Revision 63cae12bce9861cec309798d34701cf3da20bc71 authored by Peter Zijlstra on 09 December 2016, 13:59:00 UTC, committed by Ingo Molnar on 14 January 2017, 09:56:10 UTC
There is problem with installing an event in a task that is 'stuck' on an offline CPU. Blocked tasks are not dis-assosciated from offlined CPUs, after all, a blocked task doesn't run and doesn't require a CPU etc.. Only on wakeup do we ammend the situation and place the task on a available CPU. If we hit such a task with perf_install_in_context() we'll loop until either that task wakes up or the CPU comes back online, if the task waking depends on the event being installed, we're stuck. While looking into this issue, I also spotted another problem, if we hit a task with perf_install_in_context() that is in the middle of being migrated, that is we observe the old CPU before sending the IPI, but run the IPI (on the old CPU) while the task is already running on the new CPU, things also go sideways. Rework things to rely on task_curr() -- outside of rq->lock -- which is rather tricky. Imagine the following scenario where we're trying to install the first event into our task 't': CPU0 CPU1 CPU2 (current == t) t->perf_event_ctxp[] = ctx; smp_mb(); cpu = task_cpu(t); switch(t, n); migrate(t, 2); switch(p, t); ctx = t->perf_event_ctxp[]; // must not be NULL smp_function_call(cpu, ..); generic_exec_single() func(); spin_lock(ctx->lock); if (task_curr(t)) // false add_event_to_ctx(); spin_unlock(ctx->lock); perf_event_context_sched_in(); spin_lock(ctx->lock); // sees event So its CPU0's store of t->perf_event_ctxp[] that must not go 'missing'. Because if CPU2's load of that variable were to observe NULL, it would not try to schedule the ctx and we'd have a task running without its counter, which would be 'bad'. As long as we observe !NULL, we'll acquire ctx->lock. If we acquire it first and not see the event yet, then CPU0 must observe task_curr() and retry. If the install happens first, then we must see the event on sched-in and all is well. I think we can translate the first part (until the 'must not be NULL') of the scenario to a litmus test like: C C-peterz { } P0(int *x, int *y) { int r1; WRITE_ONCE(*x, 1); smp_mb(); r1 = READ_ONCE(*y); } P1(int *y, int *z) { WRITE_ONCE(*y, 1); smp_store_release(z, 1); } P2(int *x, int *z) { int r1; int r2; r1 = smp_load_acquire(z); smp_mb(); r2 = READ_ONCE(*x); } exists (0:r1=0 /\ 2:r1=1 /\ 2:r2=0) Where: x is perf_event_ctxp[], y is our tasks's CPU, and z is our task being placed on the rq of CPU2. The P0 smp_mb() is the one added by this patch, ordering the store to perf_event_ctxp[] from find_get_context() and the load of task_cpu() in task_function_call(). The smp_store_release/smp_load_acquire model the RCpc locking of the rq->lock and the smp_mb() of P2 is the context switch switching from whatever CPU2 was running to our task 't'. This litmus test evaluates into: Test C-peterz Allowed States 7 0:r1=0; 2:r1=0; 2:r2=0; 0:r1=0; 2:r1=0; 2:r2=1; 0:r1=0; 2:r1=1; 2:r2=1; 0:r1=1; 2:r1=0; 2:r2=0; 0:r1=1; 2:r1=0; 2:r2=1; 0:r1=1; 2:r1=1; 2:r2=0; 0:r1=1; 2:r1=1; 2:r2=1; No Witnesses Positive: 0 Negative: 7 Condition exists (0:r1=0 /\ 2:r1=1 /\ 2:r2=0) Observation C-peterz Never 0 7 Hash=e427f41d9146b2a5445101d3e2fcaa34 And the strong and weak model agree. Reported-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Will Deacon <will.deacon@arm.com> Cc: jeremy.linton@arm.com Link: http://lkml.kernel.org/r/20161209135900.GU3174@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
1 parent ad5013d
acompress.c
/*
* Asynchronous Compression operations
*
* Copyright (c) 2016, Intel Corporation
* Authors: Weigang Li <weigang.li@intel.com>
* Giovanni Cabiddu <giovanni.cabiddu@intel.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*
*/
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/crypto.h>
#include <crypto/algapi.h>
#include <linux/cryptouser.h>
#include <net/netlink.h>
#include <crypto/internal/acompress.h>
#include <crypto/internal/scompress.h>
#include "internal.h"
static const struct crypto_type crypto_acomp_type;
#ifdef CONFIG_NET
static int crypto_acomp_report(struct sk_buff *skb, struct crypto_alg *alg)
{
struct crypto_report_acomp racomp;
strncpy(racomp.type, "acomp", sizeof(racomp.type));
if (nla_put(skb, CRYPTOCFGA_REPORT_ACOMP,
sizeof(struct crypto_report_acomp), &racomp))
goto nla_put_failure;
return 0;
nla_put_failure:
return -EMSGSIZE;
}
#else
static int crypto_acomp_report(struct sk_buff *skb, struct crypto_alg *alg)
{
return -ENOSYS;
}
#endif
static void crypto_acomp_show(struct seq_file *m, struct crypto_alg *alg)
__attribute__ ((unused));
static void crypto_acomp_show(struct seq_file *m, struct crypto_alg *alg)
{
seq_puts(m, "type : acomp\n");
}
static void crypto_acomp_exit_tfm(struct crypto_tfm *tfm)
{
struct crypto_acomp *acomp = __crypto_acomp_tfm(tfm);
struct acomp_alg *alg = crypto_acomp_alg(acomp);
alg->exit(acomp);
}
static int crypto_acomp_init_tfm(struct crypto_tfm *tfm)
{
struct crypto_acomp *acomp = __crypto_acomp_tfm(tfm);
struct acomp_alg *alg = crypto_acomp_alg(acomp);
if (tfm->__crt_alg->cra_type != &crypto_acomp_type)
return crypto_init_scomp_ops_async(tfm);
acomp->compress = alg->compress;
acomp->decompress = alg->decompress;
acomp->dst_free = alg->dst_free;
acomp->reqsize = alg->reqsize;
if (alg->exit)
acomp->base.exit = crypto_acomp_exit_tfm;
if (alg->init)
return alg->init(acomp);
return 0;
}
static unsigned int crypto_acomp_extsize(struct crypto_alg *alg)
{
int extsize = crypto_alg_extsize(alg);
if (alg->cra_type != &crypto_acomp_type)
extsize += sizeof(struct crypto_scomp *);
return extsize;
}
static const struct crypto_type crypto_acomp_type = {
.extsize = crypto_acomp_extsize,
.init_tfm = crypto_acomp_init_tfm,
#ifdef CONFIG_PROC_FS
.show = crypto_acomp_show,
#endif
.report = crypto_acomp_report,
.maskclear = ~CRYPTO_ALG_TYPE_MASK,
.maskset = CRYPTO_ALG_TYPE_ACOMPRESS_MASK,
.type = CRYPTO_ALG_TYPE_ACOMPRESS,
.tfmsize = offsetof(struct crypto_acomp, base),
};
struct crypto_acomp *crypto_alloc_acomp(const char *alg_name, u32 type,
u32 mask)
{
return crypto_alloc_tfm(alg_name, &crypto_acomp_type, type, mask);
}
EXPORT_SYMBOL_GPL(crypto_alloc_acomp);
struct acomp_req *acomp_request_alloc(struct crypto_acomp *acomp)
{
struct crypto_tfm *tfm = crypto_acomp_tfm(acomp);
struct acomp_req *req;
req = __acomp_request_alloc(acomp);
if (req && (tfm->__crt_alg->cra_type != &crypto_acomp_type))
return crypto_acomp_scomp_alloc_ctx(req);
return req;
}
EXPORT_SYMBOL_GPL(acomp_request_alloc);
void acomp_request_free(struct acomp_req *req)
{
struct crypto_acomp *acomp = crypto_acomp_reqtfm(req);
struct crypto_tfm *tfm = crypto_acomp_tfm(acomp);
if (tfm->__crt_alg->cra_type != &crypto_acomp_type)
crypto_acomp_scomp_free_ctx(req);
if (req->flags & CRYPTO_ACOMP_ALLOC_OUTPUT) {
acomp->dst_free(req->dst);
req->dst = NULL;
}
__acomp_request_free(req);
}
EXPORT_SYMBOL_GPL(acomp_request_free);
int crypto_register_acomp(struct acomp_alg *alg)
{
struct crypto_alg *base = &alg->base;
base->cra_type = &crypto_acomp_type;
base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
base->cra_flags |= CRYPTO_ALG_TYPE_ACOMPRESS;
return crypto_register_alg(base);
}
EXPORT_SYMBOL_GPL(crypto_register_acomp);
int crypto_unregister_acomp(struct acomp_alg *alg)
{
return crypto_unregister_alg(&alg->base);
}
EXPORT_SYMBOL_GPL(crypto_unregister_acomp);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Asynchronous compression type");
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...