January 2023 - Kernel - mailweb.openeuler.org

[PATCH openEuler-5.10-LTS-SP1 01/25] x86/nospec: Unwreck the RSB stuffing
by Jialin Zhang 31 Jan '23

31 Jan '23

From: Peter Zijlstra <peterz(a)infradead.org> stable inclusion from stable-v5.10.141 commit adee8f3082b01e5dab620d651e3ec75f57c0c855 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I685FC Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 4e3aa9238277597c6c7624f302d81a7b568b6f2d upstream. Commit 2b1299322016 ("x86/speculation: Add RSB VM Exit protections") made a right mess of the RSB stuffing, rewrite the whole thing to not suck. Thanks to Andrew for the enlightening comment about Post-Barrier RSB things so we can make this code less magical. Cc: stable(a)vger.kernel.org Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lkml.kernel.org/r/YvuNdDWoUZSBjYcm@worktop.programming.kicks-ass.net [bwh: Backported to 5.10: adjust context] Signed-off-by: Ben Hutchings <benh(a)debian.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> Reviewed-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- arch/x86/include/asm/nospec-branch.h | 80 ++++++++++++++-------------- 1 file changed, 39 insertions(+), 41 deletions(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index a406ca726f46..e847b4afe7ac 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -35,33 +35,44 @@ #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ /* + * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN. + */ +#define __FILL_RETURN_SLOT \ + ANNOTATE_INTRA_FUNCTION_CALL; \ + call 772f; \ + int3; \ +772: + +/* + * Stuff the entire RSB. + * * Google experimented with loop-unrolling and this turned out to be * the optimal version — two calls, each with their own speculation * trap should their return address end up getting used, in a loop. */ -#define __FILL_RETURN_BUFFER(reg, nr, sp) \ - mov $(nr/2), reg; \ -771: \ - ANNOTATE_INTRA_FUNCTION_CALL; \ - call 772f; \ -773: /* speculation trap */ \ - UNWIND_HINT_EMPTY; \ - pause; \ - lfence; \ - jmp 773b; \ -772: \ - ANNOTATE_INTRA_FUNCTION_CALL; \ - call 774f; \ -775: /* speculation trap */ \ - UNWIND_HINT_EMPTY; \ - pause; \ - lfence; \ - jmp 775b; \ -774: \ - add $(BITS_PER_LONG/8) * 2, sp; \ - dec reg; \ - jnz 771b; \ - /* barrier for jnz misprediction */ \ +#define __FILL_RETURN_BUFFER(reg, nr) \ + mov $(nr/2), reg; \ +771: \ + __FILL_RETURN_SLOT \ + __FILL_RETURN_SLOT \ + add $(BITS_PER_LONG/8) * 2, %_ASM_SP; \ + dec reg; \ + jnz 771b; \ + /* barrier for jnz misprediction */ \ + lfence; + +/* + * Stuff a single RSB slot. + * + * To mitigate Post-Barrier RSB speculation, one CALL instruction must be + * forced to retire before letting a RET instruction execute. + * + * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed + * before this point. + */ +#define __FILL_ONE_RETURN \ + __FILL_RETURN_SLOT \ + add $(BITS_PER_LONG/8), %_ASM_SP; \ lfence; #ifdef __ASSEMBLY__ @@ -120,28 +131,15 @@ #endif .endm -.macro ISSUE_UNBALANCED_RET_GUARD - ANNOTATE_INTRA_FUNCTION_CALL - call .Lunbalanced_ret_guard_\@ - int3 -.Lunbalanced_ret_guard_\@: - add $(BITS_PER_LONG/8), %_ASM_SP - lfence -.endm - /* * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP * monstrosity above, manually. */ -.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2 -.ifb \ftr2 - ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr -.else - ALTERNATIVE_2 "jmp .Lskip_rsb_\@", "", \ftr, "jmp .Lunbalanced_\@", \ftr2 -.endif - __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP) -.Lunbalanced_\@: - ISSUE_UNBALANCED_RET_GUARD +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS) + ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \ + __stringify(__FILL_ONE_RETURN), \ftr2 + .Lskip_rsb_\@: .endm -- 2.25.1

1 24

[PATCH openEuler-5.10-LTS 01/11] rndis_wlan: Prevent buffer overflow in rndis_query_oid
by Jialin Zhang 31 Jan '23

31 Jan '23

From: Szymon Heidrich <szymon.heidrich(a)gmail.com> maillist inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6AQJP CVE: CVE-2023-23559 Reference: https://patchwork.kernel.org/project/linux-wireless/patch/20230111175031.70… ------------------------------- Since resplen and respoffs are signed integers sufficiently large values of unsigned int len and offset members of RNDIS response will result in negative values of prior variables. This may be utilized to bypass implemented security checks to either extract memory contents by manipulating offset or overflow the data buffer via memcpy by manipulating both offset and len. Additionally assure that sum of resplen and respoffs does not overflow so buffer boundaries are kept. Fixes: 80f8c5b434f9 ("rndis_wlan: copy only useful data from rndis_command respond") Signed-off-by: Szymon Heidrich <szymon.heidrich(a)gmail.com> Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- drivers/net/wireless/rndis_wlan.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index 75b5d545b49e..dc076d844868 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -694,8 +694,8 @@ static int rndis_query_oid(struct usbnet *dev, u32 oid, void *data, int *len) struct rndis_query *get; struct rndis_query_c *get_c; } u; - int ret, buflen; - int resplen, respoffs, copylen; + int ret; + size_t buflen, resplen, respoffs, copylen; buflen = *len + sizeof(*u.get); if (buflen < CONTROL_BUFFER_SIZE) @@ -730,22 +730,15 @@ static int rndis_query_oid(struct usbnet *dev, u32 oid, void *data, int *len) if (respoffs > buflen) { /* Device returned data offset outside buffer, error. */ - netdev_dbg(dev->net, "%s(%s): received invalid " - "data offset: %d > %d\n", __func__, - oid_to_string(oid), respoffs, buflen); + netdev_dbg(dev->net, + "%s(%s): received invalid data offset: %zu > %zu\n", + __func__, oid_to_string(oid), respoffs, buflen); ret = -EINVAL; goto exit_unlock; } - if ((resplen + respoffs) > buflen) { - /* Device would have returned more data if buffer would - * have been big enough. Copy just the bits that we got. - */ - copylen = buflen - respoffs; - } else { - copylen = resplen; - } + copylen = min(resplen, buflen - respoffs); if (copylen > *len) copylen = *len; -- 2.25.1

1 10

[PATCH openEuler-5.10-LTS-SP1 01/11] mm/vmpressure: fix data-race with memcg->socket_pressure
by Jialin Zhang 31 Jan '23

31 Jan '23

From: Yuanzheng Song <songyuanzheng(a)huawei.com> mainline inclusion from mainline-v5.16-rc1 commit 7e6ec49c18988f1b8dab0677271dafde5f8d9a43 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6AW65 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- When reading memcg->socket_pressure in mem_cgroup_under_socket_pressure() and writing memcg->socket_pressure in vmpressure() at the same time, the following data-race occurs: BUG: KCSAN: data-race in __sk_mem_reduce_allocated / vmpressure write to 0xffff8881286f4938 of 8 bytes by task 24550 on cpu 3: vmpressure+0x218/0x230 mm/vmpressure.c:307 shrink_node_memcgs+0x2b9/0x410 mm/vmscan.c:2658 shrink_node+0x9d2/0x11d0 mm/vmscan.c:2769 shrink_zones+0x29f/0x470 mm/vmscan.c:2972 do_try_to_free_pages+0x193/0x6e0 mm/vmscan.c:3027 try_to_free_mem_cgroup_pages+0x1c0/0x3f0 mm/vmscan.c:3345 reclaim_high mm/memcontrol.c:2440 [inline] mem_cgroup_handle_over_high+0x18b/0x4d0 mm/memcontrol.c:2624 tracehook_notify_resume include/linux/tracehook.h:197 [inline] exit_to_user_mode_loop kernel/entry/common.c:164 [inline] exit_to_user_mode_prepare+0x110/0x170 kernel/entry/common.c:191 syscall_exit_to_user_mode+0x16/0x30 kernel/entry/common.c:266 ret_from_fork+0x15/0x30 arch/x86/entry/entry_64.S:289 read to 0xffff8881286f4938 of 8 bytes by interrupt on cpu 1: mem_cgroup_under_socket_pressure include/linux/memcontrol.h:1483 [inline] sk_under_memory_pressure include/net/sock.h:1314 [inline] __sk_mem_reduce_allocated+0x1d2/0x270 net/core/sock.c:2696 __sk_mem_reclaim+0x44/0x50 net/core/sock.c:2711 sk_mem_reclaim include/net/sock.h:1490 [inline] ...... net_rx_action+0x17a/0x480 net/core/dev.c:6864 __do_softirq+0x12c/0x2af kernel/softirq.c:298 run_ksoftirqd+0x13/0x20 kernel/softirq.c:653 smpboot_thread_fn+0x33f/0x510 kernel/smpboot.c:165 kthread+0x1fc/0x220 kernel/kthread.c:292 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:296 Fix it by using READ_ONCE() and WRITE_ONCE() to read and write memcg->socket_pressure. Link: https://lkml.kernel.org/r/20211025082843.671690-1-songyuanzheng@huawei.com Signed-off-by: Yuanzheng Song <songyuanzheng(a)huawei.com> Reviewed-by: Muchun Song <songmuchun(a)bytedance.com> Cc: Shakeel Butt <shakeelb(a)google.com> Cc: Roman Gushchin <guro(a)fb.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Alex Shi <alexs(a)kernel.org> Cc: Wei Yang <richard.weiyang(a)gmail.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Cai Xinchen <caixinchen1(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- include/linux/memcontrol.h | 2 +- mm/vmpressure.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index abb2476bd282..89e4f01c5710 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1921,7 +1921,7 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) return true; do { - if (time_before(jiffies, memcg->socket_pressure)) + if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; } while ((memcg = parent_mem_cgroup(memcg))); return false; diff --git a/mm/vmpressure.c b/mm/vmpressure.c index d69019fc3789..c6a7eca666f6 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -304,7 +304,7 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, * asserted for a second in which subsequent * pressure events can occur. */ - memcg->socket_pressure = jiffies + HZ; + WRITE_ONCE(memcg->socket_pressure, jiffies + HZ); } } } -- 2.25.1

1 10

[PATCH openEuler-1.0-LTS 1/3] lib/cmdline: avoid page fault in next_arg
by Yongqiang Liu 30 Jan '23

30 Jan '23

From: Neel Natu <neelnatu(a)google.com> mainline inclusion from mainline-v6.1-rc1 commit 9847f21225c4eb0b843cb2b72ed83b32edb1e6f2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6AXHU CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/… ----------------------------------------- An argument list like "arg=val arg2 \"" can trigger a page fault if the page pointed by 'args[0xffffffff]' is not mapped and potential memory corruption otherwise (unlikely but possible if the bogus address is mapped and contents happen to match the ascii value of the quote character). The fix is to ensure that we load 'args[i-1]' only when (i > 0). Prior to this commit the following command would trigger an unhandled page fault in the kernel: root@(none):/linus/fs/fat# insmod ./fat.ko "foo=bar \"" [ 33.870507] BUG: unable to handle page fault for address: ffff888204252608 [ 33.872180] #PF: supervisor read access in kernel mode [ 33.873414] #PF: error_code(0x0000) - not-present page [ 33.874650] PGD 4401067 P4D 4401067 PUD 0 [ 33.875321] Oops: 0000 [#1] SMP DEBUG_PAGEALLOC PTI [ 33.876113] CPU: 16 PID: 399 Comm: insmod Not tainted 5.19.0-dbg-DEV #4 [ 33.877193] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-debian-1.16.0-4 04/01/2014 [ 33.878739] RIP: 0010:next_arg+0xd1/0x110 [ 33.879399] Code: 22 75 1d 41 c6 04 01 00 41 80 f8 22 74 18 eb 35 4c 89 0e 45 31 d2 4c 89 cf 48 c7 02 00 00 00 00 41 80 f8 22 75 1f 41 8d 42 ff <41> 80 3c 01 22 75 14 41 c6 04 01 00 eb 0d 48 c7 02 00 00 00 00 41 [ 33.882338] RSP: 0018:ffffc90001253d08 EFLAGS: 00010246 [ 33.883174] RAX: 00000000ffffffff RBX: ffff888104252608 RCX: 0fc317bba1c1dd00 [ 33.884311] RDX: ffffc90001253d40 RSI: ffffc90001253d48 RDI: ffff888104252609 [ 33.885450] RBP: ffffc90001253d10 R08: 0000000000000022 R09: ffff888104252609 [ 33.886595] R10: 0000000000000000 R11: ffffffff82c7ff20 R12: 0000000000000282 [ 33.887748] R13: 00000000ffff8000 R14: 0000000000000000 R15: 0000000000007fff [ 33.888887] FS: 00007f04ec7432c0(0000) GS:ffff88813d300000(0000) knlGS:0000000000000000 [ 33.890183] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 33.891111] CR2: ffff888204252608 CR3: 0000000100f36005 CR4: 0000000000170ee0 [ 33.892241] Call Trace: [ 33.892641] <TASK> [ 33.892989] parse_args+0x8f/0x220 [ 33.893538] load_module+0x138b/0x15a0 [ 33.894149] ? prepare_coming_module+0x50/0x50 [ 33.894879] ? kernel_read_file_from_fd+0x5f/0x90 [ 33.895639] __se_sys_finit_module+0xce/0x130 [ 33.896342] __x64_sys_finit_module+0x1d/0x20 [ 33.897042] do_syscall_64+0x44/0xa0 [ 33.897622] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 33.898434] RIP: 0033:0x7f04ec85ef79 [ 33.899009] Code: 48 8d 3d da db 0d 00 0f 05 eb a5 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d c7 9e 0d 00 f7 d8 64 89 01 48 [ 33.901912] RSP: 002b:00007fffae81bfe8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 [ 33.903081] RAX: ffffffffffffffda RBX: 0000559c5f1d2640 RCX: 00007f04ec85ef79 [ 33.904191] RDX: 0000000000000000 RSI: 0000559c5f1d12a0 RDI: 0000000000000003 [ 33.905304] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 [ 33.906421] R10: 0000000000000003 R11: 0000000000000246 R12: 0000559c5f1d12a0 [ 33.907526] R13: 0000000000000000 R14: 0000559c5f1d25f0 R15: 0000559c5f1d12a0 [ 33.908631] </TASK> [ 33.908986] Modules linked in: fat(+) [last unloaded: fat] [ 33.909843] CR2: ffff888204252608 [ 33.910375] ---[ end trace 0000000000000000 ]--- [ 33.911172] RIP: 0010:next_arg+0xd1/0x110 [ 33.911796] Code: 22 75 1d 41 c6 04 01 00 41 80 f8 22 74 18 eb 35 4c 89 0e 45 31 d2 4c 89 cf 48 c7 02 00 00 00 00 41 80 f8 22 75 1f 41 8d 42 ff <41> 80 3c 01 22 75 14 41 c6 04 01 00 eb 0d 48 c7 02 00 00 00 00 41 [ 33.914643] RSP: 0018:ffffc90001253d08 EFLAGS: 00010246 [ 33.915446] RAX: 00000000ffffffff RBX: ffff888104252608 RCX: 0fc317bba1c1dd00 [ 33.916544] RDX: ffffc90001253d40 RSI: ffffc90001253d48 RDI: ffff888104252609 [ 33.917636] RBP: ffffc90001253d10 R08: 0000000000000022 R09: ffff888104252609 [ 33.918727] R10: 0000000000000000 R11: ffffffff82c7ff20 R12: 0000000000000282 [ 33.919821] R13: 00000000ffff8000 R14: 0000000000000000 R15: 0000000000007fff [ 33.920908] FS: 00007f04ec7432c0(0000) GS:ffff88813d300000(0000) knlGS:0000000000000000 [ 33.922125] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 33.923017] CR2: ffff888204252608 CR3: 0000000100f36005 CR4: 0000000000170ee0 [ 33.924098] Kernel panic - not syncing: Fatal exception [ 33.925776] Kernel Offset: disabled [ 33.926347] Rebooting in 10 seconds.. Link: https://lkml.kernel.org/r/20220728232434.1666488-1-neelnatu@google.com Signed-off-by: Neel Natu <neelnatu(a)google.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- lib/cmdline.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/cmdline.c b/lib/cmdline.c index 171c19b6888e..f32d76261cc1 100644 --- a/lib/cmdline.c +++ b/lib/cmdline.c @@ -233,7 +233,7 @@ char *next_arg(char *args, char **param, char **val) args[i-1] = '\0'; } } - if (quoted && args[i-1] == '"') + if (quoted && i > 0 && args[i-1] == '"') args[i-1] = '\0'; if (args[i]) { -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS 1/3] net: sched: atm: dont intepret cls results when asked to drop
by Yongqiang Liu 30 Jan '23

30 Jan '23

From: Jamal Hadi Salim <jhs(a)mojatatu.com> stable inclusion from stable-v4.19.269 commit 5374c455ebe6102e3d5f1842c6d8ff72b3ca659f category: bugfix bugzilla: 188250, https://gitee.com/src-openeuler/kernel/issues/I6AQG9 CVE: CVE-2023-23455 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a2965c7be0522eaa18808684b7b82b248515511b ] If asked to drop a packet via TC_ACT_SHOT it is unsafe to assume res.class contains a valid pointer Fixes: b0188d4dbe5f ("[NET_SCHED]: sch_atm: Lindent") Signed-off-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/sched/sch_atm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 91bd5c839303..a3084a12239e 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -394,10 +394,13 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, result = tcf_classify(skb, fl, &res, true); if (result < 0) continue; + if (result == TC_ACT_SHOT) + goto done; + flow = (struct atm_flow_data *)res.class; if (!flow) flow = lookup_flow(sch, res.classid); - goto done; + goto drop; } } flow = NULL; -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS 1/2] net: sched: cbq: dont intepret cls results when asked to drop
by Yongqiang Liu 29 Jan '23

29 Jan '23

From: Jamal Hadi Salim <jhs(a)mojatatu.com> mainline inclusion from mainline-v6.2-rc3 commit caa4b35b4317d5147b3ab0fbdc9c075c7d2e9c12 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6AQIL CVE: CVE-2023-23454 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- If asked to drop a packet via TC_ACT_SHOT it is unsafe to assume that res.class contains a valid pointer Sample splat reported by Kyle Zeng [ 5.405624] 0: reclassify loop, rule prio 0, protocol 800 [ 5.406326] ================================================================== [ 5.407240] BUG: KASAN: slab-out-of-bounds in cbq_enqueue+0x54b/0xea0 [ 5.407987] Read of size 1 at addr ffff88800e3122aa by task poc/299 [ 5.408731] [ 5.408897] CPU: 0 PID: 299 Comm: poc Not tainted 5.10.155+ #15 [ 5.409516] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [ 5.410439] Call Trace: [ 5.410764] dump_stack+0x87/0xcd [ 5.411153] print_address_description+0x7a/0x6b0 [ 5.411687] ? vprintk_func+0xb9/0xc0 [ 5.411905] ? printk+0x76/0x96 [ 5.412110] ? cbq_enqueue+0x54b/0xea0 [ 5.412323] kasan_report+0x17d/0x220 [ 5.412591] ? cbq_enqueue+0x54b/0xea0 [ 5.412803] __asan_report_load1_noabort+0x10/0x20 [ 5.413119] cbq_enqueue+0x54b/0xea0 [ 5.413400] ? __kasan_check_write+0x10/0x20 [ 5.413679] __dev_queue_xmit+0x9c0/0x1db0 [ 5.413922] dev_queue_xmit+0xc/0x10 [ 5.414136] ip_finish_output2+0x8bc/0xcd0 [ 5.414436] __ip_finish_output+0x472/0x7a0 [ 5.414692] ip_finish_output+0x5c/0x190 [ 5.414940] ip_output+0x2d8/0x3c0 [ 5.415150] ? ip_mc_finish_output+0x320/0x320 [ 5.415429] __ip_queue_xmit+0x753/0x1760 [ 5.415664] ip_queue_xmit+0x47/0x60 [ 5.415874] __tcp_transmit_skb+0x1ef9/0x34c0 [ 5.416129] tcp_connect+0x1f5e/0x4cb0 [ 5.416347] tcp_v4_connect+0xc8d/0x18c0 [ 5.416577] __inet_stream_connect+0x1ae/0xb40 [ 5.416836] ? local_bh_enable+0x11/0x20 [ 5.417066] ? lock_sock_nested+0x175/0x1d0 [ 5.417309] inet_stream_connect+0x5d/0x90 [ 5.417548] ? __inet_stream_connect+0xb40/0xb40 [ 5.417817] __sys_connect+0x260/0x2b0 [ 5.418037] __x64_sys_connect+0x76/0x80 [ 5.418267] do_syscall_64+0x31/0x50 [ 5.418477] entry_SYSCALL_64_after_hwframe+0x61/0xc6 [ 5.418770] RIP: 0033:0x473bb7 [ 5.418952] Code: 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2a 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 18 89 54 24 0c 48 89 34 24 89 [ 5.420046] RSP: 002b:00007fffd20eb0f8 EFLAGS: 00000246 ORIG_RAX: 000000000000002a [ 5.420472] RAX: ffffffffffffffda RBX: 00007fffd20eb578 RCX: 0000000000473bb7 [ 5.420872] RDX: 0000000000000010 RSI: 00007fffd20eb110 RDI: 0000000000000007 [ 5.421271] RBP: 00007fffd20eb150 R08: 0000000000000001 R09: 0000000000000004 [ 5.421671] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001 [ 5.422071] R13: 00007fffd20eb568 R14: 00000000004fc740 R15: 0000000000000002 [ 5.422471] [ 5.422562] Allocated by task 299: [ 5.422782] __kasan_kmalloc+0x12d/0x160 [ 5.423007] kasan_kmalloc+0x5/0x10 [ 5.423208] kmem_cache_alloc_trace+0x201/0x2e0 [ 5.423492] tcf_proto_create+0x65/0x290 [ 5.423721] tc_new_tfilter+0x137e/0x1830 [ 5.423957] rtnetlink_rcv_msg+0x730/0x9f0 [ 5.424197] netlink_rcv_skb+0x166/0x300 [ 5.424428] rtnetlink_rcv+0x11/0x20 [ 5.424639] netlink_unicast+0x673/0x860 [ 5.424870] netlink_sendmsg+0x6af/0x9f0 [ 5.425100] __sys_sendto+0x58d/0x5a0 [ 5.425315] __x64_sys_sendto+0xda/0xf0 [ 5.425539] do_syscall_64+0x31/0x50 [ 5.425764] entry_SYSCALL_64_after_hwframe+0x61/0xc6 [ 5.426065] [ 5.426157] The buggy address belongs to the object at ffff88800e312200 [ 5.426157] which belongs to the cache kmalloc-128 of size 128 [ 5.426955] The buggy address is located 42 bytes to the right of [ 5.426955] 128-byte region [ffff88800e312200, ffff88800e312280) [ 5.427688] The buggy address belongs to the page: [ 5.427992] page:000000009875fabc refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xe312 [ 5.428562] flags: 0x100000000000200(slab) [ 5.428812] raw: 0100000000000200 dead000000000100 dead000000000122 ffff888007843680 [ 5.429325] raw: 0000000000000000 0000000000100010 00000001ffffffff ffff88800e312401 [ 5.429875] page dumped because: kasan: bad access detected [ 5.430214] page->mem_cgroup:ffff88800e312401 [ 5.430471] [ 5.430564] Memory state around the buggy address: [ 5.430846] ffff88800e312180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 5.431267] ffff88800e312200: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fc [ 5.431705] >ffff88800e312280: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 5.432123] ^ [ 5.432391] ffff88800e312300: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fc [ 5.432810] ffff88800e312380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 5.433229] ================================================================== [ 5.433648] Disabling lock debugging due to kernel taint Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Kyle Zeng <zengyhkyle(a)gmail.com> Signed-off-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Conflicts: net/sched/sch_cbq.c Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Liu Jian <liujian56(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/sched/sch_cbq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index bc62e1b24653..dd8e83aac042 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -236,6 +236,8 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) result = tcf_classify(skb, fl, &res, true); if (!fl || result < 0) goto fallback; + if (result == TC_ACT_SHOT) + return NULL; cl = (void *)res.class; if (!cl) { @@ -256,8 +258,6 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; /* fall through */ - case TC_ACT_SHOT: - return NULL; case TC_ACT_RECLASSIFY: return cbq_reclassify(skb, cl); } -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 1/2] Huawei BMA: Fix iBMA driver bug
by Yongqiang Liu 18 Jan '23

18 Jan '23

From: Huajingjing <huajingjing1(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I67J42 CVE: NA ------------------------------------------------- The BMA software is a system management software offered by Huawei. It supports the status monitoring, performance monitoring and event monitoring of various components, including server CPUs, memory hard disks, NICs, IB cards, PCIe cards, RAID controller cards and optical modules. In this version, the system resets due to the BMA spin lock when the memory usage is too high, the vulnerability has been rectified. Signed-off-by: Hua Jingjing <huajingjingjing1(a)huawei.com> Reviewed-by: Chen Jiesong <chenjiesong(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- .../ethernet/huawei/bma/cdev_drv/bma_cdev.c | 2 +- .../huawei/bma/edma_drv/bma_devintf.c | 110 +++++++++++------- .../ethernet/huawei/bma/edma_drv/bma_pci.h | 2 +- .../huawei/bma/kbox_drv/kbox_include.h | 2 +- .../ethernet/huawei/bma/kbox_drv/kbox_panic.c | 4 +- .../huawei/bma/kbox_drv/kbox_printk.c | 4 +- .../huawei/bma/kbox_drv/kbox_ram_op.c | 2 +- .../ethernet/huawei/bma/veth_drv/veth_hb.c | 7 +- .../ethernet/huawei/bma/veth_drv/veth_hb.h | 2 +- 9 files changed, 81 insertions(+), 54 deletions(-) diff --git a/drivers/net/ethernet/huawei/bma/cdev_drv/bma_cdev.c b/drivers/net/ethernet/huawei/bma/cdev_drv/bma_cdev.c index 0348a83005d6..9468a5a0c768 100644 --- a/drivers/net/ethernet/huawei/bma/cdev_drv/bma_cdev.c +++ b/drivers/net/ethernet/huawei/bma/cdev_drv/bma_cdev.c @@ -28,7 +28,7 @@ #ifdef DRV_VERSION #define CDEV_VERSION MICRO_TO_STR(DRV_VERSION) #else -#define CDEV_VERSION "0.3.4" +#define CDEV_VERSION "0.3.5" #endif #define CDEV_DEFAULT_NUM 4 diff --git a/drivers/net/ethernet/huawei/bma/edma_drv/bma_devintf.c b/drivers/net/ethernet/huawei/bma/edma_drv/bma_devintf.c index 7817f58f8635..556130ab8a65 100644 --- a/drivers/net/ethernet/huawei/bma/edma_drv/bma_devintf.c +++ b/drivers/net/ethernet/huawei/bma/edma_drv/bma_devintf.c @@ -419,8 +419,10 @@ EXPORT_SYMBOL(bma_intf_int_to_bmc); int bma_intf_is_link_ok(void) { - return (g_bma_dev->edma_host.statistics.remote_status == - REGISTERED) ? 1 : 0; + if ((&g_bma_dev->edma_host != NULL) && + (g_bma_dev->edma_host.statistics.remote_status == REGISTERED)) + return 1; + return 0; } EXPORT_SYMBOL(bma_intf_is_link_ok); @@ -460,14 +462,10 @@ int bma_cdev_recv_msg(void *handle, char __user *data, size_t count) } EXPORT_SYMBOL_GPL(bma_cdev_recv_msg); -int bma_cdev_add_msg(void *handle, const char __user *msg, size_t msg_len) +static int check_cdev_add_msg_param(struct bma_priv_data_s *handle, +const char __user *msg, size_t msg_len) { struct bma_priv_data_s *priv = NULL; - struct edma_msg_hdr_s *hdr = NULL; - unsigned long flags = 0; - int total_len = 0; - int ret = 0; - struct edma_host_s *phost = &g_bma_dev->edma_host; if (!handle || !msg || msg_len == 0) { BMA_LOG(DLOG_DEBUG, "input NULL point!\n"); @@ -479,54 +477,80 @@ int bma_cdev_add_msg(void *handle, const char __user *msg, size_t msg_len) return -EINVAL; } - priv = (struct bma_priv_data_s *)handle; + priv = handle; if (priv->user.type >= TYPE_MAX) { BMA_LOG(DLOG_DEBUG, "error type = %d\n", priv->user.type); return -EFAULT; } - total_len = SIZE_OF_MSG_HDR + msg_len; + + return 0; +} + +static void edma_msg_hdr_init(struct edma_msg_hdr_s *hdr, + struct bma_priv_data_s *private_data, + char *msg_buf, size_t msg_len) +{ + hdr->type = private_data->user.type; + hdr->sub_type = private_data->user.sub_type; + hdr->user_id = private_data->user.user_id; + hdr->datalen = msg_len; + BMA_LOG(DLOG_DEBUG, "msg_len is %ld\n", msg_len); + + memcpy(hdr->data, msg_buf, msg_len); +} + +int bma_cdev_add_msg(void *handle, const char __user *msg, size_t msg_len) +{ + struct bma_priv_data_s *priv = NULL; + struct edma_msg_hdr_s *hdr = NULL; + unsigned long flags = 0; + unsigned int total_len = 0; + int ret = 0; + struct edma_host_s *phost = &g_bma_dev->edma_host; + char *msg_buf = NULL; + + ret = check_cdev_add_msg_param(handle, msg, msg_len); + if (ret != 0) + return ret; + + priv = (struct bma_priv_data_s *)handle; + + total_len = (unsigned int)(SIZE_OF_MSG_HDR + msg_len); + if (phost->msg_send_write + total_len > HOST_MAX_SEND_MBX_LEN - SIZE_OF_MBX_HDR) { + BMA_LOG(DLOG_DEBUG, "msg lost,msg_send_write: %u,msg_len:%u,max_len: %d\n", + phost->msg_send_write, total_len, HOST_MAX_SEND_MBX_LEN); + return -ENOSPC; + } + + msg_buf = (char *)kmalloc(msg_len, GFP_KERNEL); + if (!msg_buf) { + BMA_LOG(DLOG_ERROR, "malloc msg_buf failed\n"); + return -ENOMEM; + } + + if (copy_from_user(msg_buf, msg, msg_len)) { + BMA_LOG(DLOG_ERROR, "copy_from_user error\n"); + kfree(msg_buf); + return -EFAULT; + } spin_lock_irqsave(&phost->send_msg_lock, flags); - if (phost->msg_send_write + total_len <= - HOST_MAX_SEND_MBX_LEN - SIZE_OF_MBX_HDR) { - hdr = (struct edma_msg_hdr_s *)(phost->msg_send_buf + - phost->msg_send_write); - hdr->type = priv->user.type; - hdr->sub_type = priv->user.sub_type; - hdr->user_id = priv->user.user_id; - hdr->datalen = msg_len; - BMA_LOG(DLOG_DEBUG, "msg_len is %ld\n", msg_len); - - if (copy_from_user(hdr->data, msg, msg_len)) { - BMA_LOG(DLOG_ERROR, "copy_from_user error\n"); - ret = -EFAULT; - goto end; - } + hdr = (struct edma_msg_hdr_s *)(phost->msg_send_buf + phost->msg_send_write); + edma_msg_hdr_init(hdr, priv, msg_buf, msg_len); - phost->msg_send_write += total_len; - phost->statistics.send_bytes += total_len; - phost->statistics.send_pkgs++; + phost->msg_send_write += total_len; + phost->statistics.send_bytes += total_len; + phost->statistics.send_pkgs++; #ifdef EDMA_TIMER - (void)mod_timer(&phost->timer, jiffies_64); + (void)mod_timer(&phost->timer, jiffies_64); #endif - BMA_LOG(DLOG_DEBUG, "msg_send_write = %d\n", - phost->msg_send_write); - - ret = msg_len; - goto end; - } else { - BMA_LOG(DLOG_DEBUG, - "msg lost,msg_send_write: %d,msg_len:%d,max_len: %d\n", - phost->msg_send_write, total_len, - HOST_MAX_SEND_MBX_LEN); - ret = -ENOSPC; - goto end; - } + BMA_LOG(DLOG_DEBUG, "msg_send_write = %d\n", phost->msg_send_write); -end: + ret = msg_len; spin_unlock_irqrestore(&g_bma_dev->edma_host.send_msg_lock, flags); + kfree(msg_buf); return ret; } EXPORT_SYMBOL_GPL(bma_cdev_add_msg); diff --git a/drivers/net/ethernet/huawei/bma/edma_drv/bma_pci.h b/drivers/net/ethernet/huawei/bma/edma_drv/bma_pci.h index 2851e583666a..b6a0d11704a2 100644 --- a/drivers/net/ethernet/huawei/bma/edma_drv/bma_pci.h +++ b/drivers/net/ethernet/huawei/bma/edma_drv/bma_pci.h @@ -71,7 +71,7 @@ struct bma_pci_dev_s { #ifdef DRV_VERSION #define BMA_VERSION MICRO_TO_STR(DRV_VERSION) #else -#define BMA_VERSION "0.3.4" +#define BMA_VERSION "0.3.5" #endif #ifdef CONFIG_ARM64 diff --git a/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_include.h b/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_include.h index ffadf3727734..b027306e52c1 100644 --- a/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_include.h +++ b/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_include.h @@ -23,7 +23,7 @@ #ifdef DRV_VERSION #define KBOX_VERSION MICRO_TO_STR(DRV_VERSION) #else -#define KBOX_VERSION "0.3.4" +#define KBOX_VERSION "0.3.5" #endif #define UNUSED(x) (x = x) diff --git a/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_panic.c b/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_panic.c index 0c17cd2bae49..2b142ae9bff6 100644 --- a/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_panic.c +++ b/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_panic.c @@ -135,7 +135,7 @@ int kbox_panic_init(void) int ret = KBOX_TRUE; g_panic_info_buf = kmalloc(SLOT_LENGTH, GFP_KERNEL); - if (IS_ERR(g_panic_info_buf) || !g_panic_info_buf) { + if (!g_panic_info_buf) { KBOX_MSG("kmalloc g_panic_info_buf fail!\n"); ret = -ENOMEM; goto fail; @@ -144,7 +144,7 @@ int kbox_panic_init(void) memset(g_panic_info_buf, 0, SLOT_LENGTH); g_panic_info_buf_tmp = kmalloc(SLOT_LENGTH, GFP_KERNEL); - if (IS_ERR(g_panic_info_buf_tmp) || !g_panic_info_buf_tmp) { + if (!g_panic_info_buf_tmp) { KBOX_MSG("kmalloc g_panic_info_buf_tmp fail!\n"); ret = -ENOMEM; goto fail; diff --git a/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_printk.c b/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_printk.c index 3b04ba206108..630a1e16ea24 100644 --- a/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_printk.c +++ b/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_printk.c @@ -304,7 +304,7 @@ int kbox_printk_init(int kbox_proc_exist) g_printk_info_buf = kmalloc(SECTION_PRINTK_LEN, GFP_KERNEL); - if (IS_ERR(g_printk_info_buf) || !g_printk_info_buf) { + if (!g_printk_info_buf) { KBOX_MSG("kmalloc g_printk_info_buf fail!\n"); ret = -ENOMEM; goto fail; @@ -314,7 +314,7 @@ int kbox_printk_init(int kbox_proc_exist) g_printk_info_buf_tmp = kmalloc(SECTION_PRINTK_LEN, GFP_KERNEL); - if (IS_ERR(g_printk_info_buf_tmp) || !g_printk_info_buf_tmp) { + if (!g_printk_info_buf_tmp) { KBOX_MSG("kmalloc g_printk_info_buf_tmp fail!\n"); ret = -ENOMEM; goto fail; diff --git a/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_ram_op.c b/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_ram_op.c index 49690bab1cef..9f6dfe55e3fb 100644 --- a/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_ram_op.c +++ b/drivers/net/ethernet/huawei/bma/kbox_drv/kbox_ram_op.c @@ -432,7 +432,7 @@ int kbox_write_op(long long offset, unsigned int count, return KBOX_FALSE; temp_buf_char = kmalloc(TEMP_BUF_DATA_SIZE, GFP_KERNEL); - if (!temp_buf_char || IS_ERR(temp_buf_char)) { + if (!temp_buf_char) { KBOX_MSG("kmalloc temp_buf_char fail!\n"); up(&user_sem); return -ENOMEM; diff --git a/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.c b/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.c index 9681ce3bfc7b..e226582693b6 100644 --- a/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.c +++ b/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.c @@ -638,6 +638,7 @@ s32 veth_refill_rxskb(struct bspveth_rxtx_q *prx_queue, int queue) next_to_fill = (next_to_fill + 1) & BSPVETH_POINT_MASK; } + mb();/* memory barriers. */ prx_queue->next_to_fill = next_to_fill; tail = prx_queue->tail; @@ -672,6 +673,7 @@ s32 bspveth_setup_rx_skb(struct bspveth_device *pvethdev, if (!idx) /* Can't alloc even one packets */ return -EFAULT; + mb();/* memory barriers. */ prx_queue->next_to_fill = idx; VETH_LOG(DLOG_DEBUG, "prx_queue->next_to_fill=%d\n", @@ -886,8 +888,6 @@ s32 bspveth_setup_all_rx_resources(struct bspveth_device *pvethdev) err = bspveth_setup_rx_resources(pvethdev, pvethdev->prx_queue[qid]); if (err) { - kfree(pvethdev->prx_queue[qid]); - pvethdev->prx_queue[qid] = NULL; VETH_LOG(DLOG_ERROR, "Allocation for Rx Queue %u failed\n", qid); @@ -1328,6 +1328,7 @@ s32 veth_send_one_pkt(struct sk_buff *skb, int queue) pbd_v->off = off; pbd_v->len = skb->len; + mb();/* memory barriers. */ head = (head + 1) & BSPVETH_POINT_MASK; ptx_queue->head = head; @@ -1424,6 +1425,7 @@ s32 veth_free_txskb(struct bspveth_rxtx_q *ptx_queue, int queue) next_to_free = (next_to_free + 1) & BSPVETH_POINT_MASK; } + mb(); /* memory barriers. */ ptx_queue->next_to_free = next_to_free; tail = ptx_queue->tail; @@ -1522,6 +1524,7 @@ s32 veth_recv_pkt(struct bspveth_rxtx_q *prx_queue, int queue) } } + mb();/* memory barriers. */ prx_queue->tail = tail; head = prx_queue->head; diff --git a/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.h b/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.h index 9a4d699e6421..503636549320 100644 --- a/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.h +++ b/drivers/net/ethernet/huawei/bma/veth_drv/veth_hb.h @@ -31,7 +31,7 @@ extern "C" { #ifdef DRV_VERSION #define VETH_VERSION MICRO_TO_STR(DRV_VERSION) #else -#define VETH_VERSION "0.3.4" +#define VETH_VERSION "0.3.5" #endif #define MODULE_NAME "veth" -- 2.25.1

1 1

[PATCH V2 RESEND openEuler-22.03-LTS] selftests/rseq: check if libc rseq support is registered
by 任敏敏(联通集团联通数字科技有限公司本部) 18 Jan '23

18 Jan '23

From: Michael Jeanson <mjeanson(a)efficios.com> mainline inclusion from mainline-v6.0-rc1 commit d1a997ba4c1bf65497d956aea90de42a6398f73a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I69PT8 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit d1a997ba4c1bf65497d956aea90de42a6398f73a upstream. When checking for libc rseq support in the library constructor, don't only depend on the symbols presence, check that the registration was completed. This targets a scenario where the libc has rseq support but it is not wired for the current architecture in 'bits/rseq.h', we want to fallback to our internal registration mechanism. Signed-off-by: Michael Jeanson <mjeanson(a)efficios.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Link: https://lore.kernel.org/r/20220614154830.1367382-4-mjeanson@efficios.com Signed-off-by: rminmin <renmm6(a)chinaunicom.cn> --- tools/testing/selftests/rseq/rseq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index 986b9458efb2..4177f9507bbe 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -111,7 +111,8 @@ void rseq_init(void) libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset"); libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size"); libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags"); - if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p) { + if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p && + *libc_rseq_size_p != 0) { /* rseq registration owned by glibc */ rseq_offset = *libc_rseq_offset_p; rseq_size = *libc_rseq_size_p; -- 2.33.0 Èç¹ûÄúŽíÎóœÓÊÕÁËžÃÓÊŒþ£¬ÇëÍš¹ýµç×ÓÓÊŒþÁ¢ŒŽÍšÖªÎÒÃÇ¡£Çë»ØžŽÓÊŒþµœ hqs-spmc@chinaunicom.cn£¬ŒŽ¿ÉÒÔÍË¶©ŽËÓÊŒþ¡£ÎÒÃÇœ«Á¢ŒŽœ«ÄúµÄÐÅÏ¢ŽÓÎÒÃÇµÄ·¢ËÍÄ¿ÂŒÖÐÉŸ³ý¡£ If you have received this email in error please notify us immediately by e-mail. Please reply to hqs-spmc(a)chinaunicom.cn ,you can unsubscribe from this mail. We will immediately remove your information from send catalogue of our.

1 0

[PATCH openEuler-5.10-LTS-SP1 01/14] tracing/osnoise: Properly unhook events if start_per_cpu_kthreads() fails
by Jialin Zhang 18 Jan '23

18 Jan '23

From: Nikita Yushchenko <nikita.yushchenko(a)virtuozzo.com> mainline inclusion from mainline-v5.17-rc1 commit 0878355b51f5f26632e652c848a8e174bb02d22d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I699A9 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- If start_per_cpu_kthreads() called from osnoise_workload_start() returns error, event hooks are left in broken state: unhook_irq_events() called but unhook_thread_events() and unhook_softirq_events() not called, and trace_osnoise_callback_enabled flag not cleared. On the next tracer enable, hooks get not installed due to trace_osnoise_callback_enabled flag. And on the further tracer disable an attempt to remove non-installed hooks happened, hitting a WARN_ON_ONCE() in tracepoint_remove_func(). Fix the error path by adding the missing part of cleanup. While at this, introduce osnoise_unhook_events() to avoid code duplication between this error path and normal tracer disable. Link: https://lkml.kernel.org/r/20220109153459.3701773-1-nikita.yushchenko@virtuo… Cc: stable(a)vger.kernel.org Fixes: bce29ac9ce0b ("trace: Add osnoise tracer") Acked-by: Daniel Bristot de Oliveira <bristot(a)kernel.org> Signed-off-by: Nikita Yushchenko <nikita.yushchenko(a)virtuozzo.com> Signed-off-by: Steven Rostedt <rostedt(a)goodmis.org> Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> Reviewed-by: Xu Kuohai <xukuohai(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- kernel/trace/trace_osnoise.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index cfb80feb291e..3f806a3be8b2 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -2103,6 +2103,13 @@ static int osnoise_hook_events(void) return -EINVAL; } +static void osnoise_unhook_events(void) +{ + unhook_thread_events(); + unhook_softirq_events(); + unhook_irq_events(); +} + /* * osnoise_workload_start - start the workload and hook to events */ @@ -2135,7 +2142,14 @@ static int osnoise_workload_start(void) retval = start_per_cpu_kthreads(); if (retval) { - unhook_irq_events(); + trace_osnoise_callback_enabled = false; + /* + * Make sure that ftrace_nmi_enter/exit() see + * trace_osnoise_callback_enabled as false before continuing. + */ + barrier(); + + osnoise_unhook_events(); return retval; } @@ -2166,9 +2180,7 @@ static void osnoise_workload_stop(void) stop_per_cpu_kthreads(); - unhook_irq_events(); - unhook_softirq_events(); - unhook_thread_events(); + osnoise_unhook_events(); } static void osnoise_tracer_start(struct trace_array *tr) -- 2.25.1

1 13

[PATCH openEuler-5.10-LTS 01/21] tmpfs: do not allocate pages on read
by Jialin Zhang 18 Jan '23

18 Jan '23

From: Hugh Dickins <hughd(a)google.com> mainline inclusion from mainline-v5.18-rc1 commit 56a8c8eb1eaf21261be8cdc4e3715239ac087342 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6113U CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- Mikulas asked in "Do we still need commit a0ee5ec520ed ('tmpfs: allocate on read when stacked')?" in [1] Lukas noticed this unusual behavior of loop device backed by tmpfs in [2]. Normally, shmem_file_read_iter() copies the ZERO_PAGE when reading holes; but if it looks like it might be a read for "a stacking filesystem", it allocates actual pages to the page cache, and even marks them as dirty. And reads from the loop device do satisfy the test that is used. This oddity was added for an old version of unionfs, to help to limit its usage to the limited size of the tmpfs mount involved; but about the same time as the tmpfs mod went in (2.6.25), unionfs was reworked to proceed differently; and the mod kept just in case others needed it. Do we still need it? I cannot answer with more certainty than "Probably not". It's nasty enough that we really should try to delete it; but if a regression is reported somewhere, then we might have to revert later. It's not quite as simple as just removing the test (as Mikulas did): xfstests generic/013 hung because splice from tmpfs failed on page not up-to-date and page mapping unset. That can be fixed just by marking the ZERO_PAGE as Uptodate, which of course it is: do so in pagecache_init() - it might be useful to others than tmpfs. My intention, though, was to stop using the ZERO_PAGE here altogether: surely iov_iter_zero() is better for this case? Sadly not: it relies on clear_user(), and the x86 clear_user() is slower than its copy_user() [3]. But while we are still using the ZERO_PAGE, let's stop dirtying its struct page cacheline with unnecessary get_page() and put_page(). Link: https://lore.kernel.org/linux-mm/alpine.LRH.2.02.2007210510230.6959@file01.… [1] Link: https://lore.kernel.org/linux-mm/20211126075100.gd64odg2bcptiqeb@work/ [2] Link: https://lore.kernel.org/lkml/2f5ca5e4-e250-a41c-11fb-a7f4ebc7e1c9@google.co… [3] Link: https://lkml.kernel.org/r/90bc5e69-9984-b5fa-a685-be55f2b64b@google.com Signed-off-by: Hugh Dickins <hughd(a)google.com> Reported-by: Mikulas Patocka <mpatocka(a)redhat.com> Reported-by: Lukas Czerner <lczerner(a)redhat.com> Acked-by: Darrick J. Wong <djwong(a)kernel.org> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Cc: Zdenek Kabelac <zkabelac(a)redhat.com> Cc: "Darrick J. Wong" <djwong(a)kernel.org> Cc: Miklos Szeredi <miklos(a)szeredi.hu> Cc: Borislav Petkov <bp(a)suse.de> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> Reviewed-by: tong tiangen <tongtiangen(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- mm/filemap.c | 6 ++++++ mm/shmem.c | 20 ++++++-------------- 2 files changed, 12 insertions(+), 14 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index 98b448d9873f..a44baa79c1e7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -996,6 +996,12 @@ void __init pagecache_init(void) init_waitqueue_head(&page_wait_table[i]); page_writeback_init(); + + /* + * tmpfs uses the ZERO_PAGE for reading holes: it is up-to-date, + * and splice's page_cache_pipe_buf_confirm() needs to see that. + */ + SetPageUptodate(ZERO_PAGE(0)); } /* diff --git a/mm/shmem.c b/mm/shmem.c index ad2d68150ed2..c5028634afee 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2573,19 +2573,10 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) struct address_space *mapping = inode->i_mapping; pgoff_t index; unsigned long offset; - enum sgp_type sgp = SGP_READ; int error = 0; ssize_t retval = 0; loff_t *ppos = &iocb->ki_pos; - /* - * Might this read be for a stacking filesystem? Then when reading - * holes of a sparse file, we actually need to allocate those pages, - * and even mark them dirty, so it cannot exceed the max_blocks limit. - */ - if (!iter_is_iovec(to)) - sgp = SGP_CACHE; - index = *ppos >> PAGE_SHIFT; offset = *ppos & ~PAGE_MASK; @@ -2594,6 +2585,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) pgoff_t end_index; unsigned long nr, ret; loff_t i_size = i_size_read(inode); + bool got_page; end_index = i_size >> PAGE_SHIFT; if (index > end_index) @@ -2604,15 +2596,13 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) break; } - error = shmem_getpage(inode, index, &page, sgp); + error = shmem_getpage(inode, index, &page, SGP_READ); if (error) { if (error == -EINVAL) error = 0; break; } if (page) { - if (sgp == SGP_CACHE) - set_page_dirty(page); unlock_page(page); } @@ -2646,9 +2636,10 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) */ if (!offset) mark_page_accessed(page); + got_page = true; } else { page = ZERO_PAGE(0); - get_page(page); + got_page = false; } /* @@ -2661,7 +2652,8 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) index += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; - put_page(page); + if (got_page) + put_page(page); if (!iov_iter_count(to)) break; if (ret < nr) { -- 2.25.1

1 20