[PATCH v5 0/2] mm: using CMA for 1 GB hugepages allocation

[PATCH v5 0/2] mm: using CMA for 1 GB hugepages allocation

[Roman Gushchin]

The patchset adds a hugetlb_cma boot option, which allows
to reserve a cma area which can be later used for 1 GB
hugepages allocations.

v5:
1) made the hugetlb_cma work if a cma reservation fails on some nodes

v4:
1) added a patch from Aslan, which is adding a useful function to cma
2) removed the hard-coded archs list from docs
3) added a warning printing on non-supported archs
4) hugetlb_lock is temporarily dropped in update_and_free_page()

Thanks!


Aslan Bakirov (1):
  mm: cma: NUMA node interface

Roman Gushchin (1):
  mm: hugetlb: optionally allocate gigantic hugepages using cma

 .../admin-guide/kernel-parameters.txt         |   8 ++
 arch/arm64/mm/init.c                          |   6 +
 arch/x86/kernel/setup.c                       |   4 +
 include/linux/cma.h                           |  13 ++-
 include/linux/hugetlb.h                       |  12 ++
 include/linux/memblock.h                      |   3 +
 mm/cma.c                                      |  16 +--
 mm/hugetlb.c                                  | 109 ++++++++++++++++++
 mm/memblock.c                                 |   2 +-
 9 files changed, 163 insertions(+), 10 deletions(-)

-- 
2.25.1

[PATCH v5 1/2] mm: cma: NUMA node interface

[Roman Gushchin]

From: Aslan Bakirov <aslan@fb.com>

I've noticed that there is no interfaces exposed by CMA which would let me
to declare contigous memory on particular NUMA node.

This patchset adds the ability to try to allocate contiguous memory on
specific node. It will fallback to other nodes if the specified one
doesn't work.

Implement a new method for declaring contigous memory on particular node
and keep cma_declare_contiguous() as a wrapper.

Signed-off-by: Aslan Bakirov <aslan@fb.com>
Acked-by: Michal Hocko <mhocko@kernel.org>
---
 include/linux/cma.h      | 13 +++++++++++--
 include/linux/memblock.h |  3 +++
 mm/cma.c                 | 16 +++++++++-------
 mm/memblock.c            |  2 +-
 4 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/include/linux/cma.h b/include/linux/cma.h
index 190184b5ff32..eae834c2162f 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -24,10 +24,19 @@ extern phys_addr_t cma_get_base(const struct cma *cma);
 extern unsigned long cma_get_size(const struct cma *cma);
 extern const char *cma_get_name(const struct cma *cma);
 
-extern int __init cma_declare_contiguous(phys_addr_t base,
+extern int __init cma_declare_contiguous_nid(phys_addr_t base,
 			phys_addr_t size, phys_addr_t limit,
 			phys_addr_t alignment, unsigned int order_per_bit,
-			bool fixed, const char *name, struct cma **res_cma);
+			bool fixed, const char *name, struct cma **res_cma,
+			int nid);
+static inline int __init cma_declare_contiguous(phys_addr_t base,
+			phys_addr_t size, phys_addr_t limit,
+			phys_addr_t alignment, unsigned int order_per_bit,
+			bool fixed, const char *name, struct cma **res_cma)
+{
+	return cma_declare_contiguous_nid(base, size, limit, alignment,
+			order_per_bit, fixed, name, res_cma, NUMA_NO_NODE);
+}
 extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 					unsigned int order_per_bit,
 					const char *name,
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 079d17d96410..6bc37a731d27 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -348,6 +348,9 @@ static inline int memblock_get_region_node(const struct memblock_region *r)
 
 phys_addr_t memblock_phys_alloc_range(phys_addr_t size, phys_addr_t align,
 				      phys_addr_t start, phys_addr_t end);
+phys_addr_t memblock_alloc_range_nid(phys_addr_t size,
+				      phys_addr_t align, phys_addr_t start,
+				      phys_addr_t end, int nid, bool exact_nid);
 phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid);
 
 static inline phys_addr_t memblock_phys_alloc(phys_addr_t size,
diff --git a/mm/cma.c b/mm/cma.c
index be55d1988c67..0463ad2ce06b 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -220,7 +220,7 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 }
 
 /**
- * cma_declare_contiguous() - reserve custom contiguous area
+ * cma_declare_contiguous_nid() - reserve custom contiguous area
  * @base: Base address of the reserved area optional, use 0 for any
  * @size: Size of the reserved area (in bytes),
  * @limit: End address of the reserved memory (optional, 0 for any).
@@ -229,6 +229,7 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
  * @fixed: hint about where to place the reserved area
  * @name: The name of the area. See function cma_init_reserved_mem()
  * @res_cma: Pointer to store the created cma region.
+ * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
  *
  * This function reserves memory from early allocator. It should be
  * called by arch specific code once the early allocator (memblock or bootmem)
@@ -238,10 +239,11 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
  * If @fixed is true, reserve contiguous area at exactly @base.  If false,
  * reserve in range from @base to @limit.
  */
-int __init cma_declare_contiguous(phys_addr_t base,
+int __init cma_declare_contiguous_nid(phys_addr_t base,
 			phys_addr_t size, phys_addr_t limit,
 			phys_addr_t alignment, unsigned int order_per_bit,
-			bool fixed, const char *name, struct cma **res_cma)
+			bool fixed, const char *name, struct cma **res_cma,
+			int nid)
 {
 	phys_addr_t memblock_end = memblock_end_of_DRAM();
 	phys_addr_t highmem_start;
@@ -336,14 +338,14 @@ int __init cma_declare_contiguous(phys_addr_t base,
 		 * memory in case of failure.
 		 */
 		if (base < highmem_start && limit > highmem_start) {
-			addr = memblock_phys_alloc_range(size, alignment,
-							 highmem_start, limit);
+			addr = memblock_alloc_range_nid(size, alignment,
+					highmem_start, limit, nid, false);
 			limit = highmem_start;
 		}
 
 		if (!addr) {
-			addr = memblock_phys_alloc_range(size, alignment, base,
-							 limit);
+			addr = memblock_alloc_range_nid(size, alignment, base,
+					limit, nid, false);
 			if (!addr) {
 				ret = -ENOMEM;
 				goto err;
diff --git a/mm/memblock.c b/mm/memblock.c
index 4d06bbaded0f..c79ba6f9920c 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1349,7 +1349,7 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
  * Return:
  * Physical address of allocated memory block on success, %0 on failure.
  */
-static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
+phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
 					phys_addr_t align, phys_addr_t start,
 					phys_addr_t end, int nid,
 					bool exact_nid)
-- 
2.25.1

Re: [PATCH v5 2/2] mm: hugetlb: optionally allocate gigantic hugepages using cma

[Michal Hocko]

On Tue 07-04-20 09:38:40, Roman Gushchin wrote:
> Commit 944d9fec8d7a ("hugetlb: add support for gigantic page allocation at
> runtime") has added the run-time allocation of gigantic pages.  However it
> actually works only at early stages of the system loading, when the
> majority of memory is free.  After some time the memory gets fragmented by
> non-movable pages, so the chances to find a contiguous 1 GB block are
> getting close to zero.  Even dropping caches manually doesn't help a lot.
> 
> At large scale rebooting servers in order to allocate gigantic hugepages
> is quite expensive and complex.  At the same time keeping some constant
> percentage of memory in reserved hugepages even if the workload isn't
> using it is a big waste: not all workloads can benefit from using 1 GB
> pages.
> 
> The following solution can solve the problem:
> 1) On boot time a dedicated cma area* is reserved. The size is passed
>    as a kernel argument.
> 2) Run-time allocations of gigantic hugepages are performed using the
>    cma allocator and the dedicated cma area
> 
> In this case gigantic hugepages can be allocated successfully with a high
> probability, however the memory isn't completely wasted if nobody is using
> 1GB hugepages: it can be used for pagecache, anon memory, THPs, etc.
> 
> * On a multi-node machine a per-node cma area is allocated on each node.
>   Following gigantic hugetlb allocation are using the first available
>   numa node if the mask isn't specified by a user.
> 
> Usage:
> 1) configure the kernel to allocate a cma area for hugetlb allocations:
>    pass hugetlb_cma=10G as a kernel argument
> 
> 2) allocate hugetlb pages as usual, e.g.
>    echo 10 > /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages
> 
> If the option isn't enabled or the allocation of the cma area failed,
> the current behavior of the system is preserved.
> 
> x86 and arm-64 are covered by this patch, other architectures can be
> trivially added later.
> 
> The patch contains clean-ups and fixes proposed and implemented by
> Aslan Bakirov and Randy Dunlap. It also contains ideas and suggestions
> proposed by Rik van Riel, Michal Hocko and Mike Kravetz. Thanks!
> 
> Signed-off-by: Roman Gushchin <guro@fb.com>
> Tested-by: Andreas Schaufler <andreas.schaufler@gmx.de>
> Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
> Acked-by: Michal Hocko <mhocko@kernel.org>
> Cc: Aslan Bakirov <aslan@fb.com>
> Cc: Randy Dunlap <rdunlap@infradead.org>
> Cc: Rik van Riel <riel@surriel.com>
> Cc: Joonsoo Kim <js1304@gmail.com>

Thanks a lot for addressing my review feedback!
-- 
Michal Hocko
SUSE Labs

Re: [PATCH v5 2/2] mm: hugetlb: optionally allocate gigantic hugepages using cma

[Roman Gushchin]

On Tue, Apr 07, 2020 at 08:15:46PM +0200, Michal Hocko wrote:
> On Tue 07-04-20 09:38:40, Roman Gushchin wrote:
> > Commit 944d9fec8d7a ("hugetlb: add support for gigantic page allocation at
> > runtime") has added the run-time allocation of gigantic pages.  However it
> > actually works only at early stages of the system loading, when the
> > majority of memory is free.  After some time the memory gets fragmented by
> > non-movable pages, so the chances to find a contiguous 1 GB block are
> > getting close to zero.  Even dropping caches manually doesn't help a lot.
> > 
> > At large scale rebooting servers in order to allocate gigantic hugepages
> > is quite expensive and complex.  At the same time keeping some constant
> > percentage of memory in reserved hugepages even if the workload isn't
> > using it is a big waste: not all workloads can benefit from using 1 GB
> > pages.
> > 
> > The following solution can solve the problem:
> > 1) On boot time a dedicated cma area* is reserved. The size is passed
> >    as a kernel argument.
> > 2) Run-time allocations of gigantic hugepages are performed using the
> >    cma allocator and the dedicated cma area
> > 
> > In this case gigantic hugepages can be allocated successfully with a high
> > probability, however the memory isn't completely wasted if nobody is using
> > 1GB hugepages: it can be used for pagecache, anon memory, THPs, etc.
> > 
> > * On a multi-node machine a per-node cma area is allocated on each node.
> >   Following gigantic hugetlb allocation are using the first available
> >   numa node if the mask isn't specified by a user.
> > 
> > Usage:
> > 1) configure the kernel to allocate a cma area for hugetlb allocations:
> >    pass hugetlb_cma=10G as a kernel argument
> > 
> > 2) allocate hugetlb pages as usual, e.g.
> >    echo 10 > /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages
> > 
> > If the option isn't enabled or the allocation of the cma area failed,
> > the current behavior of the system is preserved.
> > 
> > x86 and arm-64 are covered by this patch, other architectures can be
> > trivially added later.
> > 
> > The patch contains clean-ups and fixes proposed and implemented by
> > Aslan Bakirov and Randy Dunlap. It also contains ideas and suggestions
> > proposed by Rik van Riel, Michal Hocko and Mike Kravetz. Thanks!
> > 
> > Signed-off-by: Roman Gushchin <guro@fb.com>
> > Tested-by: Andreas Schaufler <andreas.schaufler@gmx.de>
> > Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
> > Acked-by: Michal Hocko <mhocko@kernel.org>
> > Cc: Aslan Bakirov <aslan@fb.com>
> > Cc: Randy Dunlap <rdunlap@infradead.org>
> > Cc: Rik van Riel <riel@surriel.com>
> > Cc: Joonsoo Kim <js1304@gmail.com>
> 
> Thanks a lot for addressing my review feedback!

Actually thank you for looking at it!

Andrew, can you, please, pick this version up instead of current patches and
fixes in the mm tree?
It will also fix the build on the next tree.

Thanks!

Re: [PATCH v5 1/2] mm: cma: NUMA node interface

[Andrew Morton]

On Tue, 7 Apr 2020 09:38:39 -0700 Roman Gushchin <guro@fb.com> wrote:

> From: Aslan Bakirov <aslan@fb.com>
> 
> I've noticed that there is no interfaces exposed by CMA which would let me
> to declare contigous memory on particular NUMA node.
> 
> This patchset adds the ability to try to allocate contiguous memory on
> specific node. It will fallback to other nodes if the specified one
> doesn't work.
> 
> Implement a new method for declaring contigous memory on particular node
> and keep cma_declare_contiguous() as a wrapper.
> 
> Signed-off-by: Aslan Bakirov <aslan@fb.com>
> Acked-by: Michal Hocko <mhocko@kernel.org>

This should have had your signed-off-by, as you were on the patch
delivery path.  Please send it along?

Re: [PATCH v5 1/2] mm: cma: NUMA node interface

[Roman Gushchin]

On Wed, Apr 08, 2020 at 05:53:12PM -0700, Andrew Morton wrote:
> On Tue, 7 Apr 2020 09:38:39 -0700 Roman Gushchin <guro@fb.com> wrote:
> 
> > From: Aslan Bakirov <aslan@fb.com>
> > 
> > I've noticed that there is no interfaces exposed by CMA which would let me
> > to declare contigous memory on particular NUMA node.
> > 
> > This patchset adds the ability to try to allocate contiguous memory on
> > specific node. It will fallback to other nodes if the specified one
> > doesn't work.
> > 
> > Implement a new method for declaring contigous memory on particular node
> > and keep cma_declare_contiguous() as a wrapper.
> > 
> > Signed-off-by: Aslan Bakirov <aslan@fb.com>
> > Acked-by: Michal Hocko <mhocko@kernel.org>
> 
> This should have had your signed-off-by, as you were on the patch
> delivery path.  Please send it along?
> 

Will this work?

Signed-off-by: Roman Gushchin <guro@fb.com>

If not, below if the whole patch signed.

Thanks!

--

From 63ddb2d792b548ee480d85a42c94a9e6b4722f4f Mon Sep 17 00:00:00 2001
From: Aslan Bakirov <aslan@fb.com>
Date: Mon, 6 Apr 2020 11:02:59 -0700
Subject: [PATCH 1/2] mm: cma: NUMA node interface

I've noticed that there is no interfaces exposed by CMA which would let me
to declare contigous memory on particular NUMA node.

This patchset adds the ability to try to allocate contiguous memory on
specific node. It will fallback to other nodes if the specified one
doesn't work.

Implement a new method for declaring contigous memory on particular node
and keep cma_declare_contiguous() as a wrapper.

Signed-off-by: Aslan Bakirov <aslan@fb.com>
Acked-by: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Roman Gushchin <guro@fb.com>
---
 include/linux/cma.h      | 13 +++++++++++--
 include/linux/memblock.h |  3 +++
 mm/cma.c                 | 16 +++++++++-------
 mm/memblock.c            |  2 +-
 4 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/include/linux/cma.h b/include/linux/cma.h
index 190184b5ff32..eae834c2162f 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -24,10 +24,19 @@ extern phys_addr_t cma_get_base(const struct cma *cma);
 extern unsigned long cma_get_size(const struct cma *cma);
 extern const char *cma_get_name(const struct cma *cma);
 
-extern int __init cma_declare_contiguous(phys_addr_t base,
+extern int __init cma_declare_contiguous_nid(phys_addr_t base,
 			phys_addr_t size, phys_addr_t limit,
 			phys_addr_t alignment, unsigned int order_per_bit,
-			bool fixed, const char *name, struct cma **res_cma);
+			bool fixed, const char *name, struct cma **res_cma,
+			int nid);
+static inline int __init cma_declare_contiguous(phys_addr_t base,
+			phys_addr_t size, phys_addr_t limit,
+			phys_addr_t alignment, unsigned int order_per_bit,
+			bool fixed, const char *name, struct cma **res_cma)
+{
+	return cma_declare_contiguous_nid(base, size, limit, alignment,
+			order_per_bit, fixed, name, res_cma, NUMA_NO_NODE);
+}
 extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 					unsigned int order_per_bit,
 					const char *name,
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 079d17d96410..6bc37a731d27 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -348,6 +348,9 @@ static inline int memblock_get_region_node(const struct memblock_region *r)
 
 phys_addr_t memblock_phys_alloc_range(phys_addr_t size, phys_addr_t align,
 				      phys_addr_t start, phys_addr_t end);
+phys_addr_t memblock_alloc_range_nid(phys_addr_t size,
+				      phys_addr_t align, phys_addr_t start,
+				      phys_addr_t end, int nid, bool exact_nid);
 phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid);
 
 static inline phys_addr_t memblock_phys_alloc(phys_addr_t size,
diff --git a/mm/cma.c b/mm/cma.c
index be55d1988c67..0463ad2ce06b 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -220,7 +220,7 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 }
 
 /**
- * cma_declare_contiguous() - reserve custom contiguous area
+ * cma_declare_contiguous_nid() - reserve custom contiguous area
  * @base: Base address of the reserved area optional, use 0 for any
  * @size: Size of the reserved area (in bytes),
  * @limit: End address of the reserved memory (optional, 0 for any).
@@ -229,6 +229,7 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
  * @fixed: hint about where to place the reserved area
  * @name: The name of the area. See function cma_init_reserved_mem()
  * @res_cma: Pointer to store the created cma region.
+ * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
  *
  * This function reserves memory from early allocator. It should be
  * called by arch specific code once the early allocator (memblock or bootmem)
@@ -238,10 +239,11 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
  * If @fixed is true, reserve contiguous area at exactly @base.  If false,
  * reserve in range from @base to @limit.
  */
-int __init cma_declare_contiguous(phys_addr_t base,
+int __init cma_declare_contiguous_nid(phys_addr_t base,
 			phys_addr_t size, phys_addr_t limit,
 			phys_addr_t alignment, unsigned int order_per_bit,
-			bool fixed, const char *name, struct cma **res_cma)
+			bool fixed, const char *name, struct cma **res_cma,
+			int nid)
 {
 	phys_addr_t memblock_end = memblock_end_of_DRAM();
 	phys_addr_t highmem_start;
@@ -336,14 +338,14 @@ int __init cma_declare_contiguous(phys_addr_t base,
 		 * memory in case of failure.
 		 */
 		if (base < highmem_start && limit > highmem_start) {
-			addr = memblock_phys_alloc_range(size, alignment,
-							 highmem_start, limit);
+			addr = memblock_alloc_range_nid(size, alignment,
+					highmem_start, limit, nid, false);
 			limit = highmem_start;
 		}
 
 		if (!addr) {
-			addr = memblock_phys_alloc_range(size, alignment, base,
-							 limit);
+			addr = memblock_alloc_range_nid(size, alignment, base,
+					limit, nid, false);
 			if (!addr) {
 				ret = -ENOMEM;
 				goto err;
diff --git a/mm/memblock.c b/mm/memblock.c
index 4d06bbaded0f..c79ba6f9920c 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1349,7 +1349,7 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
  * Return:
  * Physical address of allocated memory block on success, %0 on failure.
  */
-static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
+phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
 					phys_addr_t align, phys_addr_t start,
 					phys_addr_t end, int nid,
 					bool exact_nid)
-- 
2.25.1