linux/arch/x86/xen/spinlock.c
Raghavendra K T d6abfdb202 x86/spinlocks/paravirt: Fix memory corruption on unlock
Paravirt spinlock clears slowpath flag after doing unlock.
As explained by Linus currently it does:

                prev = *lock;
                add_smp(&lock->tickets.head, TICKET_LOCK_INC);

                /* add_smp() is a full mb() */

                if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG))
                        __ticket_unlock_slowpath(lock, prev);

which is *exactly* the kind of things you cannot do with spinlocks,
because after you've done the "add_smp()" and released the spinlock
for the fast-path, you can't access the spinlock any more.  Exactly
because a fast-path lock might come in, and release the whole data
structure.

Linus suggested that we should not do any writes to lock after unlock(),
and we can move slowpath clearing to fastpath lock.

So this patch implements the fix with:

 1. Moving slowpath flag to head (Oleg):
    Unlocked locks don't care about the slowpath flag; therefore we can keep
    it set after the last unlock, and clear it again on the first (try)lock.
    -- this removes the write after unlock. note that keeping slowpath flag would
    result in unnecessary kicks.
    By moving the slowpath flag from the tail to the head ticket we also avoid
    the need to access both the head and tail tickets on unlock.

 2. use xadd to avoid read/write after unlock that checks the need for
    unlock_kick (Linus):
    We further avoid the need for a read-after-release by using xadd;
    the prev head value will include the slowpath flag and indicate if we
    need to do PV kicking of suspended spinners -- on modern chips xadd
    isn't (much) more expensive than an add + load.

Result:
 setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
 benchmark overcommit %improve
 kernbench  1x           -0.13
 kernbench  2x            0.02
 dbench     1x           -1.77
 dbench     2x           -0.63

[Jeremy: Hinted missing TICKET_LOCK_INC for kick]
[Oleg: Moved slowpath flag to head, ticket_equals idea]
[PeterZ: Added detailed changelog]

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Andrew Jones <drjones@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: a.ryabinin@samsung.com
Cc: dave@stgolabs.net
Cc: hpa@zytor.com
Cc: jasowang@redhat.com
Cc: jeremy@goop.org
Cc: paul.gortmaker@windriver.com
Cc: riel@redhat.com
Cc: tglx@linutronix.de
Cc: waiman.long@hp.com
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/20150215173043.GA7471@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-18 14:53:49 +01:00

354 lines
8.3 KiB
C

/*
* Split spinlock implementation out into its own file, so it can be
* compiled in a FTRACE-compatible way.
*/
#include <linux/kernel_stat.h>
#include <linux/spinlock.h>
#include <linux/debugfs.h>
#include <linux/log2.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <asm/paravirt.h>
#include <xen/interface/xen.h>
#include <xen/events.h>
#include "xen-ops.h"
#include "debugfs.h"
enum xen_contention_stat {
TAKEN_SLOW,
TAKEN_SLOW_PICKUP,
TAKEN_SLOW_SPURIOUS,
RELEASED_SLOW,
RELEASED_SLOW_KICKED,
NR_CONTENTION_STATS
};
#ifdef CONFIG_XEN_DEBUG_FS
#define HISTO_BUCKETS 30
static struct xen_spinlock_stats
{
u32 contention_stats[NR_CONTENTION_STATS];
u32 histo_spin_blocked[HISTO_BUCKETS+1];
u64 time_blocked;
} spinlock_stats;
static u8 zero_stats;
static inline void check_zero(void)
{
u8 ret;
u8 old = READ_ONCE(zero_stats);
if (unlikely(old)) {
ret = cmpxchg(&zero_stats, old, 0);
/* This ensures only one fellow resets the stat */
if (ret == old)
memset(&spinlock_stats, 0, sizeof(spinlock_stats));
}
}
static inline void add_stats(enum xen_contention_stat var, u32 val)
{
check_zero();
spinlock_stats.contention_stats[var] += val;
}
static inline u64 spin_time_start(void)
{
return xen_clocksource_read();
}
static void __spin_time_accum(u64 delta, u32 *array)
{
unsigned index = ilog2(delta);
check_zero();
if (index < HISTO_BUCKETS)
array[index]++;
else
array[HISTO_BUCKETS]++;
}
static inline void spin_time_accum_blocked(u64 start)
{
u32 delta = xen_clocksource_read() - start;
__spin_time_accum(delta, spinlock_stats.histo_spin_blocked);
spinlock_stats.time_blocked += delta;
}
#else /* !CONFIG_XEN_DEBUG_FS */
static inline void add_stats(enum xen_contention_stat var, u32 val)
{
}
static inline u64 spin_time_start(void)
{
return 0;
}
static inline void spin_time_accum_blocked(u64 start)
{
}
#endif /* CONFIG_XEN_DEBUG_FS */
struct xen_lock_waiting {
struct arch_spinlock *lock;
__ticket_t want;
};
static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
static DEFINE_PER_CPU(char *, irq_name);
static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
static cpumask_t waiting_cpus;
static bool xen_pvspin = true;
__visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
{
int irq = __this_cpu_read(lock_kicker_irq);
struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting);
int cpu = smp_processor_id();
u64 start;
__ticket_t head;
unsigned long flags;
/* If kicker interrupts not initialized yet, just spin */
if (irq == -1)
return;
start = spin_time_start();
/*
* Make sure an interrupt handler can't upset things in a
* partially setup state.
*/
local_irq_save(flags);
/*
* We don't really care if we're overwriting some other
* (lock,want) pair, as that would mean that we're currently
* in an interrupt context, and the outer context had
* interrupts enabled. That has already kicked the VCPU out
* of xen_poll_irq(), so it will just return spuriously and
* retry with newly setup (lock,want).
*
* The ordering protocol on this is that the "lock" pointer
* may only be set non-NULL if the "want" ticket is correct.
* If we're updating "want", we must first clear "lock".
*/
w->lock = NULL;
smp_wmb();
w->want = want;
smp_wmb();
w->lock = lock;
/* This uses set_bit, which atomic and therefore a barrier */
cpumask_set_cpu(cpu, &waiting_cpus);
add_stats(TAKEN_SLOW, 1);
/* clear pending */
xen_clear_irq_pending(irq);
/* Only check lock once pending cleared */
barrier();
/*
* Mark entry to slowpath before doing the pickup test to make
* sure we don't deadlock with an unlocker.
*/
__ticket_enter_slowpath(lock);
/* make sure enter_slowpath, which is atomic does not cross the read */
smp_mb__after_atomic();
/*
* check again make sure it didn't become free while
* we weren't looking
*/
head = READ_ONCE(lock->tickets.head);
if (__tickets_equal(head, want)) {
add_stats(TAKEN_SLOW_PICKUP, 1);
goto out;
}
/* Allow interrupts while blocked */
local_irq_restore(flags);
/*
* If an interrupt happens here, it will leave the wakeup irq
* pending, which will cause xen_poll_irq() to return
* immediately.
*/
/* Block until irq becomes pending (or perhaps a spurious wakeup) */
xen_poll_irq(irq);
add_stats(TAKEN_SLOW_SPURIOUS, !xen_test_irq_pending(irq));
local_irq_save(flags);
kstat_incr_irq_this_cpu(irq);
out:
cpumask_clear_cpu(cpu, &waiting_cpus);
w->lock = NULL;
local_irq_restore(flags);
spin_time_accum_blocked(start);
}
PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning);
static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
{
int cpu;
add_stats(RELEASED_SLOW, 1);
for_each_cpu(cpu, &waiting_cpus) {
const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu);
/* Make sure we read lock before want */
if (READ_ONCE(w->lock) == lock &&
READ_ONCE(w->want) == next) {
add_stats(RELEASED_SLOW_KICKED, 1);
xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
break;
}
}
}
static irqreturn_t dummy_handler(int irq, void *dev_id)
{
BUG();
return IRQ_HANDLED;
}
void xen_init_lock_cpu(int cpu)
{
int irq;
char *name;
if (!xen_pvspin)
return;
WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n",
cpu, per_cpu(lock_kicker_irq, cpu));
name = kasprintf(GFP_KERNEL, "spinlock%d", cpu);
irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR,
cpu,
dummy_handler,
IRQF_PERCPU|IRQF_NOBALANCING,
name,
NULL);
if (irq >= 0) {
disable_irq(irq); /* make sure it's never delivered */
per_cpu(lock_kicker_irq, cpu) = irq;
per_cpu(irq_name, cpu) = name;
}
printk("cpu %d spinlock event irq %d\n", cpu, irq);
}
void xen_uninit_lock_cpu(int cpu)
{
if (!xen_pvspin)
return;
unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL);
per_cpu(lock_kicker_irq, cpu) = -1;
kfree(per_cpu(irq_name, cpu));
per_cpu(irq_name, cpu) = NULL;
}
/*
* Our init of PV spinlocks is split in two init functions due to us
* using paravirt patching and jump labels patching and having to do
* all of this before SMP code is invoked.
*
* The paravirt patching needs to be done _before_ the alternative asm code
* is started, otherwise we would not patch the core kernel code.
*/
void __init xen_init_spinlocks(void)
{
if (!xen_pvspin) {
printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
return;
}
printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
pv_lock_ops.unlock_kick = xen_unlock_kick;
}
/*
* While the jump_label init code needs to happend _after_ the jump labels are
* enabled and before SMP is started. Hence we use pre-SMP initcall level
* init. We cannot do it in xen_init_spinlocks as that is done before
* jump labels are activated.
*/
static __init int xen_init_spinlocks_jump(void)
{
if (!xen_pvspin)
return 0;
if (!xen_domain())
return 0;
static_key_slow_inc(&paravirt_ticketlocks_enabled);
return 0;
}
early_initcall(xen_init_spinlocks_jump);
static __init int xen_parse_nopvspin(char *arg)
{
xen_pvspin = false;
return 0;
}
early_param("xen_nopvspin", xen_parse_nopvspin);
#ifdef CONFIG_XEN_DEBUG_FS
static struct dentry *d_spin_debug;
static int __init xen_spinlock_debugfs(void)
{
struct dentry *d_xen = xen_init_debugfs();
if (d_xen == NULL)
return -ENOMEM;
if (!xen_pvspin)
return 0;
d_spin_debug = debugfs_create_dir("spinlocks", d_xen);
debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats);
debugfs_create_u32("taken_slow", 0444, d_spin_debug,
&spinlock_stats.contention_stats[TAKEN_SLOW]);
debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug,
&spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]);
debugfs_create_u32("taken_slow_spurious", 0444, d_spin_debug,
&spinlock_stats.contention_stats[TAKEN_SLOW_SPURIOUS]);
debugfs_create_u32("released_slow", 0444, d_spin_debug,
&spinlock_stats.contention_stats[RELEASED_SLOW]);
debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug,
&spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]);
debugfs_create_u64("time_blocked", 0444, d_spin_debug,
&spinlock_stats.time_blocked);
debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
return 0;
}
fs_initcall(xen_spinlock_debugfs);
#endif /* CONFIG_XEN_DEBUG_FS */