- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6 v2] PCI/sysfs: Take reference on device to be removed
by Xiongfeng Wang 22 Jan '24

22 Jan '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8XVM8 CVE: NA ------------------------------------ When I do some aer-inject and sysfs remove stress tests, I got the following use-after-free Calltrace: ================================================================== BUG: KASAN: use-after-free in pci_stop_bus_device+0x174/0x178 Read of size 8 at addr fffffc3e2e402218 by task bash/26311 CPU: 38 PID: 26311 Comm: bash Tainted: G W 4.19.105+ #82 Hardware name: Huawei TaiShan 2280 V2/BC82AMDC, BIOS 2280-V2 CS V5.B161.01 06/10/2021 Call trace: dump_backtrace+0x0/0x360 show_stack+0x24/0x30 dump_stack+0x130/0x164 print_address_description+0x68/0x278 kasan_report+0x204/0x330 __asan_report_load8_noabort+0x30/0x40 pci_stop_bus_device+0x174/0x178 pci_stop_and_remove_bus_device_locked+0x24/0x40 remove_store+0x1c8/0x1e0 dev_attr_store+0x60/0x80 sysfs_kf_write+0x104/0x170 kernfs_fop_write+0x23c/0x430 __vfs_write+0xec/0x4e0 vfs_write+0x12c/0x3d0 ksys_write+0xe8/0x208 __arm64_sys_write+0x70/0xa0 el0_svc_common+0x10c/0x450 el0_svc_handler+0x50/0xc0 el0_svc+0x10/0x14 Allocated by task 684: kasan_kmalloc+0xe0/0x190 kmem_cache_alloc_trace+0x110/0x240 pci_alloc_dev+0x4c/0x110 pci_scan_single_device+0x100/0x218 pci_scan_slot+0x8c/0x2d8 pci_scan_child_bus_extend+0x90/0x628 pci_scan_child_bus+0x24/0x30 pci_scan_bridge_extend+0x3b8/0xb28 pci_scan_child_bus_extend+0x350/0x628 pci_rescan_bus+0x24/0x48 pcie_do_fatal_recovery+0x390/0x4b0 handle_error_source+0x124/0x158 aer_isr+0x5a0/0x800 process_one_work+0x598/0x1250 worker_thread+0x384/0xf08 kthread+0x2a4/0x320 ret_from_fork+0x10/0x18 Freed by task 685: __kasan_slab_free+0x120/0x228 kasan_slab_free+0x10/0x18 kfree+0x88/0x218 pci_release_dev+0xb4/0xd8 device_release+0x6c/0x1c0 kobject_put+0x12c/0x400 put_device+0x24/0x30 pci_dev_put+0x24/0x30 handle_error_source+0x12c/0x158 aer_isr+0x5a0/0x800 process_one_work+0x598/0x1250 worker_thread+0x384/0xf08 kthread+0x2a4/0x320 ret_from_fork+0x10/0x18 The buggy address belongs to the object at fffffc3e2e402200 which belongs to the cache kmalloc-4096 of size 4096 The buggy address is located 24 bytes inside of 4096-byte region [fffffc3e2e402200, fffffc3e2e403200) The buggy address belongs to the page: page:ffff7ff0f8b90000 count:1 mapcount:0 mapping:ffffdc365f016e00 index:0x0 compound_mapcount: 0 flags: 0x6ffffe0000008100(slab|head) raw: 6ffffe0000008100 ffff7f70d83aae00 0000000300000003 ffffdc365f016e00 raw: 0000000000000000 0000000080070007 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: fffffc3e2e402100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fffffc3e2e402180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >fffffc3e2e402200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ fffffc3e2e402280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fffffc3e2e402300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== It is caused by the following race condition: CPU0 CPU1 remove_store() aer_isr() device_remove_file_self() handle_error_source() pci_stop_and_remove_bus_device_locked pcie_do_fatal_recovery() (blocked) pci_lock_rescan_remove() #CPU1 acquire the lock pci_stop_and_remove_bus_device() pci_unlock_rescan_remove() #CPU1 release the lock pci_lock_rescan_remove() #CPU0 acquire the lock pci_dev_put() #free pci_dev pci_stop_and_remove_bus_device() pci_stop_bus_device() #use-after-free pci_unlock_rescan_remove() An AER interrupt is triggered on CPU1. CPU1 starts to process it. A work 'aer_isr()' is scheduled on CPU1. It calling into pcie_do_fatal_recovery(), and aquire lock 'pci_rescan_remove_lock'. Before it removes the sysfs corresponding to the error pci device, a sysfs remove operation is executed on CPU0. CPU0 use device_remove_file_self() to remove the sysfs directory and wait for the lock to be released. After CPU1 finish pci_stop_and_remove_bus_device(), it release the lock and free the 'pci_dev' in pci_dev_put(). CPU0 acquire the lock and access the 'pci_dev'. Then a use-after-free is triggered. To fix this issue, we increase the reference count in remove_store() before remove the device and decrease the reference count in the end. Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> Conflicts: drivers/pci/pci-sysfs.c Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> --- drivers/pci/pci-sysfs.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 3317b9354716..e3373cdc5244 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -483,12 +483,17 @@ static ssize_t remove_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { unsigned long val; + struct pci_dev *pdev = to_pci_dev(dev); if (kstrtoul(buf, 0, &val) < 0) return -EINVAL; - if (val && device_remove_file_self(dev, attr)) - pci_stop_and_remove_bus_device_locked(to_pci_dev(dev)); + if (val) { + pci_dev_get(pdev); + if (device_remove_file_self(dev, attr)) + pci_stop_and_remove_bus_device_locked(pdev); + pci_dev_put(pdev); + } return count; } static DEVICE_ATTR_IGNORE_LOCKDEP(remove, 0220, NULL, -- 2.20.1

2 1

[PATCH OLK-6.6 v2] arm64: Add the arm64.nolse command line option
by Wei Li 22 Jan '24

22 Jan '24

From: Maria Yu <quic_aiquny(a)quicinc.com> maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4JBSJ CVE: NA Reference: https://lore.kernel.org/all/20230710055955.36551-1-quic_aiquny@quicinc.com/ -------------------------------- In order to be able to disable lse_atomic even if cpu support it, most likely because of memory controller cannot deal with the lse atomic instructions, use a new idreg override to deal with it. Signed-off-by: Maria Yu <quic_aiquny(a)quicinc.com> [liwei: Remane "arm64.nolse_atomics" to "arm64.nolse"] Signed-off-by: Wei Li <liwei391(a)huawei.com> --- Documentation/admin-guide/kernel-parameters.txt | 2 ++ arch/arm64/include/asm/cpufeature.h | 1 + arch/arm64/kernel/cpufeature.c | 4 +++- arch/arm64/kernel/idreg-override.c | 11 +++++++++++ 4 files changed, 17 insertions(+), 1 deletion(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 53c15bb5b977..4bf7d0ba2495 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -418,6 +418,8 @@ arm64.nobti [ARM64] Unconditionally disable Branch Target Identification support + arm64.nolse [ARM64] Unconditionally disable LSE Atomic support + arm64.nomops [ARM64] Unconditionally disable Memory Copy and Memory Set instructions support diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 5bba39376055..edc84c0bc16a 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -916,6 +916,7 @@ extern struct arm64_ftr_override id_aa64pfr0_override; extern struct arm64_ftr_override id_aa64pfr1_override; extern struct arm64_ftr_override id_aa64zfr0_override; extern struct arm64_ftr_override id_aa64smfr0_override; +extern struct arm64_ftr_override id_aa64isar0_override; extern struct arm64_ftr_override id_aa64isar1_override; extern struct arm64_ftr_override id_aa64isar2_override; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 455e72ce080a..75757aad5d99 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -670,6 +670,7 @@ struct arm64_ftr_override __ro_after_init id_aa64pfr0_override; struct arm64_ftr_override __ro_after_init id_aa64pfr1_override; struct arm64_ftr_override __ro_after_init id_aa64zfr0_override; struct arm64_ftr_override __ro_after_init id_aa64smfr0_override; +struct arm64_ftr_override __ro_after_init id_aa64isar0_override; struct arm64_ftr_override __ro_after_init id_aa64isar1_override; struct arm64_ftr_override __ro_after_init id_aa64isar2_override; @@ -722,7 +723,8 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_AA64DFR1_EL1, ftr_raz), /* Op1 = 0, CRn = 0, CRm = 6 */ - ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0), + ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0, + &id_aa64isar0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1, &id_aa64isar1_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2, diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index 3addc09f8746..19a730db3e37 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -105,6 +105,15 @@ static const struct ftr_set_desc pfr1 __initconst = { }, }; +static const struct ftr_set_desc isar0 __initconst = { + .name = "id_aa64isar0", + .override = &id_aa64isar0_override, + .fields = { + FIELD("atomic", ID_AA64ISAR0_EL1_ATOMIC_SHIFT, NULL), + {} + }, +}; + static const struct ftr_set_desc isar1 __initconst = { .name = "id_aa64isar1", .override = &id_aa64isar1_override, @@ -163,6 +172,7 @@ static const struct ftr_set_desc * const regs[] __initconst = { &mmfr1, &pfr0, &pfr1, + &isar0, &isar1, &isar2, &smfr0, @@ -185,6 +195,7 @@ static const struct { { "arm64.nomops", "id_aa64isar2.mops=0" }, { "arm64.nomte", "id_aa64pfr1.mte=0" }, { "nokaslr", "arm64_sw.nokaslr=1" }, + { "arm64.nolse", "id_aa64isar0.atomic=0" }, }; static int __init parse_nokaslr(char *unused) -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] netfilter: nf_tables: fix pointer math issue in nft_byteorder_eval()
by Liu Jian 21 Jan '24

21 Jan '24

From: Dan Carpenter <dan.carpenter(a)linaro.org> mainline inclusion from mainline-v6.7-rc2 commit c301f0981fdd3fd1ffac6836b423c4d7a8e0eb63 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8WQRG CVE: CVE-2024-0607 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- The problem is in nft_byteorder_eval() where we are iterating through a loop and writing to dst[0], dst[1], dst[2] and so on... On each iteration we are writing 8 bytes. But dst[] is an array of u32 so each element only has space for 4 bytes. That means that every iteration overwrites part of the previous element. I spotted this bug while reviewing commit caf3ef7468f7 ("netfilter: nf_tables: prevent OOB access in nft_byteorder_eval") which is a related issue. I think that the reason we have not detected this bug in testing is that most of time we only write one element. Fixes: ce1e7989d989 ("netfilter: nft_byteorder: provide 64bit le/be conversion") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: include/net/netfilter/nf_tables.h net/netfilter/nft_byteorder.c net/netfilter/nft_meta.c --- net/netfilter/nft_byteorder.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 46a8f894717c..ba65e1e8732b 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -41,19 +41,20 @@ static void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->size) { case 8: { + u64 *dst64 = (void *)dst; u64 src64; switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 8; i++) { src64 = get_unaligned((u64 *)&src[i]); - put_unaligned_be64(src64, &dst[i]); + put_unaligned_be64(src64, &dst64[i]); } break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 8; i++) { src64 = get_unaligned_be64(&src[i]); - put_unaligned(src64, (u64 *)&dst[i]); + put_unaligned(src64, (u64 *)&dst64[i]); } break; } -- 2.34.1

2 1

[PATCH OLK-5.10] netfilter: nf_tables: fix pointer math issue in nft_byteorder_eval()
by Liu Jian 21 Jan '24

21 Jan '24

From: Dan Carpenter <dan.carpenter(a)linaro.org> mainline inclusion from mainline-v6.7-rc2 commit c301f0981fdd3fd1ffac6836b423c4d7a8e0eb63 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8WQRG CVE: CVE-2024-0607 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- The problem is in nft_byteorder_eval() where we are iterating through a loop and writing to dst[0], dst[1], dst[2] and so on... On each iteration we are writing 8 bytes. But dst[] is an array of u32 so each element only has space for 4 bytes. That means that every iteration overwrites part of the previous element. I spotted this bug while reviewing commit caf3ef7468f7 ("netfilter: nf_tables: prevent OOB access in nft_byteorder_eval") which is a related issue. I think that the reason we have not detected this bug in testing is that most of time we only write one element. Fixes: ce1e7989d989 ("netfilter: nft_byteorder: provide 64bit le/be conversion") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: include/net/netfilter/nf_tables.h net/netfilter/nft_byteorder.c --- include/net/netfilter/nf_tables.h | 4 ++-- net/netfilter/nft_byteorder.c | 5 +++-- net/netfilter/nft_meta.c | 2 +- 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index ea893a6d9b36..7550328080bf 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -132,9 +132,9 @@ static inline u16 nft_reg_load16(const u32 *sreg) return *(u16 *)sreg; } -static inline void nft_reg_store64(u32 *dreg, u64 val) +static inline void nft_reg_store64(u64 *dreg, u64 val) { - put_unaligned(val, (u64 *)dreg); + put_unaligned(val, dreg); } static inline u64 nft_reg_load64(const u32 *sreg) diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 7b0b8fecb220..9d250bd60bb8 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -38,20 +38,21 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->size) { case 8: { + u64 *dst64 = (void *)dst; u64 src64; switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 8; i++) { src64 = nft_reg_load64(&src[i]); - nft_reg_store64(&dst[i], be64_to_cpu(src64)); + nft_reg_store64(&dst64[i], be64_to_cpu(src64)); } break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 8; i++) { src64 = (__force __u64) cpu_to_be64(nft_reg_load64(&src[i])); - nft_reg_store64(&dst[i], src64); + nft_reg_store64(&dst64[i], src64); } break; } diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 44d9b38e5f90..cb5bb0e21b66 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -63,7 +63,7 @@ nft_meta_get_eval_time(enum nft_meta_keys key, { switch (key) { case NFT_META_TIME_NS: - nft_reg_store64(dest, ktime_get_real_ns()); + nft_reg_store64((u64 *)dest, ktime_get_real_ns()); break; case NFT_META_TIME_DAY: nft_reg_store8(dest, nft_meta_weekday()); -- 2.34.1

2 1

[PATCH OLK-6.6] sched: programmable: Fix is_cpu_allowed build error
by Cheng Yu 20 Jan '24

20 Jan '24

From: Guan Jing <guanjing6(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8OIT1 -------------------------------- Patch fixes build errors like this: kernel/sched/sched.h:3625:13: error: inlining failed in call to ‘always_inline’ ‘is_cpu_allowed’: function body not available Signed-off-by: Guan Jing <guanjing6(a)huawei.com> --- kernel/sched/core.c | 11 +++++++---- kernel/sched/fair.c | 2 +- kernel/sched/sched.h | 2 +- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f49884275d02..d4f19e578341 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2469,11 +2469,7 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) * Per-CPU kthreads are allowed to run on !active && online CPUs, see * __set_cpus_allowed_ptr() and select_fallback_rq(). */ -#ifdef CONFIG_BPF_SCHED -inline bool is_cpu_allowed(struct task_struct *p, int cpu) -#else static inline bool is_cpu_allowed(struct task_struct *p, int cpu) -#endif { /* When not in the task's cpumask, no point in looking further. */ if (!cpumask_test_cpu(cpu, p->cpus_ptr)) @@ -2499,6 +2495,13 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) return cpu_online(cpu); } +#ifdef CONFIG_BPF_SCHED +bool bpf_sched_is_cpu_allowed(struct task_struct *p, int cpu) +{ + return is_cpu_allowed(p, cpu); +} +#endif + /* * This is how migration works: * diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index b0f65c68f6bb..8e180ede46d3 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8523,7 +8523,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags) ctx.select_idle_mask = this_cpu_cpumask_var_ptr(select_idle_mask); ret = bpf_sched_cfs_select_rq(&ctx); - if (ret >= 0 && is_cpu_allowed(p, ret)) { + if (ret >= 0 && bpf_sched_is_cpu_allowed(p, ret)) { rcu_read_unlock(); return ret; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b7ba69337453..150c65128adb 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3622,7 +3622,7 @@ extern u64 avg_vruntime(struct cfs_rq *cfs_rq); extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se); #ifdef CONFIG_BPF_SCHED -inline bool is_cpu_allowed(struct task_struct *p, int cpu); +bool bpf_sched_is_cpu_allowed(struct task_struct *p, int cpu); #endif #endif /* _KERNEL_SCHED_SCHED_H */ -- 2.34.1

2 1

[PATCH OLK-6.6] sched: programmable: Fix is_cpu_allowed build error
by Cheng Yu 20 Jan '24

20 Jan '24

From: Guan Jing <guanjing6(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8OIT1 -------------------------------- Patch fixes build errors like this: kernel/sched/sched.h:3625:13: error: inlining failed in call to ‘always_inline’ ‘is_cpu_allowed’: function body not available Signed-off-by: Guan Jing <guanjing6(a)huawei.com> --- kernel/sched/core.c | 34 ---------------------------------- kernel/sched/sched.h | 33 ++++++++++++++++++++++++++++++--- 2 files changed, 30 insertions(+), 37 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f49884275d02..fab7d434bd9b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2465,40 +2465,6 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) return rq->nr_pinned; } -/* - * Per-CPU kthreads are allowed to run on !active && online CPUs, see - * __set_cpus_allowed_ptr() and select_fallback_rq(). - */ -#ifdef CONFIG_BPF_SCHED -inline bool is_cpu_allowed(struct task_struct *p, int cpu) -#else -static inline bool is_cpu_allowed(struct task_struct *p, int cpu) -#endif -{ - /* When not in the task's cpumask, no point in looking further. */ - if (!cpumask_test_cpu(cpu, p->cpus_ptr)) - return false; - - /* migrate_disabled() must be allowed to finish. */ - if (is_migration_disabled(p)) - return cpu_online(cpu); - - /* Non kernel threads are not allowed during either online or offline. */ - if (!(p->flags & PF_KTHREAD)) - return cpu_active(cpu) && task_cpu_possible(cpu, p); - - /* KTHREAD_IS_PER_CPU is always allowed. */ - if (kthread_is_per_cpu(p)) - return cpu_online(cpu); - - /* Regular kernel threads don't get to stay during offline. */ - if (cpu_dying(cpu)) - return false; - - /* But are allowed during online. */ - return cpu_online(cpu); -} - /* * This is how migration works: * diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b7ba69337453..f23550fa4b73 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -68,6 +68,7 @@ #include <linux/wait_api.h> #include <linux/wait_bit.h> #include <linux/workqueue_api.h> +#include <linux/mmu_context.h> #include <trace/events/power.h> #include <trace/events/sched.h> @@ -3621,8 +3622,34 @@ static inline void init_sched_mm_cid(struct task_struct *t) { } extern u64 avg_vruntime(struct cfs_rq *cfs_rq); extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se); -#ifdef CONFIG_BPF_SCHED -inline bool is_cpu_allowed(struct task_struct *p, int cpu); -#endif +/* + * Per-CPU kthreads are allowed to run on !active && online CPUs, see + * __set_cpus_allowed_ptr() and select_fallback_rq(). + */ +static inline bool is_cpu_allowed(struct task_struct *p, int cpu) +{ + /* When not in the task's cpumask, no point in looking further. */ + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + return false; + + /* migrate_disabled() must be allowed to finish. */ + if (is_migration_disabled(p)) + return cpu_online(cpu); + + /* Non kernel threads are not allowed during either online or offline. */ + if (!(p->flags & PF_KTHREAD)) + return cpu_active(cpu) && task_cpu_possible(cpu, p); + + /* KTHREAD_IS_PER_CPU is always allowed. */ + if (kthread_is_per_cpu(p)) + return cpu_online(cpu); + + /* Regular kernel threads don't get to stay during offline. */ + if (cpu_dying(cpu)) + return false; + + /* But are allowed during online. */ + return cpu_online(cpu); +} #endif /* _KERNEL_SCHED_SCHED_H */ -- 2.34.1

2 1

[PATCH] sched: programmable: Fix is_cpu_allowed build error
by Cheng Yu 20 Jan '24

20 Jan '24

From: Guan Jing <guanjing6(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8OIT1 -------------------------------- Patch fixes build errors like this: kernel/sched/sched.h:3625:13: error: inlining failed in call to ‘always_inline’ ‘is_cpu_allowed’: function body not available Signed-off-by: Guan Jing <guanjing6(a)huawei.com> --- kernel/sched/core.c | 34 ---------------------------------- kernel/sched/sched.h | 33 ++++++++++++++++++++++++++++++--- 2 files changed, 30 insertions(+), 37 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f49884275d02..fab7d434bd9b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2465,40 +2465,6 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) return rq->nr_pinned; } -/* - * Per-CPU kthreads are allowed to run on !active && online CPUs, see - * __set_cpus_allowed_ptr() and select_fallback_rq(). - */ -#ifdef CONFIG_BPF_SCHED -inline bool is_cpu_allowed(struct task_struct *p, int cpu) -#else -static inline bool is_cpu_allowed(struct task_struct *p, int cpu) -#endif -{ - /* When not in the task's cpumask, no point in looking further. */ - if (!cpumask_test_cpu(cpu, p->cpus_ptr)) - return false; - - /* migrate_disabled() must be allowed to finish. */ - if (is_migration_disabled(p)) - return cpu_online(cpu); - - /* Non kernel threads are not allowed during either online or offline. */ - if (!(p->flags & PF_KTHREAD)) - return cpu_active(cpu) && task_cpu_possible(cpu, p); - - /* KTHREAD_IS_PER_CPU is always allowed. */ - if (kthread_is_per_cpu(p)) - return cpu_online(cpu); - - /* Regular kernel threads don't get to stay during offline. */ - if (cpu_dying(cpu)) - return false; - - /* But are allowed during online. */ - return cpu_online(cpu); -} - /* * This is how migration works: * diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b7ba69337453..f23550fa4b73 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -68,6 +68,7 @@ #include <linux/wait_api.h> #include <linux/wait_bit.h> #include <linux/workqueue_api.h> +#include <linux/mmu_context.h> #include <trace/events/power.h> #include <trace/events/sched.h> @@ -3621,8 +3622,34 @@ static inline void init_sched_mm_cid(struct task_struct *t) { } extern u64 avg_vruntime(struct cfs_rq *cfs_rq); extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se); -#ifdef CONFIG_BPF_SCHED -inline bool is_cpu_allowed(struct task_struct *p, int cpu); -#endif +/* + * Per-CPU kthreads are allowed to run on !active && online CPUs, see + * __set_cpus_allowed_ptr() and select_fallback_rq(). + */ +static inline bool is_cpu_allowed(struct task_struct *p, int cpu) +{ + /* When not in the task's cpumask, no point in looking further. */ + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + return false; + + /* migrate_disabled() must be allowed to finish. */ + if (is_migration_disabled(p)) + return cpu_online(cpu); + + /* Non kernel threads are not allowed during either online or offline. */ + if (!(p->flags & PF_KTHREAD)) + return cpu_active(cpu) && task_cpu_possible(cpu, p); + + /* KTHREAD_IS_PER_CPU is always allowed. */ + if (kthread_is_per_cpu(p)) + return cpu_online(cpu); + + /* Regular kernel threads don't get to stay during offline. */ + if (cpu_dying(cpu)) + return false; + + /* But are allowed during online. */ + return cpu_online(cpu); +} #endif /* _KERNEL_SCHED_SCHED_H */ -- 2.34.1

1 0

[PATCH OLK-5.10 v2 0/2] x86/quirks: Add parameter to clear MSIs early
by Zheng Zengkai 19 Jan '24

19 Jan '24

A crash kernel boot failure issue is reported in openeuler 5.10 series kernel(in x86 virtual machine with Hi1822 virtual nic). Finally the issue was narrowed down to irq vector conflict. Backport following patchset from kernel maillist to fix this issue. https://lore.kernel.org/linux-pci/20181018183721.27467-3-gpiccoli@canonical… Guilherme G. Piccoli (2): x86/PCI: Export find_cap() to be used in early PCI code x86/quirks: Add parameter to clear MSIs early on boot .../admin-guide/kernel-parameters.txt | 6 ++++ arch/x86/include/asm/pci-direct.h | 2 ++ arch/x86/kernel/aperture_64.c | 30 ++--------------- arch/x86/kernel/early-quirks.c | 32 +++++++++++++++++++ arch/x86/pci/common.c | 4 +++ arch/x86/pci/early.c | 25 +++++++++++++++ 6 files changed, 71 insertions(+), 28 deletions(-) -- 2.20.1

2 3

[PATCH OLK-5.10 V1] ida: Fix crash in ida_free when the bitmap is empty
by Cheng Yu 19 Jan '24

19 Jan '24

From: "Matthew Wilcox (Oracle)" <willy(a)infradead.org> mainline inclusion from mainline-v6.7-rc7 commit af73483f4e8b6f5c68c9aa63257bdd929a9c194a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8WBGZ CVE: CVE-2023-6915 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The IDA usually detects double-frees, but that detection failed to consider the case when there are no nearby IDs allocated and so we have a NULL bitmap rather than simply having a clear bit. Add some tests to the test-suite to be sure we don't inadvertently reintroduce this problem. Unfortunately they're quite noisy so include a message to disregard the warnings. Reported-by: Zhenghan Wang <wzhmmmmm(a)gmail.com> Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Cheng Yu <serein.chengyu(a)huawei.com> --- lib/idr.c | 2 +- lib/test_ida.c | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+), 1 deletion(-) diff --git a/lib/idr.c b/lib/idr.c index 7ecdfdb5309e..8331b44dd39e 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -508,7 +508,7 @@ void ida_free(struct ida *ida, unsigned int id) goto delete; xas_store(&xas, xa_mk_value(v)); } else { - if (!test_bit(bit, bitmap->bitmap)) + if (!bitmap || !test_bit(bit, bitmap->bitmap)) goto err; __clear_bit(bit, bitmap->bitmap); xas_set_mark(&xas, XA_FREE_MARK); diff --git a/lib/test_ida.c b/lib/test_ida.c index b06880625961..55105baa19da 100644 --- a/lib/test_ida.c +++ b/lib/test_ida.c @@ -150,6 +150,45 @@ static void ida_check_conv(struct ida *ida) IDA_BUG_ON(ida, !ida_is_empty(ida)); } +/* + * Check various situations where we attempt to free an ID we don't own. + */ +static void ida_check_bad_free(struct ida *ida) +{ + unsigned long i; + + printk("vvv Ignore \"not allocated\" warnings\n"); + /* IDA is empty; all of these will fail */ + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a single value entry */ + IDA_BUG_ON(ida, ida_alloc_min(ida, 3, GFP_KERNEL) != 3); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a single bitmap */ + IDA_BUG_ON(ida, ida_alloc_min(ida, 1023, GFP_KERNEL) != 1023); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a tree */ + IDA_BUG_ON(ida, ida_alloc_min(ida, (1 << 20) - 1, GFP_KERNEL) != (1 << 20) - 1); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + printk("^^^ \"not allocated\" warnings over\n"); + + ida_free(ida, 3); + ida_free(ida, 1023); + ida_free(ida, (1 << 20) - 1); + + IDA_BUG_ON(ida, !ida_is_empty(ida)); +} + static DEFINE_IDA(ida); static int ida_checks(void) @@ -162,6 +201,7 @@ static int ida_checks(void) ida_check_leaf(&ida, 1024 * 64); ida_check_max(&ida); ida_check_conv(&ida); + ida_check_bad_free(&ida); printk("IDA: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run != tests_passed) ? 0 : -EINVAL; -- 2.25.1

2 1

[PATCH OLK-5.10 V1] ida: Fix crash in ida_free when the bitmap is empty
by Cheng Yu 19 Jan '24

19 Jan '24

From: "Matthew Wilcox (Oracle)" <willy(a)infradead.org> mainline inclusion from mainline-v6.7-rc7 commit af73483f4e8b6f5c68c9aa63257bdd929a9c194a category: bugfix bugzilla: 189479 CVE: CVE-2023-6915 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The IDA usually detects double-frees, but that detection failed to consider the case when there are no nearby IDs allocated and so we have a NULL bitmap rather than simply having a clear bit. Add some tests to the test-suite to be sure we don't inadvertently reintroduce this problem. Unfortunately they're quite noisy so include a message to disregard the warnings. Reported-by: Zhenghan Wang <wzhmmmmm(a)gmail.com> Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Cheng Yu <serein.chengyu(a)huawei.com> --- lib/idr.c | 2 +- lib/test_ida.c | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+), 1 deletion(-) diff --git a/lib/idr.c b/lib/idr.c index 7ecdfdb5309e..8331b44dd39e 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -508,7 +508,7 @@ void ida_free(struct ida *ida, unsigned int id) goto delete; xas_store(&xas, xa_mk_value(v)); } else { - if (!test_bit(bit, bitmap->bitmap)) + if (!bitmap || !test_bit(bit, bitmap->bitmap)) goto err; __clear_bit(bit, bitmap->bitmap); xas_set_mark(&xas, XA_FREE_MARK); diff --git a/lib/test_ida.c b/lib/test_ida.c index b06880625961..55105baa19da 100644 --- a/lib/test_ida.c +++ b/lib/test_ida.c @@ -150,6 +150,45 @@ static void ida_check_conv(struct ida *ida) IDA_BUG_ON(ida, !ida_is_empty(ida)); } +/* + * Check various situations where we attempt to free an ID we don't own. + */ +static void ida_check_bad_free(struct ida *ida) +{ + unsigned long i; + + printk("vvv Ignore \"not allocated\" warnings\n"); + /* IDA is empty; all of these will fail */ + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a single value entry */ + IDA_BUG_ON(ida, ida_alloc_min(ida, 3, GFP_KERNEL) != 3); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a single bitmap */ + IDA_BUG_ON(ida, ida_alloc_min(ida, 1023, GFP_KERNEL) != 1023); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a tree */ + IDA_BUG_ON(ida, ida_alloc_min(ida, (1 << 20) - 1, GFP_KERNEL) != (1 << 20) - 1); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + printk("^^^ \"not allocated\" warnings over\n"); + + ida_free(ida, 3); + ida_free(ida, 1023); + ida_free(ida, (1 << 20) - 1); + + IDA_BUG_ON(ida, !ida_is_empty(ida)); +} + static DEFINE_IDA(ida); static int ida_checks(void) @@ -162,6 +201,7 @@ static int ida_checks(void) ida_check_leaf(&ida, 1024 * 64); ida_check_max(&ida); ida_check_conv(&ida); + ida_check_bad_free(&ida); printk("IDA: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run != tests_passed) ? 0 : -EINVAL; -- 2.25.1

2 1

[PATCH OLK-6.6 0/6] backport two page_owner patchsets:
by Jinjiang Tu 19 Jan '24

19 Jan '24

Backport two page_owner patchsets: * Fix page_owner's use of free timestamps * mm/page_owner: record and dump free_pid and free_tgid Audra Mitchell (5): mm/page_owner: remove free_ts from page_owner output tools/mm: remove references to free_ts from page_owner_sort tools/mm: filter out timestamps for correct collation tools/mm: fix the default case for page_owner_sort tools/mm: update the usage output to be more organized Barry Song (1): mm/page_owner: record and dump free_pid and free_tgid mm/page_owner.c | 13 ++- tools/mm/page_owner_sort.c | 217 ++++++++++++++++++------------------- 2 files changed, 113 insertions(+), 117 deletions(-) -- 2.25.1

2 7

[PATCH OLK-5.10 0/3] LoongArch: Optimize memory ops
by liweihao 19 Jan '24

19 Jan '24

Backport memory ops from upstream. WANG Rui (2): LoongArch: Optimize memory ops (memset/memcpy/memmove) LoongArch: Fix return value underflow in exception path Weihao Li (1): LoongArch: Adjust {copy, clear}_user exception handler behavior arch/loongarch/lib/clear_user.S | 166 +++++++++++++++---- arch/loongarch/lib/copy_user.S | 271 +++++++++++++++++++++++++------- arch/loongarch/lib/memcpy.S | 146 ++++++++++++++--- arch/loongarch/lib/memmove.S | 120 ++++++++------ arch/loongarch/lib/memset.S | 116 +++++++++++--- 5 files changed, 631 insertions(+), 188 deletions(-) -- 2.39.2

2 4

[PATCH OLK-5.10 0/2] LoongArch: Allow usage of LSX/LASX in the kernel
by liweihao 19 Jan '24

19 Jan '24

Backport patches from upstream so we can use LSX/LASX in the kernel. Huacai Chen (2): LoongArch: Provide kernel fpu functions LoongArch: Allow usage of LSX/LASX in the kernel arch/loongarch/include/asm/fpu.h | 3 ++ arch/loongarch/kernel/Makefile | 2 +- arch/loongarch/kernel/kfpu.c | 90 ++++++++++++++++++++++++++++++++ 3 files changed, 94 insertions(+), 1 deletion(-) create mode 100644 arch/loongarch/kernel/kfpu.c -- 2.39.2

2 3

[PATCH OLK-5.10 1/5] LoongArch: Optimize memory ops (memset/memcpy/memmove)
by liweihao 19 Jan '24

19 Jan '24

From: WANG Rui <wangrui(a)loongson.cn> LoongArch inclusion bugzilla: https://gitee.com/openeuler/kernel/issues/I76XQZ To optimize memset()/memcpy()/memmove() and so on, we use a jump table to dispatch cases for short data lengths; and for long data lengths, we split the destination into head part (first 8 bytes), tail part (last 8 bytes) and middle part. The head part and tail part may be at unaligned addresses, while the middle part is always aligned (the middle part is allowed to overlap the head/tail part). In this way, the first and last 8 bytes may be unaligned accesses, but we can make sure the data in the middle is processed at an aligned destination address. We have tested micro-bench[1] on a Loongson-3C5000 16-core machine (2.2GHz): 1. memset | length | src offset | dst offset | speed before | speed after | % | |--------|------------|------------|--------------|-------------|---------| | 8 | 0 | 0 | 696.191 | 1518.785 | 118.16% | | 8 | 0 | 1 | 696.325 | 1518.937 | 118.14% | | 50 | 0 | 0 | 969.976 | 8053.902 | 730.32% | | 50 | 0 | 1 | 970.034 | 8058.475 | 730.74% | | 300 | 0 | 0 | 5876.612 | 16544.703 | 181.53% | | 300 | 0 | 1 | 5030.849 | 16549.011 | 228.95% | | 1200 | 0 | 0 | 11797.077 | 16752.137 | 42.00% | | 1200 | 0 | 1 | 5687.141 | 16645.233 | 192.68% | | 4000 | 0 | 0 | 15723.27 | 16761.557 | 6.60% | | 4000 | 0 | 1 | 5906.114 | 16732.316 | 183.30% | | 8000 | 0 | 0 | 16751.403 | 16770.002 | 0.11% | | 8000 | 0 | 1 | 5995.449 | 16754.07 | 179.45% | 2. memcpy | length | src offset | dst offset | speed before | speed after | % | |--------|------------|------------|--------------|-------------|---------| | 8 | 0 | 0 | 696.2 | 1670.605 | 139.96% | | 8 | 0 | 1 | 696.325 | 1671.138 | 139.99% | | 50 | 0 | 0 | 969.974 | 8724.999 | 799.51% | | 50 | 0 | 1 | 970.032 | 8730.138 | 799.98% | | 300 | 0 | 0 | 5564.662 | 16272.652 | 192.43% | | 300 | 0 | 1 | 4670.436 | 14972.842 | 220.59% | | 1200 | 0 | 0 | 10740.23 | 16751.728 | 55.97% | | 1200 | 0 | 1 | 5027.741 | 14874.564 | 195.85% | | 4000 | 0 | 0 | 15122.367 | 16737.642 | 10.68% | | 4000 | 0 | 1 | 5536.918 | 14890.397 | 168.93% | | 8000 | 0 | 0 | 16505.453 | 16553.543 | 0.29% | | 8000 | 0 | 1 | 5821.619 | 14841.804 | 154.94% | 3. memmove | length | src offset | dst offset | speed before | speed after | % | |--------|------------|------------|--------------|-------------|---------| | 8 | 0 | 0 | 982.693 | 1670.568 | 70.00% | | 8 | 0 | 1 | 983.023 | 1671.174 | 70.00% | | 50 | 0 | 0 | 1230.87 | 8727.625 | 609.06% | | 50 | 0 | 1 | 1232.515 | 8730.138 | 608.32% | | 300 | 0 | 0 | 6490.375 | 16296.993 | 151.09% | | 300 | 0 | 1 | 4282.687 | 14972.842 | 249.61% | | 1200 | 0 | 0 | 11742.755 | 16752.546 | 42.66% | | 1200 | 0 | 1 | 5039.338 | 14872.951 | 195.14% | | 4000 | 0 | 0 | 15467.786 | 16737.09 | 8.21% | | 4000 | 0 | 1 | 5009.905 | 14890.542 | 197.22% | | 8000 | 0 | 0 | 16489.664 | 16553.273 | 0.39% | | 8000 | 0 | 1 | 5823.786 | 14858.646 | 155.14% | * speed: MB/s * length: byte [1] https://github.com/heiher/mem-bench Signed-off-by: WANG Rui <wangrui(a)loongson.cn> Signed-off-by: Huacai Chen <chenhuacai(a)loongson.cn> --- arch/loongarch/lib/clear_user.S | 136 +++++++++++++++-- arch/loongarch/lib/copy_user.S | 251 +++++++++++++++++++++++++------- arch/loongarch/lib/memcpy.S | 146 +++++++++++++++---- arch/loongarch/lib/memmove.S | 120 ++++++++------- arch/loongarch/lib/memset.S | 116 ++++++++++++--- 5 files changed, 602 insertions(+), 167 deletions(-) diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S index 2dc48e61a2c8..fd1d62b244f2 100644 --- a/arch/loongarch/lib/clear_user.S +++ b/arch/loongarch/lib/clear_user.S @@ -13,7 +13,14 @@ .irp to, 0, 1, 2, 3, 4, 5, 6, 7 .L_fixup_handle_\to\(): - addi.d a0, a1, (\to) * (-8) + sub.d a0, a2, a0 + addi.d a0, a0, (\to) * (-8) + jr ra +.endr + +.irp to, 0, 2, 4 +.L_fixup_handle_s\to\(): + addi.d a0, a1, -\to jr ra .endr @@ -44,7 +51,7 @@ SYM_FUNC_START(__clear_user_generic) 2: move a0, a1 jr ra - _asm_extable 1b, .L_fixup_handle_0 + _asm_extable 1b, .L_fixup_handle_s0 SYM_FUNC_END(__clear_user_generic) /* @@ -54,12 +61,21 @@ SYM_FUNC_END(__clear_user_generic) * a1: size */ SYM_FUNC_START(__clear_user_fast) - beqz a1, 10f + sltui t0, a1, 9 + bnez t0, .Lsmall - ori a2, zero, 64 - blt a1, a2, 9f + add.d a2, a0, a1 +0: st.d zero, a0, 0 + + /* align up address */ + addi.d a0, a0, 8 + bstrins.d a0, zero, 2, 0 + + addi.d a3, a2, -64 + bgeu a0, a3, .Llt64 /* set 64 bytes at a time */ +.Lloop64: 1: st.d zero, a0, 0 2: st.d zero, a0, 8 3: st.d zero, a0, 16 @@ -68,24 +84,95 @@ SYM_FUNC_START(__clear_user_fast) 6: st.d zero, a0, 40 7: st.d zero, a0, 48 8: st.d zero, a0, 56 - addi.d a0, a0, 64 - addi.d a1, a1, -64 - bge a1, a2, 1b - - beqz a1, 10f + bltu a0, a3, .Lloop64 /* set the remaining bytes */ -9: st.b zero, a0, 0 - addi.d a0, a0, 1 - addi.d a1, a1, -1 - bgt a1, zero, 9b +.Llt64: + addi.d a3, a2, -32 + bgeu a0, a3, .Llt32 +9: st.d zero, a0, 0 +10: st.d zero, a0, 8 +11: st.d zero, a0, 16 +12: st.d zero, a0, 24 + addi.d a0, a0, 32 + +.Llt32: + addi.d a3, a2, -16 + bgeu a0, a3, .Llt16 +13: st.d zero, a0, 0 +14: st.d zero, a0, 8 + addi.d a0, a0, 16 + +.Llt16: + addi.d a3, a2, -8 + bgeu a0, a3, .Llt8 +15: st.d zero, a0, 0 + +.Llt8: +16: st.d zero, a2, -8 /* return */ -10: move a0, a1 + move a0, zero + jr ra + + .align 4 +.Lsmall: + pcaddi t0, 4 + slli.d a2, a1, 4 + add.d t0, t0, a2 + jr t0 + + .align 4 + move a0, zero + jr ra + + .align 4 +17: st.b zero, a0, 0 + move a0, zero + jr ra + + .align 4 +18: st.h zero, a0, 0 + move a0, zero + jr ra + + .align 4 +19: st.h zero, a0, 0 +20: st.b zero, a0, 2 + move a0, zero + jr ra + + .align 4 +21: st.w zero, a0, 0 + move a0, zero + jr ra + + .align 4 +22: st.w zero, a0, 0 +23: st.b zero, a0, 4 + move a0, zero + jr ra + + .align 4 +24: st.w zero, a0, 0 +25: st.h zero, a0, 4 + move a0, zero + jr ra + + .align 4 +26: st.w zero, a0, 0 +27: st.w zero, a0, 3 + move a0, zero + jr ra + + .align 4 +28: st.d zero, a0, 0 + move a0, zero jr ra /* fixup and ex_table */ + _asm_extable 0b, .L_fixup_handle_0 _asm_extable 1b, .L_fixup_handle_0 _asm_extable 2b, .L_fixup_handle_1 _asm_extable 3b, .L_fixup_handle_2 @@ -95,4 +182,23 @@ SYM_FUNC_START(__clear_user_fast) _asm_extable 7b, .L_fixup_handle_6 _asm_extable 8b, .L_fixup_handle_7 _asm_extable 9b, .L_fixup_handle_0 + _asm_extable 10b, .L_fixup_handle_1 + _asm_extable 11b, .L_fixup_handle_2 + _asm_extable 12b, .L_fixup_handle_3 + _asm_extable 13b, .L_fixup_handle_0 + _asm_extable 14b, .L_fixup_handle_1 + _asm_extable 15b, .L_fixup_handle_0 + _asm_extable 16b, .L_fixup_handle_1 + _asm_extable 17b, .L_fixup_handle_s0 + _asm_extable 18b, .L_fixup_handle_s0 + _asm_extable 19b, .L_fixup_handle_s0 + _asm_extable 20b, .L_fixup_handle_s2 + _asm_extable 21b, .L_fixup_handle_s0 + _asm_extable 22b, .L_fixup_handle_s0 + _asm_extable 23b, .L_fixup_handle_s4 + _asm_extable 24b, .L_fixup_handle_s0 + _asm_extable 25b, .L_fixup_handle_s4 + _asm_extable 26b, .L_fixup_handle_s0 + _asm_extable 27b, .L_fixup_handle_s4 + _asm_extable 28b, .L_fixup_handle_s0 SYM_FUNC_END(__clear_user_fast) diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S index 55ac6020a1ad..b21f6d5d38f5 100644 --- a/arch/loongarch/lib/copy_user.S +++ b/arch/loongarch/lib/copy_user.S @@ -13,7 +13,14 @@ .irp to, 0, 1, 2, 3, 4, 5, 6, 7 .L_fixup_handle_\to\(): - addi.d a0, a2, (\to) * (-8) + sub.d a0, a2, a0 + addi.d a0, a0, (\to) * (-8) + jr ra +.endr + +.irp to, 0, 2, 4 +.L_fixup_handle_s\to\(): + addi.d a0, a2, -\to jr ra .endr @@ -47,8 +54,8 @@ SYM_FUNC_START(__copy_user_generic) 3: move a0, a2 jr ra - _asm_extable 1b, .L_fixup_handle_0 - _asm_extable 2b, .L_fixup_handle_0 + _asm_extable 1b, .L_fixup_handle_s0 + _asm_extable 2b, .L_fixup_handle_s0 SYM_FUNC_END(__copy_user_generic) /* @@ -59,65 +66,209 @@ SYM_FUNC_END(__copy_user_generic) * a2: n */ SYM_FUNC_START(__copy_user_fast) - beqz a2, 19f + sltui t0, a2, 9 + bnez t0, .Lsmall - ori a3, zero, 64 - blt a2, a3, 17f + add.d a3, a1, a2 + add.d a2, a0, a2 +0: ld.d t0, a1, 0 +1: st.d t0, a0, 0 - /* copy 64 bytes at a time */ -1: ld.d t0, a1, 0 -2: ld.d t1, a1, 8 -3: ld.d t2, a1, 16 -4: ld.d t3, a1, 24 -5: ld.d t4, a1, 32 -6: ld.d t5, a1, 40 -7: ld.d t6, a1, 48 -8: ld.d t7, a1, 56 -9: st.d t0, a0, 0 -10: st.d t1, a0, 8 -11: st.d t2, a0, 16 -12: st.d t3, a0, 24 -13: st.d t4, a0, 32 -14: st.d t5, a0, 40 -15: st.d t6, a0, 48 -16: st.d t7, a0, 56 + /* align up destination address */ + andi t1, a0, 7 + sub.d t0, zero, t1 + addi.d t0, t0, 8 + add.d a1, a1, t0 + add.d a0, a0, t0 - addi.d a0, a0, 64 - addi.d a1, a1, 64 - addi.d a2, a2, -64 - bge a2, a3, 1b + addi.d a4, a3, -64 + bgeu a1, a4, .Llt64 - beqz a2, 19f + /* copy 64 bytes at a time */ +.Lloop64: +2: ld.d t0, a1, 0 +3: ld.d t1, a1, 8 +4: ld.d t2, a1, 16 +5: ld.d t3, a1, 24 +6: ld.d t4, a1, 32 +7: ld.d t5, a1, 40 +8: ld.d t6, a1, 48 +9: ld.d t7, a1, 56 + addi.d a1, a1, 64 +10: st.d t0, a0, 0 +11: st.d t1, a0, 8 +12: st.d t2, a0, 16 +13: st.d t3, a0, 24 +14: st.d t4, a0, 32 +15: st.d t5, a0, 40 +16: st.d t6, a0, 48 +17: st.d t7, a0, 56 + addi.d a0, a0, 64 + bltu a1, a4, .Lloop64 /* copy the remaining bytes */ -17: ld.b t0, a1, 0 -18: st.b t0, a0, 0 - addi.d a0, a0, 1 - addi.d a1, a1, 1 - addi.d a2, a2, -1 - bgt a2, zero, 17b +.Llt64: + addi.d a4, a3, -32 + bgeu a1, a4, .Llt32 +18: ld.d t0, a1, 0 +19: ld.d t1, a1, 8 +20: ld.d t2, a1, 16 +21: ld.d t3, a1, 24 + addi.d a1, a1, 32 +22: st.d t0, a0, 0 +23: st.d t1, a0, 8 +24: st.d t2, a0, 16 +25: st.d t3, a0, 24 + addi.d a0, a0, 32 + +.Llt32: + addi.d a4, a3, -16 + bgeu a1, a4, .Llt16 +26: ld.d t0, a1, 0 +27: ld.d t1, a1, 8 + addi.d a1, a1, 16 +28: st.d t0, a0, 0 +29: st.d t1, a0, 8 + addi.d a0, a0, 16 + +.Llt16: + addi.d a4, a3, -8 + bgeu a1, a4, .Llt8 +30: ld.d t0, a1, 0 +31: st.d t0, a0, 0 + +.Llt8: +32: ld.d t0, a3, -8 +33: st.d t0, a2, -8 /* return */ -19: move a0, a2 + move a0, zero + jr ra + + .align 5 +.Lsmall: + pcaddi t0, 8 + slli.d a3, a2, 5 + add.d t0, t0, a3 + jr t0 + + .align 5 + move a0, zero + jr ra + + .align 5 +34: ld.b t0, a1, 0 +35: st.b t0, a0, 0 + move a0, zero + jr ra + + .align 5 +36: ld.h t0, a1, 0 +37: st.h t0, a0, 0 + move a0, zero + jr ra + + .align 5 +38: ld.h t0, a1, 0 +39: ld.b t1, a1, 2 +40: st.h t0, a0, 0 +41: st.b t1, a0, 2 + move a0, zero + jr ra + + .align 5 +42: ld.w t0, a1, 0 +43: st.w t0, a0, 0 + move a0, zero + jr ra + + .align 5 +44: ld.w t0, a1, 0 +45: ld.b t1, a1, 4 +46: st.w t0, a0, 0 +47: st.b t1, a0, 4 + move a0, zero + jr ra + + .align 5 +48: ld.w t0, a1, 0 +49: ld.h t1, a1, 4 +50: st.w t0, a0, 0 +51: st.h t1, a0, 4 + move a0, zero + jr ra + + .align 5 +52: ld.w t0, a1, 0 +53: ld.w t1, a1, 3 +54: st.w t0, a0, 0 +55: st.w t1, a0, 3 + move a0, zero + jr ra + + .align 5 +56: ld.d t0, a1, 0 +57: st.d t0, a0, 0 + move a0, zero jr ra /* fixup and ex_table */ + _asm_extable 0b, .L_fixup_handle_0 _asm_extable 1b, .L_fixup_handle_0 - _asm_extable 2b, .L_fixup_handle_1 - _asm_extable 3b, .L_fixup_handle_2 - _asm_extable 4b, .L_fixup_handle_3 - _asm_extable 5b, .L_fixup_handle_4 - _asm_extable 6b, .L_fixup_handle_5 - _asm_extable 7b, .L_fixup_handle_6 - _asm_extable 8b, .L_fixup_handle_7 + _asm_extable 2b, .L_fixup_handle_0 + _asm_extable 3b, .L_fixup_handle_0 + _asm_extable 4b, .L_fixup_handle_0 + _asm_extable 5b, .L_fixup_handle_0 + _asm_extable 6b, .L_fixup_handle_0 + _asm_extable 7b, .L_fixup_handle_0 + _asm_extable 8b, .L_fixup_handle_0 _asm_extable 9b, .L_fixup_handle_0 - _asm_extable 10b, .L_fixup_handle_1 - _asm_extable 11b, .L_fixup_handle_2 - _asm_extable 12b, .L_fixup_handle_3 - _asm_extable 13b, .L_fixup_handle_4 - _asm_extable 14b, .L_fixup_handle_5 - _asm_extable 15b, .L_fixup_handle_6 - _asm_extable 16b, .L_fixup_handle_7 - _asm_extable 17b, .L_fixup_handle_0 + _asm_extable 10b, .L_fixup_handle_0 + _asm_extable 11b, .L_fixup_handle_1 + _asm_extable 12b, .L_fixup_handle_2 + _asm_extable 13b, .L_fixup_handle_3 + _asm_extable 14b, .L_fixup_handle_4 + _asm_extable 15b, .L_fixup_handle_5 + _asm_extable 16b, .L_fixup_handle_6 + _asm_extable 17b, .L_fixup_handle_7 _asm_extable 18b, .L_fixup_handle_0 + _asm_extable 19b, .L_fixup_handle_0 + _asm_extable 20b, .L_fixup_handle_0 + _asm_extable 21b, .L_fixup_handle_0 + _asm_extable 22b, .L_fixup_handle_0 + _asm_extable 23b, .L_fixup_handle_1 + _asm_extable 24b, .L_fixup_handle_2 + _asm_extable 25b, .L_fixup_handle_3 + _asm_extable 26b, .L_fixup_handle_0 + _asm_extable 27b, .L_fixup_handle_0 + _asm_extable 28b, .L_fixup_handle_0 + _asm_extable 29b, .L_fixup_handle_1 + _asm_extable 30b, .L_fixup_handle_0 + _asm_extable 31b, .L_fixup_handle_0 + _asm_extable 32b, .L_fixup_handle_0 + _asm_extable 33b, .L_fixup_handle_1 + _asm_extable 34b, .L_fixup_handle_s0 + _asm_extable 35b, .L_fixup_handle_s0 + _asm_extable 36b, .L_fixup_handle_s0 + _asm_extable 37b, .L_fixup_handle_s0 + _asm_extable 38b, .L_fixup_handle_s0 + _asm_extable 39b, .L_fixup_handle_s0 + _asm_extable 40b, .L_fixup_handle_s0 + _asm_extable 41b, .L_fixup_handle_s2 + _asm_extable 42b, .L_fixup_handle_s0 + _asm_extable 43b, .L_fixup_handle_s0 + _asm_extable 44b, .L_fixup_handle_s0 + _asm_extable 45b, .L_fixup_handle_s0 + _asm_extable 46b, .L_fixup_handle_s0 + _asm_extable 47b, .L_fixup_handle_s4 + _asm_extable 48b, .L_fixup_handle_s0 + _asm_extable 49b, .L_fixup_handle_s0 + _asm_extable 50b, .L_fixup_handle_s0 + _asm_extable 51b, .L_fixup_handle_s4 + _asm_extable 52b, .L_fixup_handle_s0 + _asm_extable 53b, .L_fixup_handle_s0 + _asm_extable 54b, .L_fixup_handle_s0 + _asm_extable 55b, .L_fixup_handle_s4 + _asm_extable 56b, .L_fixup_handle_s0 + _asm_extable 57b, .L_fixup_handle_s0 SYM_FUNC_END(__copy_user_fast) diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S index 7c07d595ee89..612bf620760a 100644 --- a/arch/loongarch/lib/memcpy.S +++ b/arch/loongarch/lib/memcpy.S @@ -42,6 +42,65 @@ SYM_FUNC_START(__memcpy_generic) jr ra SYM_FUNC_END(__memcpy_generic) + .align 5 +SYM_FUNC_START_NOALIGN(__memcpy_small) + pcaddi t0, 8 + slli.d a2, a2, 5 + add.d t0, t0, a2 + jr t0 + + .align 5 +0: jr ra + + .align 5 +1: ld.b t0, a1, 0 + st.b t0, a0, 0 + jr ra + + .align 5 +2: ld.h t0, a1, 0 + st.h t0, a0, 0 + jr ra + + .align 5 +3: ld.h t0, a1, 0 + ld.b t1, a1, 2 + st.h t0, a0, 0 + st.b t1, a0, 2 + jr ra + + .align 5 +4: ld.w t0, a1, 0 + st.w t0, a0, 0 + jr ra + + .align 5 +5: ld.w t0, a1, 0 + ld.b t1, a1, 4 + st.w t0, a0, 0 + st.b t1, a0, 4 + jr ra + + .align 5 +6: ld.w t0, a1, 0 + ld.h t1, a1, 4 + st.w t0, a0, 0 + st.h t1, a0, 4 + jr ra + + .align 5 +7: ld.w t0, a1, 0 + ld.w t1, a1, 3 + st.w t0, a0, 0 + st.w t1, a0, 3 + jr ra + + .align 5 +8: ld.d t0, a1, 0 + st.d t0, a0, 0 + jr ra +SYM_FUNC_END(__memcpy_small) + /* * void *__memcpy_fast(void *dst, const void *src, size_t n) * @@ -50,14 +109,27 @@ SYM_FUNC_END(__memcpy_generic) * a2: n */ SYM_FUNC_START(__memcpy_fast) - move a3, a0 - beqz a2, 3f + sltui t0, a2, 9 + bnez t0, __memcpy_small + + add.d a3, a1, a2 + add.d a2, a0, a2 + ld.d a6, a1, 0 + ld.d a7, a3, -8 + + /* align up destination address */ + andi t1, a0, 7 + sub.d t0, zero, t1 + addi.d t0, t0, 8 + add.d a1, a1, t0 + add.d a5, a0, t0 - ori a4, zero, 64 - blt a2, a4, 2f + addi.d a4, a3, -64 + bgeu a1, a4, .Llt64 /* copy 64 bytes at a time */ -1: ld.d t0, a1, 0 +.Lloop64: + ld.d t0, a1, 0 ld.d t1, a1, 8 ld.d t2, a1, 16 ld.d t3, a1, 24 @@ -65,31 +137,53 @@ SYM_FUNC_START(__memcpy_fast) ld.d t5, a1, 40 ld.d t6, a1, 48 ld.d t7, a1, 56 - st.d t0, a0, 0 - st.d t1, a0, 8 - st.d t2, a0, 16 - st.d t3, a0, 24 - st.d t4, a0, 32 - st.d t5, a0, 40 - st.d t6, a0, 48 - st.d t7, a0, 56 - - addi.d a0, a0, 64 addi.d a1, a1, 64 - addi.d a2, a2, -64 - bge a2, a4, 1b - - beqz a2, 3f + st.d t0, a5, 0 + st.d t1, a5, 8 + st.d t2, a5, 16 + st.d t3, a5, 24 + st.d t4, a5, 32 + st.d t5, a5, 40 + st.d t6, a5, 48 + st.d t7, a5, 56 + addi.d a5, a5, 64 + bltu a1, a4, .Lloop64 /* copy the remaining bytes */ -2: ld.b t0, a1, 0 - st.b t0, a0, 0 - addi.d a0, a0, 1 - addi.d a1, a1, 1 - addi.d a2, a2, -1 - bgt a2, zero, 2b +.Llt64: + addi.d a4, a3, -32 + bgeu a1, a4, .Llt32 + ld.d t0, a1, 0 + ld.d t1, a1, 8 + ld.d t2, a1, 16 + ld.d t3, a1, 24 + addi.d a1, a1, 32 + st.d t0, a5, 0 + st.d t1, a5, 8 + st.d t2, a5, 16 + st.d t3, a5, 24 + addi.d a5, a5, 32 + +.Llt32: + addi.d a4, a3, -16 + bgeu a1, a4, .Llt16 + ld.d t0, a1, 0 + ld.d t1, a1, 8 + addi.d a1, a1, 16 + st.d t0, a5, 0 + st.d t1, a5, 8 + addi.d a5, a5, 16 + +.Llt16: + addi.d a4, a3, -8 + bgeu a1, a4, .Llt8 + ld.d t0, a1, 0 + st.d t0, a5, 0 + +.Llt8: + st.d a6, a0, 0 + st.d a7, a2, -8 /* return */ -3: move a0, a3 jr ra SYM_FUNC_END(__memcpy_fast) diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S index 6ffdb46da78f..d729e6cf4627 100644 --- a/arch/loongarch/lib/memmove.S +++ b/arch/loongarch/lib/memmove.S @@ -11,23 +11,9 @@ #include <asm/regdef.h> SYM_FUNC_START(memmove) - blt a0, a1, 1f /* dst < src, memcpy */ - blt a1, a0, 3f /* src < dst, rmemcpy */ + blt a0, a1, memcpy /* dst < src, memcpy */ + blt a1, a0, rmemcpy /* src < dst, rmemcpy */ jr ra /* dst == src, return */ - - /* if (src - dst) < 64, copy 1 byte at a time */ -1: ori a3, zero, 64 - sub.d t0, a1, a0 - blt t0, a3, 2f - b memcpy -2: b __memcpy_generic - - /* if (dst - src) < 64, copy 1 byte at a time */ -3: ori a3, zero, 64 - sub.d t0, a0, a1 - blt t0, a3, 4f - b rmemcpy -4: b __rmemcpy_generic SYM_FUNC_END(memmove) EXPORT_SYMBOL(memmove) @@ -73,49 +59,79 @@ SYM_FUNC_END(__rmemcpy_generic) * a2: n */ SYM_FUNC_START(__rmemcpy_fast) - move a3, a0 - beqz a2, 3f + sltui t0, a2, 9 + bnez t0, __memcpy_small - add.d a0, a0, a2 - add.d a1, a1, a2 + add.d a3, a1, a2 + add.d a2, a0, a2 + ld.d a6, a1, 0 + ld.d a7, a3, -8 + + /* align up destination address */ + andi t1, a2, 7 + sub.d a3, a3, t1 + sub.d a5, a2, t1 - ori a4, zero, 64 - blt a2, a4, 2f + addi.d a4, a1, 64 + bgeu a4, a3, .Llt64 /* copy 64 bytes at a time */ -1: ld.d t0, a1, -8 - ld.d t1, a1, -16 - ld.d t2, a1, -24 - ld.d t3, a1, -32 - ld.d t4, a1, -40 - ld.d t5, a1, -48 - ld.d t6, a1, -56 - ld.d t7, a1, -64 - st.d t0, a0, -8 - st.d t1, a0, -16 - st.d t2, a0, -24 - st.d t3, a0, -32 - st.d t4, a0, -40 - st.d t5, a0, -48 - st.d t6, a0, -56 - st.d t7, a0, -64 - - addi.d a0, a0, -64 - addi.d a1, a1, -64 - addi.d a2, a2, -64 - bge a2, a4, 1b - - beqz a2, 3f +.Lloop64: + ld.d t0, a3, -8 + ld.d t1, a3, -16 + ld.d t2, a3, -24 + ld.d t3, a3, -32 + ld.d t4, a3, -40 + ld.d t5, a3, -48 + ld.d t6, a3, -56 + ld.d t7, a3, -64 + addi.d a3, a3, -64 + st.d t0, a5, -8 + st.d t1, a5, -16 + st.d t2, a5, -24 + st.d t3, a5, -32 + st.d t4, a5, -40 + st.d t5, a5, -48 + st.d t6, a5, -56 + st.d t7, a5, -64 + addi.d a5, a5, -64 + bltu a4, a3, .Lloop64 /* copy the remaining bytes */ -2: ld.b t0, a1, -1 - st.b t0, a0, -1 - addi.d a0, a0, -1 - addi.d a1, a1, -1 - addi.d a2, a2, -1 - bgt a2, zero, 2b +.Llt64: + addi.d a4, a1, 32 + bgeu a4, a3, .Llt32 + ld.d t0, a3, -8 + ld.d t1, a3, -16 + ld.d t2, a3, -24 + ld.d t3, a3, -32 + addi.d a3, a3, -32 + st.d t0, a5, -8 + st.d t1, a5, -16 + st.d t2, a5, -24 + st.d t3, a5, -32 + addi.d a5, a5, -32 + +.Llt32: + addi.d a4, a1, 16 + bgeu a4, a3, .Llt16 + ld.d t0, a3, -8 + ld.d t1, a3, -16 + addi.d a3, a3, -16 + st.d t0, a5, -8 + st.d t1, a5, -16 + addi.d a5, a5, -16 + +.Llt16: + addi.d a4, a1, 8 + bgeu a4, a3, .Llt8 + ld.d t0, a3, -8 + st.d t0, a5, -8 + +.Llt8: + st.d a6, a0, 0 + st.d a7, a2, -8 /* return */ -3: move a0, a3 jr ra SYM_FUNC_END(__rmemcpy_fast) diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S index e7cb4ea3747d..15dcd077991b 100644 --- a/arch/loongarch/lib/memset.S +++ b/arch/loongarch/lib/memset.S @@ -54,38 +54,106 @@ SYM_FUNC_END(__memset_generic) * a2: n */ SYM_FUNC_START(__memset_fast) - move a3, a0 - beqz a2, 3f - - ori a4, zero, 64 - blt a2, a4, 2f - /* fill a1 to 64 bits */ fill_to_64 a1 - /* set 64 bytes at a time */ -1: st.d a1, a0, 0 - st.d a1, a0, 8 - st.d a1, a0, 16 - st.d a1, a0, 24 - st.d a1, a0, 32 - st.d a1, a0, 40 - st.d a1, a0, 48 - st.d a1, a0, 56 + sltui t0, a2, 9 + bnez t0, .Lsmall - addi.d a0, a0, 64 - addi.d a2, a2, -64 - bge a2, a4, 1b + add.d a2, a0, a2 + st.d a1, a0, 0 - beqz a2, 3f + /* align up address */ + addi.d a3, a0, 8 + bstrins.d a3, zero, 2, 0 + + addi.d a4, a2, -64 + bgeu a3, a4, .Llt64 + + /* set 64 bytes at a time */ +.Lloop64: + st.d a1, a3, 0 + st.d a1, a3, 8 + st.d a1, a3, 16 + st.d a1, a3, 24 + st.d a1, a3, 32 + st.d a1, a3, 40 + st.d a1, a3, 48 + st.d a1, a3, 56 + addi.d a3, a3, 64 + bltu a3, a4, .Lloop64 /* set the remaining bytes */ -2: st.b a1, a0, 0 - addi.d a0, a0, 1 - addi.d a2, a2, -1 - bgt a2, zero, 2b +.Llt64: + addi.d a4, a2, -32 + bgeu a3, a4, .Llt32 + st.d a1, a3, 0 + st.d a1, a3, 8 + st.d a1, a3, 16 + st.d a1, a3, 24 + addi.d a3, a3, 32 + +.Llt32: + addi.d a4, a2, -16 + bgeu a3, a4, .Llt16 + st.d a1, a3, 0 + st.d a1, a3, 8 + addi.d a3, a3, 16 + +.Llt16: + addi.d a4, a2, -8 + bgeu a3, a4, .Llt8 + st.d a1, a3, 0 + +.Llt8: + st.d a1, a2, -8 /* return */ -3: move a0, a3 + jr ra + + .align 4 +.Lsmall: + pcaddi t0, 4 + slli.d a2, a2, 4 + add.d t0, t0, a2 + jr t0 + + .align 4 +0: jr ra + + .align 4 +1: st.b a1, a0, 0 + jr ra + + .align 4 +2: st.h a1, a0, 0 + jr ra + + .align 4 +3: st.h a1, a0, 0 + st.b a1, a0, 2 + jr ra + + .align 4 +4: st.w a1, a0, 0 + jr ra + + .align 4 +5: st.w a1, a0, 0 + st.b a1, a0, 4 + jr ra + + .align 4 +6: st.w a1, a0, 0 + st.h a1, a0, 4 + jr ra + + .align 4 +7: st.w a1, a0, 0 + st.w a1, a0, 3 + jr ra + + .align 4 +8: st.d a1, a0, 0 jr ra SYM_FUNC_END(__memset_fast) -- 2.39.2

2 5

[PATCH 1/5] LoongArch: Optimize memory ops (memset/memcpy/memmove)
by liweihao 19 Jan '24

19 Jan '24

From: WANG Rui <wangrui(a)loongson.cn> LoongArch inclusion bugzilla: https://gitee.com/openeuler/kernel/issues/I76XQZ To optimize memset()/memcpy()/memmove() and so on, we use a jump table to dispatch cases for short data lengths; and for long data lengths, we split the destination into head part (first 8 bytes), tail part (last 8 bytes) and middle part. The head part and tail part may be at unaligned addresses, while the middle part is always aligned (the middle part is allowed to overlap the head/tail part). In this way, the first and last 8 bytes may be unaligned accesses, but we can make sure the data in the middle is processed at an aligned destination address. We have tested micro-bench[1] on a Loongson-3C5000 16-core machine (2.2GHz): 1. memset | length | src offset | dst offset | speed before | speed after | % | |--------|------------|------------|--------------|-------------|---------| | 8 | 0 | 0 | 696.191 | 1518.785 | 118.16% | | 8 | 0 | 1 | 696.325 | 1518.937 | 118.14% | | 50 | 0 | 0 | 969.976 | 8053.902 | 730.32% | | 50 | 0 | 1 | 970.034 | 8058.475 | 730.74% | | 300 | 0 | 0 | 5876.612 | 16544.703 | 181.53% | | 300 | 0 | 1 | 5030.849 | 16549.011 | 228.95% | | 1200 | 0 | 0 | 11797.077 | 16752.137 | 42.00% | | 1200 | 0 | 1 | 5687.141 | 16645.233 | 192.68% | | 4000 | 0 | 0 | 15723.27 | 16761.557 | 6.60% | | 4000 | 0 | 1 | 5906.114 | 16732.316 | 183.30% | | 8000 | 0 | 0 | 16751.403 | 16770.002 | 0.11% | | 8000 | 0 | 1 | 5995.449 | 16754.07 | 179.45% | 2. memcpy | length | src offset | dst offset | speed before | speed after | % | |--------|------------|------------|--------------|-------------|---------| | 8 | 0 | 0 | 696.2 | 1670.605 | 139.96% | | 8 | 0 | 1 | 696.325 | 1671.138 | 139.99% | | 50 | 0 | 0 | 969.974 | 8724.999 | 799.51% | | 50 | 0 | 1 | 970.032 | 8730.138 | 799.98% | | 300 | 0 | 0 | 5564.662 | 16272.652 | 192.43% | | 300 | 0 | 1 | 4670.436 | 14972.842 | 220.59% | | 1200 | 0 | 0 | 10740.23 | 16751.728 | 55.97% | | 1200 | 0 | 1 | 5027.741 | 14874.564 | 195.85% | | 4000 | 0 | 0 | 15122.367 | 16737.642 | 10.68% | | 4000 | 0 | 1 | 5536.918 | 14890.397 | 168.93% | | 8000 | 0 | 0 | 16505.453 | 16553.543 | 0.29% | | 8000 | 0 | 1 | 5821.619 | 14841.804 | 154.94% | 3. memmove | length | src offset | dst offset | speed before | speed after | % | |--------|------------|------------|--------------|-------------|---------| | 8 | 0 | 0 | 982.693 | 1670.568 | 70.00% | | 8 | 0 | 1 | 983.023 | 1671.174 | 70.00% | | 50 | 0 | 0 | 1230.87 | 8727.625 | 609.06% | | 50 | 0 | 1 | 1232.515 | 8730.138 | 608.32% | | 300 | 0 | 0 | 6490.375 | 16296.993 | 151.09% | | 300 | 0 | 1 | 4282.687 | 14972.842 | 249.61% | | 1200 | 0 | 0 | 11742.755 | 16752.546 | 42.66% | | 1200 | 0 | 1 | 5039.338 | 14872.951 | 195.14% | | 4000 | 0 | 0 | 15467.786 | 16737.09 | 8.21% | | 4000 | 0 | 1 | 5009.905 | 14890.542 | 197.22% | | 8000 | 0 | 0 | 16489.664 | 16553.273 | 0.39% | | 8000 | 0 | 1 | 5823.786 | 14858.646 | 155.14% | * speed: MB/s * length: byte [1] https://github.com/heiher/mem-bench Signed-off-by: WANG Rui <wangrui(a)loongson.cn> Signed-off-by: Huacai Chen <chenhuacai(a)loongson.cn> --- arch/loongarch/lib/clear_user.S | 136 +++++++++++++++-- arch/loongarch/lib/copy_user.S | 251 +++++++++++++++++++++++++------- arch/loongarch/lib/memcpy.S | 146 +++++++++++++++---- arch/loongarch/lib/memmove.S | 120 ++++++++------- arch/loongarch/lib/memset.S | 116 ++++++++++++--- 5 files changed, 602 insertions(+), 167 deletions(-) diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S index 2dc48e61a2c8..fd1d62b244f2 100644 --- a/arch/loongarch/lib/clear_user.S +++ b/arch/loongarch/lib/clear_user.S @@ -13,7 +13,14 @@ .irp to, 0, 1, 2, 3, 4, 5, 6, 7 .L_fixup_handle_\to\(): - addi.d a0, a1, (\to) * (-8) + sub.d a0, a2, a0 + addi.d a0, a0, (\to) * (-8) + jr ra +.endr + +.irp to, 0, 2, 4 +.L_fixup_handle_s\to\(): + addi.d a0, a1, -\to jr ra .endr @@ -44,7 +51,7 @@ SYM_FUNC_START(__clear_user_generic) 2: move a0, a1 jr ra - _asm_extable 1b, .L_fixup_handle_0 + _asm_extable 1b, .L_fixup_handle_s0 SYM_FUNC_END(__clear_user_generic) /* @@ -54,12 +61,21 @@ SYM_FUNC_END(__clear_user_generic) * a1: size */ SYM_FUNC_START(__clear_user_fast) - beqz a1, 10f + sltui t0, a1, 9 + bnez t0, .Lsmall - ori a2, zero, 64 - blt a1, a2, 9f + add.d a2, a0, a1 +0: st.d zero, a0, 0 + + /* align up address */ + addi.d a0, a0, 8 + bstrins.d a0, zero, 2, 0 + + addi.d a3, a2, -64 + bgeu a0, a3, .Llt64 /* set 64 bytes at a time */ +.Lloop64: 1: st.d zero, a0, 0 2: st.d zero, a0, 8 3: st.d zero, a0, 16 @@ -68,24 +84,95 @@ SYM_FUNC_START(__clear_user_fast) 6: st.d zero, a0, 40 7: st.d zero, a0, 48 8: st.d zero, a0, 56 - addi.d a0, a0, 64 - addi.d a1, a1, -64 - bge a1, a2, 1b - - beqz a1, 10f + bltu a0, a3, .Lloop64 /* set the remaining bytes */ -9: st.b zero, a0, 0 - addi.d a0, a0, 1 - addi.d a1, a1, -1 - bgt a1, zero, 9b +.Llt64: + addi.d a3, a2, -32 + bgeu a0, a3, .Llt32 +9: st.d zero, a0, 0 +10: st.d zero, a0, 8 +11: st.d zero, a0, 16 +12: st.d zero, a0, 24 + addi.d a0, a0, 32 + +.Llt32: + addi.d a3, a2, -16 + bgeu a0, a3, .Llt16 +13: st.d zero, a0, 0 +14: st.d zero, a0, 8 + addi.d a0, a0, 16 + +.Llt16: + addi.d a3, a2, -8 + bgeu a0, a3, .Llt8 +15: st.d zero, a0, 0 + +.Llt8: +16: st.d zero, a2, -8 /* return */ -10: move a0, a1 + move a0, zero + jr ra + + .align 4 +.Lsmall: + pcaddi t0, 4 + slli.d a2, a1, 4 + add.d t0, t0, a2 + jr t0 + + .align 4 + move a0, zero + jr ra + + .align 4 +17: st.b zero, a0, 0 + move a0, zero + jr ra + + .align 4 +18: st.h zero, a0, 0 + move a0, zero + jr ra + + .align 4 +19: st.h zero, a0, 0 +20: st.b zero, a0, 2 + move a0, zero + jr ra + + .align 4 +21: st.w zero, a0, 0 + move a0, zero + jr ra + + .align 4 +22: st.w zero, a0, 0 +23: st.b zero, a0, 4 + move a0, zero + jr ra + + .align 4 +24: st.w zero, a0, 0 +25: st.h zero, a0, 4 + move a0, zero + jr ra + + .align 4 +26: st.w zero, a0, 0 +27: st.w zero, a0, 3 + move a0, zero + jr ra + + .align 4 +28: st.d zero, a0, 0 + move a0, zero jr ra /* fixup and ex_table */ + _asm_extable 0b, .L_fixup_handle_0 _asm_extable 1b, .L_fixup_handle_0 _asm_extable 2b, .L_fixup_handle_1 _asm_extable 3b, .L_fixup_handle_2 @@ -95,4 +182,23 @@ SYM_FUNC_START(__clear_user_fast) _asm_extable 7b, .L_fixup_handle_6 _asm_extable 8b, .L_fixup_handle_7 _asm_extable 9b, .L_fixup_handle_0 + _asm_extable 10b, .L_fixup_handle_1 + _asm_extable 11b, .L_fixup_handle_2 + _asm_extable 12b, .L_fixup_handle_3 + _asm_extable 13b, .L_fixup_handle_0 + _asm_extable 14b, .L_fixup_handle_1 + _asm_extable 15b, .L_fixup_handle_0 + _asm_extable 16b, .L_fixup_handle_1 + _asm_extable 17b, .L_fixup_handle_s0 + _asm_extable 18b, .L_fixup_handle_s0 + _asm_extable 19b, .L_fixup_handle_s0 + _asm_extable 20b, .L_fixup_handle_s2 + _asm_extable 21b, .L_fixup_handle_s0 + _asm_extable 22b, .L_fixup_handle_s0 + _asm_extable 23b, .L_fixup_handle_s4 + _asm_extable 24b, .L_fixup_handle_s0 + _asm_extable 25b, .L_fixup_handle_s4 + _asm_extable 26b, .L_fixup_handle_s0 + _asm_extable 27b, .L_fixup_handle_s4 + _asm_extable 28b, .L_fixup_handle_s0 SYM_FUNC_END(__clear_user_fast) diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S index 55ac6020a1ad..b21f6d5d38f5 100644 --- a/arch/loongarch/lib/copy_user.S +++ b/arch/loongarch/lib/copy_user.S @@ -13,7 +13,14 @@ .irp to, 0, 1, 2, 3, 4, 5, 6, 7 .L_fixup_handle_\to\(): - addi.d a0, a2, (\to) * (-8) + sub.d a0, a2, a0 + addi.d a0, a0, (\to) * (-8) + jr ra +.endr + +.irp to, 0, 2, 4 +.L_fixup_handle_s\to\(): + addi.d a0, a2, -\to jr ra .endr @@ -47,8 +54,8 @@ SYM_FUNC_START(__copy_user_generic) 3: move a0, a2 jr ra - _asm_extable 1b, .L_fixup_handle_0 - _asm_extable 2b, .L_fixup_handle_0 + _asm_extable 1b, .L_fixup_handle_s0 + _asm_extable 2b, .L_fixup_handle_s0 SYM_FUNC_END(__copy_user_generic) /* @@ -59,65 +66,209 @@ SYM_FUNC_END(__copy_user_generic) * a2: n */ SYM_FUNC_START(__copy_user_fast) - beqz a2, 19f + sltui t0, a2, 9 + bnez t0, .Lsmall - ori a3, zero, 64 - blt a2, a3, 17f + add.d a3, a1, a2 + add.d a2, a0, a2 +0: ld.d t0, a1, 0 +1: st.d t0, a0, 0 - /* copy 64 bytes at a time */ -1: ld.d t0, a1, 0 -2: ld.d t1, a1, 8 -3: ld.d t2, a1, 16 -4: ld.d t3, a1, 24 -5: ld.d t4, a1, 32 -6: ld.d t5, a1, 40 -7: ld.d t6, a1, 48 -8: ld.d t7, a1, 56 -9: st.d t0, a0, 0 -10: st.d t1, a0, 8 -11: st.d t2, a0, 16 -12: st.d t3, a0, 24 -13: st.d t4, a0, 32 -14: st.d t5, a0, 40 -15: st.d t6, a0, 48 -16: st.d t7, a0, 56 + /* align up destination address */ + andi t1, a0, 7 + sub.d t0, zero, t1 + addi.d t0, t0, 8 + add.d a1, a1, t0 + add.d a0, a0, t0 - addi.d a0, a0, 64 - addi.d a1, a1, 64 - addi.d a2, a2, -64 - bge a2, a3, 1b + addi.d a4, a3, -64 + bgeu a1, a4, .Llt64 - beqz a2, 19f + /* copy 64 bytes at a time */ +.Lloop64: +2: ld.d t0, a1, 0 +3: ld.d t1, a1, 8 +4: ld.d t2, a1, 16 +5: ld.d t3, a1, 24 +6: ld.d t4, a1, 32 +7: ld.d t5, a1, 40 +8: ld.d t6, a1, 48 +9: ld.d t7, a1, 56 + addi.d a1, a1, 64 +10: st.d t0, a0, 0 +11: st.d t1, a0, 8 +12: st.d t2, a0, 16 +13: st.d t3, a0, 24 +14: st.d t4, a0, 32 +15: st.d t5, a0, 40 +16: st.d t6, a0, 48 +17: st.d t7, a0, 56 + addi.d a0, a0, 64 + bltu a1, a4, .Lloop64 /* copy the remaining bytes */ -17: ld.b t0, a1, 0 -18: st.b t0, a0, 0 - addi.d a0, a0, 1 - addi.d a1, a1, 1 - addi.d a2, a2, -1 - bgt a2, zero, 17b +.Llt64: + addi.d a4, a3, -32 + bgeu a1, a4, .Llt32 +18: ld.d t0, a1, 0 +19: ld.d t1, a1, 8 +20: ld.d t2, a1, 16 +21: ld.d t3, a1, 24 + addi.d a1, a1, 32 +22: st.d t0, a0, 0 +23: st.d t1, a0, 8 +24: st.d t2, a0, 16 +25: st.d t3, a0, 24 + addi.d a0, a0, 32 + +.Llt32: + addi.d a4, a3, -16 + bgeu a1, a4, .Llt16 +26: ld.d t0, a1, 0 +27: ld.d t1, a1, 8 + addi.d a1, a1, 16 +28: st.d t0, a0, 0 +29: st.d t1, a0, 8 + addi.d a0, a0, 16 + +.Llt16: + addi.d a4, a3, -8 + bgeu a1, a4, .Llt8 +30: ld.d t0, a1, 0 +31: st.d t0, a0, 0 + +.Llt8: +32: ld.d t0, a3, -8 +33: st.d t0, a2, -8 /* return */ -19: move a0, a2 + move a0, zero + jr ra + + .align 5 +.Lsmall: + pcaddi t0, 8 + slli.d a3, a2, 5 + add.d t0, t0, a3 + jr t0 + + .align 5 + move a0, zero + jr ra + + .align 5 +34: ld.b t0, a1, 0 +35: st.b t0, a0, 0 + move a0, zero + jr ra + + .align 5 +36: ld.h t0, a1, 0 +37: st.h t0, a0, 0 + move a0, zero + jr ra + + .align 5 +38: ld.h t0, a1, 0 +39: ld.b t1, a1, 2 +40: st.h t0, a0, 0 +41: st.b t1, a0, 2 + move a0, zero + jr ra + + .align 5 +42: ld.w t0, a1, 0 +43: st.w t0, a0, 0 + move a0, zero + jr ra + + .align 5 +44: ld.w t0, a1, 0 +45: ld.b t1, a1, 4 +46: st.w t0, a0, 0 +47: st.b t1, a0, 4 + move a0, zero + jr ra + + .align 5 +48: ld.w t0, a1, 0 +49: ld.h t1, a1, 4 +50: st.w t0, a0, 0 +51: st.h t1, a0, 4 + move a0, zero + jr ra + + .align 5 +52: ld.w t0, a1, 0 +53: ld.w t1, a1, 3 +54: st.w t0, a0, 0 +55: st.w t1, a0, 3 + move a0, zero + jr ra + + .align 5 +56: ld.d t0, a1, 0 +57: st.d t0, a0, 0 + move a0, zero jr ra /* fixup and ex_table */ + _asm_extable 0b, .L_fixup_handle_0 _asm_extable 1b, .L_fixup_handle_0 - _asm_extable 2b, .L_fixup_handle_1 - _asm_extable 3b, .L_fixup_handle_2 - _asm_extable 4b, .L_fixup_handle_3 - _asm_extable 5b, .L_fixup_handle_4 - _asm_extable 6b, .L_fixup_handle_5 - _asm_extable 7b, .L_fixup_handle_6 - _asm_extable 8b, .L_fixup_handle_7 + _asm_extable 2b, .L_fixup_handle_0 + _asm_extable 3b, .L_fixup_handle_0 + _asm_extable 4b, .L_fixup_handle_0 + _asm_extable 5b, .L_fixup_handle_0 + _asm_extable 6b, .L_fixup_handle_0 + _asm_extable 7b, .L_fixup_handle_0 + _asm_extable 8b, .L_fixup_handle_0 _asm_extable 9b, .L_fixup_handle_0 - _asm_extable 10b, .L_fixup_handle_1 - _asm_extable 11b, .L_fixup_handle_2 - _asm_extable 12b, .L_fixup_handle_3 - _asm_extable 13b, .L_fixup_handle_4 - _asm_extable 14b, .L_fixup_handle_5 - _asm_extable 15b, .L_fixup_handle_6 - _asm_extable 16b, .L_fixup_handle_7 - _asm_extable 17b, .L_fixup_handle_0 + _asm_extable 10b, .L_fixup_handle_0 + _asm_extable 11b, .L_fixup_handle_1 + _asm_extable 12b, .L_fixup_handle_2 + _asm_extable 13b, .L_fixup_handle_3 + _asm_extable 14b, .L_fixup_handle_4 + _asm_extable 15b, .L_fixup_handle_5 + _asm_extable 16b, .L_fixup_handle_6 + _asm_extable 17b, .L_fixup_handle_7 _asm_extable 18b, .L_fixup_handle_0 + _asm_extable 19b, .L_fixup_handle_0 + _asm_extable 20b, .L_fixup_handle_0 + _asm_extable 21b, .L_fixup_handle_0 + _asm_extable 22b, .L_fixup_handle_0 + _asm_extable 23b, .L_fixup_handle_1 + _asm_extable 24b, .L_fixup_handle_2 + _asm_extable 25b, .L_fixup_handle_3 + _asm_extable 26b, .L_fixup_handle_0 + _asm_extable 27b, .L_fixup_handle_0 + _asm_extable 28b, .L_fixup_handle_0 + _asm_extable 29b, .L_fixup_handle_1 + _asm_extable 30b, .L_fixup_handle_0 + _asm_extable 31b, .L_fixup_handle_0 + _asm_extable 32b, .L_fixup_handle_0 + _asm_extable 33b, .L_fixup_handle_1 + _asm_extable 34b, .L_fixup_handle_s0 + _asm_extable 35b, .L_fixup_handle_s0 + _asm_extable 36b, .L_fixup_handle_s0 + _asm_extable 37b, .L_fixup_handle_s0 + _asm_extable 38b, .L_fixup_handle_s0 + _asm_extable 39b, .L_fixup_handle_s0 + _asm_extable 40b, .L_fixup_handle_s0 + _asm_extable 41b, .L_fixup_handle_s2 + _asm_extable 42b, .L_fixup_handle_s0 + _asm_extable 43b, .L_fixup_handle_s0 + _asm_extable 44b, .L_fixup_handle_s0 + _asm_extable 45b, .L_fixup_handle_s0 + _asm_extable 46b, .L_fixup_handle_s0 + _asm_extable 47b, .L_fixup_handle_s4 + _asm_extable 48b, .L_fixup_handle_s0 + _asm_extable 49b, .L_fixup_handle_s0 + _asm_extable 50b, .L_fixup_handle_s0 + _asm_extable 51b, .L_fixup_handle_s4 + _asm_extable 52b, .L_fixup_handle_s0 + _asm_extable 53b, .L_fixup_handle_s0 + _asm_extable 54b, .L_fixup_handle_s0 + _asm_extable 55b, .L_fixup_handle_s4 + _asm_extable 56b, .L_fixup_handle_s0 + _asm_extable 57b, .L_fixup_handle_s0 SYM_FUNC_END(__copy_user_fast) diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S index 7c07d595ee89..612bf620760a 100644 --- a/arch/loongarch/lib/memcpy.S +++ b/arch/loongarch/lib/memcpy.S @@ -42,6 +42,65 @@ SYM_FUNC_START(__memcpy_generic) jr ra SYM_FUNC_END(__memcpy_generic) + .align 5 +SYM_FUNC_START_NOALIGN(__memcpy_small) + pcaddi t0, 8 + slli.d a2, a2, 5 + add.d t0, t0, a2 + jr t0 + + .align 5 +0: jr ra + + .align 5 +1: ld.b t0, a1, 0 + st.b t0, a0, 0 + jr ra + + .align 5 +2: ld.h t0, a1, 0 + st.h t0, a0, 0 + jr ra + + .align 5 +3: ld.h t0, a1, 0 + ld.b t1, a1, 2 + st.h t0, a0, 0 + st.b t1, a0, 2 + jr ra + + .align 5 +4: ld.w t0, a1, 0 + st.w t0, a0, 0 + jr ra + + .align 5 +5: ld.w t0, a1, 0 + ld.b t1, a1, 4 + st.w t0, a0, 0 + st.b t1, a0, 4 + jr ra + + .align 5 +6: ld.w t0, a1, 0 + ld.h t1, a1, 4 + st.w t0, a0, 0 + st.h t1, a0, 4 + jr ra + + .align 5 +7: ld.w t0, a1, 0 + ld.w t1, a1, 3 + st.w t0, a0, 0 + st.w t1, a0, 3 + jr ra + + .align 5 +8: ld.d t0, a1, 0 + st.d t0, a0, 0 + jr ra +SYM_FUNC_END(__memcpy_small) + /* * void *__memcpy_fast(void *dst, const void *src, size_t n) * @@ -50,14 +109,27 @@ SYM_FUNC_END(__memcpy_generic) * a2: n */ SYM_FUNC_START(__memcpy_fast) - move a3, a0 - beqz a2, 3f + sltui t0, a2, 9 + bnez t0, __memcpy_small + + add.d a3, a1, a2 + add.d a2, a0, a2 + ld.d a6, a1, 0 + ld.d a7, a3, -8 + + /* align up destination address */ + andi t1, a0, 7 + sub.d t0, zero, t1 + addi.d t0, t0, 8 + add.d a1, a1, t0 + add.d a5, a0, t0 - ori a4, zero, 64 - blt a2, a4, 2f + addi.d a4, a3, -64 + bgeu a1, a4, .Llt64 /* copy 64 bytes at a time */ -1: ld.d t0, a1, 0 +.Lloop64: + ld.d t0, a1, 0 ld.d t1, a1, 8 ld.d t2, a1, 16 ld.d t3, a1, 24 @@ -65,31 +137,53 @@ SYM_FUNC_START(__memcpy_fast) ld.d t5, a1, 40 ld.d t6, a1, 48 ld.d t7, a1, 56 - st.d t0, a0, 0 - st.d t1, a0, 8 - st.d t2, a0, 16 - st.d t3, a0, 24 - st.d t4, a0, 32 - st.d t5, a0, 40 - st.d t6, a0, 48 - st.d t7, a0, 56 - - addi.d a0, a0, 64 addi.d a1, a1, 64 - addi.d a2, a2, -64 - bge a2, a4, 1b - - beqz a2, 3f + st.d t0, a5, 0 + st.d t1, a5, 8 + st.d t2, a5, 16 + st.d t3, a5, 24 + st.d t4, a5, 32 + st.d t5, a5, 40 + st.d t6, a5, 48 + st.d t7, a5, 56 + addi.d a5, a5, 64 + bltu a1, a4, .Lloop64 /* copy the remaining bytes */ -2: ld.b t0, a1, 0 - st.b t0, a0, 0 - addi.d a0, a0, 1 - addi.d a1, a1, 1 - addi.d a2, a2, -1 - bgt a2, zero, 2b +.Llt64: + addi.d a4, a3, -32 + bgeu a1, a4, .Llt32 + ld.d t0, a1, 0 + ld.d t1, a1, 8 + ld.d t2, a1, 16 + ld.d t3, a1, 24 + addi.d a1, a1, 32 + st.d t0, a5, 0 + st.d t1, a5, 8 + st.d t2, a5, 16 + st.d t3, a5, 24 + addi.d a5, a5, 32 + +.Llt32: + addi.d a4, a3, -16 + bgeu a1, a4, .Llt16 + ld.d t0, a1, 0 + ld.d t1, a1, 8 + addi.d a1, a1, 16 + st.d t0, a5, 0 + st.d t1, a5, 8 + addi.d a5, a5, 16 + +.Llt16: + addi.d a4, a3, -8 + bgeu a1, a4, .Llt8 + ld.d t0, a1, 0 + st.d t0, a5, 0 + +.Llt8: + st.d a6, a0, 0 + st.d a7, a2, -8 /* return */ -3: move a0, a3 jr ra SYM_FUNC_END(__memcpy_fast) diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S index 6ffdb46da78f..d729e6cf4627 100644 --- a/arch/loongarch/lib/memmove.S +++ b/arch/loongarch/lib/memmove.S @@ -11,23 +11,9 @@ #include <asm/regdef.h> SYM_FUNC_START(memmove) - blt a0, a1, 1f /* dst < src, memcpy */ - blt a1, a0, 3f /* src < dst, rmemcpy */ + blt a0, a1, memcpy /* dst < src, memcpy */ + blt a1, a0, rmemcpy /* src < dst, rmemcpy */ jr ra /* dst == src, return */ - - /* if (src - dst) < 64, copy 1 byte at a time */ -1: ori a3, zero, 64 - sub.d t0, a1, a0 - blt t0, a3, 2f - b memcpy -2: b __memcpy_generic - - /* if (dst - src) < 64, copy 1 byte at a time */ -3: ori a3, zero, 64 - sub.d t0, a0, a1 - blt t0, a3, 4f - b rmemcpy -4: b __rmemcpy_generic SYM_FUNC_END(memmove) EXPORT_SYMBOL(memmove) @@ -73,49 +59,79 @@ SYM_FUNC_END(__rmemcpy_generic) * a2: n */ SYM_FUNC_START(__rmemcpy_fast) - move a3, a0 - beqz a2, 3f + sltui t0, a2, 9 + bnez t0, __memcpy_small - add.d a0, a0, a2 - add.d a1, a1, a2 + add.d a3, a1, a2 + add.d a2, a0, a2 + ld.d a6, a1, 0 + ld.d a7, a3, -8 + + /* align up destination address */ + andi t1, a2, 7 + sub.d a3, a3, t1 + sub.d a5, a2, t1 - ori a4, zero, 64 - blt a2, a4, 2f + addi.d a4, a1, 64 + bgeu a4, a3, .Llt64 /* copy 64 bytes at a time */ -1: ld.d t0, a1, -8 - ld.d t1, a1, -16 - ld.d t2, a1, -24 - ld.d t3, a1, -32 - ld.d t4, a1, -40 - ld.d t5, a1, -48 - ld.d t6, a1, -56 - ld.d t7, a1, -64 - st.d t0, a0, -8 - st.d t1, a0, -16 - st.d t2, a0, -24 - st.d t3, a0, -32 - st.d t4, a0, -40 - st.d t5, a0, -48 - st.d t6, a0, -56 - st.d t7, a0, -64 - - addi.d a0, a0, -64 - addi.d a1, a1, -64 - addi.d a2, a2, -64 - bge a2, a4, 1b - - beqz a2, 3f +.Lloop64: + ld.d t0, a3, -8 + ld.d t1, a3, -16 + ld.d t2, a3, -24 + ld.d t3, a3, -32 + ld.d t4, a3, -40 + ld.d t5, a3, -48 + ld.d t6, a3, -56 + ld.d t7, a3, -64 + addi.d a3, a3, -64 + st.d t0, a5, -8 + st.d t1, a5, -16 + st.d t2, a5, -24 + st.d t3, a5, -32 + st.d t4, a5, -40 + st.d t5, a5, -48 + st.d t6, a5, -56 + st.d t7, a5, -64 + addi.d a5, a5, -64 + bltu a4, a3, .Lloop64 /* copy the remaining bytes */ -2: ld.b t0, a1, -1 - st.b t0, a0, -1 - addi.d a0, a0, -1 - addi.d a1, a1, -1 - addi.d a2, a2, -1 - bgt a2, zero, 2b +.Llt64: + addi.d a4, a1, 32 + bgeu a4, a3, .Llt32 + ld.d t0, a3, -8 + ld.d t1, a3, -16 + ld.d t2, a3, -24 + ld.d t3, a3, -32 + addi.d a3, a3, -32 + st.d t0, a5, -8 + st.d t1, a5, -16 + st.d t2, a5, -24 + st.d t3, a5, -32 + addi.d a5, a5, -32 + +.Llt32: + addi.d a4, a1, 16 + bgeu a4, a3, .Llt16 + ld.d t0, a3, -8 + ld.d t1, a3, -16 + addi.d a3, a3, -16 + st.d t0, a5, -8 + st.d t1, a5, -16 + addi.d a5, a5, -16 + +.Llt16: + addi.d a4, a1, 8 + bgeu a4, a3, .Llt8 + ld.d t0, a3, -8 + st.d t0, a5, -8 + +.Llt8: + st.d a6, a0, 0 + st.d a7, a2, -8 /* return */ -3: move a0, a3 jr ra SYM_FUNC_END(__rmemcpy_fast) diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S index e7cb4ea3747d..15dcd077991b 100644 --- a/arch/loongarch/lib/memset.S +++ b/arch/loongarch/lib/memset.S @@ -54,38 +54,106 @@ SYM_FUNC_END(__memset_generic) * a2: n */ SYM_FUNC_START(__memset_fast) - move a3, a0 - beqz a2, 3f - - ori a4, zero, 64 - blt a2, a4, 2f - /* fill a1 to 64 bits */ fill_to_64 a1 - /* set 64 bytes at a time */ -1: st.d a1, a0, 0 - st.d a1, a0, 8 - st.d a1, a0, 16 - st.d a1, a0, 24 - st.d a1, a0, 32 - st.d a1, a0, 40 - st.d a1, a0, 48 - st.d a1, a0, 56 + sltui t0, a2, 9 + bnez t0, .Lsmall - addi.d a0, a0, 64 - addi.d a2, a2, -64 - bge a2, a4, 1b + add.d a2, a0, a2 + st.d a1, a0, 0 - beqz a2, 3f + /* align up address */ + addi.d a3, a0, 8 + bstrins.d a3, zero, 2, 0 + + addi.d a4, a2, -64 + bgeu a3, a4, .Llt64 + + /* set 64 bytes at a time */ +.Lloop64: + st.d a1, a3, 0 + st.d a1, a3, 8 + st.d a1, a3, 16 + st.d a1, a3, 24 + st.d a1, a3, 32 + st.d a1, a3, 40 + st.d a1, a3, 48 + st.d a1, a3, 56 + addi.d a3, a3, 64 + bltu a3, a4, .Lloop64 /* set the remaining bytes */ -2: st.b a1, a0, 0 - addi.d a0, a0, 1 - addi.d a2, a2, -1 - bgt a2, zero, 2b +.Llt64: + addi.d a4, a2, -32 + bgeu a3, a4, .Llt32 + st.d a1, a3, 0 + st.d a1, a3, 8 + st.d a1, a3, 16 + st.d a1, a3, 24 + addi.d a3, a3, 32 + +.Llt32: + addi.d a4, a2, -16 + bgeu a3, a4, .Llt16 + st.d a1, a3, 0 + st.d a1, a3, 8 + addi.d a3, a3, 16 + +.Llt16: + addi.d a4, a2, -8 + bgeu a3, a4, .Llt8 + st.d a1, a3, 0 + +.Llt8: + st.d a1, a2, -8 /* return */ -3: move a0, a3 + jr ra + + .align 4 +.Lsmall: + pcaddi t0, 4 + slli.d a2, a2, 4 + add.d t0, t0, a2 + jr t0 + + .align 4 +0: jr ra + + .align 4 +1: st.b a1, a0, 0 + jr ra + + .align 4 +2: st.h a1, a0, 0 + jr ra + + .align 4 +3: st.h a1, a0, 0 + st.b a1, a0, 2 + jr ra + + .align 4 +4: st.w a1, a0, 0 + jr ra + + .align 4 +5: st.w a1, a0, 0 + st.b a1, a0, 4 + jr ra + + .align 4 +6: st.w a1, a0, 0 + st.h a1, a0, 4 + jr ra + + .align 4 +7: st.w a1, a0, 0 + st.w a1, a0, 3 + jr ra + + .align 4 +8: st.d a1, a0, 0 jr ra SYM_FUNC_END(__memset_fast) -- 2.39.2

1 4

[PATCH OLK-5.10 v2 0/2] Fix io pressure when memory insufficient
by Liu Shixin 19 Jan '24

19 Jan '24

When memory is only a little and there are some pagecache can be reclaimed to avoid triggering OOM, but these pagecache is just right what the program is currently reading. The pagecache will be reclaimed and read from disk again, which will keeping a long time before OOM. Due to read-ahead, there are large of redundant read of disk which aggravate this problem. These two patch lessen the problem by early break read-ahead. Liu Shixin (2): mm/readahead: stop readahead loop if memcg charge fails mm/readahead: limit sync readahead while too many active refault include/linux/fs.h | 1 + include/linux/pagemap.h | 1 + mm/filemap.c | 16 ++++++++++++++++ mm/readahead.c | 21 ++++++++++++++++----- 4 files changed, 34 insertions(+), 5 deletions(-) -- 2.25.1

2 3

[PATCH openEuler-1.0-LTS 0/2] rtnetlink: Reject negative ifindexes in RTM_NEWLINK
by Wang Yufen 18 Jan '24

18 Jan '24

Greg Kroah-Hartman (1): Revert "rtnetlink: Reject negative ifindexes in RTM_NEWLINK" Ido Schimmel (1): rtnetlink: Reject negative ifindexes in RTM_NEWLINK net/core/rtnetlink.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) -- 1.8.3.1

2 3

[PATCH openEuler-1.0-LTS 1/2] Revert "rtnetlink: Reject negative ifindexes in RTM_NEWLINK"
by Wang Yufen 18 Jan '24

18 Jan '24

From: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> stable inclusion from stable-v4.19.296 commit 88f8a01c42535285bcf2666d1f7eb9ada0de88cc category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8XA2F CVE: NA -------------------------------- This reverts commit 42c8406432e730cb7442d97ecfdbf47084a5af4d which is commit 30188bd7838c16a98a520db1fe9df01ffc6ed368 upstream. It was improperly backported to 4.19.y, and applied to the wrong function, which obviously causes problems. A fixed version will be applied as a separate commit later. Reported-by: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Link: https://lore.kernel.org/r/ZSQeA8fhUT++iZvz@ostr-mac Cc: Ido Schimmel <idosch(a)nvidia.com> Cc: Jiri Pirko <jiri(a)nvidia.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> --- net/core/rtnetlink.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 794db63..79f6251 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2702,10 +2702,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); - else if (ifm->ifi_index < 0) { - NL_SET_ERR_MSG(extack, "ifindex can't be negative"); - return -EINVAL; - } else if (tb[IFLA_IFNAME]) + else if (tb[IFLA_IFNAME]) dev = __dev_get_by_name(net, ifname); else goto errout; -- 1.8.3.1

2 3

[PATCH OLK-6.6 00/12] aarch64 KABI reserved for module
by Yuntao Liu 18 Jan '24

18 Jan '24

reserve space for arm64 related structures. Yuntao Liu (12): kabi: reserve space for struct drm_fb_helper.h:drm_fb_helper drm_fb_helper.h:drm_fb_helper_funcs kabi: reserve space for struct drm_file.h:drm_minor drm_file.h:drm_file kabi: reserve space for struct drm_fourcc.h:drm_format_info kabi: reserve space for struct drm_gem.h:vm_operations_struct drm_gem.h:drm_gem_object kabi: reserve space for struct efi.h:efi kabi: reserve space for struct extable.h:exception_table_entry kabi: reserve space for struct fb.h:fb_deferred_io fb.h:fb_info kabi: reserve space for struct irq_work.h:irq_work kabi: reserve space for struct irqdesc.h:irq_desc kabi: reserve space for enum irqdomain_defs.h:irq_domain_bus_token kabi: reserve space for struct irqdomain.h:irq_domain kabi: reserve space for struct processor.h:thread_struct arch/arm64/include/asm/extable.h | 2 ++ arch/arm64/include/asm/processor.h | 9 +++++++++ include/drm/drm_fb_helper.h | 7 +++++++ include/drm/drm_file.h | 7 +++++++ include/drm/drm_fourcc.h | 3 +++ include/drm/drm_gem.h | 13 +++++++++++++ include/linux/efi.h | 3 +++ include/linux/fb.h | 7 +++++++ include/linux/irq_work.h | 4 ++++ include/linux/irqdesc.h | 3 +++ include/linux/irqdomain.h | 9 +++++++++ include/linux/irqdomain_defs.h | 12 ++++++++++++ 12 files changed, 79 insertions(+) -- 2.34.1

2 13

[PATCH OLK-5.10 0/3] x86/quirks: Add parameter to clear MSIs early on
by Zheng Zengkai 18 Jan '24

18 Jan '24

A crash kernel boot failure issue is reported in openeuler 5.10 series kernel(in x86 virtual machine with Hi1822 virtual nic). Finally the issue was narrowed down to irq vector conflict. Backport following patchset from kernel maillist to fix this issue. https://lore.kernel.org/linux-pci/20181018183721.27467-3-gpiccoli@canonical… Guilherme G. Piccoli (3): x86/quirks: Scan all busses for early PCI quirks x86/PCI: Export find_cap() to be used in early PCI code x86/quirks: Add parameter to clear MSIs early on boot .../admin-guide/kernel-parameters.txt | 6 +++ arch/x86/include/asm/pci-direct.h | 2 + arch/x86/kernel/aperture_64.c | 30 +------------ arch/x86/kernel/early-quirks.c | 45 ++++++++++++++++--- arch/x86/pci/common.c | 4 ++ arch/x86/pci/early.c | 25 +++++++++++ 6 files changed, 77 insertions(+), 35 deletions(-) -- 2.20.1

2 4

[PATCH OLK-6.6 0/9] Backport etmem feature to OLK 6.6
by Yuchen Tang 18 Jan '24

18 Jan '24

v4 -> v5 - fix redundant kvm config check v3 -> v4 - backport only core etmem feature - modify kernel swap enabled toggle implementation v2 -> v3 - fix code style and commit messages v1 -> v2 - make independent patches to export symbols we need - make independent patches for etmem scan and swap config - fix indentation and code style problems Yuchen Tang (9): etmem: add ETMEM feature CONFIG to mm/Kconfig etmem: add ETMEM scan feature CONFIG to mm/Kconfig mm: Export symbol __pud_trans_huge_lock mm: Export symbol walk_page_range etmem: add etmem scan feature mm: Export symbol reclaim_pages etmem: add etmem swap feature etmem: add original kernel swap enabled options etmem: enable etmem configurations arch/arm64/configs/openeuler_defconfig | 3 + arch/x86/configs/openeuler_defconfig | 3 + fs/proc/Makefile | 3 + fs/proc/base.c | 8 + fs/proc/etmem_proc.c | 216 ++++ fs/proc/etmem_scan.c | 1383 ++++++++++++++++++++++++ fs/proc/etmem_scan.h | 149 +++ fs/proc/etmem_swap.c | 109 ++ fs/proc/internal.h | 4 + include/linux/etmem.h | 47 + include/linux/mm.h | 4 + include/linux/mm_types.h | 4 + include/linux/swap.h | 1 + include/uapi/asm-generic/mman-common.h | 4 + mm/Kconfig | 33 + mm/Makefile | 1 + mm/etmem.c | 95 ++ mm/huge_memory.c | 1 + mm/internal.h | 1 - mm/madvise.c | 16 + mm/pagewalk.c | 1 + mm/swap_state.c | 4 + mm/vmscan.c | 8 + virt/kvm/kvm_main.c | 8 + 24 files changed, 2105 insertions(+), 1 deletion(-) create mode 100644 fs/proc/etmem_proc.c create mode 100644 fs/proc/etmem_scan.c create mode 100644 fs/proc/etmem_scan.h create mode 100644 fs/proc/etmem_swap.c create mode 100644 include/linux/etmem.h create mode 100644 mm/etmem.c -- 2.33.0

2 10

[PATCH OLK-5.10] tipc: fix a potential deadlock on &tx->lock
by Zhengchao Shao 18 Jan '24

18 Jan '24

From: Chengfeng Ye <dg573847474(a)gmail.com> stable inclusion from stable-v5.10.198 commit 6a24d0661fa389c241d935da38e0f6a5ee8eb1ae category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8WZL1 CVE: CVE-2024-0641 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 08e50cf071847323414df0835109b6f3560d44f5 ] It seems that tipc_crypto_key_revoke() could be be invoked by wokequeue tipc_crypto_work_rx() under process context and timer/rx callback under softirq context, thus the lock acquisition on &tx->lock seems better use spin_lock_bh() to prevent possible deadlock. This flaw was found by an experimental static analysis tool I am developing for irq-related deadlock. tipc_crypto_work_rx() <workqueue> --> tipc_crypto_key_distr() --> tipc_bcast_xmit() --> tipc_bcbase_xmit() --> tipc_bearer_bc_xmit() --> tipc_crypto_xmit() --> tipc_ehdr_build() --> tipc_crypto_key_revoke() --> spin_lock(&tx->lock) <timer interrupt> --> tipc_disc_timeout() --> tipc_bearer_xmit_skb() --> tipc_crypto_xmit() --> tipc_ehdr_build() --> tipc_crypto_key_revoke() --> spin_lock(&tx->lock) <deadlock here> Signed-off-by: Chengfeng Ye <dg573847474(a)gmail.com> Reviewed-by: Jacob Keller <jacob.e.keller(a)intel.com> Acked-by: Jon Maloy <jmaloy(a)redhat.com> Fixes: fc1b6d6de220 ("tipc: introduce TIPC encryption & authentication") Link: https://lore.kernel.org/r/20230927181414.59928-1-dg573847474@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/tipc/crypto.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index de63d6d41645..7d26d0cb207a 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1445,14 +1445,14 @@ static int tipc_crypto_key_revoke(struct net *net, u8 tx_key) struct tipc_crypto *tx = tipc_net(net)->crypto_tx; struct tipc_key key; - spin_lock(&tx->lock); + spin_lock_bh(&tx->lock); key = tx->key; WARN_ON(!key.active || tx_key != key.active); /* Free the active key */ tipc_crypto_key_set_state(tx, key.passive, 0, key.pending); tipc_crypto_key_detach(tx->aead[key.active], &tx->lock); - spin_unlock(&tx->lock); + spin_unlock_bh(&tx->lock); pr_warn("%s: key is revoked\n", tx->name); return -EKEYREVOKED; -- 2.34.1

2 1

[PATCH OLK-6.6 v2] mm/oom_kill: fix NULL pointer dereference in memcg_print_bad_task()
by Jinjiang Tu 18 Jan '24

18 Jan '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WVL2 CVE: NA -------------------------------- When memcg oom occurs, commit be8d95530886 ("memcg: support priority for oom") calls memcg_print_bad_task() to print oc->chosen when the chosen task comes from low-priority memcg. oc->chosen may be assigned with -1 in oom_evaluate_task(). Howerver, memcg_print_bad_task() does't check if oc->chosen is -1 and leads to NULL pointer dereference. To fix it, check if oc->chosen is -1 in memcg_print_bad_task(). Fixes: be8d95530886 ("memcg: support priority for oom") Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7ab0eec942ba..8327cef9d53a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4219,7 +4219,7 @@ void memcg_print_bad_task(struct oom_control *oc) if (memcg_oom_prio_disabled()) return; - if (oc->chosen) { + if (oc->chosen && oc->chosen != (void *)-1UL) { struct mem_cgroup *memcg; rcu_read_lock(); -- 2.25.1

2 1

[OLK-5.10 0/3] x86/quirks: Add parameter to clear MSIs early on boot
by Zheng Zengkai 18 Jan '24

18 Jan '24

A crash kernel boot failure issue is reported in openeuler 5.10 series kernel(in x86 virtual machine with Hi1822 virtual nic). Finally the issue was narrowed down to irq vector conflict. Backport following patchset from kernel maillist to fix this issue. https://lore.kernel.org/linux-pci/20181018183721.27467-3-gpiccoli@canonical… Guilherme G. Piccoli (3): x86/quirks: Scan all busses for early PCI quirks x86/PCI: Export find_cap() to be used in early PCI code x86/quirks: Add parameter to clear MSIs early on boot .../admin-guide/kernel-parameters.txt | 6 +++ arch/x86/include/asm/pci-direct.h | 2 + arch/x86/kernel/aperture_64.c | 30 +------------ arch/x86/kernel/early-quirks.c | 45 ++++++++++++++++--- arch/x86/pci/common.c | 4 ++ arch/x86/pci/early.c | 25 +++++++++++ 6 files changed, 77 insertions(+), 35 deletions(-) -- 2.20.1

1 3

[PATCH openEuler-1.0-LTS 0/1] fix CVE-2022-48619
by Liao Chen 18 Jan '24

18 Jan '24

fix CVE-2022-48619 Jeff LaBundy (1): Input: add bounds checking to input_set_capability() drivers/input/input.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) -- 2.34.1

2 2

[PATCH OLK-6.6] smb: client: fix OOB in receive_encrypted_standard()
by ZhaoLong Wang 18 Jan '24

18 Jan '24

From: Paulo Alcantara <pc(a)manguebit.com> stable inclusion from stable-v6.6.8 commit 534733397da26de0303057ce0b93a22bda150365 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8WEOK CVE: CVE-2024-0565 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit eec04ea119691e65227a97ce53c0da6b9b74b0b7 upstream. Fix potential OOB in receive_encrypted_standard() if server returned a large shdr->NextCommand that would end up writing off the end of @next_buffer. Fixes: b24df3e30cbf ("cifs: update receive_encrypted_standard to handle compounded responses") Cc: stable(a)vger.kernel.org Reported-by: Robert Morris <rtm(a)csail.mit.edu> Signed-off-by: Paulo Alcantara (SUSE) <pc(a)manguebit.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> --- fs/smb/client/smb2ops.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 386b62d5c133..ea7ccaea711a 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -4937,6 +4937,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -4965,14 +4966,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -4996,8 +4998,8 @@ receive_encrypted_standard(struct TCP_Server_Info *server, else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; -- 2.34.3

2 1

[PATCH openEuler-1.0-LTS] smb: client: fix OOB in receive_encrypted_standard()
by ZhaoLong Wang 18 Jan '24

18 Jan '24

From: Paulo Alcantara <pc(a)manguebit.com> mainline inclusion from mainline-v6.7-rc6 commit eec04ea119691e65227a97ce53c0da6b9b74b0b7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8WEOK CVE: CVE-2024-0565 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Fix potential OOB in receive_encrypted_standard() if server returned a large shdr->NextCommand that would end up writing off the end of @next_buffer. Fixes: b24df3e30cbf ("cifs: update receive_encrypted_standard to handle compounded responses") Cc: stable(a)vger.kernel.org Reported-by: Robert Morris <rtm(a)csail.mit.edu> Signed-off-by: Paulo Alcantara (SUSE) <pc(a)manguebit.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> Conflicts: fs/cifs/smb2ops.c Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> --- fs/cifs/smb2ops.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 4f6cc104fdb5..eba4bdfff08a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3185,6 +3185,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_sync_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -3213,14 +3214,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_sync_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -3244,8 +3246,8 @@ receive_encrypted_standard(struct TCP_Server_Info *server, else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; -- 2.34.3

2 1

[PATCH OLK-5.10] smb: client: fix OOB in receive_encrypted_standard()
by ZhaoLong Wang 18 Jan '24

18 Jan '24

From: Paulo Alcantara <pc(a)manguebit.com> mainline inclusion from mainline-v6.7-rc6 commit eec04ea119691e65227a97ce53c0da6b9b74b0b7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8WEOK CVE: CVE-2024-0565 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Fix potential OOB in receive_encrypted_standard() if server returned a large shdr->NextCommand that would end up writing off the end of @next_buffer. Fixes: b24df3e30cbf ("cifs: update receive_encrypted_standard to handle compounded responses") Cc: stable(a)vger.kernel.org Reported-by: Robert Morris <rtm(a)csail.mit.edu> Signed-off-by: Paulo Alcantara (SUSE) <pc(a)manguebit.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> Conflicts: fs/cifs/smb2ops.c Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> --- fs/cifs/smb2ops.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index b86f559751fd..caee4dedd7dc 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -4886,6 +4886,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_sync_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -4914,14 +4915,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_sync_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -4945,8 +4947,8 @@ receive_encrypted_standard(struct TCP_Server_Info *server, else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; -- 2.34.3

2 1

[PATCH OLK-6.6] mm/oom_kill: fix NULL pointer dereference in memcg_print_bad_task()
by Jinjiang Tu 18 Jan '24

18 Jan '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WVL2 CVE: NA -------------------------------- In OLK-5.10, when oc->chosen is assigned with -1 in oom_evaluate_task(), mem_cgroup_scan_tasks() will return -1, and only calls memcg_print_bad_task() when the return value is 0. commit 025b7799b35d ("mm/memcg: remove return value of mem_cgroup_scan_tasks()") removes return value of mem_cgroup_scan_tasks(). When adapting memcg oom priority feature to OLK-6.6, memcg_print_bad_task() will be called in all cases, and forgets to check if oc->chosen is -1, leading to NULL pointer dereference. Fixes: be8d95530886 ("memcg: support priority for oom") Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7ab0eec942ba..8327cef9d53a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4219,7 +4219,7 @@ void memcg_print_bad_task(struct oom_control *oc) if (memcg_oom_prio_disabled()) return; - if (oc->chosen) { + if (oc->chosen && oc->chosen != (void *)-1UL) { struct mem_cgroup *memcg; rcu_read_lock(); -- 2.25.1

2 1

[PATCH] mm/oom_kill: fix NULL pointer dereference in memcg_print_bad_task()
by Jinjiang Tu 18 Jan '24

18 Jan '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WVL2 CVE: NA -------------------------------- In OLK-5.10, when oc->chosen is assigned with -1 in oom_evaluate_task(), mem_cgroup_scan_tasks() will return -1, and only calls memcg_print_bad_task() when the return value is 0. commit 025b7799b35d ("mm/memcg: remove return value of mem_cgroup_scan_tasks()") removes return value of mem_cgroup_scan_tasks(). When adapting memcg oom priority feature to OLK-6.6, memcg_print_bad_task() will be called in all cases, and forgets to check if oc->chosen is -1, leading to NULL pointer dereference. Fixes: be8d95530886 ("memcg: support priority for oom") Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7ab0eec942ba..8327cef9d53a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4219,7 +4219,7 @@ void memcg_print_bad_task(struct oom_control *oc) if (memcg_oom_prio_disabled()) return; - if (oc->chosen) { + if (oc->chosen && oc->chosen != (void *)-1UL) { struct mem_cgroup *memcg; rcu_read_lock(); -- 2.25.1

1 0

[PATCH OLK-6.6 0/1] misc config
by Chen Ridong 18 Jan '24

18 Jan '24

Chen Ridong (1): cgroup/misc: open_eulerdefconfig open misc config by default arch/arm64/configs/openeuler_defconfig | 2 +- arch/x86/configs/openeuler_defconfig | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) -- 2.34.1

2 2

[PATCH openEuler-22.03-LTS 0/2] ext4: synchronize the casefold bugfix from the mainline
by Baokun Li 17 Jan '24

17 Jan '24

Eric Biggers (1): ext4: reject casefold inode flag without casefold feature Theodore Ts'o (1): ext4: improve error handling from ext4_dirhash() fs/ext4/hash.c | 5 ++++- fs/ext4/inode.c | 5 ++++- fs/ext4/namei.c | 40 +++++++++++++++++++++++++++++++--------- 3 files changed, 39 insertions(+), 11 deletions(-) -- 2.31.1

2 3

[PATCH openEuler-22.03-LTS-SP1 0/2] ext4: synchronize the casefold bugfix from the mainline
by Baokun Li 17 Jan '24

17 Jan '24

Eric Biggers (1): ext4: reject casefold inode flag without casefold feature Theodore Ts'o (1): ext4: improve error handling from ext4_dirhash() fs/ext4/hash.c | 5 ++++- fs/ext4/inode.c | 5 ++++- fs/ext4/namei.c | 40 +++++++++++++++++++++++++++++++--------- 3 files changed, 39 insertions(+), 11 deletions(-) -- 2.31.1

2 3

[PATCH openEuler-22.03-LTS-SP2 0/2] ext4: synchronize the casefold bugfix from the mainline
by Baokun Li 17 Jan '24

17 Jan '24

Eric Biggers (1): ext4: reject casefold inode flag without casefold feature Theodore Ts'o (1): ext4: improve error handling from ext4_dirhash() fs/ext4/hash.c | 5 ++++- fs/ext4/inode.c | 5 ++++- fs/ext4/namei.c | 40 +++++++++++++++++++++++++++++++--------- 3 files changed, 39 insertions(+), 11 deletions(-) -- 2.31.1

2 3

[PATCH OLK-5.10 0/2] ext4: synchronize the casefold bugfix from the mainline.
by Baokun Li 17 Jan '24

17 Jan '24

Eric Biggers (1): ext4: reject casefold inode flag without casefold feature Theodore Ts'o (1): ext4: improve error handling from ext4_dirhash() fs/ext4/hash.c | 5 ++++- fs/ext4/inode.c | 5 ++++- fs/ext4/namei.c | 40 +++++++++++++++++++++++++++++++--------- 3 files changed, 39 insertions(+), 11 deletions(-) -- 2.31.1

2 3

[PATCH openEuler-22.03-LTS-SP2] ext4: correct return value of ext4_convert_meta_bg
by Baokun Li 17 Jan '24

17 Jan '24

From: Kemeng Shi <shikemeng(a)huaweicloud.com> stable inclusion from stable-v5.10.202 commit 3c1ad03a5ff20645ca67a84af8a078285fe20702 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I853YM Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 48f1551592c54f7d8e2befc72a99ff4e47f7dca0 upstream. Avoid to ignore error in "err". Signed-off-by: Kemeng Shi <shikemeng(a)huaweicloud.com> Link: https://lore.kernel.org/r/20230826174712.4059355-4-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/resize.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index dffbb318a173..bdb3accc6615 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1928,9 +1928,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) errout: ret = ext4_journal_stop(handle); - if (!err) - err = ret; - return ret; + return err ? err : ret; invalid_resize_inode: ext4_error(sb, "corrupted/inconsistent resize inode"); -- 2.31.1

2 1

[PATCH openEuler-22.03-LTS-SP1] ext4: correct return value of ext4_convert_meta_bg
by Baokun Li 17 Jan '24

17 Jan '24

From: Kemeng Shi <shikemeng(a)huaweicloud.com> stable inclusion from stable-v5.10.202 commit 3c1ad03a5ff20645ca67a84af8a078285fe20702 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I853YM Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 48f1551592c54f7d8e2befc72a99ff4e47f7dca0 upstream. Avoid to ignore error in "err". Signed-off-by: Kemeng Shi <shikemeng(a)huaweicloud.com> Link: https://lore.kernel.org/r/20230826174712.4059355-4-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/resize.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index c07bcceb2619..40eb3019e966 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1928,9 +1928,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) errout: ret = ext4_journal_stop(handle); - if (!err) - err = ret; - return ret; + return err ? err : ret; invalid_resize_inode: ext4_error(sb, "corrupted/inconsistent resize inode"); -- 2.31.1

2 1

[PATCH openEuler-22.03-LTS] ext4: correct return value of ext4_convert_meta_bg
by Baokun Li 17 Jan '24

17 Jan '24

From: Kemeng Shi <shikemeng(a)huaweicloud.com> stable inclusion from stable-v5.10.202 commit 3c1ad03a5ff20645ca67a84af8a078285fe20702 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I853YM Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 48f1551592c54f7d8e2befc72a99ff4e47f7dca0 upstream. Avoid to ignore error in "err". Signed-off-by: Kemeng Shi <shikemeng(a)huaweicloud.com> Link: https://lore.kernel.org/r/20230826174712.4059355-4-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/resize.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 5df9f7140233..58980c6acbc8 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1928,9 +1928,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) errout: ret = ext4_journal_stop(handle); - if (!err) - err = ret; - return ret; + return err ? err : ret; invalid_resize_inode: ext4_error(sb, "corrupted/inconsistent resize inode"); -- 2.31.1

2 1

[PATCH OLK-5.10] ext4: correct return value of ext4_convert_meta_bg
by Baokun Li 17 Jan '24

17 Jan '24

From: Kemeng Shi <shikemeng(a)huaweicloud.com> stable inclusion from stable-v5.10.202 commit 3c1ad03a5ff20645ca67a84af8a078285fe20702 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I853YM Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 48f1551592c54f7d8e2befc72a99ff4e47f7dca0 upstream. Avoid to ignore error in "err". Signed-off-by: Kemeng Shi <shikemeng(a)huaweicloud.com> Link: https://lore.kernel.org/r/20230826174712.4059355-4-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/resize.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index dffbb318a173..bdb3accc6615 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1928,9 +1928,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) errout: ret = ext4_journal_stop(handle); - if (!err) - err = ret; - return ret; + return err ? err : ret; invalid_resize_inode: ext4_error(sb, "corrupted/inconsistent resize inode"); -- 2.31.1

2 1

[PATCH OLK-6.6 V8 00/10] sched: basic infrastructure for scheduler bpf
by Lu Jialin 17 Jan '24

17 Jan '24

From: Guan Jing <guanjing6(a)huawei.com> sched: basic infrastructure for scheduler bpf Guan Jing (10): sched: programmable: Introduce bpf sched sched: programmable: Add a tag for the task sched: programmable: Add a tag for the task group sched: programmable: Add user interface of task group tag sched: programmable: Add user interface of task tag sched: basic infrastructure for scheduler bpf sched: introduce bpf_sched_enable() sched: programmable: Add hook in select_task_rq_fair() sched: programmable: Add hook in can_migrate_task() openeuler_defconfig: enable CONFIG_BPF_SCHED arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/proc/base.c | 61 +++++++++++++ include/linux/bpf_sched.h | 50 +++++++++++ include/linux/bpf_types.h | 4 + include/linux/sched.h | 26 ++++++ include/linux/sched_hook_defs.h | 4 + include/uapi/linux/bpf.h | 2 + init/init_task.c | 3 + kernel/bpf/Kconfig | 13 +++ kernel/bpf/btf.c | 3 + kernel/bpf/syscall.c | 41 +++++++++ kernel/bpf/trampoline.c | 3 + kernel/bpf/verifier.c | 23 +++++ kernel/sched/bpf_sched.c | 64 ++++++++++++++ kernel/sched/build_utility.c | 4 + kernel/sched/core.c | 118 +++++++++++++++++++++++++ kernel/sched/fair.c | 45 ++++++++++ kernel/sched/sched.h | 10 +++ scripts/bpf_doc.py | 2 + tools/include/uapi/linux/bpf.h | 2 + 21 files changed, 480 insertions(+) create mode 100644 include/linux/bpf_sched.h create mode 100644 include/linux/sched_hook_defs.h create mode 100644 kernel/sched/bpf_sched.c -- 2.34.1

2 11

[PATCH OLK-5.10] smb: client: fix OOB in receive_encrypted_standard()
by ZhaoLong Wang 17 Jan '24

17 Jan '24

From: Paulo Alcantara <pc(a)manguebit.com> mainline inclusion from mainline-v6.7-rc6 commit eec04ea119691e65227a97ce53c0da6b9b74b0b7 category: bugfix bugzilla: 189472 CVE: CVE-2024-0565 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Fix potential OOB in receive_encrypted_standard() if server returned a large shdr->NextCommand that would end up writing off the end of @next_buffer. Fixes: b24df3e30cbf ("cifs: update receive_encrypted_standard to handle compounded responses") Cc: stable(a)vger.kernel.org Reported-by: Robert Morris <rtm(a)csail.mit.edu> Signed-off-by: Paulo Alcantara (SUSE) <pc(a)manguebit.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> Conflicts: fs/cifs/smb2ops.c Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> --- fs/cifs/smb2ops.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index b86f559751fd..caee4dedd7dc 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -4886,6 +4886,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_sync_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -4914,14 +4915,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_sync_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -4945,8 +4947,8 @@ receive_encrypted_standard(struct TCP_Server_Info *server, else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; -- 2.34.3

2 1

[PATCH openEuler-1.0-LTS] smb: client: fix OOB in receive_encrypted_standard()
by ZhaoLong Wang 17 Jan '24

17 Jan '24

From: Paulo Alcantara <pc(a)manguebit.com> mainline inclusion from mainline-v6.7-rc6 commit eec04ea119691e65227a97ce53c0da6b9b74b0b7 category: bugfix bugzilla: 189472 CVE: CVE-2024-0565 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Fix potential OOB in receive_encrypted_standard() if server returned a large shdr->NextCommand that would end up writing off the end of @next_buffer. Fixes: b24df3e30cbf ("cifs: update receive_encrypted_standard to handle compounded responses") Cc: stable(a)vger.kernel.org Reported-by: Robert Morris <rtm(a)csail.mit.edu> Signed-off-by: Paulo Alcantara (SUSE) <pc(a)manguebit.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> Conflicts: fs/cifs/smb2ops.c Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> --- fs/cifs/smb2ops.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 4f6cc104fdb5..eba4bdfff08a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3185,6 +3185,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_sync_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -3213,14 +3214,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_sync_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -3244,8 +3246,8 @@ receive_encrypted_standard(struct TCP_Server_Info *server, else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; -- 2.34.3

2 1

[PATCH OLK-6.6 0/6] kabi: net: reserve space for net
by Zhengchao Shao 17 Jan '24

17 Jan '24

Reserve space for net, inheriting the kabi reservation in kernel 5.10. Wang Hai (6): kabi: net: reserve space for net base subsystem related structure kabi: net: reserve space for net bpf subsystem related structure kabi: net: reserve space for net can subsystem related structure kabi: net: reserve space for net netfilter subsystem related structure kabi: net: reserve space for net rdma subsystem related structure kabi: net: reserve space for net sunrpc subsystem related structure include/linux/can/core.h | 4 +++ include/linux/can/dev.h | 6 ++++ include/linux/can/rx-offload.h | 4 +++ include/linux/device.h | 10 ++++++ include/linux/device/class.h | 6 ++++ include/linux/ethtool.h | 6 ++++ include/linux/inetdevice.h | 4 +++ include/linux/ipv6.h | 6 ++++ include/linux/net.h | 6 ++++ include/linux/netdevice.h | 42 ++++++++++++++++++++++++++ include/linux/netfilter.h | 13 ++++++++ include/linux/netfilter/ipset/ip_set.h | 10 ++++++ include/linux/netfilter/nfnetlink.h | 7 +++++ include/linux/netfilter_ipv6.h | 4 +++ include/linux/skbuff.h | 6 ++++ include/linux/skmsg.h | 11 +++++++ include/linux/sunrpc/cache.h | 4 +++ include/linux/sunrpc/clnt.h | 12 ++++++++ include/linux/sunrpc/sched.h | 15 +++++++++ include/linux/sunrpc/stats.h | 7 +++++ include/linux/sunrpc/xprt.h | 17 +++++++++++ include/net/dcbnl.h | 10 ++++++ include/net/dst.h | 10 ++++++ include/net/dst_ops.h | 10 ++++++ include/net/fib_rules.h | 10 ++++++ include/net/flow.h | 7 +++++ include/net/flow_dissector.h | 6 ++++ include/net/genetlink.h | 12 ++++++++ include/net/inet_connection_sock.h | 7 +++++ include/net/ip6_fib.h | 13 ++++++++ include/net/l3mdev.h | 6 ++++ include/net/lwtunnel.h | 7 +++++ include/net/neighbour.h | 11 +++++++ include/net/netdev_rx_queue.h | 5 +++ include/net/netfilter/nf_conntrack.h | 4 +++ include/net/netlink.h | 5 +++ include/net/netns/can.h | 4 +++ include/net/netns/ipv4.h | 8 +++++ include/net/netns/ipv6.h | 4 +++ include/net/netns/netfilter.h | 4 +++ include/net/netns/nftables.h | 4 +++ include/net/netns/xfrm.h | 4 +++ include/net/page_pool/types.h | 4 +++ include/net/rtnetlink.h | 10 ++++++ include/net/sch_generic.h | 11 +++++++ include/net/sock.h | 18 +++++++++++ include/net/switchdev.h | 6 ++++ include/net/tcp.h | 6 ++++ include/net/tls.h | 15 +++++++++ include/net/xdp.h | 6 ++++ include/net/xsk_buff_pool.h | 3 ++ include/rdma/ib_addr.h | 4 +++ include/rdma/rdma_cm.h | 10 ++++++ include/rdma/rdma_counter.h | 4 +++ include/rdma/rdma_netlink.h | 4 +++ include/rdma/rdma_vt.h | 7 +++++ include/rdma/rdmavt_qp.h | 5 +++ net/devlink/devl_internal.h | 5 +++ 58 files changed, 469 insertions(+) -- 2.34.1

2 7

[PATCH OLK-6.6] openeuler_defconfig: Disable new HW_RANDOM support for arm64
by Yi Yang 17 Jan '24

17 Jan '24

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8WYFN -------------------------------- New hardware features are disable by default. Disable CONFIG_HW_RANDOM_HISTB,CONFIG_HW_RANDOM_ARM_SMCCC_TRNG, CONFIG_HW_RANDOM_CN10K in openeuler_defconfig on arm64. Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 35dd6141f057..87d51893e69e 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -3568,13 +3568,13 @@ CONFIG_HW_RANDOM_TIMERIOMEM=m # CONFIG_HW_RANDOM_BA431 is not set CONFIG_HW_RANDOM_VIRTIO=m CONFIG_HW_RANDOM_HISI=y -CONFIG_HW_RANDOM_HISTB=y +# CONFIG_HW_RANDOM_HISTB is not set CONFIG_HW_RANDOM_XGENE=y CONFIG_HW_RANDOM_CAVIUM=y # CONFIG_HW_RANDOM_CCTRNG is not set # CONFIG_HW_RANDOM_XIPHERA is not set -CONFIG_HW_RANDOM_ARM_SMCCC_TRNG=y -CONFIG_HW_RANDOM_CN10K=y +# CONFIG_HW_RANDOM_ARM_SMCCC_TRNG is not set +# CONFIG_HW_RANDOM_CN10K is not set # CONFIG_APPLICOM is not set CONFIG_DEVMEM=y # CONFIG_DEVPORT is not set -- 2.25.1

2 1

[PATCH] mm/oom_kill: fix NULL pointer dereference in memcg_print_bad_task()
by Jinjiang Tu 17 Jan '24

17 Jan '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WVL2 CVE: NA -------------------------------- oc->chosen may be assigned with -1 in oom_evaluate_task(), but memcg_print_bad_task() doesn't check whether oc->chosen is -1 before dereference it. Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7ab0eec942ba..8327cef9d53a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4219,7 +4219,7 @@ void memcg_print_bad_task(struct oom_control *oc) if (memcg_oom_prio_disabled()) return; - if (oc->chosen) { + if (oc->chosen && oc->chosen != (void *)-1UL) { struct mem_cgroup *memcg; rcu_read_lock(); -- 2.25.1

1 0

[PATCH OLK-6.6] mm/oom_kill: fix NULL pointer dereference in memcg_print_bad_task()
by Jinjiang Tu 17 Jan '24

17 Jan '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WVL2 CVE: NA -------------------------------- oc->chosen may be assigned with -1 in oom_evaluate_task(), but memcg_print_bad_task() doesn't check whether oc->chosen is -1 before dereference it. Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7ab0eec942ba..8327cef9d53a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4219,7 +4219,7 @@ void memcg_print_bad_task(struct oom_control *oc) if (memcg_oom_prio_disabled()) return; - if (oc->chosen) { + if (oc->chosen && oc->chosen != (void *)-1UL) { struct mem_cgroup *memcg; rcu_read_lock(); -- 2.25.1

2 1

[PATCH OLK-6.6 v6 0/8] introduce smart_grid zone
by Yipeng Zou 17 Jan '24

17 Jan '24

The patch sets include two parts: 1. patch 1~3: Rebase smart_grid from OLK-5.10 to OLK-6.6 2. patch 4~8: introduce smart_grid zone qos and cpufreq Since V5: 1. Only modified mm/mempolicy.c review comments Since V4: 1. rebase to OLK-6.6 head Since V3: 1. fix some review comments Since V2: 1. move new sysctl form sysctl.c to fair.c 2. add smart_grid cmdline Since V1: 1. Don't init smart_grid cpufreq with dynamic_affinity disable. 2. Forbid smart_grid cgroup interface with dynamic_affinity disable. Hui Tang (1): sched: Introduce smart grid scheduling strategy for cfs Wang ShaoBo (2): sched: smart grid: init sched_grid_qos structure on QOS purpose config: enable CONFIG_QOS_SCHED_SMART_GRID by default Yipeng Zou (5): sched: introduce smart grid qos zone smart_grid: introduce /proc/pid/smart_grid_level smart_grid: introduce smart_grid_strategy_ctrl sysctl smart_grid: cpufreq: introduce smart_grid cpufreq control smart_grid: introduce smart_grid cmdline arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + drivers/cpufreq/cpufreq.c | 244 +++++++++++ fs/proc/array.c | 16 + fs/proc/base.c | 84 ++++ include/linux/cpufreq.h | 11 + include/linux/sched.h | 32 ++ include/linux/sched/grid_qos.h | 135 +++++++ init/Kconfig | 13 + kernel/fork.c | 15 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 181 +++++++++ kernel/sched/fair.c | 537 ++++++++++++++++++++++++- kernel/sched/grid/Makefile | 2 + kernel/sched/grid/internal.h | 6 + kernel/sched/grid/power.c | 27 ++ kernel/sched/grid/qos.c | 279 +++++++++++++ kernel/sched/grid/stat.c | 47 +++ kernel/sched/sched.h | 48 ++- mm/mempolicy.c | 11 +- 20 files changed, 1679 insertions(+), 12 deletions(-) create mode 100644 include/linux/sched/grid_qos.h create mode 100644 kernel/sched/grid/Makefile create mode 100644 kernel/sched/grid/internal.h create mode 100644 kernel/sched/grid/power.c create mode 100644 kernel/sched/grid/qos.c create mode 100644 kernel/sched/grid/stat.c -- 2.34.1

2 9

[PATCH OLK-6.6 0/2] Set CONFIG_NODES_SHIFT to 8
by Liu Shixin 17 Jan '24

17 Jan '24

Patch[1] allow to set NODES_SHIFT between 8 and 10 on MAXSMP. Patch[2] set NODES_SHIFT to 8 for both x86_64 and ARM64 defconfig. Liu Shixin (2): x86/Kconfig: allow NODES_SHIFT to be set on MAXSMP openeuler_defconfig: set CONFIG_NODES_SHIFT to 8 for both x86_64/ARM64 arch/arm64/configs/openeuler_defconfig | 2 +- arch/x86/Kconfig | 3 ++- arch/x86/configs/openeuler_defconfig | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) -- 2.25.1

2 3

[PATCH OLK-6.6 0/9] Backport etmem feature to OLK 6.6
by Yuchen Tang 17 Jan '24

17 Jan '24

v3 -> v4 - backport only core etmem feature - modify kernel swap enabled toggle implementation v2 -> v3 - fix code style and commit messages v1 -> v2 - make independent patches to export symbols we need - make independent patches for etmem scan and swap config - fix indentation and code style problems Yuchen Tang (9): etmem: add ETMEM feature CONFIG to mm/Kconfig etmem: add ETMEM scan feature CONFIG to mm/Kconfig mm: Export symbol __pud_trans_huge_lock mm: Export symbol walk_page_range etmem: add etmem scan feature mm: Export symbol reclaim_pages etmem: add etmem swap feature etmem: add original kernel swap enabled options etmem: enable etmem configurations arch/arm64/configs/openeuler_defconfig | 3 + arch/x86/configs/openeuler_defconfig | 3 + fs/proc/Makefile | 3 + fs/proc/base.c | 8 + fs/proc/etmem_proc.c | 216 ++++ fs/proc/etmem_scan.c | 1383 ++++++++++++++++++++++++ fs/proc/etmem_scan.h | 149 +++ fs/proc/etmem_swap.c | 109 ++ fs/proc/internal.h | 4 + include/linux/etmem.h | 47 + include/linux/mm.h | 4 + include/linux/mm_types.h | 4 + include/linux/swap.h | 1 + include/uapi/asm-generic/mman-common.h | 4 + mm/Kconfig | 33 + mm/Makefile | 1 + mm/etmem.c | 95 ++ mm/huge_memory.c | 1 + mm/internal.h | 1 - mm/madvise.c | 16 + mm/pagewalk.c | 1 + mm/swap_state.c | 4 + mm/vmscan.c | 8 + virt/kvm/kvm_main.c | 8 + 24 files changed, 2105 insertions(+), 1 deletion(-) create mode 100644 fs/proc/etmem_proc.c create mode 100644 fs/proc/etmem_scan.c create mode 100644 fs/proc/etmem_scan.h create mode 100644 fs/proc/etmem_swap.c create mode 100644 include/linux/etmem.h create mode 100644 mm/etmem.c -- 2.33.0

2 10

[PATCH openEuler-1.0-LTS] crypto: hisilicon/qm: fix several issues
by wangyuan 16 Jan '24

16 Jan '24

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8WNSG CVE: NA -------------------------------------------------------- 1.qm_hw_error parse in qm_abnormal_irq and qm_log_hw_error is different, ARRAY_SIZE(qm_hw_error) exceeds actual treatment area. 2.add method judgement in qm_clear_device. Signed-off-by: wangyuan <wangyuan46(a)huawei.com> --- drivers/crypto/hisilicon/qm.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 25bb24b4c131..6abaec751867 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -277,8 +277,7 @@ static const struct hisi_qm_hw_error qm_hw_error[] = { { .int_msk = BIT(9), .msg = "qm_sq_vf_invalid" }, { .int_msk = BIT(10), .msg = "qm_db_timeout" }, { .int_msk = BIT(11), .msg = "qm_of_fifo_of" }, - { .int_msk = BIT(12), .msg = "qm_db_random_invalid" }, - { /* sentinel */ } + { .int_msk = BIT(12), .msg = "qm_db_random_invalid" } }; static const char * const qm_db_timeout[] = { @@ -774,10 +773,11 @@ static irqreturn_t qm_aeq_irq(int irq, void *data) static irqreturn_t qm_abnormal_irq(int irq, void *data) { - const struct hisi_qm_hw_error *err = qm_hw_error; + const struct hisi_qm_hw_error *err; struct hisi_qm *qm = data; struct device *dev = &qm->pdev->dev; u32 error_status, tmp; + int i; atomic64_inc(&qm->debug.dfx.abnormal_irq_cnt); if (qm->abnormal_fix) { @@ -789,12 +789,13 @@ static irqreturn_t qm_abnormal_irq(int irq, void *data) tmp = readl(qm->io_base + QM_ABNORMAL_INT_STATUS); error_status = qm->msi_mask & tmp; - while (err->msg) { - if (err->int_msk & error_status) - dev_err(dev, "%s [error status=0x%x] found\n", - err->msg, err->int_msk); + for (i = 0; i < ARRAY_SIZE(qm_hw_error); i++) { + err = &qm_hw_error[i]; + if (!(err->int_msk & error_status)) + continue; - err++; + dev_err(dev, "%s [error status=0x%x] found\n", + err->msg, err->int_msk); } /* clear err sts */ @@ -2639,12 +2640,23 @@ static int hisi_qm_memory_init(struct hisi_qm *qm) static int qm_clear_device(struct hisi_qm *qm) { + acpi_handle handle = ACPI_HANDLE(&qm->pdev->dev); u32 val; int ret; if (qm->fun_type == QM_HW_VF) return 0; + if (!handle) { + pci_warn(qm->pdev, "Device does not support reset, return.\n"); + return 0; + } + + if (!acpi_has_method(handle, qm->err_ini.err_info.acpi_rst)) { + pci_warn(qm->pdev, "BIOS has no reset method, return.\n"); + return 0; + } + /* OOO register set and check */ writel(MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + MASTER_GLOBAL_CTRL); -- 2.33.0

2 1