linux_dsm_epyc7002/mm/sparse.c
David Hildenbrand 8068df3b60 mm/memory_hotplug: don't free usage map when removing a re-added early section
When we remove an early section, we don't free the usage map, as the
usage maps of other sections are placed into the same page.  Once the
section is removed, it is no longer an early section (especially, the
memmap is freed).  When we re-add that section, the usage map is reused,
however, it is no longer an early section.  When removing that section
again, we try to kfree() a usage map that was allocated during early
boot - bad.

Let's check against PageReserved() to see if we are dealing with an
usage map that was allocated during boot.  We could also check against
!(PageSlab(usage_page) || PageCompound(usage_page)), but PageReserved() is
cleaner.

Can be triggered using memtrace under ppc64/powernv:

  $ mount -t debugfs none /sys/kernel/debug/
  $ echo 0x20000000 > /sys/kernel/debug/powerpc/memtrace/enable
  $ echo 0x20000000 > /sys/kernel/debug/powerpc/memtrace/enable
   ------------[ cut here ]------------
   kernel BUG at mm/slub.c:3969!
   Oops: Exception in kernel mode, sig: 5 []
   LE PAGE_SIZE=3D64K MMU=3DHash SMP NR_CPUS=3D2048 NUMA PowerNV
   Modules linked in:
   CPU: 0 PID: 154 Comm: sh Not tainted 5.5.0-rc2-next-20191216-00005-g0be1dba7b7c0 
   NIP kfree+0x338/0x3b0
   LR section_deactivate+0x138/0x200
   Call Trace:
     section_deactivate+0x138/0x200
     __remove_pages+0x114/0x150
     arch_remove_memory+0x3c/0x160
     try_remove_memory+0x114/0x1a0
     __remove_memory+0x20/0x40
     memtrace_enable_set+0x254/0x850
     simple_attr_write+0x138/0x160
     full_proxy_write+0x8c/0x110
     __vfs_write+0x38/0x70
     vfs_write+0x11c/0x2a0
     ksys_write+0x84/0x140
     system_call+0x5c/0x68
   ---[ end trace 4b053cbd84e0db62 ]---

The first invocation will offline+remove memory blocks.  The second
invocation will first add+online them again, in order to offline+remove
them again (usually we are lucky and the exact same memory blocks will
get "reallocated").

Tested on powernv with boot memory: The usage map will not get freed.
Tested on x86-64 with DIMMs: The usage map will get freed.

Using Dynamic Memory under a Power DLAPR can trigger it easily.

Triggering removal (I assume after previously removed+re-added) of
memory from the HMC GUI can crash the kernel with the same call trace
and is fixed by this patch.

Link: http://lkml.kernel.org/r/20191217104637.5509-1-david@redhat.com
Fixes: 326e1b8f83 ("mm/sparsemem: introduce a SECTION_IS_EARLY flag")
Signed-off-by: David Hildenbrand <david@redhat.com>
Tested-by: Pingfan Liu <piliu@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-01-13 18:19:01 -08:00

939 lines
26 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* sparse memory mappings.
*/
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/mmzone.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:
*
* 1) mem_section - memory sections, mem_map's for valid memory
*/
#ifdef CONFIG_SPARSEMEM_EXTREME
struct mem_section **mem_section;
#else
struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
____cacheline_internodealigned_in_smp;
#endif
EXPORT_SYMBOL(mem_section);
#ifdef NODE_NOT_IN_PAGE_FLAGS
/*
* If we did not store the node number in the page then we have to
* do a lookup in the section_to_node_table in order to find which
* node the page belongs to.
*/
#if MAX_NUMNODES <= 256
static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
#else
static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
#endif
int page_to_nid(const struct page *page)
{
return section_to_node_table[page_to_section(page)];
}
EXPORT_SYMBOL(page_to_nid);
static void set_section_nid(unsigned long section_nr, int nid)
{
section_to_node_table[section_nr] = nid;
}
#else /* !NODE_NOT_IN_PAGE_FLAGS */
static inline void set_section_nid(unsigned long section_nr, int nid)
{
}
#endif
#ifdef CONFIG_SPARSEMEM_EXTREME
static noinline struct mem_section __ref *sparse_index_alloc(int nid)
{
struct mem_section *section = NULL;
unsigned long array_size = SECTIONS_PER_ROOT *
sizeof(struct mem_section);
if (slab_is_available()) {
section = kzalloc_node(array_size, GFP_KERNEL, 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;
}
static int __meminit sparse_index_init(unsigned long section_nr, int nid)
{
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 0;
section = sparse_index_alloc(nid);
if (!section)
return -ENOMEM;
mem_section[root] = section;
return 0;
}
#else /* !SPARSEMEM_EXTREME */
static inline int sparse_index_init(unsigned long section_nr, int nid)
{
return 0;
}
#endif
#ifdef CONFIG_SPARSEMEM_EXTREME
unsigned long __section_nr(struct mem_section *ms)
{
unsigned long root_nr;
struct mem_section *root = NULL;
for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
if (!root)
continue;
if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT)))
break;
}
VM_BUG_ON(!root);
return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
}
#else
unsigned long __section_nr(struct mem_section *ms)
{
return (unsigned long)(ms - mem_section[0]);
}
#endif
/*
* During early boot, before section_mem_map is used for an actual
* mem_map, we use section_mem_map to store the section's NUMA
* node. This keeps us from having to use another data structure. The
* node information is cleared just before we store the real mem_map.
*/
static inline unsigned long sparse_encode_early_nid(int nid)
{
return (nid << SECTION_NID_SHIFT);
}
static inline int sparse_early_nid(struct mem_section *section)
{
return (section->section_mem_map >> SECTION_NID_SHIFT);
}
/* Validate the physical addressing limitations of the model */
void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
unsigned long *end_pfn)
{
unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT);
/*
* Sanity checks - do not allow an architecture to pass
* in larger pfns than the maximum scope of sparsemem:
*/
if (*start_pfn > max_sparsemem_pfn) {
mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
"Start of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
*start_pfn, *end_pfn, max_sparsemem_pfn);
WARN_ON_ONCE(1);
*start_pfn = max_sparsemem_pfn;
*end_pfn = max_sparsemem_pfn;
} else if (*end_pfn > max_sparsemem_pfn) {
mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
"End of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
*start_pfn, *end_pfn, max_sparsemem_pfn);
WARN_ON_ONCE(1);
*end_pfn = max_sparsemem_pfn;
}
}
/*
* There are a number of times that we loop over NR_MEM_SECTIONS,
* looking for section_present() on each. But, when we have very
* large physical address spaces, NR_MEM_SECTIONS can also be
* very large which makes the loops quite long.
*
* Keeping track of this gives us an easy way to break out of
* those loops early.
*/
unsigned long __highest_present_section_nr;
static void section_mark_present(struct mem_section *ms)
{
unsigned long section_nr = __section_nr(ms);
if (section_nr > __highest_present_section_nr)
__highest_present_section_nr = section_nr;
ms->section_mem_map |= SECTION_MARKED_PRESENT;
}
static inline unsigned long next_present_section_nr(unsigned long 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) && \
(section_nr <= __highest_present_section_nr)); \
section_nr = next_present_section_nr(section_nr))
static inline unsigned long first_present_section_nr(void)
{
return next_present_section_nr(-1);
}
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;
}
}
/* Record a memory area against a node. */
void __init memory_present(int nid, unsigned long start, unsigned long end)
{
unsigned long pfn;
#ifdef CONFIG_SPARSEMEM_EXTREME
if (unlikely(!mem_section)) {
unsigned long size, align;
size = sizeof(struct mem_section*) * NR_SECTION_ROOTS;
align = 1 << (INTERNODE_CACHE_SHIFT);
mem_section = memblock_alloc(size, align);
if (!mem_section)
panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
__func__, size, align);
}
#endif
start &= PAGE_SECTION_MASK;
mminit_validate_memmodel_limits(&start, &end);
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
unsigned long section = pfn_to_section_nr(pfn);
struct mem_section *ms;
sparse_index_init(section, nid);
set_section_nid(section, nid);
ms = __nr_to_section(section);
if (!ms->section_mem_map) {
ms->section_mem_map = sparse_encode_early_nid(nid) |
SECTION_IS_ONLINE;
section_mark_present(ms);
}
}
}
/*
* Mark all memblocks as present using memory_present(). This is a
* convienence function that is useful for a number of arches
* to mark all of the systems memory as present during initialization.
*/
void __init memblocks_present(void)
{
struct memblock_region *reg;
for_each_memblock(memory, reg) {
memory_present(memblock_get_region_node(reg),
memblock_region_memory_base_pfn(reg),
memblock_region_memory_end_pfn(reg));
}
}
/*
* 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.
*/
static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum)
{
unsigned long coded_mem_map =
(unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
BUILD_BUG_ON(SECTION_MAP_LAST_BIT > (1UL<<PFN_SECTION_SHIFT));
BUG_ON(coded_mem_map & ~SECTION_MAP_MASK);
return coded_mem_map;
}
/*
* Decode mem_map from the coded memmap
*/
struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
{
/* mask off the extra low bits of information */
coded_mem_map &= SECTION_MAP_MASK;
return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
}
static void __meminit sparse_init_one_section(struct mem_section *ms,
unsigned long pnum, struct page *mem_map,
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 | flags;
ms->usage = usage;
}
static unsigned long usemap_size(void)
{
return BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS) * sizeof(unsigned long);
}
size_t mem_section_usage_size(void)
{
return sizeof(struct mem_section_usage) + usemap_size();
}
#ifdef CONFIG_MEMORY_HOTREMOVE
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;
int nid;
/*
* A page may contain usemaps for other sections preventing the
* page being freed and making a section unremovable while
* other sections referencing the usemap remain active. Similarly,
* a pgdat can prevent a section being removed. If section A
* contains a pgdat and section B contains the usemap, both
* sections become inter-dependent. This allocates usemaps
* from the same section as the pgdat where possible to avoid
* this problem.
*/
goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT);
limit = goal + (1UL << PA_SECTION_SHIFT);
nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
again:
usage = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, goal, limit, nid);
if (!usage && limit) {
limit = 0;
goto again;
}
return usage;
}
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;
static unsigned long old_pgdat_snr;
struct pglist_data *pgdat = NODE_DATA(nid);
int usemap_nid;
/* First call */
if (!old_usemap_snr) {
old_usemap_snr = NR_MEM_SECTIONS;
old_pgdat_snr = NR_MEM_SECTIONS;
}
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;
if (old_usemap_snr == usemap_snr && old_pgdat_snr == pgdat_snr)
/* skip redundant message */
return;
old_usemap_snr = usemap_snr;
old_pgdat_snr = pgdat_snr;
usemap_nid = sparse_early_nid(__nr_to_section(usemap_snr));
if (usemap_nid != nid) {
pr_info("node %d must be removed before remove section %ld\n",
nid, usemap_snr);
return;
}
/*
* There is a circular dependency.
* Some platforms allow un-removable section because they will just
* gather other removable sections for dynamic partitioning.
* Just notify un-removable section's number here.
*/
pr_info("Section %ld and %ld (node %d) have a circular dependency on usemap and pgdat allocations\n",
usemap_snr, pgdat_snr, nid);
}
#else
static struct mem_section_usage * __init
sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
unsigned long size)
{
return memblock_alloc_node(size, SMP_CACHE_BYTES, pgdat->node_id);
}
static void __init check_usemap_section_nr(int nid,
struct mem_section_usage *usage)
{
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
#ifdef CONFIG_SPARSEMEM_VMEMMAP
static unsigned long __init section_map_size(void)
{
return ALIGN(sizeof(struct page) * PAGES_PER_SECTION, PMD_SIZE);
}
#else
static unsigned long __init section_map_size(void)
{
return PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION);
}
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_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 */
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()? */
/*
* 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;
}
static void __init sparse_buffer_fini(void)
{
unsigned long size = sparsemap_buf_end - sparsemap_buf;
if (sparsemap_buf && size > 0)
sparse_buffer_free(size);
sparsemap_buf = NULL;
}
void * __meminit sparse_buffer_alloc(unsigned long size)
{
void *ptr = NULL;
if (sparsemap_buf) {
ptr = (void *) roundup((unsigned long)sparsemap_buf, size);
if (ptr + size > sparsemap_buf_end)
ptr = NULL;
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;
}
void __weak __meminit vmemmap_populate_print_last(void)
{
}
/*
* Initialize sparse on a specific node. The node spans [pnum_begin, pnum_end)
* And number of present sections in this node is map_count.
*/
static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
unsigned long pnum_end,
unsigned long map_count)
{
struct mem_section_usage *usage;
unsigned long pnum;
struct page *map;
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 = __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);
pnum_begin = pnum;
goto failed;
}
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;
failed:
/* We failed to allocate, mark all the following pnums as not present */
for_each_present_section_nr(pnum_begin, pnum) {
struct mem_section *ms;
if (pnum >= pnum_end)
break;
ms = __nr_to_section(pnum);
ms->section_mem_map = 0;
}
}
/*
* Allocate the accumulated non-linear sections, allocate a mem_map
* for each and record the physical to section mapping.
*/
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;
/* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */
set_pageblock_order();
for_each_present_section_nr(pnum_begin + 1, pnum_end) {
int nid = sparse_early_nid(__nr_to_section(pnum_end));
if (nid == nid_begin) {
map_count++;
continue;
}
/* Init node with sections in range [pnum_begin, pnum_end) */
sparse_init_nid(nid_begin, pnum_begin, pnum_end, map_count);
nid_begin = nid;
pnum_begin = pnum_end;
map_count = 1;
}
/* cover the last node */
sparse_init_nid(nid_begin, pnum_begin, pnum_end, map_count);
vmemmap_populate_print_last();
}
#ifdef CONFIG_MEMORY_HOTPLUG
/* Mark all memory sections within the pfn range as online */
void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
{
unsigned long pfn;
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
unsigned long section_nr = pfn_to_section_nr(pfn);
struct mem_section *ms;
/* onlining code should never touch invalid ranges */
if (WARN_ON(!valid_section_nr(section_nr)))
continue;
ms = __nr_to_section(section_nr);
ms->section_mem_map |= SECTION_IS_ONLINE;
}
}
#ifdef CONFIG_MEMORY_HOTREMOVE
/* 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;
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
unsigned long section_nr = pfn_to_section_nr(pfn);
struct mem_section *ms;
/*
* TODO this needs some double checking. Offlining code makes
* sure to check pfn_valid but those checks might be just bogus
*/
if (WARN_ON(!valid_section_nr(section_nr)))
continue;
ms = __nr_to_section(section_nr);
ms->section_mem_map &= ~SECTION_IS_ONLINE;
}
}
#endif
#ifdef CONFIG_SPARSEMEM_VMEMMAP
static struct page * __meminit populate_section_memmap(unsigned long pfn,
unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
{
return __populate_section_memmap(pfn, nr_pages, nid, altmap);
}
static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
struct vmem_altmap *altmap)
{
unsigned long start = (unsigned long) pfn_to_page(pfn);
unsigned long end = start + nr_pages * sizeof(struct page);
vmemmap_free(start, end, altmap);
}
static void free_map_bootmem(struct page *memmap)
{
unsigned long start = (unsigned long)memmap;
unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
vmemmap_free(start, end, NULL);
}
#else
struct page * __meminit populate_section_memmap(unsigned long pfn,
unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
{
struct page *page, *ret;
unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
if (page)
goto got_map_page;
ret = vmalloc(memmap_size);
if (ret)
goto got_map_ptr;
return NULL;
got_map_page:
ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
got_map_ptr:
return ret;
}
static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
struct vmem_altmap *altmap)
{
struct page *memmap = pfn_to_page(pfn);
if (is_vmalloc_addr(memmap))
vfree(memmap);
else
free_pages((unsigned long)memmap,
get_order(sizeof(struct page) * PAGES_PER_SECTION));
}
static void free_map_bootmem(struct page *memmap)
{
unsigned long maps_section_nr, removing_section_nr, i;
unsigned long magic, nr_pages;
struct page *page = virt_to_page(memmap);
nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
>> PAGE_SHIFT;
for (i = 0; i < nr_pages; i++, page++) {
magic = (unsigned long) page->freelist;
BUG_ON(magic == NODE_INFO);
maps_section_nr = pfn_to_section_nr(page_to_pfn(page));
removing_section_nr = page_private(page);
/*
* When this function is called, the removing section is
* logical offlined state. This means all pages are isolated
* from page allocator. If removing section's memmap is placed
* on the same section, it must not be freed.
* If it is freed, page allocator may allocate it which will
* be removed physically soon.
*/
if (maps_section_nr != removing_section_nr)
put_page_bootmem(page);
}
}
#endif /* CONFIG_SPARSEMEM_VMEMMAP */
static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
struct vmem_altmap *altmap)
{
DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
DECLARE_BITMAP(tmp, SUBSECTIONS_PER_SECTION) = { 0 };
struct mem_section *ms = __pfn_to_section(pfn);
bool section_is_early = early_section(ms);
struct page *memmap = NULL;
unsigned long *subsection_map = ms->usage
? &ms->usage->subsection_map[0] : NULL;
subsection_mask_set(map, pfn, nr_pages);
if (subsection_map)
bitmap_and(tmp, map, subsection_map, SUBSECTIONS_PER_SECTION);
if (WARN(!subsection_map || !bitmap_equal(tmp, map, SUBSECTIONS_PER_SECTION),
"section already deactivated (%#lx + %ld)\n",
pfn, nr_pages))
return;
/*
* 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
*/
bitmap_xor(subsection_map, map, subsection_map, SUBSECTIONS_PER_SECTION);
if (bitmap_empty(subsection_map, SUBSECTIONS_PER_SECTION)) {
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);
ms->section_mem_map = sparse_encode_mem_map(NULL, section_nr);
}
if (section_is_early && memmap)
free_map_bootmem(memmap);
else
depopulate_section_memmap(pfn, nr_pages, altmap);
}
static struct page * __meminit section_activate(int nid, unsigned long pfn,
unsigned long nr_pages, struct vmem_altmap *altmap)
{
DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
struct mem_section *ms = __pfn_to_section(pfn);
struct mem_section_usage *usage = NULL;
unsigned long *subsection_map;
struct page *memmap;
int rc = 0;
subsection_mask_set(map, pfn, nr_pages);
if (!ms->usage) {
usage = kzalloc(mem_section_usage_size(), GFP_KERNEL);
if (!usage)
return ERR_PTR(-ENOMEM);
ms->usage = usage;
}
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
bitmap_or(subsection_map, map, subsection_map,
SUBSECTIONS_PER_SECTION);
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.
*
* 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;
int ret;
ret = sparse_index_init(section_nr, nid);
if (ret < 0)
return ret;
memmap = section_activate(nid, start_pfn, nr_pages, altmap);
if (IS_ERR(memmap))
return PTR_ERR(memmap);
/*
* Poison uninitialized struct pages in order to catch invalid flags
* combinations.
*/
page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
ms = __nr_to_section(section_nr);
set_section_nid(section_nr, nid);
section_mark_present(ms);
/* Align memmap to section boundary in the subsection case */
if (section_nr_to_pfn(section_nr) != start_pfn)
memmap = pfn_to_kaddr(section_nr_to_pfn(section_nr));
sparse_init_one_section(ms, section_nr, memmap, ms->usage, 0);
return 0;
}
#ifdef CONFIG_MEMORY_FAILURE
static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
{
int i;
/*
* 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])) {
num_poisoned_pages_dec();
ClearPageHWPoison(&memmap[i]);
}
}
}
#else
static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
{
}
#endif
void sparse_remove_section(struct mem_section *ms, unsigned long pfn,
unsigned long nr_pages, unsigned long map_offset,
struct vmem_altmap *altmap)
{
clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset,
nr_pages - map_offset);
section_deactivate(pfn, nr_pages, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */