mm: fix endless reclaim on machines with unaccepted memory

JIRA: https://issues.redhat.com/browse/RHEL-27745

This patch is a backport of the following upstream commit:
commit 807174a93d24c456503692dc3f5af322ee0b640a
Author: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Date:   Fri Aug 9 14:48:47 2024 +0300

    mm: fix endless reclaim on machines with unaccepted memory

    Unaccepted memory is considered unusable free memory, which is not counted
    as free on the zone watermark check.  This causes get_page_from_freelist()
    to accept more memory to hit the high watermark, but it creates problems
    in the reclaim path.

    The reclaim path encounters a failed zone watermark check and attempts to
    reclaim memory.  This is usually successful, but if there is little or no
    reclaimable memory, it can result in endless reclaim with little to no
    progress.  This can occur early in the boot process, just after start of
    the init process when the only reclaimable memory is the page cache of the
    init executable and its libraries.

    Make unaccepted memory free from watermark check point of view.  This way
    unaccepted memory will never be the trigger of memory reclaim.  Accept
    more memory in the get_page_from_freelist() if needed.

    Link: https://lkml.kernel.org/r/20240809114854.3745464-2-kirill.shutemov@linux.intel.com
    Fixes: dcdfdd40fa82 ("mm: Add support for unaccepted memory")
    Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
    Reported-by: Jianxiong Gao <jxgao@google.com>
    Acked-by: David Hildenbrand <david@redhat.com>
    Tested-by: Jianxiong Gao <jxgao@google.com>
    Cc: Borislav Petkov <bp@alien8.de>
    Cc: Johannes Weiner <hannes@cmpxchg.org>
    Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
    Cc: Matthew Wilcox <willy@infradead.org>
    Cc: Mel Gorman <mgorman@suse.de>
    Cc: Mike Rapoport (Microsoft) <rppt@kernel.org>
    Cc: Tom Lendacky <thomas.lendacky@amd.com>
    Cc: Vlastimil Babka <vbabka@suse.cz>
    Cc: <stable@vger.kernel.org>    [6.5+]
    Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Signed-off-by: Rafael Aquini <raquini@redhat.com>
This commit is contained in:
Rafael Aquini 2024-12-09 12:19:08 -05:00
parent e424cdc28a
commit fb85eb34b8
1 changed files with 20 additions and 22 deletions

View File

@ -303,7 +303,7 @@ EXPORT_SYMBOL(nr_online_nodes);
static bool page_contains_unaccepted(struct page *page, unsigned int order);
static void accept_page(struct page *page, unsigned int order);
static bool try_to_accept_memory(struct zone *zone, unsigned int order);
static bool cond_accept_memory(struct zone *zone, unsigned int order);
static inline bool has_unaccepted_memory(void);
static bool __free_unaccepted(struct page *page);
@ -2951,9 +2951,6 @@ static inline long __zone_watermark_unusable_free(struct zone *z,
if (!(alloc_flags & ALLOC_CMA))
unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
#endif
#ifdef CONFIG_UNACCEPTED_MEMORY
unusable_free += zone_page_state(z, NR_UNACCEPTED);
#endif
return unusable_free;
}
@ -3247,6 +3244,8 @@ retry:
}
}
cond_accept_memory(zone, order);
/*
* Detect whether the number of free pages is below high
* watermark. If so, we will decrease pcp->high and free
@ -3272,10 +3271,8 @@ check_alloc_wmark:
gfp_mask)) {
int ret;
if (has_unaccepted_memory()) {
if (try_to_accept_memory(zone, order))
goto try_this_zone;
}
if (cond_accept_memory(zone, order))
goto try_this_zone;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
@ -3329,10 +3326,8 @@ try_this_zone:
return page;
} else {
if (has_unaccepted_memory()) {
if (try_to_accept_memory(zone, order))
goto try_this_zone;
}
if (cond_accept_memory(zone, order))
goto try_this_zone;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/* Try again if zone has deferred pages */
@ -6806,9 +6801,6 @@ static bool try_to_accept_memory_one(struct zone *zone)
struct page *page;
bool last;
if (list_empty(&zone->unaccepted_pages))
return false;
spin_lock_irqsave(&zone->lock, flags);
page = list_first_entry_or_null(&zone->unaccepted_pages,
struct page, lru);
@ -6834,23 +6826,29 @@ static bool try_to_accept_memory_one(struct zone *zone)
return true;
}
static bool try_to_accept_memory(struct zone *zone, unsigned int order)
static bool cond_accept_memory(struct zone *zone, unsigned int order)
{
long to_accept;
int ret = false;
bool ret = false;
if (!has_unaccepted_memory())
return false;
if (list_empty(&zone->unaccepted_pages))
return false;
/* How much to accept to get to high watermark? */
to_accept = high_wmark_pages(zone) -
(zone_page_state(zone, NR_FREE_PAGES) -
__zone_watermark_unusable_free(zone, order, 0));
__zone_watermark_unusable_free(zone, order, 0) -
zone_page_state(zone, NR_UNACCEPTED));
/* Accept at least one page */
do {
while (to_accept > 0) {
if (!try_to_accept_memory_one(zone))
break;
ret = true;
to_accept -= MAX_ORDER_NR_PAGES;
} while (to_accept > 0);
}
return ret;
}
@ -6893,7 +6891,7 @@ static void accept_page(struct page *page, unsigned int order)
{
}
static bool try_to_accept_memory(struct zone *zone, unsigned int order)
static bool cond_accept_memory(struct zone *zone, unsigned int order)
{
return false;
}