (RXRPC_TX_SMSS > 1095)
+- call->cong_cwnd = 3;
+- else
+- call->cong_cwnd = 4;
++ call->cong_cwnd = RXRPC_MIN_CWND;
+ call->cong_ssthresh = RXRPC_TX_MAX_WINDOW;
+
+ call->rxnet = rxnet;
+diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
+index 718ffd184ddb6..f7304e06aadca 100644
+--- a/net/rxrpc/input.c
++++ b/net/rxrpc/input.c
+@@ -688,9 +688,6 @@ static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb
+ call->tx_winsize = rwind;
+ }
+
+- if (call->cong_ssthresh > rwind)
+- call->cong_ssthresh = rwind;
+-
+ mtu = min(ntohl(trailer->maxMTU), ntohl(trailer->ifMTU));
+
+ peer = call->peer;
+--
+2.43.0
+
--- /dev/null
+From 70d112aa6492c9ce79b0693aeecbe031969f630e Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 26 Jan 2024 16:17:03 +0000
+Subject: rxrpc: Fix the names of the fields in the ACK trailer struct
+
+From: David Howells <dhowells@redhat.com>
+
+[ Upstream commit 17469ae0582aaacad36e8e858f58b86c369f21ef ]
+
+From AFS-3.3 a trailer containing extra info was added to the ACK packet
+format - but AF_RXRPC has the names of some of the fields mixed up compared
+to other AFS implementations.
+
+Rename the struct and the fields to make them match.
+
+Signed-off-by: David Howells <dhowells@redhat.com>
+cc: Marc Dionne <marc.dionne@auristor.com>
+cc: "David S. Miller" <davem@davemloft.net>
+cc: Eric Dumazet <edumazet@google.com>
+cc: Jakub Kicinski <kuba@kernel.org>
+cc: Paolo Abeni <pabeni@redhat.com>
+cc: linux-afs@lists.infradead.org
+cc: netdev@vger.kernel.org
+Stable-dep-of: ba4e103848d3 ("rxrpc: Fix congestion control algorithm")
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ include/trace/events/rxrpc.h | 2 +-
+ net/rxrpc/conn_event.c | 16 ++++++++--------
+ net/rxrpc/input.c | 22 +++++++++++-----------
+ net/rxrpc/output.c | 14 +++++++-------
+ net/rxrpc/protocol.h | 6 +++---
+ 5 files changed, 30 insertions(+), 30 deletions(-)
+
+diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
+index 0dd4a21d172da..3322fb93a260b 100644
+--- a/include/trace/events/rxrpc.h
++++ b/include/trace/events/rxrpc.h
+@@ -83,7 +83,7 @@
+ EM(rxrpc_badmsg_bad_abort, "bad-abort") \
+ EM(rxrpc_badmsg_bad_jumbo, "bad-jumbo") \
+ EM(rxrpc_badmsg_short_ack, "short-ack") \
+- EM(rxrpc_badmsg_short_ack_info, "short-ack-info") \
++ EM(rxrpc_badmsg_short_ack_trailer, "short-ack-trailer") \
+ EM(rxrpc_badmsg_short_hdr, "short-hdr") \
+ EM(rxrpc_badmsg_unsupported_packet, "unsup-pkt") \
+ EM(rxrpc_badmsg_zero_call, "zero-call") \
+diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
+index 1f251d758cb9d..598b4ee389fc1 100644
+--- a/net/rxrpc/conn_event.c
++++ b/net/rxrpc/conn_event.c
+@@ -88,7 +88,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
+ struct rxrpc_ackpacket ack;
+ };
+ } __attribute__((packed)) pkt;
+- struct rxrpc_ackinfo ack_info;
++ struct rxrpc_acktrailer trailer;
+ size_t len;
+ int ret, ioc;
+ u32 serial, mtu, call_id, padding;
+@@ -122,8 +122,8 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
+ iov[0].iov_len = sizeof(pkt.whdr);
+ iov[1].iov_base = &padding;
+ iov[1].iov_len = 3;
+- iov[2].iov_base = &ack_info;
+- iov[2].iov_len = sizeof(ack_info);
++ iov[2].iov_base = &trailer;
++ iov[2].iov_len = sizeof(trailer);
+
+ serial = rxrpc_get_next_serial(conn);
+
+@@ -158,14 +158,14 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
+ pkt.ack.serial = htonl(skb ? sp->hdr.serial : 0);
+ pkt.ack.reason = skb ? RXRPC_ACK_DUPLICATE : RXRPC_ACK_IDLE;
+ pkt.ack.nAcks = 0;
+- ack_info.rxMTU = htonl(rxrpc_rx_mtu);
+- ack_info.maxMTU = htonl(mtu);
+- ack_info.rwind = htonl(rxrpc_rx_window_size);
+- ack_info.jumbo_max = htonl(rxrpc_rx_jumbo_max);
++ trailer.maxMTU = htonl(rxrpc_rx_mtu);
++ trailer.ifMTU = htonl(mtu);
++ trailer.rwind = htonl(rxrpc_rx_window_size);
++ trailer.jumbo_max = htonl(rxrpc_rx_jumbo_max);
+ pkt.whdr.flags |= RXRPC_SLOW_START_OK;
+ padding = 0;
+ iov[0].iov_len += sizeof(pkt.ack);
+- len += sizeof(pkt.ack) + 3 + sizeof(ack_info);
++ len += sizeof(pkt.ack) + 3 + sizeof(trailer);
+ ioc = 3;
+
+ trace_rxrpc_tx_ack(chan->call_debug_id, serial,
+diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
+index 9691de00ade75..718ffd184ddb6 100644
+--- a/net/rxrpc/input.c
++++ b/net/rxrpc/input.c
+@@ -670,14 +670,14 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call,
+ /*
+ * Process the extra information that may be appended to an ACK packet
+ */
+-static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
+- struct rxrpc_ackinfo *ackinfo)
++static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb,
++ struct rxrpc_acktrailer *trailer)
+ {
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ struct rxrpc_peer *peer;
+ unsigned int mtu;
+ bool wake = false;
+- u32 rwind = ntohl(ackinfo->rwind);
++ u32 rwind = ntohl(trailer->rwind);
+
+ if (rwind > RXRPC_TX_MAX_WINDOW)
+ rwind = RXRPC_TX_MAX_WINDOW;
+@@ -691,7 +691,7 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
+ if (call->cong_ssthresh > rwind)
+ call->cong_ssthresh = rwind;
+
+- mtu = min(ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU));
++ mtu = min(ntohl(trailer->maxMTU), ntohl(trailer->ifMTU));
+
+ peer = call->peer;
+ if (mtu < peer->maxdata) {
+@@ -837,7 +837,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
+ struct rxrpc_ack_summary summary = { 0 };
+ struct rxrpc_ackpacket ack;
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+- struct rxrpc_ackinfo info;
++ struct rxrpc_acktrailer trailer;
+ rxrpc_serial_t ack_serial, acked_serial;
+ rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since;
+ int nr_acks, offset, ioffset;
+@@ -917,11 +917,11 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
+ goto send_response;
+ }
+
+- info.rxMTU = 0;
++ trailer.maxMTU = 0;
+ ioffset = offset + nr_acks + 3;
+- if (skb->len >= ioffset + sizeof(info) &&
+- skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0)
+- return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_info);
++ if (skb->len >= ioffset + sizeof(trailer) &&
++ skb_copy_bits(skb, ioffset, &trailer, sizeof(trailer)) < 0)
++ return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_trailer);
+
+ if (nr_acks > 0)
+ skb_condense(skb);
+@@ -950,8 +950,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
+ }
+
+ /* Parse rwind and mtu sizes if provided. */
+- if (info.rxMTU)
+- rxrpc_input_ackinfo(call, skb, &info);
++ if (trailer.maxMTU)
++ rxrpc_input_ack_trailer(call, skb, &trailer);
+
+ if (first_soft_ack == 0)
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero);
+diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
+index 4a292f860ae37..cad6a7d18e040 100644
+--- a/net/rxrpc/output.c
++++ b/net/rxrpc/output.c
+@@ -83,7 +83,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
+ struct rxrpc_txbuf *txb,
+ u16 *_rwind)
+ {
+- struct rxrpc_ackinfo ackinfo;
++ struct rxrpc_acktrailer trailer;
+ unsigned int qsize, sack, wrap, to;
+ rxrpc_seq_t window, wtop;
+ int rsize;
+@@ -126,16 +126,16 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
+ qsize = (window - 1) - call->rx_consumed;
+ rsize = max_t(int, call->rx_winsize - qsize, 0);
+ *_rwind = rsize;
+- ackinfo.rxMTU = htonl(rxrpc_rx_mtu);
+- ackinfo.maxMTU = htonl(mtu);
+- ackinfo.rwind = htonl(rsize);
+- ackinfo.jumbo_max = htonl(jmax);
++ trailer.maxMTU = htonl(rxrpc_rx_mtu);
++ trailer.ifMTU = htonl(mtu);
++ trailer.rwind = htonl(rsize);
++ trailer.jumbo_max = htonl(jmax);
+
+ *ackp++ = 0;
+ *ackp++ = 0;
+ *ackp++ = 0;
+- memcpy(ackp, &ackinfo, sizeof(ackinfo));
+- return txb->ack.nAcks + 3 + sizeof(ackinfo);
++ memcpy(ackp, &trailer, sizeof(trailer));
++ return txb->ack.nAcks + 3 + sizeof(trailer);
+ }
+
+ /*
+diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h
+index e8ee4af43ca89..4fe6b4d20ada9 100644
+--- a/net/rxrpc/protocol.h
++++ b/net/rxrpc/protocol.h
+@@ -135,9 +135,9 @@ struct rxrpc_ackpacket {
+ /*
+ * ACK packets can have a further piece of information tagged on the end
+ */
+-struct rxrpc_ackinfo {
+- __be32 rxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */
+- __be32 maxMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */
++struct rxrpc_acktrailer {
++ __be32 maxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */
++ __be32 ifMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */
+ __be32 rwind; /* Rx window size (packets) [AFS 3.4] */
+ __be32 jumbo_max; /* max packets to stick into a jumbo packet [AFS 3.5] */
+ };
+--
+2.43.0
+
--- /dev/null
+From 5ab2633fa6a84a095c122aecf694c6e16ab1c3f1 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 3 May 2024 16:07:40 +0100
+Subject: rxrpc: Only transmit one ACK per jumbo packet received
+
+From: David Howells <dhowells@redhat.com>
+
+[ Upstream commit 012b7206918dcc5a4dcf1432b3e643114c95957e ]
+
+Only generate one ACK packet for all the subpackets in a jumbo packet. If
+we would like to generate more than one ACK, we prioritise them base on
+their reason code, in the order, highest first:
+
+ OutOfSeq > NoSpace > ExceedsWin > Duplicate > Requested > Delay > Idle
+
+For the first four, we reference the lowest offending subpacket; for the
+last three, the highest.
+
+This reduces the number of ACKs we end up transmitting to one per UDP
+packet transmitted to reduce network loading and packet parsing.
+
+Fixes: 5d7edbc9231e ("rxrpc: Get rid of the Rx ring")
+Signed-off-by: David Howells <dhowells@redhat.com>
+cc: Marc Dionne <marc.dionne@auristor.com>
+cc: linux-afs@lists.infradead.org
+Reviewed-by: Jeffrey Altman <jaltman@auristor.com <mailto:jaltman@auristor.com>>
+Link: https://lore.kernel.org/r/20240503150749.1001323-3-dhowells@redhat.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/rxrpc/input.c | 46 +++++++++++++++++++++++++++++++++++-----------
+ 1 file changed, 35 insertions(+), 11 deletions(-)
+
+diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
+index f7304e06aadca..5dfda1ac51dda 100644
+--- a/net/rxrpc/input.c
++++ b/net/rxrpc/input.c
+@@ -9,6 +9,17 @@
+
+ #include "ar-internal.h"
+
++/* Override priority when generating ACKs for received DATA */
++static const u8 rxrpc_ack_priority[RXRPC_ACK__INVALID] = {
++ [RXRPC_ACK_IDLE] = 1,
++ [RXRPC_ACK_DELAY] = 2,
++ [RXRPC_ACK_REQUESTED] = 3,
++ [RXRPC_ACK_DUPLICATE] = 4,
++ [RXRPC_ACK_EXCEEDS_WINDOW] = 5,
++ [RXRPC_ACK_NOSPACE] = 6,
++ [RXRPC_ACK_OUT_OF_SEQUENCE] = 7,
++};
++
+ static void rxrpc_proto_abort(struct rxrpc_call *call, rxrpc_seq_t seq,
+ enum rxrpc_abort_reason why)
+ {
+@@ -366,7 +377,7 @@ static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb,
+ * Process a DATA packet.
+ */
+ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb,
+- bool *_notify)
++ bool *_notify, rxrpc_serial_t *_ack_serial, int *_ack_reason)
+ {
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ struct sk_buff *oos;
+@@ -419,8 +430,6 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb,
+ /* Send an immediate ACK if we fill in a hole */
+ else if (!skb_queue_empty(&call->rx_oos_queue))
+ ack_reason = RXRPC_ACK_DELAY;
+- else
+- call->ackr_nr_unacked++;
+
+ window++;
+ if (after(window, wtop)) {
+@@ -498,12 +507,16 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb,
+ }
+
+ send_ack:
+- if (ack_reason >= 0)
+- rxrpc_send_ACK(call, ack_reason, serial,
+- rxrpc_propose_ack_input_data);
+- else
+- rxrpc_propose_delay_ACK(call, serial,
+- rxrpc_propose_ack_input_data);
++ if (ack_reason >= 0) {
++ if (rxrpc_ack_priority[ack_reason] > rxrpc_ack_priority[*_ack_reason]) {
++ *_ack_serial = serial;
++ *_ack_reason = ack_reason;
++ } else if (rxrpc_ack_priority[ack_reason] == rxrpc_ack_priority[*_ack_reason] &&
++ ack_reason == RXRPC_ACK_REQUESTED) {
++ *_ack_serial = serial;
++ *_ack_reason = ack_reason;
++ }
++ }
+ }
+
+ /*
+@@ -514,9 +527,11 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb
+ struct rxrpc_jumbo_header jhdr;
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb), *jsp;
+ struct sk_buff *jskb;
++ rxrpc_serial_t ack_serial = 0;
+ unsigned int offset = sizeof(struct rxrpc_wire_header);
+ unsigned int len = skb->len - offset;
+ bool notify = false;
++ int ack_reason = 0;
+
+ while (sp->hdr.flags & RXRPC_JUMBO_PACKET) {
+ if (len < RXRPC_JUMBO_SUBPKTLEN)
+@@ -536,7 +551,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb
+ jsp = rxrpc_skb(jskb);
+ jsp->offset = offset;
+ jsp->len = RXRPC_JUMBO_DATALEN;
+- rxrpc_input_data_one(call, jskb, ¬ify);
++ rxrpc_input_data_one(call, jskb, ¬ify, &ack_serial, &ack_reason);
+ rxrpc_free_skb(jskb, rxrpc_skb_put_jumbo_subpacket);
+
+ sp->hdr.flags = jhdr.flags;
+@@ -549,7 +564,16 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb
+
+ sp->offset = offset;
+ sp->len = len;
+- rxrpc_input_data_one(call, skb, ¬ify);
++ rxrpc_input_data_one(call, skb, ¬ify, &ack_serial, &ack_reason);
++
++ if (ack_reason > 0) {
++ rxrpc_send_ACK(call, ack_reason, ack_serial,
++ rxrpc_propose_ack_input_data);
++ } else {
++ call->ackr_nr_unacked++;
++ rxrpc_propose_delay_ACK(call, sp->hdr.serial,
++ rxrpc_propose_ack_input_data);
++ }
+ if (notify) {
+ trace_rxrpc_notify_socket(call->debug_id, sp->hdr.serial);
+ rxrpc_notify_socket(call);
+--
+2.43.0
+
--- /dev/null
+From 0cda0dd31e8f9340f25dd67be09a83db4d680a09 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 6 Dec 2023 15:07:54 +0800
+Subject: selftests/net: convert test_bridge_neigh_suppress.sh to run it in
+ unique namespace
+
+From: Hangbin Liu <liuhangbin@gmail.com>
+
+[ Upstream commit 312abe3d93a35f9c486a4703d39cab52457266f0 ]
+
+Here is the test result after conversion.
+
+]# ./test_bridge_neigh_suppress.sh
+
+Per-port ARP suppression - VLAN 10
+----------------------------------
+TEST: arping [ OK ]
+TEST: ARP suppression [ OK ]
+
+...
+
+TEST: NS suppression (VLAN 20) [ OK ]
+
+Tests passed: 148
+Tests failed: 0
+
+Acked-by: David Ahern <dsahern@kernel.org>
+Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
+Reviewed-by: Ido Schimmel <idosch@nvidia.com>
+Tested-by: Ido Schimmel <idosch@nvidia.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Stable-dep-of: 9a169c267e94 ("selftests: test_bridge_neigh_suppress.sh: Fix failures due to duplicate MAC")
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ .../net/test_bridge_neigh_suppress.sh | 331 +++++++++---------
+ 1 file changed, 162 insertions(+), 169 deletions(-)
+
+diff --git a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
+index d80f2cd87614c..8533393a4f186 100755
+--- a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
++++ b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
+@@ -45,9 +45,8 @@
+ # | sw1 | | sw2 |
+ # +------------------------------------+ +------------------------------------+
+
++source lib.sh
+ ret=0
+-# Kselftest framework requirement - SKIP code is 4.
+-ksft_skip=4
+
+ # All tests in this script. Can be overridden with -t option.
+ TESTS="
+@@ -140,9 +139,6 @@ setup_topo_ns()
+ {
+ local ns=$1; shift
+
+- ip netns add $ns
+- ip -n $ns link set dev lo up
+-
+ ip netns exec $ns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1
+ ip netns exec $ns sysctl -qw net.ipv6.conf.default.ignore_routes_with_linkdown=1
+ ip netns exec $ns sysctl -qw net.ipv6.conf.all.accept_dad=0
+@@ -153,21 +149,22 @@ setup_topo()
+ {
+ local ns
+
+- for ns in h1 h2 sw1 sw2; do
++ setup_ns h1 h2 sw1 sw2
++ for ns in $h1 $h2 $sw1 $sw2; do
+ setup_topo_ns $ns
+ done
+
+ ip link add name veth0 type veth peer name veth1
+- ip link set dev veth0 netns h1 name eth0
+- ip link set dev veth1 netns sw1 name swp1
++ ip link set dev veth0 netns $h1 name eth0
++ ip link set dev veth1 netns $sw1 name swp1
+
+ ip link add name veth0 type veth peer name veth1
+- ip link set dev veth0 netns sw1 name veth0
+- ip link set dev veth1 netns sw2 name veth0
++ ip link set dev veth0 netns $sw1 name veth0
++ ip link set dev veth1 netns $sw2 name veth0
+
+ ip link add name veth0 type veth peer name veth1
+- ip link set dev veth0 netns h2 name eth0
+- ip link set dev veth1 netns sw2 name swp1
++ ip link set dev veth0 netns $h2 name eth0
++ ip link set dev veth1 netns $sw2 name swp1
+ }
+
+ setup_host_common()
+@@ -190,7 +187,7 @@ setup_host_common()
+
+ setup_h1()
+ {
+- local ns=h1
++ local ns=$h1
+ local v4addr1=192.0.2.1/28
+ local v4addr2=192.0.2.17/28
+ local v6addr1=2001:db8:1::1/64
+@@ -201,7 +198,7 @@ setup_h1()
+
+ setup_h2()
+ {
+- local ns=h2
++ local ns=$h2
+ local v4addr1=192.0.2.2/28
+ local v4addr2=192.0.2.18/28
+ local v6addr1=2001:db8:1::2/64
+@@ -254,7 +251,7 @@ setup_sw_common()
+
+ setup_sw1()
+ {
+- local ns=sw1
++ local ns=$sw1
+ local local_addr=192.0.2.33
+ local remote_addr=192.0.2.34
+ local veth_addr=192.0.2.49
+@@ -265,7 +262,7 @@ setup_sw1()
+
+ setup_sw2()
+ {
+- local ns=sw2
++ local ns=$sw2
+ local local_addr=192.0.2.34
+ local remote_addr=192.0.2.33
+ local veth_addr=192.0.2.50
+@@ -291,11 +288,7 @@ setup()
+
+ cleanup()
+ {
+- local ns
+-
+- for ns in h1 h2 sw1 sw2; do
+- ip netns del $ns &> /dev/null
+- done
++ cleanup_ns $h1 $h2 $sw1 $sw2
+ }
+
+ ################################################################################
+@@ -312,80 +305,80 @@ neigh_suppress_arp_common()
+ echo "Per-port ARP suppression - VLAN $vid"
+ echo "----------------------------------"
+
+- run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
+- run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto 0x0806 flower indev swp1 arp_tip $tip arp_sip $sip arp_op request action pass"
++ run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact"
++ run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto 0x0806 flower indev swp1 arp_tip $tip arp_sip $sip arp_op request action pass"
+
+ # Initial state - check that ARP requests are not suppressed and that
+ # ARP replies are received.
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+ log_test $? 0 "arping"
+- tc_check_packets sw1 "dev vx0 egress" 101 1
++ tc_check_packets $sw1 "dev vx0 egress" 101 1
+ log_test $? 0 "ARP suppression"
+
+ # Enable neighbor suppression and check that nothing changes compared
+ # to the initial state.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+ log_test $? 0 "\"neigh_suppress\" is on"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+ log_test $? 0 "arping"
+- tc_check_packets sw1 "dev vx0 egress" 101 2
++ tc_check_packets $sw1 "dev vx0 egress" 101 2
+ log_test $? 0 "ARP suppression"
+
+ # Install an FDB entry for the remote host and check that nothing
+ # changes compared to the initial state.
+- h2_mac=$(ip -n h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
+- run_cmd "bridge -n sw1 fdb replace $h2_mac dev vx0 master static vlan $vid"
++ h2_mac=$(ip -n $h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
++ run_cmd "bridge -n $sw1 fdb replace $h2_mac dev vx0 master static vlan $vid"
+ log_test $? 0 "FDB entry installation"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+ log_test $? 0 "arping"
+- tc_check_packets sw1 "dev vx0 egress" 101 3
++ tc_check_packets $sw1 "dev vx0 egress" 101 3
+ log_test $? 0 "ARP suppression"
+
+ # Install a neighbor on the matching SVI interface and check that ARP
+ # requests are suppressed.
+- run_cmd "ip -n sw1 neigh replace $tip lladdr $h2_mac nud permanent dev br0.$vid"
++ run_cmd "ip -n $sw1 neigh replace $tip lladdr $h2_mac nud permanent dev br0.$vid"
+ log_test $? 0 "Neighbor entry installation"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+ log_test $? 0 "arping"
+- tc_check_packets sw1 "dev vx0 egress" 101 3
++ tc_check_packets $sw1 "dev vx0 egress" 101 3
+ log_test $? 0 "ARP suppression"
+
+ # Take the second host down and check that ARP requests are suppressed
+ # and that ARP replies are received.
+- run_cmd "ip -n h2 link set dev eth0.$vid down"
++ run_cmd "ip -n $h2 link set dev eth0.$vid down"
+ log_test $? 0 "H2 down"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+ log_test $? 0 "arping"
+- tc_check_packets sw1 "dev vx0 egress" 101 3
++ tc_check_packets $sw1 "dev vx0 egress" 101 3
+ log_test $? 0 "ARP suppression"
+
+- run_cmd "ip -n h2 link set dev eth0.$vid up"
++ run_cmd "ip -n $h2 link set dev eth0.$vid up"
+ log_test $? 0 "H2 up"
+
+ # Disable neighbor suppression and check that ARP requests are no
+ # longer suppressed.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress off"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress off"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
+ log_test $? 0 "\"neigh_suppress\" is off"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+ log_test $? 0 "arping"
+- tc_check_packets sw1 "dev vx0 egress" 101 4
++ tc_check_packets $sw1 "dev vx0 egress" 101 4
+ log_test $? 0 "ARP suppression"
+
+ # Take the second host down and check that ARP requests are not
+ # suppressed and that ARP replies are not received.
+- run_cmd "ip -n h2 link set dev eth0.$vid down"
++ run_cmd "ip -n $h2 link set dev eth0.$vid down"
+ log_test $? 0 "H2 down"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip -I eth0.$vid $tip"
+ log_test $? 1 "arping"
+- tc_check_packets sw1 "dev vx0 egress" 101 5
++ tc_check_packets $sw1 "dev vx0 egress" 101 5
+ log_test $? 0 "ARP suppression"
+ }
+
+@@ -415,80 +408,80 @@ neigh_suppress_ns_common()
+ echo "Per-port NS suppression - VLAN $vid"
+ echo "---------------------------------"
+
+- run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
+- run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr type 135 code 0 action pass"
++ run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact"
++ run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr type 135 code 0 action pass"
+
+ # Initial state - check that NS messages are not suppressed and that ND
+ # messages are received.
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+ log_test $? 0 "ndisc6"
+- tc_check_packets sw1 "dev vx0 egress" 101 1
++ tc_check_packets $sw1 "dev vx0 egress" 101 1
+ log_test $? 0 "NS suppression"
+
+ # Enable neighbor suppression and check that nothing changes compared
+ # to the initial state.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+ log_test $? 0 "\"neigh_suppress\" is on"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+ log_test $? 0 "ndisc6"
+- tc_check_packets sw1 "dev vx0 egress" 101 2
++ tc_check_packets $sw1 "dev vx0 egress" 101 2
+ log_test $? 0 "NS suppression"
+
+ # Install an FDB entry for the remote host and check that nothing
+ # changes compared to the initial state.
+- h2_mac=$(ip -n h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
+- run_cmd "bridge -n sw1 fdb replace $h2_mac dev vx0 master static vlan $vid"
++ h2_mac=$(ip -n $h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
++ run_cmd "bridge -n $sw1 fdb replace $h2_mac dev vx0 master static vlan $vid"
+ log_test $? 0 "FDB entry installation"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+ log_test $? 0 "ndisc6"
+- tc_check_packets sw1 "dev vx0 egress" 101 3
++ tc_check_packets $sw1 "dev vx0 egress" 101 3
+ log_test $? 0 "NS suppression"
+
+ # Install a neighbor on the matching SVI interface and check that NS
+ # messages are suppressed.
+- run_cmd "ip -n sw1 neigh replace $daddr lladdr $h2_mac nud permanent dev br0.$vid"
++ run_cmd "ip -n $sw1 neigh replace $daddr lladdr $h2_mac nud permanent dev br0.$vid"
+ log_test $? 0 "Neighbor entry installation"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+ log_test $? 0 "ndisc6"
+- tc_check_packets sw1 "dev vx0 egress" 101 3
++ tc_check_packets $sw1 "dev vx0 egress" 101 3
+ log_test $? 0 "NS suppression"
+
+ # Take the second host down and check that NS messages are suppressed
+ # and that ND messages are received.
+- run_cmd "ip -n h2 link set dev eth0.$vid down"
++ run_cmd "ip -n $h2 link set dev eth0.$vid down"
+ log_test $? 0 "H2 down"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+ log_test $? 0 "ndisc6"
+- tc_check_packets sw1 "dev vx0 egress" 101 3
++ tc_check_packets $sw1 "dev vx0 egress" 101 3
+ log_test $? 0 "NS suppression"
+
+- run_cmd "ip -n h2 link set dev eth0.$vid up"
++ run_cmd "ip -n $h2 link set dev eth0.$vid up"
+ log_test $? 0 "H2 up"
+
+ # Disable neighbor suppression and check that NS messages are no longer
+ # suppressed.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress off"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress off"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
+ log_test $? 0 "\"neigh_suppress\" is off"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+ log_test $? 0 "ndisc6"
+- tc_check_packets sw1 "dev vx0 egress" 101 4
++ tc_check_packets $sw1 "dev vx0 egress" 101 4
+ log_test $? 0 "NS suppression"
+
+ # Take the second host down and check that NS messages are not
+ # suppressed and that ND messages are not received.
+- run_cmd "ip -n h2 link set dev eth0.$vid down"
++ run_cmd "ip -n $h2 link set dev eth0.$vid down"
+ log_test $? 0 "H2 down"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr -w 5000 $daddr eth0.$vid"
+ log_test $? 2 "ndisc6"
+- tc_check_packets sw1 "dev vx0 egress" 101 5
++ tc_check_packets $sw1 "dev vx0 egress" 101 5
+ log_test $? 0 "NS suppression"
+ }
+
+@@ -524,118 +517,118 @@ neigh_vlan_suppress_arp()
+ echo "Per-{Port, VLAN} ARP suppression"
+ echo "--------------------------------"
+
+- run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
+- run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto 0x0806 flower indev swp1 arp_tip $tip1 arp_sip $sip1 arp_op request action pass"
+- run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 102 proto 0x0806 flower indev swp1 arp_tip $tip2 arp_sip $sip2 arp_op request action pass"
++ run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact"
++ run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto 0x0806 flower indev swp1 arp_tip $tip1 arp_sip $sip1 arp_op request action pass"
++ run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 102 proto 0x0806 flower indev swp1 arp_tip $tip2 arp_sip $sip2 arp_op request action pass"
+
+- h2_mac1=$(ip -n h2 -j -p link show eth0.$vid1 | jq -r '.[]["address"]')
+- h2_mac2=$(ip -n h2 -j -p link show eth0.$vid2 | jq -r '.[]["address"]')
+- run_cmd "bridge -n sw1 fdb replace $h2_mac1 dev vx0 master static vlan $vid1"
+- run_cmd "bridge -n sw1 fdb replace $h2_mac2 dev vx0 master static vlan $vid2"
+- run_cmd "ip -n sw1 neigh replace $tip1 lladdr $h2_mac1 nud permanent dev br0.$vid1"
+- run_cmd "ip -n sw1 neigh replace $tip2 lladdr $h2_mac2 nud permanent dev br0.$vid2"
++ h2_mac1=$(ip -n $h2 -j -p link show eth0.$vid1 | jq -r '.[]["address"]')
++ h2_mac2=$(ip -n $h2 -j -p link show eth0.$vid2 | jq -r '.[]["address"]')
++ run_cmd "bridge -n $sw1 fdb replace $h2_mac1 dev vx0 master static vlan $vid1"
++ run_cmd "bridge -n $sw1 fdb replace $h2_mac2 dev vx0 master static vlan $vid2"
++ run_cmd "ip -n $sw1 neigh replace $tip1 lladdr $h2_mac1 nud permanent dev br0.$vid1"
++ run_cmd "ip -n $sw1 neigh replace $tip2 lladdr $h2_mac2 nud permanent dev br0.$vid2"
+
+ # Enable per-{Port, VLAN} neighbor suppression and check that ARP
+ # requests are not suppressed and that ARP replies are received.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_vlan_suppress on"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress on\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_vlan_suppress on"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress on\""
+ log_test $? 0 "\"neigh_vlan_suppress\" is on"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+ log_test $? 0 "arping (VLAN $vid1)"
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+ log_test $? 0 "arping (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 1
++ tc_check_packets $sw1 "dev vx0 egress" 101 1
+ log_test $? 0 "ARP suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 1
++ tc_check_packets $sw1 "dev vx0 egress" 102 1
+ log_test $? 0 "ARP suppression (VLAN $vid2)"
+
+ # Enable neighbor suppression on VLAN 10 and check that only on this
+ # VLAN ARP requests are suppressed.
+- run_cmd "bridge -n sw1 vlan set vid $vid1 dev vx0 neigh_suppress on"
+- run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress on\""
++ run_cmd "bridge -n $sw1 vlan set vid $vid1 dev vx0 neigh_suppress on"
++ run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress on\""
+ log_test $? 0 "\"neigh_suppress\" is on (VLAN $vid1)"
+- run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid2 | grep \"neigh_suppress off\""
++ run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid2 | grep \"neigh_suppress off\""
+ log_test $? 0 "\"neigh_suppress\" is off (VLAN $vid2)"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+ log_test $? 0 "arping (VLAN $vid1)"
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+ log_test $? 0 "arping (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 1
++ tc_check_packets $sw1 "dev vx0 egress" 101 1
+ log_test $? 0 "ARP suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 2
++ tc_check_packets $sw1 "dev vx0 egress" 102 2
+ log_test $? 0 "ARP suppression (VLAN $vid2)"
+
+ # Enable neighbor suppression on the port and check that it has no
+ # effect compared to previous state.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+ log_test $? 0 "\"neigh_suppress\" is on"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+ log_test $? 0 "arping (VLAN $vid1)"
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+ log_test $? 0 "arping (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 1
++ tc_check_packets $sw1 "dev vx0 egress" 101 1
+ log_test $? 0 "ARP suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 3
++ tc_check_packets $sw1 "dev vx0 egress" 102 3
+ log_test $? 0 "ARP suppression (VLAN $vid2)"
+
+ # Disable neighbor suppression on the port and check that it has no
+ # effect compared to previous state.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress off"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress off"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
+ log_test $? 0 "\"neigh_suppress\" is off"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+ log_test $? 0 "arping (VLAN $vid1)"
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+ log_test $? 0 "arping (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 1
++ tc_check_packets $sw1 "dev vx0 egress" 101 1
+ log_test $? 0 "ARP suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 4
++ tc_check_packets $sw1 "dev vx0 egress" 102 4
+ log_test $? 0 "ARP suppression (VLAN $vid2)"
+
+ # Disable neighbor suppression on VLAN 10 and check that ARP requests
+ # are no longer suppressed on this VLAN.
+- run_cmd "bridge -n sw1 vlan set vid $vid1 dev vx0 neigh_suppress off"
+- run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress off\""
++ run_cmd "bridge -n $sw1 vlan set vid $vid1 dev vx0 neigh_suppress off"
++ run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress off\""
+ log_test $? 0 "\"neigh_suppress\" is off (VLAN $vid1)"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+ log_test $? 0 "arping (VLAN $vid1)"
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+ log_test $? 0 "arping (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 2
++ tc_check_packets $sw1 "dev vx0 egress" 101 2
+ log_test $? 0 "ARP suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 5
++ tc_check_packets $sw1 "dev vx0 egress" 102 5
+ log_test $? 0 "ARP suppression (VLAN $vid2)"
+
+ # Disable per-{Port, VLAN} neighbor suppression, enable neighbor
+ # suppression on the port and check that on both VLANs ARP requests are
+ # suppressed.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_vlan_suppress off"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress off\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_vlan_suppress off"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress off\""
+ log_test $? 0 "\"neigh_vlan_suppress\" is off"
+
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+ log_test $? 0 "\"neigh_suppress\" is on"
+
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip1 -I eth0.$vid1 $tip1"
+ log_test $? 0 "arping (VLAN $vid1)"
+- run_cmd "ip netns exec h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
++ run_cmd "ip netns exec $h1 arping -q -b -c 1 -w 5 -s $sip2 -I eth0.$vid2 $tip2"
+ log_test $? 0 "arping (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 2
++ tc_check_packets $sw1 "dev vx0 egress" 101 2
+ log_test $? 0 "ARP suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 5
++ tc_check_packets $sw1 "dev vx0 egress" 102 5
+ log_test $? 0 "ARP suppression (VLAN $vid2)"
+ }
+
+@@ -655,118 +648,118 @@ neigh_vlan_suppress_ns()
+ echo "Per-{Port, VLAN} NS suppression"
+ echo "-------------------------------"
+
+- run_cmd "tc -n sw1 qdisc replace dev vx0 clsact"
+- run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr1 type 135 code 0 action pass"
+- run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 102 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr2 type 135 code 0 action pass"
++ run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact"
++ run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr1 type 135 code 0 action pass"
++ run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 102 proto ipv6 flower indev swp1 ip_proto icmpv6 dst_ip $maddr src_ip $saddr2 type 135 code 0 action pass"
+
+- h2_mac1=$(ip -n h2 -j -p link show eth0.$vid1 | jq -r '.[]["address"]')
+- h2_mac2=$(ip -n h2 -j -p link show eth0.$vid2 | jq -r '.[]["address"]')
+- run_cmd "bridge -n sw1 fdb replace $h2_mac1 dev vx0 master static vlan $vid1"
+- run_cmd "bridge -n sw1 fdb replace $h2_mac2 dev vx0 master static vlan $vid2"
+- run_cmd "ip -n sw1 neigh replace $daddr1 lladdr $h2_mac1 nud permanent dev br0.$vid1"
+- run_cmd "ip -n sw1 neigh replace $daddr2 lladdr $h2_mac2 nud permanent dev br0.$vid2"
++ h2_mac1=$(ip -n $h2 -j -p link show eth0.$vid1 | jq -r '.[]["address"]')
++ h2_mac2=$(ip -n $h2 -j -p link show eth0.$vid2 | jq -r '.[]["address"]')
++ run_cmd "bridge -n $sw1 fdb replace $h2_mac1 dev vx0 master static vlan $vid1"
++ run_cmd "bridge -n $sw1 fdb replace $h2_mac2 dev vx0 master static vlan $vid2"
++ run_cmd "ip -n $sw1 neigh replace $daddr1 lladdr $h2_mac1 nud permanent dev br0.$vid1"
++ run_cmd "ip -n $sw1 neigh replace $daddr2 lladdr $h2_mac2 nud permanent dev br0.$vid2"
+
+ # Enable per-{Port, VLAN} neighbor suppression and check that NS
+ # messages are not suppressed and that ND messages are received.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_vlan_suppress on"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress on\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_vlan_suppress on"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress on\""
+ log_test $? 0 "\"neigh_vlan_suppress\" is on"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+ log_test $? 0 "ndisc6 (VLAN $vid1)"
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+ log_test $? 0 "ndisc6 (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 1
++ tc_check_packets $sw1 "dev vx0 egress" 101 1
+ log_test $? 0 "NS suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 1
++ tc_check_packets $sw1 "dev vx0 egress" 102 1
+ log_test $? 0 "NS suppression (VLAN $vid2)"
+
+ # Enable neighbor suppression on VLAN 10 and check that only on this
+ # VLAN NS messages are suppressed.
+- run_cmd "bridge -n sw1 vlan set vid $vid1 dev vx0 neigh_suppress on"
+- run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress on\""
++ run_cmd "bridge -n $sw1 vlan set vid $vid1 dev vx0 neigh_suppress on"
++ run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress on\""
+ log_test $? 0 "\"neigh_suppress\" is on (VLAN $vid1)"
+- run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid2 | grep \"neigh_suppress off\""
++ run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid2 | grep \"neigh_suppress off\""
+ log_test $? 0 "\"neigh_suppress\" is off (VLAN $vid2)"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+ log_test $? 0 "ndisc6 (VLAN $vid1)"
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+ log_test $? 0 "ndisc6 (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 1
++ tc_check_packets $sw1 "dev vx0 egress" 101 1
+ log_test $? 0 "NS suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 2
++ tc_check_packets $sw1 "dev vx0 egress" 102 2
+ log_test $? 0 "NS suppression (VLAN $vid2)"
+
+ # Enable neighbor suppression on the port and check that it has no
+ # effect compared to previous state.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+ log_test $? 0 "\"neigh_suppress\" is on"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+ log_test $? 0 "ndisc6 (VLAN $vid1)"
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+ log_test $? 0 "ndisc6 (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 1
++ tc_check_packets $sw1 "dev vx0 egress" 101 1
+ log_test $? 0 "NS suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 3
++ tc_check_packets $sw1 "dev vx0 egress" 102 3
+ log_test $? 0 "NS suppression (VLAN $vid2)"
+
+ # Disable neighbor suppression on the port and check that it has no
+ # effect compared to previous state.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress off"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress off"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress off\""
+ log_test $? 0 "\"neigh_suppress\" is off"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+ log_test $? 0 "ndisc6 (VLAN $vid1)"
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+ log_test $? 0 "ndisc6 (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 1
++ tc_check_packets $sw1 "dev vx0 egress" 101 1
+ log_test $? 0 "NS suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 4
++ tc_check_packets $sw1 "dev vx0 egress" 102 4
+ log_test $? 0 "NS suppression (VLAN $vid2)"
+
+ # Disable neighbor suppression on VLAN 10 and check that NS messages
+ # are no longer suppressed on this VLAN.
+- run_cmd "bridge -n sw1 vlan set vid $vid1 dev vx0 neigh_suppress off"
+- run_cmd "bridge -n sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress off\""
++ run_cmd "bridge -n $sw1 vlan set vid $vid1 dev vx0 neigh_suppress off"
++ run_cmd "bridge -n $sw1 -d vlan show dev vx0 vid $vid1 | grep \"neigh_suppress off\""
+ log_test $? 0 "\"neigh_suppress\" is off (VLAN $vid1)"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+ log_test $? 0 "ndisc6 (VLAN $vid1)"
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+ log_test $? 0 "ndisc6 (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 2
++ tc_check_packets $sw1 "dev vx0 egress" 101 2
+ log_test $? 0 "NS suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 5
++ tc_check_packets $sw1 "dev vx0 egress" 102 5
+ log_test $? 0 "NS suppression (VLAN $vid2)"
+
+ # Disable per-{Port, VLAN} neighbor suppression, enable neighbor
+ # suppression on the port and check that on both VLANs NS messages are
+ # suppressed.
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_vlan_suppress off"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress off\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_vlan_suppress off"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_vlan_suppress off\""
+ log_test $? 0 "\"neigh_vlan_suppress\" is off"
+
+- run_cmd "bridge -n sw1 link set dev vx0 neigh_suppress on"
+- run_cmd "bridge -n sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
++ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
++ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+ log_test $? 0 "\"neigh_suppress\" is on"
+
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr1 -w 5000 $daddr1 eth0.$vid1"
+ log_test $? 0 "ndisc6 (VLAN $vid1)"
+- run_cmd "ip netns exec h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
++ run_cmd "ip netns exec $h1 ndisc6 -q -r 1 -s $saddr2 -w 5000 $daddr2 eth0.$vid2"
+ log_test $? 0 "ndisc6 (VLAN $vid2)"
+
+- tc_check_packets sw1 "dev vx0 egress" 101 2
++ tc_check_packets $sw1 "dev vx0 egress" 101 2
+ log_test $? 0 "NS suppression (VLAN $vid1)"
+- tc_check_packets sw1 "dev vx0 egress" 102 5
++ tc_check_packets $sw1 "dev vx0 egress" 102 5
+ log_test $? 0 "NS suppression (VLAN $vid2)"
+ }
+
+--
+2.43.0
+
--- /dev/null
+From a1389dc610b281e5a927ca276e099e9f3c9de5c2 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 7 May 2024 14:30:33 +0300
+Subject: selftests: test_bridge_neigh_suppress.sh: Fix failures due to
+ duplicate MAC
+
+From: Ido Schimmel <idosch@nvidia.com>
+
+[ Upstream commit 9a169c267e946b0f47f67e8ccc70134708ccf3d4 ]
+
+When creating the topology for the test, three veth pairs are created in
+the initial network namespace before being moved to one of the network
+namespaces created by the test.
+
+On systems where systemd-udev uses MACAddressPolicy=persistent (default
+since systemd version 242), this will result in some net devices having
+the same MAC address since they were created with the same name in the
+initial network namespace. In turn, this leads to arping / ndisc6
+failing since packets are dropped by the bridge's loopback filter.
+
+Fix by creating each net device in the correct network namespace instead
+of moving it there from the initial network namespace.
+
+Reported-by: Jakub Kicinski <kuba@kernel.org>
+Closes: https://lore.kernel.org/netdev/20240426074015.251854d4@kernel.org/
+Fixes: 7648ac72dcd7 ("selftests: net: Add bridge neighbor suppression test")
+Signed-off-by: Ido Schimmel <idosch@nvidia.com>
+Link: https://lore.kernel.org/r/20240507113033.1732534-1-idosch@nvidia.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ .../selftests/net/test_bridge_neigh_suppress.sh | 14 +++-----------
+ 1 file changed, 3 insertions(+), 11 deletions(-)
+
+diff --git a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
+index 8533393a4f186..02b986c9c247d 100755
+--- a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
++++ b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
+@@ -154,17 +154,9 @@ setup_topo()
+ setup_topo_ns $ns
+ done
+
+- ip link add name veth0 type veth peer name veth1
+- ip link set dev veth0 netns $h1 name eth0
+- ip link set dev veth1 netns $sw1 name swp1
+-
+- ip link add name veth0 type veth peer name veth1
+- ip link set dev veth0 netns $sw1 name veth0
+- ip link set dev veth1 netns $sw2 name veth0
+-
+- ip link add name veth0 type veth peer name veth1
+- ip link set dev veth0 netns $h2 name eth0
+- ip link set dev veth1 netns $sw2 name swp1
++ ip -n $h1 link add name eth0 type veth peer name swp1 netns $sw1
++ ip -n $sw1 link add name veth0 type veth peer name veth0 netns $sw2
++ ip -n $h2 link add name eth0 type veth peer name swp1 netns $sw2
+ }
+
+ setup_host_common()
+--
+2.43.0
+
net-usb-qmi_wwan-support-rolling-modules.patch
blk-iocost-do-not-warn-if-iocg-was-already-offlined.patch
sunrpc-add-a-missing-rpc_stat-for-tcp-tls.patch
+qibfs-fix-dentry-leak.patch
+xfrm-preserve-vlan-tags-for-transport-mode-software-.patch
+arm-9381-1-kasan-clear-stale-stack-poison.patch
+tcp-defer-shutdown-send_shutdown-for-tcp_syn_recv-so.patch
+tcp-use-refcount_inc_not_zero-in-tcp_twsk_unique.patch
+bluetooth-fix-use-after-free-bugs-caused-by-sco_sock.patch
+bluetooth-msft-fix-slab-use-after-free-in-msft_do_cl.patch
+bluetooth-hci-fix-potential-null-ptr-deref.patch
+bluetooth-l2cap-fix-null-ptr-deref-in-l2cap_chan_tim.patch
+net-ks8851-queue-rx-packets-in-irq-handler-instead-o.patch
+rtnetlink-correct-nested-ifla_vf_vlan_list-attribute.patch
+hwmon-corsair-cpro-use-a-separate-buffer-for-sending.patch
+hwmon-corsair-cpro-use-complete_all-instead-of-compl.patch
+hwmon-corsair-cpro-protect-ccp-wait_input_report-wit.patch
+phonet-fix-rtm_phonet_notify-skb-allocation.patch
+nfc-nci-fix-kcov-check-in-nci_rx_work.patch
+net-bridge-fix-corrupted-ethernet-header-on-multicas.patch
+ipv6-fix-potential-uninit-value-access-in-__ip6_make.patch
+selftests-net-convert-test_bridge_neigh_suppress.sh-.patch
+selftests-test_bridge_neigh_suppress.sh-fix-failures.patch
+rxrpc-fix-the-names-of-the-fields-in-the-ack-trailer.patch
+rxrpc-fix-congestion-control-algorithm.patch
+rxrpc-only-transmit-one-ack-per-jumbo-packet-receive.patch
+dt-bindings-net-mediatek-remove-wrongly-added-clocks.patch
+ipv6-fib6_rules-avoid-possible-null-dereference-in-f.patch
+net-sysfs-convert-dev-operstate-reads-to-lockless-on.patch
+hsr-simplify-code-for-announcing-hsr-nodes-timer-set.patch
+ipv6-annotate-data-races-around-cnf.disable_ipv6.patch
+ipv6-prevent-null-dereference-in-ip6_output.patch
+net-smc-fix-neighbour-and-rtable-leak-in-smc_ib_find.patch
+net-hns3-using-user-configure-after-hardware-reset.patch
+net-hns3-direct-return-when-receive-a-unknown-mailbo.patch
+net-hns3-change-type-of-numa_node_mask-as-nodemask_t.patch
+net-hns3-release-ptp-resources-if-pf-initialization-.patch
+net-hns3-use-appropriate-barrier-function-after-sett.patch
+net-hns3-fix-port-vlan-filter-not-disabled-issue.patch
+net-hns3-fix-kernel-crash-when-devlink-reload-during.patch
+net-dsa-mv88e6xxx-add-phylink_get_caps-for-the-mv88e.patch
--- /dev/null
+From 47736274421d290365f34e199df5b0d9b022486b Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 1 May 2024 12:54:48 +0000
+Subject: tcp: defer shutdown(SEND_SHUTDOWN) for TCP_SYN_RECV sockets
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit 94062790aedb505bdda209b10bea47b294d6394f ]
+
+TCP_SYN_RECV state is really special, it is only used by
+cross-syn connections, mostly used by fuzzers.
+
+In the following crash [1], syzbot managed to trigger a divide
+by zero in tcp_rcv_space_adjust()
+
+A socket makes the following state transitions,
+without ever calling tcp_init_transfer(),
+meaning tcp_init_buffer_space() is also not called.
+
+ TCP_CLOSE
+connect()
+ TCP_SYN_SENT
+ TCP_SYN_RECV
+shutdown() -> tcp_shutdown(sk, SEND_SHUTDOWN)
+ TCP_FIN_WAIT1
+
+To fix this issue, change tcp_shutdown() to not
+perform a TCP_SYN_RECV -> TCP_FIN_WAIT1 transition,
+which makes no sense anyway.
+
+When tcp_rcv_state_process() later changes socket state
+from TCP_SYN_RECV to TCP_ESTABLISH, then look at
+sk->sk_shutdown to finally enter TCP_FIN_WAIT1 state,
+and send a FIN packet from a sane socket state.
+
+This means tcp_send_fin() can now be called from BH
+context, and must use GFP_ATOMIC allocations.
+
+[1]
+divide error: 0000 [#1] PREEMPT SMP KASAN NOPTI
+CPU: 1 PID: 5084 Comm: syz-executor358 Not tainted 6.9.0-rc6-syzkaller-00022-g98369dccd2f8 #0
+Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024
+ RIP: 0010:tcp_rcv_space_adjust+0x2df/0x890 net/ipv4/tcp_input.c:767
+Code: e3 04 4c 01 eb 48 8b 44 24 38 0f b6 04 10 84 c0 49 89 d5 0f 85 a5 03 00 00 41 8b 8e c8 09 00 00 89 e8 29 c8 48 0f af c3 31 d2 <48> f7 f1 48 8d 1c 43 49 8d 96 76 08 00 00 48 89 d0 48 c1 e8 03 48
+RSP: 0018:ffffc900031ef3f0 EFLAGS: 00010246
+RAX: 0c677a10441f8f42 RBX: 000000004fb95e7e RCX: 0000000000000000
+RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
+RBP: 0000000027d4b11f R08: ffffffff89e535a4 R09: 1ffffffff25e6ab7
+R10: dffffc0000000000 R11: ffffffff8135e920 R12: ffff88802a9f8d30
+R13: dffffc0000000000 R14: ffff88802a9f8d00 R15: 1ffff1100553f2da
+FS: 00005555775c0380(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000
+CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+CR2: 00007f1155bf2304 CR3: 000000002b9f2000 CR4: 0000000000350ef0
+Call Trace:
+ <TASK>
+ tcp_recvmsg_locked+0x106d/0x25a0 net/ipv4/tcp.c:2513
+ tcp_recvmsg+0x25d/0x920 net/ipv4/tcp.c:2578
+ inet6_recvmsg+0x16a/0x730 net/ipv6/af_inet6.c:680
+ sock_recvmsg_nosec net/socket.c:1046 [inline]
+ sock_recvmsg+0x109/0x280 net/socket.c:1068
+ ____sys_recvmsg+0x1db/0x470 net/socket.c:2803
+ ___sys_recvmsg net/socket.c:2845 [inline]
+ do_recvmmsg+0x474/0xae0 net/socket.c:2939
+ __sys_recvmmsg net/socket.c:3018 [inline]
+ __do_sys_recvmmsg net/socket.c:3041 [inline]
+ __se_sys_recvmmsg net/socket.c:3034 [inline]
+ __x64_sys_recvmmsg+0x199/0x250 net/socket.c:3034
+ do_syscall_x64 arch/x86/entry/common.c:52 [inline]
+ do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83
+ entry_SYSCALL_64_after_hwframe+0x77/0x7f
+RIP: 0033:0x7faeb6363db9
+Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 c1 17 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
+RSP: 002b:00007ffcc1997168 EFLAGS: 00000246 ORIG_RAX: 000000000000012b
+RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007faeb6363db9
+RDX: 0000000000000001 RSI: 0000000020000bc0 RDI: 0000000000000005
+RBP: 0000000000000000 R08: 0000000000000000 R09: 000000000000001c
+R10: 0000000000000122 R11: 0000000000000246 R12: 0000000000000000
+R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000001
+
+Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
+Reported-by: syzbot <syzkaller@googlegroups.com>
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Acked-by: Neal Cardwell <ncardwell@google.com>
+Link: https://lore.kernel.org/r/20240501125448.896529-1-edumazet@google.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/ipv4/tcp.c | 4 ++--
+ net/ipv4/tcp_input.c | 2 ++
+ net/ipv4/tcp_output.c | 4 +++-
+ 3 files changed, 7 insertions(+), 3 deletions(-)
+
+diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
+index f8df35f7352a5..7bf774bdb9386 100644
+--- a/net/ipv4/tcp.c
++++ b/net/ipv4/tcp.c
+@@ -2710,7 +2710,7 @@ void tcp_shutdown(struct sock *sk, int how)
+ /* If we've already sent a FIN, or it's a closed state, skip this. */
+ if ((1 << sk->sk_state) &
+ (TCPF_ESTABLISHED | TCPF_SYN_SENT |
+- TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) {
++ TCPF_CLOSE_WAIT)) {
+ /* Clear out any half completed packets. FIN if needed. */
+ if (tcp_close_state(sk))
+ tcp_send_fin(sk);
+@@ -2819,7 +2819,7 @@ void __tcp_close(struct sock *sk, long timeout)
+ * machine. State transitions:
+ *
+ * TCP_ESTABLISHED -> TCP_FIN_WAIT1
+- * TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible)
++ * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult)
+ * TCP_CLOSE_WAIT -> TCP_LAST_ACK
+ *
+ * are legal only when FIN has been sent (i.e. in window),
+diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
+index e6c4929549428..f938442b202d7 100644
+--- a/net/ipv4/tcp_input.c
++++ b/net/ipv4/tcp_input.c
+@@ -6627,6 +6627,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
+
+ tcp_initialize_rcv_mss(sk);
+ tcp_fast_path_on(tp);
++ if (sk->sk_shutdown & SEND_SHUTDOWN)
++ tcp_shutdown(sk, SEND_SHUTDOWN);
+ break;
+
+ case TCP_FIN_WAIT1: {
+diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
+index ab3b7b4b4429b..5631041ae12cb 100644
+--- a/net/ipv4/tcp_output.c
++++ b/net/ipv4/tcp_output.c
+@@ -3533,7 +3533,9 @@ void tcp_send_fin(struct sock *sk)
+ return;
+ }
+ } else {
+- skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
++ skb = alloc_skb_fclone(MAX_TCP_HEADER,
++ sk_gfp_mask(sk, GFP_ATOMIC |
++ __GFP_NOWARN));
+ if (unlikely(!skb))
+ return;
+
+--
+2.43.0
+
--- /dev/null
+From a33abf620608b922d8af369143700d9633432e14 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 1 May 2024 14:31:45 -0700
+Subject: tcp: Use refcount_inc_not_zero() in tcp_twsk_unique().
+
+From: Kuniyuki Iwashima <kuniyu@amazon.com>
+
+[ Upstream commit f2db7230f73a80dbb179deab78f88a7947f0ab7e ]
+
+Anderson Nascimento reported a use-after-free splat in tcp_twsk_unique()
+with nice analysis.
+
+Since commit ec94c2696f0b ("tcp/dccp: avoid one atomic operation for
+timewait hashdance"), inet_twsk_hashdance() sets TIME-WAIT socket's
+sk_refcnt after putting it into ehash and releasing the bucket lock.
+
+Thus, there is a small race window where other threads could try to
+reuse the port during connect() and call sock_hold() in tcp_twsk_unique()
+for the TIME-WAIT socket with zero refcnt.
+
+If that happens, the refcnt taken by tcp_twsk_unique() is overwritten
+and sock_put() will cause underflow, triggering a real use-after-free
+somewhere else.
+
+To avoid the use-after-free, we need to use refcount_inc_not_zero() in
+tcp_twsk_unique() and give up on reusing the port if it returns false.
+
+[0]:
+refcount_t: addition on 0; use-after-free.
+WARNING: CPU: 0 PID: 1039313 at lib/refcount.c:25 refcount_warn_saturate+0xe5/0x110
+CPU: 0 PID: 1039313 Comm: trigger Not tainted 6.8.6-200.fc39.x86_64 #1
+Hardware name: VMware, Inc. VMware20,1/440BX Desktop Reference Platform, BIOS VMW201.00V.21805430.B64.2305221830 05/22/2023
+RIP: 0010:refcount_warn_saturate+0xe5/0x110
+Code: 42 8e ff 0f 0b c3 cc cc cc cc 80 3d aa 13 ea 01 00 0f 85 5e ff ff ff 48 c7 c7 f8 8e b7 82 c6 05 96 13 ea 01 01 e8 7b 42 8e ff <0f> 0b c3 cc cc cc cc 48 c7 c7 50 8f b7 82 c6 05 7a 13 ea 01 01 e8
+RSP: 0018:ffffc90006b43b60 EFLAGS: 00010282
+RAX: 0000000000000000 RBX: ffff888009bb3ef0 RCX: 0000000000000027
+RDX: ffff88807be218c8 RSI: 0000000000000001 RDI: ffff88807be218c0
+RBP: 0000000000069d70 R08: 0000000000000000 R09: ffffc90006b439f0
+R10: ffffc90006b439e8 R11: 0000000000000003 R12: ffff8880029ede84
+R13: 0000000000004e20 R14: ffffffff84356dc0 R15: ffff888009bb3ef0
+FS: 00007f62c10926c0(0000) GS:ffff88807be00000(0000) knlGS:0000000000000000
+CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+CR2: 0000000020ccb000 CR3: 000000004628c005 CR4: 0000000000f70ef0
+PKRU: 55555554
+Call Trace:
+ <TASK>
+ ? refcount_warn_saturate+0xe5/0x110
+ ? __warn+0x81/0x130
+ ? refcount_warn_saturate+0xe5/0x110
+ ? report_bug+0x171/0x1a0
+ ? refcount_warn_saturate+0xe5/0x110
+ ? handle_bug+0x3c/0x80
+ ? exc_invalid_op+0x17/0x70
+ ? asm_exc_invalid_op+0x1a/0x20
+ ? refcount_warn_saturate+0xe5/0x110
+ tcp_twsk_unique+0x186/0x190
+ __inet_check_established+0x176/0x2d0
+ __inet_hash_connect+0x74/0x7d0
+ ? __pfx___inet_check_established+0x10/0x10
+ tcp_v4_connect+0x278/0x530
+ __inet_stream_connect+0x10f/0x3d0
+ inet_stream_connect+0x3a/0x60
+ __sys_connect+0xa8/0xd0
+ __x64_sys_connect+0x18/0x20
+ do_syscall_64+0x83/0x170
+ entry_SYSCALL_64_after_hwframe+0x78/0x80
+RIP: 0033:0x7f62c11a885d
+Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d a3 45 0c 00 f7 d8 64 89 01 48
+RSP: 002b:00007f62c1091e58 EFLAGS: 00000296 ORIG_RAX: 000000000000002a
+RAX: ffffffffffffffda RBX: 0000000020ccb004 RCX: 00007f62c11a885d
+RDX: 0000000000000010 RSI: 0000000020ccb000 RDI: 0000000000000003
+RBP: 00007f62c1091e90 R08: 0000000000000000 R09: 0000000000000000
+R10: 0000000000000000 R11: 0000000000000296 R12: 00007f62c10926c0
+R13: ffffffffffffff88 R14: 0000000000000000 R15: 00007ffe237885b0
+ </TASK>
+
+Fixes: ec94c2696f0b ("tcp/dccp: avoid one atomic operation for timewait hashdance")
+Reported-by: Anderson Nascimento <anderson@allelesecurity.com>
+Closes: https://lore.kernel.org/netdev/37a477a6-d39e-486b-9577-3463f655a6b7@allelesecurity.com/
+Suggested-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
+Reviewed-by: Eric Dumazet <edumazet@google.com>
+Link: https://lore.kernel.org/r/20240501213145.62261-1-kuniyu@amazon.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/ipv4/tcp_ipv4.c | 8 +++++++-
+ 1 file changed, 7 insertions(+), 1 deletion(-)
+
+diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
+index c7ffab37a34cd..c464ced7137ee 100644
+--- a/net/ipv4/tcp_ipv4.c
++++ b/net/ipv4/tcp_ipv4.c
+@@ -154,6 +154,12 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
+ if (tcptw->tw_ts_recent_stamp &&
+ (!twp || (reuse && time_after32(ktime_get_seconds(),
+ tcptw->tw_ts_recent_stamp)))) {
++ /* inet_twsk_hashdance() sets sk_refcnt after putting twsk
++ * and releasing the bucket lock.
++ */
++ if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt)))
++ return 0;
++
+ /* In case of repair and re-using TIME-WAIT sockets we still
+ * want to be sure that it is safe as above but honor the
+ * sequence numbers and time stamps set as part of the repair
+@@ -174,7 +180,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
+ tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
+ tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+ }
+- sock_hold(sktw);
++
+ return 1;
+ }
+
+--
+2.43.0
+
--- /dev/null
+From 61cf6047a620ec0b06ad1fa0b55a6e9f97d47f3f Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 23 Apr 2024 18:00:24 +1200
+Subject: xfrm: Preserve vlan tags for transport mode software GRO
+
+From: Paul Davey <paul.davey@alliedtelesis.co.nz>
+
+[ Upstream commit 58fbfecab965014b6e3cc956a76b4a96265a1add ]
+
+The software GRO path for esp transport mode uses skb_mac_header_rebuild
+prior to re-injecting the packet via the xfrm_napi_dev. This only
+copies skb->mac_len bytes of header which may not be sufficient if the
+packet contains 802.1Q tags or other VLAN tags. Worse copying only the
+initial header will leave a packet marked as being VLAN tagged but
+without the corresponding tag leading to mangling when it is later
+untagged.
+
+The VLAN tags are important when receiving the decrypted esp transport
+mode packet after GRO processing to ensure it is received on the correct
+interface.
+
+Therefore record the full mac header length in xfrm*_transport_input for
+later use in corresponding xfrm*_transport_finish to copy the entire mac
+header when rebuilding the mac header for GRO. The skb->data pointer is
+left pointing skb->mac_header bytes after the start of the mac header as
+is expected by the network stack and network and transport header
+offsets reset to this location.
+
+Fixes: 7785bba299a8 ("esp: Add a software GRO codepath")
+Signed-off-by: Paul Davey <paul.davey@alliedtelesis.co.nz>
+Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ include/linux/skbuff.h | 15 +++++++++++++++
+ include/net/xfrm.h | 3 +++
+ net/ipv4/xfrm4_input.c | 6 +++++-
+ net/ipv6/xfrm6_input.c | 6 +++++-
+ net/xfrm/xfrm_input.c | 8 ++++++++
+ 5 files changed, 36 insertions(+), 2 deletions(-)
+
+diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
+index 7d54808a1e8f9..5f11f98733419 100644
+--- a/include/linux/skbuff.h
++++ b/include/linux/skbuff.h
+@@ -2962,6 +2962,21 @@ static inline void skb_mac_header_rebuild(struct sk_buff *skb)
+ }
+ }
+
++/* Move the full mac header up to current network_header.
++ * Leaves skb->data pointing at offset skb->mac_len into the mac_header.
++ * Must be provided the complete mac header length.
++ */
++static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len)
++{
++ if (skb_mac_header_was_set(skb)) {
++ const unsigned char *old_mac = skb_mac_header(skb);
++
++ skb_set_mac_header(skb, -full_mac_len);
++ memmove(skb_mac_header(skb), old_mac, full_mac_len);
++ __skb_push(skb, full_mac_len - skb->mac_len);
++ }
++}
++
+ static inline int skb_checksum_start_offset(const struct sk_buff *skb)
+ {
+ return skb->csum_start - skb_headroom(skb);
+diff --git a/include/net/xfrm.h b/include/net/xfrm.h
+index 363c7d5105542..a3fd2cfed5e33 100644
+--- a/include/net/xfrm.h
++++ b/include/net/xfrm.h
+@@ -1047,6 +1047,9 @@ struct xfrm_offload {
+ #define CRYPTO_INVALID_PACKET_SYNTAX 64
+ #define CRYPTO_INVALID_PROTOCOL 128
+
++ /* Used to keep whole l2 header for transport mode GRO */
++ __u32 orig_mac_len;
++
+ __u8 proto;
+ __u8 inner_ipproto;
+ };
+diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
+index 183f6dc372429..f6e90ba50b639 100644
+--- a/net/ipv4/xfrm4_input.c
++++ b/net/ipv4/xfrm4_input.c
+@@ -61,7 +61,11 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
+ ip_send_check(iph);
+
+ if (xo && (xo->flags & XFRM_GRO)) {
+- skb_mac_header_rebuild(skb);
++ /* The full l2 header needs to be preserved so that re-injecting the packet at l2
++ * works correctly in the presence of vlan tags.
++ */
++ skb_mac_header_rebuild_full(skb, xo->orig_mac_len);
++ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+ return 0;
+ }
+diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
+index 4156387248e40..8432b50d9ce4c 100644
+--- a/net/ipv6/xfrm6_input.c
++++ b/net/ipv6/xfrm6_input.c
+@@ -56,7 +56,11 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
+ skb_postpush_rcsum(skb, skb_network_header(skb), nhlen);
+
+ if (xo && (xo->flags & XFRM_GRO)) {
+- skb_mac_header_rebuild(skb);
++ /* The full l2 header needs to be preserved so that re-injecting the packet at l2
++ * works correctly in the presence of vlan tags.
++ */
++ skb_mac_header_rebuild_full(skb, xo->orig_mac_len);
++ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+ return 0;
+ }
+diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
+index d5ee96789d4bf..0c08bac3ed269 100644
+--- a/net/xfrm/xfrm_input.c
++++ b/net/xfrm/xfrm_input.c
+@@ -388,11 +388,15 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
+ */
+ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
+ {
++ struct xfrm_offload *xo = xfrm_offload(skb);
+ int ihl = skb->data - skb_transport_header(skb);
+
+ if (skb->transport_header != skb->network_header) {
+ memmove(skb_transport_header(skb),
+ skb_network_header(skb), ihl);
++ if (xo)
++ xo->orig_mac_len =
++ skb_mac_header_was_set(skb) ? skb_mac_header_len(skb) : 0;
+ skb->network_header = skb->transport_header;
+ }
+ ip_hdr(skb)->tot_len = htons(skb->len + ihl);
+@@ -403,11 +407,15 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
+ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
+ {
+ #if IS_ENABLED(CONFIG_IPV6)
++ struct xfrm_offload *xo = xfrm_offload(skb);
+ int ihl = skb->data - skb_transport_header(skb);
+
+ if (skb->transport_header != skb->network_header) {
+ memmove(skb_transport_header(skb),
+ skb_network_header(skb), ihl);
++ if (xo)
++ xo->orig_mac_len =
++ skb_mac_header_was_set(skb) ? skb_mac_header_len(skb) : 0;
+ skb->network_header = skb->transport_header;
+ }
+ ipv6_hdr(skb)->payload_len = htons(skb->len + ihl -
+--
+2.43.0
+
projects / thirdparty / kernel / stable-queue.git / commitdiff
