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
Raw File
ecb.c
/*
 * ECB: Electronic CodeBook mode
 *
 * Copyright (c) 2006 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/algapi.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/scatterlist.h>
#include <linux/slab.h>

struct crypto_ecb_ctx {
	struct crypto_cipher *child;
};

static int crypto_ecb_setkey(struct crypto_tfm *parent, const u8 *key,
			     unsigned int keylen)
{
	struct crypto_ecb_ctx *ctx = crypto_tfm_ctx(parent);
	struct crypto_cipher *child = ctx->child;
	int err;

	crypto_cipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
	crypto_cipher_set_flags(child, crypto_tfm_get_flags(parent) &
				       CRYPTO_TFM_REQ_MASK);
	err = crypto_cipher_setkey(child, key, keylen);
	crypto_tfm_set_flags(parent, crypto_cipher_get_flags(child) &
				     CRYPTO_TFM_RES_MASK);
	return err;
}

static int crypto_ecb_crypt(struct blkcipher_desc *desc,
			    struct blkcipher_walk *walk,
			    struct crypto_cipher *tfm,
			    void (*fn)(struct crypto_tfm *, u8 *, const u8 *))
{
	int bsize = crypto_cipher_blocksize(tfm);
	unsigned int nbytes;
	int err;

	err = blkcipher_walk_virt(desc, walk);

	while ((nbytes = walk->nbytes)) {
		u8 *wsrc = walk->src.virt.addr;
		u8 *wdst = walk->dst.virt.addr;

		do {
			fn(crypto_cipher_tfm(tfm), wdst, wsrc);

			wsrc += bsize;
			wdst += bsize;
		} while ((nbytes -= bsize) >= bsize);

		err = blkcipher_walk_done(desc, walk, nbytes);
	}

	return err;
}

static int crypto_ecb_encrypt(struct blkcipher_desc *desc,
			      struct scatterlist *dst, struct scatterlist *src,
			      unsigned int nbytes)
{
	struct blkcipher_walk walk;
	struct crypto_blkcipher *tfm = desc->tfm;
	struct crypto_ecb_ctx *ctx = crypto_blkcipher_ctx(tfm);
	struct crypto_cipher *child = ctx->child;

	blkcipher_walk_init(&walk, dst, src, nbytes);
	return crypto_ecb_crypt(desc, &walk, child,
				crypto_cipher_alg(child)->cia_encrypt);
}

static int crypto_ecb_decrypt(struct blkcipher_desc *desc,
			      struct scatterlist *dst, struct scatterlist *src,
			      unsigned int nbytes)
{
	struct blkcipher_walk walk;
	struct crypto_blkcipher *tfm = desc->tfm;
	struct crypto_ecb_ctx *ctx = crypto_blkcipher_ctx(tfm);
	struct crypto_cipher *child = ctx->child;

	blkcipher_walk_init(&walk, dst, src, nbytes);
	return crypto_ecb_crypt(desc, &walk, child,
				crypto_cipher_alg(child)->cia_decrypt);
}

static int crypto_ecb_init_tfm(struct crypto_tfm *tfm)
{
	struct crypto_instance *inst = (void *)tfm->__crt_alg;
	struct crypto_spawn *spawn = crypto_instance_ctx(inst);
	struct crypto_ecb_ctx *ctx = crypto_tfm_ctx(tfm);
	struct crypto_cipher *cipher;

	cipher = crypto_spawn_cipher(spawn);
	if (IS_ERR(cipher))
		return PTR_ERR(cipher);

	ctx->child = cipher;
	return 0;
}

static void crypto_ecb_exit_tfm(struct crypto_tfm *tfm)
{
	struct crypto_ecb_ctx *ctx = crypto_tfm_ctx(tfm);
	crypto_free_cipher(ctx->child);
}

static struct crypto_instance *crypto_ecb_alloc(struct rtattr **tb)
{
	struct crypto_instance *inst;
	struct crypto_alg *alg;
	int err;

	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_BLKCIPHER);
	if (err)
		return ERR_PTR(err);

	alg = crypto_get_attr_alg(tb, CRYPTO_ALG_TYPE_CIPHER,
				  CRYPTO_ALG_TYPE_MASK);
	if (IS_ERR(alg))
		return ERR_CAST(alg);

	inst = crypto_alloc_instance("ecb", alg);
	if (IS_ERR(inst))
		goto out_put_alg;

	inst->alg.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER;
	inst->alg.cra_priority = alg->cra_priority;
	inst->alg.cra_blocksize = alg->cra_blocksize;
	inst->alg.cra_alignmask = alg->cra_alignmask;
	inst->alg.cra_type = &crypto_blkcipher_type;

	inst->alg.cra_blkcipher.min_keysize = alg->cra_cipher.cia_min_keysize;
	inst->alg.cra_blkcipher.max_keysize = alg->cra_cipher.cia_max_keysize;

	inst->alg.cra_ctxsize = sizeof(struct crypto_ecb_ctx);

	inst->alg.cra_init = crypto_ecb_init_tfm;
	inst->alg.cra_exit = crypto_ecb_exit_tfm;

	inst->alg.cra_blkcipher.setkey = crypto_ecb_setkey;
	inst->alg.cra_blkcipher.encrypt = crypto_ecb_encrypt;
	inst->alg.cra_blkcipher.decrypt = crypto_ecb_decrypt;

out_put_alg:
	crypto_mod_put(alg);
	return inst;
}

static void crypto_ecb_free(struct crypto_instance *inst)
{
	crypto_drop_spawn(crypto_instance_ctx(inst));
	kfree(inst);
}

static struct crypto_template crypto_ecb_tmpl = {
	.name = "ecb",
	.alloc = crypto_ecb_alloc,
	.free = crypto_ecb_free,
	.module = THIS_MODULE,
};

static int __init crypto_ecb_module_init(void)
{
	return crypto_register_template(&crypto_ecb_tmpl);
}

static void __exit crypto_ecb_module_exit(void)
{
	crypto_unregister_template(&crypto_ecb_tmpl);
}

module_init(crypto_ecb_module_init);
module_exit(crypto_ecb_module_exit);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("ECB block cipher algorithm");
MODULE_ALIAS_CRYPTO("ecb");
back to top