| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <50BC0D2D.8040008@huawei.com>
Date: Mon, 3 Dec 2012 10:23:41 +0800
From: Jianguo Wu <wujianguo@...wei.com>
To: Wen Congyang <wency@...fujitsu.com>
CC: <x86@...nel.org>, <linux-mm@...ck.org>,
<linux-kernel@...r.kernel.org>, <linuxppc-dev@...ts.ozlabs.org>,
<linux-acpi@...r.kernel.org>, <linux-s390@...r.kernel.org>,
<linux-sh@...r.kernel.org>, <linux-ia64@...r.kernel.org>,
<cmetcalf@...era.com>, <sparclinux@...r.kernel.org>,
David Rientjes <rientjes@...gle.com>,
Jiang Liu <liuj97@...il.com>, Len Brown <len.brown@...el.com>,
<benh@...nel.crashing.org>, <paulus@...ba.org>,
Christoph Lameter <cl@...ux.com>,
Minchan Kim <minchan.kim@...il.com>,
Andrew Morton <akpm@...ux-foundation.org>,
KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
Yasuaki Ishimatsu <isimatu.yasuaki@...fujitsu.com>
Subject: Re: [Patch v4 08/12] memory-hotplug: remove memmap of sparse-vmemmap
Hi Congyang,
This is the new version.
Thanks,
Jianguo Wu.
Signed-off-by: Jianguo Wu <wujianguo@...wei.com>
Signed-off-by: Jiang Liu <jiang.liu@...wei.com>
---
include/linux/mm.h | 1 +
mm/sparse-vmemmap.c | 231 +++++++++++++++++++++++++++++++++++++++++++++++++++
mm/sparse.c | 3 +-
3 files changed, 234 insertions(+), 1 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5657670..1f26af5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1642,6 +1642,7 @@ int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
void vmemmap_populate_print_last(void);
void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
unsigned long size);
+void vmemmap_free(struct page *memmap, unsigned long nr_pages);
enum mf_flags {
MF_COUNT_INCREASED = 1 << 0,
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 1b7e22a..748732d 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -29,6 +29,10 @@
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
+#ifdef CONFIG_MEMORY_HOTREMOVE
+#include <asm/tlbflush.h>
+#endif
+
/*
* Allocate a block of memory to be used to back the virtual memory map
* or to back the page tables that are used to create the mapping.
@@ -224,3 +228,230 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
vmemmap_buf_end = NULL;
}
}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+
+#define PAGE_INUSE 0xFD
+
+static void vmemmap_free_pages(struct page *page, int order)
+{
+ struct zone *zone;
+ unsigned long magic;
+
+ magic = (unsigned long) page->lru.next;
+ if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
+ put_page_bootmem(page);
+
+ zone = page_zone(page);
+ zone_span_writelock(zone);
+ zone->present_pages++;
+ zone_span_writeunlock(zone);
+ totalram_pages++;
+ } else
+ free_pages((unsigned long)page_address(page), order);
+}
+
+static void free_pte_table(pmd_t *pmd)
+{
+ pte_t *pte, *pte_start;
+ int i;
+
+ pte_start = (pte_t *)pmd_page_vaddr(*pmd);
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ pte = pte_start + i;
+ if (pte_val(*pte))
+ return;
+ }
+
+ /* free a pte talbe */
+ vmemmap_free_pages(pmd_page(*pmd), 0);
+ spin_lock(&init_mm.page_table_lock);
+ pmd_clear(pmd);
+ spin_unlock(&init_mm.page_table_lock);
+}
+
+static void free_pmd_table(pud_t *pud)
+{
+ pmd_t *pmd, *pmd_start;
+ int i;
+
+ pmd_start = (pmd_t *)pud_page_vaddr(*pud);
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ pmd = pmd_start + i;
+ if (pmd_val(*pmd))
+ return;
+ }
+
+ /* free a pmd talbe */
+ vmemmap_free_pages(pud_page(*pud), 0);
+ spin_lock(&init_mm.page_table_lock);
+ pud_clear(pud);
+ spin_unlock(&init_mm.page_table_lock);
+}
+
+static void free_pud_table(pgd_t *pgd)
+{
+ pud_t *pud, *pud_start;
+ int i;
+
+ pud_start = (pud_t *)pgd_page_vaddr(*pgd);
+ for (i = 0; i < PTRS_PER_PUD; i++) {
+ pud = pud_start + i;
+ if (pud_val(*pud))
+ return;
+ }
+
+ /* free a pud table */
+ vmemmap_free_pages(pgd_page(*pgd), 0);
+ spin_lock(&init_mm.page_table_lock);
+ pgd_clear(pgd);
+ spin_unlock(&init_mm.page_table_lock);
+}
+
+static int split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase)
+{
+ struct page *page = pmd_page(*(pmd_t *)kpte);
+ int i = 0;
+ unsigned long magic;
+ unsigned long section_nr;
+
+ __split_large_page(kpte, address, pbase);
+ __flush_tlb_all();
+
+ magic = (unsigned long) page->lru.next;
+ if (magic == SECTION_INFO) {
+ section_nr = pfn_to_section_nr(page_to_pfn(page));
+ while (i < PTRS_PER_PMD) {
+ page++;
+ i++;
+ get_page_bootmem(section_nr, page, SECTION_INFO);
+ }
+ }
+
+ return 0;
+}
+
+static void vmemmap_pte_remove(pmd_t *pmd, unsigned long addr, unsigned long end)
+{
+ pte_t *pte;
+ unsigned long next;
+ void *page_addr;
+
+ pte = pte_offset_kernel(pmd, addr);
+ for (; addr < end; pte++, addr += PAGE_SIZE) {
+ next = (addr + PAGE_SIZE) & PAGE_MASK;
+ if (next > end)
+ next = end;
+
+ if (pte_none(*pte))
+ continue;
+ if (IS_ALIGNED(addr, PAGE_SIZE) &&
+ IS_ALIGNED(next, PAGE_SIZE)) {
+ vmemmap_free_pages(pte_page(*pte), 0);
+ spin_lock(&init_mm.page_table_lock);
+ pte_clear(&init_mm, addr, pte);
+ spin_unlock(&init_mm.page_table_lock);
+ } else {
+ /*
+ * Removed page structs are filled with 0xFD.
+ */
+ memset((void *)addr, PAGE_INUSE, next - addr);
+ page_addr = page_address(pte_page(*pte));
+
+ if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) {
+ spin_lock(&init_mm.page_table_lock);
+ pte_clear(&init_mm, addr, pte);
+ spin_unlock(&init_mm.page_table_lock);
+ }
+ }
+ }
+
+ free_pte_table(pmd);
+ __flush_tlb_all();
+}
+
+static void vmemmap_pmd_remove(pud_t *pud, unsigned long addr, unsigned long end)
+{
+ unsigned long next;
+ pmd_t *pmd;
+
+ pmd = pmd_offset(pud, addr);
+ for (; addr < end; addr = next, pmd++) {
+ next = pmd_addr_end(addr, end);
+ if (pmd_none(*pmd))
+ continue;
+
+ if (cpu_has_pse) {
+ unsigned long pte_base;
+
+ if (IS_ALIGNED(addr, PMD_SIZE) &&
+ IS_ALIGNED(next, PMD_SIZE)) {
+ vmemmap_free_pages(pmd_page(*pmd),
+ get_order(PMD_SIZE));
+ spin_lock(&init_mm.page_table_lock);
+ pmd_clear(pmd);
+ spin_unlock(&init_mm.page_table_lock);
+ continue;
+ }
+
+ /*
+ * We use 2M page, but we need to remove part of them,
+ * so split 2M page to 4K page.
+ */
+ pte_base = get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK);
+ if (!pte_base) {
+ WARN_ON(1);
+ continue;
+ }
+
+ split_large_page((pte_t *)pmd, addr, (pte_t *)pte_base);
+ __flush_tlb_all();
+
+ spin_lock(&init_mm.page_table_lock);
+ pmd_populate_kernel(&init_mm, pmd, (pte_t *)pte_base);
+ spin_unlock(&init_mm.page_table_lock);
+ }
+
+ vmemmap_pte_remove(pmd, addr, next);
+ }
+
+ free_pmd_table(pud);
+ __flush_tlb_all();
+}
+
+static void vmemmap_pud_remove(pgd_t *pgd, unsigned long addr, unsigned long end)
+{
+ unsigned long next;
+ pud_t *pud;
+
+ pud = pud_offset(pgd, addr);
+ for (; addr < end; addr = next, pud++) {
+ next = pud_addr_end(addr, end);
+ if (pud_none(*pud))
+ continue;
+
+ vmemmap_pmd_remove(pud, addr, next);
+ }
+
+ free_pud_table(pgd);
+ __flush_tlb_all();
+}
+
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+ unsigned long addr = (unsigned long)memmap;
+ unsigned long end = (unsigned long)(memmap + nr_pages);
+ unsigned long next;
+
+ for (; addr < end; addr = next) {
+ pgd_t *pgd = pgd_offset_k(addr);
+
+ next = pgd_addr_end(addr, end);
+ if (!pgd_present(*pgd))
+ continue;
+
+ vmemmap_pud_remove(pgd, addr, next);
+ sync_global_pgds(addr, next - 1);
+ }
+}
+#endif
diff --git a/mm/sparse.c b/mm/sparse.c
index fac95f2..4060229 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -615,10 +615,11 @@ static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
}
static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
{
- return; /* XXX: Not implemented yet */
+ vmemmap_free(memmap, nr_pages);
}
static void free_map_bootmem(struct page *page, unsigned long nr_pages)
{
+ vmemmap_free(page, nr_pages);
}
#else
static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
--
1.7.6.1
On 2012/11/30 9:45, Wen Congyang wrote:
> At 11/28/2012 05:40 PM, Jianguo Wu Wrote:
>> Hi Congyang,
>>
>> I think vmemmap's pgtable pages should be freed after all entries are cleared, I have a patch to do this.
>> The code logic is the same as [Patch v4 09/12] memory-hotplug: remove page table of x86_64 architecture.
>>
>> How do you think about this?
>>
>> Signed-off-by: Jianguo Wu <wujianguo@...wei.com>
>> Signed-off-by: Jiang Liu <jiang.liu@...wei.com>
>> ---
>> include/linux/mm.h | 1 +
>> mm/sparse-vmemmap.c | 214 +++++++++++++++++++++++++++++++++++++++++++++++++++
>> mm/sparse.c | 5 +-
>> 3 files changed, 218 insertions(+), 2 deletions(-)
>>
>> diff --git a/include/linux/mm.h b/include/linux/mm.h
>> index 5657670..1f26af5 100644
>> --- a/include/linux/mm.h
>> +++ b/include/linux/mm.h
>> @@ -1642,6 +1642,7 @@ int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
>> void vmemmap_populate_print_last(void);
>> void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
>> unsigned long size);
>> +void vmemmap_free(struct page *memmap, unsigned long nr_pages);
>>
>> enum mf_flags {
>> MF_COUNT_INCREASED = 1 << 0,
>> diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
>> index 1b7e22a..242cb28 100644
>> --- a/mm/sparse-vmemmap.c
>> +++ b/mm/sparse-vmemmap.c
>> @@ -29,6 +29,10 @@
>> #include <asm/pgalloc.h>
>> #include <asm/pgtable.h>
>>
>> +#ifdef CONFIG_MEMORY_HOTREMOVE
>> +#include <asm/tlbflush.h>
>> +#endif
>> +
>> /*
>> * Allocate a block of memory to be used to back the virtual memory map
>> * or to back the page tables that are used to create the mapping.
>> @@ -224,3 +228,213 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
>> vmemmap_buf_end = NULL;
>> }
>> }
>> +
>> +#ifdef CONFIG_MEMORY_HOTREMOVE
>> +static void vmemmap_free_pages(struct page *page, int order)
>> +{
>> + struct zone *zone;
>> + unsigned long magic;
>> +
>> + magic = (unsigned long) page->lru.next;
>> + if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
>> + put_page_bootmem(page);
>> +
>> + zone = page_zone(page);
>> + zone_span_writelock(zone);
>> + zone->present_pages++;
>> + zone_span_writeunlock(zone);
>> + totalram_pages++;
>> + } else {
>> + if (is_vmalloc_addr(page_address(page)))
>> + vfree(page_address(page));
>
> Hmm, vmemmap doesn't use vmalloc() to allocate memory.
>
>> + else
>> + free_pages((unsigned long)page_address(page), order);
>> + }
>> +}
>> +
>> +static void free_pte_table(pmd_t *pmd)
>> +{
>> + pte_t *pte, *pte_start;
>> + int i;
>> +
>> + pte_start = (pte_t *)pmd_page_vaddr(*pmd);
>> + for (i = 0; i < PTRS_PER_PTE; i++) {
>> + pte = pte_start + i;
>> + if (pte_val(*pte))
>> + return;
>> + }
>> +
>> + /* free a pte talbe */
>> + vmemmap_free_pages(pmd_page(*pmd), 0);
>> + spin_lock(&init_mm.page_table_lock);
>> + pmd_clear(pmd);
>> + spin_unlock(&init_mm.page_table_lock);
>> +}
>> +
>> +static void free_pmd_table(pud_t *pud)
>> +{
>> + pmd_t *pmd, *pmd_start;
>> + int i;
>> +
>> + pmd_start = (pmd_t *)pud_page_vaddr(*pud);
>> + for (i = 0; i < PTRS_PER_PMD; i++) {
>> + pmd = pmd_start + i;
>> + if (pmd_val(*pmd))
>> + return;
>> + }
>> +
>> + /* free a pmd talbe */
>> + vmemmap_free_pages(pud_page(*pud), 0);
>> + spin_lock(&init_mm.page_table_lock);
>> + pud_clear(pud);
>> + spin_unlock(&init_mm.page_table_lock);
>> +}
>> +
>> +static void free_pud_table(pgd_t *pgd)
>> +{
>> + pud_t *pud, *pud_start;
>> + int i;
>> +
>> + pud_start = (pud_t *)pgd_page_vaddr(*pgd);
>> + for (i = 0; i < PTRS_PER_PUD; i++) {
>> + pud = pud_start + i;
>> + if (pud_val(*pud))
>> + return;
>> + }
>> +
>> + /* free a pud table */
>> + vmemmap_free_pages(pgd_page(*pgd), 0);
>> + spin_lock(&init_mm.page_table_lock);
>> + pgd_clear(pgd);
>> + spin_unlock(&init_mm.page_table_lock);
>> +}
>> +
>> +static int split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase)
>> +{
>> + struct page *page = pmd_page(*(pmd_t *)kpte);
>> + int i = 0;
>> + unsigned long magic;
>> + unsigned long section_nr;
>> +
>> + __split_large_page(kpte, address, pbase);
>> + __flush_tlb_all();
>> +
>> + magic = (unsigned long) page->lru.next;
>> + if (magic == SECTION_INFO) {
>> + section_nr = pfn_to_section_nr(page_to_pfn(page));
>> + while (i < PTRS_PER_PMD) {
>> + page++;
>> + i++;
>> + get_page_bootmem(section_nr, page, SECTION_INFO);
>> + }
>> + }
>> +
>> + return 0;
>> +}
>> +
>> +static void vmemmap_pte_remove(pmd_t *pmd, unsigned long addr, unsigned long end)
>> +{
>> + pte_t *pte;
>> + unsigned long next;
>> +
>> + pte = pte_offset_kernel(pmd, addr);
>> + for (; addr < end; pte++, addr += PAGE_SIZE) {
>> + next = (addr + PAGE_SIZE) & PAGE_MASK;
>> + if (next > end)
>> + next = end;
>> +
>> + if (pte_none(*pte))
>> + continue;
>> + if (IS_ALIGNED(addr, PAGE_SIZE) &&
>> + IS_ALIGNED(end, PAGE_SIZE)) {
>> + vmemmap_free_pages(pte_page(*pte), 0);
>> + spin_lock(&init_mm.page_table_lock);
>> + pte_clear(&init_mm, addr, pte);
>> + spin_unlock(&init_mm.page_table_lock);
>
> If addr or end is not alianed with PAGE_SIZE, you may leak some
> memory.
>
>> + }
>> + }
>> +
>> + free_pte_table(pmd);
>> + __flush_tlb_all();
>> +}
>> +
>> +static void vmemmap_pmd_remove(pud_t *pud, unsigned long addr, unsigned long end)
>> +{
>> + unsigned long next;
>> + pmd_t *pmd;
>> +
>> + pmd = pmd_offset(pud, addr);
>> + for (; addr < end; addr = next, pmd++) {
>> + next = pmd_addr_end(addr, end);
>> + if (pmd_none(*pmd))
>> + continue;
>> +
>> + if (cpu_has_pse) {
>> + unsigned long pte_base;
>> +
>> + if (IS_ALIGNED(addr, PMD_SIZE) &&
>> + IS_ALIGNED(next, PMD_SIZE)) {
>> + vmemmap_free_pages(pmd_page(*pmd),
>> + get_order(PMD_SIZE));
>> + spin_lock(&init_mm.page_table_lock);
>> + pmd_clear(pmd);
>> + spin_unlock(&init_mm.page_table_lock);
>> + continue;
>> + }
>> +
>> + /*
>> + * We use 2M page, but we need to remove part of them,
>> + * so split 2M page to 4K page.
>> + */
>> + pte_base = get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK);
>
> get_zeored_page() may fail. You should handle this error.
>
>> + split_large_page((pte_t *)pmd, addr, (pte_t *)pte_base);
>> + __flush_tlb_all();
>> +
>> + spin_lock(&init_mm.page_table_lock);
>> + pmd_populate_kernel(&init_mm, pmd, (pte_t *)pte_base);
>> + spin_unlock(&init_mm.page_table_lock);
>> + }
>> +
>> + vmemmap_pte_remove(pmd, addr, next);
>> + }
>> +
>> + free_pmd_table(pud);
>> + __flush_tlb_all();
>> +}
>> +
>> +static void vmemmap_pud_remove(pgd_t *pgd, unsigned long addr, unsigned long end)
>> +{
>> + unsigned long next;
>> + pud_t *pud;
>> +
>> + pud = pud_offset(pgd, addr);
>> + for (; addr < end; addr = next, pud++) {
>> + next = pud_addr_end(addr, end);
>> + if (pud_none(*pud))
>> + continue;
>> +
>> + vmemmap_pmd_remove(pud, addr, next);
>> + }
>> +
>> + free_pud_table(pgd);
>> + __flush_tlb_all();
>> +}
>> +
>> +void vmemmap_free(struct page *memmap, unsigned long nr_pages)
>> +{
>> + unsigned long addr = (unsigned long)memmap;
>> + unsigned long end = (unsigned long)(memmap + nr_pages);
>> + unsigned long next;
>> +
>> + for (; addr < end; addr = next) {
>> + pgd_t *pgd = pgd_offset_k(addr);
>> +
>> + next = pgd_addr_end(addr, end);
>> + if (!pgd_present(*pgd))
>> + continue;
>> +
>> + vmemmap_pud_remove(pgd, addr, next);
>> + sync_global_pgds(addr, next);
>
> The parameter for sync_global_pgds() is [start, end], not
> [start, end)
>
>> + }
>> +}
>> +#endif
>> diff --git a/mm/sparse.c b/mm/sparse.c
>> index fac95f2..3a16d68 100644
>> --- a/mm/sparse.c
>> +++ b/mm/sparse.c
>> @@ -613,12 +613,13 @@ static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
>> /* This will make the necessary allocations eventually. */
>> return sparse_mem_map_populate(pnum, nid);
>> }
>> -static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
>> +static void __kfree_section_memmap(struct page *page, unsigned long nr_pages)
> Why do you change this line?
>
>> {
>> - return; /* XXX: Not implemented yet */
>> + vmemmap_free(page, nr_pages);
>> }
>> static void free_map_bootmem(struct page *page, unsigned long nr_pages)
>> {
>> + vmemmap_free(page, nr_pages);
>> }
>> #else
>> static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
>
>
> .
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists