mm: cma: NUMA node interface
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.
--- 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(-)
include/linux/cma.h +11 -2
@@ -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,
include/linux/memblock.h +3 -0
@@ -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,
mm/cma.c +9 -7
@@ -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, + alimit, nid, false);if (!addr) { ret = -ENOMEM ; goto err;
mm/memblock.c +1 -1
@@ -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)
Signature · 1 line
2.24.1
PATCH 2/2 mm: hugetlb: Use node interface of cma
With introduction of numa node interface for CMA, this patch is for using that interface for allocating memory on numa nodes if NUMA is configured. This will be more efficient and cleaner because first, instead of iterating mem range of each numa node, cma_declare_contigueous_nid() will do its own address finding if we pass 0 for both min_pfn and max_pfn, second, it can also handle caseswhere NUMA is not configured
by passing NUMA_NO_NODE as an argument.
In addition, checking if desired size of memory is available or not, is happening in cma_declare_contiguous_nid() because base and limit will be determined there, since 0(any) for base and 0(any) for limit is passed as argument to the function.
--- mm/hugetlb.c | 40 +++++++++++----------------------------- 1 file changed, 11 insertions(+), 29 deletions(-)
mm/hugetlb.c +11 -29
@@ -5573,42 +5573,24 @@ void __init hugetlb_cma_reserve(int order) reserved =0 ;for_each_node_state (nid,N_ONLINE ) { -unsigned long min_pfn =0 , max_pfn =0 ;int res; -#ifdef CONFIG_NUMA -unsigned long start_pfn, end_pfn; -int i; -for_each_mem_pfn_range (i, nid, &start_pfn, &end_pfn,NULL ) { -if (!min_pfn) - min_pfn = start_pfn; - max_pfn = end_pfn; - } -#else - min_pfn = min_low_pfn; - max_pfn = max_low_pfn; -#endif size =min (per_node, hugetlb_cma_size - reserved); size =round_up (size,PAGE_SIZE << order); - -if (size > ((max_pfn - min_pfn) <<PAGE_SHIFT ) /2 ) { -pr_warn ("hugetlb_cma: cma_area is too big, please try less than %lu MiB\n" , -round_down (((max_pfn - min_pfn) <<PAGE_SHIFT ) * - nr_online_nodes /2 /SZ_1M , -PAGE_SIZE << order)); -break ; - } - - res =cma_declare_contiguous (PFN_PHYS (min_pfn), size, -PFN_PHYS (max_pfn), + + +#ifndef CONFIG_NUMA + nid = NUMA_NO_NODE +#endif + res =cma_declare_contiguous_nid (0 , size, +0 ,PAGE_SIZE << order,0 , false, -"hugetlb" , &hugetlb_cma[nid]); +"hugetlb" , &hugetlb_cma[nid], nid); +if (res) { -phys_addr_t begpa =PFN_PHYS (min_pfn); -phys_addr_t endpa =PFN_PHYS (max_pfn); -pr_warn ("%s: reservation failed: err %d, node %d, [%pap, %pap)\n" , - __func__, res, nid, &begpa, &endpa); +pr_warn ("%s: reservation failed: err %d, node %d\n" , + __func__, res, nid);break ; }
Signature · 1 line
2.24.1
Re: [PATCH 2/2] mm: hugetlb: Use node interface of cma
Quoted 8 lines · Aslan Bakirov
With introduction of numa node interface for CMA, this patch is for using that interface for allocating memory on numa nodes if NUMA is configured. This will be more efficient and cleaner because first, instead of iterating mem range of each numa node,
cma_declare_contigueous_nid()will do its own address finding if we pass 0 for bothmin_pfnandmax_pfn, second, it can also handle caseswhere NUMA is not configured
by passingNUMA_NO_NODEas an argument.
Quoted 4 lines
In addition, checking if desired size of memory is available or not, is happening in
cma_declare_contiguous_nid()because base and limit will be determined there, since 0(any) for base and 0(any) for limit is passed as argument to the function.
I have asked to merge this one with the original patch from Roman several times but it seems this is not going to happen. But whatever.
You have likely missed my review feedback http://lkml.kernel.org/r/[email protected].
The ifdef CONFIG_NUMA for the nid definition is pointless.
Quoted 1 line
Signed-off-by Aslan Bakirov <[email protected]>
After fixing that, feel free to add
Quoted 65 lines
--- mm/hugetlb.c | 40 +++++++++++----------------------------- 1 file changed, 11 insertions(+), 29 deletions(-)mm/hugetlb.c +11
-29@@ -5573,42 +5573,24 @@ void __init hugetlb_cma_reserve(int order) reserved =0 ;for_each_node_state (nid,N_ONLINE ) { -unsigned long min_pfn =0 , max_pfn =0 ;int res; -#ifdef CONFIG_NUMA -unsigned long start_pfn, end_pfn; -int i; -for_each_mem_pfn_range (i, nid, &start_pfn, &end_pfn,NULL ) { -if (!min_pfn) - min_pfn = start_pfn; - max_pfn = end_pfn; - } -#else - min_pfn = min_low_pfn; - max_pfn = max_low_pfn; -#endif size =min (per_node, hugetlb_cma_size - reserved); size =round_up (size,PAGE_SIZE << order); - -if (size > ((max_pfn - min_pfn) <<PAGE_SHIFT ) /2 ) { -pr_warn ("hugetlb_cma: cma_area is too big, please try less than %lu MiB\n" , -round_down (((max_pfn - min_pfn) <<PAGE_SHIFT ) * - nr_online_nodes /2 /SZ_1M , -PAGE_SIZE << order)); -break ; - } - - res =cma_declare_contiguous (PFN_PHYS (min_pfn), size, -PFN_PHYS (max_pfn), + + +#ifndef CONFIG_NUMA + nid = NUMA_NO_NODE +#endif + res =cma_declare_contiguous_nid (0 , size, +0 ,PAGE_SIZE << order,0 , false, -"hugetlb" , &hugetlb_cma[nid]); +"hugetlb" , &hugetlb_cma[nid], nid); +if (res) { -phys_addr_t begpa =PFN_PHYS (min_pfn); -phys_addr_t endpa =PFN_PHYS (max_pfn); -pr_warn ("%s: reservation failed: err %d, node %d, [%pap, %pap)\n" , - __func__, res, nid, &begpa, &endpa); +pr_warn ("%s: reservation failed: err %d, node %d\n" , + __func__, res, nid);break ; }Signature · 2 lines
-- 2.24.1
Signature · 2 lines
Michal Hocko SUSE Labs
Aslan Bakirov
Acked-by Michal HockoRe: [PATCH 2/2] mm: hugetlb: Use node interface of cma
________________________________
From: Michal Hocko <[email protected]>
Sent: Friday, April 3, 2020 11:36 AM
To: Aslan Bakirov <[email protected]>
Cc: [email protected] <[email protected]>; [email protected] <[email protected]>; [email protected] <[email protected]>; Kernel Team <[email protected]>; [email protected] <[email protected]>; Roman Gushchin <[email protected]>; [email protected] <[email protected]>
Subject: Re: [PATCH 2/2] mm: hugetlb: Use node interface of cma
Quoted 8 lines · Aslan Bakirov
With introduction of numa node interface for CMA, this patch is for using that interface for allocating memory on numa nodes if NUMA is configured. This will be more efficient and cleaner because first, instead of iterating mem range of each numa node,
cma_declare_contigueous_nid()will do its own address finding if we pass 0 for bothmin_pfnandmax_pfn, second, it can also handle caseswhere NUMA is not configured
by passingNUMA_NO_NODEas an argument.
Quoted 4 lines
In addition, checking if desired size of memory is available or not, is happening in
cma_declare_contiguous_nid()because base and limit will be determined there, since 0(any) for base and 0(any) for limit is passed as argument to the function.
I have asked to merge this one with the original patch from Roman several times but it seems this is not going to happen. But whatever.
You have likely missed my review feedback http://lkml.kernel.org/r/[email protected].
The ifdef CONFIG_NUMA for the nid definition is pointless.
Quoted 1 line
Signed-off-by Aslan Bakirov <[email protected]>
After fixing that, feel free to add
Addressed your comment, and updated the patch. Thanks Michal.
Quoted 64 lines
--- mm/hugetlb.c | 40 +++++++++++----------------------------- 1 file changed, 11 insertions(+), 29 deletions(-)mm/hugetlb.c +11
-30@@ -5573,42 +5573,24 @@ void __init hugetlb_cma_reserve(int order) reserved =0 ;for_each_node_state (nid,N_ONLINE ) { -unsigned long min_pfn =0 , max_pfn =0 ;int res; -#ifdef CONFIG_NUMA -unsigned long start_pfn, end_pfn; -int i; -for_each_mem_pfn_range (i, nid, &start_pfn, &end_pfn,NULL ) { -if (!min_pfn) - min_pfn = start_pfn; - max_pfn = end_pfn; - } -#else - min_pfn = min_low_pfn; - max_pfn = max_low_pfn; -#endif size =min (per_node, hugetlb_cma_size - reserved); size =round_up (size,PAGE_SIZE << order); - -if (size > ((max_pfn - min_pfn) <<PAGE_SHIFT ) /2 ) { -pr_warn ("hugetlb_cma: cma_area is too big, please try less than %lu MiB\n" , -round_down (((max_pfn - min_pfn) <<PAGE_SHIFT ) * - nr_online_nodes /2 /SZ_1M , -PAGE_SIZE << order)); -break ; - } - - res =cma_declare_contiguous (PFN_PHYS (min_pfn), size, -PFN_PHYS (max_pfn), + + +#ifndef CONFIG_NUMA + nid = NUMA_NO_NODE +#endif + res =cma_declare_contiguous_nid (0 , size, +0 ,PAGE_SIZE << order,0 , false, -"hugetlb" , &hugetlb_cma[nid]); +"hugetlb" , &hugetlb_cma[nid], nid); +if (res) { -phys_addr_t begpa =PFN_PHYS (min_pfn); -phys_addr_t endpa =PFN_PHYS (max_pfn); -pr_warn ("%s: reservation failed: err %d, node %d, [%pap, %pap)\n" , - __func__, res, nid, &begpa, &endpa); +pr_warn ("%s: reservation failed: err %d, node %d\n" , + __func__, res, nid);break ; } --
Quoted 1 line
2.24.1
--
Michal Hocko
SUSE Labs