@@ -70,6 +70,10 @@ typedef int __bitwise mhp_t;
*/
#define MEMHP_MERGE_RESOURCE ((__force mhp_t)BIT(0))
+/*
+ */
+#define MEMHP_REUSE_VMEMMAP ((__force mhp_t)BIT(1))
+
/*
* Extended parameters for memory hotplug:
* altmap: alternative allocator for memmap array (optional)
@@ -79,10 +83,16 @@ typedef int __bitwise mhp_t;
struct mhp_params {
struct vmem_altmap *altmap;
pgprot_t pgprot;
+ unsigned int align;
+ mhp_t flags;
};
struct vmem_context {
struct vmem_altmap *altmap;
+ mhp_t flags;
+ unsigned int align;
+ void *block;
+ unsigned long block_page;
};
/*
@@ -3006,7 +3006,7 @@ p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
- struct vmem_altmap *altmap);
+ struct vmem_altmap *altmap, void *block);
void *vmemmap_alloc_block(unsigned long size, int node);
struct vmem_altmap;
void *vmemmap_alloc_block_buf(unsigned long size, int node,
@@ -300,6 +300,14 @@ static int check_hotplug_memory_addressable(unsigned long pfn,
return 0;
}
+static void vmem_context_init(struct vmem_context *ctx, struct mhp_params *params)
+{
+ memset(ctx, 0, sizeof(*ctx));
+ ctx->align = params->align;
+ ctx->altmap = params->altmap;
+ ctx->flags = params->flags;
+}
+
/*
* Reasonably generic function for adding memory. It is
* expected that archs that support memory hotplug will
@@ -313,7 +321,7 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
unsigned long cur_nr_pages;
int err;
struct vmem_altmap *altmap = params->altmap;
- struct vmem_context ctx = { .altmap = params->altmap };
+ struct vmem_context ctx;
if (WARN_ON_ONCE(!params->pgprot.pgprot))
return -EINVAL;
@@ -338,6 +346,8 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
if (err)
return err;
+ vmem_context_init(&ctx, params);
+
for (; pfn < end_pfn; pfn += cur_nr_pages) {
/* Select all remaining pages up to the next section boundary */
cur_nr_pages = min(end_pfn - pfn,
@@ -253,6 +253,9 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
goto err_kasan;
}
+ if (pgmap->flags & PGMAP_COMPOUND)
+ params->align = pgmap->align;
+
error = arch_add_memory(nid, range->start, range_len(range),
params);
}
@@ -141,16 +141,20 @@ void __meminit vmemmap_verify(pte_t *pte, int node,
}
pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
- struct vmem_altmap *altmap)
+ struct vmem_altmap *altmap, void *block)
{
pte_t *pte = pte_offset_kernel(pmd, addr);
if (pte_none(*pte)) {
pte_t entry;
- void *p;
-
- p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
- if (!p)
- return NULL;
+ void *p = block;
+
+ if (!block) {
+ p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
+ if (!p)
+ return NULL;
+ } else {
+ get_page(virt_to_page(block));
+ }
entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
set_pte_at(&init_mm, addr, pte, entry);
}
@@ -216,8 +220,10 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
return pgd;
}
-int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
- int node, struct vmem_altmap *altmap)
+static void *__meminit __vmemmap_populate_basepages(unsigned long start,
+ unsigned long end, int node,
+ struct vmem_altmap *altmap,
+ void *block)
{
unsigned long addr = start;
pgd_t *pgd;
@@ -229,38 +235,95 @@ int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
for (; addr < end; addr += PAGE_SIZE) {
pgd = vmemmap_pgd_populate(addr, node);
if (!pgd)
- return -ENOMEM;
+ return NULL;
p4d = vmemmap_p4d_populate(pgd, addr, node);
if (!p4d)
- return -ENOMEM;
+ return NULL;
pud = vmemmap_pud_populate(p4d, addr, node);
if (!pud)
- return -ENOMEM;
+ return NULL;
pmd = vmemmap_pmd_populate(pud, addr, node);
if (!pmd)
- return -ENOMEM;
- pte = vmemmap_pte_populate(pmd, addr, node, altmap);
+ return NULL;
+ pte = vmemmap_pte_populate(pmd, addr, node, altmap, block);
if (!pte)
- return -ENOMEM;
+ return NULL;
vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
}
+ return __va(__pfn_to_phys(pte_pfn(*pte)));
+}
+
+int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
+ int node, struct vmem_altmap *altmap)
+{
+ if (!__vmemmap_populate_basepages(start, end, node, altmap, NULL))
+ return -ENOMEM;
return 0;
}
+static struct page * __meminit vmemmap_populate_reuse(unsigned long start,
+ unsigned long end, int node,
+ struct vmem_context *ctx)
+{
+ unsigned long size, addr = start;
+ unsigned long psize = PHYS_PFN(ctx->align) * sizeof(struct page);
+
+ size = min(psize, end - start);
+
+ for (; addr < end; addr += size) {
+ unsigned long head = addr + PAGE_SIZE;
+ unsigned long tail = addr;
+ unsigned long last = addr + size;
+ void *area;
+
+ if (ctx->block_page &&
+ IS_ALIGNED((addr - ctx->block_page), psize))
+ ctx->block = NULL;
+
+ area = ctx->block;
+ if (!area) {
+ if (!__vmemmap_populate_basepages(addr, head, node,
+ ctx->altmap, NULL))
+ return NULL;
+
+ tail = head + PAGE_SIZE;
+ area = __vmemmap_populate_basepages(head, tail, node,
+ ctx->altmap, NULL);
+ if (!area)
+ return NULL;
+
+ ctx->block = area;
+ ctx->block_page = addr;
+ }
+
+ if (!__vmemmap_populate_basepages(tail, last, node,
+ ctx->altmap, area))
+ return NULL;
+ }
+
+ return (struct page*) start;
+}
+
struct page * __meminit __populate_section_memmap(unsigned long pfn,
unsigned long nr_pages, int nid, struct vmem_context *ctx)
{
unsigned long start = (unsigned long) pfn_to_page(pfn);
unsigned long end = start + nr_pages * sizeof(struct page);
struct vmem_altmap *altmap = NULL;
+ int flags = 0;
if (WARN_ON_ONCE(!IS_ALIGNED(pfn, PAGES_PER_SUBSECTION) ||
!IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION)))
return NULL;
- if (ctx)
+ if (ctx) {
altmap = ctx->altmap;
+ flags = ctx->flags;
+ }
+
+ if (flags & MEMHP_REUSE_VMEMMAP)
+ return vmemmap_populate_reuse(start, end, nid, ctx);
if (vmemmap_populate(start, end, nid, altmap))
return NULL;
Introduce a new flag, MEMHP_REUSE_VMEMMAP, which signals that that struct pages are onlined with a given alignment, and should reuse the tail pages vmemmap areas. On that circunstamce we reuse the PFN backing only the tail pages subsections, while letting the head page PFN remain different. This presumes that the backing page structs are compound pages, such as the case for compound pagemaps (i.e. ZONE_DEVICE with PGMAP_COMPOUND set) On 2M compound pagemaps, it lets us save 6 pages out of the 8 necessary PFNs necessary to describe the subsection's 32K struct pages we are onlining. On a 1G compound pagemap it let us save 4096 pages. Sections are 128M (or bigger/smaller), and such when initializing a compound memory map where we are initializing compound struct pages, we need to preserve the tail page to be reused across the rest of the areas for pagesizes which bigger than a section. Signed-off-by: Joao Martins <joao.m.martins@oracle.com> --- I wonder, rather than separating vmem_context and mhp_params, that one would just pick the latter. Albeit semantically the ctx aren't necessarily paramters, context passed from multiple sections onlining (i.e. multiple calls to populate_section_memmap). Also provided that this is internal state, which isn't passed to external modules, except @align and @flags for page size and requesting whether to reuse tail page areas. --- include/linux/memory_hotplug.h | 10 ++++ include/linux/mm.h | 2 +- mm/memory_hotplug.c | 12 ++++- mm/memremap.c | 3 ++ mm/sparse-vmemmap.c | 93 ++++++++++++++++++++++++++++------ 5 files changed, 103 insertions(+), 17 deletions(-)