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
crc32c_generic.c
/*
* Cryptographic API.
*
* CRC32C chksum
*
*@Article{castagnoli-crc,
* author = { Guy Castagnoli and Stefan Braeuer and Martin Herrman},
* title = {{Optimization of Cyclic Redundancy-Check Codes with 24
* and 32 Parity Bits}},
* journal = IEEE Transactions on Communication,
* year = {1993},
* volume = {41},
* number = {6},
* pages = {},
* month = {June},
*}
* Used by the iSCSI driver, possibly others, and derived from the
* the iscsi-crc.c module of the linux-iscsi driver at
* http://linux-iscsi.sourceforge.net.
*
* Following the example of lib/crc32, this function is intended to be
* flexible and useful for all users. Modules that currently have their
* own crc32c, but hopefully may be able to use this one are:
* net/sctp (please add all your doco to here if you change to
* use this one!)
* <endoflist>
*
* Copyright (c) 2004 Cisco Systems, Inc.
* Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au>
*
* 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 <crypto/internal/hash.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/crc32.h>
#define CHKSUM_BLOCK_SIZE 1
#define CHKSUM_DIGEST_SIZE 4
struct chksum_ctx {
u32 key;
};
struct chksum_desc_ctx {
u32 crc;
};
/*
* Steps through buffer one byte at at time, calculates reflected
* crc using table.
*/
static int chksum_init(struct shash_desc *desc)
{
struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm);
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
ctx->crc = mctx->key;
return 0;
}
/*
* Setting the seed allows arbitrary accumulators and flexible XOR policy
* If your algorithm starts with ~0, then XOR with ~0 before you set
* the seed.
*/
static int chksum_setkey(struct crypto_shash *tfm, const u8 *key,
unsigned int keylen)
{
struct chksum_ctx *mctx = crypto_shash_ctx(tfm);
if (keylen != sizeof(mctx->key)) {
crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
return -EINVAL;
}
mctx->key = le32_to_cpu(*(__le32 *)key);
return 0;
}
static int chksum_update(struct shash_desc *desc, const u8 *data,
unsigned int length)
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
ctx->crc = __crc32c_le(ctx->crc, data, length);
return 0;
}
static int chksum_final(struct shash_desc *desc, u8 *out)
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
*(__le32 *)out = ~cpu_to_le32p(&ctx->crc);
return 0;
}
static int __chksum_finup(u32 *crcp, const u8 *data, unsigned int len, u8 *out)
{
*(__le32 *)out = ~cpu_to_le32(__crc32c_le(*crcp, data, len));
return 0;
}
static int chksum_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
return __chksum_finup(&ctx->crc, data, len, out);
}
static int chksum_digest(struct shash_desc *desc, const u8 *data,
unsigned int length, u8 *out)
{
struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm);
return __chksum_finup(&mctx->key, data, length, out);
}
static int crc32c_cra_init(struct crypto_tfm *tfm)
{
struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);
mctx->key = ~0;
return 0;
}
static struct shash_alg alg = {
.digestsize = CHKSUM_DIGEST_SIZE,
.setkey = chksum_setkey,
.init = chksum_init,
.update = chksum_update,
.final = chksum_final,
.finup = chksum_finup,
.digest = chksum_digest,
.descsize = sizeof(struct chksum_desc_ctx),
.base = {
.cra_name = "crc32c",
.cra_driver_name = "crc32c-generic",
.cra_priority = 100,
.cra_blocksize = CHKSUM_BLOCK_SIZE,
.cra_alignmask = 3,
.cra_ctxsize = sizeof(struct chksum_ctx),
.cra_module = THIS_MODULE,
.cra_init = crc32c_cra_init,
}
};
static int __init crc32c_mod_init(void)
{
return crypto_register_shash(&alg);
}
static void __exit crc32c_mod_fini(void)
{
crypto_unregister_shash(&alg);
}
module_init(crc32c_mod_init);
module_exit(crc32c_mod_fini);
MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>");
MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c");
MODULE_LICENSE("GPL");
MODULE_ALIAS_CRYPTO("crc32c");
MODULE_ALIAS_CRYPTO("crc32c-generic");
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...