From b506668613ef9138cac7479a5dd47559835b6552 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Jan 2025 07:52:36 -0800 Subject: [PATCH 01/16] MAINTAINERS: update maintainers for Microchip LAN78xx Woojung Huh seems to have only replied to the list 35 times in the last 5 years, and didn't provide any reviews in 3 years. The LAN78XX driver has seen quite a bit of activity lately. gitdm missingmaints says: Subsystem USB LAN78XX ETHERNET DRIVER Changes 35 / 91 (38%) (No activity) Top reviewers: [23]: andrew@lunn.ch [3]: horms@kernel.org [2]: mateusz.polchlopek@intel.com INACTIVE MAINTAINER Woojung Huh Move Woojung to CREDITS and add new maintainers who are more likely to review LAN78xx patches. Acked-by: Woojung Huh Acked-by: Rengarajan Sundararajan Link: https://patch.msgid.link/20250108155242.2575530-3-kuba@kernel.org Signed-off-by: Jakub Kicinski --- CREDITS | 4 ++++ MAINTAINERS | 3 ++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/CREDITS b/CREDITS index 2a5f5f49269f..7a5332907ef0 100644 --- a/CREDITS +++ b/CREDITS @@ -1816,6 +1816,10 @@ D: Author/maintainer of most DRM drivers (especially ATI, MGA) D: Core DRM templates, general DRM and 3D-related hacking S: No fixed address +N: Woojung Huh +E: woojung.huh@microchip.com +D: Microchip LAN78XX USB Ethernet driver + N: Kenn Humborg E: kenn@wombat.ie D: Mods to loop device to support sparse backing files diff --git a/MAINTAINERS b/MAINTAINERS index d92c8cd9f805..58fb3c81c735 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -24252,7 +24252,8 @@ F: Documentation/devicetree/bindings/usb/nxp,isp1760.yaml F: drivers/usb/isp1760/* USB LAN78XX ETHERNET DRIVER -M: Woojung Huh +M: Thangaraj Samynathan +M: Rengarajan Sundararajan M: UNGLinuxDriver@microchip.com L: netdev@vger.kernel.org S: Maintained -- 2.51.0 From e049fb86d39139050bb792b17ef86c3918cc8068 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Jan 2025 07:52:37 -0800 Subject: [PATCH 02/16] MAINTAINERS: remove Andy Gospodarek from bonding Andy does not participate much in bonding reviews, unfortunately. Move him to CREDITS. gitdm missingmaint says: Subsystem BONDING DRIVER Changes 149 / 336 (44%) Last activity: 2024-09-05 Jay Vosburgh : Tags 68db604e16d5 2024-09-05 00:00:00 8 Andy Gospodarek : Top reviewers: [65]: jay.vosburgh@canonical.com [23]: liuhangbin@gmail.com [16]: razor@blackwall.org INACTIVE MAINTAINER Andy Gospodarek Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/20250108155242.2575530-4-kuba@kernel.org Signed-off-by: Jakub Kicinski --- CREDITS | 4 ++++ MAINTAINERS | 1 - 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/CREDITS b/CREDITS index 7a5332907ef0..cda68f04d5f1 100644 --- a/CREDITS +++ b/CREDITS @@ -1432,6 +1432,10 @@ S: 8124 Constitution Apt. 7 S: Sterling Heights, Michigan 48313 S: USA +N: Andy Gospodarek +E: andy@greyhouse.net +D: Maintenance and contributions to the network interface bonding driver. + N: Wolfgang Grandegger E: wg@grandegger.com D: Controller Area Network (device drivers) diff --git a/MAINTAINERS b/MAINTAINERS index 58fb3c81c735..c518bda0215f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4058,7 +4058,6 @@ F: net/bluetooth/ BONDING DRIVER M: Jay Vosburgh -M: Andy Gospodarek L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/bonding.rst -- 2.51.0 From 03868822c553e549ac5c28781c29f80bddee5487 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Jan 2025 07:52:38 -0800 Subject: [PATCH 03/16] MAINTAINERS: mark stmmac ethernet as an Orphan I tried a couple of things to reinvigorate the stmmac maintainers over the last few years but with little effect. The maintainers are not active, let the MAINTAINERS file reflect reality. The Synopsys IP this driver supports is very popular we need a solid maintainer to deal with the complexity of the driver. gitdm missingmaints says: Subsystem STMMAC ETHERNET DRIVER Changes 344 / 978 (35%) Last activity: 2020-05-01 Alexandre Torgue : Tags 1bb694e20839 2020-05-01 00:00:00 1 Jose Abreu : Top reviewers: [75]: horms@kernel.org [49]: andrew@lunn.ch [46]: fancer.lancer@gmail.com INACTIVE MAINTAINER Jose Abreu Acked-by: Alexandre Torgue Link: https://patch.msgid.link/20250108155242.2575530-5-kuba@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index c518bda0215f..955092ed27d6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22500,11 +22500,8 @@ F: Documentation/devicetree/bindings/phy/st,stm32mp25-combophy.yaml F: drivers/phy/st/phy-stm32-combophy.c STMMAC ETHERNET DRIVER -M: Alexandre Torgue -M: Jose Abreu L: netdev@vger.kernel.org -S: Supported -W: http://www.stlinux.com +S: Orphan F: Documentation/networking/device_drivers/ethernet/stmicro/ F: drivers/net/ethernet/stmicro/stmmac/ -- 2.51.0 From 9d7b1191d030bb0f6932722755b1103a2207421d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Jan 2025 07:52:39 -0800 Subject: [PATCH 04/16] MAINTAINERS: remove Mark Lee from MediaTek Ethernet The mailing lists have seen no email from Mark Lee in the last 4 years. gitdm missingmaints says: Subsystem MEDIATEK ETHERNET DRIVER Changes 103 / 400 (25%) Last activity: 2024-12-19 Felix Fietkau : Author 88806efc034a 2024-10-17 00:00:00 44 Tags 88806efc034a 2024-10-17 00:00:00 51 Sean Wang : Tags a5d75538295b 2020-04-07 00:00:00 1 Mark Lee : Lorenzo Bianconi : Author 0c7469ee718e 2024-12-19 00:00:00 123 Tags 0c7469ee718e 2024-12-19 00:00:00 139 Top reviewers: [32]: horms@kernel.org [15]: leonro@nvidia.com [9]: andrew@lunn.ch INACTIVE MAINTAINER Mark Lee Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250108155242.2575530-6-kuba@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 955092ed27d6..82157f7e01e4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14565,7 +14565,6 @@ F: drivers/dma/mediatek/ MEDIATEK ETHERNET DRIVER M: Felix Fietkau M: Sean Wang -M: Mark Lee M: Lorenzo Bianconi L: netdev@vger.kernel.org S: Maintained -- 2.51.0 From d4782fbab1c06fe1a3b1e064d2d6efd3e281e805 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Jan 2025 07:52:40 -0800 Subject: [PATCH 05/16] MAINTAINERS: remove Ying Xue from TIPC There is a steady stream of fixes for TIPC, even tho the development has slowed down a lot. Over last 2 years we have merged almost 70 TIPC patches, but we haven't heard from Ying Xue once: Subsystem TIPC NETWORK LAYER Changes 42 / 69 (60%) Last activity: 2023-10-04 Jon Maloy : Tags 08e50cf07184 2023-10-04 00:00:00 6 Ying Xue : Top reviewers: [9]: horms@kernel.org [8]: tung.q.nguyen@dektech.com.au [4]: jiri@nvidia.com [3]: tung.q.nguyen@endava.com [2]: kuniyu@amazon.com INACTIVE MAINTAINER Ying Xue Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250108155242.2575530-7-kuba@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 82157f7e01e4..b060b1fe8762 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -23641,7 +23641,6 @@ F: tools/testing/selftests/timers/ TIPC NETWORK LAYER M: Jon Maloy -M: Ying Xue L: netdev@vger.kernel.org (core kernel code) L: tipc-discussion@lists.sourceforge.net (user apps, general discussion) S: Maintained -- 2.51.0 From d95e2cc737017de537fc07cfc7d59307182bd0bc Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Jan 2025 07:52:41 -0800 Subject: [PATCH 06/16] MAINTAINERS: remove Noam Dagan from AMAZON ETHERNET Noam Dagan was added to ENA reviewers in 2021, we have not seen a single email from this person to any list, ever (according to lore). Git history mentions the name in 2 SoB tags from 2020. Acked-by: Arthur Kiyanovski Link: https://patch.msgid.link/20250108155242.2575530-8-kuba@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index b060b1fe8762..4996219d95b2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -949,7 +949,6 @@ AMAZON ETHERNET DRIVERS M: Shay Agroskin M: Arthur Kiyanovski R: David Arinzon -R: Noam Dagan R: Saeed Bishara L: netdev@vger.kernel.org S: Supported -- 2.51.0 From d9e03c6ffc4cd92c99418afc970ea8c8c53c66a8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 Jan 2025 07:52:42 -0800 Subject: [PATCH 07/16] MAINTAINERS: remove Lars Povlsen from Microchip Sparx5 SoC We have not seen emails or tags from Lars in almost 4 years. Steen and Daniel are pretty active, but the review coverage isn't stellar (35% of changes go in without a review tag). Subsystem ARM/Microchip Sparx5 SoC support Changes 28 / 79 (35%) Last activity: 2024-11-24 Lars Povlsen : Steen Hegelund : Tags 6c7c4b91aa43 2024-04-08 00:00:00 15 Daniel Machon : Author 48ba00da2eb4 2024-04-09 00:00:00 2 Tags f164b296638d 2024-11-24 00:00:00 6 Top reviewers: [7]: horms@kernel.org [1]: jacob.e.keller@intel.com [1]: jensemil.schulzostergaard@microchip.com [1]: horatiu.vultur@microchip.com INACTIVE MAINTAINER Lars Povlsen Acked-by: Daniel Machon Link: https://patch.msgid.link/20250108155242.2575530-9-kuba@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 4996219d95b2..4e93a00df185 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2689,7 +2689,6 @@ N: at91 N: atmel ARM/Microchip Sparx5 SoC support -M: Lars Povlsen M: Steen Hegelund M: Daniel Machon M: UNGLinuxDriver@microchip.com -- 2.51.0 From 771ec78dc8b48d562e6015bb535ed3cd37043d78 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Wed, 8 Jan 2025 16:34:29 +0100 Subject: [PATCH 08/16] mptcp: sysctl: avail sched: remove write access 'net.mptcp.available_schedulers' sysctl knob is there to list available schedulers, not to modify this list. There are then no reasons to give write access to it. Nothing would have been written anyway, but no errors would have been returned, which is unexpected. Fixes: 73c900aa3660 ("mptcp: add net.mptcp.available_schedulers") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250108-net-sysctl-current-nsproxy-v1-1-5df34b2083e8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/ctrl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 38d8121331d4..d9b57fab2a13 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -228,7 +228,7 @@ static struct ctl_table mptcp_sysctl_table[] = { { .procname = "available_schedulers", .maxlen = MPTCP_SCHED_BUF_MAX, - .mode = 0644, + .mode = 0444, .proc_handler = proc_available_schedulers, }, { -- 2.51.0 From d38e26e36206ae3d544d496513212ae931d1da0a Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Wed, 8 Jan 2025 16:34:30 +0100 Subject: [PATCH 09/16] mptcp: sysctl: sched: avoid using current->nsproxy Using the 'net' structure via 'current' is not recommended for different reasons. First, if the goal is to use it to read or write per-netns data, this is inconsistent with how the "generic" sysctl entries are doing: directly by only using pointers set to the table entry, e.g. table->data. Linked to that, the per-netns data should always be obtained from the table linked to the netns it had been created for, which may not coincide with the reader's or writer's netns. Another reason is that access to current->nsproxy->netns can oops if attempted when current->nsproxy had been dropped when the current task is exiting. This is what syzbot found, when using acct(2): Oops: general protection fault, probably for non-canonical address 0xdffffc0000000005: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000028-0x000000000000002f] CPU: 1 UID: 0 PID: 5924 Comm: syz-executor Not tainted 6.13.0-rc5-syzkaller-00004-gccb98ccef0e5 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 RIP: 0010:proc_scheduler+0xc6/0x3c0 net/mptcp/ctrl.c:125 Code: 03 42 80 3c 38 00 0f 85 fe 02 00 00 4d 8b a4 24 08 09 00 00 48 b8 00 00 00 00 00 fc ff df 49 8d 7c 24 28 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 cc 02 00 00 4d 8b 7c 24 28 48 8d 84 24 c8 00 00 RSP: 0018:ffffc900034774e8 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: 1ffff9200068ee9e RCX: ffffc90003477620 RDX: 0000000000000005 RSI: ffffffff8b08f91e RDI: 0000000000000028 RBP: 0000000000000001 R08: ffffc90003477710 R09: 0000000000000040 R10: 0000000000000040 R11: 00000000726f7475 R12: 0000000000000000 R13: ffffc90003477620 R14: ffffc90003477710 R15: dffffc0000000000 FS: 0000000000000000(0000) GS:ffff8880b8700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fee3cd452d8 CR3: 000000007d116000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: proc_sys_call_handler+0x403/0x5d0 fs/proc/proc_sysctl.c:601 __kernel_write_iter+0x318/0xa80 fs/read_write.c:612 __kernel_write+0xf6/0x140 fs/read_write.c:632 do_acct_process+0xcb0/0x14a0 kernel/acct.c:539 acct_pin_kill+0x2d/0x100 kernel/acct.c:192 pin_kill+0x194/0x7c0 fs/fs_pin.c:44 mnt_pin_kill+0x61/0x1e0 fs/fs_pin.c:81 cleanup_mnt+0x3ac/0x450 fs/namespace.c:1366 task_work_run+0x14e/0x250 kernel/task_work.c:239 exit_task_work include/linux/task_work.h:43 [inline] do_exit+0xad8/0x2d70 kernel/exit.c:938 do_group_exit+0xd3/0x2a0 kernel/exit.c:1087 get_signal+0x2576/0x2610 kernel/signal.c:3017 arch_do_signal_or_restart+0x90/0x7e0 arch/x86/kernel/signal.c:337 exit_to_user_mode_loop kernel/entry/common.c:111 [inline] exit_to_user_mode_prepare include/linux/entry-common.h:329 [inline] __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline] syscall_exit_to_user_mode+0x150/0x2a0 kernel/entry/common.c:218 do_syscall_64+0xda/0x250 arch/x86/entry/common.c:89 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fee3cb87a6a Code: Unable to access opcode bytes at 0x7fee3cb87a40. RSP: 002b:00007fffcccac688 EFLAGS: 00000202 ORIG_RAX: 0000000000000037 RAX: 0000000000000000 RBX: 00007fffcccac710 RCX: 00007fee3cb87a6a RDX: 0000000000000041 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 0000000000000003 R08: 00007fffcccac6ac R09: 00007fffcccacac7 R10: 00007fffcccac710 R11: 0000000000000202 R12: 00007fee3cd49500 R13: 00007fffcccac6ac R14: 0000000000000000 R15: 00007fee3cd4b000 Modules linked in: ---[ end trace 0000000000000000 ]--- RIP: 0010:proc_scheduler+0xc6/0x3c0 net/mptcp/ctrl.c:125 Code: 03 42 80 3c 38 00 0f 85 fe 02 00 00 4d 8b a4 24 08 09 00 00 48 b8 00 00 00 00 00 fc ff df 49 8d 7c 24 28 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 cc 02 00 00 4d 8b 7c 24 28 48 8d 84 24 c8 00 00 RSP: 0018:ffffc900034774e8 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: 1ffff9200068ee9e RCX: ffffc90003477620 RDX: 0000000000000005 RSI: ffffffff8b08f91e RDI: 0000000000000028 RBP: 0000000000000001 R08: ffffc90003477710 R09: 0000000000000040 R10: 0000000000000040 R11: 00000000726f7475 R12: 0000000000000000 R13: ffffc90003477620 R14: ffffc90003477710 R15: dffffc0000000000 FS: 0000000000000000(0000) GS:ffff8880b8700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fee3cd452d8 CR3: 000000007d116000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 ---------------- Code disassembly (best guess), 1 bytes skipped: 0: 42 80 3c 38 00 cmpb $0x0,(%rax,%r15,1) 5: 0f 85 fe 02 00 00 jne 0x309 b: 4d 8b a4 24 08 09 00 mov 0x908(%r12),%r12 12: 00 13: 48 b8 00 00 00 00 00 movabs $0xdffffc0000000000,%rax 1a: fc ff df 1d: 49 8d 7c 24 28 lea 0x28(%r12),%rdi 22: 48 89 fa mov %rdi,%rdx 25: 48 c1 ea 03 shr $0x3,%rdx * 29: 80 3c 02 00 cmpb $0x0,(%rdx,%rax,1) <-- trapping instruction 2d: 0f 85 cc 02 00 00 jne 0x2ff 33: 4d 8b 7c 24 28 mov 0x28(%r12),%r15 38: 48 rex.W 39: 8d .byte 0x8d 3a: 84 24 c8 test %ah,(%rax,%rcx,8) Here with 'net.mptcp.scheduler', the 'net' structure is not really needed, because the table->data already has a pointer to the current scheduler, the only thing needed from the per-netns data. Simply use 'data', instead of getting (most of the time) the same thing, but from a longer and indirect way. Fixes: 6963c508fd7a ("mptcp: only allow set existing scheduler for net.mptcp.scheduler") Cc: stable@vger.kernel.org Reported-by: syzbot+e364f774c6f57f2c86d1@syzkaller.appspotmail.com Closes: https://lore.kernel.org/67769ecb.050a0220.3a8527.003f.GAE@google.com Suggested-by: Al Viro Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250108-net-sysctl-current-nsproxy-v1-2-5df34b2083e8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/ctrl.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index d9b57fab2a13..81c30aa02196 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -102,16 +102,15 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) } #ifdef CONFIG_SYSCTL -static int mptcp_set_scheduler(const struct net *net, const char *name) +static int mptcp_set_scheduler(char *scheduler, const char *name) { - struct mptcp_pernet *pernet = mptcp_get_pernet(net); struct mptcp_sched_ops *sched; int ret = 0; rcu_read_lock(); sched = mptcp_sched_find(name); if (sched) - strscpy(pernet->scheduler, name, MPTCP_SCHED_NAME_MAX); + strscpy(scheduler, name, MPTCP_SCHED_NAME_MAX); else ret = -ENOENT; rcu_read_unlock(); @@ -122,7 +121,7 @@ static int mptcp_set_scheduler(const struct net *net, const char *name) static int proc_scheduler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - const struct net *net = current->nsproxy->net_ns; + char (*scheduler)[MPTCP_SCHED_NAME_MAX] = ctl->data; char val[MPTCP_SCHED_NAME_MAX]; struct ctl_table tbl = { .data = val, @@ -130,11 +129,11 @@ static int proc_scheduler(const struct ctl_table *ctl, int write, }; int ret; - strscpy(val, mptcp_get_scheduler(net), MPTCP_SCHED_NAME_MAX); + strscpy(val, *scheduler, MPTCP_SCHED_NAME_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) - ret = mptcp_set_scheduler(net, val); + ret = mptcp_set_scheduler(*scheduler, val); return ret; } -- 2.51.0 From 92cf7a51bdae24a32c592adcdd59a773ae149289 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Wed, 8 Jan 2025 16:34:31 +0100 Subject: [PATCH 10/16] mptcp: sysctl: blackhole timeout: avoid using current->nsproxy As mentioned in the previous commit, using the 'net' structure via 'current' is not recommended for different reasons: - Inconsistency: getting info from the reader's/writer's netns vs only from the opener's netns. - current->nsproxy can be NULL in some cases, resulting in an 'Oops' (null-ptr-deref), e.g. when the current task is exiting, as spotted by syzbot [1] using acct(2). The 'pernet' structure can be obtained from the table->data using container_of(). Fixes: 27069e7cb3d1 ("mptcp: disable active MPTCP in case of blackhole") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/67769ecb.050a0220.3a8527.003f.GAE@google.com [1] Suggested-by: Al Viro Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250108-net-sysctl-current-nsproxy-v1-3-5df34b2083e8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/ctrl.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 81c30aa02196..b0dd008e2114 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -160,7 +160,9 @@ static int proc_blackhole_detect_timeout(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct mptcp_pernet *pernet = mptcp_get_pernet(current->nsproxy->net_ns); + struct mptcp_pernet *pernet = container_of(table->data, + struct mptcp_pernet, + blackhole_timeout); int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); -- 2.51.0 From ea62dd1383913b5999f3d16ae99d411f41b528d4 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Wed, 8 Jan 2025 16:34:32 +0100 Subject: [PATCH 11/16] sctp: sysctl: cookie_hmac_alg: avoid using current->nsproxy As mentioned in a previous commit of this series, using the 'net' structure via 'current' is not recommended for different reasons: - Inconsistency: getting info from the reader's/writer's netns vs only from the opener's netns. - current->nsproxy can be NULL in some cases, resulting in an 'Oops' (null-ptr-deref), e.g. when the current task is exiting, as spotted by syzbot [1] using acct(2). The 'net' structure can be obtained from the table->data using container_of(). Note that table->data could also be used directly, as this is the only member needed from the 'net' structure, but that would increase the size of this fix, to use '*data' everywhere 'net->sctp.sctp_hmac_alg' is used. Fixes: 3c68198e7511 ("sctp: Make hmac algorithm selection for cookie generation dynamic") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/67769ecb.050a0220.3a8527.003f.GAE@google.com [1] Suggested-by: Al Viro Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250108-net-sysctl-current-nsproxy-v1-4-5df34b2083e8@kernel.org Signed-off-by: Jakub Kicinski --- net/sctp/sysctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index e5a5af343c4c..9848d19630a4 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -387,7 +387,8 @@ static struct ctl_table sctp_net_table[] = { static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, + sctp.sctp_hmac_alg); struct ctl_table tbl; bool changed = false; char *none = "none"; -- 2.51.0 From 9fc17b76fc70763780aa78b38fcf4742384044a5 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Wed, 8 Jan 2025 16:34:33 +0100 Subject: [PATCH 12/16] sctp: sysctl: rto_min/max: avoid using current->nsproxy As mentioned in a previous commit of this series, using the 'net' structure via 'current' is not recommended for different reasons: - Inconsistency: getting info from the reader's/writer's netns vs only from the opener's netns. - current->nsproxy can be NULL in some cases, resulting in an 'Oops' (null-ptr-deref), e.g. when the current task is exiting, as spotted by syzbot [1] using acct(2). The 'net' structure can be obtained from the table->data using container_of(). Note that table->data could also be used directly, as this is the only member needed from the 'net' structure, but that would increase the size of this fix, to use '*data' everywhere 'net->sctp.rto_min/max' is used. Fixes: 4f3fdf3bc59c ("sctp: add check rto_min and rto_max in sysctl") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/67769ecb.050a0220.3a8527.003f.GAE@google.com [1] Suggested-by: Al Viro Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250108-net-sysctl-current-nsproxy-v1-5-5df34b2083e8@kernel.org Signed-off-by: Jakub Kicinski --- net/sctp/sysctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 9848d19630a4..a5285815264d 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -433,7 +433,7 @@ static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write, static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.rto_min); unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; struct ctl_table tbl; @@ -461,7 +461,7 @@ static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write, static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.rto_max); unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; struct ctl_table tbl; -- 2.51.0 From 15649fd5415eda664ef35780c2013adeb5d9c695 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Wed, 8 Jan 2025 16:34:34 +0100 Subject: [PATCH 13/16] sctp: sysctl: auth_enable: avoid using current->nsproxy As mentioned in a previous commit of this series, using the 'net' structure via 'current' is not recommended for different reasons: - Inconsistency: getting info from the reader's/writer's netns vs only from the opener's netns. - current->nsproxy can be NULL in some cases, resulting in an 'Oops' (null-ptr-deref), e.g. when the current task is exiting, as spotted by syzbot [1] using acct(2). The 'net' structure can be obtained from the table->data using container_of(). Note that table->data could also be used directly, but that would increase the size of this fix, while 'sctp.ctl_sock' still needs to be retrieved from 'net' structure. Fixes: b14878ccb7fa ("net: sctp: cache auth_enable per endpoint") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/67769ecb.050a0220.3a8527.003f.GAE@google.com [1] Suggested-by: Al Viro Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250108-net-sysctl-current-nsproxy-v1-6-5df34b2083e8@kernel.org Signed-off-by: Jakub Kicinski --- net/sctp/sysctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index a5285815264d..9d29611621fe 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -499,7 +499,7 @@ static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write, static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.auth_enable); struct ctl_table tbl; int new_value, ret; -- 2.51.0 From c10377bbc1972d858eaf0ab366a311b39f8ef1b6 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Wed, 8 Jan 2025 16:34:35 +0100 Subject: [PATCH 14/16] sctp: sysctl: udp_port: avoid using current->nsproxy As mentioned in a previous commit of this series, using the 'net' structure via 'current' is not recommended for different reasons: - Inconsistency: getting info from the reader's/writer's netns vs only from the opener's netns. - current->nsproxy can be NULL in some cases, resulting in an 'Oops' (null-ptr-deref), e.g. when the current task is exiting, as spotted by syzbot [1] using acct(2). The 'net' structure can be obtained from the table->data using container_of(). Note that table->data could also be used directly, but that would increase the size of this fix, while 'sctp.ctl_sock' still needs to be retrieved from 'net' structure. Fixes: 046c052b475e ("sctp: enable udp tunneling socks") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/67769ecb.050a0220.3a8527.003f.GAE@google.com [1] Suggested-by: Al Viro Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250108-net-sysctl-current-nsproxy-v1-7-5df34b2083e8@kernel.org Signed-off-by: Jakub Kicinski --- net/sctp/sysctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 9d29611621fe..18fa4f44e8ec 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -528,7 +528,7 @@ static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.udp_port); unsigned int min = *(unsigned int *)ctl->extra1; unsigned int max = *(unsigned int *)ctl->extra2; struct ctl_table tbl; -- 2.51.0 From 6259d2484d0ceff42245d1f09cc8cb6ee72d847a Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Wed, 8 Jan 2025 16:34:36 +0100 Subject: [PATCH 15/16] sctp: sysctl: plpmtud_probe_interval: avoid using current->nsproxy As mentioned in a previous commit of this series, using the 'net' structure via 'current' is not recommended for different reasons: - Inconsistency: getting info from the reader's/writer's netns vs only from the opener's netns. - current->nsproxy can be NULL in some cases, resulting in an 'Oops' (null-ptr-deref), e.g. when the current task is exiting, as spotted by syzbot [1] using acct(2). The 'net' structure can be obtained from the table->data using container_of(). Note that table->data could also be used directly, as this is the only member needed from the 'net' structure, but that would increase the size of this fix, to use '*data' everywhere 'net->sctp.probe_interval' is used. Fixes: d1e462a7a5f3 ("sctp: add probe_interval in sysctl and sock/asoc/transport") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/67769ecb.050a0220.3a8527.003f.GAE@google.com [1] Suggested-by: Al Viro Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250108-net-sysctl-current-nsproxy-v1-8-5df34b2083e8@kernel.org Signed-off-by: Jakub Kicinski --- net/sctp/sysctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 18fa4f44e8ec..8e1e97be4df7 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -569,7 +569,8 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, + sctp.probe_interval); struct ctl_table tbl; int ret, new_value; -- 2.51.0 From 7f5611cbc4871c7fb1ad36c2e5a9edad63dca95c Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Wed, 8 Jan 2025 16:34:37 +0100 Subject: [PATCH 16/16] rds: sysctl: rds_tcp_{rcv,snd}buf: avoid using current->nsproxy As mentioned in a previous commit of this series, using the 'net' structure via 'current' is not recommended for different reasons: - Inconsistency: getting info from the reader's/writer's netns vs only from the opener's netns. - current->nsproxy can be NULL in some cases, resulting in an 'Oops' (null-ptr-deref), e.g. when the current task is exiting, as spotted by syzbot [1] using acct(2). The per-netns structure can be obtained from the table->data using container_of(), then the 'net' one can be retrieved from the listen socket (if available). Fixes: c6a58ffed536 ("RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/67769ecb.050a0220.3a8527.003f.GAE@google.com [1] Suggested-by: Al Viro Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250108-net-sysctl-current-nsproxy-v1-9-5df34b2083e8@kernel.org Signed-off-by: Jakub Kicinski --- net/rds/tcp.c | 39 ++++++++++++++++++++++++++++++++------- 1 file changed, 32 insertions(+), 7 deletions(-) diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 351ac1747224..0581c53e6517 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -61,8 +61,10 @@ static atomic_t rds_tcp_unloading = ATOMIC_INIT(0); static struct kmem_cache *rds_tcp_conn_slab; -static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write, - void *buffer, size_t *lenp, loff_t *fpos); +static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos); +static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos); static int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF; static int rds_tcp_min_rcvbuf = SOCK_MIN_RCVBUF; @@ -74,7 +76,7 @@ static struct ctl_table rds_tcp_sysctl_table[] = { /* data is per-net pointer */ .maxlen = sizeof(int), .mode = 0644, - .proc_handler = rds_tcp_skbuf_handler, + .proc_handler = rds_tcp_sndbuf_handler, .extra1 = &rds_tcp_min_sndbuf, }, #define RDS_TCP_RCVBUF 1 @@ -83,7 +85,7 @@ static struct ctl_table rds_tcp_sysctl_table[] = { /* data is per-net pointer */ .maxlen = sizeof(int), .mode = 0644, - .proc_handler = rds_tcp_skbuf_handler, + .proc_handler = rds_tcp_rcvbuf_handler, .extra1 = &rds_tcp_min_rcvbuf, }, }; @@ -682,10 +684,10 @@ static void rds_tcp_sysctl_reset(struct net *net) spin_unlock_irq(&rds_tcp_conn_lock); } -static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write, +static int rds_tcp_skbuf_handler(struct rds_tcp_net *rtn, + const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *fpos) { - struct net *net = current->nsproxy->net_ns; int err; err = proc_dointvec_minmax(ctl, write, buffer, lenp, fpos); @@ -694,11 +696,34 @@ static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write, *(int *)(ctl->extra1)); return err; } - if (write) + + if (write && rtn->rds_tcp_listen_sock && rtn->rds_tcp_listen_sock->sk) { + struct net *net = sock_net(rtn->rds_tcp_listen_sock->sk); + rds_tcp_sysctl_reset(net); + } + return 0; } +static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos) +{ + struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net, + sndbuf_size); + + return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos); +} + +static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos) +{ + struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net, + rcvbuf_size); + + return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos); +} + static void rds_tcp_exit(void) { rds_tcp_set_unloading(); -- 2.51.0