linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Shivank Garg <shivankg@amd.com>
To: <seanjc@google.com>, <david@redhat.com>, <vbabka@suse.cz>,
	<willy@infradead.org>, <akpm@linux-foundation.org>,
	<shuah@kernel.org>, <pbonzini@redhat.com>
Cc: <ackerleytng@google.com>, <paul@paul-moore.com>,
	<jmorris@namei.org>, <serge@hallyn.com>, <pvorel@suse.cz>,
	<bfoster@redhat.com>, <tabba@google.com>, <vannapurve@google.com>,
	<chao.gao@intel.com>, <bharata@amd.com>, <nikunj@amd.com>,
	<michael.day@amd.com>, <yan.y.zhao@intel.com>,
	<Neeraj.Upadhyay@amd.com>, <thomas.lendacky@amd.com>,
	<michael.roth@amd.com>, <aik@amd.com>, <jgg@nvidia.com>,
	<kalyazin@amazon.com>, <peterx@redhat.com>, <shivankg@amd.com>,
	<linux-fsdevel@vger.kernel.org>, <linux-mm@kvack.org>,
	<linux-kernel@vger.kernel.org>,
	<linux-security-module@vger.kernel.org>, <kvm@vger.kernel.org>,
	<linux-kselftest@vger.kernel.org>, <linux-coco@lists.linux.dev>
Subject: [PATCH RFC v7 1/8] mm/filemap: Add mempolicy support to the filemap layer
Date: Tue, 8 Apr 2025 11:23:55 +0000	[thread overview]
Message-ID: <20250408112402.181574-2-shivankg@amd.com> (raw)
In-Reply-To: <20250408112402.181574-1-shivankg@amd.com>

From: Shivansh Dhiman <shivansh.dhiman@amd.com>

Add NUMA mempolicy support to the filemap allocation path by introducing
new APIs that take a mempolicy argument:
- filemap_grab_folio_mpol()
- filemap_alloc_folio_mpol()
- __filemap_get_folio_mpol()

These APIs allow callers to specify a NUMA policy during page cache
allocations, enabling fine-grained control over memory placement. This is
particularly needed by KVM when using guest-memfd memory backends, where
the guest memory needs to be allocated according to the NUMA policy
specified by VMM.

The existing non-mempolicy APIs remain unchanged and continue to use the
default allocation behavior.

Signed-off-by: Shivansh Dhiman <shivansh.dhiman@amd.com>
Signed-off-by: Shivank Garg <shivankg@amd.com>
---
 include/linux/pagemap.h | 41 +++++++++++++++++++++++++++++++++++++++++
 mm/filemap.c            | 27 +++++++++++++++++++++++----
 2 files changed, 64 insertions(+), 4 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 26baa78f1ca7..bc5231626557 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -637,15 +637,24 @@ static inline void *detach_page_private(struct page *page)
 
 #ifdef CONFIG_NUMA
 struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order);
+struct folio *filemap_alloc_folio_mpol_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *mpol, pgoff_t ilx);
 #else
 static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
 {
 	return folio_alloc_noprof(gfp, order);
 }
+static inline struct folio *filemap_alloc_folio_mpol_noprof(gfp_t gfp,
+		unsigned int order, struct mempolicy *mpol, pgoff_t ilx)
+{
+	return filemap_alloc_folio_noprof(gfp, order);
+}
 #endif
 
 #define filemap_alloc_folio(...)				\
 	alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__))
+#define filemap_alloc_folio_mpol(...)				\
+	alloc_hooks(filemap_alloc_folio_mpol_noprof(__VA_ARGS__))
 
 static inline struct page *__page_cache_alloc(gfp_t gfp)
 {
@@ -737,6 +746,8 @@ static inline fgf_t fgf_set_order(size_t size)
 void *filemap_get_entry(struct address_space *mapping, pgoff_t index);
 struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		fgf_t fgp_flags, gfp_t gfp);
+struct folio *__filemap_get_folio_mpol(struct address_space *mapping,
+		pgoff_t index, fgf_t fgp_flags, gfp_t gfp, struct mempolicy *mpol, pgoff_t ilx);
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 		fgf_t fgp_flags, gfp_t gfp);
 
@@ -795,6 +806,36 @@ static inline struct folio *filemap_grab_folio(struct address_space *mapping,
 			mapping_gfp_mask(mapping));
 }
 
+/**
+ * filemap_grab_folio_mpol - grab a folio from the page cache.
+ * @mapping: The address space to search.
+ * @index: The page index.
+ * @mpol: The mempolicy to apply when allocating a new folio.
+ * @ilx: The interleave index, for use only with MPOL_INTERLEAVE or
+ *       MPOL_WEIGHTED_INTERLEAVE.
+ *
+ * Same as filemap_grab_folio(), except that it allocates the folio using
+ * given memory policy.
+ *
+ * Return: A found or created folio. ERR_PTR(-ENOMEM) if no folio is found
+ * and failed to create a folio.
+ */
+#ifdef CONFIG_NUMA
+static inline struct folio *filemap_grab_folio_mpol(struct address_space *mapping,
+					pgoff_t index, struct mempolicy *mpol, pgoff_t ilx)
+{
+	return __filemap_get_folio_mpol(mapping, index,
+			FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
+			mapping_gfp_mask(mapping), mpol, ilx);
+}
+#else
+static inline struct folio *filemap_grab_folio_mpol(struct address_space *mapping,
+					pgoff_t index, struct mempolicy *mpol, pgoff_t ilx)
+{
+	return filemap_grab_folio(mapping, index);
+}
+#endif /* CONFIG_NUMA */
+
 /**
  * find_get_page - find and get a page reference
  * @mapping: the address_space to search
diff --git a/mm/filemap.c b/mm/filemap.c
index b5e784f34d98..7b06ee4b4d63 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1007,6 +1007,15 @@ struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
 	return folio_alloc_noprof(gfp, order);
 }
 EXPORT_SYMBOL(filemap_alloc_folio_noprof);
+
+struct folio *filemap_alloc_folio_mpol_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *mpol, pgoff_t ilx)
+{
+	if (mpol)
+		return folio_alloc_mpol_noprof(gfp, order, mpol,
+					       ilx, numa_node_id());
+	return filemap_alloc_folio_noprof(gfp, order);
+}
 #endif
 
 /*
@@ -1880,11 +1889,14 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index)
 }
 
 /**
- * __filemap_get_folio - Find and get a reference to a folio.
+ * __filemap_get_folio_mpol - Find and get a reference to a folio.
  * @mapping: The address_space to search.
  * @index: The page index.
  * @fgp_flags: %FGP flags modify how the folio is returned.
  * @gfp: Memory allocation flags to use if %FGP_CREAT is specified.
+ * @mpol: The mempolicy to apply when allocating a new folio.
+ * @ilx: The interleave index, for use only with MPOL_INTERLEAVE or
+ *       MPOL_WEIGHTED_INTERLEAVE.
  *
  * Looks up the page cache entry at @mapping & @index.
  *
@@ -1895,8 +1907,8 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index)
  *
  * Return: The found folio or an ERR_PTR() otherwise.
  */
-struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
-		fgf_t fgp_flags, gfp_t gfp)
+struct folio *__filemap_get_folio_mpol(struct address_space *mapping, pgoff_t index,
+		fgf_t fgp_flags, gfp_t gfp, struct mempolicy *mpol, pgoff_t ilx)
 {
 	struct folio *folio;
 
@@ -1966,7 +1978,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 			err = -ENOMEM;
 			if (order > min_order)
 				alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
-			folio = filemap_alloc_folio(alloc_gfp, order);
+			folio = filemap_alloc_folio_mpol(alloc_gfp, order, mpol, ilx);
 			if (!folio)
 				continue;
 
@@ -2013,6 +2025,13 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		folio_clear_dropbehind(folio);
 	return folio;
 }
+EXPORT_SYMBOL(__filemap_get_folio_mpol);
+
+struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
+		fgf_t fgp_flags, gfp_t gfp)
+{
+	return __filemap_get_folio_mpol(mapping, index, fgp_flags, gfp, NULL, 0);
+}
 EXPORT_SYMBOL(__filemap_get_folio);
 
 static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max,
-- 
2.34.1



  reply	other threads:[~2025-04-08 11:24 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-08 11:23 [PATCH RFC v7 0/8] Add NUMA mempolicy support for KVM guest-memfd Shivank Garg
2025-04-08 11:23 ` Shivank Garg [this message]
2025-04-08 11:23 ` [PATCH RFC v7 2/8] mm/mempolicy: Export memory policy symbols Shivank Garg
2025-04-08 11:23 ` [PATCH RFC v7 3/8] security: Export security_inode_init_security_anon for KVM guest_memfd Shivank Garg
2025-04-09 20:19   ` Paul Moore
2025-04-11  6:07     ` Shivank Garg
2025-04-22 16:49       ` David Hildenbrand
2025-04-10  8:41   ` Christoph Hellwig
2025-04-11  6:51     ` Shivank Garg
2025-04-22 17:25     ` David Hildenbrand
2025-05-08  6:37       ` Shivank Garg
2025-04-08 11:23 ` [PATCH RFC v7 4/8] KVM: Add kvm_gmem_exit() cleanup function Shivank Garg
2025-04-08 11:23 ` [PATCH RFC v7 5/8] KVM: guest_memfd: Make guest mem use guest mem inodes instead of anonymous inodes Shivank Garg
2025-04-10  8:42   ` Christoph Hellwig
2025-04-10 13:53     ` Ackerley Tng
2025-04-10 14:23       ` Christoph Hellwig
2025-04-08 11:24 ` [PATCH RFC v7 6/8] KVM: guest_memfd: Add slab-allocated inode cache Shivank Garg
2025-04-08 11:24 ` [PATCH RFC v7 7/8] KVM: guest_memfd: Enforce NUMA mempolicy using shared policy Shivank Garg
2025-04-10 13:40   ` Ackerley Tng
2025-04-11  6:42     ` Shivank Garg
2025-04-08 11:24 ` [PATCH RFC v7 8/8] KVM: guest_memfd: selftests: Add tests for mmap and NUMA policy support Shivank Garg

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250408112402.181574-2-shivankg@amd.com \
    --to=shivankg@amd.com \
    --cc=Neeraj.Upadhyay@amd.com \
    --cc=ackerleytng@google.com \
    --cc=aik@amd.com \
    --cc=akpm@linux-foundation.org \
    --cc=bfoster@redhat.com \
    --cc=bharata@amd.com \
    --cc=chao.gao@intel.com \
    --cc=david@redhat.com \
    --cc=jgg@nvidia.com \
    --cc=jmorris@namei.org \
    --cc=kalyazin@amazon.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-coco@lists.linux.dev \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-security-module@vger.kernel.org \
    --cc=michael.day@amd.com \
    --cc=michael.roth@amd.com \
    --cc=nikunj@amd.com \
    --cc=paul@paul-moore.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=pvorel@suse.cz \
    --cc=seanjc@google.com \
    --cc=serge@hallyn.com \
    --cc=shuah@kernel.org \
    --cc=tabba@google.com \
    --cc=thomas.lendacky@amd.com \
    --cc=vannapurve@google.com \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.org \
    --cc=yan.y.zhao@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox