|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-devel] [PATCH v7 2/3] mm: make pages allocated with MEMF_no_refcount safe to assign
Currently it is unsafe to assign a domheap page allocated with
MEMF_no_refcount to a domain because the domain't 'tot_pages' will not
be incremented, but will be decrement when the page is freed (since
free_domheap_pages() has no way of telling that the increment was skipped).
This patch allocates a new 'count_info' bit for a PGC_extra flag
which is then used to mark pages when alloc_domheap_pages() is called
with MEMF_no_refcount. The MEMF_no_refcount is *not* passed through to
assign_pages() because it still needs to call domain_adjust_tot_pages() to
make sure the domain is appropriately referenced. assign_pages() is
accordingly modified to account pages marked with PGC_extra to an
'extra_pages' counter, which is then subtracted from 'tot_pages' before it
is checked against 'max_pages', thus avoiding over-allocation errors.
NOTE: steal_page() is also modified to decrement extra_pages in the case of
a PGC_extra page being stolen from a domain.
Also, whilst adding the extra_pages counter into struct domain, make
some cosmetic fixes to comments for neighbouring fields.
Signed-off-by: Paul Durrant <pdurrant@xxxxxxxxxx>
---
Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Cc: George Dunlap <George.Dunlap@xxxxxxxxxxxxx>
Cc: Ian Jackson <ian.jackson@xxxxxxxxxxxxx>
Cc: Jan Beulich <jbeulich@xxxxxxxx>
Cc: Julien Grall <julien@xxxxxxx>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
Cc: Stefano Stabellini <sstabellini@xxxxxxxxxx>
Cc: Wei Liu <wl@xxxxxxx>
Cc: Volodymyr Babchuk <Volodymyr_Babchuk@xxxxxxxx>
Cc: "Roger Pau Monné" <roger.pau@xxxxxxxxxx>
v7:
- s/PGC_no_refcount/PGC_extra/g
- Re-work allocation to account for 'extra' pages, also making it
safe to assign PGC_extra pages post-allocation
v6:
- Add an extra ASSERT into assign_pages() that PGC_no_refcount is not
set if MEMF_no_refcount is clear
- ASSERT that count_info is 0 in alloc_domheap_pages() and set to
PGC_no_refcount rather than ORing
v5:
- Make sure PGC_no_refcount is set before assign_pages() is called
- Don't bother to clear PGC_no_refcount in free_domheap_pages() and
drop ASSERT in free_heap_pages()
- Don't latch count_info in free_heap_pages()
v4:
- New in v4
---
xen/arch/x86/mm.c | 5 ++++
xen/common/page_alloc.c | 49 +++++++++++++++++++++++++++++-----------
xen/include/asm-arm/mm.h | 5 +++-
xen/include/asm-x86/mm.h | 7 ++++--
xen/include/xen/sched.h | 18 ++++++++-------
5 files changed, 60 insertions(+), 24 deletions(-)
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index f50c065af3..5b04db8c21 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -4266,6 +4266,11 @@ int steal_page(
page_list_del(page, &d->page_list);
/* Unlink from original owner. */
+ if ( page->count_info & PGC_extra )
+ {
+ ASSERT(d->extra_pages);
+ d->extra_pages--;
+ }
if ( !(memflags & MEMF_no_refcount) && !domain_adjust_tot_pages(d, -1) )
drop_dom_ref = true;
diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c
index 919a270587..a2d69f222a 100644
--- a/xen/common/page_alloc.c
+++ b/xen/common/page_alloc.c
@@ -2256,6 +2256,7 @@ int assign_pages(
{
int rc = 0;
unsigned long i;
+ unsigned int extra_pages = 0;
spin_lock(&d->page_alloc_lock);
@@ -2267,13 +2268,19 @@ int assign_pages(
goto out;
}
+ for ( i = 0; i < (1 << order); i++ )
+ if ( pg[i].count_info & PGC_extra )
+ extra_pages++;
+
if ( !(memflags & MEMF_no_refcount) )
{
- if ( unlikely((d->tot_pages + (1 << order)) > d->max_pages) )
+ unsigned int max_pages = d->max_pages - d->extra_pages - extra_pages;
+
+ if ( unlikely((d->tot_pages + (1 << order)) > max_pages) )
{
gprintk(XENLOG_INFO, "Over-allocation for domain %u: "
"%u > %u\n", d->domain_id,
- d->tot_pages + (1 << order), d->max_pages);
+ d->tot_pages + (1 << order), max_pages);
rc = -E2BIG;
goto out;
}
@@ -2282,13 +2289,17 @@ int assign_pages(
get_knownalive_domain(d);
}
+ d->extra_pages += extra_pages;
for ( i = 0; i < (1 << order); i++ )
{
+ unsigned long count_info = pg[i].count_info;
+
ASSERT(page_get_owner(&pg[i]) == NULL);
- ASSERT(!pg[i].count_info);
+ ASSERT(!(count_info & ~PGC_extra));
page_set_owner(&pg[i], d);
smp_wmb(); /* Domain pointer must be visible before updating refcnt. */
- pg[i].count_info = PGC_allocated | 1;
+ count_info &= PGC_extra;
+ pg[i].count_info = count_info | PGC_allocated | 1;
page_list_add_tail(&pg[i], &d->page_list);
}
@@ -2314,11 +2325,6 @@ struct page_info *alloc_domheap_pages(
if ( memflags & MEMF_no_owner )
memflags |= MEMF_no_refcount;
- else if ( (memflags & MEMF_no_refcount) && d )
- {
- ASSERT(!(memflags & MEMF_no_refcount));
- return NULL;
- }
if ( !dma_bitsize )
memflags &= ~MEMF_no_dma;
@@ -2331,11 +2337,23 @@ struct page_info *alloc_domheap_pages(
memflags, d)) == NULL)) )
return NULL;
- if ( d && !(memflags & MEMF_no_owner) &&
- assign_pages(d, pg, order, memflags) )
+ if ( d && !(memflags & MEMF_no_owner) )
{
- free_heap_pages(pg, order, memflags & MEMF_no_scrub);
- return NULL;
+ if ( memflags & MEMF_no_refcount )
+ {
+ unsigned long i;
+
+ for ( i = 0; i < (1ul << order); i++ )
+ {
+ ASSERT(!pg[i].count_info);
+ pg[i].count_info = PGC_extra;
+ }
+ }
+ if ( assign_pages(d, pg, order, memflags & ~MEMF_no_refcount) )
+ {
+ free_heap_pages(pg, order, memflags & MEMF_no_scrub);
+ return NULL;
+ }
}
return pg;
@@ -2383,6 +2401,11 @@ void free_domheap_pages(struct page_info *pg, unsigned
int order)
BUG();
}
arch_free_heap_page(d, &pg[i]);
+ if ( pg[i].count_info & PGC_extra )
+ {
+ ASSERT(d->extra_pages);
+ d->extra_pages--;
+ }
}
drop_dom_ref = !domain_adjust_tot_pages(d, -(1 << order));
diff --git a/xen/include/asm-arm/mm.h b/xen/include/asm-arm/mm.h
index 333efd3a60..7df91280bc 100644
--- a/xen/include/asm-arm/mm.h
+++ b/xen/include/asm-arm/mm.h
@@ -119,9 +119,12 @@ struct page_info
#define PGC_state_offlined PG_mask(2, 9)
#define PGC_state_free PG_mask(3, 9)
#define page_state_is(pg, st) (((pg)->count_info&PGC_state) == PGC_state_##st)
+/* Page is not reference counted */
+#define _PGC_extra PG_shift(10)
+#define PGC_extra PG_mask(1, 10)
/* Count of references to this frame. */
-#define PGC_count_width PG_shift(9)
+#define PGC_count_width PG_shift(10)
#define PGC_count_mask ((1UL<<PGC_count_width)-1)
/*
diff --git a/xen/include/asm-x86/mm.h b/xen/include/asm-x86/mm.h
index 2ca8882ad0..06d64d494d 100644
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -77,9 +77,12 @@
#define PGC_state_offlined PG_mask(2, 9)
#define PGC_state_free PG_mask(3, 9)
#define page_state_is(pg, st) (((pg)->count_info&PGC_state) == PGC_state_##st)
+/* Page is not reference counted */
+#define _PGC_extra PG_shift(10)
+#define PGC_extra PG_mask(1, 10)
- /* Count of references to this frame. */
-#define PGC_count_width PG_shift(9)
+/* Count of references to this frame. */
+#define PGC_count_width PG_shift(10)
#define PGC_count_mask ((1UL<<PGC_count_width)-1)
/*
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index 7c5c437247..763fcd56a4 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -361,15 +361,17 @@ struct domain
spinlock_t domain_lock;
- spinlock_t page_alloc_lock; /* protects all the following fields */
- struct page_list_head page_list; /* linked list */
+ spinlock_t page_alloc_lock; /* protects all the following fields */
+ struct page_list_head page_list; /* linked list */
struct page_list_head xenpage_list; /* linked list (size xenheap_pages) */
- unsigned int tot_pages; /* number of pages currently possesed */
- unsigned int xenheap_pages; /* # pages allocated from Xen heap */
- unsigned int outstanding_pages; /* pages claimed but not possessed */
- unsigned int max_pages; /* maximum value for tot_pages */
- atomic_t shr_pages; /* number of shared pages */
- atomic_t paged_pages; /* number of paged-out pages */
+ unsigned int tot_pages; /* number of pages currently possesed
*/
+ unsigned int xenheap_pages; /* number of pages from Xen heap */
+ unsigned int outstanding_pages; /* pages claimed but not possessed */
+ unsigned int extra_pages; /* extra pages not limited by
max_pages */
+ unsigned int max_pages; /* maximum value for tot_pages minus */
+ /* extra_pages */
+ atomic_t shr_pages; /* number of shared pages */
+ atomic_t paged_pages; /* number of paged-out pages */
/* Scheduling. */
void *sched_priv; /* scheduler-specific data */
--
2.20.1
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |