| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <deb9dd1d-84bf-75c7-2880-a7bcec880d47@suse.cz>
Date: Sat, 21 Apr 2018 18:16:15 +0200
From: Vlastimil Babka <vbabka@...e.cz>
To: Mike Kravetz <mike.kravetz@...cle.com>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org, linux-api@...r.kernel.org
Cc: Reinette Chatre <reinette.chatre@...el.com>,
Michal Hocko <mhocko@...nel.org>,
Christopher Lameter <cl@...ux.com>,
Guy Shattah <sguy@...lanox.com>,
Anshuman Khandual <khandual@...ux.vnet.ibm.com>,
Michal Nazarewicz <mina86@...a86.com>,
David Nellans <dnellans@...dia.com>,
Laura Abbott <labbott@...hat.com>, Pavel Machek <pavel@....cz>,
Dave Hansen <dave.hansen@...el.com>,
Andrew Morton <akpm@...ux-foundation.org>
Subject: [PATCH 2/3] mm: add find_alloc_contig_pages() interface
On 04/17/2018 04:09 AM, Mike Kravetz wrote:
> find_alloc_contig_pages() is a new interface that attempts to locate
> and allocate a contiguous range of pages. It is provided as a more
> convenient interface than alloc_contig_range() which is currently
> used by CMA and gigantic huge pages.
>
> When attempting to allocate a range of pages, migration is employed
> if possible. There is no guarantee that the routine will succeed.
> So, the user must be prepared for failure and have a fall back plan.
>
> Signed-off-by: Mike Kravetz <mike.kravetz@...cle.com>
Hi, just two quick observations, maybe discussion pointers for the
LSF/MM session:
- it's weird that find_alloc_contig_pages() takes an order, and
free_contig_pages() takes a nr_pages. I suspect the interface would be
more future-proof with both using nr_pages? Perhaps also minimum
alignment for the allocation side? Order is fine for hugetlb, but what
about other potential users?
- contig_alloc_migratetype_ok() says that MIGRATE_CMA blocks are OK to
allocate from. This silently assumes that everything allocated by this
will be migratable itself, or it might eat CMA reserves. Is it the case?
Also you then call alloc_contig_range() with MIGRATE_MOVABLE, so it will
skip/fail on MIGRATE_CMA anyway IIRC.
Vlastimil
> ---
> include/linux/gfp.h | 12 ++++++++
> mm/page_alloc.c | 89 +++++++++++++++++++++++++++++++++++++++++++++++++++--
> 2 files changed, 99 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/gfp.h b/include/linux/gfp.h
> index 86a0d06463ab..528b194cc266 100644
> --- a/include/linux/gfp.h
> +++ b/include/linux/gfp.h
> @@ -573,6 +573,18 @@ static inline bool pm_suspended_storage(void)
> extern int alloc_contig_range(unsigned long start, unsigned long end,
> unsigned migratetype, gfp_t gfp_mask);
> extern void free_contig_range(unsigned long pfn, unsigned long nr_pages);
> +extern struct page *find_alloc_contig_pages(unsigned int order, gfp_t gfp,
> + int nid, nodemask_t *nodemask);
> +extern void free_contig_pages(struct page *page, unsigned long nr_pages);
> +#else
> +static inline page *find_alloc_contig_pages(unsigned int order, gfp_t gfp,
> + int nid, nodemask_t *nodemask)
> +{
> + return NULL;
> +}
> +static void free_contig_pages(struct page *page, unsigned long nr_pages)
> +{
> +}
> #endif
>
> #ifdef CONFIG_CMA
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 0fd5e8e2456e..81070fe55c44 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -67,6 +67,7 @@
> #include <linux/ftrace.h>
> #include <linux/lockdep.h>
> #include <linux/nmi.h>
> +#include <linux/mmzone.h>
>
> #include <asm/sections.h>
> #include <asm/tlbflush.h>
> @@ -2010,9 +2011,13 @@ static __always_inline struct page *__rmqueue_cma_fallback(struct zone *zone,
> {
> return __rmqueue_smallest(zone, order, MIGRATE_CMA);
> }
> +#define contig_alloc_migratetype_ok(migratetype) \
> + ((migratetype) == MIGRATE_CMA || (migratetype) == MIGRATE_MOVABLE)
> #else
> static inline struct page *__rmqueue_cma_fallback(struct zone *zone,
> unsigned int order) { return NULL; }
> +#define contig_alloc_migratetype_ok(migratetype) \
> + ((migratetype) == MIGRATE_MOVABLE)
> #endif
>
> /*
> @@ -7822,6 +7827,9 @@ int alloc_contig_range(unsigned long start, unsigned long end,
> };
> INIT_LIST_HEAD(&cc.migratepages);
>
> + if (!contig_alloc_migratetype_ok(migratetype))
> + return -EINVAL;
> +
> /*
> * What we do here is we mark all pageblocks in range as
> * MIGRATE_ISOLATE. Because pageblock and max order pages may
> @@ -7912,8 +7920,9 @@ int alloc_contig_range(unsigned long start, unsigned long end,
>
> /* Make sure the range is really isolated. */
> if (test_pages_isolated(outer_start, end, false)) {
> - pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
> - __func__, outer_start, end);
> + if (!(migratetype == MIGRATE_MOVABLE)) /* only print for CMA */
> + pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
> + __func__, outer_start, end);
> ret = -EBUSY;
> goto done;
> }
> @@ -7949,6 +7958,82 @@ void free_contig_range(unsigned long pfn, unsigned long nr_pages)
> }
> WARN(count != 0, "%ld pages are still in use!\n", count);
> }
> +
> +static bool contig_pfn_range_valid(struct zone *z, unsigned long start_pfn,
> + unsigned long nr_pages)
> +{
> + unsigned long i, end_pfn = start_pfn + nr_pages;
> + struct page *page;
> +
> + for (i = start_pfn; i < end_pfn; i++) {
> + if (!pfn_valid(i))
> + return false;
> +
> + page = pfn_to_page(i);
> +
> + if (page_zone(page) != z)
> + return false;
> +
> + }
> +
> + return true;
> +}
> +
> +/**
> + * find_alloc_contig_pages() -- attempt to find and allocate a contiguous
> + * range of pages
> + * @order: number of pages
> + * @gfp: gfp mask used to limit search as well as during compaction
> + * @nid: target node
> + * @nodemask: mask of other possible nodes
> + *
> + * Pages can be freed with a call to free_contig_pages(), or by manually
> + * calling __free_page() for each page allocated.
> + *
> + * Return: pointer to 'order' pages on success, or NULL if not successful.
> + */
> +struct page *find_alloc_contig_pages(unsigned int order, gfp_t gfp,
> + int nid, nodemask_t *nodemask)
> +{
> + unsigned long pfn, nr_pages, flags;
> + struct page *ret_page = NULL;
> + struct zonelist *zonelist;
> + struct zoneref *z;
> + struct zone *zone;
> + int rc;
> +
> + nr_pages = 1 << order;
> + zonelist = node_zonelist(nid, gfp);
> + for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp),
> + nodemask) {
> + spin_lock_irqsave(&zone->lock, flags);
> + pfn = ALIGN(zone->zone_start_pfn, nr_pages);
> + while (zone_spans_pfn(zone, pfn + nr_pages - 1)) {
> + if (contig_pfn_range_valid(zone, pfn, nr_pages)) {
> + spin_unlock_irqrestore(&zone->lock, flags);
> +
> + rc = alloc_contig_range(pfn, pfn + nr_pages,
> + MIGRATE_MOVABLE, gfp);
> + if (!rc) {
> + ret_page = pfn_to_page(pfn);
> + return ret_page;
> + }
> + spin_lock_irqsave(&zone->lock, flags);
> + }
> + pfn += nr_pages;
> + }
> + spin_unlock_irqrestore(&zone->lock, flags);
> + }
> +
> + return ret_page;
> +}
> +EXPORT_SYMBOL_GPL(find_alloc_contig_pages);
> +
> +void free_contig_pages(struct page *page, unsigned long nr_pages)
> +{
> + free_contig_range(page_to_pfn(page), nr_pages);
> +}
> +EXPORT_SYMBOL_GPL(free_contig_pages);
> #endif
>
> #if defined CONFIG_MEMORY_HOTPLUG || defined CONFIG_CMA
>
Powered by blists - more mailing lists