From 244b2c5ca8b14627e4a17755e5922221e121c771 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 09 Oct 2024 06:15:07 +0000
Subject: [PATCH] change system file
---
kernel/mm/sparse.c | 561 +++++++++++++++++++++++++++++++++++++------------------
1 files changed, 378 insertions(+), 183 deletions(-)
diff --git a/kernel/mm/sparse.c b/kernel/mm/sparse.c
index ed60f0a..33406ea 100644
--- a/kernel/mm/sparse.c
+++ b/kernel/mm/sparse.c
@@ -5,17 +5,17 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/mmzone.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/compiler.h>
#include <linux/highmem.h>
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
#include "internal.h"
#include <asm/dma.h>
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
/*
* Permanent SPARSEMEM data:
@@ -65,10 +65,15 @@
unsigned long array_size = SECTIONS_PER_ROOT *
sizeof(struct mem_section);
- if (slab_is_available())
+ if (slab_is_available()) {
section = kzalloc_node(array_size, GFP_KERNEL, nid);
- else
- section = memblock_virt_alloc_node(array_size, nid);
+ } else {
+ section = memblock_alloc_node(array_size, SMP_CACHE_BYTES,
+ nid);
+ if (!section)
+ panic("%s: Failed to allocate %lu bytes nid=%d\n",
+ __func__, array_size, nid);
+ }
return section;
}
@@ -78,8 +83,15 @@
unsigned long root = SECTION_NR_TO_ROOT(section_nr);
struct mem_section *section;
+ /*
+ * An existing section is possible in the sub-section hotplug
+ * case. First hot-add instantiates, follow-on hot-add reuses
+ * the existing section.
+ *
+ * The mem_hotplug_lock resolves the apparent race below.
+ */
if (mem_section[root])
- return -EEXIST;
+ return 0;
section = sparse_index_alloc(nid);
if (!section)
@@ -97,7 +109,7 @@
#endif
#ifdef CONFIG_SPARSEMEM_EXTREME
-int __section_nr(struct mem_section* ms)
+unsigned long __section_nr(struct mem_section *ms)
{
unsigned long root_nr;
struct mem_section *root = NULL;
@@ -116,9 +128,9 @@
return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
}
#else
-int __section_nr(struct mem_section* ms)
+unsigned long __section_nr(struct mem_section *ms)
{
- return (int)(ms - mem_section[0]);
+ return (unsigned long)(ms - mem_section[0]);
}
#endif
@@ -173,10 +185,10 @@
* Keeping track of this gives us an easy way to break out of
* those loops early.
*/
-int __highest_present_section_nr;
+unsigned long __highest_present_section_nr;
static void section_mark_present(struct mem_section *ms)
{
- int section_nr = __section_nr(ms);
+ unsigned long section_nr = __section_nr(ms);
if (section_nr > __highest_present_section_nr)
__highest_present_section_nr = section_nr;
@@ -184,16 +196,6 @@
ms->section_mem_map |= SECTION_MARKED_PRESENT;
}
-static inline int next_present_section_nr(int section_nr)
-{
- do {
- section_nr++;
- if (present_section_nr(section_nr))
- return section_nr;
- } while ((section_nr <= __highest_present_section_nr));
-
- return -1;
-}
#define for_each_present_section_nr(start, section_nr) \
for (section_nr = next_present_section_nr(start-1); \
((section_nr != -1) && \
@@ -205,8 +207,49 @@
return next_present_section_nr(-1);
}
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static void subsection_mask_set(unsigned long *map, unsigned long pfn,
+ unsigned long nr_pages)
+{
+ int idx = subsection_map_index(pfn);
+ int end = subsection_map_index(pfn + nr_pages - 1);
+
+ bitmap_set(map, idx, end - idx + 1);
+}
+
+void __init subsection_map_init(unsigned long pfn, unsigned long nr_pages)
+{
+ int end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
+ unsigned long nr, start_sec = pfn_to_section_nr(pfn);
+
+ if (!nr_pages)
+ return;
+
+ for (nr = start_sec; nr <= end_sec; nr++) {
+ struct mem_section *ms;
+ unsigned long pfns;
+
+ pfns = min(nr_pages, PAGES_PER_SECTION
+ - (pfn & ~PAGE_SECTION_MASK));
+ ms = __nr_to_section(nr);
+ subsection_mask_set(ms->usage->subsection_map, pfn, pfns);
+
+ pr_debug("%s: sec: %lu pfns: %lu set(%d, %d)\n", __func__, nr,
+ pfns, subsection_map_index(pfn),
+ subsection_map_index(pfn + pfns - 1));
+
+ pfn += pfns;
+ nr_pages -= pfns;
+ }
+}
+#else
+void __init subsection_map_init(unsigned long pfn, unsigned long nr_pages)
+{
+}
+#endif
+
/* Record a memory area against a node. */
-void __init memory_present(int nid, unsigned long start, unsigned long end)
+static void __init memory_present(int nid, unsigned long start, unsigned long end)
{
unsigned long pfn;
@@ -216,7 +259,10 @@
size = sizeof(struct mem_section*) * NR_SECTION_ROOTS;
align = 1 << (INTERNODE_CACHE_SHIFT);
- mem_section = memblock_virt_alloc(size, align);
+ mem_section = memblock_alloc(size, align);
+ if (!mem_section)
+ panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+ __func__, size, align);
}
#endif
@@ -239,6 +285,20 @@
}
/*
+ * Mark all memblocks as present using memory_present().
+ * This is a convenience function that is useful to mark all of the systems
+ * memory as present during initialization.
+ */
+static void __init memblocks_present(void)
+{
+ unsigned long start, end;
+ int i, nid;
+
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid)
+ memory_present(nid, start, end);
+}
+
+/*
* Subtle, we encode the real pfn into the mem_map such that
* the identity pfn - section_mem_map will return the actual
* physical page frame number.
@@ -252,6 +312,7 @@
return coded_mem_map;
}
+#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Decode mem_map from the coded memmap
*/
@@ -261,36 +322,35 @@
coded_mem_map &= SECTION_MAP_MASK;
return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
}
+#endif /* CONFIG_MEMORY_HOTPLUG */
static void __meminit sparse_init_one_section(struct mem_section *ms,
unsigned long pnum, struct page *mem_map,
- unsigned long *pageblock_bitmap)
+ struct mem_section_usage *usage, unsigned long flags)
{
ms->section_mem_map &= ~SECTION_MAP_MASK;
- ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum) |
- SECTION_HAS_MEM_MAP;
- ms->pageblock_flags = pageblock_bitmap;
+ ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum)
+ | SECTION_HAS_MEM_MAP | flags;
+ ms->usage = usage;
}
-unsigned long usemap_size(void)
+static unsigned long usemap_size(void)
{
return BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS) * sizeof(unsigned long);
}
-#ifdef CONFIG_MEMORY_HOTPLUG
-static unsigned long *__kmalloc_section_usemap(void)
+size_t mem_section_usage_size(void)
{
- return kmalloc(usemap_size(), GFP_KERNEL);
+ return sizeof(struct mem_section_usage) + usemap_size();
}
-#endif /* CONFIG_MEMORY_HOTPLUG */
#ifdef CONFIG_MEMORY_HOTREMOVE
-static unsigned long * __init
+static struct mem_section_usage * __init
sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
unsigned long size)
{
+ struct mem_section_usage *usage;
unsigned long goal, limit;
- unsigned long *p;
int nid;
/*
* A page may contain usemaps for other sections preventing the
@@ -306,17 +366,16 @@
limit = goal + (1UL << PA_SECTION_SHIFT);
nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
again:
- p = memblock_virt_alloc_try_nid_nopanic(size,
- SMP_CACHE_BYTES, goal, limit,
- nid);
- if (!p && limit) {
+ usage = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, goal, limit, nid);
+ if (!usage && limit) {
limit = 0;
goto again;
}
- return p;
+ return usage;
}
-static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
+static void __init check_usemap_section_nr(int nid,
+ struct mem_section_usage *usage)
{
unsigned long usemap_snr, pgdat_snr;
static unsigned long old_usemap_snr;
@@ -330,7 +389,7 @@
old_pgdat_snr = NR_MEM_SECTIONS;
}
- usemap_snr = pfn_to_section_nr(__pa(usemap) >> PAGE_SHIFT);
+ usemap_snr = pfn_to_section_nr(__pa(usage) >> PAGE_SHIFT);
pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
if (usemap_snr == pgdat_snr)
return;
@@ -358,14 +417,15 @@
usemap_snr, pgdat_snr, nid);
}
#else
-static unsigned long * __init
+static struct mem_section_usage * __init
sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
unsigned long size)
{
- return memblock_virt_alloc_node_nopanic(size, pgdat->node_id);
+ return memblock_alloc_node(size, SMP_CACHE_BYTES, pgdat->node_id);
}
-static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
+static void __init check_usemap_section_nr(int nid,
+ struct mem_section_usage *usage)
{
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
@@ -382,18 +442,22 @@
return PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION);
}
-struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid,
- struct vmem_altmap *altmap)
+struct page __init *__populate_section_memmap(unsigned long pfn,
+ unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
{
unsigned long size = section_map_size();
struct page *map = sparse_buffer_alloc(size);
+ phys_addr_t addr = __pa(MAX_DMA_ADDRESS);
if (map)
return map;
- map = memblock_virt_alloc_try_nid(size,
- PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
- BOOTMEM_ALLOC_ACCESSIBLE, nid);
+ map = memblock_alloc_try_nid_raw(size, size, addr,
+ MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+ if (!map)
+ panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%pa\n",
+ __func__, size, PAGE_SIZE, nid, &addr);
+
return map;
}
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
@@ -401,13 +465,23 @@
static void *sparsemap_buf __meminitdata;
static void *sparsemap_buf_end __meminitdata;
+static inline void __meminit sparse_buffer_free(unsigned long size)
+{
+ WARN_ON(!sparsemap_buf || size == 0);
+ memblock_free_early(__pa(sparsemap_buf), size);
+}
+
static void __init sparse_buffer_init(unsigned long size, int nid)
{
+ phys_addr_t addr = __pa(MAX_DMA_ADDRESS);
WARN_ON(sparsemap_buf); /* forgot to call sparse_buffer_fini()? */
- sparsemap_buf =
- memblock_virt_alloc_try_nid_raw(size, PAGE_SIZE,
- __pa(MAX_DMA_ADDRESS),
- BOOTMEM_ALLOC_ACCESSIBLE, nid);
+ /*
+ * Pre-allocated buffer is mainly used by __populate_section_memmap
+ * and we want it to be properly aligned to the section size - this is
+ * especially the case for VMEMMAP which maps memmap to PMDs
+ */
+ sparsemap_buf = memblock_alloc_exact_nid_raw(size, section_map_size(),
+ addr, MEMBLOCK_ALLOC_ACCESSIBLE, nid);
sparsemap_buf_end = sparsemap_buf + size;
}
@@ -416,7 +490,7 @@
unsigned long size = sparsemap_buf_end - sparsemap_buf;
if (sparsemap_buf && size > 0)
- memblock_free_early(__pa(sparsemap_buf), size);
+ sparse_buffer_free(size);
sparsemap_buf = NULL;
}
@@ -425,11 +499,15 @@
void *ptr = NULL;
if (sparsemap_buf) {
- ptr = PTR_ALIGN(sparsemap_buf, size);
+ ptr = (void *) roundup((unsigned long)sparsemap_buf, size);
if (ptr + size > sparsemap_buf_end)
ptr = NULL;
- else
+ else {
+ /* Free redundant aligned space */
+ if ((unsigned long)(ptr - sparsemap_buf) > 0)
+ sparse_buffer_free((unsigned long)(ptr - sparsemap_buf));
sparsemap_buf = ptr + size;
+ }
}
return ptr;
}
@@ -446,23 +524,25 @@
unsigned long pnum_end,
unsigned long map_count)
{
- unsigned long pnum, usemap_longs, *usemap;
+ struct mem_section_usage *usage;
+ unsigned long pnum;
struct page *map;
- usemap_longs = BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS);
- usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nid),
- usemap_size() *
- map_count);
- if (!usemap) {
+ usage = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nid),
+ mem_section_usage_size() * map_count);
+ if (!usage) {
pr_err("%s: node[%d] usemap allocation failed", __func__, nid);
goto failed;
}
sparse_buffer_init(map_count * section_map_size(), nid);
for_each_present_section_nr(pnum_begin, pnum) {
+ unsigned long pfn = section_nr_to_pfn(pnum);
+
if (pnum >= pnum_end)
break;
- map = sparse_mem_map_populate(pnum, nid, NULL);
+ map = __populate_section_memmap(pfn, PAGES_PER_SECTION,
+ nid, NULL);
if (!map) {
pr_err("%s: node[%d] memory map backing failed. Some memory will not be available.",
__func__, nid);
@@ -470,9 +550,10 @@
sparse_buffer_fini();
goto failed;
}
- check_usemap_section_nr(nid, usemap);
- sparse_init_one_section(__nr_to_section(pnum), pnum, map, usemap);
- usemap += usemap_longs;
+ check_usemap_section_nr(nid, usage);
+ sparse_init_one_section(__nr_to_section(pnum), pnum, map, usage,
+ SECTION_IS_EARLY);
+ usage = (void *) usage + mem_section_usage_size();
}
sparse_buffer_fini();
return;
@@ -494,9 +575,13 @@
*/
void __init sparse_init(void)
{
- unsigned long pnum_begin = first_present_section_nr();
- int nid_begin = sparse_early_nid(__nr_to_section(pnum_begin));
- unsigned long pnum_end, map_count = 1;
+ unsigned long pnum_end, pnum_begin, map_count = 1;
+ int nid_begin;
+
+ memblocks_present();
+
+ pnum_begin = first_present_section_nr();
+ nid_begin = sparse_early_nid(__nr_to_section(pnum_begin));
/* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */
set_pageblock_order();
@@ -540,7 +625,7 @@
}
#ifdef CONFIG_MEMORY_HOTREMOVE
-/* Mark all memory sections within the pfn range as online */
+/* Mark all memory sections within the pfn range as offline */
void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
{
unsigned long pfn;
@@ -563,17 +648,17 @@
#endif
#ifdef CONFIG_SPARSEMEM_VMEMMAP
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
- struct vmem_altmap *altmap)
+static struct page * __meminit populate_section_memmap(unsigned long pfn,
+ unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
{
- /* This will make the necessary allocations eventually. */
- return sparse_mem_map_populate(pnum, nid, altmap);
+ return __populate_section_memmap(pfn, nr_pages, nid, altmap);
}
-static void __kfree_section_memmap(struct page *memmap,
+
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
struct vmem_altmap *altmap)
{
- unsigned long start = (unsigned long)memmap;
- unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
+ unsigned long start = (unsigned long) pfn_to_page(pfn);
+ unsigned long end = start + nr_pages * sizeof(struct page);
vmemmap_free(start, end, altmap);
}
@@ -584,42 +669,67 @@
vmemmap_free(start, end, NULL);
}
-#else
-static struct page *__kmalloc_section_memmap(void)
+
+static int clear_subsection_map(unsigned long pfn, unsigned long nr_pages)
{
- struct page *page, *ret;
- unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
+ DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
+ DECLARE_BITMAP(tmp, SUBSECTIONS_PER_SECTION) = { 0 };
+ struct mem_section *ms = __pfn_to_section(pfn);
+ unsigned long *subsection_map = ms->usage
+ ? &ms->usage->subsection_map[0] : NULL;
- page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
- if (page)
- goto got_map_page;
+ subsection_mask_set(map, pfn, nr_pages);
+ if (subsection_map)
+ bitmap_and(tmp, map, subsection_map, SUBSECTIONS_PER_SECTION);
- ret = vmalloc(memmap_size);
- if (ret)
- goto got_map_ptr;
+ if (WARN(!subsection_map || !bitmap_equal(tmp, map, SUBSECTIONS_PER_SECTION),
+ "section already deactivated (%#lx + %ld)\n",
+ pfn, nr_pages))
+ return -EINVAL;
- return NULL;
-got_map_page:
- ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
-got_map_ptr:
-
- return ret;
+ bitmap_xor(subsection_map, map, subsection_map, SUBSECTIONS_PER_SECTION);
+ return 0;
}
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
- struct vmem_altmap *altmap)
+static bool is_subsection_map_empty(struct mem_section *ms)
{
- return __kmalloc_section_memmap();
+ return bitmap_empty(&ms->usage->subsection_map[0],
+ SUBSECTIONS_PER_SECTION);
}
-static void __kfree_section_memmap(struct page *memmap,
- struct vmem_altmap *altmap)
+static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
{
- if (is_vmalloc_addr(memmap))
- vfree(memmap);
+ struct mem_section *ms = __pfn_to_section(pfn);
+ DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
+ unsigned long *subsection_map;
+ int rc = 0;
+
+ subsection_mask_set(map, pfn, nr_pages);
+
+ subsection_map = &ms->usage->subsection_map[0];
+
+ if (bitmap_empty(map, SUBSECTIONS_PER_SECTION))
+ rc = -EINVAL;
+ else if (bitmap_intersects(map, subsection_map, SUBSECTIONS_PER_SECTION))
+ rc = -EEXIST;
else
- free_pages((unsigned long)memmap,
- get_order(sizeof(struct page) * PAGES_PER_SECTION));
+ bitmap_or(subsection_map, map, subsection_map,
+ SUBSECTIONS_PER_SECTION);
+
+ return rc;
+}
+#else
+struct page * __meminit populate_section_memmap(unsigned long pfn,
+ unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+{
+ return kvmalloc_node(array_size(sizeof(struct page),
+ PAGES_PER_SECTION), GFP_KERNEL, nid);
+}
+
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
+ struct vmem_altmap *altmap)
+{
+ kvfree(pfn_to_page(pfn));
}
static void free_map_bootmem(struct page *memmap)
@@ -651,62 +761,179 @@
put_page_bootmem(page);
}
}
+
+static int clear_subsection_map(unsigned long pfn, unsigned long nr_pages)
+{
+ return 0;
+}
+
+static bool is_subsection_map_empty(struct mem_section *ms)
+{
+ return true;
+}
+
+static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
+{
+ return 0;
+}
#endif /* CONFIG_SPARSEMEM_VMEMMAP */
/*
- * returns the number of sections whose mem_maps were properly
- * set. If this is <=0, then that means that the passed-in
- * map was not consumed and must be freed.
+ * To deactivate a memory region, there are 3 cases to handle across
+ * two configurations (SPARSEMEM_VMEMMAP={y,n}):
+ *
+ * 1. deactivation of a partial hot-added section (only possible in
+ * the SPARSEMEM_VMEMMAP=y case).
+ * a) section was present at memory init.
+ * b) section was hot-added post memory init.
+ * 2. deactivation of a complete hot-added section.
+ * 3. deactivation of a complete section from memory init.
+ *
+ * For 1, when subsection_map does not empty we will not be freeing the
+ * usage map, but still need to free the vmemmap range.
+ *
+ * For 2 and 3, the SPARSEMEM_VMEMMAP={y,n} cases are unified
*/
-int __meminit sparse_add_one_section(int nid, unsigned long start_pfn,
- struct vmem_altmap *altmap)
+static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
+ struct vmem_altmap *altmap)
+{
+ struct mem_section *ms = __pfn_to_section(pfn);
+ bool section_is_early = early_section(ms);
+ struct page *memmap = NULL;
+ bool empty;
+
+ if (clear_subsection_map(pfn, nr_pages))
+ return;
+
+ empty = is_subsection_map_empty(ms);
+ if (empty) {
+ unsigned long section_nr = pfn_to_section_nr(pfn);
+
+ /*
+ * When removing an early section, the usage map is kept (as the
+ * usage maps of other sections fall into the same page). It
+ * will be re-used when re-adding the section - which is then no
+ * longer an early section. If the usage map is PageReserved, it
+ * was allocated during boot.
+ */
+ if (!PageReserved(virt_to_page(ms->usage))) {
+ kfree(ms->usage);
+ ms->usage = NULL;
+ }
+ memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+ /*
+ * Mark the section invalid so that valid_section()
+ * return false. This prevents code from dereferencing
+ * ms->usage array.
+ */
+ ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
+ }
+
+ /*
+ * The memmap of early sections is always fully populated. See
+ * section_activate() and pfn_valid() .
+ */
+ if (!section_is_early)
+ depopulate_section_memmap(pfn, nr_pages, altmap);
+ else if (memmap)
+ free_map_bootmem(memmap);
+
+ if (empty)
+ ms->section_mem_map = (unsigned long)NULL;
+}
+
+static struct page * __meminit section_activate(int nid, unsigned long pfn,
+ unsigned long nr_pages, struct vmem_altmap *altmap)
+{
+ struct mem_section *ms = __pfn_to_section(pfn);
+ struct mem_section_usage *usage = NULL;
+ struct page *memmap;
+ int rc = 0;
+
+ if (!ms->usage) {
+ usage = kzalloc(mem_section_usage_size(), GFP_KERNEL);
+ if (!usage)
+ return ERR_PTR(-ENOMEM);
+ ms->usage = usage;
+ }
+
+ rc = fill_subsection_map(pfn, nr_pages);
+ if (rc) {
+ if (usage)
+ ms->usage = NULL;
+ kfree(usage);
+ return ERR_PTR(rc);
+ }
+
+ /*
+ * The early init code does not consider partially populated
+ * initial sections, it simply assumes that memory will never be
+ * referenced. If we hot-add memory into such a section then we
+ * do not need to populate the memmap and can simply reuse what
+ * is already there.
+ */
+ if (nr_pages < PAGES_PER_SECTION && early_section(ms))
+ return pfn_to_page(pfn);
+
+ memmap = populate_section_memmap(pfn, nr_pages, nid, altmap);
+ if (!memmap) {
+ section_deactivate(pfn, nr_pages, altmap);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ return memmap;
+}
+
+/**
+ * sparse_add_section - add a memory section, or populate an existing one
+ * @nid: The node to add section on
+ * @start_pfn: start pfn of the memory range
+ * @nr_pages: number of pfns to add in the section
+ * @altmap: device page map
+ *
+ * This is only intended for hotplug.
+ *
+ * Note that only VMEMMAP supports sub-section aligned hotplug,
+ * the proper alignment and size are gated by check_pfn_span().
+ *
+ *
+ * Return:
+ * * 0 - On success.
+ * * -EEXIST - Section has been present.
+ * * -ENOMEM - Out of memory.
+ */
+int __meminit sparse_add_section(int nid, unsigned long start_pfn,
+ unsigned long nr_pages, struct vmem_altmap *altmap)
{
unsigned long section_nr = pfn_to_section_nr(start_pfn);
struct mem_section *ms;
struct page *memmap;
- unsigned long *usemap;
int ret;
- /*
- * no locking for this, because it does its own
- * plus, it does a kmalloc
- */
ret = sparse_index_init(section_nr, nid);
- if (ret < 0 && ret != -EEXIST)
+ if (ret < 0)
return ret;
- ret = 0;
- memmap = kmalloc_section_memmap(section_nr, nid, altmap);
- if (!memmap)
- return -ENOMEM;
- usemap = __kmalloc_section_usemap();
- if (!usemap) {
- __kfree_section_memmap(memmap, altmap);
- return -ENOMEM;
- }
- ms = __pfn_to_section(start_pfn);
- if (ms->section_mem_map & SECTION_MARKED_PRESENT) {
- ret = -EEXIST;
- goto out;
- }
+ memmap = section_activate(nid, start_pfn, nr_pages, altmap);
+ if (IS_ERR(memmap))
+ return PTR_ERR(memmap);
-#ifdef CONFIG_DEBUG_VM
/*
* Poison uninitialized struct pages in order to catch invalid flags
* combinations.
*/
- memset(memmap, PAGE_POISON_PATTERN, sizeof(struct page) * PAGES_PER_SECTION);
-#endif
+ page_init_poison(memmap, sizeof(struct page) * nr_pages);
+ ms = __nr_to_section(section_nr);
+ set_section_nid(section_nr, nid);
section_mark_present(ms);
- sparse_init_one_section(ms, section_nr, memmap, usemap);
-out:
- if (ret < 0) {
- kfree(usemap);
- __kfree_section_memmap(memmap, altmap);
- }
- return ret;
+ /* Align memmap to section boundary in the subsection case */
+ if (section_nr_to_pfn(section_nr) != start_pfn)
+ memmap = pfn_to_page(section_nr_to_pfn(section_nr));
+ sparse_init_one_section(ms, section_nr, memmap, ms->usage, 0);
+
+ return 0;
}
#ifdef CONFIG_MEMORY_FAILURE
@@ -714,12 +941,18 @@
{
int i;
- if (!memmap)
+ /*
+ * A further optimization is to have per section refcounted
+ * num_poisoned_pages. But that would need more space per memmap, so
+ * for now just do a quick global check to speed up this routine in the
+ * absence of bad pages.
+ */
+ if (atomic_long_read(&num_poisoned_pages) == 0)
return;
for (i = 0; i < nr_pages; i++) {
if (PageHWPoison(&memmap[i])) {
- atomic_long_sub(1, &num_poisoned_pages);
+ num_poisoned_pages_dec();
ClearPageHWPoison(&memmap[i]);
}
}
@@ -730,50 +963,12 @@
}
#endif
-static void free_section_usemap(struct page *memmap, unsigned long *usemap,
+void sparse_remove_section(struct mem_section *ms, unsigned long pfn,
+ unsigned long nr_pages, unsigned long map_offset,
struct vmem_altmap *altmap)
{
- struct page *usemap_page;
-
- if (!usemap)
- return;
-
- usemap_page = virt_to_page(usemap);
- /*
- * Check to see if allocation came from hot-plug-add
- */
- if (PageSlab(usemap_page) || PageCompound(usemap_page)) {
- kfree(usemap);
- if (memmap)
- __kfree_section_memmap(memmap, altmap);
- return;
- }
-
- /*
- * The usemap came from bootmem. This is packed with other usemaps
- * on the section which has pgdat at boot time. Just keep it as is now.
- */
-
- if (memmap)
- free_map_bootmem(memmap);
-}
-
-void sparse_remove_one_section(struct mem_section *ms, unsigned long map_offset,
- struct vmem_altmap *altmap)
-{
- struct page *memmap = NULL;
- unsigned long *usemap = NULL;
-
- if (ms->section_mem_map) {
- usemap = ms->pageblock_flags;
- memmap = sparse_decode_mem_map(ms->section_mem_map,
- __section_nr(ms));
- ms->section_mem_map = 0;
- ms->pageblock_flags = NULL;
- }
-
- clear_hwpoisoned_pages(memmap + map_offset,
- PAGES_PER_SECTION - map_offset);
- free_section_usemap(memmap, usemap, altmap);
+ clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset,
+ nr_pages - map_offset);
+ section_deactivate(pfn, nr_pages, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
--
Gitblit v1.6.2