Date: Fri, 5 Jul 2019 12:33:31 +0000 (UTC) From: Hans Petter Selasky <hselasky@FreeBSD.org> To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-stable@freebsd.org, svn-src-stable-12@freebsd.org Subject: svn commit: r349764 - in stable/12: share/man/man9 sys/kern sys/sys Message-ID: <201907051233.x65CXVdB061495@repo.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: hselasky Date: Fri Jul 5 12:33:31 2019 New Revision: 349764 URL: https://svnweb.freebsd.org/changeset/base/349764 Log: MFC r349506: Implement API for draining EPOCH(9) callbacks. The epoch_drain_callbacks() function is used to drain all pending callbacks which have been invoked by prior epoch_call() function calls on the same epoch. This function is useful when there are shared memory structure(s) referred to by the epoch callback(s) which are not refcounted and are rarely freed. The typical place for calling this function is right before freeing or invalidating the shared resource(s) used by the epoch callback(s). This function can sleep and is not optimized for performance. Differential Revision: https://reviews.freebsd.org/D20109 Sponsored by: Mellanox Technologies Modified: stable/12/share/man/man9/Makefile stable/12/share/man/man9/epoch.9 stable/12/sys/kern/subr_epoch.c stable/12/sys/sys/epoch.h Directory Properties: stable/12/ (props changed) Modified: stable/12/share/man/man9/Makefile ============================================================================== --- stable/12/share/man/man9/Makefile Fri Jul 5 12:26:30 2019 (r349763) +++ stable/12/share/man/man9/Makefile Fri Jul 5 12:33:31 2019 (r349764) @@ -941,6 +941,15 @@ MLINKS+=drbr.9 drbr_free.9 \ MLINKS+=DRIVER_MODULE.9 DRIVER_MODULE_ORDERED.9 \ DRIVER_MODULE.9 EARLY_DRIVER_MODULE.9 \ DRIVER_MODULE.9 EARLY_DRIVER_MODULE_ORDERED.9 +MLINKS+=epoch.9 epoch_context.9 \ + epoch.9 epoch_alloc.9 \ + epoch.9 epoch_free.9 \ + epoch.9 epoch_enter.9 \ + epoch.9 epoch_exit.9 \ + epoch.9 epoch_wait.9 \ + epoch.9 epoch_call.9 \ + epoch.9 epoch_drain_callbacks.9 \ + epoch.9 in_epoch.9 MLINKS+=EVENTHANDLER.9 EVENTHANDLER_DECLARE.9 \ EVENTHANDLER.9 EVENTHANDLER_DEFINE.9 \ EVENTHANDLER.9 EVENTHANDLER_DEREGISTER.9 \ Modified: stable/12/share/man/man9/epoch.9 ============================================================================== --- stable/12/share/man/man9/epoch.9 Fri Jul 5 12:26:30 2019 (r349763) +++ stable/12/share/man/man9/epoch.9 Fri Jul 5 12:33:31 2019 (r349764) @@ -26,7 +26,7 @@ .\" .\" $FreeBSD$ .\" -.Dd June 25, 2018 +.Dd June 28, 2019 .Dt EPOCH 9 .Os .Sh NAME @@ -38,6 +38,7 @@ .Nm epoch_exit , .Nm epoch_wait , .Nm epoch_call , +.Nm epoch_drain_callbacks , .Nm in_epoch , .Nd kernel epoch based reclamation .Sh SYNOPSIS @@ -60,6 +61,8 @@ .Fn epoch_wait_preempt "epoch_t epoch" .Ft void .Fn epoch_call "epoch_t epoch" "epoch_context_t ctx" "void (*callback) (epoch_context_t)" +.Ft void +.Fn epoch_drain_callbacks "epoch_t epoch" .Ft int .Fn in_epoch "epoch_t epoch" .Sh DESCRIPTION @@ -120,6 +123,18 @@ routines must be used and the caller can no longer mod in place. An item to be modified must be handled with copy on write and frees must be deferred until after a grace period has elapsed. +.Pp +The +.Fn epoch_drain_callbacks +function is used to drain all pending callbacks which have been invoked by prior +.Fn epoch_call +function calls on the same epoch. +This function is useful when there are shared memory structure(s) +referred to by the epoch callback(s) which are not refcounted and are +rarely freed. +The typical place for calling this function is right before freeing or +invalidating the shared resource(s) used by the epoch callback(s). +This function can sleep and is not optimized for performance. .Sh RETURN VALUES .Fn in_epoch curepoch will return 1 if curthread is in curepoch, 0 otherwise. Modified: stable/12/sys/kern/subr_epoch.c ============================================================================== --- stable/12/sys/kern/subr_epoch.c Fri Jul 5 12:26:30 2019 (r349763) +++ stable/12/sys/kern/subr_epoch.c Fri Jul 5 12:33:31 2019 (r349764) @@ -43,6 +43,7 @@ __FBSDID("$FreeBSD$"); #include <sys/pcpu.h> #include <sys/proc.h> #include <sys/sched.h> +#include <sys/sx.h> #include <sys/smp.h> #include <sys/sysctl.h> #include <sys/turnstile.h> @@ -64,6 +65,8 @@ static MALLOC_DEFINE(M_EPOCH, "epoch", "epoch based re TAILQ_HEAD (epoch_tdlist, epoch_tracker); typedef struct epoch_record { ck_epoch_record_t er_record; + struct epoch_context er_drain_ctx; + struct epoch *er_parent; volatile struct epoch_tdlist er_tdlist; volatile uint32_t er_gen; uint32_t er_cpuid; @@ -74,6 +77,9 @@ struct epoch { epoch_record_t e_pcpu_record; int e_idx; int e_flags; + struct sx e_drain_sx; + struct mtx e_drain_mtx; + volatile int e_drain_count; }; /* arbitrary --- needs benchmarking */ @@ -178,6 +184,7 @@ epoch_ctor(epoch_t epoch) ck_epoch_register(&epoch->e_epoch, &er->er_record, NULL); TAILQ_INIT((struct threadlist *)(uintptr_t)&er->er_tdlist); er->er_cpuid = cpu; + er->er_parent = epoch; } } @@ -203,6 +210,8 @@ epoch_alloc(int flags) MPASS(epoch_count < MAX_EPOCHS - 2); epoch->e_flags = flags; epoch->e_idx = epoch_count; + sx_init(&epoch->e_drain_sx, "epoch-drain-sx"); + mtx_init(&epoch->e_drain_mtx, "epoch-drain-mtx", NULL, MTX_DEF); allepochs[epoch_count++] = epoch; return (epoch); } @@ -210,18 +219,13 @@ epoch_alloc(int flags) void epoch_free(epoch_t epoch) { -#ifdef INVARIANTS - struct epoch_record *er; - int cpu; - CPU_FOREACH(cpu) { - er = zpcpu_get_cpu(epoch->e_pcpu_record, cpu); - MPASS(TAILQ_EMPTY(&er->er_tdlist)); - } -#endif + epoch_drain_callbacks(epoch); allepochs[epoch->e_idx] = NULL; epoch_wait(global_epoch); uma_zfree_pcpu(pcpu_zone_record, epoch->e_pcpu_record); + mtx_destroy(&epoch->e_drain_mtx); + sx_destroy(&epoch->e_drain_sx); free(epoch, M_EPOCH); } @@ -655,4 +659,81 @@ int in_epoch(epoch_t epoch) { return (in_epoch_verbose(epoch, 0)); +} + +static void +epoch_drain_cb(struct epoch_context *ctx) +{ + struct epoch *epoch = + __containerof(ctx, struct epoch_record, er_drain_ctx)->er_parent; + + if (atomic_fetchadd_int(&epoch->e_drain_count, -1) == 1) { + mtx_lock(&epoch->e_drain_mtx); + wakeup(epoch); + mtx_unlock(&epoch->e_drain_mtx); + } +} + +void +epoch_drain_callbacks(epoch_t epoch) +{ + epoch_record_t er; + struct thread *td; + int was_bound; + int old_pinned; + int old_cpu; + int cpu; + + WITNESS_WARN(WARN_GIANTOK | WARN_SLEEPOK, NULL, + "epoch_drain_callbacks() may sleep!"); + + /* too early in boot to have epoch set up */ + if (__predict_false(epoch == NULL)) + return; +#if !defined(EARLY_AP_STARTUP) + if (__predict_false(inited < 2)) + return; +#endif + DROP_GIANT(); + + sx_xlock(&epoch->e_drain_sx); + mtx_lock(&epoch->e_drain_mtx); + + td = curthread; + thread_lock(td); + old_cpu = PCPU_GET(cpuid); + old_pinned = td->td_pinned; + was_bound = sched_is_bound(td); + sched_unbind(td); + td->td_pinned = 0; + + CPU_FOREACH(cpu) + epoch->e_drain_count++; + CPU_FOREACH(cpu) { + er = zpcpu_get_cpu(epoch->e_pcpu_record, cpu); + sched_bind(td, cpu); + epoch_call(epoch, &er->er_drain_ctx, &epoch_drain_cb); + } + + /* restore CPU binding, if any */ + if (was_bound != 0) { + sched_bind(td, old_cpu); + } else { + /* get thread back to initial CPU, if any */ + if (old_pinned != 0) + sched_bind(td, old_cpu); + sched_unbind(td); + } + /* restore pinned after bind */ + td->td_pinned = old_pinned; + + thread_unlock(td); + + while (epoch->e_drain_count != 0) + msleep(epoch, &epoch->e_drain_mtx, PZERO, "EDRAIN", 0); + + mtx_unlock(&epoch->e_drain_mtx); + sx_xunlock(&epoch->e_drain_sx); + + PICKUP_GIANT(); } Modified: stable/12/sys/sys/epoch.h ============================================================================== --- stable/12/sys/sys/epoch.h Fri Jul 5 12:26:30 2019 (r349763) +++ stable/12/sys/sys/epoch.h Fri Jul 5 12:33:31 2019 (r349764) @@ -69,6 +69,7 @@ epoch_t epoch_alloc(int flags); void epoch_free(epoch_t epoch); void epoch_wait(epoch_t epoch); void epoch_wait_preempt(epoch_t epoch); +void epoch_drain_callbacks(epoch_t epoch); void epoch_call(epoch_t epoch, epoch_context_t ctx, void (*callback) (epoch_context_t)); int in_epoch(epoch_t epoch); int in_epoch_verbose(epoch_t epoch, int dump_onfail);
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201907051233.x65CXVdB061495>