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
balloon_compaction.c
/*
* mm/balloon_compaction.c
*
* Common interface for making balloon pages movable by compaction.
*
* Copyright (C) 2012, Red Hat, Inc. Rafael Aquini <aquini@redhat.com>
*/
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/balloon_compaction.h>
/*
* balloon_page_enqueue - allocates a new page and inserts it into the balloon
* page list.
* @b_dev_info: balloon device descriptor where we will insert a new page to
*
* Driver must call it to properly allocate a new enlisted balloon page
* before definitively removing it from the guest system.
* This function returns the page address for the recently enqueued page or
* NULL in the case we fail to allocate a new page this turn.
*/
struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
{
unsigned long flags;
struct page *page = alloc_page(balloon_mapping_gfp_mask() |
__GFP_NOMEMALLOC | __GFP_NORETRY);
if (!page)
return NULL;
/*
* Block others from accessing the 'page' when we get around to
* establishing additional references. We should be the only one
* holding a reference to the 'page' at this point.
*/
BUG_ON(!trylock_page(page));
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
balloon_page_insert(b_dev_info, page);
__count_vm_event(BALLOON_INFLATE);
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
unlock_page(page);
return page;
}
EXPORT_SYMBOL_GPL(balloon_page_enqueue);
/*
* balloon_page_dequeue - removes a page from balloon's page list and returns
* the its address to allow the driver release the page.
* @b_dev_info: balloon device decriptor where we will grab a page from.
*
* Driver must call it to properly de-allocate a previous enlisted balloon page
* before definetively releasing it back to the guest system.
* This function returns the page address for the recently dequeued page or
* NULL in the case we find balloon's page list temporarily empty due to
* compaction isolated pages.
*/
struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
{
struct page *page, *tmp;
unsigned long flags;
bool dequeued_page;
dequeued_page = false;
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
list_for_each_entry_safe(page, tmp, &b_dev_info->pages, lru) {
/*
* Block others from accessing the 'page' while we get around
* establishing additional references and preparing the 'page'
* to be released by the balloon driver.
*/
if (trylock_page(page)) {
#ifdef CONFIG_BALLOON_COMPACTION
if (PageIsolated(page)) {
/* raced with isolation */
unlock_page(page);
continue;
}
#endif
balloon_page_delete(page);
__count_vm_event(BALLOON_DEFLATE);
unlock_page(page);
dequeued_page = true;
break;
}
}
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
if (!dequeued_page) {
/*
* If we are unable to dequeue a balloon page because the page
* list is empty and there is no isolated pages, then something
* went out of track and some balloon pages are lost.
* BUG() here, otherwise the balloon driver may get stuck into
* an infinite loop while attempting to release all its pages.
*/
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
if (unlikely(list_empty(&b_dev_info->pages) &&
!b_dev_info->isolated_pages))
BUG();
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
page = NULL;
}
return page;
}
EXPORT_SYMBOL_GPL(balloon_page_dequeue);
#ifdef CONFIG_BALLOON_COMPACTION
bool balloon_page_isolate(struct page *page, isolate_mode_t mode)
{
struct balloon_dev_info *b_dev_info = balloon_page_device(page);
unsigned long flags;
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
list_del(&page->lru);
b_dev_info->isolated_pages++;
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
return true;
}
void balloon_page_putback(struct page *page)
{
struct balloon_dev_info *b_dev_info = balloon_page_device(page);
unsigned long flags;
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
list_add(&page->lru, &b_dev_info->pages);
b_dev_info->isolated_pages--;
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
}
/* move_to_new_page() counterpart for a ballooned page */
int balloon_page_migrate(struct address_space *mapping,
struct page *newpage, struct page *page,
enum migrate_mode mode)
{
struct balloon_dev_info *balloon = balloon_page_device(page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
return balloon->migratepage(balloon, newpage, page, mode);
}
const struct address_space_operations balloon_aops = {
.migratepage = balloon_page_migrate,
.isolate_page = balloon_page_isolate,
.putback_page = balloon_page_putback,
};
EXPORT_SYMBOL_GPL(balloon_aops);
#endif /* CONFIG_BALLOON_COMPACTION */
Computing file changes ...