- Kernel - mailweb.openeuler.org

[PATCH openEuler-5.10 01/97] PCI: aardvark: Increase polling delay to 1.5s while waiting for PIO response
by Zheng Zengkai 15 Nov '21

15 Nov '21

From: Pali Rohár <pali(a)kernel.org> stable inclusion from stable-5.10.70 commit 31bd6cd06a18315c9a1b4c6035d027f086c59942 bugzilla: 182949 https://gitee.com/openeuler/kernel/issues/I4I3GQ Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 2b58db229eb617d97d5746113b77045f1f884bcb upstream. Measurements in different conditions showed that aardvark hardware PIO response can take up to 1.44s. Increase wait timeout from 1ms to 1.5s to ensure that we do not miss responses from hardware. After 1.44s hardware returns errors (e.g. Completer abort). The previous two patches fixed checking for PIO status, so now we can use it to also catch errors which are reported by hardware after 1.44s. After applying this patch, kernel can detect and print PIO errors to dmesg: [ 6.879999] advk-pcie d0070000.pcie: Non-posted PIO Response Status: CA, 0xe00 @ 0x100004 [ 6.896436] advk-pcie d0070000.pcie: Posted PIO Response Status: COMP_ERR, 0x804 @ 0x100004 [ 6.913049] advk-pcie d0070000.pcie: Posted PIO Response Status: COMP_ERR, 0x804 @ 0x100010 [ 6.929663] advk-pcie d0070000.pcie: Non-posted PIO Response Status: CA, 0xe00 @ 0x100010 [ 6.953558] advk-pcie d0070000.pcie: Posted PIO Response Status: COMP_ERR, 0x804 @ 0x100014 [ 6.970170] advk-pcie d0070000.pcie: Non-posted PIO Response Status: CA, 0xe00 @ 0x100014 [ 6.994328] advk-pcie d0070000.pcie: Posted PIO Response Status: COMP_ERR, 0x804 @ 0x100004 Without this patch kernel prints only a generic error to dmesg: [ 5.246847] advk-pcie d0070000.pcie: config read/write timed out Link: https://lore.kernel.org/r/20210722144041.12661-3-pali@kernel.org Signed-off-by: Pali Rohár <pali(a)kernel.org> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi(a)arm.com> Reviewed-by: Marek Behún <kabel(a)kernel.org> Cc: stable(a)vger.kernel.org # 7fbcb5da811b ("PCI: aardvark: Don't rely on jiffies while holding spinlock") Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Acked-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> --- drivers/pci/controller/pci-aardvark.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index f175cff39b46..4f1a29ede576 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -214,7 +214,7 @@ (PCIE_CONF_BUS(bus) | PCIE_CONF_DEV(PCI_SLOT(devfn)) | \ PCIE_CONF_FUNC(PCI_FUNC(devfn)) | PCIE_CONF_REG(where)) -#define PIO_RETRY_CNT 500 +#define PIO_RETRY_CNT 750000 /* 1.5 s */ #define PIO_RETRY_DELAY 2 /* 2 us*/ #define LINK_WAIT_MAX_RETRIES 10 -- 2.20.1

1 96

[PATCH openEuler-5.10 1/5] arm64: remove page granularity limitation from KFENCE
by Zheng Zengkai 15 Nov '21

15 Nov '21

From: Liu Shixin <liushixin2(a)huawei.com> hulk inclusion category: bugfix bugzilla: 181005 https://gitee.com/openeuler/kernel/issues/I4DDEL ------------------------------------------------- Currently if KFENCE is enabled in arm64, the entire linear map will be mapped at page granularity which seems overkilled. Actually only the kfence pool requires to be mapped at page granularity. We can remove the restriction from KFENCE and force the linear mapping of the kfence pool at page granularity later in arch_kfence_init_pool(). Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> --- arch/arm64/include/asm/kfence.h | 70 ++++++++++++++++++++++++++++++++- arch/arm64/mm/mmu.c | 6 +-- 2 files changed, 71 insertions(+), 5 deletions(-) diff --git a/arch/arm64/include/asm/kfence.h b/arch/arm64/include/asm/kfence.h index d061176d57ea..322e95bc228d 100644 --- a/arch/arm64/include/asm/kfence.h +++ b/arch/arm64/include/asm/kfence.h @@ -8,9 +8,77 @@ #ifndef __ASM_KFENCE_H #define __ASM_KFENCE_H +#include <linux/kfence.h> #include <asm/cacheflush.h> +#include <asm/pgalloc.h> -static inline bool arch_kfence_init_pool(void) { return true; } +static inline int split_pud_page(pud_t *pud, unsigned long addr) +{ + int i; + pmd_t *pmd = pmd_alloc_one(&init_mm, addr); + unsigned long pfn = PFN_DOWN(__pa(addr)); + + if (!pmd) + return -ENOMEM; + + for (i = 0; i < PTRS_PER_PMD; i++) + set_pmd(pmd + i, pmd_mkhuge(pfn_pmd(pfn + i * PTRS_PER_PTE, PAGE_KERNEL))); + + smp_wmb(); /* See comment in __pte_alloc */ + pud_populate(&init_mm, pud, pmd); + + flush_tlb_kernel_range(addr, addr + PUD_SIZE); + return 0; +} + +static inline int split_pmd_page(pmd_t *pmd, unsigned long addr) +{ + int i; + pte_t *pte = pte_alloc_one_kernel(&init_mm); + unsigned long pfn = PFN_DOWN(__pa(addr)); + + if (!pte) + return -ENOMEM; + + for (i = 0; i < PTRS_PER_PTE; i++) + set_pte(pte + i, pfn_pte(pfn + i, PAGE_KERNEL)); + + smp_wmb(); /* See comment in __pte_alloc */ + pmd_populate_kernel(&init_mm, pmd, pte); + + flush_tlb_kernel_range(addr, addr + PMD_SIZE); + return 0; +} + +static inline bool arch_kfence_init_pool(void) +{ + unsigned long addr; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + for (addr = (unsigned long)__kfence_pool; is_kfence_address((void *)addr); + addr += PAGE_SIZE) { + pgd = pgd_offset(&init_mm, addr); + if (pgd_leaf(*pgd)) + return false; + p4d = p4d_offset(pgd, addr); + if (p4d_leaf(*p4d)) + return false; + pud = pud_offset(p4d, addr); + if (pud_leaf(*pud)) { + if (split_pud_page(pud, addr & PUD_MASK)) + return false; + } + pmd = pmd_offset(pud, addr); + if (pmd_leaf(*pmd)) { + if (split_pmd_page(pmd, addr & PMD_MASK)) + return false; + } + } + return true; +} static inline bool kfence_protect_page(unsigned long addr, bool protect) { diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index b6a9895d6655..1c2a965e65b3 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -492,8 +492,7 @@ static void __init map_mem(pgd_t *pgdp) int flags = 0; u64 i; - if (rodata_full || crash_mem_map || debug_pagealloc_enabled() || - IS_ENABLED(CONFIG_KFENCE)) + if (rodata_full || crash_mem_map || debug_pagealloc_enabled()) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; /* @@ -1458,8 +1457,7 @@ int arch_add_memory(int nid, u64 start, u64 size, * KFENCE requires linear map to be mapped at page granularity, so that * it is possible to protect/unprotect single pages in the KFENCE pool. */ - if (rodata_full || debug_pagealloc_enabled() || - IS_ENABLED(CONFIG_KFENCE)) + if (rodata_full || debug_pagealloc_enabled()) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), -- 2.20.1

1 4

[PATCH openEuler-5.10 01/56] PCI: pci-bridge-emul: Add PCIe Root Capabilities Register
by Zheng Zengkai 15 Nov '21

15 Nov '21

From: Pali Rohár <pali(a)kernel.org> stable inclusion from stable-5.10.69 commit 9e766b86a9ef653a8ca48a9f70d3dbb580284594 bugzilla: 182675 https://gitee.com/openeuler/kernel/issues/I4I3ED Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit e902bb7c24a7099d0eb0eb4cba06f2d91e9299f3 upstream. The 16-bit Root Capabilities register is at offset 0x1e in the PCIe Capability. Rename current 'rsvd' struct member to 'rootcap'. Link: https://lore.kernel.org/r/20210722144041.12661-4-pali@kernel.org Signed-off-by: Pali Rohár <pali(a)kernel.org> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi(a)arm.com> Reviewed-by: Marek Behún <kabel(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Acked-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> --- drivers/pci/pci-bridge-emul.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/pci-bridge-emul.h b/drivers/pci/pci-bridge-emul.h index b31883022a8e..49bbd37ee318 100644 --- a/drivers/pci/pci-bridge-emul.h +++ b/drivers/pci/pci-bridge-emul.h @@ -54,7 +54,7 @@ struct pci_bridge_emul_pcie_conf { __le16 slotctl; __le16 slotsta; __le16 rootctl; - __le16 rsvd; + __le16 rootcap; __le32 rootsta; __le32 devcap2; __le16 devctl2; -- 2.20.1

1 55

[PATCH openEuler-5.10 01/26] sched/fair: fix sd_llc_alloc_all() compile error
by Zheng Zengkai 15 Nov '21

15 Nov '21

From: Cheng Jian <cj.chengjian(a)huawei.com> hulk inclusion category: bugfix bugzilla: 38261, https://gitee.com/openeuler/kernel/issues/I49XPZ CVE: NA --------------------------- when CONFIG_SCHED_STEAL disabled: kernel/sched/topology.c:24:74: warning: ‘struct s_data’ declared inside parameter list will not be visible outside of this definition or declaration 24 | static inline int sd_llc_alloc_all(const struct cpumask *cpu_map, struct s_data *d) { return 0; } | ^~~~~~ kernel/sched/topology.c: In function ‘build_sched_domains’: kernel/sched/topology.c:2188:32: error: passing argument 2 of ‘sd_llc_alloc_all’ from incompatible pointer type [-Werror=incompatible-pointer-types] 2188 | if (sd_llc_alloc_all(cpu_map, &d)) | ^~ | | | struct s_data * Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- kernel/sched/topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 0564aeabbcb8..fcf6aebb13c4 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -13,8 +13,8 @@ DEFINE_MUTEX(sched_domains_mutex); static cpumask_var_t sched_domains_tmpmask; static cpumask_var_t sched_domains_tmpmask2; -#ifdef CONFIG_SCHED_STEAL struct s_data; +#ifdef CONFIG_SCHED_STEAL static int sd_llc_alloc(struct sched_domain *sd); static void sd_llc_free(struct sched_domain *sd); static int sd_llc_alloc_all(const struct cpumask *cpu_map, struct s_data *d); -- 2.20.1

1 25

[PATCH openEuler-1.0-LTS] iommu: smmuv2: fix compile error when CONFIG_ARCH_PHYTIUM is off
by Yang Yingliang 15 Nov '21

15 Nov '21

From: Zheng Zengkai <zhengzengkai(a)huawei.com> phytium inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I41AUQ -------------------------------------- Disabling CONFIG_ARCH_PHYTIUM results in following compile errors: drivers/iommu/arm-smmu.c: In function ‘phytium_smmu_def_domain_type’: drivers/iommu/arm-smmu.c:1641:6: error: implicit declaration of function ‘typeof_ft2000plus’ [-Werror=implicit-function-declaration] 1641 | if (typeof_ft2000plus() || typeof_s2500()) { | ^~~~~~~~~~~~~~~~~ drivers/iommu/arm-smmu.c:1641:29: error: implicit declaration of function ‘typeof_s2500’ [-Werror=implicit-function-declaration] 1641 | if (typeof_ft2000plus() || typeof_s2500()) { | ^~~~~~~~~~~~ cc1: some warnings being treated as errors Fix it by using CONFIG_ARCH_PHYTIUM to control phytium related code. Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Reviewed-by: Zhen Lei <thunder.leizhen(a)huawei.com> Reviewed-by: wangxiongfeng 00379786 <wangxiongfeng2(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/iommu/arm-smmu.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 18863198bb036..d1c00b1dfd2ef 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1634,8 +1634,7 @@ static void arm_smmu_put_resv_regions(struct device *dev, #ifdef CONFIG_SMMU_BYPASS_DEV -#ifdef CONFIG_ARM64 -#include <asm/cputype.h> +#ifdef CONFIG_ARCH_PHYTIUM static int phytium_smmu_def_domain_type(struct device *dev, unsigned int *type) { if (typeof_ft2000plus() || typeof_s2500()) { -- 2.25.1

1 0

[PATCH OLK-5.10] SCSI: spfc: fix typo of last_cmsn
by Yanling Song 15 Nov '21

15 Nov '21

Ramaxel inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4I0OZ CVE: NA Fix typo of last_cmsn which should be last_pmsn Signed-off-by: Yanling Song <songyl(a)ramaxel.com> --- drivers/scsi/spfc/hw/spfc_queue.c | 28 ++++++++++++++-------------- drivers/scsi/spfc/hw/spfc_queue.h | 2 +- 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/scsi/spfc/hw/spfc_queue.c b/drivers/scsi/spfc/hw/spfc_queue.c index 3f73fa26aad1..abcf1ff3f49f 100644 --- a/drivers/scsi/spfc/hw/spfc_queue.c +++ b/drivers/scsi/spfc/hw/spfc_queue.c @@ -1027,7 +1027,7 @@ u32 spfc_create_ssq(void *handle) sq_ctrl->wqe_offset = 0; sq_ctrl->head_start_cmsn = 0; sq_ctrl->head_end_cmsn = SPFC_GET_WP_END_CMSN(0, sq_ctrl->wqe_num_per_buf); - sq_ctrl->last_cmsn = 0; + sq_ctrl->last_pmsn = 0; /* Linked List SQ Owner Bit 1 valid,0 invalid */ sq_ctrl->last_pi_owner = 1; atomic_set(&sq_ctrl->sq_valid, true); @@ -3127,7 +3127,7 @@ static u32 spfc_parent_sq_ring_direct_wqe_doorbell(struct spfc_parent_ssq_info * struct spfc_hba_info *hba; hba = (struct spfc_hba_info *)sq->hba; - pmsn = sq->last_cmsn; + pmsn = sq->last_pmsn; if (sq->cache_id == INVALID_VALUE32) { FC_DRV_PRINT(UNF_LOG_IO_ATT, UNF_ERR, @@ -3166,7 +3166,7 @@ u32 spfc_parent_sq_ring_doorbell(struct spfc_parent_ssq_info *sq, u8 qos_level, struct spfc_parent_sq_db door_bell; hba = (struct spfc_hba_info *)sq->hba; - pmsn = sq->last_cmsn; + pmsn = sq->last_pmsn; /* Obtain the low 8 Bit of PMSN */ pmsn_lo = (u8)(pmsn & SPFC_PMSN_MASK); /* Obtain the high 8 Bit of PMSN */ @@ -3231,10 +3231,10 @@ u32 spfc_direct_sq_enqueue(struct spfc_parent_ssq_info *ssq, struct spfc_sqe *io FC_DRV_PRINT(UNF_LOG_NORMAL, UNF_INFO, "[info]Ssq(0x%x), xid(0x%x) qid(0x%x) add wqepage at Pmsn(0x%x), sqe_minus_cqe_cnt(0x%x)", ssq->sqn, ssq->context_id, ssq->sq_queue_id, - ssq->last_cmsn, + ssq->last_pmsn, atomic_read(&ssq->sqe_minus_cqe_cnt)); - link_wqe_msn = SPFC_MSN_DEC(ssq->last_cmsn); + link_wqe_msn = SPFC_MSN_DEC(ssq->last_pmsn); link_wqe = (struct spfc_linkwqe *)spfc_get_wqe_page_entry(tail_wpg, ssq->wqe_offset); msn_wd = be32_to_cpu(link_wqe->val_wd1); @@ -3250,7 +3250,7 @@ u32 spfc_direct_sq_enqueue(struct spfc_parent_ssq_info *ssq, struct spfc_sqe *io } sqe_in_wp = (struct spfc_sqe *)spfc_get_wqe_page_entry(tail_wpg, ssq->wqe_offset); - spfc_build_wqe_owner_pmsn(io_sqe, (ssq->last_pi_owner), ssq->last_cmsn); + spfc_build_wqe_owner_pmsn(io_sqe, (ssq->last_pi_owner), ssq->last_pmsn); SPFC_IO_STAT((struct spfc_hba_info *)ssq->hba, wqe_type); wqe_gpa = tail_wpg->wpg_phy_addr + (ssq->wqe_offset * sizeof(struct spfc_sqe)); @@ -3260,11 +3260,11 @@ u32 spfc_direct_sq_enqueue(struct spfc_parent_ssq_info *ssq, struct spfc_sqe *io dre_door_bell.wd0.cos = 0; dre_door_bell.wd0.c = 0; dre_door_bell.wd0.pi_hi = - (u32)(ssq->last_cmsn >> UNF_SHIFT_12) & SPFC_DB_WD0_PI_H_MASK; + (u32)(ssq->last_pmsn >> UNF_SHIFT_12) & SPFC_DB_WD0_PI_H_MASK; dre_door_bell.wd0.cntx_size = SPFC_CNTX_SIZE_T_256B; dre_door_bell.wd0.xid = ssq->context_id; dre_door_bell.wd1.sm_data = ssq->cache_id; - dre_door_bell.wd1.pi_lo = (u32)(ssq->last_cmsn & SPFC_DB_WD0_PI_L_MASK); + dre_door_bell.wd1.pi_lo = (u32)(ssq->last_pmsn & SPFC_DB_WD0_PI_L_MASK); io_sqe->db_val = *(u64 *)&dre_door_bell; spfc_convert_parent_wqe_to_big_endian(io_sqe); @@ -3275,7 +3275,7 @@ u32 spfc_direct_sq_enqueue(struct spfc_parent_ssq_info *ssq, struct spfc_sqe *io "[INFO]Ssq(0x%x) xid:0x%x,qid:0x%x wqegpa:0x%llx,o:0x%x,outstandind:0x%x,pmsn:0x%x,cmsn:0x%x", ssq->sqn, ssq->context_id, ssq->sq_queue_id, wqe_gpa, ssq->last_pi_owner, atomic_read(&ssq->sqe_minus_cqe_cnt), - ssq->last_cmsn, SPFC_GET_QUEUE_CMSN(ssq)); + ssq->last_pmsn, SPFC_GET_QUEUE_CMSN(ssq)); ssq->accum_wqe_cnt++; if (ssq->accum_wqe_cnt == accum_db_num) { @@ -3286,7 +3286,7 @@ u32 spfc_direct_sq_enqueue(struct spfc_parent_ssq_info *ssq, struct spfc_sqe *io } ssq->wqe_offset += 1; - ssq->last_cmsn = SPFC_MSN_INC(ssq->last_cmsn); + ssq->last_pmsn = SPFC_MSN_INC(ssq->last_pmsn); atomic_inc(&ssq->sq_wqe_cnt); atomic_inc(&ssq->sqe_minus_cqe_cnt); SPFC_SQ_IO_STAT(ssq, wqe_type); @@ -3319,7 +3319,7 @@ u32 spfc_parent_ssq_enqueue(struct spfc_parent_ssq_info *ssq, struct spfc_sqe *i FC_DRV_PRINT(UNF_LOG_NORMAL, UNF_INFO, "[info]Ssq(0x%x), xid(0x%x) qid(0x%x) add wqepage at Pmsn(0x%x), WpgCnt(0x%x)", ssq->sqn, ssq->context_id, ssq->sq_queue_id, - ssq->last_cmsn, + ssq->last_pmsn, atomic_read(&ssq->wqe_page_cnt)); cur_cmsn = SPFC_GET_QUEUE_CMSN(ssq); spfc_free_sq_wqe_page(ssq, cur_cmsn); @@ -3335,7 +3335,7 @@ u32 spfc_parent_ssq_enqueue(struct spfc_parent_ssq_info *ssq, struct spfc_sqe *i link_wqe->next_page_addr_hi = cpu_to_be32(addr_wd); addr_wd = SPFC_LSD(new_wqe_page->wpg_phy_addr); link_wqe->next_page_addr_lo = cpu_to_be32(addr_wd); - link_wqe_msn = SPFC_MSN_DEC(ssq->last_cmsn); + link_wqe_msn = SPFC_MSN_DEC(ssq->last_pmsn); msn_wd = be32_to_cpu(link_wqe->val_wd1); msn_wd |= ((u32)(link_wqe_msn & SPFC_MSNWD_L_MASK)); msn_wd |= (((u32)(link_wqe_msn & SPFC_MSNWD_H_MASK)) << UNF_SHIFT_16); @@ -3351,7 +3351,7 @@ u32 spfc_parent_ssq_enqueue(struct spfc_parent_ssq_info *ssq, struct spfc_sqe *i atomic_inc(&ssq->wqe_page_cnt); } - spfc_build_wqe_owner_pmsn(io_sqe, !(ssq->last_pi_owner), ssq->last_cmsn); + spfc_build_wqe_owner_pmsn(io_sqe, !(ssq->last_pi_owner), ssq->last_pmsn); SPFC_IO_STAT((struct spfc_hba_info *)ssq->hba, wqe_type); spfc_convert_parent_wqe_to_big_endian(io_sqe); sqe_in_wp = (struct spfc_sqe *)spfc_get_wqe_page_entry(tail_wpg, ssq->wqe_offset); @@ -3371,7 +3371,7 @@ u32 spfc_parent_ssq_enqueue(struct spfc_parent_ssq_info *ssq, struct spfc_sqe *i ssq->accum_wqe_cnt = 0; } ssq->wqe_offset += 1; - ssq->last_cmsn = SPFC_MSN_INC(ssq->last_cmsn); + ssq->last_pmsn = SPFC_MSN_INC(ssq->last_pmsn); atomic_inc(&ssq->sq_wqe_cnt); atomic_inc(&ssq->sqe_minus_cqe_cnt); SPFC_SQ_IO_STAT(ssq, wqe_type); diff --git a/drivers/scsi/spfc/hw/spfc_queue.h b/drivers/scsi/spfc/hw/spfc_queue.h index b1184eb17556..c09f098e7324 100644 --- a/drivers/scsi/spfc/hw/spfc_queue.h +++ b/drivers/scsi/spfc/hw/spfc_queue.h @@ -597,7 +597,7 @@ struct spfc_parent_ssq_info { u32 wqe_offset; u16 head_start_cmsn; u16 head_end_cmsn; - u16 last_cmsn; + u16 last_pmsn; u16 last_pi_owner; u32 queue_style; atomic_t sq_valid; -- 2.30.0

2 1

[PATCH OLK-5.10] Change CPU page size to 4KB for ARM architecture
by shenzijun 15 Nov '21

15 Nov '21

From: 沈子俊 <shenzijun(a)kylinos.cn> kylin inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4HDHZ?from=project-issue CVE: NA ---------------------------------------------------------------------- change config about ARM64_4K_PAGES in openeuler-defconfig from arch/arm64 Signed-off-by: 沈子俊 <shenzijun(a)kylinos.cn> --- arch/arm64/configs/openeuler_defconfig | 31 +++++++++++++------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 76d6a118330d..87cf82bcb30e 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -250,12 +250,12 @@ CONFIG_TRACEPOINTS=y CONFIG_ARM64=y CONFIG_64BIT=y CONFIG_MMU=y -CONFIG_ARM64_PAGE_SHIFT=16 -CONFIG_ARM64_CONT_PTE_SHIFT=5 -CONFIG_ARM64_CONT_PMD_SHIFT=5 -CONFIG_ARCH_MMAP_RND_BITS_MIN=14 -CONFIG_ARCH_MMAP_RND_BITS_MAX=14 -CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN=7 +CONFIG_ARM64_PAGE_SHIFT=12 +CONFIG_ARM64_CONT_PTE_SHIFT=4 +CONFIG_ARM64_CONT_PMD_SHIFT=4 +CONFIG_ARCH_MMAP_RND_BITS_MIN=18 +CONFIG_ARCH_MMAP_RND_BITS_MAX=24 +CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN=11 CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX=16 CONFIG_STACKTRACE_SUPPORT=y CONFIG_ILLEGAL_POINTER_VALUE=0xdead000000000000 @@ -365,17 +365,17 @@ CONFIG_HISILICON_ERRATUM_HIP08_RU_PREFETCH=y CONFIG_SOCIONEXT_SYNQUACER_PREITS=y # end of ARM errata workarounds via the alternatives framework -# CONFIG_ARM64_4K_PAGES is not set +CONFIG_ARM64_4K_PAGES=y # CONFIG_ARM64_16K_PAGES is not set -CONFIG_ARM64_64K_PAGES=y -# CONFIG_ARM64_VA_BITS_42 is not set +# CONFIG_ARM64_64K_PAGES is not set +CONFIG_ARM64_VA_BITS_39=y # CONFIG_ARM64_VA_BITS_48 is not set -CONFIG_ARM64_VA_BITS_52=y +# CONFIG_ARM64_VA_BITS_52 is not set # CONFIG_ARM64_FORCE_52BIT is not set -CONFIG_ARM64_VA_BITS=52 -# CONFIG_ARM64_PA_BITS_48 is not set -CONFIG_ARM64_PA_BITS_52=y -CONFIG_ARM64_PA_BITS=52 +CONFIG_ARM64_VA_BITS=39 +CONFIG_ARM64_PA_BITS_48=y +# CONFIG_ARM64_PA_BITS_52 is not set +CONFIG_ARM64_PA_BITS=48 # CONFIG_CPU_BIG_ENDIAN is not set CONFIG_CPU_LITTLE_ENDIAN=y CONFIG_SCHED_MC=y @@ -402,6 +402,7 @@ CONFIG_ARCH_SELECT_MEMORY_MODEL=y CONFIG_HAVE_ARCH_PFN_VALID=y CONFIG_HW_PERF_EVENTS=y CONFIG_SYS_SUPPORTS_HUGETLBFS=y +CONFIG_ARCH_WANT_HUGE_PMD_SHARE=y CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK=y CONFIG_PARAVIRT=y @@ -411,7 +412,7 @@ CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y CONFIG_ARM64_CPU_PARK=y # CONFIG_XEN is not set -CONFIG_FORCE_MAX_ZONEORDER=14 +CONFIG_FORCE_MAX_ZONEORDER=11 CONFIG_UNMAP_KERNEL_AT_EL0=y CONFIG_RODATA_FULL_DEFAULT_ENABLED=y CONFIG_ARM64_PMEM_RESERVE=y -- 2.30.0

1 0

[PATCH OLK-5.10] fix structure type undeclared error in topology.c
by shenzijun 15 Nov '21

15 Nov '21

From: 沈子俊 <shenzijun(a)kylinos.cn> kylin inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4I4E2#note_7386759 CVE: NA ------------------------------------------------------------------ add declaration of 'struct s_data' Signed-off-by: 沈子俊 <shenzijun(a)kylinos.cn> --- kernel/sched/topology.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 0564aeabbcb8..1fac5d28c0dc 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -20,6 +20,7 @@ static void sd_llc_free(struct sched_domain *sd); static int sd_llc_alloc_all(const struct cpumask *cpu_map, struct s_data *d); static void sd_llc_free_all(const struct cpumask *cpu_map); #else +struct s_data; static inline void sd_llc_free(struct sched_domain *sd) {} static inline int sd_llc_alloc_all(const struct cpumask *cpu_map, struct s_data *d) { return 0; } static inline void sd_llc_free_all(const struct cpumask *cpu_map) {} -- 2.30.0

1 0

[PATCH kernel-4.19 v2] fix the problem that the pointer may be double free
by zhangyue 15 Nov '21

15 Nov '21

kylin inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AH11?from=project-issue CVE: NA int driver/md/md.c, if the function autorun_array() is called, first called do_md_run() and then do_md_stop(), this time, the pointer mddev->private may be double free Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- drivers/md/md.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 4406bb137a27..aa204ec74066 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6000,8 +6000,10 @@ static void __md_stop(struct mddev *mddev) spin_lock(&mddev->lock); mddev->pers = NULL; spin_unlock(&mddev->lock); - pers->free(mddev, mddev->private); - mddev->private = NULL; + if (mddev->private) { + pers->free(mddev, mddev->private); + mddev->private = NULL; + } if (pers->sync_request && mddev->to_remove == NULL) mddev->to_remove = &md_redundancy_group; module_put(pers->owner); -- 2.30.0

1 0

[PATCH kernel-4.19 v2] fix the problem that the pointer "sp" is double free
by zhangyue 15 Nov '21

15 Nov '21

kylin inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AFG6?from=project-issue CVE: NA in function qla24xx_sp_unmap, it is already called sp->free(sp), then it`s not need to called sp->free(sp) after qla24xx_sp_unmap is called. Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- drivers/scsi/qla2xxx/qla_gs.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index c3195d4c25e5..a7198a1e23fb 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -4228,7 +4228,6 @@ static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res) if (rc) { /* Cleanup here to prevent memory leak */ qla24xx_sp_unmap(vha, sp); - sp->free(sp); } spin_lock_irqsave(&vha->work_lock, flags); -- 2.30.0

1 0

[PATCH kernel-4.19] fix the problem that the pointer "sp" is double free
by zhangyue 13 Nov '21

13 Nov '21

mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4AFG6?from=project-issue CVE: NA in function qla24xx_sp_unmap, it is already called sp->free(sp), then it`s not need to called sp->free(sp) after qla24xx_sp_unmap is called. Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- drivers/scsi/qla2xxx/qla_gs.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index c3195d4c25e5..a7198a1e23fb 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -4228,7 +4228,6 @@ static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res) if (rc) { /* Cleanup here to prevent memory leak */ qla24xx_sp_unmap(vha, sp); - sp->free(sp); } spin_lock_irqsave(&vha->work_lock, flags); -- 2.30.0

2 1

[PATCH OLK-5.10 0/3] support test GCM/CCM mode for SM4
by shenzijun 13 Nov '21

13 Nov '21

From: 沈子俊 <shenzijun(a)kylinos.cn> The GCM/CCM mode of SM4 is defined in the RFC 8998 specification: https://datatracker.ietf.org/doc/html/rfc8998 沈子俊 (3): crypto: tcrypt - Fix missing return value check crypto: testmgr - Add GCM/CCM mode test of SM4 algorithm crypto: tcrypt - add GCM/CCM mode test for SM4 algorithm crypto/tcrypt.c | 73 ++++++++++++++++++++--- crypto/testmgr.c | 29 ++++++++++ crypto/testmgr.h | 148 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 241 insertions(+), 9 deletions(-) -- 2.30.0

1 3

[PATCH openEuler-1.0-LTS 1/2] crypto: hisilicon - add CRYPTO_TFM_REQ_MAY_BACKLOG flag judge in sec_process()
by Yang Yingliang 12 Nov '21

12 Nov '21

From: Yu'an Wang <wangyuan46(a)huawei.com> driver inclusion category: Bugfix bugzilla: NA CVE: NA Set the flag CRYPTO_TFM_REQ_MAY_BACKLOG in the crypto driver, which can limit task process Signed-off-by: Yu'an Wang <wangyuan46(a)huawei.com> Reviewed-by: Longfang Liu <liulongfang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/crypto/hisilicon/sec2/sec.h | 1 + drivers/crypto/hisilicon/sec2/sec_crypto.c | 11 ++++++++--- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h index f6d1878edcc5c..51b93e25b750b 100644 --- a/drivers/crypto/hisilicon/sec2/sec.h +++ b/drivers/crypto/hisilicon/sec2/sec.h @@ -43,6 +43,7 @@ struct sec_req { int err_type; int req_id; + u32 flag; /* Status of the SEC request */ bool fake_busy; diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c index 68fb0e5ef761d..482aa8d26640e 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.c +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c @@ -171,10 +171,13 @@ static int sec_bd_send(struct sec_ctx *ctx, struct sec_req *req) struct sec_qp_ctx *qp_ctx = req->qp_ctx; int ret; - mutex_lock(&qp_ctx->req_lock); + if (ctx->fake_req_limit <= + atomic_read(&qp_ctx->qp->qp_status.used) && + !(req->flag & CRYPTO_TFM_REQ_MAY_BACKLOG)) + return -EBUSY; + mutex_lock(&qp_ctx->req_lock); ret = hisi_qp_send(qp_ctx->qp, &req->sec_sqe); - if (ctx->fake_req_limit <= atomic_read(&qp_ctx->qp->qp_status.used) && !ret) { list_add_tail(&req->backlog_head, &qp_ctx->backlog); @@ -917,7 +920,8 @@ static int sec_process(struct sec_ctx *ctx, struct sec_req *req) sec_update_iv(req, ctx->alg_type); ret = ctx->req_op->bd_send(ctx, req); - if (unlikely(ret != -EBUSY && ret != -EINPROGRESS)) { + if (unlikely((ret != -EBUSY && ret != -EINPROGRESS) || + (ret == -EBUSY && !(req->flag & CRYPTO_TFM_REQ_MAY_BACKLOG)))) { dev_err_ratelimited(SEC_CTX_DEV(ctx), "send sec request failed!\n"); goto err_send_req; @@ -1009,6 +1013,7 @@ static int sec_skcipher_crypto(struct skcipher_request *sk_req, bool encrypt) if (!sk_req->cryptlen) return 0; + req->flag = sk_req->base.flags; req->c_req.sk_req = sk_req; req->c_req.encrypt = encrypt; req->ctx = ctx; -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 1/3] tcp: always set retrans_stamp on recovery
by Yang Yingliang 12 Nov '21

12 Nov '21

From: Yuchung Cheng <ycheng(a)google.com> mainline inclusion from mainline-v5.1-rc1 commit 7ae189759cc48cf8b54beebff566e9fd2d4e7d7c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue CVE: NA ------------------------------------------------------------ Previously TCP socket's retrans_stamp is not set if the retransmission has failed to send. As a result if a socket is experiencing local issues to retransmit packets, determining when to abort a socket is complicated w/o knowning the starting time of the recovery since retrans_stamp may remain zero. This complication causes sub-optimal behavior that TCP may use the latest, instead of the first, retransmission time to compute the elapsed time of a stalling connection due to local issues. Then TCP may disrecard TCP retries settings and keep retrying until it finally succeed: not a good idea when the local host is already strained. The simple fix is to always timestamp the start of a recovery. It's worth noting that retrans_stamp is also used to compare echo timestamp values to detect spurious recovery. This patch does not break that because retrans_stamp is still later than when the original packet was sent. Signed-off-by: Yuchung Cheng <ycheng(a)google.com> Signed-off-by: Eric Dumazet <edumazet(a)google.com> Reviewed-by: Neal Cardwell <ncardwell(a)google.com> Reviewed-by: Soheil Hassas Yeganeh <soheil(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Conflicts: net/ipv4/tcp_timer.c Signed-off-by: Jiazhenyuan <jiazhenyuan@uniontech> #openEuler_contributor Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/ipv4/tcp_output.c | 9 ++++----- net/ipv4/tcp_timer.c | 23 +++-------------------- 2 files changed, 7 insertions(+), 25 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 97b9d671a83c9..6710056fd1b23 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3011,13 +3011,12 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) #endif TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS; tp->retrans_out += tcp_skb_pcount(skb); - - /* Save stamp of the first retransmit. */ - if (!tp->retrans_stamp) - tp->retrans_stamp = tcp_skb_timestamp(skb); - } + /* Save stamp of the first (attempted) retransmit. */ + if (!tp->retrans_stamp) + tp->retrans_stamp = tcp_skb_timestamp(skb); + if (tp->undo_retrans < 0) tp->undo_retrans = 0; tp->undo_retrans += tcp_skb_pcount(skb); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 681882a409686..8435cbad337d8 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,27 +22,13 @@ #include <linux/gfp.h> #include <net/tcp.h> -static u32 tcp_retransmit_stamp(const struct sock *sk) -{ - u32 start_ts = tcp_sk(sk)->retrans_stamp; - - if (unlikely(!start_ts)) { - struct sk_buff *head = tcp_rtx_queue_head(sk); - - if (!head) - return 0; - start_ts = tcp_skb_timestamp(head); - } - return start_ts; -} - static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); u32 elapsed, start_ts; - start_ts = tcp_retransmit_stamp(sk); - if (!icsk->icsk_user_timeout || !start_ts) + start_ts = tcp_sk(sk)->retrans_stamp; + if (!icsk->icsk_user_timeout) return icsk->icsk_rto; elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts; if (elapsed >= icsk->icsk_user_timeout) @@ -196,10 +182,7 @@ static bool retransmits_timed_out(struct sock *sk, if (!inet_csk(sk)->icsk_retransmits) return false; - start_ts = tcp_retransmit_stamp(sk); - if (!start_ts) - return false; - + start_ts = tcp_sk(sk)->retrans_stamp; if (likely(timeout == 0)) { linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS 01/49] perf/x86/intel/pt: Fix mask of num_address_ranges
by Yang Yingliang 12 Nov '21

12 Nov '21

From: Xiaoyao Li <xiaoyao.li(a)intel.com> stable inclusion from linux-4.19.207 commit f109e8a1678ce920b7f0df7865f2a31754ec5d1c -------------------------------- [ Upstream commit c53c6b7409f4cd9e542991b53d597fbe2751d7db ] Per SDM, bit 2:0 of CPUID(0x14,1).EAX[2:0] reports the number of configurable address ranges for filtering, not bit 1:0. Signed-off-by: Xiaoyao Li <xiaoyao.li(a)intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Acked-by: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Link: https://lkml.kernel.org/r/20210824040622.4081502-1-xiaoyao.li@intel.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/x86/events/intel/pt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index db969f3f175cb..774fb0f0bf6df 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -69,7 +69,7 @@ static struct pt_cap_desc { PT_CAP(topa_multiple_entries, 0, CPUID_ECX, BIT(1)), PT_CAP(single_range_output, 0, CPUID_ECX, BIT(2)), PT_CAP(payloads_lip, 0, CPUID_ECX, BIT(31)), - PT_CAP(num_address_ranges, 1, CPUID_EAX, 0x3), + PT_CAP(num_address_ranges, 1, CPUID_EAX, 0x7), PT_CAP(mtc_periods, 1, CPUID_EAX, 0xffff0000), PT_CAP(cycle_thresholds, 1, CPUID_EBX, 0xffff), PT_CAP(psb_periods, 1, CPUID_EBX, 0xffff0000), -- 2.25.1

1 48

[PATCH openEuler-1.0-LTS 1/9] Revert "EMMC: fix ascend hisi emmc probe failed problem according to mmc_host struct"
by Yang Yingliang 12 Nov '21

12 Nov '21

From: zhangguijiang <zhangguijiang(a)huawei.com> ascend inclusion category: bugfix feature: Ascend emmc adaption bugzilla: https://gitee.com/openeuler/kernel/issues/I4F4LL CVE: NA -------------------- This reverts commit 80e65cb9c78f00090a95e6db3126e3e60ec2804d. Signed-off-by: zhangguijiang <zhangguijiang(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Reviewed-by: YANHONG LU <luyanhong.luyanhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/mmc/core/sd.c | 38 +++++++++++++++++++++++++++++--- drivers/mmc/host/dw_mmc_extern.h | 2 +- include/linux/mmc/host.h | 2 +- 3 files changed, 37 insertions(+), 5 deletions(-) diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index 8760b749292b8..20ca371b9f874 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -1163,9 +1163,9 @@ static int _mmc_sd_suspend(struct mmc_host *host) err = mmc_deselect_cards(host); if (!err) { - if (!mmc_is_ascend_customized(host->parent)) + if (!(mmc_is_ascend_customized(host->parent))) mmc_power_off(host); - else if (!mmc_card_keep_power(host)) + else if (mmc_card_keep_power(host)) mmc_power_off(host); mmc_card_set_suspended(host->card); } @@ -1269,10 +1269,42 @@ static int mmc_sd_runtime_resume(struct mmc_host *host) return 0; } +#ifdef CONFIG_ASCEND_HISI_MMC +/*********************sd ops begin**********************/ +static int mmc_do_sd_reset(struct mmc_host *host) +{ + struct mmc_card *card = host->card; + + if (!host->bus_ops->power_restore) + return -EOPNOTSUPP; + + if (!card) + return -EINVAL; + + /* hw_reset for ip reset */ + if (host->ops->hw_reset) + host->ops->hw_reset(host); + + /* Only for K930/920 SD slow down clk*/ + if (host->ops->slowdown_clk) + host->ops->slowdown_clk(host, host->ios.timing); + + mmc_power_off(host); + mmc_set_clock(host, host->f_init); + /* Wait at least 200 ms */ + mmc_delay(200); + mmc_power_up(host, host->card->ocr); + (void)mmc_select_voltage(host, host->card->ocr); + + return host->bus_ops->power_restore(host); +} +#endif static int mmc_sd_hw_reset(struct mmc_host *host) { +#ifdef CONFIG_ASCEND_HISI_MMC if (mmc_is_ascend_customized(host->parent)) - return mmc_sd_reset(host); + return mmc_do_sd_reset(host); +#endif mmc_power_cycle(host, host->card->ocr); return mmc_sd_init_card(host, host->card->ocr, host->card); } diff --git a/drivers/mmc/host/dw_mmc_extern.h b/drivers/mmc/host/dw_mmc_extern.h index ab077b4955940..04d8c23f39e9a 100644 --- a/drivers/mmc/host/dw_mmc_extern.h +++ b/drivers/mmc/host/dw_mmc_extern.h @@ -8,7 +8,7 @@ #include "dw_mmc.h" -#if defined(CONFIG_MMC_DW_HI3XXX) || defined(CONFIG_MMC_DW_HI3XXX_MODULE) +#ifdef CONFIG_MMC_DW_HI3XXX_MODULE extern void dw_mci_reg_dump(struct dw_mci *host); extern void dw_mci_set_timeout(struct dw_mci *host); extern bool dw_mci_stop_abort_cmd(struct mmc_command *cmd); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index fabc23d156242..78b4d0a813b71 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -542,13 +542,13 @@ struct mmc_host { bool cqe_enabled; bool cqe_on; + unsigned long private[0] ____cacheline_aligned; #ifdef CONFIG_ASCEND_HISI_MMC const struct mmc_cmdq_host_ops *cmdq_ops; int sdio_present; unsigned int cmdq_slots; struct mmc_cmdq_context_info cmdq_ctx; #endif - unsigned long private[0] ____cacheline_aligned; }; struct device_node; -- 2.25.1

1 8

[PATCH openEuler-1.0-LTS] iommu: support phytium ft2000plus and S2500 iommu function
by Yang Yingliang 11 Nov '21

11 Nov '21

From: Mao HongBo <maohongbo(a)phytium.com.cn> phytium inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I41AUQ ----------------------------------- To fix iommu issue of device access in virtualization scenario for ft2000plus and S2500. Convert to new cputype macros naming of phytium. Signed-off-by: Mao HongBo <maohongbo(a)phytium.com.cn> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/include/asm/cputype.h | 14 +++++-- .../arm64/include/asm/phytium_machine_types.h | 37 +++++++++++++++++++ arch/arm64/kernel/topology.c | 2 +- drivers/iommu/arm-smmu.c | 29 +++++++++++++-- drivers/irqchip/irq-gic-v3-its.c | 9 +++++ drivers/pci/quirks.c | 4 ++ drivers/usb/host/xhci-pci.c | 2 +- 7 files changed, 87 insertions(+), 10 deletions(-) create mode 100644 arch/arm64/include/asm/phytium_machine_types.h diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 23298b0aedaf7..aa38796121300 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -101,8 +101,11 @@ #define HISI_CPU_PART_TSV110 0xD01 #define HISI_CPU_PART_TSV200 0xD02 -#define PHYTIUM_CPU_PART_FTC662 0x662 -#define PHYTIUM_CPU_PART_FTC663 0x663 +#define PHYTIUM_CPU_PART_1500A 0X660 +#define PHYTIUM_CPU_PART_2000AHK 0X661 +#define PHYTIUM_CPU_PART_2000PLUS 0X662 +#define PHYTIUM_CPU_PART_2004 0X663 +#define PHYTIUM_CPU_PART_2500 0X663 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) @@ -124,8 +127,11 @@ #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL) #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110) #define MIDR_HISI_TSV200 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV200) -#define MIDR_PHYTIUM_FT2000PLUS MIDR_CPU_MODEL(ARM_CPU_IMP_PHYTIUM, PHYTIUM_CPU_PART_FTC662) -#define MIDR_PHYTIUM_FT2500 MIDR_CPU_MODEL(ARM_CPU_IMP_PHYTIUM, PHYTIUM_CPU_PART_FTC663) +#define MIDR_FT_1500A MIDR_CPU_MODEL(ARM_CPU_IMP_PHYTIUM, PHYTIUM_CPU_PART_1500A) +#define MIDR_FT_2000AHK MIDR_CPU_MODEL(ARM_CPU_IMP_PHYTIUM, PHYTIUM_CPU_PART_2000AHK) +#define MIDR_FT_2000PLUS MIDR_CPU_MODEL(ARM_CPU_IMP_PHYTIUM, PHYTIUM_CPU_PART_2000PLUS) +#define MIDR_FT_2004 MIDR_CPU_MODEL(ARM_CPU_IMP_PHYTIUM, PHYTIUM_CPU_PART_2004) +#define MIDR_FT_2500 MIDR_CPU_MODEL(ARM_CPU_IMP_PHYTIUM, PHYTIUM_CPU_PART_2500) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/phytium_machine_types.h b/arch/arm64/include/asm/phytium_machine_types.h new file mode 100644 index 0000000000000..fb791988f0cee --- /dev/null +++ b/arch/arm64/include/asm/phytium_machine_types.h @@ -0,0 +1,37 @@ +/* + * Authors: Wang Yinfeng <wangyinfenng(a)phytium.com.cn> + * + * Copyright (C) 2021, PHYTIUM Information Technology Co., Ltd. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __PHYTIUM_MACHINE_TYPES_H__ +#define __PHYTIUM_MACHINE_TYPES_H__ + +#include <asm/cputype.h> +#include <linux/types.h> + +static inline bool phytium_part(u32 cpuid) +{ + return ((read_cpuid_id() & MIDR_CPU_MODEL_MASK) == cpuid); +} + +#define typeof_ft1500a() phytium_part(MIDR_FT_1500A) +#define typeof_ft2000ahk() phytium_part(MIDR_FT_2000AHK) +#define typeof_ft2000plus() phytium_part(MIDR_FT_2000PLUS) +#define typeof_ft2004() phytium_part(MIDR_FT_2004) +#define typeof_s2500() phytium_part(MIDR_FT_2500) + +#endif diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 02d3e688d657d..2646695e2f2a4 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -291,7 +291,7 @@ void store_cpu_topology(unsigned int cpuid) cpuid_topo->package_id = cpu_to_node(cpuid); /* Some PHYTIUM FT2000PLUS platform firmware has no PPTT table */ - if ((read_cpuid_id() & MIDR_CPU_MODEL_MASK) == MIDR_PHYTIUM_FT2000PLUS + if ((read_cpuid_id() & MIDR_CPU_MODEL_MASK) == MIDR_FT_2000PLUS && cpu_to_node(cpuid) == NUMA_NO_NODE) { cpuid_topo->thread_id = 0; cpuid_topo->package_id = 0; diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 8a268ab82ef02..18863198bb036 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -56,6 +56,10 @@ #include "arm-smmu-regs.h" +#ifdef CONFIG_ARCH_PHYTIUM +#include <asm/phytium_machine_types.h> +#endif + /* * Apparently, some Qualcomm arm64 platforms which appear to expose their SMMU * global register space are still, in fact, using a hypervisor to mediate it @@ -1407,6 +1411,20 @@ static int arm_smmu_add_device(struct device *dev) return -ENODEV; } +#ifdef CONFIG_ARCH_PHYTIUM + /* ft2000+ */ + if (typeof_ft2000plus()) { + int num = fwspec->num_ids; + + for (i = 0; i < num; i++) { +#define FWID_READ(id) (((u16)(id) >> 3) | (((id) >> SMR_MASK_SHIFT | 0x7000) << SMR_MASK_SHIFT)) + u32 fwid = FWID_READ(fwspec->ids[i]); + + iommu_fwspec_add_ids(dev, &fwid, 1); + } + } +#endif + ret = -EINVAL; for (i = 0; i < fwspec->num_ids; i++) { u16 sid = fwspec->ids[i]; @@ -1481,6 +1499,12 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev) if (group && smmu->s2crs[idx].group && group != smmu->s2crs[idx].group) return ERR_PTR(-EINVAL); +#ifdef CONFIG_ARCH_PHYTIUM + if (typeof_s2500()) + break; + if (typeof_ft2000plus() && !smmu->s2crs[idx].group) + continue; +#endif group = smmu->s2crs[idx].group; } @@ -1614,10 +1638,7 @@ static void arm_smmu_put_resv_regions(struct device *dev, #include <asm/cputype.h> static int phytium_smmu_def_domain_type(struct device *dev, unsigned int *type) { - u32 midr = read_cpuid_id(); - - if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_PHYTIUM_FT2000PLUS) - || ((midr & MIDR_CPU_MODEL_MASK) == MIDR_PHYTIUM_FT2500)) { + if (typeof_ft2000plus() || typeof_s2500()) { *type = IOMMU_DOMAIN_IDENTITY; return 0; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 1a2ecfa23fd8c..79648a2139412 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -51,6 +51,10 @@ #include "irq-gic-common.h" +#ifdef CONFIG_ARCH_PHYTIUM +#include <asm/phytium_machine_types.h> +#endif + #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING (1ULL << 0) #define ITS_FLAGS_WORKAROUND_CAVIUM_22375 (1ULL << 1) #define ITS_FLAGS_WORKAROUND_CAVIUM_23144 (1ULL << 2) @@ -1223,6 +1227,11 @@ static void its_irq_compose_msi_msg(struct irq_data *d, struct msi_msg *msg) msg->address_hi = upper_32_bits(addr); msg->data = its_get_event_id(d); +#ifdef CONFIG_ARCH_PHYTIUM + if (typeof_ft2000plus()) + return; +#endif + iommu_dma_map_msi_msg(d->irq, msg); } diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 961003c6dc807..99657b9bc82e0 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4646,6 +4646,10 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_ZHAOXIN, 0x9083, pci_quirk_mf_endpoint_acs }, /* Zhaoxin Root/Downstream Ports */ { PCI_VENDOR_ID_ZHAOXIN, PCI_ANY_ID, pci_quirk_zhaoxin_pcie_ports_acs }, + /* because PLX switch Vendor id is 0x10b5 on phytium cpu */ + { 0x10b5, PCI_ANY_ID, pci_quirk_xgene_acs }, + /* because rootcomplex Vendor id is 0x17cd on phytium cpu */ + { 0x17cd, PCI_ANY_ID, pci_quirk_xgene_acs }, { 0 } }; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 886cd6fc4b640..238a32cc311c9 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -313,7 +313,7 @@ static void phytium_xhci_pci_workaround(struct pci_dev *dev) u32 midr = read_cpuid_id(); /* Firmware bug, DMA mask is not reported by the firmware */ - if ((midr & MIDR_CPU_MODEL_MASK) == MIDR_PHYTIUM_FT2000PLUS) + if ((midr & MIDR_CPU_MODEL_MASK) == MIDR_FT_2000PLUS) dma_set_mask(&dev->dev, DMA_BIT_MASK(64)); } #else -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] arm64: Errata: fix kabi changed by cpu_errata and enable idc
by Yang Yingliang 11 Nov '21

11 Nov '21

From: Weilong Chen <chenweilong(a)huawei.com> ascend inclusion category: feature bugzilla: 46922 CVE: NA ------------------------------------- Patch "cache: Workaround HiSilicon Taishan DC CVAU" breaks the kabi symbols: cpu_hwcaps cpu_hwcap_keys Patch "arm64: Errata: fix kabi changed by cpu_errata" try to fix it but incomplete. Eable IDC on platform TSV{110,200}. Signed-off-by: Weilong Chen <chenweilong(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/kernel/cpufeature.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 822e6a2c0af1d..1bf9d84265de2 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -912,6 +912,19 @@ static bool has_cache_idc(const struct arm64_cpu_capabilities *entry, { u64 ctr; +#ifndef CONFIG_HISILICON_ERRATUM_1980005 + /* Fix kABI compatible for CONFIG_HISILICON_ERRATUM_1980005 */ + static const struct midr_range idc_support_list[] = { + MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_REV(MIDR_HISI_TSV200, 1, 0), + { /* sentinel */ } + }; + if (is_midr_in_range_list(read_cpuid_id(), idc_support_list)) { + pr_info("CPU features: detected: Taishan IDC coherence workaround\n"); + return true; + } +#endif + if (scope == SCOPE_SYSTEM) ctr = arm64_ftr_reg_ctrel0.sys_val; else -- 2.25.1

1 0

[PATCH openEuler-5.10 01/59] psi: support psi under cgroup v1
by Zheng Zengkai 11 Nov '21

11 Nov '21

From: Xunlei Pang <xlpang(a)linux.alibaba.com> Export "cpu|io|memory.pressure" to cgroup v1 "cpuacct" subsystem. hulk inclusion category: feature bugzilla: 182979 https://gitee.com/openeuler/kernel/issues/I4HOX6 ------------------------------------------ Reviewed-by: Joseph Qi <joseph.qi(a)linux.alibaba.com> Signed-off-by: Xunlei Pang <xlpang(a)linux.alibaba.com> Signed-off-by: Chen Wandun <chenwandun(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- init/Kconfig | 10 ++++++++++ kernel/cgroup/cgroup.c | 28 ++++++++++++++++++++++++++++ kernel/sched/cpuacct.c | 10 ++++++++++ kernel/sched/psi.c | 4 ++++ kernel/sched/sched.h | 4 ++++ 5 files changed, 56 insertions(+) diff --git a/init/Kconfig b/init/Kconfig index 04bc46ca0b9e..0afdb08131eb 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -635,6 +635,16 @@ config PSI_DEFAULT_DISABLED Say N if unsure. +config PSI_CGROUP_V1 + bool "Support PSI under cgroup v1" + default Y + depends on PSI + help + If set, pressure stall information tracking will be used + for cgroup v1 other than v2. + + Say N if unsure. + endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 701ef7ba4f95..86ab4a1305f6 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3659,6 +3659,34 @@ static void cgroup_pressure_release(struct kernfs_open_file *of) { psi_trigger_replace(&of->priv, NULL); } + +struct cftype cgroup_v1_psi_files[] = { + { + .name = "io.pressure", + .flags = CFTYPE_NO_PREFIX, + .seq_show = cgroup_io_pressure_show, + .write = cgroup_io_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, + { + .name = "memory.pressure", + .flags = CFTYPE_NO_PREFIX, + .seq_show = cgroup_memory_pressure_show, + .write = cgroup_memory_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, + { + .name = "cpu.pressure", + .flags = CFTYPE_NO_PREFIX, + .seq_show = cgroup_cpu_pressure_show, + .write = cgroup_cpu_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, + { } /* terminate */ +}; #endif /* CONFIG_PSI */ static int cgroup_freeze_show(struct seq_file *seq, void *v) diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 941c28cf9738..4e5488659339 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -374,3 +374,13 @@ struct cgroup_subsys cpuacct_cgrp_subsys = { .legacy_cftypes = files, .early_init = true, }; + +#ifdef CONFIG_PSI +static int __init cgroup_v1_psi_init(void) +{ + cgroup_add_legacy_cftypes(&cpuacct_cgrp_subsys, cgroup_v1_psi_files); + return 0; +} + +late_initcall_sync(cgroup_v1_psi_init); +#endif diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index d50a31ecedee..0b48a74cbfac 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -752,7 +752,11 @@ static struct psi_group *iterate_groups(struct task_struct *task, void **iter) struct cgroup *cgroup = NULL; if (!*iter) +#ifdef CONFIG_PSI_CGROUP_V1 + cgroup = task_cgroup(task, cpuacct_cgrp_id); +#else cgroup = task->cgroups->dfl_cgrp; +#endif else if (*iter == &psi_system) return NULL; else diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4ce573eeca4c..e29f051f824f 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2585,6 +2585,10 @@ unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned } #endif +#ifdef CONFIG_PSI +extern struct cftype cgroup_v1_psi_files[]; +#endif + #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) #define perf_domain_span(pd) (to_cpumask(((pd)->em_pd->cpus))) -- 2.20.1

1 58

[PATCH openEuler-1.0-LTS] blk-mq: don't free tags if the tag_set is used by other device in queue initialztion
by Yang Yingliang 10 Nov '21

10 Nov '21

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v5.16 commit a846a8e6c9a5949582c5a6a8bbc83a7d27fd891e category: bugfix bugzilla: 185668 CVE: NA ----------------------------------------------- We got UAF report on v5.10 as follows: [ 1446.674930] ================================================================== [ 1446.675970] BUG: KASAN: use-after-free in blk_mq_get_driver_tag+0x9a4/0xa90 [ 1446.676902] Read of size 8 at addr ffff8880185afd10 by task kworker/1:2/12348 [ 1446.677851] [ 1446.678073] CPU: 1 PID: 12348 Comm: kworker/1:2 Not tainted 5.10.0-10177-gc9c81b1e346a #2 [ 1446.679168] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 1446.680692] Workqueue: kthrotld blk_throtl_dispatch_work_fn [ 1446.681448] Call Trace: [ 1446.681800] dump_stack+0x9b/0xce [ 1446.682916] print_address_description.constprop.6+0x3e/0x60 [ 1446.685999] kasan_report.cold.9+0x22/0x3a [ 1446.687186] blk_mq_get_driver_tag+0x9a4/0xa90 [ 1446.687785] blk_mq_dispatch_rq_list+0x21a/0x1d40 [ 1446.692576] __blk_mq_do_dispatch_sched+0x394/0x830 [ 1446.695758] __blk_mq_sched_dispatch_requests+0x398/0x4f0 [ 1446.698279] blk_mq_sched_dispatch_requests+0xdf/0x140 [ 1446.698967] __blk_mq_run_hw_queue+0xc0/0x270 [ 1446.699561] __blk_mq_delay_run_hw_queue+0x4cc/0x550 [ 1446.701407] blk_mq_run_hw_queue+0x13b/0x2b0 [ 1446.702593] blk_mq_sched_insert_requests+0x1de/0x390 [ 1446.703309] blk_mq_flush_plug_list+0x4b4/0x760 [ 1446.705408] blk_flush_plug_list+0x2c5/0x480 [ 1446.708471] blk_finish_plug+0x55/0xa0 [ 1446.708980] blk_throtl_dispatch_work_fn+0x23b/0x2e0 [ 1446.711236] process_one_work+0x6d4/0xfe0 [ 1446.711778] worker_thread+0x91/0xc80 [ 1446.713400] kthread+0x32d/0x3f0 [ 1446.714362] ret_from_fork+0x1f/0x30 [ 1446.714846] [ 1446.715062] Allocated by task 1: [ 1446.715509] kasan_save_stack+0x19/0x40 [ 1446.716026] __kasan_kmalloc.constprop.1+0xc1/0xd0 [ 1446.716673] blk_mq_init_tags+0x6d/0x330 [ 1446.717207] blk_mq_alloc_rq_map+0x50/0x1c0 [ 1446.717769] __blk_mq_alloc_map_and_request+0xe5/0x320 [ 1446.718459] blk_mq_alloc_tag_set+0x679/0xdc0 [ 1446.719050] scsi_add_host_with_dma.cold.3+0xa0/0x5db [ 1446.719736] virtscsi_probe+0x7bf/0xbd0 [ 1446.720265] virtio_dev_probe+0x402/0x6c0 [ 1446.720808] really_probe+0x276/0xde0 [ 1446.721320] driver_probe_device+0x267/0x3d0 [ 1446.721892] device_driver_attach+0xfe/0x140 [ 1446.722491] __driver_attach+0x13a/0x2c0 [ 1446.723037] bus_for_each_dev+0x146/0x1c0 [ 1446.723603] bus_add_driver+0x3fc/0x680 [ 1446.724145] driver_register+0x1c0/0x400 [ 1446.724693] init+0xa2/0xe8 [ 1446.725091] do_one_initcall+0x9e/0x310 [ 1446.725626] kernel_init_freeable+0xc56/0xcb9 [ 1446.726231] kernel_init+0x11/0x198 [ 1446.726714] ret_from_fork+0x1f/0x30 [ 1446.727212] [ 1446.727433] Freed by task 26992: [ 1446.727882] kasan_save_stack+0x19/0x40 [ 1446.728420] kasan_set_track+0x1c/0x30 [ 1446.728943] kasan_set_free_info+0x1b/0x30 [ 1446.729517] __kasan_slab_free+0x111/0x160 [ 1446.730084] kfree+0xb8/0x520 [ 1446.730507] blk_mq_free_map_and_requests+0x10b/0x1b0 [ 1446.731206] blk_mq_realloc_hw_ctxs+0x8cb/0x15b0 [ 1446.731844] blk_mq_init_allocated_queue+0x374/0x1380 [ 1446.732540] blk_mq_init_queue_data+0x7f/0xd0 [ 1446.733155] scsi_mq_alloc_queue+0x45/0x170 [ 1446.733730] scsi_alloc_sdev+0x73c/0xb20 [ 1446.734281] scsi_probe_and_add_lun+0x9a6/0x2d90 [ 1446.734916] __scsi_scan_target+0x208/0xc50 [ 1446.735500] scsi_scan_channel.part.3+0x113/0x170 [ 1446.736149] scsi_scan_host_selected+0x25a/0x360 [ 1446.736783] store_scan+0x290/0x2d0 [ 1446.737275] dev_attr_store+0x55/0x80 [ 1446.737782] sysfs_kf_write+0x132/0x190 [ 1446.738313] kernfs_fop_write_iter+0x319/0x4b0 [ 1446.738921] new_sync_write+0x40e/0x5c0 [ 1446.739429] vfs_write+0x519/0x720 [ 1446.739877] ksys_write+0xf8/0x1f0 [ 1446.740332] do_syscall_64+0x2d/0x40 [ 1446.740802] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 1446.741462] [ 1446.741670] The buggy address belongs to the object at ffff8880185afd00 [ 1446.741670] which belongs to the cache kmalloc-256 of size 256 [ 1446.743276] The buggy address is located 16 bytes inside of [ 1446.743276] 256-byte region [ffff8880185afd00, ffff8880185afe00) [ 1446.744765] The buggy address belongs to the page: [ 1446.745416] page:ffffea0000616b00 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x185ac [ 1446.746694] head:ffffea0000616b00 order:2 compound_mapcount:0 compound_pincount:0 [ 1446.747719] flags: 0x1fffff80010200(slab|head) [ 1446.748337] raw: 001fffff80010200 ffffea00006a3208 ffffea000061bf08 ffff88801004f240 [ 1446.749404] raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 [ 1446.750455] page dumped because: kasan: bad access detected [ 1446.751227] [ 1446.751445] Memory state around the buggy address: [ 1446.752102] ffff8880185afc00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 1446.753090] ffff8880185afc80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 1446.754079] >ffff8880185afd00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 1446.755065] ^ [ 1446.755589] ffff8880185afd80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 1446.756574] ffff8880185afe00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 1446.757566] ================================================================== Flag 'BLK_MQ_F_TAG_QUEUE_SHARED' will be set if the second device on the same host initializes it's queue successfully. However, if the second device failed to allocate memory in blk_mq_alloc_and_init_hctx() from blk_mq_realloc_hw_ctxs() from blk_mq_init_allocated_queue(), __blk_mq_free_map_and_rqs() will be called on error path, and if 'BLK_MQ_TAG_HCTX_SHARED' is not set, 'tag_set->tags' will be freed while it's still used by the first device. To fix this issue we move release newly allocated hardware context from blk_mq_realloc_hw_ctxs to __blk_mq_update_nr_hw_queues. As there is needn't to release hardware context in blk_mq_init_allocated_queue. Fixes: 868f2f0b7206 ("blk-mq: dynamic h/w context count") Signed-off-by: Ye Bin <yebin10(a)huawei.com> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Ming Lei <ming.lei(a)redhat.com> Link: https://lore.kernel.org/r/20211108074019.1058843-1-yebin10@huawei.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> conflicts: block/blk-mq.c Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-mq.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 55c81dcafbdc2..ef62a83314a5d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2804,8 +2804,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx = hctxs[j]; if (hctx) { - if (hctx->tags) - blk_mq_free_map_and_requests(set, j); blk_mq_exit_hctx(q, set, hctx, j); hctxs[j] = NULL; } @@ -3236,8 +3234,13 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_realloc_hw_ctxs(set, q); if (q->nr_hw_queues != set->nr_hw_queues) { + int i = prev_nr_hw_queues; + pr_warn("Increasing nr_hw_queues to %d fails, fallback to %d\n", nr_hw_queues, prev_nr_hw_queues); + for (; i < set->nr_hw_queues; i++) + blk_mq_free_map_and_requests(set, i); + set->nr_hw_queues = prev_nr_hw_queues; blk_mq_map_queues(set); goto fallback; -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/2] nbd: add a flush_workqueue in nbd_start_device
by Yang Yingliang 10 Nov '21

10 Nov '21

From: Sun Ke <sunke32(a)huawei.com> mainline inclusion from mainline-v5.6-rc1 commit 5c0dd228b5fc30a3b732c7ae2657e0161ec7ed80 category: bugfix bugzilla: 185690 CVE: NA ----------------------------------------------- When kzalloc fail, may cause trying to destroy the workqueue from inside the workqueue. If num_connections is m (2 < m), and NO.1 ~ NO.n (1 < n < m) kzalloc are successful. The NO.(n + 1) failed. Then, nbd_start_device will return ENOMEM to nbd_start_device_ioctl, and nbd_start_device_ioctl will return immediately without running flush_workqueue. However, we still have n recv threads. If nbd_release run first, recv threads may have to drop the last config_refs and try to destroy the workqueue from inside the workqueue. To fix it, add a flush_workqueue in nbd_start_device. Fixes: e9e006f5fcf2 ("nbd: fix max number of supported devs") Signed-off-by: Sun Ke <sunke32(a)huawei.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/block/nbd.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 33a52be762d24..775cbb4c1bbcd 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1306,6 +1306,16 @@ static int nbd_start_device(struct nbd_device *nbd) args = kzalloc(sizeof(*args), GFP_KERNEL); if (!args) { sock_shutdown(nbd); + /* + * If num_connections is m (2 < m), + * and NO.1 ~ NO.n(1 < n < m) kzallocs are successful. + * But NO.(n + 1) failed. We still have n recv threads. + * So, add flush_workqueue here to prevent recv threads + * dropping the last config_refs and trying to destroy + * the workqueue from inside the workqueue. + */ + if (i) + flush_workqueue(nbd->recv_workq); return -ENOMEM; } sk_set_memalloc(config->socks[i]->sock->sk); -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 1/2] bpf, cgroup: Assign cgroup in cgroup_sk_alloc when called from interrupt
by Yang Yingliang 10 Nov '21

10 Nov '21

From: Daniel Borkmann <daniel(a)iogearbox.net> mainline inclusion from mainline-v5.15-rc4 commit 78cc316e9583067884eb8bd154301dc1e9ee945c category: bugfix bugzilla: 184472 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… If cgroup_sk_alloc() is called from interrupt context, then just assign the root cgroup to skcd->cgroup. Prior to commit 8520e224f547 ("bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode") we would just return, and later on in sock_cgroup_ptr(), we were NULL-testing the cgroup in fast-path, and iff indeed NULL returning the root cgroup (v ?: &cgrp_dfl_root.cgrp). Rather than re-adding the NULL-test to the fast-path we can just assign it once from cgroup_sk_alloc() given v1/v2 handling has been simplified. The migration from NULL test with returning &cgrp_dfl_root.cgrp to assigning &cgrp_dfl_root.cgrp directly does /not/ change behavior for callers of sock_cgroup_ptr(). syzkaller was able to trigger a splat in the legacy netrom code base, where the RX handler in nr_rx_frame() calls nr_make_new() which calls sk_alloc() and therefore cgroup_sk_alloc() with in_interrupt() condition. Thus the NULL skcd->cgroup, where it trips over on cgroup_sk_free() side given it expects a non-NULL object. There are a few other candidates aside from netrom which have similar pattern where in their accept-like implementation, they just call to sk_alloc() and thus cgroup_sk_alloc() instead of sk_clone_lock() with the corresponding cgroup_sk_clone() which then inherits the cgroup from the parent socket. None of them are related to core protocols where BPF cgroup programs are running from. However, in future, they should follow to implement a similar inheritance mechanism. Additionally, with a !CONFIG_CGROUP_NET_PRIO and !CONFIG_CGROUP_NET_CLASSID configuration, the same issue was exposed also prior to 8520e224f547 due to commit e876ecc67db8 ("cgroup: memcg: net: do not associate sock with unrelated cgroup") which added the early in_interrupt() return back then. Fixes: 8520e224f547 ("bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode") Fixes: e876ecc67db8 ("cgroup: memcg: net: do not associate sock with unrelated cgroup") Reported-by: syzbot+df709157a4ecaf192b03(a)syzkaller.appspotmail.com Reported-by: syzbot+533f389d4026d86a2a95(a)syzkaller.appspotmail.com Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Tested-by: syzbot+df709157a4ecaf192b03(a)syzkaller.appspotmail.com Tested-by: syzbot+533f389d4026d86a2a95(a)syzkaller.appspotmail.com Acked-by: Tejun Heo <tj(a)kernel.org> Link: https://lore.kernel.org/bpf/20210927123921.21535-1-daniel@iogearbox.net Conflicts: kernel/cgroup/cgroup.c Signed-off-by: Lu Jialin <lujialin4(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/cgroup/cgroup.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 682c5e231bddc..7897f1ab77266 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5935,8 +5935,11 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd) } /* Don't associate the sock with unrelated interrupted task's cgroup. */ - if (in_interrupt()) + if (in_interrupt()) { + cgroup_get(&cgrp_dfl_root.cgrp); + skcd->val = (unsigned long)&cgrp_dfl_root.cgrp; return; + } rcu_read_lock(); -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 1/7] sctp: use init_tag from inithdr for ABORT chunk
by Yang Yingliang 10 Nov '21

10 Nov '21

From: Xin Long <lucien.xin(a)gmail.com> mainline inclusion from mainline-v5.15 commit 4f7019c7eb33967eb87766e0e4602b5576873680 category: bugfix bugzilla: NA CVE: CVE-2021-3772 ------------------------------------------------- Currently Linux SCTP uses the verification tag of the existing SCTP asoc when failing to process and sending the packet with the ABORT chunk. This will result in the peer accepting the ABORT chunk and removing the SCTP asoc. One could exploit this to terminate a SCTP asoc. This patch is to fix it by always using the initiate tag of the received INIT chunk for the ABORT chunk to be sent. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Xin Long <lucien.xin(a)gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner(a)gmail.com> Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Huang Guobin <huangguobin4(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/sctp/sm_statefuns.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 19bd14a4eb07e..9ae0676afd5d4 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -6261,6 +6261,7 @@ static struct sctp_packet *sctp_ootb_pkt_new( * yet. */ switch (chunk->chunk_hdr->type) { + case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: { struct sctp_initack_chunk *initack; -- 2.25.1

1 6

[PATCH kernel-4.19] fix the problem that the pointer may be double free
by zhangyue 10 Nov '21

10 Nov '21

mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4AH11?from=project-issue CVE: NA int driver/md/md.c, if the function autorun_array() is called, first called do_md_run() and then do_md_stop(), this time, the pointer mddev->private may be double free Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- drivers/md/md.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 4406bb137a27..aa204ec74066 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6000,8 +6000,10 @@ static void __md_stop(struct mddev *mddev) spin_lock(&mddev->lock); mddev->pers = NULL; spin_unlock(&mddev->lock); - pers->free(mddev, mddev->private); - mddev->private = NULL; + if (mddev->private) { + pers->free(mddev, mddev->private); + mddev->private = NULL; + } if (pers->sync_request && mddev->to_remove == NULL) mddev->to_remove = &md_redundancy_group; module_put(pers->owner); -- 2.30.0

1 0

[PATCH kernel-4.19] bios_parser.c: fix uninitialized variable in device_type_from_device_id
by shenzijun 10 Nov '21

10 Nov '21

From: 沈子俊 <shenzijun(a)kylinos.cn> kylin inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AH6U?from=project-issue CVE: NA ----------------------------------------------------------------------------- add uninitialization of result_device_id.raw_device_tag Signed-off-by: 沈子俊 <shenzijun(a)kylinos.cn> --- drivers/gpu/drm/amd/display/dc/bios/bios_parser.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c index be8a2494355a..9375757fb640 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -2450,6 +2450,7 @@ static struct device_id device_type_from_device_id(uint16_t device_id) { struct device_id result_device_id; + result_device_id.raw_device_tag = 0; switch (device_id) { case ATOM_DEVICE_LCD1_SUPPORT: -- 2.30.0

1 0

Re: [PATCH openEuler-1.0-LTS 0/6] Fix the problem that the number of tcp timeout retransmissions is lost
by QiuLaibin 09 Nov '21

09 Nov '21

hi zhenyuan: 针对你先前提交的“Fix the problem that the number of tcp timeout retransmissions is lost”补丁集，我们在内部review的时候committer给了如下检视意见切换EDT主线有 tcp 和 fq 的几个patchset和bugfix, 这里建议先合入解决本问题后边的3个patch。因此是否只合后三个patch就可以满足能够解决你目前遇到的问题。 best regard On 2021/10/22 18:52, Jiazhenyuan wrote: > > > > From: Jiazhenyuan <jiazhenyuan(a)uniontech.com> > > issue: https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue > > jiazhenyuan (6): > tcp: switch tcp and sch_fq to new earliest departure time > net_sched: sch_fq: ensure maxrate fq parameter applies to EDT flows > From 9efdda4e3abed13f0903b7b6e4d4c2102019440a Mon Sep 17 00:00:00 2001 > From: Eric Dumazet <edumazet(a)google.com> Date: Sat, 24 Nov 2018 > 09:12:24 -0800 Subject: [PATCH] tcp: address problems caused by EDT > misshaps > From 7ae189759cc48cf8b54beebff566e9fd2d4e7d7c Mon Sep 17 00:00:00 2001 > From: Yuchung Cheng <ycheng(a)google.com> Date: Wed, 16 Jan 2019 > 15:05:30 -0800 Subject: [PATCH] tcp: always set retrans_stamp on > recovery > From 01a523b071618abbc634d1958229fe3bd2dfa5fa Mon Sep 17 00:00:00 2001 > From: Yuchung Cheng <ycheng(a)google.com> Date: Wed, 16 Jan 2019 > 15:05:32 -0800 Subject: [PATCH] tcp: create a helper to model > exponential backoff > From 3256a2d6ab1f71f9a1bd2d7f6f18eb8108c48d17 Mon Sep 17 00:00:00 2001 > From: Eric Dumazet <edumazet(a)google.com> Date: Mon, 30 Sep 2019 > 15:44:44 -0700 Subject: [PATCH] tcp: adjust rto_base in > retransmits_timed_out() > > net/ipv4/tcp_bbr.c | 7 +++-- > net/ipv4/tcp_input.c | 17 +++++++----- > net/ipv4/tcp_output.c | 29 ++++++++++++++------ > net/ipv4/tcp_timer.c | 64 ++++++++++++++++++++----------------------- > net/sched/sch_fq.c | 46 ++++++++++++++++++------------- > 5 files changed, 92 insertions(+), 71 deletions(-) > > -- > 2.27.0 > _______________________________________________ Kernel mailing list -- kernel(a)openeuler.org To unsubscribe send an email to kernel-leave(a)openeuler.org

2 1

(无主题)
by 汪越越 09 Nov '21

09 Nov '21

。

1 0

[PATCH openEuler-1.0-LTS 01/18] drivers/perf: arm_spe: Don't error on high-order pages for aux buf
by Yang Yingliang 09 Nov '21

09 Nov '21

From: Will Deacon <will.deacon(a)arm.com> mainline inclusion from mainline-v5.1-rc3 commit 14ae42a6f0b13130a97d94d23481128961de5d38 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4A1XO CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------------------------------------ Since commit 5768402fd9c6 ("perf/ring_buffer: Use high order allocations for AUX buffers optimistically"), the perf core tends to back aux buffer allocations with high-order pages with the order encoded in the PagePrivate data. The Arm SPE driver explicitly rejects such pages, causing the perf tool to fail with: | failed to mmap with 12 (Cannot allocate memory) In actual fact, we can simply treat these pages just like any other since the perf core takes care to populate the page array appropriately. In theory we could try to map with PMDs where possible, but for now, let's just get things working again. Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Fixes: 5768402fd9c6 ("perf/ring_buffer: Use high order allocations for AUX buffers optimistically") Reported-by: Hanjun Guo <guohanjun(a)huawei.com> Tested-by: Hanjun Guo <guohanjun(a)huawei.com> Tested-by: Sudeep Holla <sudeep.holla(a)arm.com> Signed-off-by: Will Deacon <will.deacon(a)arm.com> Signed-off-by: Qi Liu <liuqi115(a)huawei.com> Reviewed-by: Yang Jihong <yangjihong1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/perf/arm_spe_pmu.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index a11951b083307..4fb65c61c8eab 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -856,16 +856,8 @@ static void *arm_spe_pmu_setup_aux(struct perf_event *event, void **pages, if (!pglist) goto out_free_buf; - for (i = 0; i < nr_pages; ++i) { - struct page *page = virt_to_page(pages[i]); - - if (PagePrivate(page)) { - pr_warn("unexpected high-order page for auxbuf!"); - goto out_free_pglist; - } - + for (i = 0; i < nr_pages; ++i) pglist[i] = virt_to_page(pages[i]); - } buf->base = vmap(pglist, nr_pages, VM_MAP, PAGE_KERNEL); if (!buf->base) -- 2.25.1

1 17

[PATCH openEuler-1.0-LTS 1/2] drm/hisilicon: Support i2c driver algorithms for bit-shift adapters
by Yang Yingliang 09 Nov '21

09 Nov '21

From: Tian Tao <tiantao6(a)hisilicon.com> mainline inclusion from mainline-v5.14.0-rc7 commit 4eb4d99dfe3018d86f4529112aa7082f43b6996a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I469VQ CVE: NA Remove #include <drm/drm_probe_helper.h> in hibmc_drm_i2c.c. ----------------------------- Adding driver implementation to support i2c driver algorithms for bit-shift adapters, so hibmc will using the interface provided by drm to read edid. Signed-off-by: Tian Tao <tiantao6(a)hisilicon.com> Reviewed-by: Thomas Zimmermann <tzimmermann(a)suse.de> Link: https://patchwork.freedesktop.org/patch/msgid/1600778670-60370-2-git-send-e… Signed-off-by: gouhao <gouhao(a)uniontech.com> Reviewed-by: tian tao <tiantao6(a)hisilicon.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/gpu/drm/hisilicon/hibmc/Makefile | 3 +- .../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 25 +++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c | 98 +++++++++++++++++++ 3 files changed, 125 insertions(+), 1 deletion(-) create mode 100644 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c diff --git a/drivers/gpu/drm/hisilicon/hibmc/Makefile b/drivers/gpu/drm/hisilicon/hibmc/Makefile index 3df726696372f..71c248f4c7562 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/Makefile +++ b/drivers/gpu/drm/hisilicon/hibmc/Makefile @@ -1,3 +1,4 @@ -hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o hibmc_drm_fbdev.o hibmc_ttm.o +hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o \ + hibmc_drm_fbdev.o hibmc_ttm.o hibmc_drm_i2c.o obj-$(CONFIG_DRM_HISI_HIBMC) += hibmc-drm.o diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h index 4395dc6674bbc..c246151b29942 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h @@ -19,12 +19,18 @@ #ifndef HIBMC_DRM_DRV_H #define HIBMC_DRM_DRV_H +#include <linux/gpio/consumer.h> +#include <linux/i2c-algo-bit.h> +#include <linux/i2c.h> + +#include <drm/drm_edid.h> #include <drm/drmP.h> #include <drm/drm_atomic.h> #include <drm/drm_fb_helper.h> #include <drm/drm_gem.h> #include <drm/ttm/ttm_bo_driver.h> + struct hibmc_framebuffer { struct drm_framebuffer fb; struct drm_gem_object *obj; @@ -36,6 +42,13 @@ struct hibmc_fbdev { int size; }; +struct hibmc_connector { + struct drm_connector base; + + struct i2c_adapter adapter; + struct i2c_algo_bit_data bit_data; +}; + struct hibmc_drm_private { /* hw */ void __iomem *mmio; @@ -46,6 +59,7 @@ struct hibmc_drm_private { /* drm */ struct drm_device *dev; + struct hibmc_connector connector; bool mode_config_initialized; struct drm_atomic_state *suspend_state; @@ -60,6 +74,16 @@ struct hibmc_drm_private { bool mm_inited; }; +static inline struct hibmc_connector *to_hibmc_connector(struct drm_connector *connector) +{ + return container_of(connector, struct hibmc_connector, base); +} + +static inline struct hibmc_drm_private *to_hibmc_drm_private(struct drm_device *dev) +{ + return dev->dev_private; +} + #define to_hibmc_framebuffer(x) container_of(x, struct hibmc_framebuffer, fb) struct hibmc_bo { @@ -110,6 +134,7 @@ int hibmc_dumb_create(struct drm_file *file, struct drm_device *dev, int hibmc_dumb_mmap_offset(struct drm_file *file, struct drm_device *dev, u32 handle, u64 *offset); int hibmc_mmap(struct file *filp, struct vm_area_struct *vma); +int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_connector *connector); extern const struct drm_mode_config_funcs hibmc_mode_funcs; diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c new file mode 100644 index 0000000000000..ffd7c7bf4b7d8 --- /dev/null +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Hisilicon Hibmc SoC drm driver + * + * Based on the bochs drm driver. + * + * Copyright (c) 2016 Huawei Limited. + * + * Author: + * Tian Tao <tiantao6(a)hisilicon.com> + */ + +#include <linux/delay.h> +#include <linux/pci.h> + +#include <drm/drm_atomic_helper.h> + +#include "hibmc_drm_drv.h" + +#define GPIO_DATA 0x0802A0 +#define GPIO_DATA_DIRECTION 0x0802A4 + +#define I2C_SCL_MASK BIT(0) +#define I2C_SDA_MASK BIT(1) + +static void hibmc_set_i2c_signal(void *data, u32 mask, int value) +{ + struct hibmc_connector *hibmc_connector = data; + struct hibmc_drm_private *priv = to_hibmc_drm_private(hibmc_connector->base.dev); + u32 tmp_dir = readl(priv->mmio + GPIO_DATA_DIRECTION); + + if (value) { + tmp_dir &= ~mask; + writel(tmp_dir, priv->mmio + GPIO_DATA_DIRECTION); + } else { + u32 tmp_data = readl(priv->mmio + GPIO_DATA); + + tmp_data &= ~mask; + writel(tmp_data, priv->mmio + GPIO_DATA); + + tmp_dir |= mask; + writel(tmp_dir, priv->mmio + GPIO_DATA_DIRECTION); + } +} + +static int hibmc_get_i2c_signal(void *data, u32 mask) +{ + struct hibmc_connector *hibmc_connector = data; + struct hibmc_drm_private *priv = to_hibmc_drm_private(hibmc_connector->base.dev); + u32 tmp_dir = readl(priv->mmio + GPIO_DATA_DIRECTION); + + if ((tmp_dir & mask) != mask) { + tmp_dir &= ~mask; + writel(tmp_dir, priv->mmio + GPIO_DATA_DIRECTION); + } + + return (readl(priv->mmio + GPIO_DATA) & mask) ? 1 : 0; +} + +static void hibmc_ddc_setsda(void *data, int state) +{ + hibmc_set_i2c_signal(data, I2C_SDA_MASK, state); +} + +static void hibmc_ddc_setscl(void *data, int state) +{ + hibmc_set_i2c_signal(data, I2C_SCL_MASK, state); +} + +static int hibmc_ddc_getsda(void *data) +{ + return hibmc_get_i2c_signal(data, I2C_SDA_MASK); +} + +static int hibmc_ddc_getscl(void *data) +{ + return hibmc_get_i2c_signal(data, I2C_SCL_MASK); +} + +int hibmc_ddc_create(struct drm_device *drm_dev, + struct hibmc_connector *connector) +{ + connector->adapter.owner = THIS_MODULE; + connector->adapter.class = I2C_CLASS_DDC; + snprintf(connector->adapter.name, I2C_NAME_SIZE, "HIS i2c bit bus"); + connector->adapter.dev.parent = &drm_dev->pdev->dev; + i2c_set_adapdata(&connector->adapter, connector); + connector->adapter.algo_data = &connector->bit_data; + + connector->bit_data.udelay = 20; + connector->bit_data.timeout = usecs_to_jiffies(2000); + connector->bit_data.data = connector; + connector->bit_data.setsda = hibmc_ddc_setsda; + connector->bit_data.setscl = hibmc_ddc_setscl; + connector->bit_data.getsda = hibmc_ddc_getsda; + connector->bit_data.getscl = hibmc_ddc_getscl; + + return i2c_bit_add_bus(&connector->adapter); +} -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS] compiler.h: fix barrier_data() on clang
by Yang Yingliang 09 Nov '21

09 Nov '21

From: Arvind Sankar <nivedita(a)alum.mit.edu> stable inclusion from linux-4.19.164 commit b207caff4176e3a6ba273243da2db2e595e4aad2 CVE: CVE-2021-0938 -------------------------------- commit 3347acc6fcd4ee71ad18a9ff9d9dac176b517329 upstream. Commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") neglected to copy barrier_data() from compiler-gcc.h into compiler-clang.h. The definition in compiler-gcc.h was really to work around clang's more aggressive optimization, so this broke barrier_data() on clang, and consequently memzero_explicit() as well. For example, this results in at least the memzero_explicit() call in lib/crypto/sha256.c:sha256_transform() being optimized away by clang. Fix this by moving the definition of barrier_data() into compiler.h. Also move the gcc/clang definition of barrier() into compiler.h, __memory_barrier() is icc-specific (and barrier() is already defined using it in compiler-intel.h) and doesn't belong in compiler.h. [rdunlap(a)infradead.org: fix ALPHA builds when SMP is not enabled] Link: https://lkml.kernel.org/r/20201101231835.4589-1-rdunlap@infradead.org Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Signed-off-by: Arvind Sankar <nivedita(a)alum.mit.edu> Signed-off-by: Randy Dunlap <rdunlap(a)infradead.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Tested-by: Nick Desaulniers <ndesaulniers(a)google.com> Reviewed-by: Nick Desaulniers <ndesaulniers(a)google.com> Reviewed-by: Kees Cook <keescook(a)chromium.org> Cc: <stable(a)vger.kernel.org> Link: https://lkml.kernel.org/r/20201014212631.207844-1-nivedita@alum.mit.edu Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> [nd: backport to account for missing commit e506ea451254a ("compiler.h: Split {READ,WRITE}_ONCE definitions out into rwonce.h") commit d08b9f0ca6605 ("scs: Add support for Clang's Shadow Call Stack (SCS)") commit a3f8a30f3f00 ("Compiler Attributes: use feature checks instead of version checks")] Signed-off-by: Nick Desaulniers <ndesaulniers(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/compiler-clang.h | 1 - include/linux/compiler-gcc.h | 19 ------------------- include/linux/compiler.h | 18 ++++++++++++++++-- 3 files changed, 16 insertions(+), 22 deletions(-) diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index d756f2318efe0..2d6e5e4bb5d93 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -39,7 +39,6 @@ * and may be redefined here because they should not be shared with other * compilers, like ICC. */ -#define barrier() __asm__ __volatile__("" : : : "memory") #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) #define __assume_aligned(a, ...) \ __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 3ebee1ce6f982..14be095371093 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -14,25 +14,6 @@ # error Sorry, your compiler is too old - please upgrade it. #endif -/* Optimization barrier */ - -/* The "volatile" is due to gcc bugs */ -#define barrier() __asm__ __volatile__("": : :"memory") -/* - * This version is i.e. to prevent dead stores elimination on @ptr - * where gcc and llvm may behave differently when otherwise using - * normal barrier(): while gcc behavior gets along with a normal - * barrier(), llvm needs an explicit input variable to be assumed - * clobbered. The issue is as follows: while the inline asm might - * access any memory it wants, the compiler could have fit all of - * @ptr into memory registers instead, and since @ptr never escaped - * from that, it proved that the inline asm wasn't touching any of - * it. This version works well with both compilers, i.e. we're telling - * the compiler that the inline asm absolutely may see the contents - * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495 - */ -#define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory") - /* * This macro obfuscates arithmetic on a variable address so that gcc * shouldn't recognize the original var, and make assumptions about it. diff --git a/include/linux/compiler.h b/include/linux/compiler.h index bb22908c79e83..0e769548e14f8 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -79,11 +79,25 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Optimization barrier */ #ifndef barrier -# define barrier() __memory_barrier() +/* The "volatile" is due to gcc bugs */ +# define barrier() __asm__ __volatile__("": : :"memory") #endif #ifndef barrier_data -# define barrier_data(ptr) barrier() +/* + * This version is i.e. to prevent dead stores elimination on @ptr + * where gcc and llvm may behave differently when otherwise using + * normal barrier(): while gcc behavior gets along with a normal + * barrier(), llvm needs an explicit input variable to be assumed + * clobbered. The issue is as follows: while the inline asm might + * access any memory it wants, the compiler could have fit all of + * @ptr into memory registers instead, and since @ptr never escaped + * from that, it proved that the inline asm wasn't touching any of + * it. This version works well with both compilers, i.e. we're telling + * the compiler that the inline asm absolutely may see the contents + * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495 + */ +# define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory") #endif /* workaround for GCC PR82365 if needed */ -- 2.25.1

1 0

[PATCH openEuler-5.10] spfc: Fix compile errors when O=xxx is specified
by Zheng Zengkai 09 Nov '21

09 Nov '21

From: Yanling Song <songyl(a)ramaxel.com> Ramaxel inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4DBD7 CVE: NA ----------------------------------------- Fix two compile errors: 1. Compile failed when O=xxx is specified; 2. Compile conflicted when spfc and spnic are compiled in parallel by -j option because they share some .c files. make O=tmp -j200 > build.log In file included from ../drivers/scsi/spfc/hw/spfc_utils.c:4:0: ../drivers/scsi/spfc/hw/spfc_utils.h:7:10: fatal error: unf_type.h: No such file or directory #include "unf_type.h" ^~~~~~~~~~~~ compilation terminated. make[4]: *** [drivers/scsi/spfc/hw/spfc_utils.o] Error 1 make[4]: *** Waiting for unfinished jobs.... make[3]: *** [drivers/scsi/spfc] Error 2 make[3]: *** Waiting for unfinished jobs.... ../drivers/net/ethernet/ramaxel/spnic/spnic_sriov.c:9:10: fatal error: sphw_common.h: No such file or directory #include "sphw_common.h" ^~~~~~~~~~~~~~~ compilation terminated. Signed-off-by: Yanling Song <songyl(a)ramaxel.com> Reviewed-by: Zhang Lei<zhanglei48(a)huawei.com> [zzk: Adjusted commit message] Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/net/ethernet/ramaxel/spnic/Makefile | 2 +- drivers/scsi/spfc/Makefile | 30 ++++++++++----------- drivers/scsi/spfc/sphw_api_cmd.c | 1 + drivers/scsi/spfc/sphw_cmdq.c | 1 + drivers/scsi/spfc/sphw_common.c | 1 + drivers/scsi/spfc/sphw_eqs.c | 1 + drivers/scsi/spfc/sphw_hw_cfg.c | 1 + drivers/scsi/spfc/sphw_hw_comm.c | 1 + drivers/scsi/spfc/sphw_hwdev.c | 1 + drivers/scsi/spfc/sphw_hwif.c | 1 + drivers/scsi/spfc/sphw_mbox.c | 1 + drivers/scsi/spfc/sphw_mgmt.c | 1 + drivers/scsi/spfc/sphw_prof_adap.c | 1 + drivers/scsi/spfc/sphw_wq.c | 1 + 14 files changed, 28 insertions(+), 16 deletions(-) create mode 120000 drivers/scsi/spfc/sphw_api_cmd.c create mode 120000 drivers/scsi/spfc/sphw_cmdq.c create mode 120000 drivers/scsi/spfc/sphw_common.c create mode 120000 drivers/scsi/spfc/sphw_eqs.c create mode 120000 drivers/scsi/spfc/sphw_hw_cfg.c create mode 120000 drivers/scsi/spfc/sphw_hw_comm.c create mode 120000 drivers/scsi/spfc/sphw_hwdev.c create mode 120000 drivers/scsi/spfc/sphw_hwif.c create mode 120000 drivers/scsi/spfc/sphw_mbox.c create mode 120000 drivers/scsi/spfc/sphw_mgmt.c create mode 120000 drivers/scsi/spfc/sphw_prof_adap.c create mode 120000 drivers/scsi/spfc/sphw_wq.c diff --git a/drivers/net/ethernet/ramaxel/spnic/Makefile b/drivers/net/ethernet/ramaxel/spnic/Makefile index f86ccff374f6..207e1d9c431a 100644 --- a/drivers/net/ethernet/ramaxel/spnic/Makefile +++ b/drivers/net/ethernet/ramaxel/spnic/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_SPNIC) += spnic.o -subdir-ccflags-y += -I$(src)/hw +subdir-ccflags-y += -I$(srctree)/$(src)/hw spnic-objs := hw/sphw_common.o \ hw/sphw_hwif.o \ diff --git a/drivers/scsi/spfc/Makefile b/drivers/scsi/spfc/Makefile index 02fe0213e048..849b730ac733 100644 --- a/drivers/scsi/spfc/Makefile +++ b/drivers/scsi/spfc/Makefile @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_SPFC) += spfc.o -subdir-ccflags-y += -I$(src)/../../net/ethernet/ramaxel/spnic/hw -subdir-ccflags-y += -I$(src)/hw -subdir-ccflags-y += -I$(src)/common +subdir-ccflags-y += -I$(srctree)/$(src)/../../net/ethernet/ramaxel/spnic/hw +subdir-ccflags-y += -I$(srctree)/$(src)/hw +subdir-ccflags-y += -I$(srctree)/$(src)/common spfc-objs := common/unf_init.o \ common/unf_event.o \ @@ -33,15 +33,15 @@ spfc-objs := common/unf_init.o \ hw/spfc_cqm_bitmap_table.o \ hw/spfc_cqm_main.o \ hw/spfc_cqm_object.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hwdev.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_common.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hwif.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_wq.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_eqs.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_mbox.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.o + sphw_hwdev.o \ + sphw_hw_cfg.o \ + sphw_hw_comm.o \ + sphw_prof_adap.o \ + sphw_common.o \ + sphw_hwif.o \ + sphw_wq.o \ + sphw_cmdq.o \ + sphw_eqs.o \ + sphw_mbox.o \ + sphw_mgmt.o \ + sphw_api_cmd.o diff --git a/drivers/scsi/spfc/sphw_api_cmd.c b/drivers/scsi/spfc/sphw_api_cmd.c new file mode 120000 index 000000000000..27c7c0770fa3 --- /dev/null +++ b/drivers/scsi/spfc/sphw_api_cmd.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_cmdq.c b/drivers/scsi/spfc/sphw_cmdq.c new file mode 120000 index 000000000000..5ac779ba274b --- /dev/null +++ b/drivers/scsi/spfc/sphw_cmdq.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_common.c b/drivers/scsi/spfc/sphw_common.c new file mode 120000 index 000000000000..a1a30a4840e1 --- /dev/null +++ b/drivers/scsi/spfc/sphw_common.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_common.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_eqs.c b/drivers/scsi/spfc/sphw_eqs.c new file mode 120000 index 000000000000..74430dcb9dc5 --- /dev/null +++ b/drivers/scsi/spfc/sphw_eqs.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_eqs.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hw_cfg.c b/drivers/scsi/spfc/sphw_hw_cfg.c new file mode 120000 index 000000000000..4f43d68624c1 --- /dev/null +++ b/drivers/scsi/spfc/sphw_hw_cfg.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hw_comm.c b/drivers/scsi/spfc/sphw_hw_comm.c new file mode 120000 index 000000000000..c943b3b2933a --- /dev/null +++ b/drivers/scsi/spfc/sphw_hw_comm.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hwdev.c b/drivers/scsi/spfc/sphw_hwdev.c new file mode 120000 index 000000000000..b7279f17eaa2 --- /dev/null +++ b/drivers/scsi/spfc/sphw_hwdev.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hwdev.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hwif.c b/drivers/scsi/spfc/sphw_hwif.c new file mode 120000 index 000000000000..d40ef71f9033 --- /dev/null +++ b/drivers/scsi/spfc/sphw_hwif.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hwif.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_mbox.c b/drivers/scsi/spfc/sphw_mbox.c new file mode 120000 index 000000000000..1b00fe7289cc --- /dev/null +++ b/drivers/scsi/spfc/sphw_mbox.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_mbox.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_mgmt.c b/drivers/scsi/spfc/sphw_mgmt.c new file mode 120000 index 000000000000..fd18a73e9d3a --- /dev/null +++ b/drivers/scsi/spfc/sphw_mgmt.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_prof_adap.c b/drivers/scsi/spfc/sphw_prof_adap.c new file mode 120000 index 000000000000..fbc7db05dd27 --- /dev/null +++ b/drivers/scsi/spfc/sphw_prof_adap.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_wq.c b/drivers/scsi/spfc/sphw_wq.c new file mode 120000 index 000000000000..cdfcb3a610c0 --- /dev/null +++ b/drivers/scsi/spfc/sphw_wq.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_wq.c \ No newline at end of file -- 2.20.1

1 0

[PATCH OLK-5.10] SCSI:SPFC, NET:Ethernet:SPNIC: fix compile error
by Yanling Song 09 Nov '21

09 Nov '21

Ramaxel inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4DBD7 CVE: NA Fix two compile errors: 1. Compile failed when O=xxx is specified; 2. Compile confliction when spfc and spnic are compiled in parallel by -j option because they share some .c files Signed-off-by: Yanling Song <songyl(a)ramaxel.com> --- drivers/net/ethernet/ramaxel/spnic/Makefile | 2 +- drivers/scsi/spfc/Makefile | 30 ++++++++++----------- drivers/scsi/spfc/sphw_api_cmd.c | 1 + drivers/scsi/spfc/sphw_cmdq.c | 1 + drivers/scsi/spfc/sphw_common.c | 1 + drivers/scsi/spfc/sphw_eqs.c | 1 + drivers/scsi/spfc/sphw_hw_cfg.c | 1 + drivers/scsi/spfc/sphw_hw_comm.c | 1 + drivers/scsi/spfc/sphw_hwdev.c | 1 + drivers/scsi/spfc/sphw_hwif.c | 1 + drivers/scsi/spfc/sphw_mbox.c | 1 + drivers/scsi/spfc/sphw_mgmt.c | 1 + drivers/scsi/spfc/sphw_prof_adap.c | 1 + drivers/scsi/spfc/sphw_wq.c | 1 + 14 files changed, 28 insertions(+), 16 deletions(-) create mode 120000 drivers/scsi/spfc/sphw_api_cmd.c create mode 120000 drivers/scsi/spfc/sphw_cmdq.c create mode 120000 drivers/scsi/spfc/sphw_common.c create mode 120000 drivers/scsi/spfc/sphw_eqs.c create mode 120000 drivers/scsi/spfc/sphw_hw_cfg.c create mode 120000 drivers/scsi/spfc/sphw_hw_comm.c create mode 120000 drivers/scsi/spfc/sphw_hwdev.c create mode 120000 drivers/scsi/spfc/sphw_hwif.c create mode 120000 drivers/scsi/spfc/sphw_mbox.c create mode 120000 drivers/scsi/spfc/sphw_mgmt.c create mode 120000 drivers/scsi/spfc/sphw_prof_adap.c create mode 120000 drivers/scsi/spfc/sphw_wq.c diff --git a/drivers/net/ethernet/ramaxel/spnic/Makefile b/drivers/net/ethernet/ramaxel/spnic/Makefile index f86ccff374f6..207e1d9c431a 100644 --- a/drivers/net/ethernet/ramaxel/spnic/Makefile +++ b/drivers/net/ethernet/ramaxel/spnic/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_SPNIC) += spnic.o -subdir-ccflags-y += -I$(src)/hw +subdir-ccflags-y += -I$(srctree)/$(src)/hw spnic-objs := hw/sphw_common.o \ hw/sphw_hwif.o \ diff --git a/drivers/scsi/spfc/Makefile b/drivers/scsi/spfc/Makefile index 02fe0213e048..849b730ac733 100644 --- a/drivers/scsi/spfc/Makefile +++ b/drivers/scsi/spfc/Makefile @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_SPFC) += spfc.o -subdir-ccflags-y += -I$(src)/../../net/ethernet/ramaxel/spnic/hw -subdir-ccflags-y += -I$(src)/hw -subdir-ccflags-y += -I$(src)/common +subdir-ccflags-y += -I$(srctree)/$(src)/../../net/ethernet/ramaxel/spnic/hw +subdir-ccflags-y += -I$(srctree)/$(src)/hw +subdir-ccflags-y += -I$(srctree)/$(src)/common spfc-objs := common/unf_init.o \ common/unf_event.o \ @@ -33,15 +33,15 @@ spfc-objs := common/unf_init.o \ hw/spfc_cqm_bitmap_table.o \ hw/spfc_cqm_main.o \ hw/spfc_cqm_object.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hwdev.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_common.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hwif.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_wq.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_eqs.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_mbox.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.o + sphw_hwdev.o \ + sphw_hw_cfg.o \ + sphw_hw_comm.o \ + sphw_prof_adap.o \ + sphw_common.o \ + sphw_hwif.o \ + sphw_wq.o \ + sphw_cmdq.o \ + sphw_eqs.o \ + sphw_mbox.o \ + sphw_mgmt.o \ + sphw_api_cmd.o diff --git a/drivers/scsi/spfc/sphw_api_cmd.c b/drivers/scsi/spfc/sphw_api_cmd.c new file mode 120000 index 000000000000..27c7c0770fa3 --- /dev/null +++ b/drivers/scsi/spfc/sphw_api_cmd.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_cmdq.c b/drivers/scsi/spfc/sphw_cmdq.c new file mode 120000 index 000000000000..5ac779ba274b --- /dev/null +++ b/drivers/scsi/spfc/sphw_cmdq.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_common.c b/drivers/scsi/spfc/sphw_common.c new file mode 120000 index 000000000000..a1a30a4840e1 --- /dev/null +++ b/drivers/scsi/spfc/sphw_common.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_common.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_eqs.c b/drivers/scsi/spfc/sphw_eqs.c new file mode 120000 index 000000000000..74430dcb9dc5 --- /dev/null +++ b/drivers/scsi/spfc/sphw_eqs.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_eqs.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hw_cfg.c b/drivers/scsi/spfc/sphw_hw_cfg.c new file mode 120000 index 000000000000..4f43d68624c1 --- /dev/null +++ b/drivers/scsi/spfc/sphw_hw_cfg.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hw_comm.c b/drivers/scsi/spfc/sphw_hw_comm.c new file mode 120000 index 000000000000..c943b3b2933a --- /dev/null +++ b/drivers/scsi/spfc/sphw_hw_comm.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hwdev.c b/drivers/scsi/spfc/sphw_hwdev.c new file mode 120000 index 000000000000..b7279f17eaa2 --- /dev/null +++ b/drivers/scsi/spfc/sphw_hwdev.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hwdev.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hwif.c b/drivers/scsi/spfc/sphw_hwif.c new file mode 120000 index 000000000000..d40ef71f9033 --- /dev/null +++ b/drivers/scsi/spfc/sphw_hwif.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hwif.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_mbox.c b/drivers/scsi/spfc/sphw_mbox.c new file mode 120000 index 000000000000..1b00fe7289cc --- /dev/null +++ b/drivers/scsi/spfc/sphw_mbox.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_mbox.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_mgmt.c b/drivers/scsi/spfc/sphw_mgmt.c new file mode 120000 index 000000000000..fd18a73e9d3a --- /dev/null +++ b/drivers/scsi/spfc/sphw_mgmt.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_prof_adap.c b/drivers/scsi/spfc/sphw_prof_adap.c new file mode 120000 index 000000000000..fbc7db05dd27 --- /dev/null +++ b/drivers/scsi/spfc/sphw_prof_adap.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_wq.c b/drivers/scsi/spfc/sphw_wq.c new file mode 120000 index 000000000000..cdfcb3a610c0 --- /dev/null +++ b/drivers/scsi/spfc/sphw_wq.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_wq.c \ No newline at end of file -- 2.27.0

2 1

【议题申报】主线特性DAMON（Data Access Monitor）回合
by zouyue (A) 09 Nov '21

09 Nov '21

DAMON(Data Access Monitor)特性议题申报 DAMON特性是一个能轻量级在线监控特定用户空间进程的内存访问情况的内核特性模块。通过基于region采样和自适应调整region大小两种核心机制，允许用户态和内核态两种策略定义模式，进行data access访问监控和内存优化管理。应用场景： 1．监控当前内存过负载或者过高的访问频率 2．内存管理优化： 1) 高访问频率的内存区域放到LRU列表头部 2) 低访问频率的内存区域调整到LRU列表尾部或者换出 3) 大内存消耗且高访问频率的区域可以使用较大页 3．监控一些低效率的进程间通信 DAMON总体框架如下： [cid:image003.png@01D7D54E.EA5ABEE0] 特性补丁链接: http://patchwork.huawei.com/project/olk5.10/list/?series=20179

1 0

[PATCH openEuler-1.0-LTS 1/7] ath: Use safer key clearing with key cache entries
by Yang Yingliang 08 Nov '21

08 Nov '21

From: Jouni Malinen <jouni(a)codeaurora.org> stable inclusion from linux-4.19.205 commit dd5815f023b89c9a28325d8a2a5f0779b57b7190 CVE: CVE-2020-3702 -------------------------------- commit 56c5485c9e444c2e85e11694b6c44f1338fc20fd upstream. It is possible for there to be pending frames in TXQs with a reference to the key cache entry that is being deleted. If such a key cache entry is cleared, those pending frame in TXQ might get transmitted without proper encryption. It is safer to leave the previously used key into the key cache in such cases. Instead, only clear the MAC address to prevent RX processing from using this key cache entry. This is needed in particularly in AP mode where the TXQs cannot be flushed on station disconnection. This change alone may not be able to address all cases where the key cache entry might get reused for other purposes immediately (the key cache entry should be released for reuse only once the TXQs do not have any remaining references to them), but this makes it less likely to get unprotected frames and the more complete changes may end up being significantly more complex. Signed-off-by: Jouni Malinen <jouni(a)codeaurora.org> Signed-off-by: Kalle Valo <kvalo(a)codeaurora.org> Link: https://lore.kernel.org/r/20201214172118.18100-2-jouni@codeaurora.org Cc: Pali Rohár <pali(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/wireless/ath/key.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/key.c b/drivers/net/wireless/ath/key.c index 1816b4e7dc264..59618bb41f6c5 100644 --- a/drivers/net/wireless/ath/key.c +++ b/drivers/net/wireless/ath/key.c @@ -583,7 +583,16 @@ EXPORT_SYMBOL(ath_key_config); */ void ath_key_delete(struct ath_common *common, struct ieee80211_key_conf *key) { - ath_hw_keyreset(common, key->hw_key_idx); + /* Leave CCMP and TKIP (main key) configured to avoid disabling + * encryption for potentially pending frames already in a TXQ with the + * keyix pointing to this key entry. Instead, only clear the MAC address + * to prevent RX processing from using this key cache entry. + */ + if (test_bit(key->hw_key_idx, common->ccmp_keymap) || + test_bit(key->hw_key_idx, common->tkip_keymap)) + ath_hw_keysetmac(common, key->hw_key_idx, NULL); + else + ath_hw_keyreset(common, key->hw_key_idx); if (key->hw_key_idx < IEEE80211_WEP_NKID) return; -- 2.25.1

1 6

[PATCH kernel-4.19] vfs: move cap_convert_nscap() call into vfs_setxattr()
by zhangyue 08 Nov '21

08 Nov '21

mainline inclusion category: feature bugzilla:https://gitee.com/openeuler/kernel/issues/I4GVH3?from=project-issue CVE: NA cap_convert_nscap() does permission checking as well as conversion of the xattr value conditionally based on fs's user-ns. This is needed by overlayfs and probably other layered fs (ecryptfs) and is what vfs_foo() is supposed to do anyway. Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Acked-by: James Morris <jamorris(a)linux.microsoft.com> Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- fs/xattr.c | 18 ++++++++++++------ include/linux/capability.h | 2 +- security/commoncap.c | 3 +-- 3 files changed, 14 insertions(+), 9 deletions(-) diff --git a/fs/xattr.c b/fs/xattr.c index adb11cb82be5..653e12d6060f 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -263,8 +263,16 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value, { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; + const void *orig_value = value; int error; + if (size && strcmp(name, XATTR_NAME_CAPS) == 0) { + error = cap_convert_nscap(dentry, &value, size); + if (error < 0) + return error; + size = error; + } + retry_deleg: inode_lock(inode); error = __vfs_setxattr_locked(dentry, name, value, size, flags, @@ -276,6 +284,10 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value, if (!error) goto retry_deleg; } + + if (value != orig_value) + kfree(value); + return error; } EXPORT_SYMBOL_GPL(vfs_setxattr); @@ -530,12 +542,6 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) posix_acl_fix_xattr_from_user(kvalue, size); - else if (strcmp(kname, XATTR_NAME_CAPS) == 0) { - error = cap_convert_nscap(d, &kvalue, size); - if (error < 0) - goto out; - size = error; - } } error = vfs_setxattr(d, kname, kvalue, size, flags); diff --git a/include/linux/capability.h b/include/linux/capability.h index f640dcbc880c..9fee9a86505c 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -249,6 +249,6 @@ extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -extern int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size); +extern int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size); #endif /* !_LINUX_CAPABILITY_H */ diff --git a/security/commoncap.c b/security/commoncap.c index 876cfe01d939..83546a782796 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -498,7 +498,7 @@ static bool validheader(size_t size, const struct vfs_cap_data *cap) * * If all is ok, we return the new size, on error return < 0. */ -int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size) +int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; @@ -541,7 +541,6 @@ int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size) nscap->magic_etc = cpu_to_le32(nsmagic); memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); - kvfree(*ivalue); *ivalue = nscap; return newsize; } -- 2.30.0

1 0

[PATCH openEuler-1.0-LTS] ext4: if zeroout fails fall back to splitting the extent node
by Yang Yingliang 08 Nov '21

08 Nov '21

From: Theodore Ts'o <tytso(a)mit.edu> mainline inclusion from mainline-5.15-rc1 commit 308c57ccf4318236be75dfa251c84713e694457b category: bugfix bugzilla: 109297 CVE: NA --------------------------- If the underlying storage device is using thin-provisioning, it's possible for a zeroout operation to return ENOSPC. Commit df22291ff0fd ("ext4: Retry block allocation if we have free blocks left") added logic to retry block allocation since we might get free block after we commit a transaction. But the ENOSPC from thin-provisioning will confuse ext4, and lead to an infinite loop. Since using zeroout instead of splitting the extent node is an optimization, if it fails, we might as well fall back to splitting the extent node. Reported-by: yangerkun <yangerkun(a)huawei.com> Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/extents.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index fc00a78163117..10298c13a67d7 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3696,7 +3696,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, split_map.m_len - ee_block); err = ext4_ext_zeroout(inode, &zero_ex1); if (err) - goto out; + goto fallback; split_map.m_len = allocated; } if (split_map.m_lblk - ee_block + split_map.m_len < @@ -3710,7 +3710,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, ext4_ext_pblock(ex)); err = ext4_ext_zeroout(inode, &zero_ex2); if (err) - goto out; + goto fallback; } split_map.m_len += split_map.m_lblk - ee_block; @@ -3719,6 +3719,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, } } +fallback: err = ext4_split_extent(handle, inode, ppath, &split_map, split_flag, flags); if (err > 0) -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] dccp: don't duplicate ccid when cloning dccp sock
by Yang Yingliang 08 Nov '21

08 Nov '21

From: "Lin, Zhenpeng" <zplin(a)psu.edu> mainline inclusion from mainline-v5.15-rc2 commit d9ea761fdd197351890418acd462c51f241014a7 category: bugfix bugzilla: 85666 CVE: CVE-2020-16119 ------------------------------------------------- Commit 2677d2067731 ("dccp: don't free ccid2_hc_tx_sock ...") fixed a UAF but reintroduced CVE-2017-6074. When the sock is cloned, two dccps_hc_tx_ccid will reference to the same ccid. So one can free the ccid object twice from two socks after cloning. This issue was found by "Hadar Manor" as well and assigned with CVE-2020-16119, which was fixed in Ubuntu's kernel. So here I port the patch from Ubuntu to fix it. The patch prevents cloned socks from referencing the same ccid. Fixes: 2677d2067731410 ("dccp: don't free ccid2_hc_tx_sock ...") Signed-off-by: Zhenpeng Lin <zplin(a)psu.edu> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/dccp/minisocks.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index ba6fc3c1186b9..e91838a7b8497 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -98,6 +98,8 @@ struct sock *dccp_create_openreq_child(const struct sock *sk, newdp->dccps_role = DCCP_ROLE_SERVER; newdp->dccps_hc_rx_ackvec = NULL; newdp->dccps_service_list = NULL; + newdp->dccps_hc_rx_ccid = NULL; + newdp->dccps_hc_tx_ccid = NULL; newdp->dccps_service = dreq->dreq_service; newdp->dccps_timestamp_echo = dreq->dreq_timestamp_echo; newdp->dccps_timestamp_time = dreq->dreq_timestamp_time; -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 01/14] Revert "selftests/bpf: add test_spec_readahead_xfs_file to support specail async readahead"
by Yang Yingliang 05 Nov '21

05 Nov '21

From: Hou Tao <houtao1(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4H3JT CVE: NA --------------------------- There are two issues with the current solution: 1) tracepoint xfs_read_file is visible in tracefs It forms an ABI for userspace. It is bad because new field may be added into xfs_writable_file to export more information to userspace. 2) tracepoint xfs_read_file is specific to xfs HDFS can be stacked on ext4. A new solution is proposed which uses vfs bare tracepoint, so reverts commit 69513cfbe62d267c4a5e6025f31741b1f2cb946c. Signed-off-by: Hou Tao <houtao1(a)huawei.com> Reviewed-by: Kuohai Xu <xukuohai(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- tools/include/uapi/linux/xfs.h | 1 - tools/testing/selftests/bpf/Makefile | 3 +- .../bpf/test_spec_readahead_xfs_file.c | 39 ------------------- tools/testing/selftests/bpf/test_xfs_file.c | 9 +---- 4 files changed, 3 insertions(+), 49 deletions(-) delete mode 100644 tools/testing/selftests/bpf/test_spec_readahead_xfs_file.c diff --git a/tools/include/uapi/linux/xfs.h b/tools/include/uapi/linux/xfs.h index 1409b45affd34..a0d37e411ee18 100644 --- a/tools/include/uapi/linux/xfs.h +++ b/tools/include/uapi/linux/xfs.h @@ -6,7 +6,6 @@ #define FMODE_RANDOM (0x1000) #define FMODE_WILLNEED (0x400000) -#define FMODE_SPC_READAHEAD (0x800000) struct xfs_writable_file { const unsigned char *name; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 46b1d5b864f5a..8d2737285f185 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -36,8 +36,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \ test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \ get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \ - test_skb_cgroup_id_kern.o test_set_xfs_file.o test_clear_xfs_file.o \ - test_spec_readahead_xfs_file.o + test_skb_cgroup_id_kern.o test_set_xfs_file.o test_clear_xfs_file.o # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ diff --git a/tools/testing/selftests/bpf/test_spec_readahead_xfs_file.c b/tools/testing/selftests/bpf/test_spec_readahead_xfs_file.c deleted file mode 100644 index ff8794a14cdcd..0000000000000 --- a/tools/testing/selftests/bpf/test_spec_readahead_xfs_file.c +++ /dev/null @@ -1,39 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <linux/bpf.h> -#include "bpf_helpers.h" -#include <string.h> -#include <linux/xfs.h> - -/* from /sys/kernel/debug/tracing/events/xfs/xfs_read_file */ -struct xfs_read_buffer_args { - struct xfs_writable_file *file; -}; - -SEC("tracepoint/xfs/xfs_file_read") -int bpf_prog1(struct xfs_read_buffer_args *ctx) -{ - char fmt[] = "name: %s, set f_mode: %u\n"; - struct xfs_writable_file *file = ctx->file; - char name[64] = {}; - char *tmp; - unsigned long i_size; - int len; - - bpf_probe_read(&tmp, 8, &(file->name)); - len = bpf_probe_read_str(name, 64, tmp); - bpf_probe_read(&i_size, 8, &(file->i_size)); - - if (!strncmp("blk_", name, 4)) { - /* blk_xxx.meta or blk_xxx with size < 2M */ - if (len == 27 || (len == 15 && i_size <= 2 * 1024 * 1024)) - file->f_mode |= FMODE_WILLNEED; - else if (len == 15) /* blk_xxx */ - file->f_mode |= FMODE_SPC_READAHEAD; - bpf_trace_printk(fmt, sizeof(fmt), name, file->f_mode); - } - return 0; -} - -char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/test_xfs_file.c b/tools/testing/selftests/bpf/test_xfs_file.c index 89e79d959677c..247c42be029b2 100644 --- a/tools/testing/selftests/bpf/test_xfs_file.c +++ b/tools/testing/selftests/bpf/test_xfs_file.c @@ -20,7 +20,6 @@ int main(int argc, char *argv[]) { const char *set_file = "./test_set_xfs_file.o"; const char *clear_file = "./test_clear_xfs_file.o"; - const char *spec_readahead_file = "./test_spec_readahead_xfs_file.o"; const char *file = set_file; struct bpf_object *obj; int efd, err, prog_fd; @@ -32,12 +31,8 @@ int main(int argc, char *argv[]) delay = strtol(str, &endptr, 10); } - if (argc >= 2) { - if (!strcmp("clear", argv[1])) - file = clear_file; - if (!strcmp("spec_readahead", argv[1])) - file = spec_readahead_file; - } + if (argc >= 2 && !strcmp("clear", argv[1])) + file = clear_file; err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, &obj, &prog_fd); -- 2.25.1

1 13

[PATCH OLK-5.10 v3] Net:NIC:SPNIC:Fix compile error when O= is specififed
by Yanling Song 05 Nov '21

05 Nov '21

Ramaxel inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CBDP CVE: NA Net:NIC:SPNIC:Fix compile error when O= is specififed Signed-off-by: Yanling Song <songyl(a)ramaxel.com> --- Changes from V2: Move the location of "Changes from" Changes from V1: 1. Change category from feature to bugfix; 2. Add description --- drivers/net/ethernet/ramaxel/spnic/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ramaxel/spnic/Makefile b/drivers/net/ethernet/ramaxel/spnic/Makefile index f86ccff374f6..207e1d9c431a 100644 --- a/drivers/net/ethernet/ramaxel/spnic/Makefile +++ b/drivers/net/ethernet/ramaxel/spnic/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_SPNIC) += spnic.o -subdir-ccflags-y += -I$(src)/hw +subdir-ccflags-y += -I$(srctree)/$(src)/hw spnic-objs := hw/sphw_common.o \ hw/sphw_hwif.o \ -- 2.27.0

1 0

[PATCH openEuler-1.0-LTS] EMMC: fix ascend hisi emmc probe failed problem according to mmc_host struct
by Yang Yingliang 04 Nov '21

04 Nov '21

From: zhangguijiang <zhangguijiang(a)huawei.com> ascend inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4GVSG CVE: NA ------------------- Struct mmc_host using variable private[0] to point the end of struct mmc_host, at deaf01a6 we modified struct mmc_host but ignored the role of private[0] and not put it to the end of struct mmc_host. It will make mmc card probe failed, so we fix this problem, and now ascend hisi mmc card is able to probe success. Signed-off-by: zhangguijiang <zhangguijiang(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/mmc/core/sd.c | 38 +++----------------------------- drivers/mmc/host/dw_mmc_extern.h | 2 +- include/linux/mmc/host.h | 2 +- 3 files changed, 5 insertions(+), 37 deletions(-) diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index 20ca371b9f874..8760b749292b8 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -1163,9 +1163,9 @@ static int _mmc_sd_suspend(struct mmc_host *host) err = mmc_deselect_cards(host); if (!err) { - if (!(mmc_is_ascend_customized(host->parent))) + if (!mmc_is_ascend_customized(host->parent)) mmc_power_off(host); - else if (mmc_card_keep_power(host)) + else if (!mmc_card_keep_power(host)) mmc_power_off(host); mmc_card_set_suspended(host->card); } @@ -1269,42 +1269,10 @@ static int mmc_sd_runtime_resume(struct mmc_host *host) return 0; } -#ifdef CONFIG_ASCEND_HISI_MMC -/*********************sd ops begin**********************/ -static int mmc_do_sd_reset(struct mmc_host *host) -{ - struct mmc_card *card = host->card; - - if (!host->bus_ops->power_restore) - return -EOPNOTSUPP; - - if (!card) - return -EINVAL; - - /* hw_reset for ip reset */ - if (host->ops->hw_reset) - host->ops->hw_reset(host); - - /* Only for K930/920 SD slow down clk*/ - if (host->ops->slowdown_clk) - host->ops->slowdown_clk(host, host->ios.timing); - - mmc_power_off(host); - mmc_set_clock(host, host->f_init); - /* Wait at least 200 ms */ - mmc_delay(200); - mmc_power_up(host, host->card->ocr); - (void)mmc_select_voltage(host, host->card->ocr); - - return host->bus_ops->power_restore(host); -} -#endif static int mmc_sd_hw_reset(struct mmc_host *host) { -#ifdef CONFIG_ASCEND_HISI_MMC if (mmc_is_ascend_customized(host->parent)) - return mmc_do_sd_reset(host); -#endif + return mmc_sd_reset(host); mmc_power_cycle(host, host->card->ocr); return mmc_sd_init_card(host, host->card->ocr, host->card); } diff --git a/drivers/mmc/host/dw_mmc_extern.h b/drivers/mmc/host/dw_mmc_extern.h index 04d8c23f39e9a..ab077b4955940 100644 --- a/drivers/mmc/host/dw_mmc_extern.h +++ b/drivers/mmc/host/dw_mmc_extern.h @@ -8,7 +8,7 @@ #include "dw_mmc.h" -#ifdef CONFIG_MMC_DW_HI3XXX_MODULE +#if defined(CONFIG_MMC_DW_HI3XXX) || defined(CONFIG_MMC_DW_HI3XXX_MODULE) extern void dw_mci_reg_dump(struct dw_mci *host); extern void dw_mci_set_timeout(struct dw_mci *host); extern bool dw_mci_stop_abort_cmd(struct mmc_command *cmd); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 78b4d0a813b71..fabc23d156242 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -542,13 +542,13 @@ struct mmc_host { bool cqe_enabled; bool cqe_on; - unsigned long private[0] ____cacheline_aligned; #ifdef CONFIG_ASCEND_HISI_MMC const struct mmc_cmdq_host_ops *cmdq_ops; int sdio_present; unsigned int cmdq_slots; struct mmc_cmdq_context_info cmdq_ctx; #endif + unsigned long private[0] ____cacheline_aligned; }; struct device_node; -- 2.25.1

1 0

[PATCH OLK-5.10 v2] Net:NIC:SPNIC:Fix compile error when O= is specififed
by Yanling Song 04 Nov '21

04 Nov '21

Ramaxel inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CBDP CVE: NA Change from V1: 1. Change category from feature to bugfix; 2. Add description Net:NIC:SPNIC:Fix compile error when O= is specififed Signed-off-by: Yanling Song <songyl(a)ramaxel.com> --- drivers/net/ethernet/ramaxel/spnic/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ramaxel/spnic/Makefile b/drivers/net/ethernet/ramaxel/spnic/Makefile index f86ccff374f6..207e1d9c431a 100644 --- a/drivers/net/ethernet/ramaxel/spnic/Makefile +++ b/drivers/net/ethernet/ramaxel/spnic/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_SPNIC) += spnic.o -subdir-ccflags-y += -I$(src)/hw +subdir-ccflags-y += -I$(srctree)/$(src)/hw spnic-objs := hw/sphw_common.o \ hw/sphw_hwif.o \ -- 2.27.0

2 1

[PATCH openEuler-1.0-LTS] Bluetooth: cmtp: fix file refcount when cmtp_attach_device fails
by Yang Yingliang 04 Nov '21

04 Nov '21

From: Thadeu Lima de Souza Cascardo <cascardo(a)canonical.com> mainline inclusion from mainline-v5.14-rc1 commit 3cfdf8fcaafa62a4123f92eb0f4a72650da3a479 category: bugfix bugzilla: NA CVE: CVE-2021-34981 ------------------------------------------------- When cmtp_attach_device fails, cmtp_add_connection returns the error value which leads to the caller to doing fput through sockfd_put. But cmtp_session kthread, which is stopped in this path will also call fput, leading to a potential refcount underflow or a use-after-free. Add a refcount before we signal the kthread to stop. The kthread will try to grab the cmtp_session_sem mutex before doing the fput, which is held when get_file is called, so there should be no races there. Reported-by: Ryota Shiga Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo(a)canonical.com> Signed-off-by: Marcel Holtmann <marcel(a)holtmann.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: weiyang wang <wangweiyang2(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/bluetooth/cmtp/core.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 7f26a5a19ff6d..9873684a9d8ff 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -391,6 +391,11 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) if (!(session->flags & BIT(CMTP_LOOPBACK))) { err = cmtp_attach_device(session); if (err < 0) { + /* Caller will call fput in case of failure, and so + * will cmtp_session kthread. + */ + get_file(session->sock->file); + atomic_inc(&session->terminate); wake_up_interruptible(sk_sleep(session->sock->sk)); up_write(&cmtp_session_sem); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] scsi: hisi_sas: print status and error when sata io abnormally completed
by Yang Yingliang 04 Nov '21

04 Nov '21

From: Xingui Yang <yangxingui(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA --------------------- To help debugging efforts, print d2h status and error D2H: FIS Status Bits = 0x53 BSY = 0... .... Off DRDY = .1.. .... On DF = ..0. .... Off DSC = ...1 .... On DRQ = .... 0... Off Alignment Error = .... .0.. Off Sense Data Available = .... ..1. On ERR = .... ...1 On FIS Error Bits = 0x40 ICRC = 0... .... Off UNC = .1.. .... On MC (O) = ..0. .... Off IDNF = ...0 .... Off MCR (O) = .... 0... Off ABRT = .... .0.. Off EOM = .... ..0. Off CCTO = .... ...0 Off Here is an example print: hisi_sas_v3_hw 0000:74:02.0: sata d2h status 0x53, error 0x40 Signed-off-by: Xingui Yang <yangxingui(a)huawei.com> Reviewed by kangfenglong <kangfenglong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index babf6486af526..4508c4a2f02fc 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2419,6 +2419,19 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) error_info[0], error_info[1], error_info[2], error_info[3]); + if ((complete_hdr->dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) && + (task->task_proto & SAS_PROTOCOL_SATA || + task->task_proto & SAS_PROTOCOL_STP)) { + struct hisi_sas_status_buffer *status_buf = + hisi_sas_status_buf_addr_mem(slot); + u8 *iu = &status_buf->iu[0]; + struct dev_to_host_fis *d2h = + (struct dev_to_host_fis *)iu; + + dev_info(dev, "sata d2h status 0x%02x, error 0x%02x\n", + d2h->status, d2h->error); + } + if ((error_info[3] & RX_DATA_LEN_UNDERFLOW_MSK) && (task->task_proto == SAS_PROTOCOL_SSP)) { /*print detail sense info when data underflow happened*/ -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/2] Revert "scsi: hisi_sas: replace spin_lock_irqsave/spin_unlock_restore with spin_lock/spin_unlock"
by Yang Yingliang 04 Nov '21

04 Nov '21

From: Xingui Yang <yangxingui(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA --------------------- This reverts commit 5c725a983c0dedd067e5e643633db6fb5ecbeb91. this optimization patch depends on the kernel block MQ patch. If the block MQ patch is not integrated, there is a possibility that the spinlock deadlock occurs. Signed-off-by: Xingui Yang <yangxingui(a)huawei.com> Reviewed-by: Kangfenglong <kangfenglong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas_main.c | 50 ++++++++++++++------------ drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 12 ++++--- 2 files changed, 35 insertions(+), 27 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index bde4307596234..39fe67239f929 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -172,11 +172,13 @@ static void hisi_sas_slot_index_clear(struct hisi_hba *hisi_hba, int slot_idx) static void hisi_sas_slot_index_free(struct hisi_hba *hisi_hba, int slot_idx) { + unsigned long flags; + if (hisi_hba->hw->slot_index_alloc || (slot_idx >= hisi_hba->hw->max_command_entries - HISI_SAS_RESERVED_IPTT_CNT)) { - spin_lock(&hisi_hba->lock); + spin_lock_irqsave(&hisi_hba->lock, flags); hisi_sas_slot_index_clear(hisi_hba, slot_idx); - spin_unlock(&hisi_hba->lock); + spin_unlock_irqrestore(&hisi_hba->lock, flags); } } @@ -192,12 +194,13 @@ static int hisi_sas_slot_index_alloc(struct hisi_hba *hisi_hba, { int index; void *bitmap = hisi_hba->slot_index_tags; + unsigned long flags; if (scsi_cmnd) { return scsi_cmnd->request->tag; } - spin_lock(&hisi_hba->lock); + spin_lock_irqsave(&hisi_hba->lock, flags); index = find_next_zero_bit(bitmap, hisi_hba->slot_index_count, hisi_hba->last_slot_index + 1); if (index >= hisi_hba->slot_index_count) { @@ -206,13 +209,13 @@ static int hisi_sas_slot_index_alloc(struct hisi_hba *hisi_hba, hisi_hba->hw->max_command_entries - HISI_SAS_RESERVED_IPTT_CNT); if (index >= hisi_hba->slot_index_count) { - spin_unlock(&hisi_hba->lock); + spin_unlock_irqrestore(&hisi_hba->lock, flags); return -SAS_QUEUE_FULL; } } hisi_sas_slot_index_set(hisi_hba, index); hisi_hba->last_slot_index = index; - spin_unlock(&hisi_hba->lock); + spin_unlock_irqrestore(&hisi_hba->lock, flags); return index; } @@ -228,6 +231,7 @@ static void hisi_sas_slot_index_init(struct hisi_hba *hisi_hba) void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task, struct hisi_sas_slot *slot) { + unsigned long flags; int device_id = slot->device_id; struct hisi_sas_device *sas_dev = &hisi_hba->devices[device_id]; @@ -256,9 +260,9 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task, } } - spin_lock(&sas_dev->lock); + spin_lock_irqsave(&sas_dev->lock, flags); list_del_init(&slot->entry); - spin_unlock(&sas_dev->lock); + spin_unlock_irqrestore(&sas_dev->lock, flags); memset(slot, 0, offsetof(struct hisi_sas_slot, buf)); @@ -510,14 +514,14 @@ static int hisi_sas_task_prep(struct sas_task *task, slot_idx = rc; slot = &hisi_hba->slot_info[slot_idx]; - spin_lock(&dq->lock); + spin_lock_irqsave(&dq->lock, flags); wr_q_index = dq->wr_point; dq->wr_point = (dq->wr_point + 1) % HISI_SAS_QUEUE_SLOTS; list_add_tail(&slot->delivery, &dq->list); - spin_unlock(&dq->lock); - spin_lock(&sas_dev->lock); + spin_unlock_irqrestore(&dq->lock, flags); + spin_lock_irqsave(&sas_dev->lock, flags); list_add_tail(&slot->entry, &sas_dev->list); - spin_unlock(&sas_dev->lock); + spin_unlock_irqrestore(&sas_dev->lock, flags); dlvry_queue = dq->id; dlvry_queue_slot = wr_q_index; @@ -583,6 +587,7 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags, { u32 rc; u32 pass = 0; + unsigned long flags; struct hisi_hba *hisi_hba; struct device *dev; struct domain_device *device = task->dev; @@ -616,9 +621,9 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags, dev_err(dev, "task exec: failed[%d]!\n", rc); if (likely(pass)) { - spin_lock(&dq->lock); + spin_lock_irqsave(&dq->lock, flags); hisi_hba->hw->start_delivery(dq); - spin_unlock(&dq->lock); + spin_unlock_irqrestore(&dq->lock, flags); } return rc; @@ -669,11 +674,12 @@ static struct hisi_sas_device *hisi_sas_alloc_dev(struct domain_device *device) { struct hisi_hba *hisi_hba = dev_to_hisi_hba(device); struct hisi_sas_device *sas_dev = NULL; + unsigned long flags; int first = (hisi_hba->last_dev_id + 1) % HISI_SAS_MAX_DEVICES; int dev_id; int i; - spin_lock(&hisi_hba->lock); + spin_lock_irqsave(&hisi_hba->lock, flags); for (i = first; i < first + HISI_SAS_MAX_DEVICES; i++) { dev_id = i % HISI_SAS_MAX_DEVICES; if (hisi_hba->devices[dev_id].dev_type == SAS_PHY_UNUSED) { @@ -694,7 +700,7 @@ static struct hisi_sas_device *hisi_sas_alloc_dev(struct domain_device *device) } if (sas_dev) hisi_hba->last_dev_id = i; - spin_unlock(&hisi_hba->lock); + spin_unlock_irqrestore(&hisi_hba->lock, flags); return sas_dev; } @@ -1964,7 +1970,7 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, struct asd_sas_port *sas_port = device->port; struct hisi_sas_cmd_hdr *cmd_hdr_base; int dlvry_queue_slot, dlvry_queue, n_elem = 0, rc, slot_idx; - unsigned long flags; + unsigned long flags, flags_dq = 0; int wr_q_index; if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags))) @@ -1983,14 +1989,14 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, slot_idx = rc; slot = &hisi_hba->slot_info[slot_idx]; - spin_lock(&dq->lock); + spin_lock_irqsave(&dq->lock, flags_dq); wr_q_index = dq->wr_point; dq->wr_point = (dq->wr_point + 1) % HISI_SAS_QUEUE_SLOTS; list_add_tail(&slot->delivery, &dq->list); - spin_unlock(&dq->lock); - spin_lock(&sas_dev->lock); + spin_unlock_irqrestore(&dq->lock, flags_dq); + spin_lock_irqsave(&sas_dev->lock, flags); list_add_tail(&slot->entry, &sas_dev->list); - spin_unlock(&sas_dev->lock); + spin_unlock_irqrestore(&sas_dev->lock, flags); dlvry_queue = dq->id; dlvry_queue_slot = wr_q_index; @@ -2019,9 +2025,9 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, spin_unlock_irqrestore(&task->task_state_lock, flags); WRITE_ONCE(slot->ready, 1); /* send abort command to the chip */ - spin_lock(&dq->lock); + spin_lock_irqsave(&dq->lock, flags); hisi_hba->hw->start_delivery(dq); - spin_unlock(&dq->lock); + spin_unlock_irqrestore(&dq->lock, flags); return 0; diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 730191e7f55b8..fa4233454dccb 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -778,6 +778,7 @@ slot_index_alloc_quirk_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_device *sas_dev = device->lldd_dev; int sata_idx = sas_dev->sata_idx; int start, end; + unsigned long flags; if (!sata_dev) { /* @@ -801,12 +802,12 @@ slot_index_alloc_quirk_v2_hw(struct hisi_hba *hisi_hba, end = 64 * (sata_idx + 2); } - spin_lock(&hisi_hba->lock); + spin_lock_irqsave(&hisi_hba->lock, flags); while (1) { start = find_next_zero_bit(bitmap, hisi_hba->slot_index_count, start); if (start >= end) { - spin_unlock(&hisi_hba->lock); + spin_unlock_irqrestore(&hisi_hba->lock, flags); return -SAS_QUEUE_FULL; } /* @@ -818,7 +819,7 @@ slot_index_alloc_quirk_v2_hw(struct hisi_hba *hisi_hba, } set_bit(start, bitmap); - spin_unlock(&hisi_hba->lock); + spin_unlock_irqrestore(&hisi_hba->lock, flags); return start; } @@ -847,8 +848,9 @@ hisi_sas_device *alloc_dev_quirk_v2_hw(struct domain_device *device) struct hisi_sas_device *sas_dev = NULL; int i, sata_dev = dev_is_sata(device); int sata_idx = -1; + unsigned long flags; - spin_lock(&hisi_hba->lock); + spin_lock_irqsave(&hisi_hba->lock, flags); if (sata_dev) if (!sata_index_alloc_v2_hw(hisi_hba, &sata_idx)) @@ -879,7 +881,7 @@ hisi_sas_device *alloc_dev_quirk_v2_hw(struct domain_device *device) } out: - spin_unlock(&hisi_hba->lock); + spin_unlock_irqrestore(&hisi_hba->lock, flags); return sas_dev; } -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 01/18] net: hns3: limit bd numbers when getting dfx regs.
by Yang Yingliang 04 Nov '21

04 Nov '21

From: Yonglong Liu <liuyonglong(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA ---------------------------- When getting dfx regs, the bd numbers from the firmware may be very big which is not expected, and cause the buffer size overflow. This patch limit the max bd numbers to 64 to fix the problem. Signed-off-by: Yonglong Liu <liuyonglong(a)huawei.com> Reviewed-by: li yongxin <liyongxin1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 8507eb60450fe..ac5f502d5e9be 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -11180,6 +11180,8 @@ static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len) static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data) { +#define HCLGE_DFX_BD_NUM_MAX 64 + u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list); int bd_num, bd_num_max, buf_len, i; struct hclge_desc *desc_src; @@ -11202,6 +11204,13 @@ static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data) for (i = 1; i < dfx_reg_type_num; i++) bd_num_max = max_t(int, bd_num_max, bd_num_list[i]); + if (bd_num_max > HCLGE_DFX_BD_NUM_MAX) { + dev_err(&hdev->pdev->dev, + "Get dfx reg fail, invalid bd number: %d\n", + bd_num_max); + goto out; + } + buf_len = sizeof(*desc_src) * bd_num_max; desc_src = kzalloc(buf_len, GFP_KERNEL); if (!desc_src) { -- 2.25.1

1 17

[PATCH openEuler-1.0-LTS 1/2] s390/bpf: Fix 64-bit subtraction of the -0x80000000 constant
by Yang Yingliang 04 Nov '21

04 Nov '21

From: Ilya Leoshkevich <iii(a)linux.ibm.com> stable inclusion from linux-4.19.207 commit e15c2fe2def24324bfdbfb7ec2837e40b2aac7fd CVE: CVE-2021-20320 -------------------------------- commit 6e61dc9da0b7a0d91d57c2e20b5ea4fd2d4e7e53 upstream. The JIT uses agfi for subtracting constants, but -(-0x80000000) cannot be represented as a 32-bit signed binary integer. Fix by using algfi in this particular case. Reported-by: Johan Almbladh <johan.almbladh(a)anyfinetworks.com> Fixes: 054623105728 ("s390/bpf: Add s390x eBPF JIT compiler backend") Reviewed-by: Heiko Carstens <hca(a)linux.ibm.com> Signed-off-by: Ilya Leoshkevich <iii(a)linux.ibm.com> Signed-off-by: Vasily Gorbik <gor(a)linux.ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: He Fengqing <hefengqing(a)huawei.com> Reviewed-by: weiyang wang <wangweiyang2(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/s390/net/bpf_jit_comp.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 914b655eb5ba7..a8ee2f5c827d6 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -595,8 +595,13 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i case BPF_ALU64 | BPF_SUB | BPF_K: /* dst = dst - imm */ if (!imm) break; - /* agfi %dst,-imm */ - EMIT6_IMM(0xc2080000, dst_reg, -imm); + if (imm == -0x80000000) { + /* algfi %dst,0x80000000 */ + EMIT6_IMM(0xc20a0000, dst_reg, 0x80000000); + } else { + /* agfi %dst,-imm */ + EMIT6_IMM(0xc2080000, dst_reg, -imm); + } break; /* * BPF_MUL -- 2.25.1

1 1

[PATCH openEuler-21.09 2/2] tools: add a tool to calculate the CPU utilization rate
by Hongyu Li 03 Nov '21

03 Nov '21

openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CIJQ CVE: NA ---------------------------------------------------------------------- This tool can help calculate the CPU utilization rate in higher precision. Signed-off-by: Hongyu Li <543306408(a)qq.com> --- tools/accounting/Makefile | 2 +- tools/accounting/cpu_rate_cal.c | 91 ++++++++++++++++++++++++++++ tools/accounting/cpu_rate_cal_readme | 15 +++++ 3 files changed, 107 insertions(+), 1 deletion(-) create mode 100644 tools/accounting/cpu_rate_cal.c create mode 100644 tools/accounting/cpu_rate_cal_readme diff --git a/tools/accounting/Makefile b/tools/accounting/Makefile index 03687f19cbb1..471fbdd7b07b 100644 --- a/tools/accounting/Makefile +++ b/tools/accounting/Makefile @@ -2,7 +2,7 @@ CC := $(CROSS_COMPILE)gcc CFLAGS := -I../../usr/include -PROGS := getdelays +PROGS := getdelays cpu_rate_cal all: $(PROGS) diff --git a/tools/accounting/cpu_rate_cal.c b/tools/accounting/cpu_rate_cal.c new file mode 100644 index 000000000000..6d621b37c70e --- /dev/null +++ b/tools/accounting/cpu_rate_cal.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * idle_cal.c + * + * Copyright (C) 2021 + * + * cpu idle time accouting + */ + + +#include <stdlib.h> +#include <stdio.h> +#include <fcntl.h> +#include <string.h> +#include <unistd.h> +#include <time.h> +#include <limits.h> +#include <sys/time.h> + +#define BUFFSIZE 4096 +#define HZ 100 +#define FILE_NAME "/proc/stat2" + +struct cpu_info { + char name[BUFFSIZE]; + long long value[1]; +}; + +int main(void) +{ + int cpu_number = sysconf(_SC_NPROCESSORS_ONLN); + struct cpu_info *cpus = (struct cpu_info *)malloc(sizeof(struct cpu_info)*cpu_number); + struct cpu_info *cpus_2 = (struct cpu_info *)malloc(sizeof(struct cpu_info)*cpu_number); + + char buf[BUFFSIZE]; + long long sub; + double value; + + while (1) { + FILE *fp = fopen(FILE_NAME, "r"); + int i = 0; + struct timeval start, end; + + + while (i < cpu_number+1) { + int n = fscanf(fp, "%s %lld\n", cpus[i].name, &cpus[i].value[0]); + + if (n < 0) { + printf("wrong"); + return -1; + } + i += 1; + } + + gettimeofday(&start, NULL); + fflush(fp); + fclose(fp); + i = 0; + + sleep(1); + + FILE *fp_2 = fopen(FILE_NAME, "r"); + + while (i < cpu_number+1) { + int n = fscanf(fp_2, "%s %lld\n", cpus_2[i].name, &cpus_2[i].value[0]); + + if (n < 0) { + printf("wrong"); + return -1; + } + i += 1; + } + + gettimeofday(&end, NULL); + fflush(fp); + fclose(fp_2); + + sub = end.tv_sec-start.tv_sec; + value = sub*1000000.0+end.tv_usec-start.tv_usec; + system("reset"); + printf("CPU idle rate %f\n", 1000000/HZ*(cpus_2[0].value[0]-cpus[0].value[0]) + /value); + + for (int i = 1; i < cpu_number+1; i++) { + printf("CPU%d idle rate %f\n", i-1, 1-1000000/HZ + *(cpus_2[i].value[0]-cpus[i].value[0])/value); + } + } + return 0; +} + diff --git a/tools/accounting/cpu_rate_cal_readme b/tools/accounting/cpu_rate_cal_readme new file mode 100644 index 000000000000..01b5d8d930fe --- /dev/null +++ b/tools/accounting/cpu_rate_cal_readme @@ -0,0 +1,15 @@ +# calculate the cpu utilization rate + +The cpu_rate_cal.c is a tool to calculate the cpu utilization rate. It prints the cpu utilization per 1 second. The first line is the cpu utilization of all the cpus and other lines are the cpu utilizations of each cpu. + +This tool can be compiled by running + +```C +gcc cpu_rate_cal.c -o cpu_rate_cal +``` + +We can use it by running + +```C +./cpu_rate_cal +``` -- 2.17.1

1 0

[PATCH openEuler-21.09 1/2] eulerfs: add the /proc/stat2 file
by Hongyu Li 03 Nov '21

03 Nov '21

openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CIJQ CVE: NA ---------------------------------------------------------------------- The default way of calculating CPU utilization is to check which task is executed during the interval of two ticks. This leads to the inaccurate results of CPU utilization. This problem can be solved by counting the idle time via scheduler rather than the tick interval. We can record the time before executing idle process and calculate the execute time before quiting the idle process. The idle time of each CPU is given in the /proc/stat2 file. This way can give higher precision in accounting the CPU idle time compared with the /proc/stat. Signed-off-by: Hongyu Li <543306408(a)qq.com> --- fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/stat2.c | 91 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 34 ++++++++++++++++ kernel/sched/idle.c | 38 ++++++++++++++++++ 5 files changed, 171 insertions(+) create mode 100644 fs/proc/stat2.c diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..33588a37579e 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS + +config PROC_IDLE + bool "include /proc/stat2 file" + depends on PROC_FS + default y + help + Provide the CPU idle time in the /proc/stat2 file. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..b0d5f2b347d7 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += stat2.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/stat2.c b/fs/proc/stat2.c new file mode 100644 index 000000000000..6036a946c71d --- /dev/null +++ b/fs/proc/stat2.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/proc/stat2.c + * + * Copyright (C) 2007 + * + * cpu idle time accouting + */ + +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/sched/stat.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> + +#ifdef CONFIG_PROC_IDLE + +#define PROC_NAME "stat2" + +extern u64 cal_idle_sum_exec_runtime(int cpu); + +static u64 get_idle_sum_exec_runtime(int cpu) +{ + u64 idle = cal_idle_sum_exec_runtime(cpu); + + return idle; +} + +static int show_idle(struct seq_file *p, void *v) +{ + int i; + u64 idle; + + idle = 0; + + for_each_possible_cpu(i) { + + idle += get_idle_sum_exec_runtime(i); + + } + + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + + idle = get_idle_sum_exec_runtime(i); + + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + } + + return 0; +} + +static int idle_open(struct inode *inode, struct file *file) +{ + unsigned int size = 32 + 32 * num_online_cpus(); + + return single_open_size(file, show_idle, NULL, size); +} + +static struct proc_ops idle_procs_ops = { + .proc_open = idle_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init kernel_module_init(void) +{ + proc_create(PROC_NAME, 0, NULL, &idle_procs_ops); + return 0; +} + +fs_initcall(kernel_module_init); + +#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..25218a8f822f 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -19,6 +19,8 @@ */ DEFINE_PER_CPU(struct irqtime, cpu_irqtime); +extern struct static_key_true proc_idle; + static int sched_clock_irqtime; void enable_sched_clock_irqtime(void) @@ -1078,3 +1080,35 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + + +#ifdef CONFIG_PROC_IDLE + + +u64 cal_idle_sum_exec_runtime(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_entity *idle_se = &rq->idle->se; + u64 idle = idle_se->sum_exec_runtime; + + if (!static_branch_likely(&proc_idle)) + return 0ULL; + + if (rq->curr == rq->idle) { + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return idle; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle += delta_exec; + } + + return idle; +} + +#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..3714a1c0d57b 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -10,6 +10,8 @@ #include <trace/events/power.h> +DEFINE_STATIC_KEY_TRUE(proc_idle); + /* Linker adds these: start and end of __cpuidle functions */ extern char __cpuidle_text_start[], __cpuidle_text_end[]; @@ -424,8 +426,35 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE + if (!static_branch_likely(&proc_idle)) + return; + + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle_se->sum_exec_runtime += delta_exec; +#endif } +#ifdef CONFIG_PROC_IDLE +static int __init init_proc_idle(char *str) +{ + if (!strcmp(str, "false")) + static_branch_disable(&proc_idle); + + return 1; +} +__setup("proc_idle=", init_proc_idle); +#endif static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) { update_idle_core(rq); @@ -436,6 +465,15 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle; +#ifdef CONFIG_PROC_IDLE + if (static_branch_likely(&proc_idle)) { + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + + idle_se->exec_start = now; + } +#endif + set_next_task_idle(rq, next, true); return next; -- 2.17.1

1 0

[PATCH openEuler-21.09 0/2] Improve the precisoin of accounuting CPU utilization rate
by Hongyu Li 03 Nov '21

03 Nov '21

The current way of calculating the CPU utilization rate is not accurate. The accounting system only works In the interval of two ticks. However, a process can give up the CPU before the tick ending. This can be fixed by counting the idel time via the scheduler. We can use the sum_exe_runtime of the idle process of each CPU to calculate the the CPU utilization rate. The idle time of each CPU is given in the /proc/stat2 file. An example of using this file is also attached. Hongyu Li (2): eulerfs: add the /proc/stat2 file tools: add a tool to calculate the CPU utilization rate fs/proc/Kconfig | 7 +++ fs/proc/Makefile | 1 + fs/proc/stat2.c | 91 ++++++++++++++++++++++++++++ kernel/sched/cputime.c | 34 +++++++++++ kernel/sched/idle.c | 38 ++++++++++++ tools/accounting/Makefile | 2 +- tools/accounting/cpu_rate_cal.c | 91 ++++++++++++++++++++++++++++ tools/accounting/cpu_rate_cal_readme | 15 +++++ 8 files changed, 278 insertions(+), 1 deletion(-) create mode 100644 fs/proc/stat2.c create mode 100644 tools/accounting/cpu_rate_cal.c create mode 100644 tools/accounting/cpu_rate_cal_readme -- 2.17.1

1 0

[PATCH OLK-5.10] SCSI:SPFC: fix compile error
by Yanling Song 03 Nov '21

03 Nov '21

Ramaxel inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4DBD7 CVE: NA Fix two compile errors: 1. Compile failed when O=xxx is specified; 2. Compile confliction when spfc and spnic are compiled in parallel by -j option because they share some .c files Signed-off-by: Yanling Song <songyl(a)ramaxel.com> --- drivers/scsi/spfc/Makefile | 30 +++++++++++++++--------------- drivers/scsi/spfc/sphw_api_cmd.c | 1 + drivers/scsi/spfc/sphw_cmdq.c | 1 + drivers/scsi/spfc/sphw_common.c | 1 + drivers/scsi/spfc/sphw_eqs.c | 1 + drivers/scsi/spfc/sphw_hw_cfg.c | 1 + drivers/scsi/spfc/sphw_hw_comm.c | 1 + drivers/scsi/spfc/sphw_hwdev.c | 1 + drivers/scsi/spfc/sphw_hwif.c | 1 + drivers/scsi/spfc/sphw_mbox.c | 1 + drivers/scsi/spfc/sphw_mgmt.c | 1 + drivers/scsi/spfc/sphw_prof_adap.c | 1 + drivers/scsi/spfc/sphw_wq.c | 1 + 13 files changed, 27 insertions(+), 15 deletions(-) create mode 120000 drivers/scsi/spfc/sphw_api_cmd.c create mode 120000 drivers/scsi/spfc/sphw_cmdq.c create mode 120000 drivers/scsi/spfc/sphw_common.c create mode 120000 drivers/scsi/spfc/sphw_eqs.c create mode 120000 drivers/scsi/spfc/sphw_hw_cfg.c create mode 120000 drivers/scsi/spfc/sphw_hw_comm.c create mode 120000 drivers/scsi/spfc/sphw_hwdev.c create mode 120000 drivers/scsi/spfc/sphw_hwif.c create mode 120000 drivers/scsi/spfc/sphw_mbox.c create mode 120000 drivers/scsi/spfc/sphw_mgmt.c create mode 120000 drivers/scsi/spfc/sphw_prof_adap.c create mode 120000 drivers/scsi/spfc/sphw_wq.c diff --git a/drivers/scsi/spfc/Makefile b/drivers/scsi/spfc/Makefile index 02fe0213e048..849b730ac733 100644 --- a/drivers/scsi/spfc/Makefile +++ b/drivers/scsi/spfc/Makefile @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_SPFC) += spfc.o -subdir-ccflags-y += -I$(src)/../../net/ethernet/ramaxel/spnic/hw -subdir-ccflags-y += -I$(src)/hw -subdir-ccflags-y += -I$(src)/common +subdir-ccflags-y += -I$(srctree)/$(src)/../../net/ethernet/ramaxel/spnic/hw +subdir-ccflags-y += -I$(srctree)/$(src)/hw +subdir-ccflags-y += -I$(srctree)/$(src)/common spfc-objs := common/unf_init.o \ common/unf_event.o \ @@ -33,15 +33,15 @@ spfc-objs := common/unf_init.o \ hw/spfc_cqm_bitmap_table.o \ hw/spfc_cqm_main.o \ hw/spfc_cqm_object.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hwdev.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_common.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_hwif.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_wq.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_eqs.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_mbox.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.o \ - ../../net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.o + sphw_hwdev.o \ + sphw_hw_cfg.o \ + sphw_hw_comm.o \ + sphw_prof_adap.o \ + sphw_common.o \ + sphw_hwif.o \ + sphw_wq.o \ + sphw_cmdq.o \ + sphw_eqs.o \ + sphw_mbox.o \ + sphw_mgmt.o \ + sphw_api_cmd.o diff --git a/drivers/scsi/spfc/sphw_api_cmd.c b/drivers/scsi/spfc/sphw_api_cmd.c new file mode 120000 index 000000000000..27c7c0770fa3 --- /dev/null +++ b/drivers/scsi/spfc/sphw_api_cmd.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_cmdq.c b/drivers/scsi/spfc/sphw_cmdq.c new file mode 120000 index 000000000000..5ac779ba274b --- /dev/null +++ b/drivers/scsi/spfc/sphw_cmdq.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_common.c b/drivers/scsi/spfc/sphw_common.c new file mode 120000 index 000000000000..a1a30a4840e1 --- /dev/null +++ b/drivers/scsi/spfc/sphw_common.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_common.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_eqs.c b/drivers/scsi/spfc/sphw_eqs.c new file mode 120000 index 000000000000..74430dcb9dc5 --- /dev/null +++ b/drivers/scsi/spfc/sphw_eqs.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_eqs.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hw_cfg.c b/drivers/scsi/spfc/sphw_hw_cfg.c new file mode 120000 index 000000000000..4f43d68624c1 --- /dev/null +++ b/drivers/scsi/spfc/sphw_hw_cfg.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hw_comm.c b/drivers/scsi/spfc/sphw_hw_comm.c new file mode 120000 index 000000000000..c943b3b2933a --- /dev/null +++ b/drivers/scsi/spfc/sphw_hw_comm.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hwdev.c b/drivers/scsi/spfc/sphw_hwdev.c new file mode 120000 index 000000000000..b7279f17eaa2 --- /dev/null +++ b/drivers/scsi/spfc/sphw_hwdev.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hwdev.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_hwif.c b/drivers/scsi/spfc/sphw_hwif.c new file mode 120000 index 000000000000..d40ef71f9033 --- /dev/null +++ b/drivers/scsi/spfc/sphw_hwif.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_hwif.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_mbox.c b/drivers/scsi/spfc/sphw_mbox.c new file mode 120000 index 000000000000..1b00fe7289cc --- /dev/null +++ b/drivers/scsi/spfc/sphw_mbox.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_mbox.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_mgmt.c b/drivers/scsi/spfc/sphw_mgmt.c new file mode 120000 index 000000000000..fd18a73e9d3a --- /dev/null +++ b/drivers/scsi/spfc/sphw_mgmt.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_prof_adap.c b/drivers/scsi/spfc/sphw_prof_adap.c new file mode 120000 index 000000000000..fbc7db05dd27 --- /dev/null +++ b/drivers/scsi/spfc/sphw_prof_adap.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.c \ No newline at end of file diff --git a/drivers/scsi/spfc/sphw_wq.c b/drivers/scsi/spfc/sphw_wq.c new file mode 120000 index 000000000000..cdfcb3a610c0 --- /dev/null +++ b/drivers/scsi/spfc/sphw_wq.c @@ -0,0 +1 @@ +../../net/ethernet/ramaxel/spnic/hw/sphw_wq.c \ No newline at end of file -- 2.27.0

1 0

[PATCH openEuler-1.0-LTS] nbd: add sanity check for first_minor
by Yang Yingliang 02 Nov '21

02 Nov '21

From: Yu Kuai <yukuai3(a)huawei.com> hulk inclusion category: bugfix bugzilla: 182920, https://gitee.com/openeuler/kernel/issues/I4GLNX CVE: NA --------------------------- When user pass 0x100000 as index, nbd will end up create sysfs dir "/sys/block/43:0": nbd_dev_add disk->first_minor = index << part_shift -> default part_shift is 5, 0x100000 << 5 = 0x2000000 device_add_disk blk_alloc_devt MKDEV(disk->major, disk->first_minor + part->partno) -> (0x2b << 20) | (0x2000000) = 0x2b00000 register_disk device_add device_create_sys_dev_entry format_dev_t MAJOR(devt) -> 0x2b00000 >> 20 = 0x2b MINOR(devt) -> 0x2b00000 & 0xfffff = 0 sysfs_create_link -> /sys/block/43:0 If nbd created device with index 0 aready, then sysfs will compalin about dumplicated creation. On the other hand, the similar dumplicated creation will happen if "index << part_shift" over flow to a value that is less than MINORMASK. Thus fix the problem by adding sanity check for first_minor. Fixes: b0d9111a2d53 ("nbd: use an idr to keep track of nbd devices") Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/block/nbd.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 2a3794801704a..33a52be762d24 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1755,7 +1755,18 @@ static int nbd_dev_add(int index) refcount_set(&nbd->refs, 1); INIT_LIST_HEAD(&nbd->list); disk->major = NBD_MAJOR; + + /* + * Too big index can cause duplicate creation of sysfs files/links, + * because MKDEV() expect that the max first minor is MINORMASK, or + * index << part_shift can overflow. + */ disk->first_minor = index << part_shift; + if (disk->first_minor < index || disk->first_minor > MINORMASK) { + err = -EINVAL; + goto out_free_tags; + } + disk->fops = &nbd_fops; disk->private_data = nbd; sprintf(disk->disk_name, "nbd%d", index); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] perf: hisi: Fix compile error if defined MODULE
by Yang Yingliang 02 Nov '21

02 Nov '21

From: Lijun Fang <fanglijun3(a)huawei.com> ascend inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4D4WR CVE: NA --------------------------- Fix compile error if defined MODULE. Signed-off-by: Lijun Fang <fanglijun3(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/perf/hisilicon/hisi_uncore_lpddrc_pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/perf/hisilicon/hisi_uncore_lpddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_lpddrc_pmu.c index 8f8b211788e0f..ca395252ccc3d 100644 --- a/drivers/perf/hisilicon/hisi_uncore_lpddrc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_lpddrc_pmu.c @@ -241,7 +241,7 @@ static int hisi_lpddrc_pmu_init_irq(struct hisi_pmu *lpddrc_pmu, static const struct of_device_id lpddrc_of_match[] = { { .compatible = "hisilicon,lpddrc-pmu", }, {}, -} +}; MODULE_DEVICE_TABLE(of, lpddrc_of_match); static int hisi_lpddrc_pmu_init_data(struct platform_device *pdev, -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] nfc: nci: fix the UAF of rf_conn_info object
by Yang Yingliang 02 Nov '21

02 Nov '21

From: Lin Ma <linma(a)zju.edu.cn> mainline inclusion from mainline-v5.15-rc6 commit 1b1499a817c90fd1ce9453a2c98d2a01cca0e775 category: bugfix bugzilla: NA CVE: CVE-2021-3760 ------------------------------------------------- The nci_core_conn_close_rsp_packet() function will release the conn_info with given conn_id. However, it needs to set the rf_conn_info to NULL to prevent other routines like nci_rf_intf_activated_ntf_packet() to trigger the UAF. Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com> Signed-off-by: Lin Ma <linma(a)zju.edu.cn> Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/nfc/nci/rsp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c index e3bbf1937d0e9..7681f89dc312b 100644 --- a/net/nfc/nci/rsp.c +++ b/net/nfc/nci/rsp.c @@ -289,6 +289,8 @@ static void nci_core_conn_close_rsp_packet(struct nci_dev *ndev, ndev->cur_conn_id); if (conn_info) { list_del(&conn_info->list); + if (conn_info == ndev->rf_conn_info) + ndev->rf_conn_info = NULL; devm_kfree(&ndev->nfc_dev->dev, conn_info); } } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/4] ipv4: use siphash instead of Jenkins in fnhe_hashfun()
by Yang Yingliang 02 Nov '21

02 Nov '21

From: Eric Dumazet <edumazet(a)google.com> mainline inclusion from mainline-v5.14 commit 6457378fe796815c973f631a1904e147d6ee33b1 category: bugfix bugzilla: NA CVE: CVE-2021-20322 ------------------------------------------------- A group of security researchers brought to our attention the weakness of hash function used in fnhe_hashfun(). Lets use siphash instead of Jenkins Hash, to considerably reduce security risks. Also remove the inline keyword, this really is distracting. Fixes: d546c621542d ("ipv4: harden fnhe_hashfun()") Signed-off-by: Eric Dumazet <edumazet(a)google.com> Reported-by: Keyu Man <kman001(a)ucr.edu> Cc: Willy Tarreau <w(a)1wt.eu> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Xu Jia <xujia39(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/ipv4/route.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 958df3427c34f..dd43e798194ab 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -614,14 +614,14 @@ static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) return oldest; } -static inline u32 fnhe_hashfun(__be32 daddr) +static u32 fnhe_hashfun(__be32 daddr) { - static u32 fnhe_hashrnd __read_mostly; - u32 hval; + static siphash_key_t fnhe_hash_key __read_mostly; + u64 hval; - net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd)); - hval = jhash_1word((__force u32) daddr, fnhe_hashrnd); - return hash_32(hval, FNHE_HASH_SHIFT); + net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key)); + hval = siphash_1u32((__force u32) daddr, &fnhe_hash_key); + return hash_64(hval, FNHE_HASH_SHIFT); } static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS] README: README optimize
by Yang Yingliang 01 Nov '21

01 Nov '21

From: Laibin Qiu <qiulaibin(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4FS3G?from=project-issue CVE: NA --------------------------- There are some language problems in the README file, and MarkDown fromat syntax is not effective, and it needs to be adjusted. Signed-off-by: suqin <suqin2(a)huawei.com> Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- README | 291 ++++++++++++++++++++++++++++++--------------------------- 1 file changed, 155 insertions(+), 136 deletions(-) diff --git a/README b/README index 46c9ea3522c1c..21b2e09d62db2 100644 --- a/README +++ b/README @@ -1,174 +1,188 @@ -Contributions to openEuler kernel project -========================================= +# How to Contribute +------- -Sign CLA --------- +- [How to Contribute](#How to Contribute) -Before submitting any Contributions to openEuler, you have to sign CLA. + \- [Sign the CLA](#Sign the CLA) -See: - https://openeuler.org/zh/cla.html - https://openeuler.org/en/cla.html + \- [Steps of submitting patches](#Steps of submitting patches) -Steps of submitting patches ---------------------------- + \- [Use the unified patch format](#Use the unified patch format) -1. Compile and test your patches successfully. -2. Generate patches - Your patches should be based on top of latest openEuler branch, and should - use git-format-patch to generate patches, and if it's a patchset, it's - better to use --cover-letter option to describe what the patchset does. + \- [Define the patch format](#Define the patch format) - Using scripts/checkpatch.pl to make sure there's no coding style issue. + \- [Examples](#Examples) - And make sure your patch follow unified openEuler patch format describe - below. + \- [Email client - Thunderbird settings](#Email client - Thunderbird settings) -3. Send patch to openEuler mailing list - Use this command to send patches to openEuler mailing list: +- [Linux kernel](#Linux kernel) - git send-email *.patch -to="kernel(a)openeuler.org" --suppress-cc=all +### Sign the CLA - *NOTE*: that you must add --suppress-cc=all if you use git send-email, - otherwise the email will be cced to the people in upstream community and mailing - lists. +------- - *See*: How to send patches using git-send-email - https://git-scm.com/docs/git-send-email +Before making any contributions to openEuler, sign the CLA first. -4. Mark "v1, v2, v3 ..." in your patch subject if you have multiple versions - to send out. +Address: [https://openeuler.org/en/cla.html](https://openeuler.org/en/cla.html) - Use --subject-prefix="PATCH v2" option to add v2 tag for patchset. - git format-patch --subject-prefix="PATCH v2" -1 +### Steps of submitting patches +------- - Subject examples: - Subject: [PATCH v2 01/27] fork: fix some -Wmissing-prototypes warnings - Subject: [PATCH v3] ext2: improve scalability of bitmap searching +**Step 1** Compile and test your patches. -5. Upstream your kernel patch to kernel community is strongly recommended. - openEuler will sync up with kernel master timely. +**Step 2** Generate patches. -6. Sign your work - the Developer’s Certificate of Origin - As the same of upstream kernel community, you also need to sign your patch. +Your patches should be generated based on the latest openEuler branch using git-format-patch. If your patches are in a patchset, it is better to use the **--cover-letter** option to describe what the patchset does. - See: https://www.kernel.org/doc/html/latest/process/submitting-patches.html +Use **scripts/checkpatch.pl** to ensure that no coding style issue exists. - The sign-off is a simple line at the end of the explanation for the patch, - which certifies that you wrote it or otherwise have the right to pass it - on as an open-source patch. The rules are pretty simple: if you can certify - the below: +In addition, ensure that your patches comply with the unified openEuler patch format described below. - Developer’s Certificate of Origin 1.1 - ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +**Step 3** Send your patches to the openEuler mailing list. - By making a contribution to this project, I certify that: +To do so, run the following command: - (a) The contribution was created in whole or in part by me and I have - the right to submit it under the open source license indicated in - the file; or + `git send-email *.patch -to="kernel(a)openeuler.org" --suppress-cc=all` - (b The contribution is based upon previous work that, to the best of - my knowledge, is covered under an appropriate open source license - and I have the right under that license to submit that work with - modifications, whether created in whole or in part by me, under - the same open source license (unless I am permitted to submit under - a different license), as indicated in the file; or +*NOTE*: Add **--suppress-cc=all** if you use git-send-email; otherwise, the email will be copied to all people in the upstream community and mailing lists. - (c) The contribution was provided directly to me by some other person - who certified (a), (b) or (c) and I have not modified it. +For details about how to send patches using git-send-email, see [https://git-scm.com/docs/git-send-email](https://git-scm.com/docs/git-send-…. - (d) I understand and agree that this project and the contribution are - public and that a record of the contribution (including all personal - information I submit with it, including my sign-off) is maintained - indefinitely and may be redistributed consistent with this project - or the open source license(s) involved. +**Step 4** Mark "v1, v2, v3 ..." in your patch subject if you have multiple versions to send out. - then you just add a line saying: +Use the **--subject-prefix="PATCH v2"** option to add the v2 tag to the patchset. - Signed-off-by: Random J Developer <random(a)developer.example.org> + `git format-patch --subject-prefix="PATCH v2" -1` - using your real name (sorry, no pseudonyms or anonymous contributions.) +Subject examples: -Use unified patch format ------------------------- + Subject: [PATCH v2 01/27] fork: fix some -Wmissing-prototypes warnings + + Subject: [PATCH v3] ext2: improve scalability of bitmap searching + +**Step 5** Upstream your kernel patches to the kernel community (recommended). openEuler will synchronize with the kernel master in a timely manner. + +**Step 6** Sign your work - the Developer’s Certificate of Origin. + + Similar to the upstream kernel community, you also need to sign your patch. + + For details, see [https://www.kernel.org/doc/html/latest/process/submitting-patches.html](htt…. + + The sign-off is a simple line at the end of the explanation of the patch, which certifies that you wrote it or otherwise have the right to pass it on as an open source patch. The rules are pretty simple. You can certify as below: + + Developer’s Certificate of Origin 1.1 + + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + By making a contribution to this project, I certify that: + + (a) The contribution was created in whole or in part by me and I have the right to submit it under the open source license indicated in the file; + + (b) The contribution is based upon previous work that, to the best of my knowledge, is covered under an appropriate open source license and I have the right under that license to submit that work with modifications, whether created in whole or in part by me, under the same open source license (unless I am permitted to submit under a different license), as indicated in the file; + + (c) The contribution was provided directly to me by some other person who certified (a), (b) or (c) and I have not modified it. + + (d) I understand and agree that this project and the contribution are public and that a record of the contribution (including all personal information I submit with it, including my sign-off) is maintained indefinitely and may be redistributed consistent with this project or the open source license(s) involved. + +Then you add a line saying: + +Signed-off-by: Random J Developer <random(a)developer.example.org> + +Use your real name (sorry, no pseudonyms or anonymous contributions). + +### Use the unified patch format +------- Reasons: -1. long term maintainability - openEuler will merge massive patches. If all patches are merged by casual - changelog format without a unified format, the git log will be messy, and - then it's hard to figure out the original patch. +1. Long term maintainability + + openEuler will merge massive patches. If all patches are merged by casual + + changelog formats without a unified format, the git logs will be messy, and + + then it is hard to figure out the original patches. + +2. Kernel upgrade -2. kernel upgrade - We definitely will upgrade our openEuler kernel in someday, using strict - patch management will alleviate the pain to migrate patches during big upgrade. + We definitely will upgrade our openEuler kernel in someday, so strict patch management -3. easy for script parsing - Keyword highlighting is necessary for script parsing. + will alleviate the pain to migrate patches during big upgrades. -Patch format definition ------------------------ +3. Easy for script parsing + + Keyword highlighting is necessary for script parsing. + +### Define the patch format +------- + +[M] stands for "mandatory". + +[O] stands for "option". -[M] stands for "mandatory" -[O] stands for "option" $category can be: bug preparation, bugfix, perf, feature, doc, other... -If category is feature, then we also need to add feature name like below: - category: feature - feature: YYY (the feature name) +If category is feature, we need to add a feature name as below: -If the patch is related to CVE or bugzilla, then we need add the corresponding -tag like below (In general, it should include at least one of the following): - CVE: $cve-id - bugzilla: $bug-id +```cpp +category: feature +feature: YYY (the feature name) +``` -Additional changelog should include at least one of the flollwing: - 1) Why we should apply this patch - 2) What real problem in product does this patch resolved - 3) How could we reproduce this bug or how to test - 4) Other useful information for help to understand this patch or problem +If the patch is related to CVE or bugzilla, we need to add the corresponding tag as below (In general, it should include at least one of the following): -The detail information is very useful for porting patch to another kenrel branch. +```cpp +CVE: $cve-id +bugzilla: $bug-id +``` -Example for mainline patch: +Additional changelog should include at least one of the following: - mainline inclusion [M] - from $mainline-version [M] - commit $id [M] - category: $category [M] - bugzilla: $bug-id [O] - CVE: $cve-id [O] +1. Why we should apply this patch - additional changelog [O] +2. What real problems in the product does this patch resolved + +3. How could we reproduce this bug or how to test + +4. Other useful information for help to understand this patch or problem + +The detailed information is very useful for migrating a patch to another kernel branch. + +Example for mainline patch: - -------------------------------- +```cpp +mainline inclusion [M] +from $mainline-version [M] +commit $id [M] +category: $category [M] +bugzilla: $bug-id [O] +CVE: $cve-id [O] - original changelog +additional changelog [O] - Signed-off-by: $yourname <$yourname(a)huawei.com> [M] +-------------------------------- - ($mainline-version could be mainline-3.5, mainline-3.6, etc...) +original changelog +Signed-off-by: $yourname <$yourname(a)huawei.com> [M] +($mainline-version could be mainline-3.5, mainline-3.6, etc...) +``` -Examples --------- +### Examples +------- +```cpp mainline inclusion from mainline-4.10 commit 0becc0ae5b42828785b589f686725ff5bc3b9b25 category: bugfix bugzilla: 3004 -CVE: NA - -The patch fixes a BUG_ON in the product: injecting single bit ECC error -to memory before system boot use hardware inject tools, which cause a -large amount of CMCI during system booting . +CVE: N/A -[ 1.146580] mce: [Hardware Error]: Machine check events logged -[ 1.152908] ------------[ cut here ]------------ -[ 1.157751] kernel BUG at kernel/timer.c:951! -[ 1.162321] invalid opcode: 0000 [#1] SMP -... +The patch fixes a BUG_ON in the product: Injecting a single bit ECC error to the memory before system boot using hardware inject tools will cause a large amount of CMCI during system booting . +[ 1.146580] mce: [Hardware Error]: Machine check events logged +[ 1.152908] ------------[ cut here ]------------ +[ 1.157751] kernel BUG at kernel/timer.c:951! +[ 1.162321] invalid opcode: 0000 [#1] SMP ------------------------------------------------- @@ -177,33 +191,38 @@ original changelog <original S-O-B> Signed-off-by: Zhang San <zhangsan(a)huawei.com> Tested-by: Li Si <lisi(a)huawei.com> +``` + +### Email client - Thunderbird settings +------- + +If you are a new developer in the kernel community, it is highly recommended that you use the Thunderbird mail client. + +1. Thunderbird Installation + + Obtain the English version of Thunderbird from [http://www.mozilla.org/]( http://www.mozilla.org/) and install it on your system. + + Download URL: https://www.thunderbird.net/en-US/thunderbird/all/ + +2. Settings + + 2.1 Use the plain text format instead of the HTML format. + + Choose **Options > Account Settings > Composition & Addressing**, and do **NOT** select Compose message in HTML format. -Email Client - Thunderbird Settings ------------------------------------ + 2.2 Editor settings -If you are newly developer in the kernel community, it is highly recommended -to use thunderbird mail client. + **Tools > Options> Advanced > Config editor** -1. Thunderbird Installation - Get English version Thunderbird from http://www.mozilla.org/ and install - it on your system。 + \- To bring up the Thunderbird's registry editor, set **mailnews.send_plaintext_flowed** to **false**. - Download url: https://www.thunderbird.net/en-US/thunderbird/all/ + \- Disable HTML Format: Set **mail.identity.id1.compose_html** to **false**. -2. Settings - 2.1 Use plain text format instead of HTML format - Options -> Account Settings -> Composition & Addressing, do *NOT* select - "Compose message in HTML format". + \- Enable UTF-8: Set **prefs.converted-to-utf8** to **true**. - 2.2 Editor Settings - Tools->Options->Advanced->Config editor. + \- View messages in UTF-8: Set **mailnews.view_default_charset** to **UTF-8**. - - To bring up the thunderbird's registry editor, and set: - "mailnews.send_plaintext_flowed" to "false". - - Disable HTML Format: Set "mail.identity.id1.compose_html" to "false". - - Enable UTF8: Set "prefs.converted-to-utf8" to "true". - - View message in UTF-8: Set "mailnews.view_default_charset" to "UTF-8". - - Set mailnews.wraplength to 9999 for avoiding auto-wrap + \- Set **mailnews.wraplength** to **9999** to avoid auto-wrap. Linux kernel ============ -- 2.25.1

1 0

[PATCH OLK-5.10] Net:NIC:SPNIC:Fix compile error when O= is specififed
by Yanling Song 01 Nov '21

01 Nov '21

Ramaxel inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CBDP CVE: NA Signed-off-by: Yanling Song <songyl(a)ramaxel.com> --- drivers/net/ethernet/ramaxel/spnic/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ramaxel/spnic/Makefile b/drivers/net/ethernet/ramaxel/spnic/Makefile index f86ccff374f6..207e1d9c431a 100644 --- a/drivers/net/ethernet/ramaxel/spnic/Makefile +++ b/drivers/net/ethernet/ramaxel/spnic/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_SPNIC) += spnic.o -subdir-ccflags-y += -I$(src)/hw +subdir-ccflags-y += -I$(srctree)/$(src)/hw spnic-objs := hw/sphw_common.o \ hw/sphw_hwif.o \ -- 2.27.0

2 1

[PATCH OLK-5.10] SCSI:SPFC: fix compile error when O= is specified
by Yanling Song 01 Nov '21

01 Nov '21

Ramaxel inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4DBD7 CVE: NA Signed-off-by: Yanling Song <songyl(a)ramaxel.com> --- drivers/scsi/spfc/Makefile | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/spfc/Makefile b/drivers/scsi/spfc/Makefile index 02fe0213e048..205eadc35318 100644 --- a/drivers/scsi/spfc/Makefile +++ b/drivers/scsi/spfc/Makefile @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_SPFC) += spfc.o -subdir-ccflags-y += -I$(src)/../../net/ethernet/ramaxel/spnic/hw -subdir-ccflags-y += -I$(src)/hw -subdir-ccflags-y += -I$(src)/common +subdir-ccflags-y += -I$(srctree)/$(src)/../../net/ethernet/ramaxel/spnic/hw +subdir-ccflags-y += -I$(srctree)/$(src)/hw +subdir-ccflags-y += -I$(srctree)/$(src)/common spfc-objs := common/unf_init.o \ common/unf_event.o \ -- 2.27.0

2 1

[PATCH openEuler-1.0-LTS V4] README: README optimize
by Laibin Qiu 01 Nov '21

01 Nov '21

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4FS3G?from=project-issue CVE: NA --------------------------- There are some language problems in the README file, and MarkDown fromat syntax is not effective, and it needs to be adjusted. Signed-off-by: suqin <suqin2(a)huawei.com> Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> --- README | 291 ++++++++++++++++++++++++++++++--------------------------- 1 file changed, 155 insertions(+), 136 deletions(-) diff --git a/README b/README index 46c9ea352..21b2e09d6 100644 --- a/README +++ b/README @@ -1,174 +1,188 @@ -Contributions to openEuler kernel project -========================================= +# How to Contribute +------- -Sign CLA --------- +- [How to Contribute](#How to Contribute) -Before submitting any Contributions to openEuler, you have to sign CLA. + \- [Sign the CLA](#Sign the CLA) -See: - https://openeuler.org/zh/cla.html - https://openeuler.org/en/cla.html + \- [Steps of submitting patches](#Steps of submitting patches) -Steps of submitting patches ---------------------------- + \- [Use the unified patch format](#Use the unified patch format) -1. Compile and test your patches successfully. -2. Generate patches - Your patches should be based on top of latest openEuler branch, and should - use git-format-patch to generate patches, and if it's a patchset, it's - better to use --cover-letter option to describe what the patchset does. + \- [Define the patch format](#Define the patch format) - Using scripts/checkpatch.pl to make sure there's no coding style issue. + \- [Examples](#Examples) - And make sure your patch follow unified openEuler patch format describe - below. + \- [Email client - Thunderbird settings](#Email client - Thunderbird settings) -3. Send patch to openEuler mailing list - Use this command to send patches to openEuler mailing list: +- [Linux kernel](#Linux kernel) - git send-email *.patch -to="kernel(a)openeuler.org" --suppress-cc=all +### Sign the CLA - *NOTE*: that you must add --suppress-cc=all if you use git send-email, - otherwise the email will be cced to the people in upstream community and mailing - lists. +------- - *See*: How to send patches using git-send-email - https://git-scm.com/docs/git-send-email +Before making any contributions to openEuler, sign the CLA first. -4. Mark "v1, v2, v3 ..." in your patch subject if you have multiple versions - to send out. +Address: [https://openeuler.org/en/cla.html](https://openeuler.org/en/cla.html) - Use --subject-prefix="PATCH v2" option to add v2 tag for patchset. - git format-patch --subject-prefix="PATCH v2" -1 +### Steps of submitting patches +------- - Subject examples: - Subject: [PATCH v2 01/27] fork: fix some -Wmissing-prototypes warnings - Subject: [PATCH v3] ext2: improve scalability of bitmap searching +**Step 1** Compile and test your patches. -5. Upstream your kernel patch to kernel community is strongly recommended. - openEuler will sync up with kernel master timely. +**Step 2** Generate patches. -6. Sign your work - the Developer’s Certificate of Origin - As the same of upstream kernel community, you also need to sign your patch. +Your patches should be generated based on the latest openEuler branch using git-format-patch. If your patches are in a patchset, it is better to use the **--cover-letter** option to describe what the patchset does. - See: https://www.kernel.org/doc/html/latest/process/submitting-patches.html +Use **scripts/checkpatch.pl** to ensure that no coding style issue exists. - The sign-off is a simple line at the end of the explanation for the patch, - which certifies that you wrote it or otherwise have the right to pass it - on as an open-source patch. The rules are pretty simple: if you can certify - the below: +In addition, ensure that your patches comply with the unified openEuler patch format described below. - Developer’s Certificate of Origin 1.1 - ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +**Step 3** Send your patches to the openEuler mailing list. - By making a contribution to this project, I certify that: +To do so, run the following command: - (a) The contribution was created in whole or in part by me and I have - the right to submit it under the open source license indicated in - the file; or + `git send-email *.patch -to="kernel(a)openeuler.org" --suppress-cc=all` - (b The contribution is based upon previous work that, to the best of - my knowledge, is covered under an appropriate open source license - and I have the right under that license to submit that work with - modifications, whether created in whole or in part by me, under - the same open source license (unless I am permitted to submit under - a different license), as indicated in the file; or +*NOTE*: Add **--suppress-cc=all** if you use git-send-email; otherwise, the email will be copied to all people in the upstream community and mailing lists. - (c) The contribution was provided directly to me by some other person - who certified (a), (b) or (c) and I have not modified it. +For details about how to send patches using git-send-email, see [https://git-scm.com/docs/git-send-email](https://git-scm.com/docs/git-send-…. - (d) I understand and agree that this project and the contribution are - public and that a record of the contribution (including all personal - information I submit with it, including my sign-off) is maintained - indefinitely and may be redistributed consistent with this project - or the open source license(s) involved. +**Step 4** Mark "v1, v2, v3 ..." in your patch subject if you have multiple versions to send out. - then you just add a line saying: +Use the **--subject-prefix="PATCH v2"** option to add the v2 tag to the patchset. - Signed-off-by: Random J Developer <random(a)developer.example.org> + `git format-patch --subject-prefix="PATCH v2" -1` - using your real name (sorry, no pseudonyms or anonymous contributions.) +Subject examples: -Use unified patch format ------------------------- + Subject: [PATCH v2 01/27] fork: fix some -Wmissing-prototypes warnings + + Subject: [PATCH v3] ext2: improve scalability of bitmap searching + +**Step 5** Upstream your kernel patches to the kernel community (recommended). openEuler will synchronize with the kernel master in a timely manner. + +**Step 6** Sign your work - the Developer’s Certificate of Origin. + + Similar to the upstream kernel community, you also need to sign your patch. + + For details, see [https://www.kernel.org/doc/html/latest/process/submitting-patches.html](htt…. + + The sign-off is a simple line at the end of the explanation of the patch, which certifies that you wrote it or otherwise have the right to pass it on as an open source patch. The rules are pretty simple. You can certify as below: + + Developer’s Certificate of Origin 1.1 + + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + By making a contribution to this project, I certify that: + + (a) The contribution was created in whole or in part by me and I have the right to submit it under the open source license indicated in the file; + + (b) The contribution is based upon previous work that, to the best of my knowledge, is covered under an appropriate open source license and I have the right under that license to submit that work with modifications, whether created in whole or in part by me, under the same open source license (unless I am permitted to submit under a different license), as indicated in the file; + + (c) The contribution was provided directly to me by some other person who certified (a), (b) or (c) and I have not modified it. + + (d) I understand and agree that this project and the contribution are public and that a record of the contribution (including all personal information I submit with it, including my sign-off) is maintained indefinitely and may be redistributed consistent with this project or the open source license(s) involved. + +Then you add a line saying: + +Signed-off-by: Random J Developer <random(a)developer.example.org> + +Use your real name (sorry, no pseudonyms or anonymous contributions). + +### Use the unified patch format +------- Reasons: -1. long term maintainability - openEuler will merge massive patches. If all patches are merged by casual - changelog format without a unified format, the git log will be messy, and - then it's hard to figure out the original patch. +1. Long term maintainability + + openEuler will merge massive patches. If all patches are merged by casual + + changelog formats without a unified format, the git logs will be messy, and + + then it is hard to figure out the original patches. + +2. Kernel upgrade -2. kernel upgrade - We definitely will upgrade our openEuler kernel in someday, using strict - patch management will alleviate the pain to migrate patches during big upgrade. + We definitely will upgrade our openEuler kernel in someday, so strict patch management -3. easy for script parsing - Keyword highlighting is necessary for script parsing. + will alleviate the pain to migrate patches during big upgrades. -Patch format definition ------------------------ +3. Easy for script parsing + + Keyword highlighting is necessary for script parsing. + +### Define the patch format +------- + +[M] stands for "mandatory". + +[O] stands for "option". -[M] stands for "mandatory" -[O] stands for "option" $category can be: bug preparation, bugfix, perf, feature, doc, other... -If category is feature, then we also need to add feature name like below: - category: feature - feature: YYY (the feature name) +If category is feature, we need to add a feature name as below: -If the patch is related to CVE or bugzilla, then we need add the corresponding -tag like below (In general, it should include at least one of the following): - CVE: $cve-id - bugzilla: $bug-id +```cpp +category: feature +feature: YYY (the feature name) +``` -Additional changelog should include at least one of the flollwing: - 1) Why we should apply this patch - 2) What real problem in product does this patch resolved - 3) How could we reproduce this bug or how to test - 4) Other useful information for help to understand this patch or problem +If the patch is related to CVE or bugzilla, we need to add the corresponding tag as below (In general, it should include at least one of the following): -The detail information is very useful for porting patch to another kenrel branch. +```cpp +CVE: $cve-id +bugzilla: $bug-id +``` -Example for mainline patch: +Additional changelog should include at least one of the following: - mainline inclusion [M] - from $mainline-version [M] - commit $id [M] - category: $category [M] - bugzilla: $bug-id [O] - CVE: $cve-id [O] +1. Why we should apply this patch - additional changelog [O] +2. What real problems in the product does this patch resolved + +3. How could we reproduce this bug or how to test + +4. Other useful information for help to understand this patch or problem + +The detailed information is very useful for migrating a patch to another kernel branch. + +Example for mainline patch: - -------------------------------- +```cpp +mainline inclusion [M] +from $mainline-version [M] +commit $id [M] +category: $category [M] +bugzilla: $bug-id [O] +CVE: $cve-id [O] - original changelog +additional changelog [O] - Signed-off-by: $yourname <$yourname(a)huawei.com> [M] +-------------------------------- - ($mainline-version could be mainline-3.5, mainline-3.6, etc...) +original changelog +Signed-off-by: $yourname <$yourname(a)huawei.com> [M] +($mainline-version could be mainline-3.5, mainline-3.6, etc...) +``` -Examples --------- +### Examples +------- +```cpp mainline inclusion from mainline-4.10 commit 0becc0ae5b42828785b589f686725ff5bc3b9b25 category: bugfix bugzilla: 3004 -CVE: NA - -The patch fixes a BUG_ON in the product: injecting single bit ECC error -to memory before system boot use hardware inject tools, which cause a -large amount of CMCI during system booting . +CVE: N/A -[ 1.146580] mce: [Hardware Error]: Machine check events logged -[ 1.152908] ------------[ cut here ]------------ -[ 1.157751] kernel BUG at kernel/timer.c:951! -[ 1.162321] invalid opcode: 0000 [#1] SMP -... +The patch fixes a BUG_ON in the product: Injecting a single bit ECC error to the memory before system boot using hardware inject tools will cause a large amount of CMCI during system booting . +[ 1.146580] mce: [Hardware Error]: Machine check events logged +[ 1.152908] ------------[ cut here ]------------ +[ 1.157751] kernel BUG at kernel/timer.c:951! +[ 1.162321] invalid opcode: 0000 [#1] SMP ------------------------------------------------- @@ -177,33 +191,38 @@ original changelog <original S-O-B> Signed-off-by: Zhang San <zhangsan(a)huawei.com> Tested-by: Li Si <lisi(a)huawei.com> +``` + +### Email client - Thunderbird settings +------- + +If you are a new developer in the kernel community, it is highly recommended that you use the Thunderbird mail client. + +1. Thunderbird Installation + + Obtain the English version of Thunderbird from [http://www.mozilla.org/]( http://www.mozilla.org/) and install it on your system. + + Download URL: https://www.thunderbird.net/en-US/thunderbird/all/ + +2. Settings + + 2.1 Use the plain text format instead of the HTML format. + + Choose **Options > Account Settings > Composition & Addressing**, and do **NOT** select Compose message in HTML format. -Email Client - Thunderbird Settings ------------------------------------ + 2.2 Editor settings -If you are newly developer in the kernel community, it is highly recommended -to use thunderbird mail client. + **Tools > Options> Advanced > Config editor** -1. Thunderbird Installation - Get English version Thunderbird from http://www.mozilla.org/ and install - it on your system。 + \- To bring up the Thunderbird's registry editor, set **mailnews.send_plaintext_flowed** to **false**. - Download url: https://www.thunderbird.net/en-US/thunderbird/all/ + \- Disable HTML Format: Set **mail.identity.id1.compose_html** to **false**. -2. Settings - 2.1 Use plain text format instead of HTML format - Options -> Account Settings -> Composition & Addressing, do *NOT* select - "Compose message in HTML format". + \- Enable UTF-8: Set **prefs.converted-to-utf8** to **true**. - 2.2 Editor Settings - Tools->Options->Advanced->Config editor. + \- View messages in UTF-8: Set **mailnews.view_default_charset** to **UTF-8**. - - To bring up the thunderbird's registry editor, and set: - "mailnews.send_plaintext_flowed" to "false". - - Disable HTML Format: Set "mail.identity.id1.compose_html" to "false". - - Enable UTF8: Set "prefs.converted-to-utf8" to "true". - - View message in UTF-8: Set "mailnews.view_default_charset" to "UTF-8". - - Set mailnews.wraplength to 9999 for avoiding auto-wrap + \- Set **mailnews.wraplength** to **9999** to avoid auto-wrap. Linux kernel ============ -- 2.22.0

1 0

[PATCH openEuler-1.0-LTS] PM: hibernate: Get block device exclusively in swsusp_check()
by Yang Yingliang 01 Nov '21

01 Nov '21

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v5.16 commit 39fbef4b0f77f9c89c8f014749ca533643a37c9f category: bugfix bugzilla: 182871 CVE: NA ----------------------------------------------- The following kernel crash can be triggered: [ 89.266592] ------------[ cut here ]------------ [ 89.267427] kernel BUG at fs/buffer.c:3020! [ 89.268264] invalid opcode: 0000 [#1] SMP KASAN PTI [ 89.269116] CPU: 7 PID: 1750 Comm: kmmpd-loop0 Not tainted 5.10.0-862.14.0.6.x86_64-08610-gc932cda3cef4-dirty #20 [ 89.273169] RIP: 0010:submit_bh_wbc.isra.0+0x538/0x6d0 [ 89.277157] RSP: 0018:ffff888105ddfd08 EFLAGS: 00010246 [ 89.278093] RAX: 0000000000000005 RBX: ffff888124231498 RCX: ffffffffb2772612 [ 89.279332] RDX: 1ffff11024846293 RSI: 0000000000000008 RDI: ffff888124231498 [ 89.280591] RBP: ffff8881248cc000 R08: 0000000000000001 R09: ffffed1024846294 [ 89.281851] R10: ffff88812423149f R11: ffffed1024846293 R12: 0000000000003800 [ 89.283095] R13: 0000000000000001 R14: 0000000000000000 R15: ffff8881161f7000 [ 89.284342] FS: 0000000000000000(0000) GS:ffff88839b5c0000(0000) knlGS:0000000000000000 [ 89.285711] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 89.286701] CR2: 00007f166ebc01a0 CR3: 0000000435c0e000 CR4: 00000000000006e0 [ 89.287919] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 89.289138] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 89.290368] Call Trace: [ 89.290842] write_mmp_block+0x2ca/0x510 [ 89.292218] kmmpd+0x433/0x9a0 [ 89.294902] kthread+0x2dd/0x3e0 [ 89.296268] ret_from_fork+0x22/0x30 [ 89.296906] Modules linked in: by running the following commands: 1. mkfs.ext4 -O mmp /dev/sda -b 1024 2. mount /dev/sda /home/test 3. echo "/dev/sda" > /sys/power/resume That happens because swsusp_check() calls set_blocksize() on the target partition which confuses the file system: Thread1 Thread2 mount /dev/sda /home/test get s_mmp_bh --> has mapped flag start kmmpd thread echo "/dev/sda" > /sys/power/resume resume_store software_resume swsusp_check set_blocksize truncate_inode_pages_range truncate_cleanup_page block_invalidatepage discard_buffer --> clean mapped flag write_mmp_block submit_bh submit_bh_wbc BUG_ON(!buffer_mapped(bh)) To address this issue, modify swsusp_check() to open the target block device with exclusive access. Signed-off-by: Ye Bin <yebin10(a)huawei.com> [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/power/swap.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/power/swap.c b/kernel/power/swap.c index d7f6c1a288d33..4fde37fce4ea4 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -1512,9 +1512,10 @@ int swsusp_read(unsigned int *flags_p) int swsusp_check(void) { int error; + void *holder; hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, - FMODE_READ, NULL); + FMODE_READ | FMODE_EXCL, &holder); if (!IS_ERR(hib_resume_bdev)) { set_blocksize(hib_resume_bdev, PAGE_SIZE); clear_page(swsusp_header); @@ -1536,7 +1537,7 @@ int swsusp_check(void) put: if (error) - blkdev_put(hib_resume_bdev, FMODE_READ); + blkdev_put(hib_resume_bdev, FMODE_READ | FMODE_EXCL); else pr_debug("Image signature found, resuming\n"); } else { -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS V3] README: README optimize
by Laibin Qiu 01 Nov '21

01 Nov '21

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4FS3G?from=project-issue CVE: NA --------------------------- There are some language problems in the README file, and MarkDown fromat syntax is not effective, and it needs to be adjusted. Signed-off-by: suqin <suqin2(a)huawei.com> Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> --- README | 311 +++++++++++++++++++++++++++++---------------------------- 1 file changed, 161 insertions(+), 150 deletions(-) diff --git a/README b/README index 46c9ea352..3374c4726 100644 --- a/README +++ b/README @@ -1,174 +1,188 @@ -Contributions to openEuler kernel project -========================================= +# How to Contribute +------- -Sign CLA --------- +- [How to Contribute](#How to Contribute) -Before submitting any Contributions to openEuler, you have to sign CLA. + \- [Sign the CLA](#Sign the CLA) -See: - https://openeuler.org/zh/cla.html - https://openeuler.org/en/cla.html + \- [Steps of submitting patches](#Steps of submitting patches) -Steps of submitting patches ---------------------------- + \- [Use the unified patch format](#Use the unified patch format) -1. Compile and test your patches successfully. -2. Generate patches - Your patches should be based on top of latest openEuler branch, and should - use git-format-patch to generate patches, and if it's a patchset, it's - better to use --cover-letter option to describe what the patchset does. + \- [Define the patch format](#Define the patch format) - Using scripts/checkpatch.pl to make sure there's no coding style issue. + \- [Examples](#Examples) - And make sure your patch follow unified openEuler patch format describe - below. + \- [Email client - Thunderbird settings](#Email client - Thunderbird settings) -3. Send patch to openEuler mailing list - Use this command to send patches to openEuler mailing list: +- [Linux kernel](#Linux kernel) - git send-email *.patch -to="kernel(a)openeuler.org" --suppress-cc=all +### Sign the CLA - *NOTE*: that you must add --suppress-cc=all if you use git send-email, - otherwise the email will be cced to the people in upstream community and mailing - lists. +------- - *See*: How to send patches using git-send-email - https://git-scm.com/docs/git-send-email +Before making any contributions to openEuler, sign the CLA first. -4. Mark "v1, v2, v3 ..." in your patch subject if you have multiple versions - to send out. +Address: [https://openeuler.org/en/cla.html](https://openeuler.org/en/cla.html) - Use --subject-prefix="PATCH v2" option to add v2 tag for patchset. - git format-patch --subject-prefix="PATCH v2" -1 +### Steps of submitting patches +------- - Subject examples: - Subject: [PATCH v2 01/27] fork: fix some -Wmissing-prototypes warnings - Subject: [PATCH v3] ext2: improve scalability of bitmap searching +**Step 1** Compile and test your patches. -5. Upstream your kernel patch to kernel community is strongly recommended. - openEuler will sync up with kernel master timely. +**Step 2** Generate patches. -6. Sign your work - the Developer’s Certificate of Origin - As the same of upstream kernel community, you also need to sign your patch. +Your patches should be generated based on the latest openEuler branch using git-format-patch. If your patches are in a patchset, it is better to use the **--cover-letter** option to describe what the patchset does. - See: https://www.kernel.org/doc/html/latest/process/submitting-patches.html +Use **scripts/checkpatch.pl** to ensure that no coding style issue exists. - The sign-off is a simple line at the end of the explanation for the patch, - which certifies that you wrote it or otherwise have the right to pass it - on as an open-source patch. The rules are pretty simple: if you can certify - the below: +In addition, ensure that your patches comply with the unified openEuler patch format described below. - Developer’s Certificate of Origin 1.1 - ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +**Step 3** Send your patches to the openEuler mailing list. - By making a contribution to this project, I certify that: +To do so, run the following command: - (a) The contribution was created in whole or in part by me and I have - the right to submit it under the open source license indicated in - the file; or + `git send-email *.patch -to="kernel(a)openeuler.org" --suppress-cc=all` - (b The contribution is based upon previous work that, to the best of - my knowledge, is covered under an appropriate open source license - and I have the right under that license to submit that work with - modifications, whether created in whole or in part by me, under - the same open source license (unless I am permitted to submit under - a different license), as indicated in the file; or +*NOTE*: Add **--suppress-cc=all** if you use git-send-email; otherwise, the email will be copied to all people in the upstream community and mailing lists. - (c) The contribution was provided directly to me by some other person - who certified (a), (b) or (c) and I have not modified it. +For details about how to send patches using git-send-email, see [https://git-scm.com/docs/git-send-email](https://git-scm.com/docs/git-send-…. - (d) I understand and agree that this project and the contribution are - public and that a record of the contribution (including all personal - information I submit with it, including my sign-off) is maintained - indefinitely and may be redistributed consistent with this project - or the open source license(s) involved. +**Step 4** Mark "v1, v2, v3 ..." in your patch subject if you have multiple versions to send out. - then you just add a line saying: +Use the **--subject-prefix="PATCH v2"** option to add the v2 tag to the patchset. - Signed-off-by: Random J Developer <random(a)developer.example.org> + `git format-patch --subject-prefix="PATCH v2" -1` - using your real name (sorry, no pseudonyms or anonymous contributions.) +Subject examples: -Use unified patch format ------------------------- + Subject: [PATCH v2 01/27] fork: fix some -Wmissing-prototypes warnings + + Subject: [PATCH v3] ext2: improve scalability of bitmap searching + +**Step 5** Upstream your kernel patches to the kernel community (recommended). openEuler will synchronize with the kernel master in a timely manner. + +**Step 6** Sign your work - the Developer’s Certificate of Origin. + + Similar to the upstream kernel community, you also need to sign your patch. + + For details, see [https://www.kernel.org/doc/html/latest/process/submitting-patches.html](htt…. + + The sign-off is a simple line at the end of the explanation of the patch, which certifies that you wrote it or otherwise have the right to pass it on as an open source patch. The rules are pretty simple. You can certify as below: + + Developer’s Certificate of Origin 1.1 + + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + By making a contribution to this project, I certify that: + + (a) The contribution was created in whole or in part by me and I have the right to submit it under the open source license indicated in the file; + + (b) The contribution is based upon previous work that, to the best of my knowledge, is covered under an appropriate open source license and I have the right under that license to submit that work with modifications, whether created in whole or in part by me, under the same open source license (unless I am permitted to submit under a different license), as indicated in the file; + + (c) The contribution was provided directly to me by some other person who certified (a), (b) or (c) and I have not modified it. + + (d) I understand and agree that this project and the contribution are public and that a record of the contribution (including all personal information I submit with it, including my sign-off) is maintained indefinitely and may be redistributed consistent with this project or the open source license(s) involved. + +Then you add a line saying: + +Signed-off-by: Random J Developer <random(a)developer.example.org> + +Use your real name (sorry, no pseudonyms or anonymous contributions). + +### Use the unified patch format +------- Reasons: -1. long term maintainability - openEuler will merge massive patches. If all patches are merged by casual - changelog format without a unified format, the git log will be messy, and - then it's hard to figure out the original patch. +1. Long term maintainability + + openEuler will merge massive patches. If all patches are merged by casual + + changelog formats without a unified format, the git logs will be messy, and + + then it is hard to figure out the original patches. + +2. Kernel upgrade -2. kernel upgrade - We definitely will upgrade our openEuler kernel in someday, using strict - patch management will alleviate the pain to migrate patches during big upgrade. + We definitely will upgrade our openEuler kernel in someday, so strict patch management -3. easy for script parsing - Keyword highlighting is necessary for script parsing. + will alleviate the pain to migrate patches during big upgrades. -Patch format definition ------------------------ +3. Easy for script parsing + + Keyword highlighting is necessary for script parsing. + +### Define the patch format +------- + +[M] stands for "mandatory". + +[O] stands for "option". -[M] stands for "mandatory" -[O] stands for "option" $category can be: bug preparation, bugfix, perf, feature, doc, other... -If category is feature, then we also need to add feature name like below: - category: feature - feature: YYY (the feature name) +If category is feature, we need to add a feature name as below: -If the patch is related to CVE or bugzilla, then we need add the corresponding -tag like below (In general, it should include at least one of the following): - CVE: $cve-id - bugzilla: $bug-id +```cpp +category: feature +feature: YYY (the feature name) +``` -Additional changelog should include at least one of the flollwing: - 1) Why we should apply this patch - 2) What real problem in product does this patch resolved - 3) How could we reproduce this bug or how to test - 4) Other useful information for help to understand this patch or problem +If the patch is related to CVE or bugzilla, we need to add the corresponding tag as below (In general, it should include at least one of the following): -The detail information is very useful for porting patch to another kenrel branch. +```cpp +CVE: $cve-id +bugzilla: $bug-id +``` -Example for mainline patch: +Additional changelog should include at least one of the following: - mainline inclusion [M] - from $mainline-version [M] - commit $id [M] - category: $category [M] - bugzilla: $bug-id [O] - CVE: $cve-id [O] +1. Why we should apply this patch - additional changelog [O] +2. What real problems in the product does this patch resolved + +3. How could we reproduce this bug or how to test + +4. Other useful information for help to understand this patch or problem + +The detailed information is very useful for migrating a patch to another kernel branch. + +Example for mainline patch: - -------------------------------- +```cpp +mainline inclusion [M] +from $mainline-version [M] +commit $id [M] +category: $category [M] +bugzilla: $bug-id [O] +CVE: $cve-id [O] - original changelog +additional changelog [O] - Signed-off-by: $yourname <$yourname(a)huawei.com> [M] +-------------------------------- - ($mainline-version could be mainline-3.5, mainline-3.6, etc...) +original changelog +Signed-off-by: $yourname <$yourname(a)huawei.com> [M] +($mainline-version could be mainline-3.5, mainline-3.6, etc...) +``` -Examples --------- +### Examples +------- +```cpp mainline inclusion from mainline-4.10 commit 0becc0ae5b42828785b589f686725ff5bc3b9b25 category: bugfix bugzilla: 3004 -CVE: NA - -The patch fixes a BUG_ON in the product: injecting single bit ECC error -to memory before system boot use hardware inject tools, which cause a -large amount of CMCI during system booting . +CVE: N/A -[ 1.146580] mce: [Hardware Error]: Machine check events logged -[ 1.152908] ------------[ cut here ]------------ -[ 1.157751] kernel BUG at kernel/timer.c:951! -[ 1.162321] invalid opcode: 0000 [#1] SMP -... +The patch fixes a BUG_ON in the product: Injecting a single bit ECC error to the memory before system boot using hardware inject tools will cause a large amount of CMCI during system booting . +[ 1.146580] mce: [Hardware Error]: Machine check events logged +[ 1.152908] ------------[ cut here ]------------ +[ 1.157751] kernel BUG at kernel/timer.c:951! +[ 1.162321] invalid opcode: 0000 [#1] SMP ------------------------------------------------- @@ -177,50 +191,47 @@ original changelog <original S-O-B> Signed-off-by: Zhang San <zhangsan(a)huawei.com> Tested-by: Li Si <lisi(a)huawei.com> +``` + +### Email client - Thunderbird settings +------- + +If you are a new developer in the kernel community, it is highly recommended that you use the Thunderbird mail client. + +1. Thunderbird Installation + + Obtain the English version of Thunderbird from [http://www.mozilla.org/]( http://www.mozilla.org/) and install it on your system. + + Download URL: https://www.thunderbird.net/en-US/thunderbird/all/ + +2. Settings + + 2.1 Use the plain text format instead of the HTML format. + + Choose **Options > Account Settings > Composition & Addressing**, and do **NOT** select Compose message in HTML format. -Email Client - Thunderbird Settings ------------------------------------ + 2.2 Editor settings -If you are newly developer in the kernel community, it is highly recommended -to use thunderbird mail client. + **Tools > Options> Advanced > Config editor** -1. Thunderbird Installation - Get English version Thunderbird from http://www.mozilla.org/ and install - it on your system。 + \- To bring up the Thunderbird's registry editor, set **mailnews.send_plaintext_flowed** to **false**. - Download url: https://www.thunderbird.net/en-US/thunderbird/all/ + \- Disable HTML Format: Set **mail.identity.id1.compose_html** to **false**. -2. Settings - 2.1 Use plain text format instead of HTML format - Options -> Account Settings -> Composition & Addressing, do *NOT* select - "Compose message in HTML format". + \- Enable UTF-8: Set **prefs.converted-to-utf8** to **true**. - 2.2 Editor Settings - Tools->Options->Advanced->Config editor. + \- View messages in UTF-8: Set **mailnews.view_default_charset** to **UTF-8**. - - To bring up the thunderbird's registry editor, and set: - "mailnews.send_plaintext_flowed" to "false". - - Disable HTML Format: Set "mail.identity.id1.compose_html" to "false". - - Enable UTF8: Set "prefs.converted-to-utf8" to "true". - - View message in UTF-8: Set "mailnews.view_default_charset" to "UTF-8". - - Set mailnews.wraplength to 9999 for avoiding auto-wrap + \- Set **mailnews.wraplength** to **9999** to avoid auto-wrap. -Linux kernel -============ +# Linux kernel +------- -There are several guides for kernel developers and users. These guides can -be rendered in a number of formats, like HTML and PDF. Please read -Documentation/admin-guide/README.rst first. +There are several guides for kernel developers and users, which can be rendered in a number of formats, like HTML and PDF. You can read **Documentation/admin-guide/README.rst** first. -In order to build the documentation, use ``make htmldocs`` or -``make pdfdocs``. The formatted documentation can also be read online at: +In order to build the documentation, use **make htmldocs** or **make pdfdocs**. The formatted documentation can also be read online at: https://www.kernel.org/doc/html/latest/ - https://www.kernel.org/doc/html/latest/ +There are various text files in the Documentation/ subdirectory, several of which use the Restructured Text markup notation. See Documentation/00-INDEX for a list of what is contained in each file. -There are various text files in the Documentation/ subdirectory, -several of them using the Restructured Text markup notation. -See Documentation/00-INDEX for a list of what is contained in each file. +Read the **Documentation/process/changes.rst** file, as it contains the requirements for building and running the kernel, and information about the problems that may be caused by upgrading your kernel. -Please read the Documentation/process/changes.rst file, as it contains the -requirements for building and running the kernel, and information about -the problems which may result by upgrading your kernel. -- 2.22.0

1 0

[PATCH openEuler-1.0-LTS] blk-cgroup: synchronize blkg creation against policy deactivation
by Yang Yingliang 01 Nov '21

01 Nov '21

From: Yu Kuai <yukuai3(a)huawei.com> mainline inclusion from mainline-v5.16 commit 0c9d338c8443b06da8e8d3bfce824c5ea6d3488f category: bugfix bugzilla: 182378 CVE: NA --------------------------- Our test reports a null pointer dereference: [ 168.534653] ================================================================== [ 168.535614] Disabling lock debugging due to kernel taint [ 168.536346] BUG: kernel NULL pointer dereference, address: 0000000000000008 [ 168.537274] #PF: supervisor read access in kernel mode [ 168.537964] #PF: error_code(0x0000) - not-present page [ 168.538667] PGD 0 P4D 0 [ 168.539025] Oops: 0000 [#1] PREEMPT SMP KASAN [ 168.539656] CPU: 13 PID: 759 Comm: bash Tainted: G B 5.15.0-rc2-next-202100 [ 168.540954] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20190727_0738364 [ 168.542736] RIP: 0010:bfq_pd_init+0x88/0x1e0 [ 168.543318] Code: 98 00 00 00 e8 c9 e4 5b ff 4c 8b 65 00 49 8d 7c 24 08 e8 bb e4 5b ff 4d0 [ 168.545803] RSP: 0018:ffff88817095f9c0 EFLAGS: 00010002 [ 168.546497] RAX: 0000000000000001 RBX: ffff888101a1c000 RCX: 0000000000000000 [ 168.547438] RDX: 0000000000000003 RSI: 0000000000000002 RDI: ffff888106553428 [ 168.548402] RBP: ffff888106553400 R08: ffffffff961bcaf4 R09: 0000000000000001 [ 168.549365] R10: ffffffffa2e16c27 R11: fffffbfff45c2d84 R12: 0000000000000000 [ 168.550291] R13: ffff888101a1c098 R14: ffff88810c7a08c8 R15: ffffffffa55541a0 [ 168.551221] FS: 00007fac75227700(0000) GS:ffff88839ba80000(0000) knlGS:0000000000000000 [ 168.552278] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 168.553040] CR2: 0000000000000008 CR3: 0000000165ce7000 CR4: 00000000000006e0 [ 168.554000] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 168.554929] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 168.555888] Call Trace: [ 168.556221] <TASK> [ 168.556510] blkg_create+0x1c0/0x8c0 [ 168.556989] blkg_conf_prep+0x574/0x650 [ 168.557502] ? stack_trace_save+0x99/0xd0 [ 168.558033] ? blkcg_conf_open_bdev+0x1b0/0x1b0 [ 168.558629] tg_set_conf.constprop.0+0xb9/0x280 [ 168.559231] ? kasan_set_track+0x29/0x40 [ 168.559758] ? kasan_set_free_info+0x30/0x60 [ 168.560344] ? tg_set_limit+0xae0/0xae0 [ 168.560853] ? do_sys_openat2+0x33b/0x640 [ 168.561383] ? do_sys_open+0xa2/0x100 [ 168.561877] ? __x64_sys_open+0x4e/0x60 [ 168.562383] ? __kasan_check_write+0x20/0x30 [ 168.562951] ? copyin+0x48/0x70 [ 168.563390] ? _copy_from_iter+0x234/0x9e0 [ 168.563948] tg_set_conf_u64+0x17/0x20 [ 168.564467] cgroup_file_write+0x1ad/0x380 [ 168.565014] ? cgroup_file_poll+0x80/0x80 [ 168.565568] ? __mutex_lock_slowpath+0x30/0x30 [ 168.566165] ? pgd_free+0x100/0x160 [ 168.566649] kernfs_fop_write_iter+0x21d/0x340 [ 168.567246] ? cgroup_file_poll+0x80/0x80 [ 168.567796] new_sync_write+0x29f/0x3c0 [ 168.568314] ? new_sync_read+0x410/0x410 [ 168.568840] ? __handle_mm_fault+0x1c97/0x2d80 [ 168.569425] ? copy_page_range+0x2b10/0x2b10 [ 168.570007] ? _raw_read_lock_bh+0xa0/0xa0 [ 168.570622] vfs_write+0x46e/0x630 [ 168.571091] ksys_write+0xcd/0x1e0 [ 168.571563] ? __x64_sys_read+0x60/0x60 [ 168.572081] ? __kasan_check_write+0x20/0x30 [ 168.572659] ? do_user_addr_fault+0x446/0xff0 [ 168.573264] __x64_sys_write+0x46/0x60 [ 168.573774] do_syscall_64+0x35/0x80 [ 168.574264] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 168.574960] RIP: 0033:0x7fac74915130 [ 168.575456] Code: 73 01 c3 48 8b 0d 58 ed 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 444 [ 168.577969] RSP: 002b:00007ffc3080e288 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 168.578986] RAX: ffffffffffffffda RBX: 0000000000000009 RCX: 00007fac74915130 [ 168.579937] RDX: 0000000000000009 RSI: 000056007669f080 RDI: 0000000000000001 [ 168.580884] RBP: 000056007669f080 R08: 000000000000000a R09: 00007fac75227700 [ 168.581841] R10: 000056007655c8f0 R11: 0000000000000246 R12: 0000000000000009 [ 168.582796] R13: 0000000000000001 R14: 00007fac74be55e0 R15: 00007fac74be08c0 [ 168.583757] </TASK> [ 168.584063] Modules linked in: [ 168.584494] CR2: 0000000000000008 [ 168.584964] ---[ end trace 2475611ad0f77a1a ]--- This is because blkg_alloc() is called from blkg_conf_prep() without holding 'q->queue_lock', and elevator is exited before blkg_create(): thread 1 thread 2 blkg_conf_prep spin_lock_irq(&q->queue_lock); blkg_lookup_check -> return NULL spin_unlock_irq(&q->queue_lock); blkg_alloc blkcg_policy_enabled -> true pd = ->pd_alloc_fn blkg->pd[i] = pd blk_mq_exit_sched bfq_exit_queue blkcg_deactivate_policy spin_lock_irq(&q->queue_lock); __clear_bit(pol->plid, q->blkcg_pols); spin_unlock_irq(&q->queue_lock); q->elevator = NULL; spin_lock_irq(&q->queue_lock); blkg_create if (blkg->pd[i]) ->pd_init_fn -> q->elevator is NULL spin_unlock_irq(&q->queue_lock); Because blkcg_deactivate_policy() requires queue to be frozen, we can grab q_usage_counter to synchoronize blkg_conf_prep() against blkcg_deactivate_policy(). Fixes: e21b7a0b9887 ("block, bfq: add full hierarchical scheduling and cgroups support") Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Acked-by: Tejun Heo <tj(a)kernel.org> Link: https://lore.kernel.org/r/20211020014036.2141723-1-yukuai3@huawei.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Conflict: block/blk-cgroup.c - commit ed6cddefdfd3 ("block: convert the rest of block to bdev_get_queue") is not backported. - commit 015d254cb02b ("blkcg: separate blkcg_conf_get_disk() out of blkg_conf_prep()") is not backported. Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-cgroup.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 7dca3a0144243..d4a8d8fbe1a0e 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -857,6 +857,14 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, q = disk->queue; + /* + * blkcg_deactivate_policy() requires queue to be frozen, we can grab + * q_usage_counter to prevent concurrent with blkcg_deactivate_policy(). + */ + ret = blk_queue_enter(q, 0); + if (ret) + goto fail; + rcu_read_lock(); spin_lock_irq(q->queue_lock); @@ -891,13 +899,13 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, new_blkg = blkg_alloc(pos, q, GFP_KERNEL); if (unlikely(!new_blkg)) { ret = -ENOMEM; - goto fail; + goto fail_exit_queue; } if (radix_tree_preload(GFP_KERNEL)) { blkg_free(new_blkg); ret = -ENOMEM; - goto fail; + goto fail_exit_queue; } rcu_read_lock(); @@ -926,6 +934,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, goto success; } success: + blk_queue_exit(q); ctx->disk = disk; ctx->blkg = blkg; ctx->body = body; @@ -936,6 +945,8 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, fail_unlock: spin_unlock_irq(q->queue_lock); rcu_read_unlock(); +fail_exit_queue: + blk_queue_exit(q); fail: put_disk_and_module(disk); /* -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] isdn: cpai: check ctr->cnr to avoid array index out of bound
by Yang Yingliang 01 Nov '21

01 Nov '21

From: Xiaolong Huang <butterflyhuangxx(a)gmail.com> stable inclusion from linux-4.19.214 commit 7d91adc0ccb060ce564103315189466eb822cc6a CVE: CVE-2021-3896 -------------------------------- commit 1f3e2e97c003f80c4b087092b225c8787ff91e4d upstream. The cmtp_add_connection() would add a cmtp session to a controller and run a kernel thread to process cmtp. __module_get(THIS_MODULE); session->task = kthread_run(cmtp_session, session, "kcmtpd_ctr_%d", session->num); During this process, the kernel thread would call detach_capi_ctr() to detach a register controller. if the controller was not attached yet, detach_capi_ctr() would trigger an array-index-out-bounds bug. [ 46.866069][ T6479] UBSAN: array-index-out-of-bounds in drivers/isdn/capi/kcapi.c:483:21 [ 46.867196][ T6479] index -1 is out of range for type 'capi_ctr *[32]' [ 46.867982][ T6479] CPU: 1 PID: 6479 Comm: kcmtpd_ctr_0 Not tainted 5.15.0-rc2+ #8 [ 46.869002][ T6479] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 [ 46.870107][ T6479] Call Trace: [ 46.870473][ T6479] dump_stack_lvl+0x57/0x7d [ 46.870974][ T6479] ubsan_epilogue+0x5/0x40 [ 46.871458][ T6479] __ubsan_handle_out_of_bounds.cold+0x43/0x48 [ 46.872135][ T6479] detach_capi_ctr+0x64/0xc0 [ 46.872639][ T6479] cmtp_session+0x5c8/0x5d0 [ 46.873131][ T6479] ? __init_waitqueue_head+0x60/0x60 [ 46.873712][ T6479] ? cmtp_add_msgpart+0x120/0x120 [ 46.874256][ T6479] kthread+0x147/0x170 [ 46.874709][ T6479] ? set_kthread_struct+0x40/0x40 [ 46.875248][ T6479] ret_from_fork+0x1f/0x30 [ 46.875773][ T6479] Signed-off-by: Xiaolong Huang <butterflyhuangxx(a)gmail.com> Acked-by: Arnd Bergmann <arnd(a)arndb.de> Link: https://lore.kernel.org/r/20211008065830.305057-1-butterflyhuangxx@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Rui Xiang <rui.xiang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/isdn/capi/kcapi.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c index a4ceb61c5b603..ed9ee2bbf232e 100644 --- a/drivers/isdn/capi/kcapi.c +++ b/drivers/isdn/capi/kcapi.c @@ -565,6 +565,11 @@ int detach_capi_ctr(struct capi_ctr *ctr) ctr_down(ctr, CAPI_CTR_DETACHED); + if (ctr->cnr < 1 || ctr->cnr - 1 >= CAPI_MAXCONTR) { + err = -EINVAL; + goto unlock_out; + } + if (capi_controller[ctr->cnr - 1] != ctr) { err = -EINVAL; goto unlock_out; -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] nbd: Fix use-after-free in pid_show
by Yang Yingliang 01 Nov '21

01 Nov '21

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v5.16 commit 0c98057be9efa32de78dbc4685fc73da9d71faa1 category: bugfix bugzilla: 182939 CVE: NA ----------------------------------------------- I got issue as follows: [ 263.886511] BUG: KASAN: use-after-free in pid_show+0x11f/0x13f [ 263.888359] Read of size 4 at addr ffff8880bf0648c0 by task cat/746 [ 263.890479] CPU: 0 PID: 746 Comm: cat Not tainted 4.19.90-dirty #140 [ 263.893162] Call Trace: [ 263.893509] dump_stack+0x108/0x15f [ 263.893999] print_address_description+0xa5/0x372 [ 263.894641] kasan_report.cold+0x236/0x2a8 [ 263.895696] __asan_report_load4_noabort+0x25/0x30 [ 263.896365] pid_show+0x11f/0x13f [ 263.897422] dev_attr_show+0x48/0x90 [ 263.898361] sysfs_kf_seq_show+0x24d/0x4b0 [ 263.899479] kernfs_seq_show+0x14e/0x1b0 [ 263.900029] seq_read+0x43f/0x1150 [ 263.900499] kernfs_fop_read+0xc7/0x5a0 [ 263.903764] vfs_read+0x113/0x350 [ 263.904231] ksys_read+0x103/0x270 [ 263.905230] __x64_sys_read+0x77/0xc0 [ 263.906284] do_syscall_64+0x106/0x360 [ 263.906797] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Reproduce this issue as follows: 1. nbd-server 8000 /tmp/disk 2. nbd-client localhost 8000 /dev/nbd1 3. cat /sys/block/nbd1/pid Then trigger use-after-free in pid_show. Reason is after do step '2', nbd-client progress is already exit. So it's task_struct already freed. To solve this issue, revert part of 6521d39a64b3's modify and remove useless 'recv_task' member of nbd_device. Fixes: 6521d39a64b3 ("nbd: Remove variable 'pid'") Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Link: https://lore.kernel.org/r/20211020073959.2679255-1-yebin10@huawei.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> conflicts: drivers/block/nbd.c Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/block/nbd.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 45e6ae6add382..2a3794801704a 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -112,11 +112,11 @@ struct nbd_device { struct workqueue_struct *recv_workq; struct list_head list; - struct task_struct *task_recv; struct task_struct *task_setup; struct completion *destroy_complete; unsigned long flags; + pid_t pid; /* pid of nbd-client, if attached */ }; #define NBD_CMD_REQUEUED 1 @@ -211,7 +211,7 @@ static ssize_t pid_show(struct device *dev, struct gendisk *disk = dev_to_disk(dev); struct nbd_device *nbd = (struct nbd_device *)disk->private_data; - return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv)); + return sprintf(buf, "%d\n", nbd->pid); } static const struct device_attribute pid_attr = { @@ -329,7 +329,7 @@ static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize, struct nbd_config *config = nbd->config; config->blksize = blocksize; config->bytesize = blocksize * nr_blocks; - if (nbd->task_recv != NULL) + if (nbd->pid) nbd_size_update(nbd, false); } @@ -1234,7 +1234,7 @@ static void nbd_config_put(struct nbd_device *nbd) if (test_and_clear_bit(NBD_RT_HAS_PID_FILE, &config->runtime_flags)) device_remove_file(disk_to_dev(nbd->disk), &pid_attr); - nbd->task_recv = NULL; + nbd->pid = 0; nbd_clear_sock(nbd); if (config->num_connections) { int i; @@ -1269,7 +1269,7 @@ static int nbd_start_device(struct nbd_device *nbd) int num_connections = config->num_connections; int error = 0, i; - if (nbd->task_recv) + if (nbd->pid) return -EBUSY; if (!config->socks) return -EINVAL; @@ -1288,7 +1288,7 @@ static int nbd_start_device(struct nbd_device *nbd) } blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections); - nbd->task_recv = current; + nbd->pid = task_pid_nr(current); nbd_parse_flags(nbd); @@ -1546,8 +1546,8 @@ static int nbd_dbg_tasks_show(struct seq_file *s, void *unused) { struct nbd_device *nbd = s->private; - if (nbd->task_recv) - seq_printf(s, "recv: %d\n", task_pid_nr(nbd->task_recv)); + if (nbd->pid) + seq_printf(s, "recv: %d\n", nbd->pid); return 0; } @@ -2106,7 +2106,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) mutex_lock(&nbd->config_lock); config = nbd->config; if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) || - !nbd->task_recv) { + !nbd->pid) { dev_err(nbd_to_dev(nbd), "not configured, cannot reconfigure\n"); ret = -EINVAL; -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] iommu/arm-smmu-v3: Add suspend and resume support
by Yang Yingliang 01 Nov '21

01 Nov '21

From: Bixuan Cui <cuibixuan(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4DZ7Q CVE: NA ------------------------------------------------------- Add suspend and resume support for smmuv3. The smmu is stopped when suspending and started when resuming. Signed-off-by: Bixuan Cui <cuibixuan(a)huawei.com> Signed-off-by: Zhou Guanghui <zhouguanghui1(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/iommu/arm-smmu-v3.c | 98 +++++++++++++++++++++++++++++++++---- 1 file changed, 88 insertions(+), 10 deletions(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 560980c54014a..12d503bb3b1e0 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -693,6 +693,7 @@ struct arm_smmu_device { unsigned int mpam_partid_max; unsigned int mpam_pmg_max; + bool bypass; }; struct arm_smmu_stream { @@ -3455,6 +3456,13 @@ static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo; doorbell &= MSI_CFG0_ADDR_MASK; +#ifdef CONFIG_PM_SLEEP + /* Saves the msg (base addr of msi irq) and restores it during resume */ + desc->msg.address_lo = msg->address_lo; + desc->msg.address_hi = msg->address_hi; + desc->msg.data = msg->data; +#endif + writeq_relaxed(doorbell, smmu->base + cfg[0]); writel_relaxed(msg->data, smmu->base + cfg[1]); writel_relaxed(ARM_SMMU_MEMATTR_DEVICE_nGnRE, smmu->base + cfg[2]); @@ -3510,6 +3518,40 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu) devm_add_action(dev, arm_smmu_free_msis, dev); } +#ifdef CONFIG_PM_SLEEP +static void arm_smmu_resume_msis(struct arm_smmu_device *smmu) +{ + struct msi_desc *desc; + struct device *dev = smmu->dev; + + for_each_msi_entry(desc, dev) { + switch (desc->platform.msi_index) { + case EVTQ_MSI_INDEX: + case GERROR_MSI_INDEX: + case PRIQ_MSI_INDEX: { + phys_addr_t *cfg = arm_smmu_msi_cfg[desc->platform.msi_index]; + struct msi_msg *msg = &desc->msg; + phys_addr_t doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo; + + doorbell &= MSI_CFG0_ADDR_MASK; + writeq_relaxed(doorbell, smmu->base + cfg[0]); + writel_relaxed(msg->data, smmu->base + cfg[1]); + writel_relaxed(ARM_SMMU_MEMATTR_DEVICE_nGnRE, + smmu->base + cfg[2]); + break; + } + default: + continue; + + } + } +} +#else +static void arm_smmu_resume_msis(struct arm_smmu_device *smmu) +{ +} +#endif + static void arm_smmu_setup_message_based_spi(struct arm_smmu_device *smmu) { struct irq_desc *desc; @@ -3541,11 +3583,17 @@ static void arm_smmu_setup_message_based_spi(struct arm_smmu_device *smmu) } } -static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu) +static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu, bool resume) { int irq, ret; - arm_smmu_setup_msis(smmu); + if (!resume) + arm_smmu_setup_msis(smmu); + else { + /* The irq doesn't need to be re-requested during resume */ + arm_smmu_resume_msis(smmu); + return; + } /* Request interrupt lines */ irq = smmu->evtq.q.irq; @@ -3587,7 +3635,7 @@ static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu) } } -static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu) +static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu, bool resume) { int ret, irq; u32 irqen_flags = IRQ_CTRL_EVTQ_IRQEN | IRQ_CTRL_GERROR_IRQEN; @@ -3614,7 +3662,7 @@ static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu) if (ret < 0) dev_warn(smmu->dev, "failed to enable combined irq\n"); } else - arm_smmu_setup_unique_irqs(smmu); + arm_smmu_setup_unique_irqs(smmu, resume); if (smmu->features & ARM_SMMU_FEAT_PRI) irqen_flags |= IRQ_CTRL_PRIQ_IRQEN; @@ -3642,7 +3690,7 @@ static int arm_smmu_device_disable(struct arm_smmu_device *smmu) return ret; } -static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) +static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool resume) { int ret; u32 reg, enables; @@ -3747,7 +3795,7 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) } } - ret = arm_smmu_setup_irqs(smmu); + ret = arm_smmu_setup_irqs(smmu, resume); if (ret) { dev_err(smmu->dev, "failed to setup irqs\n"); return ret; @@ -3757,7 +3805,7 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) enables &= ~(CR0_EVTQEN | CR0_PRIQEN); /* Enable the SMMU interface, or ensure bypass */ - if (!bypass || disable_bypass) { + if (!smmu->bypass || disable_bypass) { enables |= CR0_SMMUEN; } else { ret = arm_smmu_update_gbpa(smmu, 0, GBPA_ABORT); @@ -4383,6 +4431,26 @@ int arm_smmu_get_dev_user_mpam_en(struct device *dev, int *user_mpam_en) } EXPORT_SYMBOL(arm_smmu_get_dev_user_mpam_en); +#ifdef CONFIG_PM_SLEEP +static int arm_smmu_suspend(struct device *dev) +{ + /* + * The smmu is powered off and related registers are automatically + * cleared when suspend. No need to do anything. + */ + return 0; +} + +static int arm_smmu_resume(struct device *dev) +{ + struct arm_smmu_device *smmu = dev_get_drvdata(dev); + + arm_smmu_device_reset(smmu, true); + + return 0; +} +#endif + static int arm_smmu_device_probe(struct platform_device *pdev) { int irq, ret; @@ -4390,7 +4458,6 @@ static int arm_smmu_device_probe(struct platform_device *pdev) resource_size_t ioaddr; struct arm_smmu_device *smmu; struct device *dev = &pdev->dev; - bool bypass; smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL); if (!smmu) { @@ -4408,7 +4475,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev) } /* Set bypass mode according to firmware probing result */ - bypass = !!ret; + smmu->bypass = !!ret; /* Base address */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -4454,7 +4521,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev) platform_set_drvdata(pdev, smmu); /* Reset the device */ - ret = arm_smmu_device_reset(smmu, bypass); + ret = arm_smmu_device_reset(smmu, false); if (ret) return ret; @@ -4527,11 +4594,22 @@ static const struct of_device_id arm_smmu_of_match[] = { }; MODULE_DEVICE_TABLE(of, arm_smmu_of_match); +#ifdef CONFIG_PM_SLEEP +static const struct dev_pm_ops arm_smmu_pm_ops = { + .suspend = arm_smmu_suspend, + .resume = arm_smmu_resume, +}; +#define ARM_SMMU_PM_OPS (&arm_smmu_pm_ops) +#else +#define ARM_SMMU_PM_OPS NULL +#endif + static struct platform_driver arm_smmu_driver = { .driver = { .name = "arm-smmu-v3", .of_match_table = of_match_ptr(arm_smmu_of_match), .suppress_bind_attrs = true, + .pm = ARM_SMMU_PM_OPS, }, .probe = arm_smmu_device_probe, .remove = arm_smmu_device_remove, -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/2] scsi: scsi_debug: Fix out-of-bound read in resp_readcap16()
by Yang Yingliang 01 Nov '21

01 Nov '21

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v5.16 commit 4e3ace0051e7e504b55d239daab8789dd89b863c category: bugfix bugzilla: 176010 CVE: NA ----------------------------------------------- The following warning was observed running syzkaller: [ 3813.830724] sg_write: data in/out 65466/242 bytes for SCSI command 0x9e-- guessing data in; [ 3813.830724] program syz-executor not setting count and/or reply_len properly [ 3813.836956] ================================================================== [ 3813.839465] BUG: KASAN: stack-out-of-bounds in sg_copy_buffer+0x157/0x1e0 [ 3813.841773] Read of size 4096 at addr ffff8883cf80f540 by task syz-executor/1549 [ 3813.846612] Call Trace: [ 3813.846995] dump_stack+0x108/0x15f [ 3813.847524] print_address_description+0xa5/0x372 [ 3813.848243] kasan_report.cold+0x236/0x2a8 [ 3813.849439] check_memory_region+0x240/0x270 [ 3813.850094] memcpy+0x30/0x80 [ 3813.850553] sg_copy_buffer+0x157/0x1e0 [ 3813.853032] sg_copy_from_buffer+0x13/0x20 [ 3813.853660] fill_from_dev_buffer+0x135/0x370 [ 3813.854329] resp_readcap16+0x1ac/0x280 [ 3813.856917] schedule_resp+0x41f/0x1630 [ 3813.858203] scsi_debug_queuecommand+0xb32/0x17e0 [ 3813.862699] scsi_dispatch_cmd+0x330/0x950 [ 3813.863329] scsi_request_fn+0xd8e/0x1710 [ 3813.863946] __blk_run_queue+0x10b/0x230 [ 3813.864544] blk_execute_rq_nowait+0x1d8/0x400 [ 3813.865220] sg_common_write.isra.0+0xe61/0x2420 [ 3813.871637] sg_write+0x6c8/0xef0 [ 3813.878853] __vfs_write+0xe4/0x800 [ 3813.883487] vfs_write+0x17b/0x530 [ 3813.884008] ksys_write+0x103/0x270 [ 3813.886268] __x64_sys_write+0x77/0xc0 [ 3813.886841] do_syscall_64+0x106/0x360 [ 3813.887415] entry_SYSCALL_64_after_hwframe+0x44/0xa9 This issue can be reproduced with the following syzkaller log: r0 = openat(0xffffffffffffff9c, &(0x7f0000000040)='./file0\x00', 0x26e1, 0x0) r1 = syz_open_procfs(0xffffffffffffffff, &(0x7f0000000000)='fd/3\x00') open_by_handle_at(r1, &(0x7f00000003c0)=ANY=[@ANYRESHEX], 0x602000) r2 = syz_open_dev$sg(&(0x7f0000000000), 0x0, 0x40782) write$binfmt_aout(r2, &(0x7f0000000340)=ANY=[@ANYBLOB="00000000deff000000000000000000000000000000000000000000000000000047f007af9e107a41ec395f1bded7be24277a1501ff6196a83366f4e6362bc0ff2b247f68a972989b094b2da4fb3607fcf611a22dd04310d28c75039d"], 0x126) In resp_readcap16() we get "int alloc_len" value -1104926854, and then pass the huge arr_len to fill_from_dev_buffer(), but arr is only 32 bytes. This leads to OOB in sg_copy_buffer(). To solve this issue, define alloc_len as u32. Link: https://lore.kernel.org/r/20211013033913.2551004-2-yebin10@huawei.com Acked-by: Douglas Gilbert <dgilbert(a)interlog.com> Signed-off-by: Ye Bin <yebin10(a)huawei.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> conflicts: drivers/scsi/scsi_debug.c Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/scsi_debug.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 082b2695e02f3..d8befc6fbec9c 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -1665,7 +1665,7 @@ static int resp_readcap16(struct scsi_cmnd *scp, { unsigned char *cmd = scp->cmnd; unsigned char arr[SDEBUG_READCAP16_ARR_SZ]; - int alloc_len; + u32 alloc_len; alloc_len = get_unaligned_be32(cmd + 10); /* following just in case virtual_gb changed */ @@ -1694,7 +1694,7 @@ static int resp_readcap16(struct scsi_cmnd *scp, } return fill_from_dev_buffer(scp, arr, - min(alloc_len, SDEBUG_READCAP16_ARR_SZ)); + min_t(u32, alloc_len, SDEBUG_READCAP16_ARR_SZ)); } #define SDEBUG_MAX_TGTPGS_ARR_SZ 1412 -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS V2] README: README optimize
by Laibin Qiu 01 Nov '21

01 Nov '21

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4FS3G?from=project-issue CVE: NA --------------------------- There are some language problems in the README file, and MarkDown fromat syntax is not effective, and it needs to be adjusted. Signed-off-by: suqin <suqin2(a)huawei.com> Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> --- README | 226 ---------------------------------------- README.md | 237 ++++++++++++++++++++++++++++++++++++++++++ scripts/checkpatch.pl | 2 +- 3 files changed, 238 insertions(+), 227 deletions(-) delete mode 100644 README create mode 100644 README.md diff --git a/README b/README deleted file mode 100644 index 46c9ea352..000000000 --- a/README +++ /dev/null @@ -1,226 +0,0 @@ -Contributions to openEuler kernel project -========================================= - -Sign CLA --------- - -Before submitting any Contributions to openEuler, you have to sign CLA. - -See: - https://openeuler.org/zh/cla.html - https://openeuler.org/en/cla.html - -Steps of submitting patches ---------------------------- - -1. Compile and test your patches successfully. -2. Generate patches - Your patches should be based on top of latest openEuler branch, and should - use git-format-patch to generate patches, and if it's a patchset, it's - better to use --cover-letter option to describe what the patchset does. - - Using scripts/checkpatch.pl to make sure there's no coding style issue. - - And make sure your patch follow unified openEuler patch format describe - below. - -3. Send patch to openEuler mailing list - Use this command to send patches to openEuler mailing list: - - git send-email *.patch -to="kernel(a)openeuler.org" --suppress-cc=all - - *NOTE*: that you must add --suppress-cc=all if you use git send-email, - otherwise the email will be cced to the people in upstream community and mailing - lists. - - *See*: How to send patches using git-send-email - https://git-scm.com/docs/git-send-email - -4. Mark "v1, v2, v3 ..." in your patch subject if you have multiple versions - to send out. - - Use --subject-prefix="PATCH v2" option to add v2 tag for patchset. - git format-patch --subject-prefix="PATCH v2" -1 - - Subject examples: - Subject: [PATCH v2 01/27] fork: fix some -Wmissing-prototypes warnings - Subject: [PATCH v3] ext2: improve scalability of bitmap searching - -5. Upstream your kernel patch to kernel community is strongly recommended. - openEuler will sync up with kernel master timely. - -6. Sign your work - the Developer’s Certificate of Origin - As the same of upstream kernel community, you also need to sign your patch. - - See: https://www.kernel.org/doc/html/latest/process/submitting-patches.html - - The sign-off is a simple line at the end of the explanation for the patch, - which certifies that you wrote it or otherwise have the right to pass it - on as an open-source patch. The rules are pretty simple: if you can certify - the below: - - Developer’s Certificate of Origin 1.1 - ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - - By making a contribution to this project, I certify that: - - (a) The contribution was created in whole or in part by me and I have - the right to submit it under the open source license indicated in - the file; or - - (b The contribution is based upon previous work that, to the best of - my knowledge, is covered under an appropriate open source license - and I have the right under that license to submit that work with - modifications, whether created in whole or in part by me, under - the same open source license (unless I am permitted to submit under - a different license), as indicated in the file; or - - (c) The contribution was provided directly to me by some other person - who certified (a), (b) or (c) and I have not modified it. - - (d) I understand and agree that this project and the contribution are - public and that a record of the contribution (including all personal - information I submit with it, including my sign-off) is maintained - indefinitely and may be redistributed consistent with this project - or the open source license(s) involved. - - then you just add a line saying: - - Signed-off-by: Random J Developer <random(a)developer.example.org> - - using your real name (sorry, no pseudonyms or anonymous contributions.) - -Use unified patch format ------------------------- - -Reasons: - -1. long term maintainability - openEuler will merge massive patches. If all patches are merged by casual - changelog format without a unified format, the git log will be messy, and - then it's hard to figure out the original patch. - -2. kernel upgrade - We definitely will upgrade our openEuler kernel in someday, using strict - patch management will alleviate the pain to migrate patches during big upgrade. - -3. easy for script parsing - Keyword highlighting is necessary for script parsing. - -Patch format definition ------------------------ - -[M] stands for "mandatory" -[O] stands for "option" -$category can be: bug preparation, bugfix, perf, feature, doc, other... - -If category is feature, then we also need to add feature name like below: - category: feature - feature: YYY (the feature name) - -If the patch is related to CVE or bugzilla, then we need add the corresponding -tag like below (In general, it should include at least one of the following): - CVE: $cve-id - bugzilla: $bug-id - -Additional changelog should include at least one of the flollwing: - 1) Why we should apply this patch - 2) What real problem in product does this patch resolved - 3) How could we reproduce this bug or how to test - 4) Other useful information for help to understand this patch or problem - -The detail information is very useful for porting patch to another kenrel branch. - -Example for mainline patch: - - mainline inclusion [M] - from $mainline-version [M] - commit $id [M] - category: $category [M] - bugzilla: $bug-id [O] - CVE: $cve-id [O] - - additional changelog [O] - - -------------------------------- - - original changelog - - Signed-off-by: $yourname <$yourname(a)huawei.com> [M] - - ($mainline-version could be mainline-3.5, mainline-3.6, etc...) - -Examples --------- - -mainline inclusion -from mainline-4.10 -commit 0becc0ae5b42828785b589f686725ff5bc3b9b25 -category: bugfix -bugzilla: 3004 -CVE: NA - -The patch fixes a BUG_ON in the product: injecting single bit ECC error -to memory before system boot use hardware inject tools, which cause a -large amount of CMCI during system booting . - -[ 1.146580] mce: [Hardware Error]: Machine check events logged -[ 1.152908] ------------[ cut here ]------------ -[ 1.157751] kernel BUG at kernel/timer.c:951! -[ 1.162321] invalid opcode: 0000 [#1] SMP -... - -------------------------------------------------- - -original changelog - -<original S-O-B> -Signed-off-by: Zhang San <zhangsan(a)huawei.com> -Tested-by: Li Si <lisi(a)huawei.com> - -Email Client - Thunderbird Settings ------------------------------------ - -If you are newly developer in the kernel community, it is highly recommended -to use thunderbird mail client. - -1. Thunderbird Installation - Get English version Thunderbird from http://www.mozilla.org/ and install - it on your system。 - - Download url: https://www.thunderbird.net/en-US/thunderbird/all/ - -2. Settings - 2.1 Use plain text format instead of HTML format - Options -> Account Settings -> Composition & Addressing, do *NOT* select - "Compose message in HTML format". - - 2.2 Editor Settings - Tools->Options->Advanced->Config editor. - - - To bring up the thunderbird's registry editor, and set: - "mailnews.send_plaintext_flowed" to "false". - - Disable HTML Format: Set "mail.identity.id1.compose_html" to "false". - - Enable UTF8: Set "prefs.converted-to-utf8" to "true". - - View message in UTF-8: Set "mailnews.view_default_charset" to "UTF-8". - - Set mailnews.wraplength to 9999 for avoiding auto-wrap - -Linux kernel -============ - -There are several guides for kernel developers and users. These guides can -be rendered in a number of formats, like HTML and PDF. Please read -Documentation/admin-guide/README.rst first. - -In order to build the documentation, use ``make htmldocs`` or -``make pdfdocs``. The formatted documentation can also be read online at: - - https://www.kernel.org/doc/html/latest/ - -There are various text files in the Documentation/ subdirectory, -several of them using the Restructured Text markup notation. -See Documentation/00-INDEX for a list of what is contained in each file. - -Please read the Documentation/process/changes.rst file, as it contains the -requirements for building and running the kernel, and information about -the problems which may result by upgrading your kernel. diff --git a/README.md b/README.md new file mode 100644 index 000000000..3374c4726 --- /dev/null +++ b/README.md @@ -0,0 +1,237 @@ +# How to Contribute +------- + +- [How to Contribute](#How to Contribute) + + \- [Sign the CLA](#Sign the CLA) + + \- [Steps of submitting patches](#Steps of submitting patches) + + \- [Use the unified patch format](#Use the unified patch format) + + \- [Define the patch format](#Define the patch format) + + \- [Examples](#Examples) + + \- [Email client - Thunderbird settings](#Email client - Thunderbird settings) + +- [Linux kernel](#Linux kernel) + +### Sign the CLA + +------- + +Before making any contributions to openEuler, sign the CLA first. + +Address: [https://openeuler.org/en/cla.html](https://openeuler.org/en/cla.html) + +### Steps of submitting patches +------- + +**Step 1** Compile and test your patches. + +**Step 2** Generate patches. + +Your patches should be generated based on the latest openEuler branch using git-format-patch. If your patches are in a patchset, it is better to use the **--cover-letter** option to describe what the patchset does. + +Use **scripts/checkpatch.pl** to ensure that no coding style issue exists. + +In addition, ensure that your patches comply with the unified openEuler patch format described below. + +**Step 3** Send your patches to the openEuler mailing list. + +To do so, run the following command: + + `git send-email *.patch -to="kernel(a)openeuler.org" --suppress-cc=all` + +*NOTE*: Add **--suppress-cc=all** if you use git-send-email; otherwise, the email will be copied to all people in the upstream community and mailing lists. + +For details about how to send patches using git-send-email, see [https://git-scm.com/docs/git-send-email](https://git-scm.com/docs/git-send-…. + +**Step 4** Mark "v1, v2, v3 ..." in your patch subject if you have multiple versions to send out. + +Use the **--subject-prefix="PATCH v2"** option to add the v2 tag to the patchset. + + `git format-patch --subject-prefix="PATCH v2" -1` + +Subject examples: + + Subject: [PATCH v2 01/27] fork: fix some -Wmissing-prototypes warnings + + Subject: [PATCH v3] ext2: improve scalability of bitmap searching + +**Step 5** Upstream your kernel patches to the kernel community (recommended). openEuler will synchronize with the kernel master in a timely manner. + +**Step 6** Sign your work - the Developer’s Certificate of Origin. + + Similar to the upstream kernel community, you also need to sign your patch. + + For details, see [https://www.kernel.org/doc/html/latest/process/submitting-patches.html](htt…. + + The sign-off is a simple line at the end of the explanation of the patch, which certifies that you wrote it or otherwise have the right to pass it on as an open source patch. The rules are pretty simple. You can certify as below: + + Developer’s Certificate of Origin 1.1 + + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + By making a contribution to this project, I certify that: + + (a) The contribution was created in whole or in part by me and I have the right to submit it under the open source license indicated in the file; + + (b) The contribution is based upon previous work that, to the best of my knowledge, is covered under an appropriate open source license and I have the right under that license to submit that work with modifications, whether created in whole or in part by me, under the same open source license (unless I am permitted to submit under a different license), as indicated in the file; + + (c) The contribution was provided directly to me by some other person who certified (a), (b) or (c) and I have not modified it. + + (d) I understand and agree that this project and the contribution are public and that a record of the contribution (including all personal information I submit with it, including my sign-off) is maintained indefinitely and may be redistributed consistent with this project or the open source license(s) involved. + +Then you add a line saying: + +Signed-off-by: Random J Developer <random(a)developer.example.org> + +Use your real name (sorry, no pseudonyms or anonymous contributions). + +### Use the unified patch format +------- + +Reasons: + +1. Long term maintainability + + openEuler will merge massive patches. If all patches are merged by casual + + changelog formats without a unified format, the git logs will be messy, and + + then it is hard to figure out the original patches. + +2. Kernel upgrade + + We definitely will upgrade our openEuler kernel in someday, so strict patch management + + will alleviate the pain to migrate patches during big upgrades. + +3. Easy for script parsing + + Keyword highlighting is necessary for script parsing. + +### Define the patch format +------- + +[M] stands for "mandatory". + +[O] stands for "option". + +$category can be: bug preparation, bugfix, perf, feature, doc, other... + +If category is feature, we need to add a feature name as below: + +```cpp +category: feature +feature: YYY (the feature name) +``` + +If the patch is related to CVE or bugzilla, we need to add the corresponding tag as below (In general, it should include at least one of the following): + +```cpp +CVE: $cve-id +bugzilla: $bug-id +``` + +Additional changelog should include at least one of the following: + +1. Why we should apply this patch + +2. What real problems in the product does this patch resolved + +3. How could we reproduce this bug or how to test + +4. Other useful information for help to understand this patch or problem + +The detailed information is very useful for migrating a patch to another kernel branch. + +Example for mainline patch: + +```cpp +mainline inclusion [M] +from $mainline-version [M] +commit $id [M] +category: $category [M] +bugzilla: $bug-id [O] +CVE: $cve-id [O] + +additional changelog [O] + +-------------------------------- + +original changelog +Signed-off-by: $yourname <$yourname(a)huawei.com> [M] +($mainline-version could be mainline-3.5, mainline-3.6, etc...) +``` + +### Examples +------- + +```cpp +mainline inclusion +from mainline-4.10 +commit 0becc0ae5b42828785b589f686725ff5bc3b9b25 +category: bugfix +bugzilla: 3004 +CVE: N/A + +The patch fixes a BUG_ON in the product: Injecting a single bit ECC error to the memory before system boot using hardware inject tools will cause a large amount of CMCI during system booting . +[ 1.146580] mce: [Hardware Error]: Machine check events logged +[ 1.152908] ------------[ cut here ]------------ +[ 1.157751] kernel BUG at kernel/timer.c:951! +[ 1.162321] invalid opcode: 0000 [#1] SMP + +------------------------------------------------- + +original changelog + +<original S-O-B> +Signed-off-by: Zhang San <zhangsan(a)huawei.com> +Tested-by: Li Si <lisi(a)huawei.com> +``` + +### Email client - Thunderbird settings +------- + +If you are a new developer in the kernel community, it is highly recommended that you use the Thunderbird mail client. + +1. Thunderbird Installation + + Obtain the English version of Thunderbird from [http://www.mozilla.org/]( http://www.mozilla.org/) and install it on your system. + + Download URL: https://www.thunderbird.net/en-US/thunderbird/all/ + +2. Settings + + 2.1 Use the plain text format instead of the HTML format. + + Choose **Options > Account Settings > Composition & Addressing**, and do **NOT** select Compose message in HTML format. + + 2.2 Editor settings + + **Tools > Options> Advanced > Config editor** + + \- To bring up the Thunderbird's registry editor, set **mailnews.send_plaintext_flowed** to **false**. + + \- Disable HTML Format: Set **mail.identity.id1.compose_html** to **false**. + + \- Enable UTF-8: Set **prefs.converted-to-utf8** to **true**. + + \- View messages in UTF-8: Set **mailnews.view_default_charset** to **UTF-8**. + + \- Set **mailnews.wraplength** to **9999** to avoid auto-wrap. + +# Linux kernel +------- + +There are several guides for kernel developers and users, which can be rendered in a number of formats, like HTML and PDF. You can read **Documentation/admin-guide/README.rst** first. + +In order to build the documentation, use **make htmldocs** or **make pdfdocs**. The formatted documentation can also be read online at: https://www.kernel.org/doc/html/latest/ + +There are various text files in the Documentation/ subdirectory, several of which use the Restructured Text markup notation. See Documentation/00-INDEX for a list of what is contained in each file. + +Read the **Documentation/process/changes.rst** file, as it contains the requirements for building and running the kernel, and information about the problems that may be caused by upgrading your kernel. + diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 161b0224d..d9a8ae4da 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -1063,7 +1063,7 @@ sub top_of_kernel_tree { my @tree_check = ( "COPYING", "CREDITS", "Kbuild", "MAINTAINERS", "Makefile", - "README", "Documentation", "arch", "include", "drivers", + "README.md", "Documentation", "arch", "include", "drivers", "fs", "init", "ipc", "kernel", "lib", "scripts", ); -- 2.22.0

1 0

[PATCH openEuler-1.0-LTS] scsi: hisi_sas: unsupported DIX between OS and HBA only for SATA device
by Yang Yingliang 01 Nov '21

01 Nov '21

From: Yang Xingui <yangxingui(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA Signed-off-by: Yang Xingui <yangxingui(a)huawei.com> Reviewed-by: Ouyangdelong <ouyangdelong(a)huawei.com> Reviewed-by: Kangfenglong <kangfenglong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas.h | 10 ++++++++++ drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 7 ++++++- 2 files changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h index 3fd32606ecb00..8e9424e62a150 100644 --- a/drivers/scsi/hisi_sas/hisi_sas.h +++ b/drivers/scsi/hisi_sas/hisi_sas.h @@ -77,6 +77,16 @@ #define HISI_SAS_SATA_PROTOCOL_FPDMA 0x8 #define HISI_SAS_SATA_PROTOCOL_ATAPI 0x10 +#define HISI_SAS_DIF_PROT_MASK (SHOST_DIF_TYPE1_PROTECTION | \ + SHOST_DIF_TYPE2_PROTECTION | \ + SHOST_DIF_TYPE3_PROTECTION) + +#define HISI_SAS_DIX_PROT_MASK (SHOST_DIX_TYPE1_PROTECTION | \ + SHOST_DIX_TYPE2_PROTECTION | \ + SHOST_DIX_TYPE3_PROTECTION) + +#define HISI_SAS_PROT_MASK (HISI_SAS_DIF_PROT_MASK | HISI_SAS_DIX_PROT_MASK) + #define CLEAR_ITCT_TIMEOUT 20 struct hisi_hba; diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 0e4cc16e542d6..9d6e21be35841 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -3357,9 +3357,14 @@ hisi_sas_shost_alloc_pci(struct pci_dev *pdev) hisi_hba->dev = dev; hisi_hba->shost = shost; SHOST_TO_SAS_HA(shost) = &hisi_hba->sha; - hisi_hba->enable_dix_dif = enable_dix_dif; hisi_hba->user_ctl_irq = user_ctl_irq; + if (enable_dix_dif & ~HISI_SAS_PROT_MASK) + dev_err(dev, "unsupported protection mask 0x%x, using default (0x0)\n", + enable_dix_dif); + else + hisi_hba->enable_dix_dif = enable_dix_dif; + timer_setup(&hisi_hba->timer, NULL, 0); if (hisi_sas_get_fw_info(hisi_hba) < 0) -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 01/19] nbd: don't handle response without a corresponding request message
by Yang Yingliang 30 Oct '21

30 Oct '21

From: Yu Kuai <yukuai3(a)huawei.com> mainline inclusion from mainline-next-20211018 commit b5644a3a79bf3be5f1238db1b2f241374b27b0f0 category: bugfix bugzilla: 49890 CVE: NA --------------------------- While handling a response message from server, nbd_read_stat() will try to get request by tag, and then complete the request. However, this is problematic if nbd haven't sent a corresponding request message: t1 t2 submit_bio nbd_queue_rq blk_mq_start_request recv_work nbd_read_stat blk_mq_tag_to_rq blk_mq_complete_request nbd_send_cmd Thus add a new cmd flag 'NBD_CMD_INFLIGHT', it will be set in nbd_send_cmd() and checked in nbd_read_stat(). Noted that this patch can't fix that blk_mq_tag_to_rq() might return a freed request, and this will be fixed in following patches. Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Ming Lei <ming.lei(a)redhat.com> Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Link: https://lore.kernel.org/r/20210916093350.1410403-2-yukuai3@huawei.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/block/nbd.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 6a72c07ce3cba..05153b84d5400 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -120,6 +120,12 @@ struct nbd_device { }; #define NBD_CMD_REQUEUED 1 +/* + * This flag will be set if nbd_queue_rq() succeed, and will be checked and + * cleared in completion. Both setting and clearing of the flag are protected + * by cmd->lock. + */ +#define NBD_CMD_INFLIGHT 2 struct nbd_cmd { struct nbd_device *nbd; @@ -369,6 +375,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, if (!mutex_trylock(&cmd->lock)) return BLK_EH_RESET_TIMER; + __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); if (!refcount_inc_not_zero(&nbd->config_refs)) { cmd->status = BLK_STS_TIMEOUT; mutex_unlock(&cmd->lock); @@ -674,6 +681,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) cmd = blk_mq_rq_to_pdu(req); mutex_lock(&cmd->lock); + if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) { + dev_err(disk_to_dev(nbd->disk), "Suspicious reply %d (status %u flags %lu)", + tag, cmd->status, cmd->flags); + ret = -ENOENT; + goto out; + } if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) { dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n", req, cmd->cmd_cookie, nbd_handle_to_cookie(handle)); @@ -768,6 +781,7 @@ static void nbd_clear_req(struct request *req, void *data, bool reserved) struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); mutex_lock(&cmd->lock); + __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); cmd->status = BLK_STS_IOERR; mutex_unlock(&cmd->lock); @@ -903,7 +917,13 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) * returns EAGAIN can be retried on a different socket. */ ret = nbd_send_cmd(nbd, cmd, index); - if (ret == -EAGAIN) { + /* + * Access to this flag is protected by cmd->lock, thus it's safe to set + * the flag after nbd_send_cmd() succeed to send request to server. + */ + if (!ret) + __set_bit(NBD_CMD_INFLIGHT, &cmd->flags); + else if (ret == -EAGAIN) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); -- 2.25.1

1 18

[PATCH openEuler-1.0-LTS 1/5] numa: Move the management structures for cdm nodes to ddr
by Yang Yingliang 30 Oct '21

30 Oct '21

From: Wang Wensheng <wangwensheng4(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4D63I CVE: NA ------------------------------------------------- The cdm nodes are easiler to raise an ECC error and it may cause the kernel crash if the essential structures went wrong. So move the management structures for hbm nodes to the ddr nodes of the same partion to reduce the probability of kernel crashes. Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/Kconfig | 10 ++++++++ arch/arm64/mm/numa.c | 54 +++++++++++++++++++++++++++++++++++++++- include/linux/nodemask.h | 7 ++++++ mm/sparse.c | 8 +++--- 4 files changed, 75 insertions(+), 4 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 9d49b9524e1d4..2f34aef79179e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1470,6 +1470,16 @@ config ASCEND_SHARE_POOL help This feature allows multiple processes to share virtual memory both in kernel and user level, which is only enabled for ascend platform. + +config ASCEND_CLEAN_CDM + bool "move the management structure for HBM to DDR" + def_bool n + depends on COHERENT_DEVICE + help + The cdm nodes sometimes are easiler to raise an ECC error and it may + cause the kernel crash if the essential structures went wrong. So move + the management structures for hbm nodes to the ddr nodes of the same + partion to reduce the probability of kernel crashes. endif endmenu diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index a9d3ad5ee0cc3..a194bad6fdfcf 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -45,6 +45,57 @@ inline int arch_check_node_cdm(int nid) return node_isset(nid, cdmmask); } +#ifdef CONFIG_ASCEND_CLEAN_CDM +/** + * cdm_node_to_ddr_node - Convert the cdm node to the ddr node of the + * same partion. + * @nid: input node ID + * + * Here is a typical memory topology in usage. + * There are some DDR and HBM in each partion and DDRs present at first, then + * come all the HBMs of the first partion, then HBMs of the second partion, etc. + * + * ------------------------- + * | P0 | P1 | + * ----------- | ----------- + * |node0 DDR| | |node1 DDR| + * |---------- | ----------| + * |node2 HBM| | |node4 HBM| + * |---------- | ----------| + * |node3 HBM| | |node5 HBM| + * ----------- | ----------- + * + * Return: + * This function returns a ddr node which is of the same partion with the input + * node if the input node is a HBM node. + * The input nid is returned if it is a DDR node or if the memory topology of + * the system doesn't apply to the above model. + */ +int __init cdm_node_to_ddr_node(int nid) +{ + nodemask_t ddr_mask; + int nr_ddr, cdm_per_part, fake_nid; + int nr_cdm = nodes_weight(cdmmask); + + if (!nr_cdm || nodes_empty(numa_nodes_parsed)) + return nid; + + if (!node_isset(nid, cdmmask)) + return nid; + + nodes_xor(ddr_mask, cdmmask, numa_nodes_parsed); + nr_ddr = nodes_weight(ddr_mask); + cdm_per_part = nr_cdm / nr_ddr ? : 1; + + fake_nid = (nid - nr_ddr) / cdm_per_part; + fake_nid = !node_isset(fake_nid, cdmmask) ? fake_nid : nid; + + pr_info("nid: %d, fake_nid: %d\n", nid, fake_nid); + + return fake_nid; +} +#endif + static int __init cdm_nodes_setup(char *s) { int nid; @@ -264,11 +315,12 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) u64 nd_pa; void *nd; int tnid; + int fake_nid = cdm_node_to_ddr_node(nid); if (start_pfn >= end_pfn) pr_info("Initmem setup node %d [<memory-less node>]\n", nid); - nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, fake_nid); nd = __va(nd_pa); /* report and initialize */ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 41fb047bdba80..7c0571b95ce4d 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -508,6 +508,12 @@ static inline int node_random(const nodemask_t *mask) #ifdef CONFIG_COHERENT_DEVICE extern int arch_check_node_cdm(int nid); +#ifdef CONFIG_ASCEND_CLEAN_CDM +extern int cdm_node_to_ddr_node(int nid); +#else +static inline int cdm_node_to_ddr_node(int nid) { return nid; } +#endif + static inline nodemask_t system_mem_nodemask(void) { nodemask_t system_mem; @@ -551,6 +557,7 @@ static inline void node_clear_state_cdm(int node) #else static inline int arch_check_node_cdm(int nid) { return 0; } +static inline int cdm_node_to_ddr_node(int nid) { return nid; } static inline nodemask_t system_mem_nodemask(void) { diff --git a/mm/sparse.c b/mm/sparse.c index 62ae3880a9add..f19d2ca250cee 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -458,21 +458,23 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin, { unsigned long pnum, usemap_longs, *usemap; struct page *map; + int fake_nid = cdm_node_to_ddr_node(nid); usemap_longs = BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS); - usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nid), + usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(fake_nid), usemap_size() * map_count); if (!usemap) { pr_err("%s: node[%d] usemap allocation failed", __func__, nid); goto failed; } - sparse_buffer_init(map_count * section_map_size(), nid); + + sparse_buffer_init(map_count * section_map_size(), fake_nid); for_each_present_section_nr(pnum_begin, pnum) { if (pnum >= pnum_end) break; - map = sparse_mem_map_populate(pnum, nid, NULL); + map = sparse_mem_map_populate(pnum, fake_nid, NULL); if (!map) { pr_err("%s: node[%d] memory map backing failed. Some memory will not be available.", __func__, nid); -- 2.25.1

1 4

[PATCH openEuler-1.0-LTS 1/4] perf: hisi: Add support for HiSilicon SoC PMU driver dt probe
by Yang Yingliang 30 Oct '21

30 Oct '21

From: Fang Lijun <fanglijun3(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4D4WR CVE: NA --------------------------- Add support for hisi PMU driver dt probe, Fix its compile error when disable CONFIG_ACPI. Signed-off-by: Fang Lijun <fanglijun3(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/perf/Kconfig | 2 +- drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c | 1 + drivers/perf/hisilicon/hisi_uncore_hha_pmu.c | 23 +++++++++++++++---- drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c | 20 +++++++++++++--- 4 files changed, 38 insertions(+), 8 deletions(-) diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index 92be6a36a128f..d4b9681418f88 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -72,7 +72,7 @@ config ARM_DSU_PMU config HISI_PMU bool "HiSilicon SoC PMU" - depends on ARM64 && ACPI + depends on ARM64 help Support for HiSilicon SoC uncore performance monitoring unit (PMU), such as: L3C, HHA and DDRC. diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c index 090667d487504..3f3f4ab3aacce 100644 --- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c @@ -17,6 +17,7 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/list.h> +#include <linux/of.h> #include <linux/platform_device.h> #include <linux/smp.h> diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c index c35bc248db7e7..4dd4d6b650aed 100644 --- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c @@ -17,6 +17,7 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/list.h> +#include <linux/of.h> #include <linux/platform_device.h> #include <linux/smp.h> @@ -235,20 +236,34 @@ static const struct acpi_device_id hisi_hha_pmu_acpi_match[] = { }; MODULE_DEVICE_TABLE(acpi, hisi_hha_pmu_acpi_match); -static int hisi_hha_pmu_init_data(struct platform_device *pdev, +#ifdef CONFIG_ACPI +static int hisi_hha_pmu_init_index(struct platform_device *pdev, struct hisi_pmu *hha_pmu) { - unsigned long long id; - struct resource *res; acpi_status status; + unsigned long long id; status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), - "_UID", NULL, &id); + "_UID", NULL, &id); if (ACPI_FAILURE(status)) return -EINVAL; hha_pmu->index_id = id; + return 0; +} +#endif + +static int hisi_hha_pmu_init_data(struct platform_device *pdev, + struct hisi_pmu *hha_pmu) +{ + struct resource *res; + +#ifdef CONFIG_ACPI + if (hisi_hha_pmu_init_index(pdev, hha_pmu)) + dev_info(&pdev->dev, "Can not init index id by acpi!\n"); +#endif + /* * Use SCCL_ID and UID to identify the HHA PMU, while * SCCL_ID is in MPIDR[aff2]. diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c index 6ce1d69c63198..4a42926800e50 100644 --- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c @@ -17,6 +17,7 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/list.h> +#include <linux/of.h> #include <linux/platform_device.h> #include <linux/smp.h> @@ -234,20 +235,33 @@ static const struct acpi_device_id hisi_l3c_pmu_acpi_match[] = { }; MODULE_DEVICE_TABLE(acpi, hisi_l3c_pmu_acpi_match); -static int hisi_l3c_pmu_init_data(struct platform_device *pdev, +#ifdef CONFIG_ACPI +static int hisi_l3c_pmu_init_index(struct platform_device *pdev, struct hisi_pmu *l3c_pmu) { unsigned long long id; - struct resource *res; acpi_status status; status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), - "_UID", NULL, &id); + "_UID", NULL, &id); if (ACPI_FAILURE(status)) return -EINVAL; l3c_pmu->index_id = id; + return 0; +} +#endif + +static int hisi_l3c_pmu_init_data(struct platform_device *pdev, + struct hisi_pmu *l3c_pmu) +{ + struct resource *res; + +#ifdef CONFIG_ACPI + if (hisi_l3c_pmu_init_index(pdev, l3c_pmu)) + dev_info(&pdev->dev, "Can not init index id by acpi!"); +#endif /* * Use the SCCL_ID and CCL_ID to identify the L3C PMU, while * SCCL_ID is in MPIDR[aff2] and CCL_ID is in MPIDR[aff1]. -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS 1/7] corelockup: Add support of cpu core hang check
by Yang Yingliang 30 Oct '21

30 Oct '21

From: Dong Kai <dongkai11(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4F3V1 CVE: NA -------------------------------- The softlockup and hardlockup detector only check the status of the cpu which it resides. If certain cpu core suspends, they are both not works. There is no any valid log but the cpu already abnormal and brings a lot of problems of system. To detect this case, we add the corelockup detector. First we use whether cpu core can responds to nmi as a sectence to determine if it is suspended. Then things is simple. Per cpu core maintains it's nmi interrupt counts and detector the nmi_counts of next cpu core. If the nmi interrupt counts not changed any more which means it can't respond nmi normally, we regard it as suspend. To ensure robustness, only consecutive lost nmi more than two times then trigger the warn. The detection chain is as following: cpu0->cpu1->...->cpuN->cpu0 Signed-off-by: Dong Kai <dongkai11(a)huawei.com> Reviewed-by: Kuohai Xu <xukuohai(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/nmi.h | 6 ++ kernel/watchdog.c | 15 +++- kernel/watchdog_hld.c | 165 ++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 8 ++ 4 files changed, 192 insertions(+), 2 deletions(-) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 84f324d65068b..745d66c36e244 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -124,6 +124,12 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } # endif #endif +#ifdef CONFIG_CORELOCKUP_DETECTOR +extern void corelockup_detector_init(void); +extern void corelockup_detector_online_cpu(unsigned int cpu); +extern void corelockup_detector_offline_cpu(unsigned int cpu); +#endif + void watchdog_nmi_stop(void); void watchdog_nmi_start(void); int watchdog_nmi_probe(void); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 0dd17265dcbd4..8b54fd30a597f 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -551,15 +551,23 @@ static void softlockup_start_all(void) int lockup_detector_online_cpu(unsigned int cpu) { - if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) { watchdog_enable(cpu); +#ifdef CONFIG_CORELOCKUP_DETECTOR + corelockup_detector_online_cpu(cpu); +#endif + } return 0; } int lockup_detector_offline_cpu(unsigned int cpu) { - if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) { watchdog_disable(cpu); +#ifdef CONFIG_CORELOCKUP_DETECTOR + corelockup_detector_offline_cpu(cpu); +#endif + } return 0; } @@ -783,4 +791,7 @@ void __init lockup_detector_init(void) if (!watchdog_nmi_probe()) nmi_watchdog_available = true; lockup_detector_setup(); +#ifdef CONFIG_CORELOCKUP_DETECTOR + corelockup_detector_init(); +#endif } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 904a95262fcf6..e965c31958203 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -39,6 +39,163 @@ notrace void __weak arch_touch_nmi_watchdog(void) } EXPORT_SYMBOL(arch_touch_nmi_watchdog); +#ifdef CONFIG_CORELOCKUP_DETECTOR +/* + * The softlockup and hardlockup detector only check the status + * of the cpu which it resides. If certain cpu core suspends, + * they are both not works. There is no any valid log but the + * cpu already abnormal and brings a lot of problems of system. + * To detect this case, we add the corelockup detector. + * + * First we use whether cpu core can responds to nmi as a sectence + * to determine if it is suspended. Then things is simple. Per cpu + * core maintains it's nmi interrupt counts and detector the + * nmi_counts of next cpu core. If the nmi interrupt counts not + * changed any more which means it can't respond nmi normally, we + * regard it as suspend. + * + * To ensure robustness, only consecutive lost nmi more than two + * times then trigger the warn. + * + * The detection chain is as following: + * cpu0->cpu1->...->cpuN->cpu0 + * + * detector_cpu: the target cpu to detector of current cpu + * nmi_interrupts: the nmi counts of current cpu + * nmi_cnt_saved: saved nmi counts of detector_cpu + * nmi_cnt_missed: the nmi consecutive miss counts of detector_cpu + */ +static DEFINE_PER_CPU(unsigned int, detector_cpu); +static DEFINE_PER_CPU(unsigned long, nmi_interrupts); +static DEFINE_PER_CPU(unsigned long, nmi_cnt_saved); +static DEFINE_PER_CPU(unsigned long, nmi_cnt_missed); +static DEFINE_PER_CPU(bool, core_watchdog_warn); + +static void watchdog_nmi_interrupts(void) +{ + __this_cpu_inc(nmi_interrupts); +} + +static void corelockup_status_copy(unsigned int from, unsigned int to) +{ + per_cpu(nmi_cnt_saved, to) = per_cpu(nmi_cnt_saved, from); + per_cpu(nmi_cnt_missed, to) = per_cpu(nmi_cnt_missed, from); + + /* always update detector cpu at the end */ + per_cpu(detector_cpu, to) = per_cpu(detector_cpu, from); +} + +static void corelockup_status_init(unsigned int cpu, unsigned int target) +{ + /* + * initialize saved count to max to avoid unnecessary misjudge + * caused by delay running of nmi on target cpu + */ + per_cpu(nmi_cnt_saved, cpu) = ULONG_MAX; + per_cpu(nmi_cnt_missed, cpu) = 0; + + /* always update detector cpu at the end */ + per_cpu(detector_cpu, cpu) = target; +} + +void __init corelockup_detector_init(void) +{ + unsigned int cpu, next; + + /* detector cpu is set to the next valid logically one */ + for_each_cpu_and(cpu, &watchdog_cpumask, cpu_online_mask) { + next = cpumask_next_and(cpu, &watchdog_cpumask, + cpu_online_mask); + if (next >= nr_cpu_ids) + next = cpumask_first_and(&watchdog_cpumask, + cpu_online_mask); + corelockup_status_init(cpu, next); + } +} + +/* + * Before: first->next + * After: first->[new]->next + */ +void corelockup_detector_online_cpu(unsigned int cpu) +{ + unsigned int first = cpumask_first_and(&watchdog_cpumask, + cpu_online_mask); + + if (WARN_ON(first >= nr_cpu_ids)) + return; + + /* cpu->next */ + corelockup_status_copy(first, cpu); + + /* first->cpu */ + corelockup_status_init(first, cpu); +} + +/* + * Before: prev->cpu->next + * After: prev->next + */ +void corelockup_detector_offline_cpu(unsigned int cpu) +{ + unsigned int prev = nr_cpu_ids; + unsigned int i; + + /* found prev cpu */ + for_each_cpu_and(i, &watchdog_cpumask, cpu_online_mask) { + if (per_cpu(detector_cpu, i) == cpu) { + prev = i; + break; + } + } + + if (WARN_ON(prev == nr_cpu_ids)) + return; + + /* prev->next */ + corelockup_status_copy(cpu, prev); +} + +static bool is_corelockup(unsigned int cpu) +{ + unsigned long nmi_int = per_cpu(nmi_interrupts, cpu); + + /* skip check if only one cpu online */ + if (cpu == smp_processor_id()) + return false; + + if (__this_cpu_read(nmi_cnt_saved) != nmi_int) { + __this_cpu_write(nmi_cnt_saved, nmi_int); + __this_cpu_write(nmi_cnt_missed, 0); + per_cpu(core_watchdog_warn, cpu) = false; + return false; + } + + __this_cpu_inc(nmi_cnt_missed); + if (__this_cpu_read(nmi_cnt_missed) > 2) + return true; + + return false; +} +NOKPROBE_SYMBOL(is_corelockup); + +static void watchdog_corelockup_check(struct pt_regs *regs) +{ + unsigned int cpu = __this_cpu_read(detector_cpu); + + if (is_corelockup(cpu)) { + if (per_cpu(core_watchdog_warn, cpu) == true) + return; + pr_emerg("Watchdog detected core LOCKUP on cpu %d\n", cpu); + + if (hardlockup_panic) + nmi_panic(regs, "Core LOCKUP"); + + per_cpu(core_watchdog_warn, cpu) = true; + } +} +#endif + #ifdef CONFIG_HARDLOCKUP_CHECK_TIMESTAMP static DEFINE_PER_CPU(ktime_t, last_timestamp); static DEFINE_PER_CPU(unsigned int, nmi_rearmed); @@ -106,6 +263,14 @@ static inline bool watchdog_check_timestamp(void) void watchdog_hardlockup_check(struct pt_regs *regs) { +#ifdef CONFIG_CORELOCKUP_DETECTOR + /* Kick nmi interrupts */ + watchdog_nmi_interrupts(); + + /* corelockup check */ + watchdog_corelockup_check(regs); +#endif + if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 0ee305de7d0ec..4a78bacd405bd 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -881,6 +881,14 @@ config HARDLOCKUP_DETECTOR chance to run. The current stack trace is displayed upon detection and the system will stay locked up. +config CORELOCKUP_DETECTOR + bool "Detect Core Lockups" + depends on HARDLOCKUP_DETECTOR && SOFTLOCKUP_DETECTOR + depends on ARM64 + default n + help + Corelockups is used to check whether cpu core hungup or not. + config BOOTPARAM_HARDLOCKUP_PANIC bool "Panic (Reboot) On Hard Lockups" depends on HARDLOCKUP_DETECTOR -- 2.25.1

1 6

[PATCH openEuler-1.0-LTS 01/41] share_pool: Rename sp_stat_idr to sp_proc_stat_idr
by Yang Yingliang 30 Oct '21

30 Oct '21

From: Tang Yizhou <tangyizhou(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4EUVI CVE: NA ------------------------------------------------- We are going to redesign the accounting subsystem of share pool. We need to disambiguate the meaning of sp_stat_idr, as we will introduce an struct which representing per-spg statistics. Signed-off-by: Tang Yizhou <tangyizhou(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Zhou Guanghui <zhouguanghui1(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/share_pool.c | 44 ++++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 22 deletions(-) diff --git a/mm/share_pool.c b/mm/share_pool.c index cd6e137fe6698..c4b8daa47fcfd 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -95,9 +95,9 @@ static DEFINE_IDA(sp_group_id_ida); /*** Statistical and maintenance tools ***/ /* idr of all sp_proc_stats */ -static DEFINE_IDR(sp_stat_idr); -/* rw semaphore for sp_stat_idr and mm->sp_stat_id */ -static DECLARE_RWSEM(sp_stat_sem); +static DEFINE_IDR(sp_proc_stat_idr); +/* rw semaphore for sp_proc_stat_idr */ +static DECLARE_RWSEM(sp_proc_stat_sem); /* for kthread buff_module_guard_work */ static struct sp_proc_stat kthread_stat; @@ -107,7 +107,7 @@ static struct sp_proc_stat *sp_get_proc_stat_locked(int tgid) { struct sp_proc_stat *stat; - stat = idr_find(&sp_stat_idr, tgid); + stat = idr_find(&sp_proc_stat_idr, tgid); /* maybe NULL or not, we always return it */ return stat; @@ -118,7 +118,7 @@ static struct sp_proc_stat *sp_get_proc_stat_ref_locked(int tgid) { struct sp_proc_stat *stat; - stat = idr_find(&sp_stat_idr, tgid); + stat = idr_find(&sp_proc_stat_idr, tgid); if (!stat || !atomic_inc_not_zero(&stat->use_count)) stat = NULL; @@ -137,16 +137,16 @@ static struct sp_proc_stat *sp_init_proc_stat(struct task_struct *tsk, int id, tgid = tsk->tgid; int ret; - down_write(&sp_stat_sem); + down_write(&sp_proc_stat_sem); id = mm->sp_group_master->sp_stat_id; if (id) { /* other threads in the same process may have initialized it */ stat = sp_get_proc_stat_locked(tgid); if (stat) { - up_write(&sp_stat_sem); + up_write(&sp_proc_stat_sem); return stat; } else { - up_write(&sp_stat_sem); + up_write(&sp_proc_stat_sem); /* if enter this branch, that's our mistake */ pr_err_ratelimited("share pool: proc stat invalid id %d\n", id); return ERR_PTR(-EBUSY); @@ -155,7 +155,7 @@ static struct sp_proc_stat *sp_init_proc_stat(struct task_struct *tsk, stat = kzalloc(sizeof(*stat), GFP_KERNEL); if (stat == NULL) { - up_write(&sp_stat_sem); + up_write(&sp_proc_stat_sem); pr_err_ratelimited("share pool: alloc proc stat failed due to lack of memory\n"); return ERR_PTR(-ENOMEM); } @@ -167,16 +167,16 @@ static struct sp_proc_stat *sp_init_proc_stat(struct task_struct *tsk, stat->mm = mm; get_task_comm(stat->comm, tsk); - ret = idr_alloc(&sp_stat_idr, stat, tgid, tgid + 1, GFP_KERNEL); + ret = idr_alloc(&sp_proc_stat_idr, stat, tgid, tgid + 1, GFP_KERNEL); if (ret < 0) { - up_write(&sp_stat_sem); + up_write(&sp_proc_stat_sem); pr_err_ratelimited("share pool: proc stat idr alloc failed %d\n", ret); kfree(stat); return ERR_PTR(ret); } mm->sp_group_master->sp_stat_id = ret; - up_write(&sp_stat_sem); + up_write(&sp_proc_stat_sem); return stat; } @@ -184,9 +184,9 @@ static struct sp_proc_stat *sp_get_proc_stat(int tgid) { struct sp_proc_stat *stat; - down_read(&sp_stat_sem); + down_read(&sp_proc_stat_sem); stat = sp_get_proc_stat_locked(tgid); - up_read(&sp_stat_sem); + up_read(&sp_proc_stat_sem); return stat; } @@ -195,9 +195,9 @@ struct sp_proc_stat *sp_get_proc_stat_ref(int tgid) { struct sp_proc_stat *stat; - down_read(&sp_stat_sem); + down_read(&sp_proc_stat_sem); stat = sp_get_proc_stat_ref_locked(tgid); - up_read(&sp_stat_sem); + up_read(&sp_proc_stat_sem); return stat; } @@ -2850,10 +2850,10 @@ __setup("enable_sp_multi_group_mode", enable_sp_multi_group_mode); static void free_sp_proc_stat(struct sp_proc_stat *stat) { - down_write(&sp_stat_sem); + down_write(&sp_proc_stat_sem); stat->mm->sp_group_master->sp_stat_id = 0; - idr_remove(&sp_stat_idr, stat->tgid); - up_write(&sp_stat_sem); + idr_remove(&sp_proc_stat_idr, stat->tgid); + up_write(&sp_proc_stat_sem); kfree(stat); } @@ -3163,9 +3163,9 @@ static int proc_stat_show(struct seq_file *seq, void *offset) byte2kb(atomic64_read(&kthread_stat.k2u_size))); /* pay attention to potential ABBA deadlock */ - down_read(&sp_stat_sem); - idr_for_each(&sp_stat_idr, idr_proc_stat_cb, seq); - up_read(&sp_stat_sem); + down_read(&sp_proc_stat_sem); + idr_for_each(&sp_proc_stat_idr, idr_proc_stat_cb, seq); + up_read(&sp_proc_stat_sem); return 0; } -- 2.25.1

1 40

[PATCH openEuler-1.0-LTS 1/7] sharepool: Fix ASLR broken
by Yang Yingliang 30 Oct '21

30 Oct '21

From: Wang Wensheng <wangwensheng4(a)huawei.com> ascend inclusion category: bugfix bugzilla: NA CVE: NA --------------------------- To avoid mmap vspace reserved for sharepool, we currently change the high_limit to MMAP_SHARE_POOL_START in arch_get_unmapped_area() and arch_get_unmapped_area_topdown(). In mmap-topdown scene, this make the start address of mmap being always MMAP_SHARE_POOL_START. ASLR got broken. To fix this, this patch set the mm->mmap_base based on MMAP_SHARE_POOL_START instead of STACK_TOP in topdown scene. Fixes: 4bdd5c21793e ("ascend: memory: introduce do_mm_populate and hugetlb_insert_hugepage") Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/mm/mmap.c | 6 +++++- include/linux/share_pool.h | 4 ++-- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index ac89686c4af89..87f29df8126ba 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -28,6 +28,7 @@ #include <linux/io.h> #include <linux/personality.h> #include <linux/random.h> +#include <linux/share_pool.h> #include <asm/cputype.h> @@ -80,7 +81,10 @@ static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) else if (gap > MAX_GAP) gap = MAX_GAP; - return PAGE_ALIGN(STACK_TOP - gap - rnd); + if (sp_is_enabled()) + return ALIGN_DOWN(MMAP_SHARE_POOL_START - rnd, PAGE_SIZE); + else + return PAGE_ALIGN(STACK_TOP - gap - rnd); } /* diff --git a/include/linux/share_pool.h b/include/linux/share_pool.h index 9650f257b3ad7..9557a8be46677 100644 --- a/include/linux/share_pool.h +++ b/include/linux/share_pool.h @@ -130,8 +130,6 @@ struct sp_proc_stat { atomic64_t k2u_size; }; -#ifdef CONFIG_ASCEND_SHARE_POOL - #define MAP_SHARE_POOL 0x100000 #define MMAP_TOP_4G_SIZE 0x100000000UL @@ -148,6 +146,8 @@ struct sp_proc_stat { #define MMAP_SHARE_POOL_START (MMAP_SHARE_POOL_END - MMAP_SHARE_POOL_SIZE) #define MMAP_SHARE_POOL_16G_START (MMAP_SHARE_POOL_END - MMAP_SHARE_POOL_DVPP_SIZE) +#ifdef CONFIG_ASCEND_SHARE_POOL + static inline void sp_init_mm(struct mm_struct *mm) { mm->sp_group = NULL; -- 2.25.1

1 6

[PATCH openEuler-5.10 01/20] perf stat: Add --quiet option
by Zheng Zengkai 30 Oct '21

30 Oct '21

From: Andi Kleen <andi(a)firstfloor.org> mainline inclusion from mainline-5.11 commit 55a4de94c64bacffbcd802c954764e0de2ab217f category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMQA CVE: NA -------------------------------- Add a new --quiet option to 'perf stat'. This is useful with 'perf stat record' to write the data only to the perf.data file, which can lower measurement overhead because the data doesn't need to be formatted. On my 4C desktop: % time ./perf stat record -e $(python -c 'print ",\ ".join(["cycles"]*1000)') -a -I 1000 sleep 5 ... real 0m5.377s user 0m0.238s sys 0m0.452s % time ./perf stat record --quiet -e $(python -c 'print ",\ ".join(["cycles"]*1000)') -a -I 1000 sleep 5 real 0m5.452s user 0m0.183s sys 0m0.423s In this example it cuts the user time by 20%. On systems with more cores the savings are higher. Signed-off-by: Andi Kleen <andi(a)firstfloor.org> Acked-by: Jiri Olsa <jolsa(a)kernel.org> Cc: Alexey Budankov <alexey.budankov(a)linux.intel.com> Link: http://lore.kernel.org/lkml/20201027002737.30942-1-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Signed-off-by: yin-xiujiang <yinxiujiang(a)kylinos.cn> Reviewed-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> Reviewed-by: Yang Jihong <yangjihong1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- tools/perf/Documentation/perf-stat.txt | 4 ++++ tools/perf/builtin-stat.c | 6 +++++- tools/perf/util/stat.h | 1 + 3 files changed, 10 insertions(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 9f9f29025e49..f9bcd95bf352 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -320,6 +320,10 @@ STAT RECORD ----------- Stores stat data into perf data file. +--quiet:: +Don't print output. This is useful with perf stat record below to only +write data to the perf.data file. + -o file:: --output file:: Output file name. diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index b01af171d94f..89e80a3bc9c3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -973,6 +973,8 @@ static void print_counters(struct timespec *ts, int argc, const char **argv) if (STAT_RECORD && perf_stat.data.is_pipe) return; + if (stat_config.quiet) + return; perf_evlist__print_counters(evsel_list, &stat_config, &target, ts, argc, argv); } @@ -1171,6 +1173,8 @@ static struct option stat_options[] = { "threads of same physical core"), OPT_BOOLEAN(0, "summary", &stat_config.summary, "print summary for interval mode"), + OPT_BOOLEAN(0, "quiet", &stat_config.quiet, + "don't print output (useful with record)"), #ifdef HAVE_LIBPFM OPT_CALLBACK(0, "pfm-events", &evsel_list, "event", "libpfm4 event selector. use 'perf list' to list available events", @@ -2132,7 +2136,7 @@ int cmd_stat(int argc, const char **argv) goto out; } - if (!output) { + if (!output && !stat_config.quiet) { struct timespec tm; mode = append_file ? "a" : "w"; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 487010c624be..05adf8165025 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -122,6 +122,7 @@ struct perf_stat_config { bool metric_no_group; bool metric_no_merge; bool stop_read_counter; + bool quiet; FILE *output; unsigned int interval; unsigned int timeout; -- 2.20.1

1 19

[PATCH openEuler-1.0-LTS 001/103] mm/vmalloc: Hugepage vmalloc mappings
by Yang Yingliang 30 Oct '21

30 Oct '21

From: Nicholas Piggin <npiggin(a)gmail.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4EUVI CVE: NA https://lwn.net/ml/linux-kernel/20200825145753.529284-12-npiggin@gmail.com/ Don't distinction between vmalloc and hugepage vmalloc, because there is no size print in alloc_large_system_hash in v4.19. And this patch add page_order in vm_struct, it will break kabi. -------------- Support huge page vmalloc mappings. Config option HAVE_ARCH_HUGE_VMALLOC enables support on architectures that define HAVE_ARCH_HUGE_VMAP and supports PMD sized vmap mappings. vmalloc will attempt to allocate PMD-sized pages if allocating PMD size or larger, and fall back to small pages if that was unsuccessful. Allocations that do not use PAGE_KERNEL prot are not permitted to use huge pages, because not all callers expect this (e.g., module allocations vs strict module rwx). This reduces TLB misses by nearly 30x on a `git diff` workload on a 2-node POWER9 (59,800 -> 2,100) and reduces CPU cycles by 0.54%. This can result in more internal fragmentation and memory overhead for a given allocation, an option nohugevmalloc is added to disable at boot. Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com> Signed-off-by: Rui Xiang <rui.xiang(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Reviewed-by: Zefan Li <lizefan(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/Kconfig | 4 + include/linux/vmalloc.h | 1 + mm/vmalloc.c | 160 +++++++++++++++++++++++++++++++--------- 3 files changed, 130 insertions(+), 35 deletions(-) diff --git a/arch/Kconfig b/arch/Kconfig index e906cbb213444..00f55932ba781 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -559,6 +559,10 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD config HAVE_ARCH_HUGE_VMAP bool +config HAVE_ARCH_HUGE_VMALLOC + depends on HAVE_ARCH_HUGE_VMAP + bool + config HAVE_ARCH_SOFT_DIRTY bool diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 496ac80046c01..07b4b1141ed8a 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -39,6 +39,7 @@ struct vm_struct { unsigned long size; unsigned long flags; struct page **pages; + unsigned int page_order; unsigned int nr_pages; phys_addr_t phys_addr; const void *caller; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index fc6394184a1ba..e76b806a6c003 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -41,6 +41,19 @@ #include "internal.h" +#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC +static bool __ro_after_init vmap_allow_huge = true; + +static int __init set_nohugevmalloc(char *str) +{ + vmap_allow_huge = false; + return 0; +} +early_param("nohugevmalloc", set_nohugevmalloc); +#else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ +static const bool vmap_allow_huge = false; +#endif /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ + struct vfree_deferred { struct llist_head list; struct work_struct wq; @@ -410,6 +423,61 @@ static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr, return 0; } +static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end, + pgprot_t prot, struct page **pages) +{ + pgd_t *pgd; + unsigned long next; + int err = 0; + int nr = 0; + + BUG_ON(addr >= end); + pgd = pgd_offset_k(addr); + do { + next = pgd_addr_end(addr, end); + err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr); + if (err) + return err; + } while (pgd++, addr = next, addr != end); + + return 0; +} + +static int vmap_pages_range_noflush(unsigned long addr, unsigned long end, + pgprot_t prot, struct page **pages, unsigned int page_shift) +{ + unsigned int i, nr = (end - addr) >> PAGE_SHIFT; + + WARN_ON(page_shift < PAGE_SHIFT); + + if (page_shift == PAGE_SHIFT) + return vmap_small_pages_range_noflush(addr, end, prot, pages); + + for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) { + int err; + + err = vmap_range_noflush(addr, addr + (1UL << page_shift), + __pa(page_address(pages[i])), prot, + page_shift); + if (err) + return err; + + addr += 1UL << page_shift; + } + + return 0; +} + +static int vmap_pages_range(unsigned long addr, unsigned long end, + pgprot_t prot, struct page **pages, unsigned int page_shift) +{ + int err; + + err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift); + flush_cache_vmap(addr, end); + return err; +} + /** * map_kernel_range_noflush - map kernel VM area with the specified pages * @addr: start of the VM area to map @@ -431,22 +499,7 @@ static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr, int map_kernel_range_noflush(unsigned long addr, unsigned long size, pgprot_t prot, struct page **pages) { - unsigned long end = addr + size; - unsigned long next; - pgd_t *pgd; - int err = 0; - int nr = 0; - - BUG_ON(addr >= end); - pgd = pgd_offset_k(addr); - do { - next = pgd_addr_end(addr, end); - err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr); - if (err) - return err; - } while (pgd++, addr = next, addr != end); - - return 0; + return vmap_pages_range_noflush(addr, addr + size, prot, pages, PAGE_SHIFT); } int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot, @@ -2270,11 +2323,11 @@ static void __vunmap(const void *addr, int deallocate_pages) if (deallocate_pages) { int i; - for (i = 0; i < area->nr_pages; i++) { + for (i = 0; i < area->nr_pages; i += 1U << area->page_order) { struct page *page = area->pages[i]; BUG_ON(!page); - __free_pages(page, 0); + __free_pages(page, area->page_order); } kvfree(area->pages); @@ -2403,9 +2456,12 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, pgprot_t prot, int node, const void *caller); static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, - pgprot_t prot, int node) + pgprot_t prot, unsigned int page_shift, int node) { struct page **pages; + unsigned long addr = (unsigned long)area->addr; + unsigned long size = get_vm_area_size(area); + unsigned int page_order = page_shift - PAGE_SHIFT; unsigned int nr_pages; unsigned long array_size; unsigned int i; @@ -2415,7 +2471,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, 0 : __GFP_HIGHMEM; - nr_pages = get_vm_area_size(area) >> PAGE_SHIFT; + nr_pages = size >> PAGE_SHIFT; array_size = (unsigned long)nr_pages * sizeof(struct page *); /* Please note that the recursion is strictly bounded. */ @@ -2434,27 +2490,27 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, area->pages = pages; area->nr_pages = nr_pages; + area->page_order = page_order; - for (i = 0; i < area->nr_pages; i++) { + for (i = 0; i < area->nr_pages; i += 1U << page_order) { struct page *page; + int p; - if (node == NUMA_NO_NODE) - page = alloc_page(alloc_mask|highmem_mask); - else - page = alloc_pages_node(node, alloc_mask|highmem_mask, 0); - + page = alloc_pages_node(node, alloc_mask|highmem_mask, page_order); if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vunmap() */ area->nr_pages = i; goto fail; } - area->pages[i] = page; + + for (p = 0; p < (1U << page_order); p++) + area->pages[i + p] = page + p; + if (gfpflags_allow_blocking(gfp_mask|highmem_mask)) cond_resched(); } - if (map_kernel_range((unsigned long)area->addr, get_vm_area_size(area), - prot, pages) < 0) + if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0) goto fail; return area->addr; @@ -2462,7 +2518,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, fail: warn_alloc(gfp_mask, NULL, "vmalloc: allocation failure, allocated %ld of %ld bytes", - (area->nr_pages*PAGE_SIZE), area->size); + (area->nr_pages*PAGE_SIZE), size); vfree(area->addr); return NULL; } @@ -2491,19 +2547,42 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, struct vm_struct *area; void *addr; unsigned long real_size = size; + unsigned long real_align = align; + unsigned int shift = PAGE_SHIFT; - size = PAGE_ALIGN(size); if (!size || (size >> PAGE_SHIFT) > totalram_pages) goto fail; + if (vmap_allow_huge && (pgprot_val(prot) == pgprot_val(PAGE_KERNEL))) { + unsigned long size_per_node; + + /* + * Try huge pages. Only try for PAGE_KERNEL allocations, + * others like modules don't yet expect huge pages in + * their allocations due to apply_to_page_range not + * supporting them. + */ + + size_per_node = size; + if (node == NUMA_NO_NODE) + size_per_node /= num_online_nodes(); + if (size_per_node >= PMD_SIZE) { + shift = PMD_SHIFT; + align = max(real_align, 1UL << shift); + size = ALIGN(real_size, 1UL << shift); + } + } + +again: + size = PAGE_ALIGN(size); area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED | vm_flags, start, end, node, gfp_mask, caller); if (!area) goto fail; - addr = __vmalloc_area_node(area, gfp_mask, prot, node); + addr = __vmalloc_area_node(area, gfp_mask, prot, shift, node); if (!addr) - return NULL; + goto fail; /* * First make sure the mappings are removed from all page-tables @@ -2523,8 +2602,19 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, return addr; fail: - warn_alloc(gfp_mask, NULL, + if (shift > PAGE_SHIFT) { + free_vm_area(area); + shift = PAGE_SHIFT; + align = real_align; + size = real_size; + goto again; + } + + if (!area) { + /* Warn for area allocation, page allocations already warn */ + warn_alloc(gfp_mask, NULL, "vmalloc: allocation failure: %lu bytes", real_size); + } return NULL; } @@ -3503,7 +3593,7 @@ static int s_show(struct seq_file *m, void *p) seq_printf(m, " %pS", v->caller); if (v->nr_pages) - seq_printf(m, " pages=%d", v->nr_pages); + seq_printf(m, " pages=%d order=%d", v->nr_pages, v->page_order); if (v->phys_addr) seq_printf(m, " phys=%pa", &v->phys_addr); -- 2.25.1

1 102

[PATCH openEuler-1.0-LTS 01/26] mm: add do_vm_mmap
by Yang Yingliang 29 Oct '21

29 Oct '21

From: Fang Lijun <fanglijun3(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4D63I CVE: NA ------------------------------------------------- An interface do_vm_mmap is added to support the allocation in the address spaces of other processes. Signed-off-by: Fang Lijun <fanglijun3(a)huawei.com> Signed-off-by: Zhou Guanghui <zhouguanghui1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/mm.h | 3 +++ mm/mmap.c | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index 75d94ea5d1c20..58fe28dd959b9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2436,6 +2436,9 @@ static inline void mm_populate(unsigned long addr, unsigned long len) {} extern int __must_check vm_brk(unsigned long, unsigned long); extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); +extern unsigned long do_vm_mmap(struct mm_struct *mm, unsigned long addr, + unsigned long len, unsigned long prot, + unsigned long flag, unsigned long pgoff); extern unsigned long __must_check vm_mmap(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/mm/mmap.c b/mm/mmap.c index 80779bbb1c048..f7f1fd3b5fa39 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3094,6 +3094,40 @@ int vm_munmap(unsigned long start, size_t len) } EXPORT_SYMBOL(vm_munmap); +/* + * Must acquire an additional reference to the mm struct to prevent the + * mm struct of other process from being released. + * + * This interface is applicable only to kernel thread scenarios. + */ +unsigned long do_vm_mmap(struct mm_struct *mm, unsigned long addr, + unsigned long len, unsigned long prot, + unsigned long flag, unsigned long pgoff) +{ + unsigned long ret; + unsigned long populate; + LIST_HEAD(uf); + + if (mm == NULL || current->mm) + return -EINVAL; + + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + + current->mm = mm; + ret = do_mmap_pgoff(0, addr, len, prot, flag, pgoff, + &populate, &uf); + + current->mm = NULL; + up_write(&mm->mmap_sem); + userfaultfd_unmap_complete(mm, &uf); + if (populate) + mm_populate(ret, populate); + + return ret; +} +EXPORT_SYMBOL(do_vm_mmap); + SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { profile_munmap(addr); -- 2.25.1

1 25

Re: [PATCH openEuler-21.03] vfio-ccw: Reset FSM state to IDLE inside FSM
by Wangshaobo (bobo) 29 Oct '21

29 Oct '21

Reviewed-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> 在 2021/10/28 22:42, Chen Silong 写道: > From: Eric Farman <farman(a)linux.ibm.com> > > stable inclusion > from stable-v5.10.44 > commit cad3dc73c0645d00adfe96cebc8d950897cc1227 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=453 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 6c02ac4c9211edabe17bda437ac97e578756f31b ] > > When an I/O request is made, the fsm_io_request() routine > moves the FSM state from IDLE to CP_PROCESSING, and then > fsm_io_helper() moves it to CP_PENDING if the START SUBCHANNEL > received a cc0. Yet, the error case to go from CP_PROCESSING > back to IDLE is done after the FSM call returns. > > Let's move this up into the FSM proper, to provide some > better symmetry when unwinding in this case. > > Signed-off-by: Eric Farman <farman(a)linux.ibm.com> > Reviewed-by: Cornelia Huck <cohuck(a)redhat.com> > Acked-by: Matthew Rosato <mjrosato(a)linux.ibm.com> > Message-Id: <20210511195631.3995081-3-farman(a)linux.ibm.com> > Signed-off-by: Cornelia Huck <cohuck(a)redhat.com> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: Chen Silong <2019117735(a)my.swjtu.edu.cn> > --- > drivers/s390/cio/vfio_ccw_fsm.c | 1 + > drivers/s390/cio/vfio_ccw_ops.c | 2 -- > 2 files changed, 1 insertion(+), 2 deletions(-) > > diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c > index 23e61aa638e4..e435a9cd92da 100644 > --- a/drivers/s390/cio/vfio_ccw_fsm.c > +++ b/drivers/s390/cio/vfio_ccw_fsm.c > @@ -318,6 +318,7 @@ static void fsm_io_request(struct vfio_ccw_private *private, > } > > err_out: > + private->state = VFIO_CCW_STATE_IDLE; > trace_vfio_ccw_fsm_io_request(scsw->cmd.fctl, schid, > io_region->ret_code, errstr); > } > diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c > index 1ad5f7018ec2..2280f51dd679 100644 > --- a/drivers/s390/cio/vfio_ccw_ops.c > +++ b/drivers/s390/cio/vfio_ccw_ops.c > @@ -276,8 +276,6 @@ static ssize_t vfio_ccw_mdev_write_io_region(struct vfio_ccw_private *private, > } > > vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ); > - if (region->ret_code != 0) > - private->state = VFIO_CCW_STATE_IDLE; > ret = (region->ret_code != 0) ? region->ret_code : count; > > out_unlock:

1 0

[PATCH openEuler-1.0-LTS V3 0/6] Fix the problem that the number of tcp timeout retransmissions is lost
by Laibin Qiu 29 Oct '21

29 Oct '21

issue: https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue Eric Dumazet (4): tcp: switch tcp and sch_fq to new earliest departure time model net_sched: sch_fq: ensure maxrate fq parameter applies to EDT flows tcp: address problems caused by EDT misshaps tcp: adjust rto_base in retransmits_timed_out() Yuchung Cheng (2): tcp: always set retrans_stamp on recovery tcp: create a helper to model exponential backoff net/ipv4/tcp_bbr.c | 7 +++-- net/ipv4/tcp_input.c | 17 +++++++----- net/ipv4/tcp_output.c | 31 +++++++++++++++------ net/ipv4/tcp_timer.c | 64 ++++++++++++++++++++----------------------- net/sched/sch_fq.c | 46 ++++++++++++++++++------------- 5 files changed, 93 insertions(+), 72 deletions(-) -- 2.22.0

1 6

[PATCH openEuler-1.0-LTS V2 0/6] Fix the problem that the
by Laibin Qiu 29 Oct '21

29 Oct '21

issue: https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue Eric Dumazet (4): tcp: switch tcp and sch_fq to new earliest departure time model net_sched: sch_fq: ensure maxrate fq parameter applies to EDT flows tcp: address problems caused by EDT misshaps tcp: adjust rto_base in retransmits_timed_out() Yuchung Cheng (2): tcp: always set retrans_stamp on recovery tcp: create a helper to model exponential backoff net/ipv4/tcp_bbr.c | 7 +++-- net/ipv4/tcp_input.c | 17 +++++++----- net/ipv4/tcp_output.c | 31 +++++++++++++++------ net/ipv4/tcp_timer.c | 64 ++++++++++++++++++++----------------------- net/sched/sch_fq.c | 46 ++++++++++++++++++------------- 5 files changed, 93 insertions(+), 72 deletions(-) -- 2.22.0

1 6

[PATCH openEuler-1.0-LTS] README: README optimize
by Laibin Qiu 29 Oct '21

29 Oct '21

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4FS3G?from=project-issue CVE: NA --------------------------- There are some language problems in the README file, and MarkDown fromat syntax is not effective, and it needs to be adjusted. Signed-off-by: suqin <suqin2(a)huawei.com> Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> --- README | 226 --------------------------------------------------- README.md | 237 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 237 insertions(+), 226 deletions(-) delete mode 100644 README create mode 100644 README.md diff --git a/README b/README deleted file mode 100644 index 46c9ea352..000000000 --- a/README +++ /dev/null @@ -1,226 +0,0 @@ -Contributions to openEuler kernel project -========================================= - -Sign CLA --------- - -Before submitting any Contributions to openEuler, you have to sign CLA. - -See: - https://openeuler.org/zh/cla.html - https://openeuler.org/en/cla.html - -Steps of submitting patches ---------------------------- - -1. Compile and test your patches successfully. -2. Generate patches - Your patches should be based on top of latest openEuler branch, and should - use git-format-patch to generate patches, and if it's a patchset, it's - better to use --cover-letter option to describe what the patchset does. - - Using scripts/checkpatch.pl to make sure there's no coding style issue. - - And make sure your patch follow unified openEuler patch format describe - below. - -3. Send patch to openEuler mailing list - Use this command to send patches to openEuler mailing list: - - git send-email *.patch -to="kernel(a)openeuler.org" --suppress-cc=all - - *NOTE*: that you must add --suppress-cc=all if you use git send-email, - otherwise the email will be cced to the people in upstream community and mailing - lists. - - *See*: How to send patches using git-send-email - https://git-scm.com/docs/git-send-email - -4. Mark "v1, v2, v3 ..." in your patch subject if you have multiple versions - to send out. - - Use --subject-prefix="PATCH v2" option to add v2 tag for patchset. - git format-patch --subject-prefix="PATCH v2" -1 - - Subject examples: - Subject: [PATCH v2 01/27] fork: fix some -Wmissing-prototypes warnings - Subject: [PATCH v3] ext2: improve scalability of bitmap searching - -5. Upstream your kernel patch to kernel community is strongly recommended. - openEuler will sync up with kernel master timely. - -6. Sign your work - the Developer’s Certificate of Origin - As the same of upstream kernel community, you also need to sign your patch. - - See: https://www.kernel.org/doc/html/latest/process/submitting-patches.html - - The sign-off is a simple line at the end of the explanation for the patch, - which certifies that you wrote it or otherwise have the right to pass it - on as an open-source patch. The rules are pretty simple: if you can certify - the below: - - Developer’s Certificate of Origin 1.1 - ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - - By making a contribution to this project, I certify that: - - (a) The contribution was created in whole or in part by me and I have - the right to submit it under the open source license indicated in - the file; or - - (b The contribution is based upon previous work that, to the best of - my knowledge, is covered under an appropriate open source license - and I have the right under that license to submit that work with - modifications, whether created in whole or in part by me, under - the same open source license (unless I am permitted to submit under - a different license), as indicated in the file; or - - (c) The contribution was provided directly to me by some other person - who certified (a), (b) or (c) and I have not modified it. - - (d) I understand and agree that this project and the contribution are - public and that a record of the contribution (including all personal - information I submit with it, including my sign-off) is maintained - indefinitely and may be redistributed consistent with this project - or the open source license(s) involved. - - then you just add a line saying: - - Signed-off-by: Random J Developer <random(a)developer.example.org> - - using your real name (sorry, no pseudonyms or anonymous contributions.) - -Use unified patch format ------------------------- - -Reasons: - -1. long term maintainability - openEuler will merge massive patches. If all patches are merged by casual - changelog format without a unified format, the git log will be messy, and - then it's hard to figure out the original patch. - -2. kernel upgrade - We definitely will upgrade our openEuler kernel in someday, using strict - patch management will alleviate the pain to migrate patches during big upgrade. - -3. easy for script parsing - Keyword highlighting is necessary for script parsing. - -Patch format definition ------------------------ - -[M] stands for "mandatory" -[O] stands for "option" -$category can be: bug preparation, bugfix, perf, feature, doc, other... - -If category is feature, then we also need to add feature name like below: - category: feature - feature: YYY (the feature name) - -If the patch is related to CVE or bugzilla, then we need add the corresponding -tag like below (In general, it should include at least one of the following): - CVE: $cve-id - bugzilla: $bug-id - -Additional changelog should include at least one of the flollwing: - 1) Why we should apply this patch - 2) What real problem in product does this patch resolved - 3) How could we reproduce this bug or how to test - 4) Other useful information for help to understand this patch or problem - -The detail information is very useful for porting patch to another kenrel branch. - -Example for mainline patch: - - mainline inclusion [M] - from $mainline-version [M] - commit $id [M] - category: $category [M] - bugzilla: $bug-id [O] - CVE: $cve-id [O] - - additional changelog [O] - - -------------------------------- - - original changelog - - Signed-off-by: $yourname <$yourname(a)huawei.com> [M] - - ($mainline-version could be mainline-3.5, mainline-3.6, etc...) - -Examples --------- - -mainline inclusion -from mainline-4.10 -commit 0becc0ae5b42828785b589f686725ff5bc3b9b25 -category: bugfix -bugzilla: 3004 -CVE: NA - -The patch fixes a BUG_ON in the product: injecting single bit ECC error -to memory before system boot use hardware inject tools, which cause a -large amount of CMCI during system booting . - -[ 1.146580] mce: [Hardware Error]: Machine check events logged -[ 1.152908] ------------[ cut here ]------------ -[ 1.157751] kernel BUG at kernel/timer.c:951! -[ 1.162321] invalid opcode: 0000 [#1] SMP -... - -------------------------------------------------- - -original changelog - -<original S-O-B> -Signed-off-by: Zhang San <zhangsan(a)huawei.com> -Tested-by: Li Si <lisi(a)huawei.com> - -Email Client - Thunderbird Settings ------------------------------------ - -If you are newly developer in the kernel community, it is highly recommended -to use thunderbird mail client. - -1. Thunderbird Installation - Get English version Thunderbird from http://www.mozilla.org/ and install - it on your system。 - - Download url: https://www.thunderbird.net/en-US/thunderbird/all/ - -2. Settings - 2.1 Use plain text format instead of HTML format - Options -> Account Settings -> Composition & Addressing, do *NOT* select - "Compose message in HTML format". - - 2.2 Editor Settings - Tools->Options->Advanced->Config editor. - - - To bring up the thunderbird's registry editor, and set: - "mailnews.send_plaintext_flowed" to "false". - - Disable HTML Format: Set "mail.identity.id1.compose_html" to "false". - - Enable UTF8: Set "prefs.converted-to-utf8" to "true". - - View message in UTF-8: Set "mailnews.view_default_charset" to "UTF-8". - - Set mailnews.wraplength to 9999 for avoiding auto-wrap - -Linux kernel -============ - -There are several guides for kernel developers and users. These guides can -be rendered in a number of formats, like HTML and PDF. Please read -Documentation/admin-guide/README.rst first. - -In order to build the documentation, use ``make htmldocs`` or -``make pdfdocs``. The formatted documentation can also be read online at: - - https://www.kernel.org/doc/html/latest/ - -There are various text files in the Documentation/ subdirectory, -several of them using the Restructured Text markup notation. -See Documentation/00-INDEX for a list of what is contained in each file. - -Please read the Documentation/process/changes.rst file, as it contains the -requirements for building and running the kernel, and information about -the problems which may result by upgrading your kernel. diff --git a/README.md b/README.md new file mode 100644 index 000000000..20832fd85 --- /dev/null +++ b/README.md @@ -0,0 +1,237 @@ +# How to Contribute +------- + +- [How to Contribute](#How to Contribute) + + \- [Sign the CLA](#Sign the CLA) + + \- [Steps of submitting patches](#Steps of submitting patches) + + \- [Use the unified patch format](#Use the unified patch format) + + \- [Define the patch format](#Define the patch format) + + \- [Examples](#Examples) + + \- [Email client - Thunderbird settings](#Email client - Thunderbird settings) + +- [Linux kernel](#Linux kernel) + +### Sign the CLA + +------- + +Before making any contributions to openEuler, sign the CLA first. + +Address: [https://openeuler.org/en/cla.html](https://openeuler.org/en/cla.html) + +### Steps of submitting patches +------- + +**Step 1** Compile and test your patches. + +**Step 2** Generate patches. + +Your patches should be generated based on the latest openEuler branch using git-format-patch. If your patches are in a patchset, it is better to use the **--cover-letter** option to describe what the patchset does. + +Use **scripts/checkpatch.pl** to ensure that no coding style issue exists. + +In addition, ensure that your patches comply with the unified openEuler patch format described below. + +**Step 3** Send your patches to the openEuler mailing list. + +To do so, run the following command: + + `git send-email *.patch -to="kernel(a)openeuler.org" --suppress-cc=all` + +*NOTE*: Add **--suppress-cc=all** if you use git-send-email; otherwise, the email will be copied to all people in the upstream community and mailing lists. + +For details about how to send patches using git-send-email, see [https://git-scm.com/docs/git-send-email](https://git-scm.com/docs/git-send-…. + +**Step 4** Mark "v1, v2, v3 ..." in your patch subject if you have multiple versions to send out. + +Use the **--subject-prefix="PATCH v2"** option to add the v2 tag to the patchset. + + `git format-patch --subject-prefix="PATCH v2" -1` + +Subject examples: + + Subject: [PATCH v2 01/27] fork: fix some -Wmissing-prototypes warnings + + Subject: [PATCH v3] ext2: improve scalability of bitmap searching + +**Step 5** Upstream your kernel patches to the kernel community (recommended). openEuler will synchronize with the kernel master in a timely manner. + +**Step 6** Sign your work - the Developer’s Certificate of Origin. + + Similar to the upstream kernel community, you also need to sign your patch. + + For details, see [https://www.kernel.org/doc/html/latest/process/submitting-patches.html](htt…. + + The sign-off is a simple line at the end of the explanation of the patch, which certifies that you wrote it or otherwise have the right to pass it on as an open source patch. The rules are pretty simple. You can certify as below: + + Developer’s Certificate of Origin 1.1 + + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + By making a contribution to this project, I certify that: + + (a) The contribution was created in whole or in part by me and I have the right to submit it under the open source license indicated in the file; + + (b) The contribution is based upon previous work that, to the best of my knowledge, is covered under an appropriate open source license and I have the right under that license to submit that work with modifications, whether created in whole or in part by me, under the same open source license (unless I am permitted to submit under a different license), as indicated in the file; + + (c) The contribution was provided directly to me by some other person who certified (a), (b) or (c) and I have not modified it. + + (d) I understand and agree that this project and the contribution are public and that a record of the contribution (including all personal information I submit with it, including my sign-off) is maintained indefinitely and may be redistributed consistent with this project or the open source license(s) involved. + +Then you add a line saying: + +Signed-off-by: Random J Developer <random(a)developer.example.org> + +Use your real name (sorry, no pseudonyms or anonymous contributions). + +### Use the unified patch format +------- + +Reasons: + +1. Long term maintainability + + openEuler will merge massive patches. If all patches are merged by casual + + changelog formats without a unified format, the git logs will be messy, and + + then it is hard to figure out the original patches. + +2. Kernel upgrade + + We definitely will upgrade our openEuler kernel in someday, so strict patch management + + will alleviate the pain to migrate patches during big upgrades. + +3. Easy for script parsing + + Keyword highlighting is necessary for script parsing. + +### Define the patch format +------- + +[M] stands for "mandatory". + +[O] stands for "option". + +$category can be: bug preparation, bugfix, perf, feature, doc, other... + +If category is feature, we need to add a feature name as below: + +```cpp +category: feature +feature: YYY (the feature name) +``` + +If the patch is related to CVE or bugzilla, we need to add the corresponding tag as below (In general, it should include at least one of the following): + +```cpp +CVE: $cve-id +bugzilla: $bug-id +``` + +Additional changelog should include at least one of the following: + +1. Why we should apply this patch + +2. What real problems in the product does this patch resolved + +3. How could we reproduce this bug or how to test + +4. Other useful information for help to understand this patch or problem + +The detailed information is very useful for migrating a patch to another kernel branch. + +Example for mainline patch: + +```cpp +mainline inclusion [M] +from $mainline-version [M] +commit $id [M] +category: $category [M] +bugzilla: $bug-id [O] +CVE: $cve-id [O] + +additional changelog [O] + +-------------------------------- + +original changelog +Signed-off-by: $yourname <$yourname(a)huawei.com> [M] +($mainline-version could be mainline-3.5, mainline-3.6, etc...) +``` + +### Examples +------- + +```cpp +mainline inclusion +from mainline-4.10 +commit 0becc0ae5b42828785b589f686725ff5bc3b9b25 +category: bugfix +bugzilla: 3004 +CVE: N/A + +The patch fixes a BUG_ON in the product: Injecting a single bit ECC error to the memory before system boot using hardware inject tools will cause a large amount of CMCI during system booting . +[ 1.146580] mce: [Hardware Error]: Machine check events logged +[ 1.152908] ------------[ cut here ]------------ +[ 1.157751] kernel BUG at kernel/timer.c:951! +[ 1.162321] invalid opcode: 0000 [#1] SMP + +------------------------------------------------- + +original changelog + +<original S-O-B> +Signed-off-by: Zhang San <zhangsan(a)huawei.com> +Tested-by: Li Si <lisi(a)huawei.com> +``` + +### Email client - Thunderbird settings +------- + +If you are a new developer in the kernel community, it is highly recommended that you use the Thunderbird mail client. + +1. Thunderbird Installation + + Obtain the English version of Thunderbird from [http://www.mozilla.org/]( http://www.mozilla.org/) and install it on your system. + + Download URL: https://www.thunderbird.net/en-US/thunderbird/all/ + +2. Settings + + 2.1 Use the plain text format instead of the HTML format. + + Choose **Options > Account Settings > Composition & Addressing**, and do **NOT** select Compose message in HTML format. + + 2.2 Editor settings + + **Tools > Options> Advanced > Config editor** + + \- To bring up the Thunderbird's registry editor, set **mailnews.send_plaintext_flowed** to **false**. + + \- Disable HTML Format: Set **mail.identity.id1.compose_html** to **false**. + + \- Enable UTF-8: Set **prefs.converted-to-utf8** to **true**. + + \- View messages in UTF-8: Set **mailnews.view_default_charset** to **UTF-8**. + + \- Set **mailnews.wraplength** to **9999** to avoid auto-wrap. + +# Linux kernel +------- + +There are several guides for kernel developers and users, which can be rendered in a number of formats, like HTML and PDF. You can read **Documentation/admin-guide/README.rst** first. + +In order to build the documentation, use **make htmldocs** or **make pdfdocs**. The formatted documentation can also be read online at: https://www.kernel.org/doc/html/latest/ + +There are various text files in the Documentation/ subdirectory, several of which use the Restructured Text markup notation. See Documentation/00-INDEX for a list of what is contained in each file. + +Read the **Documentation/process/changes.rst** file, as it contains the requirements for building and running the kernel, and information about the problems that may be caused by upgrading your kernel. + -- 2.22.0

1 0

[PATCH openEuler-1.0-LTS v2 00/26] support psi feature
by Liu Xinpeng 28 Oct '21

28 Oct '21

backport psi feature and avoid kabi change bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 Baruch Siach (1): psi: fix reference to kernel commandline enable Dan Schatzberg (1): kernel/sched/psi.c: expose pressure metrics on root cgroup Johannes Weiner (12): mm: workingset: tell cache transitions from workingset thrashing sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD sched: loadavg: make calc_load_n() public sched: sched.h: make rq locking and clock functions available in stats.h sched: introduce this_rq_lock_irq() psi: pressure stall information for CPU, memory, and IO psi: cgroup support psi: make disabling/enabling easier for vendor kernels psi: fix aggregation idle shut-off psi: avoid divide-by-zero crash inside virtual machines fs: kernfs: add poll file operation sched/psi: Fix sampling error and rare div0 crashes with cgroups and high uptime Josef Bacik (1): blk-iolatency: use a percentile approache for ssd's Liu Xinpeng (2): psi:enable psi in config psi:avoid kabi change Miklos Szeredi (1): fuse: ignore PG_workingset after stealing Olof Johansson (1): kernel/sched/psi.c: simplify cgroup_move_task() Suren Baghdasaryan (6): psi: introduce state_mask to represent stalled psi states psi: make psi_enable static psi: rename psi fields in preparation for psi trigger addition psi: split update_stats into parts psi: track changed states include/: refactor headers to allow kthread.h inclusion in psi_types.h Yafang Shao (1): mm, memcg: add workingset_restore in memory.stat Documentation/accounting/psi.txt | 73 +++ Documentation/admin-guide/cgroup-v2.rst | 22 + Documentation/admin-guide/kernel-parameters.txt | 4 + arch/arm64/configs/openeuler_defconfig | 2 + arch/powerpc/platforms/cell/cpufreq_spudemand.c | 2 +- arch/powerpc/platforms/cell/spufs/sched.c | 9 +- arch/s390/appldata/appldata_os.c | 4 - arch/x86/configs/openeuler_defconfig | 2 + block/blk-iolatency.c | 183 +++++- drivers/cpuidle/governors/menu.c | 4 - drivers/spi/spi-rockchip.c | 1 + fs/fuse/dev.c | 1 + fs/kernfs/file.c | 31 +- fs/proc/loadavg.c | 3 - include/linux/cgroup-defs.h | 12 + include/linux/cgroup.h | 17 + include/linux/kernfs.h | 8 + include/linux/kthread.h | 4 + include/linux/mmzone.h | 3 + include/linux/page-flags.h | 5 + include/linux/psi.h | 55 ++ include/linux/psi_types.h | 95 +++ include/linux/sched.h | 13 + include/linux/sched/loadavg.h | 24 +- include/linux/swap.h | 1 + include/trace/events/mmflags.h | 1 + init/Kconfig | 28 + kernel/cgroup/cgroup.c | 55 +- kernel/debug/kdb/kdb_main.c | 7 +- kernel/fork.c | 4 + kernel/kthread.c | 3 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 16 +- kernel/sched/loadavg.c | 139 ++-- kernel/sched/psi.c | 823 ++++++++++++++++++++++++ kernel/sched/sched.h | 178 ++--- kernel/sched/stats.h | 86 +++ kernel/workqueue.c | 23 + kernel/workqueue_internal.h | 6 +- mm/compaction.c | 5 + mm/filemap.c | 20 +- mm/huge_memory.c | 1 + mm/memcontrol.c | 2 + mm/migrate.c | 2 + mm/page_alloc.c | 9 + mm/swap_state.c | 1 + mm/vmscan.c | 10 + mm/vmstat.c | 1 + mm/workingset.c | 117 +++- 49 files changed, 1837 insertions(+), 279 deletions(-) create mode 100644 Documentation/accounting/psi.txt create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h create mode 100644 kernel/sched/psi.c -- 1.8.3.1

1 25

[PATCH openEuler-1.0-LTS] config: update hulk_defconfig
by Yang Yingliang 28 Oct '21

28 Oct '21

hulk inclusion category: bugfix bugzilla: NA CVE: NA --------------------------- enable CONFIG_HISILICON_ERRATUM_1980005 by default for test. set default value of CONFIG_MMC_DW_IDMAC and CONFIG_MMC_DW_HI3XXX. Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/configs/hulk_defconfig | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm64/configs/hulk_defconfig b/arch/arm64/configs/hulk_defconfig index b146c2e2a93dc..01e02aa2cb092 100644 --- a/arch/arm64/configs/hulk_defconfig +++ b/arch/arm64/configs/hulk_defconfig @@ -398,7 +398,7 @@ CONFIG_ARM64_ERRATUM_845719=y # CONFIG_QCOM_QDF2400_ERRATUM_0065 is not set # CONFIG_SOCIONEXT_SYNQUACER_PREITS is not set CONFIG_HISILICON_ERRATUM_161600802=y -# CONFIG_HISILICON_ERRATUM_1980005 is not set +CONFIG_HISILICON_ERRATUM_1980005=y # CONFIG_QCOM_FALKOR_ERRATUM_E1041 is not set CONFIG_HISILICON_ERRATUM_HIP08_RU_PREFETCH=y # CONFIG_HISILICON_HIP08_RU_PREFETCH_DEFAULT_OFF is not set @@ -4204,10 +4204,12 @@ CONFIG_MMC_SPI=m CONFIG_MMC_CB710=m CONFIG_MMC_VIA_SDMMC=m CONFIG_MMC_DW=m +# CONFIG_MMC_DW_IDMAC is not set CONFIG_MMC_DW_PLTFM=m CONFIG_MMC_DW_BLUEFIELD=m # CONFIG_MMC_DW_EXYNOS is not set # CONFIG_MMC_DW_HI3798CV200 is not set +# CONFIG_MMC_DW_HI3XXX is not set # CONFIG_MMC_DW_K3 is not set # CONFIG_MMC_DW_PCI is not set CONFIG_MMC_VUB300=m -- 2.25.1

1 0

[PATCH kernel-4.19 1/4] iommu/arm-smmu: Prevent forced unbinding of Arm SMMU drivers
by Yang Yingliang 28 Oct '21

28 Oct '21

From: Will Deacon <will(a)kernel.org> mainline inclusion from mainline-v5.5-rc1 commit 34debdca68efd5625a2fcea7df1a215591a01f80 category: bugfix bugzilla: 95382 CVE: NA ------------------------------------------------- Forcefully unbinding the Arm SMMU drivers is a pretty dangerous operation, since it will likely lead to catastrophic failure for any DMA devices mastering through the SMMU being unbound. When the driver then attempts to "handle" the fatal faults, it's very easy to trip over dead data structures, leading to use-after-free. On John's machine, he reports that the machine was "unusable" due to loss of the storage controller following a forced unbind of the SMMUv3 driver: | # cd ./bus/platform/drivers/arm-smmu-v3 | # echo arm-smmu-v3.0.auto > unbind | hisi_sas_v2_hw HISI0162:01: CQE_AXI_W_ERR (0x800) found! | platform arm-smmu-v3.0.auto: CMD_SYNC timeout at 0x00000146 | [hwprod 0x00000146, hwcons 0x00000000] Prevent this forced unbinding of the drivers by setting "suppress_bind_attrs" to true. Link: https://lore.kernel.org/lkml/06dfd385-1af0-3106-4cc5-6a5b8e864759@huawei.com Reported-by: John Garry <john.garry(a)huawei.com> Signed-off-by: Will Deacon <will(a)kernel.org> Tested-by: John Garry <john.garry(a)huawei.com> # smmu v3 Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Joerg Roedel <jroedel(a)suse.de> Signed-off-by: Nanyong Sun <sunnanyong(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/iommu/arm-smmu-v3.c | 5 +++-- drivers/iommu/arm-smmu.c | 7 ++++--- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index c9ff437cb3283..49408e73716e7 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -4532,8 +4532,9 @@ MODULE_DEVICE_TABLE(of, arm_smmu_of_match); static struct platform_driver arm_smmu_driver = { .driver = { - .name = "arm-smmu-v3", - .of_match_table = of_match_ptr(arm_smmu_of_match), + .name = "arm-smmu-v3", + .of_match_table = of_match_ptr(arm_smmu_of_match), + .suppress_bind_attrs = true, }, .probe = arm_smmu_device_probe, .remove = arm_smmu_device_remove, diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index f948de8af412c..2c2bdeac758e0 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -2287,9 +2287,10 @@ static SIMPLE_DEV_PM_OPS(arm_smmu_pm_ops, NULL, arm_smmu_pm_resume); static struct platform_driver arm_smmu_driver = { .driver = { - .name = "arm-smmu", - .of_match_table = of_match_ptr(arm_smmu_of_match), - .pm = &arm_smmu_pm_ops, + .name = "arm-smmu", + .of_match_table = of_match_ptr(arm_smmu_of_match), + .pm = &arm_smmu_pm_ops, + .suppress_bind_attrs = true, }, .probe = arm_smmu_device_probe, .remove = arm_smmu_device_remove, -- 2.25.1

2 4

[PATCH kernel-4.19 v6 00/23] support psi feature
by Liu Xinpeng 28 Oct '21

28 Oct '21

backport psi feature from upstream 5.4 bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 Baruch Siach (1): psi: fix reference to kernel commandline enable Dan Schatzberg (1): kernel/sched/psi.c: expose pressure metrics on root cgroup Johannes Weiner (11): sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD sched: loadavg: make calc_load_n() public sched: sched.h: make rq locking and clock functions available in stats.h sched: introduce this_rq_lock_irq() psi: pressure stall information for CPU, memory, and IO psi: cgroup support psi: make disabling/enabling easier for vendor kernels psi: fix aggregation idle shut-off psi: avoid divide-by-zero crash inside virtual machines fs: kernfs: add poll file operation sched/psi: Fix sampling error and rare div0 crashes with cgroups and high uptime Josef Bacik (1): blk-iolatency: use a percentile approache for ssd's Liu Xinpeng (2): psi:enable psi in config psi:avoid kabi change Olof Johansson (1): kernel/sched/psi.c: simplify cgroup_move_task() Suren Baghdasaryan (6): psi: introduce state_mask to represent stalled psi states psi: make psi_enable static psi: rename psi fields in preparation for psi trigger addition psi: split update_stats into parts psi: track changed states include/: refactor headers to allow kthread.h inclusion in psi_types.h Documentation/accounting/psi.txt | 73 +++ Documentation/admin-guide/cgroup-v2.rst | 18 + Documentation/admin-guide/kernel-parameters.txt | 4 + arch/arm64/configs/openeuler_defconfig | 2 + arch/powerpc/platforms/cell/cpufreq_spudemand.c | 2 +- arch/powerpc/platforms/cell/spufs/sched.c | 9 +- arch/s390/appldata/appldata_os.c | 4 - arch/x86/configs/openeuler_defconfig | 2 + block/blk-iolatency.c | 183 +++++- drivers/cpuidle/governors/menu.c | 4 - drivers/spi/spi-rockchip.c | 1 + fs/kernfs/file.c | 31 +- fs/proc/loadavg.c | 3 - include/linux/cgroup-defs.h | 12 + include/linux/cgroup.h | 17 + include/linux/kernfs.h | 8 + include/linux/kthread.h | 4 + include/linux/psi.h | 55 ++ include/linux/psi_types.h | 95 +++ include/linux/sched.h | 13 + include/linux/sched/loadavg.h | 24 +- init/Kconfig | 28 + kernel/cgroup/cgroup.c | 55 +- kernel/debug/kdb/kdb_main.c | 7 +- kernel/fork.c | 4 + kernel/kthread.c | 3 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 16 +- kernel/sched/loadavg.c | 139 ++-- kernel/sched/psi.c | 823 ++++++++++++++++++++++++ kernel/sched/sched.h | 178 ++--- kernel/sched/stats.h | 86 +++ kernel/workqueue.c | 23 + kernel/workqueue_internal.h | 6 +- mm/compaction.c | 5 + mm/filemap.c | 11 + mm/page_alloc.c | 9 + mm/vmscan.c | 9 + 38 files changed, 1726 insertions(+), 241 deletions(-) create mode 100644 Documentation/accounting/psi.txt create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h create mode 100644 kernel/sched/psi.c -- 1.8.3.1

2 24

[PATCH kernel-4.19 1/8] EMMC: ascend customized emmc host
by Yang Yingliang 28 Oct '21

28 Oct '21

From: zhangguijiang <zhangguijiang(a)huawei.com> ascend inclusion category: feature feature: Ascend emmc adaption bugzilla: https://gitee.com/openeuler/kernel/issues/I4F4LL CVE: NA -------------------- To identify Ascend HiSilicon emmc chip, we add a customized property to dts. In this patch we add an interface to read this property. At the same time, we provided a switch, which is CONFIG_ASCEND_HISI_MMC, for you to get rid of our modifications. Signed-off-by: zhangguijiang <zhangguijiang(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/mmc/Kconfig | 10 ++++ drivers/mmc/core/host.c | 43 ++++++++++++--- include/linux/mmc/host.h | 115 +++++++++++++++++++++++++++++++++++++++ include/linux/mmc/pm.h | 1 + 4 files changed, 162 insertions(+), 7 deletions(-) diff --git a/drivers/mmc/Kconfig b/drivers/mmc/Kconfig index ec21388311db2..8b29ecadd1862 100644 --- a/drivers/mmc/Kconfig +++ b/drivers/mmc/Kconfig @@ -12,6 +12,16 @@ menuconfig MMC If you want MMC/SD/SDIO support, you should say Y here and also to your specific host controller driver. +config ASCEND_HISI_MMC + bool "Ascend HiSilicon MMC card support" + depends on MMC + default n + help + This selects for Hisilicon SoC specific extensions to the + Synopsys DesignWare Memory Card Interface driver. + You should select this option if you want mmc support on + Ascend platform. + if MMC source "drivers/mmc/core/Kconfig" diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index dd1c14d8f6863..b29ee31e7865e 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -348,6 +348,11 @@ int mmc_of_parse(struct mmc_host *host) EXPORT_SYMBOL(mmc_of_parse); +static inline int mmc_is_ascend_hi_mci_1(struct device *dev) +{ + return !strncmp(dev_name(dev), "hi_mci.1", strlen("hi_mci.1")); +} + /** * mmc_alloc_host - initialise the per-host structure. * @extra: sizeof private data structure @@ -374,7 +379,10 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) } host->index = err; - + if (mmc_is_ascend_customized(dev)) { + if (mmc_is_ascend_hi_mci_1(dev)) + host->index = 1; + } dev_set_name(&host->class_dev, "mmc%d", host->index); host->parent = dev; @@ -383,10 +391,11 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) device_initialize(&host->class_dev); device_enable_async_suspend(&host->class_dev); - if (mmc_gpio_alloc(host)) { - put_device(&host->class_dev); - return NULL; - } + if (!mmc_is_ascend_customized(host->parent)) + if (mmc_gpio_alloc(host)) { + put_device(&host->class_dev); + return NULL; + } spin_lock_init(&host->lock); init_waitqueue_head(&host->wq); @@ -439,7 +448,9 @@ int mmc_add_host(struct mmc_host *host) #endif mmc_start_host(host); - mmc_register_pm_notifier(host); + if (!mmc_is_ascend_customized(host->parent) || + !(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY)) + mmc_register_pm_notifier(host); return 0; } @@ -456,7 +467,9 @@ EXPORT_SYMBOL(mmc_add_host); */ void mmc_remove_host(struct mmc_host *host) { - mmc_unregister_pm_notifier(host); + if (!mmc_is_ascend_customized(host->parent) || + !(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY)) + mmc_unregister_pm_notifier(host); mmc_stop_host(host); #ifdef CONFIG_DEBUG_FS @@ -483,3 +496,19 @@ void mmc_free_host(struct mmc_host *host) } EXPORT_SYMBOL(mmc_free_host); + + +int mmc_is_ascend_customized(struct device *dev) +{ +#ifdef CONFIG_ASCEND_HISI_MMC + static int is_ascend_customized = -1; + + if (is_ascend_customized == -1) + is_ascend_customized = ((dev == NULL) ? 0 : + of_find_property(dev->of_node, "customized", NULL) != NULL); + return is_ascend_customized; +#else + return 0; +#endif +} +EXPORT_SYMBOL(mmc_is_ascend_customized); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 7e8e5b20e82b0..2cd5a73ab12a2 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -19,6 +19,9 @@ #include <linux/mmc/pm.h> #include <linux/dma-direction.h> +#include <linux/jiffies.h> +#include <linux/version.h> + struct mmc_ios { unsigned int clock; /* clock rate */ unsigned short vdd; @@ -63,6 +66,7 @@ struct mmc_ios { #define MMC_TIMING_MMC_DDR52 8 #define MMC_TIMING_MMC_HS200 9 #define MMC_TIMING_MMC_HS400 10 +#define MMC_TIMING_NEW_SD MMC_TIMING_UHS_SDR12 unsigned char signal_voltage; /* signalling voltage (1.8V or 3.3V) */ @@ -78,7 +82,25 @@ struct mmc_ios { #define MMC_SET_DRIVER_TYPE_D 3 bool enhanced_strobe; /* hs400es selection */ +#ifdef CONFIG_ASCEND_HISI_MMC + unsigned int clock_store; /*store the clock before power off*/ +#endif +}; + +#ifdef CONFIG_ASCEND_HISI_MMC +struct mmc_cmdq_host_ops { + int (*enable)(struct mmc_host *mmc); + int (*disable)(struct mmc_host *mmc, bool soft); + int (*restore_irqs)(struct mmc_host *mmc); + int (*request)(struct mmc_host *mmc, struct mmc_request *mrq); + int (*halt)(struct mmc_host *mmc, bool halt); + void (*post_req)(struct mmc_host *mmc, struct mmc_request *mrq, + int err); + void (*disable_immediately)(struct mmc_host *mmc); + int (*clear_and_halt)(struct mmc_host *mmc); }; +#endif + struct mmc_host; @@ -168,6 +190,12 @@ struct mmc_host_ops { */ int (*multi_io_quirk)(struct mmc_card *card, unsigned int direction, int blk_size); +#ifdef CONFIG_ASCEND_HISI_MMC + /* Slow down clk for ascend chip SD cards */ + void (*slowdown_clk)(struct mmc_host *host, int timing); + int (*enable_enhanced_strobe)(struct mmc_host *host); + int (*send_cmd_direct)(struct mmc_host *host, struct mmc_request *mrq); +#endif }; struct mmc_cqe_ops { @@ -255,6 +283,30 @@ struct mmc_context_info { wait_queue_head_t wait; }; +#ifdef CONFIG_ASCEND_HISI_MMC +/** + * mmc_cmdq_context_info - describes the contexts of cmdq + * @active_reqs requests being processed + * @active_dcmd dcmd in progress, don't issue any + * more dcmd requests + * @rpmb_in_wait do not pull any more reqs till rpmb is handled + * @cmdq_state state of cmdq engine + * @req_starved completion should invoke the request_fn since + * no tags were available + * @cmdq_ctx_lock acquire this before accessing this structure + */ +struct mmc_cmdq_context_info { + unsigned long active_reqs; /* in-flight requests */ + bool active_dcmd; + bool rpmb_in_wait; + unsigned long curr_state; + + /* no free tag available */ + unsigned long req_starved; + spinlock_t cmdq_ctx_lock; +}; +#endif + struct regulator; struct mmc_pwrseq; @@ -328,6 +380,9 @@ struct mmc_host { #define MMC_CAP_UHS_SDR50 (1 << 18) /* Host supports UHS SDR50 mode */ #define MMC_CAP_UHS_SDR104 (1 << 19) /* Host supports UHS SDR104 mode */ #define MMC_CAP_UHS_DDR50 (1 << 20) /* Host supports UHS DDR50 mode */ +#ifdef CONFIG_ASCEND_HISI_MMC +#define MMC_CAP_RUNTIME_RESUME (1 << 20) /* Resume at runtime_resume. */ +#endif #define MMC_CAP_UHS (MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 | \ MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 | \ MMC_CAP_UHS_DDR50) @@ -368,6 +423,34 @@ struct mmc_host { #define MMC_CAP2_CQE (1 << 23) /* Has eMMC command queue engine */ #define MMC_CAP2_CQE_DCMD (1 << 24) /* CQE can issue a direct command */ #define MMC_CAP2_AVOID_3_3V (1 << 25) /* Host must negotiate down from 3.3V */ +#ifdef CONFIG_ASCEND_HISI_MMC +#define MMC_CAP2_CACHE_CTRL (1 << 1) /* Allow cache control */ +#define MMC_CAP2_NO_MULTI_READ (1 << 3) /* Multiblock read don't work */ +#define MMC_CAP2_NO_SLEEP_CMD (1 << 4) /* Don't allow sleep command */ +#define MMC_CAP2_BROKEN_VOLTAGE (1 << 7) /* Use the broken voltage */ +#define MMC_CAP2_DETECT_ON_ERR (1 << 8) /* I/O err check card removal */ +#define MMC_CAP2_HC_ERASE_SZ (1 << 9) /* High-capacity erase size */ +#define MMC_CAP2_PACKED_RD (1 << 12) /* Allow packed read */ +#define MMC_CAP2_PACKED_WR (1 << 13) /* Allow packed write */ +#define MMC_CAP2_PACKED_CMD (MMC_CAP2_PACKED_RD | \ + MMC_CAP2_PACKED_WR) +#define MMC_CAP2_CMD_QUEUE (1 << 18) /* support eMMC command queue */ +#define MMC_CAP2_ENHANCED_STROBE (1 << 19) +#define MMC_CAP2_CACHE_FLUSH_BARRIER (1 << 20) +/* Allow background operations auto enable control */ +#define MMC_CAP2_BKOPS_AUTO_CTRL (1 << 21) +/* Allow background operations manual enable control */ +#define MMC_CAP2_BKOPS_MANUAL_CTRL (1 << 22) + +/* host is connected by via modem through sdio */ +#define MMC_CAP2_SUPPORT_VIA_MODEM (1 << 26) +/* host is connected by wifi through sdio */ +#define MMC_CAP2_SUPPORT_WIFI (1 << 27) +/* host is connected to 1102 wifi */ +#define MMC_CAP2_SUPPORT_WIFI_CMD11 (1 << 28) +/* host do not support low power for wifi*/ +#define MMC_CAP2_WIFI_NO_LOWPWR (1 << 29) +#endif int fixed_drv_type; /* fixed driver type for non-removable media */ @@ -461,6 +544,12 @@ struct mmc_host { bool cqe_on; unsigned long private[0] ____cacheline_aligned; +#ifdef CONFIG_ASCEND_HISI_MMC + const struct mmc_cmdq_host_ops *cmdq_ops; + int sdio_present; + unsigned int cmdq_slots; + struct mmc_cmdq_context_info cmdq_ctx; +#endif }; struct device_node; @@ -588,4 +677,30 @@ static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data) int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); int mmc_abort_tuning(struct mmc_host *host, u32 opcode); +#ifdef CONFIG_ASCEND_HISI_MMC +int mmc_cache_ctrl(struct mmc_host *host, u8 enable); +int mmc_card_awake(struct mmc_host *host); +int mmc_card_sleep(struct mmc_host *host); +int mmc_card_can_sleep(struct mmc_host *host); +#else +static inline int mmc_cache_ctrl(struct mmc_host *host, u8 enable) +{ + return 0; +} +static inline int mmc_card_awake(struct mmc_host *host) +{ + return 0; +} +static inline int mmc_card_sleep(struct mmc_host *host) +{ + return 0; +} +static inline int mmc_card_can_sleep(struct mmc_host *host) +{ + return 0; +} +#endif + +int mmc_is_ascend_customized(struct device *dev); + #endif /* LINUX_MMC_HOST_H */ diff --git a/include/linux/mmc/pm.h b/include/linux/mmc/pm.h index 4a139204c20c0..6e2d6a135c7e0 100644 --- a/include/linux/mmc/pm.h +++ b/include/linux/mmc/pm.h @@ -26,5 +26,6 @@ typedef unsigned int mmc_pm_flag_t; #define MMC_PM_KEEP_POWER (1 << 0) /* preserve card power during suspend */ #define MMC_PM_WAKE_SDIO_IRQ (1 << 1) /* wake up host system on SDIO IRQ assertion */ +#define MMC_PM_IGNORE_PM_NOTIFY (1 << 2) /* ignore mmc pm notify */ #endif /* LINUX_MMC_PM_H */ -- 2.25.1

1 7

[PATCH openEuler-1.0-LTS 1/8] EMMC: ascend customized emmc host
by Yang Yingliang 27 Oct '21

27 Oct '21

From: zhangguijiang <zhangguijiang(a)huawei.com> ascend inclusion category: feature feature: Ascend emmc adaption bugzilla: https://gitee.com/openeuler/kernel/issues/I4F4LL CVE: NA -------------------- To identify Ascend HiSilicon emmc chip, we add a customized property to dts. In this patch we add an interface to read this property. At the same time, we provided a switch, which is CONFIG_ASCEND_HISI_MMC, for you to get rid of our modifications. Signed-off-by: zhangguijiang <zhangguijiang(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/mmc/Kconfig | 10 ++++ drivers/mmc/core/host.c | 47 +++++++++++++--- include/linux/mmc/host.h | 115 +++++++++++++++++++++++++++++++++++++++ include/linux/mmc/pm.h | 1 + 4 files changed, 164 insertions(+), 9 deletions(-) diff --git a/drivers/mmc/Kconfig b/drivers/mmc/Kconfig index ec21388311db2..8b29ecadd1862 100644 --- a/drivers/mmc/Kconfig +++ b/drivers/mmc/Kconfig @@ -12,6 +12,16 @@ menuconfig MMC If you want MMC/SD/SDIO support, you should say Y here and also to your specific host controller driver. +config ASCEND_HISI_MMC + bool "Ascend HiSilicon MMC card support" + depends on MMC + default n + help + This selects for Hisilicon SoC specific extensions to the + Synopsys DesignWare Memory Card Interface driver. + You should select this option if you want mmc support on + Ascend platform. + if MMC source "drivers/mmc/core/Kconfig" diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index f57f5de542064..69cc778706855 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -348,6 +348,11 @@ int mmc_of_parse(struct mmc_host *host) EXPORT_SYMBOL(mmc_of_parse); +static inline int mmc_is_ascend_hi_mci_1(struct device *dev) +{ + return !strncmp(dev_name(dev), "hi_mci.1", strlen("hi_mci.1")); +} + /** * mmc_alloc_host - initialise the per-host structure. * @extra: sizeof private data structure @@ -374,7 +379,10 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) } host->index = err; - + if (mmc_is_ascend_customized(dev)) { + if (mmc_is_ascend_hi_mci_1(dev)) + host->index = 1; + } dev_set_name(&host->class_dev, "mmc%d", host->index); host->parent = dev; @@ -383,12 +391,13 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) device_initialize(&host->class_dev); device_enable_async_suspend(&host->class_dev); - if (mmc_gpio_alloc(host)) { - put_device(&host->class_dev); - ida_simple_remove(&mmc_host_ida, host->index); - kfree(host); - return NULL; - } + if (!mmc_is_ascend_customized(host->parent)) + if (mmc_gpio_alloc(host)) { + put_device(&host->class_dev); + ida_simple_remove(&mmc_host_ida, host->index); + kfree(host); + return NULL; + } spin_lock_init(&host->lock); init_waitqueue_head(&host->wq); @@ -441,7 +450,9 @@ int mmc_add_host(struct mmc_host *host) #endif mmc_start_host(host); - mmc_register_pm_notifier(host); + if (!mmc_is_ascend_customized(host->parent) || + !(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY)) + mmc_register_pm_notifier(host); return 0; } @@ -458,7 +469,9 @@ EXPORT_SYMBOL(mmc_add_host); */ void mmc_remove_host(struct mmc_host *host) { - mmc_unregister_pm_notifier(host); + if (!mmc_is_ascend_customized(host->parent) || + !(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY)) + mmc_unregister_pm_notifier(host); mmc_stop_host(host); #ifdef CONFIG_DEBUG_FS @@ -485,3 +498,19 @@ void mmc_free_host(struct mmc_host *host) } EXPORT_SYMBOL(mmc_free_host); + + +int mmc_is_ascend_customized(struct device *dev) +{ +#ifdef CONFIG_ASCEND_HISI_MMC + static int is_ascend_customized = -1; + + if (is_ascend_customized == -1) + is_ascend_customized = ((dev == NULL) ? 0 : + of_find_property(dev->of_node, "customized", NULL) != NULL); + return is_ascend_customized; +#else + return 0; +#endif +} +EXPORT_SYMBOL(mmc_is_ascend_customized); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 840462ed1ec7e..78b4d0a813b71 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -19,6 +19,9 @@ #include <linux/mmc/pm.h> #include <linux/dma-direction.h> +#include <linux/jiffies.h> +#include <linux/version.h> + struct mmc_ios { unsigned int clock; /* clock rate */ unsigned short vdd; @@ -63,6 +66,7 @@ struct mmc_ios { #define MMC_TIMING_MMC_DDR52 8 #define MMC_TIMING_MMC_HS200 9 #define MMC_TIMING_MMC_HS400 10 +#define MMC_TIMING_NEW_SD MMC_TIMING_UHS_SDR12 unsigned char signal_voltage; /* signalling voltage (1.8V or 3.3V) */ @@ -78,7 +82,25 @@ struct mmc_ios { #define MMC_SET_DRIVER_TYPE_D 3 bool enhanced_strobe; /* hs400es selection */ +#ifdef CONFIG_ASCEND_HISI_MMC + unsigned int clock_store; /*store the clock before power off*/ +#endif +}; + +#ifdef CONFIG_ASCEND_HISI_MMC +struct mmc_cmdq_host_ops { + int (*enable)(struct mmc_host *mmc); + int (*disable)(struct mmc_host *mmc, bool soft); + int (*restore_irqs)(struct mmc_host *mmc); + int (*request)(struct mmc_host *mmc, struct mmc_request *mrq); + int (*halt)(struct mmc_host *mmc, bool halt); + void (*post_req)(struct mmc_host *mmc, struct mmc_request *mrq, + int err); + void (*disable_immediately)(struct mmc_host *mmc); + int (*clear_and_halt)(struct mmc_host *mmc); }; +#endif + struct mmc_host; @@ -168,6 +190,12 @@ struct mmc_host_ops { */ int (*multi_io_quirk)(struct mmc_card *card, unsigned int direction, int blk_size); +#ifdef CONFIG_ASCEND_HISI_MMC + /* Slow down clk for ascend chip SD cards */ + void (*slowdown_clk)(struct mmc_host *host, int timing); + int (*enable_enhanced_strobe)(struct mmc_host *host); + int (*send_cmd_direct)(struct mmc_host *host, struct mmc_request *mrq); +#endif }; struct mmc_cqe_ops { @@ -255,6 +283,30 @@ struct mmc_context_info { wait_queue_head_t wait; }; +#ifdef CONFIG_ASCEND_HISI_MMC +/** + * mmc_cmdq_context_info - describes the contexts of cmdq + * @active_reqs requests being processed + * @active_dcmd dcmd in progress, don't issue any + * more dcmd requests + * @rpmb_in_wait do not pull any more reqs till rpmb is handled + * @cmdq_state state of cmdq engine + * @req_starved completion should invoke the request_fn since + * no tags were available + * @cmdq_ctx_lock acquire this before accessing this structure + */ +struct mmc_cmdq_context_info { + unsigned long active_reqs; /* in-flight requests */ + bool active_dcmd; + bool rpmb_in_wait; + unsigned long curr_state; + + /* no free tag available */ + unsigned long req_starved; + spinlock_t cmdq_ctx_lock; +}; +#endif + struct regulator; struct mmc_pwrseq; @@ -328,6 +380,9 @@ struct mmc_host { #define MMC_CAP_UHS_SDR50 (1 << 18) /* Host supports UHS SDR50 mode */ #define MMC_CAP_UHS_SDR104 (1 << 19) /* Host supports UHS SDR104 mode */ #define MMC_CAP_UHS_DDR50 (1 << 20) /* Host supports UHS DDR50 mode */ +#ifdef CONFIG_ASCEND_HISI_MMC +#define MMC_CAP_RUNTIME_RESUME (1 << 20) /* Resume at runtime_resume. */ +#endif #define MMC_CAP_UHS (MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 | \ MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 | \ MMC_CAP_UHS_DDR50) @@ -367,6 +422,34 @@ struct mmc_host { #define MMC_CAP2_CQE (1 << 23) /* Has eMMC command queue engine */ #define MMC_CAP2_CQE_DCMD (1 << 24) /* CQE can issue a direct command */ #define MMC_CAP2_AVOID_3_3V (1 << 25) /* Host must negotiate down from 3.3V */ +#ifdef CONFIG_ASCEND_HISI_MMC +#define MMC_CAP2_CACHE_CTRL (1 << 1) /* Allow cache control */ +#define MMC_CAP2_NO_MULTI_READ (1 << 3) /* Multiblock read don't work */ +#define MMC_CAP2_NO_SLEEP_CMD (1 << 4) /* Don't allow sleep command */ +#define MMC_CAP2_BROKEN_VOLTAGE (1 << 7) /* Use the broken voltage */ +#define MMC_CAP2_DETECT_ON_ERR (1 << 8) /* I/O err check card removal */ +#define MMC_CAP2_HC_ERASE_SZ (1 << 9) /* High-capacity erase size */ +#define MMC_CAP2_PACKED_RD (1 << 12) /* Allow packed read */ +#define MMC_CAP2_PACKED_WR (1 << 13) /* Allow packed write */ +#define MMC_CAP2_PACKED_CMD (MMC_CAP2_PACKED_RD | \ + MMC_CAP2_PACKED_WR) +#define MMC_CAP2_CMD_QUEUE (1 << 18) /* support eMMC command queue */ +#define MMC_CAP2_ENHANCED_STROBE (1 << 19) +#define MMC_CAP2_CACHE_FLUSH_BARRIER (1 << 20) +/* Allow background operations auto enable control */ +#define MMC_CAP2_BKOPS_AUTO_CTRL (1 << 21) +/* Allow background operations manual enable control */ +#define MMC_CAP2_BKOPS_MANUAL_CTRL (1 << 22) + +/* host is connected by via modem through sdio */ +#define MMC_CAP2_SUPPORT_VIA_MODEM (1 << 26) +/* host is connected by wifi through sdio */ +#define MMC_CAP2_SUPPORT_WIFI (1 << 27) +/* host is connected to 1102 wifi */ +#define MMC_CAP2_SUPPORT_WIFI_CMD11 (1 << 28) +/* host do not support low power for wifi*/ +#define MMC_CAP2_WIFI_NO_LOWPWR (1 << 29) +#endif int fixed_drv_type; /* fixed driver type for non-removable media */ @@ -460,6 +543,12 @@ struct mmc_host { bool cqe_on; unsigned long private[0] ____cacheline_aligned; +#ifdef CONFIG_ASCEND_HISI_MMC + const struct mmc_cmdq_host_ops *cmdq_ops; + int sdio_present; + unsigned int cmdq_slots; + struct mmc_cmdq_context_info cmdq_ctx; +#endif }; struct device_node; @@ -587,4 +676,30 @@ static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data) int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); int mmc_abort_tuning(struct mmc_host *host, u32 opcode); +#ifdef CONFIG_ASCEND_HISI_MMC +int mmc_cache_ctrl(struct mmc_host *host, u8 enable); +int mmc_card_awake(struct mmc_host *host); +int mmc_card_sleep(struct mmc_host *host); +int mmc_card_can_sleep(struct mmc_host *host); +#else +static inline int mmc_cache_ctrl(struct mmc_host *host, u8 enable) +{ + return 0; +} +static inline int mmc_card_awake(struct mmc_host *host) +{ + return 0; +} +static inline int mmc_card_sleep(struct mmc_host *host) +{ + return 0; +} +static inline int mmc_card_can_sleep(struct mmc_host *host) +{ + return 0; +} +#endif + +int mmc_is_ascend_customized(struct device *dev); + #endif /* LINUX_MMC_HOST_H */ diff --git a/include/linux/mmc/pm.h b/include/linux/mmc/pm.h index 4a139204c20c0..6e2d6a135c7e0 100644 --- a/include/linux/mmc/pm.h +++ b/include/linux/mmc/pm.h @@ -26,5 +26,6 @@ typedef unsigned int mmc_pm_flag_t; #define MMC_PM_KEEP_POWER (1 << 0) /* preserve card power during suspend */ #define MMC_PM_WAKE_SDIO_IRQ (1 << 1) /* wake up host system on SDIO IRQ assertion */ +#define MMC_PM_IGNORE_PM_NOTIFY (1 << 2) /* ignore mmc pm notify */ #endif /* LINUX_MMC_PM_H */ -- 2.25.1

1 7

[PATCH openEuler-21.03 00/37] 补丁合入创新分支告知
by Wang ShaoBo 27 Oct '21

27 Oct '21

首先非常感谢大家参与openEuler社区，并给openEuler kernel开源项目提补丁。 openEuler kernel开源项目的openEuler-21.03创新分支以更加开阔的视野接纳企业，高校以及所有爱好和关注Linux内核人士的想法和建议，期望和大家共同探索底层软件在构建云与计算、5G、终端等全场景下的前景和潜力，共同推动底软在物联网、智能计算背景下的全新视界；另外openEuler-21.03创新分支同时希望给高校提供更多的教学素材，为高校基础研究和产教结合道路奉献绵薄之力。 - 如果您对如何参与openEuler kernel开源项目有疑问，可以发邮件至bobo.shaobowang(a)huawei.com, 也可以参考文档：https://mp.weixin.qq.com/s/a42a5VfayFeJgWitqbI8Qw - 您也可以通过openEuler kernel官网提交issue: https://gitee.com/openeuler/kernel 以下补丁已经过社区maintainer review和openEuler社区的验证测试，将合入到openEuler-21.03分支5.10.0-4.25.0版本。 0ee74f5aa533 (HEAD -> openEuler-21.03, tag: 5.10.0-4.25.0) RDS tcp loopback connection can hang fc7ec5aebb45 usb: gadget: f_fs: Ensure io_completion_wq is idle during unbind dae6a368dafc ALSA: seq: Fix race of snd_seq_timer_open() 3a00695cb8e2 RDMA/mlx4: Do not map the core_clock page to user space unless enabled ed4fd7c42adc Revert "ACPI: sleep: Put the FACS table after using it" 37c85837cf42 ASoC: Intel: bytcr_rt5640: Add quirk for the Glavey TM800A550L tablet 94fccf25dd49 nvme-tcp: remove incorrect Kconfig dep in BLK_DEV_NVME 47f090fbcbb9 regulator: fan53880: Fix missing n_voltages setting 0b9b74807478 net/nfc/rawsock.c: fix a permission check bug 789459f344e7 scsi: core: Only put parent device if host state differs from SHOST_CREATED 08f8e0fb4b59 usb: typec: ucsi: Clear PPM capability data in ucsi_init() error path 0e2bd1220f8a phy: cadence: Sierra: Fix error return code in cdns_sierra_phy_probe() 47f3671cfd67 usb: pd: Set PD_T_SINK_WAIT_CAP to 310ms 559b80a5925d scsi: core: Fix failure handling of scsi_add_host_with_dma() e897c103ecde ALSA: hda/realtek: headphone and mic don't work on an Acer laptop d39b22f602f5 isdn: mISDN: netjet: Fix crash in nj_probe: 1013d6a98975 nvmet: fix false keep-alive timeout when a controller is torn down 9ffec7fff577 cgroup: disable controllers at parse time e2c4bbd88218 RDMA/ipoib: Fix warning caused by destroying non-initial netns 0eb3e33d9814 gpio: wcd934x: Fix shift-out-of-bounds error af64e02cb927 NFSv4: Fix deadlock between nfs4_evict_inode() and nfs4_opendata_get_inode() 34a0d49e311d usb: dwc3: ep0: fix NULL pointer exception ca5ed7b6d2ac spi: bcm2835: Fix out-of-bounds access with more than 4 slaves 420a6301307e NFSv4: nfs4_proc_set_acl needs to restore NFS_CAP_UIDGID_NOMAP on error. 762e6acf28f1 regulator: core: resolve supply for boot-on/always-on regulators d84eb5070d03 net: macb: ensure the device is available before accessing GEMGXL control registers b9a3b65556e9 sched/fair: Make sure to update tg contrib for blocked load 074babe38e68 KVM: x86: Ensure liveliness of nested VM-Enter fail tracepoint message 447f10de04c8 ALSA: firewire-lib: fix the context to call snd_pcm_stop_xrun() 262986c9f618 dm verity: fix require_signatures module_param permissions bfa96859a312 usb: chipidea: udc: assign interrupt number to USB gadget structure 177f5f81e9fc regulator: max77620: Use device_set_of_node_from_dev() 818f49a8aa09 USB: serial: omninet: add device id for Zyxel Omni 56K Plus 1790bfdad278 spi: Cleanup on failure of initial setup 642b2258a1f7 drm/msm/a6xx: avoid shadow NULL reference in failure path be1c43cba161 USB: f_ncm: ncm_bitrate (speed) is unsigned e41037151205 nvme-fabrics: decode host pathing error for connect 期待后续合作。 Alexandre GRIVEAUX (1): USB: serial: omninet: add device id for Zyxel Omni 56K Plus Axel Lin (1): regulator: fan53880: Fix missing n_voltages setting Dai Ngo (1): NFSv4: nfs4_proc_set_acl needs to restore NFS_CAP_UIDGID_NOMAP on error. Dmitry Baryshkov (1): regulator: core: resolve supply for boot-on/always-on regulators Dmitry Osipenko (1): regulator: max77620: Use device_set_of_node_from_dev() Hannes Reinecke (1): nvme-fabrics: decode host pathing error for connect Hans de Goede (1): ASoC: Intel: bytcr_rt5640: Add quirk for the Glavey TM800A550L tablet Hui Wang (1): ALSA: hda/realtek: headphone and mic don't work on an Acer laptop Jeimon (1): net/nfc/rawsock.c: fix a permission check bug John Keeping (1): dm verity: fix require_signatures module_param permissions Jonathan Marek (1): drm/msm/a6xx: avoid shadow NULL reference in failure path Kamal Heib (1): RDMA/ipoib: Fix warning caused by destroying non-initial netns Kyle Tso (1): usb: pd: Set PD_T_SINK_WAIT_CAP to 310ms Li Jun (1): usb: chipidea: udc: assign interrupt number to USB gadget structure Lukas Wunner (2): spi: Cleanup on failure of initial setup spi: bcm2835: Fix out-of-bounds access with more than 4 slaves Maciej Żenczykowski (1): USB: f_ncm: ncm_bitrate (speed) is unsigned Marian-Cristian Rotariu (1): usb: dwc3: ep0: fix NULL pointer exception Mayank Rana (1): usb: typec: ucsi: Clear PPM capability data in ucsi_init() error path Ming Lei (2): scsi: core: Fix failure handling of scsi_add_host_with_dma() scsi: core: Only put parent device if host state differs from SHOST_CREATED Rao Shoaib (1): RDS tcp loopback connection can hang Sagi Grimberg (2): nvmet: fix false keep-alive timeout when a controller is torn down nvme-tcp: remove incorrect Kconfig dep in BLK_DEV_NVME Sean Christopherson (1): KVM: x86: Ensure liveliness of nested VM-Enter fail tracepoint message Shakeel Butt (1): cgroup: disable controllers at parse time Shay Drory (1): RDMA/mlx4: Do not map the core_clock page to user space unless enabled Srinivas Kandagatla (1): gpio: wcd934x: Fix shift-out-of-bounds error Takashi Iwai (1): ALSA: seq: Fix race of snd_seq_timer_open() Takashi Sakamoto (1): ALSA: firewire-lib: fix the context to call snd_pcm_stop_xrun() Trond Myklebust (1): NFSv4: Fix deadlock between nfs4_evict_inode() and nfs4_opendata_get_inode() Vincent Guittot (1): sched/fair: Make sure to update tg contrib for blocked load Wang Wensheng (1): phy: cadence: Sierra: Fix error return code in cdns_sierra_phy_probe() Wesley Cheng (1): usb: gadget: f_fs: Ensure io_completion_wq is idle during unbind Zhang Rui (1): Revert "ACPI: sleep: Put the FACS table after using it" Zheyu Ma (1): isdn: mISDN: netjet: Fix crash in nj_probe: Zong Li (1): net: macb: ensure the device is available before accessing GEMGXL control registers arch/x86/kvm/trace.h | 6 ++-- drivers/acpi/sleep.c | 4 +-- drivers/gpio/gpio-wcd934x.c | 2 +- drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 2 +- drivers/infiniband/hw/mlx4/main.c | 5 +-- drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 1 + drivers/isdn/hardware/mISDN/netjet.c | 1 - drivers/md/dm-verity-verify-sig.c | 2 +- drivers/net/ethernet/cadence/macb_main.c | 3 ++ drivers/net/ethernet/mellanox/mlx4/fw.c | 3 ++ drivers/net/ethernet/mellanox/mlx4/fw.h | 1 + drivers/net/ethernet/mellanox/mlx4/main.c | 6 ++++ drivers/nvme/host/Kconfig | 3 +- drivers/nvme/host/fabrics.c | 5 +++ drivers/nvme/target/core.c | 15 ++++++--- drivers/nvme/target/nvmet.h | 2 +- drivers/phy/cadence/phy-cadence-sierra.c | 1 + drivers/regulator/core.c | 6 ++++ drivers/regulator/fan53880.c | 3 ++ drivers/regulator/max77620-regulator.c | 7 +++++ drivers/scsi/hosts.c | 16 +++++----- drivers/spi/spi-bcm2835.c | 10 ++++-- drivers/spi/spi-bitbang.c | 18 ++++++++--- drivers/spi/spi-fsl-spi.c | 4 +++ drivers/spi/spi-omap-uwire.c | 9 +++++- drivers/spi/spi-omap2-mcspi.c | 33 ++++++++++++-------- drivers/spi/spi-pxa2xx.c | 9 +++++- drivers/usb/chipidea/udc.c | 1 + drivers/usb/dwc3/ep0.c | 3 ++ drivers/usb/gadget/function/f_fs.c | 3 ++ drivers/usb/gadget/function/f_ncm.c | 2 +- drivers/usb/serial/omninet.c | 2 ++ drivers/usb/typec/ucsi/ucsi.c | 1 + fs/nfs/nfs4_fs.h | 1 + fs/nfs/nfs4proc.c | 20 +++++++++++- include/linux/mlx4/device.h | 1 + include/linux/usb/pd.h | 2 +- kernel/cgroup/cgroup.c | 13 ++++---- kernel/sched/fair.c | 2 +- net/nfc/rawsock.c | 2 +- net/rds/connection.c | 23 ++++++++++---- net/rds/tcp.c | 4 +-- net/rds/tcp.h | 3 +- net/rds/tcp_listen.c | 6 ++++ sound/core/seq/seq_timer.c | 10 +++++- sound/firewire/amdtp-stream.c | 2 +- sound/pci/hda/patch_realtek.c | 12 +++++++ sound/soc/intel/boards/bytcr_rt5640.c | 11 +++++++ 48 files changed, 228 insertions(+), 73 deletions(-) -- 2.25.1

1 37

[PATCH] Add the limit on page cache
by wenzhiwei 27 Oct '21

27 Oct '21

kylin inclusion category: feature bugfix: https://gitee.com/openeuler-competition/summer-2021/issues/I3EIMT?from=proj… CVE: NA -------------------------------------------------- In some atomic operation scenarios, such as interrupt context, it is not possible to sleep. Therefore, when memory allocation in this scenario, it will not enter the direct_reclaim link, and will not even wake up the kswapd process. For example, in the soft interrupt processing function of the network card receiving packets, there may be a phenomenon that the page cache is too occupied and the remaining memory of the system is insufficient, and the memory cannot be allocated for the received data packet, and the packet is directly lost. This is the problem to be solved by the page cache limit. The page cache limit is mainly used to detect whether the page cache exceeds the upper limit we set (/proc/sys/vm/pagecache_limit_ratio) when the page cache is added to the application (that is, when the add_to_page_cache_lru function is called) Provides 3 /proc interfaces, respectively: echo x > /proc/sys/vm/pagecache_limit_ratio（0 < x < 100）:Enable page cache limit function x means limit the percentage of page cache to the total system memory /proc/sys/vm/pagecache_limit_ignore_dirty :Whether to ignore dirty pages when calculating the memory occupied by the page cache. The default value is 1, which means ignore. Because the recycling of dirty pages is time-consuming. /proc/sys/vm/pagecache_limit_async:1 means asynchronous recycling, 0 means synchronous recycling signed-off-by: wen zhiwei <wenzhiwei(a)kylinos.cn> Signed-off-by: wenzhiwei <wenzhiwei(a)kylinos.cn> --- include/linux/memcontrol.h | 7 +- include/linux/mmzone.h | 7 + include/linux/swap.h | 15 + include/trace/events/vmscan.h | 28 +- kernel/sysctl.c | 139 ++++++++ mm/filemap.c | 2 + mm/page_alloc.c | 52 +++ mm/vmscan.c | 650 ++++++++++++++++++++++++++++++++-- mm/workingset.c | 1 + 9 files changed, 862 insertions(+), 39 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 71a5b589bddb..731a2cd2ea86 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -50,6 +50,7 @@ enum memcg_memory_event { struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; + int priority; unsigned int generation; }; @@ -492,8 +493,7 @@ mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) * @node combination. This can be the node lruvec, if the memory * controller is disabled. */ -static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, - struct pglist_data *pgdat) +static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct mem_cgroup_per_node *mz; struct lruvec *lruvec; @@ -1066,8 +1066,7 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new) { } -static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, - struct pglist_data *pgdat) +static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { return &pgdat->__lruvec; } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 82fceef88448..d3c5258e5d0d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -445,6 +445,13 @@ struct zone { * changes. */ long lowmem_reserve[MAX_NR_ZONES]; + /* + * This atomic counter is set when there is pagecache limit + * reclaim going on on this particular zone. Other potential + * reclaiers should back off to prevent from heavy lru_lock + * bouncing. + */ + atomic_t pagecache_reclaim; #ifdef CONFIG_NEED_MULTIPLE_NODES int node; diff --git a/include/linux/swap.h b/include/linux/swap.h index 9b708c0288bc..b9329e575836 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -377,6 +377,21 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; + +#define ADDITIONAL_RECLAIM_RATIO 2 +extern unsigned long pagecache_over_limit(void); +extern void shrink_page_cache(gfp_t mask, struct page *page); +extern unsigned long vm_pagecache_limit_pages; +extern unsigned long vm_pagecache_limit_reclaim_pages; +extern int unsigned vm_pagecache_limit_ratio; +extern int vm_pagecache_limit_reclaim_ratio; +extern unsigned int vm_pagecache_ignore_dirty; +extern unsigned long pagecache_over_limit(void); +extern unsigned int vm_pagecache_limit_async; +extern int kpagecache_limitd_run(void); +extern void kpagecache_limitd_stop(void); +extern unsigned int vm_pagecache_ignore_slab; + extern int remove_mapping(struct address_space *mapping, struct page *page); extern unsigned long reclaim_pages(struct list_head *page_list); diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 2070df64958e..3bfe47a85f6f 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -183,48 +183,48 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_re #endif /* CONFIG_MEMCG */ TRACE_EVENT(mm_shrink_slab_start, - TP_PROTO(struct shrinker *shr, struct shrink_control *sc, - long nr_objects_to_shrink, unsigned long cache_items, - unsigned long long delta, unsigned long total_scan, - int priority), - - TP_ARGS(shr, sc, nr_objects_to_shrink, cache_items, delta, total_scan, - priority), + TP_PROTO(struct shrinker *shr, struct shrink_control *sc, + long nr_objects_to_shrink,unsigned long pgs_scanned, + unsigned long lru_pgs, unsigned long cache_items, + unsigned long long delta, unsigned long total_scan), + TP_ARGS(shr, sc, nr_objects_to_shrink,pgs_scanned, lru_pgs, cache_items, delta, total_scan), TP_STRUCT__entry( __field(struct shrinker *, shr) __field(void *, shrink) __field(int, nid) __field(long, nr_objects_to_shrink) __field(gfp_t, gfp_flags) + __field(unsigned long, pgs_scanned) + __field(unsigned long, lru_pgs) __field(unsigned long, cache_items) __field(unsigned long long, delta) __field(unsigned long, total_scan) - __field(int, priority) ), TP_fast_assign( - __entry->shr = shr; + __entry->shr = shr; __entry->shrink = shr->scan_objects; __entry->nid = sc->nid; __entry->nr_objects_to_shrink = nr_objects_to_shrink; __entry->gfp_flags = sc->gfp_mask; + __entry->pgs_scanned = pgs_scanned; + __entry->lru_pgs = lru_pgs; __entry->cache_items = cache_items; __entry->delta = delta; __entry->total_scan = total_scan; - __entry->priority = priority; ), - - TP_printk("%pS %p: nid: %d objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d", +TP_printk("%pF %p: nid: %d objects to shrink %ld gfp_flags %s pgs_scanned %ld lru_pgs %ld cache items %ld delta %lld total_scan %ld", __entry->shrink, __entry->shr, __entry->nid, __entry->nr_objects_to_shrink, show_gfp_flags(__entry->gfp_flags), + __entry->pgs_scanned, + __entry->lru_pgs, __entry->cache_items, __entry->delta, - __entry->total_scan, - __entry->priority) + __entry->total_scan) ); TRACE_EVENT(mm_shrink_slab_end, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c7ca58de3b1b..4ef436cdfdad 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -111,6 +111,7 @@ static int sixty = 60; #endif +static int zero; static int __maybe_unused neg_one = -1; static int __maybe_unused two = 2; static int __maybe_unused four = 4; @@ -648,6 +649,68 @@ static int do_proc_dointvec(struct ctl_table *table, int write, return __do_proc_dointvec(table->data, table, write, buffer, lenp, ppos, conv, data); } +int setup_pagecache_limit(void) +{ + /* reclaim $ADDITIONAL_RECLAIM_PAGES more than limit. */ + vm_pagecache_limit_reclaim_ratio = vm_pagecache_limit_ratio + ADDITIONAL_RECLAIM_RATIO; + + if (vm_pagecache_limit_reclaim_ratio > 100) + vm_pagecache_limit_reclaim_ratio = 100; + if (vm_pagecache_limit_ratio == 0) + vm_pagecache_limit_reclaim_ratio = 0; + + vm_pagecache_limit_pages = vm_pagecache_limit_ratio * totalram_pages() / 100; + vm_pagecache_limit_reclaim_pages = vm_pagecache_limit_reclaim_ratio * totalram_pages() / 100; + return 0; +} + +static int pc_limit_proc_dointvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (write && !ret) + ret = setup_pagecache_limit(); + return ret; +} +static int pc_reclaim_limit_proc_dointvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int pre_reclaim_ratio = vm_pagecache_limit_reclaim_ratio; + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (write && vm_pagecache_limit_ratio == 0) + return -EINVAL; + + if (write && !ret) { + if (vm_pagecache_limit_reclaim_ratio - vm_pagecache_limit_ratio < ADDITIONAL_RECLAIM_RATIO) { + vm_pagecache_limit_reclaim_ratio = pre_reclaim_ratio; + return -EINVAL; + } + vm_pagecache_limit_reclaim_pages = vm_pagecache_limit_reclaim_ratio * totalram_pages() / 100; + } + return ret; +} +static int pc_limit_async_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (write && vm_pagecache_limit_ratio == 0) + return -EINVAL; + + if (write && !ret) { + if (vm_pagecache_limit_async > 0) { + if (kpagecache_limitd_run()) { + vm_pagecache_limit_async = 0; + return -EINVAL; + } + } + else { + kpagecache_limitd_stop(); + } + } + return ret; +} static int do_proc_douintvec_w(unsigned int *tbl_data, struct ctl_table *table, @@ -2711,6 +2774,14 @@ static struct ctl_table kern_table[] = { }, { } }; +static int pc_limit_proc_dointvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); + +static int pc_reclaim_limit_proc_dointvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); + +static int pc_limit_async_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table vm_table[] = { { @@ -2833,6 +2904,74 @@ static struct ctl_table vm_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = &two_hundred, }, + { + .procname = "pagecache_limit_ratio", + .data = &vm_pagecache_limit_ratio, + .maxlen = sizeof(vm_pagecache_limit_ratio), + .mode = 0644, + .proc_handler = &pc_limit_proc_dointvec, + .extra1 = &zero, + .extra2 = &one_hundred, + }, + { + .procname = "pagecache_limit_reclaim_ratio", + .data = &vm_pagecache_limit_reclaim_ratio, + .maxlen = sizeof(vm_pagecache_limit_reclaim_ratio), + .mode = 0644, + .proc_handler = &pc_reclaim_limit_proc_dointvec, + .extra1 = &zero, + .extra2 = &one_hundred, + }, + { + .procname = "pagecache_limit_ignore_dirty", + .data = &vm_pagecache_ignore_dirty, + .maxlen = sizeof(vm_pagecache_ignore_dirty), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#ifdef CONFIG_SHRINK_PAGECACHE + { + .procname = "cache_reclaim_s", + .data = &vm_cache_reclaim_s, + .maxlen = sizeof(vm_cache_reclaim_s), + .mode = 0644, + .proc_handler = cache_reclaim_sysctl_handler, + .extra1 = &vm_cache_reclaim_s_min, + .extra2 = &vm_cache_reclaim_s_max, + }, + { + .procname = "cache_reclaim_weight", + .data = &vm_cache_reclaim_weight, + .maxlen = sizeof(vm_cache_reclaim_weight), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &vm_cache_reclaim_weight_min, + .extra2 = &vm_cache_reclaim_weight_max, + }, + { + .procname = "cache_reclaim_enable", + .data = &vm_cache_reclaim_enable, + .maxlen = sizeof(vm_cache_reclaim_enable), + .mode = 0644, + .proc_handler = cache_reclaim_enable_handler, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "pagecache_limit_async", + .data = &vm_pagecache_limit_async, + .maxlen = sizeof(vm_pagecache_limit_async), + .mode = 0644, + .proc_handler = &pc_limit_async_handler, + }, + { + .procname = "pagecache_limit_ignore_slab", + .data = &vm_pagecache_ignore_slab, + .maxlen = sizeof(vm_pagecache_ignore_slab), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif #ifdef CONFIG_HUGETLB_PAGE { .procname = "nr_hugepages", diff --git a/mm/filemap.c b/mm/filemap.c index ef611eb34aa7..808d4f02b5a5 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -922,6 +922,8 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, { void *shadow = NULL; int ret; + if (unlikely(vm_pagecache_limit_pages) && pagecache_over_limit() > 0) + shrink_page_cache(gfp_mask, page); __SetPageLocked(page); ret = __add_to_page_cache_locked(page, mapping, offset, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 71afec177233..08feba42d3d7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8933,6 +8933,58 @@ void zone_pcp_reset(struct zone *zone) local_irq_restore(flags); } +/* Returns a number that's positive if the pagecache is above + * the set limit*/ +unsigned long pagecache_over_limit() +{ + unsigned long should_reclaim_pages = 0; + unsigned long overlimit_pages = 0; + unsigned long delta_pages = 0; + unsigned long pgcache_lru_pages = 0; + /* We only want to limit unmapped and non-shmem page cache pages; + * normally all shmem pages are mapped as well*/ + unsigned long pgcache_pages = global_node_page_state(NR_FILE_PAGES) + - max_t(unsigned long, + global_node_page_state(NR_FILE_MAPPED), + global_node_page_state(NR_SHMEM)); + /* We certainly can't free more than what's on the LRU lists + * minus the dirty ones*/ + if (vm_pagecache_ignore_slab) + pgcache_lru_pages = global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE); + else + pgcache_lru_pages = global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE) + + global_node_page_state(NR_SLAB_RECLAIMABLE_B) + + global_node_page_state(NR_SLAB_UNRECLAIMABLE_B); + + if (vm_pagecache_ignore_dirty != 0) + pgcache_lru_pages -= global_node_page_state(NR_FILE_DIRTY) / vm_pagecache_ignore_dirty; + /* Paranoia */ + if (unlikely(pgcache_lru_pages > LONG_MAX)) + return 0; + + /* Limit it to 94% of LRU (not all there might be unmapped) */ + pgcache_lru_pages -= pgcache_lru_pages/16; + if (vm_pagecache_ignore_slab) + pgcache_pages = min_t(unsigned long, pgcache_pages, pgcache_lru_pages); + else + pgcache_pages = pgcache_lru_pages; + + /* + *delta_pages: we should reclaim at least 2% more pages than overlimit_page, values get from + * /proc/vm/pagecache_limit_reclaim_pages + *should_reclaim_pages: the real pages we will reclaim, but it should less than pgcache_pages; + */ + if (pgcache_pages > vm_pagecache_limit_pages) { + overlimit_pages = pgcache_pages - vm_pagecache_limit_pages; + delta_pages = vm_pagecache_limit_reclaim_pages - vm_pagecache_limit_pages; + should_reclaim_pages = min_t(unsigned long, delta_pages, vm_pagecache_limit_pages) + overlimit_pages; + return should_reclaim_pages; + } + return 0; +} + #ifdef CONFIG_MEMORY_HOTREMOVE /* * All pages in the range must be in a single zone, must not contain holes, diff --git a/mm/vmscan.c b/mm/vmscan.c index 23f8a5242de7..1fe2c74a1c10 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -175,6 +175,39 @@ struct scan_control { */ int vm_swappiness = 60; +/* + * The total number of pages which are beyond the high watermark within all + * zones. + */ +unsigned long vm_pagecache_limit_pages __read_mostly = 0; +unsigned long vm_pagecache_limit_reclaim_pages = 0; +unsigned int vm_pagecache_limit_ratio __read_mostly = 0; +int vm_pagecache_limit_reclaim_ratio __read_mostly = 0; +unsigned int vm_pagecache_ignore_dirty __read_mostly = 1; + +unsigned long vm_total_pages; +static struct task_struct *kpclimitd = NULL; +unsigned int vm_pagecache_ignore_slab __read_mostly = 1; +unsigned int vm_pagecache_limit_async __read_mostly = 0; + +#ifdef CONFIG_SHRINK_PAGECACHE +unsigned long vm_cache_limit_ratio; +unsigned long vm_cache_limit_ratio_min; +unsigned long vm_cache_limit_ratio_max; +unsigned long vm_cache_limit_mbytes __read_mostly; +unsigned long vm_cache_limit_mbytes_min; +unsigned long vm_cache_limit_mbytes_max; +static bool kpclimitd_context = false; +int vm_cache_reclaim_s __read_mostly; +int vm_cache_reclaim_s_min; +int vm_cache_reclaim_s_max; +int vm_cache_reclaim_weight __read_mostly; +int vm_cache_reclaim_weight_min; +int vm_cache_reclaim_weight_max; +int vm_cache_reclaim_enable; +static DEFINE_PER_CPU(struct delayed_work, vmscan_work); +#endif + static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { @@ -187,10 +220,12 @@ static void set_task_reclaim_state(struct task_struct *task, task->reclaim_state = rs; } +static bool kpclimitd_context = false; static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG +static DEFINE_IDR(shrinker_idr); static int shrinker_nr_max; /* The shrinker_info is expanded in a batch of BITS_PER_LONG */ @@ -346,7 +381,6 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) } } -static DEFINE_IDR(shrinker_idr); static int prealloc_memcg_shrinker(struct shrinker *shrinker) { @@ -646,7 +680,9 @@ EXPORT_SYMBOL(unregister_shrinker); #define SHRINK_BATCH 128 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, - struct shrinker *shrinker, int priority) + struct shrinker *shrinker, + unsigned long nr_scanned, + unsigned long nr_eligible) { unsigned long freed = 0; unsigned long long delta; @@ -670,8 +706,10 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, nr = xchg_nr_deferred(shrinker, shrinkctl); if (shrinker->seeks) { - delta = freeable >> priority; - delta *= 4; + //delta = freeable >> priority; + //delta *= 4; + delta = (4 * nr_scanned) / shrinker->seeks; + delta *= freeable; do_div(delta, shrinker->seeks); } else { /* @@ -682,12 +720,12 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, delta = freeable / 2; } - total_scan = nr >> priority; + total_scan = nr; total_scan += delta; total_scan = min(total_scan, (2 * freeable)); trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, - freeable, delta, total_scan, priority); + freeable, delta, total_scan, nr_scanned,nr_eligible); /* * Normally, we should not scan less than batch_size objects in one @@ -744,7 +782,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, #ifdef CONFIG_MEMCG static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, int priority) + struct mem_cgroup *memcg, unsigned long nr_scanned, unsigned long nr_eligible) { struct shrinker_info *info; unsigned long ret, freed = 0; @@ -780,7 +818,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, !(shrinker->flags & SHRINKER_NONSLAB)) continue; - ret = do_shrink_slab(&sc, shrinker, priority); + ret = do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible); if (ret == SHRINK_EMPTY) { clear_bit(i, info->map); /* @@ -799,7 +837,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, * set_bit() do_shrink_slab() */ smp_mb__after_atomic(); - ret = do_shrink_slab(&sc, shrinker, priority); + ret = do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible); if (ret == SHRINK_EMPTY) ret = 0; else @@ -846,7 +884,8 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, */ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, - int priority) + unsigned long nr_scanned, + unsigned long nr_eligible) { unsigned long ret, freed = 0; struct shrinker *shrinker; @@ -859,7 +898,8 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, * oom. */ if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) - return shrink_slab_memcg(gfp_mask, nid, memcg, priority); + return 0; + // return shrink_slab_memcg(gfp_mask, nid, memcg, priority); if (!down_read_trylock(&shrinker_rwsem)) goto out; @@ -871,7 +911,14 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, .memcg = memcg, }; - ret = do_shrink_slab(&sc, shrinker, priority); + if (memcg_kmem_enabled() && + !!memcg != !!(shrinker->flags & SHRINKER_MEMCG_AWARE)) + continue; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + sc.nid = 0; + + ret = do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible); if (ret == SHRINK_EMPTY) ret = 0; freed += ret; @@ -905,7 +952,7 @@ void drop_slab_node(int nid) freed = 0; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { - freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); + freed += shrink_slab(GFP_KERNEL, nid, memcg, 1000,1000); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); } while (freed > 10); } @@ -2369,7 +2416,7 @@ unsigned long reclaim_pages(struct list_head *page_list) EXPORT_SYMBOL_GPL(reclaim_pages); static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, - struct lruvec *lruvec, struct scan_control *sc) + struct lruvec *lruvec, struct mem_cgroup *memcg, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) @@ -2683,7 +2730,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, - lruvec, sc); + lruvec, NULL, sc); } } @@ -2836,7 +2883,7 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long reclaimed; unsigned long scanned; - + unsigned long lru_pages; /* * This loop can become CPU-bound when target memcgs * aren't eligible for reclaim - either because they @@ -2873,7 +2920,8 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, - sc->priority); + sc->nr_scanned - scanned, + lru_pages); /* Record the group's reclaim efficiency */ vmpressure(sc->gfp_mask, memcg, false, @@ -3202,6 +3250,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { + struct mem_cgroup *memcg; struct lruvec *target_lruvec; unsigned long refaults; @@ -3273,8 +3322,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, if (cgroup_reclaim(sc)) { struct lruvec *lruvec; - lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, - zone->zone_pgdat); + lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, zone->zone_pgdat); clear_bit(LRUVEC_CONGESTED, &lruvec->flags); } } @@ -3745,6 +3793,8 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, return sc->nr_scanned >= sc->nr_to_reclaim; } +static void __shrink_page_cache(gfp_t mask); + /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is @@ -4208,6 +4258,27 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, wake_up_interruptible(&pgdat->kswapd_wait); } +/* + * The reclaimable count would be mostly accurate. + * The less reclaimable pages may be + * - mlocked pages, which will be moved to unevictable list when encountered + * - mapped pages, which may require several travels to be reclaimed + * - dirty pages, which is not "instantly" reclaimable + */ + +static unsigned long global_reclaimable_pages(void) +{ + int nr; + + nr = global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE); + + if (get_nr_swap_pages() > 0) + nr += global_node_page_state(NR_ACTIVE_ANON) + + global_node_page_state(NR_INACTIVE_ANON); + return nr; +} + #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of @@ -4246,6 +4317,498 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) return nr_reclaimed; } #endif /* CONFIG_HIBERNATION */ +/* + * Returns non-zero if the lock has been acquired, false if somebody + * else is holding the lock. + */ +static int pagecache_reclaim_lock_zone(struct zone *zone) +{ + return atomic_add_unless(&zone->pagecache_reclaim, 1, 1); +} + +static void pagecache_reclaim_unlock_zone(struct zone *zone) +{ + BUG_ON(atomic_dec_return(&zone->pagecache_reclaim)); +} + +/* + * Potential page cache reclaimers who are not able to take + * reclaim lock on any zone are sleeping on this waitqueue. + * So this is basically a congestion wait queue for them. + */ +DECLARE_WAIT_QUEUE_HEAD(pagecache_reclaim_wq); +DECLARE_WAIT_QUEUE_HEAD(kpagecache_limitd_wq); + +/* + * Similar to shrink_zone but it has a different consumer - pagecache limit + * so we cannot reuse the original function - and we do not want to clobber + * that code path so we have to live with this code duplication. + * + * In short this simply scans through the given lru for all cgroups for the + * give zone. + * + * returns true if we managed to cumulatively reclaim (via nr_reclaimed) + * the given nr_to_reclaim pages, false otherwise. The caller knows that + * it doesn't have to touch other zones if the target was hit already. + * + * DO NOT USE OUTSIDE of shrink_all_zones unless you have a really really + * really good reason. + */ + +static bool shrink_zone_per_memcg(struct zone *zone, enum lru_list lru, + unsigned long nr_to_scan, unsigned long nr_to_reclaim, + unsigned long *nr_reclaimed, struct scan_control *sc) +{ + struct mem_cgroup *root = sc->target_mem_cgroup; + struct mem_cgroup *memcg; + struct mem_cgroup_reclaim_cookie reclaim = { + .pgdat = zone->zone_pgdat, + .priority = sc->priority, + }; + + memcg = mem_cgroup_iter(root, NULL, &reclaim); + do { + struct lruvec *lruvec; + + lruvec = mem_cgroup_lruvec(memcg, zone->zone_pgdat); + *nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, memcg, sc); + if (*nr_reclaimed >= nr_to_reclaim) { + mem_cgroup_iter_break(root, memcg); + return true; + } + memcg = mem_cgroup_iter(root, memcg, &reclaim); + } while (memcg); + + return false; +} +/* + * Tries to reclaim 'nr_pages' pages from LRU lists system-wide, for given + * pass. + * + * For pass > 3 we also try to shrink the LRU lists that contain a few pages + * + * Returns the number of scanned zones. + */ +static int shrink_all_zones(unsigned long nr_pages, int pass, + struct scan_control *sc) +{ + struct zone *zone; + unsigned long nr_reclaimed = 0; + unsigned int nr_locked_zones = 0; + DEFINE_WAIT(wait); + + prepare_to_wait(&pagecache_reclaim_wq, &wait, TASK_INTERRUPTIBLE); + + for_each_populated_zone(zone) { + enum lru_list lru; + + /* + * Back off if somebody is already reclaiming this zone + * for the pagecache reclaim. + */ + if (!pagecache_reclaim_lock_zone(zone)) + continue; + + + /* + * This reclaimer might scan a zone so it will never + * sleep on pagecache_reclaim_wq + */ + finish_wait(&pagecache_reclaim_wq, &wait); + nr_locked_zones++; + + for_each_evictable_lru(lru) { + enum zone_stat_item ls = NR_ZONE_LRU_BASE + lru; + unsigned long lru_pages = zone_page_state(zone, ls); + + /* For pass = 0, we don't shrink the active list */ + if (pass == 0 && (lru == LRU_ACTIVE_ANON || + lru == LRU_ACTIVE_FILE)) + continue; + + /* Original code relied on nr_saved_scan which is no + * longer present so we are just considering LRU pages. + * This means that the zone has to have quite large + * LRU list for default priority and minimum nr_pages + * size (8*SWAP_CLUSTER_MAX). In the end we will tend + * to reclaim more from large zones wrt. small. + * This should be OK because shrink_page_cache is called + * when we are getting to short memory condition so + * LRUs tend to be large. + */ + if (((lru_pages >> sc->priority) + 1) >= nr_pages || pass >= 3) { + unsigned long nr_to_scan; + + nr_to_scan = min(nr_pages, lru_pages); + + /* + * A bit of a hack but the code has always been + * updating sc->nr_reclaimed once per shrink_all_zones + * rather than accumulating it for all calls to shrink + * lru. This costs us an additional argument to + * shrink_zone_per_memcg but well... + * + * Let's stick with this for bug-to-bug compatibility + */ + while (nr_to_scan > 0) { + /* shrink_list takes lru_lock with IRQ off so we + * should be careful about really huge nr_to_scan + */ + unsigned long batch = min_t(unsigned long, nr_to_scan, SWAP_CLUSTER_MAX); + + if (shrink_zone_per_memcg(zone, lru, + batch, nr_pages, &nr_reclaimed, sc)) { + pagecache_reclaim_unlock_zone(zone); + goto out_wakeup; + } + nr_to_scan -= batch; + } + } + } + pagecache_reclaim_unlock_zone(zone); + } + /* + * We have to go to sleep because all the zones are already reclaimed. + * One of the reclaimer will wake us up or __shrink_page_cache will + * do it if there is nothing to be done. + */ + if (!nr_locked_zones) { + if (!kpclimitd_context) + schedule(); + finish_wait(&pagecache_reclaim_wq, &wait); + goto out; + } + +out_wakeup: + wake_up_interruptible(&pagecache_reclaim_wq); + sc->nr_reclaimed += nr_reclaimed; +out: + return nr_locked_zones; +} + +/* + * Function to shrink the page cache + * + * This function calculates the number of pages (nr_pages) the page + * cache is over its limit and shrinks the page cache accordingly. + * + * The maximum number of pages, the page cache shrinks in one call of + * this function is limited to SWAP_CLUSTER_MAX pages. Therefore it may + * require a number of calls to actually reach the vm_pagecache_limit_kb. + * + * This function is similar to shrink_all_memory, except that it may never + * swap out mapped pages and only does four passes. + */ +static void __shrink_page_cache(gfp_t mask) +{ + unsigned long ret = 0; + int pass = 0; + struct reclaim_state reclaim_state; + struct scan_control sc = { + .gfp_mask = mask, + .may_swap = 0, + .may_unmap = 0, + .may_writepage = 0, + .target_mem_cgroup = NULL, + .reclaim_idx = MAX_NR_ZONES, + }; + struct reclaim_state *old_rs = current->reclaim_state; + long nr_pages; + + /* We might sleep during direct reclaim so make atomic context + * is certainly a bug. + */ + BUG_ON(!(mask & __GFP_RECLAIM)); + +retry: + /* How many pages are we over the limit?*/ + nr_pages = pagecache_over_limit(); + + /* + * Return early if there's no work to do. + * Wake up reclaimers that couldn't scan any zone due to congestion. + * There is apparently nothing to do so they do not have to sleep. + * This makes sure that no sleeping reclaimer will stay behind. + * Allow breaching the limit if the task is on the way out. + */ + if (nr_pages <= 0 || fatal_signal_pending(current)) { + wake_up_interruptible(&pagecache_reclaim_wq); + goto out; + } + + /* But do a few at least */ + nr_pages = max_t(unsigned long, nr_pages, 8*SWAP_CLUSTER_MAX); + + current->reclaim_state = &reclaim_state; + + /* + * Shrink the LRU in 4 passes: + * 0 = Reclaim from inactive_list only (fast) + * 1 = Reclaim from active list but don't reclaim mapped and dirtied (not that fast) + * 2 = Reclaim from active list but don't reclaim mapped (2nd pass) + * it may reclaim dirtied if vm_pagecache_ignore_dirty = 0 + * 3 = same as pass 2, but it will reclaim some few pages , detail in shrink_all_zones + */ + for (; pass <= 3; pass++) { + for (sc.priority = DEF_PRIORITY; sc.priority >= 0; sc.priority--) { + unsigned long nr_to_scan = nr_pages - ret; + struct mem_cgroup *memcg = NULL; + int nid; + + sc.nr_scanned = 0; + + /* + * No zone reclaimed because of too many reclaimers. Retry whether + * there is still something to do + */ + if (!shrink_all_zones(nr_to_scan, pass, &sc)) + goto retry; + + ret += sc.nr_reclaimed; + if (ret >= nr_pages) + goto out; + + reclaim_state.reclaimed_slab = 0; + for_each_online_node(nid) { + do { + shrink_slab(mask, nid, memcg, sc.nr_scanned, + global_reclaimable_pages()); + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); + } + ret += reclaim_state.reclaimed_slab; + + if (ret >= nr_pages) + goto out; + + } + if (pass == 1) { + if (vm_pagecache_ignore_dirty == 1 || + (mask & (__GFP_IO | __GFP_FS)) != (__GFP_IO | __GFP_FS) ) + break; + else + sc.may_writepage = 1; + } + } + +out: + current->reclaim_state = old_rs; +} + +#ifdef CONFIG_SHRINK_PAGECACHE +static unsigned long __shrink_page_cache(gfp_t mask) +{ + struct scan_control sc = { + .gfp_mask = current_gfp_context(mask), + .reclaim_idx = gfp_zone(mask), + .may_writepage = !laptop_mode, + .nr_to_reclaim = SWAP_CLUSTER_MAX * + (unsigned long)vm_cache_reclaim_weight, + .may_unmap = 1, + .may_swap = 1, + .order = 0, + .priority = DEF_PRIORITY, + .target_mem_cgroup = NULL, + .nodemask = NULL, + }; + + struct zonelist *zonelist = node_zonelist(numa_node_id(), mask); + + return do_try_to_free_pages(zonelist, &sc); +} + + +static void shrink_page_cache_work(struct work_struct *w); +static void shrink_shepherd(struct work_struct *w); +static DECLARE_DEFERRABLE_WORK(shepherd, shrink_shepherd); + +static void shrink_shepherd(struct work_struct *w) +{ + int cpu; + + get_online_cpus(); + + for_each_online_cpu(cpu) { + struct delayed_work *work = &per_cpu(vmscan_work, cpu); + + if (!delayed_work_pending(work) && vm_cache_reclaim_enable) + queue_delayed_work_on(cpu, system_wq, work, 0); + } + + put_online_cpus(); + + /* we want all kernel thread to stop */ + if (vm_cache_reclaim_enable) { + if (vm_cache_reclaim_s == 0) + schedule_delayed_work(&shepherd, + round_jiffies_relative(120 * HZ)); + else + schedule_delayed_work(&shepherd, + round_jiffies_relative((unsigned long) + vm_cache_reclaim_s * HZ)); + } +} +static void shrink_shepherd_timer(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct delayed_work *work = &per_cpu(vmscan_work, cpu); + + INIT_DEFERRABLE_WORK(work, shrink_page_cache_work); + } + + schedule_delayed_work(&shepherd, + round_jiffies_relative((unsigned long)vm_cache_reclaim_s * HZ)); +} + +unsigned long shrink_page_cache(gfp_t mask) +{ + unsigned long nr_pages; + + /* We reclaim the highmem zone too, it is useful for 32bit arch */ + nr_pages = __shrink_page_cache(mask | __GFP_HIGHMEM); + + return nr_pages; +} +static void shrink_page_cache_work(struct work_struct *w) +{ + struct delayed_work *work = to_delayed_work(w); + unsigned long nr_pages; + + /* + * if vm_cache_reclaim_enable or vm_cache_reclaim_s is zero, + * we do not shrink page cache again. + */ + if (vm_cache_reclaim_s == 0 || !vm_cache_reclaim_enable) + return; + + /* It should wait more time if we hardly reclaim the page cache */ + nr_pages = shrink_page_cache(GFP_KERNEL); + if ((nr_pages < SWAP_CLUSTER_MAX) && vm_cache_reclaim_enable) + queue_delayed_work_on(smp_processor_id(), system_wq, work, + round_jiffies_relative(120 * HZ)); +} + +static void shrink_page_cache_init(void) +{ + vm_cache_limit_ratio = 0; + vm_cache_limit_ratio_min = 0; + vm_cache_limit_ratio_max = 100; + vm_cache_limit_mbytes = 0; + vm_cache_limit_mbytes_min = 0; + vm_cache_limit_mbytes_max = totalram_pages >> (20 - PAGE_SHIFT); + vm_cache_reclaim_s = 0; + vm_cache_reclaim_s_min = 0; + vm_cache_reclaim_s_max = 43200; + vm_cache_reclaim_weight = 1; + vm_cache_reclaim_weight_min = 1; + vm_cache_reclaim_weight_max = 100; + vm_cache_reclaim_enable = 1; + + shrink_shepherd_timer(); +} + +static int kswapd_cpu_down_prep(unsigned int cpu) +{ + cancel_delayed_work_sync(&per_cpu(vmscan_work, cpu)); + + return 0; +} +int cache_reclaim_enable_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (ret) + return ret; + + if (write) + schedule_delayed_work(&shepherd, round_jiffies_relative((unsigned long)vm_cache_reclaim_s * HZ)); + + return 0; +} + +int cache_reclaim_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (ret) + return ret; + + if (write) + mod_delayed_work(system_wq, &shepherd, + round_jiffies_relative( + (unsigned long)vm_cache_reclaim_s * HZ)); + + return ret; +} +#endif + +static int kpagecache_limitd(void *data) +{ + DEFINE_WAIT(wait); + kpclimitd_context = true; + + /* + * make sure all work threads woken up, when switch to async mode + */ + if (waitqueue_active(&pagecache_reclaim_wq)) + wake_up_interruptible(&pagecache_reclaim_wq); + + for ( ; ; ) { + __shrink_page_cache(GFP_KERNEL); + prepare_to_wait(&kpagecache_limitd_wq, &wait, TASK_INTERRUPTIBLE); + + if (!kthread_should_stop()) + schedule(); + else { + finish_wait(&kpagecache_limitd_wq, &wait); + break; + } + finish_wait(&kpagecache_limitd_wq, &wait); + } + kpclimitd_context = false; + return 0; +} + +static void wakeup_kpclimitd(gfp_t mask) +{ + if (!waitqueue_active(&kpagecache_limitd_wq)) + return; + wake_up_interruptible(&kpagecache_limitd_wq); +} + +void shrink_page_cache(gfp_t mask, struct page *page) +{ + if (0 == vm_pagecache_limit_async) + __shrink_page_cache(mask); + else + wakeup_kpclimitd(mask); +} + +/* It's optimal to keep kswapds on the same CPUs as their memory, but + not required for correctness. So if the last cpu in a node goes + away, we get changed to run anywhere: as the first one comes back, + restore their cpu bindings. */ +static int kswapd_cpu_online(unsigned int cpu) +{ + int nid; + + for_each_node_state(nid, N_MEMORY) { + pg_data_t *pgdat = NODE_DATA(nid); + const struct cpumask *mask; + + mask = cpumask_of_node(pgdat->node_id); + + if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids) + /* One of our CPUs online: restore mask */ + set_cpus_allowed_ptr(pgdat->kswapd, mask); + } + return 0; +} /* * This kswapd start function will be called by init and node-hot-add. @@ -4286,16 +4849,61 @@ void kswapd_stop(int nid) static int __init kswapd_init(void) { - int nid; + /*int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); - return 0; + return 0;*/ + int nid, ret; + + swap_setup(); + for_each_node_state(nid, N_MEMORY) + kswapd_run(nid); +#ifdef CONFIG_SHRINK_PAGECACHE + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "mm/vmscan:online", kswapd_cpu_online, + kswapd_cpu_down_prep); +#else + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "mm/vmscan:online", kswapd_cpu_online, + NULL); +#endif + WARN_ON(ret < 0); +#ifdef CONFIG_SHRINK_PAGECACHE + shrink_page_cache_init(); +#endif + return 0; + } module_init(kswapd_init) +int kpagecache_limitd_run(void) +{ + int ret = 0; + + if (kpclimitd) + return 0; + + kpclimitd = kthread_run(kpagecache_limitd, NULL, "kpclimitd"); + if (IS_ERR(kpclimitd)) { + pr_err("Failed to start kpagecache_limitd thread\n"); + ret = PTR_ERR(kpclimitd); + kpclimitd = NULL; + } + return ret; + +} + +void kpagecache_limitd_stop(void) +{ + if (kpclimitd) { + kthread_stop(kpclimitd); + kpclimitd = NULL; + } +} + #ifdef CONFIG_NUMA /* * Node reclaim mode diff --git a/mm/workingset.c b/mm/workingset.c index bba4380405b4..9a5ad145b9bd 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -253,6 +253,7 @@ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages) void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) { struct pglist_data *pgdat = page_pgdat(page); + struct mem_cgroup *memcg = page_memcg(page); unsigned long eviction; struct lruvec *lruvec; int memcgid; -- 2.30.0

1 0

[PATCH kernel-4.19] drivers/txgbe: fix buffer not null terminated by strncpy in txgbe_ethtool.c
by shenzijun 26 Oct '21

26 Oct '21

From: 沈子俊 <shenzijun(a)kylinos.cn> kylin inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AG3E?from=project-issue CVE: NA --------------------------------------------------- change copy size in the function strncpy(). Signed-off-by: 沈子俊 <shenzijun(a)kylinos.cn> --- drivers/net/ethernet/netswift/txgbe/txgbe_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/netswift/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/netswift/txgbe/txgbe_ethtool.c index 5cb8ef61e04b..9af9f19fb491 100644 --- a/drivers/net/ethernet/netswift/txgbe/txgbe_ethtool.c +++ b/drivers/net/ethernet/netswift/txgbe/txgbe_ethtool.c @@ -1040,7 +1040,7 @@ static void txgbe_get_drvinfo(struct net_device *netdev, strncpy(drvinfo->version, txgbe_driver_version, sizeof(drvinfo->version) - 1); strncpy(drvinfo->fw_version, adapter->eeprom_id, - sizeof(drvinfo->fw_version)); + sizeof(drvinfo->fw_version) - 1); strncpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info) - 1); if (adapter->num_tx_queues <= TXGBE_NUM_RX_QUEUES) { -- 2.30.0

1 0

[PATCH openEuler-1.0-LTS] blk-mq: complete req in softirq context in case of single queue
by Yang Yingliang 26 Oct '21

26 Oct '21

From: Ming Lei <ming.lei(a)redhat.com> mainline inclusion from mainline-4.20-rc1 commit 36e765392e48e0322222347c4d21078c0b94758c category: bugfix bugzilla: 175585 CVE: NA ------------------------------------------------- Lot of controllers may have only one irq vector for completing IO request. And usually affinity of the only irq vector is all possible CPUs, however, on most of ARCH, there may be only one specific CPU for handling this interrupt. So if all IOs are completed in hardirq context, it is inevitable to degrade IO performance because of increased irq latency. This patch tries to address this issue by allowing to complete request in softirq context, like the legacy IO path. IOPS is observed as ~13%+ in the following randread test on raid0 over virtio-scsi. mdadm --create --verbose /dev/md0 --level=0 --chunk=1024 --raid-devices=8 /dev/sdb /dev/sdc /dev/sdd /dev/sde /dev/sdf /dev/sdg /dev/sdh /dev/sdi fio --time_based --name=benchmark --runtime=30 --filename=/dev/md0 --nrfiles=1 --ioengine=libaio --iodepth=32 --direct=1 --invalidate=1 --verify=0 --verify_fatal=0 --numjobs=32 --rw=randread --blocksize=4k Cc: Dongli Zhang <dongli.zhang(a)oracle.com> Cc: Zach Marano <zmarano(a)google.com> Cc: Christoph Hellwig <hch(a)lst.de> Cc: Bart Van Assche <bvanassche(a)acm.org> Cc: Jianchao Wang <jianchao.w.wang(a)oracle.com> Signed-off-by: Ming Lei <ming.lei(a)redhat.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Lihong Kou <koulihong(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-mq.c | 14 ++++++++++++++ block/blk-softirq.c | 5 ++--- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 7106c94ea58fe..55c81dcafbdc2 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -600,6 +600,20 @@ void blk_mq_force_complete_rq(struct request *rq) if (rq->internal_tag != -1) blk_mq_sched_completed_request(rq); + /* + * Most of single queue controllers, there is only one irq vector + * for handling IO completion, and the only irq's affinity is set + * as all possible CPUs. On most of ARCHs, this affinity means the + * irq is handled on one specific CPU. + * + * So complete IO reqeust in softirq context in case of single queue + * for not degrading IO performance by irqsoff latency. + */ + if (rq->q->nr_hw_queues == 1) { + __blk_complete_request(rq); + return; + } + if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) { rq->q->softirq_done_fn(rq); return; diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 15c1f5e12eb89..e47a2f751884d 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -97,8 +97,8 @@ static int blk_softirq_cpu_dead(unsigned int cpu) void __blk_complete_request(struct request *req) { - int ccpu, cpu; struct request_queue *q = req->q; + int cpu, ccpu = q->mq_ops ? req->mq_ctx->cpu : req->cpu; unsigned long flags; bool shared = false; @@ -110,8 +110,7 @@ void __blk_complete_request(struct request *req) /* * Select completion CPU */ - if (req->cpu != -1) { - ccpu = req->cpu; + if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && ccpu != -1) { if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) shared = cpus_share_cache(cpu, ccpu); } else -- 2.25.1

1 0

[PATCH kernel-4.19] blk-mq: complete req in softirq context in case of single queue
by Yang Yingliang 26 Oct '21

26 Oct '21

From: Ming Lei <ming.lei(a)redhat.com> mainline inclusion from mainline-4.20-rc1 commit 36e765392e48e0322222347c4d21078c0b94758c category: bugfix bugzilla: 175585 CVE: NA ------------------------------------------------- Lot of controllers may have only one irq vector for completing IO request. And usually affinity of the only irq vector is all possible CPUs, however, on most of ARCH, there may be only one specific CPU for handling this interrupt. So if all IOs are completed in hardirq context, it is inevitable to degrade IO performance because of increased irq latency. This patch tries to address this issue by allowing to complete request in softirq context, like the legacy IO path. IOPS is observed as ~13%+ in the following randread test on raid0 over virtio-scsi. mdadm --create --verbose /dev/md0 --level=0 --chunk=1024 --raid-devices=8 /dev/sdb /dev/sdc /dev/sdd /dev/sde /dev/sdf /dev/sdg /dev/sdh /dev/sdi fio --time_based --name=benchmark --runtime=30 --filename=/dev/md0 --nrfiles=1 --ioengine=libaio --iodepth=32 --direct=1 --invalidate=1 --verify=0 --verify_fatal=0 --numjobs=32 --rw=randread --blocksize=4k Cc: Dongli Zhang <dongli.zhang(a)oracle.com> Cc: Zach Marano <zmarano(a)google.com> Cc: Christoph Hellwig <hch(a)lst.de> Cc: Bart Van Assche <bvanassche(a)acm.org> Cc: Jianchao Wang <jianchao.w.wang(a)oracle.com> Signed-off-by: Ming Lei <ming.lei(a)redhat.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Lihong Kou <koulihong(a)huawei.com> Reviewed-by: Tao Hou <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-mq.c | 14 ++++++++++++++ block/blk-softirq.c | 5 ++--- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index be1e2ad4631aa..52a04f6ffeea2 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -603,6 +603,20 @@ void blk_mq_force_complete_rq(struct request *rq) if (rq->internal_tag != -1) blk_mq_sched_completed_request(rq); + /* + * Most of single queue controllers, there is only one irq vector + * for handling IO completion, and the only irq's affinity is set + * as all possible CPUs. On most of ARCHs, this affinity means the + * irq is handled on one specific CPU. + * + * So complete IO reqeust in softirq context in case of single queue + * for not degrading IO performance by irqsoff latency. + */ + if (rq->q->nr_hw_queues == 1) { + __blk_complete_request(rq); + return; + } + if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) { rq->q->softirq_done_fn(rq); return; diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 15c1f5e12eb89..e47a2f751884d 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -97,8 +97,8 @@ static int blk_softirq_cpu_dead(unsigned int cpu) void __blk_complete_request(struct request *req) { - int ccpu, cpu; struct request_queue *q = req->q; + int cpu, ccpu = q->mq_ops ? req->mq_ctx->cpu : req->cpu; unsigned long flags; bool shared = false; @@ -110,8 +110,7 @@ void __blk_complete_request(struct request *req) /* * Select completion CPU */ - if (req->cpu != -1) { - ccpu = req->cpu; + if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && ccpu != -1) { if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) shared = cpus_share_cache(cpu, ccpu); } else -- 2.25.1

1 0

[PATCH kernel-4.19 1/8] ovl: simplify setting of origin for index lookup
by Yang Yingliang 26 Oct '21

26 Oct '21

From: Vivek Goyal <vgoyal(a)redhat.com> mainline inclusion from mainline-v5.8-rc1 commit 59fb20138a9b5249a4176d5bbc5c670a97343061 category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- overlayfs can keep index of copied up files and directories and it seems to serve two primary puroposes. For regular files, it avoids breaking lower hardlinks over copy up. For directories it seems to be used for various error checks. During ovl_lookup(), we lookup for index using lower dentry in many a cases. That lower dentry is called "origin" and following is a summary of current logic. If there is no upperdentry, always lookup for index using lower dentry. For regular files it helps avoiding breaking hard links over copyup and for directories it seems to be just error checks. If there is an upperdentry, then there are 3 possible cases. - For directories, lower dentry is found using two ways. One is regular path based lookup in lower layers and second is using ORIGIN xattr on upper dentry. First verify that path based lookup lower dentry matches the one pointed by upper ORIGIN xattr. If yes, use this verified origin for index lookup. - For regular files (non-metacopy), there is no path based lookup in lower layers as lookup stops once we find upper dentry. So there is no origin verification. If there is ORIGIN xattr present on upper, use that to lookup index otherwise don't. - For regular metacopy files, again lower dentry is found using path based lookup as well as ORIGIN xattr on upper. Path based lookup is continued in this case to find lower data dentry for metacopy upper. So like directories we only use verified origin. If ORIGIN xattr is not present (Either because lower did not support file handles or because this is hardlink copied up with index=off), then don't use path lookup based lower dentry as origin. This is same as regular non-metacopy file case. Suggested-by: Amir Goldstein <amir73il(a)gmail.com> Signed-off-by: Vivek Goyal <vgoyal(a)redhat.com> Reviewed-by: Amir Goldstein <amir73il(a)gmail.com> Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Signed-off-by: Zheng Liang <zhengliang6(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/overlayfs/namei.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 145bfdde53feb..968ad757c578e 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -1014,25 +1014,30 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, } stack = origin_path; ctr = 1; + origin = origin_path->dentry; origin_path = NULL; } /* - * Lookup index by lower inode and verify it matches upper inode. - * We only trust dir index if we verified that lower dir matches - * origin, otherwise dir index entries may be inconsistent and we - * ignore them. + * Always lookup index if there is no-upperdentry. * - * For non-dir upper metacopy dentry, we already set "origin" if we - * verified that lower matched upper origin. If upper origin was - * not present (because lower layer did not support fh encode/decode), - * or indexing is not enabled, do not set "origin" and skip looking up - * index. This case should be handled in same way as a non-dir upper - * without ORIGIN is handled. + * For the case of upperdentry, we have set origin by now if it + * needed to be set. There are basically three cases. + * + * For directories, lookup index by lower inode and verify it matches + * upper inode. We only trust dir index if we verified that lower dir + * matches origin, otherwise dir index entries may be inconsistent + * and we ignore them. + * + * For regular upper, we already set origin if upper had ORIGIN + * xattr. There is no verification though as there is no path + * based dentry lookup in lower in this case. + * + * For metacopy upper, we set a verified origin already if index + * is enabled and if upper had an ORIGIN xattr. * - * Always lookup index of non-dir non-metacopy and non-upper. */ - if (ctr && (!upperdentry || (!d.is_dir && !metacopy))) + if (!upperdentry && ctr) origin = stack[0].dentry; if (origin && ovl_indexdir(dentry->d_sb) && -- 2.25.1

1 7

Re: [PATCH openEuler-21.03] USB: f_ncm: ncm_bitrate (speed) is unsigned
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:03, xjx00 写道: > From: Maciej Żenczykowski <maze(a)google.com> > > stable inclusion > from stable-v5.10.44 > commit 0f5a20b1fd9da3ac9f7c6edcad522712ca694d5c > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=358 > CVE: NA > > ------------------------------------------------- > > commit 3370139745853f7826895293e8ac3aec1430508e upstream. > > [ 190.544755] configfs-gadget gadget: notify speed -44967296 > > This is because 4250000000 - 2**32 is -44967296. > > Fixes: 9f6ce4240a2b ("usb: gadget: f_ncm.c added") > Cc: Brooke Basile <brookebasile(a)gmail.com> > Cc: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org> > Cc: Felipe Balbi <balbi(a)kernel.org> > Cc: Lorenzo Colitti <lorenzo(a)google.com> > Cc: Yauheni Kaliuta <yauheni.kaliuta(a)nokia.com> > Cc: Linux USB Mailing List <linux-usb(a)vger.kernel.org> > Acked-By: Lorenzo Colitti <lorenzo(a)google.com> > Signed-off-by: Maciej Żenczykowski <maze(a)google.com> > Cc: stable <stable(a)vger.kernel.org> > Link: https://lore.kernel.org/r/20210608005344.3762668-1-zenczykowski@gmail.com > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: xjx00 <xjxyklwx(a)126.com> > --- > drivers/usb/gadget/function/f_ncm.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c > index 019bea8e09cc..0d23c6c11a13 100644 > --- a/drivers/usb/gadget/function/f_ncm.c > +++ b/drivers/usb/gadget/function/f_ncm.c > @@ -583,7 +583,7 @@ static void ncm_do_notify(struct f_ncm *ncm) > data[0] = cpu_to_le32(ncm_bitrate(cdev->gadget)); > data[1] = data[0]; > > - DBG(cdev, "notify speed %d\n", ncm_bitrate(cdev->gadget)); > + DBG(cdev, "notify speed %u\n", ncm_bitrate(cdev->gadget)); > ncm->notify_state = NCM_NOTIFY_CONNECT; > break; > }

2 1

Re: [PATCH openEuler-21.03] ALSA: firewire-lib: fix the context to call snd_pcm_stop_xrun()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:17, lihao 写道: > From: Takashi Sakamoto <o-takashi(a)sakamocchi.jp> > > stable inclusion > from stable-v5.10.44 > commit 98f842951f8aa222e8a8453e6dbce6c056e9984f > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=430 > CVE: NA > > ------------------------------------------------- > > commit 9981b20a5e3694f4625ab5a1ddc98ce7503f6d12 upstream. > > In the workqueue to queue wake-up event, isochronous context is not > processed, thus it's useless to check context for the workqueue to switch > status of runtime for PCM substream to XRUN. On the other hand, in > software IRQ context of 1394 OHCI, it's needed. > > This commit fixes the bug introduced when tasklet was replaced with > workqueue. > > Cc: <stable(a)vger.kernel.org> > Fixes: 2b3d2987d800 ("ALSA: firewire: Replace tasklet with work") > Signed-off-by: Takashi Sakamoto <o-takashi(a)sakamocchi.jp> > Link: https://lore.kernel.org/r/20210605091054.68866-1-o-takashi@sakamocchi.jp > Signed-off-by: Takashi Iwai <tiwai(a)suse.de> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: lihao <380525608(a)qq.com> > --- > sound/firewire/amdtp-stream.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c > index e0faa6601966..5805c5de39fb 100644 > --- a/sound/firewire/amdtp-stream.c > +++ b/sound/firewire/amdtp-stream.c > @@ -804,7 +804,7 @@ static void generate_pkt_descs(struct amdtp_stream *s, struct pkt_desc *descs, > static inline void cancel_stream(struct amdtp_stream *s) > { > s->packet_index = -1; > - if (current_work() == &s->period_work) > + if (in_interrupt()) > amdtp_stream_pcm_abort(s); > WRITE_ONCE(s->pcm_buffer_pointer, SNDRV_PCM_POS_XRUN); > }

1 0

Re: [PATCH openEuler-21.03] drm/msm/a6xx: avoid shadow NULL reference in failure path
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:02, lzb 写道: > From: Jonathan Marek <jonathan(a)marek.ca> > > stable inclusion > from stable-v5.10.44 > commit fd681a8c7ac8f649a0718f6cbf2fe75d0587c9a2 > bugzilla: > CVE: NA > > https://bugzilla.openeuler.org/show_bug.cgi?id=472-------------------------… > > commit ce86c239e4d218ae6040bec18e6d19a58edb8b7c upstream. > > If a6xx_hw_init() fails before creating the shadow_bo, the a6xx_pm_suspend > code referencing it will crash. Change the condition to one that avoids > this problem (note: creation of shadow_bo is behind this same condition) > > Fixes: e8b0b994c3a5 ("drm/msm/a6xx: Clear shadow on suspend") > Signed-off-by: Jonathan Marek <jonathan(a)marek.ca> > Reviewed-by: Akhil P Oommen <akhilpo(a)codeaurora.org> > Link: https://lore.kernel.org/r/20210513171431.18632-6-jonathan@marek.ca > Signed-off-by: Rob Clark <robdclark(a)chromium.org> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: lzb <zbliancs(a)qq.com> > --- > drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c > index 722c2fe3bfd5..7061ba457c5b 100644 > --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c > +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c > @@ -1055,7 +1055,7 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) > if (ret) > return ret; > > - if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) > + if (a6xx_gpu->shadow_bo) > for (i = 0; i < gpu->nr_rings; i++) > a6xx_gpu->shadow[i] = 0; >

1 0

Re: [PATCH openEuler-21.03] sched/fair: Make sure to update tg contrib for blocked load
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:09, wjy 写道: > From: Vincent Guittot <vincent.guittot(a)linaro.org> > > stable inclusion > from stable-v5.10.44 > commit 32e22db8b25ea165bd9e446c7f92b089c8568eaf > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=379 > CVE: NA > > ------------------------------------------------- > > commit 02da26ad5ed6ea8680e5d01f20661439611ed776 upstream. > > During the update of fair blocked load (__update_blocked_fair()), we > update the contribution of the cfs in tg->load_avg if cfs_rq's pelt > has decayed. Nevertheless, the pelt values of a cfs_rq could have > been recently updated while propagating the change of a child. In this > case, cfs_rq's pelt will not decayed because it has already been > updated and we don't update tg->load_avg. > > __update_blocked_fair > ... > for_each_leaf_cfs_rq_safe: child cfs_rq > update cfs_rq_load_avg() for child cfs_rq > ... > update_load_avg(cfs_rq_of(se), se, 0) > ... > update cfs_rq_load_avg() for parent cfs_rq > -propagation of child's load makes parent cfs_rq->load_sum > becoming null > -UPDATE_TG is not set so it doesn't update parent > cfs_rq->tg_load_avg_contrib > .. > for_each_leaf_cfs_rq_safe: parent cfs_rq > update cfs_rq_load_avg() for parent cfs_rq > - nothing to do because parent cfs_rq has already been updated > recently so cfs_rq->tg_load_avg_contrib is not updated > ... > parent cfs_rq is decayed > list_del_leaf_cfs_rq parent cfs_rq > - but it still contibutes to tg->load_avg > > we must set UPDATE_TG flags when propagting pending load to the parent > > Fixes: 039ae8bcf7a5 ("sched/fair: Fix O(nr_cgroups) in the load balancing path") > Reported-by: Odin Ugedal <odin(a)uged.al> > Signed-off-by: Vincent Guittot <vincent.guittot(a)linaro.org> > Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> > Reviewed-by: Odin Ugedal <odin(a)uged.al> > Link: https://lkml.kernel.org/r/20210527122916.27683-3-vincent.guittot@linaro.org > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: wjy <464310675(a)qq.com> > --- > kernel/sched/fair.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c > index 1ad0e52487f6..43497d88a330 100644 > --- a/kernel/sched/fair.c > +++ b/kernel/sched/fair.c > @@ -7961,7 +7961,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) > /* Propagate pending load changes to the parent, if any: */ > se = cfs_rq->tg->se[cpu]; > if (se && !skip_blocked_update(se)) > - update_load_avg(cfs_rq_of(se), se, 0); > + update_load_avg(cfs_rq_of(se), se, UPDATE_TG); > > /* > * There can be a lot of idle CPU cgroups. Don't let fully

1 0

Re: [PATCH openEuler-21.03] NFSv4: Fix second deadlock in nfs4_evict_inode()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:13, wyp 写道: > From: Trond Myklebust <trond.myklebust(a)hammerspace.com> > > stable inclusion > from stable-v5.10.44 > commit d973bd0d6e7f9b4ea976cc619e8d6e0d235b9056 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=462 > CVE: NA > > ------------------------------------------------- > > commit c3aba897c6e67fa464ec02b1f17911577d619713 upstream. > > If the inode is being evicted but has to return a layout first, then > that too can cause a deadlock in the corner case where the server > reboots. > > Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: Hang <haihangyiyuan(a)163.com> > Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> > Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> > --- > fs/nfs/nfs4proc.c | 9 +++++++-- > 1 file changed, 7 insertions(+), 2 deletions(-) > > diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c > index c92d6ff0fcea..eedcbe6832fb 100644 > --- a/fs/nfs/nfs4proc.c > +++ b/fs/nfs/nfs4proc.c > @@ -9619,15 +9619,20 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) > &task_setup_data.rpc_client, &msg); > > dprintk("--> %s\n", __func__); > + lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!sync) { > - lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!lrp->inode) { > nfs4_layoutreturn_release(lrp); > return -EAGAIN; > } > task_setup_data.flags |= RPC_TASK_ASYNC; > } > - nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, 0); > + if (!lrp->inode) > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 1); > + else > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 0); > task = rpc_run_task(&task_setup_data); > if (IS_ERR(task)) > return PTR_ERR(task);

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:15, gpj 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:18, dqh 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] spi: Cleanup on failure of initial setup
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:18, dqh 写道: > From: Lukas Wunner <lukas(a)wunner.de> > > stable inclusion > from stable-v5.10.44 > commit fa05ba61967ad051f5f2b7c4f39d6c56719c9900 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=470 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 2ec6f20b33eb4f62ab90bdcd620436c883ec3af6 ] > > Commit c7299fea6769 ("spi: Fix spi device unregister flow") changed the > SPI core's behavior if the ->setup() hook returns an error upon adding > an spi_device: Before, the ->cleanup() hook was invoked to free any > allocations that were made by ->setup(). With the commit, that's no > longer the case, so the ->setup() hook is expected to free the > allocations itself. > > I've identified 5 drivers which depend on the old behavior and am fixing > them up hereinafter: spi-bitbang.c spi-fsl-spi.c spi-omap-uwire.c > spi-omap2-mcspi.c spi-pxa2xx.c > > Importantly, ->setup() is not only invoked on spi_device *addition*: > It may subsequently be called to *change* SPI parameters. If changing > these SPI parameters fails, freeing memory allocations would be wrong. > That should only be done if the spi_device is finally destroyed. > I am therefore using a bool "initial_setup" in 4 of the affected drivers > to differentiate between the invocation on *adding* the spi_device and > any subsequent invocations: spi-bitbang.c spi-fsl-spi.c spi-omap-uwire.c > spi-omap2-mcspi.c > > In spi-pxa2xx.c, it seems the ->setup() hook can only fail on spi_device > addition, not any subsequent calls. It therefore doesn't need the bool. > > It's worth noting that 5 other drivers already perform a cleanup if the > ->setup() hook fails. Before c7299fea6769, they caused a double-free > if ->setup() failed on spi_device addition. Since the commit, they're > fine. These drivers are: spi-mpc512x-psc.c spi-pl022.c spi-s3c64xx.c > spi-st-ssc4.c spi-tegra114.c > > (spi-pxa2xx.c also already performs a cleanup, but only in one of > several error paths.) > > Fixes: c7299fea6769 ("spi: Fix spi device unregister flow") > Signed-off-by: Lukas Wunner <lukas(a)wunner.de> > Cc: Saravana Kannan <saravanak(a)google.com> > Acked-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com> # pxa2xx > Link: https://lore.kernel.org/r/f76a0599469f265b69c371538794101fa37b5536.16221493… > Signed-off-by: Mark Brown <broonie(a)kernel.org> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: dqh <1486653795(a)qq.com> > --- > drivers/spi/spi-bitbang.c | 18 ++++++++++++++---- > drivers/spi/spi-fsl-spi.c | 4 ++++ > drivers/spi/spi-omap-uwire.c | 9 ++++++++- > drivers/spi/spi-omap2-mcspi.c | 33 ++++++++++++++++++++------------- > drivers/spi/spi-pxa2xx.c | 9 ++++++++- > 5 files changed, 54 insertions(+), 19 deletions(-) > > diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c > index 1a7352abd878..3d8948a17095 100644 > --- a/drivers/spi/spi-bitbang.c > +++ b/drivers/spi/spi-bitbang.c > @@ -181,6 +181,8 @@ int spi_bitbang_setup(struct spi_device *spi) > { > struct spi_bitbang_cs *cs = spi->controller_state; > struct spi_bitbang *bitbang; > + bool initial_setup = false; > + int retval; > > bitbang = spi_master_get_devdata(spi->master); > > @@ -189,22 +191,30 @@ int spi_bitbang_setup(struct spi_device *spi) > if (!cs) > return -ENOMEM; > spi->controller_state = cs; > + initial_setup = true; > } > > /* per-word shift register access, in hardware or bitbanging */ > cs->txrx_word = bitbang->txrx_word[spi->mode & (SPI_CPOL|SPI_CPHA)]; > - if (!cs->txrx_word) > - return -EINVAL; > + if (!cs->txrx_word) { > + retval = -EINVAL; > + goto err_free; > + } > > if (bitbang->setup_transfer) { > - int retval = bitbang->setup_transfer(spi, NULL); > + retval = bitbang->setup_transfer(spi, NULL); > if (retval < 0) > - return retval; > + goto err_free; > } > > dev_dbg(&spi->dev, "%s, %u nsec/bit\n", __func__, 2 * cs->nsecs); > > return 0; > + > +err_free: > + if (initial_setup) > + kfree(cs); > + return retval; > } > EXPORT_SYMBOL_GPL(spi_bitbang_setup); > > diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c > index d0e5aa18b7ba..bdf94cc7be1a 100644 > --- a/drivers/spi/spi-fsl-spi.c > +++ b/drivers/spi/spi-fsl-spi.c > @@ -440,6 +440,7 @@ static int fsl_spi_setup(struct spi_device *spi) > { > struct mpc8xxx_spi *mpc8xxx_spi; > struct fsl_spi_reg __iomem *reg_base; > + bool initial_setup = false; > int retval; > u32 hw_mode; > struct spi_mpc8xxx_cs *cs = spi_get_ctldata(spi); > @@ -452,6 +453,7 @@ static int fsl_spi_setup(struct spi_device *spi) > if (!cs) > return -ENOMEM; > spi_set_ctldata(spi, cs); > + initial_setup = true; > } > mpc8xxx_spi = spi_master_get_devdata(spi->master); > > @@ -475,6 +477,8 @@ static int fsl_spi_setup(struct spi_device *spi) > retval = fsl_spi_setup_transfer(spi, NULL); > if (retval < 0) { > cs->hw_mode = hw_mode; /* Restore settings */ > + if (initial_setup) > + kfree(cs); > return retval; > } > > diff --git a/drivers/spi/spi-omap-uwire.c b/drivers/spi/spi-omap-uwire.c > index 71402f71ddd8..df28c6664aba 100644 > --- a/drivers/spi/spi-omap-uwire.c > +++ b/drivers/spi/spi-omap-uwire.c > @@ -424,15 +424,22 @@ static int uwire_setup_transfer(struct spi_device *spi, struct spi_transfer *t) > static int uwire_setup(struct spi_device *spi) > { > struct uwire_state *ust = spi->controller_state; > + bool initial_setup = false; > + int status; > > if (ust == NULL) { > ust = kzalloc(sizeof(*ust), GFP_KERNEL); > if (ust == NULL) > return -ENOMEM; > spi->controller_state = ust; > + initial_setup = true; > } > > - return uwire_setup_transfer(spi, NULL); > + status = uwire_setup_transfer(spi, NULL); > + if (status && initial_setup) > + kfree(ust); > + > + return status; > } > > static void uwire_cleanup(struct spi_device *spi) > diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c > index d4c9510af393..3596bbe4b776 100644 > --- a/drivers/spi/spi-omap2-mcspi.c > +++ b/drivers/spi/spi-omap2-mcspi.c > @@ -1032,8 +1032,22 @@ static void omap2_mcspi_release_dma(struct spi_master *master) > } > } > > +static void omap2_mcspi_cleanup(struct spi_device *spi) > +{ > + struct omap2_mcspi_cs *cs; > + > + if (spi->controller_state) { > + /* Unlink controller state from context save list */ > + cs = spi->controller_state; > + list_del(&cs->node); > + > + kfree(cs); > + } > +} > + > static int omap2_mcspi_setup(struct spi_device *spi) > { > + bool initial_setup = false; > int ret; > struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master); > struct omap2_mcspi_regs *ctx = &mcspi->ctx; > @@ -1051,35 +1065,28 @@ static int omap2_mcspi_setup(struct spi_device *spi) > spi->controller_state = cs; > /* Link this to context save list */ > list_add_tail(&cs->node, &ctx->cs); > + initial_setup = true; > } > > ret = pm_runtime_get_sync(mcspi->dev); > if (ret < 0) { > pm_runtime_put_noidle(mcspi->dev); > + if (initial_setup) > + omap2_mcspi_cleanup(spi); > > return ret; > } > > ret = omap2_mcspi_setup_transfer(spi, NULL); > + if (ret && initial_setup) > + omap2_mcspi_cleanup(spi); > + > pm_runtime_mark_last_busy(mcspi->dev); > pm_runtime_put_autosuspend(mcspi->dev); > > return ret; > } > > -static void omap2_mcspi_cleanup(struct spi_device *spi) > -{ > - struct omap2_mcspi_cs *cs; > - > - if (spi->controller_state) { > - /* Unlink controller state from context save list */ > - cs = spi->controller_state; > - list_del(&cs->node); > - > - kfree(cs); > - } > -} > - > static irqreturn_t omap2_mcspi_irq_handler(int irq, void *data) > { > struct omap2_mcspi *mcspi = data; > diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c > index d6b534d38e5d..56a62095ec8c 100644 > --- a/drivers/spi/spi-pxa2xx.c > +++ b/drivers/spi/spi-pxa2xx.c > @@ -1254,6 +1254,8 @@ static int setup_cs(struct spi_device *spi, struct chip_data *chip, > chip->gpio_cs_inverted = spi->mode & SPI_CS_HIGH; > > err = gpiod_direction_output(gpiod, !chip->gpio_cs_inverted); > + if (err) > + gpiod_put(chip->gpiod_cs); > } > > return err; > @@ -1267,6 +1269,7 @@ static int setup(struct spi_device *spi) > struct driver_data *drv_data = > spi_controller_get_devdata(spi->controller); > uint tx_thres, tx_hi_thres, rx_thres; > + int err; > > switch (drv_data->ssp_type) { > case QUARK_X1000_SSP: > @@ -1413,7 +1416,11 @@ static int setup(struct spi_device *spi) > if (drv_data->ssp_type == CE4100_SSP) > return 0; > > - return setup_cs(spi, chip, chip_info); > + err = setup_cs(spi, chip, chip_info); > + if (err) > + kfree(chip); > + > + return err; > } > > static void cleanup(struct spi_device *spi)

1 0

Re: [PATCH openEuler-21.03] usb: chipidea: udc: assign interrupt number to USB gadget structure
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:19, chensiyan96 写道: > From: Li Jun <jun.li(a)nxp.com> > > stable inclusion > from stable-v5.10.44 > commit 2e2145ccfbcb0dd38d8423681d22b595ca735846 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=376 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 9e3927f6373da54cb17e17f4bd700907e1123d2f ] > > Chipidea also need sync interrupt before unbind the udc while > gadget remove driver, otherwise setup irq handling may happen > while unbind, see below dump generated from android function > switch stress test: > > [ 4703.503056] android_work: sent uevent USB_STATE=CONNECTED > [ 4703.514642] android_work: sent uevent USB_STATE=DISCONNECTED > [ 4703.651339] android_work: sent uevent USB_STATE=CONNECTED > [ 4703.661806] init: Control message: Processed ctl.stop for 'adbd' from pid: 561 (system_server) > [ 4703.673469] init: processing action (init.svc.adbd=stopped) from (/system/etc/init/hw/init.usb.configfs.rc:14) > [ 4703.676451] Unable to handle kernel read from unreadable memory at virtual address 0000000000000090 > [ 4703.676454] Mem abort info: > [ 4703.676458] ESR = 0x96000004 > [ 4703.676461] EC = 0x25: DABT (current EL), IL = 32 bits > [ 4703.676464] SET = 0, FnV = 0 > [ 4703.676466] EA = 0, S1PTW = 0 > [ 4703.676468] Data abort info: > [ 4703.676471] ISV = 0, ISS = 0x00000004 > [ 4703.676473] CM = 0, WnR = 0 > [ 4703.676478] user pgtable: 4k pages, 48-bit VAs, pgdp=000000004a867000 > [ 4703.676481] [0000000000000090] pgd=0000000000000000, p4d=0000000000000000 > [ 4703.676503] Internal error: Oops: 96000004 [#1] PREEMPT SMP > [ 4703.758297] Modules linked in: synaptics_dsx_i2c moal(O) mlan(O) > [ 4703.764327] CPU: 0 PID: 235 Comm: lmkd Tainted: G W O 5.10.9-00001-g3f5fd8487c38-dirty #63 > [ 4703.773720] Hardware name: NXP i.MX8MNano EVK board (DT) > [ 4703.779033] pstate: 60400085 (nZCv daIf +PAN -UAO -TCO BTYPE=--) > [ 4703.785046] pc : _raw_write_unlock_bh+0xc0/0x2c8 > [ 4703.789667] lr : android_setup+0x4c/0x168 > [ 4703.793676] sp : ffff80001256bd80 > [ 4703.796989] x29: ffff80001256bd80 x28: 00000000000000a8 > [ 4703.802304] x27: ffff800012470000 x26: ffff80006d923000 > [ 4703.807616] x25: ffff800012471000 x24: ffff00000b091140 > [ 4703.812929] x23: ffff0000077dbd38 x22: ffff0000077da490 > [ 4703.818242] x21: ffff80001256be30 x20: 0000000000000000 > [ 4703.823554] x19: 0000000000000080 x18: ffff800012561048 > [ 4703.828867] x17: 0000000000000000 x16: 0000000000000039 > [ 4703.834180] x15: ffff8000106ad258 x14: ffff80001194c277 > [ 4703.839493] x13: 0000000000003934 x12: 0000000000000000 > [ 4703.844805] x11: 0000000000000000 x10: 0000000000000001 > [ 4703.850117] x9 : 0000000000000000 x8 : 0000000000000090 > [ 4703.855429] x7 : 6f72646e61203a70 x6 : ffff8000124f2450 > [ 4703.860742] x5 : ffffffffffffffff x4 : 0000000000000009 > [ 4703.866054] x3 : ffff8000108a290c x2 : ffff00007fb3a9c8 > [ 4703.871367] x1 : 0000000000000000 x0 : 0000000000000090 > [ 4703.876681] Call trace: > [ 4703.879129] _raw_write_unlock_bh+0xc0/0x2c8 > [ 4703.883397] android_setup+0x4c/0x168 > [ 4703.887059] udc_irq+0x824/0xa9c > [ 4703.890287] ci_irq+0x124/0x148 > [ 4703.893429] __handle_irq_event_percpu+0x84/0x268 > [ 4703.898131] handle_irq_event+0x64/0x14c > [ 4703.902054] handle_fasteoi_irq+0x110/0x210 > [ 4703.906236] __handle_domain_irq+0x8c/0xd4 > [ 4703.910332] gic_handle_irq+0x6c/0x124 > [ 4703.914081] el1_irq+0xdc/0x1c0 > [ 4703.917221] _raw_spin_unlock_irq+0x20/0x54 > [ 4703.921405] finish_task_switch+0x84/0x224 > [ 4703.925502] __schedule+0x4a4/0x734 > [ 4703.928990] schedule+0xa0/0xe8 > [ 4703.932132] do_notify_resume+0x150/0x184 > [ 4703.936140] work_pending+0xc/0x40c > [ 4703.939633] Code: d5384613 521b0a69 d5184609 f9800111 (885ffd01) > [ 4703.945732] ---[ end trace ba5c1875ae49d53c ]--- > [ 4703.950350] Kernel panic - not syncing: Oops: Fatal exception in interrupt > [ 4703.957223] SMP: stopping secondary CPUs > [ 4703.961151] Kernel Offset: disabled > [ 4703.964638] CPU features: 0x0240002,2000200c > [ 4703.968905] Memory Limit: none > [ 4703.971963] Rebooting in 5 seconds.. > > Tested-by: faqiang.zhu <faqiang.zhu(a)nxp.com> > Signed-off-by: Li Jun <jun.li(a)nxp.com> > Link: https://lore.kernel.org/r/1620989984-7653-1-git-send-email-jun.li@nxp.com > Signed-off-by: Peter Chen <peter.chen(a)kernel.org> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: chensiyan96 <3225973902(a)qq.com> > --- > drivers/usb/chipidea/udc.c | 1 + > 1 file changed, 1 insertion(+) > > diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c > index 60ea932afe2b..5f35cdd2cf1d 100644 > --- a/drivers/usb/chipidea/udc.c > +++ b/drivers/usb/chipidea/udc.c > @@ -2055,6 +2055,7 @@ static int udc_start(struct ci_hdrc *ci) > ci->gadget.name = ci->platdata->name; > ci->gadget.otg_caps = otg_caps; > ci->gadget.sg_supported = 1; > + ci->gadget.irq = ci->irq; > > if (ci->platdata->flags & CI_HDRC_REQUIRES_ALIGNED_DMA) > ci->gadget.quirk_avoids_skb_reserve = 1;

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:25, ZhuoliHuang 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:26, lihao 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:27, zanderzhao 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] scsi: core: Fix failure handling of scsi_add_host_with_dma()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:32, dongenyang 写道: > From: Ming Lei <ming.lei(a)redhat.com> > > stable inclusion > from stable-v5.10.44 > commit 146446a43b3dbaa3a58364ef99fd606b3f324832 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=361 > CVE: NA > > ------------------------------------------------- > > commit 3719f4ff047e20062b8314c23ec3cab84d74c908 upstream. > > When scsi_add_host_with_dma() returns failure, the caller will call > scsi_host_put(shost) to release everything allocated for this host > instance. Consequently we can't also free allocated stuff in > scsi_add_host_with_dma(), otherwise we will end up with a double free. > > Strictly speaking, host resource allocations should have been done in > scsi_host_alloc(). However, the allocations may need information which is > not yet provided by the driver when that function is called. So leave the > allocations where they are but rely on host device's release handler to > free resources. > > Link: https://lore.kernel.org/r/20210602133029.2864069-3-ming.lei@redhat.com > Cc: Bart Van Assche <bvanassche(a)acm.org> > Cc: John Garry <john.garry(a)huawei.com> > Cc: Hannes Reinecke <hare(a)suse.de> > Tested-by: John Garry <john.garry(a)huawei.com> > Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> > Reviewed-by: John Garry <john.garry(a)huawei.com> > Reviewed-by: Hannes Reinecke <hare(a)suse.de> > Signed-off-by: Ming Lei <ming.lei(a)redhat.com> > Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: dongenyang <sdlpdey(a)163.com> > --- > drivers/scsi/hosts.c | 14 ++++++-------- > 1 file changed, 6 insertions(+), 8 deletions(-) > > diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c > index 2f162603876f..85ec3cce43f1 100644 > --- a/drivers/scsi/hosts.c > +++ b/drivers/scsi/hosts.c > @@ -278,23 +278,22 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, > > if (!shost->work_q) { > error = -EINVAL; > - goto out_free_shost_data; > + goto out_del_dev; > } > } > > error = scsi_sysfs_add_host(shost); > if (error) > - goto out_destroy_host; > + goto out_del_dev; > > scsi_proc_host_add(shost); > scsi_autopm_put_host(shost); > return error; > > - out_destroy_host: > - if (shost->work_q) > - destroy_workqueue(shost->work_q); > - out_free_shost_data: > - kfree(shost->shost_data); > + /* > + * Any host allocation in this function will be freed in > + * scsi_host_dev_release(). > + */ > out_del_dev: > device_del(&shost->shost_dev); > out_del_gendev: > @@ -304,7 +303,6 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, > pm_runtime_disable(&shost->shost_gendev); > pm_runtime_set_suspended(&shost->shost_gendev); > pm_runtime_put_noidle(&shost->shost_gendev); > - scsi_mq_destroy_tags(shost); > fail: > return error; > }

1 0

Re: [PATCH openEuler-21.03] USB: f_ncm: ncm_bitrate (speed) is unsigned
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:32, xjx00 写道: > From: Maciej Żenczykowski <maze(a)google.com> > > stable inclusion > from stable-v5.10.44 > commit 0f5a20b1fd9da3ac9f7c6edcad522712ca694d5c > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=358 > CVE: NA > > ------------------------------------------------- > > commit 3370139745853f7826895293e8ac3aec1430508e upstream. > > [ 190.544755] configfs-gadget gadget: notify speed -44967296 > > This is because 4250000000 - 2**32 is -44967296. > > Fixes: 9f6ce4240a2b ("usb: gadget: f_ncm.c added") > Cc: Brooke Basile <brookebasile(a)gmail.com> > Cc: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org> > Cc: Felipe Balbi <balbi(a)kernel.org> > Cc: Lorenzo Colitti <lorenzo(a)google.com> > Cc: Yauheni Kaliuta <yauheni.kaliuta(a)nokia.com> > Cc: Linux USB Mailing List <linux-usb(a)vger.kernel.org> > Acked-By: Lorenzo Colitti <lorenzo(a)google.com> > Signed-off-by: Maciej Żenczykowski <maze(a)google.com> > Cc: stable <stable(a)vger.kernel.org> > Link: https://lore.kernel.org/r/20210608005344.3762668-1-zenczykowski@gmail.com > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: xjx00 <xjxyklwx(a)126.com> > --- > drivers/usb/gadget/function/f_ncm.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c > index 019bea8e09cc..0d23c6c11a13 100644 > --- a/drivers/usb/gadget/function/f_ncm.c > +++ b/drivers/usb/gadget/function/f_ncm.c > @@ -583,7 +583,7 @@ static void ncm_do_notify(struct f_ncm *ncm) > data[0] = cpu_to_le32(ncm_bitrate(cdev->gadget)); > data[1] = data[0]; > > - DBG(cdev, "notify speed %d\n", ncm_bitrate(cdev->gadget)); > + DBG(cdev, "notify speed %u\n", ncm_bitrate(cdev->gadget)); > ncm->notify_state = NCM_NOTIFY_CONNECT; > break; > }

1 0

Re: [PATCH openEuler-21.03] gpio: wcd934x: Fix shift-out-of-bounds error
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 20:18, zcj 写道: > From: Srinivas Kandagatla <srinivas.kandagatla(a)linaro.org> > > stable inclusion > from stable-v5.10.44 > commit e0b518a2eb44d8a74c19e50f79a8ed393e96d634 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=463 > CVE: NA > > ------------------------------------------------- > > commit dbec64b11c65d74f31427e2b9d5746fbf17bf840 upstream. > > bit-mask for pins 0 to 4 is BIT(0) to BIT(4) however we ended up with BIT(n - 1) > which is not right, and this was caught by below usban check > > UBSAN: shift-out-of-bounds in drivers/gpio/gpio-wcd934x.c:34:14 > > Fixes: 59c324683400 ("gpio: wcd934x: Add support to wcd934x gpio controller") > Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla(a)linaro.org> > Reviewed-by: Andy Shevchenko <andy.shevchenko(a)gmail.com> > Reviewed-by: Bjorn Andersson <bjorn.andersson(a)linaro.org> > Signed-off-by: Bartosz Golaszewski <bgolaszewski(a)baylibre.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: zcj <2459770937(a)qq.com> > --- > drivers/gpio/gpio-wcd934x.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/gpio/gpio-wcd934x.c b/drivers/gpio/gpio-wcd934x.c > index 1cbce5990855..97e6caedf1f3 100644 > --- a/drivers/gpio/gpio-wcd934x.c > +++ b/drivers/gpio/gpio-wcd934x.c > @@ -7,7 +7,7 @@ > #include <linux/slab.h> > #include <linux/of_device.h> > > -#define WCD_PIN_MASK(p) BIT(p - 1) > +#define WCD_PIN_MASK(p) BIT(p) > #define WCD_REG_DIR_CTL_OFFSET 0x42 > #define WCD_REG_VAL_CTL_OFFSET 0x43 > #define WCD934X_NPINS 5

1 0

Re: [PATCH openEuler-21.03] regulator: fan53880: Fix missing n_voltages setting
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 20:49, lantianbaiyun 写道: > From: Axel Lin <axel.lin(a)ingics.com> > > stable inclusion > from stable-v5.10.44 > commit 5a5f5cfb5f0996d65eae3cc034513d90f4be6783 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=401 > CVE: NA > > ------------------------------------------------- > > commit 34991ee96fd8477479dd15adadceb6b28b30d9b0 upstream. > > Fixes: e6dea51e2d41 ("regulator: fan53880: Add initial support") > Signed-off-by: Axel Lin <axel.lin(a)ingics.com> > Acked-by: Christoph Fritz <chf.fritz(a)googlemail.com> > Link: https://lore.kernel.org/r/20210517105325.1227393-1-axel.lin@ingics.com > Signed-off-by: Mark Brown <broonie(a)kernel.org> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: lantianbaiyun <lianyi21(a)mails.ucas.ac.cn> > --- > drivers/regulator/fan53880.c | 3 +++ > 1 file changed, 3 insertions(+) > > diff --git a/drivers/regulator/fan53880.c b/drivers/regulator/fan53880.c > index e83eb4fb1876..1684faf82ed2 100644 > --- a/drivers/regulator/fan53880.c > +++ b/drivers/regulator/fan53880.c > @@ -51,6 +51,7 @@ static const struct regulator_ops fan53880_ops = { > REGULATOR_LINEAR_RANGE(800000, 0xf, 0x73, 25000), \ > }, \ > .n_linear_ranges = 2, \ > + .n_voltages = 0x74, \ > .vsel_reg = FAN53880_LDO ## _num ## VOUT, \ > .vsel_mask = 0x7f, \ > .enable_reg = FAN53880_ENABLE, \ > @@ -76,6 +77,7 @@ static const struct regulator_desc fan53880_regulators[] = { > REGULATOR_LINEAR_RANGE(600000, 0x1f, 0xf7, 12500), > }, > .n_linear_ranges = 2, > + .n_voltages = 0xf8, > .vsel_reg = FAN53880_BUCKVOUT, > .vsel_mask = 0x7f, > .enable_reg = FAN53880_ENABLE, > @@ -95,6 +97,7 @@ static const struct regulator_desc fan53880_regulators[] = { > REGULATOR_LINEAR_RANGE(3000000, 0x4, 0x70, 25000), > }, > .n_linear_ranges = 2, > + .n_voltages = 0x71, > .vsel_reg = FAN53880_BOOSTVOUT, > .vsel_mask = 0x7f, > .enable_reg = FAN53880_ENABLE_BOOST,

1 0

Re: [PATCH openEuler-21.03] NFSv4: Fix second deadlock in nfs4_evict_inode()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 20:55, smilezhangs 写道: > From: Trond Myklebust <trond.myklebust(a)hammerspace.com> > > stable inclusion > from stable-v5.10.44 > commit d973bd0d6e7f9b4ea976cc619e8d6e0d235b9056 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=462 > CVE: NA > > ------------------------------------------------- > > commit c3aba897c6e67fa464ec02b1f17911577d619713 upstream. > > If the inode is being evicted but has to return a layout first, then > that too can cause a deadlock in the corner case where the server > reboots. > > Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: Hang <haihangyiyuan(a)163.com> > Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> > Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> > --- > fs/nfs/nfs4proc.c | 9 +++++++-- > 1 file changed, 7 insertions(+), 2 deletions(-) > > diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c > index c92d6ff0fcea..eedcbe6832fb 100644 > --- a/fs/nfs/nfs4proc.c > +++ b/fs/nfs/nfs4proc.c > @@ -9619,15 +9619,20 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) > &task_setup_data.rpc_client, &msg); > > dprintk("--> %s\n", __func__); > + lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!sync) { > - lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!lrp->inode) { > nfs4_layoutreturn_release(lrp); > return -EAGAIN; > } > task_setup_data.flags |= RPC_TASK_ASYNC; > } > - nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, 0); > + if (!lrp->inode) > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 1); > + else > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 0); > task = rpc_run_task(&task_setup_data); > if (IS_ERR(task)) > return PTR_ERR(task);

1 0

Re: [PATCH openEuler-21.03] net/nfc/rawsock.c: fix a permission check bug
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:10, lf 写道: > From: Jeimon <jjjinmeng.zhou(a)gmail.com> > > stable inclusion > from stable-v5.10.44 > commit 1e5cab50208c8fb7351b798cb1d569debfeb994a > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=371 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 8ab78863e9eff11910e1ac8bcf478060c29b379e ] > > The function rawsock_create() calls a privileged function sk_alloc(), which requires a ns-aware check to check net->user_ns, i.e., ns_capable(). However, the original code checks the init_user_ns using capable(). So we replace the capable() with ns_capable(). > > Signed-off-by: Jeimon <jjjinmeng.zhou(a)gmail.com> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: lf <15042944259(a)163.com> > --- > net/nfc/rawsock.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c > index 9c7eb8455ba8..5f1d438a0a23 100644 > --- a/net/nfc/rawsock.c > +++ b/net/nfc/rawsock.c > @@ -329,7 +329,7 @@ static int rawsock_create(struct net *net, struct socket *sock, > return -ESOCKTNOSUPPORT; > > if (sock->type == SOCK_RAW) { > - if (!capable(CAP_NET_RAW)) > + if (!ns_capable(net->user_ns, CAP_NET_RAW)) > return -EPERM; > sock->ops = &rawsock_raw_ops; > } else {

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:09, lf 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] Revert "ACPI: sleep: Put the FACS table after using it"
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:18, ws 写道: > From: Zhang Rui <rui.zhang(a)intel.com> > > stable inclusion > from stable-v5.10.44 > commit afd87792db355282c4608356b98bb2dd650a6885 > Bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=438 > CVE: NA > > ------------------------------------------------- > > commit f1ffa9d4cccc8fdf6c03fb1b3429154d22037988 upstream. > > Commit 95722237cb2a ("ACPI: sleep: Put the FACS table after using it") > puts the FACS table during initialization. > > But the hardware signature bits in the FACS table need to be accessed, > after every hibernation, to compare with the original hardware > signature. > > So there is no reason to release the FACS table mapping after > initialization. > > This reverts commit 95722237cb2ae4f7b73471058cdb19e8f4057c93. > > An alternative solution is to use acpi_gbl_FACS variable instead, which > is mapped by the ACPICA core and never released. > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=212277 > Reported-by: Stephan Hohe <sth.dev(a)tejp.de> > Signed-off-by: Zhang Rui <rui.zhang(a)intel.com> > Cc: 5.8+ <stable(a)vger.kernel.org> # 5.8+ > Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: ws <3045672234(a)qq.com> > --- > drivers/acpi/sleep.c | 4 +--- > 1 file changed, 1 insertion(+), 3 deletions(-) > > diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c > index aff13bf4d947..31c9d0c8ae11 100644 > --- a/drivers/acpi/sleep.c > +++ b/drivers/acpi/sleep.c > @@ -1290,10 +1290,8 @@ static void acpi_sleep_hibernate_setup(void) > return; > > acpi_get_table(ACPI_SIG_FACS, 1, (struct acpi_table_header **)&facs); > - if (facs) { > + if (facs) > s4_hardware_signature = facs->hardware_signature; > - acpi_put_table((struct acpi_table_header *)facs); > - } > } > #else /* !CONFIG_HIBERNATION */ > static inline void acpi_sleep_hibernate_setup(void) {}

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:27, lcr 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] RDMA/mlx4: Do not map the core_clock page to user space unless enabled
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:27, gaodawei 写道: > From: Shay Drory <shayd(a)nvidia.com> > > stable inclusion > from stable-v5.10.44 > commit cb1aa1da04882d1860f733e24aeebdbbc85724d7 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=454 > CVE: NA > > ------------------------------------------------- > > commit 404e5a12691fe797486475fe28cc0b80cb8bef2c upstream. > > Currently when mlx4 maps the hca_core_clock page to the user space there > are read-modifiable registers, one of which is semaphore, on this page as > well as the clock counter. If user reads the wrong offset, it can modify > the semaphore and hang the device. > > Do not map the hca_core_clock page to the user space unless the device has > been put in a backwards compatibility mode to support this feature. > > After this patch, mlx4 core_clock won't be mapped to user space on the > majority of existing devices and the uverbs device time feature in > ibv_query_rt_values_ex() will be disabled. > > Fixes: 52033cfb5aab ("IB/mlx4: Add mmap call to map the hardware clock") > Link: https://lore.kernel.org/r/9632304e0d6790af84b3b706d8c18732bc0d5e27.16227263… > Signed-off-by: Shay Drory <shayd(a)nvidia.com> > Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> > Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: gaodawei <810789471(a)qq.com> > --- > drivers/infiniband/hw/mlx4/main.c | 5 +---- > drivers/net/ethernet/mellanox/mlx4/fw.c | 3 +++ > drivers/net/ethernet/mellanox/mlx4/fw.h | 1 + > drivers/net/ethernet/mellanox/mlx4/main.c | 6 ++++++ > include/linux/mlx4/device.h | 1 + > 5 files changed, 12 insertions(+), 4 deletions(-) > > diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c > index cd0fba6b0964..7b11aff8a5ea 100644 > --- a/drivers/infiniband/hw/mlx4/main.c > +++ b/drivers/infiniband/hw/mlx4/main.c > @@ -580,12 +580,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, > props->cq_caps.max_cq_moderation_count = MLX4_MAX_CQ_COUNT; > props->cq_caps.max_cq_moderation_period = MLX4_MAX_CQ_PERIOD; > > - if (!mlx4_is_slave(dev->dev)) > - err = mlx4_get_internal_clock_params(dev->dev, &clock_params); > - > if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) { > resp.response_length += sizeof(resp.hca_core_clock_offset); > - if (!err && !mlx4_is_slave(dev->dev)) { > + if (!mlx4_get_internal_clock_params(dev->dev, &clock_params)) { > resp.comp_mask |= MLX4_IB_QUERY_DEV_RESP_MASK_CORE_CLOCK_OFFSET; > resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE; > } > diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c > index f6cfec81ccc3..dc4ac1a2b6b6 100644 > --- a/drivers/net/ethernet/mellanox/mlx4/fw.c > +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c > @@ -823,6 +823,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) > #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET 0xb0 > #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET 0xa8 > #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET 0xac > +#define QUERY_DEV_CAP_MAP_CLOCK_TO_USER 0xc1 > #define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET 0xcc > #define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET 0xd0 > #define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET 0xd2 > @@ -841,6 +842,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) > > if (mlx4_is_mfunc(dev)) > disable_unsupported_roce_caps(outbox); > + MLX4_GET(field, outbox, QUERY_DEV_CAP_MAP_CLOCK_TO_USER); > + dev_cap->map_clock_to_user = field & 0x80; > MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_QP_OFFSET); > dev_cap->reserved_qps = 1 << (field & 0xf); > MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_QP_OFFSET); > diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h > index 8f020f26ebf5..cf64e54eecb0 100644 > --- a/drivers/net/ethernet/mellanox/mlx4/fw.h > +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h > @@ -131,6 +131,7 @@ struct mlx4_dev_cap { > u32 health_buffer_addrs; > struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1]; > bool wol_port[MLX4_MAX_PORTS + 1]; > + bool map_clock_to_user; > }; > > struct mlx4_func_cap { > diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c > index c326b434734e..00c84656b2e7 100644 > --- a/drivers/net/ethernet/mellanox/mlx4/main.c > +++ b/drivers/net/ethernet/mellanox/mlx4/main.c > @@ -498,6 +498,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) > } > } > > + dev->caps.map_clock_to_user = dev_cap->map_clock_to_user; > dev->caps.uar_page_size = PAGE_SIZE; > dev->caps.num_uars = dev_cap->uar_size / PAGE_SIZE; > dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay; > @@ -1948,6 +1949,11 @@ int mlx4_get_internal_clock_params(struct mlx4_dev *dev, > if (mlx4_is_slave(dev)) > return -EOPNOTSUPP; > > + if (!dev->caps.map_clock_to_user) { > + mlx4_dbg(dev, "Map clock to user is not supported.\n"); > + return -EOPNOTSUPP; > + } > + > if (!params) > return -EINVAL; > > diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h > index 06e066e04a4b..eb8169c03d89 100644 > --- a/include/linux/mlx4/device.h > +++ b/include/linux/mlx4/device.h > @@ -631,6 +631,7 @@ struct mlx4_caps { > bool wol_port[MLX4_MAX_PORTS + 1]; > struct mlx4_rate_limit_caps rl_caps; > u32 health_buffer_addrs; > + bool map_clock_to_user; > }; > > struct mlx4_buf_list {

1 0

Re: [PATCH openEuler-21.03] NFSv4: Fix second deadlock in nfs4_evict_inode()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:31, smilezhangs 写道: > From: Trond Myklebust <trond.myklebust(a)hammerspace.com> > > stable inclusion > from stable-v5.10.44 > commit d973bd0d6e7f9b4ea976cc619e8d6e0d235b9056 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=462 > CVE: NA > > ------------------------------------------------- > > commit c3aba897c6e67fa464ec02b1f17911577d619713 upstream. > > If the inode is being evicted but has to return a layout first, then > that too can cause a deadlock in the corner case where the server > reboots. > > Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: Hang <haihangyiyuan(a)163.com> > Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> > Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> > --- > fs/nfs/nfs4proc.c | 9 +++++++-- > 1 file changed, 7 insertions(+), 2 deletions(-) > > diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c > index c92d6ff0fcea..eedcbe6832fb 100644 > --- a/fs/nfs/nfs4proc.c > +++ b/fs/nfs/nfs4proc.c > @@ -9619,15 +9619,20 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) > &task_setup_data.rpc_client, &msg); > > dprintk("--> %s\n", __func__); > + lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!sync) { > - lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!lrp->inode) { > nfs4_layoutreturn_release(lrp); > return -EAGAIN; > } > task_setup_data.flags |= RPC_TASK_ASYNC; > } > - nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, 0); > + if (!lrp->inode) > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 1); > + else > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 0); > task = rpc_run_task(&task_setup_data); > if (IS_ERR(task)) > return PTR_ERR(task);

1 0

Re: [PATCH openEuler-21.03] scsi: core: Only put parent device if host state differs from SHOST_CREATED
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:37, yangshuo 写道: > From: Ming Lei <ming.lei(a)redhat.com> > > stable inclusion > from stable-v5.10.44 > commit 5b537408f2733d510060e72596befa44c3435cb6 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=403 > CVE: NA > > ------------------------------------------------- > > commit 1e0d4e6225996f05271de1ebcb1a7c9381af0b27 upstream. > > get_device(shost->shost_gendev.parent) is called after host state has > switched to SHOST_RUNNING. scsi_host_dev_release() shouldn't release the > parent device if host state is still SHOST_CREATED. > > Link: https://lore.kernel.org/r/20210602133029.2864069-5-ming.lei@redhat.com > Cc: Bart Van Assche <bvanassche(a)acm.org> > Cc: John Garry <john.garry(a)huawei.com> > Cc: Hannes Reinecke <hare(a)suse.de> > Tested-by: John Garry <john.garry(a)huawei.com> > Reviewed-by: John Garry <john.garry(a)huawei.com> > Signed-off-by: Ming Lei <ming.lei(a)redhat.com> > Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: yangshuo <look4polaris(a)163.com> > --- > drivers/scsi/hosts.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c > index 2f162603876f..f1b7061aa0d9 100644 > --- a/drivers/scsi/hosts.c > +++ b/drivers/scsi/hosts.c > @@ -345,7 +345,7 @@ static void scsi_host_dev_release(struct device *dev) > > ida_simple_remove(&host_index_ida, shost->host_no); > > - if (parent) > + if (shost->shost_state != SHOST_CREATED) > put_device(parent); > kfree(shost); > }

1 0

Re: [PATCH openEuler-21.03] dm verity: fix require_signatures module_param permissions
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 22:40, huangzhuoli 写道: > From: John Keeping <john(a)metanate.com> > > stable inclusion > from stable-v5.10.44 > commit 90547d5db50bcb2705709e420e0af51535109113 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=426 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 0c1f3193b1cdd21e7182f97dc9bca7d284d18a15 ] > > The third parameter of module_param() is permissions for the sysfs node > but it looks like it is being used as the initial value of the parameter > here. In fact, false here equates to omitting the file from sysfs and > does not affect the value of require_signatures. > > Making the parameter writable is not simple because going from > false->true is fine but it should not be possible to remove the > requirement to verify a signature. But it can be useful to inspect the > value of this parameter from userspace, so change the permissions to > make a read-only file in sysfs. > > Signed-off-by: John Keeping <john(a)metanate.com> > Signed-off-by: Mike Snitzer <snitzer(a)redhat.com> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: huangzhuoli <bioagr_huangzl(a)163.com> > --- > drivers/md/dm-verity-verify-sig.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c > index 614e43db93aa..919154ae4cae 100644 > --- a/drivers/md/dm-verity-verify-sig.c > +++ b/drivers/md/dm-verity-verify-sig.c > @@ -15,7 +15,7 @@ > #define DM_VERITY_VERIFY_ERR(s) DM_VERITY_ROOT_HASH_VERIFICATION " " s > > static bool require_signatures; > -module_param(require_signatures, bool, false); > +module_param(require_signatures, bool, 0444); > MODULE_PARM_DESC(require_signatures, > "Verify the roothash of dm-verity hash tree"); >

1 0

Re: [PATCH openEuler-21.03] dm verity: fix require_signatures module_param permissions
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 22:40, huangzhuoli 写道: > From: John Keeping <john(a)metanate.com> > > stable inclusion > from stable-v5.10.44 > commit 90547d5db50bcb2705709e420e0af51535109113 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=426 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 0c1f3193b1cdd21e7182f97dc9bca7d284d18a15 ] > > The third parameter of module_param() is permissions for the sysfs node > but it looks like it is being used as the initial value of the parameter > here. In fact, false here equates to omitting the file from sysfs and > does not affect the value of require_signatures. > > Making the parameter writable is not simple because going from > false->true is fine but it should not be possible to remove the > requirement to verify a signature. But it can be useful to inspect the > value of this parameter from userspace, so change the permissions to > make a read-only file in sysfs. > > Signed-off-by: John Keeping <john(a)metanate.com> > Signed-off-by: Mike Snitzer <snitzer(a)redhat.com> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: huangzhuoli <bioagr_huangzl(a)163.com> > --- > drivers/md/dm-verity-verify-sig.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c > index 614e43db93aa..919154ae4cae 100644 > --- a/drivers/md/dm-verity-verify-sig.c > +++ b/drivers/md/dm-verity-verify-sig.c > @@ -15,7 +15,7 @@ > #define DM_VERITY_VERIFY_ERR(s) DM_VERITY_ROOT_HASH_VERIFICATION " " s > > static bool require_signatures; > -module_param(require_signatures, bool, false); > +module_param(require_signatures, bool, 0444); > MODULE_PARM_DESC(require_signatures, > "Verify the roothash of dm-verity hash tree"); >

1 0

Re: [PATCH openEuler-21.03] ALSA: seq: Fix race of snd_seq_timer_open()
by chengjian (D) 26 Oct '21

26 Oct '21

您好，感谢参与 openEuler kernel 开发您的 signed-off-by 没有加。另外您的邮箱用户名可能不正确：显示为 yourname。在 2021/10/23 23:05, yourname 写道: > From: Takashi Iwai <tiwai(a)suse.de> > > stable inclusion > from stable-v5.10.44 > commit bd7d88b0874f82f7b29d1a53e574cedaf23166ba > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=445 > CVE: NA > > ------------------------------------------------- > > commit 83e197a8414c0ba545e7e3916ce05f836f349273 upstream. > > The timer instance per queue is exclusive, and snd_seq_timer_open() > should have managed the concurrent accesses. It looks as if it's > checking the already existing timer instance at the beginning, but > it's not right, because there is no protection, hence any later > concurrent call of snd_seq_timer_open() may override the timer > instance easily. This may result in UAF, as the leftover timer > instance can keep running while the queue itself gets closed, as > spotted by syzkaller recently. > > For avoiding the race, add a proper check at the assignment of > tmr->timeri again, and return -EBUSY if it's been already registered. > > Reported-by: syzbot+ddc1260a83ed1cbf6fb5(a)syzkaller.appspotmail.com > Cc: <stable(a)vger.kernel.org> > Link: https://lore.kernel.org/r/000000000000dce34f05c42f110c@google.com > Link: https://lore.kernel.org/r/20210610152059.24633-1-tiwai@suse.de > Signed-off-by: Takashi Iwai <tiwai(a)suse.de> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: yourname <625267121(a)qq.com> > --- > sound/core/seq/seq_timer.c | 10 +++++++++- > 1 file changed, 9 insertions(+), 1 deletion(-) > > diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c > index 1645e4142e30..9863be6fd43e 100644 > --- a/sound/core/seq/seq_timer.c > +++ b/sound/core/seq/seq_timer.c > @@ -297,8 +297,16 @@ int snd_seq_timer_open(struct snd_seq_queue *q) > return err; > } > spin_lock_irq(&tmr->lock); > - tmr->timeri = t; > + if (tmr->timeri) > + err = -EBUSY; > + else > + tmr->timeri = t; > spin_unlock_irq(&tmr->lock); > + if (err < 0) { > + snd_timer_close(t); > + snd_timer_instance_free(t); > + return err; > + } > return 0; > } >

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 23:05, yourname 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> 您好，感谢参与 openEuler kernel 开发您的 signed-off-by 没有加。另外您的邮箱用户名可能不正确：显示为 yourname。 > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

[PATCH openEuler-21.03] usb: gadget: f_fs: Ensure io_completion_wq is idle during unbind
by liuhao 26 Oct '21

26 Oct '21

From: Wesley Cheng <wcheng(a)codeaurora.org> stable inclusion from stable-v5.10.44 commit 5cead896962d8b25dee8a8efc85b076572732b86 bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=406 CVE: NA ------------------------------------------------- commit 6fc1db5e6211e30fbb1cee8d7925d79d4ed2ae14 upstream. During unbind, ffs_func_eps_disable() will be executed, resulting in completion callbacks for any pending USB requests. When using AIO, irrespective of the completion status, io_data work is queued to io_completion_wq to evaluate and handle the completed requests. Since work runs asynchronously to the unbind() routine, there can be a scenario where the work runs after the USB gadget has been fully removed, resulting in accessing of a resource which has been already freed. (i.e. usb_ep_free_request() accessing the USB ep structure) Explicitly drain the io_completion_wq, instead of relying on the destroy_workqueue() (in ffs_data_put()) to make sure no pending completion work items are running. Signed-off-by: Wesley Cheng <wcheng(a)codeaurora.org> Cc: stable <stable(a)vger.kernel.org> Link: https://lore.kernel.org/r/1621644261-1236-1-git-send-email-wcheng@codeauror… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: liuhao <qq1107732331(a)qq.com> --- drivers/usb/gadget/function/f_fs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index ffe67d836b0c..7df180b110af 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3566,6 +3566,9 @@ static void ffs_func_unbind(struct usb_configuration *c, ffs->func = NULL; } + /* Drain any pending AIO completions */ + drain_workqueue(ffs->io_completion_wq); + if (!--opts->refcnt) functionfs_unbind(ffs); -- 2.23.0

2 1

Re: [PATCH openEuler-21.03] NFSv4: nfs4_proc_set_acl needs to restore NFS_CAP_UIDGID_NOMAP on error.
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/24 16:58, wangyongpan 写道: > From: Dai Ngo <dai.ngo(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit 6e13b9bc66f0e34238aa7b9486a0575177fb7955 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=414 > CVE: NA > > ------------------------------------------------- > > commit f8849e206ef52b584cd9227255f4724f0cc900bb upstream. > > Currently if __nfs4_proc_set_acl fails with NFS4ERR_BADOWNER it > re-enables the idmapper by clearing NFS_CAP_UIDGID_NOMAP before > retrying again. The NFS_CAP_UIDGID_NOMAP remains cleared even if > the retry fails. This causes problem for subsequent setattr > requests for v4 server that does not have idmapping configured. > > This patch modifies nfs4_proc_set_acl to detect NFS4ERR_BADOWNER > and NFS4ERR_BADNAME and skips the retry, since the kernel isn't > involved in encoding the ACEs, and return -EINVAL. > > Steps to reproduce the problem: > > # mount -o vers=4.1,sec=sys server:/export/test /tmp/mnt > # touch /tmp/mnt/file1 > # chown 99 /tmp/mnt/file1 > # nfs4_setfacl -a A::unknown.user@xyz.com:wrtncy /tmp/mnt/file1 > Failed setxattr operation: Invalid argument > # chown 99 /tmp/mnt/file1 > chown: changing ownership of ‘/tmp/mnt/file1’: Invalid argument > # umount /tmp/mnt > # mount -o vers=4.1,sec=sys server:/export/test /tmp/mnt > # chown 99 /tmp/mnt/file1 > # > > v2: detect NFS4ERR_BADOWNER and NFS4ERR_BADNAME and skip retry > in nfs4_proc_set_acl. > Signed-off-by: Dai Ngo <dai.ngo(a)oracle.com> > Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: wangyongpan <1071630525(a)qq.com> > --- > fs/nfs/nfs4proc.c | 8 ++++++++ > 1 file changed, 8 insertions(+) > > diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c > index eedcbe6832fb..f387b34bc5e5 100644 > --- a/fs/nfs/nfs4proc.c > +++ b/fs/nfs/nfs4proc.c > @@ -5942,6 +5942,14 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen > do { > err = __nfs4_proc_set_acl(inode, buf, buflen); > trace_nfs4_set_acl(inode, err); > + if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) { > + /* > + * no need to retry since the kernel > + * isn't involved in encoding the ACEs. > + */ > + err = -EINVAL; > + break; > + } > err = nfs4_handle_exception(NFS_SERVER(inode), err, > &exception); > } while (exception.retry);

1 0

[PATCH kernel-5.10] Add a kcpuid tool to show raw CPU features
by zhangyue 26 Oct '21

26 Oct '21

From: Feng Tang <feng.tang(a)intel.com> mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMMB?from=project-issue CVE: NA ------------------------------------ End users frequently want to know what features their processor supports, independent of what the kernel supports. /proc/cpuinfo is great. It is omnipresent and since it is provided by the kernel it is always as up to date as the kernel. But, it could be ambiguous about processor features which can be disabled by the kernel at boot-time or compile-time. There are some user space tools showing more raw features, but they are not bound with kernel, and go with distros. Many end users are still using old distros with new kernels (upgraded by themselves), and may not upgrade the distros only to get a newer tool. So here arise the need for a new tool, which * shows raw CPU features read from the CPUID instruction * will be easier to update compared to existing userspace tooling (perhaps distributed like perf) * inherits "modern" kernel development process, in contrast to some of the existing userspace CPUID tools which are still being developed without git and distributed in tarballs from non-https sites. * Can produce output consistent with /proc/cpuinfo to make comparison easier. The CPUID leaf definitions are kept in an .csv file which allows for updating only that file to add support for new feature leafs. This is based on prototype code from Borislav Petkov (http://sr71.net/~dave/intel/stupid-cpuid.c) [ bp: - Massage, add #define _GNU_SOURCE to fix implicit declaration of function ‘strcasestr' warning - remove superfluous newlines - fallback to cpuid.csv in the current dir if none found - fix typos - move comments over the lines instead of sideways. ] Originally-from: Borislav Petkov <bp(a)alien8.de> Suggested-by: Dave Hansen <dave.hansen(a)intel.com> Suggested-by: Borislav Petkov <bp(a)alien8.de> Signed-off-by: Feng Tang <feng.tang(a)intel.com> Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- tools/arch/x86/kcpuid/Makefile | 24 ++ tools/arch/x86/kcpuid/cpuid.csv | 400 +++++++++++++++++++ tools/arch/x86/kcpuid/kcpuid.c | 657 ++++++++++++++++++++++++++++++++ 3 files changed, 1081 insertions(+) create mode 100644 tools/arch/x86/kcpuid/Makefile create mode 100644 tools/arch/x86/kcpuid/cpuid.csv create mode 100644 tools/arch/x86/kcpuid/kcpuid.c diff --git a/tools/arch/x86/kcpuid/Makefile b/tools/arch/x86/kcpuid/Makefile new file mode 100644 index 000000000000..a2f1e855092c --- /dev/null +++ b/tools/arch/x86/kcpuid/Makefile @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for x86/kcpuid tool + +kcpuid : kcpuid.c + +CFLAGS = -Wextra + +BINDIR ?= /usr/sbin + +HWDATADIR ?= /usr/share/misc/ + +override CFLAGS += -O2 -Wall -I../../../include + +%: %.c + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +.PHONY : clean +clean : + @rm -f kcpuid + +install : kcpuid + install -d $(DESTDIR)$(BINDIR) + install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid + install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv diff --git a/tools/arch/x86/kcpuid/cpuid.csv b/tools/arch/x86/kcpuid/cpuid.csv new file mode 100644 index 000000000000..e422fad9a98e --- /dev/null +++ b/tools/arch/x86/kcpuid/cpuid.csv @@ -0,0 +1,400 @@ +# The basic row format is: +# LEAF, SUBLEAF, register_name, bits, short_name, long_description + +# Leaf 00H + 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + +# Leaf 01H + 1, 0, EAX, 3:0, stepping, Stepping ID + 1, 0, EAX, 7:4, model, Model + 1, 0, EAX, 11:8, family, Family ID + 1, 0, EAX, 13:12, processor, Processor Type + 1, 0, EAX, 19:16, model_ext, Extended Model ID + 1, 0, EAX, 27:20, family_ext, Extended Family ID + + 1, 0, EBX, 7:0, brand, Brand Index + 1, 0, EBX, 15:8, clflush_size, CLFLUSH line size (value * 8) in bytes + 1, 0, EBX, 23:16, max_cpu_id, Maxim number of addressable logic cpu in this package + 1, 0, EBX, 31:24, apic_id, Initial APIC ID + + 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + 1, 0, ECX, 1, pclmulqdq, PCLMULQDQ instruction supported + 1, 0, ECX, 2, dtes64, DS area uses 64-bit layout + 1, 0, ECX, 3, mwait, MONITOR/MWAIT supported + 1, 0, ECX, 4, ds_cpl, CPL Qualified Debug Store which allows for branch message storage qualified by CPL + 1, 0, ECX, 5, vmx, Virtual Machine Extensions supported + 1, 0, ECX, 6, smx, Safer Mode Extension supported + 1, 0, ECX, 7, eist, Enhanced Intel SpeedStep Technology + 1, 0, ECX, 8, tm2, Thermal Monitor 2 + 1, 0, ECX, 9, ssse3, Supplemental Streaming SIMD Extensions 3 (SSSE3) + 1, 0, ECX, 10, l1_ctx_id, L1 data cache could be set to either adaptive mode or shared mode (check IA32_MISC_ENABLE bit 24 definition) + 1, 0, ECX, 11, sdbg, IA32_DEBUG_INTERFACE MSR for silicon debug supported + 1, 0, ECX, 12, fma, FMA extensions using YMM state supported + 1, 0, ECX, 13, cmpxchg16b, 'CMPXCHG16B - Compare and Exchange Bytes' supported + 1, 0, ECX, 14, xtpr_update, xTPR Update Control supported + 1, 0, ECX, 15, pdcm, Perfmon and Debug Capability present + 1, 0, ECX, 17, pcid, Process-Context Identifiers feature present + 1, 0, ECX, 18, dca, Prefetching data from a memory mapped device supported + 1, 0, ECX, 19, sse4_1, SSE4.1 feature present + 1, 0, ECX, 20, sse4_2, SSE4.2 feature present + 1, 0, ECX, 21, x2apic, x2APIC supported + 1, 0, ECX, 22, movbe, MOVBE instruction supported + 1, 0, ECX, 23, popcnt, POPCNT instruction supported + 1, 0, ECX, 24, tsc_deadline_timer, LAPIC supports one-shot operation using a TSC deadline value + 1, 0, ECX, 25, aesni, AESNI instruction supported + 1, 0, ECX, 26, xsave, XSAVE/XRSTOR processor extended states (XSETBV/XGETBV/XCR0) + 1, 0, ECX, 27, osxsave, OS has set CR4.OSXSAVE bit to enable XSETBV/XGETBV/XCR0 + 1, 0, ECX, 28, avx, AVX instruction supported + 1, 0, ECX, 29, f16c, 16-bit floating-point conversion instruction supported + 1, 0, ECX, 30, rdrand, RDRAND instruction supported + + 1, 0, EDX, 0, fpu, x87 FPU on chip + 1, 0, EDX, 1, vme, Virtual-8086 Mode Enhancement + 1, 0, EDX, 2, de, Debugging Extensions + 1, 0, EDX, 3, pse, Page Size Extensions + 1, 0, EDX, 4, tsc, Time Stamp Counter + 1, 0, EDX, 5, msr, RDMSR and WRMSR Support + 1, 0, EDX, 6, pae, Physical Address Extensions + 1, 0, EDX, 7, mce, Machine Check Exception + 1, 0, EDX, 8, cx8, CMPXCHG8B instr + 1, 0, EDX, 9, apic, APIC on Chip + 1, 0, EDX, 11, sep, SYSENTER and SYSEXIT instrs + 1, 0, EDX, 12, mtrr, Memory Type Range Registers + 1, 0, EDX, 13, pge, Page Global Bit + 1, 0, EDX, 14, mca, Machine Check Architecture + 1, 0, EDX, 15, cmov, Conditional Move Instrs + 1, 0, EDX, 16, pat, Page Attribute Table + 1, 0, EDX, 17, pse36, 36-Bit Page Size Extension + 1, 0, EDX, 18, psn, Processor Serial Number + 1, 0, EDX, 19, clflush, CLFLUSH instr +# 1, 0, EDX, 20, + 1, 0, EDX, 21, ds, Debug Store + 1, 0, EDX, 22, acpi, Thermal Monitor and Software Controlled Clock Facilities + 1, 0, EDX, 23, mmx, Intel MMX Technology + 1, 0, EDX, 24, fxsr, XSAVE and FXRSTOR Instrs + 1, 0, EDX, 25, sse, SSE + 1, 0, EDX, 26, sse2, SSE2 + 1, 0, EDX, 27, ss, Self Snoop + 1, 0, EDX, 28, hit, Max APIC IDs + 1, 0, EDX, 29, tm, Thermal Monitor +# 1, 0, EDX, 30, + 1, 0, EDX, 31, pbe, Pending Break Enable + +# Leaf 02H +# cache and TLB descriptor info + +# Leaf 03H +# Precessor Serial Number, introduced on Pentium III, not valid for +# latest models + +# Leaf 04H +# thread/core and cache topology + 4, 0, EAX, 4:0, cache_type, Cache type like instr/data or unified + 4, 0, EAX, 7:5, cache_level, Cache Level (starts at 1) + 4, 0, EAX, 8, cache_self_init, Cache Self Initialization + 4, 0, EAX, 9, fully_associate, Fully Associative cache +# 4, 0, EAX, 13:10, resvd, resvd + 4, 0, EAX, 25:14, max_logical_id, Max number of addressable IDs for logical processors sharing the cache + 4, 0, EAX, 31:26, max_phy_id, Max number of addressable IDs for processors in phy package + + 4, 0, EBX, 11:0, cache_linesize, Size of a cache line in bytes + 4, 0, EBX, 21:12, cache_partition, Physical Line partitions + 4, 0, EBX, 31:22, cache_ways, Ways of associativity + 4, 0, ECX, 31:0, cache_sets, Number of Sets - 1 + 4, 0, EDX, 0, c_wbinvd, 1 means WBINVD/INVD is not ganranteed to act upon lower level caches of non-originating threads sharing this cache + 4, 0, EDX, 1, c_incl, Whether cache is inclusive of lower cache level + 4, 0, EDX, 2, c_comp_index, Complex Cache Indexing + +# Leaf 05H +# MONITOR/MWAIT + 5, 0, EAX, 15:0, min_mon_size, Smallest monitor line size in bytes + 5, 0, EBX, 15:0, max_mon_size, Largest monitor line size in bytes + 5, 0, ECX, 0, mwait_ext, Enum of Monitor-Mwait extensions supported + 5, 0, ECX, 1, mwait_irq_break, Largest monitor line size in bytes + 5, 0, EDX, 3:0, c0_sub_stats, Number of C0* sub C-states supported using MWAIT + 5, 0, EDX, 7:4, c1_sub_stats, Number of C1* sub C-states supported using MWAIT + 5, 0, EDX, 11:8, c2_sub_stats, Number of C2* sub C-states supported using MWAIT + 5, 0, EDX, 15:12, c3_sub_stats, Number of C3* sub C-states supported using MWAIT + 5, 0, EDX, 19:16, c4_sub_stats, Number of C4* sub C-states supported using MWAIT + 5, 0, EDX, 23:20, c5_sub_stats, Number of C5* sub C-states supported using MWAIT + 5, 0, EDX, 27:24, c6_sub_stats, Number of C6* sub C-states supported using MWAIT + 5, 0, EDX, 31:28, c7_sub_stats, Number of C7* sub C-states supported using MWAIT + +# Leaf 06H +# Thermal & Power Management + + 6, 0, EAX, 0, dig_temp, Digital temperature sensor supported + 6, 0, EAX, 1, turbo, Intel Turbo Boost + 6, 0, EAX, 2, arat, Always running APIC timer +# 6, 0, EAX, 3, resv, Reserved + 6, 0, EAX, 4, pln, Power limit notifications supported + 6, 0, EAX, 5, ecmd, Clock modulation duty cycle extension supported + 6, 0, EAX, 6, ptm, Package thermal management supported + 6, 0, EAX, 7, hwp, HWP base register + 6, 0, EAX, 8, hwp_notify, HWP notification + 6, 0, EAX, 9, hwp_act_window, HWP activity window + 6, 0, EAX, 10, hwp_energy, HWP energy performance preference + 6, 0, EAX, 11, hwp_pkg_req, HWP package level request +# 6, 0, EAX, 12, resv, Reserved + 6, 0, EAX, 13, hdc, HDC base registers supported + 6, 0, EAX, 14, turbo3, Turbo Boost Max 3.0 + 6, 0, EAX, 15, hwp_cap, Highest Performance change supported + 6, 0, EAX, 16, hwp_peci, HWP PECI override is supported + 6, 0, EAX, 17, hwp_flex, Flexible HWP is supported + 6, 0, EAX, 18, hwp_fast, Fast access mode for the IA32_HWP_REQUEST MSR is supported +# 6, 0, EAX, 19, resv, Reserved + 6, 0, EAX, 20, hwp_ignr, Ignoring Idle Logical Processor HWP request is supported + + 6, 0, EBX, 3:0, therm_irq_thresh, Number of Interrupt Thresholds in Digital Thermal Sensor + 6, 0, ECX, 0, aperfmperf, Presence of IA32_MPERF and IA32_APERF + 6, 0, ECX, 3, energ_bias, Performance-energy bias preference supported + +# Leaf 07H +# ECX == 0 +# AVX512 refers to https://en.wikipedia.org/wiki/AVX-512 +# XXX: Do we really need to enumerate each and every AVX512 sub features + + 7, 0, EBX, 0, fsgsbase, RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE supported + 7, 0, EBX, 1, tsc_adjust, TSC_ADJUST MSR supported + 7, 0, EBX, 2, sgx, Software Guard Extensions + 7, 0, EBX, 3, bmi1, BMI1 + 7, 0, EBX, 4, hle, Hardware Lock Elision + 7, 0, EBX, 5, avx2, AVX2 +# 7, 0, EBX, 6, fdp_excp_only, x87 FPU Data Pointer updated only on x87 exceptions + 7, 0, EBX, 7, smep, Supervisor-Mode Execution Prevention + 7, 0, EBX, 8, bmi2, BMI2 + 7, 0, EBX, 9, rep_movsb, Enhanced REP MOVSB/STOSB + 7, 0, EBX, 10, invpcid, INVPCID instruction + 7, 0, EBX, 11, rtm, Restricted Transactional Memory + 7, 0, EBX, 12, rdt_m, Intel RDT Monitoring capability + 7, 0, EBX, 13, depc_fpu_cs_ds, Deprecates FPU CS and FPU DS + 7, 0, EBX, 14, mpx, Memory Protection Extensions + 7, 0, EBX, 15, rdt_a, Intel RDT Allocation capability + 7, 0, EBX, 16, avx512f, AVX512 Foundation instr + 7, 0, EBX, 17, avx512dq, AVX512 Double and Quadword AVX512 instr + 7, 0, EBX, 18, rdseed, RDSEED instr + 7, 0, EBX, 19, adx, ADX instr + 7, 0, EBX, 20, smap, Supervisor Mode Access Prevention + 7, 0, EBX, 21, avx512ifma, AVX512 Integer Fused Multiply Add +# 7, 0, EBX, 22, resvd, resvd + 7, 0, EBX, 23, clflushopt, CLFLUSHOPT instr + 7, 0, EBX, 24, clwb, CLWB instr + 7, 0, EBX, 25, intel_pt, Intel Processor Trace instr + 7, 0, EBX, 26, avx512pf, Prefetch + 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr + 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr + 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr + 7, 0, EBX, 26, avx512bw, AVX512 Byte & Word instr + 7, 0, EBX, 28, avx512vl, AVX512 Vector Length Extentions (VL) + 7, 0, ECX, 0, prefetchwt1, X + 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions + 7, 0, ECX, 2, umip, User-mode Instruction Prevention + + 7, 0, ECX, 3, pku, Protection Keys for User-mode pages + 7, 0, ECX, 4, ospke, CR4 PKE set to enable protection keys +# 7, 0, ECX, 16:5, resvd, resvd + 7, 0, ECX, 21:17, mawau, The value of MAWAU used by the BNDLDX and BNDSTX instructions in 64-bit mode + 7, 0, ECX, 22, rdpid, RDPID and IA32_TSC_AUX +# 7, 0, ECX, 29:23, resvd, resvd + 7, 0, ECX, 30, sgx_lc, SGX Launch Configuration +# 7, 0, ECX, 31, resvd, resvd + +# Leaf 08H +# + + +# Leaf 09H +# Direct Cache Access (DCA) information + 9, 0, ECX, 31:0, dca_cap, The value of IA32_PLATFORM_DCA_CAP + +# Leaf 0AH +# Architectural Performance Monitoring +# +# Do we really need to print out the PMU related stuff? +# Does normal user really care about it? +# + 0xA, 0, EAX, 7:0, pmu_ver, Performance Monitoring Unit version + 0xA, 0, EAX, 15:8, pmu_gp_cnt_num, Numer of general-purose PMU counters per logical CPU + 0xA, 0, EAX, 23:16, pmu_cnt_bits, Bit wideth of PMU counter + 0xA, 0, EAX, 31:24, pmu_ebx_bits, Length of EBX bit vector to enumerate PMU events + + 0xA, 0, EBX, 0, pmu_no_core_cycle_evt, Core cycle event not available + 0xA, 0, EBX, 1, pmu_no_instr_ret_evt, Instruction retired event not available + 0xA, 0, EBX, 2, pmu_no_ref_cycle_evt, Reference cycles event not available + 0xA, 0, EBX, 3, pmu_no_llc_ref_evt, Last-level cache reference event not available + 0xA, 0, EBX, 4, pmu_no_llc_mis_evt, Last-level cache misses event not available + 0xA, 0, EBX, 5, pmu_no_br_instr_ret_evt, Branch instruction retired event not available + 0xA, 0, EBX, 6, pmu_no_br_mispredict_evt, Branch mispredict retired event not available + + 0xA, 0, ECX, 4:0, pmu_fixed_cnt_num, Performance Monitoring Unit version + 0xA, 0, ECX, 12:5, pmu_fixed_cnt_bits, Numer of PMU counters per logical CPU + +# Leaf 0BH +# Extended Topology Enumeration Leaf +# + + 0xB, 0, EAX, 4:0, id_shift, Number of bits to shift right on x2APIC ID to get a unique topology ID of the next level type + 0xB, 0, EBX, 15:0, cpu_nr, Number of logical processors at this level type + 0xB, 0, ECX, 15:8, lvl_type, 0-Invalid 1-SMT 2-Core + 0xB, 0, EDX, 31:0, x2apic_id, x2APIC ID the current logical processor + + +# Leaf 0DH +# Processor Extended State + + 0xD, 0, EAX, 0, x87, X87 state + 0xD, 0, EAX, 1, sse, SSE state + 0xD, 0, EAX, 2, avx, AVX state + 0xD, 0, EAX, 4:3, mpx, MPX state + 0xD, 0, EAX, 7:5, avx512, AVX-512 state + 0xD, 0, EAX, 9, pkru, PKRU state + + 0xD, 0, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 0, ECX, 31:0, max_sz_xsave, Maximum size (bytes) of the XSAVE/XRSTOR save area + + 0xD, 1, EAX, 0, xsaveopt, XSAVEOPT available + 0xD, 1, EAX, 1, xsavec, XSAVEC and compacted form supported + 0xD, 1, EAX, 2, xgetbv, XGETBV supported + 0xD, 1, EAX, 3, xsaves, XSAVES/XRSTORS and IA32_XSS supported + + 0xD, 1, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 1, ECX, 8, pt, PT state + 0xD, 1, ECX, 11, cet_usr, CET user state + 0xD, 1, ECX, 12, cet_supv, CET supervisor state + 0xD, 1, ECX, 13, hdc, HDC state + 0xD, 1, ECX, 16, hwp, HWP state + +# Leaf 0FH +# Intel RDT Monitoring + + 0xF, 0, EBX, 31:0, rmid_range, Maximum range (zero-based) of RMID within this physical processor of all types + 0xF, 0, EDX, 1, l3c_rdt_mon, L3 Cache RDT Monitoring supported + + 0xF, 1, ECX, 31:0, rmid_range, Maximum range (zero-based) of RMID of this types + 0xF, 1, EDX, 0, l3c_ocp_mon, L3 Cache occupancy Monitoring supported + 0xF, 1, EDX, 1, l3c_tbw_mon, L3 Cache Total Bandwidth Monitoring supported + 0xF, 1, EDX, 2, l3c_lbw_mon, L3 Cache Local Bandwidth Monitoring supported + +# Leaf 10H +# Intel RDT Allocation + + 0x10, 0, EBX, 1, l3c_rdt_alloc, L3 Cache Allocation supported + 0x10, 0, EBX, 2, l2c_rdt_alloc, L2 Cache Allocation supported + 0x10, 0, EBX, 3, mem_bw_alloc, Memory Bandwidth Allocation supported + + +# Leaf 12H +# SGX Capability +# +# Some detailed SGX features not added yet + + 0x12, 0, EAX, 0, sgx1, L3 Cache Allocation supported + 0x12, 1, EAX, 0, sgx2, L3 Cache Allocation supported + + +# Leaf 14H +# Intel Processor Tracer +# + +# Leaf 15H +# Time Stamp Counter and Nominal Core Crystal Clock Information + + 0x15, 0, EAX, 31:0, tsc_denominator, The denominator of the TSC/”core crystal clock” ratio + 0x15, 0, EBX, 31:0, tsc_numerator, The numerator of the TSC/”core crystal clock” ratio + 0x15, 0, ECX, 31:0, nom_freq, Nominal frequency of the core crystal clock in Hz + +# Leaf 16H +# Processor Frequency Information + + 0x16, 0, EAX, 15:0, cpu_base_freq, Processor Base Frequency in MHz + 0x16, 0, EBX, 15:0, cpu_max_freq, Maximum Frequency in MHz + 0x16, 0, ECX, 15:0, bus_freq, Bus (Reference) Frequency in MHz + +# Leaf 17H +# System-On-Chip Vendor Attribute + + 0x17, 0, EAX, 31:0, max_socid, Maximum input value of supported sub-leaf + 0x17, 0, EBX, 15:0, soc_vid, SOC Vendor ID + 0x17, 0, EBX, 16, std_vid, SOC Vendor ID is assigned via an industry standard scheme + 0x17, 0, ECX, 31:0, soc_pid, SOC Project ID assigned by vendor + 0x17, 0, EDX, 31:0, soc_sid, SOC Stepping ID + +# Leaf 18H +# Deterministic Address Translation Parameters + + +# Leaf 19H +# Key Locker Leaf + + +# Leaf 1AH +# Hybrid Information + + 0x1A, 0, EAX, 31:24, core_type, 20H-Intel_Atom 40H-Intel_Core + + +# Leaf 1FH +# V2 Extended Topology - A preferred superset to leaf 0BH + + +# According to SDM +# 40000000H - 4FFFFFFFH is invalid range + + +# Leaf 80000001H +# Extended Processor Signature and Feature Bits + +0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode +0x80000001, 0, ECX, 5, lzcnt, LZCNT +0x80000001, 0, ECX, 8, prefetchw, PREFETCHW + +0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported +0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available +0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported +0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available +#0x80000001, 0, EDX, 29, 64b, 64b Architecture supported + +# Leaf 80000002H/80000003H/80000004H +# Processor Brand String + +# Leaf 80000005H +# Reserved + +# Leaf 80000006H +# Extended L2 Cache Features + +0x80000006, 0, ECX, 7:0, clsize, Cache Line size in bytes +0x80000006, 0, ECX, 15:12, l2c_assoc, L2 Associativity +0x80000006, 0, ECX, 31:16, csize, Cache size in 1K units + + +# Leaf 80000007H + +0x80000007, 0, EDX, 8, nonstop_tsc, Invariant TSC available + + +# Leaf 80000008H + +0x80000008, 0, EAX, 7:0, phy_adr_bits, Physical Address Bits +0x80000008, 0, EAX, 15:8, lnr_adr_bits, Linear Address Bits +0x80000007, 0, EBX, 9, wbnoinvd, WBNOINVD + +# 0x8000001E +# EAX: Extended APIC ID +0x8000001E, 0, EAX, 31:0, extended_apic_id, Extended APIC ID +# EBX: Core Identifiers +0x8000001E, 0, EBX, 7:0, core_id, Identifies the logical core ID +0x8000001E, 0, EBX, 15:8, threads_per_core, The number of threads per core is threads_per_core + 1 +# ECX: Node Identifiers +0x8000001E, 0, ECX, 7:0, node_id, Node ID +0x8000001E, 0, ECX, 10:8, nodes_per_processor, Nodes per processor { 0: 1 node, else reserved } + +# 8000001F: AMD Secure Encryption +0x8000001F, 0, EAX, 0, sme, Secure Memory Encryption +0x8000001F, 0, EAX, 1, sev, Secure Encrypted Virtualization +0x8000001F, 0, EAX, 2, vmpgflush, VM Page Flush MSR +0x8000001F, 0, EAX, 3, seves, SEV Encrypted State +0x8000001F, 0, EBX, 5:0, c-bit, Page table bit number used to enable memory encryption +0x8000001F, 0, EBX, 11:6, mem_encrypt_physaddr_width, Reduction of physical address space in bits with SME enabled +0x8000001F, 0, ECX, 31:0, num_encrypted_guests, Maximum ASID value that may be used for an SEV-enabled guest +0x8000001F, 0, EDX, 31:0, minimum_sev_asid, Minimum ASID value that must be used for an SEV-enabled, SEV-ES-disabled guest \ No newline at end of file diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c new file mode 100644 index 000000000000..936a3a2aad04 --- /dev/null +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> +#include <getopt.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef unsigned int u32; +typedef unsigned long long u64; + +char *def_csv = "/usr/share/misc/cpuid.csv"; +char *user_csv; + + +/* Cover both single-bit flag and multiple-bits fields */ +struct bits_desc { + /* start and end bits */ + int start, end; + /* 0 or 1 for 1-bit flag */ + int value; + char simp[32]; + char detail[256]; +}; + +/* descriptor info for eax/ebx/ecx/edx */ +struct reg_desc { + /* number of valid entries */ + int nr; + struct bits_desc descs[32]; +}; + +enum { + R_EAX = 0, + R_EBX, + R_ECX, + R_EDX, + NR_REGS +}; + +struct subleaf { + u32 index; + u32 sub; + u32 eax, ebx, ecx, edx; + struct reg_desc info[NR_REGS]; +}; + +/* Represent one leaf (basic or extended) */ +struct cpuid_func { + /* + * Array of subleafs for this func, if there is no subleafs + * then the leafs[0] is the main leaf + */ + struct subleaf *leafs; + int nr; +}; + +struct cpuid_range { + /* array of main leafs */ + struct cpuid_func *funcs; + /* number of valid leafs */ + int nr; + bool is_ext; +}; + +/* + * basic: basic functions range: [0... ] + * ext: extended functions range: [0x80000000... ] + */ +struct cpuid_range *leafs_basic, *leafs_ext; + +static int num_leafs; +static bool is_amd; +static bool show_details; +static bool show_raw; +static bool show_flags_only = true; +static u32 user_index = 0xFFFFFFFF; +static u32 user_sub = 0xFFFFFFFF; +static int flines; + +static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline bool has_subleafs(u32 f) +{ + if (f == 0x7 || f == 0xd) + return true; + + if (is_amd) { + if (f == 0x8000001d) + return true; + return false; + } + + switch (f) { + case 0x4: + case 0xb: + case 0xf: + case 0x10: + case 0x14: + case 0x18: + case 0x1f: + return true; + default: + return false; + } +} + +static void leaf_print_raw(struct subleaf *leaf) +{ + if (has_subleafs(leaf->index)) { + if (leaf->sub == 0) + printf("0x%08x: subleafs:\n", leaf->index); + + printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->sub, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } else { + printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->index, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } +} + +/* Return true is the input eax/ebx/ecx/edx are all zero */ +static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf, + u32 a, u32 b, u32 c, u32 d) +{ + struct cpuid_func *func; + struct subleaf *leaf; + int s = 0; + + if (a == 0 && b == 0 && c == 0 && d == 0) + return true; + + /* + * Cut off vendor-prefix from CPUID function as we're using it as an + * index into ->funcs. + */ + func = &range->funcs[f & 0xffff]; + + if (!func->leafs) { + func->leafs = malloc(sizeof(struct subleaf)); + if (!func->leafs) + perror("malloc func leaf"); + + func->nr = 1; + } else { + s = func->nr; + func->leafs = realloc(func->leafs, (s + 1) * sizeof(*leaf)); + if (!func->leafs) + perror("realloc f->leafs"); + + func->nr++; + } + + leaf = &func->leafs[s]; + + leaf->index = f; + leaf->sub = subleaf; + leaf->eax = a; + leaf->ebx = b; + leaf->ecx = c; + leaf->edx = d; + + return false; +} + +static void raw_dump_range(struct cpuid_range *range) +{ + u32 f; + int i; + + printf("%s Leafs :\n", range->is_ext ? "Extended" : "Basic"); + printf("================\n"); + + for (f = 0; (int)f < range->nr; f++) { + struct cpuid_func *func = &range->funcs[f]; + u32 index = f; + + if (range->is_ext) + index += 0x80000000; + + /* Skip leaf without valid items */ + if (!func->nr) + continue; + + /* First item is the main leaf, followed by all subleafs */ + for (i = 0; i < func->nr; i++) + leaf_print_raw(&func->leafs[i]); + } +} + +#define MAX_SUBLEAF_NUM 32 +struct cpuid_range *setup_cpuid_range(u32 input_eax) +{ + u32 max_func, idx_func; + int subleaf; + struct cpuid_range *range; + u32 eax, ebx, ecx, edx; + u32 f = input_eax; + int max_subleaf; + bool allzero; + + eax = input_eax; + ebx = ecx = edx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + max_func = eax; + idx_func = (max_func & 0xffff) + 1; + + range = malloc(sizeof(struct cpuid_range)); + if (!range) + perror("malloc range"); + + if (input_eax & 0x80000000) + range->is_ext = true; + else + range->is_ext = false; + + range->funcs = malloc(sizeof(struct cpuid_func) * idx_func); + if (!range->funcs) + perror("malloc range->funcs"); + + range->nr = idx_func; + memset(range->funcs, 0, sizeof(struct cpuid_func) * idx_func); + + for (; f <= max_func; f++) { + eax = f; + subleaf = ecx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + + if (!has_subleafs(f)) + continue; + + max_subleaf = MAX_SUBLEAF_NUM; + + /* + * Some can provide the exact number of subleafs, + * others have to be tried (0xf) + */ + if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18) + max_subleaf = (eax & 0xff) + 1; + + if (f == 0xb) + max_subleaf = 2; + + for (subleaf = 1; subleaf < max_subleaf; subleaf++) { + eax = f; + ecx = subleaf; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, + eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + } + + } + + return range; +} + +/* + * The basic row format for cpuid.csv is + * LEAF,SUBLEAF,register_name,bits,short name,long description + * + * like: + * 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + * 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + */ +static int parse_line(char *line) +{ + char *str; + int i; + struct cpuid_range *range; + struct cpuid_func *func; + struct subleaf *leaf; + u32 index; + u32 sub; + char buffer[512]; + char *buf; + /* + * Tokens: + * 1. leaf + * 2. subleaf + * 3. register + * 4. bits + * 5. short name + * 6. long detail + */ + char *tokens[6]; + struct reg_desc *reg; + struct bits_desc *bdesc; + int reg_index; + char *start, *end; + + /* Skip comments and NULL line */ + if (line[0] == '#' || line[0] == '\n') + return 0; + + strncpy(buffer, line, 511); + buffer[511] = 0; + str = buffer; + for (i = 0; i < 5; i++) { + tokens[i] = strtok(str, ","); + if (!tokens[i]) + goto err_exit; + str = NULL; + } + tokens[5] = strtok(str, "\n"); + if (!tokens[5]) + goto err_exit; + + /* index/main-leaf */ + index = strtoull(tokens[0], NULL, 0); + + if (index & 0x80000000) + range = leafs_ext; + else + range = leafs_basic; + + index &= 0x7FFFFFFF; + /* Skip line parsing for non-existing indexes */ + if ((int)index >= range->nr) + return -1; + + func = &range->funcs[index]; + + /* Return if the index has no valid item on this platform */ + if (!func->nr) + return 0; + + /* subleaf */ + sub = strtoul(tokens[1], NULL, 0); + if ((int)sub > func->nr) + return -1; + + leaf = &func->leafs[sub]; + buf = tokens[2]; + + if (strcasestr(buf, "EAX")) + reg_index = R_EAX; + else if (strcasestr(buf, "EBX")) + reg_index = R_EBX; + else if (strcasestr(buf, "ECX")) + reg_index = R_ECX; + else if (strcasestr(buf, "EDX")) + reg_index = R_EDX; + else + goto err_exit; + + reg = &leaf->info[reg_index]; + bdesc = &reg->descs[reg->nr++]; + + /* bit flag or bits field */ + buf = tokens[3]; + + end = strtok(buf, ":"); + bdesc->end = strtoul(end, NULL, 0); + bdesc->start = bdesc->end; + + /* start != NULL means it is bit fields */ + start = strtok(NULL, ":"); + if (start) + bdesc->start = strtoul(start, NULL, 0); + + strcpy(bdesc->simp, tokens[4]); + strcpy(bdesc->detail, tokens[5]); + return 0; + +err_exit: + printf("Warning: wrong line format:\n"); + printf("\tline[%d]: %s\n", flines, line); + return -1; +} + +/* Parse csv file, and construct the array of all leafs and subleafs */ +static void parse_text(void) +{ + FILE *file; + char *filename, *line = NULL; + size_t len = 0; + int ret; + + if (show_raw) + return; + + filename = user_csv ? user_csv : def_csv; + file = fopen(filename, "r"); + if (!file) { + /* Fallback to a csv in the same dir */ + file = fopen("./cpuid.csv", "r"); + } + + if (!file) { + printf("Fail to open '%s'\n", filename); + return; + } + + while (1) { + ret = getline(&line, &len, file); + flines++; + if (ret > 0) + parse_line(line); + + if (feof(file)) + break; + } + + fclose(file); +} + + +/* Decode every eax/ebx/ecx/edx */ +static void decode_bits(u32 value, struct reg_desc *rdesc) +{ + struct bits_desc *bdesc; + int start, end, i; + u32 mask; + + for (i = 0; i < rdesc->nr; i++) { + bdesc = &rdesc->descs[i]; + + start = bdesc->start; + end = bdesc->end; + if (start == end) { + /* single bit flag */ + if (value & (1 << start)) + printf("\t%-20s %s%s\n", + bdesc->simp, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } else { + /* bit fields */ + if (show_flags_only) + continue; + + mask = ((u64)1 << (end - start + 1)) - 1; + printf("\t%-20s\t: 0x%-8x\t%s%s\n", + bdesc->simp, + (value >> start) & mask, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } + } +} + +static void show_leaf(struct subleaf *leaf) +{ + if (!leaf) + return; + + if (show_raw) + leaf_print_raw(leaf); + + decode_bits(leaf->eax, &leaf->info[R_EAX]); + decode_bits(leaf->ebx, &leaf->info[R_EBX]); + decode_bits(leaf->ecx, &leaf->info[R_ECX]); + decode_bits(leaf->edx, &leaf->info[R_EDX]); +} + +static void show_func(struct cpuid_func *func) +{ + int i; + + if (!func) + return; + + for (i = 0; i < func->nr; i++) + show_leaf(&func->leafs[i]); +} + +static void show_range(struct cpuid_range *range) +{ + int i; + + for (i = 0; i < range->nr; i++) + show_func(&range->funcs[i]); +} + +static inline struct cpuid_func *index_to_func(u32 index) +{ + struct cpuid_range *range; + + range = (index & 0x80000000) ? leafs_ext : leafs_basic; + index &= 0x7FFFFFFF; + + if (((index & 0xFFFF) + 1) > (u32)range->nr) { + printf("ERR: invalid input index (0x%x)\n", index); + return NULL; + } + return &range->funcs[index]; +} + +static void show_info(void) +{ + struct cpuid_func *func; + + if (show_raw) { + /* Show all of the raw output of 'cpuid' instr */ + raw_dump_range(leafs_basic); + raw_dump_range(leafs_ext); + return; + } + + if (user_index != 0xFFFFFFFF) { + /* Only show specific leaf/subleaf info */ + func = index_to_func(user_index); + if (!func) + return; + + /* Dump the raw data also */ + show_raw = true; + + if (user_sub != 0xFFFFFFFF) { + if (user_sub + 1 <= (u32)func->nr) { + show_leaf(&func->leafs[user_sub]); + return; + } + + printf("ERR: invalid input subleaf (0x%x)\n", user_sub); + } + + show_func(func); + return; + } + + printf("CPU features:\n=============\n\n"); + show_range(leafs_basic); + show_range(leafs_ext); +} + +static void setup_platform_cpuid(void) +{ + u32 eax, ebx, ecx, edx; + + /* Check vendor */ + eax = ebx = ecx = edx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + + /* "htuA" */ + if (ebx == 0x68747541) + is_amd = true; + + /* Setup leafs for the basic and extended range */ + leafs_basic = setup_cpuid_range(0x0); + leafs_ext = setup_cpuid_range(0x80000000); +} + +static void usage(void) +{ + printf("kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n" + "\t-a|--all Show both bit flags and complex bit fields info\n" + "\t-b|--bitflags Show boolean flags only\n" + "\t-d|--detail Show details of the flag/fields (default)\n" + "\t-f|--flags Specify the cpuid csv file\n" + "\t-h|--help Show usage info\n" + "\t-l|--leaf=index Specify the leaf you want to check\n" + "\t-r|--raw Show raw cpuid data\n" + "\t-s|--subleaf=sub Specify the subleaf you want to check\n" + ); +} + +static struct option opts[] = { + { "all", no_argument, NULL, 'a' }, /* show both bit flags and fields */ + { "bitflags", no_argument, NULL, 'b' }, /* only show bit flags, default on */ + { "detail", no_argument, NULL, 'd' }, /* show detail descriptions */ + { "file", required_argument, NULL, 'f' }, /* use user's cpuid file */ + { "help", no_argument, NULL, 'h'}, /* show usage */ + { "leaf", required_argument, NULL, 'l'}, /* only check a specific leaf */ + { "raw", no_argument, NULL, 'r'}, /* show raw CPUID leaf data */ + { "subleaf", required_argument, NULL, 's'}, /* check a specific subleaf */ + { NULL, 0, NULL, 0 } +}; + +static int parse_options(int argc, char *argv[]) +{ + int c; + + while ((c = getopt_long(argc, argv, "abdf:hl:rs:", + opts, NULL)) != -1) + switch (c) { + case 'a': + show_flags_only = false; + break; + case 'b': + show_flags_only = true; + break; + case 'd': + show_details = true; + break; + case 'f': + user_csv = optarg; + break; + case 'h': + usage(); + exit(1); + break; + case 'l': + /* main leaf */ + user_index = strtoul(optarg, NULL, 0); + break; + case 'r': + show_raw = true; + break; + case 's': + /* subleaf */ + user_sub = strtoul(optarg, NULL, 0); + break; + default: + printf("%s: Invalid option '%c'\n", argv[0], optopt); + return -1; + } + + return 0; +} + +/* + * Do 4 things in turn: + * 1. Parse user options + * 2. Parse and store all the CPUID leaf data supported on this platform + * 2. Parse the csv file, while skipping leafs which are not available + * on this platform + * 3. Print leafs info based on user options + */ +int main(int argc, char *argv[]) +{ + if (parse_options(argc, argv)) + return -1; + + /* Setup the cpuid leafs of current platform */ + setup_platform_cpuid(); + + /* Read and parse the 'cpuid.csv' */ + parse_text(); + + show_info(); + return 0; +} \ No newline at end of file -- 2.30.0

1 0

[PATCH kernel-5.10] Add a kcpuid tool to show raw CPU features
by zhangyue 26 Oct '21

26 Oct '21

From: Feng Tang <feng.tang(a)intel.com> mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMMB?from=project-issue CVE: NA ------------------------------------ End users frequently want to know what features their processor supports, independent of what the kernel supports. /proc/cpuinfo is great. It is omnipresent and since it is provided by the kernel it is always as up to date as the kernel. But, it could be ambiguous about processor features which can be disabled by the kernel at boot-time or compile-time. There are some user space tools showing more raw features, but they are not bound with kernel, and go with distros. Many end users are still using old distros with new kernels (upgraded by themselves), and may not upgrade the distros only to get a newer tool. So here arise the need for a new tool, which * shows raw CPU features read from the CPUID instruction * will be easier to update compared to existing userspace tooling (perhaps distributed like perf) * inherits "modern" kernel development process, in contrast to some of the existing userspace CPUID tools which are still being developed without git and distributed in tarballs from non-https sites. * Can produce output consistent with /proc/cpuinfo to make comparison easier. The CPUID leaf definitions are kept in an .csv file which allows for updating only that file to add support for new feature leafs. This is based on prototype code from Borislav Petkov (http://sr71.net/~dave/intel/stupid-cpuid.c) [ bp: - Massage, add #define _GNU_SOURCE to fix implicit declaration of function ‘strcasestr' warning - remove superfluous newlines - fallback to cpuid.csv in the current dir if none found - fix typos - move comments over the lines instead of sideways. ] Originally-from: Borislav Petkov <bp(a)alien8.de> Suggested-by: Dave Hansen <dave.hansen(a)intel.com> Suggested-by: Borislav Petkov <bp(a)alien8.de> Signed-off-by: Feng Tang <feng.tang(a)intel.com> Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- tools/arch/x86/kcpuid/Makefile | 24 ++ tools/arch/x86/kcpuid/cpuid.csv | 400 +++++++++++++++++++ tools/arch/x86/kcpuid/kcpuid.c | 657 ++++++++++++++++++++++++++++++++ 3 files changed, 1081 insertions(+) create mode 100644 tools/arch/x86/kcpuid/Makefile create mode 100644 tools/arch/x86/kcpuid/cpuid.csv create mode 100644 tools/arch/x86/kcpuid/kcpuid.c diff --git a/tools/arch/x86/kcpuid/Makefile b/tools/arch/x86/kcpuid/Makefile new file mode 100644 index 000000000000..a2f1e855092c --- /dev/null +++ b/tools/arch/x86/kcpuid/Makefile @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for x86/kcpuid tool + +kcpuid : kcpuid.c + +CFLAGS = -Wextra + +BINDIR ?= /usr/sbin + +HWDATADIR ?= /usr/share/misc/ + +override CFLAGS += -O2 -Wall -I../../../include + +%: %.c + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +.PHONY : clean +clean : + @rm -f kcpuid + +install : kcpuid + install -d $(DESTDIR)$(BINDIR) + install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid + install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv diff --git a/tools/arch/x86/kcpuid/cpuid.csv b/tools/arch/x86/kcpuid/cpuid.csv new file mode 100644 index 000000000000..e422fad9a98e --- /dev/null +++ b/tools/arch/x86/kcpuid/cpuid.csv @@ -0,0 +1,400 @@ +# The basic row format is: +# LEAF, SUBLEAF, register_name, bits, short_name, long_description + +# Leaf 00H + 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + +# Leaf 01H + 1, 0, EAX, 3:0, stepping, Stepping ID + 1, 0, EAX, 7:4, model, Model + 1, 0, EAX, 11:8, family, Family ID + 1, 0, EAX, 13:12, processor, Processor Type + 1, 0, EAX, 19:16, model_ext, Extended Model ID + 1, 0, EAX, 27:20, family_ext, Extended Family ID + + 1, 0, EBX, 7:0, brand, Brand Index + 1, 0, EBX, 15:8, clflush_size, CLFLUSH line size (value * 8) in bytes + 1, 0, EBX, 23:16, max_cpu_id, Maxim number of addressable logic cpu in this package + 1, 0, EBX, 31:24, apic_id, Initial APIC ID + + 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + 1, 0, ECX, 1, pclmulqdq, PCLMULQDQ instruction supported + 1, 0, ECX, 2, dtes64, DS area uses 64-bit layout + 1, 0, ECX, 3, mwait, MONITOR/MWAIT supported + 1, 0, ECX, 4, ds_cpl, CPL Qualified Debug Store which allows for branch message storage qualified by CPL + 1, 0, ECX, 5, vmx, Virtual Machine Extensions supported + 1, 0, ECX, 6, smx, Safer Mode Extension supported + 1, 0, ECX, 7, eist, Enhanced Intel SpeedStep Technology + 1, 0, ECX, 8, tm2, Thermal Monitor 2 + 1, 0, ECX, 9, ssse3, Supplemental Streaming SIMD Extensions 3 (SSSE3) + 1, 0, ECX, 10, l1_ctx_id, L1 data cache could be set to either adaptive mode or shared mode (check IA32_MISC_ENABLE bit 24 definition) + 1, 0, ECX, 11, sdbg, IA32_DEBUG_INTERFACE MSR for silicon debug supported + 1, 0, ECX, 12, fma, FMA extensions using YMM state supported + 1, 0, ECX, 13, cmpxchg16b, 'CMPXCHG16B - Compare and Exchange Bytes' supported + 1, 0, ECX, 14, xtpr_update, xTPR Update Control supported + 1, 0, ECX, 15, pdcm, Perfmon and Debug Capability present + 1, 0, ECX, 17, pcid, Process-Context Identifiers feature present + 1, 0, ECX, 18, dca, Prefetching data from a memory mapped device supported + 1, 0, ECX, 19, sse4_1, SSE4.1 feature present + 1, 0, ECX, 20, sse4_2, SSE4.2 feature present + 1, 0, ECX, 21, x2apic, x2APIC supported + 1, 0, ECX, 22, movbe, MOVBE instruction supported + 1, 0, ECX, 23, popcnt, POPCNT instruction supported + 1, 0, ECX, 24, tsc_deadline_timer, LAPIC supports one-shot operation using a TSC deadline value + 1, 0, ECX, 25, aesni, AESNI instruction supported + 1, 0, ECX, 26, xsave, XSAVE/XRSTOR processor extended states (XSETBV/XGETBV/XCR0) + 1, 0, ECX, 27, osxsave, OS has set CR4.OSXSAVE bit to enable XSETBV/XGETBV/XCR0 + 1, 0, ECX, 28, avx, AVX instruction supported + 1, 0, ECX, 29, f16c, 16-bit floating-point conversion instruction supported + 1, 0, ECX, 30, rdrand, RDRAND instruction supported + + 1, 0, EDX, 0, fpu, x87 FPU on chip + 1, 0, EDX, 1, vme, Virtual-8086 Mode Enhancement + 1, 0, EDX, 2, de, Debugging Extensions + 1, 0, EDX, 3, pse, Page Size Extensions + 1, 0, EDX, 4, tsc, Time Stamp Counter + 1, 0, EDX, 5, msr, RDMSR and WRMSR Support + 1, 0, EDX, 6, pae, Physical Address Extensions + 1, 0, EDX, 7, mce, Machine Check Exception + 1, 0, EDX, 8, cx8, CMPXCHG8B instr + 1, 0, EDX, 9, apic, APIC on Chip + 1, 0, EDX, 11, sep, SYSENTER and SYSEXIT instrs + 1, 0, EDX, 12, mtrr, Memory Type Range Registers + 1, 0, EDX, 13, pge, Page Global Bit + 1, 0, EDX, 14, mca, Machine Check Architecture + 1, 0, EDX, 15, cmov, Conditional Move Instrs + 1, 0, EDX, 16, pat, Page Attribute Table + 1, 0, EDX, 17, pse36, 36-Bit Page Size Extension + 1, 0, EDX, 18, psn, Processor Serial Number + 1, 0, EDX, 19, clflush, CLFLUSH instr +# 1, 0, EDX, 20, + 1, 0, EDX, 21, ds, Debug Store + 1, 0, EDX, 22, acpi, Thermal Monitor and Software Controlled Clock Facilities + 1, 0, EDX, 23, mmx, Intel MMX Technology + 1, 0, EDX, 24, fxsr, XSAVE and FXRSTOR Instrs + 1, 0, EDX, 25, sse, SSE + 1, 0, EDX, 26, sse2, SSE2 + 1, 0, EDX, 27, ss, Self Snoop + 1, 0, EDX, 28, hit, Max APIC IDs + 1, 0, EDX, 29, tm, Thermal Monitor +# 1, 0, EDX, 30, + 1, 0, EDX, 31, pbe, Pending Break Enable + +# Leaf 02H +# cache and TLB descriptor info + +# Leaf 03H +# Precessor Serial Number, introduced on Pentium III, not valid for +# latest models + +# Leaf 04H +# thread/core and cache topology + 4, 0, EAX, 4:0, cache_type, Cache type like instr/data or unified + 4, 0, EAX, 7:5, cache_level, Cache Level (starts at 1) + 4, 0, EAX, 8, cache_self_init, Cache Self Initialization + 4, 0, EAX, 9, fully_associate, Fully Associative cache +# 4, 0, EAX, 13:10, resvd, resvd + 4, 0, EAX, 25:14, max_logical_id, Max number of addressable IDs for logical processors sharing the cache + 4, 0, EAX, 31:26, max_phy_id, Max number of addressable IDs for processors in phy package + + 4, 0, EBX, 11:0, cache_linesize, Size of a cache line in bytes + 4, 0, EBX, 21:12, cache_partition, Physical Line partitions + 4, 0, EBX, 31:22, cache_ways, Ways of associativity + 4, 0, ECX, 31:0, cache_sets, Number of Sets - 1 + 4, 0, EDX, 0, c_wbinvd, 1 means WBINVD/INVD is not ganranteed to act upon lower level caches of non-originating threads sharing this cache + 4, 0, EDX, 1, c_incl, Whether cache is inclusive of lower cache level + 4, 0, EDX, 2, c_comp_index, Complex Cache Indexing + +# Leaf 05H +# MONITOR/MWAIT + 5, 0, EAX, 15:0, min_mon_size, Smallest monitor line size in bytes + 5, 0, EBX, 15:0, max_mon_size, Largest monitor line size in bytes + 5, 0, ECX, 0, mwait_ext, Enum of Monitor-Mwait extensions supported + 5, 0, ECX, 1, mwait_irq_break, Largest monitor line size in bytes + 5, 0, EDX, 3:0, c0_sub_stats, Number of C0* sub C-states supported using MWAIT + 5, 0, EDX, 7:4, c1_sub_stats, Number of C1* sub C-states supported using MWAIT + 5, 0, EDX, 11:8, c2_sub_stats, Number of C2* sub C-states supported using MWAIT + 5, 0, EDX, 15:12, c3_sub_stats, Number of C3* sub C-states supported using MWAIT + 5, 0, EDX, 19:16, c4_sub_stats, Number of C4* sub C-states supported using MWAIT + 5, 0, EDX, 23:20, c5_sub_stats, Number of C5* sub C-states supported using MWAIT + 5, 0, EDX, 27:24, c6_sub_stats, Number of C6* sub C-states supported using MWAIT + 5, 0, EDX, 31:28, c7_sub_stats, Number of C7* sub C-states supported using MWAIT + +# Leaf 06H +# Thermal & Power Management + + 6, 0, EAX, 0, dig_temp, Digital temperature sensor supported + 6, 0, EAX, 1, turbo, Intel Turbo Boost + 6, 0, EAX, 2, arat, Always running APIC timer +# 6, 0, EAX, 3, resv, Reserved + 6, 0, EAX, 4, pln, Power limit notifications supported + 6, 0, EAX, 5, ecmd, Clock modulation duty cycle extension supported + 6, 0, EAX, 6, ptm, Package thermal management supported + 6, 0, EAX, 7, hwp, HWP base register + 6, 0, EAX, 8, hwp_notify, HWP notification + 6, 0, EAX, 9, hwp_act_window, HWP activity window + 6, 0, EAX, 10, hwp_energy, HWP energy performance preference + 6, 0, EAX, 11, hwp_pkg_req, HWP package level request +# 6, 0, EAX, 12, resv, Reserved + 6, 0, EAX, 13, hdc, HDC base registers supported + 6, 0, EAX, 14, turbo3, Turbo Boost Max 3.0 + 6, 0, EAX, 15, hwp_cap, Highest Performance change supported + 6, 0, EAX, 16, hwp_peci, HWP PECI override is supported + 6, 0, EAX, 17, hwp_flex, Flexible HWP is supported + 6, 0, EAX, 18, hwp_fast, Fast access mode for the IA32_HWP_REQUEST MSR is supported +# 6, 0, EAX, 19, resv, Reserved + 6, 0, EAX, 20, hwp_ignr, Ignoring Idle Logical Processor HWP request is supported + + 6, 0, EBX, 3:0, therm_irq_thresh, Number of Interrupt Thresholds in Digital Thermal Sensor + 6, 0, ECX, 0, aperfmperf, Presence of IA32_MPERF and IA32_APERF + 6, 0, ECX, 3, energ_bias, Performance-energy bias preference supported + +# Leaf 07H +# ECX == 0 +# AVX512 refers to https://en.wikipedia.org/wiki/AVX-512 +# XXX: Do we really need to enumerate each and every AVX512 sub features + + 7, 0, EBX, 0, fsgsbase, RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE supported + 7, 0, EBX, 1, tsc_adjust, TSC_ADJUST MSR supported + 7, 0, EBX, 2, sgx, Software Guard Extensions + 7, 0, EBX, 3, bmi1, BMI1 + 7, 0, EBX, 4, hle, Hardware Lock Elision + 7, 0, EBX, 5, avx2, AVX2 +# 7, 0, EBX, 6, fdp_excp_only, x87 FPU Data Pointer updated only on x87 exceptions + 7, 0, EBX, 7, smep, Supervisor-Mode Execution Prevention + 7, 0, EBX, 8, bmi2, BMI2 + 7, 0, EBX, 9, rep_movsb, Enhanced REP MOVSB/STOSB + 7, 0, EBX, 10, invpcid, INVPCID instruction + 7, 0, EBX, 11, rtm, Restricted Transactional Memory + 7, 0, EBX, 12, rdt_m, Intel RDT Monitoring capability + 7, 0, EBX, 13, depc_fpu_cs_ds, Deprecates FPU CS and FPU DS + 7, 0, EBX, 14, mpx, Memory Protection Extensions + 7, 0, EBX, 15, rdt_a, Intel RDT Allocation capability + 7, 0, EBX, 16, avx512f, AVX512 Foundation instr + 7, 0, EBX, 17, avx512dq, AVX512 Double and Quadword AVX512 instr + 7, 0, EBX, 18, rdseed, RDSEED instr + 7, 0, EBX, 19, adx, ADX instr + 7, 0, EBX, 20, smap, Supervisor Mode Access Prevention + 7, 0, EBX, 21, avx512ifma, AVX512 Integer Fused Multiply Add +# 7, 0, EBX, 22, resvd, resvd + 7, 0, EBX, 23, clflushopt, CLFLUSHOPT instr + 7, 0, EBX, 24, clwb, CLWB instr + 7, 0, EBX, 25, intel_pt, Intel Processor Trace instr + 7, 0, EBX, 26, avx512pf, Prefetch + 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr + 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr + 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr + 7, 0, EBX, 26, avx512bw, AVX512 Byte & Word instr + 7, 0, EBX, 28, avx512vl, AVX512 Vector Length Extentions (VL) + 7, 0, ECX, 0, prefetchwt1, X + 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions + 7, 0, ECX, 2, umip, User-mode Instruction Prevention + + 7, 0, ECX, 3, pku, Protection Keys for User-mode pages + 7, 0, ECX, 4, ospke, CR4 PKE set to enable protection keys +# 7, 0, ECX, 16:5, resvd, resvd + 7, 0, ECX, 21:17, mawau, The value of MAWAU used by the BNDLDX and BNDSTX instructions in 64-bit mode + 7, 0, ECX, 22, rdpid, RDPID and IA32_TSC_AUX +# 7, 0, ECX, 29:23, resvd, resvd + 7, 0, ECX, 30, sgx_lc, SGX Launch Configuration +# 7, 0, ECX, 31, resvd, resvd + +# Leaf 08H +# + + +# Leaf 09H +# Direct Cache Access (DCA) information + 9, 0, ECX, 31:0, dca_cap, The value of IA32_PLATFORM_DCA_CAP + +# Leaf 0AH +# Architectural Performance Monitoring +# +# Do we really need to print out the PMU related stuff? +# Does normal user really care about it? +# + 0xA, 0, EAX, 7:0, pmu_ver, Performance Monitoring Unit version + 0xA, 0, EAX, 15:8, pmu_gp_cnt_num, Numer of general-purose PMU counters per logical CPU + 0xA, 0, EAX, 23:16, pmu_cnt_bits, Bit wideth of PMU counter + 0xA, 0, EAX, 31:24, pmu_ebx_bits, Length of EBX bit vector to enumerate PMU events + + 0xA, 0, EBX, 0, pmu_no_core_cycle_evt, Core cycle event not available + 0xA, 0, EBX, 1, pmu_no_instr_ret_evt, Instruction retired event not available + 0xA, 0, EBX, 2, pmu_no_ref_cycle_evt, Reference cycles event not available + 0xA, 0, EBX, 3, pmu_no_llc_ref_evt, Last-level cache reference event not available + 0xA, 0, EBX, 4, pmu_no_llc_mis_evt, Last-level cache misses event not available + 0xA, 0, EBX, 5, pmu_no_br_instr_ret_evt, Branch instruction retired event not available + 0xA, 0, EBX, 6, pmu_no_br_mispredict_evt, Branch mispredict retired event not available + + 0xA, 0, ECX, 4:0, pmu_fixed_cnt_num, Performance Monitoring Unit version + 0xA, 0, ECX, 12:5, pmu_fixed_cnt_bits, Numer of PMU counters per logical CPU + +# Leaf 0BH +# Extended Topology Enumeration Leaf +# + + 0xB, 0, EAX, 4:0, id_shift, Number of bits to shift right on x2APIC ID to get a unique topology ID of the next level type + 0xB, 0, EBX, 15:0, cpu_nr, Number of logical processors at this level type + 0xB, 0, ECX, 15:8, lvl_type, 0-Invalid 1-SMT 2-Core + 0xB, 0, EDX, 31:0, x2apic_id, x2APIC ID the current logical processor + + +# Leaf 0DH +# Processor Extended State + + 0xD, 0, EAX, 0, x87, X87 state + 0xD, 0, EAX, 1, sse, SSE state + 0xD, 0, EAX, 2, avx, AVX state + 0xD, 0, EAX, 4:3, mpx, MPX state + 0xD, 0, EAX, 7:5, avx512, AVX-512 state + 0xD, 0, EAX, 9, pkru, PKRU state + + 0xD, 0, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 0, ECX, 31:0, max_sz_xsave, Maximum size (bytes) of the XSAVE/XRSTOR save area + + 0xD, 1, EAX, 0, xsaveopt, XSAVEOPT available + 0xD, 1, EAX, 1, xsavec, XSAVEC and compacted form supported + 0xD, 1, EAX, 2, xgetbv, XGETBV supported + 0xD, 1, EAX, 3, xsaves, XSAVES/XRSTORS and IA32_XSS supported + + 0xD, 1, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 1, ECX, 8, pt, PT state + 0xD, 1, ECX, 11, cet_usr, CET user state + 0xD, 1, ECX, 12, cet_supv, CET supervisor state + 0xD, 1, ECX, 13, hdc, HDC state + 0xD, 1, ECX, 16, hwp, HWP state + +# Leaf 0FH +# Intel RDT Monitoring + + 0xF, 0, EBX, 31:0, rmid_range, Maximum range (zero-based) of RMID within this physical processor of all types + 0xF, 0, EDX, 1, l3c_rdt_mon, L3 Cache RDT Monitoring supported + + 0xF, 1, ECX, 31:0, rmid_range, Maximum range (zero-based) of RMID of this types + 0xF, 1, EDX, 0, l3c_ocp_mon, L3 Cache occupancy Monitoring supported + 0xF, 1, EDX, 1, l3c_tbw_mon, L3 Cache Total Bandwidth Monitoring supported + 0xF, 1, EDX, 2, l3c_lbw_mon, L3 Cache Local Bandwidth Monitoring supported + +# Leaf 10H +# Intel RDT Allocation + + 0x10, 0, EBX, 1, l3c_rdt_alloc, L3 Cache Allocation supported + 0x10, 0, EBX, 2, l2c_rdt_alloc, L2 Cache Allocation supported + 0x10, 0, EBX, 3, mem_bw_alloc, Memory Bandwidth Allocation supported + + +# Leaf 12H +# SGX Capability +# +# Some detailed SGX features not added yet + + 0x12, 0, EAX, 0, sgx1, L3 Cache Allocation supported + 0x12, 1, EAX, 0, sgx2, L3 Cache Allocation supported + + +# Leaf 14H +# Intel Processor Tracer +# + +# Leaf 15H +# Time Stamp Counter and Nominal Core Crystal Clock Information + + 0x15, 0, EAX, 31:0, tsc_denominator, The denominator of the TSC/”core crystal clock” ratio + 0x15, 0, EBX, 31:0, tsc_numerator, The numerator of the TSC/”core crystal clock” ratio + 0x15, 0, ECX, 31:0, nom_freq, Nominal frequency of the core crystal clock in Hz + +# Leaf 16H +# Processor Frequency Information + + 0x16, 0, EAX, 15:0, cpu_base_freq, Processor Base Frequency in MHz + 0x16, 0, EBX, 15:0, cpu_max_freq, Maximum Frequency in MHz + 0x16, 0, ECX, 15:0, bus_freq, Bus (Reference) Frequency in MHz + +# Leaf 17H +# System-On-Chip Vendor Attribute + + 0x17, 0, EAX, 31:0, max_socid, Maximum input value of supported sub-leaf + 0x17, 0, EBX, 15:0, soc_vid, SOC Vendor ID + 0x17, 0, EBX, 16, std_vid, SOC Vendor ID is assigned via an industry standard scheme + 0x17, 0, ECX, 31:0, soc_pid, SOC Project ID assigned by vendor + 0x17, 0, EDX, 31:0, soc_sid, SOC Stepping ID + +# Leaf 18H +# Deterministic Address Translation Parameters + + +# Leaf 19H +# Key Locker Leaf + + +# Leaf 1AH +# Hybrid Information + + 0x1A, 0, EAX, 31:24, core_type, 20H-Intel_Atom 40H-Intel_Core + + +# Leaf 1FH +# V2 Extended Topology - A preferred superset to leaf 0BH + + +# According to SDM +# 40000000H - 4FFFFFFFH is invalid range + + +# Leaf 80000001H +# Extended Processor Signature and Feature Bits + +0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode +0x80000001, 0, ECX, 5, lzcnt, LZCNT +0x80000001, 0, ECX, 8, prefetchw, PREFETCHW + +0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported +0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available +0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported +0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available +#0x80000001, 0, EDX, 29, 64b, 64b Architecture supported + +# Leaf 80000002H/80000003H/80000004H +# Processor Brand String + +# Leaf 80000005H +# Reserved + +# Leaf 80000006H +# Extended L2 Cache Features + +0x80000006, 0, ECX, 7:0, clsize, Cache Line size in bytes +0x80000006, 0, ECX, 15:12, l2c_assoc, L2 Associativity +0x80000006, 0, ECX, 31:16, csize, Cache size in 1K units + + +# Leaf 80000007H + +0x80000007, 0, EDX, 8, nonstop_tsc, Invariant TSC available + + +# Leaf 80000008H + +0x80000008, 0, EAX, 7:0, phy_adr_bits, Physical Address Bits +0x80000008, 0, EAX, 15:8, lnr_adr_bits, Linear Address Bits +0x80000007, 0, EBX, 9, wbnoinvd, WBNOINVD + +# 0x8000001E +# EAX: Extended APIC ID +0x8000001E, 0, EAX, 31:0, extended_apic_id, Extended APIC ID +# EBX: Core Identifiers +0x8000001E, 0, EBX, 7:0, core_id, Identifies the logical core ID +0x8000001E, 0, EBX, 15:8, threads_per_core, The number of threads per core is threads_per_core + 1 +# ECX: Node Identifiers +0x8000001E, 0, ECX, 7:0, node_id, Node ID +0x8000001E, 0, ECX, 10:8, nodes_per_processor, Nodes per processor { 0: 1 node, else reserved } + +# 8000001F: AMD Secure Encryption +0x8000001F, 0, EAX, 0, sme, Secure Memory Encryption +0x8000001F, 0, EAX, 1, sev, Secure Encrypted Virtualization +0x8000001F, 0, EAX, 2, vmpgflush, VM Page Flush MSR +0x8000001F, 0, EAX, 3, seves, SEV Encrypted State +0x8000001F, 0, EBX, 5:0, c-bit, Page table bit number used to enable memory encryption +0x8000001F, 0, EBX, 11:6, mem_encrypt_physaddr_width, Reduction of physical address space in bits with SME enabled +0x8000001F, 0, ECX, 31:0, num_encrypted_guests, Maximum ASID value that may be used for an SEV-enabled guest +0x8000001F, 0, EDX, 31:0, minimum_sev_asid, Minimum ASID value that must be used for an SEV-enabled, SEV-ES-disabled guest \ No newline at end of file diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c new file mode 100644 index 000000000000..936a3a2aad04 --- /dev/null +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> +#include <getopt.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef unsigned int u32; +typedef unsigned long long u64; + +char *def_csv = "/usr/share/misc/cpuid.csv"; +char *user_csv; + + +/* Cover both single-bit flag and multiple-bits fields */ +struct bits_desc { + /* start and end bits */ + int start, end; + /* 0 or 1 for 1-bit flag */ + int value; + char simp[32]; + char detail[256]; +}; + +/* descriptor info for eax/ebx/ecx/edx */ +struct reg_desc { + /* number of valid entries */ + int nr; + struct bits_desc descs[32]; +}; + +enum { + R_EAX = 0, + R_EBX, + R_ECX, + R_EDX, + NR_REGS +}; + +struct subleaf { + u32 index; + u32 sub; + u32 eax, ebx, ecx, edx; + struct reg_desc info[NR_REGS]; +}; + +/* Represent one leaf (basic or extended) */ +struct cpuid_func { + /* + * Array of subleafs for this func, if there is no subleafs + * then the leafs[0] is the main leaf + */ + struct subleaf *leafs; + int nr; +}; + +struct cpuid_range { + /* array of main leafs */ + struct cpuid_func *funcs; + /* number of valid leafs */ + int nr; + bool is_ext; +}; + +/* + * basic: basic functions range: [0... ] + * ext: extended functions range: [0x80000000... ] + */ +struct cpuid_range *leafs_basic, *leafs_ext; + +static int num_leafs; +static bool is_amd; +static bool show_details; +static bool show_raw; +static bool show_flags_only = true; +static u32 user_index = 0xFFFFFFFF; +static u32 user_sub = 0xFFFFFFFF; +static int flines; + +static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline bool has_subleafs(u32 f) +{ + if (f == 0x7 || f == 0xd) + return true; + + if (is_amd) { + if (f == 0x8000001d) + return true; + return false; + } + + switch (f) { + case 0x4: + case 0xb: + case 0xf: + case 0x10: + case 0x14: + case 0x18: + case 0x1f: + return true; + default: + return false; + } +} + +static void leaf_print_raw(struct subleaf *leaf) +{ + if (has_subleafs(leaf->index)) { + if (leaf->sub == 0) + printf("0x%08x: subleafs:\n", leaf->index); + + printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->sub, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } else { + printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->index, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } +} + +/* Return true is the input eax/ebx/ecx/edx are all zero */ +static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf, + u32 a, u32 b, u32 c, u32 d) +{ + struct cpuid_func *func; + struct subleaf *leaf; + int s = 0; + + if (a == 0 && b == 0 && c == 0 && d == 0) + return true; + + /* + * Cut off vendor-prefix from CPUID function as we're using it as an + * index into ->funcs. + */ + func = &range->funcs[f & 0xffff]; + + if (!func->leafs) { + func->leafs = malloc(sizeof(struct subleaf)); + if (!func->leafs) + perror("malloc func leaf"); + + func->nr = 1; + } else { + s = func->nr; + func->leafs = realloc(func->leafs, (s + 1) * sizeof(*leaf)); + if (!func->leafs) + perror("realloc f->leafs"); + + func->nr++; + } + + leaf = &func->leafs[s]; + + leaf->index = f; + leaf->sub = subleaf; + leaf->eax = a; + leaf->ebx = b; + leaf->ecx = c; + leaf->edx = d; + + return false; +} + +static void raw_dump_range(struct cpuid_range *range) +{ + u32 f; + int i; + + printf("%s Leafs :\n", range->is_ext ? "Extended" : "Basic"); + printf("================\n"); + + for (f = 0; (int)f < range->nr; f++) { + struct cpuid_func *func = &range->funcs[f]; + u32 index = f; + + if (range->is_ext) + index += 0x80000000; + + /* Skip leaf without valid items */ + if (!func->nr) + continue; + + /* First item is the main leaf, followed by all subleafs */ + for (i = 0; i < func->nr; i++) + leaf_print_raw(&func->leafs[i]); + } +} + +#define MAX_SUBLEAF_NUM 32 +struct cpuid_range *setup_cpuid_range(u32 input_eax) +{ + u32 max_func, idx_func; + int subleaf; + struct cpuid_range *range; + u32 eax, ebx, ecx, edx; + u32 f = input_eax; + int max_subleaf; + bool allzero; + + eax = input_eax; + ebx = ecx = edx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + max_func = eax; + idx_func = (max_func & 0xffff) + 1; + + range = malloc(sizeof(struct cpuid_range)); + if (!range) + perror("malloc range"); + + if (input_eax & 0x80000000) + range->is_ext = true; + else + range->is_ext = false; + + range->funcs = malloc(sizeof(struct cpuid_func) * idx_func); + if (!range->funcs) + perror("malloc range->funcs"); + + range->nr = idx_func; + memset(range->funcs, 0, sizeof(struct cpuid_func) * idx_func); + + for (; f <= max_func; f++) { + eax = f; + subleaf = ecx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + + if (!has_subleafs(f)) + continue; + + max_subleaf = MAX_SUBLEAF_NUM; + + /* + * Some can provide the exact number of subleafs, + * others have to be tried (0xf) + */ + if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18) + max_subleaf = (eax & 0xff) + 1; + + if (f == 0xb) + max_subleaf = 2; + + for (subleaf = 1; subleaf < max_subleaf; subleaf++) { + eax = f; + ecx = subleaf; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, + eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + } + + } + + return range; +} + +/* + * The basic row format for cpuid.csv is + * LEAF,SUBLEAF,register_name,bits,short name,long description + * + * like: + * 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + * 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + */ +static int parse_line(char *line) +{ + char *str; + int i; + struct cpuid_range *range; + struct cpuid_func *func; + struct subleaf *leaf; + u32 index; + u32 sub; + char buffer[512]; + char *buf; + /* + * Tokens: + * 1. leaf + * 2. subleaf + * 3. register + * 4. bits + * 5. short name + * 6. long detail + */ + char *tokens[6]; + struct reg_desc *reg; + struct bits_desc *bdesc; + int reg_index; + char *start, *end; + + /* Skip comments and NULL line */ + if (line[0] == '#' || line[0] == '\n') + return 0; + + strncpy(buffer, line, 511); + buffer[511] = 0; + str = buffer; + for (i = 0; i < 5; i++) { + tokens[i] = strtok(str, ","); + if (!tokens[i]) + goto err_exit; + str = NULL; + } + tokens[5] = strtok(str, "\n"); + if (!tokens[5]) + goto err_exit; + + /* index/main-leaf */ + index = strtoull(tokens[0], NULL, 0); + + if (index & 0x80000000) + range = leafs_ext; + else + range = leafs_basic; + + index &= 0x7FFFFFFF; + /* Skip line parsing for non-existing indexes */ + if ((int)index >= range->nr) + return -1; + + func = &range->funcs[index]; + + /* Return if the index has no valid item on this platform */ + if (!func->nr) + return 0; + + /* subleaf */ + sub = strtoul(tokens[1], NULL, 0); + if ((int)sub > func->nr) + return -1; + + leaf = &func->leafs[sub]; + buf = tokens[2]; + + if (strcasestr(buf, "EAX")) + reg_index = R_EAX; + else if (strcasestr(buf, "EBX")) + reg_index = R_EBX; + else if (strcasestr(buf, "ECX")) + reg_index = R_ECX; + else if (strcasestr(buf, "EDX")) + reg_index = R_EDX; + else + goto err_exit; + + reg = &leaf->info[reg_index]; + bdesc = &reg->descs[reg->nr++]; + + /* bit flag or bits field */ + buf = tokens[3]; + + end = strtok(buf, ":"); + bdesc->end = strtoul(end, NULL, 0); + bdesc->start = bdesc->end; + + /* start != NULL means it is bit fields */ + start = strtok(NULL, ":"); + if (start) + bdesc->start = strtoul(start, NULL, 0); + + strcpy(bdesc->simp, tokens[4]); + strcpy(bdesc->detail, tokens[5]); + return 0; + +err_exit: + printf("Warning: wrong line format:\n"); + printf("\tline[%d]: %s\n", flines, line); + return -1; +} + +/* Parse csv file, and construct the array of all leafs and subleafs */ +static void parse_text(void) +{ + FILE *file; + char *filename, *line = NULL; + size_t len = 0; + int ret; + + if (show_raw) + return; + + filename = user_csv ? user_csv : def_csv; + file = fopen(filename, "r"); + if (!file) { + /* Fallback to a csv in the same dir */ + file = fopen("./cpuid.csv", "r"); + } + + if (!file) { + printf("Fail to open '%s'\n", filename); + return; + } + + while (1) { + ret = getline(&line, &len, file); + flines++; + if (ret > 0) + parse_line(line); + + if (feof(file)) + break; + } + + fclose(file); +} + + +/* Decode every eax/ebx/ecx/edx */ +static void decode_bits(u32 value, struct reg_desc *rdesc) +{ + struct bits_desc *bdesc; + int start, end, i; + u32 mask; + + for (i = 0; i < rdesc->nr; i++) { + bdesc = &rdesc->descs[i]; + + start = bdesc->start; + end = bdesc->end; + if (start == end) { + /* single bit flag */ + if (value & (1 << start)) + printf("\t%-20s %s%s\n", + bdesc->simp, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } else { + /* bit fields */ + if (show_flags_only) + continue; + + mask = ((u64)1 << (end - start + 1)) - 1; + printf("\t%-20s\t: 0x%-8x\t%s%s\n", + bdesc->simp, + (value >> start) & mask, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } + } +} + +static void show_leaf(struct subleaf *leaf) +{ + if (!leaf) + return; + + if (show_raw) + leaf_print_raw(leaf); + + decode_bits(leaf->eax, &leaf->info[R_EAX]); + decode_bits(leaf->ebx, &leaf->info[R_EBX]); + decode_bits(leaf->ecx, &leaf->info[R_ECX]); + decode_bits(leaf->edx, &leaf->info[R_EDX]); +} + +static void show_func(struct cpuid_func *func) +{ + int i; + + if (!func) + return; + + for (i = 0; i < func->nr; i++) + show_leaf(&func->leafs[i]); +} + +static void show_range(struct cpuid_range *range) +{ + int i; + + for (i = 0; i < range->nr; i++) + show_func(&range->funcs[i]); +} + +static inline struct cpuid_func *index_to_func(u32 index) +{ + struct cpuid_range *range; + + range = (index & 0x80000000) ? leafs_ext : leafs_basic; + index &= 0x7FFFFFFF; + + if (((index & 0xFFFF) + 1) > (u32)range->nr) { + printf("ERR: invalid input index (0x%x)\n", index); + return NULL; + } + return &range->funcs[index]; +} + +static void show_info(void) +{ + struct cpuid_func *func; + + if (show_raw) { + /* Show all of the raw output of 'cpuid' instr */ + raw_dump_range(leafs_basic); + raw_dump_range(leafs_ext); + return; + } + + if (user_index != 0xFFFFFFFF) { + /* Only show specific leaf/subleaf info */ + func = index_to_func(user_index); + if (!func) + return; + + /* Dump the raw data also */ + show_raw = true; + + if (user_sub != 0xFFFFFFFF) { + if (user_sub + 1 <= (u32)func->nr) { + show_leaf(&func->leafs[user_sub]); + return; + } + + printf("ERR: invalid input subleaf (0x%x)\n", user_sub); + } + + show_func(func); + return; + } + + printf("CPU features:\n=============\n\n"); + show_range(leafs_basic); + show_range(leafs_ext); +} + +static void setup_platform_cpuid(void) +{ + u32 eax, ebx, ecx, edx; + + /* Check vendor */ + eax = ebx = ecx = edx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + + /* "htuA" */ + if (ebx == 0x68747541) + is_amd = true; + + /* Setup leafs for the basic and extended range */ + leafs_basic = setup_cpuid_range(0x0); + leafs_ext = setup_cpuid_range(0x80000000); +} + +static void usage(void) +{ + printf("kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n" + "\t-a|--all Show both bit flags and complex bit fields info\n" + "\t-b|--bitflags Show boolean flags only\n" + "\t-d|--detail Show details of the flag/fields (default)\n" + "\t-f|--flags Specify the cpuid csv file\n" + "\t-h|--help Show usage info\n" + "\t-l|--leaf=index Specify the leaf you want to check\n" + "\t-r|--raw Show raw cpuid data\n" + "\t-s|--subleaf=sub Specify the subleaf you want to check\n" + ); +} + +static struct option opts[] = { + { "all", no_argument, NULL, 'a' }, /* show both bit flags and fields */ + { "bitflags", no_argument, NULL, 'b' }, /* only show bit flags, default on */ + { "detail", no_argument, NULL, 'd' }, /* show detail descriptions */ + { "file", required_argument, NULL, 'f' }, /* use user's cpuid file */ + { "help", no_argument, NULL, 'h'}, /* show usage */ + { "leaf", required_argument, NULL, 'l'}, /* only check a specific leaf */ + { "raw", no_argument, NULL, 'r'}, /* show raw CPUID leaf data */ + { "subleaf", required_argument, NULL, 's'}, /* check a specific subleaf */ + { NULL, 0, NULL, 0 } +}; + +static int parse_options(int argc, char *argv[]) +{ + int c; + + while ((c = getopt_long(argc, argv, "abdf:hl:rs:", + opts, NULL)) != -1) + switch (c) { + case 'a': + show_flags_only = false; + break; + case 'b': + show_flags_only = true; + break; + case 'd': + show_details = true; + break; + case 'f': + user_csv = optarg; + break; + case 'h': + usage(); + exit(1); + break; + case 'l': + /* main leaf */ + user_index = strtoul(optarg, NULL, 0); + break; + case 'r': + show_raw = true; + break; + case 's': + /* subleaf */ + user_sub = strtoul(optarg, NULL, 0); + break; + default: + printf("%s: Invalid option '%c'\n", argv[0], optopt); + return -1; + } + + return 0; +} + +/* + * Do 4 things in turn: + * 1. Parse user options + * 2. Parse and store all the CPUID leaf data supported on this platform + * 2. Parse the csv file, while skipping leafs which are not available + * on this platform + * 3. Print leafs info based on user options + */ +int main(int argc, char *argv[]) +{ + if (parse_options(argc, argv)) + return -1; + + /* Setup the cpuid leafs of current platform */ + setup_platform_cpuid(); + + /* Read and parse the 'cpuid.csv' */ + parse_text(); + + show_info(); + return 0; +} \ No newline at end of file -- 2.30.0

1 0

[PATCH kernel-5.10] Add a kcpuid tool to show raw CPU features
by zhangyue 25 Oct '21

25 Oct '21

From: Feng Tang <feng.tang(a)intel.com> mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMMB?from=project-issue CVE: NA ------------------------------------ End users frequently want to know what features their processor supports, independent of what the kernel supports. /proc/cpuinfo is great. It is omnipresent and since it is provided by the kernel it is always as up to date as the kernel. But, it could be ambiguous about processor features which can be disabled by the kernel at boot-time or compile-time. There are some user space tools showing more raw features, but they are not bound with kernel, and go with distros. Many end users are still using old distros with new kernels (upgraded by themselves), and may not upgrade the distros only to get a newer tool. So here arise the need for a new tool, which * shows raw CPU features read from the CPUID instruction * will be easier to update compared to existing userspace tooling (perhaps distributed like perf) * inherits "modern" kernel development process, in contrast to some of the existing userspace CPUID tools which are still being developed without git and distributed in tarballs from non-https sites. * Can produce output consistent with /proc/cpuinfo to make comparison easier. The CPUID leaf definitions are kept in an .csv file which allows for updating only that file to add support for new feature leafs. This is based on prototype code from Borislav Petkov (http://sr71.net/~dave/intel/stupid-cpuid.c) [ bp: - Massage, add #define _GNU_SOURCE to fix implicit declaration of function ‘strcasestr' warning - remove superfluous newlines - fallback to cpuid.csv in the current dir if none found - fix typos - move comments over the lines instead of sideways. ] Originally-from: Borislav Petkov <bp(a)alien8.de> Suggested-by: Dave Hansen <dave.hansen(a)intel.com> Suggested-by: Borislav Petkov <bp(a)alien8.de> Signed-off-by: Feng Tang <feng.tang(a)intel.com> Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- tools/arch/x86/kcpuid/Makefile | 24 ++ tools/arch/x86/kcpuid/cpuid.csv | 400 +++++++++++++++++++ tools/arch/x86/kcpuid/kcpuid.c | 657 ++++++++++++++++++++++++++++++++ 3 files changed, 1081 insertions(+) create mode 100644 tools/arch/x86/kcpuid/Makefile create mode 100644 tools/arch/x86/kcpuid/cpuid.csv create mode 100644 tools/arch/x86/kcpuid/kcpuid.c diff --git a/tools/arch/x86/kcpuid/Makefile b/tools/arch/x86/kcpuid/Makefile new file mode 100644 index 000000000000..a2f1e855092c --- /dev/null +++ b/tools/arch/x86/kcpuid/Makefile @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for x86/kcpuid tool + +kcpuid : kcpuid.c + +CFLAGS = -Wextra + +BINDIR ?= /usr/sbin + +HWDATADIR ?= /usr/share/misc/ + +override CFLAGS += -O2 -Wall -I../../../include + +%: %.c + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +.PHONY : clean +clean : + @rm -f kcpuid + +install : kcpuid + install -d $(DESTDIR)$(BINDIR) + install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid + install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv diff --git a/tools/arch/x86/kcpuid/cpuid.csv b/tools/arch/x86/kcpuid/cpuid.csv new file mode 100644 index 000000000000..e422fad9a98e --- /dev/null +++ b/tools/arch/x86/kcpuid/cpuid.csv @@ -0,0 +1,400 @@ +# The basic row format is: +# LEAF, SUBLEAF, register_name, bits, short_name, long_description + +# Leaf 00H + 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + +# Leaf 01H + 1, 0, EAX, 3:0, stepping, Stepping ID + 1, 0, EAX, 7:4, model, Model + 1, 0, EAX, 11:8, family, Family ID + 1, 0, EAX, 13:12, processor, Processor Type + 1, 0, EAX, 19:16, model_ext, Extended Model ID + 1, 0, EAX, 27:20, family_ext, Extended Family ID + + 1, 0, EBX, 7:0, brand, Brand Index + 1, 0, EBX, 15:8, clflush_size, CLFLUSH line size (value * 8) in bytes + 1, 0, EBX, 23:16, max_cpu_id, Maxim number of addressable logic cpu in this package + 1, 0, EBX, 31:24, apic_id, Initial APIC ID + + 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + 1, 0, ECX, 1, pclmulqdq, PCLMULQDQ instruction supported + 1, 0, ECX, 2, dtes64, DS area uses 64-bit layout + 1, 0, ECX, 3, mwait, MONITOR/MWAIT supported + 1, 0, ECX, 4, ds_cpl, CPL Qualified Debug Store which allows for branch message storage qualified by CPL + 1, 0, ECX, 5, vmx, Virtual Machine Extensions supported + 1, 0, ECX, 6, smx, Safer Mode Extension supported + 1, 0, ECX, 7, eist, Enhanced Intel SpeedStep Technology + 1, 0, ECX, 8, tm2, Thermal Monitor 2 + 1, 0, ECX, 9, ssse3, Supplemental Streaming SIMD Extensions 3 (SSSE3) + 1, 0, ECX, 10, l1_ctx_id, L1 data cache could be set to either adaptive mode or shared mode (check IA32_MISC_ENABLE bit 24 definition) + 1, 0, ECX, 11, sdbg, IA32_DEBUG_INTERFACE MSR for silicon debug supported + 1, 0, ECX, 12, fma, FMA extensions using YMM state supported + 1, 0, ECX, 13, cmpxchg16b, 'CMPXCHG16B - Compare and Exchange Bytes' supported + 1, 0, ECX, 14, xtpr_update, xTPR Update Control supported + 1, 0, ECX, 15, pdcm, Perfmon and Debug Capability present + 1, 0, ECX, 17, pcid, Process-Context Identifiers feature present + 1, 0, ECX, 18, dca, Prefetching data from a memory mapped device supported + 1, 0, ECX, 19, sse4_1, SSE4.1 feature present + 1, 0, ECX, 20, sse4_2, SSE4.2 feature present + 1, 0, ECX, 21, x2apic, x2APIC supported + 1, 0, ECX, 22, movbe, MOVBE instruction supported + 1, 0, ECX, 23, popcnt, POPCNT instruction supported + 1, 0, ECX, 24, tsc_deadline_timer, LAPIC supports one-shot operation using a TSC deadline value + 1, 0, ECX, 25, aesni, AESNI instruction supported + 1, 0, ECX, 26, xsave, XSAVE/XRSTOR processor extended states (XSETBV/XGETBV/XCR0) + 1, 0, ECX, 27, osxsave, OS has set CR4.OSXSAVE bit to enable XSETBV/XGETBV/XCR0 + 1, 0, ECX, 28, avx, AVX instruction supported + 1, 0, ECX, 29, f16c, 16-bit floating-point conversion instruction supported + 1, 0, ECX, 30, rdrand, RDRAND instruction supported + + 1, 0, EDX, 0, fpu, x87 FPU on chip + 1, 0, EDX, 1, vme, Virtual-8086 Mode Enhancement + 1, 0, EDX, 2, de, Debugging Extensions + 1, 0, EDX, 3, pse, Page Size Extensions + 1, 0, EDX, 4, tsc, Time Stamp Counter + 1, 0, EDX, 5, msr, RDMSR and WRMSR Support + 1, 0, EDX, 6, pae, Physical Address Extensions + 1, 0, EDX, 7, mce, Machine Check Exception + 1, 0, EDX, 8, cx8, CMPXCHG8B instr + 1, 0, EDX, 9, apic, APIC on Chip + 1, 0, EDX, 11, sep, SYSENTER and SYSEXIT instrs + 1, 0, EDX, 12, mtrr, Memory Type Range Registers + 1, 0, EDX, 13, pge, Page Global Bit + 1, 0, EDX, 14, mca, Machine Check Architecture + 1, 0, EDX, 15, cmov, Conditional Move Instrs + 1, 0, EDX, 16, pat, Page Attribute Table + 1, 0, EDX, 17, pse36, 36-Bit Page Size Extension + 1, 0, EDX, 18, psn, Processor Serial Number + 1, 0, EDX, 19, clflush, CLFLUSH instr +# 1, 0, EDX, 20, + 1, 0, EDX, 21, ds, Debug Store + 1, 0, EDX, 22, acpi, Thermal Monitor and Software Controlled Clock Facilities + 1, 0, EDX, 23, mmx, Intel MMX Technology + 1, 0, EDX, 24, fxsr, XSAVE and FXRSTOR Instrs + 1, 0, EDX, 25, sse, SSE + 1, 0, EDX, 26, sse2, SSE2 + 1, 0, EDX, 27, ss, Self Snoop + 1, 0, EDX, 28, hit, Max APIC IDs + 1, 0, EDX, 29, tm, Thermal Monitor +# 1, 0, EDX, 30, + 1, 0, EDX, 31, pbe, Pending Break Enable + +# Leaf 02H +# cache and TLB descriptor info + +# Leaf 03H +# Precessor Serial Number, introduced on Pentium III, not valid for +# latest models + +# Leaf 04H +# thread/core and cache topology + 4, 0, EAX, 4:0, cache_type, Cache type like instr/data or unified + 4, 0, EAX, 7:5, cache_level, Cache Level (starts at 1) + 4, 0, EAX, 8, cache_self_init, Cache Self Initialization + 4, 0, EAX, 9, fully_associate, Fully Associative cache +# 4, 0, EAX, 13:10, resvd, resvd + 4, 0, EAX, 25:14, max_logical_id, Max number of addressable IDs for logical processors sharing the cache + 4, 0, EAX, 31:26, max_phy_id, Max number of addressable IDs for processors in phy package + + 4, 0, EBX, 11:0, cache_linesize, Size of a cache line in bytes + 4, 0, EBX, 21:12, cache_partition, Physical Line partitions + 4, 0, EBX, 31:22, cache_ways, Ways of associativity + 4, 0, ECX, 31:0, cache_sets, Number of Sets - 1 + 4, 0, EDX, 0, c_wbinvd, 1 means WBINVD/INVD is not ganranteed to act upon lower level caches of non-originating threads sharing this cache + 4, 0, EDX, 1, c_incl, Whether cache is inclusive of lower cache level + 4, 0, EDX, 2, c_comp_index, Complex Cache Indexing + +# Leaf 05H +# MONITOR/MWAIT + 5, 0, EAX, 15:0, min_mon_size, Smallest monitor line size in bytes + 5, 0, EBX, 15:0, max_mon_size, Largest monitor line size in bytes + 5, 0, ECX, 0, mwait_ext, Enum of Monitor-Mwait extensions supported + 5, 0, ECX, 1, mwait_irq_break, Largest monitor line size in bytes + 5, 0, EDX, 3:0, c0_sub_stats, Number of C0* sub C-states supported using MWAIT + 5, 0, EDX, 7:4, c1_sub_stats, Number of C1* sub C-states supported using MWAIT + 5, 0, EDX, 11:8, c2_sub_stats, Number of C2* sub C-states supported using MWAIT + 5, 0, EDX, 15:12, c3_sub_stats, Number of C3* sub C-states supported using MWAIT + 5, 0, EDX, 19:16, c4_sub_stats, Number of C4* sub C-states supported using MWAIT + 5, 0, EDX, 23:20, c5_sub_stats, Number of C5* sub C-states supported using MWAIT + 5, 0, EDX, 27:24, c6_sub_stats, Number of C6* sub C-states supported using MWAIT + 5, 0, EDX, 31:28, c7_sub_stats, Number of C7* sub C-states supported using MWAIT + +# Leaf 06H +# Thermal & Power Management + + 6, 0, EAX, 0, dig_temp, Digital temperature sensor supported + 6, 0, EAX, 1, turbo, Intel Turbo Boost + 6, 0, EAX, 2, arat, Always running APIC timer +# 6, 0, EAX, 3, resv, Reserved + 6, 0, EAX, 4, pln, Power limit notifications supported + 6, 0, EAX, 5, ecmd, Clock modulation duty cycle extension supported + 6, 0, EAX, 6, ptm, Package thermal management supported + 6, 0, EAX, 7, hwp, HWP base register + 6, 0, EAX, 8, hwp_notify, HWP notification + 6, 0, EAX, 9, hwp_act_window, HWP activity window + 6, 0, EAX, 10, hwp_energy, HWP energy performance preference + 6, 0, EAX, 11, hwp_pkg_req, HWP package level request +# 6, 0, EAX, 12, resv, Reserved + 6, 0, EAX, 13, hdc, HDC base registers supported + 6, 0, EAX, 14, turbo3, Turbo Boost Max 3.0 + 6, 0, EAX, 15, hwp_cap, Highest Performance change supported + 6, 0, EAX, 16, hwp_peci, HWP PECI override is supported + 6, 0, EAX, 17, hwp_flex, Flexible HWP is supported + 6, 0, EAX, 18, hwp_fast, Fast access mode for the IA32_HWP_REQUEST MSR is supported +# 6, 0, EAX, 19, resv, Reserved + 6, 0, EAX, 20, hwp_ignr, Ignoring Idle Logical Processor HWP request is supported + + 6, 0, EBX, 3:0, therm_irq_thresh, Number of Interrupt Thresholds in Digital Thermal Sensor + 6, 0, ECX, 0, aperfmperf, Presence of IA32_MPERF and IA32_APERF + 6, 0, ECX, 3, energ_bias, Performance-energy bias preference supported + +# Leaf 07H +# ECX == 0 +# AVX512 refers to https://en.wikipedia.org/wiki/AVX-512 +# XXX: Do we really need to enumerate each and every AVX512 sub features + + 7, 0, EBX, 0, fsgsbase, RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE supported + 7, 0, EBX, 1, tsc_adjust, TSC_ADJUST MSR supported + 7, 0, EBX, 2, sgx, Software Guard Extensions + 7, 0, EBX, 3, bmi1, BMI1 + 7, 0, EBX, 4, hle, Hardware Lock Elision + 7, 0, EBX, 5, avx2, AVX2 +# 7, 0, EBX, 6, fdp_excp_only, x87 FPU Data Pointer updated only on x87 exceptions + 7, 0, EBX, 7, smep, Supervisor-Mode Execution Prevention + 7, 0, EBX, 8, bmi2, BMI2 + 7, 0, EBX, 9, rep_movsb, Enhanced REP MOVSB/STOSB + 7, 0, EBX, 10, invpcid, INVPCID instruction + 7, 0, EBX, 11, rtm, Restricted Transactional Memory + 7, 0, EBX, 12, rdt_m, Intel RDT Monitoring capability + 7, 0, EBX, 13, depc_fpu_cs_ds, Deprecates FPU CS and FPU DS + 7, 0, EBX, 14, mpx, Memory Protection Extensions + 7, 0, EBX, 15, rdt_a, Intel RDT Allocation capability + 7, 0, EBX, 16, avx512f, AVX512 Foundation instr + 7, 0, EBX, 17, avx512dq, AVX512 Double and Quadword AVX512 instr + 7, 0, EBX, 18, rdseed, RDSEED instr + 7, 0, EBX, 19, adx, ADX instr + 7, 0, EBX, 20, smap, Supervisor Mode Access Prevention + 7, 0, EBX, 21, avx512ifma, AVX512 Integer Fused Multiply Add +# 7, 0, EBX, 22, resvd, resvd + 7, 0, EBX, 23, clflushopt, CLFLUSHOPT instr + 7, 0, EBX, 24, clwb, CLWB instr + 7, 0, EBX, 25, intel_pt, Intel Processor Trace instr + 7, 0, EBX, 26, avx512pf, Prefetch + 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr + 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr + 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr + 7, 0, EBX, 26, avx512bw, AVX512 Byte & Word instr + 7, 0, EBX, 28, avx512vl, AVX512 Vector Length Extentions (VL) + 7, 0, ECX, 0, prefetchwt1, X + 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions + 7, 0, ECX, 2, umip, User-mode Instruction Prevention + + 7, 0, ECX, 3, pku, Protection Keys for User-mode pages + 7, 0, ECX, 4, ospke, CR4 PKE set to enable protection keys +# 7, 0, ECX, 16:5, resvd, resvd + 7, 0, ECX, 21:17, mawau, The value of MAWAU used by the BNDLDX and BNDSTX instructions in 64-bit mode + 7, 0, ECX, 22, rdpid, RDPID and IA32_TSC_AUX +# 7, 0, ECX, 29:23, resvd, resvd + 7, 0, ECX, 30, sgx_lc, SGX Launch Configuration +# 7, 0, ECX, 31, resvd, resvd + +# Leaf 08H +# + + +# Leaf 09H +# Direct Cache Access (DCA) information + 9, 0, ECX, 31:0, dca_cap, The value of IA32_PLATFORM_DCA_CAP + +# Leaf 0AH +# Architectural Performance Monitoring +# +# Do we really need to print out the PMU related stuff? +# Does normal user really care about it? +# + 0xA, 0, EAX, 7:0, pmu_ver, Performance Monitoring Unit version + 0xA, 0, EAX, 15:8, pmu_gp_cnt_num, Numer of general-purose PMU counters per logical CPU + 0xA, 0, EAX, 23:16, pmu_cnt_bits, Bit wideth of PMU counter + 0xA, 0, EAX, 31:24, pmu_ebx_bits, Length of EBX bit vector to enumerate PMU events + + 0xA, 0, EBX, 0, pmu_no_core_cycle_evt, Core cycle event not available + 0xA, 0, EBX, 1, pmu_no_instr_ret_evt, Instruction retired event not available + 0xA, 0, EBX, 2, pmu_no_ref_cycle_evt, Reference cycles event not available + 0xA, 0, EBX, 3, pmu_no_llc_ref_evt, Last-level cache reference event not available + 0xA, 0, EBX, 4, pmu_no_llc_mis_evt, Last-level cache misses event not available + 0xA, 0, EBX, 5, pmu_no_br_instr_ret_evt, Branch instruction retired event not available + 0xA, 0, EBX, 6, pmu_no_br_mispredict_evt, Branch mispredict retired event not available + + 0xA, 0, ECX, 4:0, pmu_fixed_cnt_num, Performance Monitoring Unit version + 0xA, 0, ECX, 12:5, pmu_fixed_cnt_bits, Numer of PMU counters per logical CPU + +# Leaf 0BH +# Extended Topology Enumeration Leaf +# + + 0xB, 0, EAX, 4:0, id_shift, Number of bits to shift right on x2APIC ID to get a unique topology ID of the next level type + 0xB, 0, EBX, 15:0, cpu_nr, Number of logical processors at this level type + 0xB, 0, ECX, 15:8, lvl_type, 0-Invalid 1-SMT 2-Core + 0xB, 0, EDX, 31:0, x2apic_id, x2APIC ID the current logical processor + + +# Leaf 0DH +# Processor Extended State + + 0xD, 0, EAX, 0, x87, X87 state + 0xD, 0, EAX, 1, sse, SSE state + 0xD, 0, EAX, 2, avx, AVX state + 0xD, 0, EAX, 4:3, mpx, MPX state + 0xD, 0, EAX, 7:5, avx512, AVX-512 state + 0xD, 0, EAX, 9, pkru, PKRU state + + 0xD, 0, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 0, ECX, 31:0, max_sz_xsave, Maximum size (bytes) of the XSAVE/XRSTOR save area + + 0xD, 1, EAX, 0, xsaveopt, XSAVEOPT available + 0xD, 1, EAX, 1, xsavec, XSAVEC and compacted form supported + 0xD, 1, EAX, 2, xgetbv, XGETBV supported + 0xD, 1, EAX, 3, xsaves, XSAVES/XRSTORS and IA32_XSS supported + + 0xD, 1, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 1, ECX, 8, pt, PT state + 0xD, 1, ECX, 11, cet_usr, CET user state + 0xD, 1, ECX, 12, cet_supv, CET supervisor state + 0xD, 1, ECX, 13, hdc, HDC state + 0xD, 1, ECX, 16, hwp, HWP state + +# Leaf 0FH +# Intel RDT Monitoring + + 0xF, 0, EBX, 31:0, rmid_range, Maximum range (zero-based) of RMID within this physical processor of all types + 0xF, 0, EDX, 1, l3c_rdt_mon, L3 Cache RDT Monitoring supported + + 0xF, 1, ECX, 31:0, rmid_range, Maximum range (zero-based) of RMID of this types + 0xF, 1, EDX, 0, l3c_ocp_mon, L3 Cache occupancy Monitoring supported + 0xF, 1, EDX, 1, l3c_tbw_mon, L3 Cache Total Bandwidth Monitoring supported + 0xF, 1, EDX, 2, l3c_lbw_mon, L3 Cache Local Bandwidth Monitoring supported + +# Leaf 10H +# Intel RDT Allocation + + 0x10, 0, EBX, 1, l3c_rdt_alloc, L3 Cache Allocation supported + 0x10, 0, EBX, 2, l2c_rdt_alloc, L2 Cache Allocation supported + 0x10, 0, EBX, 3, mem_bw_alloc, Memory Bandwidth Allocation supported + + +# Leaf 12H +# SGX Capability +# +# Some detailed SGX features not added yet + + 0x12, 0, EAX, 0, sgx1, L3 Cache Allocation supported + 0x12, 1, EAX, 0, sgx2, L3 Cache Allocation supported + + +# Leaf 14H +# Intel Processor Tracer +# + +# Leaf 15H +# Time Stamp Counter and Nominal Core Crystal Clock Information + + 0x15, 0, EAX, 31:0, tsc_denominator, The denominator of the TSC/”core crystal clock” ratio + 0x15, 0, EBX, 31:0, tsc_numerator, The numerator of the TSC/”core crystal clock” ratio + 0x15, 0, ECX, 31:0, nom_freq, Nominal frequency of the core crystal clock in Hz + +# Leaf 16H +# Processor Frequency Information + + 0x16, 0, EAX, 15:0, cpu_base_freq, Processor Base Frequency in MHz + 0x16, 0, EBX, 15:0, cpu_max_freq, Maximum Frequency in MHz + 0x16, 0, ECX, 15:0, bus_freq, Bus (Reference) Frequency in MHz + +# Leaf 17H +# System-On-Chip Vendor Attribute + + 0x17, 0, EAX, 31:0, max_socid, Maximum input value of supported sub-leaf + 0x17, 0, EBX, 15:0, soc_vid, SOC Vendor ID + 0x17, 0, EBX, 16, std_vid, SOC Vendor ID is assigned via an industry standard scheme + 0x17, 0, ECX, 31:0, soc_pid, SOC Project ID assigned by vendor + 0x17, 0, EDX, 31:0, soc_sid, SOC Stepping ID + +# Leaf 18H +# Deterministic Address Translation Parameters + + +# Leaf 19H +# Key Locker Leaf + + +# Leaf 1AH +# Hybrid Information + + 0x1A, 0, EAX, 31:24, core_type, 20H-Intel_Atom 40H-Intel_Core + + +# Leaf 1FH +# V2 Extended Topology - A preferred superset to leaf 0BH + + +# According to SDM +# 40000000H - 4FFFFFFFH is invalid range + + +# Leaf 80000001H +# Extended Processor Signature and Feature Bits + +0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode +0x80000001, 0, ECX, 5, lzcnt, LZCNT +0x80000001, 0, ECX, 8, prefetchw, PREFETCHW + +0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported +0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available +0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported +0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available +#0x80000001, 0, EDX, 29, 64b, 64b Architecture supported + +# Leaf 80000002H/80000003H/80000004H +# Processor Brand String + +# Leaf 80000005H +# Reserved + +# Leaf 80000006H +# Extended L2 Cache Features + +0x80000006, 0, ECX, 7:0, clsize, Cache Line size in bytes +0x80000006, 0, ECX, 15:12, l2c_assoc, L2 Associativity +0x80000006, 0, ECX, 31:16, csize, Cache size in 1K units + + +# Leaf 80000007H + +0x80000007, 0, EDX, 8, nonstop_tsc, Invariant TSC available + + +# Leaf 80000008H + +0x80000008, 0, EAX, 7:0, phy_adr_bits, Physical Address Bits +0x80000008, 0, EAX, 15:8, lnr_adr_bits, Linear Address Bits +0x80000007, 0, EBX, 9, wbnoinvd, WBNOINVD + +# 0x8000001E +# EAX: Extended APIC ID +0x8000001E, 0, EAX, 31:0, extended_apic_id, Extended APIC ID +# EBX: Core Identifiers +0x8000001E, 0, EBX, 7:0, core_id, Identifies the logical core ID +0x8000001E, 0, EBX, 15:8, threads_per_core, The number of threads per core is threads_per_core + 1 +# ECX: Node Identifiers +0x8000001E, 0, ECX, 7:0, node_id, Node ID +0x8000001E, 0, ECX, 10:8, nodes_per_processor, Nodes per processor { 0: 1 node, else reserved } + +# 8000001F: AMD Secure Encryption +0x8000001F, 0, EAX, 0, sme, Secure Memory Encryption +0x8000001F, 0, EAX, 1, sev, Secure Encrypted Virtualization +0x8000001F, 0, EAX, 2, vmpgflush, VM Page Flush MSR +0x8000001F, 0, EAX, 3, seves, SEV Encrypted State +0x8000001F, 0, EBX, 5:0, c-bit, Page table bit number used to enable memory encryption +0x8000001F, 0, EBX, 11:6, mem_encrypt_physaddr_width, Reduction of physical address space in bits with SME enabled +0x8000001F, 0, ECX, 31:0, num_encrypted_guests, Maximum ASID value that may be used for an SEV-enabled guest +0x8000001F, 0, EDX, 31:0, minimum_sev_asid, Minimum ASID value that must be used for an SEV-enabled, SEV-ES-disabled guest \ No newline at end of file diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c new file mode 100644 index 000000000000..936a3a2aad04 --- /dev/null +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> +#include <getopt.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef unsigned int u32; +typedef unsigned long long u64; + +char *def_csv = "/usr/share/misc/cpuid.csv"; +char *user_csv; + + +/* Cover both single-bit flag and multiple-bits fields */ +struct bits_desc { + /* start and end bits */ + int start, end; + /* 0 or 1 for 1-bit flag */ + int value; + char simp[32]; + char detail[256]; +}; + +/* descriptor info for eax/ebx/ecx/edx */ +struct reg_desc { + /* number of valid entries */ + int nr; + struct bits_desc descs[32]; +}; + +enum { + R_EAX = 0, + R_EBX, + R_ECX, + R_EDX, + NR_REGS +}; + +struct subleaf { + u32 index; + u32 sub; + u32 eax, ebx, ecx, edx; + struct reg_desc info[NR_REGS]; +}; + +/* Represent one leaf (basic or extended) */ +struct cpuid_func { + /* + * Array of subleafs for this func, if there is no subleafs + * then the leafs[0] is the main leaf + */ + struct subleaf *leafs; + int nr; +}; + +struct cpuid_range { + /* array of main leafs */ + struct cpuid_func *funcs; + /* number of valid leafs */ + int nr; + bool is_ext; +}; + +/* + * basic: basic functions range: [0... ] + * ext: extended functions range: [0x80000000... ] + */ +struct cpuid_range *leafs_basic, *leafs_ext; + +static int num_leafs; +static bool is_amd; +static bool show_details; +static bool show_raw; +static bool show_flags_only = true; +static u32 user_index = 0xFFFFFFFF; +static u32 user_sub = 0xFFFFFFFF; +static int flines; + +static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline bool has_subleafs(u32 f) +{ + if (f == 0x7 || f == 0xd) + return true; + + if (is_amd) { + if (f == 0x8000001d) + return true; + return false; + } + + switch (f) { + case 0x4: + case 0xb: + case 0xf: + case 0x10: + case 0x14: + case 0x18: + case 0x1f: + return true; + default: + return false; + } +} + +static void leaf_print_raw(struct subleaf *leaf) +{ + if (has_subleafs(leaf->index)) { + if (leaf->sub == 0) + printf("0x%08x: subleafs:\n", leaf->index); + + printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->sub, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } else { + printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->index, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } +} + +/* Return true is the input eax/ebx/ecx/edx are all zero */ +static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf, + u32 a, u32 b, u32 c, u32 d) +{ + struct cpuid_func *func; + struct subleaf *leaf; + int s = 0; + + if (a == 0 && b == 0 && c == 0 && d == 0) + return true; + + /* + * Cut off vendor-prefix from CPUID function as we're using it as an + * index into ->funcs. + */ + func = &range->funcs[f & 0xffff]; + + if (!func->leafs) { + func->leafs = malloc(sizeof(struct subleaf)); + if (!func->leafs) + perror("malloc func leaf"); + + func->nr = 1; + } else { + s = func->nr; + func->leafs = realloc(func->leafs, (s + 1) * sizeof(*leaf)); + if (!func->leafs) + perror("realloc f->leafs"); + + func->nr++; + } + + leaf = &func->leafs[s]; + + leaf->index = f; + leaf->sub = subleaf; + leaf->eax = a; + leaf->ebx = b; + leaf->ecx = c; + leaf->edx = d; + + return false; +} + +static void raw_dump_range(struct cpuid_range *range) +{ + u32 f; + int i; + + printf("%s Leafs :\n", range->is_ext ? "Extended" : "Basic"); + printf("================\n"); + + for (f = 0; (int)f < range->nr; f++) { + struct cpuid_func *func = &range->funcs[f]; + u32 index = f; + + if (range->is_ext) + index += 0x80000000; + + /* Skip leaf without valid items */ + if (!func->nr) + continue; + + /* First item is the main leaf, followed by all subleafs */ + for (i = 0; i < func->nr; i++) + leaf_print_raw(&func->leafs[i]); + } +} + +#define MAX_SUBLEAF_NUM 32 +struct cpuid_range *setup_cpuid_range(u32 input_eax) +{ + u32 max_func, idx_func; + int subleaf; + struct cpuid_range *range; + u32 eax, ebx, ecx, edx; + u32 f = input_eax; + int max_subleaf; + bool allzero; + + eax = input_eax; + ebx = ecx = edx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + max_func = eax; + idx_func = (max_func & 0xffff) + 1; + + range = malloc(sizeof(struct cpuid_range)); + if (!range) + perror("malloc range"); + + if (input_eax & 0x80000000) + range->is_ext = true; + else + range->is_ext = false; + + range->funcs = malloc(sizeof(struct cpuid_func) * idx_func); + if (!range->funcs) + perror("malloc range->funcs"); + + range->nr = idx_func; + memset(range->funcs, 0, sizeof(struct cpuid_func) * idx_func); + + for (; f <= max_func; f++) { + eax = f; + subleaf = ecx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + + if (!has_subleafs(f)) + continue; + + max_subleaf = MAX_SUBLEAF_NUM; + + /* + * Some can provide the exact number of subleafs, + * others have to be tried (0xf) + */ + if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18) + max_subleaf = (eax & 0xff) + 1; + + if (f == 0xb) + max_subleaf = 2; + + for (subleaf = 1; subleaf < max_subleaf; subleaf++) { + eax = f; + ecx = subleaf; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, + eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + } + + } + + return range; +} + +/* + * The basic row format for cpuid.csv is + * LEAF,SUBLEAF,register_name,bits,short name,long description + * + * like: + * 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + * 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + */ +static int parse_line(char *line) +{ + char *str; + int i; + struct cpuid_range *range; + struct cpuid_func *func; + struct subleaf *leaf; + u32 index; + u32 sub; + char buffer[512]; + char *buf; + /* + * Tokens: + * 1. leaf + * 2. subleaf + * 3. register + * 4. bits + * 5. short name + * 6. long detail + */ + char *tokens[6]; + struct reg_desc *reg; + struct bits_desc *bdesc; + int reg_index; + char *start, *end; + + /* Skip comments and NULL line */ + if (line[0] == '#' || line[0] == '\n') + return 0; + + strncpy(buffer, line, 511); + buffer[511] = 0; + str = buffer; + for (i = 0; i < 5; i++) { + tokens[i] = strtok(str, ","); + if (!tokens[i]) + goto err_exit; + str = NULL; + } + tokens[5] = strtok(str, "\n"); + if (!tokens[5]) + goto err_exit; + + /* index/main-leaf */ + index = strtoull(tokens[0], NULL, 0); + + if (index & 0x80000000) + range = leafs_ext; + else + range = leafs_basic; + + index &= 0x7FFFFFFF; + /* Skip line parsing for non-existing indexes */ + if ((int)index >= range->nr) + return -1; + + func = &range->funcs[index]; + + /* Return if the index has no valid item on this platform */ + if (!func->nr) + return 0; + + /* subleaf */ + sub = strtoul(tokens[1], NULL, 0); + if ((int)sub > func->nr) + return -1; + + leaf = &func->leafs[sub]; + buf = tokens[2]; + + if (strcasestr(buf, "EAX")) + reg_index = R_EAX; + else if (strcasestr(buf, "EBX")) + reg_index = R_EBX; + else if (strcasestr(buf, "ECX")) + reg_index = R_ECX; + else if (strcasestr(buf, "EDX")) + reg_index = R_EDX; + else + goto err_exit; + + reg = &leaf->info[reg_index]; + bdesc = &reg->descs[reg->nr++]; + + /* bit flag or bits field */ + buf = tokens[3]; + + end = strtok(buf, ":"); + bdesc->end = strtoul(end, NULL, 0); + bdesc->start = bdesc->end; + + /* start != NULL means it is bit fields */ + start = strtok(NULL, ":"); + if (start) + bdesc->start = strtoul(start, NULL, 0); + + strcpy(bdesc->simp, tokens[4]); + strcpy(bdesc->detail, tokens[5]); + return 0; + +err_exit: + printf("Warning: wrong line format:\n"); + printf("\tline[%d]: %s\n", flines, line); + return -1; +} + +/* Parse csv file, and construct the array of all leafs and subleafs */ +static void parse_text(void) +{ + FILE *file; + char *filename, *line = NULL; + size_t len = 0; + int ret; + + if (show_raw) + return; + + filename = user_csv ? user_csv : def_csv; + file = fopen(filename, "r"); + if (!file) { + /* Fallback to a csv in the same dir */ + file = fopen("./cpuid.csv", "r"); + } + + if (!file) { + printf("Fail to open '%s'\n", filename); + return; + } + + while (1) { + ret = getline(&line, &len, file); + flines++; + if (ret > 0) + parse_line(line); + + if (feof(file)) + break; + } + + fclose(file); +} + + +/* Decode every eax/ebx/ecx/edx */ +static void decode_bits(u32 value, struct reg_desc *rdesc) +{ + struct bits_desc *bdesc; + int start, end, i; + u32 mask; + + for (i = 0; i < rdesc->nr; i++) { + bdesc = &rdesc->descs[i]; + + start = bdesc->start; + end = bdesc->end; + if (start == end) { + /* single bit flag */ + if (value & (1 << start)) + printf("\t%-20s %s%s\n", + bdesc->simp, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } else { + /* bit fields */ + if (show_flags_only) + continue; + + mask = ((u64)1 << (end - start + 1)) - 1; + printf("\t%-20s\t: 0x%-8x\t%s%s\n", + bdesc->simp, + (value >> start) & mask, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } + } +} + +static void show_leaf(struct subleaf *leaf) +{ + if (!leaf) + return; + + if (show_raw) + leaf_print_raw(leaf); + + decode_bits(leaf->eax, &leaf->info[R_EAX]); + decode_bits(leaf->ebx, &leaf->info[R_EBX]); + decode_bits(leaf->ecx, &leaf->info[R_ECX]); + decode_bits(leaf->edx, &leaf->info[R_EDX]); +} + +static void show_func(struct cpuid_func *func) +{ + int i; + + if (!func) + return; + + for (i = 0; i < func->nr; i++) + show_leaf(&func->leafs[i]); +} + +static void show_range(struct cpuid_range *range) +{ + int i; + + for (i = 0; i < range->nr; i++) + show_func(&range->funcs[i]); +} + +static inline struct cpuid_func *index_to_func(u32 index) +{ + struct cpuid_range *range; + + range = (index & 0x80000000) ? leafs_ext : leafs_basic; + index &= 0x7FFFFFFF; + + if (((index & 0xFFFF) + 1) > (u32)range->nr) { + printf("ERR: invalid input index (0x%x)\n", index); + return NULL; + } + return &range->funcs[index]; +} + +static void show_info(void) +{ + struct cpuid_func *func; + + if (show_raw) { + /* Show all of the raw output of 'cpuid' instr */ + raw_dump_range(leafs_basic); + raw_dump_range(leafs_ext); + return; + } + + if (user_index != 0xFFFFFFFF) { + /* Only show specific leaf/subleaf info */ + func = index_to_func(user_index); + if (!func) + return; + + /* Dump the raw data also */ + show_raw = true; + + if (user_sub != 0xFFFFFFFF) { + if (user_sub + 1 <= (u32)func->nr) { + show_leaf(&func->leafs[user_sub]); + return; + } + + printf("ERR: invalid input subleaf (0x%x)\n", user_sub); + } + + show_func(func); + return; + } + + printf("CPU features:\n=============\n\n"); + show_range(leafs_basic); + show_range(leafs_ext); +} + +static void setup_platform_cpuid(void) +{ + u32 eax, ebx, ecx, edx; + + /* Check vendor */ + eax = ebx = ecx = edx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + + /* "htuA" */ + if (ebx == 0x68747541) + is_amd = true; + + /* Setup leafs for the basic and extended range */ + leafs_basic = setup_cpuid_range(0x0); + leafs_ext = setup_cpuid_range(0x80000000); +} + +static void usage(void) +{ + printf("kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n" + "\t-a|--all Show both bit flags and complex bit fields info\n" + "\t-b|--bitflags Show boolean flags only\n" + "\t-d|--detail Show details of the flag/fields (default)\n" + "\t-f|--flags Specify the cpuid csv file\n" + "\t-h|--help Show usage info\n" + "\t-l|--leaf=index Specify the leaf you want to check\n" + "\t-r|--raw Show raw cpuid data\n" + "\t-s|--subleaf=sub Specify the subleaf you want to check\n" + ); +} + +static struct option opts[] = { + { "all", no_argument, NULL, 'a' }, /* show both bit flags and fields */ + { "bitflags", no_argument, NULL, 'b' }, /* only show bit flags, default on */ + { "detail", no_argument, NULL, 'd' }, /* show detail descriptions */ + { "file", required_argument, NULL, 'f' }, /* use user's cpuid file */ + { "help", no_argument, NULL, 'h'}, /* show usage */ + { "leaf", required_argument, NULL, 'l'}, /* only check a specific leaf */ + { "raw", no_argument, NULL, 'r'}, /* show raw CPUID leaf data */ + { "subleaf", required_argument, NULL, 's'}, /* check a specific subleaf */ + { NULL, 0, NULL, 0 } +}; + +static int parse_options(int argc, char *argv[]) +{ + int c; + + while ((c = getopt_long(argc, argv, "abdf:hl:rs:", + opts, NULL)) != -1) + switch (c) { + case 'a': + show_flags_only = false; + break; + case 'b': + show_flags_only = true; + break; + case 'd': + show_details = true; + break; + case 'f': + user_csv = optarg; + break; + case 'h': + usage(); + exit(1); + break; + case 'l': + /* main leaf */ + user_index = strtoul(optarg, NULL, 0); + break; + case 'r': + show_raw = true; + break; + case 's': + /* subleaf */ + user_sub = strtoul(optarg, NULL, 0); + break; + default: + printf("%s: Invalid option '%c'\n", argv[0], optopt); + return -1; + } + + return 0; +} + +/* + * Do 4 things in turn: + * 1. Parse user options + * 2. Parse and store all the CPUID leaf data supported on this platform + * 2. Parse the csv file, while skipping leafs which are not available + * on this platform + * 3. Print leafs info based on user options + */ +int main(int argc, char *argv[]) +{ + if (parse_options(argc, argv)) + return -1; + + /* Setup the cpuid leafs of current platform */ + setup_platform_cpuid(); + + /* Read and parse the 'cpuid.csv' */ + parse_text(); + + show_info(); + return 0; +} \ No newline at end of file -- 2.30.0

1 0

[PATCH] Add a kcpuid tool to show raw CPU features
by zhangyue 25 Oct '21

25 Oct '21

From: Feng Tang <feng.tang(a)intel.com> mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMMB?from=project-issue CVE: NA ------------------------------------ End users frequently want to know what features their processor supports, independent of what the kernel supports. /proc/cpuinfo is great. It is omnipresent and since it is provided by the kernel it is always as up to date as the kernel. But, it could be ambiguous about processor features which can be disabled by the kernel at boot-time or compile-time. There are some user space tools showing more raw features, but they are not bound with kernel, and go with distros. Many end users are still using old distros with new kernels (upgraded by themselves), and may not upgrade the distros only to get a newer tool. So here arise the need for a new tool, which * shows raw CPU features read from the CPUID instruction * will be easier to update compared to existing userspace tooling (perhaps distributed like perf) * inherits "modern" kernel development process, in contrast to some of the existing userspace CPUID tools which are still being developed without git and distributed in tarballs from non-https sites. * Can produce output consistent with /proc/cpuinfo to make comparison easier. The CPUID leaf definitions are kept in an .csv file which allows for updating only that file to add support for new feature leafs. This is based on prototype code from Borislav Petkov (http://sr71.net/~dave/intel/stupid-cpuid.c) [ bp: - Massage, add #define _GNU_SOURCE to fix implicit declaration of function ‘strcasestr' warning - remove superfluous newlines - fallback to cpuid.csv in the current dir if none found - fix typos - move comments over the lines instead of sideways. ] Originally-from: Borislav Petkov <bp(a)alien8.de> Suggested-by: Dave Hansen <dave.hansen(a)intel.com> Suggested-by: Borislav Petkov <bp(a)alien8.de> Signed-off-by: Feng Tang <feng.tang(a)intel.com> Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- tools/arch/x86/kcpuid/Makefile | 24 ++ tools/arch/x86/kcpuid/cpuid.csv | 400 +++++++++++++++++++ tools/arch/x86/kcpuid/kcpuid.c | 657 ++++++++++++++++++++++++++++++++ 3 files changed, 1081 insertions(+) create mode 100644 tools/arch/x86/kcpuid/Makefile create mode 100644 tools/arch/x86/kcpuid/cpuid.csv create mode 100644 tools/arch/x86/kcpuid/kcpuid.c diff --git a/tools/arch/x86/kcpuid/Makefile b/tools/arch/x86/kcpuid/Makefile new file mode 100644 index 000000000000..a2f1e855092c --- /dev/null +++ b/tools/arch/x86/kcpuid/Makefile @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for x86/kcpuid tool + +kcpuid : kcpuid.c + +CFLAGS = -Wextra + +BINDIR ?= /usr/sbin + +HWDATADIR ?= /usr/share/misc/ + +override CFLAGS += -O2 -Wall -I../../../include + +%: %.c + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +.PHONY : clean +clean : + @rm -f kcpuid + +install : kcpuid + install -d $(DESTDIR)$(BINDIR) + install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid + install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv diff --git a/tools/arch/x86/kcpuid/cpuid.csv b/tools/arch/x86/kcpuid/cpuid.csv new file mode 100644 index 000000000000..e422fad9a98e --- /dev/null +++ b/tools/arch/x86/kcpuid/cpuid.csv @@ -0,0 +1,400 @@ +# The basic row format is: +# LEAF, SUBLEAF, register_name, bits, short_name, long_description + +# Leaf 00H + 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + +# Leaf 01H + 1, 0, EAX, 3:0, stepping, Stepping ID + 1, 0, EAX, 7:4, model, Model + 1, 0, EAX, 11:8, family, Family ID + 1, 0, EAX, 13:12, processor, Processor Type + 1, 0, EAX, 19:16, model_ext, Extended Model ID + 1, 0, EAX, 27:20, family_ext, Extended Family ID + + 1, 0, EBX, 7:0, brand, Brand Index + 1, 0, EBX, 15:8, clflush_size, CLFLUSH line size (value * 8) in bytes + 1, 0, EBX, 23:16, max_cpu_id, Maxim number of addressable logic cpu in this package + 1, 0, EBX, 31:24, apic_id, Initial APIC ID + + 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + 1, 0, ECX, 1, pclmulqdq, PCLMULQDQ instruction supported + 1, 0, ECX, 2, dtes64, DS area uses 64-bit layout + 1, 0, ECX, 3, mwait, MONITOR/MWAIT supported + 1, 0, ECX, 4, ds_cpl, CPL Qualified Debug Store which allows for branch message storage qualified by CPL + 1, 0, ECX, 5, vmx, Virtual Machine Extensions supported + 1, 0, ECX, 6, smx, Safer Mode Extension supported + 1, 0, ECX, 7, eist, Enhanced Intel SpeedStep Technology + 1, 0, ECX, 8, tm2, Thermal Monitor 2 + 1, 0, ECX, 9, ssse3, Supplemental Streaming SIMD Extensions 3 (SSSE3) + 1, 0, ECX, 10, l1_ctx_id, L1 data cache could be set to either adaptive mode or shared mode (check IA32_MISC_ENABLE bit 24 definition) + 1, 0, ECX, 11, sdbg, IA32_DEBUG_INTERFACE MSR for silicon debug supported + 1, 0, ECX, 12, fma, FMA extensions using YMM state supported + 1, 0, ECX, 13, cmpxchg16b, 'CMPXCHG16B - Compare and Exchange Bytes' supported + 1, 0, ECX, 14, xtpr_update, xTPR Update Control supported + 1, 0, ECX, 15, pdcm, Perfmon and Debug Capability present + 1, 0, ECX, 17, pcid, Process-Context Identifiers feature present + 1, 0, ECX, 18, dca, Prefetching data from a memory mapped device supported + 1, 0, ECX, 19, sse4_1, SSE4.1 feature present + 1, 0, ECX, 20, sse4_2, SSE4.2 feature present + 1, 0, ECX, 21, x2apic, x2APIC supported + 1, 0, ECX, 22, movbe, MOVBE instruction supported + 1, 0, ECX, 23, popcnt, POPCNT instruction supported + 1, 0, ECX, 24, tsc_deadline_timer, LAPIC supports one-shot operation using a TSC deadline value + 1, 0, ECX, 25, aesni, AESNI instruction supported + 1, 0, ECX, 26, xsave, XSAVE/XRSTOR processor extended states (XSETBV/XGETBV/XCR0) + 1, 0, ECX, 27, osxsave, OS has set CR4.OSXSAVE bit to enable XSETBV/XGETBV/XCR0 + 1, 0, ECX, 28, avx, AVX instruction supported + 1, 0, ECX, 29, f16c, 16-bit floating-point conversion instruction supported + 1, 0, ECX, 30, rdrand, RDRAND instruction supported + + 1, 0, EDX, 0, fpu, x87 FPU on chip + 1, 0, EDX, 1, vme, Virtual-8086 Mode Enhancement + 1, 0, EDX, 2, de, Debugging Extensions + 1, 0, EDX, 3, pse, Page Size Extensions + 1, 0, EDX, 4, tsc, Time Stamp Counter + 1, 0, EDX, 5, msr, RDMSR and WRMSR Support + 1, 0, EDX, 6, pae, Physical Address Extensions + 1, 0, EDX, 7, mce, Machine Check Exception + 1, 0, EDX, 8, cx8, CMPXCHG8B instr + 1, 0, EDX, 9, apic, APIC on Chip + 1, 0, EDX, 11, sep, SYSENTER and SYSEXIT instrs + 1, 0, EDX, 12, mtrr, Memory Type Range Registers + 1, 0, EDX, 13, pge, Page Global Bit + 1, 0, EDX, 14, mca, Machine Check Architecture + 1, 0, EDX, 15, cmov, Conditional Move Instrs + 1, 0, EDX, 16, pat, Page Attribute Table + 1, 0, EDX, 17, pse36, 36-Bit Page Size Extension + 1, 0, EDX, 18, psn, Processor Serial Number + 1, 0, EDX, 19, clflush, CLFLUSH instr +# 1, 0, EDX, 20, + 1, 0, EDX, 21, ds, Debug Store + 1, 0, EDX, 22, acpi, Thermal Monitor and Software Controlled Clock Facilities + 1, 0, EDX, 23, mmx, Intel MMX Technology + 1, 0, EDX, 24, fxsr, XSAVE and FXRSTOR Instrs + 1, 0, EDX, 25, sse, SSE + 1, 0, EDX, 26, sse2, SSE2 + 1, 0, EDX, 27, ss, Self Snoop + 1, 0, EDX, 28, hit, Max APIC IDs + 1, 0, EDX, 29, tm, Thermal Monitor +# 1, 0, EDX, 30, + 1, 0, EDX, 31, pbe, Pending Break Enable + +# Leaf 02H +# cache and TLB descriptor info + +# Leaf 03H +# Precessor Serial Number, introduced on Pentium III, not valid for +# latest models + +# Leaf 04H +# thread/core and cache topology + 4, 0, EAX, 4:0, cache_type, Cache type like instr/data or unified + 4, 0, EAX, 7:5, cache_level, Cache Level (starts at 1) + 4, 0, EAX, 8, cache_self_init, Cache Self Initialization + 4, 0, EAX, 9, fully_associate, Fully Associative cache +# 4, 0, EAX, 13:10, resvd, resvd + 4, 0, EAX, 25:14, max_logical_id, Max number of addressable IDs for logical processors sharing the cache + 4, 0, EAX, 31:26, max_phy_id, Max number of addressable IDs for processors in phy package + + 4, 0, EBX, 11:0, cache_linesize, Size of a cache line in bytes + 4, 0, EBX, 21:12, cache_partition, Physical Line partitions + 4, 0, EBX, 31:22, cache_ways, Ways of associativity + 4, 0, ECX, 31:0, cache_sets, Number of Sets - 1 + 4, 0, EDX, 0, c_wbinvd, 1 means WBINVD/INVD is not ganranteed to act upon lower level caches of non-originating threads sharing this cache + 4, 0, EDX, 1, c_incl, Whether cache is inclusive of lower cache level + 4, 0, EDX, 2, c_comp_index, Complex Cache Indexing + +# Leaf 05H +# MONITOR/MWAIT + 5, 0, EAX, 15:0, min_mon_size, Smallest monitor line size in bytes + 5, 0, EBX, 15:0, max_mon_size, Largest monitor line size in bytes + 5, 0, ECX, 0, mwait_ext, Enum of Monitor-Mwait extensions supported + 5, 0, ECX, 1, mwait_irq_break, Largest monitor line size in bytes + 5, 0, EDX, 3:0, c0_sub_stats, Number of C0* sub C-states supported using MWAIT + 5, 0, EDX, 7:4, c1_sub_stats, Number of C1* sub C-states supported using MWAIT + 5, 0, EDX, 11:8, c2_sub_stats, Number of C2* sub C-states supported using MWAIT + 5, 0, EDX, 15:12, c3_sub_stats, Number of C3* sub C-states supported using MWAIT + 5, 0, EDX, 19:16, c4_sub_stats, Number of C4* sub C-states supported using MWAIT + 5, 0, EDX, 23:20, c5_sub_stats, Number of C5* sub C-states supported using MWAIT + 5, 0, EDX, 27:24, c6_sub_stats, Number of C6* sub C-states supported using MWAIT + 5, 0, EDX, 31:28, c7_sub_stats, Number of C7* sub C-states supported using MWAIT + +# Leaf 06H +# Thermal & Power Management + + 6, 0, EAX, 0, dig_temp, Digital temperature sensor supported + 6, 0, EAX, 1, turbo, Intel Turbo Boost + 6, 0, EAX, 2, arat, Always running APIC timer +# 6, 0, EAX, 3, resv, Reserved + 6, 0, EAX, 4, pln, Power limit notifications supported + 6, 0, EAX, 5, ecmd, Clock modulation duty cycle extension supported + 6, 0, EAX, 6, ptm, Package thermal management supported + 6, 0, EAX, 7, hwp, HWP base register + 6, 0, EAX, 8, hwp_notify, HWP notification + 6, 0, EAX, 9, hwp_act_window, HWP activity window + 6, 0, EAX, 10, hwp_energy, HWP energy performance preference + 6, 0, EAX, 11, hwp_pkg_req, HWP package level request +# 6, 0, EAX, 12, resv, Reserved + 6, 0, EAX, 13, hdc, HDC base registers supported + 6, 0, EAX, 14, turbo3, Turbo Boost Max 3.0 + 6, 0, EAX, 15, hwp_cap, Highest Performance change supported + 6, 0, EAX, 16, hwp_peci, HWP PECI override is supported + 6, 0, EAX, 17, hwp_flex, Flexible HWP is supported + 6, 0, EAX, 18, hwp_fast, Fast access mode for the IA32_HWP_REQUEST MSR is supported +# 6, 0, EAX, 19, resv, Reserved + 6, 0, EAX, 20, hwp_ignr, Ignoring Idle Logical Processor HWP request is supported + + 6, 0, EBX, 3:0, therm_irq_thresh, Number of Interrupt Thresholds in Digital Thermal Sensor + 6, 0, ECX, 0, aperfmperf, Presence of IA32_MPERF and IA32_APERF + 6, 0, ECX, 3, energ_bias, Performance-energy bias preference supported + +# Leaf 07H +# ECX == 0 +# AVX512 refers to https://en.wikipedia.org/wiki/AVX-512 +# XXX: Do we really need to enumerate each and every AVX512 sub features + + 7, 0, EBX, 0, fsgsbase, RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE supported + 7, 0, EBX, 1, tsc_adjust, TSC_ADJUST MSR supported + 7, 0, EBX, 2, sgx, Software Guard Extensions + 7, 0, EBX, 3, bmi1, BMI1 + 7, 0, EBX, 4, hle, Hardware Lock Elision + 7, 0, EBX, 5, avx2, AVX2 +# 7, 0, EBX, 6, fdp_excp_only, x87 FPU Data Pointer updated only on x87 exceptions + 7, 0, EBX, 7, smep, Supervisor-Mode Execution Prevention + 7, 0, EBX, 8, bmi2, BMI2 + 7, 0, EBX, 9, rep_movsb, Enhanced REP MOVSB/STOSB + 7, 0, EBX, 10, invpcid, INVPCID instruction + 7, 0, EBX, 11, rtm, Restricted Transactional Memory + 7, 0, EBX, 12, rdt_m, Intel RDT Monitoring capability + 7, 0, EBX, 13, depc_fpu_cs_ds, Deprecates FPU CS and FPU DS + 7, 0, EBX, 14, mpx, Memory Protection Extensions + 7, 0, EBX, 15, rdt_a, Intel RDT Allocation capability + 7, 0, EBX, 16, avx512f, AVX512 Foundation instr + 7, 0, EBX, 17, avx512dq, AVX512 Double and Quadword AVX512 instr + 7, 0, EBX, 18, rdseed, RDSEED instr + 7, 0, EBX, 19, adx, ADX instr + 7, 0, EBX, 20, smap, Supervisor Mode Access Prevention + 7, 0, EBX, 21, avx512ifma, AVX512 Integer Fused Multiply Add +# 7, 0, EBX, 22, resvd, resvd + 7, 0, EBX, 23, clflushopt, CLFLUSHOPT instr + 7, 0, EBX, 24, clwb, CLWB instr + 7, 0, EBX, 25, intel_pt, Intel Processor Trace instr + 7, 0, EBX, 26, avx512pf, Prefetch + 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr + 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr + 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr + 7, 0, EBX, 26, avx512bw, AVX512 Byte & Word instr + 7, 0, EBX, 28, avx512vl, AVX512 Vector Length Extentions (VL) + 7, 0, ECX, 0, prefetchwt1, X + 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions + 7, 0, ECX, 2, umip, User-mode Instruction Prevention + + 7, 0, ECX, 3, pku, Protection Keys for User-mode pages + 7, 0, ECX, 4, ospke, CR4 PKE set to enable protection keys +# 7, 0, ECX, 16:5, resvd, resvd + 7, 0, ECX, 21:17, mawau, The value of MAWAU used by the BNDLDX and BNDSTX instructions in 64-bit mode + 7, 0, ECX, 22, rdpid, RDPID and IA32_TSC_AUX +# 7, 0, ECX, 29:23, resvd, resvd + 7, 0, ECX, 30, sgx_lc, SGX Launch Configuration +# 7, 0, ECX, 31, resvd, resvd + +# Leaf 08H +# + + +# Leaf 09H +# Direct Cache Access (DCA) information + 9, 0, ECX, 31:0, dca_cap, The value of IA32_PLATFORM_DCA_CAP + +# Leaf 0AH +# Architectural Performance Monitoring +# +# Do we really need to print out the PMU related stuff? +# Does normal user really care about it? +# + 0xA, 0, EAX, 7:0, pmu_ver, Performance Monitoring Unit version + 0xA, 0, EAX, 15:8, pmu_gp_cnt_num, Numer of general-purose PMU counters per logical CPU + 0xA, 0, EAX, 23:16, pmu_cnt_bits, Bit wideth of PMU counter + 0xA, 0, EAX, 31:24, pmu_ebx_bits, Length of EBX bit vector to enumerate PMU events + + 0xA, 0, EBX, 0, pmu_no_core_cycle_evt, Core cycle event not available + 0xA, 0, EBX, 1, pmu_no_instr_ret_evt, Instruction retired event not available + 0xA, 0, EBX, 2, pmu_no_ref_cycle_evt, Reference cycles event not available + 0xA, 0, EBX, 3, pmu_no_llc_ref_evt, Last-level cache reference event not available + 0xA, 0, EBX, 4, pmu_no_llc_mis_evt, Last-level cache misses event not available + 0xA, 0, EBX, 5, pmu_no_br_instr_ret_evt, Branch instruction retired event not available + 0xA, 0, EBX, 6, pmu_no_br_mispredict_evt, Branch mispredict retired event not available + + 0xA, 0, ECX, 4:0, pmu_fixed_cnt_num, Performance Monitoring Unit version + 0xA, 0, ECX, 12:5, pmu_fixed_cnt_bits, Numer of PMU counters per logical CPU + +# Leaf 0BH +# Extended Topology Enumeration Leaf +# + + 0xB, 0, EAX, 4:0, id_shift, Number of bits to shift right on x2APIC ID to get a unique topology ID of the next level type + 0xB, 0, EBX, 15:0, cpu_nr, Number of logical processors at this level type + 0xB, 0, ECX, 15:8, lvl_type, 0-Invalid 1-SMT 2-Core + 0xB, 0, EDX, 31:0, x2apic_id, x2APIC ID the current logical processor + + +# Leaf 0DH +# Processor Extended State + + 0xD, 0, EAX, 0, x87, X87 state + 0xD, 0, EAX, 1, sse, SSE state + 0xD, 0, EAX, 2, avx, AVX state + 0xD, 0, EAX, 4:3, mpx, MPX state + 0xD, 0, EAX, 7:5, avx512, AVX-512 state + 0xD, 0, EAX, 9, pkru, PKRU state + + 0xD, 0, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 0, ECX, 31:0, max_sz_xsave, Maximum size (bytes) of the XSAVE/XRSTOR save area + + 0xD, 1, EAX, 0, xsaveopt, XSAVEOPT available + 0xD, 1, EAX, 1, xsavec, XSAVEC and compacted form supported + 0xD, 1, EAX, 2, xgetbv, XGETBV supported + 0xD, 1, EAX, 3, xsaves, XSAVES/XRSTORS and IA32_XSS supported + + 0xD, 1, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 1, ECX, 8, pt, PT state + 0xD, 1, ECX, 11, cet_usr, CET user state + 0xD, 1, ECX, 12, cet_supv, CET supervisor state + 0xD, 1, ECX, 13, hdc, HDC state + 0xD, 1, ECX, 16, hwp, HWP state + +# Leaf 0FH +# Intel RDT Monitoring + + 0xF, 0, EBX, 31:0, rmid_range, Maximum range (zero-based) of RMID within this physical processor of all types + 0xF, 0, EDX, 1, l3c_rdt_mon, L3 Cache RDT Monitoring supported + + 0xF, 1, ECX, 31:0, rmid_range, Maximum range (zero-based) of RMID of this types + 0xF, 1, EDX, 0, l3c_ocp_mon, L3 Cache occupancy Monitoring supported + 0xF, 1, EDX, 1, l3c_tbw_mon, L3 Cache Total Bandwidth Monitoring supported + 0xF, 1, EDX, 2, l3c_lbw_mon, L3 Cache Local Bandwidth Monitoring supported + +# Leaf 10H +# Intel RDT Allocation + + 0x10, 0, EBX, 1, l3c_rdt_alloc, L3 Cache Allocation supported + 0x10, 0, EBX, 2, l2c_rdt_alloc, L2 Cache Allocation supported + 0x10, 0, EBX, 3, mem_bw_alloc, Memory Bandwidth Allocation supported + + +# Leaf 12H +# SGX Capability +# +# Some detailed SGX features not added yet + + 0x12, 0, EAX, 0, sgx1, L3 Cache Allocation supported + 0x12, 1, EAX, 0, sgx2, L3 Cache Allocation supported + + +# Leaf 14H +# Intel Processor Tracer +# + +# Leaf 15H +# Time Stamp Counter and Nominal Core Crystal Clock Information + + 0x15, 0, EAX, 31:0, tsc_denominator, The denominator of the TSC/”core crystal clock” ratio + 0x15, 0, EBX, 31:0, tsc_numerator, The numerator of the TSC/”core crystal clock” ratio + 0x15, 0, ECX, 31:0, nom_freq, Nominal frequency of the core crystal clock in Hz + +# Leaf 16H +# Processor Frequency Information + + 0x16, 0, EAX, 15:0, cpu_base_freq, Processor Base Frequency in MHz + 0x16, 0, EBX, 15:0, cpu_max_freq, Maximum Frequency in MHz + 0x16, 0, ECX, 15:0, bus_freq, Bus (Reference) Frequency in MHz + +# Leaf 17H +# System-On-Chip Vendor Attribute + + 0x17, 0, EAX, 31:0, max_socid, Maximum input value of supported sub-leaf + 0x17, 0, EBX, 15:0, soc_vid, SOC Vendor ID + 0x17, 0, EBX, 16, std_vid, SOC Vendor ID is assigned via an industry standard scheme + 0x17, 0, ECX, 31:0, soc_pid, SOC Project ID assigned by vendor + 0x17, 0, EDX, 31:0, soc_sid, SOC Stepping ID + +# Leaf 18H +# Deterministic Address Translation Parameters + + +# Leaf 19H +# Key Locker Leaf + + +# Leaf 1AH +# Hybrid Information + + 0x1A, 0, EAX, 31:24, core_type, 20H-Intel_Atom 40H-Intel_Core + + +# Leaf 1FH +# V2 Extended Topology - A preferred superset to leaf 0BH + + +# According to SDM +# 40000000H - 4FFFFFFFH is invalid range + + +# Leaf 80000001H +# Extended Processor Signature and Feature Bits + +0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode +0x80000001, 0, ECX, 5, lzcnt, LZCNT +0x80000001, 0, ECX, 8, prefetchw, PREFETCHW + +0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported +0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available +0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported +0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available +#0x80000001, 0, EDX, 29, 64b, 64b Architecture supported + +# Leaf 80000002H/80000003H/80000004H +# Processor Brand String + +# Leaf 80000005H +# Reserved + +# Leaf 80000006H +# Extended L2 Cache Features + +0x80000006, 0, ECX, 7:0, clsize, Cache Line size in bytes +0x80000006, 0, ECX, 15:12, l2c_assoc, L2 Associativity +0x80000006, 0, ECX, 31:16, csize, Cache size in 1K units + + +# Leaf 80000007H + +0x80000007, 0, EDX, 8, nonstop_tsc, Invariant TSC available + + +# Leaf 80000008H + +0x80000008, 0, EAX, 7:0, phy_adr_bits, Physical Address Bits +0x80000008, 0, EAX, 15:8, lnr_adr_bits, Linear Address Bits +0x80000007, 0, EBX, 9, wbnoinvd, WBNOINVD + +# 0x8000001E +# EAX: Extended APIC ID +0x8000001E, 0, EAX, 31:0, extended_apic_id, Extended APIC ID +# EBX: Core Identifiers +0x8000001E, 0, EBX, 7:0, core_id, Identifies the logical core ID +0x8000001E, 0, EBX, 15:8, threads_per_core, The number of threads per core is threads_per_core + 1 +# ECX: Node Identifiers +0x8000001E, 0, ECX, 7:0, node_id, Node ID +0x8000001E, 0, ECX, 10:8, nodes_per_processor, Nodes per processor { 0: 1 node, else reserved } + +# 8000001F: AMD Secure Encryption +0x8000001F, 0, EAX, 0, sme, Secure Memory Encryption +0x8000001F, 0, EAX, 1, sev, Secure Encrypted Virtualization +0x8000001F, 0, EAX, 2, vmpgflush, VM Page Flush MSR +0x8000001F, 0, EAX, 3, seves, SEV Encrypted State +0x8000001F, 0, EBX, 5:0, c-bit, Page table bit number used to enable memory encryption +0x8000001F, 0, EBX, 11:6, mem_encrypt_physaddr_width, Reduction of physical address space in bits with SME enabled +0x8000001F, 0, ECX, 31:0, num_encrypted_guests, Maximum ASID value that may be used for an SEV-enabled guest +0x8000001F, 0, EDX, 31:0, minimum_sev_asid, Minimum ASID value that must be used for an SEV-enabled, SEV-ES-disabled guest \ No newline at end of file diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c new file mode 100644 index 000000000000..936a3a2aad04 --- /dev/null +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> +#include <getopt.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef unsigned int u32; +typedef unsigned long long u64; + +char *def_csv = "/usr/share/misc/cpuid.csv"; +char *user_csv; + + +/* Cover both single-bit flag and multiple-bits fields */ +struct bits_desc { + /* start and end bits */ + int start, end; + /* 0 or 1 for 1-bit flag */ + int value; + char simp[32]; + char detail[256]; +}; + +/* descriptor info for eax/ebx/ecx/edx */ +struct reg_desc { + /* number of valid entries */ + int nr; + struct bits_desc descs[32]; +}; + +enum { + R_EAX = 0, + R_EBX, + R_ECX, + R_EDX, + NR_REGS +}; + +struct subleaf { + u32 index; + u32 sub; + u32 eax, ebx, ecx, edx; + struct reg_desc info[NR_REGS]; +}; + +/* Represent one leaf (basic or extended) */ +struct cpuid_func { + /* + * Array of subleafs for this func, if there is no subleafs + * then the leafs[0] is the main leaf + */ + struct subleaf *leafs; + int nr; +}; + +struct cpuid_range { + /* array of main leafs */ + struct cpuid_func *funcs; + /* number of valid leafs */ + int nr; + bool is_ext; +}; + +/* + * basic: basic functions range: [0... ] + * ext: extended functions range: [0x80000000... ] + */ +struct cpuid_range *leafs_basic, *leafs_ext; + +static int num_leafs; +static bool is_amd; +static bool show_details; +static bool show_raw; +static bool show_flags_only = true; +static u32 user_index = 0xFFFFFFFF; +static u32 user_sub = 0xFFFFFFFF; +static int flines; + +static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline bool has_subleafs(u32 f) +{ + if (f == 0x7 || f == 0xd) + return true; + + if (is_amd) { + if (f == 0x8000001d) + return true; + return false; + } + + switch (f) { + case 0x4: + case 0xb: + case 0xf: + case 0x10: + case 0x14: + case 0x18: + case 0x1f: + return true; + default: + return false; + } +} + +static void leaf_print_raw(struct subleaf *leaf) +{ + if (has_subleafs(leaf->index)) { + if (leaf->sub == 0) + printf("0x%08x: subleafs:\n", leaf->index); + + printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->sub, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } else { + printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->index, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } +} + +/* Return true is the input eax/ebx/ecx/edx are all zero */ +static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf, + u32 a, u32 b, u32 c, u32 d) +{ + struct cpuid_func *func; + struct subleaf *leaf; + int s = 0; + + if (a == 0 && b == 0 && c == 0 && d == 0) + return true; + + /* + * Cut off vendor-prefix from CPUID function as we're using it as an + * index into ->funcs. + */ + func = &range->funcs[f & 0xffff]; + + if (!func->leafs) { + func->leafs = malloc(sizeof(struct subleaf)); + if (!func->leafs) + perror("malloc func leaf"); + + func->nr = 1; + } else { + s = func->nr; + func->leafs = realloc(func->leafs, (s + 1) * sizeof(*leaf)); + if (!func->leafs) + perror("realloc f->leafs"); + + func->nr++; + } + + leaf = &func->leafs[s]; + + leaf->index = f; + leaf->sub = subleaf; + leaf->eax = a; + leaf->ebx = b; + leaf->ecx = c; + leaf->edx = d; + + return false; +} + +static void raw_dump_range(struct cpuid_range *range) +{ + u32 f; + int i; + + printf("%s Leafs :\n", range->is_ext ? "Extended" : "Basic"); + printf("================\n"); + + for (f = 0; (int)f < range->nr; f++) { + struct cpuid_func *func = &range->funcs[f]; + u32 index = f; + + if (range->is_ext) + index += 0x80000000; + + /* Skip leaf without valid items */ + if (!func->nr) + continue; + + /* First item is the main leaf, followed by all subleafs */ + for (i = 0; i < func->nr; i++) + leaf_print_raw(&func->leafs[i]); + } +} + +#define MAX_SUBLEAF_NUM 32 +struct cpuid_range *setup_cpuid_range(u32 input_eax) +{ + u32 max_func, idx_func; + int subleaf; + struct cpuid_range *range; + u32 eax, ebx, ecx, edx; + u32 f = input_eax; + int max_subleaf; + bool allzero; + + eax = input_eax; + ebx = ecx = edx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + max_func = eax; + idx_func = (max_func & 0xffff) + 1; + + range = malloc(sizeof(struct cpuid_range)); + if (!range) + perror("malloc range"); + + if (input_eax & 0x80000000) + range->is_ext = true; + else + range->is_ext = false; + + range->funcs = malloc(sizeof(struct cpuid_func) * idx_func); + if (!range->funcs) + perror("malloc range->funcs"); + + range->nr = idx_func; + memset(range->funcs, 0, sizeof(struct cpuid_func) * idx_func); + + for (; f <= max_func; f++) { + eax = f; + subleaf = ecx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + + if (!has_subleafs(f)) + continue; + + max_subleaf = MAX_SUBLEAF_NUM; + + /* + * Some can provide the exact number of subleafs, + * others have to be tried (0xf) + */ + if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18) + max_subleaf = (eax & 0xff) + 1; + + if (f == 0xb) + max_subleaf = 2; + + for (subleaf = 1; subleaf < max_subleaf; subleaf++) { + eax = f; + ecx = subleaf; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, + eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + } + + } + + return range; +} + +/* + * The basic row format for cpuid.csv is + * LEAF,SUBLEAF,register_name,bits,short name,long description + * + * like: + * 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + * 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + */ +static int parse_line(char *line) +{ + char *str; + int i; + struct cpuid_range *range; + struct cpuid_func *func; + struct subleaf *leaf; + u32 index; + u32 sub; + char buffer[512]; + char *buf; + /* + * Tokens: + * 1. leaf + * 2. subleaf + * 3. register + * 4. bits + * 5. short name + * 6. long detail + */ + char *tokens[6]; + struct reg_desc *reg; + struct bits_desc *bdesc; + int reg_index; + char *start, *end; + + /* Skip comments and NULL line */ + if (line[0] == '#' || line[0] == '\n') + return 0; + + strncpy(buffer, line, 511); + buffer[511] = 0; + str = buffer; + for (i = 0; i < 5; i++) { + tokens[i] = strtok(str, ","); + if (!tokens[i]) + goto err_exit; + str = NULL; + } + tokens[5] = strtok(str, "\n"); + if (!tokens[5]) + goto err_exit; + + /* index/main-leaf */ + index = strtoull(tokens[0], NULL, 0); + + if (index & 0x80000000) + range = leafs_ext; + else + range = leafs_basic; + + index &= 0x7FFFFFFF; + /* Skip line parsing for non-existing indexes */ + if ((int)index >= range->nr) + return -1; + + func = &range->funcs[index]; + + /* Return if the index has no valid item on this platform */ + if (!func->nr) + return 0; + + /* subleaf */ + sub = strtoul(tokens[1], NULL, 0); + if ((int)sub > func->nr) + return -1; + + leaf = &func->leafs[sub]; + buf = tokens[2]; + + if (strcasestr(buf, "EAX")) + reg_index = R_EAX; + else if (strcasestr(buf, "EBX")) + reg_index = R_EBX; + else if (strcasestr(buf, "ECX")) + reg_index = R_ECX; + else if (strcasestr(buf, "EDX")) + reg_index = R_EDX; + else + goto err_exit; + + reg = &leaf->info[reg_index]; + bdesc = &reg->descs[reg->nr++]; + + /* bit flag or bits field */ + buf = tokens[3]; + + end = strtok(buf, ":"); + bdesc->end = strtoul(end, NULL, 0); + bdesc->start = bdesc->end; + + /* start != NULL means it is bit fields */ + start = strtok(NULL, ":"); + if (start) + bdesc->start = strtoul(start, NULL, 0); + + strcpy(bdesc->simp, tokens[4]); + strcpy(bdesc->detail, tokens[5]); + return 0; + +err_exit: + printf("Warning: wrong line format:\n"); + printf("\tline[%d]: %s\n", flines, line); + return -1; +} + +/* Parse csv file, and construct the array of all leafs and subleafs */ +static void parse_text(void) +{ + FILE *file; + char *filename, *line = NULL; + size_t len = 0; + int ret; + + if (show_raw) + return; + + filename = user_csv ? user_csv : def_csv; + file = fopen(filename, "r"); + if (!file) { + /* Fallback to a csv in the same dir */ + file = fopen("./cpuid.csv", "r"); + } + + if (!file) { + printf("Fail to open '%s'\n", filename); + return; + } + + while (1) { + ret = getline(&line, &len, file); + flines++; + if (ret > 0) + parse_line(line); + + if (feof(file)) + break; + } + + fclose(file); +} + + +/* Decode every eax/ebx/ecx/edx */ +static void decode_bits(u32 value, struct reg_desc *rdesc) +{ + struct bits_desc *bdesc; + int start, end, i; + u32 mask; + + for (i = 0; i < rdesc->nr; i++) { + bdesc = &rdesc->descs[i]; + + start = bdesc->start; + end = bdesc->end; + if (start == end) { + /* single bit flag */ + if (value & (1 << start)) + printf("\t%-20s %s%s\n", + bdesc->simp, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } else { + /* bit fields */ + if (show_flags_only) + continue; + + mask = ((u64)1 << (end - start + 1)) - 1; + printf("\t%-20s\t: 0x%-8x\t%s%s\n", + bdesc->simp, + (value >> start) & mask, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } + } +} + +static void show_leaf(struct subleaf *leaf) +{ + if (!leaf) + return; + + if (show_raw) + leaf_print_raw(leaf); + + decode_bits(leaf->eax, &leaf->info[R_EAX]); + decode_bits(leaf->ebx, &leaf->info[R_EBX]); + decode_bits(leaf->ecx, &leaf->info[R_ECX]); + decode_bits(leaf->edx, &leaf->info[R_EDX]); +} + +static void show_func(struct cpuid_func *func) +{ + int i; + + if (!func) + return; + + for (i = 0; i < func->nr; i++) + show_leaf(&func->leafs[i]); +} + +static void show_range(struct cpuid_range *range) +{ + int i; + + for (i = 0; i < range->nr; i++) + show_func(&range->funcs[i]); +} + +static inline struct cpuid_func *index_to_func(u32 index) +{ + struct cpuid_range *range; + + range = (index & 0x80000000) ? leafs_ext : leafs_basic; + index &= 0x7FFFFFFF; + + if (((index & 0xFFFF) + 1) > (u32)range->nr) { + printf("ERR: invalid input index (0x%x)\n", index); + return NULL; + } + return &range->funcs[index]; +} + +static void show_info(void) +{ + struct cpuid_func *func; + + if (show_raw) { + /* Show all of the raw output of 'cpuid' instr */ + raw_dump_range(leafs_basic); + raw_dump_range(leafs_ext); + return; + } + + if (user_index != 0xFFFFFFFF) { + /* Only show specific leaf/subleaf info */ + func = index_to_func(user_index); + if (!func) + return; + + /* Dump the raw data also */ + show_raw = true; + + if (user_sub != 0xFFFFFFFF) { + if (user_sub + 1 <= (u32)func->nr) { + show_leaf(&func->leafs[user_sub]); + return; + } + + printf("ERR: invalid input subleaf (0x%x)\n", user_sub); + } + + show_func(func); + return; + } + + printf("CPU features:\n=============\n\n"); + show_range(leafs_basic); + show_range(leafs_ext); +} + +static void setup_platform_cpuid(void) +{ + u32 eax, ebx, ecx, edx; + + /* Check vendor */ + eax = ebx = ecx = edx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + + /* "htuA" */ + if (ebx == 0x68747541) + is_amd = true; + + /* Setup leafs for the basic and extended range */ + leafs_basic = setup_cpuid_range(0x0); + leafs_ext = setup_cpuid_range(0x80000000); +} + +static void usage(void) +{ + printf("kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n" + "\t-a|--all Show both bit flags and complex bit fields info\n" + "\t-b|--bitflags Show boolean flags only\n" + "\t-d|--detail Show details of the flag/fields (default)\n" + "\t-f|--flags Specify the cpuid csv file\n" + "\t-h|--help Show usage info\n" + "\t-l|--leaf=index Specify the leaf you want to check\n" + "\t-r|--raw Show raw cpuid data\n" + "\t-s|--subleaf=sub Specify the subleaf you want to check\n" + ); +} + +static struct option opts[] = { + { "all", no_argument, NULL, 'a' }, /* show both bit flags and fields */ + { "bitflags", no_argument, NULL, 'b' }, /* only show bit flags, default on */ + { "detail", no_argument, NULL, 'd' }, /* show detail descriptions */ + { "file", required_argument, NULL, 'f' }, /* use user's cpuid file */ + { "help", no_argument, NULL, 'h'}, /* show usage */ + { "leaf", required_argument, NULL, 'l'}, /* only check a specific leaf */ + { "raw", no_argument, NULL, 'r'}, /* show raw CPUID leaf data */ + { "subleaf", required_argument, NULL, 's'}, /* check a specific subleaf */ + { NULL, 0, NULL, 0 } +}; + +static int parse_options(int argc, char *argv[]) +{ + int c; + + while ((c = getopt_long(argc, argv, "abdf:hl:rs:", + opts, NULL)) != -1) + switch (c) { + case 'a': + show_flags_only = false; + break; + case 'b': + show_flags_only = true; + break; + case 'd': + show_details = true; + break; + case 'f': + user_csv = optarg; + break; + case 'h': + usage(); + exit(1); + break; + case 'l': + /* main leaf */ + user_index = strtoul(optarg, NULL, 0); + break; + case 'r': + show_raw = true; + break; + case 's': + /* subleaf */ + user_sub = strtoul(optarg, NULL, 0); + break; + default: + printf("%s: Invalid option '%c'\n", argv[0], optopt); + return -1; + } + + return 0; +} + +/* + * Do 4 things in turn: + * 1. Parse user options + * 2. Parse and store all the CPUID leaf data supported on this platform + * 2. Parse the csv file, while skipping leafs which are not available + * on this platform + * 3. Print leafs info based on user options + */ +int main(int argc, char *argv[]) +{ + if (parse_options(argc, argv)) + return -1; + + /* Setup the cpuid leafs of current platform */ + setup_platform_cpuid(); + + /* Read and parse the 'cpuid.csv' */ + parse_text(); + + show_info(); + return 0; +} \ No newline at end of file -- 2.30.0

1 0

[PATCH kernel-4.19 1/3] net: hns3: use ae_dev->ops->reset_event to do reset.
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Yonglong Liu <liuyonglong(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA ---------------------------- IT products want to know whether a reset is happened, so need to use ae_dev->ops->reset_event to notify them. Signed-off-by: Yonglong Liu <liuyonglong(a)huawei.com> Reviewed-by: li yongxin <liyongxin1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 98a1d3d2870a9..8507eb60450fe 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3933,6 +3933,7 @@ static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev, static void hclge_reset_timer(struct timer_list *t) { struct hclge_dev *hdev = from_timer(hdev, t, reset_timer); + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); /* if default_reset_request has no value, it means that this reset * request has already be handled, so just return here @@ -3942,7 +3943,9 @@ static void hclge_reset_timer(struct timer_list *t) dev_info(&hdev->pdev->dev, "triggering reset in reset timer\n"); - hclge_reset_event(hdev->pdev, NULL); + + if (ae_dev->ops->reset_event) + ae_dev->ops->reset_event(hdev->pdev, NULL); } static bool hclge_reset_end(struct hnae3_handle *handle, bool done) -- 2.25.1

1 2

[PATCH kernel-4.19] media: firewire: firedtv-avc: fix a buffer overflow in avc_ca_pmt()
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Dan Carpenter <dan.carpenter(a)oracle.com> mainline inclusion from mainline-v5.16 commit 35d2969ea3c7d32aee78066b1f3cf61a0d935a4e category: bugfix bugzilla: NA CVE: CVE-2021-42739 ------------------------------------------------- The bounds checking in avc_ca_pmt() is not strict enough. It should be checking "read_pos + 4" because it's reading 5 bytes. If the "es_info_length" is non-zero then it reads a 6th byte so there needs to be an additional check for that. I also added checks for the "write_pos". I don't think these are required because "read_pos" and "write_pos" are tied together so checking one ought to be enough. But they make the code easier to understand for me. The check on write_pos is: if (write_pos + 4 >= sizeof(c->operand) - 4) { The first "+ 4" is because we're writing 5 bytes and the last " - 4" is to leave space for the CRC. The other problem is that "length" can be invalid. It comes from "data_length" in fdtv_ca_pmt(). Cc: stable(a)vger.kernel.org Reported-by: Luo Likang <luolikang(a)nsfocus.com> Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> Signed-off-by: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/media/firewire/firedtv-avc.c | 14 +++++++++++--- drivers/media/firewire/firedtv-ci.c | 2 ++ 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/media/firewire/firedtv-avc.c b/drivers/media/firewire/firedtv-avc.c index 3ef5df1648d77..8c31cf90c5907 100644 --- a/drivers/media/firewire/firedtv-avc.c +++ b/drivers/media/firewire/firedtv-avc.c @@ -1169,7 +1169,11 @@ int avc_ca_pmt(struct firedtv *fdtv, char *msg, int length) read_pos += program_info_length; write_pos += program_info_length; } - while (read_pos < length) { + while (read_pos + 4 < length) { + if (write_pos + 4 >= sizeof(c->operand) - 4) { + ret = -EINVAL; + goto out; + } c->operand[write_pos++] = msg[read_pos++]; c->operand[write_pos++] = msg[read_pos++]; c->operand[write_pos++] = msg[read_pos++]; @@ -1181,13 +1185,17 @@ int avc_ca_pmt(struct firedtv *fdtv, char *msg, int length) c->operand[write_pos++] = es_info_length >> 8; c->operand[write_pos++] = es_info_length & 0xff; if (es_info_length > 0) { + if (read_pos >= length) { + ret = -EINVAL; + goto out; + } pmt_cmd_id = msg[read_pos++]; if (pmt_cmd_id != 1 && pmt_cmd_id != 4) dev_err(fdtv->device, "invalid pmt_cmd_id %d at stream level\n", pmt_cmd_id); - if (es_info_length > sizeof(c->operand) - 4 - - write_pos) { + if (es_info_length > sizeof(c->operand) - 4 - write_pos || + es_info_length > length - read_pos) { ret = -EINVAL; goto out; } diff --git a/drivers/media/firewire/firedtv-ci.c b/drivers/media/firewire/firedtv-ci.c index 8dc5a7495abee..14f779812d250 100644 --- a/drivers/media/firewire/firedtv-ci.c +++ b/drivers/media/firewire/firedtv-ci.c @@ -138,6 +138,8 @@ static int fdtv_ca_pmt(struct firedtv *fdtv, void *arg) } else { data_length = msg->msg[3]; } + if (data_length > sizeof(msg->msg) - data_pos) + return -EINVAL; return avc_ca_pmt(fdtv, &msg->msg[data_pos], data_length); } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] GPIO : support ascend gpio driver
by Yang Yingliang 25 Oct '21

25 Oct '21

From: wuhuaye <wuhuaye(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4DLVR CVE: NA ------------------------------------------------- Hi everyone， This patch add some special gpio register configuration. It is necessary to configure some gpio register when gpio-dwapb function is enable in Ascend platform. Signed-off-by: wuhuaye <wuhuaye(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/mm/init.c | 17 ++++++++++ drivers/gpio/gpio-dwapb.c | 66 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 82 insertions(+), 1 deletion(-) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 5449ae2d26bee..55fc6a0206796 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -941,6 +941,12 @@ __setup("keepinitrd", keepinitrd_setup); void ascend_enable_all_features(void) { +#ifdef CONFIG_GPIO_DWAPB + extern bool enable_ascend_gpio_dwapb; + + enable_ascend_gpio_dwapb = true; +#endif + if (IS_ENABLED(CONFIG_ASCEND_DVPP_MMAP)) enable_mmap_dvpp = 1; @@ -974,6 +980,17 @@ static int __init ascend_enable_setup(char *__unused) } early_param("ascend_enable_all", ascend_enable_setup); + +static int __init ascend_mini_enable_setup(char *s) +{ +#ifdef CONFIG_GPIO_DWAPB + extern bool enable_ascend_mini_gpio_dwapb; + + enable_ascend_mini_gpio_dwapb = true; +#endif + return 1; +} +__setup("ascend_mini_enable", ascend_mini_enable_setup); #endif diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 044888fd96a1f..2cdbb4a11075f 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -50,6 +50,9 @@ #define GPIO_EXT_PORTB 0x54 #define GPIO_EXT_PORTC 0x58 #define GPIO_EXT_PORTD 0x5c +#define GPIO_INTCOMB_MASK 0xffc +#define GPIO_INT_MASK_REG 0x3804 +#define MEM_PERI_SUBCTRL_IOBASE 0x1 #define DWAPB_MAX_PORTS 4 #define GPIO_EXT_PORT_STRIDE 0x04 /* register stride 32 bits */ @@ -64,6 +67,8 @@ #define GPIO_INTSTATUS_V2 0x3c #define GPIO_PORTA_EOI_V2 0x40 +bool enable_ascend_mini_gpio_dwapb; +bool enable_ascend_gpio_dwapb; struct dwapb_gpio; #ifdef CONFIG_PM_SLEEP @@ -77,10 +82,11 @@ struct dwapb_context { u32 int_type; u32 int_pol; u32 int_deb; + u32 int_comb_mask; u32 wake_en; }; #endif - +static void __iomem *peri_subctrl_base_addr; struct dwapb_gpio_port { struct gpio_chip gc; bool is_registered; @@ -232,6 +238,11 @@ static void dwapb_irq_enable(struct irq_data *d) val = dwapb_read(gpio, GPIO_INTEN); val |= BIT(d->hwirq); dwapb_write(gpio, GPIO_INTEN, val); + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTMASK); + val &= ~BIT(d->hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + } spin_unlock_irqrestore(&gc->bgpio_lock, flags); } @@ -244,6 +255,11 @@ static void dwapb_irq_disable(struct irq_data *d) u32 val; spin_lock_irqsave(&gc->bgpio_lock, flags); + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTMASK); + val |= BIT(d->hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + } val = dwapb_read(gpio, GPIO_INTEN); val &= ~BIT(d->hwirq); dwapb_write(gpio, GPIO_INTEN, val); @@ -393,6 +409,7 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio, unsigned int hwirq, ngpio = gc->ngpio; struct irq_chip_type *ct; int err, i; + u32 val; gpio->domain = irq_domain_create_linear(fwnode, ngpio, &irq_generic_chip_ops, gpio); @@ -470,6 +487,12 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio, irq_create_mapping(gpio->domain, hwirq); port->gc.to_irq = dwapb_gpio_to_irq; + + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTCOMB_MASK); + val |= BIT(0); + dwapb_write(gpio, GPIO_INTCOMB_MASK, val); + } } static void dwapb_irq_teardown(struct dwapb_gpio *gpio) @@ -478,6 +501,7 @@ static void dwapb_irq_teardown(struct dwapb_gpio *gpio) struct gpio_chip *gc = &port->gc; unsigned int ngpio = gc->ngpio; irq_hw_number_t hwirq; + u32 val; if (!gpio->domain) return; @@ -487,6 +511,12 @@ static void dwapb_irq_teardown(struct dwapb_gpio *gpio) irq_domain_remove(gpio->domain); gpio->domain = NULL; + + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTCOMB_MASK); + val &= ~BIT(0); + dwapb_write(gpio, GPIO_INTCOMB_MASK, val); + } } static int dwapb_gpio_add_port(struct dwapb_gpio *gpio, @@ -660,6 +690,22 @@ static int dwapb_gpio_probe(struct platform_device *pdev) int err; struct device *dev = &pdev->dev; struct dwapb_platform_data *pdata = dev_get_platdata(dev); + struct device_node *np = dev->of_node; + unsigned int value; + + if (enable_ascend_mini_gpio_dwapb && enable_ascend_gpio_dwapb) { + peri_subctrl_base_addr = of_iomap(np, MEM_PERI_SUBCTRL_IOBASE); + if (!peri_subctrl_base_addr) { + dev_err(&pdev->dev, "sysctrl iomap not find!\n"); + } else { + dev_dbg(&pdev->dev, "sysctrl iomap find!\n"); + value = readl(peri_subctrl_base_addr + + GPIO_INT_MASK_REG); + value &= ~1UL; + writel(value, peri_subctrl_base_addr + + GPIO_INT_MASK_REG); + } + } if (!pdata) { pdata = dwapb_gpio_get_pdata(dev); @@ -742,6 +788,10 @@ static int dwapb_gpio_remove(struct platform_device *pdev) reset_control_assert(gpio->rst); clk_disable_unprepare(gpio->clk); + if ((peri_subctrl_base_addr != NULL) && enable_ascend_mini_gpio_dwapb && + enable_ascend_gpio_dwapb) + iounmap(peri_subctrl_base_addr); + return 0; } @@ -778,6 +828,9 @@ static int dwapb_gpio_suspend(struct device *dev) ctx->int_pol = dwapb_read(gpio, GPIO_INT_POLARITY); ctx->int_type = dwapb_read(gpio, GPIO_INTTYPE_LEVEL); ctx->int_deb = dwapb_read(gpio, GPIO_PORTA_DEBOUNCE); + if (enable_ascend_gpio_dwapb) + ctx->int_comb_mask = + dwapb_read(gpio, GPIO_INTCOMB_MASK); /* Mask out interrupts */ dwapb_write(gpio, GPIO_INTMASK, @@ -798,6 +851,7 @@ static int dwapb_gpio_resume(struct device *dev) struct gpio_chip *gc = &gpio->ports[0].gc; unsigned long flags; int i; + unsigned int value; if (!IS_ERR(gpio->clk)) clk_prepare_enable(gpio->clk); @@ -826,6 +880,9 @@ static int dwapb_gpio_resume(struct device *dev) dwapb_write(gpio, GPIO_PORTA_DEBOUNCE, ctx->int_deb); dwapb_write(gpio, GPIO_INTEN, ctx->int_en); dwapb_write(gpio, GPIO_INTMASK, ctx->int_mask); + if (enable_ascend_gpio_dwapb) + dwapb_write(gpio, + GPIO_INTCOMB_MASK, ctx->int_comb_mask); /* Clear out spurious interrupts */ dwapb_write(gpio, GPIO_PORTA_EOI, 0xffffffff); @@ -833,6 +890,13 @@ static int dwapb_gpio_resume(struct device *dev) } spin_unlock_irqrestore(&gc->bgpio_lock, flags); + if ((peri_subctrl_base_addr != NULL) && enable_ascend_mini_gpio_dwapb && + enable_ascend_gpio_dwapb) { + value = readl(peri_subctrl_base_addr + GPIO_INT_MASK_REG); + value &= ~1UL; + writel(value, peri_subctrl_base_addr + GPIO_INT_MASK_REG); + } + return 0; } #endif -- 2.25.1

1 0

[PATCH kernel-4.19] GPIO : support ascend gpio driver
by Yang Yingliang 25 Oct '21

25 Oct '21

From: wuhuaye <wuhuaye(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4DLVR CVE: NA ------------------------------------------------- Hi everyone， This patch add some special gpio register configuration. It is necessary to configure some gpio register when gpio-dwapb function is enable in Ascend platform. Signed-off-by: wuhuaye <wuhuaye(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/mm/init.c | 17 ++++++++++ drivers/gpio/gpio-dwapb.c | 66 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 82 insertions(+), 1 deletion(-) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 2399a257eaf33..8cdf92626c2c6 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -944,6 +944,12 @@ __setup("keepinitrd", keepinitrd_setup); void ascend_enable_all_features(void) { +#ifdef CONFIG_GPIO_DWAPB + extern bool enable_ascend_gpio_dwapb; + + enable_ascend_gpio_dwapb = true; +#endif + if (IS_ENABLED(CONFIG_ASCEND_DVPP_MMAP)) enable_mmap_dvpp = 1; @@ -981,6 +987,17 @@ static int __init ascend_enable_setup(char *__unused) } early_param("ascend_enable_all", ascend_enable_setup); + +static int __init ascend_mini_enable_setup(char *s) +{ +#ifdef CONFIG_GPIO_DWAPB + extern bool enable_ascend_mini_gpio_dwapb; + + enable_ascend_mini_gpio_dwapb = true; +#endif + return 1; +} +__setup("ascend_mini_enable", ascend_mini_enable_setup); #endif diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 2a56efced7988..4c332f0ed8524 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -50,6 +50,9 @@ #define GPIO_EXT_PORTB 0x54 #define GPIO_EXT_PORTC 0x58 #define GPIO_EXT_PORTD 0x5c +#define GPIO_INTCOMB_MASK 0xffc +#define GPIO_INT_MASK_REG 0x3804 +#define MEM_PERI_SUBCTRL_IOBASE 0x1 #define DWAPB_DRIVER_NAME "gpio-dwapb" #define DWAPB_MAX_PORTS 4 @@ -66,6 +69,8 @@ #define GPIO_INTSTATUS_V2 0x3c #define GPIO_PORTA_EOI_V2 0x40 +bool enable_ascend_mini_gpio_dwapb; +bool enable_ascend_gpio_dwapb; struct dwapb_gpio; #ifdef CONFIG_PM_SLEEP @@ -79,10 +84,11 @@ struct dwapb_context { u32 int_type; u32 int_pol; u32 int_deb; + u32 int_comb_mask; u32 wake_en; }; #endif - +static void __iomem *peri_subctrl_base_addr; struct dwapb_gpio_port { struct gpio_chip gc; bool is_registered; @@ -234,6 +240,11 @@ static void dwapb_irq_enable(struct irq_data *d) val = dwapb_read(gpio, GPIO_INTEN); val |= BIT(d->hwirq); dwapb_write(gpio, GPIO_INTEN, val); + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTMASK); + val &= ~BIT(d->hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + } spin_unlock_irqrestore(&gc->bgpio_lock, flags); } @@ -246,6 +257,11 @@ static void dwapb_irq_disable(struct irq_data *d) u32 val; spin_lock_irqsave(&gc->bgpio_lock, flags); + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTMASK); + val |= BIT(d->hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + } val = dwapb_read(gpio, GPIO_INTEN); val &= ~BIT(d->hwirq); dwapb_write(gpio, GPIO_INTEN, val); @@ -395,6 +411,7 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio, unsigned int hwirq, ngpio = gc->ngpio; struct irq_chip_type *ct; int err, i; + u32 val; gpio->domain = irq_domain_create_linear(fwnode, ngpio, &irq_generic_chip_ops, gpio); @@ -472,6 +489,12 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio, irq_create_mapping(gpio->domain, hwirq); port->gc.to_irq = dwapb_gpio_to_irq; + + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTCOMB_MASK); + val |= BIT(0); + dwapb_write(gpio, GPIO_INTCOMB_MASK, val); + } } static void dwapb_irq_teardown(struct dwapb_gpio *gpio) @@ -480,6 +503,7 @@ static void dwapb_irq_teardown(struct dwapb_gpio *gpio) struct gpio_chip *gc = &port->gc; unsigned int ngpio = gc->ngpio; irq_hw_number_t hwirq; + u32 val; if (!gpio->domain) return; @@ -489,6 +513,12 @@ static void dwapb_irq_teardown(struct dwapb_gpio *gpio) irq_domain_remove(gpio->domain); gpio->domain = NULL; + + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTCOMB_MASK); + val &= ~BIT(0); + dwapb_write(gpio, GPIO_INTCOMB_MASK, val); + } } static int dwapb_gpio_add_port(struct dwapb_gpio *gpio, @@ -669,6 +699,22 @@ static int dwapb_gpio_probe(struct platform_device *pdev) int err; struct device *dev = &pdev->dev; struct dwapb_platform_data *pdata = dev_get_platdata(dev); + struct device_node *np = dev->of_node; + unsigned int value; + + if (enable_ascend_mini_gpio_dwapb && enable_ascend_gpio_dwapb) { + peri_subctrl_base_addr = of_iomap(np, MEM_PERI_SUBCTRL_IOBASE); + if (!peri_subctrl_base_addr) { + dev_err(&pdev->dev, "sysctrl iomap not find!\n"); + } else { + dev_dbg(&pdev->dev, "sysctrl iomap find!\n"); + value = readl(peri_subctrl_base_addr + + GPIO_INT_MASK_REG); + value &= ~1UL; + writel(value, peri_subctrl_base_addr + + GPIO_INT_MASK_REG); + } + } if (!pdata) { pdata = dwapb_gpio_get_pdata(dev); @@ -751,6 +797,10 @@ static int dwapb_gpio_remove(struct platform_device *pdev) reset_control_assert(gpio->rst); clk_disable_unprepare(gpio->clk); + if ((peri_subctrl_base_addr != NULL) && enable_ascend_mini_gpio_dwapb && + enable_ascend_gpio_dwapb) + iounmap(peri_subctrl_base_addr); + return 0; } @@ -787,6 +837,9 @@ static int dwapb_gpio_suspend(struct device *dev) ctx->int_pol = dwapb_read(gpio, GPIO_INT_POLARITY); ctx->int_type = dwapb_read(gpio, GPIO_INTTYPE_LEVEL); ctx->int_deb = dwapb_read(gpio, GPIO_PORTA_DEBOUNCE); + if (enable_ascend_gpio_dwapb) + ctx->int_comb_mask = + dwapb_read(gpio, GPIO_INTCOMB_MASK); /* Mask out interrupts */ dwapb_write(gpio, GPIO_INTMASK, @@ -807,6 +860,7 @@ static int dwapb_gpio_resume(struct device *dev) struct gpio_chip *gc = &gpio->ports[0].gc; unsigned long flags; int i; + unsigned int value; if (!IS_ERR(gpio->clk)) clk_prepare_enable(gpio->clk); @@ -835,6 +889,9 @@ static int dwapb_gpio_resume(struct device *dev) dwapb_write(gpio, GPIO_PORTA_DEBOUNCE, ctx->int_deb); dwapb_write(gpio, GPIO_INTEN, ctx->int_en); dwapb_write(gpio, GPIO_INTMASK, ctx->int_mask); + if (enable_ascend_gpio_dwapb) + dwapb_write(gpio, + GPIO_INTCOMB_MASK, ctx->int_comb_mask); /* Clear out spurious interrupts */ dwapb_write(gpio, GPIO_PORTA_EOI, 0xffffffff); @@ -842,6 +899,13 @@ static int dwapb_gpio_resume(struct device *dev) } spin_unlock_irqrestore(&gc->bgpio_lock, flags); + if ((peri_subctrl_base_addr != NULL) && enable_ascend_mini_gpio_dwapb && + enable_ascend_gpio_dwapb) { + value = readl(peri_subctrl_base_addr + GPIO_INT_MASK_REG); + value &= ~1UL; + writel(value, peri_subctrl_base_addr + GPIO_INT_MASK_REG); + } + return 0; } #endif -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/9] iommu/arm-smmu-v3: Add support to configure mpam in STE/CD context
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Xingang Wang <wangxingang5(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I49RB2 CVE: NA ------------------------------------------------- To support limiting qos of device, the partid and pmg need to be set into the SMMU STE/CD context. This introduce support of SMMU mpam feature and add interface to set mpam configuration in STE/CD. Signed-off-by: Xingang Wang <wangxingang5(a)huawei.com> Signed-off-by: Rui Zhu <zhurui3(a)huawei.com> Reviewed-by: Yingtai Xie <xieyingtai(a)huawei.com> Reviewed-by: Zhen Lei <thunder.leizhen(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/iommu/arm-smmu-v3-context.c | 25 +++++ drivers/iommu/arm-smmu-v3.c | 151 ++++++++++++++++++++++++++++ include/linux/ascend_smmu.h | 9 ++ 3 files changed, 185 insertions(+) create mode 100644 include/linux/ascend_smmu.h diff --git a/drivers/iommu/arm-smmu-v3-context.c b/drivers/iommu/arm-smmu-v3-context.c index 2351de86d31f1..b30a93e076608 100644 --- a/drivers/iommu/arm-smmu-v3-context.c +++ b/drivers/iommu/arm-smmu-v3-context.c @@ -66,6 +66,9 @@ #define CTXDESC_CD_1_TTB0_MASK GENMASK_ULL(51, 4) +#define CTXDESC_CD_5_PARTID_MASK GENMASK_ULL(47, 32) +#define CTXDESC_CD_5_PMG_MASK GENMASK_ULL(55, 48) + /* Convert between AArch64 (CPU) TCR format and SMMU CD format */ #define ARM_SMMU_TCR2CD(tcr, fld) FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \ FIELD_GET(ARM64_TCR_##fld, tcr)) @@ -563,6 +566,28 @@ static int arm_smmu_set_cd(struct iommu_pasid_table_ops *ops, int pasid, return arm_smmu_write_ctx_desc(tbl, pasid, cd); } +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg) +{ + struct arm_smmu_cd_tables *tbl = pasid_ops_to_tables(ops); + u64 val; + __le64 *cdptr = arm_smmu_get_cd_ptr(tbl, ssid); + + if (!cdptr) + return -ENOMEM; + + val = le64_to_cpu(cdptr[5]); + val &= ~CTXDESC_CD_5_PARTID_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PARTID_MASK, partid); + val &= ~CTXDESC_CD_5_PMG_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PMG_MASK, pmg); + WRITE_ONCE(cdptr[5], cpu_to_le64(val)); + + iommu_pasid_flush(&tbl->pasid, ssid, true); + + return 0; +} + static void arm_smmu_clear_cd(struct iommu_pasid_table_ops *ops, int pasid, struct iommu_pasid_entry *entry) { diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 6731b47558f4d..c282fc129222f 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -88,6 +88,10 @@ #define IDR1_SSIDSIZE GENMASK(10, 6) #define IDR1_SIDSIZE GENMASK(5, 0) +#define ARM_SMMU_IDR3 0xc +#define IDR3_MPAM (1 << 7) +#define ARM_SMMU_IDR3_CFG 0x140C + #define ARM_SMMU_IDR5 0x14 #define IDR5_STALL_MAX GENMASK(31, 16) #define IDR5_GRAN64K (1 << 6) @@ -186,6 +190,10 @@ #define ARM_SMMU_PRIQ_IRQ_CFG1 0xd8 #define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc +#define ARM_SMMU_MPAMIDR 0x130 +#define MPAMIDR_PMG_MAX GENMASK(23, 16) +#define MPAMIDR_PARTID_MAX GENMASK(15, 0) + /* Common MSI config fields */ #define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2) #define MSI_CFG2_SH GENMASK(5, 4) @@ -250,6 +258,7 @@ #define STRTAB_STE_1_S1COR GENMASK_ULL(5, 4) #define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) +#define STRTAB_STE_1_S1MPAM (1UL << 26) #define STRTAB_STE_1_S1STALLD (1UL << 27) #define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) @@ -273,6 +282,11 @@ #define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) +#define STRTAB_STE_4_PARTID_MASK GENMASK_ULL(31, 16) + +#define STRTAB_STE_5_MPAM_NS (1UL << 8) +#define STRTAB_STE_5_PMG_MASK GENMASK_ULL(7, 0) + /* Command queue */ #define CMDQ_ENT_SZ_SHIFT 4 #define CMDQ_ENT_DWORDS ((1 << CMDQ_ENT_SZ_SHIFT) >> 3) @@ -634,6 +648,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_SVA (1 << 17) #define ARM_SMMU_FEAT_HA (1 << 18) #define ARM_SMMU_FEAT_HD (1 << 19) +#define ARM_SMMU_FEAT_MPAM (1 << 20) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -672,6 +687,9 @@ struct arm_smmu_device { struct mutex streams_mutex; struct iopf_queue *iopf_queue; + + unsigned int mpam_partid_max; + unsigned int mpam_pmg_max; }; struct arm_smmu_stream { @@ -3977,6 +3995,25 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) if (smmu->sid_bits <= STRTAB_SPLIT) smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB; + /* IDR3 */ + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + + if (!(reg & IDR3_MPAM)) { + reg |= FIELD_PREP(IDR3_MPAM, 1); + writel(reg, smmu->base + ARM_SMMU_IDR3_CFG); + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + if (!(reg & IDR3_MPAM)) + dev_warn(smmu->dev, "enable smmu mpam failed\n"); + } + + if (reg & IDR3_MPAM) { + reg = readl_relaxed(smmu->base + ARM_SMMU_MPAMIDR); + smmu->mpam_partid_max = FIELD_GET(MPAMIDR_PARTID_MAX, reg); + smmu->mpam_pmg_max = FIELD_GET(MPAMIDR_PMG_MAX, reg); + if (smmu->mpam_partid_max || smmu->mpam_pmg_max) + smmu->features |= ARM_SMMU_FEAT_MPAM; + } + /* IDR5 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5); @@ -4124,6 +4161,120 @@ static unsigned long arm_smmu_resource_size(struct arm_smmu_device *smmu) return SZ_128K; } +static int arm_smmu_set_ste_mpam(struct arm_smmu_device *smmu, + int sid, int partid, int pmg, int s1mpam) +{ + u64 val; + __le64 *ste; + + if (!arm_smmu_sid_in_range(smmu, sid)) + return -ERANGE; + + /* get ste ptr */ + ste = arm_smmu_get_step_for_sid(smmu, sid); + + /* write s1mpam to ste */ + val = le64_to_cpu(ste[1]); + val &= ~STRTAB_STE_1_S1MPAM; + val |= FIELD_PREP(STRTAB_STE_1_S1MPAM, s1mpam); + WRITE_ONCE(ste[1], cpu_to_le64(val)); + + val = le64_to_cpu(ste[4]); + val &= ~STRTAB_STE_4_PARTID_MASK; + val |= FIELD_PREP(STRTAB_STE_4_PARTID_MASK, partid); + WRITE_ONCE(ste[4], cpu_to_le64(val)); + + val = le64_to_cpu(ste[5]); + val &= ~STRTAB_STE_5_PMG_MASK; + val |= FIELD_PREP(STRTAB_STE_5_PMG_MASK, pmg); + WRITE_ONCE(ste[5], cpu_to_le64(val)); + + arm_smmu_sync_ste_for_sid(smmu, sid); + + return 0; +} + +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg); + +static int arm_smmu_set_mpam(struct arm_smmu_device *smmu, + int sid, int ssid, int partid, int pmg, int s1mpam) +{ + struct arm_smmu_master_data *master = arm_smmu_find_master(smmu, sid); + struct arm_smmu_s1_cfg *cfg = master ? master->ste.s1_cfg : NULL; + struct arm_smmu_domain *domain = master ? master->domain : NULL; + int ret; + + struct arm_smmu_cmdq_ent prefetch_cmd = { + .opcode = CMDQ_OP_PREFETCH_CFG, + .prefetch = { + .sid = sid, + }, + }; + + if (!(smmu->features & ARM_SMMU_FEAT_MPAM)) + return -ENODEV; + + if (WARN_ON(!domain)) + return -EINVAL; + + if (WARN_ON(!cfg)) + return -EINVAL; + + if (WARN_ON(ssid >= (1 << master->ssid_bits))) + return -E2BIG; + + if (partid > smmu->mpam_partid_max || pmg > smmu->mpam_pmg_max) { + dev_err(smmu->dev, + "mpam rmid out of range: partid[0, %d] pmg[0, %d]\n", + smmu->mpam_partid_max, smmu->mpam_pmg_max); + return -ERANGE; + } + + ret = arm_smmu_set_ste_mpam(smmu, sid, partid, pmg, s1mpam); + if (ret < 0) { + dev_err(smmu->dev, "set ste mpam configuration error %d\n", + ret); + return ret; + } + + /* do not modify cd table which owned by guest */ + if (domain->stage == ARM_SMMU_DOMAIN_NESTED) { + dev_err(smmu->dev, + "mpam: smmu cd is owned by guest, not modified\n"); + return 0; + } + + ret = arm_smmu_set_cd_mpam(cfg->ops, ssid, partid, pmg); + if (s1mpam && ret < 0) { + dev_err(smmu->dev, "set cd mpam configuration error %d\n", + ret); + return ret; + } + + /* It's likely that we'll want to use the new STE soon */ + if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH)) + arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd); + + dev_info(smmu->dev, "partid %d, pmg %d\n", partid, pmg); + + return 0; +} + +/** + * arm_smmu_set_dev_mpam() - Set mpam configuration to SMMU STE/CD + */ +int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, int pmg, + int s1mpam) +{ + struct arm_smmu_master_data *master = dev->iommu_fwspec->iommu_priv; + struct arm_smmu_device *smmu = master->domain->smmu; + int sid = master->streams->id; + + return arm_smmu_set_mpam(smmu, sid, ssid, partid, pmg, s1mpam); +} +EXPORT_SYMBOL(arm_smmu_set_dev_mpam); + static int arm_smmu_device_probe(struct platform_device *pdev) { int irq, ret; diff --git a/include/linux/ascend_smmu.h b/include/linux/ascend_smmu.h new file mode 100644 index 0000000000000..bd0edd25057e1 --- /dev/null +++ b/include/linux/ascend_smmu.h @@ -0,0 +1,9 @@ +#ifndef __LINUX_ASCEND_SMMU_H +#define __LINUX_ASCEND_SMMU_H + +#include <linux/device.h> + +extern int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, + int pmg, int s1mpam); + +#endif /* __LINUX_ASCEND_SMMU_H */ -- 2.25.1

1 8

[PATCH kernel-4.19 1/9] iommu/arm-smmu-v3: Add support to configure mpam in STE/CD context
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Xingang Wang <wangxingang5(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I49RB2 CVE: NA ------------------------------------------------- To support limiting qos of device, the partid and pmg need to be set into the SMMU STE/CD context. This introduce support of SMMU mpam feature and add interface to set mpam configuration in STE/CD. Signed-off-by: Xingang Wang <wangxingang5(a)huawei.com> Signed-off-by: Rui Zhu <zhurui3(a)huawei.com> Reviewed-by: Yingtai Xie <xieyingtai(a)huawei.com> Reviewed-by: Zhen Lei <thunder.leizhen(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/iommu/arm-smmu-v3-context.c | 25 +++++ drivers/iommu/arm-smmu-v3.c | 151 ++++++++++++++++++++++++++++ include/linux/ascend_smmu.h | 9 ++ 3 files changed, 185 insertions(+) create mode 100644 include/linux/ascend_smmu.h diff --git a/drivers/iommu/arm-smmu-v3-context.c b/drivers/iommu/arm-smmu-v3-context.c index 2351de86d31f1..b30a93e076608 100644 --- a/drivers/iommu/arm-smmu-v3-context.c +++ b/drivers/iommu/arm-smmu-v3-context.c @@ -66,6 +66,9 @@ #define CTXDESC_CD_1_TTB0_MASK GENMASK_ULL(51, 4) +#define CTXDESC_CD_5_PARTID_MASK GENMASK_ULL(47, 32) +#define CTXDESC_CD_5_PMG_MASK GENMASK_ULL(55, 48) + /* Convert between AArch64 (CPU) TCR format and SMMU CD format */ #define ARM_SMMU_TCR2CD(tcr, fld) FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \ FIELD_GET(ARM64_TCR_##fld, tcr)) @@ -563,6 +566,28 @@ static int arm_smmu_set_cd(struct iommu_pasid_table_ops *ops, int pasid, return arm_smmu_write_ctx_desc(tbl, pasid, cd); } +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg) +{ + struct arm_smmu_cd_tables *tbl = pasid_ops_to_tables(ops); + u64 val; + __le64 *cdptr = arm_smmu_get_cd_ptr(tbl, ssid); + + if (!cdptr) + return -ENOMEM; + + val = le64_to_cpu(cdptr[5]); + val &= ~CTXDESC_CD_5_PARTID_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PARTID_MASK, partid); + val &= ~CTXDESC_CD_5_PMG_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PMG_MASK, pmg); + WRITE_ONCE(cdptr[5], cpu_to_le64(val)); + + iommu_pasid_flush(&tbl->pasid, ssid, true); + + return 0; +} + static void arm_smmu_clear_cd(struct iommu_pasid_table_ops *ops, int pasid, struct iommu_pasid_entry *entry) { diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 8b5083c3e0a16..6634d596f7efc 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -88,6 +88,10 @@ #define IDR1_SSIDSIZE GENMASK(10, 6) #define IDR1_SIDSIZE GENMASK(5, 0) +#define ARM_SMMU_IDR3 0xc +#define IDR3_MPAM (1 << 7) +#define ARM_SMMU_IDR3_CFG 0x140C + #define ARM_SMMU_IDR5 0x14 #define IDR5_STALL_MAX GENMASK(31, 16) #define IDR5_GRAN64K (1 << 6) @@ -186,6 +190,10 @@ #define ARM_SMMU_PRIQ_IRQ_CFG1 0xd8 #define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc +#define ARM_SMMU_MPAMIDR 0x130 +#define MPAMIDR_PMG_MAX GENMASK(23, 16) +#define MPAMIDR_PARTID_MAX GENMASK(15, 0) + /* Common MSI config fields */ #define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2) #define MSI_CFG2_SH GENMASK(5, 4) @@ -250,6 +258,7 @@ #define STRTAB_STE_1_S1COR GENMASK_ULL(5, 4) #define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) +#define STRTAB_STE_1_S1MPAM (1UL << 26) #define STRTAB_STE_1_S1STALLD (1UL << 27) #define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) @@ -273,6 +282,11 @@ #define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) +#define STRTAB_STE_4_PARTID_MASK GENMASK_ULL(31, 16) + +#define STRTAB_STE_5_MPAM_NS (1UL << 8) +#define STRTAB_STE_5_PMG_MASK GENMASK_ULL(7, 0) + /* Command queue */ #define CMDQ_ENT_SZ_SHIFT 4 #define CMDQ_ENT_DWORDS ((1 << CMDQ_ENT_SZ_SHIFT) >> 3) @@ -634,6 +648,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_SVA (1 << 17) #define ARM_SMMU_FEAT_HA (1 << 18) #define ARM_SMMU_FEAT_HD (1 << 19) +#define ARM_SMMU_FEAT_MPAM (1 << 20) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -672,6 +687,9 @@ struct arm_smmu_device { struct mutex streams_mutex; struct iopf_queue *iopf_queue; + + unsigned int mpam_partid_max; + unsigned int mpam_pmg_max; }; struct arm_smmu_stream { @@ -3980,6 +3998,25 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) if (smmu->sid_bits <= STRTAB_SPLIT) smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB; + /* IDR3 */ + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + + if (!(reg & IDR3_MPAM)) { + reg |= FIELD_PREP(IDR3_MPAM, 1); + writel(reg, smmu->base + ARM_SMMU_IDR3_CFG); + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + if (!(reg & IDR3_MPAM)) + dev_warn(smmu->dev, "enable smmu mpam failed\n"); + } + + if (reg & IDR3_MPAM) { + reg = readl_relaxed(smmu->base + ARM_SMMU_MPAMIDR); + smmu->mpam_partid_max = FIELD_GET(MPAMIDR_PARTID_MAX, reg); + smmu->mpam_pmg_max = FIELD_GET(MPAMIDR_PMG_MAX, reg); + if (smmu->mpam_partid_max || smmu->mpam_pmg_max) + smmu->features |= ARM_SMMU_FEAT_MPAM; + } + /* IDR5 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5); @@ -4127,6 +4164,120 @@ static unsigned long arm_smmu_resource_size(struct arm_smmu_device *smmu) return SZ_128K; } +static int arm_smmu_set_ste_mpam(struct arm_smmu_device *smmu, + int sid, int partid, int pmg, int s1mpam) +{ + u64 val; + __le64 *ste; + + if (!arm_smmu_sid_in_range(smmu, sid)) + return -ERANGE; + + /* get ste ptr */ + ste = arm_smmu_get_step_for_sid(smmu, sid); + + /* write s1mpam to ste */ + val = le64_to_cpu(ste[1]); + val &= ~STRTAB_STE_1_S1MPAM; + val |= FIELD_PREP(STRTAB_STE_1_S1MPAM, s1mpam); + WRITE_ONCE(ste[1], cpu_to_le64(val)); + + val = le64_to_cpu(ste[4]); + val &= ~STRTAB_STE_4_PARTID_MASK; + val |= FIELD_PREP(STRTAB_STE_4_PARTID_MASK, partid); + WRITE_ONCE(ste[4], cpu_to_le64(val)); + + val = le64_to_cpu(ste[5]); + val &= ~STRTAB_STE_5_PMG_MASK; + val |= FIELD_PREP(STRTAB_STE_5_PMG_MASK, pmg); + WRITE_ONCE(ste[5], cpu_to_le64(val)); + + arm_smmu_sync_ste_for_sid(smmu, sid); + + return 0; +} + +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg); + +static int arm_smmu_set_mpam(struct arm_smmu_device *smmu, + int sid, int ssid, int partid, int pmg, int s1mpam) +{ + struct arm_smmu_master_data *master = arm_smmu_find_master(smmu, sid); + struct arm_smmu_s1_cfg *cfg = master ? master->ste.s1_cfg : NULL; + struct arm_smmu_domain *domain = master ? master->domain : NULL; + int ret; + + struct arm_smmu_cmdq_ent prefetch_cmd = { + .opcode = CMDQ_OP_PREFETCH_CFG, + .prefetch = { + .sid = sid, + }, + }; + + if (!(smmu->features & ARM_SMMU_FEAT_MPAM)) + return -ENODEV; + + if (WARN_ON(!domain)) + return -EINVAL; + + if (WARN_ON(!cfg)) + return -EINVAL; + + if (WARN_ON(ssid >= (1 << master->ssid_bits))) + return -E2BIG; + + if (partid > smmu->mpam_partid_max || pmg > smmu->mpam_pmg_max) { + dev_err(smmu->dev, + "mpam rmid out of range: partid[0, %d] pmg[0, %d]\n", + smmu->mpam_partid_max, smmu->mpam_pmg_max); + return -ERANGE; + } + + ret = arm_smmu_set_ste_mpam(smmu, sid, partid, pmg, s1mpam); + if (ret < 0) { + dev_err(smmu->dev, "set ste mpam configuration error %d\n", + ret); + return ret; + } + + /* do not modify cd table which owned by guest */ + if (domain->stage == ARM_SMMU_DOMAIN_NESTED) { + dev_err(smmu->dev, + "mpam: smmu cd is owned by guest, not modified\n"); + return 0; + } + + ret = arm_smmu_set_cd_mpam(cfg->ops, ssid, partid, pmg); + if (s1mpam && ret < 0) { + dev_err(smmu->dev, "set cd mpam configuration error %d\n", + ret); + return ret; + } + + /* It's likely that we'll want to use the new STE soon */ + if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH)) + arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd); + + dev_info(smmu->dev, "partid %d, pmg %d\n", partid, pmg); + + return 0; +} + +/** + * arm_smmu_set_dev_mpam() - Set mpam configuration to SMMU STE/CD + */ +int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, int pmg, + int s1mpam) +{ + struct arm_smmu_master_data *master = dev->iommu_fwspec->iommu_priv; + struct arm_smmu_device *smmu = master->domain->smmu; + int sid = master->streams->id; + + return arm_smmu_set_mpam(smmu, sid, ssid, partid, pmg, s1mpam); +} +EXPORT_SYMBOL(arm_smmu_set_dev_mpam); + static int arm_smmu_device_probe(struct platform_device *pdev) { int irq, ret; diff --git a/include/linux/ascend_smmu.h b/include/linux/ascend_smmu.h new file mode 100644 index 0000000000000..bd0edd25057e1 --- /dev/null +++ b/include/linux/ascend_smmu.h @@ -0,0 +1,9 @@ +#ifndef __LINUX_ASCEND_SMMU_H +#define __LINUX_ASCEND_SMMU_H + +#include <linux/device.h> + +extern int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, + int pmg, int s1mpam); + +#endif /* __LINUX_ASCEND_SMMU_H */ -- 2.25.1

1 8

[PATCH openEuler-1.0-LTS 0/6] Fix the problem that the number of tcp timeout retransmissions is lost
by jiazhenyuan 25 Oct '21

25 Oct '21

From: Jiazhenyuan <jiazhenyuan(a)uniontech.com> issue: https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue jiazhenyuan (6): tcp: switch tcp and sch_fq to new earliest departure time net_sched: sch_fq: ensure maxrate fq parameter applies to EDT flows From 9efdda4e3abed13f0903b7b6e4d4c2102019440a Mon Sep 17 00:00:00 2001 From: Eric Dumazet <edumazet(a)google.com> Date: Sat, 24 Nov 2018 09:12:24 -0800 Subject: [PATCH] tcp: address problems caused by EDT misshaps From 7ae189759cc48cf8b54beebff566e9fd2d4e7d7c Mon Sep 17 00:00:00 2001 From: Yuchung Cheng <ycheng(a)google.com> Date: Wed, 16 Jan 2019 15:05:30 -0800 Subject: [PATCH] tcp: always set retrans_stamp on recovery From 01a523b071618abbc634d1958229fe3bd2dfa5fa Mon Sep 17 00:00:00 2001 From: Yuchung Cheng <ycheng(a)google.com> Date: Wed, 16 Jan 2019 15:05:32 -0800 Subject: [PATCH] tcp: create a helper to model exponential backoff From 3256a2d6ab1f71f9a1bd2d7f6f18eb8108c48d17 Mon Sep 17 00:00:00 2001 From: Eric Dumazet <edumazet(a)google.com> Date: Mon, 30 Sep 2019 15:44:44 -0700 Subject: [PATCH] tcp: adjust rto_base in retransmits_timed_out() net/ipv4/tcp_bbr.c | 7 +++-- net/ipv4/tcp_input.c | 17 +++++++----- net/ipv4/tcp_output.c | 29 ++++++++++++++------ net/ipv4/tcp_timer.c | 64 ++++++++++++++++++++----------------------- net/sched/sch_fq.c | 46 ++++++++++++++++++------------- 5 files changed, 92 insertions(+), 71 deletions(-) -- 2.27.0

2 7

[PATCH openEuler-1.0-LTS] nvme-rdma: destroy cm id before destroy qp to avoid use after free
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Ruozhu Li <liruozhu(a)huawei.com> mainline inclusion from mainline-v5.15-rc2 commit 9817d763dbe15327b9b3ff4404fa6f27f927e744 category: bugfix bugzilla: NA CVE: NA Link: https://gitee.com/openeuler/kernel/issues/I1WGZE We got a panic when host received a rej cm event soon after a connect error cm event. When host get connect error cm event, it will destroy qp immediately. But cm_id is still valid then.Another cm event rise here, try to access the qp which was destroyed.Then we got a kernel panic blow: [87816.777089] [20473] ib_cm:cm_rep_handler:2343: cm_rep_handler: Stale connection. local_comm_id -154357094, remote_comm_id -1133609861 [87816.777223] [20473] ib_cm:cm_init_qp_rtr_attr:4162: cm_init_qp_rtr_attr: local_id -1150387077, cm_id_priv->id.state: 13 [87816.777225] [20473] rdma_cm:cma_rep_recv:1871: RDMA CM: CONNECT_ERROR: failed to handle reply. status -22 [87816.777395] [20473] ib_cm:ib_send_cm_rej:2781: ib_send_cm_rej: local_id -1150387077, cm_id->state: 13 [87816.777398] [20473] nvme_rdma:nvme_rdma_cm_handler:1718: nvme nvme278: connect error (6): status -22 id 00000000c3809aff [87816.801155] [20473] nvme_rdma:nvme_rdma_cm_handler:1742: nvme nvme278: CM error event 6 [87816.801160] [20473] rdma_cm:cma_ib_handler:1947: RDMA CM: REJECTED: consumer defined [87816.801163] nvme nvme278: rdma connection establishment failed (-104) [87816.801168] BUG: unable to handle kernel NULL pointer dereference at 0000000000000370 [87816.801201] RIP: 0010:_ib_modify_qp+0x6e/0x3a0 [ib_core] [87816.801215] Call Trace: [87816.801223] cma_modify_qp_err+0x52/0x80 [rdma_cm] [87816.801228] ? __dynamic_pr_debug+0x8a/0xb0 [87816.801232] cma_ib_handler+0x25a/0x2f0 [rdma_cm] [87816.801235] cm_process_work+0x60/0xe0 [ib_cm] [87816.801238] cm_work_handler+0x13b/0x1b97 [ib_cm] [87816.801243] ? __switch_to_asm+0x35/0x70 [87816.801244] ? __switch_to_asm+0x41/0x70 [87816.801246] ? __switch_to_asm+0x35/0x70 [87816.801248] ? __switch_to_asm+0x41/0x70 [87816.801252] ? __switch_to+0x8c/0x480 [87816.801254] ? __switch_to_asm+0x41/0x70 [87816.801256] ? __switch_to_asm+0x35/0x70 [87816.801259] process_one_work+0x1a7/0x3b0 [87816.801263] worker_thread+0x30/0x390 [87816.801266] ? create_worker+0x1a0/0x1a0 [87816.801268] kthread+0x112/0x130 [87816.801270] ? kthread_flush_work_fn+0x10/0x10 [87816.801272] ret_from_fork+0x35/0x40 ------------------------------------------------- We should always destroy cm_id before destroy qp to avoid to get cma event after qp was destroyed, which may lead to use after free. In RDMA connection establishment error flow, don't destroy qp in cm event handler.Just report cm_error to upper level, qp will be destroy in nvme_rdma_alloc_queue() after destroy cm id. Signed-off-by: Ruozhu Li <liruozhu(a)huawei.com> Reviewed-by: Max Gurtovoy <mgurtovoy(a)nvidia.com> Signed-off-by: Christoph Hellwig <hch(a)lst.de> Conflicts: drivers/nvme/host/rdma.c [lrz: adjust context] Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/nvme/host/rdma.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index b8e0d637ddcfc..049edb9ed1858 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -575,8 +575,8 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) if (!test_and_clear_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags)) return; - nvme_rdma_destroy_queue_ib(queue); rdma_destroy_id(queue->cm_id); + nvme_rdma_destroy_queue_ib(queue); mutex_destroy(&queue->queue_lock); } @@ -1509,14 +1509,10 @@ static int nvme_rdma_conn_established(struct nvme_rdma_queue *queue) for (i = 0; i < queue->queue_size; i++) { ret = nvme_rdma_post_recv(queue, &queue->rsp_ring[i]); if (ret) - goto out_destroy_queue_ib; + return ret; } return 0; - -out_destroy_queue_ib: - nvme_rdma_destroy_queue_ib(queue); - return ret; } static int nvme_rdma_conn_rejected(struct nvme_rdma_queue *queue, @@ -1608,14 +1604,10 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) if (ret) { dev_err(ctrl->ctrl.device, "rdma_connect failed (%d).\n", ret); - goto out_destroy_queue_ib; + return ret; } return 0; - -out_destroy_queue_ib: - nvme_rdma_destroy_queue_ib(queue); - return ret; } static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, @@ -1646,8 +1638,6 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, case RDMA_CM_EVENT_ROUTE_ERROR: case RDMA_CM_EVENT_CONNECT_ERROR: case RDMA_CM_EVENT_UNREACHABLE: - nvme_rdma_destroy_queue_ib(queue); - /* fall through */ case RDMA_CM_EVENT_ADDR_ERROR: dev_dbg(queue->ctrl->ctrl.device, "CM error event %d\n", ev->event); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] arm64: Errata: fix kabi changed by cpu_errata
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Weilong Chen <chenweilong(a)huawei.com> ascend inclusion category: feature bugzilla: 46922 CVE: NA ------------------------------------- Patch "cache: Workaround HiSilicon Taishan DC CVAU" breaks the kabi symbols: cpu_hwcaps cpu_hwcap_keys Fix by using CONFIG_HISILICON_ERRATUM_1980005 to protect it. Signed-off-by: Weilong Chen <chenweilong(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/include/asm/cpucaps.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index d6c863d2cf984..69515f9077e34 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -56,8 +56,12 @@ #define ARM64_WORKAROUND_1463225 35 #define ARM64_HAS_CRC32 36 #define ARM64_SSBS 37 +#ifdef CONFIG_HISILICON_ERRATUM_1980005 #define ARM64_WORKAROUND_HISILICON_1980005 38 #define ARM64_NCAPS 39 +#else +#define ARM64_NCAPS 38 +#endif #endif /* __ASM_CPUCAPS_H */ -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 01/45] af_unix: fix garbage collect vs MSG_PEEK
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Miklos Szeredi <mszeredi(a)redhat.com> stable inclusion from linux-4.19.200 commit 1dabafa9f61118b1377fde424d9a94bf8dbf2813 -------------------------------- commit cbcf01128d0a92e131bd09f1688fe032480b65ca upstream. unix_gc() assumes that candidate sockets can never gain an external reference (i.e. be installed into an fd) while the unix_gc_lock is held. Except for MSG_PEEK this is guaranteed by modifying inflight count under the unix_gc_lock. MSG_PEEK does not touch any variable protected by unix_gc_lock (file count is not), yet it needs to be serialized with garbage collection. Do this by locking/unlocking unix_gc_lock: 1) increment file count 2) lock/unlock barrier to make sure incremented file count is visible to garbage collection 3) install file into fd This is a lock barrier (unlike smp_mb()) that ensures that garbage collection is run completely before or completely after the barrier. Cc: <stable(a)vger.kernel.org> Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/unix/af_unix.c | 51 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 49 insertions(+), 2 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 337c4797ab167..98c253afa0db2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1517,6 +1517,53 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) return err; } +static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + scm->fp = scm_fp_dup(UNIXCB(skb).fp); + + /* + * Garbage collection of unix sockets starts by selecting a set of + * candidate sockets which have reference only from being in flight + * (total_refs == inflight_refs). This condition is checked once during + * the candidate collection phase, and candidates are marked as such, so + * that non-candidates can later be ignored. While inflight_refs is + * protected by unix_gc_lock, total_refs (file count) is not, hence this + * is an instantaneous decision. + * + * Once a candidate, however, the socket must not be reinstalled into a + * file descriptor while the garbage collection is in progress. + * + * If the above conditions are met, then the directed graph of + * candidates (*) does not change while unix_gc_lock is held. + * + * Any operations that changes the file count through file descriptors + * (dup, close, sendmsg) does not change the graph since candidates are + * not installed in fds. + * + * Dequeing a candidate via recvmsg would install it into an fd, but + * that takes unix_gc_lock to decrement the inflight count, so it's + * serialized with garbage collection. + * + * MSG_PEEK is special in that it does not change the inflight count, + * yet does install the socket into an fd. The following lock/unlock + * pair is to ensure serialization with garbage collection. It must be + * done between incrementing the file count and installing the file into + * an fd. + * + * If garbage collection starts after the barrier provided by the + * lock/unlock, then it will see the elevated refcount and not mark this + * as a candidate. If a garbage collection is already in progress + * before the file count was incremented, then the lock/unlock pair will + * ensure that garbage collection is finished before progressing to + * installing the fd. + * + * (*) A -> B where B is on the queue of A or B is on the queue of C + * which is on the queue of listening socket A. + */ + spin_lock(&unix_gc_lock); + spin_unlock(&unix_gc_lock); +} + static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) { int err = 0; @@ -2142,7 +2189,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, sk_peek_offset_fwd(sk, size); if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); } err = (flags & MSG_TRUNC) ? skb->len - skip : size; @@ -2383,7 +2430,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, /* It is questionable, see note in unix_dgram_recvmsg. */ if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); sk_peek_offset_fwd(sk, chunk); -- 2.25.1

1 44

[PATCH kernel-4.19 1/9] iommu/arm-smmu-v3: Add support to configure mpam in STE/CD context
by Yang Yingliang 22 Oct '21

22 Oct '21

From: Xingang Wang <wangxingang5(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I49RB2 CVE: NA ------------------------------------------------- To support limiting qos of device, the partid and pmg need to be set into the SMMU STE/CD context. This introduce support of SMMU mpam feature and add interface to set mpam configuration in STE/CD. Signed-off-by: Xingang Wang <wangxingang5(a)huawei.com> Signed-off-by: Rui Zhu <zhurui3(a)huawei.com> Reviewed-by: Yingtai Xie <xieyingtai(a)huawei.com> Reviewed-by: Zhen Lei <thunder.leizhen(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/iommu/arm-smmu-v3-context.c | 25 +++++ drivers/iommu/arm-smmu-v3.c | 151 ++++++++++++++++++++++++++++ include/linux/ascend_smmu.h | 9 ++ 3 files changed, 185 insertions(+) create mode 100644 include/linux/ascend_smmu.h diff --git a/drivers/iommu/arm-smmu-v3-context.c b/drivers/iommu/arm-smmu-v3-context.c index 2351de86d31f1..b30a93e076608 100644 --- a/drivers/iommu/arm-smmu-v3-context.c +++ b/drivers/iommu/arm-smmu-v3-context.c @@ -66,6 +66,9 @@ #define CTXDESC_CD_1_TTB0_MASK GENMASK_ULL(51, 4) +#define CTXDESC_CD_5_PARTID_MASK GENMASK_ULL(47, 32) +#define CTXDESC_CD_5_PMG_MASK GENMASK_ULL(55, 48) + /* Convert between AArch64 (CPU) TCR format and SMMU CD format */ #define ARM_SMMU_TCR2CD(tcr, fld) FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \ FIELD_GET(ARM64_TCR_##fld, tcr)) @@ -563,6 +566,28 @@ static int arm_smmu_set_cd(struct iommu_pasid_table_ops *ops, int pasid, return arm_smmu_write_ctx_desc(tbl, pasid, cd); } +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg) +{ + struct arm_smmu_cd_tables *tbl = pasid_ops_to_tables(ops); + u64 val; + __le64 *cdptr = arm_smmu_get_cd_ptr(tbl, ssid); + + if (!cdptr) + return -ENOMEM; + + val = le64_to_cpu(cdptr[5]); + val &= ~CTXDESC_CD_5_PARTID_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PARTID_MASK, partid); + val &= ~CTXDESC_CD_5_PMG_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PMG_MASK, pmg); + WRITE_ONCE(cdptr[5], cpu_to_le64(val)); + + iommu_pasid_flush(&tbl->pasid, ssid, true); + + return 0; +} + static void arm_smmu_clear_cd(struct iommu_pasid_table_ops *ops, int pasid, struct iommu_pasid_entry *entry) { diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 8b5083c3e0a16..6634d596f7efc 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -88,6 +88,10 @@ #define IDR1_SSIDSIZE GENMASK(10, 6) #define IDR1_SIDSIZE GENMASK(5, 0) +#define ARM_SMMU_IDR3 0xc +#define IDR3_MPAM (1 << 7) +#define ARM_SMMU_IDR3_CFG 0x140C + #define ARM_SMMU_IDR5 0x14 #define IDR5_STALL_MAX GENMASK(31, 16) #define IDR5_GRAN64K (1 << 6) @@ -186,6 +190,10 @@ #define ARM_SMMU_PRIQ_IRQ_CFG1 0xd8 #define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc +#define ARM_SMMU_MPAMIDR 0x130 +#define MPAMIDR_PMG_MAX GENMASK(23, 16) +#define MPAMIDR_PARTID_MAX GENMASK(15, 0) + /* Common MSI config fields */ #define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2) #define MSI_CFG2_SH GENMASK(5, 4) @@ -250,6 +258,7 @@ #define STRTAB_STE_1_S1COR GENMASK_ULL(5, 4) #define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) +#define STRTAB_STE_1_S1MPAM (1UL << 26) #define STRTAB_STE_1_S1STALLD (1UL << 27) #define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) @@ -273,6 +282,11 @@ #define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) +#define STRTAB_STE_4_PARTID_MASK GENMASK_ULL(31, 16) + +#define STRTAB_STE_5_MPAM_NS (1UL << 8) +#define STRTAB_STE_5_PMG_MASK GENMASK_ULL(7, 0) + /* Command queue */ #define CMDQ_ENT_SZ_SHIFT 4 #define CMDQ_ENT_DWORDS ((1 << CMDQ_ENT_SZ_SHIFT) >> 3) @@ -634,6 +648,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_SVA (1 << 17) #define ARM_SMMU_FEAT_HA (1 << 18) #define ARM_SMMU_FEAT_HD (1 << 19) +#define ARM_SMMU_FEAT_MPAM (1 << 20) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -672,6 +687,9 @@ struct arm_smmu_device { struct mutex streams_mutex; struct iopf_queue *iopf_queue; + + unsigned int mpam_partid_max; + unsigned int mpam_pmg_max; }; struct arm_smmu_stream { @@ -3980,6 +3998,25 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) if (smmu->sid_bits <= STRTAB_SPLIT) smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB; + /* IDR3 */ + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + + if (!(reg & IDR3_MPAM)) { + reg |= FIELD_PREP(IDR3_MPAM, 1); + writel(reg, smmu->base + ARM_SMMU_IDR3_CFG); + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + if (!(reg & IDR3_MPAM)) + dev_warn(smmu->dev, "enable smmu mpam failed\n"); + } + + if (reg & IDR3_MPAM) { + reg = readl_relaxed(smmu->base + ARM_SMMU_MPAMIDR); + smmu->mpam_partid_max = FIELD_GET(MPAMIDR_PARTID_MAX, reg); + smmu->mpam_pmg_max = FIELD_GET(MPAMIDR_PMG_MAX, reg); + if (smmu->mpam_partid_max || smmu->mpam_pmg_max) + smmu->features |= ARM_SMMU_FEAT_MPAM; + } + /* IDR5 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5); @@ -4127,6 +4164,120 @@ static unsigned long arm_smmu_resource_size(struct arm_smmu_device *smmu) return SZ_128K; } +static int arm_smmu_set_ste_mpam(struct arm_smmu_device *smmu, + int sid, int partid, int pmg, int s1mpam) +{ + u64 val; + __le64 *ste; + + if (!arm_smmu_sid_in_range(smmu, sid)) + return -ERANGE; + + /* get ste ptr */ + ste = arm_smmu_get_step_for_sid(smmu, sid); + + /* write s1mpam to ste */ + val = le64_to_cpu(ste[1]); + val &= ~STRTAB_STE_1_S1MPAM; + val |= FIELD_PREP(STRTAB_STE_1_S1MPAM, s1mpam); + WRITE_ONCE(ste[1], cpu_to_le64(val)); + + val = le64_to_cpu(ste[4]); + val &= ~STRTAB_STE_4_PARTID_MASK; + val |= FIELD_PREP(STRTAB_STE_4_PARTID_MASK, partid); + WRITE_ONCE(ste[4], cpu_to_le64(val)); + + val = le64_to_cpu(ste[5]); + val &= ~STRTAB_STE_5_PMG_MASK; + val |= FIELD_PREP(STRTAB_STE_5_PMG_MASK, pmg); + WRITE_ONCE(ste[5], cpu_to_le64(val)); + + arm_smmu_sync_ste_for_sid(smmu, sid); + + return 0; +} + +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg); + +static int arm_smmu_set_mpam(struct arm_smmu_device *smmu, + int sid, int ssid, int partid, int pmg, int s1mpam) +{ + struct arm_smmu_master_data *master = arm_smmu_find_master(smmu, sid); + struct arm_smmu_s1_cfg *cfg = master ? master->ste.s1_cfg : NULL; + struct arm_smmu_domain *domain = master ? master->domain : NULL; + int ret; + + struct arm_smmu_cmdq_ent prefetch_cmd = { + .opcode = CMDQ_OP_PREFETCH_CFG, + .prefetch = { + .sid = sid, + }, + }; + + if (!(smmu->features & ARM_SMMU_FEAT_MPAM)) + return -ENODEV; + + if (WARN_ON(!domain)) + return -EINVAL; + + if (WARN_ON(!cfg)) + return -EINVAL; + + if (WARN_ON(ssid >= (1 << master->ssid_bits))) + return -E2BIG; + + if (partid > smmu->mpam_partid_max || pmg > smmu->mpam_pmg_max) { + dev_err(smmu->dev, + "mpam rmid out of range: partid[0, %d] pmg[0, %d]\n", + smmu->mpam_partid_max, smmu->mpam_pmg_max); + return -ERANGE; + } + + ret = arm_smmu_set_ste_mpam(smmu, sid, partid, pmg, s1mpam); + if (ret < 0) { + dev_err(smmu->dev, "set ste mpam configuration error %d\n", + ret); + return ret; + } + + /* do not modify cd table which owned by guest */ + if (domain->stage == ARM_SMMU_DOMAIN_NESTED) { + dev_err(smmu->dev, + "mpam: smmu cd is owned by guest, not modified\n"); + return 0; + } + + ret = arm_smmu_set_cd_mpam(cfg->ops, ssid, partid, pmg); + if (s1mpam && ret < 0) { + dev_err(smmu->dev, "set cd mpam configuration error %d\n", + ret); + return ret; + } + + /* It's likely that we'll want to use the new STE soon */ + if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH)) + arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd); + + dev_info(smmu->dev, "partid %d, pmg %d\n", partid, pmg); + + return 0; +} + +/** + * arm_smmu_set_dev_mpam() - Set mpam configuration to SMMU STE/CD + */ +int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, int pmg, + int s1mpam) +{ + struct arm_smmu_master_data *master = dev->iommu_fwspec->iommu_priv; + struct arm_smmu_device *smmu = master->domain->smmu; + int sid = master->streams->id; + + return arm_smmu_set_mpam(smmu, sid, ssid, partid, pmg, s1mpam); +} +EXPORT_SYMBOL(arm_smmu_set_dev_mpam); + static int arm_smmu_device_probe(struct platform_device *pdev) { int irq, ret; diff --git a/include/linux/ascend_smmu.h b/include/linux/ascend_smmu.h new file mode 100644 index 0000000000000..bd0edd25057e1 --- /dev/null +++ b/include/linux/ascend_smmu.h @@ -0,0 +1,9 @@ +#ifndef __LINUX_ASCEND_SMMU_H +#define __LINUX_ASCEND_SMMU_H + +#include <linux/device.h> + +extern int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, + int pmg, int s1mpam); + +#endif /* __LINUX_ASCEND_SMMU_H */ -- 2.25.1

1 8

[PATCH kernel-4.19] efi: Change down_interruptible() in virt_efi_reset_system() to down_trylock()
by Yang Yingliang 22 Oct '21

22 Oct '21

From: Zhang Jianhua <chris.zjh(a)huawei.com> hulk inclusion category: bugfix bugzilla: 182892, https://gitee.com/openeuler/kernel/issues/I4F04R -------- While reboot the system by sysrq, the following bug will be occur. BUG: sleeping function called from invalid context at kernel/locking/semaphore.c:90 in_atomic(): 0, irqs_disabled(): 128, non_block: 0, pid: 10052, name: rc.shutdown CPU: 3 PID: 10052 Comm: rc.shutdown Tainted: G W O 5.10.0 #1 Call trace: dump_backtrace+0x0/0x1c8 show_stack+0x18/0x28 dump_stack+0xd0/0x110 ___might_sleep+0x14c/0x160 __might_sleep+0x74/0x88 down_interruptible+0x40/0x118 virt_efi_reset_system+0x3c/0xd0 efi_reboot+0xd4/0x11c machine_restart+0x60/0x9c emergency_restart+0x1c/0x2c sysrq_handle_reboot+0x1c/0x2c __handle_sysrq+0xd0/0x194 write_sysrq_trigger+0xbc/0xe4 proc_reg_write+0xd4/0xf0 vfs_write+0xa8/0x148 ksys_write+0x6c/0xd8 __arm64_sys_write+0x18/0x28 el0_svc_common.constprop.3+0xe4/0x16c do_el0_svc+0x1c/0x2c el0_svc+0x20/0x30 el0_sync_handler+0x80/0x17c el0_sync+0x158/0x180 The reason for this problem is that irq has been disabled in machine_restart() and then it calls down_interruptible() in virt_efi_reset_system(), which would occur sleep in irq context, it is dangerous! Commit 99409b935c9a("locking/semaphore: Add might_sleep() to down_*() family") add might_sleep() in down_interruptible(), so the bug info is here. down_trylock() can solve this problem, cause there is no might_sleep. Signed-off-by: Zhang Jianhua <chris.zjh(a)huawei.com> Reviewed-by: Chen Lifu <chenlifu(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Reviewed-by: Liao Chang <liaochang1(a)huawei.com> Reviewed-by: He Ying <heying24(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Reviewed-by: Yihang Xu <xuyihang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/firmware/efi/runtime-wrappers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index 04288719721fc..ecee810f7a6fa 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -408,7 +408,7 @@ static void virt_efi_reset_system(int reset_type, unsigned long data_size, efi_char16_t *data) { - if (down_interruptible(&efi_runtime_lock)) { + if (down_trylock(&efi_runtime_lock)) { pr_warn("failed to invoke the reset_system() runtime service:\n" "could not get exclusive access to the firmware\n"); return; -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] svm: Use vma->vm_pgoff for the nid
by Yang Yingliang 22 Oct '21

22 Oct '21

From: Lijun Fang <fanglijun3(a)huawei.com> ascend inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4DZYE CVE: NA --------------------------- svm_mmap use the pgoff flag for the security requirement nid, which used as cdm node. Signed-off-by: Lijun Fang <fanglijun3(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/char/svm.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/char/svm.c b/drivers/char/svm.c index f312b7e02263c..62092fbaa0104 100644 --- a/drivers/char/svm.c +++ b/drivers/char/svm.c @@ -1820,9 +1820,17 @@ static int svm_mmap(struct file *file, struct vm_area_struct *vma) if ((vma->vm_end < vma->vm_start) || (vm_size > MMAP_PHY32_MAX)) return -EINVAL; - page = alloc_pages(GFP_KERNEL | GFP_DMA32, get_order(vm_size)); + /* vma->vm_pgoff transfer the nid */ + if (vma->vm_pgoff == 0) + page = alloc_pages(GFP_KERNEL | GFP_DMA32, + get_order(vm_size)); + else + page = alloc_pages_node((int)vma->vm_pgoff, + GFP_KERNEL | __GFP_THISNODE, + get_order(vm_size)); if (!page) { - dev_err(sdev->dev, "fail to alloc page\n"); + dev_err(sdev->dev, "fail to alloc page on node 0x%lx\n", + vma->vm_pgoff); return -ENOMEM; } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] Ascend/hugetlb:support alloc normal and buddy hugepage
by Yang Yingliang 22 Oct '21

22 Oct '21

From: Zhou Guanghui <zhouguanghui1(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4D63I CVE: NA ---------------------------------------------------- The current function hugetlb_alloc_hugepage implements the allocation from static hugepages first. When the static hugepage is used up, it attempts to apply for hugepages from buddy system. Two additional modes are supported: static hugepages only and buddy hugepages only. Signed-off-by: Zhou Guanghui <zhouguanghui1(a)huawei.com> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/hugetlb.h | 11 +++++++++-- mm/hugetlb.c | 35 +++++++++++++++++++++++++++++++++-- 2 files changed, 42 insertions(+), 4 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 830c41a5ca70e..de6cdfa51694c 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -374,8 +374,15 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); #ifdef CONFIG_ASCEND_FEATURES +#define HUGETLB_ALLOC_NONE 0x00 +#define HUGETLB_ALLOC_NORMAL 0x01 /* normal hugepage */ +#define HUGETLB_ALLOC_BUDDY 0x02 /* buddy hugepage */ +#define HUGETLB_ALLOC_MASK (HUGETLB_ALLOC_NONE | \ + HUGETLB_ALLOC_NORMAL | \ + HUGETLB_ALLOC_BUDDY) + const struct hstate *hugetlb_get_hstate(void); -struct page *hugetlb_alloc_hugepage(int nid); +struct page *hugetlb_alloc_hugepage(int nid, int flag); int hugetlb_insert_hugepage_pte(struct mm_struct *mm, unsigned long addr, pgprot_t prot, struct page *hpage); #else @@ -384,7 +391,7 @@ static inline const struct hstate *hugetlb_get_hstate(void) return NULL; } -static inline struct page *hugetlb_alloc_hugepage(int nid) +static inline struct page *hugetlb_alloc_hugepage(int nid, int flag) { return NULL; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3091c61bb63e3..907b1351b0f5f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5233,17 +5233,48 @@ const struct hstate *hugetlb_get_hstate(void) } EXPORT_SYMBOL_GPL(hugetlb_get_hstate); +static struct page *hugetlb_alloc_hugepage_normal(struct hstate *h, + gfp_t gfp_mask, int nid) +{ + struct page *page = NULL; + + spin_lock(&hugetlb_lock); + if (h->free_huge_pages - h->resv_huge_pages > 0) + page = dequeue_huge_page_nodemask(h, gfp_mask, nid, NULL, NULL); + spin_unlock(&hugetlb_lock); + + return page; +} + /* * Allocate hugepage without reserve */ -struct page *hugetlb_alloc_hugepage(int nid) +struct page *hugetlb_alloc_hugepage(int nid, int flag) { + struct hstate *h = &default_hstate; + gfp_t gfp_mask = htlb_alloc_mask(h); + struct page *page = NULL; + VM_WARN_ON(nid < 0 || nid >= MAX_NUMNODES); + if (flag & ~HUGETLB_ALLOC_MASK) + return NULL; + if (nid == NUMA_NO_NODE) nid = numa_mem_id(); - return alloc_huge_page_node(&default_hstate, nid); + gfp_mask |= __GFP_THISNODE; + + if (flag & HUGETLB_ALLOC_NORMAL) + page = hugetlb_alloc_hugepage_normal(h, gfp_mask, nid); + else if (flag & HUGETLB_ALLOC_BUDDY) { + if (enable_charge_mighp) + gfp_mask |= __GFP_ACCOUNT; + page = alloc_migrate_huge_page(h, gfp_mask, nid, NULL); + } else + page = alloc_huge_page_node(h, nid); + + return page; } EXPORT_SYMBOL_GPL(hugetlb_alloc_hugepage); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] Ascend/memcg: Use CONFIG_ASCEND_FEATURES for customized interfaces
by Yang Yingliang 22 Oct '21

22 Oct '21

From: Zhou Guanghui <zhouguanghui1(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4D63I CVE: NA ------------------------------------------------------------- The following functions are used only in the ascend scenario: hugetlb_get_hstate, hugetlb_alloc_hugepage, hugetlb_insert_hugepage_pte, hugetlb_insert_hugepage_pte_by_pa Remove unused interface hugetlb_insert_hugepage Signed-off-by: Zhou Guanghui <zhouguanghui1(a)huawei.com> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/hugetlb.h | 33 ++++++++++++++++++++++++++------- mm/hugetlb.c | 2 +- 2 files changed, 27 insertions(+), 8 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6831b24defd64..830c41a5ca70e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -373,11 +373,27 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); -#ifdef CONFIG_ARM64 +#ifdef CONFIG_ASCEND_FEATURES const struct hstate *hugetlb_get_hstate(void); struct page *hugetlb_alloc_hugepage(int nid); int hugetlb_insert_hugepage_pte(struct mm_struct *mm, unsigned long addr, pgprot_t prot, struct page *hpage); +#else +static inline const struct hstate *hugetlb_get_hstate(void) +{ + return NULL; +} + +static inline struct page *hugetlb_alloc_hugepage(int nid) +{ + return NULL; +} + +static inline int hugetlb_insert_hugepage_pte(struct mm_struct *mm, + unsigned long addr, pgprot_t prot, struct page *hpage) +{ + return -EPERM; +} #endif /* arch callback */ @@ -614,12 +630,6 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr { } -static inline int hugetlb_insert_hugepage_pte_by_pa(struct mm_struct *mm, - unsigned long vir_addr, - pgprot_t prot, unsigned long phy_addr) -{ - return 0; -} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, @@ -632,4 +642,13 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h, return ptl; } +#ifndef CONFIG_ASCEND_FEATURES +static inline int hugetlb_insert__hugepage_pte_by_pa(struct mm_struct *mm, + unsigned long vir_addr, + pgprot_t prot, unsigned long phy_addr) +{ + return -EPERM; +} +#endif + #endif /* _LINUX_HUGETLB_H */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5132fefb60c86..3091c61bb63e3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5226,7 +5226,7 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) } } -#ifdef CONFIG_ARM64 +#ifdef CONFIG_ASCEND_FEATURES const struct hstate *hugetlb_get_hstate(void) { return &default_hstate; -- 2.25.1

1 0

[PATCH kernel-4.19 1/2] fuse: truncate pagecache on atomic_o_trunc
by Yang Yingliang 22 Oct '21

22 Oct '21

From: Miklos Szeredi <mszeredi(a)redhat.com> mainline inclusion from mainline-5.14 commit 76224355db7570cbe6b6f75c8929a1558828dd55 category: bugfix bugzilla: 181107 CVE: NA --------------------------- fuse_finish_open() will be called with FUSE_NOWRITE in case of atomic O_TRUNC. This can deadlock with fuse_wait_on_page_writeback() in fuse_launder_page() triggered by invalidate_inode_pages2(). Fix by replacing invalidate_inode_pages2() in fuse_finish_open() with a truncate_pagecache() call. This makes sense regardless of FOPEN_KEEP_CACHE or fc->writeback cache, so do it unconditionally. Reported-by: Xie Yongji <xieyongji(a)bytedance.com> Reported-and-tested-by: syzbot+bea44a5189836d956894(a)syzkaller.appspotmail.com Fixes: e4648309b85a ("fuse: truncate pending writes on O_TRUNC") Cc: <stable(a)vger.kernel.org> Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Conflict: fs/fuse/file.c Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/fuse/file.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 41e2a7b567d7f..5ecabacabd477 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -178,8 +178,6 @@ void fuse_finish_open(struct inode *inode, struct file *file) if (ff->open_flags & FOPEN_DIRECT_IO) file->f_op = &fuse_direct_io_file_operations; - if (!(ff->open_flags & FOPEN_KEEP_CACHE)) - invalidate_inode_pages2(inode->i_mapping); if (ff->open_flags & FOPEN_STREAM) stream_open(inode, file); else if (ff->open_flags & FOPEN_NONSEEKABLE) @@ -191,10 +189,13 @@ void fuse_finish_open(struct inode *inode, struct file *file) fi->attr_version = ++fc->attr_version; i_size_write(inode, 0); spin_unlock(&fc->lock); + truncate_pagecache(inode, 0); fuse_invalidate_attr(inode); if (fc->writeback_cache) file_update_time(file); - } + } else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); + if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache) fuse_link_write_file(file); } -- 2.25.1

1 1

unsubscribe
by 🐟๛ก(ｰ̀ωｰ́ก) 22 Oct '21

22 Oct '21

unsubscribe

1 0

(no subject)
by 🐟๛ก(ｰ̀ωｰ́ก) 22 Oct '21

22 Oct '21

help

1 0

[PATCH kernel-4.19 1/4] ext4: check and update i_disksize properly
by Yang Yingliang 22 Oct '21

22 Oct '21

From: Zhang Yi <yi.zhang(a)huawei.com> mainline inclusion from mainline-5.15-rc4 commit 4df031ff5876d94b48dd9ee486ba5522382a06b2 category: perf bugzilla: NA CVE: NA --------------------------- After commit 3da40c7b0898 ("ext4: only call ext4_truncate when size <= isize"), i_disksize could always be updated to i_size in ext4_setattr(), and we could sure that i_disksize <= i_size since holding inode lock and if i_disksize < i_size there are delalloc writes pending in the range upto i_size. If the end of the current write is <= i_size, there's no need to touch i_disksize since writeback will push i_disksize upto i_size eventually. So we can switch to check i_size instead of i_disksize in ext4_da_write_end() when write to the end of the file. we also could remove ext4_mark_inode_dirty() together because we defer inode dirtying to generic_write_end() or ext4_da_write_inline_data_end(). Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Link: https://lore.kernel.org/r/20210716122024.1105856-2-yi.zhang@huawei.com Conflicts: fs/ext4/inode.c Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/inode.c | 34 ++++++++++++++++++---------------- 1 file changed, 18 insertions(+), 16 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b1bede3c489e7..9bb38c936e020 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3190,35 +3190,37 @@ static int ext4_da_write_end(struct file *file, end = start + copied - 1; /* - * generic_write_end() will run mark_inode_dirty() if i_size - * changes. So let's piggyback the i_disksize mark_inode_dirty - * into that. + * Since we are holding inode lock, we are sure i_disksize <= + * i_size. We also know that if i_disksize < i_size, there are + * delalloc writes pending in the range upto i_size. If the end of + * the current write is <= i_size, there's no need to touch + * i_disksize since writeback will push i_disksize upto i_size + * eventually. If the end of the current write is > i_size and + * inside an allocated block (ext4_da_should_update_i_disksize() + * check), we need to update i_disksize here as neither + * ext4_writepage() nor certain ext4_writepages() paths not + * allocating blocks update i_disksize. + * + * Note that we defer inode dirtying to generic_write_end() / + * ext4_da_write_inline_data_end(). */ new_i_size = pos + copied; - if (copied && new_i_size > EXT4_I(inode)->i_disksize) { + if (copied && new_i_size > inode->i_size) { if (ext4_has_inline_data(inode) || - ext4_da_should_update_i_disksize(page, end)) { + ext4_da_should_update_i_disksize(page, end)) ext4_update_i_disksize(inode, new_i_size); - /* We need to mark inode dirty even if - * new_i_size is less that inode->i_size - * bu greater than i_disksize.(hint delalloc) - */ - ext4_mark_inode_dirty(handle, inode); - } } if (write_mode != CONVERT_INLINE_DATA && ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && ext4_has_inline_data(inode)) - ret2 = ext4_da_write_inline_data_end(inode, pos, len, copied, + ret = ext4_da_write_inline_data_end(inode, pos, len, copied, page); else - ret2 = generic_write_end(file, mapping, pos, len, copied, + ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); - copied = ret2; - if (ret2 < 0) - ret = ret2; + copied = ret; ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; -- 2.25.1

1 3

[PATCH v3 openEuler-1.0-LTS 0/2] drm/hisilicon: Fix hibmc did not get edid
by Gou Hao 22 Oct '21

22 Oct '21

From: gouhao <gouhao(a)uniontech.com> Fix hibmc did not get edid. issue: https://gitee.com/openeuler/kernel/issues/I469VQ gouhao (2): drm/hisilicon: Support i2c driver algorithms for bit-shift adapters drm/hisilicon: Features to support reading resolutions from EDID drivers/gpu/drm/hisilicon/hibmc/Makefile | 3 +- .../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 25 +++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c | 98 +++++++++++++++++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 54 ++++++---- 4 files changed, 162 insertions(+), 18 deletions(-) create mode 100644 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c -- 2.20.1

1 2

[PATCH kernel-4.19 openEuler-1.0-LTS] sched/topology: Fix sched_domain_topology_level alloc in sched_init_numa()
by Cheng Jian 21 Oct '21

21 Oct '21

From: Dietmar Eggemann <dietmar.eggemann(a)arm.com> mainline inclusion from mainline-v5.12-rc1 commit 71e5f6644fb2f3304fcb310145ded234a37e7cc1 category: bugfix bugzilla: 182847,https://gitee.com/openeuler/kernel/issues/I4EVBL CVE: NA ---------------------------------------------------------- Commit "sched/topology: Make sched_init_numa() use a set for the deduplicating sort" allocates 'i + nr_levels (level)' instead of 'i + nr_levels + 1' sched_domain_topology_level. This led to an Oops (on Arm64 juno with CONFIG_SCHED_DEBUG): sched_init_domains build_sched_domains() __free_domain_allocs() __sdt_free() { ... for_each_sd_topology(tl) ... sd = *per_cpu_ptr(sdd->sd, j); <-- ... } Signed-off-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Tested-by: Vincent Guittot <vincent.guittot(a)linaro.org> Tested-by: Barry Song <song.bao.hua(a)hisilicon.com> Link: https://lkml.kernel.org/r/6000e39e-7d28-c360-9cd6-8798fd22a9bf@arm.com Fixes: 620a6dc40754 ("sched/topology: Make sched_init_numa() use a set for the deduplicating sort") Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- kernel/sched/topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 23f0a69b2ed4..ad5591520c99 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1548,7 +1548,7 @@ void sched_init_numa(void) /* Compute default topology size */ for (i = 0; sched_domain_topology[i].mask; i++); - tl = kzalloc((i + nr_levels) * + tl = kzalloc((i + nr_levels + 1) * sizeof(struct sched_domain_topology_level), GFP_KERNEL); if (!tl) return; -- 2.25.1

1 0

[PATCH openEuler-5.10 000/118] Backport LTS 5.10.68
by Zheng Zengkai 21 Oct '21

21 Oct '21

Backport LTS 5.10.68 patches from upstream. Adrian Bunk (1): bnx2x: Fix enabling network interfaces without VFs Alex Elder (1): net: ipa: initialize all filter table slots Alexander Egorenkov (1): s390/sclp: fix Secure-IPL facility detection Anand Jain (1): btrfs: fix upper limit for max_inline for page size 64K Andrea Claudi (1): selftest: net: fix typo in altname test Andy Shevchenko (2): PCI: Sync __pci_register_driver() stub for CONFIG_PCI=n mfd: lpc_sch: Partially revert "Add support for Intel Quark X1000" Anshuman Khandual (1): KVM: arm64: Restrict IPA size to maximum 48 bits on 4K and 16K page size Arnaldo Carvalho de Melo (1): perf bench inject-buildid: Handle writen() errors Arnd Bergmann (1): drm/rockchip: cdn-dp-core: Make cdn_dp_core_resume __maybe_unused Aya Levin (1): udp_tunnel: Fix udp_tunnel_nic work-queue type Baptiste Lepers (1): events: Reuse value read using READ_ONCE instead of re-reading it Benjamin Hesmans (1): netfilter: socket: icmp6: fix use-after-scope Christophe JAILLET (4): PCI: tegra: Fix OF node reference leak mtd: rawnand: cafe: Fix a resource leak in the error handling path of 'cafe_nand_probe()' gpio: mpc8xxx: Fix a resources leak in the error handling path of 'mpc8xxx_probe()' gpio: mpc8xxx: Use 'devm_gpiochip_add_data()' to simplify the code and avoid a leak Dan Carpenter (1): PCI: Fix pci_dev_str_match_path() alloc while atomic bug Daniele Palmas (1): net: usb: cdc_mbim: avoid altsetting toggling for Telit LN920 David Heidelberg (1): dt-bindings: arm: Fix Toradex compatible typo David Hildenbrand (1): mm/memory_hotplug: use "unsigned long" for PFN in zone_for_pfn_range() Dinghao Liu (2): PCI: rcar: Fix runtime PM imbalance in rcar_pcie_ep_probe() qlcnic: Remove redundant unlock in qlcnic_pinit_from_rom Edwin Peer (3): bnxt_en: make bnxt_free_skbs() safe to call after bnxt_free_mem() bnxt_en: fix stored FW_PSID version masks bnxt_en: log firmware debug notifications Eli Cohen (1): net/{mlx5|nfp|bnxt}: Remove unnecessary RTNL lock assert Eric Dumazet (3): net-caif: avoid user-triggerable WARN_ON(1) net/af_unix: fix a data-race in unix_dgram_poll fq_codel: reject silly quantum parameters Ernst Sjöstrand (1): drm/amd/amdgpu: Increase HWIP_MAX_INSTANCE to 10 Evan Quan (1): PCI: Add AMD GPU multi-function power dependencies Florian Fainelli (2): r6040: Restore MDIO clock frequency after MAC reset net: dsa: bcm_sf2: Fix array overrun in bcm_sf2_num_active_ports() George Cherian (1): PCI: Add ACS quirks for Cavium multi-function devices Gustavo A. R. Silva (1): netfilter: Fix fall-through warnings for Clang Hans de Goede (1): mfd: axp20x: Update AXP288 volatile ranges Hoang Le (1): tipc: increase timeout in tipc_sk_enqueue() Ilya Leoshkevich (3): s390/bpf: Fix optimizing out zero-extensions s390/bpf: Fix 64-bit subtraction of the -0x80000000 constant s390/bpf: Fix branch shortening during codegen pass Jan Kiszka (1): watchdog: Start watchdog in watchdog_set_last_hw_keepalive only if appropriate Jeff Moyer (1): x86/pat: Pass valid address to sanitize_phys() Juergen Gross (2): xen: reset legacy rtc flag for PV domU PM: base: power: don't try to use non-existing RTC for storing data Keith Busch (1): nvme-tcp: fix io_work priority inversion Kishon Vijay Abraham I (3): PCI: cadence: Use bitfield for *quirk_retrain_flag* instead of bool PCI: j721e: Add PCIe support for J7200 PCI: j721e: Add PCIe support for AM64 Kortan (1): gen_compile_commands: fix missing 'sys' package Li Huafei (1): perf unwind: Do not overwrite FEATURE_CHECK_LDFLAGS-libunwind-{x86,aarch64} Lin, Zhenpeng (1): dccp: don't duplicate ccid when cloning dccp sock Linus Walleij (3): mfd: db8500-prcmu: Adjust map to reality backlight: ktd253: Stabilize backlight net: dsa: tag_rtl4_a: Fix egress tags Lucas Stach (8): drm/etnaviv: return context from etnaviv_iommu_context_get drm/etnaviv: put submit prev MMU context when it exists drm/etnaviv: stop abusing mmu_context as FE running marker drm/etnaviv: keep MMU context across runtime suspend/resume drm/etnaviv: exec and MMU state is lost when resetting the GPU drm/etnaviv: fix MMU context leak on GPU reset drm/etnaviv: reference MMU context when setting up hardware state drm/etnaviv: add missing MMU context put when reaping MMU mapping Maor Gottlieb (1): net/mlx5: Fix potential sleeping in atomic context Marc Zyngier (1): mfd: Don't use irq_create_mapping() to resolve a mapping Mark Brown (1): arm64/sve: Use correct size when reinitialising SVE state Masami Hiramatsu (2): tracing/probes: Reject events which have the same name of existing one tracing/boot: Fix a hist trigger dependency for boot time tracing Matthias Schiffer (1): mfd: tqmx86: Clear GPIO IRQ resource when no IRQ is set Matthieu Baerts (1): selftests: mptcp: clean tmp files in simult_flows Michael Chan (6): bnxt_en: Fix asic.rev in devlink dev info command bnxt_en: Consolidate firmware reset event logging. bnxt_en: Convert to use netif_level() helpers. bnxt_en: Improve logging of error recovery settings information. bnxt_en: Fix possible unintended driver initiated error recovery bnxt_en: Fix error recovery regression Michael Petlan (1): perf machine: Initialize srcline string member in add_location struct Mike Rapoport (1): x86/mm: Fix kern_addr_valid() to cope with existing but not present entries Miklos Szeredi (1): fuse: fix use after free in fuse_read_interrupt() Miquel Raynal (1): dt-bindings: mtd: gpmc: Fix the ECC bytes vs. OOB bytes equation Nadeem Athani (1): PCI: cadence: Add quirk flag to set minimum delay in LTSSM Detect.Quiet state Nicholas Piggin (1): KVM: PPC: Book3S HV: Tolerate treclaim. in fake-suspend mode changing registers Oliver Upton (2): KVM: arm64: Fix read-side race on updates to vcpu reset state KVM: arm64: Handle PSCI resets before userspace touches vCPU state Om Prakash Singh (2): PCI: tegra194: Fix handling BME_CHGED event PCI: tegra194: Fix MSI-X programming Paolo Abeni (1): vhost_net: fix OoB on sendmsg() failure. Paolo Valente (1): block, bfq: honor already-setup queue merges Pavel Skripkin (1): netfilter: nft_ct: protect nft_ct_pcpu_template_refcnt with mutex Rafał Miłecki (3): net: dsa: b53: Fix calculating number of switch ports net: dsa: b53: Set correct number of ports in the DSA struct net: dsa: b53: Fix IMP port setup on BCM5301x Randy Dunlap (3): ptp: dp83640: don't define PAGE0 ARC: export clear_user_page() for modules mfd: lpc_sch: Rename GPIOBASE to prevent build error Rob Herring (2): PCI: of: Don't fail devm_pci_alloc_host_bridge() on missing 'ranges' PCI: iproc: Fix BCMA probe resource handling Robert Foss (1): drm/bridge: lt9611: Fix handling of 4k panels Ryoga Saito (1): Set fc_nlinfo in nh_create_ipv4, nh_create_ipv6 Saeed Mahameed (2): ethtool: Fix rxnfc copy to user buffer overflow net/mlx5: FWTrace, cancel work on alloc pd error flow Shai Malin (1): qed: Handle management FW error Smadar Fuks (1): octeontx2-af: Add additional register check to rvu_poll_reg() Sukadev Bhattiprolu (1): ibmvnic: check failover_pending in login response Tony Luck (1): x86/mce: Avoid infinite loop for copy from user recovery Vishal Aslot (1): PCI: ibmphp: Fix double unmap of io_mem Vladimir Oltean (1): net: dsa: destroy the phylink instance on any error in dsa_slave_phy_setup Wasim Khan (1): PCI: Add ACS quirks for NXP LX2xx0 and LX2xx2 platforms Will Deacon (1): x86/uaccess: Fix 32-bit __get_user_asm_u64() when CC_HAS_ASM_GOTO_OUTPUT=y Willem de Bruijn (1): ip_gre: validate csum_start only on pull Xin Long (1): tipc: fix an use-after-free issue in tipc_recvmsg Xiyu Yang (1): net/l2tp: Fix reference count leak in l2tp_udp_recv_core Yang Li (3): ethtool: Fix an error code in cxgb2.c NTB: Fix an error code in ntb_msit_probe() NTB: perf: Fix an error code in perf_setup_inbuf() Yoshihiro Shimoda (1): net: renesas: sh_eth: Fix freeing wrong tx descriptor Ziyang Xuan (1): net: hso: add failure handler for add_net_device zhenggy (1): tcp: fix tp->undo_retrans accounting in tcp_sacktag_one() .../devicetree/bindings/arm/tegra.yaml | 2 +- .../devicetree/bindings/mtd/gpmc-nand.txt | 2 +- arch/arc/mm/cache.c | 2 +- arch/arm64/kernel/fpsimd.c | 2 +- arch/arm64/kvm/arm.c | 8 ++ arch/arm64/kvm/reset.c | 24 ++++-- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 36 ++++++++- arch/s390/net/bpf_jit_comp.c | 70 ++++++++-------- arch/x86/include/asm/uaccess.h | 4 +- arch/x86/kernel/cpu/mce/core.c | 43 +++++++--- arch/x86/mm/init_64.c | 6 +- arch/x86/mm/pat/memtype.c | 7 +- arch/x86/xen/enlighten_pv.c | 7 ++ block/bfq-iosched.c | 16 +++- drivers/base/power/trace.c | 10 +++ drivers/gpio/gpio-mpc8xxx.c | 5 +- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 +- drivers/gpu/drm/bridge/lontium-lt9611.c | 8 +- drivers/gpu/drm/etnaviv/etnaviv_buffer.c | 3 +- drivers/gpu/drm/etnaviv/etnaviv_gem.c | 3 +- drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c | 3 +- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 43 +++++----- drivers/gpu/drm/etnaviv/etnaviv_gpu.h | 1 + drivers/gpu/drm/etnaviv/etnaviv_iommu.c | 4 + drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c | 8 ++ drivers/gpu/drm/etnaviv/etnaviv_mmu.c | 1 + drivers/gpu/drm/etnaviv/etnaviv_mmu.h | 4 +- drivers/gpu/drm/rockchip/cdn-dp-core.c | 4 +- drivers/mfd/ab8500-core.c | 2 +- drivers/mfd/axp20x.c | 3 +- drivers/mfd/db8500-prcmu.c | 14 ++-- drivers/mfd/lpc_sch.c | 36 ++------- drivers/mfd/stmpe.c | 4 +- drivers/mfd/tc3589x.c | 2 +- drivers/mfd/tqmx86.c | 2 + drivers/mfd/wm8994-irq.c | 2 +- drivers/mtd/nand/raw/cafe_nand.c | 4 +- drivers/net/dsa/b53/b53_common.c | 33 ++++++-- drivers/net/dsa/b53/b53_priv.h | 1 + drivers/net/dsa/bcm_sf2.c | 2 +- .../net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 80 +++++++++++++------ .../net/ethernet/broadcom/bnxt/bnxt_devlink.c | 6 +- drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 3 - drivers/net/ethernet/chelsio/cxgb/cxgb2.c | 1 + drivers/net/ethernet/ibm/ibmvnic.c | 8 ++ .../net/ethernet/marvell/octeontx2/af/rvu.c | 12 ++- .../mellanox/mlx5/core/diag/fw_tracer.c | 3 +- .../ethernet/mellanox/mlx5/core/en/rep/tc.c | 3 - .../net/ethernet/mellanox/mlx5/core/fs_core.c | 5 +- .../ethernet/netronome/nfp/flower/offload.c | 3 - drivers/net/ethernet/qlogic/qed/qed_mcp.c | 6 +- .../net/ethernet/qlogic/qlcnic/qlcnic_init.c | 1 - drivers/net/ethernet/rdc/r6040.c | 9 ++- drivers/net/ethernet/renesas/sh_eth.c | 1 + drivers/net/ipa/ipa_table.c | 3 +- drivers/net/phy/dp83640_reg.h | 2 +- drivers/net/usb/cdc_mbim.c | 5 ++ drivers/net/usb/hso.c | 11 ++- drivers/ntb/test/ntb_msi_test.c | 4 +- drivers/ntb/test/ntb_perf.c | 1 + drivers/nvme/host/tcp.c | 20 ++--- drivers/pci/controller/cadence/pci-j721e.c | 61 ++++++++++++-- .../pci/controller/cadence/pcie-cadence-ep.c | 4 + .../controller/cadence/pcie-cadence-host.c | 3 + drivers/pci/controller/cadence/pcie-cadence.c | 16 ++++ drivers/pci/controller/cadence/pcie-cadence.h | 17 +++- drivers/pci/controller/dwc/pcie-tegra194.c | 32 ++++---- drivers/pci/controller/pci-tegra.c | 13 +-- drivers/pci/controller/pcie-iproc-bcma.c | 16 ++-- drivers/pci/controller/pcie-rcar-ep.c | 4 +- drivers/pci/hotplug/TODO | 3 - drivers/pci/hotplug/ibmphp_ebda.c | 5 +- drivers/pci/of.c | 2 +- drivers/pci/pci.c | 2 +- drivers/pci/quirks.c | 58 +++++++++++++- drivers/s390/char/sclp_early.c | 3 +- drivers/vhost/net.c | 11 ++- drivers/video/backlight/ktd253-backlight.c | 75 ++++++++++++----- drivers/watchdog/watchdog_dev.c | 5 +- fs/btrfs/disk-io.c | 45 ++++++----- fs/fuse/dev.c | 4 +- include/linux/memory_hotplug.h | 4 +- include/linux/pci.h | 5 +- include/linux/pci_ids.h | 3 +- include/linux/sched.h | 1 + include/linux/skbuff.h | 2 +- include/uapi/linux/pkt_sched.h | 2 + kernel/events/core.c | 2 +- kernel/trace/trace_boot.c | 15 ++-- kernel/trace/trace_kprobe.c | 6 +- kernel/trace/trace_probe.c | 25 ++++++ kernel/trace/trace_probe.h | 1 + kernel/trace/trace_uprobe.c | 6 +- mm/memory_hotplug.c | 4 +- net/caif/chnl_net.c | 19 +---- net/dccp/minisocks.c | 2 + net/dsa/slave.c | 12 ++- net/dsa/tag_rtl4_a.c | 7 +- net/ethtool/ioctl.c | 2 +- net/ipv4/ip_gre.c | 9 ++- net/ipv4/nexthop.c | 2 + net/ipv4/tcp_input.c | 2 +- net/ipv4/udp_tunnel_nic.c | 2 +- net/ipv6/netfilter/nf_socket_ipv6.c | 4 +- net/l2tp/l2tp_core.c | 4 +- net/netfilter/nf_conntrack_proto_dccp.c | 1 + net/netfilter/nf_tables_api.c | 1 + net/netfilter/nft_ct.c | 10 ++- net/sched/sch_fq_codel.c | 12 ++- net/tipc/socket.c | 10 ++- net/unix/af_unix.c | 2 +- scripts/clang-tools/gen_compile_commands.py | 1 + tools/perf/Makefile.config | 8 +- tools/perf/bench/inject-buildid.c | 52 +++++++----- tools/perf/util/machine.c | 1 + tools/testing/selftests/net/altnames.sh | 2 +- .../selftests/net/mptcp/simult_flows.sh | 4 +- 118 files changed, 853 insertions(+), 393 deletions(-) -- 2.20.1

1 118

[PATCH openEuler-21.03 00/20] openEuler kernel 21.03创新版本
by Wang ShaoBo 21 Oct '21

21 Oct '21

openEuler kernel 21.03创新版本补丁 Alexander Kuznetsov (1): cgroup1: don't allow '\n' in renaming Andy Shevchenko (1): usb: typec: intel_pmc_mux: Put fwnode in error case during ->probe() Anna Schumaker (1): NFS: Fix use-after-free in nfs4_init_client() Desmond Cheong Zhi Xi (1): drm: Fix use-after-free read in drm_getunique() Eric Farman (2): vfio-ccw: Reset FSM state to IDLE inside FSM vfio-ccw: Serialize FSM IDLE state with I/O completion Jeremy Szu (1): ALSA: hda/realtek: fix mute/micmute LEDs for HP EliteBook 840 Aero G8 Jerome Brunet (1): ASoC: meson: gx-card: fix sound-dai dt schema Johannes Berg (1): netlink: disable IRQs for netlink_lock_table() Li Jun (1): usb: typec: tcpm: cancel vdm and state machine hrtimer when unregister tcpm port Linus Walleij (1): drm/mcde: Fix off by 10^3 in calculation Maciej Żenczykowski (1): usb: f_ncm: only first packet of aggregate needs to start timer Saravana Kannan (1): spi: Fix spi device unregister flow Tiezhu Yang (1): MIPS: Fix kernel hang under FUNCTION_GRAPH_TRACER and PREEMPT_TRACER Trond Myklebust (1): NFSv4: Fix second deadlock in nfs4_evict_inode() Vincent Guittot (1): sched/fair: Keep load_avg and load_sum synced Wesley Cheng (1): usb: dwc3: gadget: Disable gadget IRQ during pullup disable Wolfram Sang (1): mmc: renesas_sdhi: abort tuning when timeout detected Zhen Lei (1): tools/bootconfig: Fix error return code in apply_xbc() Zou Wei (1): ASoC: sti-sas: add missing MODULE_DEVICE_TABLE .../bindings/sound/amlogic,gx-sound-card.yaml | 4 ++-- arch/mips/lib/mips-atomic.c | 12 ++++++------ drivers/gpu/drm/drm_ioctl.c | 9 +++++---- drivers/gpu/drm/mcde/mcde_dsi.c | 2 +- drivers/mmc/host/renesas_sdhi_core.c | 7 ++++++- drivers/s390/cio/vfio_ccw_drv.c | 12 ++++++++++-- drivers/s390/cio/vfio_ccw_fsm.c | 1 + drivers/s390/cio/vfio_ccw_ops.c | 2 -- drivers/spi/spi.c | 18 ++++++++++++------ drivers/usb/dwc3/gadget.c | 11 +++++------ drivers/usb/gadget/function/f_ncm.c | 8 ++++---- drivers/usb/typec/mux/intel_pmc_mux.c | 4 +++- drivers/usb/typec/tcpm/tcpm.c | 3 +++ fs/nfs/nfs4client.c | 2 +- fs/nfs/nfs4proc.c | 9 +++++++-- kernel/cgroup/cgroup-v1.c | 4 ++++ kernel/sched/fair.c | 11 +++++------ net/netlink/af_netlink.c | 6 ++++-- sound/pci/hda/patch_realtek.c | 1 + sound/soc/codecs/sti-sas.c | 1 + tools/bootconfig/main.c | 1 + 21 files changed, 82 insertions(+), 46 deletions(-) -- 2.25.1

2 21

[openEuler-5.10 000/303] Backport LTS 5.10.67
by Zheng Zengkai 21 Oct '21

21 Oct '21

Backport LTS 5.10.67 patches from upstream. Ahmad Fatoum (1): clk: imx8m: fix clock tree update of TF-A managed clocks Alexey Kardashevskiy (1): KVM: PPC: Fix clearing never mapped TCEs in realmode Alim Akhtar (1): scsi: ufs: ufs-exynos: Fix static checker warning Alyssa Rosenzweig (3): drm/panfrost: Simplify lock_region calculation drm/panfrost: Use u64 for size in lock_region drm/panfrost: Clamp lock region to Bifrost minimum Amir Goldstein (1): fanotify: limit number of event merge attempts Andreas Obergschwandtner (1): ARM: tegra: tamonten: Fix UART pad setting Andrey Grodzovsky (1): drm/amdgpu: Fix BUG_ON assert Andy Shevchenko (1): ata: sata_dwc_460ex: No need to call phy_exit() befre phy_init() AngeloGioacchino Del Regno (2): arm64: dts: qcom: sdm630: Rewrite memory map arm64: dts: qcom: sdm630: Fix TLMM node and pinctrl configuration Ani Sinha (1): x86/hyperv: fix for unwanted manipulation of sched_clock when TSC marked unstable Anirudh Rayabharam (1): usbip: give back URBs for unsent unlink requests during cleanup Anna Schumaker (1): sunrpc: Fix return value of get_srcport() Anson Jacob (1): drm/amd/amdgpu: Update debugfs link_settings output link_rate field in hex Anthony Iliopoulos (1): dma-debug: fix debugfs initialization order Arnd Bergmann (2): ethtool: improve compat ioctl handling m68knommu: only set CONFIG_ISA_DMA_API for ColdFire sub-arch Arne Welzel (1): dm crypt: Avoid percpu_counter spinlock contention in crypt_page_alloc() Aurabindo Pillai (1): drm/amd/display: Update number of DCN3 clock states Bart Van Assche (1): scsi: ufs: Fix memory corruption by ufshcd_read_desc_param() Bob Peterson (2): gfs2: Fix glock recursion in freeze_go_xmote_bh gfs2: Don't call dlm after protocol is unmounted Boris Brezillon (1): drm/panfrost: Make sure MMU context lifetime is not bound to panfrost_priv Brandon Wyman (1): hwmon: (pmbus/ibm-cffps) Fix write bits for LED control Brijesh Singh (1): crypto: ccp - shutdown SEV firmware on kexec Cezary Rojewski (1): ASoC: Intel: Skylake: Fix module configuration for KPB and MIXER Chao Yu (5): f2fs: fix to do sanity check for sb/cp fields correctly f2fs: quota: fix potential deadlock f2fs: fix to account missing .skipped_gc_rwsem f2fs: fix unexpected ENOENT comes from f2fs_map_blocks() f2fs: fix to unmap pages from userspace process in punch_hole() Chengfeng Ye (1): selftests/bpf: Fix potential unreleased lock Chin-Yen Lee (2): rtw88: use read_poll_timeout instead of fixed sleep rtw88: wow: fix size access error of probe request Chris Chiu (1): rtl8xxxu: Fix the handling of TX A-MPDU aggregation Christoph Hellwig (1): scsi: bsg: Remove support for SCSI_IOCTL_SEND_COMMAND Christophe JAILLET (1): staging: ks7010: Fix the initialization of the 'sleep_status' structure Codrin Ciubotariu (1): clk: at91: clk-generated: Limit the requested rate to our range Colin Ian King (3): ceph: fix dereference of null pointer cf scsi: BusLogic: Use %X for u32 sized integer rather than %lX parport: remove non-zero check on count Damien Le Moal (1): block: bfq: fix bfq_set_next_ioprio_data() Dan Carpenter (3): scsi: smartpqi: Fix an error code in pqi_get_raid_map() scsi: qedi: Fix error codes in qedi_alloc_global_queues() scsi: qedf: Fix error codes in qedf_alloc_global_queues() Darrick J. Wong (1): iomap: pass writeback errors to the mapping David Heidelberg (4): ARM: 9105/1: atags_to_fdt: don't warn about stack size ARM: dts: qcom: apq8064: correct clock names drm/msm: mdp4: drop vblank get/put from prepare/complete_commit drm/msi/mdp4: populate priv->kms in mdp4_kms_init David Howells (1): fscache: Fix cookie key hashing David Laight (1): fs/io_uring Don't use the return value from import_iovec(). Desmond Cheong Zhi Xi (8): btrfs: reset replace target device to allocation state on close drm: avoid blocking in drm_clients_info's rcu section drm: serialize drm_file.master with a new spinlock drm: protect drm_master pointers in drm_lease.c Bluetooth: skip invalid hci_sync_conn_complete_evt drm/vmwgfx: fix potential UAF in vmwgfx_surface.c Bluetooth: schedule SCO timeouts with delayed_work Bluetooth: avoid circular locks in sco_sock_connect Ding Hui (1): cifs: fix wrong release in sess_alloc_buffer() failed path Dinghao Liu (1): media: atomisp: Fix runtime PM imbalance in atomisp_pci_probe Dinh Nguyen (3): clk: socfpga: agilex: fix the parents of the psi_ref_clk clk: socfpga: agilex: fix up s2f_user0_clk representation clk: socfpga: agilex: add the bypass register for s2f_usr0 clock Dmitry Osipenko (2): rtc: tps65910: Correct driver module alias ARM: tegra: acer-a500: Remove bogus USB VBUS regulators Dmitry Torokhov (1): HID: input: do not report stylus battery state as "full" Dom Cobley (1): drm/vc4: hdmi: Set HD_CTL_WHOLSMP and HD_CTL_CHALIGN_SET Eli Cohen (1): net: Fix offloading indirect devices dependency on qdisc order creation Eran Ben Elisha (1): net/mlx5: Fix variable type to match 64bit Evan Wang (1): PCI: aardvark: Fix checking for PIO status Evgeny Novikov (3): USB: EHCI: ehci-mv: improve error handling in mv_ehci_enable() media: platform: stm32: unprepare clocks at handling errors in probe media: tegra-cec: Handle errors of clk_prepare_enable() Ezequiel Garcia (1): media: hantro: vp8: Move noisy WARN_ON to vpu_debug Fabiano Rosas (1): KVM: PPC: Book3S HV: Fix copy_tofrom_guest routines Gautham R. Shenoy (1): cpuidle: pseries: Fixup CEDE0 latency only for POWER10 onwards Geert Uytterhoeven (2): staging: board: Fix uninitialized spinlock when attaching genpd drm/bridge: nwl-dsi: Avoid potential multiplication overflow on 32-bit Georgi Djakov (1): arm64: dts: qcom: sm8250: Fix epss_l3 unit address Greg Kroah-Hartman (1): serial: 8250_pci: make setup_port() parameters explicitly unsigned Gustavo A. R. Silva (2): ipv4: ip_output.c: Fix out-of-bounds warning in ip_copy_addrs() flow_dissector: Fix out-of-bounds warnings Gustaw Lewandowski (1): ASoC: Intel: Skylake: Fix passing loadable flag for module Haimin Zhang (1): fix array-index-out-of-bounds in taprio_change Halil Pasic (1): s390/pv: fix the forcing of the swiotlb Hans Verkuil (1): media: v4l2-dv-timings.c: fix wrong condition in two for-loops Hans de Goede (3): libata: add ATA_HORKAGE_NO_NCQ_TRIM for Samsung 860 and 870 SSDs platform/x86: dell-smbios-wmi: Add missing kfree in error-exit from run_smbios_call ASoC: Intel: bytcr_rt5640: Move "Platform Clock" routes to the maps for the matching in-/output Harshvardhan Jha (1): 9p/xen: Fix end of loop tests for list_for_each_entry Heiko Carstens (1): s390/jump_label: print real address in a case of a jump label bug Hyun Kwon (1): PCI: xilinx-nwl: Enable the clock through CCF Ilan Peer (1): iwlwifi: mvm: Fix scan channel flags settings Iwona Winiarska (2): soc: aspeed: lpc-ctrl: Fix boundary check for mmap soc: aspeed: p2a-ctrl: Fix boundary check for mmap J. Bruce Fields (3): rpc: fix gss_svc_init cleanup on failure lockd: lockd server-side shouldn't set fl_ops nfsd: fix crash on LOCKT on reexported NFSv3 Jack Pham (1): usb: gadget: composite: Allow bMaxPower=0 if self-powered Jaegeuk Kim (2): f2fs: deallocate compressed pages when error happens f2fs: should put a page beyond EOF when preparing a write Jaehyoung Choi (1): pinctrl: samsung: Fix pinctrl bank pin count Jan Hoffmann (1): net: dsa: lantiq_gswip: fix maximum frame length Jason Gunthorpe (1): vfio: Use config not menuconfig for VFIO_NOIOMMU Jens Axboe (1): io-wq: fix wakeup race when adding new work Jernej Skrabec (1): arm64: dts: allwinner: h6: tanix-tx6: Fix regulator node names Jerry (Fangzhi) Zuo (1): drm/amd/display: Update bounding box states (v2) Jianjun Wang (1): PCI: Export pci_pio_to_address() for module use Jim Broadus (1): HID: i2c-hid: Fix Elan touchpad regression Jiri Slaby (2): xtensa: ISS: don't panic in rs_init hvsi: don't panic on tty_register_driver failure Joel Stanley (1): powerpc/config: Renable MTD_PHYSMAP_OF Johan Almbladh (3): bpf/tests: Fix copy-and-paste error in double word test bpf/tests: Do not PASS tests without actually testing the result mac80211: Fix monitor MTU limit so that A-MSDUs get through Johannes Berg (4): iwlwifi: pcie: free RBs during configure iwlwifi: mvm: avoid static queue number aliasing iwlwifi: mvm: fix access to BSS elements iwlwifi: fw: correctly limit to monitor dump Jonathan Cameron (1): iio: dac: ad5624r: Fix incorrect handling of an optional regulator. Josef Bacik (1): btrfs: wake up async_delalloc_pages waiters after submit Joseph Gates (1): wcn36xx: Ensure finish scan is not requested before start scan Juergen Gross (1): xen: fix setting of max_pfn in shared_info Juhee Kang (1): samples: bpf: Fix tracex7 error raised on the missing argument Julian Wiedmann (2): s390/qdio: fix roll-back after timeout on ESTABLISH ccw s390/qdio: cancel the ESTABLISH ccw after timeout Jussi Maki (1): selftests/bpf: Fix xdp_tx.c prog section name Kajol Jain (1): powerpc/perf/hv-gpci: Fix counter value parsing Kees Cook (2): staging: rts5208: Fix get_ms_information() heap buffer size lib/test_stackinit: Fix static initializer test Kelly Devilliv (2): usb: host: fotg210: fix the endpoint's transactional opportunities calculation usb: host: fotg210: fix the actual_length of an iso packet Konrad Dybcio (1): drm/msm/dsi: Fix DSI and DSI PHY regulator config from SDM660 Krzysztof Hałasa (1): media: TDA1997x: fix tda1997x_query_dv_timings() return value Krzysztof Kozlowski (1): power: supply: max17042: handle fails of reading status register Krzysztof Wilczyński (1): PCI: Return ~0 data on pciconfig_read() CAP_SYS_ADMIN failure Kuogee Hsieh (1): drm/msm/dp: return correct edid checksum after corrupted edid checksum read Laurent Dufour (1): powerpc/numa: Consider the max NUMA node for migratable LPAR Laurent Pinchart (1): media: imx258: Rectify mismatch of VTS value Laurentiu Tudor (1): bus: fsl-mc: fix mmio base address for child DPRCs Leon Romanovsky (4): RDMA/iwcm: Release resources if iw_cm module initialization fails docs: Fix infiniband uverbs minor number RDMA/efa: Remove double QP type assignment RDMA/mlx5: Delete not-available udata check Li Jun (1): usb: chipidea: host: fix port index underflow and UBSAN complains Li Zhijian (2): selftests/bpf: Enlarge select() timeout for test_maps mm/hmm: bypass devmap pte when all pfn requested flags are fulfilled Liu Zixian (1): mm/hugetlb: initialize hugetlb_usage in mm_init Loic Poulain (1): wcn36xx: Fix missing frame timestamp for beacon/probe-resp Lu Baolu (1): iommu/vt-d: Update the virtual command related registers Luben Tuikov (1): drm/amdgpu: Fix amdgpu_ras_eeprom_init() Luiz Augusto von Dentz (1): Bluetooth: Fix handling of LE Enhanced Connection Complete Luke Hsiao (1): tcp: enable data-less, empty-cookie SYN with TFO_SERVER_COOKIE_NOT_REQD Maciej W. Rozycki (2): serial: 8250: Define RX trigger levels for OxSemi 950 devices scsi: BusLogic: Fix missing pr_cont() use Maciej Żenczykowski (1): usb: gadget: u_ether: fix a potential null pointer dereference Manish Narani (2): mmc: sdhci-of-arasan: Modified SD default speed to 19MHz for ZynqMP mmc: sdhci-of-arasan: Check return value of non-void funtions Manivannan Sadhasivam (1): soc: qcom: aoss: Fix the out of bound usage of cooling_devs Marc Zyngier (2): pinctrl: stmfx: Fix hazardous u8[] to unsigned long cast of: Don't allow __of_attached_node_sysfs() without CONFIG_SYSFS Marcos Paulo de Souza (1): btrfs: tree-log: check btrfs_lookup_data_extent return value Marek Behún (2): PCI: Restrict ASMedia ASM1062 SATA Max Payload Size Supported pinctrl: armada-37xx: Correct PWM pins definitions Marek Marczykowski-Górecki (1): PCI/MSI: Skip masking MSI-X on Xen PV Marek Vasut (4): net: phy: Fix data type in DP83822 dp8382x_disable_wol() ARM: dts: stm32: Set {bitclock,frame}-master phandles on DHCOM SoM ARM: dts: stm32: Set {bitclock,frame}-master phandles on ST DKx ARM: dts: stm32: Update AV96 adv7513 node per dtbs_check Mark Brown (2): kselftest/arm64: mte: Fix misleading output when skipping tests kselftest/arm64: pac: Fix skipping of tests on systems without PAC Mark Rutland (1): arm64: head: avoid over-mapping in map_memory Martynas Pumputis (2): libbpf: Fix reuse of pinned map on older kernel libbpf: Fix race when pinning maps in parallel Masahiro Yamada (1): kbuild: Fix 'no symbols' warning when CONFIG_TRIM_UNUSD_KSYMS=y Mathias Nyman (1): Revert "USB: xhci: fix U1/U2 handling for hardware with XHCI_INTEL_HOST quirk set" Mauro Carvalho Chehab (2): media: uvc: don't do DMA on stack media: dib8000: rewrite the init prbs logic Miaoqing Pan (1): ath9k: fix sleeping in atomic context Michal Suchanek (1): powerpc/stacktrace: Include linux/delay.h Mike Kravetz (1): hugetlb: fix hugetlb cgroup refcounting during vma split Mike Marciniszyn (1): IB/hfi1: Adjust pkey entry in index 0 Mikulas Patocka (1): parisc: fix crash with signals and alloca Nadav Amit (1): userfaultfd: prevent concurrent API initialization Nadezda Lutovinova (1): usb: musb: musb_dsps: request_irq() after initializing musb Nathan Chancellor (3): cpuidle: pseries: Mark pseries_idle_proble() as __init net: ethernet: stmmac: Do not use unreachable() in ipq806x_gmac_probe() drm/exynos: Always initialize mapping in exynos_drm_register_dma() Nicholas Piggin (1): KVM: PPC: Book3S HV Nested: Reflect guest PMU in-use to L0 when guest SPRs are live Nicolas Ferre (1): ARM: dts: at91: use the right property for shutdown controller Niklas Cassel (2): blk-zoned: allow zone management send operations without CAP_SYS_ADMIN blk-zoned: allow BLKREPORTZONE without CAP_SYS_ADMIN Niklas Schnelle (1): s390: make PCI mio support a machine flag Niklas Söderlund (1): nfp: fix return statement in nfp_net_parse_meta() Nishad Kamdar (1): mmc: core: Return correct emmc response in case of ioctl error Nuno Sá (1): iio: ltc2983: fix device probe Oak Zeng (1): drm/amdgpu: Fix a printing message Oleksij Rempel (1): MIPS: Malta: fix alignment of the devicetree buffer Olga Kornievskaia (1): SUNRPC query transport's source port Oliver Logush (1): drm/amd/display: Fix timer_per_pixel unit error Pali Rohár (2): PCI: aardvark: Configure PCIe resources from 'ranges' DT property PCI: aardvark: Fix masking and unmasking legacy INTx interrupts Patryk Duda (1): platform/chrome: cros_ec_proto: Send command again when timeout occurs Paul Cercueil (1): pinctrl: ingenic: Fix incorrect pull up/down info Pavel Begunkov (5): io_uring: limit fixed table size by RLIMIT_NOFILE io_uring: place fixed tables under memcg limits io_uring: add ->splice_fd_in checks io_uring: fail links of cancelled timeouts io_uring: remove duplicated io_size from rw Peter Geis (1): clk: rockchip: drop GRF dependency for rk3328/rk3036 pll types Pierre-Louis Bossart (2): ASoC: Intel: update sof_pcm512x quirks soundwire: intel: fix potential race condition during power down Ping-Ke Shih (1): rtw88: wow: build wow function only if CONFIG_PM is on Pratik R. Sampat (1): cpufreq: powernv: Fix init_chip_info initialization in numa=off Quanyang Wang (2): drm: xlnx: zynqmp_dpsub: Call pm_runtime_get_sync before setting pixel clock drm: xlnx: zynqmp: release reset to DP controller before accessing DP registers Raag Jadav (1): arm64: dts: ls1046a: fix eeprom entries Rafael J. Wysocki (1): PCI: Use pci_update_current_state() in pci_enable_device_flags() Rajendra Nayak (2): nvmem: qfprom: Fix up qfprom_disable_fuse_blowing() ordering opp: Don't print an error if required-opps is missing Rajkumar Subbiah (1): drm/dp_mst: Fix return code on sideband message failure Randy Dunlap (2): openrisc: don't printk() unconditionally ASoC: atmel: ATMEL drivers don't need HAS_DMA Rik van Riel (1): mm,vmscan: fix divide by zero in get_scan_count Robin Gong (2): Revert "dmaengine: imx-sdma: refine to load context only once" dmaengine: imx-sdma: remove duplicated sdma_load_context Rolf Eike Beer (1): tools/thermal/tmon: Add cross compiling support Roy Chan (2): drm/amd/display: fix missing writeback disablement if plane is removed drm/amd/display: fix incorrect CM/TF programming sequence in dwb Sagi Grimberg (2): nvme-tcp: don't check blk_mq_tag_to_rq when receiving pdu data nvme: code command_id with a genctr for use-after-free validation Sanjay R Mehta (1): thunderbolt: Fix port linking by checking all adapters Sasha Neftin (1): igc: Check if num of q_vectors is smaller than max before array access Saurav Kashyap (2): scsi: qla2xxx: Changes to support kdump kernel scsi: qla2xxx: Sync queue idx with queue_pair_map idx Sean Anderson (1): crypto: mxs-dcp - Use sg_mapping_iter to copy data Sean Keely (1): drm/amdkfd: Account for SH/SE count when setting up cu masks. Sean Young (1): media: rc-loopback: return number of emitters rather than error Sebastian Reichel (1): ARM: dts: imx53-ppd: Fix ACHC entry Shuah Khan (2): selftests: firmware: Fix ignored return val of asprintf() warn usbip:vhci_hcd USB port can get stuck in the disabled state Srikar Dronamraju (1): powerpc/smp: Update cpu_core_map on all PowerPc systems Stefan Assmann (2): iavf: do not override the adapter state in the watchdog task iavf: fix locking of critical sections Steven Rostedt (VMware) (1): selftests/ftrace: Fix requirement check of README file Stuart Hayes (1): PCI/portdrv: Enable Bandwidth Notification only if port supports it Subbaraya Sundeep (1): octeontx2-pf: Fix NIX1_RX interface backpressure Sugar Zhang (1): ASoC: rockchip: i2s: Fix regmap_ops hang Thierry Reding (1): arm64: tegra: Fix compatible string for Tegra132 CPUs Thomas Hebb (1): mmc: rtsx_pci: Fix long reads when clock is prescaled Thomas Zimmermann (1): drm/mgag200: Select clock in PLL update functions Tianjia Zhang (1): Smack: Fix wrong semantics in smk_access_entry() Tony Lindgren (1): serial: 8250_omap: Handle optional overrun-throttle-ms property Trond Myklebust (5): NFSv4/pNFS: Fix a layoutget livelock loop NFSv4/pNFS: Always allow update of a zero valued layout barrier NFSv4/pnfs: The layout barrier indicate a minimal value for the seqid SUNRPC: Fix potential memory corruption SUNRPC/xprtrdma: Fix reconnection locking Tuo Li (2): gpu: drm: amd: amdgpu: amdgpu_i2c: fix possible uninitialized-variable access in amdgpu_i2c_router_select_ddc_port() drm/display: fix possible null-pointer dereference in dcn10_set_clock() Ulrich Hecht (1): serial: sh-sci: fix break handling for sysrq Umang Jain (1): media: imx258: Limit the max analogue gain to 480 Vidya Sagar (1): arm64: tegra: Fix Tegra194 PCIe EP compatible string Vinod Koul (6): arm64: dts: qcom: ipq8074: fix pci node reg property arm64: dts: qcom: sdm660: use reg value for memory node arm64: dts: qcom: ipq6018: drop '0x' from unit address arm64: dts: qcom: sdm630: don't use underscore in node name arm64: dts: qcom: msm8994: don't use underscore in node name arm64: dts: qcom: msm8996: don't use underscore in node name Wang Hai (1): VMCI: fix NULL pointer dereference when unmapping queue pair Wei Li (1): scsi: fdomain: Fix error return code in fdomain_probe() Wenpeng Liang (1): RDMA/hns: Fix QP's resp incomplete assignment Wentao_Liang (1): net/mlx5: DR, fix a potential use-after-free bug Will Deacon (1): arm64: mm: Fix TLBI vs ASID rollover Xiaotan Luo (1): ASoC: rockchip: i2s: Fixup config for DAIFMT_DSP_A/B Xin Long (1): tipc: keep the skb in rcv queue until the whole data is read Yajun Deng (1): netlink: Deal with ESRCH error in nlmsg_notify() Yang Yingliang (2): media: atomisp: pci: fix error return code in atomisp_pci_probe() net: w5100: check return value after calling platform_get_resource() Yangtao Li (1): f2fs: reduce the scope of setting fsck tag when de->name_len is zero Yevgeny Kliteynik (1): net/mlx5: DR, Enable QP retransmission Yonghong Song (1): selftests/bpf: Fix flaky send_signal test Yongqiang Niu (1): soc: mediatek: cmdq: add address shift in jump Yufeng Mo (1): bonding: 3ad: fix the concurrency between __bond_release_one() and bond_3ad_state_machine_handler() Zekun Shen (1): ath9k: fix OOB read ar9300_eeprom_restore_internal Zhang Qilong (1): iwlwifi: mvm: fix a memory leak in iwl_mvm_mac_ctxt_beacon_changed Zhaoyu Liu (1): pinctrl: remove empty lines in pinctrl subsystem Zhen Lei (2): pinctrl: single: Fix error return code in pcs_parse_bits_in_pinctrl_entry() workqueue: Fix possible memory leaks in wq_numa_init() Zheyu Ma (5): video: fbdev: kyro: fix a DoS bug by restricting user input tty: serial: jsm: hold port lock when reporting modem line changes video: fbdev: asiliantfb: Error out if 'pixclock' equals zero video: fbdev: kyro: Error out if 'pixclock' equals zero video: fbdev: riva: Error out if 'pixclock' equals zero Zhouyi Zhou (1): rcu: Fix macro name CONFIG_TASKS_RCU_TRACE chenying (1): ovl: fix BUG_ON() in may_delete() when called from ovl_cleanup() sumiyawang (1): libnvdimm/pmem: Fix crash triggered when I/O in-flight during unbind zhenwei pi (1): crypto: public_key: fix overflow during implicit conversion 王贇 (1): net: fix NULL pointer reference in cipso_v4_doi_free Documentation/admin-guide/devices.txt | 6 +- .../pinctrl/marvell,armada-37xx-pinctrl.txt | 8 +- arch/arm/boot/compressed/Makefile | 2 + arch/arm/boot/dts/at91-kizbox3_common.dtsi | 2 +- arch/arm/boot/dts/at91-sam9x60ek.dts | 2 +- arch/arm/boot/dts/at91-sama5d27_som1_ek.dts | 2 +- arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts | 2 +- arch/arm/boot/dts/at91-sama5d2_icp.dts | 2 +- arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts | 2 +- arch/arm/boot/dts/at91-sama5d2_xplained.dts | 2 +- arch/arm/boot/dts/imx53-ppd.dts | 23 +- arch/arm/boot/dts/qcom-apq8064.dtsi | 6 +- arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi | 8 +- .../boot/dts/stm32mp15xx-dhcor-avenger96.dtsi | 6 +- arch/arm/boot/dts/stm32mp15xx-dkx.dtsi | 8 +- .../boot/dts/tegra20-acer-a500-picasso.dts | 25 +- arch/arm/boot/dts/tegra20-tamonten.dtsi | 14 +- .../dts/allwinner/sun50i-h6-tanix-tx6.dts | 4 +- .../boot/dts/freescale/fsl-ls1046a-frwy.dts | 8 +- .../boot/dts/freescale/fsl-ls1046a-rdb.dts | 7 +- arch/arm64/boot/dts/nvidia/tegra132.dtsi | 4 +- arch/arm64/boot/dts/nvidia/tegra194.dtsi | 6 +- arch/arm64/boot/dts/qcom/ipq6018.dtsi | 2 +- arch/arm64/boot/dts/qcom/ipq8074-hk01.dts | 2 +- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 16 +- arch/arm64/boot/dts/qcom/msm8994.dtsi | 6 +- arch/arm64/boot/dts/qcom/msm8996.dtsi | 4 +- arch/arm64/boot/dts/qcom/sdm630.dtsi | 257 ++++++++++------- arch/arm64/boot/dts/qcom/sm8250.dtsi | 2 +- arch/arm64/include/asm/kernel-pgtable.h | 4 +- arch/arm64/include/asm/mmu.h | 29 +- arch/arm64/include/asm/tlbflush.h | 11 +- arch/arm64/kernel/head.S | 11 +- arch/m68k/Kconfig.bus | 2 +- arch/mips/mti-malta/malta-dtshim.c | 2 +- arch/openrisc/kernel/entry.S | 2 + arch/parisc/kernel/signal.c | 6 + arch/powerpc/configs/mpc885_ads_defconfig | 1 + arch/powerpc/include/asm/pmc.h | 7 + arch/powerpc/kernel/smp.c | 11 +- arch/powerpc/kernel/stacktrace.c | 1 + arch/powerpc/kvm/book3s_64_mmu_radix.c | 6 +- arch/powerpc/kvm/book3s_64_vio_hv.c | 9 +- arch/powerpc/kvm/book3s_hv.c | 20 ++ arch/powerpc/mm/numa.c | 13 +- arch/powerpc/perf/hv-gpci.c | 2 +- arch/s390/include/asm/setup.h | 2 + arch/s390/kernel/early.c | 4 + arch/s390/kernel/jump_label.c | 2 +- arch/s390/mm/init.c | 2 +- arch/s390/pci/pci.c | 5 +- arch/x86/kernel/cpu/mshyperv.c | 9 +- arch/x86/xen/p2m.c | 4 +- arch/xtensa/platforms/iss/console.c | 17 +- block/bfq-iosched.c | 2 +- block/blk-zoned.c | 6 - block/bsg.c | 5 +- drivers/ata/libata-core.c | 4 + drivers/ata/sata_dwc_460ex.c | 12 +- drivers/bus/fsl-mc/fsl-mc-bus.c | 24 +- drivers/clk/at91/clk-generated.c | 6 + drivers/clk/imx/clk-composite-8m.c | 3 +- drivers/clk/imx/clk-imx8mm.c | 7 +- drivers/clk/imx/clk-imx8mn.c | 7 +- drivers/clk/imx/clk-imx8mq.c | 7 +- drivers/clk/imx/clk.h | 16 +- drivers/clk/rockchip/clk-pll.c | 2 +- drivers/clk/socfpga/clk-agilex.c | 19 +- drivers/cpufreq/powernv-cpufreq.c | 16 +- drivers/cpuidle/cpuidle-pseries.c | 18 +- drivers/crypto/ccp/sev-dev.c | 49 ++-- drivers/crypto/ccp/sp-pci.c | 12 + drivers/crypto/mxs-dcp.c | 36 +-- drivers/dma/imx-sdma.c | 13 +- drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +- .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 2 +- drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 2 +- drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c | 84 ++++-- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h | 1 + .../amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 16 +- .../amd/display/dc/dcn10/dcn10_hw_sequencer.c | 11 +- .../drm/amd/display/dc/dcn20/dcn20_hwseq.c | 14 +- .../drm/amd/display/dc/dcn20/dcn20_resource.c | 2 +- .../drm/amd/display/dc/dcn30/dcn30_dwb_cm.c | 90 ++++-- .../drm/amd/display/dc/dcn30/dcn30_hwseq.c | 12 +- .../drm/amd/display/dc/dcn30/dcn30_resource.c | 42 ++- drivers/gpu/drm/bridge/nwl-dsi.c | 2 +- drivers/gpu/drm/drm_auth.c | 42 ++- drivers/gpu/drm/drm_debugfs.c | 3 +- drivers/gpu/drm/drm_dp_mst_topology.c | 10 +- drivers/gpu/drm/drm_file.c | 1 + drivers/gpu/drm/drm_lease.c | 81 ++++-- drivers/gpu/drm/exynos/exynos_drm_dma.c | 2 + drivers/gpu/drm/mgag200/mgag200_drv.h | 16 ++ drivers/gpu/drm/mgag200/mgag200_mode.c | 20 +- drivers/gpu/drm/mgag200/mgag200_reg.h | 9 +- drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c | 17 +- drivers/gpu/drm/msm/dp/dp_panel.c | 9 +- drivers/gpu/drm/msm/dsi/dsi_cfg.c | 1 - drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c | 2 +- drivers/gpu/drm/panfrost/panfrost_device.h | 8 +- drivers/gpu/drm/panfrost/panfrost_drv.c | 50 +--- drivers/gpu/drm/panfrost/panfrost_gem.c | 20 +- drivers/gpu/drm/panfrost/panfrost_job.c | 4 +- drivers/gpu/drm/panfrost/panfrost_mmu.c | 191 ++++++++----- drivers/gpu/drm/panfrost/panfrost_mmu.h | 5 +- drivers/gpu/drm/panfrost/panfrost_regs.h | 2 + drivers/gpu/drm/vc4/vc4_hdmi.c | 4 +- drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 4 +- drivers/gpu/drm/xlnx/zynqmp_disp.c | 3 +- drivers/gpu/drm/xlnx/zynqmp_dp.c | 22 +- drivers/hid/hid-input.c | 2 - drivers/hid/i2c-hid/i2c-hid-core.c | 5 +- drivers/hwmon/pmbus/ibm-cffps.c | 6 +- drivers/iio/dac/ad5624r_spi.c | 18 +- drivers/iio/temperature/ltc2983.c | 30 +- drivers/infiniband/core/iwcm.c | 19 +- drivers/infiniband/hw/efa/efa_verbs.c | 1 - drivers/infiniband/hw/hfi1/init.c | 7 +- drivers/infiniband/hw/hns/hns_roce_qp.c | 3 +- drivers/infiniband/hw/mlx5/qp.c | 3 - drivers/iommu/intel/pasid.h | 10 +- drivers/mailbox/mtk-cmdq-mailbox.c | 3 +- drivers/md/dm-crypt.c | 7 +- drivers/media/cec/platform/stm32/stm32-cec.c | 26 +- drivers/media/cec/platform/tegra/tegra_cec.c | 10 +- drivers/media/dvb-frontends/dib8000.c | 58 ++-- drivers/media/i2c/imx258.c | 4 +- drivers/media/i2c/tda1997x.c | 5 +- drivers/media/rc/rc-loopback.c | 2 +- drivers/media/usb/uvc/uvc_v4l2.c | 34 ++- drivers/media/v4l2-core/v4l2-dv-timings.c | 4 +- drivers/misc/vmw_vmci/vmci_queue_pair.c | 6 +- drivers/mmc/core/block.c | 3 +- drivers/mmc/host/rtsx_pci_sdmmc.c | 36 ++- drivers/mmc/host/sdhci-of-arasan.c | 36 ++- drivers/net/bonding/bond_main.c | 3 +- drivers/net/dsa/lantiq_gswip.c | 3 +- drivers/net/ethernet/intel/iavf/iavf_main.c | 58 +++- drivers/net/ethernet/intel/igc/igc_main.c | 9 +- .../marvell/octeontx2/nic/otx2_common.c | 15 + drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 8 +- .../mellanox/mlx5/core/steering/dr_rule.c | 2 +- .../mellanox/mlx5/core/steering/dr_send.c | 1 + .../ethernet/netronome/nfp/nfp_net_common.c | 2 +- .../ethernet/stmicro/stmmac/dwmac-ipq806x.c | 18 +- drivers/net/ethernet/wiznet/w5100.c | 2 + drivers/net/phy/dp83822.c | 8 +- .../net/wireless/ath/ath9k/ar9003_eeprom.c | 3 +- drivers/net/wireless/ath/ath9k/hw.c | 12 +- drivers/net/wireless/ath/wcn36xx/main.c | 5 +- drivers/net/wireless/ath/wcn36xx/txrx.c | 4 + drivers/net/wireless/ath/wcn36xx/wcn36xx.h | 1 + drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 2 +- .../net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 4 +- .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 8 +- drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 24 +- drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 30 +- drivers/net/wireless/intel/iwlwifi/pcie/rx.c | 5 +- .../net/wireless/intel/iwlwifi/pcie/trans.c | 3 + .../net/wireless/realtek/rtl8xxxu/rtl8xxxu.h | 2 + .../wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 33 ++- drivers/net/wireless/realtek/rtw88/Makefile | 2 +- drivers/net/wireless/realtek/rtw88/fw.c | 8 +- drivers/net/wireless/realtek/rtw88/fw.h | 1 + drivers/net/wireless/realtek/rtw88/wow.c | 21 +- drivers/nvdimm/pmem.c | 4 +- drivers/nvme/host/core.c | 3 +- drivers/nvme/host/nvme.h | 47 +++- drivers/nvme/host/pci.c | 2 +- drivers/nvme/host/rdma.c | 4 +- drivers/nvme/host/tcp.c | 38 +-- drivers/nvme/target/loop.c | 4 +- drivers/nvmem/qfprom.c | 6 +- drivers/of/kobj.c | 2 +- drivers/opp/of.c | 12 +- drivers/parport/ieee1284_ops.c | 2 +- drivers/pci/controller/pci-aardvark.c | 266 +++++++++++++++++- drivers/pci/controller/pcie-xilinx-nwl.c | 12 + drivers/pci/msi.c | 3 + drivers/pci/pci.c | 7 +- drivers/pci/pcie/portdrv_core.c | 9 +- drivers/pci/quirks.c | 1 + drivers/pci/syscall.c | 4 +- drivers/pinctrl/actions/pinctrl-owl.c | 1 - drivers/pinctrl/core.c | 1 - drivers/pinctrl/freescale/pinctrl-imx1-core.c | 1 - drivers/pinctrl/mvebu/pinctrl-armada-37xx.c | 17 +- drivers/pinctrl/pinctrl-at91.c | 1 - drivers/pinctrl/pinctrl-ingenic.c | 6 +- drivers/pinctrl/pinctrl-single.c | 1 + drivers/pinctrl/pinctrl-st.c | 1 - drivers/pinctrl/pinctrl-stmfx.c | 6 +- drivers/pinctrl/pinctrl-sx150x.c | 1 - drivers/pinctrl/qcom/pinctrl-sdm845.c | 1 - drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c | 1 - drivers/pinctrl/renesas/pfc-r8a77950.c | 1 - drivers/pinctrl/renesas/pfc-r8a77951.c | 1 - drivers/pinctrl/renesas/pfc-r8a7796.c | 1 - drivers/pinctrl/renesas/pfc-r8a77965.c | 1 - drivers/pinctrl/samsung/pinctrl-samsung.c | 2 +- drivers/platform/chrome/cros_ec_proto.c | 9 + drivers/platform/x86/dell-smbios-wmi.c | 1 + drivers/power/supply/max17042_battery.c | 6 +- drivers/rtc/rtc-tps65910.c | 2 +- drivers/s390/cio/qdio_main.c | 82 +++--- drivers/scsi/BusLogic.c | 6 +- drivers/scsi/pcmcia/fdomain_cs.c | 4 +- drivers/scsi/qedf/qedf_main.c | 10 +- drivers/scsi/qedi/qedi_main.c | 14 +- drivers/scsi/qla2xxx/qla_nvme.c | 5 +- drivers/scsi/qla2xxx/qla_os.c | 6 + drivers/scsi/smartpqi/smartpqi_init.c | 1 + drivers/scsi/ufs/ufs-exynos.c | 4 +- drivers/scsi/ufs/ufs-exynos.h | 2 +- drivers/scsi/ufs/ufshcd.c | 8 +- drivers/soc/aspeed/aspeed-lpc-ctrl.c | 2 +- drivers/soc/aspeed/aspeed-p2a-ctrl.c | 2 +- drivers/soc/qcom/qcom_aoss.c | 8 +- drivers/soundwire/intel.c | 23 +- drivers/staging/board/board.c | 7 +- drivers/staging/ks7010/ks7010_sdio.c | 2 +- .../staging/media/atomisp/pci/atomisp_v4l2.c | 4 +- .../staging/media/hantro/hantro_g1_vp8_dec.c | 13 +- .../media/hantro/rk3399_vpu_hw_vp8_dec.c | 13 +- drivers/staging/rts5208/rtsx_scsi.c | 10 +- drivers/thunderbolt/switch.c | 2 +- drivers/tty/hvc/hvsi.c | 19 +- drivers/tty/serial/8250/8250_omap.c | 25 +- drivers/tty/serial/8250/8250_pci.c | 2 +- drivers/tty/serial/8250/8250_port.c | 3 +- drivers/tty/serial/jsm/jsm_neo.c | 2 + drivers/tty/serial/jsm/jsm_tty.c | 3 + drivers/tty/serial/sh-sci.c | 7 +- drivers/usb/chipidea/host.c | 14 +- drivers/usb/gadget/composite.c | 8 +- drivers/usb/gadget/function/u_ether.c | 5 +- drivers/usb/host/ehci-mv.c | 23 +- drivers/usb/host/fotg210-hcd.c | 41 ++- drivers/usb/host/fotg210.h | 5 - drivers/usb/host/xhci.c | 24 +- drivers/usb/musb/musb_dsps.c | 13 +- drivers/usb/usbip/vhci_hcd.c | 32 ++- drivers/vfio/Kconfig | 2 +- drivers/video/fbdev/asiliantfb.c | 3 + drivers/video/fbdev/kyro/fbdev.c | 8 + drivers/video/fbdev/riva/fbdev.c | 3 + fs/btrfs/inode.c | 10 +- fs/btrfs/tree-log.c | 4 +- fs/btrfs/volumes.c | 3 + fs/ceph/caps.c | 3 + fs/cifs/sess.c | 2 +- fs/f2fs/compress.c | 12 +- fs/f2fs/data.c | 16 ++ fs/f2fs/dir.c | 14 +- fs/f2fs/file.c | 4 +- fs/f2fs/gc.c | 4 +- fs/f2fs/super.c | 106 ++++--- fs/fscache/cookie.c | 14 +- fs/fscache/internal.h | 2 + fs/fscache/main.c | 39 +++ fs/gfs2/glops.c | 17 +- fs/gfs2/lock_dlm.c | 5 + fs/io-wq.c | 8 +- fs/io_uring.c | 70 +++-- fs/iomap/buffered-io.c | 2 +- fs/lockd/svclock.c | 30 +- fs/nfs/pnfs.c | 16 +- fs/nfsd/nfs4state.c | 5 +- fs/notify/fanotify/fanotify.c | 6 + fs/overlayfs/dir.c | 6 +- fs/userfaultfd.c | 91 +++--- include/crypto/public_key.h | 4 +- include/drm/drm_auth.h | 1 + include/drm/drm_file.h | 18 +- include/linux/ethtool.h | 4 - include/linux/hugetlb.h | 9 + include/linux/hugetlb_cgroup.h | 12 + include/linux/intel-iommu.h | 6 +- include/linux/rcupdate.h | 2 +- include/linux/sunrpc/xprt.h | 1 + include/linux/sunrpc/xprtsock.h | 1 + include/net/flow_offload.h | 1 + include/uapi/linux/serial_reg.h | 1 + kernel/dma/debug.c | 7 +- kernel/fork.c | 1 + kernel/rcu/tree_plugin.h | 8 +- kernel/workqueue.c | 12 +- lib/test_bpf.c | 13 +- lib/test_stackinit.c | 20 +- mm/hmm.c | 5 +- mm/hugetlb.c | 4 +- mm/vmscan.c | 2 +- net/9p/trans_xen.c | 4 +- net/bluetooth/hci_event.c | 108 +++++-- net/bluetooth/sco.c | 74 +++-- net/core/flow_dissector.c | 12 +- net/core/flow_offload.c | 89 +++++- net/ethtool/ioctl.c | 136 +++++++-- net/ipv4/ip_output.c | 5 +- net/ipv4/tcp_fastopen.c | 3 +- net/mac80211/iface.c | 11 +- net/netfilter/nf_flow_table_offload.c | 1 + net/netfilter/nf_tables_offload.c | 1 + net/netlabel/netlabel_cipso_v4.c | 4 +- net/netlink/af_netlink.c | 4 +- net/sched/cls_api.c | 1 + net/sched/sch_taprio.c | 4 +- net/socket.c | 125 +------- net/sunrpc/auth_gss/svcauth_gss.c | 2 +- net/sunrpc/xprt.c | 8 +- net/sunrpc/xprtrdma/transport.c | 11 +- net/sunrpc/xprtsock.c | 7 + net/tipc/socket.c | 36 ++- samples/bpf/test_override_return.sh | 1 + samples/bpf/tracex7_user.c | 5 + scripts/gen_ksymdeps.sh | 8 +- security/smack/smack_access.c | 17 +- sound/soc/atmel/Kconfig | 1 - sound/soc/intel/boards/bytcr_rt5640.c | 9 +- sound/soc/intel/boards/sof_pcm512x.c | 13 +- sound/soc/intel/skylake/skl-messages.c | 11 +- sound/soc/intel/skylake/skl-pcm.c | 25 +- sound/soc/rockchip/rockchip_i2s.c | 35 ++- tools/lib/bpf/libbpf.c | 63 ++++- .../selftests/arm64/mte/mte_common_util.c | 2 +- tools/testing/selftests/arm64/pauth/pac.c | 10 +- .../selftests/bpf/prog_tests/send_signal.c | 16 ++ .../bpf/prog_tests/sockopt_inherit.c | 4 +- tools/testing/selftests/bpf/progs/xdp_tx.c | 2 +- tools/testing/selftests/bpf/test_maps.c | 2 +- tools/testing/selftests/bpf/test_xdp_veth.sh | 2 +- .../testing/selftests/firmware/fw_namespace.c | 3 +- .../testing/selftests/ftrace/test.d/functions | 2 +- tools/thermal/tmon/Makefile | 2 +- 340 files changed, 3158 insertions(+), 1635 deletions(-) -- 2.20.1

1 303

[openEuler-5.10 00/15] bugfix for mm/fs
by Zheng Zengkai 21 Oct '21

21 Oct '21

Backport bugfix patches for mm/fs from upstream. Ard Biesheuvel (1): arm64: mm: account for hotplug memory when randomizing the linear region Dan Carpenter (1): crypto: ccp - fix resource leaks in ccp_run_aes_gcm_cmd() Florian Fainelli (1): ARM: Qualify enabling of swiotlb_init() Guo Xuenan (3): Revert "compiler: remove CONFIG_OPTIMIZE_INLINING entirely" disable OPTIMIZE_INLINING by default make OPTIMIZE_INLINING config editable Johannes Weiner (1): mm: vmscan: fix missing psi annotation for node_reclaim() John Garry (1): blk-mq-sched: Fix blk_mq_sched_alloc_tags() error handling Lu Baolu (1): iommu/vt-d: Fix clearing real DMA device's scalable-mode context entries Piotr Krysiuk (1): bpf, mips: Validate conditional branch offsets Rafael Aquini (1): ipc: replace costly bailout check in sysvipc_find_ipc() Sanjay Kumar (1): iommu/vt-d: Global devTLB flush when present context entry changed Vlastimil Babka (1): mm: slub: fix slub_debug disabling for list of slabs Xu Kuohai (1): bpf: Fix integer overflow in prealloc_elems_and_freelist() yangerkun (1): ext4: flush s_error_work before journal destroy in ext4_fill_super arch/arm/mm/init.c | 6 +- arch/arm64/kvm/sys_regs.h | 5 ++ arch/arm64/mm/init.c | 13 +++-- arch/mips/net/bpf_jit.c | 57 ++++++++++++++----- arch/x86/configs/i386_defconfig | 1 + arch/x86/configs/x86_64_defconfig | 1 + block/blk-mq-sched.c | 19 ++----- drivers/crypto/ccp/ccp-ops.c | 14 +++-- .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 5 ++ .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h | 5 +- drivers/iommu/intel/iommu.c | 34 +++++++---- .../pci/hive_isp_css_include/print_support.h | 4 ++ fs/ext4/super.c | 5 +- include/linux/compiler_types.h | 8 +++ ipc/util.c | 16 ++---- kernel/bpf/stackmap.c | 3 +- kernel/configs/tiny.config | 1 + lib/Kconfig.debug | 13 +++++ mm/slub.c | 13 +++-- mm/vmscan.c | 3 + 20 files changed, 154 insertions(+), 72 deletions(-) -- 2.20.1

1 15

[PATCH openEuler-5.10 00/46] Series of kfence
by Zheng Zengkai 21 Oct '21

21 Oct '21

Backport kfence feature from mainline. Alexander Potapenko (10): mm: add Kernel Electric-Fence infrastructure x86, kfence: enable KFENCE for x86 mm, kfence: insert KFENCE hooks for SLAB mm, kfence: insert KFENCE hooks for SLUB kfence, kasan: make KFENCE compatible with KASAN tracing: add error_report_end trace point kfence: use error_report_end tracepoint kasan: use error_report_end tracepoint kfence: move the size check to the beginning of __kfence_alloc() kfence: skip all GFP_ZONEMASK allocations Christophe Leroy (2): powerpc/32s: Always map kernel text and rodata with BATs powerpc: Enable KFENCE for PPC32 Hyeonggon Yoo (1): mm, slub: change run-time assertion in kmalloc_index() to compile-time Jisheng Zhang (1): arm64: mm: don't use CON and BLK mapping if KFENCE is enabled Kefeng Wang (3): ARM: mm: Provide set_memory_valid() ARM: mm: Provide is_write_fault() ARM: Support KFENCE for ARM Marco Elver (22): arm64, kfence: enable KFENCE for ARM64 kfence: use pt_regs to generate stack trace on faults kfence, Documentation: add KFENCE documentation kfence: add test suite MAINTAINERS: add entry for KFENCE kfence: report sensitive information based on no_hash_pointers kfence: fix printk format for ptrdiff_t kfence, slab: fix cache_alloc_debugcheck_after() for bulk allocations kfence: fix reports if constant function prefixes exist kfence: make compatible with kmemleak kfence, x86: fix preemptible warning on KPTI-enabled systems kfence: zero guard page after out-of-bounds access kfence: await for allocation using wait_event kfence: maximize allocation wait timeout duration kfence: use power-efficient work queue to run delayed work kfence: use TASK_IDLE when awaiting allocation kfence: unconditionally use unbound work queue kfence: fix is_kfence_address() for addresses below KFENCE_POOL_SIZE kfence, x86: only define helpers if !MODULE lib/vsprintf: do not show no_hash_pointers message multiple times kfence: test: fail fast if disabled at boot kfence: show cpu and timestamp in alloc/free info Stephen Boyd (1): slub: force on no_hash_pointers when slub_debug is enabled Sven Schnelle (1): kfence: add function to mask address bits Timur Tabi (3): lib: use KSTM_MODULE_GLOBALS macro in kselftest drivers kselftest: add support for skipped tests lib/vsprintf: no_hash_pointers prints all addresses as unhashed Vlastimil Babka (1): printk: clarify the documentation for plain pointer printing Weizhao Ouyang (1): kfence: defer kfence_test_init to ensure that kunit debugfs is created .../admin-guide/kernel-parameters.txt | 15 + Documentation/core-api/printk-formats.rst | 26 +- Documentation/dev-tools/index.rst | 1 + Documentation/dev-tools/kfence.rst | 306 ++++++ MAINTAINERS | 12 + arch/arm/Kconfig | 1 + arch/arm/include/asm/kfence.h | 53 ++ arch/arm/include/asm/set_memory.h | 5 + arch/arm/mm/fault.c | 16 +- arch/arm/mm/pageattr.c | 41 +- arch/arm64/Kconfig | 1 + arch/arm64/include/asm/kfence.h | 22 + arch/arm64/mm/fault.c | 4 + arch/arm64/mm/mmu.c | 11 +- arch/powerpc/Kconfig | 13 +- arch/powerpc/include/asm/kfence.h | 33 + arch/powerpc/kernel/head_book3s_32.S | 4 +- arch/powerpc/mm/book3s32/mmu.c | 8 +- arch/powerpc/mm/fault.c | 7 +- arch/powerpc/mm/init_32.c | 3 + arch/powerpc/mm/mmu_decl.h | 5 + arch/powerpc/mm/nohash/8xx.c | 4 +- arch/x86/Kconfig | 1 + arch/x86/include/asm/kfence.h | 73 ++ arch/x86/mm/fault.c | 6 + include/linux/kernel.h | 2 + include/linux/kfence.h | 223 +++++ include/linux/slab.h | 17 +- include/linux/slab_def.h | 3 + include/linux/slub_def.h | 3 + include/trace/events/error_report.h | 74 ++ init/main.c | 3 + kernel/trace/Makefile | 1 + kernel/trace/error_report-traces.c | 11 + lib/Kconfig.debug | 1 + lib/Kconfig.kfence | 83 ++ lib/test_bitmap.c | 3 +- lib/test_printf.c | 12 +- lib/vsprintf.c | 46 +- mm/Makefile | 1 + mm/kasan/common.c | 18 + mm/kasan/generic.c | 3 +- mm/kasan/report.c | 8 +- mm/kfence/Makefile | 6 + mm/kfence/core.c | 891 ++++++++++++++++++ mm/kfence/kfence.h | 108 +++ mm/kfence/kfence_test.c | 873 +++++++++++++++++ mm/kfence/report.c | 274 ++++++ mm/kmemleak.c | 3 +- mm/slab.c | 41 +- mm/slab_common.c | 12 +- mm/slub.c | 80 +- tools/testing/selftests/kselftest_module.h | 18 +- 53 files changed, 3405 insertions(+), 84 deletions(-) create mode 100644 Documentation/dev-tools/kfence.rst create mode 100644 arch/arm/include/asm/kfence.h create mode 100644 arch/arm64/include/asm/kfence.h create mode 100644 arch/powerpc/include/asm/kfence.h create mode 100644 arch/x86/include/asm/kfence.h create mode 100644 include/linux/kfence.h create mode 100644 include/trace/events/error_report.h create mode 100644 kernel/trace/error_report-traces.c create mode 100644 lib/Kconfig.kfence create mode 100644 mm/kfence/Makefile create mode 100644 mm/kfence/core.c create mode 100644 mm/kfence/kfence.h create mode 100644 mm/kfence/kfence_test.c create mode 100644 mm/kfence/report.c -- 2.20.1

1 46

[PATCH v3 openEuler-1.0-LTS 2/2] drm/hisilicon: Features to support reading resolutions from EDID
by Gou Hao 21 Oct '21

21 Oct '21

From: Tian Tao <tiantao6(a)hisilicon.com> mainline inclusion from mainline-v5.14.0-rc7 commit a0d078d06e516184e2f575f3803935697b5e3ac6 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I469VQ CVE: NA Refactoring hibmc_vdac_init, hibmc_connector_init method. --------------------------------------- Use drm_get_edid to get the resolution, if that fails, set it to a fixed resolution. Rewrite the desrtoy callback function to release resources. Signed-off-by: Tian Tao <tiantao6(a)hisilicon.com> Reviewed-by: Thomas Zimmermann <tzimmermann(a)suse.de> Link: https://patchwork.freedesktop.org/patch/msgid/1600778670-60370-3-git-send-e… Signed-off-by: gouhao <gouhao(a)uniontech.com> --- .../gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 54 +++++++++++++------ 1 file changed, 37 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c index 90319a902..aeef73037 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c @@ -59,11 +59,23 @@ static int hibmc_valid_mode(int w, int h) static int hibmc_connector_get_modes(struct drm_connector *connector) { int count; + void *edid; + struct hibmc_connector *hibmc_connector = to_hibmc_connector(connector); + + edid = drm_get_edid(connector, &hibmc_connector->adapter); + if (edid) { + drm_connector_update_edid_property(connector, edid); + count = drm_add_edid_modes(connector, edid); + if (count) + goto out; + } drm_connector_update_edid_property(connector, NULL); count = drm_add_modes_noedid(connector, 1920, 1200); drm_set_preferred_mode(connector, 1024, 768); +out: + kfree(edid); return count; } @@ -93,39 +105,41 @@ static const struct drm_connector_helper_funcs .best_encoder = hibmc_connector_best_encoder, }; +static void hibmc_connector_destroy(struct drm_connector *connector) +{ + struct hibmc_connector *hibmc_connector = to_hibmc_connector(connector); + + i2c_del_adapter(&hibmc_connector->adapter); + drm_connector_cleanup(connector); +} + static const struct drm_connector_funcs hibmc_connector_funcs = { .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = drm_connector_cleanup, + .destroy = hibmc_connector_destroy, .reset = drm_atomic_helper_connector_reset, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static struct drm_connector * +static int hibmc_connector_init(struct hibmc_drm_private *priv) { struct drm_device *dev = priv->dev; - struct drm_connector *connector; + struct drm_connector *connector = &priv->connector.base; int ret; - connector = devm_kzalloc(dev->dev, sizeof(*connector), GFP_KERNEL); - if (!connector) { - DRM_ERROR("failed to alloc memory when init connector\n"); - return ERR_PTR(-ENOMEM); - } - ret = drm_connector_init(dev, connector, &hibmc_connector_funcs, DRM_MODE_CONNECTOR_VGA); if (ret) { DRM_ERROR("failed to init connector: %d\n", ret); - return ERR_PTR(ret); + return ret; } drm_connector_helper_add(connector, &hibmc_connector_helper_funcs); drm_connector_register(connector); - return connector; + return 0; } static void hibmc_encoder_mode_set(struct drm_encoder *encoder, @@ -155,15 +169,21 @@ static const struct drm_encoder_funcs hibmc_encoder_funcs = { int hibmc_vdac_init(struct hibmc_drm_private *priv) { struct drm_device *dev = priv->dev; + struct hibmc_connector *hibmc_connector = &priv->connector; struct drm_encoder *encoder; - struct drm_connector *connector; + struct drm_connector *connector = &hibmc_connector->base; int ret; - connector = hibmc_connector_init(priv); - if (IS_ERR(connector)) { - DRM_ERROR("failed to create connector: %ld\n", - PTR_ERR(connector)); - return PTR_ERR(connector); + ret = hibmc_connector_init(priv); + if (ret) { + DRM_ERROR("failed to init connector: %d\n", ret); + return ret; + } + + ret = hibmc_ddc_create(dev, hibmc_connector); + if (ret) { + DRM_ERROR("failed to create ddc: %d\n", ret); + return ret; } encoder = devm_kzalloc(dev->dev, sizeof(*encoder), GFP_KERNEL); -- 2.20.1

1 0

[PATCH v3 openEuler-1.0-LTS 1/2] drm/hisilicon: Support i2c driver algorithms for bit-shift adapters
by Gou Hao 21 Oct '21

21 Oct '21

From: Tian Tao <tiantao6(a)hisilicon.com> mainline inclusion from mainline-v5.14.0-rc7 commit 4eb4d99dfe3018d86f4529112aa7082f43b6996a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I469VQ CVE: NA Remove #include <drm/drm_probe_helper.h> in hibmc_drm_i2c.c. ----------------------------- Adding driver implementation to support i2c driver algorithms for bit-shift adapters, so hibmc will using the interface provided by drm to read edid. Signed-off-by: Tian Tao <tiantao6(a)hisilicon.com> Reviewed-by: Thomas Zimmermann <tzimmermann(a)suse.de> Link: https://patchwork.freedesktop.org/patch/msgid/1600778670-60370-2-git-send-e… Signed-off-by: gouhao <gouhao(a)uniontech.com> --- drivers/gpu/drm/hisilicon/hibmc/Makefile | 3 +- .../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 25 +++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c | 98 +++++++++++++++++++ 3 files changed, 125 insertions(+), 1 deletion(-) create mode 100644 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c diff --git a/drivers/gpu/drm/hisilicon/hibmc/Makefile b/drivers/gpu/drm/hisilicon/hibmc/Makefile index 3df726696..71c248f4c 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/Makefile +++ b/drivers/gpu/drm/hisilicon/hibmc/Makefile @@ -1,3 +1,4 @@ -hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o hibmc_drm_fbdev.o hibmc_ttm.o +hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o \ + hibmc_drm_fbdev.o hibmc_ttm.o hibmc_drm_i2c.o obj-$(CONFIG_DRM_HISI_HIBMC) += hibmc-drm.o diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h index 4395dc667..c246151b2 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h @@ -19,12 +19,18 @@ #ifndef HIBMC_DRM_DRV_H #define HIBMC_DRM_DRV_H +#include <linux/gpio/consumer.h> +#include <linux/i2c-algo-bit.h> +#include <linux/i2c.h> + +#include <drm/drm_edid.h> #include <drm/drmP.h> #include <drm/drm_atomic.h> #include <drm/drm_fb_helper.h> #include <drm/drm_gem.h> #include <drm/ttm/ttm_bo_driver.h> + struct hibmc_framebuffer { struct drm_framebuffer fb; struct drm_gem_object *obj; @@ -36,6 +42,13 @@ struct hibmc_fbdev { int size; }; +struct hibmc_connector { + struct drm_connector base; + + struct i2c_adapter adapter; + struct i2c_algo_bit_data bit_data; +}; + struct hibmc_drm_private { /* hw */ void __iomem *mmio; @@ -46,6 +59,7 @@ struct hibmc_drm_private { /* drm */ struct drm_device *dev; + struct hibmc_connector connector; bool mode_config_initialized; struct drm_atomic_state *suspend_state; @@ -60,6 +74,16 @@ struct hibmc_drm_private { bool mm_inited; }; +static inline struct hibmc_connector *to_hibmc_connector(struct drm_connector *connector) +{ + return container_of(connector, struct hibmc_connector, base); +} + +static inline struct hibmc_drm_private *to_hibmc_drm_private(struct drm_device *dev) +{ + return dev->dev_private; +} + #define to_hibmc_framebuffer(x) container_of(x, struct hibmc_framebuffer, fb) struct hibmc_bo { @@ -110,6 +134,7 @@ int hibmc_dumb_create(struct drm_file *file, struct drm_device *dev, int hibmc_dumb_mmap_offset(struct drm_file *file, struct drm_device *dev, u32 handle, u64 *offset); int hibmc_mmap(struct file *filp, struct vm_area_struct *vma); +int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_connector *connector); extern const struct drm_mode_config_funcs hibmc_mode_funcs; diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c new file mode 100644 index 000000000..ffd7c7bf4 --- /dev/null +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Hisilicon Hibmc SoC drm driver + * + * Based on the bochs drm driver. + * + * Copyright (c) 2016 Huawei Limited. + * + * Author: + * Tian Tao <tiantao6(a)hisilicon.com> + */ + +#include <linux/delay.h> +#include <linux/pci.h> + +#include <drm/drm_atomic_helper.h> + +#include "hibmc_drm_drv.h" + +#define GPIO_DATA 0x0802A0 +#define GPIO_DATA_DIRECTION 0x0802A4 + +#define I2C_SCL_MASK BIT(0) +#define I2C_SDA_MASK BIT(1) + +static void hibmc_set_i2c_signal(void *data, u32 mask, int value) +{ + struct hibmc_connector *hibmc_connector = data; + struct hibmc_drm_private *priv = to_hibmc_drm_private(hibmc_connector->base.dev); + u32 tmp_dir = readl(priv->mmio + GPIO_DATA_DIRECTION); + + if (value) { + tmp_dir &= ~mask; + writel(tmp_dir, priv->mmio + GPIO_DATA_DIRECTION); + } else { + u32 tmp_data = readl(priv->mmio + GPIO_DATA); + + tmp_data &= ~mask; + writel(tmp_data, priv->mmio + GPIO_DATA); + + tmp_dir |= mask; + writel(tmp_dir, priv->mmio + GPIO_DATA_DIRECTION); + } +} + +static int hibmc_get_i2c_signal(void *data, u32 mask) +{ + struct hibmc_connector *hibmc_connector = data; + struct hibmc_drm_private *priv = to_hibmc_drm_private(hibmc_connector->base.dev); + u32 tmp_dir = readl(priv->mmio + GPIO_DATA_DIRECTION); + + if ((tmp_dir & mask) != mask) { + tmp_dir &= ~mask; + writel(tmp_dir, priv->mmio + GPIO_DATA_DIRECTION); + } + + return (readl(priv->mmio + GPIO_DATA) & mask) ? 1 : 0; +} + +static void hibmc_ddc_setsda(void *data, int state) +{ + hibmc_set_i2c_signal(data, I2C_SDA_MASK, state); +} + +static void hibmc_ddc_setscl(void *data, int state) +{ + hibmc_set_i2c_signal(data, I2C_SCL_MASK, state); +} + +static int hibmc_ddc_getsda(void *data) +{ + return hibmc_get_i2c_signal(data, I2C_SDA_MASK); +} + +static int hibmc_ddc_getscl(void *data) +{ + return hibmc_get_i2c_signal(data, I2C_SCL_MASK); +} + +int hibmc_ddc_create(struct drm_device *drm_dev, + struct hibmc_connector *connector) +{ + connector->adapter.owner = THIS_MODULE; + connector->adapter.class = I2C_CLASS_DDC; + snprintf(connector->adapter.name, I2C_NAME_SIZE, "HIS i2c bit bus"); + connector->adapter.dev.parent = &drm_dev->pdev->dev; + i2c_set_adapdata(&connector->adapter, connector); + connector->adapter.algo_data = &connector->bit_data; + + connector->bit_data.udelay = 20; + connector->bit_data.timeout = usecs_to_jiffies(2000); + connector->bit_data.data = connector; + connector->bit_data.setsda = hibmc_ddc_setsda; + connector->bit_data.setscl = hibmc_ddc_setscl; + connector->bit_data.getsda = hibmc_ddc_getsda; + connector->bit_data.getscl = hibmc_ddc_getscl; + + return i2c_bit_add_bus(&connector->adapter); +} -- 2.20.1

1 0

[PATCH v3 openEuler-1.0-LTS 0/2] drm/hisilicon: Fix hibmc did not get edid
by Gou Hao 21 Oct '21

21 Oct '21

From: gouhao <gouhao(a)uniontech.com> Fix hibmc did not get edid. issue: https://gitee.com/openeuler/kernel/issues/I469VQ gouhao (2): drm/hisilicon: Support i2c driver algorithms for bit-shift adapters drm/hisilicon: Features to support reading resolutions from EDID drivers/gpu/drm/hisilicon/hibmc/Makefile | 3 +- .../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 25 +++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c | 98 +++++++++++++++++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 54 ++++++---- 4 files changed, 162 insertions(+), 18 deletions(-) create mode 100644 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c -- 2.20.1

1 0

[PATCH openEuler-21.03] etmem: corret ept page walk under 4 level page table
by Kemeng Shi 21 Oct '21

21 Oct '21

euleros inclusion category: feature feature: etmem bugzilla: 48246 ------------------------------------------------- Function ept_pgd_range does not work for vm has 4 level page table. Call ept_p4d_range instead to fix this. Signed-off-by: Kemeng Shi <shikemeng(a)huawei.com> --- fs/proc/etmem_scan.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/proc/etmem_scan.c b/fs/proc/etmem_scan.c index cdc8f341af67..b4655c85f8c5 100644 --- a/fs/proc/etmem_scan.c +++ b/fs/proc/etmem_scan.c @@ -557,9 +557,8 @@ static int ept_page_range(struct page_idle_ctrl *pic, ept_root = __va(mmu->root_hpa); - // walk start at p4d when host enable 5 level table pages but - // vm only get 4 level table pages - if (mmu->shadow_root_level == 4 + (!!pgtable_l5_enabled())) + // Walk start at p4d when vm get 4 level table pages + if (mmu->shadow_root_level != 4) err = ept_pgd_range(pic, (pgd_t *)ept_root, addr, end, walk); else err = ept_p4d_range(pic, (p4d_t *)ept_root, addr, end, walk); -- 2.30.0

1 0

Re:[v1,openEuler-1.0-LTS,1/4] tcp: address problems caused by EDT misshaps
by QiuLaibin 21 Oct '21

21 Oct '21

hi zhenyuan: 非常感谢您的提交；但是在您提交的附1补丁集中，我们发现tcp: address problems caused by EDT misshaps中修复的前向补丁Fixes: ab408b6dc744 ("tcp: switch tcp and sch_fq to new earliest departure time model") 在版本中并未合入，请再确认一下。 best regard附1： issue: https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue jiazhenyuan (4): tcp: address problems caused by EDT misshaps ^^^^^^^ tcp: always set retrans_stamp on recovery tcp: create a helper to model exponential backoff tcp: adjust rto_base in retransmits_timed_out() net/ipv4/tcp_input.c | 16 +++++++---- net/ipv4/tcp_output.c | 9 +++--- net/ipv4/tcp_timer.c | 65 ++++++++++++++++++++----------------------- 3 files changed, 44 insertions(+), 46 deletions(-): *附2：* [v1,openEuler-1.0-LTS,1/4] tcp: address problems caused by EDT misshaps From: Eric Dumazet <edumazet(a)google.com> mainline inclusion from mainline-v5.3.0 commit 9efdda4e3abed13f0903b7b6e4d4c2102019440a category: bugfix bugzilla:https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue CVE: NA ------------------------------------------------------------ When a qdisc setup including pacing FQ is dismantled and recreated, some TCP packets are sent earlier than instructed by TCP stack. TCP can be fooled when ACK comes back, because the following operation can return a negative value. tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; Some paths in TCP stack were not dealing properly with this, this patch addresses four of them. Fixes: ab408b6dc744 ("tcp: switch tcp and sch_fq to new earliest departure time model") ^^^^^^^^^^^^^^^ <= 当前版本未合入该patch Signed-off-by: Eric Dumazet <edumazet(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Jiazhenyuan <jiazhenyuan(a)uniontech.com> --- net/ipv4/tcp_input.c | 16 ++++++++++------ net/ipv4/tcp_timer.c | 10 ++++++---- 2 files changed, 16 insertions(+), 10 deletions(-)

1 0

[PATCH kernel-4.19] net:fix tcp timeout retransmits are always missing 2 times
by Yang Yingliang 21 Oct '21

21 Oct '21

From: jiazhenyuan <jiazhenyuan(a)uniontech.com> mainline inclusion from mainline-v5.4-rc2 commit 3256a2d6ab1f71f9a1bd2d7f6f18eb8108c48d17 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue CVE: NA --------------------------------------------------------------- tcp: adjust rto_base in retransmits_timed_out() The cited commit exposed an old retransmits_timed_out() bug which assumed it could call tcp_model_timeout() with TCP_RTO_MIN as rto_base for all states. But flows in SYN_SENT or SYN_RECV state uses a different RTO base (1 sec instead of 200 ms, unless BPF choses another value) This caused a reduction of SYN retransmits from 6 to 4 with the default /proc/sys/net/ipv4/tcp_syn_retries value. Fixes: a41e8a8 ("tcp: better handle TCP_USER_TIMEOUT in SYN_SENT state") Signed-off-by: Eric Dumazet <edumazet(a)google.com> Cc: Yuchung Cheng <ycheng(a)google.com> Cc: Marek Majkowski <marek(a)cloudflare.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: jiazhenyuan <jiazhenyuan(a)uniontech.com> # openEuler_contributor Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/ipv4/tcp_timer.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 681882a409686..81a47e87c35d4 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -190,7 +190,7 @@ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout) { - const unsigned int rto_base = TCP_RTO_MIN; + unsigned int rto_base = TCP_RTO_MIN; unsigned int linear_backoff_thresh, start_ts; if (!inet_csk(sk)->icsk_retransmits) @@ -201,6 +201,9 @@ static bool retransmits_timed_out(struct sock *sk, return false; if (likely(timeout == 0)) { + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) + rto_base = tcp_timeout_init(sk); + linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); if (boundary <= linear_backoff_thresh) -- 2.25.1

1 0

[PATCH kernel-4.19] blk-wbt: fix IO hang due to negative inflight counter
by Yang Yingliang 21 Oct '21

21 Oct '21

From: Laibin Qiu <qiulaibin(a)huawei.com> hulk inclusion category: bugfix bugzilla: 182135, https://gitee.com/openeuler/kernel/issues/I4ENC8 CVE: NA -------------------------- Block test reported the following stack, Some req has been watting for wakeup in wbt_wait, and vmcore showed that wbt inflight counter is -1. So Request cannot be awakened. PID: 75416 TASK: ffff88836c098000 CPU: 2 COMMAND: "fsstress" [ffff8882e59a7608] __schedule at ffffffffb2d22a25 [ffff8882e59a7720] schedule at ffffffffb2d2358f [ffff8882e59a7738] io_schedule at ffffffffb2d23bdc [ffff8882e59a7750] rq_qos_wait at ffffffffb2400fde [ffff8882e59a7878] wbt_wait at ffffffffb243a051 [ffff8882e59a7910] __rq_qos_throttle at ffffffffb2400a20 [ffff8882e59a7930] blk_mq_make_request at ffffffffb23de038 [ffff8882e59a7a98] generic_make_request at ffffffffb23c393d [ffff8882e59a7b80] submit_bio at ffffffffb23c3db8 [ffff8882e59a7c48] submit_bio_wait at ffffffffb23b3a5d [ffff8882e59a7cf0] blkdev_issue_flush at ffffffffb23c8f4c [ffff8882e59a7d20] ext4_sync_fs at ffffffffc06dd708 [ext4] [ffff8882e59a7dd0] sync_filesystem at ffffffffb21e8335 [ffff8882e59a7df8] ovl_sync_fs at ffffffffc0fd853a [overlay] [ffff8882e59a7e10] sync_fs_one_sb at ffffffffb21e8221 [ffff8882e59a7e30] iterate_supers at ffffffffb218401e [ffff8882e59a7e70] ksys_sync at ffffffffb21e8588 [ffff8882e59a7f20] __x64_sys_sync at ffffffffb21e861f [ffff8882e59a7f28] do_syscall_64 at ffffffffb1c06bc8 [ffff8882e59a7f50] entry_SYSCALL_64_after_hwframe at ffffffffb2e000ad RIP: 00007f479ab13347 RSP: 00007ffd4dda9fe8 RFLAGS: 00000202 RAX: ffffffffffffffda RBX: 0000000000000068 RCX: 00007f479ab13347 RDX: 0000000000000000 RSI: 000000003e1b142d RDI: 0000000000000068 RBP: 0000000051eb851f R8: 00007f479abd4034 R9: 00007f479abd40a0 R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000402c20 R13: 0000000000000001 R14: 0000000000000000 R15: 7fffffffffffffff The ->inflight counter may be negative (-1) if 1) blk-wbt was disabled when the IO was issued, which will add inflight count. 2) blk-wbt was enabled before this IO tracked. 3) the ->inflight counter is decreased from 0 to -1 in endio(). This fixes the problem by freezing the queue while enabling wbt, there is no inflight rq running. Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-wbt.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index a9f11d12bea92..b65504f330442 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -23,6 +23,7 @@ #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/swap.h> +#include <linux/blk-mq.h> #include "blk-wbt.h" #include "blk-rq-qos.h" @@ -822,9 +823,16 @@ int wbt_init(struct request_queue *q) rq_qos_add(q, &rwb->rqos); blk_stat_add_callback(q, rwb->cb); - rwb->min_lat_nsec = wbt_default_latency_nsec(q); + /* + * Ensure that the queue is idled by freezing the queue + * while enabling wbt, there is no inflight rq running. + */ + blk_mq_freeze_queue(q); + rwb->min_lat_nsec = wbt_default_latency_nsec(q); wbt_queue_depth_changed(&rwb->rqos); + + blk_mq_unfreeze_queue(q); wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); return 0; -- 2.25.1

2 1

unsubscribe
by 🐟๛ก(ｰ̀ωｰ́ก) 20 Oct '21

20 Oct '21

unsubscribe

1 0

[PATCH kernel-4.19] sharepool: Fix ASLR broken
by Yang Yingliang 20 Oct '21

20 Oct '21

From: Wang Wensheng <wangwensheng4(a)huawei.com> ascend inclusion category: bugfix bugzilla: NA CVE: NA --------------------------- To avoid mmap vspace reserved for sharepool, we currently change the high_limit to MMAP_SHARE_POOL_START in arch_get_unmapped_area() and arch_get_unmapped_area_topdown(). In mmap-topdown scene, this make the start address of mmap being always MMAP_SHARE_POOL_START. ASLR got broken. To fix this, this patch set the mm->mmap_base based on MMAP_SHARE_POOL_START instead of STACK_TOP in topdown scene. Fixes: 4bdd5c21793e ("ascend: memory: introduce do_mm_populate and hugetlb_insert_hugepage") Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/mm/mmap.c | 6 +++++- include/linux/share_pool.h | 4 ++-- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 157f2caa13516..aca257158611f 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -28,6 +28,7 @@ #include <linux/io.h> #include <linux/personality.h> #include <linux/random.h> +#include <linux/share_pool.h> #include <asm/cputype.h> @@ -80,7 +81,10 @@ static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) else if (gap > MAX_GAP) gap = MAX_GAP; - return PAGE_ALIGN(STACK_TOP - gap - rnd); + if (sp_is_enabled()) + return ALIGN_DOWN(MMAP_SHARE_POOL_START - rnd, PAGE_SIZE); + else + return PAGE_ALIGN(STACK_TOP - gap - rnd); } /* diff --git a/include/linux/share_pool.h b/include/linux/share_pool.h index 9650f257b3ad7..9557a8be46677 100644 --- a/include/linux/share_pool.h +++ b/include/linux/share_pool.h @@ -130,8 +130,6 @@ struct sp_proc_stat { atomic64_t k2u_size; }; -#ifdef CONFIG_ASCEND_SHARE_POOL - #define MAP_SHARE_POOL 0x100000 #define MMAP_TOP_4G_SIZE 0x100000000UL @@ -148,6 +146,8 @@ struct sp_proc_stat { #define MMAP_SHARE_POOL_START (MMAP_SHARE_POOL_END - MMAP_SHARE_POOL_SIZE) #define MMAP_SHARE_POOL_16G_START (MMAP_SHARE_POOL_END - MMAP_SHARE_POOL_DVPP_SIZE) +#ifdef CONFIG_ASCEND_SHARE_POOL + static inline void sp_init_mm(struct mm_struct *mm) { mm->sp_group = NULL; -- 2.25.1

1 0

[PATCH kernel-4.19] numa/cdm: Introduce a hbm_per_part variable
by Yang Yingliang 20 Oct '21

20 Oct '21

From: Wang Wensheng <wangwensheng4(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4D63I CVE: NA ------------------------------------------------- Not all cdm nodes are hbm and we don't need to operate on the other nodes. So we should specify the hbm count per partion. Here we assume that all the hbm nodes appear at first of all the cdm nodes in one partion. Otherwise the management structure of the hbm nodes could not be moved, which is not worse than closing this feature. Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/mm/numa.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index 82d53927554d8..c65a71de8d5fb 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -63,7 +63,9 @@ inline int arch_check_node_cdm(int nid) * |node2 HBM| | |node4 HBM| * |---------- | ----------| * |node3 HBM| | |node5 HBM| - * ----------- | ----------- + * |---------- | ----------| + * | ... | | | ... | + * |---------- | ----------| * * Return: * This function returns a ddr node which is of the same partion with the input @@ -76,6 +78,12 @@ int __init cdm_node_to_ddr_node(int nid) nodemask_t ddr_mask; int nr_ddr, cdm_per_part, fake_nid; int nr_cdm = nodes_weight(cdmmask); + /* + * Specify the count of hbm nodes whoes management structrue would be + * moved. Here number 2 is a magic and we should make it configable + * for extending + */ + int hbm_per_part = 2; if (!nr_cdm || nodes_empty(numa_nodes_parsed)) return nid; @@ -87,11 +95,12 @@ int __init cdm_node_to_ddr_node(int nid) nr_ddr = nodes_weight(ddr_mask); cdm_per_part = nr_cdm / nr_ddr; - if (cdm_per_part == 0 || nid < nr_ddr) + if (cdm_per_part == 0 || nid < nr_ddr || + nid >= (hbm_per_part + 1) * nr_ddr) /* our assumption has borken, just return the original nid. */ return nid; - fake_nid = (nid - nr_ddr) / cdm_per_part; + fake_nid = (nid - nr_ddr) / hbm_per_part; fake_nid = !node_isset(fake_nid, cdmmask) ? fake_nid : nid; pr_info("nid: %d, fake_nid: %d\n", nid, fake_nid); -- 2.25.1

1 0

[PATCH kernel-4.19] uacce: misc fixes
by Yang Yingliang 20 Oct '21

20 Oct '21

From: Yu'an Wang <wangyuan46(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA 1.add input para check of uacce_unregister api 2.change uacce_qfrt_str to internal interface, because it is used just in uacce.c Signed-off-by: Yu'an Wang <wangyuan46(a)huawei.com> Reviewed-by: Longfang Liu <liulongfang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/misc/uacce/uacce.c | 6 ++++-- include/linux/uacce.h | 1 - 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c index db7b3936aec6f..b0cdc244e882a 100644 --- a/drivers/misc/uacce/uacce.c +++ b/drivers/misc/uacce/uacce.c @@ -126,11 +126,10 @@ static void uacce_hw_err_destroy(struct uacce *uacce) } } -const char *uacce_qfrt_str(struct uacce_qfile_region *qfr) +static const char *uacce_qfrt_str(struct uacce_qfile_region *qfr) { return qfrt_str[qfr->type]; } -EXPORT_SYMBOL_GPL(uacce_qfrt_str); /** * uacce_wake_up - Wake up the process who is waiting this queue @@ -1302,6 +1301,9 @@ EXPORT_SYMBOL_GPL(uacce_register); */ int uacce_unregister(struct uacce *uacce) { + if (!uacce) + return -ENODEV; + if (atomic_read(&uacce->ref) > 0) { printk_ratelimited("Fail to unregister uacce, please close all uacce queues!\n"); return -EAGAIN; diff --git a/include/linux/uacce.h b/include/linux/uacce.h index 43737c3f7f525..b43b65abdce39 100644 --- a/include/linux/uacce.h +++ b/include/linux/uacce.h @@ -128,7 +128,6 @@ struct uacce { int uacce_register(struct uacce *uacce); int uacce_unregister(struct uacce *uacce); void uacce_wake_up(struct uacce_queue *q); -const char *uacce_qfrt_str(struct uacce_qfile_region *qfr); struct uacce *dev_to_uacce(struct device *dev); int uacce_hw_err_isolate(struct uacce *uacce); -- 2.25.1

1 0

[PATCH kernel-4.19 1/6] mm/page_alloc.c: memory hotplug: free pages as higher order
by Yang Yingliang 20 Oct '21

20 Oct '21

From: Arun KS <arunks(a)codeaurora.org> mainline inclusion from mainline-v5.1-rc1 commit a9cd410a3d296846a8125aa43d97a573a354c472 category: feature bugzilla: 182882 CVE: NA ----------------------------------------------- When freeing pages are done with higher order, time spent on coalescing pages by buddy allocator can be reduced. With section size of 256MB, hot add latency of a single section shows improvement from 50-60 ms to less than 1 ms, hence improving the hot add latency by 60 times. Modify external providers of online callback to align with the change. [arunks(a)codeaurora.org: v11] Link: http://lkml.kernel.org/r/1547792588-18032-1-git-send-email-arunks@codeauror… [akpm(a)linux-foundation.org: remove unused local, per Arun] [akpm(a)linux-foundation.org: avoid return of void-returning __free_pages_core(), per Oscar] [akpm(a)linux-foundation.org: fix it for mm-convert-totalram_pages-and-totalhigh_pages-variables-to-atomic.patch] [arunks(a)codeaurora.org: v8] Link: http://lkml.kernel.org/r/1547032395-24582-1-git-send-email-arunks@codeauror… [arunks(a)codeaurora.org: v9] Link: http://lkml.kernel.org/r/1547098543-26452-1-git-send-email-arunks@codeauror… Link: http://lkml.kernel.org/r/1538727006-5727-1-git-send-email-arunks@codeaurora… Signed-off-by: Arun KS <arunks(a)codeaurora.org> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Acked-by: Michal Hocko <mhocko(a)suse.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Reviewed-by: Alexander Duyck <alexander.h.duyck(a)linux.intel.com> Cc: K. Y. Srinivasan <kys(a)microsoft.com> Cc: Haiyang Zhang <haiyangz(a)microsoft.com> Cc: Stephen Hemminger <sthemmin(a)microsoft.com> Cc: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Cc: Juergen Gross <jgross(a)suse.com> Cc: Dan Williams <dan.j.williams(a)intel.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Joonsoo Kim <iamjoonsoo.kim(a)lge.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Mathieu Malaterre <malat(a)debian.org> Cc: "Kirill A. Shutemov" <kirill.shutemov(a)linux.intel.com> Cc: Souptick Joarder <jrdr.linux(a)gmail.com> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: Aaron Lu <aaron.lu(a)intel.com> Cc: Srivatsa Vaddagiri <vatsa(a)codeaurora.org> Cc: Vinayak Menon <vinmenon(a)codeaurora.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Conflicts: mm/page_alloc.c mm/memory_hotplug.c [Peng Liu: adjust context] Signed-off-by: Peng Liu <liupeng256(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/hv/hv_balloon.c | 7 ++++--- drivers/xen/balloon.c | 15 ++++++++++----- include/linux/memory_hotplug.h | 2 +- mm/internal.h | 1 + mm/memory_hotplug.c | 33 +++++++++++++++++++++------------ mm/page_alloc.c | 8 ++++---- 6 files changed, 41 insertions(+), 25 deletions(-) diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index e5fc719a34e70..23d9156915271 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -771,7 +771,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, } } -static void hv_online_page(struct page *pg) +static void hv_online_page(struct page *pg, unsigned int order) { struct hv_hotadd_state *has; unsigned long flags; @@ -780,10 +780,11 @@ static void hv_online_page(struct page *pg) spin_lock_irqsave(&dm_device.ha_lock, flags); list_for_each_entry(has, &dm_device.ha_region_list, list) { /* The page belongs to a different HAS. */ - if ((pfn < has->start_pfn) || (pfn >= has->end_pfn)) + if ((pfn < has->start_pfn) || + (pfn + (1UL << order) > has->end_pfn)) continue; - hv_page_online_one(has, pg); + hv_bring_pgs_online(has, pfn, 1UL << order); break; } spin_unlock_irqrestore(&dm_device.ha_lock, flags); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index b23edf64c2b21..630fd49a7ce84 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -369,14 +369,19 @@ static enum bp_state reserve_additional_memory(void) return BP_ECANCELED; } -static void xen_online_page(struct page *page) +static void xen_online_page(struct page *page, unsigned int order) { - __online_page_set_limits(page); + unsigned long i, size = (1 << order); + unsigned long start_pfn = page_to_pfn(page); + struct page *p; + pr_debug("Online %lu pages starting at pfn 0x%lx\n", size, start_pfn); mutex_lock(&balloon_mutex); - - __balloon_append(page); - + for (i = 0; i < size; i++) { + p = pfn_to_page(start_pfn + i); + __online_page_set_limits(p); + __balloon_append(p); + } mutex_unlock(&balloon_mutex); } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 5653178768227..8782f0e993704 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -89,7 +89,7 @@ extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, unsigned long *valid_start, unsigned long *valid_end); extern void __offline_isolated_pages(unsigned long, unsigned long); -typedef void (*online_page_callback_t)(struct page *page); +typedef void (*online_page_callback_t)(struct page *page, unsigned int order); extern int set_online_page_callback(online_page_callback_t callback); extern int restore_online_page_callback(online_page_callback_t callback); diff --git a/mm/internal.h b/mm/internal.h index 3bb7ca86e84eb..415a6a326bb4d 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -163,6 +163,7 @@ static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, extern int __isolate_free_page(struct page *page, unsigned int order); extern void __free_pages_bootmem(struct page *page, unsigned long pfn, unsigned int order); +extern void __free_pages_core(struct page *page, unsigned int order); extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 967adfc17dd26..64a3ec9365911 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -48,7 +48,7 @@ * and restore_online_page_callback() for generic callback restore. */ -static void generic_online_page(struct page *page); +static void generic_online_page(struct page *page, unsigned int order); static online_page_callback_t online_page_callback = generic_online_page; static DEFINE_MUTEX(online_page_callback_lock); @@ -580,26 +580,35 @@ void __online_page_free(struct page *page) } EXPORT_SYMBOL_GPL(__online_page_free); -static void generic_online_page(struct page *page) +static void generic_online_page(struct page *page, unsigned int order) { - __online_page_set_limits(page); - __online_page_increment_counters(page); - __online_page_free(page); + __free_pages_core(page, order); + adjust_managed_page_count(page, 1UL << order); +} + +static int online_pages_blocks(unsigned long start, unsigned long nr_pages) +{ + unsigned long end = start + nr_pages; + int order, onlined_pages = 0; + + while (start < end) { + order = min(MAX_ORDER - 1, + get_order(PFN_PHYS(end) - PFN_PHYS(start))); + (*online_page_callback)(pfn_to_page(start), order); + + onlined_pages += (1UL << order); + start += (1UL << order); + } + return onlined_pages; } static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages, void *arg) { - unsigned long i; unsigned long onlined_pages = *(unsigned long *)arg; - struct page *page; if (PageReserved(pfn_to_page(start_pfn))) - for (i = 0; i < nr_pages; i++) { - page = pfn_to_page(start_pfn + i); - (*online_page_callback)(page); - onlined_pages++; - } + onlined_pages += online_pages_blocks(start_pfn, nr_pages); online_mem_sections(start_pfn, start_pfn + nr_pages); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 12e0899f3b9c8..e0002e5c3d06d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1288,7 +1288,7 @@ static void __free_pages_ok(struct page *page, unsigned int order) local_irq_restore(flags); } -static void __init __free_pages_boot_core(struct page *page, unsigned int order) +void __free_pages_core(struct page *page, unsigned int order) { unsigned int nr_pages = 1 << order; struct page *p = page; @@ -1368,7 +1368,7 @@ void __init __free_pages_bootmem(struct page *page, unsigned long pfn, return; page_zone(page)->managed_pages += 1UL << order; - return __free_pages_boot_core(page, order); + return __free_pages_core(page, order); } /* @@ -1459,14 +1459,14 @@ static void __init deferred_free_range(unsigned long pfn, if (nr_pages == pageblock_nr_pages && (pfn & (pageblock_nr_pages - 1)) == 0) { set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_boot_core(page, pageblock_order); + __free_pages_core(page, pageblock_order); return; } for (i = 0; i < nr_pages; i++, page++, pfn++) { if ((pfn & (pageblock_nr_pages - 1)) == 0) set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_boot_core(page, 0); + __free_pages_core(page, 0); } } -- 2.25.1

1 5

[PATCH kernel-4.19] raid1: ensure write behind bio has less than BIO_MAX_VECS sectors
by Yang Yingliang 20 Oct '21

20 Oct '21

From: Guoqing Jiang <jiangguoqing(a)kylinos.cn> mainline inclusion from mainline-v5.15-rc1 commit 6607cd319b6b91bff94e90f798a61c031650b514 category: bugfix bugzilla: 182883, https://gitee.com/openeuler/kernel/issues/I4ENHY CVE: NA ------------------------------------------------- We can't split write behind bio with more than BIO_MAX_VECS sectors, otherwise the below call trace was triggered because we could allocate oversized write behind bio later. [ 8.097936] bvec_alloc+0x90/0xc0 [ 8.098934] bio_alloc_bioset+0x1b3/0x260 [ 8.099959] raid1_make_request+0x9ce/0xc50 [raid1] [ 8.100988] ? __bio_clone_fast+0xa8/0xe0 [ 8.102008] md_handle_request+0x158/0x1d0 [md_mod] [ 8.103050] md_submit_bio+0xcd/0x110 [md_mod] [ 8.104084] submit_bio_noacct+0x139/0x530 [ 8.105127] submit_bio+0x78/0x1d0 [ 8.106163] ext4_io_submit+0x48/0x60 [ext4] [ 8.107242] ext4_writepages+0x652/0x1170 [ext4] [ 8.108300] ? do_writepages+0x41/0x100 [ 8.109338] ? __ext4_mark_inode_dirty+0x240/0x240 [ext4] [ 8.110406] do_writepages+0x41/0x100 [ 8.111450] __filemap_fdatawrite_range+0xc5/0x100 [ 8.112513] file_write_and_wait_range+0x61/0xb0 [ 8.113564] ext4_sync_file+0x73/0x370 [ext4] [ 8.114607] __x64_sys_fsync+0x33/0x60 [ 8.115635] do_syscall_64+0x33/0x40 [ 8.116670] entry_SYSCALL_64_after_hwframe+0x44/0xae Thanks for the comment from Christoph. [1]. https://bugs.archlinux.org/task/70992 Cc: stable(a)vger.kernel.org # v5.12+ Reported-by: Jens Stutte <jens(a)chianterastutte.eu> Tested-by: Jens Stutte <jens(a)chianterastutte.eu> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Guoqing Jiang <jiangguoqing(a)kylinos.cn> Signed-off-by: Song Liu <songliubraving(a)fb.com> Conflict: drivers/md/raid1.c [ Mainline patch 6607cd319b6b ("raid1: ensure write behind bio has less than BIO_MAX_VECS sectors"), BIO_MAX_VECS is used directly, but the BIO_MAX_VECS was renamed previously and the corresponding patch a8affc03a9b37 ("block: rename BIO_MAX_PAGES to BIO_MAX_VECS") was not incorporated. So we modify BIO_MAX_VECS to the original BIO_MAX_PAGES.] Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/md/raid1.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index cfc23bf440f84..0c30a1fdb561c 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1318,6 +1318,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, struct raid1_plug_cb *plug = NULL; int first_clone; int max_sectors; + bool write_behind = false; if (mddev_is_clustered(mddev) && md_cluster_ops->area_resyncing(mddev, WRITE, @@ -1370,6 +1371,15 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, max_sectors = r1_bio->sectors; for (i = 0; i < disks; i++) { struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); + + /* + * The write-behind io is only attempted on drives marked as + * write-mostly, which means we could allocate write behind + * bio later. + */ + if (rdev && test_bit(WriteMostly, &rdev->flags)) + write_behind = true; + if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { atomic_inc(&rdev->nr_pending); blocked_rdev = rdev; @@ -1444,6 +1454,15 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, goto retry_write; } + /* + * When using a bitmap, we may call alloc_behind_master_bio below. + * alloc_behind_master_bio allocates a copy of the data payload a page + * at a time and thus needs a new bio that can fit the whole payload + * this bio in page sized chunks. + */ + if (write_behind && bitmap) + max_sectors = min_t(int, max_sectors, + BIO_MAX_PAGES * (PAGE_SIZE >> 9)); if (max_sectors < bio_sectors(bio)) { struct bio *split = bio_split(bio, max_sectors, GFP_NOIO, &conf->bio_split); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] blk-wbt: fix IO hang due to negative inflight counter
by Yang Yingliang 20 Oct '21

20 Oct '21

From: Laibin Qiu <qiulaibin(a)huawei.com> hulk inclusion category: bugfix bugzilla: 182135, https://gitee.com/openeuler/kernel/issues/I4ENC8 CVE: NA -------------------------- Block test reported the following stack, Some req has been watting for wakeup in wbt_wait, and vmcore showed that wbt inflight counter is -1. So Request cannot be awakened. PID: 75416 TASK: ffff88836c098000 CPU: 2 COMMAND: "fsstress" [ffff8882e59a7608] __schedule at ffffffffb2d22a25 [ffff8882e59a7720] schedule at ffffffffb2d2358f [ffff8882e59a7738] io_schedule at ffffffffb2d23bdc [ffff8882e59a7750] rq_qos_wait at ffffffffb2400fde [ffff8882e59a7878] wbt_wait at ffffffffb243a051 [ffff8882e59a7910] __rq_qos_throttle at ffffffffb2400a20 [ffff8882e59a7930] blk_mq_make_request at ffffffffb23de038 [ffff8882e59a7a98] generic_make_request at ffffffffb23c393d [ffff8882e59a7b80] submit_bio at ffffffffb23c3db8 [ffff8882e59a7c48] submit_bio_wait at ffffffffb23b3a5d [ffff8882e59a7cf0] blkdev_issue_flush at ffffffffb23c8f4c [ffff8882e59a7d20] ext4_sync_fs at ffffffffc06dd708 [ext4] [ffff8882e59a7dd0] sync_filesystem at ffffffffb21e8335 [ffff8882e59a7df8] ovl_sync_fs at ffffffffc0fd853a [overlay] [ffff8882e59a7e10] sync_fs_one_sb at ffffffffb21e8221 [ffff8882e59a7e30] iterate_supers at ffffffffb218401e [ffff8882e59a7e70] ksys_sync at ffffffffb21e8588 [ffff8882e59a7f20] __x64_sys_sync at ffffffffb21e861f [ffff8882e59a7f28] do_syscall_64 at ffffffffb1c06bc8 [ffff8882e59a7f50] entry_SYSCALL_64_after_hwframe at ffffffffb2e000ad RIP: 00007f479ab13347 RSP: 00007ffd4dda9fe8 RFLAGS: 00000202 RAX: ffffffffffffffda RBX: 0000000000000068 RCX: 00007f479ab13347 RDX: 0000000000000000 RSI: 000000003e1b142d RDI: 0000000000000068 RBP: 0000000051eb851f R8: 00007f479abd4034 R9: 00007f479abd40a0 R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000402c20 R13: 0000000000000001 R14: 0000000000000000 R15: 7fffffffffffffff The ->inflight counter may be negative (-1) if 1) blk-wbt was disabled when the IO was issued, which will add inflight count. 2) blk-wbt was enabled before this IO tracked. 3) the ->inflight counter is decreased from 0 to -1 in endio(). This fixes the problem by freezing the queue while enabling wbt, there is no inflight rq running. Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-wbt.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 3d9f61633e688..ffd5c17f5a101 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -23,6 +23,9 @@ #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/swap.h> +#ifndef __GENKSYMS__ +#include <linux/blk-mq.h> +#endif #include "blk-wbt.h" #include "blk-rq-qos.h" @@ -824,9 +827,16 @@ int wbt_init(struct request_queue *q) rq_qos_add(q, &rwb->rqos); blk_stat_add_callback(q, rwb->cb); - rwb->min_lat_nsec = wbt_default_latency_nsec(q); + /* + * Ensure that the queue is idled by freezing the queue + * while enabling wbt, there is no inflight rq running. + */ + blk_mq_freeze_queue(q); + rwb->min_lat_nsec = wbt_default_latency_nsec(q); wbt_set_queue_depth(q, blk_queue_depth(q)); + + blk_mq_unfreeze_queue(q); wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); return 0; -- 2.25.1

1 0

[PATCH OLK-5.10 v3 0/1] scsi: spfc: initial commit the spfc module
by Yanling Song 20 Oct '21

20 Oct '21

Ramaxel inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4DBD7 CVE: NA Initial commit the spfc module for ramaxel Super FC adapter Changes since v2: - 1. Change comments of default N to M in kconfig. - 2. Update MACRO to sync with file name. - 3. Remove new blank line at EOF. - 4. Remove unncessary initialization of local varaibles. Changes since v1: - Add UNF_PORT_CFG_SET_PORT_STATE state Yanling Song (1): scsi: spfc: initial commit the spfc module arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + drivers/scsi/Kconfig | 1 + drivers/scsi/Makefile | 1 + drivers/scsi/spfc/Kconfig | 16 + drivers/scsi/spfc/Makefile | 47 + drivers/scsi/spfc/common/unf_common.h | 1755 +++++++ drivers/scsi/spfc/common/unf_disc.c | 1276 +++++ drivers/scsi/spfc/common/unf_disc.h | 51 + drivers/scsi/spfc/common/unf_event.c | 517 ++ drivers/scsi/spfc/common/unf_event.h | 83 + drivers/scsi/spfc/common/unf_exchg.c | 2317 +++++++++ drivers/scsi/spfc/common/unf_exchg.h | 436 ++ drivers/scsi/spfc/common/unf_exchg_abort.c | 825 +++ drivers/scsi/spfc/common/unf_exchg_abort.h | 23 + drivers/scsi/spfc/common/unf_fcstruct.h | 459 ++ drivers/scsi/spfc/common/unf_gs.c | 2521 +++++++++ drivers/scsi/spfc/common/unf_gs.h | 58 + drivers/scsi/spfc/common/unf_init.c | 353 ++ drivers/scsi/spfc/common/unf_io.c | 1220 +++++ drivers/scsi/spfc/common/unf_io.h | 96 + drivers/scsi/spfc/common/unf_io_abnormal.c | 986 ++++ drivers/scsi/spfc/common/unf_io_abnormal.h | 19 + drivers/scsi/spfc/common/unf_log.h | 178 + drivers/scsi/spfc/common/unf_lport.c | 1008 ++++ drivers/scsi/spfc/common/unf_lport.h | 519 ++ drivers/scsi/spfc/common/unf_ls.c | 4883 ++++++++++++++++++ drivers/scsi/spfc/common/unf_ls.h | 61 + drivers/scsi/spfc/common/unf_npiv.c | 1005 ++++ drivers/scsi/spfc/common/unf_npiv.h | 47 + drivers/scsi/spfc/common/unf_npiv_portman.c | 360 ++ drivers/scsi/spfc/common/unf_npiv_portman.h | 17 + drivers/scsi/spfc/common/unf_portman.c | 2431 +++++++++ drivers/scsi/spfc/common/unf_portman.h | 96 + drivers/scsi/spfc/common/unf_rport.c | 2286 ++++++++ drivers/scsi/spfc/common/unf_rport.h | 301 ++ drivers/scsi/spfc/common/unf_scsi.c | 1462 ++++++ drivers/scsi/spfc/common/unf_scsi_common.h | 570 ++ drivers/scsi/spfc/common/unf_service.c | 1439 ++++++ drivers/scsi/spfc/common/unf_service.h | 66 + drivers/scsi/spfc/common/unf_type.h | 216 + drivers/scsi/spfc/hw/spfc_chipitf.c | 1105 ++++ drivers/scsi/spfc/hw/spfc_chipitf.h | 797 +++ drivers/scsi/spfc/hw/spfc_cqm_bat_cla.c | 1646 ++++++ drivers/scsi/spfc/hw/spfc_cqm_bat_cla.h | 215 + drivers/scsi/spfc/hw/spfc_cqm_bitmap_table.c | 891 ++++ drivers/scsi/spfc/hw/spfc_cqm_bitmap_table.h | 65 + drivers/scsi/spfc/hw/spfc_cqm_main.c | 1256 +++++ drivers/scsi/spfc/hw/spfc_cqm_main.h | 414 ++ drivers/scsi/spfc/hw/spfc_cqm_object.c | 958 ++++ drivers/scsi/spfc/hw/spfc_cqm_object.h | 279 + drivers/scsi/spfc/hw/spfc_hba.c | 1751 +++++++ drivers/scsi/spfc/hw/spfc_hba.h | 341 ++ drivers/scsi/spfc/hw/spfc_hw_wqe.h | 1645 ++++++ drivers/scsi/spfc/hw/spfc_io.c | 1193 +++++ drivers/scsi/spfc/hw/spfc_io.h | 138 + drivers/scsi/spfc/hw/spfc_lld.c | 997 ++++ drivers/scsi/spfc/hw/spfc_lld.h | 76 + drivers/scsi/spfc/hw/spfc_module.h | 297 ++ drivers/scsi/spfc/hw/spfc_parent_context.h | 269 + drivers/scsi/spfc/hw/spfc_queue.c | 4857 +++++++++++++++++ drivers/scsi/spfc/hw/spfc_queue.h | 711 +++ drivers/scsi/spfc/hw/spfc_service.c | 2168 ++++++++ drivers/scsi/spfc/hw/spfc_service.h | 282 + drivers/scsi/spfc/hw/spfc_utils.c | 102 + drivers/scsi/spfc/hw/spfc_utils.h | 202 + drivers/scsi/spfc/hw/spfc_wqe.c | 646 +++ drivers/scsi/spfc/hw/spfc_wqe.h | 239 + 68 files changed, 53547 insertions(+) create mode 100644 drivers/scsi/spfc/Kconfig create mode 100644 drivers/scsi/spfc/Makefile create mode 100644 drivers/scsi/spfc/common/unf_common.h create mode 100644 drivers/scsi/spfc/common/unf_disc.c create mode 100644 drivers/scsi/spfc/common/unf_disc.h create mode 100644 drivers/scsi/spfc/common/unf_event.c create mode 100644 drivers/scsi/spfc/common/unf_event.h create mode 100644 drivers/scsi/spfc/common/unf_exchg.c create mode 100644 drivers/scsi/spfc/common/unf_exchg.h create mode 100644 drivers/scsi/spfc/common/unf_exchg_abort.c create mode 100644 drivers/scsi/spfc/common/unf_exchg_abort.h create mode 100644 drivers/scsi/spfc/common/unf_fcstruct.h create mode 100644 drivers/scsi/spfc/common/unf_gs.c create mode 100644 drivers/scsi/spfc/common/unf_gs.h create mode 100644 drivers/scsi/spfc/common/unf_init.c create mode 100644 drivers/scsi/spfc/common/unf_io.c create mode 100644 drivers/scsi/spfc/common/unf_io.h create mode 100644 drivers/scsi/spfc/common/unf_io_abnormal.c create mode 100644 drivers/scsi/spfc/common/unf_io_abnormal.h create mode 100644 drivers/scsi/spfc/common/unf_log.h create mode 100644 drivers/scsi/spfc/common/unf_lport.c create mode 100644 drivers/scsi/spfc/common/unf_lport.h create mode 100644 drivers/scsi/spfc/common/unf_ls.c create mode 100644 drivers/scsi/spfc/common/unf_ls.h create mode 100644 drivers/scsi/spfc/common/unf_npiv.c create mode 100644 drivers/scsi/spfc/common/unf_npiv.h create mode 100644 drivers/scsi/spfc/common/unf_npiv_portman.c create mode 100644 drivers/scsi/spfc/common/unf_npiv_portman.h create mode 100644 drivers/scsi/spfc/common/unf_portman.c create mode 100644 drivers/scsi/spfc/common/unf_portman.h create mode 100644 drivers/scsi/spfc/common/unf_rport.c create mode 100644 drivers/scsi/spfc/common/unf_rport.h create mode 100644 drivers/scsi/spfc/common/unf_scsi.c create mode 100644 drivers/scsi/spfc/common/unf_scsi_common.h create mode 100644 drivers/scsi/spfc/common/unf_service.c create mode 100644 drivers/scsi/spfc/common/unf_service.h create mode 100644 drivers/scsi/spfc/common/unf_type.h create mode 100644 drivers/scsi/spfc/hw/spfc_chipitf.c create mode 100644 drivers/scsi/spfc/hw/spfc_chipitf.h create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_bat_cla.c create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_bat_cla.h create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_bitmap_table.c create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_bitmap_table.h create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_main.c create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_main.h create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_object.c create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_object.h create mode 100644 drivers/scsi/spfc/hw/spfc_hba.c create mode 100644 drivers/scsi/spfc/hw/spfc_hba.h create mode 100644 drivers/scsi/spfc/hw/spfc_hw_wqe.h create mode 100644 drivers/scsi/spfc/hw/spfc_io.c create mode 100644 drivers/scsi/spfc/hw/spfc_io.h create mode 100644 drivers/scsi/spfc/hw/spfc_lld.c create mode 100644 drivers/scsi/spfc/hw/spfc_lld.h create mode 100644 drivers/scsi/spfc/hw/spfc_module.h create mode 100644 drivers/scsi/spfc/hw/spfc_parent_context.h create mode 100644 drivers/scsi/spfc/hw/spfc_queue.c create mode 100644 drivers/scsi/spfc/hw/spfc_queue.h create mode 100644 drivers/scsi/spfc/hw/spfc_service.c create mode 100644 drivers/scsi/spfc/hw/spfc_service.h create mode 100644 drivers/scsi/spfc/hw/spfc_utils.c create mode 100644 drivers/scsi/spfc/hw/spfc_utils.h create mode 100644 drivers/scsi/spfc/hw/spfc_wqe.c create mode 100644 drivers/scsi/spfc/hw/spfc_wqe.h -- 2.30.0

2 2

[PATCH kernel-4.19 v6 00/23] support psi feature
by Liu Xinpeng 19 Oct '21

19 Oct '21

backport psi feature from upstream 5.4 bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 Baruch Siach (1): psi: fix reference to kernel commandline enable Dan Schatzberg (1): kernel/sched/psi.c: expose pressure metrics on root cgroup Johannes Weiner (11): sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD sched: loadavg: make calc_load_n() public sched: sched.h: make rq locking and clock functions available in stats.h sched: introduce this_rq_lock_irq() psi: pressure stall information for CPU, memory, and IO psi: cgroup support psi: make disabling/enabling easier for vendor kernels psi: fix aggregation idle shut-off psi: avoid divide-by-zero crash inside virtual machines fs: kernfs: add poll file operation sched/psi: Fix sampling error and rare div0 crashes with cgroups and high uptime Josef Bacik (1): blk-iolatency: use a percentile approache for ssd's Liu Xinpeng (2): psi:enable psi in config psi:avoid kabi change Olof Johansson (1): kernel/sched/psi.c: simplify cgroup_move_task() Suren Baghdasaryan (6): psi: introduce state_mask to represent stalled psi states psi: make psi_enable static psi: rename psi fields in preparation for psi trigger addition psi: split update_stats into parts psi: track changed states include/: refactor headers to allow kthread.h inclusion in psi_types.h Documentation/accounting/psi.txt | 73 +++ Documentation/admin-guide/cgroup-v2.rst | 18 + Documentation/admin-guide/kernel-parameters.txt | 4 + arch/arm64/configs/openeuler_defconfig | 2 + arch/powerpc/platforms/cell/cpufreq_spudemand.c | 2 +- arch/powerpc/platforms/cell/spufs/sched.c | 9 +- arch/s390/appldata/appldata_os.c | 4 - arch/x86/configs/openeuler_defconfig | 2 + block/blk-iolatency.c | 183 +++++- drivers/cpuidle/governors/menu.c | 4 - drivers/spi/spi-rockchip.c | 1 + fs/kernfs/file.c | 31 +- fs/proc/loadavg.c | 3 - include/linux/cgroup-defs.h | 12 + include/linux/cgroup.h | 17 + include/linux/kernfs.h | 8 + include/linux/kthread.h | 4 + include/linux/psi.h | 55 ++ include/linux/psi_types.h | 95 +++ include/linux/sched.h | 13 + include/linux/sched/loadavg.h | 24 +- init/Kconfig | 28 + kernel/cgroup/cgroup.c | 55 +- kernel/debug/kdb/kdb_main.c | 7 +- kernel/fork.c | 4 + kernel/kthread.c | 3 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 16 +- kernel/sched/loadavg.c | 139 ++-- kernel/sched/psi.c | 823 ++++++++++++++++++++++++ kernel/sched/sched.h | 178 ++--- kernel/sched/stats.h | 86 +++ kernel/workqueue.c | 23 + kernel/workqueue_internal.h | 6 +- mm/compaction.c | 5 + mm/filemap.c | 11 + mm/page_alloc.c | 9 + mm/vmscan.c | 9 + 38 files changed, 1726 insertions(+), 241 deletions(-) create mode 100644 Documentation/accounting/psi.txt create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h create mode 100644 kernel/sched/psi.c -- 1.8.3.1

1 22

[PATCH openEuler-5.10 0/4] Backport LTS 5.10.66
by Zheng Zengkai 19 Oct '21

19 Oct '21

Backport LTS 5.10.66 patches from upstream. Greg Kroah-Hartman (3): Revert "block: nbd: add sanity check for first_minor" Revert "posix-cpu-timers: Force next expiration recalc after itimer reset" Revert "time: Handle negative seconds correctly in timespec64_to_ns()" Sasha Levin (1): Revert "Bluetooth: Move shutdown callback before flushing tx and rx queue" drivers/block/nbd.c | 10 ---------- include/linux/time64.h | 9 ++------- kernel/time/posix-cpu-timers.c | 2 ++ net/bluetooth/hci_core.c | 8 -------- 4 files changed, 4 insertions(+), 25 deletions(-) -- 2.20.1

1 4

[PATCH openEuler-5.10 000/236] Backport LTS 5.10.65
by Zheng Zengkai 19 Oct '21

19 Oct '21

Backport LTS 5.10.65 patches from upstream. Abhishek Naik (1): iwlwifi: skip first element in the WTAS ACPI table Ahmad Fatoum (1): brcmfmac: pcie: fix oops on failure to resume and reprobe Alexander Gordeev (1): s390/kasan: fix large PMD pages address alignment check Amit Engel (1): nvmet: pass back cntlid on successful completion Anand Moon (3): ARM: dts: meson8b: odroidc1: Fix the pwm regulator supply properties ARM: dts: meson8b: mxq: Fix the pwm regulator supply properties ARM: dts: meson8b: ec100: Fix the pwm regulator supply properties Andrey Ignatov (1): bpf: Fix possible out of bound write in narrow load handling Andrii Nakryiko (1): libbpf: Re-build libbpf.so when libbpf.map changes Andy Duan (1): tty: serial: fsl_lpuart: fix the wrong mapbase value Andy Shevchenko (1): leds: lt3593: Put fwnode in any case during ->probe() Austin Kim (1): IMA: remove -Wmissing-prototypes warning Aya Levin (1): net/mlx5: Register to devlink ingress VLAN filter trap Babu Moger (1): x86/resctrl: Fix a maybe-uninitialized build warning treated as error Ben Hutchings (1): crypto: omap - Fix inconsistent locking of device lists Benjamin Coddington (1): lockd: Fix invalid lockowner cast after vfs_test_lock Biju Das (1): arm64: dts: renesas: hihope-rzg2-ex: Add EtherAVB internal rx delay Bjorn Andersson (1): soc: qcom: rpmhpd: Use corner in power_off Bob Peterson (1): gfs2: init system threads before freeze lock Borislav Petkov (1): x86/mce: Defer processing of early errors Brett Creeley (1): ice: Only lock to update netdev dev_addr Cezary Rojewski (3): ASoC: Intel: kbl_da7219_max98927: Fix format selection for max98373 ASoC: Intel: Skylake: Leave data as is when invoking TLV IPCs ASoC: Intel: Skylake: Fix module resource and format selection Chen-Yu Tsai (3): irqchip/gic-v3: Fix priority comparison when non-secure priorities are used regulator: vctrl: Use locked regulator_get_voltage in probe path regulator: vctrl: Avoid lockdep warning in enable/disable ops Chih-Kang Chang (1): mac80211: Fix insufficient headroom issue for AMSDU Christoph Hellwig (1): bcache: add proper error unwinding in bcache_device_init Christophe JAILLET (9): spi: coldfire-qspi: Use clk_disable_unprepare in the remove function media: cxd2880-spi: Fix an error handling path drm/msm/dsi: Fix some reference counted resource leaks firmware: raspberrypi: Fix a leak in 'rpi_firmware_get()' usb: bdc: Fix an error handling path in 'bdc_probe()' when no suitable DMA config is available usb: bdc: Fix a resource leak in the error handling path of 'bdc_probe()' ASoC: wcd9335: Fix a double irq free in the remove function ASoC: wcd9335: Fix a memory leak in the error handling path of the probe function ASoC: wcd9335: Disable irq on slave ports in the remove function Chunguang Xu (1): blk-throtl: optimize IOPS throttle for large IO scenarios Chunyan Zhang (1): spi: sprd: Fix the wrong WDG_LOAD_VAL Claudiu Beznea (1): ARM: dts: at91: add pinctrl-{names, 0} for all gpios Colin Ian King (4): gfs2: Fix memory leak of object lsi on error return path 6lowpan: iphc: Fix an off-by-one check of array index media: venus: venc: Fix potential null pointer dereference on pointer fmt Bluetooth: increase BTNAMSIZ to 21 chars to fix potential buffer overflow Curtis Malainey (1): ASoC: Intel: Fix platform ID matching Damien Le Moal (1): libata: fix ata_host_start() Dan Carpenter (5): media: rockchip/rga: fix error handling in probe Bluetooth: sco: prevent information leak in sco_conn_defer_accept() rsi: fix error code in rsi_load_9116_firmware() rsi: fix an error code in rsi_probe() ath6kl: wmi: fix an error code in ath6kl_wmi_sync_point() Daniel Thompson (1): backlight: pwm_bl: Improve bootloader/kernel device handover David Heidelberg (2): drm/msm/mdp4: refactor HW revision detection into read_mdp_hw_revision drm/msm/mdp4: move HW revision detection to earlier phase Desmond Cheong Zhi Xi (2): fcntl: fix potential deadlock for &fasync_struct.fa_lock Bluetooth: fix repeated calls to sco_sock_kill Dietmar Eggemann (1): sched/deadline: Fix missing clock update in migrate_task_rq_dl() Dmitry Baryshkov (1): drm/msm/dpu: make dpu_hw_ctl_clear_all_blendstages clear necessary LMs Dmitry Osipenko (2): regulator: tps65910: Silence deferred probe error power: supply: smb347-charger: Add missing pin control activation Dongliang Mu (4): media: dvb-usb: fix uninit-value in dvb_usb_adapter_dvb_init media: dvb-usb: fix uninit-value in vp702x_read_mac_addr media: dvb-usb: Fix error handling in dvb_usb_i2c_init media: em28xx-input: fix refcount bug in em28xx_usb_disconnect Douglas Anderson (2): ASoC: rt5682: Properly turn off regulators if wrong device ID ASoC: rt5682: Remove unused variable in rt5682_i2c_remove() Dylan Hung (1): ARM: dts: aspeed-g6: Fix HVI3C function-group in pinctrl dtsi Emmanuel Grumbach (1): iwlwifi: follow the new inclusive terminology Eric Biggers (1): blk-crypto: fix check for too-large dun_bytes Eric Dumazet (3): ipv6: make exception cache less predictible ipv4: make exception cache less predictible ipv4: fix endianness issue in inet_rtm_getroute_build_skb() Evgeny Novikov (1): usb: ehci-orion: Handle errors of clk_prepare_enable() in probe Frederic Weisbecker (1): posix-cpu-timers: Force next expiration recalc after itimer reset Geert Uytterhoeven (5): m68k: Fix invalid RMW_INSNS on CPUs that lack CAS soc: rockchip: ROCKCHIP_GRF should not default to y, unconditionally arm64: dts: renesas: r8a77995: draak: Remove bogus adv7511w properties arm64: dts: renesas: rzg2: Convert EtherAVB to explicit delay handling usb: gadget: udc: renesas_usb3: Fix soc_device_match() abuse Giovanni Cabiddu (4): crypto: qat - do not ignore errors from enable_vf2pf_comms() crypto: qat - handle both source of interrupt in VF ISR crypto: qat - do not export adf_iov_putmsg() crypto: qat - use proper type for vf_mask Haiyue Wang (1): gve: fix the wrong AdminQ buffer overflow check Halil Pasic (1): KVM: s390: index kvm->arch.idle_mask by vcpu_idx Hans de Goede (2): power: supply: axp288_fuel_gauge: Report register-address on readb / writeb errors leds: trigger: audio: Add an activate callback to ensure the initial brightness is set Harald Freudenberger (2): s390/zcrypt: fix wrong offset index for APKA master key valid state s390/ap: fix state machine hang after failure to enable irq Harshvardhan Jha (1): drm/gma500: Fix end of loop tests for list_for_each_entry He Fengqing (1): bpf: Fix potential memleak and UAF in the verifier. Hongbo Li (1): lib/mpi: use kcalloc in mpi_resize Huacai Chen (1): irqchip/loongson-pch-pic: Improve edge triggered interrupt support Ilya Leoshkevich (1): selftests/bpf: Fix test_core_autosize on big-endian machines J. Bruce Fields (1): nfsd4: Fix forced-expiry locking Jaegeuk Kim (1): f2fs: guarantee to write dirty data when enabling checkpoint back Jan Kara (1): udf: Check LVID earlier Jens Axboe (1): io_uring: IORING_OP_WRITE needs hash_reg_file set Jeongtae Park (1): regmap: fix the offset of register error log Jiapeng Chong (2): leds: is31fl32xx: Fix missing error code in is31fl32xx_parse_dt() net/mlx5: Fix missing return value in mlx5_devlink_eswitch_inline_mode_set() Jose Blanquicet (1): selftests/bpf: Fix bpf-iter-tcp4 test to print correctly the dest IP Juhee Kang (1): samples: pktgen: add missing IPv6 option to pktgen scripts Julia Lawall (1): drm/of: free the right object Justin M. Forbes (1): iwlwifi Add support for ax201 in Samsung Galaxy Book Flex2 Alpha Kai-Heng Feng (2): drm/amdgpu/acp: Make PM domain really work Bluetooth: Move shutdown callback before flushing tx and rx queue Kevin Mitchell (1): lkdtm: replace SCSI_DISPATCH_CMD with SCSI_QUEUE_RQ Kim Phillips (1): perf/x86/amd/ibs: Extend PERF_PMU_CAP_NO_EXCLUDE to IBS Op Krzysztof Hałasa (1): media: TDA1997x: enable EDID support Krzysztof Kozlowski (1): arm64: dts: exynos: correct GIC CPU interfaces address range on Exynos7 Kuniyuki Iwashima (1): bpf: Fix a typo of reuseport map in bpf.h. Len Baker (1): CIFS: Fix a potencially linear read overflow Leon Romanovsky (3): ionic: cleanly release devlink instance devlink: Break parameter notification sequence to be before/after unload/load driver devlink: Clear whole devlink_flash_notify struct Linus Walleij (1): clk: kirkwood: Fix a clocking boot regression Lukas Bulwahn (1): clk: staging: correct reference to config IOMEM to config HAS_IOMEM Lukas Hannen (1): time: Handle negative seconds correctly in timespec64_to_ns() Lukasz Luba (1): PM: EM: Increase energy calculation precision Marco Chiappero (2): crypto: qat - fix reuse of completion variable crypto: qat - fix naming for init/shutdown VF to PF notifications Marek Vasut (3): drm: mxsfb: Enable recovery on underflow drm: mxsfb: Increase number of outstanding requests on V4 and newer HW drm: mxsfb: Clear FIFO_CLEAR bit Martin Blumenstingl (1): ARM: dts: meson8: Use a higher default GPU clock frequency Martin KaFai Lau (1): tcp: seq_file: Avoid skipping sk during tcp_seek_last_pos Martynas Pumputis (1): libbpf: Fix removal of inner map in bpf_object__create_map Matija Glavinic Pecotic (1): spi: davinci: invoke chipselect callback Matthew Cover (1): bpf, samples: Add missing mprog-disable to xdp_redirect_cpu's optstring Mauro Carvalho Chehab (1): media: rockchip/rga: use pm_runtime_resume_and_get() Maxim Levitsky (1): KVM: VMX: avoid running vmx_handle_exit_irqoff in case of emulation Maxim Mikityanskiy (2): net/mlx5e: Prohibit inner indir TIRs in IPoIB net/mlx5e: Block LRO if firmware asks for tunneled LRO Mika Penttilä (1): sched/numa: Fix is_core_idle() Miklos Szeredi (2): fuse: truncate pagecache on atomic_o_trunc fuse: flush extending writes Ming Lei (1): block: return ELEVATOR_DISCARD_MERGE if possible Nadezda Lutovinova (1): usb: gadget: mv_u3d: request_irq() after initializing UDC Nguyen Dinh Phi (1): tty: Fix data race between tiocsti() and flush_to_ldisc() Nicolas Saenz Julienne (1): firmware: raspberrypi: Keep count of all consumers Niklas Schnelle (1): s390/pci: fix misleading rc in clp_set_pci_fn() Pali Rohár (3): udf: Fix iocharset=utf8 mount option isofs: joliet: Fix iocharset=utf8 mount option arm64: dts: marvell: armada-37xx: Extend PCIe MEM space Parav Pandit (1): net/mlx5: Fix unpublish devlink parameters Paul E. McKenney (1): rcu: Add lockdep_assert_irqs_disabled() to rcu_sched_clock_irq() and callees Pavel Begunkov (1): bio: fix page leak bio_add_hw_page failure Pavel Skripkin (6): m68k: emu: Fix invalid free in nfeth_cleanup() block: nbd: add sanity check for first_minor media: go7007: fix memory leak in go7007_usb_probe media: go7007: remove redundant initialization net: cipso: fix warnings in netlbl_cipsov4_add_std Bluetooth: add timeout sanity check to hci_inquiry Peter Oberparleiter (2): s390/debug: keep debug data on resize s390/debug: fix debug area life cycle Peter Robinson (1): power: supply: cw2015: use dev_err_probe to allow deferred probe Peter Zijlstra (2): locking/mutex: Fix HANDOFF condition locking/lockdep: Mark local_lock_t Philipp Zabel (1): media: coda: fix frame_mem_ctrl for YUV420 and YVU420 formats Phong Hoang (1): clocksource/drivers/sh_cmt: Fix wrong setting if don't request IRQ for clock source channel Qiuxu Zhuo (1): EDAC/i10nm: Fix NVDIMM detection Quanyang Wang (1): spi: spi-zynq-qspi: use wait_for_completion_timeout to make zynq_qspi_exec_mem_op not interruptible Quentin Perret (2): sched/deadline: Fix reset_on_fork reporting of DL tasks sched: Fix UCLAMP_FLAG_IDLE setting Rafael J. Wysocki (2): PCI: PM: Avoid forcing PCI_D0 for wakeup reasons inconsistently PCI: PM: Enable PME if it can be signaled from D3cold Ruozhu Li (2): nvme-tcp: don't update queue count when failing to set io queues nvme-rdma: don't update queue count when failing to set io queues Sean Anderson (1): crypto: mxs-dcp - Check for DMA mapping errors Sean Christopherson (2): Revert "KVM: x86: mmu: Add guest physical address check in translate_gpa()" KVM: nVMX: Unconditionally clear nested.pi_pending on nested VM-Enter Sebastian Krzyszkowiak (1): power: supply: max17042_battery: fix typo in MAx17042_TOFF Sergey Senozhatsky (1): rcu/tree: Handle VM stoppage in stall detection Sergey Shtylyov (15): i2c: highlander: add IRQ check usb: dwc3: meson-g12a: add IRQ check usb: dwc3: qcom: add IRQ check usb: gadget: udc: at91: add IRQ check usb: gadget: udc: s3c2410: add IRQ check usb: phy: fsl-usb: add IRQ check usb: phy: twl6030: add IRQ checks usb: host: ohci-tmio: add IRQ check usb: phy: tahvo: add IRQ check i2c: synquacer: fix deferred probing i2c: iop3xx: fix deferred probing i2c: s3c2410: fix IRQ check i2c: hix5hd2: fix IRQ check i2c: mt65xx: fix IRQ check i2c: xlp9xx: fix main IRQ check Shuyi Cheng (1): libbpf: Fix the possible memory leak on error Smita Koralahalli (1): EDAC/mce_amd: Do not load edac_mce_amd module on guests Stefan Assmann (1): i40e: improve locking of mac_filter_hash Stefan Berger (2): certs: Trigger creation of RSA module signing key if it's not an RSA key tpm: ibmvtpm: Avoid error message when process gets signal while waiting Stefan Wahren (1): net: qualcomm: fix QCA7000 checksum handling Stephan Gerhold (1): soc: qcom: smsm: Fix missed interrupts if state changes while masked Stephen Boyd (1): ASoC: rt5682: Implement remove callback Steven Price (1): drm/of: free the iterator object on failure Stian Skjelstad (1): udf_get_extendedattr() had no boundary checks. Subbaraya Sundeep (2): octeontx2-af: Fix loop in free and unmap counter octeontx2-af: Fix static code analyzer reported issues Sudarsana Reddy Kalluru (1): atlantic: Fix driver resume flow. Sunil Goutham (1): octeontx2-af: Set proper errorcode for IPv4 checksum errors Sven Eckelmann (1): debugfs: Return error during {full/open}_proxy_open() on rmmod THOBY Simon (1): IMA: remove the dependency on CRYPTO_MD5 Tedd Ho-Jeong An (1): Bluetooth: mgmt: Fix wrong opcode in the response for add_adv cmd Tetsuo Handa (1): fbmem: don't allow too huge resolutions Thomas Gleixner (3): hrtimer: Avoid double reprogramming in __hrtimer_start_range_ns() hrtimer: Ensure timerfd notification for HIGHRES=n locking/local_lock: Add missing owner initialization Tian Tao (1): i2c: fix platform_get_irq.cocci warnings Tony Lindgren (6): crypto: omap-sham - clear dma flags only after omap_sham_update_dma_stop() spi: spi-fsl-dspi: Fix issue with uninitialized dma_slave_config spi: spi-pic32: Fix issue with uninitialized dma_slave_config mmc: sdhci: Fix issue with uninitialized dma_slave_config mmc: dw_mmc: Fix issue with uninitialized dma_slave_config mmc: moxart: Fix issue with uninitialized dma_slave_config Valentin Schneider (1): PM: cpu: Make notifier chain use a raw_spinlock_t Vineeth Vijayan (1): s390/cio: add dev_busid sysfs entry for each subchannel Waiman Long (3): cgroup/cpuset: Fix a partition bug with hotplug cgroup/cpuset: Miscellaneous code cleanup cgroup/cpuset: Fix violation of cpuset locking rule Wei Yongjun (1): drm/panfrost: Fix missing clk_disable_unprepare() on error in panfrost_clk_init() William Breathitt Gray (1): counter: 104-quad-8: Return error when invalid mode during ceiling_write Xiyu Yang (1): net: sched: Fix qdisc_rate_table refcount leak when get tcf_block failed Xu Yu (1): mm/swap: consider max pages in iomap_swapfile_add_extent Yanfei Xu (2): rcu: Fix to include first blocked task in stall warning rcu: Fix stall-warning deadlock due to non-release of rcu_node ->lock Yizhuo (1): media: atomisp: fix the uninitialized use and rename "retvalue" Zelin Deng (1): KVM: x86: Update vCPU's hv_clock before back to guest when tsc_offset is adjusted Zenghui Yu (1): bcma: Fix memory leak for internally-handled cores Zhang Qilong (1): ASoC: mediatek: mt8183: Fix Unbalanced pm_runtime_enable in mt8183_afe_pcm_dev_probe Zhen Lei (3): genirq/timings: Fix error return code in irq_timings_test_irqs() firmware: fix theoretical UAF race with firmware cache and resume driver core: Fix error return code in really_probe() .../fault-injection/provoke-crashes.rst | 2 +- arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi | 4 +- arch/arm/boot/dts/at91-sam9x60ek.dts | 16 +- arch/arm/boot/dts/at91-sama5d3_xplained.dts | 29 +++ arch/arm/boot/dts/at91-sama5d4_xplained.dts | 19 ++ arch/arm/boot/dts/meson8.dtsi | 5 + arch/arm/boot/dts/meson8b-ec100.dts | 4 +- arch/arm/boot/dts/meson8b-mxq.dts | 4 +- arch/arm/boot/dts/meson8b-odroidc1.dts | 4 +- arch/arm64/boot/dts/exynos/exynos7.dtsi | 2 +- .../dts/marvell/armada-3720-turris-mox.dts | 17 ++ arch/arm64/boot/dts/marvell/armada-37xx.dtsi | 11 +- .../boot/dts/renesas/beacon-renesom-som.dtsi | 3 +- .../boot/dts/renesas/hihope-rzg2-ex.dtsi | 3 +- arch/arm64/boot/dts/renesas/r8a774a1.dtsi | 2 + arch/arm64/boot/dts/renesas/r8a774b1.dtsi | 2 + arch/arm64/boot/dts/renesas/r8a774c0.dtsi | 1 + arch/arm64/boot/dts/renesas/r8a774e1.dtsi | 2 + .../arm64/boot/dts/renesas/r8a77995-draak.dts | 4 - arch/m68k/Kconfig.cpu | 8 +- arch/m68k/emu/nfeth.c | 4 +- arch/s390/include/asm/kvm_host.h | 1 + arch/s390/kernel/debug.c | 176 +++++++++++------- arch/s390/kvm/interrupt.c | 12 +- arch/s390/kvm/kvm-s390.c | 2 +- arch/s390/kvm/kvm-s390.h | 2 +- arch/s390/mm/kasan_init.c | 41 ++-- arch/s390/pci/pci.c | 7 +- arch/s390/pci/pci_clp.c | 33 ++-- arch/x86/events/amd/ibs.c | 1 + arch/x86/include/asm/mce.h | 1 + arch/x86/kernel/cpu/mce/core.c | 11 +- arch/x86/kernel/cpu/resctrl/monitor.c | 6 + arch/x86/kvm/mmu/mmu.c | 6 - arch/x86/kvm/vmx/nested.c | 7 +- arch/x86/kvm/vmx/vmx.c | 3 + arch/x86/kvm/x86.c | 4 + block/bfq-iosched.c | 3 + block/bio.c | 15 +- block/blk-crypto.c | 2 +- block/blk-merge.c | 18 +- block/blk-throttle.c | 32 ++++ block/blk.h | 2 + block/elevator.c | 3 + block/mq-deadline.c | 2 + certs/Makefile | 8 + drivers/ata/libata-core.c | 2 +- drivers/base/dd.c | 16 +- drivers/base/firmware_loader/main.c | 20 +- drivers/base/regmap/regmap.c | 2 +- drivers/bcma/main.c | 6 +- drivers/block/nbd.c | 10 + drivers/char/tpm/tpm_ibmvtpm.c | 26 +-- drivers/char/tpm/tpm_ibmvtpm.h | 2 +- drivers/clk/mvebu/kirkwood.c | 1 + drivers/clocksource/sh_cmt.c | 30 +-- drivers/counter/104-quad-8.c | 5 +- drivers/crypto/mxs-dcp.c | 45 ++++- drivers/crypto/omap-aes.c | 8 +- drivers/crypto/omap-des.c | 8 +- drivers/crypto/omap-sham.c | 14 +- .../qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.c | 4 +- .../qat/qat_c62xvf/adf_c62xvf_hw_data.c | 4 +- .../crypto/qat/qat_common/adf_common_drv.h | 8 +- drivers/crypto/qat/qat_common/adf_init.c | 5 +- drivers/crypto/qat/qat_common/adf_isr.c | 7 +- drivers/crypto/qat/qat_common/adf_pf2vf_msg.c | 3 +- drivers/crypto/qat/qat_common/adf_vf2pf_msg.c | 12 +- drivers/crypto/qat/qat_common/adf_vf_isr.c | 7 +- .../qat_dh895xccvf/adf_dh895xccvf_hw_data.c | 4 +- drivers/edac/i10nm_base.c | 6 +- drivers/edac/mce_amd.c | 3 + drivers/firmware/raspberrypi.c | 46 ++++- drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c | 54 +++--- drivers/gpu/drm/drm_of.c | 6 +- drivers/gpu/drm/gma500/oaktrail_lvds.c | 2 +- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c | 10 +- drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c | 68 ++++--- drivers/gpu/drm/msm/dsi/dsi.c | 6 +- drivers/gpu/drm/mxsfb/mxsfb_drv.c | 3 + drivers/gpu/drm/mxsfb/mxsfb_drv.h | 1 + drivers/gpu/drm/mxsfb/mxsfb_kms.c | 40 ++++ drivers/gpu/drm/mxsfb/mxsfb_regs.h | 9 + drivers/gpu/drm/panfrost/panfrost_device.c | 3 +- drivers/i2c/busses/i2c-highlander.c | 2 +- drivers/i2c/busses/i2c-hix5hd2.c | 4 +- drivers/i2c/busses/i2c-iop3xx.c | 6 +- drivers/i2c/busses/i2c-mt65xx.c | 2 +- drivers/i2c/busses/i2c-s3c2410.c | 2 +- drivers/i2c/busses/i2c-synquacer.c | 2 +- drivers/i2c/busses/i2c-xlp9xx.c | 2 +- drivers/irqchip/irq-gic-v3.c | 23 ++- drivers/irqchip/irq-loongson-pch-pic.c | 19 +- drivers/leds/leds-is31fl32xx.c | 1 + drivers/leds/leds-lt3593.c | 5 +- drivers/leds/trigger/ledtrig-audio.c | 37 +++- drivers/md/bcache/super.c | 16 +- drivers/media/i2c/tda1997x.c | 1 + drivers/media/platform/coda/coda-bit.c | 18 +- drivers/media/platform/qcom/venus/venc.c | 2 + drivers/media/platform/rockchip/rga/rga-buf.c | 3 +- drivers/media/platform/rockchip/rga/rga.c | 29 ++- drivers/media/spi/cxd2880-spi.c | 7 +- drivers/media/usb/dvb-usb/dvb-usb-i2c.c | 9 +- drivers/media/usb/dvb-usb/dvb-usb-init.c | 2 +- drivers/media/usb/dvb-usb/nova-t-usb2.c | 6 +- drivers/media/usb/dvb-usb/vp702x.c | 12 +- drivers/media/usb/em28xx/em28xx-input.c | 1 - drivers/media/usb/go7007/go7007-driver.c | 26 --- drivers/media/usb/go7007/go7007-usb.c | 2 +- drivers/misc/lkdtm/core.c | 2 +- drivers/mmc/host/dw_mmc.c | 1 + drivers/mmc/host/moxart-mmc.c | 1 + drivers/mmc/host/sdhci.c | 1 + .../ethernet/aquantia/atlantic/aq_pci_func.c | 3 + drivers/net/ethernet/google/gve/gve_adminq.c | 6 +- .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 23 ++- drivers/net/ethernet/intel/ice/ice_main.c | 13 +- .../ethernet/marvell/octeontx2/af/rvu_npc.c | 16 +- .../net/ethernet/mellanox/mlx5/core/devlink.c | 52 ++++++ .../net/ethernet/mellanox/mlx5/core/en/fs.h | 6 - .../net/ethernet/mellanox/mlx5/core/en_fs.c | 10 +- .../net/ethernet/mellanox/mlx5/core/en_main.c | 15 ++ .../mellanox/mlx5/core/eswitch_offloads.c | 5 +- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 18 +- .../ethernet/pensando/ionic/ionic_devlink.c | 14 +- drivers/net/ethernet/qualcomm/qca_spi.c | 2 +- drivers/net/ethernet/qualcomm/qca_uart.c | 2 +- drivers/net/wireless/ath/ath6kl/wmi.c | 4 +- .../broadcom/brcm80211/brcmfmac/pcie.c | 2 +- drivers/net/wireless/intel/iwlwifi/fw/acpi.c | 32 ++-- drivers/net/wireless/intel/iwlwifi/fw/acpi.h | 10 +- .../wireless/intel/iwlwifi/fw/api/commands.h | 2 +- .../wireless/intel/iwlwifi/fw/api/nvm-reg.h | 8 +- .../net/wireless/intel/iwlwifi/fw/api/scan.h | 12 +- drivers/net/wireless/intel/iwlwifi/fw/file.h | 2 +- .../net/wireless/intel/iwlwifi/iwl-config.h | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 6 +- .../net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 10 +- .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 13 +- drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 24 +-- drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 1 + drivers/net/wireless/rsi/rsi_91x_hal.c | 4 +- drivers/net/wireless/rsi/rsi_91x_usb.c | 1 + drivers/nvme/host/rdma.c | 4 +- drivers/nvme/host/tcp.c | 4 +- drivers/nvme/target/fabrics-cmd.c | 9 +- drivers/pci/pci.c | 25 ++- drivers/power/supply/axp288_fuel_gauge.c | 4 +- drivers/power/supply/cw2015_battery.c | 4 +- drivers/power/supply/max17042_battery.c | 2 +- drivers/power/supply/smb347-charger.c | 10 + drivers/regulator/tps65910-regulator.c | 10 +- drivers/regulator/vctrl-regulator.c | 73 +++++--- drivers/s390/cio/css.c | 17 ++ drivers/s390/crypto/ap_bus.c | 25 +-- drivers/s390/crypto/ap_bus.h | 10 +- drivers/s390/crypto/ap_queue.c | 20 +- drivers/s390/crypto/zcrypt_ccamisc.c | 8 +- drivers/soc/qcom/rpmhpd.c | 5 +- drivers/soc/qcom/smsm.c | 11 +- drivers/soc/rockchip/Kconfig | 4 +- drivers/spi/spi-coldfire-qspi.c | 2 +- drivers/spi/spi-davinci.c | 8 +- drivers/spi/spi-fsl-dspi.c | 1 + drivers/spi/spi-pic32.c | 1 + drivers/spi/spi-sprd-adi.c | 2 +- drivers/spi/spi-zynq-qspi.c | 8 +- drivers/staging/clocking-wizard/Kconfig | 2 +- .../media/atomisp/i2c/atomisp-mt9m114.c | 11 +- drivers/tty/serial/fsl_lpuart.c | 2 +- drivers/tty/tty_io.c | 4 +- drivers/usb/dwc3/dwc3-meson-g12a.c | 2 + drivers/usb/dwc3/dwc3-qcom.c | 4 + drivers/usb/gadget/udc/at91_udc.c | 4 +- drivers/usb/gadget/udc/bdc/bdc_core.c | 30 +-- drivers/usb/gadget/udc/mv_u3d_core.c | 19 +- drivers/usb/gadget/udc/renesas_usb3.c | 17 +- drivers/usb/gadget/udc/s3c2410_udc.c | 4 + drivers/usb/host/ehci-orion.c | 8 +- drivers/usb/host/ohci-tmio.c | 3 + drivers/usb/phy/phy-fsl-usb.c | 2 + drivers/usb/phy/phy-tahvo.c | 4 +- drivers/usb/phy/phy-twl6030-usb.c | 5 + drivers/video/backlight/pwm_bl.c | 54 +++--- drivers/video/fbdev/core/fbmem.c | 6 + fs/cifs/cifs_unicode.c | 9 +- fs/debugfs/file.c | 8 +- fs/f2fs/file.c | 5 +- fs/f2fs/super.c | 11 +- fs/fcntl.c | 5 +- fs/fuse/file.c | 9 +- fs/gfs2/ops_fstype.c | 43 +++++ fs/gfs2/super.c | 61 +----- fs/io_uring.c | 1 + fs/iomap/swapfile.c | 6 + fs/isofs/inode.c | 27 ++- fs/isofs/isofs.h | 1 - fs/isofs/joliet.c | 4 +- fs/lockd/svclock.c | 2 +- fs/nfsd/nfs4state.c | 4 +- fs/udf/misc.c | 13 +- fs/udf/super.c | 75 ++++---- fs/udf/udf_sb.h | 2 - fs/udf/unicode.c | 4 +- include/linux/blkdev.h | 16 ++ include/linux/energy_model.h | 16 ++ include/linux/hrtimer.h | 5 - include/linux/local_lock_internal.h | 39 ++-- include/linux/lockdep.h | 15 +- include/linux/lockdep_types.h | 18 +- include/linux/mlx5/mlx5_ifc.h | 3 +- include/linux/power/max17042_battery.h | 2 +- include/linux/time64.h | 9 +- include/soc/bcm2835/raspberrypi-firmware.h | 2 + include/uapi/linux/bpf.h | 2 +- kernel/bpf/verifier.c | 31 +-- kernel/cgroup/cpuset.c | 95 ++++++---- kernel/cpu_pm.c | 50 +++-- kernel/irq/timings.c | 2 + kernel/locking/lockdep.c | 16 +- kernel/locking/mutex.c | 15 +- kernel/power/energy_model.c | 4 +- kernel/rcu/tree.c | 4 + kernel/rcu/tree_plugin.h | 1 + kernel/rcu/tree_stall.h | 34 +++- kernel/sched/core.c | 25 ++- kernel/sched/deadline.c | 8 +- kernel/sched/fair.c | 2 +- kernel/sched/sched.h | 2 + kernel/time/hrtimer.c | 92 ++++++--- kernel/time/posix-cpu-timers.c | 2 - kernel/time/tick-internal.h | 3 + lib/mpi/mpiutil.c | 2 +- net/6lowpan/debugfs.c | 3 +- net/bluetooth/cmtp/cmtp.h | 2 +- net/bluetooth/hci_core.c | 14 ++ net/bluetooth/mgmt.c | 2 +- net/bluetooth/sco.c | 11 +- net/core/devlink.c | 36 ++-- net/ipv4/route.c | 48 +++-- net/ipv4/tcp_ipv4.c | 5 +- net/ipv6/route.c | 5 +- net/mac80211/tx.c | 4 +- net/netlabel/netlabel_cipso_v4.c | 8 +- net/sched/sch_cbq.c | 2 +- samples/bpf/xdp_redirect_cpu_user.c | 2 +- samples/pktgen/pktgen_sample04_many_flows.sh | 12 +- .../pktgen/pktgen_sample05_flow_per_thread.sh | 12 +- security/integrity/ima/Kconfig | 1 - security/integrity/ima/ima_mok.c | 2 +- sound/soc/codecs/rt5682-i2c.c | 20 ++ sound/soc/codecs/wcd9335.c | 23 ++- sound/soc/intel/boards/kbl_da7219_max98927.c | 55 +----- .../intel/common/soc-acpi-intel-cml-match.c | 2 +- .../intel/common/soc-acpi-intel-kbl-match.c | 2 +- sound/soc/intel/skylake/skl-topology.c | 25 +-- sound/soc/mediatek/mt8183/mt8183-afe-pcm.c | 43 +++-- tools/include/uapi/linux/bpf.h | 2 +- tools/lib/bpf/Makefile | 10 +- tools/lib/bpf/libbpf.c | 16 +- .../selftests/bpf/progs/bpf_iter_tcp4.c | 2 +- .../selftests/bpf/progs/test_core_autosize.c | 20 +- 263 files changed, 2072 insertions(+), 1182 deletions(-) -- 2.20.1

1 236

[PATCH openEuler-5.10 00/23] Backport LTS 5.10.64
by Zheng Zengkai 19 Oct '21

19 Oct '21

Backport LTS 5.10.64 patches from upstream. Alexander Tsoy (1): ALSA: usb-audio: Add registration quirk for JBL Quantum 800 Chunfeng Yun (4): usb: gadget: tegra-xudc: fix the wrong mult value for HS isoc or intr usb: mtu3: restore HS function when set SS/SSP usb: mtu3: use @mult for HS isoc or intr usb: mtu3: fix the wrong HS mult value Esben Haabendal (1): net: ll_temac: Remove left-over debug message Hayes Wang (1): Revert "r8169: avoid link-up interrupt issue on RTL8106e if user enables ASPM" Jiri Slaby (1): tty: drop termiox user definitions Marek Behún (1): PCI: Call Max Payload Size-related fixup quirks early Mathias Nyman (2): xhci: fix even more unsafe memory usage in xhci tracing xhci: fix unsafe memory usage in xhci tracing Ming Lei (3): blk-mq: fix kernel panic during iterating over flush request blk-mq: fix is_flush_rq blk-mq: clearing flush request reference in tags->rqs[] Pablo Neira Ayuso (2): netfilter: nf_tables: initialize set before expression setup netfilter: nftables: clone set element expression template Paul Gortmaker (1): x86/reboot: Limit Dell Optiplex 990 quirk to early BIOS versions Randy Dunlap (2): net: kcov: don't select SKB_EXTENSIONS when there is no NET net: linux/skbuff.h: combine SKB_EXTENSIONS + KCOV handling Suravee Suthikulpanit (1): x86/events/amd/iommu: Fix invalid Perf result due to IOMMU PMC power-gating Tom Rix (1): USB: serial: mos7720: improve OOM-handling in read_mos_reg() Vignesh Raghavendra (1): serial: 8250: 8250_omap: Fix unused variable warning Yoshihiro Shimoda (1): usb: host: xhci-rcar: Don't reload firmware after the completion arch/x86/events/amd/iommu.c | 47 ++++++------ arch/x86/kernel/reboot.c | 3 +- block/blk-core.c | 1 - block/blk-flush.c | 13 ++++ block/blk-mq.c | 37 +++++++++- block/blk.h | 6 +- drivers/net/ethernet/realtek/r8169_main.c | 1 + drivers/net/ethernet/xilinx/ll_temac_main.c | 4 +- drivers/pci/quirks.c | 12 +-- drivers/tty/serial/8250/8250_omap.c | 26 +++---- drivers/usb/gadget/udc/tegra-xudc.c | 4 +- drivers/usb/host/xhci-debugfs.c | 14 +++- drivers/usb/host/xhci-rcar.c | 7 ++ drivers/usb/host/xhci-ring.c | 3 +- drivers/usb/host/xhci-trace.h | 26 ++++--- drivers/usb/host/xhci.h | 73 +++++++++--------- drivers/usb/mtu3/mtu3_core.c | 4 +- drivers/usb/mtu3/mtu3_gadget.c | 6 +- drivers/usb/serial/mos7720.c | 4 +- include/linux/skbuff.h | 4 +- include/uapi/linux/termios.h | 15 ---- lib/Kconfig.debug | 2 +- net/netfilter/nf_tables_api.c | 82 +++++++++++++-------- sound/usb/quirks.c | 1 + 24 files changed, 234 insertions(+), 161 deletions(-) -- 2.20.1

1 23

[PATCH openEuler-5.10 0/2] livepatch: Add klp_{register,unregister}
by Zheng Zengkai 19 Oct '21

19 Oct '21

livepatch: Add klp_{register,unregister}_patch for stop_machine model. Yang Jihong (2): livepatch: Add klp_{register,unregister}_patch for stop_machine model livepatch: Adapt livepatch-sample for stop_machine model include/linux/livepatch.h | 15 +- kernel/livepatch/core.c | 257 ++++++++++++++++++++------- samples/livepatch/livepatch-sample.c | 37 ++++ 3 files changed, 239 insertions(+), 70 deletions(-) -- 2.20.1

1 2

[PATCH openEuler-5.10 00/27] Backport LTS 5.10.63
by Zheng Zengkai 19 Oct '21

19 Oct '21

Backport LTS 5.10.63 patches from upstream. Al Viro (1): new helper: inode_wrong_type() Amir Goldstein (1): fuse: fix illegal access to inode with reused nodeid Andy Shevchenko (1): spi: Switch to signed types for *_native_cs SPI controller fields Christoph Hellwig (1): cryptoloop: add a deprecation warning Eric Biggers (4): fscrypt: add fscrypt_symlink_getattr() for computing st_size ext4: report correct st_size for encrypted symlinks f2fs: report correct st_size for encrypted symlinks ubifs: report correct st_size for encrypted symlinks Greg Kroah-Hartman (3): Revert "ucounts: Increase ucounts reference counter before the security hook" Revert "cred: add missing return error code when set_cred_ucounts() failed" Revert "Add a reference to ucounts for each cred" Harini Katakam (1): net: macb: Add a NULL check on desc_ptp Johnathon Clark (1): ALSA: hda/realtek: Quirk for HP Spectre x360 14 amp setup Kim Phillips (2): perf/x86/amd/ibs: Work around erratum #1197 perf/x86/amd/power: Assign pmu.module Krzysztof Hałasa (1): gpu: ipu-v3: Fix i.MX IPU-v3 offset calculations for (semi)planar U/V formats Maciej Falkowski (1): ARM: OMAP1: ams-delta: remove unused function ams_delta_camera_power Matthieu Baerts (1): static_call: Fix unused variable warn w/o MODULE Pavel Skripkin (1): media: stkwebcam: fix memory leak in stk_camera_probe Randy Dunlap (1): xtensa: fix kconfig unmet dependency warning for HAVE_FUTEX_CMPXCHG Sai Krishna Potthuri (1): reset: reset-zynqmp: Fixed the argument data type Shai Malin (2): qed: Fix the VF msix vectors flow qede: Fix memset corruption Takashi Iwai (1): ALSA: hda/realtek: Workaround for conflicting SSID on ASUS ROG Strix G17 Tuo Li (1): ceph: fix possible null-pointer dereference in ceph_mdsmap_decode() Xiaoyao Li (1): perf/x86/intel/pt: Fix mask of num_address_ranges Zubin Mithra (1): ALSA: pcm: fix divide error in snd_pcm_lib_ioctl arch/arm/mach-omap1/board-ams-delta.c | 14 ------- arch/x86/events/amd/ibs.c | 8 ++++ arch/x86/events/amd/power.c | 1 + arch/x86/events/intel/pt.c | 2 +- arch/xtensa/Kconfig | 2 +- drivers/block/Kconfig | 4 +- drivers/block/cryptoloop.c | 2 + drivers/gpu/ipu-v3/ipu-cpmem.c | 30 ++++++------- drivers/media/usb/stkwebcam/stk-webcam.c | 6 ++- drivers/net/ethernet/cadence/macb_ptp.c | 11 ++++- drivers/net/ethernet/qlogic/qed/qed_main.c | 7 +++- drivers/net/ethernet/qlogic/qede/qede_main.c | 2 +- drivers/reset/reset-zynqmp.c | 3 +- fs/9p/vfs_inode.c | 4 +- fs/9p/vfs_inode_dotl.c | 4 +- fs/ceph/mdsmap.c | 8 ++-- fs/cifs/inode.c | 5 +-- fs/crypto/hooks.c | 44 ++++++++++++++++++++ fs/exec.c | 4 -- fs/ext4/symlink.c | 11 ++++- fs/f2fs/namei.c | 11 ++++- fs/fuse/dir.c | 6 +-- fs/fuse/fuse_i.h | 7 ++++ fs/fuse/inode.c | 4 +- fs/fuse/readdir.c | 7 +++- fs/nfs/inode.c | 6 +-- fs/nfsd/nfsproc.c | 2 +- fs/overlayfs/namei.c | 4 +- fs/ubifs/file.c | 12 +++++- include/linux/cred.h | 2 - include/linux/fs.h | 5 +++ include/linux/fscrypt.h | 7 ++++ include/linux/spi/spi.h | 4 +- include/linux/user_namespace.h | 4 -- kernel/cred.c | 41 ------------------ kernel/fork.c | 6 --- kernel/static_call.c | 4 +- kernel/sys.c | 12 ------ kernel/ucount.c | 40 ++---------------- kernel/user_namespace.c | 3 -- sound/core/pcm_lib.c | 2 +- sound/pci/hda/patch_realtek.c | 11 +++++ 42 files changed, 193 insertions(+), 179 deletions(-) -- 2.20.1

1 27

[PATCH openEuler-5.10 00/89] Backport LTS 5.10.62
by Zheng Zengkai 19 Oct '21

19 Oct '21

Backport LTS 5.10.62 patches from upstream. Aaron Ma (1): igc: fix page fault when thunderbolt is unplugged Adam Ford (1): clk: renesas: rcar-usb2-clock-sel: Fix kernel NULL pointer dereference Alexey Gladkov (1): ucounts: Increase ucounts reference counter before the security hook Andrey Ignatov (1): rtnetlink: Return correct error on changing device netns Ben Skeggs (2): drm/nouveau/disp: power down unused DP links during init drm/nouveau/kms/nv50: workaround EFI GOP window channel format differences Benjamin Berg (2): usb: typec: ucsi: acpi: Always decode connector change information usb: typec: ucsi: Work around PPM losing change information Bjorn Andersson (1): usb: typec: ucsi: Clear pending after acking connector change Christophe JAILLET (1): xgene-v2: Fix a resource leak in the error handling path of 'xge_probe()' Colin Ian King (1): perf/x86/intel/uncore: Fix integer overflow on 23 bit left shift of a u32 DENG Qingfang (1): net: dsa: mt7530: fix VLAN traffic leaks again Daniel Borkmann (1): bpf: Fix ringbuf helper function compatibility Davide Caratti (1): net/sched: ets: fix crash when flipping from 'strict' to 'quantum' Denis Efremov (1): Revert "floppy: reintroduce O_NDELAY fix" Derek Fang (1): ASoC: rt5682: Adjust headset volume button threshold Dinghao Liu (1): RDMA/bnxt_re: Remove unpaired rtnl unlock in bnxt_re_dev_init() Eric Dumazet (2): ipv6: use siphash in rt6_exception_hash() ipv4: use siphash instead of Jenkins in fnhe_hashfun() Filipe Manana (1): btrfs: fix race between marking inode needs to be logged and log syncing Florian Westphal (1): netfilter: conntrack: collect all entries in one cycle Frieder Schrempf (1): mtd: spinand: Fix incorrect parameters for on-die ECC Gal Pressman (1): RDMA/efa: Free IRQ vectors on error flow Gerd Rausch (1): net/rds: dma_map_sg is entitled to merge entries Guenter Roeck (1): ARC: Fix CONFIG_STACKDEPOT Guo Ren (2): riscv: Fixup wrong ftrace remove cflag riscv: Fixup patch_text panic in ftrace Helge Deller (1): Revert "parisc: Add assembly implementations for memset, strlen, strcpy, strncpy and strcat" Jacob Keller (1): ice: do not abort devlink info if board identifier can't be found Jerome Brunet (1): usb: gadget: u_audio: fix race condition on endpoint stop Johan Hovold (1): Revert "USB: serial: ch341: fix character loss at high transfer rates" Johannes Berg (1): iwlwifi: pnvm: accept multiple HW-type TLVs Kees Cook (1): lkdtm: Enable DOUBLE_FAULT on all architectures Kenneth Feng (2): Revert "drm/amd/pm: fix workload mismatch on vega10" drm/amd/pm: change the workload type for some cards Li Jinlin (1): scsi: core: Fix hang of freezing queue between blocking and running device Linus Torvalds (2): pipe: avoid unnecessary EPOLLET wakeups under normal loads pipe: do FASYNC notifications for every pipe IO, not just state changes Mark Brown (2): ASoC: component: Remove misplaced prefix handling in pin control functions net: mscc: Fix non-GPL export of regmap APIs Mark Yacoub (1): drm: Copy drm_wait_vblank to user before returning Mathieu Desnoyers (1): tracepoint: Use rcu get state and cond sync for static call updates Matthew Brost (1): drm/i915: Fix syncmap memory leak Maxim Kiselev (1): net: marvell: fix MVNETA_TX_IN_PRGRS bit number Michael S. Tsirkin (1): tools/virtio: fix build Michał Mirosław (1): opp: remove WARN when no valid OPPs remain Michel Dänzer (1): drm/amdgpu: Cancel delayed work when GFXOFF is disabled Miklos Szeredi (1): ovl: fix uninitialized pointer read in ovl_lookup_real_one() Ming Lei (2): blk-iocost: fix lockdep warning on blkcg->lock blk-mq: don't grab rq's refcount in blk_mq_check_expired() Naresh Kumar PBS (1): RDMA/bnxt_re: Add missing spin lock initialization Neeraj Upadhyay (1): vringh: Use wiov->used to check for read/write desc order Parav Pandit (2): virtio: Improve vq->broken access to avoid any compiler optimization virtio_pci: Support surprise removal of virtio pci device Paul E. McKenney (5): srcu: Provide internal interface to start a Tree SRCU grace period srcu: Provide polling interfaces for Tree SRCU grace periods srcu: Provide internal interface to start a Tiny SRCU grace period srcu: Make Tiny SRCU use multi-bit grace-period counter srcu: Provide polling interfaces for Tiny SRCU grace periods Pauli Virtanen (1): Bluetooth: btusb: check conditions before enabling USB ALT 3 for WBS Peter Collingbourne (1): net: don't unconditionally copy_from_user a struct ifreq for socket ioctls Petko Manolov (1): net: usb: pegasus: fixes of set_register(s) return value evaluation; Petr Vorel (1): arm64: dts: qcom: msm8994-angler: Fix gpio-reserved-ranges 85-88 Qu Wenruo (1): Revert "btrfs: compression: don't try to compress if we don't have enough pages" Rahul Lakkireddy (1): cxgb4: dont touch blocked freelist bitmap after free Richard Guy Briggs (1): audit: move put_tree() to avoid trim_trees refcount underflow and UAF Rob Herring (1): dt-bindings: sifive-l2-cache: Fix 'select' matching Sasha Neftin (2): e1000e: Fix the max snoop/no-snoop latency for 10M e1000e: Do not take care about recovery NVM checksum Shai Malin (2): qed: qed ll2 race condition fixes qed: Fix null-pointer dereference in qed_rdma_create_qp() Shreyansh Chouhan (1): ip_gre: add validation for csum_start Stefan Mätje (1): can: usb: esd_usb2: esd_usb2_rx_event(): fix the interchange of the CAN RX and TX error counters Takashi Iwai (1): usb: renesas-xhci: Prefer firmware loading on unknown ROM state Thara Gopinath (1): cpufreq: blocklist Qualcomm sm8150 in cpufreq-dt-platdev Thinh Nguyen (1): usb: dwc3: gadget: Fix dwc3_calc_trbs_left() Toshiki Nishioka (1): igc: Use num_tx_queues when iterating over tx_ring queue Tuo Li (1): IB/hfi1: Fix possible null-pointer dereference in _extend_sdma_tx_descs() Ulf Hansson (1): Revert "mmc: sdhci-iproc: Set SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN on BCM2711" Vincent Chen (1): riscv: Ensure the value of FP registers in the core dump file is up to date Vincent Whitchurch (1): virtio_vdpa: reject invalid vq indices Wesley Cheng (1): usb: dwc3: gadget: Stop EP0 transfers during pullup disable Wong Vee Khee (1): net: stmmac: fix kernel panic due to NULL pointer dereference of plat->est Xiaoliang Yang (1): net: stmmac: add mutex lock to protect est parameters Xin Long (1): tipc: call tipc_wait_for_connect only when dlen is not 0 Xiubo Li (1): ceph: correctly handle releasing an embedded cap flush Yonghong Song (2): bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper bpf: Fix potentially incorrect results with bpf_get_local_storage() Zhengjun Zhang (1): USB: serial: option: add new VID/PID to support Fibocom FG150 .../bindings/riscv/sifive-l2-cache.yaml | 6 +- arch/arc/kernel/vmlinux.lds.S | 2 + .../boot/dts/qcom/msm8994-angler-rev-101.dts | 4 + arch/parisc/include/asm/string.h | 15 -- arch/parisc/kernel/parisc_ksyms.c | 4 - arch/parisc/lib/Makefile | 4 +- arch/parisc/lib/memset.c | 72 ++++++++++ arch/parisc/lib/string.S | 136 ------------------ arch/riscv/kernel/Makefile | 5 +- arch/riscv/kernel/ptrace.c | 4 + arch/riscv/mm/Makefile | 3 +- arch/x86/events/intel/uncore_snbep.c | 2 +- block/blk-iocost.c | 8 +- block/blk-mq.c | 30 +--- drivers/block/floppy.c | 30 ++-- drivers/bluetooth/btusb.c | 22 +-- drivers/clk/renesas/rcar-usb2-clock-sel.c | 2 +- drivers/cpufreq/cpufreq-dt-platdev.c | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 11 +- drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 36 +++-- .../drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 15 +- drivers/gpu/drm/drm_ioc32.c | 4 +- drivers/gpu/drm/i915/gt/intel_timeline.c | 8 ++ drivers/gpu/drm/nouveau/dispnv50/disp.c | 27 ++++ drivers/gpu/drm/nouveau/dispnv50/head.c | 13 +- drivers/gpu/drm/nouveau/dispnv50/head.h | 1 + drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c | 2 +- drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.h | 1 + .../gpu/drm/nouveau/nvkm/engine/disp/outp.c | 9 ++ drivers/infiniband/hw/bnxt_re/ib_verbs.c | 1 + drivers/infiniband/hw/bnxt_re/main.c | 1 - drivers/infiniband/hw/efa/efa_main.c | 1 + drivers/infiniband/hw/hfi1/sdma.c | 9 +- drivers/misc/lkdtm/core.c | 2 - drivers/mmc/host/sdhci-iproc.c | 3 +- drivers/mtd/nand/spi/core.c | 6 +- drivers/mtd/nand/spi/macronix.c | 6 +- drivers/mtd/nand/spi/toshiba.c | 6 +- drivers/net/can/usb/esd_usb2.c | 4 +- drivers/net/dsa/mt7530.c | 5 +- drivers/net/ethernet/apm/xgene-v2/main.c | 4 +- .../net/ethernet/chelsio/cxgb4/cxgb4_main.c | 7 +- drivers/net/ethernet/intel/e1000e/ich8lan.c | 32 +++-- drivers/net/ethernet/intel/e1000e/ich8lan.h | 3 + drivers/net/ethernet/intel/ice/ice_devlink.c | 4 +- drivers/net/ethernet/intel/igc/igc_main.c | 36 +++-- drivers/net/ethernet/intel/igc/igc_ptp.c | 3 +- drivers/net/ethernet/marvell/mvneta.c | 2 +- drivers/net/ethernet/mscc/ocelot_io.c | 16 +-- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 20 +++ drivers/net/ethernet/qlogic/qed/qed_rdma.c | 3 +- .../net/ethernet/stmicro/stmmac/stmmac_tc.c | 22 ++- drivers/net/usb/pegasus.c | 4 +- drivers/net/wireless/intel/iwlwifi/fw/pnvm.c | 25 ++-- drivers/opp/of.c | 5 +- drivers/scsi/scsi_sysfs.c | 9 +- drivers/usb/dwc3/gadget.c | 23 ++- drivers/usb/gadget/function/u_audio.c | 5 +- drivers/usb/host/xhci-pci-renesas.c | 35 +++-- drivers/usb/serial/ch341.c | 1 - drivers/usb/serial/option.c | 2 + drivers/usb/typec/ucsi/ucsi.c | 125 +++++++++++++--- drivers/usb/typec/ucsi/ucsi.h | 2 + drivers/usb/typec/ucsi/ucsi_acpi.c | 5 +- drivers/vhost/vringh.c | 2 +- drivers/virtio/virtio_pci_common.c | 7 + drivers/virtio/virtio_ring.c | 6 +- drivers/virtio/virtio_vdpa.c | 3 + fs/btrfs/btrfs_inode.h | 15 ++ fs/btrfs/file.c | 11 +- fs/btrfs/inode.c | 6 +- fs/btrfs/transaction.h | 2 +- fs/ceph/caps.c | 21 +-- fs/ceph/mds_client.c | 7 +- fs/ceph/snap.c | 3 + fs/ceph/super.h | 3 +- fs/overlayfs/export.c | 2 +- fs/pipe.c | 33 +++-- include/linux/bpf-cgroup.h | 4 +- include/linux/bpf.h | 4 +- include/linux/netdevice.h | 4 + include/linux/pipe_fs_i.h | 2 + include/linux/rcupdate.h | 2 + include/linux/srcu.h | 3 + include/linux/srcutiny.h | 7 +- include/linux/stmmac.h | 1 + kernel/audit_tree.c | 2 +- kernel/bpf/helpers.c | 4 +- kernel/bpf/verifier.c | 8 +- kernel/cred.c | 12 +- kernel/rcu/srcutiny.c | 77 ++++++++-- kernel/rcu/srcutree.c | 127 ++++++++++++---- kernel/tracepoint.c | 81 +++++++++-- net/core/rtnetlink.c | 3 +- net/ipv4/ip_gre.c | 2 + net/ipv4/route.c | 12 +- net/ipv6/route.c | 20 ++- net/netfilter/nf_conntrack_core.c | 71 +++------ net/rds/ib_frmr.c | 4 +- net/sched/sch_ets.c | 7 + net/socket.c | 6 +- net/tipc/socket.c | 2 +- sound/soc/codecs/rt5682.c | 1 + sound/soc/soc-component.c | 63 ++++---- tools/virtio/Makefile | 3 +- tools/virtio/linux/spinlock.h | 56 ++++++++ tools/virtio/linux/virtio.h | 2 + 107 files changed, 1025 insertions(+), 600 deletions(-) create mode 100644 arch/parisc/lib/memset.c delete mode 100644 arch/parisc/lib/string.S create mode 100644 tools/virtio/linux/spinlock.h -- 2.20.1

1 89

[PATCH openEuler-5.10] ARM: spectre-v2: turn off the mitigation via boot cmdline param
by Zheng Zengkai 19 Oct '21

19 Oct '21

From: "GONG, Ruiqi" <gongruiqi1(a)huawei.com> hulk inclusion category: feature feature: switch of spectre mitigation bugzilla: 180851 https://gitee.com/openeuler/kernel/issues/I4EF1O ------------------------------------------------- We enable spectre mitigation by default for ARM32, which may cause performance regression. To offer an option to turn off this feature, implement a cmdline parameter 'nospectre_v2' compatible with mainline, which sets up a switch to skip invalidating BTB/icache for A9/A15 in context switching and user abort. Signed-off-by: GONG, Ruiqi <gongruiqi1(a)huawei.com> Cc: Hanjun Guo <guohanjun(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> --- arch/arm/include/asm/system_misc.h | 1 + arch/arm/mm/proc-v7-bugs.c | 18 ++++++++++++++++++ arch/arm/mm/proc-v7.S | 15 +++++++++++++++ 3 files changed, 34 insertions(+) diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h index 66f6a3ae68d2..a7ac0c9f38e5 100644 --- a/arch/arm/include/asm/system_misc.h +++ b/arch/arm/include/asm/system_misc.h @@ -37,6 +37,7 @@ static inline void harden_branch_predictor(void) #define UDBG_BUS (1 << 4) extern unsigned int user_debug; +extern int nospectre_v2; #endif /* !__ASSEMBLY__ */ diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 114c05ab4dd9..d7750cddc334 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -8,6 +8,19 @@ #include <asm/proc-fns.h> #include <asm/system_misc.h> +/* + * 32-bit ARM spectre hardening, enabled by default, can be disabled via boot + * cmdline param 'nospectre_v2' to avoid performance regression. + */ +int nospectre_v2 __read_mostly; + +static int __init nospectre_v2_setup(char *str) +{ + nospectre_v2 = 1; + return 0; +} +early_param("nospectre_v2", nospectre_v2_setup); + #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR DEFINE_PER_CPU(harden_branch_predictor_fn_t, harden_branch_predictor_fn); @@ -41,6 +54,11 @@ static void cpu_v7_spectre_init(void) const char *spectre_v2_method = NULL; int cpu = smp_processor_id(); + if (nospectre_v2) { + pr_info_once("Spectre v2: hardening is disabled\n"); + return; + } + if (per_cpu(harden_branch_predictor_fn, cpu)) return; diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 28c9d32fa99a..a59ddfd7a179 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -111,17 +111,32 @@ ENTRY(cpu_v7_hvc_switch_mm) b cpu_v7_switch_mm ENDPROC(cpu_v7_hvc_switch_mm) #endif + +.globl nospectre_v2 ENTRY(cpu_v7_iciallu_switch_mm) + adr r3, 3f + ldr r3, [r3] + cmp r3, #1 + beq 1f mov r3, #0 mcr p15, 0, r3, c7, c5, 0 @ ICIALLU +1: b cpu_v7_switch_mm ENDPROC(cpu_v7_iciallu_switch_mm) ENTRY(cpu_v7_bpiall_switch_mm) + adr r3, 3f + ldr r3, [r3] + cmp r3, #1 + beq 1f mov r3, #0 mcr p15, 0, r3, c7, c5, 6 @ flush BTAC/BTB +1: b cpu_v7_switch_mm ENDPROC(cpu_v7_bpiall_switch_mm) + .align +3: .long nospectre_v2 + string cpu_v7_name, "ARMv7 Processor" .align -- 2.20.1

1 0

[PATCH openEuler-5.10 00/38] bugfix and enhancement for mm/fs/livepatch
by Zheng Zengkai 19 Oct '21

19 Oct '21

Backport bugfix and enhancement patches for mm/fs/livepatch/sched. Al Viro (2): switch file_open_root() to struct path take LOOKUP_{ROOT,ROOT_GRABBED,JUMPED} out of LOOKUP_... space Chen Jun (1): mm: Fix the uninitialized use in overcommit_policy_handler Guoqing Jiang (1): md: revert io stats accounting Kefeng Wang (1): once: Fix panic when module unload Leah Rumancik (1): ext4: wipe ext4_dir_entry2 upon file deletion Li Hua (2): sched/idle: Optimize the loop time algorithm to reduce multicore disturb sched/idle: Reported an error when an illegal negative value is passed Vasily Averin (7): memcg: enable accounting for pids in nested pid namespaces memcg: enable accounting for mnt_cache entries memcg: enable accounting for fasync_cache memcg: enable accounting for new namesapces and struct nsproxy memcg: enable accounting for signals memcg: enable accounting for posix_timers_cache slab memcg: enable accounting for ldt_struct objects Vignesh Raghavendra (1): serial: 8250: 8250_omap: Fix possible array out of bounds access Yang Jihong (1): perf annotate: Add itrace options support Yang Yang (1): kyber: introduce kyber_depth_updated() Ye Bin (1): ext4: fix potential uninitialized access to retval in kmmpd Ye Weihua (9): livepatch: Add state describe for force livepatch: checks only if the replaced instruction is on the stack livepatch/arm64: only check stack top livepatch/arm: only check stack top livepatch/ppc32: only check stack top livepatch/ppc64: only check stack top livepatch/x86: only check stack top livepatch: move arch_klp_mem_recycle after the return value judgment livepatch: Fix compile warnning Yu Jiahua (1): sched: Aware multi-core system for optimize loadtracking Yu Kuai (2): blk-mq: clear active_queues before clearing BLK_MQ_F_TAG_QUEUE_SHARED blk-mq: fix divide by zero crash in tg_may_dispatch() Yutian Yang (1): memcg: charge fs_context and legacy_fs_context Zhang Yi (5): ext4: move inode eio simulation behind io completeion ext4: make the updating inode data procedure atomic ext4: factor out ext4_fill_raw_inode() ext4: move ext4_fill_raw_inode() related functions ext4: prevent getting empty inode buffer Zheng Zucheng (1): sysctl: Refactor IAS framework Documentation/filesystems/path-lookup.rst | 6 +- Documentation/filesystems/porting.rst | 9 + arch/arm/kernel/livepatch.c | 221 +++++++++++-- arch/arm64/kernel/livepatch.c | 209 +++++++++++-- arch/powerpc/kernel/livepatch_32.c | 209 +++++++++++-- arch/powerpc/kernel/livepatch_64.c | 227 ++++++++++---- arch/um/drivers/mconsole_kern.c | 2 +- arch/x86/kernel/ldt.c | 6 +- arch/x86/kernel/livepatch.c | 347 +++++++++++++++------ block/blk-mq.c | 6 +- block/blk-sysfs.c | 7 + block/blk-throttle.c | 37 ++- block/kyber-iosched.c | 29 +- drivers/md/md.c | 45 --- drivers/md/md.h | 1 - drivers/tty/serial/8250/8250_omap.c | 1 + fs/coredump.c | 4 +- fs/ext4/inode.c | 332 +++++++++++--------- fs/ext4/mmp.c | 2 +- fs/ext4/namei.c | 24 +- fs/fcntl.c | 3 +- fs/fhandle.c | 2 +- fs/fs_context.c | 4 +- fs/internal.h | 2 +- fs/kernel_read_file.c | 2 +- fs/namei.c | 60 ++-- fs/namespace.c | 7 +- fs/nfs/nfstrace.h | 4 - fs/open.c | 4 +- fs/proc/proc_sysctl.c | 2 +- include/linux/blkdev.h | 1 + include/linux/fs.h | 9 +- include/linux/kernel.h | 4 +- include/linux/livepatch.h | 4 + include/linux/namei.h | 3 - include/linux/once.h | 4 +- include/linux/sched/sysctl.h | 8 +- init/Kconfig | 36 ++- ipc/namespace.c | 2 +- kernel/cgroup/namespace.c | 2 +- kernel/livepatch/core.c | 2 +- kernel/nsproxy.c | 2 +- kernel/pid_namespace.c | 5 +- kernel/sched/fair.c | 86 ++--- kernel/sched/idle.c | 48 ++- kernel/signal.c | 2 +- kernel/sysctl.c | 84 ++--- kernel/time/namespace.c | 4 +- kernel/time/posix-timers.c | 4 +- kernel/user_namespace.c | 2 +- kernel/usermode_driver.c | 2 +- lib/once.c | 11 +- mm/util.c | 4 +- security/integrity/ima/ima_digest_list.c | 2 +- tools/perf/Documentation/perf-annotate.txt | 7 + tools/perf/builtin-annotate.c | 11 + 56 files changed, 1494 insertions(+), 669 deletions(-) -- 2.20.1

1 38

[PATCH openEuler-5.10 01/12] hfs: fix null-ptr-deref in hfs_find_init()
by Zheng Zengkai 19 Oct '21

19 Oct '21

From: Yang Yingliang <yangyingliang(a)huawei.com> hulk inclusion category: bugfix bugzilla: 179898 https://gitee.com/openeuler/kernel/issues/I4DDEL CVE: CVE-2018-12928 --------------------------- It will cause a null-ptr-deref in hfs_find_init() in fuzz test. [ 107.092729] hfs: continuing without an alternate MDB [ 107.097632] general protection fault, probably for non-canonical address 0xdffffc0000000008: 0000 [#1] SMP KASAN PTI [ 107.104679] KASAN: null-ptr-deref in range [0x0000000000000040-0x0000000000000047] [ 107.109100] CPU: 0 PID: 379 Comm: hfs_inject Not tainted 5.7.0-rc7-00001-g24627f5f2973 #897 [ 107.114142] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 107.121095] RIP: 0010:hfs_find_init+0x72/0x170 [ 107.123609] Code: c1 ea 03 80 3c 02 00 0f 85 e6 00 00 00 4c 8d 65 40 48 c7 43 18 00 00 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 e2 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e a5 00 00 00 8b 45 40 be c0 0c [ 107.134660] RSP: 0018:ffff88810291f3f8 EFLAGS: 00010202 [ 107.137897] RAX: dffffc0000000000 RBX: ffff88810291f468 RCX: 1ffff110175cdf05 [ 107.141874] RDX: 0000000000000008 RSI: ffff88810291f468 RDI: ffff88810291f480 [ 107.145844] RBP: 0000000000000000 R08: 0000000000000000 R09: ffffed1020381013 [ 107.149431] R10: ffff88810291f500 R11: ffffed1020381012 R12: 0000000000000040 [ 107.152315] R13: 0000000000000000 R14: ffff888101c0814a R15: ffff88810291f468 [ 107.155464] FS: 00000000009ea880(0000) GS:ffff88810c600000(0000) knlGS:0000000000000000 [ 107.159795] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 107.162987] CR2: 00005605a19dd284 CR3: 0000000103a0c006 CR4: 0000000000020ef0 [ 107.166665] Call Trace: [ 107.167969] ? find_held_lock+0x33/0x1c0 [ 107.169972] hfs_ext_read_extent+0x16b/0xb00 [ 107.172092] ? create_page_buffers+0x14e/0x1b0 [ 107.174303] ? hfs_free_extents+0x280/0x280 [ 107.176437] ? lock_downgrade+0x730/0x730 [ 107.178272] hfs_get_block+0x496/0x8a0 [ 107.179972] block_read_full_page+0x241/0x8d0 [ 107.181971] ? hfs_extend_file+0xae0/0xae0 [ 107.183814] ? end_buffer_async_read_io+0x10/0x10 [ 107.185954] ? add_to_page_cache_lru+0x13f/0x1f0 [ 107.188006] ? add_to_page_cache_locked+0x10/0x10 [ 107.190175] do_read_cache_page+0xc6a/0x1180 [ 107.192096] ? generic_file_read_iter+0x4c0/0x4c0 [ 107.194234] ? hfs_btree_open+0x408/0x1000 [ 107.196068] ? lock_downgrade+0x730/0x730 [ 107.197926] ? wake_bit_function+0x180/0x180 [ 107.199845] ? lockdep_init_map_waits+0x267/0x7c0 [ 107.201895] hfs_btree_open+0x455/0x1000 [ 107.203479] hfs_mdb_get+0x122c/0x1ae8 [ 107.205065] ? hfs_mdb_put+0x350/0x350 [ 107.206590] ? queue_work_node+0x260/0x260 [ 107.208309] ? rcu_read_lock_sched_held+0xa1/0xd0 [ 107.210227] ? lockdep_init_map_waits+0x267/0x7c0 [ 107.212144] ? lockdep_init_map_waits+0x267/0x7c0 [ 107.213979] hfs_fill_super+0x9ba/0x1280 [ 107.215444] ? bdev_name.isra.9+0xf1/0x2b0 [ 107.217028] ? hfs_remount+0x190/0x190 [ 107.218428] ? pointer+0x5da/0x710 [ 107.219745] ? file_dentry_name+0xf0/0xf0 [ 107.221262] ? mount_bdev+0xd1/0x330 [ 107.222592] ? vsnprintf+0x7bd/0x1250 [ 107.224007] ? pointer+0x710/0x710 [ 107.225332] ? down_write+0xe5/0x160 [ 107.226698] ? hfs_remount+0x190/0x190 [ 107.228120] ? snprintf+0x91/0xc0 [ 107.229388] ? vsprintf+0x10/0x10 [ 107.230628] ? sget+0x3af/0x4a0 [ 107.231848] ? hfs_remount+0x190/0x190 [ 107.233300] mount_bdev+0x26e/0x330 [ 107.234611] ? hfs_statfs+0x540/0x540 [ 107.236015] legacy_get_tree+0x101/0x1f0 [ 107.237431] ? security_capable+0x58/0x90 [ 107.238832] vfs_get_tree+0x89/0x2d0 [ 107.240082] ? ns_capable_common+0x5c/0xd0 [ 107.241521] do_mount+0xd8a/0x1720 [ 107.242727] ? lock_downgrade+0x730/0x730 [ 107.244116] ? copy_mount_string+0x20/0x20 [ 107.245557] ? _copy_from_user+0xbe/0x100 [ 107.246967] ? memdup_user+0x47/0x70 [ 107.248212] __x64_sys_mount+0x162/0x1b0 [ 107.249537] do_syscall_64+0xa5/0x4f0 [ 107.250742] entry_SYSCALL_64_after_hwframe+0x49/0xb3 [ 107.252369] RIP: 0033:0x44e8ea [ 107.253360] Code: 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 [ 107.259240] RSP: 002b:00007ffd910e4c28 EFLAGS: 00000207 ORIG_RAX: 00000000000000a5 [ 107.261668] RAX: ffffffffffffffda RBX: 0000000000400400 RCX: 000000000044e8ea [ 107.263920] RDX: 000000000049321e RSI: 0000000000493222 RDI: 00007ffd910e4d00 [ 107.266177] RBP: 00007ffd910e5d10 R08: 0000000000000000 R09: 000000000000000a [ 107.268451] R10: 0000000000000001 R11: 0000000000000207 R12: 0000000000401c40 [ 107.270721] R13: 0000000000000000 R14: 00000000006ba018 R15: 0000000000000000 [ 107.273025] Modules linked in: [ 107.274029] Dumping ftrace buffer: [ 107.275121] (ftrace buffer empty) [ 107.276370] ---[ end trace c5e0b9d684f3570e ]--- We need check tree in hfs_find_init(). https://lore.kernel.org/linux-fsdevel/20180419024358.GA5215@bombadil.infrad… https://marc.info/?l=linux-fsdevel&m=152406881024567&w=2 References: CVE-2018-12928 Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> --- fs/hfs/bfind.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index ef9498a6e88a..ae44c8fa86ec 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -16,6 +16,8 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) { void *ptr; + if (!tree) + return -EINVAL; fd->tree = tree; fd->bnode = NULL; ptr = kmalloc(tree->max_key_len * 2 + 4, GFP_KERNEL); -- 2.20.1

1 11

[PATCH openEuler-5.10 00/94] Backport LTS 5.10.61
by Zheng Zengkai 19 Oct '21

19 Oct '21

Backport LTS 5.10.61 patches from upstream. Adrian Larumbe (1): dmaengine: xilinx_dma: Fix read-after-free bug when terminating transfers Alan Stern (2): USB: core: Avoid WARNings for 0-length descriptor requests USB: core: Fix incorrect pipe calculation in do_proc_control() Andreas Persson (1): mtd: cfi_cmdset_0002: fix crash when erasing/writing AMD cards Andy Shevchenko (1): ptp_pch: Restore dependency on PCI Arkadiusz Kubalewski (1): i40e: Fix ATR queue selection Bing Guo (1): drm/amd/display: Fix Dynamic bpp issue with 8K30 with Navi 1X Bjorn Andersson (1): clk: qcom: gdsc: Ensure regulator init state matches GDSC state Christophe Kerello (1): mmc: mmci: stm32: Check when the voltage switch procedure should be done Dan Carpenter (1): media: zr364xx: fix memory leaks in probe() Dave Gerlach (1): ARM: dts: am43x-epos-evm: Reduce i2c0 bus speed for tps65218 Dinghao Liu (1): net: qlcnic: add missed unlock in qlcnic_83xx_flash_read32 Dong Aisheng (1): clk: imx6q: fix uart earlycon unwork Dongliang Mu (2): ipack: tpci200: fix many double free issues in tpci200_pci_probe ipack: tpci200: fix memory leak in the tpci200_register Eli Cohen (1): vdpa/mlx5: Avoid destroying MR on empty iotlb Evgeny Novikov (1): media: zr364xx: propagate errors from zr364xx_start_readpipe() Frank Wunderlich (1): iommu: Check if group is NULL before remove device Harshvardhan Jha (2): net: xfrm: Fix end of loop tests for list_for_each_entry scsi: megaraid_mm: Fix end of loop tests for list_for_each_entry() Hayes Wang (1): r8152: fix writing USB_BP2_EN Ido Schimmel (1): Revert "flow_offload: action should not be NULL when it is referenced" Igor Pylypiv (1): scsi: pm80xx: Fix TMF task completion race condition Ilya Leoshkevich (1): bpf: Clear zext_dst of dead insns Ivan T. Ivanov (1): net: usb: lan78xx: don't modify phy_device state concurrently Jakub Kicinski (4): bnxt: don't lock the tx queue from napi poll bnxt: disable napi before canceling DIM bnxt: make sure xmit_more + errors does not miss doorbells bnxt: count Tx drops Jaroslav Kysela (1): ALSA: hda - fix the 'Capture Switch' value change notifications Jason Wang (1): virtio-net: use NETIF_F_GRO_HW instead of NETIF_F_LRO Jeff Layton (1): fs: warn about impending deprecation of mandatory locks Jens Axboe (2): io_uring: fix xa_alloc_cycle() error return value check io_uring: only assign io_uring_enter() SQPOLL error in actual error case Johannes Weiner (1): mm: memcontrol: fix occasional OOMs due to proportional memory.low reclaim Jouni Malinen (5): ath: Use safer key clearing with key cache entries ath9k: Clear key cache explicitly on disabling hardware ath: Export ath_hw_keysetmac() ath: Modify ath_key_delete() to not need full key entry ath9k: Postpone key cache entry deletion for TXQ frames reference it Kai-Heng Feng (1): ALSA: hda/realtek: Limit mic boost on HP ProBook 445 G8 Kristin Paget (1): ALSA: hda/realtek: Enable 4-speaker output for Dell XPS 15 9510 laptop Lahav Schlesinger (1): vrf: Reset skb conntrack connection on VRF rcv Liu Yi L (1): iommu/vt-d: Fix incomplete cache flush in intel_pasid_tear_down_entry() Lu Baolu (1): iommu/vt-d: Consolidate duplicate cache invaliation code Marcin Bachry (1): PCI: Increase D3 delay for AMD Renoir/Cezanne XHCI Marek Behún (1): cpufreq: armada-37xx: forbid cpufreq for 1.2 GHz variant Michael Chan (2): bnxt_en: Disable aRFS if running on 212 firmware bnxt_en: Add missing DMA memory barriers NeilBrown (1): btrfs: prevent rename2 from exchanging a subvol with a directory from different parents Nicolas Saenz Julienne (2): mmc: sdhci-iproc: Cap min clock frequency on BCM2711 mmc: sdhci-iproc: Set SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN on BCM2711 Niklas Schnelle (1): s390/pci: fix use after free of zpci_dev Ole Bjørn Midtbø (1): Bluetooth: hidp: use correct wait queue when removing ctrl_wait Parav Pandit (1): virtio: Protect vqs list access Pavel Skripkin (2): media: drivers/media/usb: fix memory leak in zr364xx_probe net: 6pack: fix slab-out-of-bounds in decode_data Peter Ujfalusi (1): dmaengine: of-dma: router_xlate to return -EPROBE_DEFER if controller is not yet available Petko Manolov (1): net: usb: pegasus: Check the return value of get_geristers() and friends; Petr Vorel (1): arm64: dts: qcom: msm8992-bullhead: Remove PSCI Prabhakar Kushwaha (1): qede: fix crash in rmmod qede while automatic debug collection Qingqing Zhuo (1): drm/amd/display: workaround for hard hang on HPD on native DP Randy Dunlap (1): dccp: add do-while-0 stubs for dccp_pr_debug macros Saravana Kannan (2): net: mdio-mux: Don't ignore memory allocation errors net: mdio-mux: Handle -EPROBE_DEFER correctly Shaik Sajida Bhanu (1): mmc: sdhci-msm: Update the software timeout value for sdhc Sreekanth Reddy (1): scsi: core: Avoid printing an error if target_alloc() returns -ENXIO Srinivas Kandagatla (4): arm64: dts: qcom: c630: fix correct powerdown pin for WSA881x slimbus: messaging: start transaction ids from 1 instead of zero slimbus: messaging: check for valid transaction id slimbus: ngd: reset dma setup during runtime pm Steven Rostedt (VMware) (1): tracing / histogram: Fix NULL pointer dereference on strcmp() on NULL event name Sudeep Holla (1): ARM: dts: nomadik: Fix up interrupt controller node names Sylwester Dziedziuch (1): iavf: Fix ping is lost after untrusted VF had tried to change MAC Takashi Iwai (2): ALSA: hda/via: Apply runtime PM workaround for ASUS B23E ASoC: intel: atom: Fix breakage for PCM buffer address setup Toke Høiland-Jørgensen (1): sch_cake: fix srchost/dsthost hashing mode Tony Lindgren (1): bus: ti-sysc: Fix error handling for sysc_check_active_timer() Uwe Kleine-König (1): spi: spi-mux: Add module info needed for autoloading Vincent Whitchurch (1): mmc: dw_mmc: Fix hang on data CRC error Wang Hai (1): ixgbe, xsk: clean up the resources in ixgbe_xsk_pool_enable error path Wanpeng Li (1): KVM: X86: Fix warning caused by stale emulation context Wei Huang (1): KVM: x86: Factor out x86 instruction emulation with decoding Xie Yongji (2): vhost-vdpa: Fix integer overflow in vhost_vdpa_process_iotlb_update() vhost: Fix the calculation in vhost_overflow() Xuan Zhuo (1): virtio-net: support XDP when not more queues Ye Bin (1): scsi: scsi_dh_rdac: Avoid crash during rdac_bus_attach() Yifan Zhang (1): drm/amdgpu: fix the doorbell missing when in CGPG issue for renoir. Yongqiang Niu (2): soc / drm: mediatek: Move DDP component defines into mtk-mmsys.h drm/mediatek: Fix aal size config Yu Kuai (1): dmaengine: usb-dmac: Fix PM reference leak in usb_dmac_probe() jason-jh.lin (1): drm/mediatek: Add AAL output size configuration kaixi.fan (1): ovs: clear skb->tstamp in forwarding path lijinlin (1): scsi: core: Fix capacity set to zero after offlinining device arch/arm/boot/dts/am43x-epos-evm.dts | 2 +- arch/arm/boot/dts/ste-nomadik-stn8815.dtsi | 4 +- .../dts/qcom/msm8992-bullhead-rev-101.dts | 4 + .../boot/dts/qcom/sdm850-lenovo-yoga-c630.dts | 4 +- arch/s390/pci/pci.c | 6 + arch/s390/pci/pci_bus.h | 5 + arch/x86/kvm/x86.c | 62 ++++++---- arch/x86/kvm/x86.h | 2 + drivers/bus/ti-sysc.c | 4 +- drivers/clk/imx/clk-imx6q.c | 2 +- drivers/clk/qcom/gdsc.c | 54 ++++++--- drivers/cpufreq/armada-37xx-cpufreq.c | 6 +- drivers/dma/of-dma.c | 9 +- drivers/dma/sh/usb-dmac.c | 2 +- drivers/dma/xilinx/xilinx_dma.c | 12 ++ drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 21 +++- .../amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c | 4 +- .../gpu/drm/amd/display/dc/dcn20/dcn20_optc.c | 2 +- drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 4 +- drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 34 +----- drivers/iommu/intel/pasid.c | 26 ++-- drivers/iommu/intel/pasid.h | 6 + drivers/iommu/intel/svm.c | 55 ++------- drivers/iommu/iommu.c | 3 + drivers/ipack/carriers/tpci200.c | 60 +++++----- drivers/media/usb/zr364xx/zr364xx.c | 77 ++++++++---- drivers/mmc/host/dw_mmc.c | 6 +- drivers/mmc/host/mmci_stm32_sdmmc.c | 7 +- drivers/mmc/host/sdhci-iproc.c | 21 +++- drivers/mmc/host/sdhci-msm.c | 18 +++ drivers/mtd/chips/cfi_cmdset_0002.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 113 ++++++++++++------ drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 + drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +- drivers/net/ethernet/intel/iavf/iavf.h | 1 + drivers/net/ethernet/intel/iavf/iavf_main.c | 1 + .../net/ethernet/intel/iavf/iavf_virtchnl.c | 47 +++++++- drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 5 +- drivers/net/ethernet/qlogic/qede/qede.h | 1 + drivers/net/ethernet/qlogic/qede/qede_main.c | 8 ++ .../ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 4 +- drivers/net/hamradio/6pack.c | 6 + drivers/net/mdio/mdio-mux.c | 36 ++++-- drivers/net/usb/lan78xx.c | 16 ++- drivers/net/usb/pegasus.c | 108 ++++++++++++----- drivers/net/usb/r8152.c | 2 +- drivers/net/virtio_net.c | 76 ++++++++---- drivers/net/vrf.c | 4 + drivers/net/wireless/ath/ath.h | 3 +- drivers/net/wireless/ath/ath5k/mac80211-ops.c | 2 +- drivers/net/wireless/ath/ath9k/htc_drv_main.c | 2 +- drivers/net/wireless/ath/ath9k/hw.h | 1 + drivers/net/wireless/ath/ath9k/main.c | 95 ++++++++++++++- drivers/net/wireless/ath/key.c | 41 ++++--- drivers/pci/quirks.c | 1 + drivers/ptp/Kconfig | 3 +- drivers/scsi/device_handler/scsi_dh_rdac.c | 4 +- drivers/scsi/megaraid/megaraid_mm.c | 21 +++- drivers/scsi/pm8001/pm8001_sas.c | 32 +++-- drivers/scsi/scsi_scan.c | 3 +- drivers/scsi/scsi_sysfs.c | 9 +- drivers/slimbus/messaging.c | 7 +- drivers/slimbus/qcom-ngd-ctrl.c | 5 +- drivers/soc/mediatek/mtk-mmsys.c | 4 +- drivers/spi/spi-mux.c | 8 ++ drivers/usb/core/devio.c | 2 +- drivers/usb/core/message.c | 6 + drivers/vdpa/mlx5/core/mr.c | 9 -- drivers/vhost/vdpa.c | 3 +- drivers/vhost/vhost.c | 10 +- drivers/virtio/virtio.c | 1 + drivers/virtio/virtio_ring.c | 8 ++ fs/btrfs/inode.c | 10 +- fs/io_uring.c | 16 +-- fs/namespace.c | 6 +- include/linux/memcontrol.h | 29 ++--- include/linux/soc/mediatek/mtk-mmsys.h | 33 +++++ include/linux/virtio.h | 1 + include/net/flow_offload.h | 12 +- kernel/bpf/verifier.c | 1 + kernel/trace/trace_events_hist.c | 2 + mm/vmscan.c | 27 +++-- net/bluetooth/hidp/core.c | 2 +- net/dccp/dccp.h | 6 +- net/openvswitch/vport.c | 1 + net/sched/sch_cake.c | 2 +- net/xfrm/xfrm_ipcomp.c | 2 +- sound/pci/hda/hda_generic.c | 10 +- sound/pci/hda/patch_realtek.c | 12 +- sound/pci/hda/patch_via.c | 1 + sound/soc/intel/atom/sst-mfld-platform-pcm.c | 2 +- 91 files changed, 964 insertions(+), 447 deletions(-) -- 2.20.1

1 94

[PATCH openEuler-5.10 000/101] Backport LTS 5.10.60
by Zheng Zengkai 19 Oct '21

19 Oct '21

Backport LTS 5.10.60 patches from upstream. Alex Deucher (1): drm/amdgpu: don't enable baco on boco platforms in runpm Andy Shevchenko (1): pinctrl: tigerlake: Fix GPIO mapping for newer version of software Anirudh Venkataramanan (1): ice: Prevent probing virtual functions Anson Jacob (1): drm/amd/display: use GFP_ATOMIC in amdgpu_dm_irq_schedule_work Antti Keränen (1): iio: adis: set GPIO reset pin direction Ard Biesheuvel (3): efi/libstub: arm64: Force Image reallocation if BSS was not reserved efi/libstub: arm64: Relax 2M alignment again for relocatable kernels efi/libstub: arm64: Double check image alignment at entry Aya Levin (1): net/mlx5: Fix return value from tracer initialization Babu Moger (1): x86/resctrl: Fix default monitoring groups reporting Ben Dai (1): genirq/timings: Prevent potential array overflow in __irq_timings_store() Ben Hutchings (8): net: phy: micrel: Fix link detection on ksz87xx switch" net: dsa: microchip: Fix ksz_read64() net: dsa: microchip: ksz8795: Fix VLAN filtering net: dsa: microchip: Fix probing KSZ87xx switch with DT node for host port net: dsa: microchip: ksz8795: Fix PVID tag insertion net: dsa: microchip: ksz8795: Reject unsupported VLAN configuration net: dsa: microchip: ksz8795: Fix VLAN untagged flag change on deletion net: dsa: microchip: ksz8795: Use software untagging on CPU port Benjamin Herrenschmidt (1): arm64: efi: kaslr: Fix occasional random alloc (and boot) failure Bixuan Cui (1): genirq/msi: Ensure deactivation on teardown Brett Creeley (1): ice: don't remove netdev->dev_addr from uc sync list Chris Lesiak (1): iio: humidity: hdc100x: Add margin to the conversion time Christian Hewitt (1): drm/meson: fix colour distortion from HDR set during vendor u-boot Christophe Leroy (1): powerpc/smp: Fix OOPS in topology_init() Colin Ian King (1): iio: adc: Fix incorrect exit of for-loop DENG Qingfang (1): net: dsa: mt7530: add the missing RxUnicast MIB counter Dan Williams (2): ACPI: NFIT: Fix support for virtual SPA ranges libnvdimm/region: Fix label activation vs errors Dongliang Mu (2): ieee802154: hwsim: fix GPF in hwsim_set_edge_lqi ieee802154: hwsim: fix GPF in hwsim_new_edge_nl Eric Bernstein (1): drm/amd/display: Remove invalid assert for ODM + MPC case Eric Dumazet (2): net: igmp: fix data-race in igmp_ifc_timer_expire() net: igmp: increase size of mr_ifc_count Ewan D. Milne (1): scsi: lpfc: Move initialization of phba->poll_list earlier to avoid crash Greg Kroah-Hartman (1): i2c: dev: zero out array used for i2c reads from userspace Grygorii Strashko (1): net: ethernet: ti: cpsw: fix min eth packet size for non-switch use-cases Guennadi Liakhovetski (1): ASoC: SOF: Intel: hda-ipc: fix reply size checking Guillaume Nault (1): bareudp: Fix invalid read beyond skb's linear data Hangbin Liu (1): net: sched: act_mirred: Reset ct info when mirror/redirect skb Hans de Goede (3): platform/x86: pcengines-apuv2: Add missing terminating entries to gpio-lookup tables vboxsf: Add vboxsf_[create|release]_sf_handle() helpers vboxsf: Add support for the atomic_open directory-inode op Hsin-Yi Wang (1): pinctrl: mediatek: Fix fallback behavior for bias_set_combo Hsuan-Chi Kuo (1): seccomp: Fix setting loaded filter count during TSYNC Jeff Layton (3): ceph: add some lockdep assertions around snaprealm handling ceph: clean up locking annotation for ceph_get_snap_realm and __lookup_snap_realm ceph: take snap_empty_lock atomically with snaprealm refcount change John Hubbard (1): net: mvvp2: fix short frame size on s390 Karsten Graul (1): net/smc: fix wait on already cleared link Longpeng(Mike) (1): vsock/virtio: avoid potential deadlock when vsock device remove Luis Henriques (1): ceph: reduce contention in ceph_check_delayed_caps() Mark Brown (1): ASoC: tlv320aic31xx: Fix jack detection after suspend Matt Roper (1): drm/i915: Only access SFC_DONE when media domain is not fused off Maxim Levitsky (2): KVM: nSVM: avoid picking up unsupported bits from L2 in int_ctl (CVE-2021-3653) KVM: nSVM: always intercept VMLOAD/VMSAVE when nested (CVE-2021-3656) Maximilian Heyne (1): xen/events: Fix race in set_evtchn_to_irq Md Fahad Iqbal Polash (1): iavf: Set RSS LUT and key in reset handle path Nathan Chancellor (1): vmlinux.lds.h: Handle clang's module.{c,d}tor sections Neal Cardwell (1): tcp_bbr: fix u32 wrap bug in round logic if bbr_init() called after 2B packets Nikolay Aleksandrov (1): net: bridge: fix flags interpretation for extern learn fdb entries Pali Rohár (1): ppp: Fix generating ifname when empty IFLA_IFNAME is specified Randy Dunlap (1): x86/tools: Fix objdump version check again Richard Fitzgerald (5): ASoC: cs42l42: Correct definition of ADC Volume control ASoC: cs42l42: Don't allow SND_SOC_DAIFMT_LEFT_J ASoC: cs42l42: Fix inversion of ADC Notch Switch control ASoC: cs42l42: Remove duplicate control for WNF filter frequency ASoC: cs42l42: Fix LRCLK frame start edge Robin Gögge (1): libbpf: Fix probe for BPF_PROG_TYPE_CGROUP_SOCKOPT Roi Dayan (1): psample: Add a fwd declaration for skbuff Sean Christopherson (2): KVM: VMX: Use current VMCS to query WAITPKG support for MSR emulation KVM: nVMX: Use vmx_need_pf_intercept() when deciding if L0 wants a #PF Shay Drory (1): net/mlx5: Synchronize correct IRQ when destroying CQ Shyam Prasad N (1): cifs: create sd context must be a multiple of 8 Takashi Iwai (4): ASoC: amd: Fix reference to PCM buffer address ASoC: xilinx: Fix reference to PCM buffer address ASoC: uniphier: Fix reference to PCM buffer address ASoC: intel: atom: Fix reference to PCM buffer address Takeshi Misawa (1): net: Fix memory leak in ieee802154_raw_deliver Tatsuhiko Yasumatsu (1): bpf: Fix integer overflow involving bucket_size Thomas Gleixner (11): genirq: Provide IRQCHIP_AFFINITY_PRE_STARTUP x86/msi: Force affinity setup before startup x86/ioapic: Force affinity setup before startup PCI/MSI: Enable and mask MSI-X early PCI/MSI: Mask all unused MSI-X entries PCI/MSI: Enforce that MSI-X table entry is masked for update PCI/MSI: Enforce MSI[X] entry updates to be visible PCI/MSI: Do not set invalid bits in MSI mask PCI/MSI: Correct misleading comments PCI/MSI: Use msi_mask_irq() in pci_msi_shutdown() PCI/MSI: Protect msi_desc::masked for multi-MSI Uwe Kleine-König (1): iio: adc: ti-ads7950: Ensure CS is deasserted after reading channels Vineet Gupta (1): ARC: fp: set FPU_STATUS.FWE to enable FPU_STATUS update on context switch Vladimir Oltean (4): net: dsa: lan9303: fix broken backpressure in .port_fdb_dump net: dsa: lantiq: fix broken backpressure in .port_fdb_dump net: dsa: sja1105: fix broken backpressure in .port_fdb_dump net: bridge: validate the NUD_PERMANENT bit when adding an extern_learn FDB entry Willy Tarreau (1): net: linkwatch: fix failure to restore device state across suspend/resume Xie Yongji (1): nbd: Aovid double completion of a request Yajun Deng (1): netfilter: nf_conntrack_bridge: Fix memory leak when error Yang Yingliang (1): net: bridge: fix memleak in br_add_if() arch/arc/kernel/fpu.c | 9 +- arch/powerpc/kernel/sysfs.c | 2 +- arch/x86/include/asm/svm.h | 2 + arch/x86/kernel/apic/io_apic.c | 6 +- arch/x86/kernel/apic/msi.c | 13 +- arch/x86/kernel/cpu/resctrl/monitor.c | 27 ++-- arch/x86/kvm/svm/nested.c | 14 +- arch/x86/kvm/svm/svm.c | 8 +- arch/x86/kvm/vmx/nested.c | 3 +- arch/x86/kvm/vmx/vmx.h | 2 +- arch/x86/tools/chkobjdump.awk | 1 + drivers/acpi/nfit/core.c | 3 + drivers/base/core.c | 1 + drivers/block/nbd.c | 14 +- drivers/firmware/efi/libstub/arm64-stub.c | 69 ++++++++-- drivers/firmware/efi/libstub/randomalloc.c | 2 + drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 + .../drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c | 2 +- .../drm/amd/display/dc/dcn30/dcn30_resource.c | 1 - drivers/gpu/drm/i915/i915_gpu_error.c | 19 ++- drivers/gpu/drm/meson/meson_registers.h | 5 + drivers/gpu/drm/meson/meson_viu.c | 7 +- drivers/i2c/i2c-dev.c | 5 +- drivers/iio/adc/palmas_gpadc.c | 4 +- drivers/iio/adc/ti-ads7950.c | 1 - drivers/iio/humidity/hdc100x.c | 6 +- drivers/iio/imu/adis.c | 3 +- drivers/infiniband/hw/mlx5/cq.c | 4 +- drivers/infiniband/hw/mlx5/devx.c | 3 +- drivers/net/bareudp.c | 16 ++- drivers/net/dsa/lan9303-core.c | 34 ++--- drivers/net/dsa/lantiq_gswip.c | 14 +- drivers/net/dsa/microchip/ksz8795.c | 91 +++++++++++-- drivers/net/dsa/microchip/ksz_common.c | 2 +- drivers/net/dsa/microchip/ksz_common.h | 9 +- drivers/net/dsa/mt7530.c | 1 + drivers/net/dsa/sja1105/sja1105_main.c | 4 +- drivers/net/ethernet/intel/iavf/iavf_main.c | 13 +- drivers/net/ethernet/intel/ice/ice_main.c | 28 ++-- drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/cq.c | 1 + .../mellanox/mlx5/core/diag/fw_tracer.c | 11 +- .../net/ethernet/mellanox/mlx5/core/en_main.c | 13 +- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 20 ++- .../ethernet/mellanox/mlx5/core/fpga/conn.c | 4 +- .../net/ethernet/mellanox/mlx5/core/lib/eq.h | 2 + .../mellanox/mlx5/core/steering/dr_send.c | 4 +- drivers/net/ethernet/ti/cpsw_new.c | 7 +- drivers/net/ethernet/ti/cpsw_priv.h | 4 +- drivers/net/ieee802154/mac802154_hwsim.c | 6 +- drivers/net/phy/micrel.c | 2 - drivers/net/ppp/ppp_generic.c | 2 +- drivers/nvdimm/namespace_devs.c | 17 ++- drivers/pci/msi.c | 125 +++++++++++------- drivers/pinctrl/intel/pinctrl-tigerlake.c | 26 ++-- .../pinctrl/mediatek/pinctrl-mtk-common-v2.c | 8 +- drivers/platform/x86/pcengines-apuv2.c | 2 + drivers/scsi/lpfc/lpfc_init.c | 3 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 3 +- drivers/xen/events/events_base.c | 20 ++- fs/ceph/caps.c | 17 ++- fs/ceph/mds_client.c | 25 ++-- fs/ceph/snap.c | 54 +++++--- fs/ceph/super.h | 2 +- fs/cifs/smb2pdu.c | 2 +- fs/vboxsf/dir.c | 48 +++++++ fs/vboxsf/file.c | 71 ++++++---- fs/vboxsf/vfsmod.h | 7 + include/asm-generic/vmlinux.lds.h | 1 + include/linux/device.h | 1 + include/linux/inetdevice.h | 2 +- include/linux/irq.h | 2 + include/linux/mlx5/driver.h | 3 +- include/linux/msi.h | 2 +- include/net/psample.h | 2 + include/uapi/linux/neighbour.h | 7 +- kernel/bpf/hashtab.c | 4 +- kernel/irq/chip.c | 5 +- kernel/irq/msi.c | 13 +- kernel/irq/timings.c | 5 + kernel/seccomp.c | 2 +- net/bridge/br_fdb.c | 23 +++- net/bridge/br_if.c | 2 + net/bridge/netfilter/nf_conntrack_bridge.c | 6 + net/core/link_watch.c | 5 +- net/ieee802154/socket.c | 7 +- net/ipv4/igmp.c | 21 ++- net/ipv4/tcp_bbr.c | 2 +- net/sched/act_mirred.c | 3 + net/smc/smc_core.h | 2 + net/smc/smc_llc.c | 10 +- net/smc/smc_tx.c | 18 ++- net/smc/smc_wr.c | 10 ++ net/vmw_vsock/virtio_transport.c | 7 +- sound/soc/amd/acp-pcm-dma.c | 2 +- sound/soc/amd/raven/acp3x-pcm-dma.c | 2 +- sound/soc/amd/renoir/acp3x-pdm-dma.c | 2 +- sound/soc/codecs/cs42l42.c | 39 +++--- sound/soc/codecs/tlv320aic31xx.c | 10 ++ sound/soc/intel/atom/sst-mfld-platform-pcm.c | 3 +- sound/soc/sof/intel/hda-ipc.c | 4 +- sound/soc/uniphier/aio-dma.c | 2 +- sound/soc/xilinx/xlnx_formatter_pcm.c | 4 +- tools/lib/bpf/libbpf_probes.c | 4 +- 104 files changed, 829 insertions(+), 366 deletions(-) -- 2.20.1

1 101

[PATCH openEuler-5.10 00/18] Backport LTS 5.10.59
by Zheng Zengkai 19 Oct '21

19 Oct '21

Backport LTS 5.10.59 patches from upstream. Adam Ford (3): arm64: dts: renesas: rzg2: Add usb2_clksel to RZ/G2 M/N/H arm64: dts: renesas: beacon: Fix USB extal reference arm64: dts: renesas: beacon: Fix USB ref clock references Allen Pais (1): firmware: tee_bnxt: Release TEE shm, session, and context during kexec Daniel Borkmann (1): bpf: Add lockdown check for probe_write_user helper Hans de Goede (2): vboxsf: Honor excl flag to the dir-inode create op vboxsf: Make vboxsf_dir_create() return the handle for the created file Jeremy Szu (1): ALSA: hda/realtek: fix mute/micmute LEDs for HP ProBook 650 G8 Notebook PC Longfang Liu (1): USB:ehci:fix Kunpeng920 ehci hardware problem Luke D Jones (1): ALSA: hda: Add quirk for ASUS Flow x13 Mike Rapoport (1): mm: make zone_to_nid() and zone_set_nid() available for DISCONTIGMEM Miklos Szeredi (1): ovl: prevent private clone if bind mount is not allowed Pali Rohár (1): ppp: Fix generating ppp unit id when ifname is not specified Reinette Chatre (1): Revert "selftests/resctrl: Use resctrl/info for feature detection" Sean Christopherson (1): KVM: SVM: Fix off-by-one indexing when nullifying last used SEV VMCB Sumit Garg (1): tee: Correct inappropriate usage of TEE_SHM_DMA_BUF flag Takashi Iwai (1): ALSA: pcm: Fix mmap breakage without explicit buffer setup YueHaibing (1): net: xilinx_emaclite: Do not print real IOMEM pointer .../dts/renesas/beacon-renesom-baseboard.dtsi | 4 +- .../boot/dts/renesas/beacon-renesom-som.dtsi | 6 ++- arch/arm64/boot/dts/renesas/r8a774a1.dtsi | 15 ++++++ arch/arm64/boot/dts/renesas/r8a774b1.dtsi | 15 ++++++ arch/arm64/boot/dts/renesas/r8a774e1.dtsi | 15 ++++++ arch/x86/kvm/svm/sev.c | 2 +- drivers/firmware/broadcom/tee_bnxt_fw.c | 14 +++-- drivers/net/ethernet/xilinx/xilinx_emaclite.c | 5 +- drivers/net/ppp/ppp_generic.c | 19 +++++-- drivers/tee/optee/call.c | 2 +- drivers/tee/optee/core.c | 3 +- drivers/tee/optee/rpc.c | 5 +- drivers/tee/optee/shm_pool.c | 8 ++- drivers/tee/tee_shm.c | 4 +- drivers/usb/host/ehci-pci.c | 3 ++ fs/namespace.c | 42 ++++++++++----- fs/vboxsf/dir.c | 28 ++++++---- include/linux/mmzone.h | 4 +- include/linux/security.h | 1 + include/linux/tee_drv.h | 1 + kernel/trace/bpf_trace.c | 5 +- security/security.c | 1 + sound/core/pcm_native.c | 5 +- sound/pci/hda/patch_realtek.c | 2 + tools/testing/selftests/resctrl/resctrl.h | 6 +-- tools/testing/selftests/resctrl/resctrlfs.c | 52 ++++--------------- 26 files changed, 168 insertions(+), 99 deletions(-) -- 2.20.1

1 18

[PATCH openEuler-5.10 1/2] sched/rt: Fix double enqueue caused by rt_effective_prio
by Zheng Zengkai 19 Oct '21

19 Oct '21

From: Peter Zijlstra <peterz(a)infradead.org> stable inclusion from stable-5.10.58 commit a3e6bd0c71bb5e4821aff9ab8f221bfc08039d73 bugzilla: 176984 https://gitee.com/openeuler/kernel/issues/I4E2P4 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit f558c2b834ec27e75d37b1c860c139e7b7c3a8e4 upstream. Double enqueues in rt runqueues (list) have been reported while running a simple test that spawns a number of threads doing a short sleep/run pattern while being concurrently setscheduled between rt and fair class. WARNING: CPU: 3 PID: 2825 at kernel/sched/rt.c:1294 enqueue_task_rt+0x355/0x360 CPU: 3 PID: 2825 Comm: setsched__13 RIP: 0010:enqueue_task_rt+0x355/0x360 Call Trace: __sched_setscheduler+0x581/0x9d0 _sched_setscheduler+0x63/0xa0 do_sched_setscheduler+0xa0/0x150 __x64_sys_sched_setscheduler+0x1a/0x30 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae list_add double add: new=ffff9867cb629b40, prev=ffff9867cb629b40, next=ffff98679fc67ca0. kernel BUG at lib/list_debug.c:31! invalid opcode: 0000 [#1] PREEMPT_RT SMP PTI CPU: 3 PID: 2825 Comm: setsched__13 RIP: 0010:__list_add_valid+0x41/0x50 Call Trace: enqueue_task_rt+0x291/0x360 __sched_setscheduler+0x581/0x9d0 _sched_setscheduler+0x63/0xa0 do_sched_setscheduler+0xa0/0x150 __x64_sys_sched_setscheduler+0x1a/0x30 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae __sched_setscheduler() uses rt_effective_prio() to handle proper queuing of priority boosted tasks that are setscheduled while being boosted. rt_effective_prio() is however called twice per each __sched_setscheduler() call: first directly by __sched_setscheduler() before dequeuing the task and then by __setscheduler() to actually do the priority change. If the priority of the pi_top_task is concurrently being changed however, it might happen that the two calls return different results. If, for example, the first call returned the same rt priority the task was running at and the second one a fair priority, the task won't be removed by the rt list (on_list still set) and then enqueued in the fair runqueue. When eventually setscheduled back to rt it will be seen as enqueued already and the WARNING/BUG be issued. Fix this by calling rt_effective_prio() only once and then reusing the return value. While at it refactor code as well for clarity. Concurrent priority inheritance handling is still safe and will eventually converge to a new state by following the inheritance chain(s). Fixes: 0782e63bc6fe ("sched: Handle priority boosted tasks proper in setscheduler()") [squashed Peterz changes; added changelog] Reported-by: Mark Simmons <msimmons(a)redhat.com> Signed-off-by: Juri Lelli <juri.lelli(a)redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lkml.kernel.org/r/20210803104501.38333-1-juri.lelli@redhat.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Acked-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Signed-off-by: Zheng Zucheng <zhengzucheng(a)huawei.com> --- kernel/sched/core.c | 95 ++++++++++++++++++--------------------------- 1 file changed, 37 insertions(+), 58 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index cb5c2f9be849..d5434cc99934 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1590,12 +1590,18 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); } -/* - * __normal_prio - return the priority that is based on the static prio - */ -static inline int __normal_prio(struct task_struct *p) +static inline int __normal_prio(int policy, int rt_prio, int nice) { - return p->static_prio; + int prio; + + if (dl_policy(policy)) + prio = MAX_DL_PRIO - 1; + else if (rt_policy(policy)) + prio = MAX_RT_PRIO - 1 - rt_prio; + else + prio = NICE_TO_PRIO(nice); + + return prio; } /* @@ -1607,15 +1613,7 @@ static inline int __normal_prio(struct task_struct *p) */ static inline int normal_prio(struct task_struct *p) { - int prio; - - if (task_has_dl_policy(p)) - prio = MAX_DL_PRIO-1; - else if (task_has_rt_policy(p)) - prio = MAX_RT_PRIO-1 - p->rt_priority; - else - prio = __normal_prio(p); - return prio; + return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio)); } /* @@ -3240,7 +3238,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) } else if (PRIO_TO_NICE(p->static_prio) < 0) p->static_prio = NICE_TO_PRIO(0); - p->prio = p->normal_prio = __normal_prio(p); + p->prio = p->normal_prio = p->static_prio; set_load_weight(p, false); /* @@ -4986,6 +4984,18 @@ int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flag } EXPORT_SYMBOL(default_wake_function); +static void __setscheduler_prio(struct task_struct *p, int prio) +{ + if (dl_prio(prio)) + p->sched_class = &dl_sched_class; + else if (rt_prio(prio)) + p->sched_class = &rt_sched_class; + else + p->sched_class = &fair_sched_class; + + p->prio = prio; +} + #ifdef CONFIG_RT_MUTEXES static inline int __rt_effective_prio(struct task_struct *pi_task, int prio) @@ -5101,22 +5111,19 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) } else { p->dl.pi_se = &p->dl; } - p->sched_class = &dl_sched_class; } else if (rt_prio(prio)) { if (dl_prio(oldprio)) p->dl.pi_se = &p->dl; if (oldprio < prio) queue_flag |= ENQUEUE_HEAD; - p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) p->dl.pi_se = &p->dl; if (rt_prio(oldprio)) p->rt.timeout = 0; - p->sched_class = &fair_sched_class; } - p->prio = prio; + __setscheduler_prio(p, prio); if (queued) enqueue_task(rq, p, queue_flag); @@ -5349,35 +5356,6 @@ static void __setscheduler_params(struct task_struct *p, set_load_weight(p, true); } -/* Actually do priority change: must hold pi & rq lock. */ -static void __setscheduler(struct rq *rq, struct task_struct *p, - const struct sched_attr *attr, bool keep_boost) -{ - /* - * If params can't change scheduling class changes aren't allowed - * either. - */ - if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS) - return; - - __setscheduler_params(p, attr); - - /* - * Keep a potential priority boosting if called from - * sched_setscheduler(). - */ - p->prio = normal_prio(p); - if (keep_boost) - p->prio = rt_effective_prio(p, p->prio); - - if (dl_prio(p->prio)) - p->sched_class = &dl_sched_class; - else if (rt_prio(p->prio)) - p->sched_class = &rt_sched_class; - else - p->sched_class = &fair_sched_class; -} - /* * Check the target process has a UID that matches the current process's: */ @@ -5398,10 +5376,8 @@ static int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi) { - int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : - MAX_RT_PRIO - 1 - attr->sched_priority; - int retval, oldprio, oldpolicy = -1, queued, running; - int new_effective_prio, policy = attr->sched_policy; + int oldpolicy = -1, policy = attr->sched_policy; + int retval, oldprio, newprio, queued, running; const struct sched_class *prev_class; struct rq_flags rf; int reset_on_fork; @@ -5611,6 +5587,7 @@ static int __sched_setscheduler(struct task_struct *p, p->sched_reset_on_fork = reset_on_fork; oldprio = p->prio; + newprio = __normal_prio(policy, attr->sched_priority, attr->sched_nice); if (pi) { /* * Take priority boosted tasks into account. If the new @@ -5619,8 +5596,8 @@ static int __sched_setscheduler(struct task_struct *p, * the runqueue. This will be done when the task deboost * itself. */ - new_effective_prio = rt_effective_prio(p, newprio); - if (new_effective_prio == oldprio) + newprio = rt_effective_prio(p, newprio); + if (newprio == oldprio) queue_flags &= ~DEQUEUE_MOVE; } @@ -5633,7 +5610,10 @@ static int __sched_setscheduler(struct task_struct *p, prev_class = p->sched_class; - __setscheduler(rq, p, attr, pi); + if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) { + __setscheduler_params(p, attr); + __setscheduler_prio(p, newprio); + } __setscheduler_uclamp(p, attr); if (queued) { @@ -7640,7 +7620,6 @@ static inline int alloc_qos_sched_group(struct task_group *tg, static void sched_change_qos_group(struct task_struct *tsk, struct task_group *tg) { struct sched_attr attr; - struct rq *rq = task_rq(tsk); /* * No need to re-setcheduler when a task is exiting or the task @@ -7651,8 +7630,8 @@ static void sched_change_qos_group(struct task_struct *tsk, struct task_group *t (tg->qos_level == -1)) { attr.sched_priority = 0; attr.sched_policy = SCHED_IDLE; - attr.sched_nice = PRIO_TO_NICE(tsk->static_prio); - __setscheduler(rq, tsk, &attr, 0); + __setscheduler_params(tsk, &attr); + __setscheduler_prio(tsk, tsk->static_prio); } } -- 2.20.1

1 1

[PATCH openEuler-1.0-LTS 1/4] ovl: fix out of date comment and unreachable code
by Yang Yingliang 19 Oct '21

19 Oct '21

From: Amir Goldstein <amir73il(a)gmail.com> mainline inclusion from mainline-v5.7-rc1 commit 735c907d7b7df501e951ba07134b9f6f989a94e4 category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- ovl_inode_update() is no longer called from create object code path. Fixes: 01b39dcc9568 ("ovl: use inode_insert5() to hash a newly...") Signed-off-by: Amir Goldstein <amir73il(a)gmail.com> Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Signed-off-by: Zheng Liang <zhengliang6(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/overlayfs/inode.c | 8 +++++--- fs/overlayfs/util.c | 2 -- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d1e9d926150b1..b016343a7209b 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -555,9 +555,11 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev, * bits to encode layer), set the same value used for st_ino to i_ino, * so inode number exposed via /proc/locks and a like will be * consistent with d_ino and st_ino values. An i_ino value inconsistent - * with d_ino also causes nfsd readdirplus to fail. When called from - * ovl_new_inode(), ino arg is 0, so i_ino will be updated to real - * upper inode i_ino on ovl_inode_init() or ovl_inode_update(). + * with d_ino also causes nfsd readdirplus to fail. + * + * When called from ovl_create_object() => ovl_new_inode(), with + * ino = 0, i_ino will be updated to consistent value later on in + * ovl_get_inode() => ovl_fill_inode(). */ if (ovl_same_dev(inode->i_sb)) { inode->i_ino = ino; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index eb9411461b695..b83955f31ded0 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -419,8 +419,6 @@ void ovl_inode_update(struct inode *inode, struct dentry *upperdentry) smp_wmb(); OVL_I(inode)->__upperdentry = upperdentry; if (inode_unhashed(inode)) { - if (!inode->i_ino) - inode->i_ino = upperinode->i_ino; inode->i_private = upperinode; __insert_inode_hash(inode, (unsigned long) upperinode); } -- 2.25.1

1 3

[PATCH kernel-4.19 1/4] ovl: fix out of date comment and unreachable code
by Yang Yingliang 19 Oct '21

19 Oct '21

From: Amir Goldstein <amir73il(a)gmail.com> mainline inclusion from mainline-v5.7-rc1 commit 735c907d7b7df501e951ba07134b9f6f989a94e4 category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- ovl_inode_update() is no longer called from create object code path. Fixes: 01b39dcc9568 ("ovl: use inode_insert5() to hash a newly...") Signed-off-by: Amir Goldstein <amir73il(a)gmail.com> Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Signed-off-by: Zheng Liang <zhengliang6(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/overlayfs/inode.c | 8 +++++--- fs/overlayfs/util.c | 2 -- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d1e9d926150b1..b016343a7209b 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -555,9 +555,11 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev, * bits to encode layer), set the same value used for st_ino to i_ino, * so inode number exposed via /proc/locks and a like will be * consistent with d_ino and st_ino values. An i_ino value inconsistent - * with d_ino also causes nfsd readdirplus to fail. When called from - * ovl_new_inode(), ino arg is 0, so i_ino will be updated to real - * upper inode i_ino on ovl_inode_init() or ovl_inode_update(). + * with d_ino also causes nfsd readdirplus to fail. + * + * When called from ovl_create_object() => ovl_new_inode(), with + * ino = 0, i_ino will be updated to consistent value later on in + * ovl_get_inode() => ovl_fill_inode(). */ if (ovl_same_dev(inode->i_sb)) { inode->i_ino = ino; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index eb9411461b695..b83955f31ded0 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -419,8 +419,6 @@ void ovl_inode_update(struct inode *inode, struct dentry *upperdentry) smp_wmb(); OVL_I(inode)->__upperdentry = upperdentry; if (inode_unhashed(inode)) { - if (!inode->i_ino) - inode->i_ino = upperinode->i_ino; inode->i_private = upperinode; __insert_inode_hash(inode, (unsigned long) upperinode); } -- 2.25.1

1 3

Re: [PATCH openEuler-1.0-LTS V2 5/5] drm/hisilicon: Features to support reading resolutions from EDID
by QiuLaibin 19 Oct '21

19 Oct '21

hi gouhao: 这个补丁删除了hibmc_connector_init使用点，导致hibmc_connector_init函数申明但无使用点告警。同时注意到本patch部分代码在主线通过 be8c8403f63cf ("drm/hisilicon: Code refactoring for hibmc_drv_vdac") 合入，因此希望能够直接将该patch作为本patch的前向补丁一起合入。 best regard >>>>>>>>>>>>>>>>>>>>>>>>>> [WARNING] build_arm64_kabi <<<<<<<<<<<<<<<<<<<<<<<<<< make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- defconfig && make -j8 ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c:125:1: warning: ‘hibmc_connector_init’ defined but not used [-Wunused-function] hibmc_connector_init(struct hibmc_drm_private *priv) ^~~~~~~~~~~~~~~~~~~~ ==================================END================================== On 2021/9/18 11:11, Gou Hao wrote: > From: Tian Tao <tiantao6(a)hisilicon.com> mainline inclusion from > mainline-v5.14.0-rc7 commit a0d078d06e516184e2f575f3803935697b5e3ac6 > category: bugfix bugzilla: > https://gitee.com/openeuler/kernel/issues/I469VQCVE: NA The > modification of hibmc_vdac_init in the original patch cannot be > incorporated. In this patch, the hibmc_vdac_init is backport from the > mainline code. --------------------------------------- Use > drm_get_edid to get the resolution, if that fails, set it to a fixed > resolution. Rewrite the desrtoy callback function to release > resources. Signed-off-by: Tian Tao <tiantao6(a)hisilicon.com> > Reviewed-by: Thomas Zimmermann <tzimmermann(a)suse.de> Link: > https://patchwork.freedesktop.org/patch/msgid/1600778670-60370-3-git-send... > <https://patchwork.freedesktop.org/patch/msgid/1600778670-60370-3-git-send-e…>Signed-off-by: > gouhao <gouhao(a)uniontech.com> --- > .../gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 55 ++++++++++++++----- > 1 file changed, 41 insertions(+), 14 deletions(-) diff --git > a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c > b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c index > 90319a902..762e3404e 100644 --- > a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c +++ > b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c @@ -59,11 +59,23 @@ > static int hibmc_valid_mode(int w, int h) static int > hibmc_connector_get_modes(struct drm_connector *connector) { int > count; + void *edid; + struct hibmc_connector *hibmc_connector = > to_hibmc_connector(connector); + + edid = drm_get_edid(connector, > &hibmc_connector->adapter); + if (edid) { + > drm_connector_update_edid_property(connector, edid); + count = > drm_add_edid_modes(connector, edid); + if (count) + goto out; + } > drm_connector_update_edid_property(connector, NULL); count = > drm_add_modes_noedid(connector, 1920, 1200); > drm_set_preferred_mode(connector, 1024, 768); +out: + kfree(edid); > return count; } @@ -86,6 +98,14 @@ hibmc_connector_best_encoder(struct > drm_connector *connector) return drm_encoder_find(connector->dev, > NULL, connector->encoder_ids[0]); } +static void > hibmc_connector_destroy(struct drm_connector *connector) +{ + struct > hibmc_connector *hibmc_connector = to_hibmc_connector(connector); + + > i2c_del_adapter(&hibmc_connector->adapter); + > drm_connector_cleanup(connector); +} + static const struct > drm_connector_helper_funcs hibmc_connector_helper_funcs = { .get_modes > = hibmc_connector_get_modes, @@ -95,7 +115,7 @@ static const struct > drm_connector_helper_funcs static const struct drm_connector_funcs > hibmc_connector_funcs = { .fill_modes = > drm_helper_probe_single_connector_modes, - .destroy = > drm_connector_cleanup, + .destroy = hibmc_connector_destroy, .reset = > drm_atomic_helper_connector_reset, .atomic_duplicate_state = > drm_atomic_helper_connector_duplicate_state, .atomic_destroy_state = > drm_atomic_helper_connector_destroy_state, @@ -155,21 +175,16 @@ > static const struct drm_encoder_funcs hibmc_encoder_funcs = { int > hibmc_vdac_init(struct hibmc_drm_private *priv) { struct drm_device > *dev = priv->dev; - struct drm_encoder *encoder; - struct > drm_connector *connector; + struct hibmc_connector *hibmc_connector = > &priv->connector; + struct drm_encoder *encoder = &priv->encoder; + > struct drm_connector *connector = &hibmc_connector->base; int ret; - > connector = hibmc_connector_init(priv); > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 删除后导致hibmc_connector_init函数申明但无使用点告警。 > - if (IS_ERR(connector)) { - DRM_ERROR("failed to create connector: > %ld\n", - PTR_ERR(connector)); - return PTR_ERR(connector); - } - - > encoder = devm_kzalloc(dev->dev, sizeof(*encoder), GFP_KERNEL); - if > (!encoder) { - DRM_ERROR("failed to alloc memory when init > encoder\n"); - return -ENOMEM; + + ret = hibmc_ddc_create(dev, > hibmc_connector); + if (ret) { + DRM_ERROR("failed to create ddc: > %d\n", ret); + return ret; } encoder->possible_crtcs = 0x1; @@ -181,6 > +196,18 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) } > drm_encoder_helper_add(encoder, &hibmc_encoder_helper_funcs); + + ret > = drm_connector_init_with_ddc(dev, connector, + > &hibmc_connector_funcs, + DRM_MODE_CONNECTOR_VGA, + > &hibmc_connector->adapter); + if (ret) { + DRM_ERROR("failed to init > connector: %d\n", ret); + return ret; + } + + > drm_connector_helper_add(connector, &hibmc_connector_helper_funcs); + > drm_connector_attach_encoder(connector, encoder); return 0; -- 2.20.1 >

1 0

[PATCH openEuler-1.0-LTS V2 0/5] drm/hisilicon: Fix hibmc did not get edid
by Gou Hao 19 Oct '21

19 Oct '21

From: gouhao <gouhao(a)uniontech.com> Fix hibmc did not get edid. issue: https://gitee.com/openeuler/kernel/issues/I469VQ gouhao (5): drm-Split-out-drm_probe_helper.h drm-Add-ddc-link-in-sysfs-created-by-drm_connector drm-Add-drm_connector_init-variant-with-ddc drm/hisilicon: Support i2c driver algorithms for bit-shift adapters drm/hisilicon: Features to support reading resolutions from EDID drivers/gpu/drm/drm_connector.c | 35 +++++++ drivers/gpu/drm/drm_sysfs.c | 8 ++ drivers/gpu/drm/hisilicon/hibmc/Makefile | 3 +- .../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 26 +++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c | 99 +++++++++++++++++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 55 ++++++++--- include/drm/drm_connector.h | 18 ++++ include/drm/drm_probe_helper.h | 27 +++++ 8 files changed, 256 insertions(+), 15 deletions(-) create mode 100644 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c create mode 100644 include/drm/drm_probe_helper.h -- 2.20.1

4 8

[PATCH openEuler-21.03 00/10] openEuler patches
by Wang ShaoBo 18 Oct '21

18 Oct '21

openEuler patches Andi Kleen (1): perf stat: Add a new --quiet option to 'perf stat' Chris Packham (1): i2c: mpc: Make use of i2c_recover_bus() Desmond Cheong Zhi Xi (1): drm: Lock pointer access in drm_master_release() Jiri Olsa (1): bpf: Forbid trampoline attach for functions with variable arguments Kees Cook (1): proc: Track /proc/$pid/attr/ opener mm_struct Liangyan (1): tracing: Correct the length check which causes memory corruption Steven Rostedt (VMware) (1): ftrace: Do not blindly read the ip address in ftrace_bug() mpiglet (1): arm64/mpam: add return value check for acpi_get_table() wenzhiwei11 (1): arm64/mpam: fix the problem that the ret variable is not initialized yin-xiujiang (1): arm64/mpam: fix device_errcode out of bounds arch/arm64/kernel/mpam/mpam_ctrlmon.c | 2 +- arch/arm64/kernel/mpam/mpam_device.c | 2 +- drivers/acpi/arm64/mpam.c | 2 +- drivers/gpu/drm/drm_auth.c | 3 ++- drivers/i2c/busses/i2c-mpc.c | 18 ++++++++++++++++-- fs/proc/base.c | 9 ++++++++- kernel/bpf/btf.c | 12 ++++++++++++ kernel/trace/ftrace.c | 8 +++++++- kernel/trace/trace.c | 2 +- tools/perf/Documentation/perf-stat.txt | 4 ++++ tools/perf/builtin-stat.c | 6 +++++- tools/perf/util/stat.h | 1 + 12 files changed, 59 insertions(+), 10 deletions(-) -- 2.25.1

1 10

[PATCH openEuler-1.0-LTS] soc: aspeed: lpc-ctrl: Fix boundary check for mmap
by Yang Yingliang 18 Oct '21

18 Oct '21

From: Iwona Winiarska <iwona.winiarska(a)intel.com> stable inclusion from linux-4.19.207 commit 9c8891b638319ddba9cfa330247922cd960c95b0 CVE: CVE-2021-42252 -------------------------------- commit b49a0e69a7b1a68c8d3f64097d06dabb770fec96 upstream. The check mixes pages (vm_pgoff) with bytes (vm_start, vm_end) on one side of the comparison, and uses resource address (rather than just the resource size) on the other side of the comparison. This can allow malicious userspace to easily bypass the boundary check and map pages that are located outside memory-region reserved by the driver. Fixes: 6c4e97678501 ("drivers/misc: Add Aspeed LPC control driver") Cc: stable(a)vger.kernel.org Signed-off-by: Iwona Winiarska <iwona.winiarska(a)intel.com> Reviewed-by: Andrew Jeffery <andrew(a)aj.id.au> Tested-by: Andrew Jeffery <andrew(a)aj.id.au> Reviewed-by: Joel Stanley <joel(a)aj.id.au> Signed-off-by: Joel Stanley <joel(a)jms.id.au> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/misc/aspeed-lpc-ctrl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/aspeed-lpc-ctrl.c b/drivers/misc/aspeed-lpc-ctrl.c index a024f8042259a..870ab0dfcde06 100644 --- a/drivers/misc/aspeed-lpc-ctrl.c +++ b/drivers/misc/aspeed-lpc-ctrl.c @@ -50,7 +50,7 @@ static int aspeed_lpc_ctrl_mmap(struct file *file, struct vm_area_struct *vma) unsigned long vsize = vma->vm_end - vma->vm_start; pgprot_t prot = vma->vm_page_prot; - if (vma->vm_pgoff + vsize > lpc_ctrl->mem_base + lpc_ctrl->mem_size) + if (vma->vm_pgoff + vma_pages(vma) > lpc_ctrl->mem_size >> PAGE_SHIFT) return -EINVAL; /* ast2400/2500 AHB accesses are not cache coherent */ -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/2] mmap: userswap: fix memory leak in do_mmap
by Yang Yingliang 18 Oct '21

18 Oct '21

From: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AHP2 CVE: NA ------------------------------------------------- When userswap is enabled, the memory pointed by 'pages' is not freed in abnormal branch in do_mmap(). To fix the issue and keep do_mmap() mostly unchanged, we rename do_mmap() to __do_mmap() and extract the memory alloc and free code out of __do_mmap(). When __do_mmap() returns a error value, we goto the error label to free the memory. Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/mmap.c | 406 ++++++++++++++++++++++++++++-------------------------- 1 file changed, 211 insertions(+), 195 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 90cff771af771..074fbc0c559a7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1373,173 +1373,8 @@ int unregister_mmap_notifier(struct notifier_block *nb) EXPORT_SYMBOL_GPL(unregister_mmap_notifier); #endif -#ifdef CONFIG_USERSWAP -/* - * Check if pages between 'addr ~ addr+len' can be user swapped. If so, get - * the reference of the pages and return the pages through input parameters - * 'ppages'. - */ -int pages_can_be_swapped(struct mm_struct *mm, unsigned long addr, - unsigned long len, struct page ***ppages) -{ - struct vm_area_struct *vma; - struct page *page = NULL; - struct page **pages = NULL; - unsigned long addr_start, addr_end; - unsigned long ret; - int i, page_num = 0; - - pages = kmalloc(sizeof(struct page *) * (len / PAGE_SIZE), GFP_KERNEL); - if (!pages) - return -ENOMEM; - - addr_start = addr; - addr_end = addr + len; - while (addr < addr_end) { - vma = find_vma(mm, addr); - if (!vma || !vma_is_anonymous(vma) || - (vma->vm_flags & VM_LOCKED) || vma->vm_file - || (vma->vm_flags & VM_STACK) || (vma->vm_flags & (VM_IO | VM_PFNMAP))) { - ret = -EINVAL; - goto out; - } - if (!(vma->vm_flags & VM_UFFD_MISSING)) { - ret = -EAGAIN; - goto out; - } -get_again: - /* follow_page will inc page ref, dec the ref after we remap the page */ - page = follow_page(vma, addr, FOLL_GET); - if (IS_ERR_OR_NULL(page)) { - ret = -ENODEV; - goto out; - } - pages[page_num] = page; - page_num++; - if (!PageAnon(page) || !PageSwapBacked(page) || PageHuge(page) || PageSwapCache(page)) { - ret = -EINVAL; - goto out; - } else if (PageTransCompound(page)) { - if (trylock_page(page)) { - if (!split_huge_page(page)) { - put_page(page); - page_num--; - unlock_page(page); - goto get_again; - } else { - unlock_page(page); - ret = -EINVAL; - goto out; - } - } else { - ret = -EINVAL; - goto out; - } - } - if (page_mapcount(page) > 1 || page_mapcount(page) + 1 != page_count(page)) { - ret = -EBUSY; - goto out; - } - addr += PAGE_SIZE; - } - - *ppages = pages; - return 0; - -out: - for (i = 0; i < page_num; i++) - put_page(pages[i]); - if (pages) - kfree(pages); - *ppages = NULL; - return ret; -} - -/* - * In uswap situation, we use the bit 0 of the returned address to indicate - * whether the pages are dirty. - */ -#define USWAP_PAGES_DIRTY 1 - -/* unmap the pages between 'addr ~ addr+len' and remap them to a new address */ -unsigned long do_user_swap(struct mm_struct *mm, unsigned long addr_start, - unsigned long len, struct page **pages, unsigned long new_addr) -{ - struct vm_area_struct *vma; - struct page *page; - pmd_t *pmd; - pte_t *pte, old_pte; - spinlock_t *ptl; - unsigned long addr, addr_end; - bool pages_dirty = false; - int i, err; - - addr_end = addr_start + len; - lru_add_drain(); - mmu_notifier_invalidate_range_start(mm, addr_start, addr_end); - addr = addr_start; - i = 0; - while (addr < addr_end) { - page = pages[i]; - vma = find_vma(mm, addr); - if (!vma) { - mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); - WARN_ON("find_vma failed\n"); - return -EINVAL; - } - pmd = mm_find_pmd(mm, addr); - if (!pmd) { - mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); - WARN_ON("mm_find_pmd failed, addr:%llx\n"); - return -ENXIO; - } - pte = pte_offset_map_lock(mm, pmd, addr, &ptl); - flush_cache_page(vma, addr, pte_pfn(*pte)); - old_pte = ptep_clear_flush(vma, addr, pte); - if (pte_dirty(old_pte) || PageDirty(page)) - pages_dirty = true; - set_pte(pte, swp_entry_to_pte(swp_entry(SWP_USERSWAP_ENTRY, page_to_pfn(page)))); - dec_mm_counter(mm, MM_ANONPAGES); - page_remove_rmap(page, false); - put_page(page); - - pte_unmap_unlock(pte, ptl); - vma->vm_flags |= VM_USWAP; - page->mapping = NULL; - addr += PAGE_SIZE; - i++; - } - mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); - - addr_start = new_addr; - addr_end = new_addr + len; - addr = addr_start; - vma = find_vma(mm, addr); - i = 0; - while (addr < addr_end) { - page = pages[i]; - if (addr > vma->vm_end - 1) - vma = find_vma(mm, addr); - err = vm_insert_page(vma, addr, page); - if (err) { - pr_err("vm_insert_page failed:%d\n", err); - } - i++; - addr += PAGE_SIZE; - } - vma->vm_flags |= VM_USWAP; - - if (pages_dirty) - new_addr = new_addr | USWAP_PAGES_DIRTY; - - return new_addr; -} -#endif - -/* - * The caller must hold down_write(&current->mm->mmap_sem). - */ -unsigned long do_mmap(struct file *file, unsigned long addr, +static inline +unsigned long __do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, @@ -1547,12 +1382,6 @@ unsigned long do_mmap(struct file *file, unsigned long addr, { struct mm_struct *mm = current->mm; int pkey = 0; -#ifdef CONFIG_USERSWAP - struct page **pages = NULL; - unsigned long addr_start = addr; - int i, page_num = 0; - unsigned long ret; -#endif *populate = 0; @@ -1569,17 +1398,6 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (!(file && path_noexec(&file->f_path))) prot |= PROT_EXEC; -#ifdef CONFIG_USERSWAP - if (enable_userswap && (flags & MAP_REPLACE)) { - if (offset_in_page(addr) || (len % PAGE_SIZE)) - return -EINVAL; - page_num = len / PAGE_SIZE; - ret = pages_can_be_swapped(mm, addr, len, &pages); - if (ret) - return ret; - } -#endif - /* force arch specific MAP_FIXED handling in get_unmapped_area */ if (flags & MAP_FIXED_NOREPLACE) flags |= MAP_FIXED; @@ -1752,25 +1570,203 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (flags & MAP_CHECKNODE) set_vm_checknode(&vm_flags, flags); -#ifdef CONFIG_USERSWAP - /* mark the vma as special to avoid merging with other vmas */ - if (enable_userswap && (flags & MAP_REPLACE)) - vm_flags |= VM_SPECIAL; -#endif - addr = mmap_region(file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) || (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) *populate = len; -#ifndef CONFIG_USERSWAP return addr; -#else - if (!enable_userswap || !(flags & MAP_REPLACE)) - return addr; +} + +#ifdef CONFIG_USERSWAP +/* + * Check if pages between 'addr ~ addr+len' can be user swapped. If so, get + * the reference of the pages and return the pages through input parameters + * 'ppages'. + */ +int pages_can_be_swapped(struct mm_struct *mm, unsigned long addr, + unsigned long len, struct page ***ppages) +{ + struct vm_area_struct *vma; + struct page *page = NULL; + struct page **pages = NULL; + unsigned long addr_start, addr_end; + unsigned long ret; + int i, page_num = 0; + + pages = kmalloc(sizeof(struct page *) * (len / PAGE_SIZE), GFP_KERNEL); + if (!pages) + return -ENOMEM; + + addr_start = addr; + addr_end = addr + len; + while (addr < addr_end) { + vma = find_vma(mm, addr); + if (!vma || !vma_is_anonymous(vma) || + (vma->vm_flags & VM_LOCKED) || vma->vm_file + || (vma->vm_flags & VM_STACK) || (vma->vm_flags & (VM_IO | VM_PFNMAP))) { + ret = -EINVAL; + goto out; + } + if (!(vma->vm_flags & VM_UFFD_MISSING)) { + ret = -EAGAIN; + goto out; + } +get_again: + /* follow_page will inc page ref, dec the ref after we remap the page */ + page = follow_page(vma, addr, FOLL_GET); + if (IS_ERR_OR_NULL(page)) { + ret = -ENODEV; + goto out; + } + pages[page_num] = page; + page_num++; + if (!PageAnon(page) || !PageSwapBacked(page) || PageHuge(page) || PageSwapCache(page)) { + ret = -EINVAL; + goto out; + } else if (PageTransCompound(page)) { + if (trylock_page(page)) { + if (!split_huge_page(page)) { + put_page(page); + page_num--; + unlock_page(page); + goto get_again; + } else { + unlock_page(page); + ret = -EINVAL; + goto out; + } + } else { + ret = -EINVAL; + goto out; + } + } + if (page_mapcount(page) > 1 || page_mapcount(page) + 1 != page_count(page)) { + ret = -EBUSY; + goto out; + } + addr += PAGE_SIZE; + } + + *ppages = pages; + return 0; + +out: + for (i = 0; i < page_num; i++) + put_page(pages[i]); + if (pages) + kfree(pages); + *ppages = NULL; + return ret; +} + +/* + * In uswap situation, we use the bit 0 of the returned address to indicate + * whether the pages are dirty. + */ +#define USWAP_PAGES_DIRTY 1 + +/* unmap the pages between 'addr ~ addr+len' and remap them to a new address */ +unsigned long do_user_swap(struct mm_struct *mm, unsigned long addr_start, + unsigned long len, struct page **pages, unsigned long new_addr) +{ + struct vm_area_struct *vma; + struct page *page; + pmd_t *pmd; + pte_t *pte, old_pte; + spinlock_t *ptl; + unsigned long addr, addr_end; + bool pages_dirty = false; + int i, err; + addr_end = addr_start + len; + lru_add_drain(); + mmu_notifier_invalidate_range_start(mm, addr_start, addr_end); + addr = addr_start; + i = 0; + while (addr < addr_end) { + page = pages[i]; + vma = find_vma(mm, addr); + if (!vma) { + mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); + WARN_ON("find_vma failed\n"); + return -EINVAL; + } + pmd = mm_find_pmd(mm, addr); + if (!pmd) { + mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); + WARN_ON("mm_find_pmd failed, addr:%llx\n"); + return -ENXIO; + } + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + flush_cache_page(vma, addr, pte_pfn(*pte)); + old_pte = ptep_clear_flush(vma, addr, pte); + if (pte_dirty(old_pte) || PageDirty(page)) + pages_dirty = true; + set_pte(pte, swp_entry_to_pte(swp_entry(SWP_USERSWAP_ENTRY, page_to_pfn(page)))); + dec_mm_counter(mm, MM_ANONPAGES); + page_remove_rmap(page, false); + put_page(page); + + pte_unmap_unlock(pte, ptl); + vma->vm_flags |= VM_USWAP; + page->mapping = NULL; + addr += PAGE_SIZE; + i++; + } + mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); + + addr_start = new_addr; + addr_end = new_addr + len; + addr = addr_start; + vma = find_vma(mm, addr); + i = 0; + while (addr < addr_end) { + page = pages[i]; + if (addr > vma->vm_end - 1) + vma = find_vma(mm, addr); + err = vm_insert_page(vma, addr, page); + if (err) { + pr_err("vm_insert_page failed:%d\n", err); + } + i++; + addr += PAGE_SIZE; + } + vma->vm_flags |= VM_USWAP; + + if (pages_dirty) + new_addr = new_addr | USWAP_PAGES_DIRTY; + + return new_addr; +} + +static inline +unsigned long do_uswap_mmap(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, + unsigned long flags, vm_flags_t vm_flags, + unsigned long pgoff, unsigned long *populate, + struct list_head *uf) +{ + struct mm_struct *mm = current->mm; + unsigned long addr_start = addr; + struct page **pages = NULL; + unsigned long ret; + int i, page_num = 0; + + if (!len || offset_in_page(addr) || (len % PAGE_SIZE)) + return -EINVAL; + + page_num = len / PAGE_SIZE; + ret = pages_can_be_swapped(mm, addr, len, &pages); + if (ret) + return ret; + + /* mark the vma as special to avoid merging with other vmas */ + vm_flags |= VM_SPECIAL; + + addr = __do_mmap(file, addr, len, prot, flags, vm_flags, pgoff, + populate, uf); if (IS_ERR_VALUE(addr)) { - pr_info("mmap_region failed, return addr:%lx\n", addr); ret = addr; goto out; } @@ -1780,10 +1776,30 @@ unsigned long do_mmap(struct file *file, unsigned long addr, /* follow_page() above increased the reference*/ for (i = 0; i < page_num; i++) put_page(pages[i]); + if (pages) kfree(pages); + return ret; +} +#endif + +/* + * The caller must hold down_write(&current->mm->mmap_sem). + */ +unsigned long do_mmap(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, + unsigned long flags, vm_flags_t vm_flags, + unsigned long pgoff, unsigned long *populate, + struct list_head *uf) +{ +#ifdef CONFIG_USERSWAP + if (enable_userswap && (flags & MAP_REPLACE)) + return do_uswap_mmap(file, addr, len, prot, flags, vm_flags, + pgoff, populate, uf); #endif + return __do_mmap(file, addr, len, prot, flags, vm_flags, + pgoff, populate, uf); } unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, -- 2.25.1

1 1

Re: [PATCH openEuler-21.03] MIPS: Fix kernel hang under FUNCTION_GRAPH_TRACER and PREEMPT_TRACER
by chengjian (D) 18 Oct '21

18 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/16 23:06, jack 写道: > From: Tiezhu Yang <yangtiezhu(a)loongson.cn> > > stable inclusion > from stable-v5.10.44 > commit 7519ece673e300b0362572edbde7e030552705ec > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=417 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 78cf0eb926cb1abeff2106bae67752e032fe5f3e ] > > When update the latest mainline kernel with the following three configs, > the kernel hangs during startup: > > (1) CONFIG_FUNCTION_GRAPH_TRACER=y > (2) CONFIG_PREEMPT_TRACER=y > (3) CONFIG_FTRACE_STARTUP_TEST=y > > When update the latest mainline kernel with the above two configs (1) > and (2), the kernel starts normally, but it still hangs when execute > the following command: > > echo "function_graph" > /sys/kernel/debug/tracing/current_tracer > > Without CONFIG_PREEMPT_TRACER=y, the above two kinds of kernel hangs > disappeared, so it seems that CONFIG_PREEMPT_TRACER has some influences > with function_graph tracer at the first glance. > > I use ejtag to find out the epc address is related with preempt_enable() > in the file arch/mips/lib/mips-atomic.c, because function tracing can > trace the preempt_{enable,disable} calls that are traced, replace them > with preempt_{enable,disable}_notrace to prevent function tracing from > going into an infinite loop, and then it can fix the kernel hang issue. > > By the way, it seems that this commit is a complement and improvement of > commit f93a1a00f2bd ("MIPS: Fix crash that occurs when function tracing > is enabled"). > > Signed-off-by: Tiezhu Yang <yangtiezhu(a)loongson.cn> > Cc: Steven Rostedt <rostedt(a)goodmis.org> > Signed-off-by: Thomas Bogendoerfer <tsbogend(a)alpha.franken.de> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: jack <18380124974(a)163.com> > --- > arch/mips/lib/mips-atomic.c | 12 ++++++------ > 1 file changed, 6 insertions(+), 6 deletions(-) > > diff --git a/arch/mips/lib/mips-atomic.c b/arch/mips/lib/mips-atomic.c > index de03838b343b..a9b72eacfc0b 100644 > --- a/arch/mips/lib/mips-atomic.c > +++ b/arch/mips/lib/mips-atomic.c > @@ -37,7 +37,7 @@ > */ > notrace void arch_local_irq_disable(void) > { > - preempt_disable(); > + preempt_disable_notrace(); > > __asm__ __volatile__( > " .set push \n" > @@ -53,7 +53,7 @@ notrace void arch_local_irq_disable(void) > : /* no inputs */ > : "memory"); > > - preempt_enable(); > + preempt_enable_notrace(); > } > EXPORT_SYMBOL(arch_local_irq_disable); > > @@ -61,7 +61,7 @@ notrace unsigned long arch_local_irq_save(void) > { > unsigned long flags; > > - preempt_disable(); > + preempt_disable_notrace(); > > __asm__ __volatile__( > " .set push \n" > @@ -78,7 +78,7 @@ notrace unsigned long arch_local_irq_save(void) > : /* no inputs */ > : "memory"); > > - preempt_enable(); > + preempt_enable_notrace(); > > return flags; > } > @@ -88,7 +88,7 @@ notrace void arch_local_irq_restore(unsigned long flags) > { > unsigned long __tmp1; > > - preempt_disable(); > + preempt_disable_notrace(); > > __asm__ __volatile__( > " .set push \n" > @@ -106,7 +106,7 @@ notrace void arch_local_irq_restore(unsigned long flags) > : "0" (flags) > : "memory"); > > - preempt_enable(); > + preempt_enable_notrace(); > } > EXPORT_SYMBOL(arch_local_irq_restore); >

1 0

[PATCH kernel-4.19] arm64/mpam: fix the problem that the ret variable is not initialized
by Yang Yingliang 18 Oct '21

18 Oct '21

From: wenzhiwei11 <wenzhiwei(a)kylinos.cn> kylin inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AHUL CVE: NA --------------------------------------------------- initialize the value "ret" in "schemata_list_init()" Signed-off-by: wenzhiwei11 <wenzhiwei(a)kylinos.cn> # openEuler_contributor Reviewed-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/kernel/mpam/mpam_ctrlmon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/mpam/mpam_ctrlmon.c b/arch/arm64/kernel/mpam/mpam_ctrlmon.c index b1d32d432556c..b7508ad8c5314 100644 --- a/arch/arm64/kernel/mpam/mpam_ctrlmon.c +++ b/arch/arm64/kernel/mpam/mpam_ctrlmon.c @@ -127,7 +127,7 @@ static int add_schema(enum resctrl_conf_type t, struct resctrl_resource *r) int schemata_list_init(void) { - int ret; + int ret = 0; struct mpam_resctrl_res *res; struct resctrl_resource *r; -- 2.25.1

1 0

[PATCH openEuler-21.03] drm: Lock pointer access in drm_master_release()
by holmes 18 Oct '21

18 Oct '21

From: Desmond Cheong Zhi Xi <desmondcheongzx(a)gmail.com> stable inclusion from stable-v5.10.44 commit aa8591a58cbd2986090709e4202881f18e8ae30e bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=435 CVE: NA ------------------------------------------------- commit c336a5ee984708db4826ef9e47d184e638e29717 upstream. This patch eliminates the following smatch warning: drivers/gpu/drm/drm_auth.c:320 drm_master_release() warn: unlocked access 'master' (line 318) expected lock '&dev->master_mutex' The 'file_priv->master' field should be protected by the mutex lock to '&dev->master_mutex'. This is because other processes can concurrently modify this field and free the current 'file_priv->master' pointer. This could result in a use-after-free error when 'master' is dereferenced in subsequent function calls to 'drm_legacy_lock_master_cleanup()' or to 'drm_lease_revoke()'. An example of a scenario that would produce this error can be seen from a similar bug in 'drm_getunique()' that was reported by Syzbot: https://syzkaller.appspot.com/bug?id=148d2f1dfac64af52ffd27b661981a540724f8… In the Syzbot report, another process concurrently acquired the device's master mutex in 'drm_setmaster_ioctl()', then overwrote 'fpriv->master' in 'drm_new_set_master()'. The old value of 'fpriv->master' was subsequently freed before the mutex was unlocked. Reported-by: Dan Carpenter <dan.carpenter(a)oracle.com> Signed-off-by: Desmond Cheong Zhi Xi <desmondcheongzx(a)gmail.com> Cc: stable(a)vger.kernel.org Signed-off-by: Daniel Vetter <daniel.vetter(a)ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210609092119.173590-1-desmo… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: holmes <holmes(a)my.swjtu.edu.cn> --- drivers/gpu/drm/drm_auth.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c index f2d46b7ac6f9..232abbba3686 100644 --- a/drivers/gpu/drm/drm_auth.c +++ b/drivers/gpu/drm/drm_auth.c @@ -314,9 +314,10 @@ int drm_master_open(struct drm_file *file_priv) void drm_master_release(struct drm_file *file_priv) { struct drm_device *dev = file_priv->minor->dev; - struct drm_master *master = file_priv->master; + struct drm_master *master; mutex_lock(&dev->master_mutex); + master = file_priv->master; if (file_priv->magic) idr_remove(&file_priv->master->magic_map, file_priv->magic); -- 2.23.0

3 4

[PATCH kernel-4.19 1/3] NFS: Add a helper nfs_client_for_each_server()
by Yang Yingliang 18 Oct '21

18 Oct '21

From: Trond Myklebust <trond.myklebust(a)hammerspace.com> mainline inclusion from mainline-v5.7-rc1 commit 3c9e502b59fbd243cfac7cc6c875e432d285102a category: bugfix bugzilla: 182252 CVE: NA ----------------------------------------------- Add a helper nfs_client_for_each_server() to iterate through all the filesystems that are attached to a struct nfs_client, and apply a function to all the active ones. Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> Signed-off-by: ChenXiaoSong <chenxiaosong2(a)huawei.com> Reviewed-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/nfs/internal.h | 4 +++- fs/nfs/super.c | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+), 1 deletion(-) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index cc07189a501fa..c3c0b40f163f1 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -417,7 +417,9 @@ extern int __init register_nfs_fs(void); extern void __exit unregister_nfs_fs(void); extern bool nfs_sb_active(struct super_block *sb); extern void nfs_sb_deactive(struct super_block *sb); - +extern int nfs_client_for_each_server(struct nfs_client *clp, + int (*fn)(struct nfs_server *, void *), + void *data); /* io.c */ extern void nfs_start_io_read(struct inode *inode); extern void nfs_end_io_read(struct inode *inode); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index fe107348aabe6..48bcdcf4d039e 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -429,6 +429,41 @@ void nfs_sb_deactive(struct super_block *sb) } EXPORT_SYMBOL_GPL(nfs_sb_deactive); +static int __nfs_list_for_each_server(struct list_head *head, + int (*fn)(struct nfs_server *, void *), + void *data) +{ + struct nfs_server *server, *last = NULL; + int ret = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(server, head, client_link) { + if (!nfs_sb_active(server->super)) + continue; + rcu_read_unlock(); + if (last) + nfs_sb_deactive(last->super); + last = server; + ret = fn(server, data); + if (ret) + goto out; + rcu_read_lock(); + } + rcu_read_unlock(); +out: + if (last) + nfs_sb_deactive(last->super); + return ret; +} + +int nfs_client_for_each_server(struct nfs_client *clp, + int (*fn)(struct nfs_server *, void *), + void *data) +{ + return __nfs_list_for_each_server(&clp->cl_superblocks, fn, data); +} +EXPORT_SYMBOL_GPL(nfs_client_for_each_server); + /* * Deliver file system statistics to userspace */ -- 2.25.1

1 2

[PATCH kernel-4.19 1/2] mmap: userswap: fix memory leak in do_mmap
by Yang Yingliang 18 Oct '21

18 Oct '21

From: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AHP2 CVE: NA ------------------------------------------------- When userswap is enabled, the memory pointed by 'pages' is not freed in abnormal branch in do_mmap(). To fix the issue and keep do_mmap() mostly unchanged, we rename do_mmap() to __do_mmap() and extract the memory alloc and free code out of __do_mmap(). When __do_mmap() returns a error value, we goto the error label to free the memory. Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/mmap.c | 404 +++++++++++++++++++++++++++--------------------------- 1 file changed, 204 insertions(+), 200 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 378e1869ac7a0..69848726063c7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1384,172 +1384,6 @@ static unsigned long __mmap_region(struct mm_struct *mm, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf); -#ifdef CONFIG_USERSWAP -/* - * Check if pages between 'addr ~ addr+len' can be user swapped. If so, get - * the reference of the pages and return the pages through input parameters - * 'ppages'. - */ -int pages_can_be_swapped(struct mm_struct *mm, unsigned long addr, - unsigned long len, struct page ***ppages) -{ - struct vm_area_struct *vma; - struct page *page = NULL; - struct page **pages = NULL; - unsigned long addr_start, addr_end; - unsigned long ret; - int i, page_num = 0; - - pages = kmalloc(sizeof(struct page *) * (len / PAGE_SIZE), GFP_KERNEL); - if (!pages) - return -ENOMEM; - - addr_start = addr; - addr_end = addr + len; - while (addr < addr_end) { - vma = find_vma(mm, addr); - if (!vma || !vma_is_anonymous(vma) || - (vma->vm_flags & VM_LOCKED) || vma->vm_file - || (vma->vm_flags & VM_STACK) || (vma->vm_flags & (VM_IO | VM_PFNMAP))) { - ret = -EINVAL; - goto out; - } - if (!(vma->vm_flags & VM_UFFD_MISSING)) { - ret = -EAGAIN; - goto out; - } -get_again: - /* follow_page will inc page ref, dec the ref after we remap the page */ - page = follow_page(vma, addr, FOLL_GET); - if (IS_ERR_OR_NULL(page)) { - ret = -ENODEV; - goto out; - } - pages[page_num] = page; - page_num++; - if (!PageAnon(page) || !PageSwapBacked(page) || PageHuge(page) || PageSwapCache(page)) { - ret = -EINVAL; - goto out; - } else if (PageTransCompound(page)) { - if (trylock_page(page)) { - if (!split_huge_page(page)) { - put_page(page); - page_num--; - unlock_page(page); - goto get_again; - } else { - unlock_page(page); - ret = -EINVAL; - goto out; - } - } else { - ret = -EINVAL; - goto out; - } - } - if (page_mapcount(page) > 1 || page_mapcount(page) + 1 != page_count(page)) { - ret = -EBUSY; - goto out; - } - addr += PAGE_SIZE; - } - - *ppages = pages; - return 0; - -out: - for (i = 0; i < page_num; i++) - put_page(pages[i]); - if (pages) - kfree(pages); - *ppages = NULL; - return ret; -} - -/* - * In uswap situation, we use the bit 0 of the returned address to indicate - * whether the pages are dirty. - */ -#define USWAP_PAGES_DIRTY 1 - -/* unmap the pages between 'addr ~ addr+len' and remap them to a new address */ -unsigned long do_user_swap(struct mm_struct *mm, unsigned long addr_start, - unsigned long len, struct page **pages, unsigned long new_addr) -{ - struct vm_area_struct *vma; - struct page *page; - pmd_t *pmd; - pte_t *pte, old_pte; - spinlock_t *ptl; - unsigned long addr, addr_end; - bool pages_dirty = false; - int i, err; - - addr_end = addr_start + len; - lru_add_drain(); - mmu_notifier_invalidate_range_start(mm, addr_start, addr_end); - addr = addr_start; - i = 0; - while (addr < addr_end) { - page = pages[i]; - vma = find_vma(mm, addr); - if (!vma) { - mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); - WARN_ON("find_vma failed\n"); - return -EINVAL; - } - pmd = mm_find_pmd(mm, addr); - if (!pmd) { - mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); - WARN_ON("mm_find_pmd failed, addr:%llx\n"); - return -ENXIO; - } - pte = pte_offset_map_lock(mm, pmd, addr, &ptl); - flush_cache_page(vma, addr, pte_pfn(*pte)); - old_pte = ptep_clear_flush(vma, addr, pte); - if (pte_dirty(old_pte) || PageDirty(page)) - pages_dirty = true; - set_pte(pte, swp_entry_to_pte(swp_entry(SWP_USERSWAP_ENTRY, page_to_pfn(page)))); - dec_mm_counter(mm, MM_ANONPAGES); - page_remove_rmap(page, false); - put_page(page); - - pte_unmap_unlock(pte, ptl); - vma->vm_flags |= VM_USWAP; - page->mapping = NULL; - addr += PAGE_SIZE; - i++; - } - mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); - - addr_start = new_addr; - addr_end = new_addr + len; - addr = addr_start; - vma = find_vma(mm, addr); - i = 0; - while (addr < addr_end) { - page = pages[i]; - if (addr > vma->vm_end - 1) - vma = find_vma(mm, addr); - err = vm_insert_page(vma, addr, page); - if (err) { - pr_err("vm_insert_page failed:%d\n", err); - } - i++; - addr += PAGE_SIZE; - } - vma->vm_flags |= VM_USWAP; - - if (pages_dirty) - new_addr = new_addr | USWAP_PAGES_DIRTY; - - return new_addr; -} -#endif - -/* - * The caller must hold down_write(&current->mm->mmap_sem). - */ unsigned long __do_mmap(struct mm_struct *mm, struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, @@ -1557,12 +1391,6 @@ unsigned long __do_mmap(struct mm_struct *mm, struct file *file, unsigned long *populate, struct list_head *uf) { int pkey = 0; -#ifdef CONFIG_USERSWAP - struct page **pages = NULL; - unsigned long addr_start = addr; - int i, page_num = 0; - unsigned long ret; -#endif *populate = 0; @@ -1579,17 +1407,6 @@ unsigned long __do_mmap(struct mm_struct *mm, struct file *file, if (!(file && path_noexec(&file->f_path))) prot |= PROT_EXEC; -#ifdef CONFIG_USERSWAP - if (enable_userswap && (flags & MAP_REPLACE)) { - if (offset_in_page(addr) || (len % PAGE_SIZE)) - return -EINVAL; - page_num = len / PAGE_SIZE; - ret = pages_can_be_swapped(mm, addr, len, &pages); - if (ret) - return ret; - } -#endif - /* force arch specific MAP_FIXED handling in get_unmapped_area */ if (flags & MAP_FIXED_NOREPLACE) flags |= MAP_FIXED; @@ -1766,25 +1583,203 @@ unsigned long __do_mmap(struct mm_struct *mm, struct file *file, if (flags & MAP_CHECKNODE) set_vm_checknode(&vm_flags, flags); -#ifdef CONFIG_USERSWAP - /* mark the vma as special to avoid merging with other vmas */ - if (enable_userswap && (flags & MAP_REPLACE)) - vm_flags |= VM_SPECIAL; -#endif - addr = __mmap_region(mm, file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) || (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) *populate = len; -#ifndef CONFIG_USERSWAP return addr; -#else - if (!enable_userswap || !(flags & MAP_REPLACE)) - return addr; +} +#ifdef CONFIG_USERSWAP +/* + * Check if pages between 'addr ~ addr+len' can be user swapped. If so, get + * the reference of the pages and return the pages through input parameters + * 'ppages'. + */ +int pages_can_be_swapped(struct mm_struct *mm, unsigned long addr, + unsigned long len, struct page ***ppages) +{ + struct vm_area_struct *vma; + struct page *page = NULL; + struct page **pages = NULL; + unsigned long addr_start, addr_end; + unsigned long ret; + int i, page_num = 0; + + pages = kmalloc(sizeof(struct page *) * (len / PAGE_SIZE), GFP_KERNEL); + if (!pages) + return -ENOMEM; + + addr_start = addr; + addr_end = addr + len; + while (addr < addr_end) { + vma = find_vma(mm, addr); + if (!vma || !vma_is_anonymous(vma) || + (vma->vm_flags & VM_LOCKED) || vma->vm_file + || (vma->vm_flags & VM_STACK) || (vma->vm_flags & (VM_IO | VM_PFNMAP))) { + ret = -EINVAL; + goto out; + } + if (!(vma->vm_flags & VM_UFFD_MISSING)) { + ret = -EAGAIN; + goto out; + } +get_again: + /* follow_page will inc page ref, dec the ref after we remap the page */ + page = follow_page(vma, addr, FOLL_GET); + if (IS_ERR_OR_NULL(page)) { + ret = -ENODEV; + goto out; + } + pages[page_num] = page; + page_num++; + if (!PageAnon(page) || !PageSwapBacked(page) || PageHuge(page) || PageSwapCache(page)) { + ret = -EINVAL; + goto out; + } else if (PageTransCompound(page)) { + if (trylock_page(page)) { + if (!split_huge_page(page)) { + put_page(page); + page_num--; + unlock_page(page); + goto get_again; + } else { + unlock_page(page); + ret = -EINVAL; + goto out; + } + } else { + ret = -EINVAL; + goto out; + } + } + if (page_mapcount(page) > 1 || page_mapcount(page) + 1 != page_count(page)) { + ret = -EBUSY; + goto out; + } + addr += PAGE_SIZE; + } + + *ppages = pages; + return 0; + +out: + for (i = 0; i < page_num; i++) + put_page(pages[i]); + if (pages) + kfree(pages); + *ppages = NULL; + return ret; +} + +/* + * In uswap situation, we use the bit 0 of the returned address to indicate + * whether the pages are dirty. + */ +#define USWAP_PAGES_DIRTY 1 + +/* unmap the pages between 'addr ~ addr+len' and remap them to a new address */ +unsigned long do_user_swap(struct mm_struct *mm, unsigned long addr_start, + unsigned long len, struct page **pages, unsigned long new_addr) +{ + struct vm_area_struct *vma; + struct page *page; + pmd_t *pmd; + pte_t *pte, old_pte; + spinlock_t *ptl; + unsigned long addr, addr_end; + bool pages_dirty = false; + int i, err; + + addr_end = addr_start + len; + lru_add_drain(); + mmu_notifier_invalidate_range_start(mm, addr_start, addr_end); + addr = addr_start; + i = 0; + while (addr < addr_end) { + page = pages[i]; + vma = find_vma(mm, addr); + if (!vma) { + mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); + WARN_ON("find_vma failed\n"); + return -EINVAL; + } + pmd = mm_find_pmd(mm, addr); + if (!pmd) { + mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); + WARN_ON("mm_find_pmd failed, addr:%llx\n"); + return -ENXIO; + } + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + flush_cache_page(vma, addr, pte_pfn(*pte)); + old_pte = ptep_clear_flush(vma, addr, pte); + if (pte_dirty(old_pte) || PageDirty(page)) + pages_dirty = true; + set_pte(pte, swp_entry_to_pte(swp_entry(SWP_USERSWAP_ENTRY, page_to_pfn(page)))); + dec_mm_counter(mm, MM_ANONPAGES); + page_remove_rmap(page, false); + put_page(page); + + pte_unmap_unlock(pte, ptl); + vma->vm_flags |= VM_USWAP; + page->mapping = NULL; + addr += PAGE_SIZE; + i++; + } + mmu_notifier_invalidate_range_end(mm, addr_start, addr_end); + + addr_start = new_addr; + addr_end = new_addr + len; + addr = addr_start; + vma = find_vma(mm, addr); + i = 0; + while (addr < addr_end) { + page = pages[i]; + if (addr > vma->vm_end - 1) + vma = find_vma(mm, addr); + err = vm_insert_page(vma, addr, page); + if (err) { + pr_err("vm_insert_page failed:%d\n", err); + } + i++; + addr += PAGE_SIZE; + } + vma->vm_flags |= VM_USWAP; + + if (pages_dirty) + new_addr = new_addr | USWAP_PAGES_DIRTY; + + return new_addr; +} + +static inline +unsigned long do_uswap_mmap(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, + unsigned long flags, vm_flags_t vm_flags, + unsigned long pgoff, unsigned long *populate, + struct list_head *uf) +{ + struct mm_struct *mm = current->mm; + unsigned long addr_start = addr; + struct page **pages = NULL; + unsigned long ret; + int i, page_num = 0; + + if (!len || offset_in_page(addr) || (len % PAGE_SIZE)) + return -EINVAL; + + page_num = len / PAGE_SIZE; + ret = pages_can_be_swapped(mm, addr, len, &pages); + if (ret) + return ret; + + /* mark the vma as special to avoid merging with other vmas */ + vm_flags |= VM_SPECIAL; + + addr = __do_mmap(current->mm, file, addr, len, prot, flags, vm_flags, + pgoff, populate, uf); if (IS_ERR_VALUE(addr)) { - pr_info("mmap_region failed, return addr:%lx\n", addr); ret = addr; goto out; } @@ -1794,23 +1789,32 @@ unsigned long __do_mmap(struct mm_struct *mm, struct file *file, /* follow_page() above increased the reference*/ for (i = 0; i < page_num; i++) put_page(pages[i]); + if (pages) kfree(pages); + return ret; -#endif } +#endif /* * The caller must hold down_write(&current->mm->mmap_sem). */ -unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, vm_flags_t vm_flags, - unsigned long pgoff, unsigned long *populate, struct list_head *uf) +unsigned long do_mmap(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, + unsigned long flags, vm_flags_t vm_flags, + unsigned long pgoff, unsigned long *populate, + struct list_head *uf) { - return __do_mmap(current->mm, file, addr, len, prot, flags, vm_flags, pgoff, populate, uf); +#ifdef CONFIG_USERSWAP + if (enable_userswap && (flags & MAP_REPLACE)) + return do_uswap_mmap(file, addr, len, prot, flags, vm_flags, + pgoff, populate, uf); +#endif + return __do_mmap(current->mm, file, addr, len, prot, flags, vm_flags, + pgoff, populate, uf); } - unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) -- 2.25.1

1 1

[PATCH kernel-4.19] blktrace: Fix uaf in blk_trace access after removing by sysfs
by Yang Yingliang 18 Oct '21

18 Oct '21

From: Zhihao Cheng <chengzhihao1(a)huawei.com> mainline inclusion from mainline-5.15-rc3 commit 5afedf670caf30a2b5a52da96eb7eac7dee6a9c9 category: bugfix bugzilla: 181454 CVE: NA --------------------------- There is an use-after-free problem triggered by following process: P1(sda) P2(sdb) echo 0 > /sys/block/sdb/trace/enable blk_trace_remove_queue synchronize_rcu blk_trace_free relay_close rcu_read_lock __blk_add_trace trace_note_tsk (Iterate running_trace_list) relay_close_buf relay_destroy_buf kfree(buf) trace_note(sdb's bt) relay_reserve buf->offset <- nullptr deference (use-after-free) !!! rcu_read_unlock [ 502.714379] BUG: kernel NULL pointer dereference, address: 0000000000000010 [ 502.715260] #PF: supervisor read access in kernel mode [ 502.715903] #PF: error_code(0x0000) - not-present page [ 502.716546] PGD 103984067 P4D 103984067 PUD 17592b067 PMD 0 [ 502.717252] Oops: 0000 [#1] SMP [ 502.720308] RIP: 0010:trace_note.isra.0+0x86/0x360 [ 502.732872] Call Trace: [ 502.733193] __blk_add_trace.cold+0x137/0x1a3 [ 502.733734] blk_add_trace_rq+0x7b/0xd0 [ 502.734207] blk_add_trace_rq_issue+0x54/0xa0 [ 502.734755] blk_mq_start_request+0xde/0x1b0 [ 502.735287] scsi_queue_rq+0x528/0x1140 ... [ 502.742704] sg_new_write.isra.0+0x16e/0x3e0 [ 502.747501] sg_ioctl+0x466/0x1100 Reproduce method: ioctl(/dev/sda, BLKTRACESETUP, blk_user_trace_setup[buf_size=127]) ioctl(/dev/sda, BLKTRACESTART) ioctl(/dev/sdb, BLKTRACESETUP, blk_user_trace_setup[buf_size=127]) ioctl(/dev/sdb, BLKTRACESTART) echo 0 > /sys/block/sdb/trace/enable & // Add delay(mdelay/msleep) before kernel enters blk_trace_free() ioctl$SG_IO(/dev/sda, SG_IO, ...) // Enters trace_note_tsk() after blk_trace_free() returned // Use mdelay in rcu region rather than msleep(which may schedule out) Remove blk_trace from running_list before calling blk_trace_free() by sysfs if blk_trace is at Blktrace_running state. Fixes: c71a896154119f ("blktrace: add ftrace plugin") Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Link: https://lore.kernel.org/r/20210923134921.109194-1-chengzhihao1@huawei.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/trace/blktrace.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index da0ee8cc15a72..2df442fb46bb2 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1662,6 +1662,14 @@ static int blk_trace_remove_queue(struct request_queue *q) if (bt == NULL) return -EINVAL; + if (bt->trace_state == Blktrace_running) { + bt->trace_state = Blktrace_stopped; + spin_lock_irq(&running_trace_lock); + list_del_init(&bt->running_list); + spin_unlock_irq(&running_trace_lock); + relay_flush(bt->rchan); + } + put_probe_ref(); synchronize_rcu(); blk_trace_free(bt); -- 2.25.1

1 0

[PATCH openEuler-21.03] drm: Lock pointer access in drm_master_release()
by holmes 18 Oct '21

18 Oct '21

From: Desmond Cheong Zhi Xi <desmondcheongzx(a)gmail.com> stable inclusion from stable-v5.10.44 commit aa8591a58cbd2986090709e4202881f18e8ae30e bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=435 CVE: NA ------------------------------------------------- commit c336a5ee984708db4826ef9e47d184e638e29717 upstream. This patch eliminates the following smatch warning: drivers/gpu/drm/drm_auth.c:320 drm_master_release() warn: unlocked access 'master' (line 318) expected lock '&dev->master_mutex' The 'file_priv->master' field should be protected by the mutex lock to '&dev->master_mutex'. This is because other processes can concurrently modify this field and free the current 'file_priv->master' pointer. This could result in a use-after-free error when 'master' is dereferenced in subsequent function calls to 'drm_legacy_lock_master_cleanup()' or to 'drm_lease_revoke()'. An example of a scenario that would produce this error can be seen from a similar bug in 'drm_getunique()' that was reported by Syzbot: https://syzkaller.appspot.com/bug?id=148d2f1dfac64af52ffd27b661981a540724f8… In the Syzbot report, another process concurrently acquired the device's master mutex in 'drm_setmaster_ioctl()', then overwrote 'fpriv->master' in 'drm_new_set_master()'. The old value of 'fpriv->master' was subsequently freed before the mutex was unlocked. Reported-by: Dan Carpenter <dan.carpenter(a)oracle.com> Signed-off-by: Desmond Cheong Zhi Xi <desmondcheongzx(a)gmail.com> Cc: stable(a)vger.kernel.org Signed-off-by: Daniel Vetter <daniel.vetter(a)ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210609092119.173590-1-desmo… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: holmes <holmes(a)my.swjtu.edu.cn> --- drivers/gpu/drm/drm_auth.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c index f2d46b7ac6f9..232abbba3686 100644 --- a/drivers/gpu/drm/drm_auth.c +++ b/drivers/gpu/drm/drm_auth.c @@ -314,9 +314,10 @@ int drm_master_open(struct drm_file *file_priv) void drm_master_release(struct drm_file *file_priv) { struct drm_device *dev = file_priv->minor->dev; - struct drm_master *master = file_priv->master; + struct drm_master *master; mutex_lock(&dev->master_mutex); + master = file_priv->master; if (file_priv->magic) idr_remove(&file_priv->master->magic_map, file_priv->magic); -- 2.23.0

1 1

[PATCH OLK-5.10 v2 0/1] scsi: spfc: initial commit the spfc module
by Yanling Song 18 Oct '21

18 Oct '21

Ramaxel inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4DBD7 CVE: NA Initial commit the spfc module for ramaxel Super FC adapter Changes since v1: - Add UNF_PORT_CFG_SET_PORT_STATE state Yanling Song (1): scsi: spfc: initial commit the spfc module arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + drivers/scsi/Kconfig | 1 + drivers/scsi/Makefile | 1 + drivers/scsi/spfc/Kconfig | 17 + drivers/scsi/spfc/Makefile | 47 + drivers/scsi/spfc/common/unf_common.h | 1755 +++++++ drivers/scsi/spfc/common/unf_disc.c | 1276 +++++ drivers/scsi/spfc/common/unf_disc.h | 51 + drivers/scsi/spfc/common/unf_event.c | 517 ++ drivers/scsi/spfc/common/unf_event.h | 84 + drivers/scsi/spfc/common/unf_exchg.c | 2317 +++++++++ drivers/scsi/spfc/common/unf_exchg.h | 436 ++ drivers/scsi/spfc/common/unf_exchg_abort.c | 825 +++ drivers/scsi/spfc/common/unf_exchg_abort.h | 23 + drivers/scsi/spfc/common/unf_fcstruct.h | 459 ++ drivers/scsi/spfc/common/unf_gs.c | 2521 +++++++++ drivers/scsi/spfc/common/unf_gs.h | 58 + drivers/scsi/spfc/common/unf_init.c | 353 ++ drivers/scsi/spfc/common/unf_io.c | 1220 +++++ drivers/scsi/spfc/common/unf_io.h | 96 + drivers/scsi/spfc/common/unf_io_abnormal.c | 986 ++++ drivers/scsi/spfc/common/unf_io_abnormal.h | 19 + drivers/scsi/spfc/common/unf_log.h | 178 + drivers/scsi/spfc/common/unf_lport.c | 1008 ++++ drivers/scsi/spfc/common/unf_lport.h | 519 ++ drivers/scsi/spfc/common/unf_ls.c | 4884 ++++++++++++++++++ drivers/scsi/spfc/common/unf_ls.h | 61 + drivers/scsi/spfc/common/unf_npiv.c | 1005 ++++ drivers/scsi/spfc/common/unf_npiv.h | 47 + drivers/scsi/spfc/common/unf_npiv_portman.c | 360 ++ drivers/scsi/spfc/common/unf_npiv_portman.h | 17 + drivers/scsi/spfc/common/unf_portman.c | 2431 +++++++++ drivers/scsi/spfc/common/unf_portman.h | 96 + drivers/scsi/spfc/common/unf_rport.c | 2286 ++++++++ drivers/scsi/spfc/common/unf_rport.h | 301 ++ drivers/scsi/spfc/common/unf_scsi.c | 1463 ++++++ drivers/scsi/spfc/common/unf_scsi_common.h | 570 ++ drivers/scsi/spfc/common/unf_service.c | 1439 ++++++ drivers/scsi/spfc/common/unf_service.h | 66 + drivers/scsi/spfc/common/unf_type.h | 216 + drivers/scsi/spfc/hw/spfc_chipitf.c | 1105 ++++ drivers/scsi/spfc/hw/spfc_chipitf.h | 797 +++ drivers/scsi/spfc/hw/spfc_cqm_bat_cla.c | 1646 ++++++ drivers/scsi/spfc/hw/spfc_cqm_bat_cla.h | 215 + drivers/scsi/spfc/hw/spfc_cqm_bitmap_table.c | 891 ++++ drivers/scsi/spfc/hw/spfc_cqm_bitmap_table.h | 65 + drivers/scsi/spfc/hw/spfc_cqm_main.c | 1257 +++++ drivers/scsi/spfc/hw/spfc_cqm_main.h | 414 ++ drivers/scsi/spfc/hw/spfc_cqm_object.c | 959 ++++ drivers/scsi/spfc/hw/spfc_cqm_object.h | 279 + drivers/scsi/spfc/hw/spfc_hba.c | 1751 +++++++ drivers/scsi/spfc/hw/spfc_hba.h | 341 ++ drivers/scsi/spfc/hw/spfc_hw_wqe.h | 1645 ++++++ drivers/scsi/spfc/hw/spfc_io.c | 1193 +++++ drivers/scsi/spfc/hw/spfc_io.h | 138 + drivers/scsi/spfc/hw/spfc_lld.c | 998 ++++ drivers/scsi/spfc/hw/spfc_lld.h | 76 + drivers/scsi/spfc/hw/spfc_module.h | 297 ++ drivers/scsi/spfc/hw/spfc_parent_context.h | 269 + drivers/scsi/spfc/hw/spfc_queue.c | 4857 +++++++++++++++++ drivers/scsi/spfc/hw/spfc_queue.h | 711 +++ drivers/scsi/spfc/hw/spfc_service.c | 2169 ++++++++ drivers/scsi/spfc/hw/spfc_service.h | 282 + drivers/scsi/spfc/hw/spfc_utils.c | 102 + drivers/scsi/spfc/hw/spfc_utils.h | 202 + drivers/scsi/spfc/hw/spfc_wqe.c | 646 +++ drivers/scsi/spfc/hw/spfc_wqe.h | 239 + 68 files changed, 53555 insertions(+) create mode 100644 drivers/scsi/spfc/Kconfig create mode 100644 drivers/scsi/spfc/Makefile create mode 100644 drivers/scsi/spfc/common/unf_common.h create mode 100644 drivers/scsi/spfc/common/unf_disc.c create mode 100644 drivers/scsi/spfc/common/unf_disc.h create mode 100644 drivers/scsi/spfc/common/unf_event.c create mode 100644 drivers/scsi/spfc/common/unf_event.h create mode 100644 drivers/scsi/spfc/common/unf_exchg.c create mode 100644 drivers/scsi/spfc/common/unf_exchg.h create mode 100644 drivers/scsi/spfc/common/unf_exchg_abort.c create mode 100644 drivers/scsi/spfc/common/unf_exchg_abort.h create mode 100644 drivers/scsi/spfc/common/unf_fcstruct.h create mode 100644 drivers/scsi/spfc/common/unf_gs.c create mode 100644 drivers/scsi/spfc/common/unf_gs.h create mode 100644 drivers/scsi/spfc/common/unf_init.c create mode 100644 drivers/scsi/spfc/common/unf_io.c create mode 100644 drivers/scsi/spfc/common/unf_io.h create mode 100644 drivers/scsi/spfc/common/unf_io_abnormal.c create mode 100644 drivers/scsi/spfc/common/unf_io_abnormal.h create mode 100644 drivers/scsi/spfc/common/unf_log.h create mode 100644 drivers/scsi/spfc/common/unf_lport.c create mode 100644 drivers/scsi/spfc/common/unf_lport.h create mode 100644 drivers/scsi/spfc/common/unf_ls.c create mode 100644 drivers/scsi/spfc/common/unf_ls.h create mode 100644 drivers/scsi/spfc/common/unf_npiv.c create mode 100644 drivers/scsi/spfc/common/unf_npiv.h create mode 100644 drivers/scsi/spfc/common/unf_npiv_portman.c create mode 100644 drivers/scsi/spfc/common/unf_npiv_portman.h create mode 100644 drivers/scsi/spfc/common/unf_portman.c create mode 100644 drivers/scsi/spfc/common/unf_portman.h create mode 100644 drivers/scsi/spfc/common/unf_rport.c create mode 100644 drivers/scsi/spfc/common/unf_rport.h create mode 100644 drivers/scsi/spfc/common/unf_scsi.c create mode 100644 drivers/scsi/spfc/common/unf_scsi_common.h create mode 100644 drivers/scsi/spfc/common/unf_service.c create mode 100644 drivers/scsi/spfc/common/unf_service.h create mode 100644 drivers/scsi/spfc/common/unf_type.h create mode 100644 drivers/scsi/spfc/hw/spfc_chipitf.c create mode 100644 drivers/scsi/spfc/hw/spfc_chipitf.h create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_bat_cla.c create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_bat_cla.h create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_bitmap_table.c create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_bitmap_table.h create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_main.c create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_main.h create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_object.c create mode 100644 drivers/scsi/spfc/hw/spfc_cqm_object.h create mode 100644 drivers/scsi/spfc/hw/spfc_hba.c create mode 100644 drivers/scsi/spfc/hw/spfc_hba.h create mode 100644 drivers/scsi/spfc/hw/spfc_hw_wqe.h create mode 100644 drivers/scsi/spfc/hw/spfc_io.c create mode 100644 drivers/scsi/spfc/hw/spfc_io.h create mode 100644 drivers/scsi/spfc/hw/spfc_lld.c create mode 100644 drivers/scsi/spfc/hw/spfc_lld.h create mode 100644 drivers/scsi/spfc/hw/spfc_module.h create mode 100644 drivers/scsi/spfc/hw/spfc_parent_context.h create mode 100644 drivers/scsi/spfc/hw/spfc_queue.c create mode 100644 drivers/scsi/spfc/hw/spfc_queue.h create mode 100644 drivers/scsi/spfc/hw/spfc_service.c create mode 100644 drivers/scsi/spfc/hw/spfc_service.h create mode 100644 drivers/scsi/spfc/hw/spfc_utils.c create mode 100644 drivers/scsi/spfc/hw/spfc_utils.h create mode 100644 drivers/scsi/spfc/hw/spfc_wqe.c create mode 100644 drivers/scsi/spfc/hw/spfc_wqe.h -- 2.30.0

2 2

[PATCH kernel-4.19 v5 00/23] support psi feature
by Liu Xinpeng 17 Oct '21

17 Oct '21

backport psi feature from upstream 5.4 bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 Baruch Siach (1): psi: fix reference to kernel commandline enable Dan Schatzberg (1): kernel/sched/psi.c: expose pressure metrics on root cgroup Johannes Weiner (11): sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD sched: loadavg: make calc_load_n() public sched: sched.h: make rq locking and clock functions available in stats.h sched: introduce this_rq_lock_irq() psi: pressure stall information for CPU, memory, and IO psi: cgroup support psi: make disabling/enabling easier for vendor kernels psi: fix aggregation idle shut-off psi: avoid divide-by-zero crash inside virtual machines fs: kernfs: add poll file operation sched/psi: Fix sampling error and rare div0 crashes with cgroups and high uptime Josef Bacik (1): blk-iolatency: use a percentile approache for ssd's Liu Xinpeng (2): psi:enable psi in config psi:avoid kabi change Olof Johansson (1): kernel/sched/psi.c: simplify cgroup_move_task() Suren Baghdasaryan (6): psi: introduce state_mask to represent stalled psi states psi: make psi_enable static psi: rename psi fields in preparation for psi trigger addition psi: split update_stats into parts psi: track changed states include/: refactor headers to allow kthread.h inclusion in psi_types.h Documentation/accounting/psi.txt | 73 +++ Documentation/admin-guide/cgroup-v2.rst | 18 + Documentation/admin-guide/kernel-parameters.txt | 4 + arch/arm64/configs/openeuler_defconfig | 2 + arch/powerpc/platforms/cell/cpufreq_spudemand.c | 2 +- arch/powerpc/platforms/cell/spufs/sched.c | 9 +- arch/s390/appldata/appldata_os.c | 4 - arch/x86/configs/openeuler_defconfig | 2 + block/blk-iolatency.c | 183 +++++- drivers/cpuidle/governors/menu.c | 4 - drivers/spi/spi-rockchip.c | 1 + fs/kernfs/file.c | 31 +- fs/proc/loadavg.c | 3 - include/linux/cgroup-defs.h | 12 + include/linux/cgroup.h | 17 + include/linux/kernfs.h | 8 + include/linux/kthread.h | 4 + include/linux/psi.h | 55 ++ include/linux/psi_types.h | 95 +++ include/linux/sched.h | 13 + include/linux/sched/loadavg.h | 24 +- init/Kconfig | 28 + kernel/cgroup/cgroup.c | 55 +- kernel/debug/kdb/kdb_main.c | 7 +- kernel/fork.c | 4 + kernel/kthread.c | 3 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 16 +- kernel/sched/loadavg.c | 139 ++-- kernel/sched/psi.c | 823 ++++++++++++++++++++++++ kernel/sched/sched.h | 178 ++--- kernel/sched/stats.h | 86 +++ kernel/workqueue.c | 23 + kernel/workqueue_internal.h | 6 +- mm/compaction.c | 5 + mm/filemap.c | 11 + mm/page_alloc.c | 9 + mm/vmscan.c | 9 + 38 files changed, 1726 insertions(+), 241 deletions(-) create mode 100644 Documentation/accounting/psi.txt create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h create mode 100644 kernel/sched/psi.c -- 1.8.3.1

1 22

Re: Re: [PATCH kernel-4.19 v4 19/22] kernel/sched/psi.c: expose pressure metrics on root cgroup
by 刘新朋 17 Oct '21

17 Oct '21

1 0

[PATCH kernel-4.19 v4 00/22] support PSI feature
by Liu Xinpeng 16 Oct '21

16 Oct '21

backport psi feature from upstream 5.4 bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 Dan Schatzberg (1): kernel/sched/psi.c: expose pressure metrics on root cgroup Johannes Weiner (11): sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD sched: loadavg: make calc_load_n() public sched: sched.h: make rq locking and clock functions available in stats.h sched: introduce this_rq_lock_irq() psi: pressure stall information for CPU, memory, and IO psi: cgroup support psi: make disabling/enabling easier for vendor kernels psi: fix aggregation idle shut-off psi: avoid divide-by-zero crash inside virtual machines fs: kernfs: add poll file operation sched/psi: Fix sampling error and rare div0 crashes with cgroups and high uptime Josef Bacik (1): blk-iolatency: use a percentile approache for ssd's Liu Xinpeng (2): psi:enable psi in config psi:avoid kabi change Olof Johansson (1): kernel/sched/psi.c: simplify cgroup_move_task() Suren Baghdasaryan (6): psi: introduce state_mask to represent stalled psi states psi: make psi_enable static psi: rename psi fields in preparation for psi trigger addition psi: split update_stats into parts psi: track changed states include/: refactor headers to allow kthread.h inclusion in psi_types.h Documentation/accounting/psi.txt | 73 +++ Documentation/admin-guide/cgroup-v2.rst | 18 + Documentation/admin-guide/kernel-parameters.txt | 4 + arch/arm64/configs/openeuler_defconfig | 2 + arch/powerpc/platforms/cell/cpufreq_spudemand.c | 2 +- arch/powerpc/platforms/cell/spufs/sched.c | 9 +- arch/s390/appldata/appldata_os.c | 4 - arch/x86/configs/openeuler_defconfig | 2 + block/blk-iolatency.c | 183 +++++- drivers/cpuidle/governors/menu.c | 4 - drivers/spi/spi-rockchip.c | 1 + fs/kernfs/file.c | 31 +- fs/proc/loadavg.c | 3 - include/linux/cgroup-defs.h | 12 + include/linux/cgroup.h | 16 + include/linux/kernfs.h | 8 + include/linux/kthread.h | 4 + include/linux/psi.h | 55 ++ include/linux/psi_types.h | 95 +++ include/linux/sched.h | 13 + include/linux/sched/loadavg.h | 24 +- init/Kconfig | 28 + kernel/cgroup/cgroup.c | 55 +- kernel/debug/kdb/kdb_main.c | 7 +- kernel/fork.c | 4 + kernel/kthread.c | 3 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 16 +- kernel/sched/loadavg.c | 139 ++-- kernel/sched/psi.c | 823 ++++++++++++++++++++++++ kernel/sched/sched.h | 178 ++--- kernel/sched/stats.h | 86 +++ kernel/workqueue.c | 23 + kernel/workqueue_internal.h | 6 +- mm/compaction.c | 5 + mm/filemap.c | 11 + mm/page_alloc.c | 9 + mm/vmscan.c | 9 + 38 files changed, 1725 insertions(+), 241 deletions(-) create mode 100644 Documentation/accounting/psi.txt create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h create mode 100644 kernel/sched/psi.c -- 1.8.3.1

2 27

[PATCH openEuler-5.10 000/133] Backport LTS 5.10.58
by Zheng Zengkai 15 Oct '21

15 Oct '21

Backport LTS 5.10.58 patches from upstream. Aharon Landau (1): RDMA/mlx5: Delay emptying a cache entry when a new MR is added to it recently Alex Deucher (1): drm/amdgpu/display: only enable aux backlight control for OLED panels Alex Xu (Hello71) (1): pipe: increase minimum default pipe size to 2 pages Alexander Monakov (1): ALSA: hda/realtek: add mic quirk for Acer SF314-42 Alexander Tsoy (1): ALSA: usb-audio: Add registration quirk for JBL Quantum 600 Allen Pais (1): optee: fix tee out of memory failure seen during kexec reboot Andy Shevchenko (1): serial: 8250_pci: Enumerate Elkhart Lake UARTs via dedicated driver Anirudh Rayabharam (2): firmware_loader: use -ETIMEDOUT instead of -EAGAIN in fw_load_sysfs_fallback firmware_loader: fix use-after-free in firmware_fallback_sysfs Antoine Tenart (1): net: ipv6: fix returned variable type in ip6_skb_dst_mtu Arnd Bergmann (2): soc: ixp4xx: fix printing resources soc: ixp4xx/qmgr: fix invalid __iomem access Brian Norris (1): clk: fix leak on devm_clk_bulk_get_all() unwind Christoph Hellwig (1): libata: fix ata_pio_sector for CONFIG_HIGHMEM Claudiu Beznea (1): usb: host: ohci-at91: suspend/resume ports after/before OHCI accesses Colin Ian King (2): ARM: imx: fix missing 3rd argument in macro imx_mmdc_perf_init interconnect: Fix undersized devress_alloc allocation Dan Carpenter (1): bnx2x: fix an error code in bnx2x_nic_load() Daniele Palmas (1): USB: serial: option: add Telit FD980 composition 0x1056 Dario Binacchi (2): clk: stm32f4: fix post divisor setup for I2S/SAI PLLs ARM: dts: am437x-l4: fix typo in can@0 node David Bauer (1): USB: serial: ftdi_sio: add device ID for Auto-M3 OP-COM v2 Dmitry Osipenko (2): clk: tegra: Implement disable_unused() of tegra_clk_sdmmc_mux_ops usb: otg-fsm: Fix hrtimer list corruption Dmitry Safonov (1): net/xfrm/compat: Copy xfrm_spdattr_type_t atributes Dongliang Mu (1): spi: meson-spicc: fix memory leak in meson_spicc_remove Fei Qin (1): nfp: update ethtool reporting of pauseframe control Filip Schauer (1): drivers core: Fix oops when driver probe fails Frederic Weisbecker (1): xfrm: Fix RCU vs hash_resize_mutex lock inversion H. Nikolaus Schaller (2): omap5-board-common: remove not physically existing vdds_1v8_main fixed-regulator mips: Fix non-POSIX regexp Hans Verkuil (1): media: videobuf2-core: dequeue if start_streaming fails Harshvardhan Jha (1): net: qede: Fix end of loop tests for list_for_each_entry Huang Pei (1): MIPS: check return value of pgtable_pmd_page_ctor Hui Su (1): scripts/tracing: fix the bug that can't parse raw_trace_func Jakub Sitnicki (1): net, gro: Set inner transport header offset in tcp/udp GRO hook Jaroslav Kysela (1): ALSA: pcm - fix mmap capability check for the snd-dummy driver Jens Wiklander (1): tee: add tee_shm_alloc_kernel_buf() Johan Hovold (1): media: rtl28xxu: fix zero-length control request Jon Hunter (1): serial: tegra: Only print FIFO error message when an error occurs Jonathan Gray (1): drm/i915: avoid uninitialised var in eb_parse() Juergen Borleis (1): dmaengine: imx-dma: configure the generic DMA type to make it work Kajol Jain (1): fpga: dfl: fme: Fix cpu hotplug issue in performance reporting Kamal Agrawal (1): tracing: Fix NULL pointer dereference in start_creating Kevin Hilman (1): bus: ti-sysc: AM3: RNG is GP only Kunihiko Hayashi (1): dmaengine: uniphier-xdmac: Use readl_poll_timeout_atomic() in atomic state Kyle Tso (1): usb: typec: tcpm: Keep other events when receiving FRS and Sourcing_vbus events Letu Ren (1): net/qla3xxx: fix schedule while atomic in ql_wait_for_drvr_lock and ql_adapter_reset Li Manyi (1): scsi: sr: Return correct event when media event code is 3 Like Xu (1): perf/x86/amd: Don't touch the AMD64_EVENTSEL_HOSTONLY bit inside the guest Maciej W. Rozycki (2): serial: 8250: Mask out floating 16/32-bit bus bits MIPS: Malta: Do not byte-swap accesses to the CBUS UART Marek Vasut (5): ARM: dts: imx: Swap M53Menlo pinctrl_power_button/pinctrl_power_out pins spi: imx: mx51-ecspi: Reinstate low-speed CONFIGREG delay spi: imx: mx51-ecspi: Fix low-speed CONFIGREG delay calculation ARM: dts: stm32: Disable LAN8710 EDPD on DHCOM ARM: dts: stm32: Fix touchscreen IRQ line assignment on DHCOM Mario Kleiner (1): serial: 8250_pci: Avoid irq sharing for MSI(-X) interrupts. Mark Rutland (1): arm64: stacktrace: avoid tracing arch_stack_walk() Masami Hiramatsu (1): tracing: Reject string operand in the histogram expression Mathieu Desnoyers (2): tracepoint: static call: Compare data on transition from 2->1 callees tracepoint: Fix static call function vs data state mismatch Matt Roper (1): drm/i915: Correct SFC_DONE register offset Matteo Croce (1): virt_wifi: fix error on connect Matthias Schiffer (1): gpio: tqmx86: really make IRQ optional Maxim Devaev (2): usb: gadget: f_hid: added GET_IDLE and SET_IDLE handlers usb: gadget: f_hid: idle uses the highest byte for duration Maxime Chevallier (1): ARM: dts: imx6qdl-sr-som: Increase the PHY reset duration to 10ms Michael Walle (1): arm64: dts: ls1028: sl28: fix networking for variant 2 Mike Tipton (3): interconnect: Zero initial BW after sync-state interconnect: Always call pre_aggregate before aggregate interconnect: qcom: icc-rpmh: Ensure floor BW is enforced for all nodes Nikos Liolios (1): ALSA: hda/realtek: Fix headset mic for Acer SWIFT SF314-56 (ALC256) Oleksandr Suvorov (1): ARM: dts: colibri-imx6ull: limit SDIO clock to 25MHz Oleksij Rempel (1): net: dsa: qca: ar9331: reorder MDIO write sequence Pali Rohár (1): arm64: dts: armada-3720-turris-mox: remove mrvl,i2c-fast-mode Paolo Bonzini (2): KVM: x86: accept userspace interrupt only if no event is injected KVM: Do not leak memory for duplicate debugfs directories Pavel Skripkin (6): net: xfrm: fix memory leak in xfrm_user_rcv_msg net: pegasus: fix uninit-value in get_interrupt_interval net: fec: fix use-after-free in fec_drv_remove net: vxge: fix use-after-free in vxge_device_unregister staging: rtl8712: get rid of flush_scheduled_work staging: rtl8712: error handling refactoring Pawel Laszczak (1): usb: cdns3: Fixed incorrect gadget state Peter Zijlstra (1): sched/rt: Fix double enqueue caused by rt_effective_prio Phil Elwell (1): usb: gadget: f_hid: fixed NULL pointer dereference Prarit Bhargava (1): alpha: Send stop IPI to send to online CPUs Qiang.zhang (1): USB: usbtmc: Fix RCU stall warning Rafael J. Wysocki (1): Revert "ACPICA: Fix memory leak caused by _CID repair function" Rasmus Villemoes (1): Revert "gpio: mpc8xxx: change the gpio interrupt flags." Sean Christopherson (1): KVM: x86/mmu: Fix per-cpu counter corruption on 32-bit builds Shirish S (1): drm/amdgpu/display: fix DMUB firmware version info Shreyansh Chouhan (1): reiserfs: check directory items on read from disk Steve Bennett (1): net: phy: micrel: Fix detection of ksz87xx switch Steve French (1): smb3: rc uninitialized in one fallocate path Steven Rostedt (VMware) (1): tracing / histogram: Give calculation hist_fields a size Takashi Iwai (2): ALSA: seq: Fix racy deletion of subscriber ALSA: usb-audio: Fix superfluous autosuspend recovery Tero Kristo (1): ARM: omap2+: hwmod: fix potential NULL pointer access Tetsuo Handa (1): Bluetooth: defer cleanup of resources in hci_unregister_dev() Theodore Ts'o (1): ext4: fix potential htree corruption when growing large_dir directories Thomas Gleixner (1): timers: Move clearing of base::timer_running under base:: Lock Tony Lindgren (1): bus: ti-sysc: Fix gpt12 system timer issue with reserved status Tyler Hicks (4): optee: Clear stale cache entries during initialization optee: Fix memory leak when failing to register shm pages optee: Refuse to load the driver under the kdump kernel tpm_ftpm_tee: Free and unregister TEE shared memory during kexec Vladimir Oltean (6): arm64: dts: ls1028a: fix node name for the sysclk arm64: dts: armada-3720-turris-mox: fixed indices for the SDHC controllers net: dsa: sja1105: overwrite dynamic FDB entries with static ones in .port_fdb_add net: dsa: sja1105: invalidate dynamic FDB entries learned concurrently with statically added ones net: dsa: sja1105: be stateless with FDB entries on SJA1105P/Q/R/S/SJA1110 too net: dsa: sja1105: match FDB entries regardless of inner/outer VLAN tag Wang Hai (1): net: natsemi: Fix missing pci_disable_device() in probe and remove Wei Shuyu (1): md/raid10: properly indicate failure when ending a failed write request Wesley Cheng (1): usb: dwc3: gadget: Avoid runtime resume if disabling pullup Will Deacon (1): arm64: vdso: Avoid ISB after reading from cntvct_el0 Willy Tarreau (1): USB: serial: ch341: fix character loss at high transfer rates Xiangyang Zhang (1): staging: rtl8723bs: Fix a resource leak in sd_int_dpc Xin Long (1): sctp: move the active_key update after sh_keys is added Xiu Jianfeng (1): selinux: correct the return value when loads initial sids Yang Yingliang (2): ARM: imx: add missing iounmap() ARM: imx: add missing clk_disable_unprepare() Yu Kuai (2): blk-iolatency: error out if blk_get_queue() failed in iolatency_set_limit() reiserfs: add check for root_inode in reiserfs_fill_super Yunsheng Lin (1): net: sched: fix lockdep_set_class() typo error for sch->seqlock Zhang Qilong (3): dmaengine: stm32-dma: Fix PM usage counter imbalance in stm32 dma ops dmaengine: stm32-dmamux: Fix PM usage counter unbalance in stm32 dmamux ops usb: gadget: remove leaked entry from udc driver list Zheyu Ma (1): pcmcia: i82092: fix a null pointer dereference bug Zhiyong Tao (1): serial: 8250_mtk: fix uart corruption issue when rx power off chihhao.chen (1): ALSA: usb-audio: fix incorrect clock source setting arch/alpha/kernel/smp.c | 2 +- arch/arm/boot/dts/am437x-l4.dtsi | 2 +- arch/arm/boot/dts/imx53-m53menlo.dts | 4 +- arch/arm/boot/dts/imx6qdl-sr-som.dtsi | 8 +- arch/arm/boot/dts/imx6ull-colibri-wifi.dtsi | 1 + arch/arm/boot/dts/omap5-board-common.dtsi | 9 +- arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi | 24 +++-- arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi | 1 + arch/arm/mach-imx/mmdc.c | 17 ++- arch/arm/mach-omap2/omap_hwmod.c | 10 +- .../fsl-ls1028a-kontron-sl28-var2.dts | 2 + .../arm64/boot/dts/freescale/fsl-ls1028a.dtsi | 2 +- .../dts/marvell/armada-3720-turris-mox.dts | 3 + arch/arm64/include/asm/arch_timer.h | 21 ---- arch/arm64/include/asm/barrier.h | 19 ++++ arch/arm64/include/asm/vdso/gettimeofday.h | 6 +- arch/arm64/kernel/stacktrace.c | 2 +- arch/mips/Makefile | 2 +- arch/mips/include/asm/pgalloc.h | 17 +-- arch/mips/mti-malta/malta-platform.c | 3 +- arch/x86/events/perf_event.h | 3 +- arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/x86.c | 13 ++- block/blk-iolatency.c | 6 +- drivers/acpi/acpica/nsrepair2.c | 7 -- drivers/ata/libata-sff.c | 35 ++++-- drivers/base/dd.c | 4 +- drivers/base/firmware_loader/fallback.c | 14 +-- drivers/base/firmware_loader/firmware.h | 10 +- drivers/base/firmware_loader/main.c | 2 + drivers/bus/ti-sysc.c | 22 ++-- drivers/char/tpm/tpm_ftpm_tee.c | 8 +- drivers/clk/clk-devres.c | 9 +- drivers/clk/clk-stm32f4.c | 10 +- drivers/clk/tegra/clk-sdmmc-mux.c | 10 ++ drivers/dma/imx-dma.c | 2 + drivers/dma/stm32-dma.c | 4 +- drivers/dma/stm32-dmamux.c | 6 +- drivers/dma/uniphier-xdmac.c | 4 +- drivers/fpga/dfl-fme-perf.c | 2 + drivers/gpio/gpio-mpc8xxx.c | 2 +- drivers/gpio/gpio-tqmx86.c | 6 +- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 6 +- .../gpu/drm/i915/gem/i915_gem_execbuffer.c | 7 ++ drivers/gpu/drm/i915/i915_reg.h | 2 +- drivers/infiniband/hw/mlx5/mr.c | 4 +- drivers/interconnect/core.c | 9 +- drivers/interconnect/qcom/icc-rpmh.c | 12 +-- drivers/md/raid1.c | 2 - drivers/md/raid10.c | 4 +- .../media/common/videobuf2/videobuf2-core.c | 13 ++- drivers/media/usb/dvb-usb-v2/rtl28xxu.c | 11 +- drivers/net/dsa/qca/ar9331.c | 14 ++- drivers/net/dsa/sja1105/sja1105_main.c | 85 +++++++++++---- .../net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 +- drivers/net/ethernet/freescale/fec_main.c | 2 +- drivers/net/ethernet/natsemi/natsemi.c | 8 +- .../net/ethernet/neterion/vxge/vxge-main.c | 6 +- .../ethernet/netronome/nfp/nfp_net_ethtool.c | 2 + .../net/ethernet/qlogic/qede/qede_filter.c | 4 +- drivers/net/ethernet/qlogic/qla3xxx.c | 6 +- drivers/net/phy/micrel.c | 10 +- drivers/net/usb/pegasus.c | 14 ++- drivers/net/wireless/virt_wifi.c | 52 +++++---- drivers/pcmcia/i82092.c | 1 + drivers/scsi/sr.c | 2 +- drivers/soc/ixp4xx/ixp4xx-npe.c | 11 +- drivers/soc/ixp4xx/ixp4xx-qmgr.c | 9 +- drivers/spi/spi-imx.c | 52 +++++---- drivers/spi/spi-meson-spicc.c | 2 + drivers/staging/rtl8712/hal_init.c | 30 ++++-- drivers/staging/rtl8712/rtl8712_led.c | 8 ++ drivers/staging/rtl8712/rtl871x_led.h | 1 + drivers/staging/rtl8712/rtl871x_pwrctrl.c | 8 ++ drivers/staging/rtl8712/rtl871x_pwrctrl.h | 1 + drivers/staging/rtl8712/usb_intf.c | 51 ++++----- drivers/staging/rtl8723bs/hal/sdio_ops.c | 2 + drivers/tee/optee/call.c | 36 ++++++- drivers/tee/optee/core.c | 40 +++++++ drivers/tee/optee/optee_private.h | 1 + drivers/tee/optee/shm_pool.c | 12 ++- drivers/tee/tee_shm.c | 18 ++++ drivers/tty/serial/8250/8250_mtk.c | 5 + drivers/tty/serial/8250/8250_pci.c | 7 ++ drivers/tty/serial/8250/8250_port.c | 12 ++- drivers/tty/serial/serial-tegra.c | 6 +- drivers/usb/cdns3/ep0.c | 1 + drivers/usb/class/usbtmc.c | 9 +- drivers/usb/common/usb-otg-fsm.c | 6 +- drivers/usb/dwc3/gadget.c | 11 ++ drivers/usb/gadget/function/f_hid.c | 44 ++++++-- drivers/usb/gadget/udc/max3420_udc.c | 14 ++- drivers/usb/host/ohci-at91.c | 9 +- drivers/usb/serial/ch341.c | 1 + drivers/usb/serial/ftdi_sio.c | 1 + drivers/usb/serial/ftdi_sio_ids.h | 3 + drivers/usb/serial/option.c | 2 + drivers/usb/typec/tcpm/tcpm.c | 4 +- fs/cifs/smb2ops.c | 3 +- fs/ext4/namei.c | 2 +- fs/pipe.c | 19 +++- fs/reiserfs/stree.c | 31 +++++- fs/reiserfs/super.c | 8 ++ include/linux/tee_drv.h | 1 + include/linux/usb/otg-fsm.h | 1 + include/net/bluetooth/hci_core.h | 1 + include/net/ip6_route.h | 2 +- include/net/netns/xfrm.h | 1 + kernel/sched/core.c | 90 ++++++---------- kernel/time/timer.c | 6 +- kernel/trace/trace.c | 4 +- kernel/trace/trace_events_hist.c | 24 ++++- kernel/tracepoint.c | 102 ++++++++++++++---- net/bluetooth/hci_core.c | 16 +-- net/bluetooth/hci_sock.c | 49 ++++++--- net/bluetooth/hci_sysfs.c | 3 + net/ipv4/tcp_offload.c | 3 + net/ipv4/udp_offload.c | 4 + net/sched/sch_generic.c | 2 +- net/sctp/auth.c | 14 ++- net/xfrm/xfrm_compat.c | 49 ++++++++- net/xfrm/xfrm_policy.c | 17 ++- net/xfrm/xfrm_user.c | 10 ++ scripts/tracing/draw_functrace.py | 6 +- security/selinux/ss/policydb.c | 10 +- sound/core/pcm_native.c | 2 +- sound/core/seq/seq_ports.c | 39 ++++--- sound/pci/hda/patch_realtek.c | 2 + sound/usb/card.c | 2 +- sound/usb/clock.c | 6 ++ sound/usb/quirks.c | 1 + virt/kvm/kvm_main.c | 18 +++- 132 files changed, 1110 insertions(+), 470 deletions(-) -- 2.20.1

2 132