- Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS] ALSA: usb-audio: Fix out of bounds reads when finding clock sources
by Luo Gengkun 14 Jan '25

14 Jan '25

From: Takashi Iwai <tiwai(a)suse.de> stable inclusion from stable-v5.10.231 commit 45a92cbc88e4013bfed7fd2ccab3ade45f8e896b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBDHGG CVE: CVE-2024-53150 Reference: https://git.kernel.org/stable/c/45a92cbc88e4013bfed7fd2ccab3ade45f8e896b -------------------------------- commit a3dd4d63eeb452cfb064a13862fb376ab108f6a6 upstream. The current USB-audio driver code doesn't check bLength of each descriptor at traversing for clock descriptors. That is, when a device provides a bogus descriptor with a shorter bLength, the driver might hit out-of-bounds reads. For addressing it, this patch adds sanity checks to the validator functions for the clock descriptor traversal. When the descriptor length is shorter than expected, it's skipped in the loop. For the clock source and clock multiplier descriptors, we can just check bLength against the sizeof() of each descriptor type. OTOH, the clock selector descriptor of UAC2 and UAC3 has an array of bNrInPins elements and two more fields at its tail, hence those have to be checked in addition to the sizeof() check. Reported-by: Benoît Sevens <bsevens(a)google.com> Cc: <stable(a)vger.kernel.org> Link: https://lore.kernel.org/20241121140613.3651-1-bsevens@google.com Link: https://patch.msgid.link/20241125144629.20757-1-tiwai@suse.de Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Signed-off-by: Benoît Sevens <bsevens(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Luo Gengkun <luogengkun2(a)huawei.com> --- sound/usb/clock.c | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) diff --git a/sound/usb/clock.c b/sound/usb/clock.c index 01b414448312..de8d7e2c6b3a 100644 --- a/sound/usb/clock.c +++ b/sound/usb/clock.c @@ -35,6 +35,10 @@ #include "clock.h" #include "quirks.h" +/* check whether the descriptor bLength has the minimal length */ +#define DESC_LENGTH_CHECK(p) \ + (p->bLength >= sizeof(*p)) + static void *find_uac_clock_desc(struct usb_host_interface *iface, int id, bool (*validator)(void *, int), u8 type) { @@ -52,36 +56,60 @@ static void *find_uac_clock_desc(struct usb_host_interface *iface, int id, static bool validate_clock_source_v2(void *p, int id) { struct uac_clock_source_descriptor *cs = p; + if (!DESC_LENGTH_CHECK(cs)) + return false; return cs->bClockID == id; } static bool validate_clock_source_v3(void *p, int id) { struct uac3_clock_source_descriptor *cs = p; + if (!DESC_LENGTH_CHECK(cs)) + return false; return cs->bClockID == id; } static bool validate_clock_selector_v2(void *p, int id) { struct uac_clock_selector_descriptor *cs = p; - return cs->bClockID == id; + if (!DESC_LENGTH_CHECK(cs)) + return false; + if (cs->bClockID != id) + return false; + /* additional length check for baCSourceID array (in bNrInPins size) + * and two more fields (which sizes depend on the protocol) + */ + return cs->bLength >= sizeof(*cs) + cs->bNrInPins + + 1 /* bmControls */ + 1 /* iClockSelector */; } static bool validate_clock_selector_v3(void *p, int id) { struct uac3_clock_selector_descriptor *cs = p; - return cs->bClockID == id; + if (!DESC_LENGTH_CHECK(cs)) + return false; + if (cs->bClockID != id) + return false; + /* additional length check for baCSourceID array (in bNrInPins size) + * and two more fields (which sizes depend on the protocol) + */ + return cs->bLength >= sizeof(*cs) + cs->bNrInPins + + 4 /* bmControls */ + 2 /* wCSelectorDescrStr */; } static bool validate_clock_multiplier_v2(void *p, int id) { struct uac_clock_multiplier_descriptor *cs = p; + if (!DESC_LENGTH_CHECK(cs)) + return false; return cs->bClockID == id; } static bool validate_clock_multiplier_v3(void *p, int id) { struct uac3_clock_multiplier_descriptor *cs = p; + if (!DESC_LENGTH_CHECK(cs)) + return false; return cs->bClockID == id; } -- 2.34.1

2 1

[openeuler:OLK-6.6] BUILD REGRESSION 4fbc633527d173d6e350da6be39009c6a449a802
by kernel test robot 14 Jan '25

14 Jan '25

tree/branch: https://gitee.com/openeuler/kernel.git OLK-6.6 branch HEAD: 4fbc633527d173d6e350da6be39009c6a449a802 !14846 net: stmmac: fix TSO DMA API usage causing oops Error/Warning (recently discovered and may have been fixed): https://lore.kernel.org/oe-kbuild-all/202501140558.Dz2Pe9bS-lkp@intel.com https://lore.kernel.org/oe-kbuild-all/202501140732.yHKX6wmK-lkp@intel.com drivers/i2c/busses/i2c-zhaoxin-smbus.c:367:36: warning: unused variable 'zxsmb_acpi_match' [-Wunused-const-variable] drivers/irqchip/irq-gic-v3.c:1086:43: error: incompatible integer to pointer conversion passing 'int' to parameter of type 'void *' [-Wint-conversion] include/../drivers/pci/msi/msi.h:113:57: warning: declaration of 'struct msix_entry' will not be visible outside of this function [-Wvisibility] Error/Warning ids grouped by kconfigs: recent_errors |-- arm64-allmodconfig | |-- block-blk-io-hierarchy-iodump.c:warning:no-previous-prototype-for-function-__bio_stage_hierarchy_start | |-- drivers-net-ethernet-huawei-hibifur-bifur_event.c:warning:no-previous-prototype-for-function-bifur_net_event_callback | |-- drivers-net-ethernet-huawei-hibifur-bifur_event.c:warning:no-previous-prototype-for-function-bifur_notify_all_vfs_link_changed | |-- drivers-net-ethernet-huawei-hibifur-bifur_event.c:warning:no-previous-prototype-for-function-bifur_notify_vf_link_status | |-- drivers-net-ethernet-huawei-hibifur-bifur_main.c:warning:no-previous-prototype-for-function-bifur_enable_disable_vf_all | |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_alloc_proc_file | |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_cmd_exec | |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_file_write | |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_free_knl_msg_buf | |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_global_dev_close | |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_global_dev_open | |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_global_file_add | |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_global_file_del | |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_msg_copy_from_usr | |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_msg_copy_to_usr | |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_proc_write | |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_dev_file_add | |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_dev_file_del | |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_dev_proc_build | |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_dev_proc_destroy | |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_proc_close | |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_proc_open | |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_vf_info_hold | `-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_vf_info_put |-- arm64-randconfig-002-20250114 | |-- drivers-i2c-busses-i2c-zhaoxin-smbus.c:warning:unused-variable-zxsmb_acpi_match | `-- kernel-cgroup-cgroup.c:error:use-of-undeclared-identifier-cgroup_psi_stat_show |-- arm64-randconfig-004-20250114 | |-- drivers-irqchip-irq-gic-v3.c:error:incompatible-integer-to-pointer-conversion-passing-int-to-parameter-of-type-void | `-- include-..-drivers-pci-msi-msi.h:warning:declaration-of-struct-msix_entry-will-not-be-visible-outside-of-this-function |-- loongarch-allmodconfig | `-- drivers-irqchip-irq-loongson-eiointc.c:warning:unused-variable-cores |-- loongarch-allnoconfig | `-- drivers-irqchip-irq-loongson-eiointc.c:warning:unused-variable-cores |-- loongarch-allyesconfig | `-- drivers-irqchip-irq-loongson-eiointc.c:warning:unused-variable-cores |-- loongarch-randconfig-002-20250114 | `-- drivers-irqchip-irq-loongson-eiointc.c:warning:unused-variable-cores |-- x86_64-allnoconfig | `-- samples-trace_events-trace_custom_sched.c:linux-version.h-not-needed. `-- x86_64-allyesconfig |-- block-blk-io-hierarchy-iodump.c:warning:no-previous-prototype-for-function-__bio_stage_hierarchy_start |-- drivers-net-ethernet-huawei-hibifur-bifur_event.c:warning:no-previous-prototype-for-function-bifur_net_event_callback |-- drivers-net-ethernet-huawei-hibifur-bifur_event.c:warning:no-previous-prototype-for-function-bifur_notify_all_vfs_link_changed |-- drivers-net-ethernet-huawei-hibifur-bifur_event.c:warning:no-previous-prototype-for-function-bifur_notify_vf_link_status |-- drivers-net-ethernet-huawei-hibifur-bifur_main.c:warning:no-previous-prototype-for-function-bifur_enable_disable_vf_all |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_alloc_proc_file |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_cmd_exec |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_file_write |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_free_knl_msg_buf |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_global_dev_close |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_global_dev_open |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_global_file_add |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_global_file_del |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_msg_copy_from_usr |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_msg_copy_to_usr |-- drivers-net-ethernet-huawei-hibifur-bifur_pfile.c:warning:no-previous-prototype-for-function-bifur_proc_write |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_dev_file_add |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_dev_file_del |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_dev_proc_build |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_dev_proc_destroy |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_proc_close |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_proc_open |-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_vf_info_hold `-- drivers-net-ethernet-huawei-hibifur-bifur_vf_mgr.c:warning:no-previous-prototype-for-function-bifur_vf_info_put elapsed time: 738m configs tested: 19 configs skipped: 113 tested configs: arm64 allmodconfig clang-18 arm64 allnoconfig gcc-14.2.0 arm64 randconfig-001-20250114 clang-17 arm64 randconfig-002-20250114 clang-19 arm64 randconfig-003-20250114 gcc-14.2.0 arm64 randconfig-004-20250114 clang-20 loongarch allmodconfig gcc-14.2.0 loongarch allnoconfig gcc-14.2.0 loongarch randconfig-001-20250114 gcc-14.2.0 loongarch randconfig-002-20250114 gcc-14.2.0 x86_64 allnoconfig clang-19 x86_64 allyesconfig clang-19 x86_64 buildonly-randconfig-001-20250114 clang-19 x86_64 buildonly-randconfig-002-20250114 clang-19 x86_64 buildonly-randconfig-003-20250114 clang-19 x86_64 buildonly-randconfig-004-20250114 clang-19 x86_64 buildonly-randconfig-005-20250114 clang-19 x86_64 buildonly-randconfig-006-20250114 clang-19 x86_64 defconfig gcc-11 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-5.10] sched: psi: fix bogus pressure spikes from aggregation race
by Chen Ridong 14 Jan '25

14 Jan '25

From: Johannes Weiner <hannes(a)cmpxchg.org> stable inclusion from stable-v6.6.55 commit 1f997b1d13e0b9819468e577622e747b546516fe category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IB6YDK Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 3840cbe24cf060ea05a585ca497814609f5d47d1 ] Brandon reports sporadic, non-sensical spikes in cumulative pressure time (total=) when reading cpu.pressure at a high rate. This is due to a race condition between reader aggregation and tasks changing states. While it affects all states and all resources captured by PSI, in practice it most likely triggers with CPU pressure, since scheduling events are so frequent compared to other resource events. The race context is the live snooping of ongoing stalls during a pressure read. The read aggregates per-cpu records for stalls that have concluded, but will also incorporate ad-hoc the duration of any active state that hasn't been recorded yet. This is important to get timely measurements of ongoing stalls. Those ad-hoc samples are calculated on-the-fly up to the current time on that CPU; since the stall hasn't concluded, it's expected that this is the minimum amount of stall time that will enter the per-cpu records once it does. The problem is that the path that concludes the state uses a CPU clock read that is not synchronized against aggregators; the clock is read outside of the seqlock protection. This allows aggregators to race and snoop a stall with a longer duration than will actually be recorded. With the recorded stall time being less than the last snapshot remembered by the aggregator, a subsequent sample will underflow and observe a bogus delta value, resulting in an erratic jump in pressure. Fix this by moving the clock read of the state change into the seqlock protection. This ensures no aggregation can snoop live stalls past the time that's recorded when the state concludes. Reported-by: Brandon Duffany <brandon(a)buildbuddy.io> Link: https://bugzilla.kernel.org/show_bug.cgi?id=219194 Link: https://lore.kernel.org/lkml/20240827121851.GB438928@cmpxchg.org/ Fixes: d67515514ca5 ("psi: Reduce calls to sched_clock() in psi") Cc: stable(a)vger.kernel.org Signed-off-by: Johannes Weiner <hannes(a)cmpxchg.org> Reviewed-by: Chengming Zhou <chengming.zhou(a)linux.dev> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: kernel/sched/psi.c [ Context conflicts and psi_cgroup_restart(re-enable) is not merged. Move the update_psi_stat_delta into the psi_group_change functions ] Signed-off-by: Chen Ridong <chenridong(a)huawei.com> --- kernel/sched/psi.c | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 977c973d1e70..b0068145b185 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -962,13 +962,14 @@ static void record_times(struct psi_group_cpu *groupc, u64 now) } static void psi_group_change(struct psi_group *group, int cpu, - unsigned int clear, unsigned int set, u64 now, + unsigned int clear, unsigned int set, bool wake_clock) { struct psi_group_cpu *groupc; unsigned int t, m; enum psi_states s; u32 state_mask; + u64 now; groupc = per_cpu_ptr(group->pcpu, cpu); @@ -981,7 +982,9 @@ static void psi_group_change(struct psi_group *group, int cpu, * change requested through the @clear and @set bits. */ write_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); + update_psi_stat_delta(group, cpu, now); record_times(groupc, now); record_cpu_stat_times(group, cpu); @@ -1110,7 +1113,6 @@ void psi_task_change(struct task_struct *task, int clear, int set) int cpu = task_cpu(task); struct psi_group *group; void *iter = NULL; - u64 now; int stat_set = 0; int stat_clear = 0; @@ -1120,11 +1122,8 @@ void psi_task_change(struct task_struct *task, int clear, int set) psi_flags_change(task, clear, set); psi_stat_flags_change(task, &stat_set, &stat_clear, set, clear); - now = cpu_clock(cpu); - while ((group = iterate_groups(task, &iter))) { - update_psi_stat_delta(group, cpu, now); - psi_group_change(group, cpu, clear, set, now, true); + psi_group_change(group, cpu, clear, set, true); psi_group_stat_change(group, cpu, stat_clear, stat_set); } } @@ -1135,7 +1134,6 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, struct psi_group *group, *common = NULL; int cpu = task_cpu(prev); void *iter; - u64 now = cpu_clock(cpu); if (next->pid) { update_throttle_type(next, cpu, true); @@ -1153,8 +1151,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, break; } - update_psi_stat_delta(group, cpu, now); - psi_group_change(group, cpu, 0, TSK_ONCPU, now, true); + psi_group_change(group, cpu, 0, TSK_ONCPU, true); psi_group_stat_change(group, cpu, 0, 0); } } @@ -1196,8 +1193,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, iter = NULL; while ((group = iterate_groups(prev, &iter)) && group != common) { - update_psi_stat_delta(group, cpu, now); - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); psi_group_stat_change(group, cpu, stat_clear, stat_set); } #ifdef CONFIG_PSI_FINE_GRAINED @@ -1214,8 +1210,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, memstall_type_change) { clear &= ~TSK_ONCPU; for (; group; group = iterate_groups(prev, &iter)) { - update_psi_stat_delta(group, cpu, now); - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); psi_group_stat_change(group, cpu, stat_clear, stat_set); } @@ -1238,12 +1233,11 @@ void psi_account_irqtime(struct task_struct *task, u32 delta) if (!task->pid) return; - now = cpu_clock(cpu); - while ((group = iterate_groups(task, &iter))) { groupc = per_cpu_ptr(group->pcpu, cpu); write_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); update_psi_stat_delta(group, cpu, now); record_stat_times(to_psi_group_ext(group), cpu); -- 2.34.1

2 1

[PATCH OLK-6.6] sched: psi: fix bogus pressure spikes from aggregation race
by Chen Ridong 14 Jan '25

14 Jan '25

From: Johannes Weiner <hannes(a)cmpxchg.org> stable inclusion from stable-v6.6.55 commit 1f997b1d13e0b9819468e577622e747b546516fe category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IB6YDK Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 3840cbe24cf060ea05a585ca497814609f5d47d1 ] Brandon reports sporadic, non-sensical spikes in cumulative pressure time (total=) when reading cpu.pressure at a high rate. This is due to a race condition between reader aggregation and tasks changing states. While it affects all states and all resources captured by PSI, in practice it most likely triggers with CPU pressure, since scheduling events are so frequent compared to other resource events. The race context is the live snooping of ongoing stalls during a pressure read. The read aggregates per-cpu records for stalls that have concluded, but will also incorporate ad-hoc the duration of any active state that hasn't been recorded yet. This is important to get timely measurements of ongoing stalls. Those ad-hoc samples are calculated on-the-fly up to the current time on that CPU; since the stall hasn't concluded, it's expected that this is the minimum amount of stall time that will enter the per-cpu records once it does. The problem is that the path that concludes the state uses a CPU clock read that is not synchronized against aggregators; the clock is read outside of the seqlock protection. This allows aggregators to race and snoop a stall with a longer duration than will actually be recorded. With the recorded stall time being less than the last snapshot remembered by the aggregator, a subsequent sample will underflow and observe a bogus delta value, resulting in an erratic jump in pressure. Fix this by moving the clock read of the state change into the seqlock protection. This ensures no aggregation can snoop live stalls past the time that's recorded when the state concludes. Reported-by: Brandon Duffany <brandon(a)buildbuddy.io> Link: https://bugzilla.kernel.org/show_bug.cgi?id=219194 Link: https://lore.kernel.org/lkml/20240827121851.GB438928@cmpxchg.org/ Fixes: df77430639c9 ("psi: Reduce calls to sched_clock() in psi") Cc: stable(a)vger.kernel.org Signed-off-by: Johannes Weiner <hannes(a)cmpxchg.org> Reviewed-by: Chengming Zhou <chengming.zhou(a)linux.dev> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: kernel/sched/psi.c [ Just context conflicts. ] Signed-off-by: Chen Ridong <chenridong(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> --- kernel/sched/psi.c | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 9f68756a3bafe..1c8b1f9975138 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -988,13 +988,14 @@ static void record_times(struct psi_group_cpu *groupc, u64 now) } static void psi_group_change(struct psi_group *group, int cpu, - unsigned int clear, unsigned int set, u64 now, + unsigned int clear, unsigned int set, bool wake_clock) { struct psi_group_cpu *groupc; unsigned int t, m; enum psi_states s; u32 state_mask; + u64 now; groupc = per_cpu_ptr(group->pcpu, cpu); @@ -1008,6 +1009,7 @@ static void psi_group_change(struct psi_group *group, int cpu, * SOME and FULL time these may have resulted in. */ write_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); /* * Start with TSK_ONCPU, which doesn't have a corresponding @@ -1150,7 +1152,6 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; - u64 now; int stat_set = 0; int stat_clear = 0; @@ -1160,11 +1161,9 @@ void psi_task_change(struct task_struct *task, int clear, int set) psi_flags_change(task, clear, set); psi_stat_flags_change(task, &stat_set, &stat_clear, set, clear); - now = cpu_clock(cpu); - group = task_psi_group(task); do { - psi_group_change(group, cpu, clear, set, now, true); + psi_group_change(group, cpu, clear, set, true); psi_group_stat_change(group, cpu, stat_clear, stat_set); } while ((group = group->parent)); } @@ -1174,7 +1173,6 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, { struct psi_group *group, *common = NULL; int cpu = task_cpu(prev); - u64 now = cpu_clock(cpu); if (next->pid) { update_throttle_type(next, cpu, true); @@ -1192,7 +1190,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, break; } - psi_group_change(group, cpu, 0, TSK_ONCPU, now, true); + psi_group_change(group, cpu, 0, TSK_ONCPU, true); psi_group_stat_change(group, cpu, 0, 0); } while ((group = group->parent)); } @@ -1236,7 +1234,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, do { if (group == common) break; - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); psi_group_stat_change(group, cpu, stat_clear, stat_set); } while ((group = group->parent)); @@ -1255,7 +1253,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, memstall_type_change) { clear &= ~TSK_ONCPU; for (; group; group = group->parent) { - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); psi_group_stat_change(group, cpu, stat_clear, stat_set); } } @@ -1268,7 +1266,6 @@ void psi_account_irqtime(struct task_struct *task, u32 delta) int cpu = task_cpu(task); struct psi_group *group; struct psi_group_cpu *groupc; - u64 now; if (static_branch_likely(&psi_disabled)) return; @@ -1276,14 +1273,15 @@ void psi_account_irqtime(struct task_struct *task, u32 delta) if (!task->pid) return; - now = cpu_clock(cpu); - group = task_psi_group(task); do { + u64 now; + if (!group->enabled) continue; groupc = per_cpu_ptr(group->pcpu, cpu); + now = cpu_clock(cpu); write_seqcount_begin(&groupc->seq); @@ -1497,11 +1495,9 @@ void psi_cgroup_restart(struct psi_group *group) for_each_possible_cpu(cpu) { struct rq *rq = cpu_rq(cpu); struct rq_flags rf; - u64 now; rq_lock_irq(rq, &rf); - now = cpu_clock(cpu); - psi_group_change(group, cpu, 0, 0, now, true); + psi_group_change(group, cpu, 0, 0, true); rq_unlock_irq(rq, &rf); } } -- 2.34.1

2 1

[PATCH OLK-5.10] sched: psi: fix bogus pressure spikes from aggregation race
by Chen Ridong 14 Jan '25

14 Jan '25

From: Johannes Weiner <hannes(a)cmpxchg.org> stable inclusion from stable-v6.6.55 commit 1f997b1d13e0b9819468e577622e747b546516fe category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IB6YDK Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 3840cbe24cf060ea05a585ca497814609f5d47d1 ] Brandon reports sporadic, non-sensical spikes in cumulative pressure time (total=) when reading cpu.pressure at a high rate. This is due to a race condition between reader aggregation and tasks changing states. While it affects all states and all resources captured by PSI, in practice it most likely triggers with CPU pressure, since scheduling events are so frequent compared to other resource events. The race context is the live snooping of ongoing stalls during a pressure read. The read aggregates per-cpu records for stalls that have concluded, but will also incorporate ad-hoc the duration of any active state that hasn't been recorded yet. This is important to get timely measurements of ongoing stalls. Those ad-hoc samples are calculated on-the-fly up to the current time on that CPU; since the stall hasn't concluded, it's expected that this is the minimum amount of stall time that will enter the per-cpu records once it does. The problem is that the path that concludes the state uses a CPU clock read that is not synchronized against aggregators; the clock is read outside of the seqlock protection. This allows aggregators to race and snoop a stall with a longer duration than will actually be recorded. With the recorded stall time being less than the last snapshot remembered by the aggregator, a subsequent sample will underflow and observe a bogus delta value, resulting in an erratic jump in pressure. Fix this by moving the clock read of the state change into the seqlock protection. This ensures no aggregation can snoop live stalls past the time that's recorded when the state concludes. Reported-by: Brandon Duffany <brandon(a)buildbuddy.io> Link: https://bugzilla.kernel.org/show_bug.cgi?id=219194 Link: https://lore.kernel.org/lkml/20240827121851.GB438928@cmpxchg.org/ Fixes: df77430639c9 ("psi: Reduce calls to sched_clock() in psi") Cc: stable(a)vger.kernel.org Signed-off-by: Johannes Weiner <hannes(a)cmpxchg.org> Reviewed-by: Chengming Zhou <chengming.zhou(a)linux.dev> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: kernel/sched/psi.c [ Context conflicts and psi_cgroup_restart(re-enable) is not merged. Move the update_psi_stat_delta into the psi_group_change functions ] Signed-off-by: Chen Ridong <chenridong(a)huawei.com> --- kernel/sched/psi.c | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 977c973d1e70..b0068145b185 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -962,13 +962,14 @@ static void record_times(struct psi_group_cpu *groupc, u64 now) } static void psi_group_change(struct psi_group *group, int cpu, - unsigned int clear, unsigned int set, u64 now, + unsigned int clear, unsigned int set, bool wake_clock) { struct psi_group_cpu *groupc; unsigned int t, m; enum psi_states s; u32 state_mask; + u64 now; groupc = per_cpu_ptr(group->pcpu, cpu); @@ -981,7 +982,9 @@ static void psi_group_change(struct psi_group *group, int cpu, * change requested through the @clear and @set bits. */ write_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); + update_psi_stat_delta(group, cpu, now); record_times(groupc, now); record_cpu_stat_times(group, cpu); @@ -1110,7 +1113,6 @@ void psi_task_change(struct task_struct *task, int clear, int set) int cpu = task_cpu(task); struct psi_group *group; void *iter = NULL; - u64 now; int stat_set = 0; int stat_clear = 0; @@ -1120,11 +1122,8 @@ void psi_task_change(struct task_struct *task, int clear, int set) psi_flags_change(task, clear, set); psi_stat_flags_change(task, &stat_set, &stat_clear, set, clear); - now = cpu_clock(cpu); - while ((group = iterate_groups(task, &iter))) { - update_psi_stat_delta(group, cpu, now); - psi_group_change(group, cpu, clear, set, now, true); + psi_group_change(group, cpu, clear, set, true); psi_group_stat_change(group, cpu, stat_clear, stat_set); } } @@ -1135,7 +1134,6 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, struct psi_group *group, *common = NULL; int cpu = task_cpu(prev); void *iter; - u64 now = cpu_clock(cpu); if (next->pid) { update_throttle_type(next, cpu, true); @@ -1153,8 +1151,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, break; } - update_psi_stat_delta(group, cpu, now); - psi_group_change(group, cpu, 0, TSK_ONCPU, now, true); + psi_group_change(group, cpu, 0, TSK_ONCPU, true); psi_group_stat_change(group, cpu, 0, 0); } } @@ -1196,8 +1193,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, iter = NULL; while ((group = iterate_groups(prev, &iter)) && group != common) { - update_psi_stat_delta(group, cpu, now); - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); psi_group_stat_change(group, cpu, stat_clear, stat_set); } #ifdef CONFIG_PSI_FINE_GRAINED @@ -1214,8 +1210,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, memstall_type_change) { clear &= ~TSK_ONCPU; for (; group; group = iterate_groups(prev, &iter)) { - update_psi_stat_delta(group, cpu, now); - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); psi_group_stat_change(group, cpu, stat_clear, stat_set); } @@ -1238,12 +1233,11 @@ void psi_account_irqtime(struct task_struct *task, u32 delta) if (!task->pid) return; - now = cpu_clock(cpu); - while ((group = iterate_groups(task, &iter))) { groupc = per_cpu_ptr(group->pcpu, cpu); write_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); update_psi_stat_delta(group, cpu, now); record_stat_times(to_psi_group_ext(group), cpu); -- 2.34.1

2 1

[openeuler:OLK-6.6 1823/1823] drivers/irqchip/irq-gic-v3.c:1086:43: error: incompatible integer to pointer conversion passing 'int' to parameter of type 'void *'
by kernel test robot 14 Jan '25

14 Jan '25

tree: https://gitee.com/openeuler/kernel.git OLK-6.6 head: 4fbc633527d173d6e350da6be39009c6a449a802 commit: 63f9ef213a477c796c6b343010762513f6315f83 [1823/1823] arm64: Add debugfs dir for xint config: arm64-randconfig-004-20250114 (https://download.01.org/0day-ci/archive/20250114/202501140732.yHKX6wmK-lkp@…) compiler: clang version 20.0.0git (https://github.com/llvm/llvm-project f5cd181ffbb7cb61d582fe130d46580d5969d47a) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250114/202501140732.yHKX6wmK-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202501140732.yHKX6wmK-lkp@intel.com/ All errors (new ones prefixed by >>): In file included from drivers/irqchip/irq-gic-v3.c:25: In file included from include/linux/irqchip/arm-gic-v3.h:632: In file included from arch/arm64/include/asm/arch_gicv3.h:17: In file included from arch/arm64/include/asm/cacheflush.h:11: In file included from include/linux/kgdb.h:19: In file included from include/linux/kprobes.h:28: In file included from include/linux/ftrace.h:13: In file included from include/linux/kallsyms.h:13: In file included from include/linux/mm.h:2247: include/linux/vmstat.h:508:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 508 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 509 | item]; | ~~~~ include/linux/vmstat.h:515:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 515 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 516 | NR_VM_NUMA_EVENT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~~ include/linux/vmstat.h:522:36: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion] 522 | return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" | ~~~~~~~~~~~ ^ ~~~ include/linux/vmstat.h:527:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 527 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 528 | NR_VM_NUMA_EVENT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~~ include/linux/vmstat.h:536:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 536 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 537 | NR_VM_NUMA_EVENT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~~ drivers/irqchip/irq-gic-v3.c:1042:23: error: call to undeclared function 'pde_data'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration] 1042 | int irq = (int)(long)pde_data(file_inode(file)); | ^ drivers/irqchip/irq-gic-v3.c:1086:43: error: call to undeclared function 'pde_data'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration] 1086 | return single_open(file, xint_proc_show, pde_data(inode)); | ^ >> drivers/irqchip/irq-gic-v3.c:1086:43: error: incompatible integer to pointer conversion passing 'int' to parameter of type 'void *' [-Wint-conversion] 1086 | return single_open(file, xint_proc_show, pde_data(inode)); | ^~~~~~~~~~~~~~~ include/linux/seq_file.h:166:74: note: passing argument to parameter here 166 | int single_open(struct file *, int (*)(struct seq_file *, void *), void *); | ^ drivers/irqchip/irq-gic-v3.c:1089:30: error: variable has incomplete type 'const struct proc_ops' 1089 | static const struct proc_ops xint_proc_ops = { | ^ drivers/irqchip/irq-gic-v3.c:1089:21: note: forward declaration of 'struct proc_ops' 1089 | static const struct proc_ops xint_proc_ops = { | ^ drivers/irqchip/irq-gic-v3.c:1103:2: error: call to undeclared function 'proc_create_data'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration] 1103 | proc_create_data("xint", 0644, desc->dir, &xint_proc_ops, irqp); | ^ drivers/irqchip/irq-gic-v3.c:1111:2: error: call to undeclared function 'remove_proc_entry'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration] 1111 | remove_proc_entry("xint", desc->dir); | ^ 5 warnings and 6 errors generated. vim +1086 drivers/irqchip/irq-gic-v3.c 3053668e6b2119 Jinjie Ruan 2024-11-25 1083 3053668e6b2119 Jinjie Ruan 2024-11-25 1084 static int xint_proc_open(struct inode *inode, struct file *file) 3053668e6b2119 Jinjie Ruan 2024-11-25 1085 { 3053668e6b2119 Jinjie Ruan 2024-11-25 @1086 return single_open(file, xint_proc_show, pde_data(inode)); 3053668e6b2119 Jinjie Ruan 2024-11-25 1087 } 3053668e6b2119 Jinjie Ruan 2024-11-25 1088 :::::: The code at line 1086 was first introduced by commit :::::: 3053668e6b211924bb67c19d791a5a532eca2ad8 arm64: Introduce Xint software solution :::::: TO: Jinjie Ruan <ruanjinjie(a)huawei.com> :::::: CC: Jinjie Ruan <ruanjinjie(a)huawei.com> -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[openeuler:OLK-6.6 1823/1823] include/../drivers/pci/msi/msi.h:113:57: warning: declaration of 'struct msix_entry' will not be visible outside of this function
by kernel test robot 14 Jan '25

14 Jan '25

tree: https://gitee.com/openeuler/kernel.git OLK-6.6 head: 4fbc633527d173d6e350da6be39009c6a449a802 commit: ad540a13eb8292fc92651b3bf281088a502a85f9 [1823/1823] virtcca feature: fix msi iova map config: arm64-randconfig-004-20250114 (https://download.01.org/0day-ci/archive/20250114/202501140558.Dz2Pe9bS-lkp@…) compiler: clang version 20.0.0git (https://github.com/llvm/llvm-project f5cd181ffbb7cb61d582fe130d46580d5969d47a) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250114/202501140558.Dz2Pe9bS-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202501140558.Dz2Pe9bS-lkp@intel.com/ All warnings (new ones prefixed by >>): In file included from drivers/coda/coda_pci.c:5: In file included from include/linux/kvm_host.h:16: In file included from include/linux/mm.h:2243: include/linux/vmstat.h:508:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 508 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 509 | item]; | ~~~~ include/linux/vmstat.h:515:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 515 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 516 | NR_VM_NUMA_EVENT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~~ include/linux/vmstat.h:522:36: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion] 522 | return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" | ~~~~~~~~~~~ ^ ~~~ include/linux/vmstat.h:527:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 527 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 528 | NR_VM_NUMA_EVENT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~~ include/linux/vmstat.h:536:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 536 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 537 | NR_VM_NUMA_EVENT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~~ In file included from drivers/coda/coda_pci.c:8: >> include/../drivers/pci/msi/msi.h:113:57: warning: declaration of 'struct msix_entry' will not be visible outside of this function [-Wvisibility] 113 | int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, | ^ 6 warnings generated. vim +113 include/../drivers/pci/msi/msi.h 897a0b6aa8c7ee Ahmed S. Darwish 2022-11-11 107 b12d0bec385b7a Ahmed S. Darwish 2022-11-11 108 /* MSI internal functions invoked from the public APIs */ b12d0bec385b7a Ahmed S. Darwish 2022-11-11 109 void pci_msi_shutdown(struct pci_dev *dev); 18e1926b8c8b7c Ahmed S. Darwish 2022-11-11 110 void pci_msix_shutdown(struct pci_dev *dev); b12d0bec385b7a Ahmed S. Darwish 2022-11-11 111 void pci_free_msi_irqs(struct pci_dev *dev); bbda3407982211 Ahmed S. Darwish 2022-11-11 112 int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, struct irq_affinity *affd); be7496c1ef47e1 Ahmed S. Darwish 2022-11-11 @113 int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, be7496c1ef47e1 Ahmed S. Darwish 2022-11-11 114 int maxvec, struct irq_affinity *affd, int flags); 57127da98bc876 Ahmed S. Darwish 2022-11-11 115 void __pci_restore_msi_state(struct pci_dev *dev); 57127da98bc876 Ahmed S. Darwish 2022-11-11 116 void __pci_restore_msix_state(struct pci_dev *dev); b12d0bec385b7a Ahmed S. Darwish 2022-11-11 117 :::::: The code at line 113 was first introduced by commit :::::: be7496c1ef47e1ba8c4b389ee23178fcf066cc4e PCI/MSI: Move pci_enable_msix_range() to api.c :::::: TO: Ahmed S. Darwish <darwi(a)linutronix.de> :::::: CC: Thomas Gleixner <tglx(a)linutronix.de> -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-5.10] [Backport] btrfs: check folio mapping after unlock in relocate_one_folio()
by Yongjian Sun 13 Jan '25

13 Jan '25

mainline inclusion from mainline-v6.12-rc3 commit 3e74859ee35edc33a022c3f3971df066ea0ca6b9 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBG2PL CVE: CVE-2024-56758 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- When we call btrfs_read_folio() to bring a folio uptodate, we unlock the folio. The result of that is that a different thread can modify the mapping (like remove it with invalidate) before we call folio_lock(). This results in an invalid page and we need to try again. In particular, if we are relocating concurrently with aborting a transaction, this can result in a crash like the following: BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0000 [#1] SMP CPU: 76 PID: 1411631 Comm: kworker/u322:5 Workqueue: events_unbound btrfs_reclaim_bgs_work RIP: 0010:set_page_extent_mapped+0x20/0xb0 RSP: 0018:ffffc900516a7be8 EFLAGS: 00010246 RAX: ffffea009e851d08 RBX: ffffea009e0b1880 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffc900516a7b90 RDI: ffffea009e0b1880 RBP: 0000000003573000 R08: 0000000000000001 R09: ffff88c07fd2f3f0 R10: 0000000000000000 R11: 0000194754b575be R12: 0000000003572000 R13: 0000000003572fff R14: 0000000000100cca R15: 0000000005582fff FS: 0000000000000000(0000) GS:ffff88c07fd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000407d00f002 CR4: 00000000007706f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> ? __die+0x78/0xc0 ? page_fault_oops+0x2a8/0x3a0 ? __switch_to+0x133/0x530 ? wq_worker_running+0xa/0x40 ? exc_page_fault+0x63/0x130 ? asm_exc_page_fault+0x22/0x30 ? set_page_extent_mapped+0x20/0xb0 relocate_file_extent_cluster+0x1a7/0x940 relocate_data_extent+0xaf/0x120 relocate_block_group+0x20f/0x480 btrfs_relocate_block_group+0x152/0x320 btrfs_relocate_chunk+0x3d/0x120 btrfs_reclaim_bgs_work+0x2ae/0x4e0 process_scheduled_works+0x184/0x370 worker_thread+0xc6/0x3e0 ? blk_add_timer+0xb0/0xb0 kthread+0xae/0xe0 ? flush_tlb_kernel_range+0x90/0x90 ret_from_fork+0x2f/0x40 ? flush_tlb_kernel_range+0x90/0x90 ret_from_fork_asm+0x11/0x20 </TASK> This occurs because cleanup_one_transaction() calls destroy_delalloc_inodes() which calls invalidate_inode_pages2() which takes the folio_lock before setting mapping to NULL. We fail to check this, and subsequently call set_extent_mapping(), which assumes that mapping != NULL (in fact it asserts that in debug mode) Note that the "fixes" patch here is not the one that introduced the race (the very first iteration of this code from 2009) but a more recent change that made this particular crash happen in practice. Fixes: e7f1326cc24e ("btrfs: set page extent mapped after read_folio in relocate_one_page") CC: stable(a)vger.kernel.org # 6.1+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: Boris Burkov <boris(a)bur.io> Signed-off-by: David Sterba <dsterba(a)suse.com> Conflicts: fs/btrfs/relocation.c [The Evolution from Page to Folio] Signed-off-by: Yongjian Sun <sunyongjian1(a)huawei.com> --- fs/btrfs/relocation.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index a67dd544a52d..48915256fd8b 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2732,7 +2732,7 @@ static int relocate_file_extent_cluster(struct inode *inode, PAGE_SIZE); if (ret) goto out; - +again: page = find_lock_page(inode->i_mapping, index); if (!page) { page_cache_sync_readahead(inode->i_mapping, @@ -2769,6 +2769,11 @@ static int relocate_file_extent_cluster(struct inode *inode, ret = -EIO; goto out; } + if (page->mapping != inode->i_mapping) { + unlock_page(page); + put_page(page); + goto again; + } } page_start = page_offset(page); -- 2.39.2

2 1

[PATCH OLK-5.10] drm/i915/hdcp: Add encoder check in hdcp2_get_capability
by He Yujie 13 Jan '25

13 Jan '25

From: Suraj Kandpal <suraj.kandpal(a)intel.com> mainline inclusion from mainline-v6.12-rc1 commit d34f4f058edf1235c103ca9c921dc54820d14d40 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IB5KQZ CVE: CVE-2024-53050 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Add encoder check in intel_hdcp2_get_capability to avoid null pointer error. Signed-off-by: Suraj Kandpal <suraj.kandpal(a)intel.com> Reviewed-by: Dnyaneshwar Bhadane <dnyaneshwar.bhadane(a)intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240722064451.3610512-3-sura… Conflicts: drivers/gpu/drm/i915/display/intel_hdcp.c drivers/gpu/drm/i915/display/intel_dp_hdcp.c [ Context conflict: 130849f8ec14("drm/i915/hdcp: Use intel_connector as argument for hdcp_2_2_capable") a35239a89259("drm/i915/hdcp: Use correct aux for capability check scenario") 287c0de8b294("drm/i915/hdcp: Move to direct reads for HDCP") 55d9b2b8e440("drm/i915/hdcp: Refactor intel_dp_hdcp2_capable") 8e754d9e9e8a("drm/i915/hdcp: Rename hdcp capable functions") the above patches are not merge. ] Signed-off-by: He Yujie <coka.heyujie(a)huawei.com> --- drivers/gpu/drm/i915/display/intel_hdcp.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 17a8c2e73a82..020dff600883 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -86,7 +86,7 @@ bool intel_hdcp_capable(struct intel_connector *connector) /* Is HDCP2.2 capable on Platform and Sink */ bool intel_hdcp2_capable(struct intel_connector *connector) { - struct intel_digital_port *dig_port = intel_attached_dig_port(connector); + struct intel_digital_port *dig_port; struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_hdcp *hdcp = &connector->hdcp; bool capable = false; @@ -103,6 +103,11 @@ bool intel_hdcp2_capable(struct intel_connector *connector) } mutex_unlock(&dev_priv->hdcp_comp_mutex); + if (!intel_attached_encoder(connector)) + return false; + + dig_port = intel_attached_dig_port(connector); + /* Sink's capability for HDCP2.2 */ hdcp->shim->hdcp_2_2_capable(dig_port, &capable); -- 2.34.1

2 1

[PATCH OLK-5.10] octeontx2-pf: handle otx2_mbox_get_rsp errors in otx2_ethtool.c
by He Yujie 13 Jan '25

13 Jan '25

From: Dipendra Khadka <kdipendra88(a)gmail.com> stable inclusion from stable-v5.10.231 commit 5ff9de1f2712cbca53da2e37d831eea7ffcb43b6 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEGGI CVE: CVE-2024-56728 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit e26f8eac6bb20b20fdb8f7dc695711ebce4c7c5c ] Add error pointer check after calling otx2_mbox_get_rsp(). Fixes: 75f36270990c ("octeontx2-pf: Support to enable/disable pause frames via ethtool") Fixes: d0cf9503e908 ("octeontx2-pf: ethtool fec mode support") Signed-off-by: Dipendra Khadka <kdipendra88(a)gmail.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Signed-off-by: Andrew Lunn <andrew(a)lunn.ch> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c [ Context conflict: d0cf9503e908 ("octeontx2-pf: ethtool fec mode support") is not merged ] Signed-off-by: He Yujie <coka.heyujie(a)huawei.com> --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 196354c142fe..43642eab200a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -264,6 +264,11 @@ static void otx2_get_pauseparam(struct net_device *netdev, if (!otx2_sync_mbox_msg(&pfvf->mbox)) { rsp = (struct cgx_pause_frm_cfg *) otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &req->hdr); + if (IS_ERR(rsp)) { + mutex_unlock(&pfvf->mbox.lock); + return; + } + pause->rx_pause = rsp->rx_pause; pause->tx_pause = rsp->tx_pause; } -- 2.34.1

2 1