Commit 8d400913 authored by Oscar Salvador's avatar Oscar Salvador Committed by Linus Torvalds

x86/vmemmap: handle unpopulated sub-pmd ranges

When sizeof(struct page) is not a power of 2, sections do not span a PMD
anymore and so when populating them some parts of the PMD will remain
unused.

Because of this, PMDs will be left behind when depopulating sections since
remove_pmd_table() thinks that those unused parts are still in use.

Fix this by marking the unused parts with PAGE_UNUSED, so memchr_inv()
will do the right thing and will let us free the PMD when the last user of
it is gone.

This patch is based on a similar patch by David Hildenbrand:

https://lore.kernel.org/linux-mm/20200722094558.9828-9-david@redhat.com/

[osalvador@suse.de: go back to the ifdef version]
  Link: https://lkml.kernel.org/r/YGy++mSft7K4u+88@localhost.localdomain

Link: https://lkml.kernel.org/r/20210309214050.4674-4-osalvador@suse.deSigned-off-by: default avatarOscar Salvador <osalvador@suse.de>
Reviewed-by: default avatarDavid Hildenbrand <david@redhat.com>
Acked-by: default avatarDave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 69ccfe74
...@@ -826,6 +826,51 @@ void __init paging_init(void) ...@@ -826,6 +826,51 @@ void __init paging_init(void)
zone_sizes_init(); zone_sizes_init();
} }
#ifdef CONFIG_SPARSEMEM_VMEMMAP
#define PAGE_UNUSED 0xFD
/* Returns true if the PMD is completely unused and thus it can be freed */
static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end)
{
unsigned long start = ALIGN_DOWN(addr, PMD_SIZE);
memset((void *)addr, PAGE_UNUSED, end - addr);
return !memchr_inv((void *)start, PAGE_UNUSED, PMD_SIZE);
}
static void __meminit vmemmap_use_sub_pmd(unsigned long start)
{
/*
* As we expect to add in the same granularity as we remove, it's
* sufficient to mark only some piece used to block the memmap page from
* getting removed when removing some other adjacent memmap (just in
* case the first memmap never gets initialized e.g., because the memory
* block never gets onlined).
*/
memset((void *)start, 0, sizeof(struct page));
}
static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
{
/*
* Could be our memmap page is filled with PAGE_UNUSED already from a
* previous remove. Make sure to reset it.
*/
vmemmap_use_sub_pmd(start);
/*
* Mark with PAGE_UNUSED the unused parts of the new memmap range
*/
if (!IS_ALIGNED(start, PMD_SIZE))
memset((void *)start, PAGE_UNUSED,
start - ALIGN_DOWN(start, PMD_SIZE));
if (!IS_ALIGNED(end, PMD_SIZE))
memset((void *)end, PAGE_UNUSED,
ALIGN(end, PMD_SIZE) - end);
}
#endif
/* /*
* Memory hotplug specific functions * Memory hotplug specific functions
*/ */
...@@ -871,8 +916,6 @@ int arch_add_memory(int nid, u64 start, u64 size, ...@@ -871,8 +916,6 @@ int arch_add_memory(int nid, u64 start, u64 size,
return add_pages(nid, start_pfn, nr_pages, params); return add_pages(nid, start_pfn, nr_pages, params);
} }
#define PAGE_INUSE 0xFD
static void __meminit free_pagetable(struct page *page, int order) static void __meminit free_pagetable(struct page *page, int order)
{ {
unsigned long magic; unsigned long magic;
...@@ -1006,7 +1049,6 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, ...@@ -1006,7 +1049,6 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
unsigned long next, pages = 0; unsigned long next, pages = 0;
pte_t *pte_base; pte_t *pte_base;
pmd_t *pmd; pmd_t *pmd;
void *page_addr;
pmd = pmd_start + pmd_index(addr); pmd = pmd_start + pmd_index(addr);
for (; addr < end; addr = next, pmd++) { for (; addr < end; addr = next, pmd++) {
...@@ -1026,22 +1068,16 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, ...@@ -1026,22 +1068,16 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
pmd_clear(pmd); pmd_clear(pmd);
spin_unlock(&init_mm.page_table_lock); spin_unlock(&init_mm.page_table_lock);
pages++; pages++;
} else { }
/* If here, we are freeing vmemmap pages. */ #ifdef CONFIG_SPARSEMEM_VMEMMAP
memset((void *)addr, PAGE_INUSE, next - addr); else if (vmemmap_pmd_is_unused(addr, next)) {
page_addr = page_address(pmd_page(*pmd));
if (!memchr_inv(page_addr, PAGE_INUSE,
PMD_SIZE)) {
free_hugepage_table(pmd_page(*pmd), free_hugepage_table(pmd_page(*pmd),
altmap); altmap);
spin_lock(&init_mm.page_table_lock); spin_lock(&init_mm.page_table_lock);
pmd_clear(pmd); pmd_clear(pmd);
spin_unlock(&init_mm.page_table_lock); spin_unlock(&init_mm.page_table_lock);
}
} }
#endif
continue; continue;
} }
...@@ -1492,11 +1528,17 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, ...@@ -1492,11 +1528,17 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
addr_end = addr + PMD_SIZE; addr_end = addr + PMD_SIZE;
p_end = p + PMD_SIZE; p_end = p + PMD_SIZE;
if (!IS_ALIGNED(addr, PMD_SIZE) ||
!IS_ALIGNED(next, PMD_SIZE))
vmemmap_use_new_sub_pmd(addr, next);
continue; continue;
} else if (altmap) } else if (altmap)
return -ENOMEM; /* no fallback */ return -ENOMEM; /* no fallback */
} else if (pmd_large(*pmd)) { } else if (pmd_large(*pmd)) {
vmemmap_verify((pte_t *)pmd, node, addr, next); vmemmap_verify((pte_t *)pmd, node, addr, next);
vmemmap_use_sub_pmd(addr);
continue; continue;
} }
if (vmemmap_populate_basepages(addr, next, node, NULL)) if (vmemmap_populate_basepages(addr, next, node, NULL))
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment