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
bfin_cf_pcmcia.c
/*
 * file: drivers/pcmcia/bfin_cf.c
 *
 * based on: drivers/pcmcia/omap_cf.c
 * omap_cf.c -- OMAP 16xx CompactFlash controller driver
 *
 * Copyright (c) 2005 David Brownell
 * Copyright (c) 2006-2008 Michael Hennerich Analog Devices Inc.
 *
 * bugs:         enter bugs at http://blackfin.uclinux.org/
 *
 * 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, or (at your option)
 * any later version.
 *
 * this program is distributed in the hope that it will be useful,
 * but without any warranty; without even the implied warranty of
 * merchantability or fitness for a particular purpose.  see the
 * gnu general public license for more details.
 *
 * you should have received a copy of the gnu general public license
 * along with this program; see the file copying.
 * if not, write to the free software foundation,
 * 59 temple place - suite 330, boston, ma 02111-1307, usa.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/platform_device.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/io.h>
#include <linux/gpio.h>

#include <pcmcia/ss.h>
#include <pcmcia/cisreg.h>

#define	SZ_1K	0x00000400
#define	SZ_8K	0x00002000
#define	SZ_2K	(2 * SZ_1K)

#define	POLL_INTERVAL	(2 * HZ)

#define	CF_ATASEL_ENA 	0x20311802	/* Inverts RESET */
#define	CF_ATASEL_DIS 	0x20311800

#define bfin_cf_present(pfx) (gpio_get_value(pfx))

/*--------------------------------------------------------------------------*/

static const char driver_name[] = "bfin_cf_pcmcia";

struct bfin_cf_socket {
	struct pcmcia_socket socket;

	struct timer_list timer;
	unsigned present:1;
	unsigned active:1;

	struct platform_device *pdev;
	unsigned long phys_cf_io;
	unsigned long phys_cf_attr;
	u_int irq;
	u_short cd_pfx;
};

/*--------------------------------------------------------------------------*/
static int bfin_cf_reset(void)
{
	outw(0, CF_ATASEL_ENA);
	mdelay(200);
	outw(0, CF_ATASEL_DIS);

	return 0;
}

static int bfin_cf_ss_init(struct pcmcia_socket *s)
{
	return 0;
}

/* the timer is primarily to kick this socket's pccardd */
static void bfin_cf_timer(unsigned long _cf)
{
	struct bfin_cf_socket *cf = (void *)_cf;
	unsigned short present = bfin_cf_present(cf->cd_pfx);

	if (present != cf->present) {
		cf->present = present;
		dev_dbg(&cf->pdev->dev, ": card %s\n",
			 present ? "present" : "gone");
		pcmcia_parse_events(&cf->socket, SS_DETECT);
	}

	if (cf->active)
		mod_timer(&cf->timer, jiffies + POLL_INTERVAL);
}

static int bfin_cf_get_status(struct pcmcia_socket *s, u_int *sp)
{
	struct bfin_cf_socket *cf;

	if (!sp)
		return -EINVAL;

	cf = container_of(s, struct bfin_cf_socket, socket);

	if (bfin_cf_present(cf->cd_pfx)) {
		*sp = SS_READY | SS_DETECT | SS_POWERON | SS_3VCARD;
		s->pcmcia_irq = 0;
		s->pci_irq = cf->irq;

	} else
		*sp = 0;
	return 0;
}

static int
bfin_cf_set_socket(struct pcmcia_socket *sock, struct socket_state_t *s)
{

	struct bfin_cf_socket *cf;
	cf = container_of(sock, struct bfin_cf_socket, socket);

	switch (s->Vcc) {
	case 0:
	case 33:
		break;
	case 50:
		break;
	default:
		return -EINVAL;
	}

	if (s->flags & SS_RESET) {
		disable_irq(cf->irq);
		bfin_cf_reset();
		enable_irq(cf->irq);
	}

	dev_dbg(&cf->pdev->dev, ": Vcc %d, io_irq %d, flags %04x csc %04x\n",
		 s->Vcc, s->io_irq, s->flags, s->csc_mask);

	return 0;
}

static int bfin_cf_ss_suspend(struct pcmcia_socket *s)
{
	return bfin_cf_set_socket(s, &dead_socket);
}

/* regions are 2K each:  mem, attrib, io (and reserved-for-ide) */

static int bfin_cf_set_io_map(struct pcmcia_socket *s, struct pccard_io_map *io)
{
	struct bfin_cf_socket *cf;

	cf = container_of(s, struct bfin_cf_socket, socket);
	io->flags &= MAP_ACTIVE | MAP_ATTRIB | MAP_16BIT;
	io->start = cf->phys_cf_io;
	io->stop = io->start + SZ_2K - 1;
	return 0;
}

static int
bfin_cf_set_mem_map(struct pcmcia_socket *s, struct pccard_mem_map *map)
{
	struct bfin_cf_socket *cf;

	if (map->card_start)
		return -EINVAL;
	cf = container_of(s, struct bfin_cf_socket, socket);
	map->static_start = cf->phys_cf_io;
	map->flags &= MAP_ACTIVE | MAP_ATTRIB | MAP_16BIT;
	if (map->flags & MAP_ATTRIB)
		map->static_start = cf->phys_cf_attr;

	return 0;
}

static struct pccard_operations bfin_cf_ops = {
	.init = bfin_cf_ss_init,
	.suspend = bfin_cf_ss_suspend,
	.get_status = bfin_cf_get_status,
	.set_socket = bfin_cf_set_socket,
	.set_io_map = bfin_cf_set_io_map,
	.set_mem_map = bfin_cf_set_mem_map,
};

/*--------------------------------------------------------------------------*/

static int bfin_cf_probe(struct platform_device *pdev)
{
	struct bfin_cf_socket *cf;
	struct resource *io_mem, *attr_mem;
	int irq;
	unsigned short cd_pfx;
	int status = 0;

	dev_info(&pdev->dev, "Blackfin CompactFlash/PCMCIA Socket Driver\n");

	irq = platform_get_irq(pdev, 0);
	if (irq <= 0)
		return -EINVAL;

	cd_pfx = platform_get_irq(pdev, 1);	/*Card Detect GPIO PIN */

	if (gpio_request(cd_pfx, "pcmcia: CD")) {
		dev_err(&pdev->dev,
		       "Failed ro request Card Detect GPIO_%d\n",
		       cd_pfx);
		return -EBUSY;
	}
	gpio_direction_input(cd_pfx);

	cf = kzalloc(sizeof *cf, GFP_KERNEL);
	if (!cf) {
		gpio_free(cd_pfx);
		return -ENOMEM;
	}

	cf->cd_pfx = cd_pfx;

	setup_timer(&cf->timer, bfin_cf_timer, (unsigned long)cf);

	cf->pdev = pdev;
	platform_set_drvdata(pdev, cf);

	cf->irq = irq;
	cf->socket.pci_irq = irq;

	irq_set_irq_type(irq, IRQF_TRIGGER_LOW);

	io_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	attr_mem = platform_get_resource(pdev, IORESOURCE_MEM, 1);

	if (!io_mem || !attr_mem)
		goto fail0;

	cf->phys_cf_io = io_mem->start;
	cf->phys_cf_attr = attr_mem->start;

	/* pcmcia layer only remaps "real" memory */
	cf->socket.io_offset = (unsigned long)
	    ioremap(cf->phys_cf_io, SZ_2K);

	if (!cf->socket.io_offset)
		goto fail0;

	dev_err(&pdev->dev, ": on irq %d\n", irq);

	dev_dbg(&pdev->dev, ": %s\n",
		 bfin_cf_present(cf->cd_pfx) ? "present" : "(not present)");

	cf->socket.owner = THIS_MODULE;
	cf->socket.dev.parent = &pdev->dev;
	cf->socket.ops = &bfin_cf_ops;
	cf->socket.resource_ops = &pccard_static_ops;
	cf->socket.features = SS_CAP_PCCARD | SS_CAP_STATIC_MAP
	    | SS_CAP_MEM_ALIGN;
	cf->socket.map_size = SZ_2K;

	status = pcmcia_register_socket(&cf->socket);
	if (status < 0)
		goto fail2;

	cf->active = 1;
	mod_timer(&cf->timer, jiffies + POLL_INTERVAL);
	return 0;

fail2:
	iounmap((void __iomem *)cf->socket.io_offset);
	release_mem_region(cf->phys_cf_io, SZ_8K);

fail0:
	gpio_free(cf->cd_pfx);
	kfree(cf);
	platform_set_drvdata(pdev, NULL);

	return status;
}

static int bfin_cf_remove(struct platform_device *pdev)
{
	struct bfin_cf_socket *cf = platform_get_drvdata(pdev);

	gpio_free(cf->cd_pfx);
	cf->active = 0;
	pcmcia_unregister_socket(&cf->socket);
	del_timer_sync(&cf->timer);
	iounmap((void __iomem *)cf->socket.io_offset);
	release_mem_region(cf->phys_cf_io, SZ_8K);
	platform_set_drvdata(pdev, NULL);
	kfree(cf);
	return 0;
}

static struct platform_driver bfin_cf_driver = {
	.driver = {
		   .name = driver_name,
		   },
	.probe = bfin_cf_probe,
	.remove = bfin_cf_remove,
};

module_platform_driver(bfin_cf_driver);

MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>");
MODULE_DESCRIPTION("BFIN CF/PCMCIA Driver");
MODULE_LICENSE("GPL");
back to top