November 2021 - Kernel - mailweb.openeuler.org

[PATCH OLK-5.10] mm: introduce process_mrelease system call
by Wen Zhiwei 18 Jan '22

18 Jan '22

mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4FHN2?from=project-issue CVE: NA --------------------------- In modern systems it's not unusual to have a system component monitoring memory conditions of the system and tasked with keeping system memory pressure under control. One way to accomplish that is to kill non-essential processes to free up memory for more important ones. Examples of this are Facebook's OOM killer daemon called oomd and Android's low memory killer daemon called lmkd. For such system component it's important to be able to free memory quickly and efficiently. Unfortunately the time process takes to free up its memory after receiving a SIGKILL might vary based on the state of the process (uninterruptible sleep), size and OPP level of the core the process is running. A mechanism to free resources of the target process in a more predictable way would improve system's ability to control its memory pressure. Introduce process_mrelease system call that releases memory of a dying process from the context of the caller. This way the memory is freed in a more controllable way with CPU affinity and priority of the caller. The workload of freeing the memory will also be charged to the caller. The operation is allowed only on a dying process. Signed-off-by: Suren Baghdasaryan <surenb(a)google.com> Reviewed-by: Shakeel Butt <shakeelb(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Acked-by: Christian Brauner <christian.brauner(a)ubuntu.com> Cc: David Rientjes <rientjes(a)google.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Roman Gushchin <guro(a)fb.com> Cc: Rik van Riel <riel(a)surriel.com> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Oleg Nesterov <oleg(a)redhat.com> Cc: Jann Horn <jannh(a)google.com> Cc: Geert Uytterhoeven <geert(a)linux-m68k.org> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Christian Brauner <christian.brauner(a)ubuntu.com> Cc: Florian Weimer <fweimer(a)redhat.com> Cc: Jan Engelhardt <jengelh(a)inai.de> Cc: Tim Murray <timmurray(a)google.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Wen Zhiwei <wenzhiwei(a)kylinos.cn> --- arch/arm64/include/asm/unistd32.h | 3 +- arch/x86/entry/syscalls/syscall_64.tbl | 2 +- include/linux/syscalls.h | 3 ++ include/uapi/asm-generic/unistd.h | 5 +- kernel/sys_ni.c | 1 + mm/oom_kill.c | 72 +++++++++++++++++++++++++ tools/include/uapi/asm-generic/unistd.h | 4 +- 7 files changed, 86 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 107f08e03b9f..e1786b2e8551 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -889,7 +889,8 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_process_madvise 440 __SYSCALL(__NR_process_madvise, sys_process_madvise) - +#define __NR_process_mrelease 441 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) /* * Please add new compat syscalls above this comment and update * __NR_compat_syscalls in asm/unistd.h. diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 379819244b91..6eec6496d72c 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -362,7 +362,7 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise - +441 common process_mrelease sys_process_mrelease # # Due to a historical design error, certain syscalls are numbered differently # in x32 as compared to native x86_64. These syscalls have numbers 512-547. diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index aea0ce9f3b74..764bfcdbbcb0 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -905,6 +905,9 @@ asmlinkage long sys_mincore(unsigned long start, size_t len, asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior); asmlinkage long sys_process_madvise(int pidfd, const struct iovec __user *vec, size_t vlen, int behavior, unsigned int flags); + +asmlinkage long sys_process_mrelease(int pidfd, unsigned int flags); + asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long prot, unsigned long pgoff, unsigned long flags); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 2056318988f7..e5f38ea960c4 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -859,9 +859,12 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_process_madvise 440 __SYSCALL(__NR_process_madvise, sys_process_madvise) +#define __NR_process_mrelease 441 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) #undef __NR_syscalls -#define __NR_syscalls 441 +#define __NR_syscalls 442 + /* * 32 bit systems traditionally used different diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index f27ac94d5fa7..6b8203edf531 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -281,6 +281,7 @@ COND_SYSCALL(munlockall); COND_SYSCALL(mincore); COND_SYSCALL(madvise); COND_SYSCALL(process_madvise); +COND_SYSCALL(process_mrelease); COND_SYSCALL(remap_file_pages); COND_SYSCALL(mbind); COND_SYSCALL_COMPAT(mbind); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index fb39b0902476..d169eb511518 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -43,6 +43,7 @@ #include <linux/kthread.h> #include <linux/init.h> #include <linux/mmu_notifier.h> +#include <linux/syscalls.h> #include <asm/tlb.h> #include "internal.h" @@ -1186,3 +1187,74 @@ void pagefault_out_of_memory(void) out_of_memory(&oc); mutex_unlock(&oom_lock); } + +SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags) +{ +#ifdef CONFIG_MMU + struct mm_struct *mm = NULL; + struct task_struct *task; + struct task_struct *p; + unsigned int f_flags; + bool reap = false; + struct pid *pid; + long ret = 0; + + if (flags) + return -EINVAL; + + pid = pidfd_get_pid(pidfd, &f_flags); + if (IS_ERR(pid)) + return PTR_ERR(pid); + + task = get_pid_task(pid, PIDTYPE_TGID); + if (!task) { + ret = -ESRCH; + goto put_pid; + } + + /* + * Make sure to choose a thread which still has a reference to mm + * during the group exit + */ + p = find_lock_task_mm(task); + if (!p) { + ret = -ESRCH; + goto put_task; + } + + if (mmget_not_zero(p->mm)) { + mm = p->mm; + if (task_will_free_mem(p)) + reap = true; + else { + /* Error only if the work has not been done already */ + if (!test_bit(MMF_OOM_SKIP, &mm->flags)) + ret = -EINVAL; + } + } + task_unlock(p); + + if (!reap) + goto drop_mm; + + if (mmap_read_lock_killable(mm)) { + ret = -EINTR; + goto drop_mm; + } + if (!__oom_reap_task_mm(mm)) + ret = -EAGAIN; + mmap_read_unlock(mm); + +drop_mm: + if (mm) + mmput(mm); +put_task: + put_task_struct(task); +put_pid: + put_pid(pid); + return ret; +#else + return -ENOSYS; +#endif /* CONFIG_MMU */ +} + diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 2056318988f7..c252faa802d3 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -859,9 +859,11 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_process_madvise 440 __SYSCALL(__NR_process_madvise, sys_process_madvise) +#define __NR_process_mrelease 441 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) #undef __NR_syscalls -#define __NR_syscalls 441 +#define __NR_syscalls 442 /* * 32 bit systems traditionally used different -- 2.30.0

2 1

[PATCH OLK-5.10] crypto:rmd320 rmd128 rmd256-remove RIPE-MD 320 128 256 hash algorithm
by Wen Zhiwei 18 Jan '22

18 Jan '22

mainlin inclusion category: performance bugzilla: NA CVE: NA ----------------------------------------------------------- RIPE-MD 256 is never referenced anywhere in the kernel, and unlikely to be depended upon by userspace via AF_ALG. So let's remove it Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Wen Zhiwei <wenzhiwei(a)kylinos.cn> --- crypto/tcrypt.c | 42 +----------------------------------------- 1 file changed, 1 insertion(+), 41 deletions(-) diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index 8609174e036e..c8b0d31631f5 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -71,7 +71,7 @@ static const char *check[] = { "blowfish", "twofish", "serpent", "sha384", "sha512", "md4", "aes", "cast6", "arc4", "michael_mic", "deflate", "crc32c", "tea", "xtea", "khazad", "wp512", "wp384", "wp256", "tnepres", "xeta", "fcrypt", - "camellia", "seed", "salsa20", "rmd128", "rmd160", "rmd256", "rmd320", + "camellia", "seed", "salsa20", "rmd160", "lzo", "lzo-rle", "cts", "sha3-224", "sha3-256", "sha3-384", "sha3-512", "streebog256", "streebog512", NULL @@ -1860,22 +1860,10 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb) ret += tcrypt_test("cts(cbc(aes))"); break; - case 39: - ret += tcrypt_test("rmd128"); - break; - case 40: ret += tcrypt_test("rmd160"); break; - case 41: - ret += tcrypt_test("rmd256"); - break; - - case 42: - ret += tcrypt_test("rmd320"); - break; - case 43: ret += tcrypt_test("ecb(seed)"); break; @@ -1948,10 +1936,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb) ret += tcrypt_test("xcbc(aes)"); break; - case 107: - ret += tcrypt_test("hmac(rmd128)"); - break; - case 108: ret += tcrypt_test("hmac(rmd160)"); break; @@ -2402,22 +2386,10 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb) test_hash_speed("sha224", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; fallthrough; - case 314: - test_hash_speed("rmd128", sec, generic_hash_speed_template); - if (mode > 300 && mode < 400) break; - fallthrough; case 315: test_hash_speed("rmd160", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; fallthrough; - case 316: - test_hash_speed("rmd256", sec, generic_hash_speed_template); - if (mode > 300 && mode < 400) break; - fallthrough; - case 317: - test_hash_speed("rmd320", sec, generic_hash_speed_template); - if (mode > 300 && mode < 400) break; - fallthrough; case 318: klen = 16; test_hash_speed("ghash", sec, generic_hash_speed_template); @@ -2526,22 +2498,10 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb) test_ahash_speed("sha224", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; fallthrough; - case 414: - test_ahash_speed("rmd128", sec, generic_hash_speed_template); - if (mode > 400 && mode < 500) break; - fallthrough; case 415: test_ahash_speed("rmd160", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; fallthrough; - case 416: - test_ahash_speed("rmd256", sec, generic_hash_speed_template); - if (mode > 400 && mode < 500) break; - fallthrough; - case 417: - test_ahash_speed("rmd320", sec, generic_hash_speed_template); - if (mode > 400 && mode < 500) break; - fallthrough; case 418: test_ahash_speed("sha3-224", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; -- 2.30.0

2 1

[PATCH OLK-5.10] Add Intel SGX hardware bits
by zhangyue 15 Jan '22

15 Jan '22

mainline inclusion category: feature bugzilla:https://gitee.com/openeuler/kernel/issues/I4CMMB?from=project-issue CVE: NA Populate X86_FEATURE_SGX feature from CPUID and tie it to the Kconfig option with disabled-features.h. IA32_FEATURE_CONTROL.SGX_ENABLE must be examined in addition to the CPUID bits to enable full SGX support. The BIOS must both set this bit and lock IA32_FEATURE_CONTROL for SGX to be supported (Intel SDM section 36.7.1). The setting or clearing of this bit has no impact on the CPUID bits above, which is why it needs to be detected separately. Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com> Co-developed-by: Jarkko Sakkinen <jarkko(a)kernel.org> Signed-off-by: Jarkko Sakkinen <jarkko(a)kernel.org> Signed-off-by: Borislav Petkov <bp(a)suse.de> Acked-by: Jethro Beekman <jethro(a)fortanix.com> Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/disabled-features.h | 8 +++++++- arch/x86/include/asm/msr-index.h | 1 + 3 files changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index dad350d42ecf..1181f5c7bbef 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -241,6 +241,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ #define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3B */ +#define X86_FEATURE_SGX ( 9*32+ 2) /* Software Guard Extensions */ #define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ #define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ #define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 09db5b8f1444..24d66717c642 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -59,6 +59,12 @@ /* Force disable because it's broken beyond repair */ #define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) +#ifdef CONFIG_X86_SGX +#define DISABLE_SGX 0 +#else +#define DISABLE_SGX (1 << (X86_FEATURE_SGX & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -71,7 +77,7 @@ #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) #define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_SMAP) +#define DISABLED_MASK9 (DISABLE_SMAP|DISABLE_SGX) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 972a34d93505..258d555d22f2 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -609,6 +609,7 @@ #define FEAT_CTL_LOCKED BIT(0) #define FEAT_CTL_VMX_ENABLED_INSIDE_SMX BIT(1) #define FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX BIT(2) +#define FEAT_CTL_SGX_ENABLED BIT(18) #define FEAT_CTL_LMCE_ENABLED BIT(20) #define MSR_IA32_TSC_ADJUST 0x0000003b -- 2.30.0

2 1

perf spe-c2c record失败的问题
by haoxin 15 Dec '21

15 Dec '21

您好，我采用最细的openEuler-1.0测试perf spe-c2c的功能，但是发现/sys/devices下没有arm_spe_0这个目录执行perf spe-c2c record时显示： event syntax error: 'arm_spe_0/ts_enable=1,pct_enable=1,pa_enable=1,load_filter=1,jitter=1,store_filter=1,min_latency=0/' \___ Cannot find PMU `arm_spe_0'. Missing kernel support? 想问下您这是为什么？需要哪里开启spe功能吗？

3 2

[PATCH openEuler-5.10 00/17] Memory cgroup enhancement
by Zheng Zengkai 30 Nov '21

30 Nov '21

Memory cgroup enhancement. Johannes Weiner (9): mm: memcontrol: fix cpuhotplug statistics flushing mm: memcontrol: kill mem_cgroup_nodeinfo() mm: memcontrol: privatize memcg_page_state query functions cgroup: rstat: support cgroup1 cgroup: rstat: punt root-level optimization to individual controllers mm: memcontrol: switch to rstat mm: memcontrol: consolidate lruvec stat flushing kselftests: cgroup: update kmem test for new vmstat implementation mm: memcontrol: fix blocking rstat function called from atomic cgroup1 thresholding code Miaohe Lin (1): mm, memcg: remove unused functions Shakeel Butt (5): memcg: switch lruvec stats to rstat memcg: infrastructure to flush memcg stats memcg: flush lruvec stats in the refault memcg: flush stats only if updated memcg: unify memcg stat flushing Tejun Heo (2): cgroup: rstat: fix A-A deadlock on 32bit around u64_stats_sync blk-cgroup: blk_cgroup_bio_start() should use irq-safe operations on blkg->iostat_cpu block/blk-cgroup.c | 36 +- include/linux/memcontrol.h | 179 ++++------ kernel/cgroup/cgroup.c | 34 +- kernel/cgroup/rstat.c | 82 +++-- mm/memcontrol.c | 391 ++++++++++----------- mm/vmscan.c | 6 + mm/workingset.c | 1 + tools/testing/selftests/cgroup/test_kmem.c | 22 +- 8 files changed, 372 insertions(+), 379 deletions(-) -- 2.20.1

1 17

[openEuler-5.10] hugetlbfs: flush TLBs correctly after huge_pmd_unshare
by Zheng Zengkai 30 Nov '21

30 Nov '21

From: Nadav Amit <namit(a)vmware.com> stable inclusion from stable-5.10.82 commit 40bc831ab5f630431010d1ff867390b07418a7ee category: bugfix bugzilla: 185820 https://gitee.com/openeuler/kernel/issues/I4DDEL CVE: CVE-2021-4002 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ----------------------------------------------- commit a4a118f2eead1d6c49e00765de89878288d4b890 upstream. When __unmap_hugepage_range() calls to huge_pmd_unshare() succeed, a TLB flush is missing. This TLB flush must be performed before releasing the i_mmap_rwsem, in order to prevent an unshared PMDs page from being released and reused before the TLB flush took place. Arguably, a comprehensive solution would use mmu_gather interface to batch the TLB flushes and the PMDs page release, however it is not an easy solution: (1) try_to_unmap_one() and try_to_migrate_one() also call huge_pmd_unshare() and they cannot use the mmu_gather interface; and (2) deferring the release of the page reference for the PMDs page until after i_mmap_rwsem is dropeed can confuse huge_pmd_unshare() into thinking PMDs are shared when they are not. Fix __unmap_hugepage_range() by adding the missing TLB flush, and forcing a flush when unshare is successful. Fixes: 24669e58477e ("hugetlb: use mmu_gather instead of a temporary linked list for accumulating pages)" # 3.6 Signed-off-by: Nadav Amit <namit(a)vmware.com> Reviewed-by: Mike Kravetz <mike.kravetz(a)oracle.com> Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.vnet.ibm.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu(a)jp.fujitsu.com> Cc: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> 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> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- mm/hugetlb.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1bbe763dce73..47dd6b5e0040 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4017,6 +4017,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mmu_notifier_range range; + bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -4045,10 +4046,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, &address, ptep)) { spin_unlock(ptl); - /* - * We just unmapped a page of PMDs by clearing a PUD. - * The caller's TLB flush range should cover this area. - */ + tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); + force_flush = true; continue; } @@ -4105,6 +4104,22 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } mmu_notifier_invalidate_range_end(&range); tlb_end_vma(tlb, vma); + + /* + * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We + * could defer the flush until now, since by holding i_mmap_rwsem we + * guaranteed that the last refernece would not be dropped. But we must + * do the flushing before we return, as otherwise i_mmap_rwsem will be + * dropped and the last reference to the shared PMDs page might be + * dropped as well. + * + * In theory we could defer the freeing of the PMD pages as well, but + * huge_pmd_unshare() relies on the exact page_count for the PMD page to + * detect sharing, so we cannot defer the release of the page either. + * Instead, do flush now. + */ + if (force_flush) + tlb_flush_mmu_tlbonly(tlb); } void __unmap_hugepage_range_final(struct mmu_gather *tlb, -- 2.20.1

1 0

[PATCH openEuler-5.10 00/19] Backport 5.10.79 LTS
by Zheng Zengkai 30 Nov '21

30 Nov '21

Backport 5.10.79 LTS patches from upstream. Geert Uytterhoeven (1): usb: gadget: Mark USB_FSL_QE broken on 64-bit Gustavo A. R. Silva (1): media: staging/intel-ipu3: css: Fix wrong size comparison imgu_css_fw_init James Buren (1): usb-storage: Add compatibility quirk flags for iODD 2531/2541 Jan Kara (1): isofs: Fix out of bound access for corrupted isofs image Johan Hovold (8): comedi: dt9812: fix DMA buffers on stack comedi: ni_usb6501: fix NULL-deref in command paths comedi: vmk80xx: fix transfer-buffer overflows comedi: vmk80xx: fix bulk-buffer overflow comedi: vmk80xx: fix bulk and interrupt message timeouts staging: r8712u: fix control-message timeout staging: rtl8192u: fix control-message timeouts rsi: fix control-message timeout Juergen Gross (1): Revert "x86/kvm: fix vcpu-id indexed array sizes" Neal Liu (1): usb: ehci: handshake CMD_RUN instead of STS_HALT Paolo Bonzini (1): KVM: x86: avoid warning with -Wbitwise-instead-of-logical Pavel Skripkin (1): staging: rtl8712: fix use-after-free in rtl8712_dl_fw Petr Mladek (1): printk/console: Allow to disable console output by using console="" or console=null Todd Kjos (1): binder: don't detect sender/target during buffer cleanup Viraj Shah (1): usb: musb: Balance list entry in musb_gadget_queue arch/x86/kvm/ioapic.c | 2 +- arch/x86/kvm/ioapic.h | 4 +- arch/x86/kvm/mmu/mmu.c | 2 +- drivers/android/binder.c | 14 +-- drivers/net/wireless/rsi/rsi_91x_usb.c | 2 +- drivers/staging/comedi/drivers/dt9812.c | 115 +++++++++++++++----- drivers/staging/comedi/drivers/ni_usb6501.c | 10 ++ drivers/staging/comedi/drivers/vmk80xx.c | 28 ++--- drivers/staging/media/ipu3/ipu3-css-fw.c | 7 +- drivers/staging/media/ipu3/ipu3-css-fw.h | 2 +- drivers/staging/rtl8192u/r8192U_core.c | 18 +-- drivers/staging/rtl8712/usb_intf.c | 4 +- drivers/staging/rtl8712/usb_ops_linux.c | 2 +- drivers/usb/gadget/udc/Kconfig | 1 + drivers/usb/host/ehci-hcd.c | 11 +- drivers/usb/host/ehci-platform.c | 6 + drivers/usb/host/ehci.h | 1 + drivers/usb/musb/musb_gadget.c | 4 +- drivers/usb/storage/unusual_devs.h | 10 ++ fs/isofs/inode.c | 2 + kernel/printk/printk.c | 9 +- 21 files changed, 180 insertions(+), 74 deletions(-) -- 2.20.1

1 19

[PATCH openEuler-5.10 1/3] ima: Fix warning: no previous prototype for function 'ima_add_kexec_buffer'
by Zheng Zengkai 30 Nov '21

30 Nov '21

From: Lakshmi Ramasubramanian <nramas(a)linux.microsoft.com> mainline inclusion from mainline-5.14 commit: c67913492fec317bc53ffdff496b6ba856d2868c category: bugfix bugzilla: 182971 https://gitee.com/openeuler/kernel/issues/I4DDEL Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- The function prototype for ima_add_kexec_buffer() is present in 'linux/ima.h'. But this header file is not included in ima_kexec.c where the function is implemented. This results in the following compiler warning when "-Wmissing-prototypes" flag is turned on: security/integrity/ima/ima_kexec.c:81:6: warning: no previous prototype for function 'ima_add_kexec_buffer' [-Wmissing-prototypes] Include the header file 'linux/ima.h' in ima_kexec.c to fix the compiler warning. Fixes: dce92f6b11c3 (arm64: Enable passing IMA log to next kernel on kexec) Reported-by: kernel test robot <lkp(a)intel.com> Signed-off-by: Lakshmi Ramasubramanian <nramas(a)linux.microsoft.com> Acked-by: Rob Herring <robh(a)kernel.org> Signed-off-by: Mimi Zohar <zohar(a)linux.ibm.com> Signed-off-by: Guo Zihua <guozihua(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- security/integrity/ima/ima_kexec.c | 1 + 1 file changed, 1 insertion(+) diff --git a/security/integrity/ima/ima_kexec.c b/security/integrity/ima/ima_kexec.c index 667887665823..f799cc278a9a 100644 --- a/security/integrity/ima/ima_kexec.c +++ b/security/integrity/ima/ima_kexec.c @@ -11,6 +11,7 @@ #include <linux/vmalloc.h> #include <linux/kexec.h> #include <linux/of.h> +#include <linux/ima.h> #include "ima.h" #ifdef CONFIG_IMA_KEXEC -- 2.20.1

1 2

[PATCH openEuler-5.10 01/10] powerpc/booke: Disable STRICT_KERNEL_RWX, DEBUG_PAGEALLOC and KFENCE
by Zheng Zengkai 30 Nov '21

30 Nov '21

From: Christophe Leroy <christophe.leroy(a)csgroup.eu> mainline inclusion from mainline-v5.16-rc1 commit 68b44f94d6370e2c6c790fedd28e637fa9964a93 category: bugfix bugzilla: 185780 https://gitee.com/openeuler/kernel/issues/I4EUY7 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------------- fsl_booke and 44x are not able to map kernel linear memory with pages, so they can't support DEBUG_PAGEALLOC and KFENCE, and STRICT_KERNEL_RWX is also a problem for now. Enable those only on book3s (both 32 and 64 except KFENCE), 8xx and 40x. Fixes: 88df6e90fa97 ("[POWERPC] DEBUG_PAGEALLOC for 32-bit") Fixes: 95902e6c8864 ("powerpc/mm: Implement STRICT_KERNEL_RWX on PPC32") Fixes: 90cbac0e995d ("powerpc: Enable KFENCE for PPC32") Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://lore.kernel.org/r/d1ad9fdd9b27da3fdfa16510bb542ed51fa6e134.16342921… Conflicts: arch/powerpc/Kconfig 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> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- arch/powerpc/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 81a629c5133c..da2b1c3b9ae4 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -135,7 +135,7 @@ config PPC select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64 - select ARCH_HAS_STRICT_KERNEL_RWX if (PPC32 && !HIBERNATION) + select ARCH_HAS_STRICT_KERNEL_RWX if (PPC_BOOK3S_32 || PPC_8xx || 40x) && !HIBERNATION select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE select ARCH_HAS_COPY_MC if PPC64 @@ -184,7 +184,7 @@ config PPC select HAVE_ARCH_KASAN if PPC32 && PPC_PAGE_SHIFT <= 14 select HAVE_ARCH_KASAN_VMALLOC if PPC32 && PPC_PAGE_SHIFT <= 14 select HAVE_ARCH_KGDB - select HAVE_ARCH_KFENCE if PPC32 + select HAVE_ARCH_KFENCE if PPC_BOOK3S_32 || PPC_8xx || 40x select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT select HAVE_ARCH_NVRAM_OPS @@ -360,7 +360,7 @@ config PPC_OF_PLATFORM_PCI depends on PPC64 # not supported on 32 bits yet config ARCH_SUPPORTS_DEBUG_PAGEALLOC - depends on PPC32 || PPC_BOOK3S_64 + depends on PPC_BOOK3S || PPC_8xx || 40x def_bool y config ARCH_SUPPORTS_UPROBES -- 2.20.1

1 9

[PATCH openEuler-5.10 01/14] ubifs: fix slab-out-of-bounds in ubifs_change_lp
by Zheng Zengkai 30 Nov '21

30 Nov '21

From: Baokun Li <libaokun1(a)huawei.com> hulk inclusion category: bugfix bugzilla: 182993 https://gitee.com/openeuler/kernel/issues/I4DDEL --------------------------- Hulk Robot reported a KASAN report about slab-out-of-bounds: ================================================================== BUG: KASAN: slab-out-of-bounds in ubifs_change_lp+0x3a9/0x1390 [ubifs] Read of size 8 at addr ffff888101c961f8 by task fsstress/1068 [...] Call Trace: check_memory_region+0x1c1/0x1e0 ubifs_change_lp+0x3a9/0x1390 [ubifs] ubifs_change_one_lp+0x170/0x220 [ubifs] ubifs_garbage_collect+0x7f9/0xda0 [ubifs] ubifs_budget_space+0xfe4/0x1bd0 [ubifs] ubifs_write_begin+0x528/0x10c0 [ubifs] Allocated by task 1068: kmemdup+0x25/0x50 ubifs_lpt_lookup_dirty+0x372/0xb00 [ubifs] ubifs_update_one_lp+0x46/0x260 [ubifs] ubifs_tnc_end_commit+0x98b/0x1720 [ubifs] do_commit+0x6cb/0x1950 [ubifs] ubifs_run_commit+0x15a/0x2b0 [ubifs] ubifs_budget_space+0x1061/0x1bd0 [ubifs] ubifs_write_begin+0x528/0x10c0 [ubifs] [...] ================================================================== In ubifs_garbage_collect(), if ubifs_find_dirty_leb returns an error, lp is an uninitialized variable. But lp.num might be used in the out branch, which is a random value. If the value is -1 or another value that can pass the check, soob may occur in the ubifs_change_lp() in the following procedure. To solve this problem, we initialize lp.lnum to -1, and then initialize it correctly in ubifs_find_dirty_leb, which is not equal to -1, and ubifs_return_leb is executed only when lp.lnum != -1. if find a retained or indexing LEB and continue to next loop, but break before find another LEB, the "taken" flag of this LEB will be cleaned in ubi_return_lebi(). This bug has also been fixed in this patch. Reported-by: Hulk Robot <hulkci(a)huawei.com> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> --- fs/ubifs/gc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c index dc3e26e9ed7b..05e1eeae8457 100644 --- a/fs/ubifs/gc.c +++ b/fs/ubifs/gc.c @@ -692,6 +692,9 @@ int ubifs_garbage_collect(struct ubifs_info *c, int anyway) for (i = 0; ; i++) { int space_before, space_after; + /* Maybe continue after find and break before find */ + lp.lnum = -1; + cond_resched(); /* Give the commit an opportunity to run */ @@ -843,7 +846,8 @@ int ubifs_garbage_collect(struct ubifs_info *c, int anyway) ubifs_wbuf_sync_nolock(wbuf); ubifs_ro_mode(c, ret); mutex_unlock(&wbuf->io_mutex); - ubifs_return_leb(c, lp.lnum); + if (lp.lnum != -1) + ubifs_return_leb(c, lp.lnum); return ret; } -- 2.20.1

1 13

Re:Welcome to the "Kernel" mailing list
by 杨嫣 30 Nov '21

30 Nov '21

您好 Kernel，     我想通过此列表交流。   ------------------ Original ------------------ From:  "kernel-request"<kernel-request(a)openeuler.org>; Date:  Tue, Nov 30, 2021 04:12 PM To:  "杨嫣"<yan.yang(a)i-soft.com.cn>; Subject:  Welcome to the "Kernel" mailing list   欢迎使用“Kernel”邮件列表！要通过此列表交流，请发送电子邮件至:     kernel(a)openeuler.org 取消订阅或调整选项请发送电子邮件至:     kernel-leave(a)openeuler.org 在主题或正文中使用"help"一词(不包括引号), 您将会收到一条带有说明的信息。更改设置需要用到密码，但出于安全考虑，此处不包括此密码。如果您忘记了密码，则需要通过网络用户界面重置密码。 Welcome to the "Kernel" mailing list! To post to this list, send your email to:   kernel(a)openeuler.org You can unsubscribe or make adjustments to your options via email by sending a message to:   kernel-leave(a)openeuler.org with the word 'help' in the subject or body (don't include the quotes), and you will receive a message with instructions.  You will need your password to change your options, but for security purposes, this password is not included here.  If you have forgotten your password, you will need to reset it via the web UI.

1 0

[PATCH openEuler-1.0-LTS] defconfig: update the defconfigs to support 9P
by Yang Yingliang 30 Nov '21

30 Nov '21

From: Laibin Qiu <qiulaibin(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4ICQF?from=project-issue CVE: NA ------------------------------------------------- Enable configs to support 9P. 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> --- arch/arm64/configs/openeuler_defconfig | 9 ++++++++- arch/x86/configs/openeuler_defconfig | 10 +++++++++- 2 files changed, 17 insertions(+), 2 deletions(-) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index c63a2f829db02..c2cb98dcf340b 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -1729,7 +1729,10 @@ CONFIG_RFKILL=m CONFIG_RFKILL_LEDS=y CONFIG_RFKILL_INPUT=y CONFIG_RFKILL_GPIO=m -# CONFIG_NET_9P is not set +CONFIG_NET_9P=m +CONFIG_NET_9P_VIRTIO=m +# CONFIG_NET_9P_RDMA is not set +# CONFIG_NET_9P_DEBUG is not set # CONFIG_CAIF is not set CONFIG_CEPH_LIB=m # CONFIG_CEPH_LIB_PRETTYDEBUG is not set @@ -5356,6 +5359,10 @@ CONFIG_CIFS_DFS_UPCALL=y # CONFIG_CIFS_FSCACHE is not set # CONFIG_CODA_FS is not set # CONFIG_AFS_FS is not set +CONFIG_9P_FS=m +CONFIG_9P_FSCACHE=y +CONFIG_9P_FS_POSIX_ACL=y +CONFIG_9P_FS_SECURITY=y CONFIG_NLS=y CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=y diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 0b103110f821c..8a1c4daf5c4b0 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -1805,7 +1805,11 @@ CONFIG_RFKILL=m CONFIG_RFKILL_LEDS=y CONFIG_RFKILL_INPUT=y # CONFIG_RFKILL_GPIO is not set -# CONFIG_NET_9P is not set +CONFIG_NET_9P=m +CONFIG_NET_9P_VIRTIO=m +# CONFIG_NET_9P_XEN is not set +# CONFIG_NET_9P_RDMA is not set +# CONFIG_NET_9P_DEBUG is not set # CONFIG_CAIF is not set CONFIG_CEPH_LIB=m # CONFIG_CEPH_LIB_PRETTYDEBUG is not set @@ -6838,6 +6842,10 @@ CONFIG_CIFS_DFS_UPCALL=y # CONFIG_CIFS_FSCACHE is not set # CONFIG_CODA_FS is not set # CONFIG_AFS_FS is not set +CONFIG_9P_FS=m +CONFIG_9P_FSCACHE=y +CONFIG_9P_FS_POSIX_ACL=y +CONFIG_9P_FS_SECURITY=y CONFIG_NLS=y CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=y -- 2.25.1

1 0

kernel sig 申报一个议题：openEuler 22.03增加ntfs3新驱动支持ntfs文件系统
by 尹秀江 30 Nov '21

30 Nov '21

1 0

【Meeting Notice】openEuler kernel 技术分享第十五期 & 双周例会 Time: 2021-12-03 14:00-16:30
by Meeting Book 30 Nov '21

30 Nov '21

1 0

kernel sig 申报一个议题：openEuler 22.03 LTS 核心 CONFIG （PageSize/NR_CPUS/NODES_SHIFT）选择讨论
by Xie XiuQi 29 Nov '21

29 Nov '21

议题：openEuler 22.03 LTS 核心 CONFIG （PageSize/NR_CPUS/NODES_SHIFT）讨论 https://gitee.com/openeuler/kernel/issues/I4HDHZ 欢迎提前在 issue 中讨论

1 0

[PATCH openEuler-5.10 01/31] timer_list: avoid other cpu soft lockup when printing timer list
by Zheng Zengkai 29 Nov '21

29 Nov '21

From: Yang Yingliang <yangyingliang(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4IYRE --------------------------- If system has many cpus (e.g. 128), it will spend a lot of time to print message to the console when execute echo q > /proc/sysrq-trigger. When /proc/sys/kernel/numa_balancing is enabled, if the migration threads is woke up, the thread cannot continue until the print finish, it will trigger a soft lockup. PID: 619 TASK: ffffa02fdd8bec80 CPU: 121 COMMAND: "migration/121" #0 [ffff00000a103b10] __crash_kexec at ffff0000081bf200 #1 [ffff00000a103ca0] panic at ffff0000080ec93c #2 [ffff00000a103d80] watchdog_timer_fn at ffff0000081f8a14 #3 [ffff00000a103e00] __run_hrtimer at ffff00000819701c #4 [ffff00000a103e40] __hrtimer_run_queues at ffff000008197420 #5 [ffff00000a103ea0] hrtimer_interrupt at ffff00000819831c #6 [ffff00000a103f10] arch_timer_dying_cpu at ffff000008b53144 #7 [ffff00000a103f30] handle_percpu_devid_irq at ffff000008174e34 #8 [ffff00000a103f70] generic_handle_irq at ffff00000816c5e8 #9 [ffff00000a103f90] __handle_domain_irq at ffff00000816d1f4 #10 [ffff00000a103fd0] gic_handle_irq at ffff000008081860 --- <IRQ stack> --- #11 [ffff00000d6e3d50] el1_irq at ffff0000080834c8 #12 [ffff00000d6e3d60] multi_cpu_stop at ffff0000081d9964 #13 [ffff00000d6e3db0] cpu_stopper_thread at ffff0000081d9cfc #14 [ffff00000d6e3e10] smpboot_thread_fn at ffff00000811e0a8 #15 [ffff00000d6e3e70] kthread at ffff000008118988 To avoid this soft lockup, add touch_all_softlockup_watchdogs() in sysrq_timer_list_show() Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-By: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: wangxiongfeng 00379786 <wangxiongfeng2(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- kernel/time/timer_list.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index acb326f5f50a..4cb0e6f62e97 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -289,13 +289,17 @@ void sysrq_timer_list_show(void) timer_list_header(NULL, now); - for_each_online_cpu(cpu) + for_each_online_cpu(cpu) { + touch_all_softlockup_watchdogs(); print_cpu(NULL, cpu, now); + } #ifdef CONFIG_GENERIC_CLOCKEVENTS timer_list_show_tickdevices_header(NULL); - for_each_online_cpu(cpu) + for_each_online_cpu(cpu) { + touch_all_softlockup_watchdogs(); print_tickdevice(NULL, tick_get_device(cpu), cpu); + } #endif return; } -- 2.20.1

1 30

[PATCH openEuler-1.0-LTS 01/13] sched: Introduce qos scheduler for co-location
by Yang Yingliang 29 Nov '21

29 Nov '21

From: Zheng Zucheng <zhengzucheng(a)huawei.com> hulk inclusion category: feature bugzilla: 51828, https://gitee.com/openeuler/kernel/issues/I4K96G CVE: NA -------------------------------- We introduce the idea of qos level to scheduler, which now is supported with different scheduler policies. The qos scheduler will change the policy of correlative tasks when the qos level of a task group is modified with cpu.qos_level cpu cgroup file. In this way we are able to satisfy different needs of tasks in different qos levels. Signed-off-by: Zhang Qiao <zhangqiao22(a)huawei.com> Signed-off-by: Zheng Zucheng <zhengzucheng(a)huawei.com> Reviewed-by: Chen Hui <judy.chenhui(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- init/Kconfig | 8 ++++ kernel/sched/core.c | 93 ++++++++++++++++++++++++++++++++++++++++++++ kernel/sched/sched.h | 4 ++ 3 files changed, 105 insertions(+) diff --git a/init/Kconfig b/init/Kconfig index c05347a29ca4d..a338519692d54 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -777,6 +777,14 @@ menuconfig CGROUP_SCHED tasks. if CGROUP_SCHED +config QOS_SCHED + bool "Qos task scheduling" + depends on CGROUP_SCHED + depends on CFS_BANDWIDTH + depends on X86 + + default n + config FAIR_GROUP_SCHED bool "Group scheduling for SCHED_OTHER" depends on CGROUP_SCHED diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8866cd7f19c43..23160df884e49 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6338,6 +6338,15 @@ void ia64_set_curr_task(int cpu, struct task_struct *p) /* task_group_lock serializes the addition/removal of task groups */ static DEFINE_SPINLOCK(task_group_lock); +#ifdef CONFIG_QOS_SCHED +static int alloc_qos_sched_group(struct task_group *tg, struct task_group *parent) +{ + tg->qos_level = parent->qos_level; + + return 1; +} +#endif + static void sched_free_group(struct task_group *tg) { free_fair_sched_group(tg); @@ -6358,6 +6367,11 @@ struct task_group *sched_create_group(struct task_group *parent) if (!alloc_fair_sched_group(tg, parent)) goto err; +#ifdef CONFIG_QOS_SCHED + if (!alloc_qos_sched_group(tg, parent)) + goto err; +#endif + if (!alloc_rt_sched_group(tg, parent)) goto err; @@ -6426,6 +6440,30 @@ static void sched_change_group(struct task_struct *tsk, int type) tg = autogroup_task_group(tsk, tg); tsk->sched_task_group = tg; +#ifdef CONFIG_QOS_SCHED + /* + * No need to re-setcheduler when a task is exiting or the task + * is in an autogroup. + */ + if (!rt_task(tsk) + && !(tsk->flags & PF_EXITING) + && !task_group_is_autogroup(tg)) { + struct rq *rq = task_rq(tsk); + struct sched_attr attr = { + .sched_priority = 0, + }; + + if (tg->qos_level == -1) { + attr.sched_policy = SCHED_IDLE; + } else { + attr.sched_policy = SCHED_NORMAL; + } + attr.sched_nice = PRIO_TO_NICE(tsk->static_prio); + + __setscheduler(rq, tsk, &attr, 0); + } +#endif + #ifdef CONFIG_FAIR_GROUP_SCHED if (tsk->sched_class->task_change_group) tsk->sched_class->task_change_group(tsk, type); @@ -6886,6 +6924,54 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css, } #endif /* CONFIG_RT_GROUP_SCHED */ +#ifdef CONFIG_QOS_SCHED +static int cpu_qos_write(struct cgroup_subsys_state *css, + struct cftype *cftype, s64 qos_level) +{ + struct css_task_iter it; + struct task_struct *tsk; + struct task_group *tg; + struct sched_param param; + int pid, policy; + tg = css_tg(css); + + if (!tg->se[0]) + return -EINVAL; + + if (qos_level != -1 && qos_level != 0) + return -EINVAL; + + if (tg->qos_level == qos_level) + goto done; + + if (qos_level == -1) { + policy = SCHED_IDLE; + } else { + policy = SCHED_NORMAL; + } + + tg->qos_level = qos_level; + + param.sched_priority = 0; + css_task_iter_start(css, 0, &it); + while ((tsk = css_task_iter_next(&it))) { + pid = task_tgid_vnr(tsk); + + if (pid > 0 && !rt_task(tsk)) + sched_setscheduler(tsk, policy, &param); + } + css_task_iter_end(&it); + +done: + return 0; +} + +static s64 cpu_qos_read(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return css_tg(css)->qos_level; +} +#endif /* CONFIG_QOS_SCHED */ + static struct cftype cpu_legacy_files[] = { #ifdef CONFIG_FAIR_GROUP_SCHED { @@ -6921,6 +7007,13 @@ static struct cftype cpu_legacy_files[] = { .read_u64 = cpu_rt_period_read_uint, .write_u64 = cpu_rt_period_write_uint, }, +#endif +#ifdef CONFIG_QOS_SCHED + { + .name = "qos_level", + .read_s64 = cpu_qos_read, + .write_s64 = cpu_qos_write, + }, #endif { } /* Terminate */ }; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index e6238db9dc996..c263cb2f35c5d 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -402,7 +402,11 @@ struct task_group { struct cfs_bandwidth cfs_bandwidth; +#if defined(CONFIG_QOS_SCHED) && !defined(__GENKSYMS__) + long qos_level; +#else KABI_RESERVE(1) +#endif KABI_RESERVE(2) }; -- 2.25.1

1 12

【议题申报】主题：SM4相关patch合入
by 沈子俊 29 Nov '21

29 Nov '21

1 0

[PATCH openEuler-1.0-LTS 1/3] ACPI: CPPC: Fix cppc_cpufreq_init failed in CPU Hotplug situation
by Yang Yingliang 27 Nov '21

27 Nov '21

From: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4HYY4?from=project-issue CVE: NA ------------------------------------------------- Per-CPU variables cpc_desc_ptr are initialized in acpi_cppc_processor_probe() when the processor devices are present and added into the system. But when cpu_possible_mask and cpu_present_mask is not equal, only cpc_desc_ptr in cpu_present_mask are initialized, this will cause acpi_get_psd_map() failed in cppc_cpufreq_init(). To fix this issue, we parse the _PSD method for all possible CPUs to get the P-State topology and modify acpi_get_psd_map() to rely on this information. Signed-off-by: Xiongfeng Wang <wangxiongfeng(a)huawei.com> Reviewed-by: Keqian Zhu <zhukeqian1(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/acpi/cppc_acpi.c | 93 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 89 insertions(+), 4 deletions(-) diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 6134f20a13f0c..e71c0e0572bea 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -415,7 +415,7 @@ static int acpi_get_psd(struct cpc_desc *cpc_ptr, acpi_handle handle) * * Return: 0 for success or negative value for err. */ -int acpi_get_psd_map(struct cppc_cpudata **all_cpu_data) +static int __acpi_get_psd_map(struct cppc_cpudata **all_cpu_data, struct cpc_desc **cpc_pptr) { int count_target; int retval = 0; @@ -441,7 +441,7 @@ int acpi_get_psd_map(struct cppc_cpudata **all_cpu_data) if (cpumask_test_cpu(i, covered_cpus)) continue; - cpc_ptr = per_cpu(cpc_desc_ptr, i); + cpc_ptr = cpc_pptr[i]; if (!cpc_ptr) { retval = -EFAULT; goto err_ret; @@ -466,7 +466,7 @@ int acpi_get_psd_map(struct cppc_cpudata **all_cpu_data) if (i == j) continue; - match_cpc_ptr = per_cpu(cpc_desc_ptr, j); + match_cpc_ptr = cpc_pptr[j]; if (!match_cpc_ptr) { retval = -EFAULT; goto err_ret; @@ -499,7 +499,7 @@ int acpi_get_psd_map(struct cppc_cpudata **all_cpu_data) if (!match_pr) continue; - match_cpc_ptr = per_cpu(cpc_desc_ptr, j); + match_cpc_ptr = cpc_pptr[j]; if (!match_cpc_ptr) { retval = -EFAULT; goto err_ret; @@ -532,6 +532,91 @@ int acpi_get_psd_map(struct cppc_cpudata **all_cpu_data) free_cpumask_var(covered_cpus); return retval; } + +static acpi_status acpi_parse_cpc(acpi_handle handle, u32 lvl, void *data, + void **ret_p) +{ + struct acpi_device *adev = NULL; + struct cpc_desc *cpc_ptr, **cpc_pptr; + acpi_status status = AE_OK; + const int device_declaration = 1; + unsigned long long uid; + phys_cpuid_t phys_id; + int logical_id, ret; + int *parsed_core_num = (int *)ret_p; + + if (acpi_bus_get_device(handle, &adev)) + return AE_OK; + + if (strcmp(acpi_device_hid(adev), ACPI_PROCESSOR_DEVICE_HID)) + return AE_OK; + + status = acpi_evaluate_integer(handle, METHOD_NAME__UID, NULL, &uid); + if (ACPI_FAILURE(status)) + return AE_OK; + phys_id = acpi_get_phys_id(handle, device_declaration, uid); + if (invalid_phys_cpuid(phys_id)) + return AE_OK; + logical_id = acpi_map_cpuid(phys_id, uid); + if (logical_id < 0) + return AE_OK; + + cpc_pptr = (struct cpc_desc **)data; + cpc_ptr = cpc_pptr[logical_id]; + cpc_ptr->cpu_id = logical_id; + + ret = acpi_get_psd(cpc_ptr, handle); + if (ret) + return ret; + + (*parsed_core_num)++; + + return AE_OK; +} + +int acpi_get_psd_map(struct cppc_cpudata **all_cpu_data) +{ + struct cpc_desc **cpc_pptr, *cpc_ptr; + int parsed_core_num = 0; + int i, ret; + + cpc_pptr = kcalloc(num_possible_cpus(), sizeof(void *), GFP_KERNEL); + if (!cpc_pptr) + return -ENOMEM; + for_each_possible_cpu(i) { + cpc_pptr[i] = kzalloc(sizeof(struct cpc_desc), GFP_KERNEL); + if (!cpc_pptr[i]) { + ret = -ENOMEM; + goto out; + } + } + + /* + * We can not use acpi_get_devices() to walk the processor devices + * because some processor device is not present. + */ + ret = acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, acpi_parse_cpc, NULL, + cpc_pptr, (void **)&parsed_core_num); + if (ret) + goto out; + if (parsed_core_num != num_possible_cpus()) { + ret = -EINVAL; + goto out; + } + + ret = __acpi_get_psd_map(all_cpu_data, cpc_pptr); + +out: + for_each_possible_cpu(i) { + cpc_ptr = cpc_pptr[i]; + if (cpc_ptr) + kfree(cpc_ptr); + } + kfree(cpc_pptr); + + return ret; +} EXPORT_SYMBOL_GPL(acpi_get_psd_map); static int register_pcc_channel(int pcc_ss_idx) -- 2.25.1

1 2

[PATCH openEuler-5.10 16/31] perf, kvm/arm64: perf-kvm-stat to report VM TRAP
by Zheng Zengkai 26 Nov '21

26 Nov '21

From: Zenghui Yu <yuzenghui(a)huawei.com> virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4IZPY CVE: NA ------------------------------------------------- When guest exits due to "TRAP", we can analyze the guest exit reasons deeplier. Enhance perf-kvm-stat to record and analyze VM TRAP events. There is a mapping between guest's "trap_code" (ESR_ELx's bits[31:26]) and "trap_reason" - kvm_arm_exception_class. Copy it from kernel to aarch64_guest_exits.h, export it to userspace. This patch records two new KVM tracepoints: "kvm:kvm_trap_enter" and "kvm:kvm_trap_exit", and reports statistical data between these two tracepoints. A simple test go below: # ./tools/perf/perf kvm stat record -p 20763 [ perf record: Woken up 92 times to write data ] [ perf record: Captured and wrote 203.727 MB perf.data.guest (2601786 samples) ] # ./tools/perf/perf kvm stat report --event=vmexit Analyze events for all VMs, all VCPUs: VM-EXIT Samples Samples% Time% Min Time Max Time Avg time TRAP 640931 97.12% 100.00% 2.44us 14683.86us 3446.49us ( +- 0.05% ) IRQ 19019 2.88% 0.00% 0.90us 461.94us 2.12us ( +- 2.09% ) Total Samples:659950, Total events handled time:2209005391.30us. # ./tools/perf/perf kvm stat report --event=trap Analyze events for all VMs, all VCPUs: TRAP-EVENT Samples Samples% Time% Min Time Max Time Avg time WFx 601194 93.80% 99.98% 0.90us 4294.04us 3671.01us ( +- 0.03% ) SYS64 33714 5.26% 0.01% 1.10us 41.34us 5.68us ( +- 0.18% ) DABT_LOW 6014 0.94% 0.00% 1.12us 18.04us 2.57us ( +- 0.91% ) IABT_LOW 12 0.00% 0.01% 12597.76us 14679.96us 12893.61us ( +- 1.34% ) Total Samples:640934, Total events handled time:2207353434.56us. Signed-off-by: Zenghui Yu <yuzenghui(a)huawei.com> Reviewed-by: Hailiang Zhang <zhang.zhanghailiang(a)huawei.com> Signed-off-by: Zenghui Yu <yuzenghui(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Link: https://lore.kernel.org/r/1560330526-15468-6-git-send-email-yuzenghui@huawe… Link: https://gitee.com/openeuler/kernel/commit/59634497418b Reviewed-by: Yanan Wang <wangyanan55(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- .../arch/arm64/util/aarch64_guest_exits.h | 72 +++++++++++++++++++ tools/perf/arch/arm64/util/kvm-stat.c | 68 ++++++++++++++++++ 2 files changed, 140 insertions(+) diff --git a/tools/perf/arch/arm64/util/aarch64_guest_exits.h b/tools/perf/arch/arm64/util/aarch64_guest_exits.h index aec2e6e012d3..76e8f0358182 100644 --- a/tools/perf/arch/arm64/util/aarch64_guest_exits.h +++ b/tools/perf/arch/arm64/util/aarch64_guest_exits.h @@ -24,4 +24,76 @@ {ARM_EXCEPTION_TRAP, "TRAP" }, \ {ARM_EXCEPTION_HYP_GONE, "HYP_GONE" } +/* esr.h */ +#define ESR_ELx_EC_UNKNOWN (0x00) +#define ESR_ELx_EC_WFx (0x01) +/* Unallocated EC: 0x02 */ +#define ESR_ELx_EC_CP15_32 (0x03) +#define ESR_ELx_EC_CP15_64 (0x04) +#define ESR_ELx_EC_CP14_MR (0x05) +#define ESR_ELx_EC_CP14_LS (0x06) +#define ESR_ELx_EC_FP_ASIMD (0x07) +#define ESR_ELx_EC_CP10_ID (0x08) /* EL2 only */ +#define ESR_ELx_EC_PAC (0x09) /* EL2 and above */ +/* Unallocated EC: 0x0A - 0x0B */ +#define ESR_ELx_EC_CP14_64 (0x0C) +#define ESR_ELx_EC_BTI (0x0D) +#define ESR_ELx_EC_ILL (0x0E) +/* Unallocated EC: 0x0F - 0x10 */ +#define ESR_ELx_EC_SVC32 (0x11) +#define ESR_ELx_EC_HVC32 (0x12) /* EL2 only */ +#define ESR_ELx_EC_SMC32 (0x13) /* EL2 and above */ +/* Unallocated EC: 0x14 */ +#define ESR_ELx_EC_SVC64 (0x15) +#define ESR_ELx_EC_HVC64 (0x16) /* EL2 and above */ +#define ESR_ELx_EC_SMC64 (0x17) /* EL2 and above */ +#define ESR_ELx_EC_SYS64 (0x18) +#define ESR_ELx_EC_SVE (0x19) +#define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ +/* Unallocated EC: 0x1B */ +#define ESR_ELx_EC_FPAC (0x1C) /* EL1 and above */ +/* Unallocated EC: 0x1D - 0x1E */ +#define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ +#define ESR_ELx_EC_IABT_LOW (0x20) +#define ESR_ELx_EC_IABT_CUR (0x21) +#define ESR_ELx_EC_PC_ALIGN (0x22) +/* Unallocated EC: 0x23 */ +#define ESR_ELx_EC_DABT_LOW (0x24) +#define ESR_ELx_EC_DABT_CUR (0x25) +#define ESR_ELx_EC_SP_ALIGN (0x26) +/* Unallocated EC: 0x27 */ +#define ESR_ELx_EC_FP_EXC32 (0x28) +/* Unallocated EC: 0x29 - 0x2B */ +#define ESR_ELx_EC_FP_EXC64 (0x2C) +/* Unallocated EC: 0x2D - 0x2E */ +#define ESR_ELx_EC_SERROR (0x2F) +#define ESR_ELx_EC_BREAKPT_LOW (0x30) +#define ESR_ELx_EC_BREAKPT_CUR (0x31) +#define ESR_ELx_EC_SOFTSTP_LOW (0x32) +#define ESR_ELx_EC_SOFTSTP_CUR (0x33) +#define ESR_ELx_EC_WATCHPT_LOW (0x34) +#define ESR_ELx_EC_WATCHPT_CUR (0x35) +/* Unallocated EC: 0x36 - 0x37 */ +#define ESR_ELx_EC_BKPT32 (0x38) +/* Unallocated EC: 0x39 */ +#define ESR_ELx_EC_VECTOR32 (0x3A) /* EL2 only */ +/* Unallocated EC: 0x3B */ +#define ESR_ELx_EC_BRK64 (0x3C) +/* Unallocated EC: 0x3D - 0x3F */ +#define ESR_ELx_EC_MAX (0x3F) + +/* kvm_arm.h */ +#define ECN(x) { ESR_ELx_EC_##x, #x } + +#define kvm_arm_exception_class \ + ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \ + ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(PAC), ECN(CP14_64), \ + ECN(SVC64), ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(SVE), \ + ECN(IMP_DEF), ECN(IABT_LOW), ECN(IABT_CUR), \ + ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \ + ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \ + ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \ + ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ + ECN(BKPT32), ECN(VECTOR32), ECN(BRK64) + #endif /* ARCH_PERF_AARCH64_GUEST_EXITS_H */ diff --git a/tools/perf/arch/arm64/util/kvm-stat.c b/tools/perf/arch/arm64/util/kvm-stat.c index 2fed20370829..a0a97073d2d1 100644 --- a/tools/perf/arch/arm64/util/kvm-stat.c +++ b/tools/perf/arch/arm64/util/kvm-stat.c @@ -4,10 +4,14 @@ * Copyright(c) 2019 Huawei Technologies Co., Ltd */ +#include <string.h> +#include "../../../util/debug.h" +#include "../../../util/evsel.h" #include "../../../util/kvm-stat.h" #include "aarch64_guest_exits.h" define_exit_reasons_table(arm64_exit_reasons, kvm_arm_exception_type); +define_exit_reasons_table(arm64_trap_reasons, kvm_arm_exception_class); static struct kvm_events_ops exit_events = { .is_begin_event = exit_event_begin, @@ -22,14 +26,78 @@ const char *kvm_exit_reason = "ret"; const char *kvm_entry_trace = "kvm:kvm_entry"; const char *kvm_exit_trace = "kvm:kvm_exit"; +const char *kvm_trap_reason = "esr_ec"; +const char *kvm_trap_enter_trace = "kvm:kvm_trap_enter"; +const char *kvm_trap_exit_trace = "kvm:kvm_trap_exit"; + +static void trap_event_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->info = 0; + key->key = evsel__intval(evsel, sample, kvm_trap_reason); +} + +static const char *get_trap_reason(u64 exit_code) +{ + struct exit_reasons_table *tbl = arm64_trap_reasons; + + while (tbl->reason != NULL) { + if (tbl->exit_code == exit_code) + return tbl->reason; + tbl++; + } + + pr_err("Unknown kvm trap exit code: %lld on aarch64\n", + (unsigned long long)exit_code); + return "UNKNOWN"; +} + +static bool trap_event_end(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return (!strcmp(evsel->name, kvm_trap_exit_trace)); +} + +static bool trap_event_begin(struct evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + if (!strcmp(evsel->name, kvm_trap_enter_trace)) { + trap_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static void trap_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + const char *trap_reason = get_trap_reason(key->key); + + scnprintf(decode, decode_str_len, "%s", trap_reason); +} + +static struct kvm_events_ops trap_events = { + .is_begin_event = trap_event_begin, + .is_end_event = trap_event_end, + .decode_key = trap_event_decode_key, + .name = "TRAP-EVENT", +}; + const char *kvm_events_tp[] = { "kvm:kvm_entry", "kvm:kvm_exit", + "kvm:kvm_trap_enter", + "kvm:kvm_trap_exit", NULL, }; struct kvm_reg_events_ops kvm_reg_events_ops[] = { { .name = "vmexit", .ops = &exit_events }, + { .name = "trap", .ops = &trap_events }, { NULL, NULL }, }; -- 2.20.1

1 0

[PATCH openEuler-5.10 01/31] SCSI: spfc: fix typo of last_cmsn
by Zheng Zengkai 26 Nov '21

26 Nov '21

From: Yanling Song <songyl(a)ramaxel.com> 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> Reviewed-by: Zhang Lei<zhanglei48(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.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; -- 2.20.1

1 30

[PATCH OLK5.10] scsi:spraid: use bsg module to replace with ioctrl
by Yanling Song 26 Nov '21

26 Nov '21

Ramaxel inclusion category: features bugzilla: https://gitee.com/openeuler/kernel/issues/I4JXCG CVE: NA Changes: 1. Use BSG module to replace with ioctrl 2. Use email as MODULE_AUTHOR 3. Add error handling for PCIE error case; 4. Support SMR hdd in hba mode. Signed-off-by: Yanling Song <songyl(a)ramaxel.com> Reviewed-by: Jiang Yu<yujiang(a)ramaxel.com> --- drivers/scsi/spraid/spraid.h | 146 ++- drivers/scsi/spraid/spraid_main.c | 1412 +++++++++++++++-------------- 2 files changed, 840 insertions(+), 718 deletions(-) diff --git a/drivers/scsi/spraid/spraid.h b/drivers/scsi/spraid/spraid.h index da46d8e1b4b6..6a04fb65ec93 100644 --- a/drivers/scsi/spraid/spraid.h +++ b/drivers/scsi/spraid/spraid.h @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ #ifndef __SPRAID_H_ #define __SPRAID_H_ @@ -24,7 +25,7 @@ #define SENSE_SIZE(depth) ((depth) * SCSI_SENSE_BUFFERSIZE) #define SPRAID_AQ_DEPTH 128 -#define SPRAID_NR_AEN_COMMANDS 1 +#define SPRAID_NR_AEN_COMMANDS 16 #define SPRAID_AQ_BLK_MQ_DEPTH (SPRAID_AQ_DEPTH - SPRAID_NR_AEN_COMMANDS) #define SPRAID_AQ_MQ_TAG_DEPTH (SPRAID_AQ_BLK_MQ_DEPTH - 1) @@ -44,7 +45,7 @@ #define SMALL_POOL_SIZE 256 #define MAX_SMALL_POOL_NUM 16 -#define MAX_CMD_PER_DEV 32 +#define MAX_CMD_PER_DEV 64 #define MAX_CDB_LEN 32 #define SPRAID_UP_TO_MULTY4(x) (((x) + 4) & (~0x03)) @@ -53,7 +54,7 @@ #define PCI_VENDOR_ID_RAMAXEL_LOGIC 0x1E81 -#define SPRAID_SERVER_DEVICE_HAB_DID 0x2100 +#define SPRAID_SERVER_DEVICE_HBA_DID 0x2100 #define SPRAID_SERVER_DEVICE_RAID_DID 0x2200 #define IO_6_DEFAULT_TX_LEN 256 @@ -142,11 +143,15 @@ enum { enum { SPRAID_AEN_DEV_CHANGED = 0x00, + SPRAID_AEN_FW_ACT_START = 0x01, SPRAID_AEN_HOST_PROBING = 0x10, }; enum { - SPRAID_AEN_TIMESYN = 0x07 + SPRAID_AEN_TIMESYN = 0x00, + SPRAID_AEN_FW_ACT_FINISH = 0x02, + SPRAID_AEN_EVENT_MIN = 0x80, + SPRAID_AEN_EVENT_MAX = 0xff, }; enum { @@ -175,6 +180,16 @@ enum spraid_state { SPRAID_DEAD, }; +enum { + SPRAID_CARD_HBA, + SPRAID_CARD_RAID, +}; + +enum spraid_cmd_type { + SPRAID_CMD_ADM, + SPRAID_CMD_IOPT, +}; + struct spraid_completion { __le32 result; union { @@ -217,8 +232,6 @@ struct spraid_dev { struct dma_pool *prp_page_pool; struct dma_pool *prp_small_pool[MAX_SMALL_POOL_NUM]; mempool_t *iod_mempool; - struct blk_mq_tag_set admin_tagset; - struct request_queue *admin_q; void __iomem *bar; u32 max_qid; u32 num_vecs; @@ -232,23 +245,27 @@ struct spraid_dev { u32 ctrl_config; u32 online_queues; u64 cap; - struct device ctrl_device; - struct cdev cdev; int instance; struct spraid_ctrl_info *ctrl_info; struct spraid_dev_info *devices; - struct spraid_ioq_ptcmd *ioq_ptcmds; + struct spraid_cmd *adm_cmds; + struct list_head adm_cmd_list; + spinlock_t adm_cmd_lock; /* spinlock for lock handling */ + + struct spraid_cmd *ioq_ptcmds; struct list_head ioq_pt_list; - spinlock_t ioq_pt_lock; + spinlock_t ioq_pt_lock; /* spinlock for lock handling */ - struct work_struct aen_work; struct work_struct scan_work; struct work_struct timesyn_work; struct work_struct reset_work; + struct work_struct fw_act_work; enum spraid_state state; - spinlock_t state_lock; + spinlock_t state_lock; /* spinlock for lock handling */ + + struct request_queue *bsg_queue; }; struct spraid_sgl_desc { @@ -347,6 +364,35 @@ struct spraid_get_info { __u32 rsvd12[4]; }; +struct spraid_usr_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + union { + struct { + __le16 subopcode; + __le16 rsvd1; + } info_0; + __le32 cdw2; + }; + union { + struct { + __le16 data_len; + __le16 param_len; + } info_1; + __le32 cdw3; + }; + __u64 metadata; + union spraid_data_ptr dptr; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; +}; + enum { SPRAID_CMD_FLAG_SGL_METABUF = (1 << 6), SPRAID_CMD_FLAG_SGL_METASEG = (1 << 7), @@ -393,6 +439,7 @@ struct spraid_admin_command { struct spraid_get_info get_info; struct spraid_abort_cmd abort; struct spraid_reset_cmd reset; + struct spraid_usr_cmd usr_cmd; }; }; @@ -456,9 +503,6 @@ struct spraid_ioq_command { }; }; -#define SPRAID_IOCTL_RESET_CMD _IOWR('N', 0x80, struct spraid_passthru_common_cmd) -#define SPRAID_IOCTL_ADMIN_CMD _IOWR('N', 0x41, struct spraid_passthru_common_cmd) - struct spraid_passthru_common_cmd { __u8 opcode; __u8 flags; @@ -494,8 +538,6 @@ struct spraid_passthru_common_cmd { __u32 result1; }; -#define SPRAID_IOCTL_IOQ_CMD _IOWR('N', 0x42, struct spraid_ioq_passthru_cmd) - struct spraid_ioq_passthru_cmd { __u8 opcode; __u8 flags; @@ -560,7 +602,21 @@ struct spraid_ioq_passthru_cmd { __u32 result1; }; -struct spraid_ioq_ptcmd { +struct spraid_bsg_request { + u32 msgcode; + u32 control; + union { + struct spraid_passthru_common_cmd admcmd; + struct spraid_ioq_passthru_cmd ioqcmd; + }; +}; + +enum { + SPRAID_BSG_ADM, + SPRAID_BSG_IOQ, +}; + +struct spraid_cmd { int qid; int cid; u32 result0; @@ -572,14 +628,6 @@ struct spraid_ioq_ptcmd { struct list_head list; }; -struct spraid_admin_request { - struct spraid_admin_command *cmd; - u32 result0; - u32 result1; - u16 flags; - u16 status; -}; - struct spraid_queue { struct spraid_dev *hdev; spinlock_t sq_lock; /* spinlock for lock handling */ @@ -607,7 +655,6 @@ struct spraid_queue { }; struct spraid_iod { - struct spraid_admin_request req; struct spraid_queue *spraidq; enum spraid_cmd_state state; int npages; @@ -623,13 +670,51 @@ struct spraid_iod { }; #define SPRAID_DEV_INFO_ATTR_BOOT(attr) ((attr) & 0x01) -#define SPRAID_DEV_INFO_ATTR_HDD(attr) ((attr) & 0x02) +#define SPRAID_DEV_INFO_ATTR_VD(attr) (((attr) & 0x02) == 0x0) #define SPRAID_DEV_INFO_ATTR_PT(attr) (((attr) & 0x22) == 0x02) #define SPRAID_DEV_INFO_ATTR_RAWDISK(attr) ((attr) & 0x20) #define SPRAID_DEV_INFO_FLAG_VALID(flag) ((flag) & 0x01) #define SPRAID_DEV_INFO_FLAG_CHANGE(flag) ((flag) & 0x02) +#define BGTASK_TYPE_REBUILD 4 +#define USR_CMD_READ 0xc2 +#define USR_CMD_RDLEN 0x1000 +#define USR_CMD_VDINFO 0x704 +#define USR_CMD_BGTASK 0x504 +#define VDINFO_PARAM_LEN 0x04 + +struct spraid_vd_info { + __u8 name[32]; + __le16 id; + __u8 rg_id; + __u8 rg_level; + __u8 sg_num; + __u8 sg_disk_num; + __u8 vd_status; + __u8 vd_type; + __u8 rsvd1[4056]; +}; + +#define MAX_REALTIME_BGTASK_NUM 32 + +struct bgtask_info { + __u8 type; + __u8 progress; + __u8 rate; + __u8 rsvd0; + __le16 vd_id; + __le16 time_left; + __u8 rsvd1[4]; +}; + +struct spraid_bgtask { + __u8 sw; + __u8 task_num; + __u8 rsvd[6]; + struct bgtask_info bgtask[MAX_REALTIME_BGTASK_NUM]; +}; + struct spraid_dev_info { __le32 hdid; __le16 target; @@ -649,6 +734,11 @@ struct spraid_dev_list { struct spraid_sdev_hostdata { u32 hdid; + u16 max_io_kb; + u8 attr; + u8 flag; + u8 rg_id; + u8 rsvd[3]; }; #endif diff --git a/drivers/scsi/spraid/spraid_main.c b/drivers/scsi/spraid/spraid_main.c index a0a75ecb0027..86489164f672 100644 --- a/drivers/scsi/spraid/spraid_main.c +++ b/drivers/scsi/spraid/spraid_main.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -/* - * Linux spraid device driver - * Copyright(c) 2021 Ramaxel Memory Technology, Ltd - */ +/* Copyright(c) 2021 Ramaxel Memory Technology, Ltd */ + +/* Ramaxel Raid SPXXX Series Linux Driver */ + #define pr_fmt(fmt) "spraid: " fmt #include <linux/sched/signal.h> @@ -23,6 +23,8 @@ #include <linux/debugfs.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/blkdev.h> +#include <linux/bsg-lib.h> +#include <asm/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> @@ -30,6 +32,8 @@ #include <scsi/scsi_host.h> #include <scsi/scsi_transport.h> #include <scsi/scsi_dbg.h> +#include <scsi/sg.h> + #include "spraid.h" @@ -112,10 +116,10 @@ MODULE_PARM_DESC(small_pool_num, "set prp small pool num, default 4, MAX 16"); static void spraid_free_queue(struct spraid_queue *spraidq); static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result); -static void spraid_handle_aen_vs(struct spraid_dev *hdev, u32 result); +static void spraid_handle_aen_vs(struct spraid_dev *hdev, u32 result, u32 result1); static DEFINE_IDA(spraid_instance_ida); -static dev_t spraid_chr_devt; + static struct class *spraid_class; #define SPRAID_CAP_TIMEOUT_UNIT_MS (HZ / 2) @@ -147,6 +151,13 @@ enum FW_STAT_CODE { FW_STAT_NEED_RETRY }; +static const char * const raid_levels[] = {"0", "1", "5", "6", "10", "50", "60", "NA"}; + +static const char * const raid_states[] = { + "NA", "NORMAL", "FAULT", "DEGRADE", "NOT_FORMATTED", "FORMATTING", "SANITIZING", + "INITIALIZING", "INITIALIZE_FAIL", "DELETING", "DELETE_FAIL", "WRITE_PROTECT" +}; + static int ioq_depth_set(const char *val, const struct kernel_param *kp) { int n = 0; @@ -263,12 +274,6 @@ static int spraid_pci_enable(struct spraid_dev *hdev) return ret; } -static inline -struct spraid_admin_request *spraid_admin_req(struct request *req) -{ - return blk_mq_rq_to_pdu(req); -} - static int spraid_npages_prp(u32 size, struct spraid_dev *hdev) { u32 nprps = DIV_ROUND_UP(size + hdev->page_size, hdev->page_size); @@ -419,7 +424,7 @@ static void spraid_submit_cmd(struct spraid_queue *spraidq, const void *cmd) writel(spraidq->sq_tail, spraidq->q_db); spin_unlock_irqrestore(&spraidq->sq_lock, flags); - dev_log_dbg(spraidq->hdev->dev, "cid[%d], qid[%d], opcode[0x%x], flags[0x%x], hdid[%u]\n", + dev_log_dbg(spraidq->hdev->dev, "cid[%d] qid[%d], opcode[0x%x], flags[0x%x], hdid[%u]\n", acd->command_id, spraidq->qid, acd->opcode, acd->flags, le32_to_cpu(acd->hdid)); } @@ -814,7 +819,7 @@ static void spraid_map_status(struct spraid_iod *iod, struct scsi_cmnd *scmd, if (scmd->result & SAM_STAT_CHECK_CONDITION) { memset(scmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); memcpy(scmd->sense_buffer, iod->sense, SCSI_SENSE_BUFFERSIZE); - set_driver_byte(scmd, DRIVER_SENSE); + scmd->result = (scmd->result & 0x00ffffff) | (DRIVER_SENSE << 24); } break; case FW_STAT_ABORTED: @@ -850,14 +855,13 @@ static int spraid_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) int ret; if (unlikely(!scmd)) { - dev_err(hdev->dev, "err, scmd is null, return 0\n"); + dev_err(hdev->dev, "err, scmd is null\n"); return 0; } if (unlikely(hdev->state != SPRAID_LIVE)) { set_host_byte(scmd, DID_NO_CONNECT); scmd->scsi_done(scmd); - dev_err(hdev->dev, "[%s] err, hdev state is not live\n", __func__); return 0; } @@ -894,7 +898,7 @@ static int spraid_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) WRITE_ONCE(iod->state, SPRAID_CMD_IN_FLIGHT); spraid_submit_cmd(ioq, &ioq_cmd); elapsed = jiffies - scmd->jiffies_at_alloc; - dev_log_dbg(hdev->dev, "cid[%d], qid[%d] submit IO cost %3ld.%3ld seconds\n", + dev_log_dbg(hdev->dev, "cid[%d] qid[%d] submit IO cost %3ld.%3ld seconds\n", cid, hwq, elapsed / HZ, elapsed % HZ); return 0; @@ -945,6 +949,10 @@ static int spraid_slave_alloc(struct scsi_device *sdev) scan_host: hostdata->hdid = le32_to_cpu(hdev->devices[idx].hdid); + hostdata->max_io_kb = le16_to_cpu(hdev->devices[idx].max_io_kb); + hostdata->attr = hdev->devices[idx].attr; + hostdata->flag = hdev->devices[idx].flag; + hostdata->rg_id = 0xff; sdev->hostdata = hostdata; up_read(&hdev->devices_rwsem); return 0; @@ -964,7 +972,7 @@ static int spraid_slave_configure(struct scsi_device *sdev) struct spraid_sdev_hostdata *hostdata = sdev->hostdata; u32 max_sec = sdev->host->max_sectors; - if (!hostdata) { + if (hostdata) { idx = hostdata->hdid - 1; if (sdev->channel == hdev->devices[idx].channel && sdev->id == le16_to_cpu(hdev->devices[idx].target) && @@ -1176,6 +1184,75 @@ static inline bool spraid_cqe_pending(struct spraid_queue *spraidq) spraidq->cq_phase; } +static void spraid_sata_report_zone_handle(struct scsi_cmnd *scmd, struct spraid_iod *iod) +{ + int i = 0; + unsigned int bytes = 0; + struct scatterlist *sg = scsi_sglist(scmd); + + scsi_for_each_sg(scmd, sg, iod->nsge, i) { + unsigned int offset = 0; + + if (bytes == 0) { + char *hdr; + u32 list_length; + u64 max_lba, opt_lba; + u16 same; + + hdr = sg_virt(sg); + + list_length = get_unaligned_le32(&hdr[0]); + same = get_unaligned_le16(&hdr[4]); + max_lba = get_unaligned_le64(&hdr[8]); + opt_lba = get_unaligned_le64(&hdr[16]); + put_unaligned_be32(list_length, &hdr[0]); + hdr[4] = same & 0xf; + put_unaligned_be64(max_lba, &hdr[8]); + put_unaligned_be64(opt_lba, &hdr[16]); + offset += 64; + bytes += 64; + } + while (offset < sg_dma_len(sg)) { + char *rec; + u8 cond, type, non_seq, reset; + u64 size, start, wp; + + rec = sg_virt(sg) + offset; + type = rec[0] & 0xf; + cond = (rec[1] >> 4) & 0xf; + non_seq = (rec[1] & 2); + reset = (rec[1] & 1); + size = get_unaligned_le64(&rec[8]); + start = get_unaligned_le64(&rec[16]); + wp = get_unaligned_le64(&rec[24]); + rec[0] = type; + rec[1] = (cond << 4) | non_seq | reset; + put_unaligned_be64(size, &rec[8]); + put_unaligned_be64(start, &rec[16]); + put_unaligned_be64(wp, &rec[24]); + WARN_ON(offset + 64 > sg_dma_len(sg)); + offset += 64; + bytes += 64; + } + } +} + +static inline void spraid_handle_ata_cmd(struct spraid_dev *hdev, struct scsi_cmnd *scmd, + struct spraid_iod *iod) +{ + if (hdev->ctrl_info->card_type != SPRAID_CARD_HBA) + return; + + switch (scmd->cmnd[0]) { + case ZBC_IN: + dev_info(hdev->dev, "[%s] process report zone\n", __func__); + spraid_sata_report_zone_handle(scmd, iod); + break; + default: + break; + } +} + static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, struct spraid_completion *cqe) { struct spraid_dev *hdev = ioq->hdev; @@ -1197,12 +1274,12 @@ static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, struct spraid_com iod = scsi_cmd_priv(scmd); elapsed = jiffies - scmd->jiffies_at_alloc; - dev_log_dbg(hdev->dev, "cid[%d], qid[%d] finish IO cost %3ld.%3ld seconds\n", + dev_log_dbg(hdev->dev, "cid[%d] qid[%d] finish IO cost %3ld.%3ld seconds\n", cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); if (cmpxchg(&iod->state, SPRAID_CMD_IN_FLIGHT, SPRAID_CMD_COMPLETE) != SPRAID_CMD_IN_FLIGHT) { - dev_warn(hdev->dev, "cid[%d], qid[%d] enters abnormal handler, cost %3ld.%3ld seconds\n", + dev_warn(hdev->dev, "cid[%d] qid[%d] enters abnormal handler, cost %3ld.%3ld seconds\n", cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); WRITE_ONCE(iod->state, SPRAID_CMD_TMO_COMPLETE); @@ -1215,6 +1292,8 @@ static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, struct spraid_com return; } + spraid_handle_ata_cmd(hdev, scmd, iod); + spraid_map_status(iod, scmd, cqe); if (iod->nsge) { iod->nsge = 0; @@ -1224,38 +1303,36 @@ static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, struct spraid_com scmd->scsi_done(scmd); } -static inline void spraid_end_admin_request(struct request *req, __le16 status, - __le32 result0, __le32 result1) -{ - struct spraid_admin_request *rq = spraid_admin_req(req); - - rq->status = le16_to_cpu(status) >> 1; - rq->result0 = le32_to_cpu(result0); - rq->result1 = le32_to_cpu(result1); - blk_mq_complete_request(req); -} - static void spraid_complete_adminq_cmnd(struct spraid_queue *adminq, struct spraid_completion *cqe) { - struct blk_mq_tags *tags = adminq->hdev->admin_tagset.tags[0]; - struct request *req; + struct spraid_dev *hdev = adminq->hdev; + struct spraid_cmd *adm_cmd; - req = blk_mq_tag_to_rq(tags, cqe->cmd_id); - if (unlikely(!req)) { + adm_cmd = hdev->adm_cmds + cqe->cmd_id; + if (unlikely(adm_cmd->state == SPRAID_CMD_IDLE)) { dev_warn(adminq->hdev->dev, "Invalid id %d completed on queue %d\n", cqe->cmd_id, le16_to_cpu(cqe->sq_id)); return; } - spraid_end_admin_request(req, cqe->status, cqe->result, cqe->result1); + + adm_cmd->status = le16_to_cpu(cqe->status) >> 1; + adm_cmd->result0 = le32_to_cpu(cqe->result); + adm_cmd->result1 = le32_to_cpu(cqe->result1); + + complete(&adm_cmd->cmd_done); } +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid); + static void spraid_complete_aen(struct spraid_queue *spraidq, struct spraid_completion *cqe) { struct spraid_dev *hdev = spraidq->hdev; u32 result = le32_to_cpu(cqe->result); - dev_info(hdev->dev, "rcv aen, status[%x], result[%x]\n", - le16_to_cpu(cqe->status) >> 1, result); + dev_info(hdev->dev, "rcv aen, cid[%d], status[0x%x], result[0x%x]\n", + cqe->cmd_id, le16_to_cpu(cqe->status) >> 1, result); + + spraid_send_aen(hdev, cqe->cmd_id); if ((le16_to_cpu(cqe->status) >> 1) != SPRAID_SC_SUCCESS) return; @@ -1264,22 +1341,19 @@ static void spraid_complete_aen(struct spraid_queue *spraidq, struct spraid_comp spraid_handle_aen_notice(hdev, result); break; case SPRAID_AEN_VS: - spraid_handle_aen_vs(hdev, result); + spraid_handle_aen_vs(hdev, result, le32_to_cpu(cqe->result1)); break; default: dev_warn(hdev->dev, "Unsupported async event type: %u\n", result & 0x7); break; } - queue_work(spraid_wq, &hdev->aen_work); } -static void spraid_put_ioq_ptcmd(struct spraid_dev *hdev, struct spraid_ioq_ptcmd *cmd); - static void spraid_complete_ioq_sync_cmnd(struct spraid_queue *ioq, struct spraid_completion *cqe) { struct spraid_dev *hdev = ioq->hdev; - struct spraid_ioq_ptcmd *ptcmd; + struct spraid_cmd *ptcmd; ptcmd = hdev->ioq_ptcmds + (ioq->qid - 1) * SPRAID_PTCMDS_PERQ + cqe->cmd_id - SPRAID_IO_BLK_MQ_DEPTH; @@ -1289,8 +1363,6 @@ static void spraid_complete_ioq_sync_cmnd(struct spraid_queue *ioq, struct sprai ptcmd->result1 = le32_to_cpu(cqe->result1); complete(&ptcmd->cmd_done); - - spraid_put_ioq_ptcmd(hdev, ptcmd); } static inline void spraid_handle_cqe(struct spraid_queue *spraidq, u16 idx) @@ -1304,7 +1376,7 @@ static inline void spraid_handle_cqe(struct spraid_queue *spraidq, u16 idx) return; } - dev_log_dbg(hdev->dev, "cid[%d], qid[%d], result[0x%x], sq_id[%d], status[0x%x]\n", + dev_log_dbg(hdev->dev, "cid[%d] qid[%d], result[0x%x], sq_id[%d], status[0x%x]\n", cqe->cmd_id, spraidq->qid, le32_to_cpu(cqe->result), le16_to_cpu(cqe->sq_id), le16_to_cpu(cqe->status)); @@ -1452,62 +1524,117 @@ static u32 spraid_bar_size(struct spraid_dev *hdev, u32 nr_ioqs) return (SPRAID_REG_DBS + ((nr_ioqs + 1) * 8 * hdev->db_stride)); } -static inline void spraid_clear_spraid_request(struct request *req) +static int spraid_alloc_admin_cmds(struct spraid_dev *hdev) { - if (!(req->rq_flags & RQF_DONTPREP)) { - spraid_admin_req(req)->flags = 0; - req->rq_flags |= RQF_DONTPREP; + int i; + + INIT_LIST_HEAD(&hdev->adm_cmd_list); + spin_lock_init(&hdev->adm_cmd_lock); + + hdev->adm_cmds = kcalloc_node(SPRAID_AQ_BLK_MQ_DEPTH, sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); + + if (!hdev->adm_cmds) { + dev_err(hdev->dev, "Alloc admin cmds failed\n"); + return -ENOMEM; + } + + for (i = 0; i < SPRAID_AQ_BLK_MQ_DEPTH; i++) { + hdev->adm_cmds[i].qid = 0; + hdev->adm_cmds[i].cid = i; + list_add_tail(&(hdev->adm_cmds[i].list), &hdev->adm_cmd_list); } + + dev_info(hdev->dev, "Alloc admin cmds success, num[%d]\n", SPRAID_AQ_BLK_MQ_DEPTH); + + return 0; } -static struct request *spraid_alloc_admin_request(struct request_queue *q, - struct spraid_admin_command *cmd, - blk_mq_req_flags_t flags) +static void spraid_free_admin_cmds(struct spraid_dev *hdev) { - u32 op = COMMAND_IS_WRITE(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN; - struct request *req; + kfree(hdev->adm_cmds); + INIT_LIST_HEAD(&hdev->adm_cmd_list); +} - req = blk_mq_alloc_request(q, op, flags); - if (IS_ERR(req)) - return req; - req->cmd_flags |= REQ_FAILFAST_DRIVER; - spraid_clear_spraid_request(req); - spraid_admin_req(req)->cmd = cmd; +static struct spraid_cmd *spraid_get_cmd(struct spraid_dev *hdev, enum spraid_cmd_type type) +{ + struct spraid_cmd *cmd = NULL; + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; - return req; + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } + + spin_lock_irqsave(slock, flags); + if (list_empty(head)) { + spin_unlock_irqrestore(slock, flags); + dev_err(hdev->dev, "err, cmd[%d] list empty\n", type); + return NULL; + } + cmd = list_entry(head->next, struct spraid_cmd, list); + list_del_init(&cmd->list); + spin_unlock_irqrestore(slock, flags); + + WRITE_ONCE(cmd->state, SPRAID_CMD_IN_FLIGHT); + + return cmd; } -static int spraid_submit_admin_sync_cmd(struct request_queue *q, - struct spraid_admin_command *cmd, - u32 *result, void *buffer, - u32 bufflen, u32 timeout, int at_head, blk_mq_req_flags_t flags) +static void spraid_put_cmd(struct spraid_dev *hdev, struct spraid_cmd *cmd, + enum spraid_cmd_type type) { - struct request *req; - int ret; + unsigned long flags; + struct list_head *head = &hdev->adm_cmd_list; + spinlock_t *slock = &hdev->adm_cmd_lock; + + if (type == SPRAID_CMD_IOPT) { + head = &hdev->ioq_pt_list; + slock = &hdev->ioq_pt_lock; + } - req = spraid_alloc_admin_request(q, cmd, flags); - if (IS_ERR(req)) - return PTR_ERR(req); + spin_lock_irqsave(slock, flags); + WRITE_ONCE(cmd->state, SPRAID_CMD_IDLE); + list_add_tail(&cmd->list, head); + spin_unlock_irqrestore(slock, flags); +} - req->timeout = timeout ? timeout : ADMIN_TIMEOUT; - if (buffer && bufflen) { - ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL); - if (ret) - goto out; + +static int spraid_submit_admin_sync_cmd(struct spraid_dev *hdev, struct spraid_admin_command *cmd, + u32 *result0, u32 *result1, u32 timeout) +{ + struct spraid_cmd *adm_cmd = spraid_get_cmd(hdev, SPRAID_CMD_ADM); + + if (!adm_cmd) { + dev_err(hdev->dev, "err, get admin cmd failed\n"); + return -EFAULT; } - blk_execute_rq(req->q, NULL, req, at_head); - if (result) - *result = spraid_admin_req(req)->result0; + timeout = timeout ? timeout : ADMIN_TIMEOUT; - if (spraid_admin_req(req)->flags & SPRAID_REQ_CANCELLED) - ret = -EINTR; - else - ret = spraid_admin_req(req)->status; + init_completion(&adm_cmd->cmd_done); -out: - blk_mq_free_request(req); - return ret; + cmd->common.command_id = adm_cmd->cid; + spraid_submit_cmd(&hdev->queues[0], cmd); + + if (!wait_for_completion_timeout(&adm_cmd->cmd_done, timeout)) { + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout, opcode[0x%x] subopcode[0x%x]\n", + __func__, adm_cmd->cid, adm_cmd->qid, cmd->usr_cmd.opcode, + cmd->usr_cmd.info_0.subopcode); + WRITE_ONCE(adm_cmd->state, SPRAID_CMD_TIMEOUT); + return -EINVAL; + } + + if (result0) + *result0 = adm_cmd->result0; + if (result1) + *result1 = adm_cmd->result1; + + spraid_put_cmd(hdev, adm_cmd, SPRAID_CMD_ADM); + + return adm_cmd->status; } static int spraid_create_cq(struct spraid_dev *hdev, u16 qid, @@ -1524,8 +1651,7 @@ static int spraid_create_cq(struct spraid_dev *hdev, u16 qid, admin_cmd.create_cq.cq_flags = cpu_to_le16(flags); admin_cmd.create_cq.irq_vector = cpu_to_le16(cq_vector); - return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - NULL, 0, 0, 0, 0); + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); } static int spraid_create_sq(struct spraid_dev *hdev, u16 qid, @@ -1542,8 +1668,7 @@ static int spraid_create_sq(struct spraid_dev *hdev, u16 qid, admin_cmd.create_sq.sq_flags = cpu_to_le16(flags); admin_cmd.create_sq.cqid = cpu_to_le16(qid); - return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - NULL, 0, 0, 0, 0); + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); } static void spraid_free_queue(struct spraid_queue *spraidq) @@ -1581,8 +1706,7 @@ static int spraid_delete_queue(struct spraid_dev *hdev, u8 op, u16 id) admin_cmd.delete_queue.opcode = op; admin_cmd.delete_queue.qid = cpu_to_le16(id); - ret = spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - NULL, 0, 0, 0, 0); + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); if (ret) dev_err(hdev->dev, "Delete %s:[%d] failed\n", @@ -1663,19 +1787,28 @@ static int spraid_set_features(struct spraid_dev *hdev, u32 fid, u32 dword11, vo size_t buflen, u32 *result) { struct spraid_admin_command admin_cmd; - u32 res; int ret; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + + if (buffer && buflen) { + data_ptr = dma_alloc_coherent(hdev->dev, buflen, &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memcpy(data_ptr, buffer, buflen); + } memset(&admin_cmd, 0, sizeof(admin_cmd)); admin_cmd.features.opcode = SPRAID_ADMIN_SET_FEATURES; admin_cmd.features.fid = cpu_to_le32(fid); admin_cmd.features.dword11 = cpu_to_le32(dword11); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); - ret = spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, &res, - buffer, buflen, 0, 0, 0); + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, result, NULL, 0); - if (!ret && result) - *result = res; + if (data_ptr) + dma_free_coherent(hdev->dev, buflen, data_ptr, data_dma); return ret; } @@ -1764,8 +1897,7 @@ static int spraid_setup_io_queues(struct spraid_dev *hdev) break; } dev_info(hdev->dev, "[%s] max_qid: %d, queue_count: %d, online_queue: %d, ioq_depth: %d\n", - __func__, hdev->max_qid, hdev->queue_count, - hdev->online_queues, hdev->ioq_depth); + __func__, hdev->max_qid, hdev->queue_count, hdev->online_queues, hdev->ioq_depth); return spraid_create_io_queues(hdev); } @@ -1889,10 +2021,11 @@ static int spraid_get_dev_list(struct spraid_dev *hdev, struct spraid_dev_info * u32 nd = le32_to_cpu(hdev->ctrl_info->nd); struct spraid_admin_command admin_cmd; struct spraid_dev_list *list_buf; + dma_addr_t data_dma = 0; u32 i, idx, hdid, ndev; int ret = 0; - list_buf = kmalloc(sizeof(*list_buf), GFP_KERNEL); + list_buf = dma_alloc_coherent(hdev->dev, PAGE_SIZE, &data_dma, GFP_KERNEL); if (!list_buf) return -ENOMEM; @@ -1901,9 +2034,9 @@ static int spraid_get_dev_list(struct spraid_dev *hdev, struct spraid_dev_info * admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; admin_cmd.get_info.type = SPRAID_GET_INFO_DEV_LIST; admin_cmd.get_info.cdw11 = cpu_to_le32(idx); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); - ret = spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, list_buf, - sizeof(*list_buf), 0, 0, 0); + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); if (ret) { dev_err(hdev->dev, "Get device list failed, nd: %u, idx: %u, ret: %d\n", @@ -1916,12 +2049,11 @@ static int spraid_get_dev_list(struct spraid_dev *hdev, struct spraid_dev_info * for (i = 0; i < ndev; i++) { hdid = le32_to_cpu(list_buf->devices[i].hdid); - dev_info(hdev->dev, "list_buf->devices[%d], hdid: %u target: %d, channel: %d, lun: %d, attr[%x]\n", - i, hdid, - le16_to_cpu(list_buf->devices[i].target), - list_buf->devices[i].channel, - list_buf->devices[i].lun, - list_buf->devices[i].attr); + dev_info(hdev->dev, "list_buf->devices[%d], hdid: %u target: %d, channel: %d, lun: %d, attr[0x%x]\n", + i, hdid, le16_to_cpu(list_buf->devices[i].target), + list_buf->devices[i].channel, + list_buf->devices[i].lun, + list_buf->devices[i].attr); if (hdid > nd || hdid == 0) { dev_err(hdev->dev, "err, hdid[%d] invalid\n", hdid); continue; @@ -1936,21 +2068,29 @@ static int spraid_get_dev_list(struct spraid_dev *hdev, struct spraid_dev_info * } out: - kfree(list_buf); + dma_free_coherent(hdev->dev, PAGE_SIZE, list_buf, data_dma); return ret; } -static void spraid_send_aen(struct spraid_dev *hdev) +static void spraid_send_aen(struct spraid_dev *hdev, u16 cid) { struct spraid_queue *adminq = &hdev->queues[0]; struct spraid_admin_command admin_cmd; memset(&admin_cmd, 0, sizeof(admin_cmd)); admin_cmd.common.opcode = SPRAID_ADMIN_ASYNC_EVENT; - admin_cmd.common.command_id = SPRAID_AQ_BLK_MQ_DEPTH; + admin_cmd.common.command_id = cid; spraid_submit_cmd(adminq, &admin_cmd); - dev_info(hdev->dev, "send aen, cid[%d]\n", SPRAID_AQ_BLK_MQ_DEPTH); + dev_info(hdev->dev, "send aen, cid[%d]\n", cid); +} + +static inline void spraid_send_all_aen(struct spraid_dev *hdev) +{ + u16 i; + + for (i = 0; i < hdev->ctrl_info->aerl; i++) + spraid_send_aen(hdev, i + SPRAID_AQ_BLK_MQ_DEPTH); } static int spraid_add_device(struct spraid_dev *hdev, struct spraid_dev_info *device) @@ -1976,7 +2116,7 @@ static int spraid_rescan_device(struct spraid_dev *hdev, struct spraid_dev_info sdev = scsi_device_lookup(shost, device->channel, le16_to_cpu(device->target), 0); if (!sdev) { - dev_warn(hdev->dev, "Device is not exit, channel: %d, target_id: %d, lun: %d\n", + dev_warn(hdev->dev, "device is not exit rescan it, channel: %d, target_id: %d, lun: %d\n", device->channel, le16_to_cpu(device->target), 0); return -ENODEV; } @@ -1993,7 +2133,7 @@ static int spraid_remove_device(struct spraid_dev *hdev, struct spraid_dev_info sdev = scsi_device_lookup(shost, org_device->channel, le16_to_cpu(org_device->target), 0); if (!sdev) { - dev_warn(hdev->dev, "Device is not exit, channel: %d, target_id: %d, lun: %d\n", + dev_warn(hdev->dev, "device is not exit remove it, channel: %d, target_id: %d, lun: %d\n", org_device->channel, le16_to_cpu(org_device->target), 0); return -ENODEV; } @@ -2083,6 +2223,15 @@ static void spraid_timesyn_work(struct work_struct *work) spraid_configure_timestamp(hdev); } +static int spraid_init_ctrl_info(struct spraid_dev *hdev); +static void spraid_fw_act_work(struct work_struct *work) +{ + struct spraid_dev *hdev = container_of(work, struct spraid_dev, fw_act_work); + + if (spraid_init_ctrl_info(hdev)) + dev_err(hdev->dev, "get ctrl info failed after fw act\n"); +} + static void spraid_queue_scan(struct spraid_dev *hdev) { queue_work(spraid_wq, &hdev->scan_work); @@ -2094,6 +2243,9 @@ static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result) case SPRAID_AEN_DEV_CHANGED: spraid_queue_scan(hdev); break; + case SPRAID_AEN_FW_ACT_START: + dev_info(hdev->dev, "fw activation starting\n"); + break; case SPRAID_AEN_HOST_PROBING: break; default: @@ -2101,25 +2253,25 @@ static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result) } } -static void spraid_handle_aen_vs(struct spraid_dev *hdev, u32 result) +static void spraid_handle_aen_vs(struct spraid_dev *hdev, u32 result, u32 result1) { - switch (result) { + switch ((result & 0xff00) >> 8) { case SPRAID_AEN_TIMESYN: queue_work(spraid_wq, &hdev->timesyn_work); break; + case SPRAID_AEN_FW_ACT_FINISH: + dev_info(hdev->dev, "fw activation finish\n"); + queue_work(spraid_wq, &hdev->fw_act_work); + break; + case SPRAID_AEN_EVENT_MIN ... SPRAID_AEN_EVENT_MAX: + dev_info(hdev->dev, "rcv card event[%d], param1[0x%x] param2[0x%x]\n", + (result & 0xff00) >> 8, result, result1); + break; default: - dev_warn(hdev->dev, "async event result: %x\n", result); + dev_warn(hdev->dev, "async event result: 0x%x\n", result); } } -static void spraid_async_event_work(struct work_struct *work) -{ - struct spraid_dev *hdev = - container_of(work, struct spraid_dev, aen_work); - - spraid_send_aen(hdev); -} - static int spraid_alloc_resources(struct spraid_dev *hdev) { int ret, nqueue; @@ -2149,10 +2301,16 @@ static int spraid_alloc_resources(struct spraid_dev *hdev) goto destroy_dma_pools; } + ret = spraid_alloc_admin_cmds(hdev); + if (ret) + goto free_queues; + dev_info(hdev->dev, "[%s] queues num: %d\n", __func__, nqueue); return 0; +free_queues: + kfree(hdev->queues); destroy_dma_pools: spraid_destroy_dma_pools(hdev); free_ctrl_info: @@ -2164,50 +2322,18 @@ static int spraid_alloc_resources(struct spraid_dev *hdev) static void spraid_free_resources(struct spraid_dev *hdev) { + spraid_free_admin_cmds(hdev); kfree(hdev->queues); spraid_destroy_dma_pools(hdev); kfree(hdev->ctrl_info); ida_free(&spraid_instance_ida, hdev->instance); } -static void spraid_setup_passthrough(struct request *req, struct spraid_admin_command *cmd) -{ - memcpy(cmd, spraid_admin_req(req)->cmd, sizeof(*cmd)); - cmd->common.flags &= ~SPRAID_CMD_FLAG_SGL_ALL; -} - -static inline void spraid_clear_hreq(struct request *req) -{ - if (!(req->rq_flags & RQF_DONTPREP)) { - spraid_admin_req(req)->flags = 0; - req->rq_flags |= RQF_DONTPREP; - } -} - -static blk_status_t spraid_setup_admin_cmd(struct request *req, struct spraid_admin_command *cmd) +static void spraid_bsg_unmap_data(struct spraid_dev *hdev, struct bsg_job *job) { - spraid_clear_hreq(req); - - memset(cmd, 0, sizeof(*cmd)); - switch (req_op(req)) { - case REQ_OP_DRV_IN: - case REQ_OP_DRV_OUT: - spraid_setup_passthrough(req, cmd); - break; - default: - WARN_ON_ONCE(1); - return BLK_STS_IOERR; - } - - cmd->common.command_id = req->tag; - return BLK_STS_OK; -} - -static void spraid_unmap_data(struct spraid_dev *hdev, struct request *req) -{ - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - enum dma_data_direction dma_dir = rq_data_dir(req) ? - DMA_TO_DEVICE : DMA_FROM_DEVICE; + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; if (iod->nsge) dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); @@ -2215,36 +2341,36 @@ static void spraid_unmap_data(struct spraid_dev *hdev, struct request *req) spraid_free_iod_res(hdev, iod); } -static blk_status_t spraid_admin_map_data(struct spraid_dev *hdev, struct request *req, - struct spraid_admin_command *cmd) +static int spraid_bsg_map_data(struct spraid_dev *hdev, struct bsg_job *job, + struct spraid_admin_command *cmd) { - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - struct request_queue *admin_q = req->q; - enum dma_data_direction dma_dir = rq_data_dir(req) ? - DMA_TO_DEVICE : DMA_FROM_DEVICE; - blk_status_t ret = BLK_STS_IOERR; - int nr_mapped; - int res; + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_iod *iod = job->dd_data; + enum dma_data_direction dma_dir = rq_data_dir(rq) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + int ret = 0; + + iod->sg = job->request_payload.sg_list; + iod->nsge = job->request_payload.sg_cnt; + iod->length = job->request_payload.payload_len; + iod->use_sgl = false; + iod->npages = -1; + iod->sg_drv_mgmt = false; - sg_init_table(iod->sg, blk_rq_nr_phys_segments(req)); - iod->nsge = blk_rq_map_sg(admin_q, req, iod->sg); if (!iod->nsge) goto out; - dev_info(hdev->dev, "nseg: %u, nsge: %u\n", - blk_rq_nr_phys_segments(req), iod->nsge); - - ret = BLK_STS_RESOURCE; - nr_mapped = dma_map_sg_attrs(hdev->dev, iod->sg, iod->nsge, dma_dir, DMA_ATTR_NO_WARN); - if (!nr_mapped) + ret = dma_map_sg_attrs(hdev->dev, iod->sg, iod->nsge, dma_dir, DMA_ATTR_NO_WARN); + if (!ret) goto out; - res = spraid_setup_prps(hdev, iod); - if (res) + ret = spraid_setup_prps(hdev, iod); + if (ret) goto unmap; + cmd->common.dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg)); cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); - return BLK_STS_OK; + + return 0; unmap: dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); @@ -2252,137 +2378,29 @@ static blk_status_t spraid_admin_map_data(struct spraid_dev *hdev, struct reques return ret; } -static blk_status_t spraid_init_admin_iod(struct request *rq, struct spraid_dev *hdev) -{ - struct spraid_iod *iod = blk_mq_rq_to_pdu(rq); - int nents = blk_rq_nr_phys_segments(rq); - unsigned int size = blk_rq_payload_bytes(rq); - - if (nents > SPRAID_INT_PAGES || size > SPRAID_INT_BYTES(hdev)) { - iod->sg = mempool_alloc(hdev->iod_mempool, GFP_ATOMIC); - if (!iod->sg) - return BLK_STS_RESOURCE; - } else { - iod->sg = iod->inline_sg; - } - - iod->nsge = 0; - iod->use_sgl = false; - iod->npages = -1; - iod->length = size; - iod->sg_drv_mgmt = true; - - return BLK_STS_OK; -} - -static blk_status_t spraid_queue_admin_rq(struct blk_mq_hw_ctx *hctx, - const struct blk_mq_queue_data *bd) -{ - struct spraid_queue *adminq = hctx->driver_data; - struct spraid_dev *hdev = adminq->hdev; - struct request *req = bd->rq; - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - struct spraid_admin_command cmd; - blk_status_t ret; - - ret = spraid_setup_admin_cmd(req, &cmd); - if (ret) - goto out; - - ret = spraid_init_admin_iod(req, hdev); - if (ret) - goto out; - - if (blk_rq_nr_phys_segments(req)) { - ret = spraid_admin_map_data(hdev, req, &cmd); - if (ret) - goto cleanup_iod; - } - - blk_mq_start_request(req); - spraid_submit_cmd(adminq, &cmd); - return BLK_STS_OK; - -cleanup_iod: - spraid_free_iod_res(hdev, iod); -out: - return ret; -} - -static blk_status_t spraid_error_status(struct request *req) -{ - switch (spraid_admin_req(req)->status & 0x7ff) { - case SPRAID_SC_SUCCESS: - return BLK_STS_OK; - default: - return BLK_STS_IOERR; - } -} - -static void spraid_complete_admin_rq(struct request *req) -{ - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - struct spraid_dev *hdev = iod->spraidq->hdev; - - if (blk_rq_nr_phys_segments(req)) - spraid_unmap_data(hdev, req); - blk_mq_end_request(req, spraid_error_status(req)); -} - -static int spraid_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) -{ - struct spraid_dev *hdev = data; - struct spraid_queue *adminq = &hdev->queues[0]; - - WARN_ON(hctx_idx != 0); - WARN_ON(hdev->admin_tagset.tags[0] != hctx->tags); - - hctx->driver_data = adminq; - return 0; -} - -static int spraid_admin_init_request(struct blk_mq_tag_set *set, struct request *req, - unsigned int hctx_idx, unsigned int numa_node) -{ - struct spraid_dev *hdev = set->driver_data; - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - struct spraid_queue *adminq = &hdev->queues[0]; - - WARN_ON(!adminq); - iod->spraidq = adminq; - return 0; -} - -static enum blk_eh_timer_return -spraid_admin_timeout(struct request *req, bool reserved) -{ - struct spraid_iod *iod = blk_mq_rq_to_pdu(req); - struct spraid_queue *spraidq = iod->spraidq; - struct spraid_dev *hdev = spraidq->hdev; - - dev_err(hdev->dev, "Admin cid[%d] qid[%d] timeout\n", - req->tag, spraidq->qid); - - if (spraid_poll_cq(spraidq, req->tag)) { - dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, completion polled\n", - req->tag, spraidq->qid); - return BLK_EH_DONE; - } - - spraid_end_admin_request(req, cpu_to_le16(-EINVAL), 0, 0); - return BLK_EH_DONE; -} - static int spraid_get_ctrl_info(struct spraid_dev *hdev, struct spraid_ctrl_info *ctrl_info) { struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; memset(&admin_cmd, 0, sizeof(admin_cmd)); admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; admin_cmd.get_info.type = SPRAID_GET_INFO_CTRL; + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(ctrl_info, data_ptr, sizeof(struct spraid_ctrl_info)); - return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - ctrl_info, sizeof(struct spraid_ctrl_info), 0, 0, 0); + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; } static int spraid_init_ctrl_info(struct spraid_dev *hdev) @@ -2416,6 +2434,11 @@ static int spraid_init_ctrl_info(struct spraid_dev *hdev) dev_info(hdev->dev, "[%s]sn = %s\n", __func__, hdev->ctrl_info->sn); dev_info(hdev->dev, "[%s]fr = %s\n", __func__, hdev->ctrl_info->fr); + if (!hdev->ctrl_info->aerl) + hdev->ctrl_info->aerl = 1; + if (hdev->ctrl_info->aerl > SPRAID_NR_AEN_COMMANDS) + hdev->ctrl_info->aerl = SPRAID_NR_AEN_COMMANDS; + return 0; } @@ -2444,99 +2467,54 @@ static void spraid_free_iod_ext_mem_pool(struct spraid_dev *hdev) mempool_destroy(hdev->iod_mempool); } -static int spraid_submit_user_cmd(struct request_queue *q, struct spraid_admin_command *cmd, - void __user *ubuffer, unsigned int bufflen, u32 *result, - unsigned int timeout) +static int spraid_user_admin_cmd(struct spraid_dev *hdev, struct bsg_job *job) { - struct request *req; - struct bio *bio = NULL; - int ret; - - req = spraid_alloc_admin_request(q, cmd, 0); - if (IS_ERR(req)) - return PTR_ERR(req); - - req->timeout = timeout ? timeout : ADMIN_TIMEOUT; - spraid_admin_req(req)->flags |= SPRAID_REQ_USERCMD; - - if (ubuffer && bufflen) { - ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, GFP_KERNEL); - if (ret) - goto out; - bio = req->bio; - } - blk_execute_rq(req->q, NULL, req, 0); - if (spraid_admin_req(req)->flags & SPRAID_REQ_CANCELLED) - ret = -EINTR; - else - ret = spraid_admin_req(req)->status; - if (result) { - result[0] = spraid_admin_req(req)->result0; - result[1] = spraid_admin_req(req)->result1; - } - if (bio) - blk_rq_unmap_user(bio); -out: - blk_mq_free_request(req); - return ret; -} - -static int spraid_user_admin_cmd(struct spraid_dev *hdev, - struct spraid_passthru_common_cmd __user *ucmd) -{ - struct spraid_passthru_common_cmd cmd; + struct spraid_bsg_request *bsg_req = (struct spraid_bsg_request *)(job->request); + struct spraid_passthru_common_cmd *cmd = &(bsg_req->admcmd); struct spraid_admin_command admin_cmd; - u32 timeout = 0; + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); + u32 result[2] = {0}; int status; - if (!capable(CAP_SYS_ADMIN)) { - dev_err(hdev->dev, "Current user hasn't administrator right, reject service\n"); - return -EACCES; - } - - if (copy_from_user(&cmd, ucmd, sizeof(cmd))) { - dev_err(hdev->dev, "Copy command from user space to kernel space failed\n"); - return -EFAULT; - } - - if (cmd.flags) { - dev_err(hdev->dev, "Invalid flags in user command\n"); - return -EINVAL; + if (hdev->state >= SPRAID_RESETTING) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not right\n", __func__, + hdev->state); + return -EBUSY; } - dev_info(hdev->dev, "user_admin_cmd opcode: 0x%x, subopcode: 0x%x\n", - cmd.opcode, cmd.cdw2 & 0x7ff); + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init\n", + __func__, cmd->opcode, cmd->info_0.subopcode); memset(&admin_cmd, 0, sizeof(admin_cmd)); - admin_cmd.common.opcode = cmd.opcode; - admin_cmd.common.flags = cmd.flags; - admin_cmd.common.hdid = cpu_to_le32(cmd.nsid); - admin_cmd.common.cdw2[0] = cpu_to_le32(cmd.cdw2); - admin_cmd.common.cdw2[1] = cpu_to_le32(cmd.cdw3); - admin_cmd.common.cdw10 = cpu_to_le32(cmd.cdw10); - admin_cmd.common.cdw11 = cpu_to_le32(cmd.cdw11); - admin_cmd.common.cdw12 = cpu_to_le32(cmd.cdw12); - admin_cmd.common.cdw13 = cpu_to_le32(cmd.cdw13); - admin_cmd.common.cdw14 = cpu_to_le32(cmd.cdw14); - admin_cmd.common.cdw15 = cpu_to_le32(cmd.cdw15); - - if (cmd.timeout_ms) - timeout = msecs_to_jiffies(cmd.timeout_ms); - - status = spraid_submit_user_cmd(hdev->admin_q, &admin_cmd, - (void __user *)(uintptr_t)cmd.addr, cmd.info_1.data_len, - &cmd.result0, timeout); - - dev_info(hdev->dev, "user_admin_cmd status: 0x%x, result0: 0x%x, result1: 0x%x\n", - status, cmd.result0, cmd.result1); + admin_cmd.common.opcode = cmd->opcode; + admin_cmd.common.flags = cmd->flags; + admin_cmd.common.hdid = cpu_to_le32(cmd->nsid); + admin_cmd.common.cdw2[0] = cpu_to_le32(cmd->cdw2); + admin_cmd.common.cdw2[1] = cpu_to_le32(cmd->cdw3); + admin_cmd.common.cdw10 = cpu_to_le32(cmd->cdw10); + admin_cmd.common.cdw11 = cpu_to_le32(cmd->cdw11); + admin_cmd.common.cdw12 = cpu_to_le32(cmd->cdw12); + admin_cmd.common.cdw13 = cpu_to_le32(cmd->cdw13); + admin_cmd.common.cdw14 = cpu_to_le32(cmd->cdw14); + admin_cmd.common.cdw15 = cpu_to_le32(cmd->cdw15); + + status = spraid_bsg_map_data(hdev, job, &admin_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; + } + status = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, &result[0], &result[1], timeout); if (status >= 0) { - if (put_user(cmd.result0, &ucmd->result0)) - return -EFAULT; - if (put_user(cmd.result1, &ucmd->result1)) - return -EFAULT; + job->reply_len = sizeof(result); + memcpy(job->reply, result, sizeof(result)); } + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x], status[0x%x] result0[0x%x] result1[0x%x]\n", + __func__, cmd->opcode, cmd->info_0.subopcode, status, result[0], result[1]); + + spraid_bsg_unmap_data(hdev, job); + return status; } @@ -2548,8 +2526,8 @@ static int spraid_alloc_ioq_ptcmds(struct spraid_dev *hdev) INIT_LIST_HEAD(&hdev->ioq_pt_list); spin_lock_init(&hdev->ioq_pt_lock); - hdev->ioq_ptcmds = kcalloc_node(ptnum, sizeof(struct spraid_ioq_ptcmd), - GFP_KERNEL, hdev->numa_node); + hdev->ioq_ptcmds = kcalloc_node(ptnum, sizeof(struct spraid_cmd), + GFP_KERNEL, hdev->numa_node); if (!hdev->ioq_ptcmds) { dev_err(hdev->dev, "Alloc ioq_ptcmds failed\n"); @@ -2567,55 +2545,33 @@ static int spraid_alloc_ioq_ptcmds(struct spraid_dev *hdev) return 0; } -static struct spraid_ioq_ptcmd *spraid_get_ioq_ptcmd(struct spraid_dev *hdev) -{ - struct spraid_ioq_ptcmd *cmd = NULL; - unsigned long flags; - - spin_lock_irqsave(&hdev->ioq_pt_lock, flags); - if (list_empty(&hdev->ioq_pt_list)) { - spin_unlock_irqrestore(&hdev->ioq_pt_lock, flags); - dev_err(hdev->dev, "err, ioq ptcmd list empty\n"); - return NULL; - } - cmd = list_entry((&hdev->ioq_pt_list)->next, struct spraid_ioq_ptcmd, list); - list_del_init(&cmd->list); - spin_unlock_irqrestore(&hdev->ioq_pt_lock, flags); - - WRITE_ONCE(cmd->state, SPRAID_CMD_IDLE); - - return cmd; -} - -static void spraid_put_ioq_ptcmd(struct spraid_dev *hdev, struct spraid_ioq_ptcmd *cmd) +static void spraid_free_ioq_ptcmds(struct spraid_dev *hdev) { - unsigned long flags; - - spin_lock_irqsave(&hdev->ioq_pt_lock, flags); - list_add(&cmd->list, (&hdev->ioq_pt_list)->next); - spin_unlock_irqrestore(&hdev->ioq_pt_lock, flags); + kfree(hdev->ioq_ptcmds); + INIT_LIST_HEAD(&hdev->ioq_pt_list); } static int spraid_submit_ioq_sync_cmd(struct spraid_dev *hdev, struct spraid_ioq_command *cmd, - u32 *result, void **sense, u32 timeout) + u32 *result, u32 *reslen, u32 timeout) { - struct spraid_queue *ioq; int ret; dma_addr_t sense_dma; - struct spraid_ioq_ptcmd *pt_cmd = spraid_get_ioq_ptcmd(hdev); - - *sense = NULL; + struct spraid_queue *ioq; + void *sense_addr = NULL; + struct spraid_cmd *pt_cmd = spraid_get_cmd(hdev, SPRAID_CMD_IOPT); - if (!pt_cmd) + if (!pt_cmd) { + dev_err(hdev->dev, "err, get ioq cmd failed\n"); return -EFAULT; + } - dev_info(hdev->dev, "[%s] ptcmd, cid[%d], qid[%d]\n", __func__, pt_cmd->cid, pt_cmd->qid); + timeout = timeout ? timeout : ADMIN_TIMEOUT; init_completion(&pt_cmd->cmd_done); ioq = &hdev->queues[pt_cmd->qid]; ret = pt_cmd->cid * SCSI_SENSE_BUFFERSIZE; - pt_cmd->priv = ioq->sense + ret; + sense_addr = ioq->sense + ret; sense_dma = ioq->sense_dma_addr + ret; cmd->common.sense_addr = cpu_to_le64(sense_dma); @@ -2625,262 +2581,90 @@ static int spraid_submit_ioq_sync_cmd(struct spraid_dev *hdev, struct spraid_ioq spraid_submit_cmd(ioq, cmd); if (!wait_for_completion_timeout(&pt_cmd->cmd_done, timeout)) { - dev_err(hdev->dev, "[%s] cid[%d], qid[%d] timeout\n", - __func__, pt_cmd->cid, pt_cmd->qid); + dev_err(hdev->dev, "[%s] cid[%d] qid[%d] timeout, opcode[0x%x] subopcode[0x%x]\n", + __func__, pt_cmd->cid, pt_cmd->qid, cmd->common.opcode, + (le32_to_cpu(cmd->common.cdw3[0]) & 0xffff)); WRITE_ONCE(pt_cmd->state, SPRAID_CMD_TIMEOUT); return -EINVAL; } - if (result) { - result[0] = pt_cmd->result0; - result[1] = pt_cmd->result1; + if (result && reslen) { + if ((pt_cmd->status & 0x17f) == 0x101) { + memcpy(result, sense_addr, SCSI_SENSE_BUFFERSIZE); + *reslen = SCSI_SENSE_BUFFERSIZE; + } } - if ((pt_cmd->status & 0x17f) == 0x101) - *sense = pt_cmd->priv; + spraid_put_cmd(hdev, pt_cmd, SPRAID_CMD_IOPT); return pt_cmd->status; } -static int spraid_user_ioq_cmd(struct spraid_dev *hdev, - struct spraid_ioq_passthru_cmd __user *ucmd) +static int spraid_user_ioq_cmd(struct spraid_dev *hdev, struct bsg_job *job) { - struct spraid_ioq_passthru_cmd cmd; + struct spraid_bsg_request *bsg_req = (struct spraid_bsg_request *)(job->request); + struct spraid_ioq_passthru_cmd *cmd = &(bsg_req->ioqcmd); struct spraid_ioq_command ioq_cmd; - u32 timeout = 0; int status = 0; - u8 *data_ptr = NULL; - dma_addr_t data_dma; - enum dma_data_direction dma_dir = DMA_NONE; - void *sense = NULL; - - if (!capable(CAP_SYS_ADMIN)) { - dev_err(hdev->dev, "Current user hasn't administrator right, reject service\n"); - return -EACCES; - } - - if (copy_from_user(&cmd, ucmd, sizeof(cmd))) { - dev_err(hdev->dev, "Copy command from user space to kernel space failed\n"); - return -EFAULT; - } + u32 timeout = msecs_to_jiffies(cmd->timeout_ms); - if (cmd.data_len > PAGE_SIZE) { + if (cmd->data_len > PAGE_SIZE) { dev_err(hdev->dev, "[%s] data len bigger than 4k\n", __func__); return -EFAULT; } - dev_info(hdev->dev, "[%s] opcode: 0x%x, subopcode: 0x%x, datalen: %d\n", - __func__, cmd.opcode, cmd.info_1.subopcode, cmd.data_len); - - if (cmd.addr && cmd.data_len) { - data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, &data_dma, GFP_KERNEL); - if (!data_ptr) - return -ENOMEM; - - dma_dir = (cmd.opcode & 1) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + if (hdev->state != SPRAID_LIVE) { + dev_err(hdev->dev, "[%s] err, host state:[%d] is not live\n", __func__, + hdev->state); + return -EBUSY; } - if (dma_dir == DMA_TO_DEVICE) { - if (copy_from_user(data_ptr, (void __user *)(uintptr_t)cmd.addr, cmd.data_len)) { - dev_err(hdev->dev, "[%s] copy user data failed\n", __func__); - status = -EFAULT; - goto free_dma_mem; - } - } + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x] init, datalen[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, cmd->data_len); memset(&ioq_cmd, 0, sizeof(ioq_cmd)); - ioq_cmd.common.opcode = cmd.opcode; - ioq_cmd.common.flags = cmd.flags; - ioq_cmd.common.hdid = cpu_to_le32(cmd.nsid); - ioq_cmd.common.sense_len = cpu_to_le16(cmd.info_0.res_sense_len); - ioq_cmd.common.cdb_len = cmd.info_0.cdb_len; - ioq_cmd.common.rsvd2 = cmd.info_0.rsvd0; - ioq_cmd.common.cdw3[0] = cpu_to_le32(cmd.cdw3); - ioq_cmd.common.cdw3[1] = cpu_to_le32(cmd.cdw4); - ioq_cmd.common.cdw3[2] = cpu_to_le32(cmd.cdw5); - ioq_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); - - ioq_cmd.common.cdw10[0] = cpu_to_le32(cmd.cdw10); - ioq_cmd.common.cdw10[1] = cpu_to_le32(cmd.cdw11); - ioq_cmd.common.cdw10[2] = cpu_to_le32(cmd.cdw12); - ioq_cmd.common.cdw10[3] = cpu_to_le32(cmd.cdw13); - ioq_cmd.common.cdw10[4] = cpu_to_le32(cmd.cdw14); - ioq_cmd.common.cdw10[5] = cpu_to_le32(cmd.data_len); - - memcpy(ioq_cmd.common.cdb, &cmd.cdw16, cmd.info_0.cdb_len); - - ioq_cmd.common.cdw26[0] = cpu_to_le32(cmd.cdw26[0]); - ioq_cmd.common.cdw26[1] = cpu_to_le32(cmd.cdw26[1]); - ioq_cmd.common.cdw26[2] = cpu_to_le32(cmd.cdw26[2]); - ioq_cmd.common.cdw26[3] = cpu_to_le32(cmd.cdw26[3]); - - if (cmd.timeout_ms) - timeout = msecs_to_jiffies(cmd.timeout_ms); - timeout = timeout ? timeout : ADMIN_TIMEOUT; - - status = spraid_submit_ioq_sync_cmd(hdev, &ioq_cmd, &cmd.result0, &sense, timeout); - - if (status >= 0) { - if (put_user(cmd.result0, &ucmd->result0)) { - status = -EFAULT; - goto free_dma_mem; - } - if (put_user(cmd.result1, &ucmd->result1)) { - status = -EFAULT; - goto free_dma_mem; - } - if (dma_dir == DMA_FROM_DEVICE && - copy_to_user((void __user *)(uintptr_t)cmd.addr, data_ptr, cmd.data_len)) { - status = -EFAULT; - goto free_dma_mem; - } + ioq_cmd.common.opcode = cmd->opcode; + ioq_cmd.common.flags = cmd->flags; + ioq_cmd.common.hdid = cpu_to_le32(cmd->nsid); + ioq_cmd.common.sense_len = cpu_to_le16(cmd->info_0.res_sense_len); + ioq_cmd.common.cdb_len = cmd->info_0.cdb_len; + ioq_cmd.common.rsvd2 = cmd->info_0.rsvd0; + ioq_cmd.common.cdw3[0] = cpu_to_le32(cmd->cdw3); + ioq_cmd.common.cdw3[1] = cpu_to_le32(cmd->cdw4); + ioq_cmd.common.cdw3[2] = cpu_to_le32(cmd->cdw5); + + ioq_cmd.common.cdw10[0] = cpu_to_le32(cmd->cdw10); + ioq_cmd.common.cdw10[1] = cpu_to_le32(cmd->cdw11); + ioq_cmd.common.cdw10[2] = cpu_to_le32(cmd->cdw12); + ioq_cmd.common.cdw10[3] = cpu_to_le32(cmd->cdw13); + ioq_cmd.common.cdw10[4] = cpu_to_le32(cmd->cdw14); + ioq_cmd.common.cdw10[5] = cpu_to_le32(cmd->data_len); + + memcpy(ioq_cmd.common.cdb, &cmd->cdw16, cmd->info_0.cdb_len); + + ioq_cmd.common.cdw26[0] = cpu_to_le32(cmd->cdw26[0]); + ioq_cmd.common.cdw26[1] = cpu_to_le32(cmd->cdw26[1]); + ioq_cmd.common.cdw26[2] = cpu_to_le32(cmd->cdw26[2]); + ioq_cmd.common.cdw26[3] = cpu_to_le32(cmd->cdw26[3]); + + status = spraid_bsg_map_data(hdev, job, (struct spraid_admin_command *)&ioq_cmd); + if (status) { + dev_err(hdev->dev, "[%s] err, map data failed\n", __func__); + return status; } - if (sense) { - if (copy_to_user((void *__user *)(uintptr_t)cmd.sense_addr, - sense, cmd.info_0.res_sense_len)) { - status = -EFAULT; - goto free_dma_mem; - } - } + status = spraid_submit_ioq_sync_cmd(hdev, &ioq_cmd, job->reply, &job->reply_len, timeout); -free_dma_mem: - if (data_ptr) - dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + dev_info(hdev->dev, "[%s] opcode[0x%x] subopcode[0x%x], status[0x%x] reply_len[%d]\n", + __func__, cmd->opcode, cmd->info_1.subopcode, status, job->reply_len); - return status; + spraid_bsg_unmap_data(hdev, job); + return status; } static int spraid_reset_work_sync(struct spraid_dev *hdev); -static int spraid_user_reset_cmd(struct spraid_dev *hdev) -{ - int ret; - - dev_info(hdev->dev, "[%s] start user reset cmd\n", __func__); - ret = spraid_reset_work_sync(hdev); - dev_info(hdev->dev, "[%s] stop user reset cmd[%d]\n", __func__, ret); - - return ret; -} - -static int hdev_open(struct inode *inode, struct file *file) -{ - struct spraid_dev *hdev = - container_of(inode->i_cdev, struct spraid_dev, cdev); - file->private_data = hdev; - return 0; -} - -static long hdev_ioctl(struct file *file, u32 cmd, unsigned long arg) -{ - struct spraid_dev *hdev = file->private_data; - void __user *argp = (void __user *)arg; - - switch (cmd) { - case SPRAID_IOCTL_ADMIN_CMD: - return spraid_user_admin_cmd(hdev, argp); - case SPRAID_IOCTL_IOQ_CMD: - return spraid_user_ioq_cmd(hdev, argp); - case SPRAID_IOCTL_RESET_CMD: - return spraid_user_reset_cmd(hdev); - default: - return -ENOTTY; - } -} - -static const struct file_operations spraid_dev_fops = { - .owner = THIS_MODULE, - .open = hdev_open, - .unlocked_ioctl = hdev_ioctl, - .compat_ioctl = hdev_ioctl, -}; - -static int spraid_create_cdev(struct spraid_dev *hdev) -{ - int ret; - - device_initialize(&hdev->ctrl_device); - hdev->ctrl_device.devt = MKDEV(MAJOR(spraid_chr_devt), hdev->instance); - hdev->ctrl_device.class = spraid_class; - hdev->ctrl_device.parent = hdev->dev; - dev_set_drvdata(&hdev->ctrl_device, hdev); - ret = dev_set_name(&hdev->ctrl_device, "spraid%d", hdev->instance); - if (ret) - return ret; - cdev_init(&hdev->cdev, &spraid_dev_fops); - hdev->cdev.owner = THIS_MODULE; - ret = cdev_device_add(&hdev->cdev, &hdev->ctrl_device); - if (ret) { - dev_err(hdev->dev, "Add cdev failed, ret: %d", ret); - put_device(&hdev->ctrl_device); - kfree_const(hdev->ctrl_device.kobj.name); - return ret; - } - - return 0; -} - -static inline void spraid_remove_cdev(struct spraid_dev *hdev) -{ - cdev_device_del(&hdev->cdev, &hdev->ctrl_device); -} - -static const struct blk_mq_ops spraid_admin_mq_ops = { - .queue_rq = spraid_queue_admin_rq, - .complete = spraid_complete_admin_rq, - .init_hctx = spraid_admin_init_hctx, - .init_request = spraid_admin_init_request, - .timeout = spraid_admin_timeout, -}; - -static void spraid_remove_admin_tagset(struct spraid_dev *hdev) -{ - if (hdev->admin_q && !blk_queue_dying(hdev->admin_q)) { - blk_mq_unquiesce_queue(hdev->admin_q); - blk_cleanup_queue(hdev->admin_q); - blk_mq_free_tag_set(&hdev->admin_tagset); - } -} - -static int spraid_alloc_admin_tags(struct spraid_dev *hdev) -{ - if (!hdev->admin_q) { - hdev->admin_tagset.ops = &spraid_admin_mq_ops; - hdev->admin_tagset.nr_hw_queues = 1; - - hdev->admin_tagset.queue_depth = SPRAID_AQ_MQ_TAG_DEPTH; - hdev->admin_tagset.timeout = ADMIN_TIMEOUT; - hdev->admin_tagset.numa_node = hdev->numa_node; - hdev->admin_tagset.cmd_size = - spraid_cmd_size(hdev, true, false); - hdev->admin_tagset.flags = BLK_MQ_F_NO_SCHED; - hdev->admin_tagset.driver_data = hdev; - - if (blk_mq_alloc_tag_set(&hdev->admin_tagset)) { - dev_err(hdev->dev, "Allocate admin tagset failed\n"); - return -ENOMEM; - } - - hdev->admin_q = blk_mq_init_queue(&hdev->admin_tagset); - if (IS_ERR(hdev->admin_q)) { - dev_err(hdev->dev, "Initialize admin request queue failed\n"); - blk_mq_free_tag_set(&hdev->admin_tagset); - return -ENOMEM; - } - if (!blk_get_queue(hdev->admin_q)) { - dev_err(hdev->dev, "Get admin request queue failed\n"); - spraid_remove_admin_tagset(hdev); - hdev->admin_q = NULL; - return -ENODEV; - } - } else { - blk_mq_unquiesce_queue(hdev->admin_q); - } - return 0; -} - static bool spraid_check_scmd_completed(struct scsi_cmnd *scmd) { struct spraid_dev *hdev = shost_priv(scmd->device->host); @@ -2891,7 +2675,7 @@ static bool spraid_check_scmd_completed(struct scsi_cmnd *scmd) spraid_get_tag_from_scmd(scmd, &hwq, &cid); spraidq = &hdev->queues[hwq]; if (READ_ONCE(iod->state) == SPRAID_CMD_COMPLETE || spraid_poll_cq(spraidq, cid)) { - dev_warn(hdev->dev, "cid[%d], qid[%d] has been completed\n", + dev_warn(hdev->dev, "cid[%d] qid[%d] has been completed\n", cid, spraidq->qid); return true; } @@ -2927,8 +2711,7 @@ static int spraid_send_abort_cmd(struct spraid_dev *hdev, u32 hdid, u16 qid, u16 admin_cmd.abort.sqid = cpu_to_le16(qid); admin_cmd.abort.cid = cpu_to_le16(cid); - return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - NULL, 0, 0, 0, 0); + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); } /* send reset command by admin quueue temporary */ @@ -2941,8 +2724,7 @@ static int spraid_send_reset_cmd(struct spraid_dev *hdev, int type, u32 hdid) admin_cmd.reset.hdid = cpu_to_le32(hdid); admin_cmd.reset.type = type; - return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, - NULL, 0, 0, 0, 0); + return spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); } static bool spraid_change_host_state(struct spraid_dev *hdev, enum spraid_state newstate) @@ -3022,7 +2804,7 @@ static void spraid_back_fault_cqe(struct spraid_queue *ioq, struct spraid_comple scsi_dma_unmap(scmd); spraid_free_iod_res(hdev, iod); scmd->scsi_done(scmd); - dev_warn(hdev->dev, "Back fault CQE, cid[%d], qid[%d]\n", + dev_warn(hdev->dev, "Back fault CQE, cid[%d] qid[%d]\n", cqe->cmd_id, ioq->qid); } @@ -3106,17 +2888,13 @@ static void spraid_reset_work(struct work_struct *work) if (ret) goto pci_disable; - ret = spraid_alloc_admin_tags(hdev); - if (ret) - goto pci_disable; - ret = spraid_setup_io_queues(hdev); if (ret || hdev->online_queues <= hdev->shost->nr_hw_queues) goto pci_disable; spraid_change_host_state(hdev, SPRAID_LIVE); - spraid_send_aen(hdev); + spraid_send_all_aen(hdev); return; @@ -3288,6 +3066,62 @@ static int spraid_shost_reset_handler(struct scsi_cmnd *scmd) return SUCCESS; } +static pci_ers_result_t spraid_pci_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter pci error detect, state:%d\n", state); + + switch (state) { + case pci_channel_io_normal: + dev_warn(hdev->dev, "channel is normal, do nothing\n"); + + return PCI_ERS_RESULT_CAN_RECOVER; + case pci_channel_io_frozen: + dev_warn(hdev->dev, "channel io frozen, need reset controller\n"); + + scsi_block_requests(hdev->shost); + + spraid_change_host_state(hdev, SPRAID_RESETTING); + + return PCI_ERS_RESULT_NEED_RESET; + case pci_channel_io_perm_failure: + dev_warn(hdev->dev, "channel io failure, request disconnect\n"); + + return PCI_ERS_RESULT_DISCONNECT; + } + + return PCI_ERS_RESULT_NEED_RESET; +} + +static pci_ers_result_t spraid_pci_slot_reset(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "restart after slot reset\n"); + + pci_restore_state(pdev); + + if (!queue_work(spraid_wq, &hdev->reset_work)) { + dev_err(hdev->dev, "[%s] err, the device is resetting state\n", __func__); + return PCI_ERS_RESULT_NONE; + } + + flush_work(&hdev->reset_work); + + scsi_unblock_requests(hdev->shost); + + return PCI_ERS_RESULT_RECOVERED; +} + +static void spraid_reset_done(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + dev_info(hdev->dev, "enter spraid reset done\n"); +} + static ssize_t csts_pp_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct Scsi_Host *shost = class_to_shost(cdev); @@ -3347,7 +3181,7 @@ static ssize_t fw_version_show(struct device *cdev, struct device_attribute *att struct Scsi_Host *shost = class_to_shost(cdev); struct spraid_dev *hdev = shost_priv(shost); - return snprintf(buf, sizeof(hdev->ctrl_info->fr), "%s\n", hdev->ctrl_info->fr); + return snprintf(buf, PAGE_SIZE, "%s\n", hdev->ctrl_info->fr); } static DEVICE_ATTR_RO(csts_pp); @@ -3365,6 +3199,173 @@ static struct device_attribute *spraid_host_attrs[] = { NULL, }; +static int spraid_get_vd_info(struct spraid_dev *hdev, struct spraid_vd_info *vd_info, u16 vid) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_VDINFO); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.usr_cmd.info_1.param_len = cpu_to_le16(VDINFO_PARAM_LEN); + admin_cmd.usr_cmd.cdw10 = cpu_to_le32(vid); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(vd_info, data_ptr, sizeof(struct spraid_vd_info)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static int spraid_get_bgtask(struct spraid_dev *hdev, struct spraid_bgtask *bgtask) +{ + struct spraid_admin_command admin_cmd; + u8 *data_ptr = NULL; + dma_addr_t data_dma = 0; + int ret; + + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.usr_cmd.opcode = USR_CMD_READ; + admin_cmd.usr_cmd.info_0.subopcode = cpu_to_le16(USR_CMD_BGTASK); + admin_cmd.usr_cmd.info_1.data_len = cpu_to_le16(USR_CMD_RDLEN); + admin_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ret = spraid_submit_admin_sync_cmd(hdev, &admin_cmd, NULL, NULL, 0); + if (!ret) + memcpy(bgtask, data_ptr, sizeof(struct spraid_bgtask)); + + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return ret; +} + +static ssize_t raid_level_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + vd_info->rg_level = ARRAY_SIZE(raid_levels) - 1; + + ret = (vd_info->rg_level < ARRAY_SIZE(raid_levels)) ? + vd_info->rg_level : (ARRAY_SIZE(raid_levels) - 1); + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "RAID-%s\n", raid_levels[ret]); +} + +static ssize_t raid_state_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_sdev_hostdata *hostdata; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) { + vd_info->vd_status = 0; + vd_info->rg_id = 0xff; + } + + ret = (vd_info->vd_status < ARRAY_SIZE(raid_states)) ? vd_info->vd_status : 0; + + kfree(vd_info); + + return snprintf(buf, PAGE_SIZE, "%s\n", raid_states[ret]); +} + +static ssize_t raid_resync_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev; + struct spraid_dev *hdev; + struct spraid_vd_info *vd_info; + struct spraid_bgtask *bgtask; + struct spraid_sdev_hostdata *hostdata; + u8 rg_id, i, progress = 0; + int ret; + + sdev = to_scsi_device(dev); + hdev = shost_priv(sdev->host); + hostdata = sdev->hostdata; + + vd_info = kmalloc(sizeof(*vd_info), GFP_KERNEL); + if (!vd_info || !SPRAID_DEV_INFO_ATTR_VD(hostdata->attr)) + return snprintf(buf, PAGE_SIZE, "NA\n"); + + ret = spraid_get_vd_info(hdev, vd_info, sdev->id); + if (ret) + goto out; + + rg_id = vd_info->rg_id; + + bgtask = (struct spraid_bgtask *)vd_info; + ret = spraid_get_bgtask(hdev, bgtask); + if (ret) + goto out; + for (i = 0; i < bgtask->task_num; i++) { + if ((bgtask->bgtask[i].type == BGTASK_TYPE_REBUILD) && + (le16_to_cpu(bgtask->bgtask[i].vd_id) == rg_id)) + progress = bgtask->bgtask[i].progress; + } + +out: + kfree(vd_info); + return snprintf(buf, PAGE_SIZE, "%d\n", progress); +} + +static DEVICE_ATTR_RO(raid_level); +static DEVICE_ATTR_RO(raid_state); +static DEVICE_ATTR_RO(raid_resync); + +static struct device_attribute *spraid_dev_attrs[] = { + &dev_attr_raid_level, + &dev_attr_raid_state, + &dev_attr_raid_resync, + NULL, +}; + +static struct pci_error_handlers spraid_err_handler = { + .error_detected = spraid_pci_error_detected, + .slot_reset = spraid_pci_slot_reset, + .reset_done = spraid_reset_done, +}; + static struct scsi_host_template spraid_driver_template = { .module = THIS_MODULE, .name = "Ramaxel Logic spraid driver", @@ -3379,9 +3380,10 @@ static struct scsi_host_template spraid_driver_template = { .eh_bus_reset_handler = spraid_bus_reset_handler, .eh_host_reset_handler = spraid_shost_reset_handler, .change_queue_depth = scsi_change_queue_depth, - .host_tagset = 1, + .host_tagset = 0, .this_id = -1, .shost_attrs = spraid_host_attrs, + .sdev_attrs = spraid_dev_attrs, }; static void spraid_shutdown(struct pci_dev *pdev) @@ -3392,11 +3394,50 @@ static void spraid_shutdown(struct pci_dev *pdev) spraid_disable_admin_queue(hdev, true); } +/* bsg dispatch user command */ +static int spraid_bsg_host_dispatch(struct bsg_job *job) +{ + struct Scsi_Host *shost = dev_to_shost(job->dev); + struct spraid_dev *hdev = shost_priv(shost); + struct request *rq = blk_mq_rq_from_pdu(job); + struct spraid_bsg_request *bsg_req = (struct spraid_bsg_request *)(job->request); + int ret = 0; + + dev_info(hdev->dev, "[%s] msgcode[%d], msglen[%d], timeout[%d], req_nsge[%d], req_len[%d]\n", + __func__, bsg_req->msgcode, job->request_len, rq->timeout, + job->request_payload.sg_cnt, job->request_payload.payload_len); + + job->reply_len = 0; + + switch (bsg_req->msgcode) { + case SPRAID_BSG_ADM: + ret = spraid_user_admin_cmd(hdev, job); + break; + case SPRAID_BSG_IOQ: + ret = spraid_user_ioq_cmd(hdev, job); + break; + default: + dev_info(hdev->dev, "[%s] unsupport msgcode[%d]\n", __func__, bsg_req->msgcode); + break; + } + + bsg_job_done(job, ret, 0); + return 0; +} + +static inline void spraid_remove_bsg(struct spraid_dev *hdev) +{ + if (hdev->bsg_queue) { + bsg_unregister_queue(hdev->bsg_queue); + blk_cleanup_queue(hdev->bsg_queue); + } +} static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct spraid_dev *hdev; struct Scsi_Host *shost; int node, ret; + char bsg_name[15]; shost = scsi_host_alloc(&spraid_driver_template, sizeof(*hdev)); if (!shost) { @@ -3421,10 +3462,10 @@ static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto put_dev; init_rwsem(&hdev->devices_rwsem); - INIT_WORK(&hdev->aen_work, spraid_async_event_work); INIT_WORK(&hdev->scan_work, spraid_scan_work); INIT_WORK(&hdev->timesyn_work, spraid_timesyn_work); INIT_WORK(&hdev->reset_work, spraid_reset_work); + INIT_WORK(&hdev->fw_act_work, spraid_fw_act_work); spin_lock_init(&hdev->state_lock); ret = spraid_alloc_resources(hdev); @@ -3439,17 +3480,13 @@ static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) goto pci_disable; - ret = spraid_alloc_admin_tags(hdev); - if (ret) - goto disable_admin_q; - ret = spraid_init_ctrl_info(hdev); if (ret) - goto free_admin_tagset; + goto disable_admin_q; ret = spraid_alloc_iod_ext_mem_pool(hdev); if (ret) - goto free_admin_tagset; + goto disable_admin_q; ret = spraid_setup_io_queues(hdev); if (ret) @@ -3464,9 +3501,14 @@ static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto remove_io_queues; } - ret = spraid_create_cdev(hdev); - if (ret) + snprintf(bsg_name, sizeof(bsg_name), "spraid%d", shost->host_no); + hdev->bsg_queue = bsg_setup_queue(&shost->shost_gendev, bsg_name, spraid_bsg_host_dispatch, + NULL, spraid_cmd_size(hdev, true, false)); + if (IS_ERR(hdev->bsg_queue)) { + dev_err(hdev->dev, "err, setup bsg failed\n"); + hdev->bsg_queue = NULL; goto remove_io_queues; + } if (hdev->online_queues == SPRAID_ADMIN_QUEUE_NUM) { dev_warn(hdev->dev, "warn only admin queue can be used\n"); @@ -3475,11 +3517,11 @@ static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) hdev->state = SPRAID_LIVE; - spraid_send_aen(hdev); + spraid_send_all_aen(hdev); ret = spraid_dev_list_init(hdev); if (ret) - goto remove_cdev; + goto remove_bsg; ret = spraid_configure_timestamp(hdev); if (ret) @@ -3487,20 +3529,18 @@ static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = spraid_alloc_ioq_ptcmds(hdev); if (ret) - goto remove_cdev; + goto remove_bsg; scsi_scan_host(hdev->shost); return 0; -remove_cdev: - spraid_remove_cdev(hdev); +remove_bsg: + spraid_remove_bsg(hdev); remove_io_queues: spraid_remove_io_queues(hdev); free_iod_mempool: spraid_free_iod_ext_mem_pool(hdev); -free_admin_tagset: - spraid_remove_admin_tagset(hdev); disable_admin_q: spraid_disable_admin_queue(hdev, false); pci_disable: @@ -3532,14 +3572,12 @@ static void spraid_remove(struct pci_dev *pdev) } flush_work(&hdev->reset_work); + spraid_remove_bsg(hdev); scsi_remove_host(shost); - - kfree(hdev->ioq_ptcmds); + spraid_free_ioq_ptcmds(hdev); kfree(hdev->devices); - spraid_remove_cdev(hdev); spraid_remove_io_queues(hdev); spraid_free_iod_ext_mem_pool(hdev); - spraid_remove_admin_tagset(hdev); spraid_disable_admin_queue(hdev, false); spraid_pci_disable(hdev); spraid_free_resources(hdev); @@ -3551,7 +3589,7 @@ static void spraid_remove(struct pci_dev *pdev) } static const struct pci_device_id spraid_id_table[] = { - { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, SPRAID_SERVER_DEVICE_HAB_DID) }, + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, SPRAID_SERVER_DEVICE_HBA_DID) }, { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, SPRAID_SERVER_DEVICE_RAID_DID) }, { 0, } }; @@ -3563,6 +3601,7 @@ static struct pci_driver spraid_driver = { .probe = spraid_probe, .remove = spraid_remove, .shutdown = spraid_shutdown, + .err_handler = &spraid_err_handler, }; static int __init spraid_init(void) @@ -3573,14 +3612,10 @@ static int __init spraid_init(void) if (!spraid_wq) return -ENOMEM; - ret = alloc_chrdev_region(&spraid_chr_devt, 0, SPRAID_MINORS, "spraid"); - if (ret < 0) - goto destroy_wq; - spraid_class = class_create(THIS_MODULE, "spraid"); if (IS_ERR(spraid_class)) { ret = PTR_ERR(spraid_class); - goto unregister_chrdev; + goto destroy_wq; } ret = pci_register_driver(&spraid_driver); @@ -3591,8 +3626,6 @@ static int __init spraid_init(void) destroy_class: class_destroy(spraid_class); -unregister_chrdev: - unregister_chrdev_region(spraid_chr_devt, SPRAID_MINORS); destroy_wq: destroy_workqueue(spraid_wq); @@ -3603,12 +3636,11 @@ static void __exit spraid_exit(void) { pci_unregister_driver(&spraid_driver); class_destroy(spraid_class); - unregister_chrdev_region(spraid_chr_devt, SPRAID_MINORS); destroy_workqueue(spraid_wq); ida_destroy(&spraid_instance_ida); } -MODULE_AUTHOR("Ramaxel Memory Technology"); +MODULE_AUTHOR("songyl(a)ramaxel.com"); MODULE_DESCRIPTION("Ramaxel Memory Technology SPraid Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(SPRAID_DRV_VERSION); -- 2.27.0

1 0

Re: [PATCH openEuler-1.0-LTS 1/1] ras: report cpu logical index to userspace in arm event
by Xie XiuQi 25 Nov '21

25 Nov '21

Hi，这个补丁在 openEuler 20.03 有合入吗？修改 trace 格式相当于是修改ABI了，为避免与上层应用，如rasdaemon 等存在兼容性问题，这个在之前版本也是修改过吗？还有，这个如果是为了增加 cpu logical index，是不是看一看推一下上游社区，免得每个版本都 port 这个补丁。 On 2021/11/25 15:30, lostway(a)zju.edu.cn wrote: > From: Lostwayzxc <luoshengwei(a)huawei.com> > > kunpeng inclusion > category: feature > bugzilla: https://gitee.com/openeuler/kernel/issues/I4IG00?from=project-issue > CVE: NA > > When the arm event is reported, the rasdaemon needs to know the cpu logical index, > but there is only mpidr without mapping between it and cpu logical index. Since the > kernel has saved the mapping, get the logical index by function get_logical_index() > and report it directly to userspace via perf i/f. > > Signed-off-by: Shengwei Luo <luoshengwei(a)huawei.com> > --- > drivers/ras/ras.c | 8 +++++++- > include/linux/ras.h | 11 +++++++++++ > include/ras/ras_event.h | 10 +++++++--- > 3 files changed, 25 insertions(+), 4 deletions(-) > > diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c > index 9302ed7f4258..a526f124a5ff 100644 > --- a/drivers/ras/ras.c > +++ b/drivers/ras/ras.c > @@ -32,6 +32,7 @@ void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev) > struct cper_arm_err_info *err_info; > struct cper_arm_ctx_info *ctx_info; > int n, sz; > + int cpu; > > pei_len = sizeof(struct cper_arm_err_info) * err->err_info_num; > pei_err = (u8 *)err + sizeof(struct cper_sec_proc_arm); > @@ -58,8 +59,13 @@ void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev) > } > ven_err_data = (u8 *)ctx_info; > > + cpu = GET_LOGICAL_INDEX(err->mpidr); > + /* when the return value is invalid, set cpu index to a large integer */ > + if (cpu < 0) > + cpu = 0xFFFF; > + > trace_arm_event(err, pei_err, pei_len, ctx_err, ctx_len, > - ven_err_data, vsei_len, sev); > + ven_err_data, vsei_len, sev, cpu); > } > > static int __init ras_init(void) > diff --git a/include/linux/ras.h b/include/linux/ras.h > index 3431b4a5fa42..e5ec31ad7a13 100644 > --- a/include/linux/ras.h > +++ b/include/linux/ras.h > @@ -40,4 +40,15 @@ static inline void > log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev) { return; } > #endif > > +#if defined(CONFIG_ARM) || defined(CONFIG_ARM64) > +#include <asm/smp_plat.h> > +/* > + * Include ARM specific SMP header which provides a function mapping mpidr to > + * cpu logical index. > + */ > +#define GET_LOGICAL_INDEX(mpidr) get_logical_index(mpidr & MPIDR_HWID_BITMASK) > +#else > +#define GET_LOGICAL_INDEX(mpidr) -EINVAL > +#endif /* CONFIG_ARM || CONFIG_ARM64 */ > + > #endif /* __RAS_H__ */ > diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h > index 7c8cb123ba32..2d6a662886e6 100644 > --- a/include/ras/ras_event.h > +++ b/include/ras/ras_event.h > @@ -182,9 +182,10 @@ TRACE_EVENT(arm_event, > const u32 ctx_len, > const u8 *oem, > const u32 oem_len, > - u8 sev), > + u8 sev, > + int cpu), > > - TP_ARGS(proc, pei_err, pei_len, ctx_err, ctx_len, oem, oem_len, sev), > + TP_ARGS(proc, pei_err, pei_len, ctx_err, ctx_len, oem, oem_len, sev, cpu), > > TP_STRUCT__entry( > __field(u64, mpidr) > @@ -199,6 +200,7 @@ TRACE_EVENT(arm_event, > __field(u32, oem_len) > __dynamic_array(u8, buf2, oem_len) > __field(u8, sev) > + __field(int, cpu) > ), > > TP_fast_assign( > @@ -225,11 +227,13 @@ TRACE_EVENT(arm_event, > __entry->oem_len = oem_len; > memcpy(__get_dynamic_array(buf2), oem, oem_len); > __entry->sev = sev; > + __entry->cpu = cpu; > ), > > - TP_printk("error: %d; affinity level: %d; MPIDR: %016llx; MIDR: %016llx; " > + TP_printk("cpu: %d; error: %d; affinity level: %d; MPIDR: %016llx; MIDR: %016llx; " > "running state: %d; PSCI state: %d; " > "%s: %d; %s: %s; %s: %d; %s: %s; %s: %d; %s: %s", > + __entry->cpu, > __entry->sev, > __entry->affinity, __entry->mpidr, __entry->midr, > __entry->running_state, __entry->psci_state, >

1 0

Re: 我是普华操作系统的杨嫣，想加入openEuler的kernel sig组
by Xie XiuQi 24 Nov '21

24 Nov '21

你好，欢迎参与 openEuler kernel。 kernel sig 例会是隔周的周五下午。下次会议时间是 12月3号（下周五）下午2:10~4:00. 你可以订阅一下 kernel(a)openeuler.org 和 kernel-discuss(a)openeuer.org. 可以直接发邮件报议题。 On 2021/11/24 13:11, yan.yang(a)i-soft.com.cn wrote: > 您好， > > 我是普华基础软件的杨嫣，负责跟踪OpenEuler的内核新动向，想参加贵司的kernel sig组的会议，但是看网页上没有写具体会议时间，及参会方式，麻烦您告知一下，我要怎么参与到SIG组的会议中，感谢！ > > ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ > > */Best Regards/* > > 杨嫣* * > > > > 地址：北京市朝阳区容达路7号院（太极信息产业园）E座3层 > > 邮编：100102 > > 电话（Tel）: +86 10 8406 5566-8102 > > 传真（Fax）：+86 10 8496 6005 > > 手机（Mobile）: +86 158 1062 8953 > > 网站（Web）: www.i-soft.com.cn <http://www.i-soft.com.cn/> >

1 0

[PATCH openEuler-1.0-LTS] lib/clear_user: ensure loop in __arch_clear_user cache-aligned v2
by Yang Yingliang 24 Nov '21

24 Nov '21

From: Cheng Jian <cj.chengjian(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I3OX0C CVE: NA -------------------------------- We must ensure that the following four instructions are cache-aligned. Otherwise, it will cause problems with the performance of libMicro pread. 1: # uao_user_alternative 9f, str, sttr, xzr, x0, 8 str xzr, [x0], #8 nop subs x1, x1, #8 b.pl 1b with this patch: prc thr usecs/call samples errors cnt/samp size pread_z100 1 1 5.88400 807 0 1 102400 The result of pread can range from 5 to 9 depending on the alignment performance of this function. Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/lib/clear_user.S | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 9ebc5d84e6154..410768a8d4166 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -20,7 +20,7 @@ #include <asm/asm-uaccess.h> .text - .align 6 + /* Prototype: int __arch_clear_user(void *addr, size_t sz) * Purpose : clear some user memory * Params : addr - user memory address to clear @@ -34,6 +34,9 @@ ENTRY(__arch_clear_user) mov x2, x1 // save the size for fixup return subs x1, x1, #8 b.mi 2f +#ifdef CONFIG_ARCH_HISI + .align 5 +#endif 1: uao_user_alternative 9f, str, sttr, xzr, x0, 8 subs x1, x1, #8 -- 2.25.1

1 0