May 2022 - Linux-stable-mirror

[PATCH] ftrace: clean up hash direct_functions on register failures

by Song Liu

We see the following GPF when register_ftrace_direct fails: [ ] general protection fault, probably for non-canonical address \ 0x200000000000010: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI [...] [ ] RIP: 0010:ftrace_find_rec_direct+0x53/0x70 [ ] Code: 48 c1 e0 03 48 03 42 08 48 8b 10 31 c0 48 85 d2 74 [...] [ ] RSP: 0018:ffffc9000138bc10 EFLAGS: 00010206 [ ] RAX: 0000000000000000 RBX: ffffffff813e0df0 RCX: 000000000000003b [ ] RDX: 0200000000000000 RSI: 000000000000000c RDI: ffffffff813e0df0 [ ] RBP: ffffffffa00a3000 R08: ffffffff81180ce0 R09: 0000000000000001 [ ] R10: ffffc9000138bc18 R11: 0000000000000001 R12: ffffffff813e0df0 [ ] R13: ffffffff813e0df0 R14: ffff888171b56400 R15: 0000000000000000 [ ] FS: 00007fa9420c7780(0000) GS:ffff888ff6a00000(0000) knlGS:000000000 [ ] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ ] CR2: 000000000770d000 CR3: 0000000107d50003 CR4: 0000000000370ee0 [ ] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ ] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ ] Call Trace: [ ] <TASK> [ ] register_ftrace_direct+0x54/0x290 [ ] ? render_sigset_t+0xa0/0xa0 [ ] bpf_trampoline_update+0x3f5/0x4a0 [ ] ? 0xffffffffa00a3000 [ ] bpf_trampoline_link_prog+0xa9/0x140 [ ] bpf_tracing_prog_attach+0x1dc/0x450 [ ] bpf_raw_tracepoint_open+0x9a/0x1e0 [ ] ? find_held_lock+0x2d/0x90 [ ] ? lock_release+0x150/0x430 [ ] __sys_bpf+0xbd6/0x2700 [ ] ? lock_is_held_type+0xd8/0x130 [ ] __x64_sys_bpf+0x1c/0x20 [ ] do_syscall_64+0x3a/0x80 [ ] entry_SYSCALL_64_after_hwframe+0x44/0xae [ ] RIP: 0033:0x7fa9421defa9 [ ] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 9 f8 [...] [ ] RSP: 002b:00007ffed743bd78 EFLAGS: 00000246 ORIG_RAX: 0000000000000141 [ ] RAX: ffffffffffffffda RBX: 00000000069d2480 RCX: 00007fa9421defa9 [ ] RDX: 0000000000000078 RSI: 00007ffed743bd80 RDI: 0000000000000011 [ ] RBP: 00007ffed743be00 R08: 0000000000bb7270 R09: 0000000000000000 [ ] R10: 00000000069da210 R11: 0000000000000246 R12: 0000000000000001 [ ] R13: 00007ffed743c4b0 R14: 00000000069d2480 R15: 0000000000000001 [ ] </TASK> [ ] Modules linked in: klp_vm(OK) [ ] ---[ end trace 0000000000000000 ]--- One way to trigger this is: 1. load a livepatch that patches kernel function xxx; 2. run bpftrace -e 'kfunc:xxx {}', this will fail (expected for now); 3. repeat #2 => gpf. This is because the entry is added to direct_functions, but not removed. Fix this by remove the entry from direct_functions when register_ftrace_direct fails. Also remove the last trailing space from ftrace.c, so we don't have to worry about it anymore. Cc: stable(a)vger.kernel.org Fixes: 763e34e74bb7 ("ftrace: Add register_ftrace_direct()") Signed-off-by: Song Liu <song(a)kernel.org> --- kernel/trace/ftrace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4f1d2f5e7263..375293c5f3e9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4465,7 +4465,7 @@ int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper, * @ip: The instruction pointer address to remove the data from * * Returns the data if it is found, otherwise NULL. - * Note, if the data pointer is used as the data itself, (see + * Note, if the data pointer is used as the data itself, (see * ftrace_func_mapper_find_ip(), then the return value may be meaningless, * if the data pointer was set to zero. */ @@ -5200,8 +5200,10 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) if (!ret && !(direct_ops.flags & FTRACE_OPS_FL_ENABLED)) { ret = register_ftrace_function(&direct_ops); - if (ret) + if (ret) { ftrace_set_filter_ip(&direct_ops, ip, 1, 0); + remove_hash_entry(direct_functions, entry); + } } if (ret) { -- 2.30.2

3 years, 1 month

3
5
0 0

[PATCH] x86, kvm: use correct GFP flags for preemption disabled

by Paolo Bonzini

Commit ddd7ed842627 ("x86/kvm: Alloc dummy async #PF token outside of raw spinlock") leads to the following Smatch static checker warning: arch/x86/kernel/kvm.c:212 kvm_async_pf_task_wake() warn: sleeping in atomic context arch/x86/kernel/kvm.c 202 raw_spin_lock(&b->lock); 203 n = _find_apf_task(b, token); 204 if (!n) { 205 /* 206 * Async #PF not yet handled, add a dummy entry for the token. 207 * Allocating the token must be down outside of the raw lock 208 * as the allocator is preemptible on PREEMPT_RT kernels. 209 */ 210 if (!dummy) { 211 raw_spin_unlock(&b->lock); --> 212 dummy = kzalloc(sizeof(*dummy), GFP_KERNEL); ^^^^^^^^^^ Smatch thinks the caller has preempt disabled. The `smdb.py preempt kvm_async_pf_task_wake` output call tree is: sysvec_kvm_asyncpf_interrupt() <- disables preempt -> __sysvec_kvm_asyncpf_interrupt() -> kvm_async_pf_task_wake() The caller is this: arch/x86/kernel/kvm.c 290 DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt) 291 { 292 struct pt_regs *old_regs = set_irq_regs(regs); 293 u32 token; 294 295 ack_APIC_irq(); 296 297 inc_irq_stat(irq_hv_callback_count); 298 299 if (__this_cpu_read(apf_reason.enabled)) { 300 token = __this_cpu_read(apf_reason.token); 301 kvm_async_pf_task_wake(token); 302 __this_cpu_write(apf_reason.token, 0); 303 wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1); 304 } 305 306 set_irq_regs(old_regs); 307 } The DEFINE_IDTENTRY_SYSVEC() is a wrapper that calls this function from the call_on_irqstack_cond(). It's inside the call_on_irqstack_cond() where preempt is disabled (unless it's already disabled). The irq_enter/exit_rcu() functions disable/enable preempt. Reported-by: Dan Carpenter <dan.carpenter(a)oracle.com> Cc: stable(a)vger.kernel.org Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> --- arch/x86/kernel/kvm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 35b3c5836703..1a3658f7e6d9 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -209,7 +209,7 @@ void kvm_async_pf_task_wake(u32 token) */ if (!dummy) { raw_spin_unlock(&b->lock); - dummy = kzalloc(sizeof(*dummy), GFP_KERNEL); + dummy = kzalloc(sizeof(*dummy), GFP_ATOMIC); /* * Continue looping on allocation failure, eventually -- 2.31.1

3 years, 1 month

1
0
0 0

Hola

by andrea mamon

Querido amigo , Mucho tiempo, espero que todo esté bien junto con su familia, si es así, gloria a Dios Todopoderoso. Bueno, lamento escuchar esta noticia y entender que la culpa no es mía. Me complace informarles sobre mi éxito en la transferencia de esos fondos bajo la cooperación de un nuevo socio de EE. UU. Actualmente estoy en EE. UU. para recibir tratamiento mientras tanto, no olvidé sus esfuerzos pasados ??e intentos de obtener los fondos a pesar de que nos falló de alguna manera. Ahora comuníquese con mi pastor mientras estaba en Togo. Dejé $ 500,000.00 para usted. como su propia parte para compensar sus esfuerzos de entrada durante la transacción sin importar que falle debido a su falta de comprensión. Nombre: Pastora María Antonio Dirección: 55 avenida slyvanus olympio Correo electrónico: chika_abarla2008(a)yahoo.com Pídale que le envíe la cantidad total de $ 500,000.00 dólares estadounidenses que dejé como compensación por todos los esfuerzos e intentos anteriores para ayudarme en este asunto. Aprecié mucho sus esfuerzos en ese momento. Así que siéntase libre y póngase en contacto con ellos e indíqueles cómo desea recibir su parte. Por favor, avísame de inmediato si recibes tu parte para que podamos compartir la alegría juntos después de todos los sufrimientos en ese momento, está bien. En este momento, estoy muy ocupado con mi tratamiento y mi salud. Así que no dude en ponerse en contacto con mi pastor hoy de inmediato para reclamar. tu fondo Gracias de nuevo y que Dios los bendiga. Saludos, señora andrea mamón

3 years, 1 month

1
0
0 0

[RESEND][PATCH] KVM: PPC: Book3S HV: fix incorrect NULL check on list iterator

by Xiaomeng Tong

The bug is here: if (!p) return ret; The list iterator value 'p' will *always* be set and non-NULL by list_for_each_entry(), so it is incorrect to assume that the iterator value will be NULL if the list is empty or no element is found. To fix the bug, Use a new value 'iter' as the list iterator, while use the old value 'p' as a dedicated variable to point to the found element. Cc: stable(a)vger.kernel.org Fixes: dfaa973ae9605 ("KVM: PPC: Book3S HV: In H_SVM_INIT_DONE, migrate remaining normal-GFNs to secure-GFNs") Signed-off-by: Xiaomeng Tong <xiam0nd.tong(a)gmail.com> --- arch/powerpc/kvm/book3s_hv_uvmem.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index e414ca44839f..0cb20ee6a632 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -360,13 +360,15 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm, static bool kvmppc_next_nontransitioned_gfn(const struct kvm_memory_slot *memslot, struct kvm *kvm, unsigned long *gfn) { - struct kvmppc_uvmem_slot *p; + struct kvmppc_uvmem_slot *p = NULL, *iter; bool ret = false; unsigned long i; - list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) - if (*gfn >= p->base_pfn && *gfn < p->base_pfn + p->nr_pfns) + list_for_each_entry(iter, &kvm->arch.uvmem_pfns, list) + if (*gfn >= iter->base_pfn && *gfn < iter->base_pfn + iter->nr_pfns) { + p = iter; break; + } if (!p) return ret; /* -- 2.17.1

3 years, 1 month

2
1
0 0

[PATCH RESEND] KVM: powerpc: remove extraneous asterisk from rm_host_ipi_action comment

by Bagas Sanjaya

kernel test robot reported kernel-doc warning for rm_host_ipi_action(): >> arch/powerpc/kvm/book3s_hv_rm_xics.c:887: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Host Operations poked by RM KVM Since the function is static, remove the extraneous (second) asterisk at the head of function comment. Fixes: 0c2a66062470cd ("KVM: PPC: Book3S HV: Host side kick VCPU when poked by real-mode KVM") Link: https://lore.kernel.org/linux-doc/202204252334.Cd2IsiII-lkp@intel.com/ Reported-by: kernel test robot <lkp(a)intel.com> Cc: Suresh Warrier <warrier(a)linux.vnet.ibm.com> Cc: Paul Mackerras <paulus(a)samba.org> Cc: Anders Roxell <anders.roxell(a)linaro.org> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Benjamin Herrenschmidt <benh(a)kernel.crashing.org> Cc: Nicholas Piggin <npiggin(a)gmail.com> Cc: Fabiano Rosas <farosas(a)linux.ibm.com> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Alexey Kardashevskiy <aik(a)ozlabs.ru> Cc: linuxppc-dev(a)lists.ozlabs.org Cc: kvm(a)vger.kernel.org Cc: stable(a)vger.kernel.org # v5.15, v5.17 Cc: linux-kernel(a)vger.kernel.org Signed-off-by: Bagas Sanjaya <bagasdotme(a)gmail.com> --- arch/powerpc/kvm/book3s_hv_rm_xics.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index 587c33fc45640f..6e16bd751c8423 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -883,7 +883,7 @@ long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, /* --- Non-real mode XICS-related built-in routines --- */ -/** +/* * Host Operations poked by RM KVM */ static void rm_host_ipi_action(int action, void *data) base-commit: a7391ad3572431a354c927cf8896e86e50d7d0bf -- An old man doll... just what I always wanted! - Clara

3 years, 1 month

3
2
0 0

Gooday my beloved,

by Jackie James

Hello my dear, I sent this mail praying it will get to you in a good condition of health, since I myself are in a very critical health condition in which I sleep every night without knowing if I may be alive to see the next day. I bring peace and love to you. It is by the grace of God, I had no choice than to do what is lawful and right in the sight of God for eternal life and in the sight of man, for witness of God’s mercy and glory upon my life,I am Mrs,Jackie Grayson,a widow.I am suffering from a long time brain tumor, It has defiled all forms of medical treatment, and right now I have about a few months to leave, according to medical experts. The situation has gotten complicated recently with my inability to hear proper, am communicating with you with the help of the chief nurse herein the hospital, from all indication my conditions is really deteriorating and it is quite obvious that, according to my doctors they have advised me that I may not live too long, Because this illness has gotten to a very bad stage. I plead that you will not expose or betray this trust and confidence that I am about to repose on you for the mutual benefit of the orphans and the less privilege. I have some funds I inherited from my late husband, the sum of ($11,500,000.00 Dollars).Having known my condition, I decided to donate this fund to you believing that you will utilize it the way i am going to instruct herein. I need you to assist me and reclaim this money and use it for Charity works, for orphanages and gives justice and help to the poor, needy and widows says The Lord." Jeremiah 22:15-16.“ and also build schools for less privilege that will be named after my late husband if possible and to promote the word of God and the effort that the house of God is maintained. I do not want a situation where this money will be used in an ungodly manner. That's why I'm taking this decision. I'm not afraid of death, so I know where I'm going. I accept this decision because I do not have any child who will inherit this money after I die. Please I want your sincerely and urgent answer to know if you will be able to execute this project for the glory of God, and I will give you more information on how the fund will be transferred to your bank account. May the grace, peace, love and the truth in the Word of God be with you and all those that you love and care for. I'm waiting for your immediate reply, Respectfully, Mrs,Jackie Grayson. Writting From the hospital, May God Bless you,

3 years, 1 month

1
0
0 0

[PATCH 4/4] bcache: avoid journal no-space deadlock by reserving 1 journal bucket

by Coly Li

The journal no-space deadlock was reported time to time. Such deadlock can happen in the following situation. When all journal buckets are fully filled by active jset with heavy write I/O load, the cache set registration (after a reboot) will load all active jsets and inserting them into the btree again (which is called journal replay). If a journaled bkey is inserted into a btree node and results btree node split, new journal request might be triggered. For example, the btree grows one more level after the node split, then the root node record in cache device super block will be upgrade by bch_journal_meta() from bch_btree_set_root(). But there is no space in journal buckets, the journal replay has to wait for new journal bucket to be reclaimed after at least one journal bucket replayed. This is one example that how the journal no-space deadlock happens. The solution to avoid the deadlock is to reserve 1 journal bucket in run time, and only permit the reserved journal bucket to be used during cache set registration procedure for things like journal replay. Then the journal space will never be fully filled, there is no chance for journal no-space deadlock to happen anymore. This patch adds a new member "bool do_reserve" in struct journal, it is inititalized to 0 (false) when struct journal is allocated, and set to 1 (true) by bch_journal_space_reserve() when all initialization done in run_cache_set(). In the run time when journal_reclaim() tries to allocate a new journal bucket, free_journal_buckets() is called to check whether there are enough free journal buckets to use. If there is only 1 free journal bucket and journal->do_reserve is 1 (true), the last bucket is reserved and free_journal_buckets() will return 0 to indicate no free journal bucket. Then journal_reclaim() will give up, and try next time to see whetheer there is free journal bucket to allocate. By this method, there is always 1 jouranl bucket reserved in run time. During the cache set registration, journal->do_reserve is 0 (false), so the reserved journal bucket can be used to avoid the no-space deadlock. Reported-by: Nikhil Kshirsagar <nkshirsagar(a)gmail.com> Signed-off-by: Coly Li <colyli(a)suse.de> Cc: stable(a)vger.kernel.org --- drivers/md/bcache/journal.c | 31 ++++++++++++++++++++++++++----- drivers/md/bcache/journal.h | 2 ++ drivers/md/bcache/super.c | 1 + 3 files changed, 29 insertions(+), 5 deletions(-) diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index df5347ea450b..e5da469a4235 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -405,6 +405,11 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list) return ret; } +void bch_journal_space_reserve(struct journal *j) +{ + j->do_reserve = true; +} + /* Journalling */ static void btree_flush_write(struct cache_set *c) @@ -621,12 +626,30 @@ static void do_journal_discard(struct cache *ca) } } +static unsigned int free_journal_buckets(struct cache_set *c) +{ + struct journal *j = &c->journal; + struct cache *ca = c->cache; + struct journal_device *ja = &c->cache->journal; + unsigned int n; + + /* In case njournal_buckets is not power of 2 */ + if (ja->cur_idx >= ja->discard_idx) + n = ca->sb.njournal_buckets + ja->discard_idx - ja->cur_idx; + else + n = ja->discard_idx - ja->cur_idx; + + if (n > (1 + j->do_reserve)) + return n - (1 + j->do_reserve); + + return 0; +} + static void journal_reclaim(struct cache_set *c) { struct bkey *k = &c->journal.key; struct cache *ca = c->cache; uint64_t last_seq; - unsigned int next; struct journal_device *ja = &ca->journal; atomic_t p __maybe_unused; @@ -649,12 +672,10 @@ static void journal_reclaim(struct cache_set *c) if (c->journal.blocks_free) goto out; - next = (ja->cur_idx + 1) % ca->sb.njournal_buckets; - /* No space available on this device */ - if (next == ja->discard_idx) + if (!free_journal_buckets(c)) goto out; - ja->cur_idx = next; + ja->cur_idx = (ja->cur_idx + 1) % ca->sb.njournal_buckets; k->ptr[0] = MAKE_PTR(0, bucket_to_sector(c, ca->sb.d[ja->cur_idx]), ca->sb.nr_this_dev); diff --git a/drivers/md/bcache/journal.h b/drivers/md/bcache/journal.h index f2ea34d5f431..cd316b4a1e95 100644 --- a/drivers/md/bcache/journal.h +++ b/drivers/md/bcache/journal.h @@ -105,6 +105,7 @@ struct journal { spinlock_t lock; spinlock_t flush_write_lock; bool btree_flushing; + bool do_reserve; /* used when waiting because the journal was full */ struct closure_waitlist wait; struct closure io; @@ -182,5 +183,6 @@ int bch_journal_replay(struct cache_set *c, struct list_head *list); void bch_journal_free(struct cache_set *c); int bch_journal_alloc(struct cache_set *c); +void bch_journal_space_reserve(struct journal *j); #endif /* _BCACHE_JOURNAL_H */ diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index bf3de149d3c9..2bb55278d22d 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -2128,6 +2128,7 @@ static int run_cache_set(struct cache_set *c) flash_devs_run(c); + bch_journal_space_reserve(&c->journal); set_bit(CACHE_SET_RUNNING, &c->flags); return 0; err: -- 2.35.3

3 years, 1 month

1
0
0 0

[PATCH 3/4] bcache: remove incremental dirty sector counting for bch_sectors_dirty_init()

by Coly Li

After making bch_sectors_dirty_init() being multithreaded, the existing incremental dirty sector counting in bch_root_node_dirty_init() doesn't release btree occupation after iterating 500000 (INIT_KEYS_EACH_TIME) bkeys. Because a read lock is added on btree root node to prevent the btree to be split during the dirty sectors counting, other I/O requester has no chance to gain the write lock even restart bcache_btree(). That is to say, the incremental dirty sectors counting is incompatible to the multhreaded bch_sectors_dirty_init(). We have to choose one and drop another one. In my testing, with 512 bytes random writes, I generate 1.2T dirty data and a btree with 400K nodes. With single thread and incremental dirty sectors counting, it takes 30+ minites to register the backing device. And with multithreaded dirty sectors counting, the backing device registration can be accomplished within 2 minutes. The 30+ minutes V.S. 2- minutes difference makes me decide to keep multithreaded bch_sectors_dirty_init() and drop the incremental dirty sectors counting. This is what this patch does. But INIT_KEYS_EACH_TIME is kept, in sectors_dirty_init_fn() the CPU will be released by cond_resched() after every INIT_KEYS_EACH_TIME keys iterated. This is to avoid the watchdog reports a bogus soft lockup warning. Fixes: b144e45fc576 ("bcache: make bch_sectors_dirty_init() to be multithreaded") Signed-off-by: Coly Li <colyli(a)suse.de> Cc: stable(a)vger.kernel.org --- drivers/md/bcache/writeback.c | 41 +++++++++++------------------------ 1 file changed, 13 insertions(+), 28 deletions(-) diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index d24c09490f8e..75b71199800d 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -805,13 +805,11 @@ static int bch_writeback_thread(void *arg) /* Init */ #define INIT_KEYS_EACH_TIME 500000 -#define INIT_KEYS_SLEEP_MS 100 struct sectors_dirty_init { struct btree_op op; unsigned int inode; size_t count; - struct bkey start; }; static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b, @@ -827,11 +825,8 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b, KEY_START(k), KEY_SIZE(k)); op->count++; - if (atomic_read(&b->c->search_inflight) && - !(op->count % INIT_KEYS_EACH_TIME)) { - bkey_copy_key(&op->start, k); - return -EAGAIN; - } + if (!(op->count % INIT_KEYS_EACH_TIME)) + cond_resched(); return MAP_CONTINUE; } @@ -846,24 +841,16 @@ static int bch_root_node_dirty_init(struct cache_set *c, bch_btree_op_init(&op.op, -1); op.inode = d->id; op.count = 0; - op.start = KEY(op.inode, 0, 0); - - do { - ret = bcache_btree(map_keys_recurse, - k, - c->root, - &op.op, - &op.start, - sectors_dirty_init_fn, - 0); - if (ret == -EAGAIN) - schedule_timeout_interruptible( - msecs_to_jiffies(INIT_KEYS_SLEEP_MS)); - else if (ret < 0) { - pr_warn("sectors dirty init failed, ret=%d!\n", ret); - break; - } - } while (ret == -EAGAIN); + + ret = bcache_btree(map_keys_recurse, + k, + c->root, + &op.op, + &KEY(op.inode, 0, 0), + sectors_dirty_init_fn, + 0); + if (ret < 0) + pr_warn("sectors dirty init failed, ret=%d!\n", ret); return ret; } @@ -907,7 +894,6 @@ static int bch_dirty_init_thread(void *arg) goto out; } skip_nr--; - cond_resched(); } if (p) { @@ -917,7 +903,6 @@ static int bch_dirty_init_thread(void *arg) p = NULL; prev_idx = cur_idx; - cond_resched(); } out: @@ -956,11 +941,11 @@ void bch_sectors_dirty_init(struct bcache_device *d) bch_btree_op_init(&op.op, -1); op.inode = d->id; op.count = 0; - op.start = KEY(op.inode, 0, 0); for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid) sectors_dirty_init_fn(&op.op, c->root, k); + rw_unlock(0, c->root); return; } -- 2.35.3

3 years, 1 month

1
0
0 0

[PATCH 2/4] bcache: improve multithreaded bch_sectors_dirty_init()

by Coly Li

Commit b144e45fc576 ("bcache: make bch_sectors_dirty_init() to be multithreaded") makes bch_sectors_dirty_init() to be much faster when counting dirty sectors by iterating all dirty keys in the btree. But it isn't in ideal shape yet, still can be improved. This patch does the following changes to improve current parallel dirty keys iteration on the btree, - Add read lock to root node when multiple threads iterating the btree, to prevent the root node gets split by I/Os from other registered bcache devices. - Remove local variable "char name[32]" and generate kernel thread name string directly when calling kthread_run(). - Allocate "struct bch_dirty_init_state state" directly on stack and avoid the unnecessary dynamic memory allocation for it. - Decrease BCH_DIRTY_INIT_THRD_MAX from 64 to 12 which is enough indeed. - Increase &state->started to count created kernel thread after it succeeds to create. - When wait for all dirty key counting threads to finish, use wait_event() to replace wait_event_interruptible(). With the above changes, the code is more clear, and some potential error conditions are avoided. Fixes: b144e45fc576 ("bcache: make bch_sectors_dirty_init() to be multithreaded") Signed-off-by: Coly Li <colyli(a)suse.de> Cc: stable(a)vger.kernel.org --- drivers/md/bcache/writeback.c | 62 ++++++++++++++--------------------- drivers/md/bcache/writeback.h | 2 +- 2 files changed, 26 insertions(+), 38 deletions(-) diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 9ee0005874cd..d24c09490f8e 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -948,10 +948,10 @@ void bch_sectors_dirty_init(struct bcache_device *d) struct btree_iter iter; struct sectors_dirty_init op; struct cache_set *c = d->c; - struct bch_dirty_init_state *state; - char name[32]; + struct bch_dirty_init_state state; /* Just count root keys if no leaf node */ + rw_lock(0, c->root, c->root->level); if (c->root->level == 0) { bch_btree_op_init(&op.op, -1); op.inode = d->id; @@ -961,54 +961,42 @@ void bch_sectors_dirty_init(struct bcache_device *d) for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid) sectors_dirty_init_fn(&op.op, c->root, k); + rw_unlock(0, c->root); return; } - state = kzalloc(sizeof(struct bch_dirty_init_state), GFP_KERNEL); - if (!state) { - pr_warn("sectors dirty init failed: cannot allocate memory\n"); - return; - } - - state->c = c; - state->d = d; - state->total_threads = bch_btre_dirty_init_thread_nr(); - state->key_idx = 0; - spin_lock_init(&state->idx_lock); - atomic_set(&state->started, 0); - atomic_set(&state->enough, 0); - init_waitqueue_head(&state->wait); - - for (i = 0; i < state->total_threads; i++) { - /* Fetch latest state->enough earlier */ + state.c = c; + state.d = d; + state.total_threads = bch_btre_dirty_init_thread_nr(); + state.key_idx = 0; + spin_lock_init(&state.idx_lock); + atomic_set(&state.started, 0); + atomic_set(&state.enough, 0); + init_waitqueue_head(&state.wait); + + for (i = 0; i < state.total_threads; i++) { + /* Fetch latest state.enough earlier */ smp_mb__before_atomic(); - if (atomic_read(&state->enough)) + if (atomic_read(&state.enough)) break; - state->infos[i].state = state; - atomic_inc(&state->started); - snprintf(name, sizeof(name), "bch_dirty_init[%d]", i); - - state->infos[i].thread = - kthread_run(bch_dirty_init_thread, - &state->infos[i], - name); - if (IS_ERR(state->infos[i].thread)) { + state.infos[i].state = &state; + state.infos[i].thread = + kthread_run(bch_dirty_init_thread, &state.infos[i], + "bch_dirtcnt[%d]", i); + if (IS_ERR(state.infos[i].thread)) { pr_err("fails to run thread bch_dirty_init[%d]\n", i); for (--i; i >= 0; i--) - kthread_stop(state->infos[i].thread); + kthread_stop(state.infos[i].thread); goto out; } + atomic_inc(&state.started); } - /* - * Must wait for all threads to stop. - */ - wait_event_interruptible(state->wait, - atomic_read(&state->started) == 0); - out: - kfree(state); + /* Must wait for all threads to stop. */ + wait_event(state.wait, atomic_read(&state.started) == 0); + rw_unlock(0, c->root); } void bch_cached_dev_writeback_init(struct cached_dev *dc) diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index 02b2f9df73f6..31df716951f6 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -20,7 +20,7 @@ #define BCH_WRITEBACK_FRAGMENT_THRESHOLD_MID 57 #define BCH_WRITEBACK_FRAGMENT_THRESHOLD_HIGH 64 -#define BCH_DIRTY_INIT_THRD_MAX 64 +#define BCH_DIRTY_INIT_THRD_MAX 12 /* * 14 (16384ths) is chosen here as something that each backing device * should be a reasonable fraction of the share, and not to blow up -- 2.35.3

3 years, 1 month

1
0
0 0

[PATCH 1/4] bcache: improve multithreaded bch_btree_check()

by Coly Li

Commit 8e7102273f59 ("bcache: make bch_btree_check() to be multithreaded") makes bch_btree_check() to be much faster when checking all btree nodes during cache device registration. But it isn't in ideal shap yet, still can be improved. This patch does the following thing to improve current parallel btree nodes check by multiple threads in bch_btree_check(), - Add read lock to root node while checking all the btree nodes with multiple threads. Although currently it is not mandatory but it is good to have a read lock in code logic. - Remove local variable 'char name[32]', and generate kernel thread name string directly when calling kthread_run(). - Allocate local variable "struct btree_check_state check_state" on the stack and avoid unnecessary dynamic memory allocation for it. - Reduce BCH_BTR_CHKTHREAD_MAX from 64 to 12 which is enough indeed. - Increase check_state->started to count created kernel thread after it succeeds to create. - When wait for all checking kernel threads to finish, use wait_event() to replace wait_event_interruptible(). With this change, the code is more clear, and some potential error conditions are avoided. Fixes: 8e7102273f59 ("bcache: make bch_btree_check() to be multithreaded") Signed-off-by: Coly Li <colyli(a)suse.de> Cc: stable(a)vger.kernel.org --- drivers/md/bcache/btree.c | 58 ++++++++++++++++++--------------------- drivers/md/bcache/btree.h | 2 +- 2 files changed, 27 insertions(+), 33 deletions(-) diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index ad9f16689419..2362bb8ef6d1 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -2006,8 +2006,7 @@ int bch_btree_check(struct cache_set *c) int i; struct bkey *k = NULL; struct btree_iter iter; - struct btree_check_state *check_state; - char name[32]; + struct btree_check_state check_state; /* check and mark root node keys */ for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid) @@ -2018,63 +2017,58 @@ int bch_btree_check(struct cache_set *c) if (c->root->level == 0) return 0; - check_state = kzalloc(sizeof(struct btree_check_state), GFP_KERNEL); - if (!check_state) - return -ENOMEM; - - check_state->c = c; - check_state->total_threads = bch_btree_chkthread_nr(); - check_state->key_idx = 0; - spin_lock_init(&check_state->idx_lock); - atomic_set(&check_state->started, 0); - atomic_set(&check_state->enough, 0); - init_waitqueue_head(&check_state->wait); + check_state.c = c; + check_state.total_threads = bch_btree_chkthread_nr(); + check_state.key_idx = 0; + spin_lock_init(&check_state.idx_lock); + atomic_set(&check_state.started, 0); + atomic_set(&check_state.enough, 0); + init_waitqueue_head(&check_state.wait); + rw_lock(0, c->root, c->root->level); /* * Run multiple threads to check btree nodes in parallel, - * if check_state->enough is non-zero, it means current + * if check_state.enough is non-zero, it means current * running check threads are enough, unncessary to create * more. */ - for (i = 0; i < check_state->total_threads; i++) { - /* fetch latest check_state->enough earlier */ + for (i = 0; i < check_state.total_threads; i++) { + /* fetch latest check_state.enough earlier */ smp_mb__before_atomic(); - if (atomic_read(&check_state->enough)) + if (atomic_read(&check_state.enough)) break; - check_state->infos[i].result = 0; - check_state->infos[i].state = check_state; - snprintf(name, sizeof(name), "bch_btrchk[%u]", i); - atomic_inc(&check_state->started); + check_state.infos[i].result = 0; + check_state.infos[i].state = &check_state; - check_state->infos[i].thread = + check_state.infos[i].thread = kthread_run(bch_btree_check_thread, - &check_state->infos[i], - name); - if (IS_ERR(check_state->infos[i].thread)) { + &check_state.infos[i], + "bch_btrchk[%d]", i); + if (IS_ERR(check_state.infos[i].thread)) { pr_err("fails to run thread bch_btrchk[%d]\n", i); for (--i; i >= 0; i--) - kthread_stop(check_state->infos[i].thread); + kthread_stop(check_state.infos[i].thread); ret = -ENOMEM; goto out; } + atomic_inc(&check_state.started); } /* * Must wait for all threads to stop. */ - wait_event_interruptible(check_state->wait, - atomic_read(&check_state->started) == 0); + wait_event(check_state.wait, atomic_read(&check_state.started) == 0); - for (i = 0; i < check_state->total_threads; i++) { - if (check_state->infos[i].result) { - ret = check_state->infos[i].result; + for (i = 0; i < check_state.total_threads; i++) { + if (check_state.infos[i].result) { + ret = check_state.infos[i].result; goto out; } } out: - kfree(check_state); + rw_unlock(0, c->root); return ret; } diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 50482107134f..1b5fdbc0d83e 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -226,7 +226,7 @@ struct btree_check_info { int result; }; -#define BCH_BTR_CHKTHREAD_MAX 64 +#define BCH_BTR_CHKTHREAD_MAX 12 struct btree_check_state { struct cache_set *c; int total_threads; -- 2.35.3

3 years, 1 month

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2022