luck/tmp_suning_uos_patched
1
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity

powerpc: Reduce PTE table memory wastage

Browse Source 
We allocate one page for the last level of linux page table. With THP and
large page size of 16MB, that would mean we are wasting large part
of that page. To map 16MB area, we only need a PTE space of 2K with 64K
page size. This patch reduce the space wastage by sharing the page
allocated for the last level of linux page table with multiple pmd
entries. We call these smaller chunks PTE page fragments and allocated
page, PTE page.

In order to support systems which doesn't have 64K HPTE support, we also
add another 2K to PTE page fragment. The second half of the PTE fragments
is used for storing slot and secondary bit information of an HPTE. With this
we now have a 4K PTE fragment.

We use a simple approach to share the PTE page. On allocation, we bump the
PTE page refcount to 16 and share the PTE page with the next 16 pte alloc
request. This should help in the node locality of the PTE page fragment,
assuming that the immediate pte alloc request will mostly come from the
same NUMA node. We don't try to reuse the freed PTE page fragment. Hence
we could be waisting some space.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This commit is contained in:
Aneesh Kumar K.V 2013-04-28 09:37:33 +00:00 committed by Benjamin Herrenschmidt
parent d614bb0412
commit 5c1f6ee9a3
7 changed files with 195 additions and 58 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
arch/powerpc/include/asm/mmu-book3e.h
View File

@ -231,6 +231,10 @@ typedef struct {
u64 high_slices_psize; /* 4 bits per slice for now */
u16 user_psize; /* page size index */
#endif
#ifdef CONFIG_PPC_64K_PAGES
/* for 4K PTE fragment support */
void *pte_frag;
#endif
} mm_context_t;
/* Page size definitions, common between 32 and 64-bit

4
arch/powerpc/include/asm/mmu-hash64.h
View File

@ -516,6 +516,10 @@ typedef struct {
unsigned long acop; /* mask of enabled coprocessor types */
unsigned int cop_pid; /* pid value used with coprocessors */
#endif /* CONFIG_PPC_ICSWX */
#ifdef CONFIG_PPC_64K_PAGES
/* for 4K PTE fragment support */
void *pte_frag;
#endif
} mm_context_t;

4
arch/powerpc/include/asm/page.h
View File

@ -393,7 +393,11 @@ void arch_free_page(struct page *page, int order);
struct vm_area_struct;
#ifdef CONFIG_PPC_64K_PAGES
typedef pte_t *pgtable_t;
#else
typedef struct page *pgtable_t;
#endif
#include <asm-generic/memory_model.h>
#endif /* __ASSEMBLY__ */

82
arch/powerpc/include/asm/pgalloc-64.h
View File

@ -152,6 +152,23 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
}
#else /* if CONFIG_PPC_64K_PAGES */
/*
* we support 16 fragments per PTE page.
*/
#define PTE_FRAG_NR 16
/*
* We use a 2K PTE page fragment and another 2K for storing
* real_pte_t hash index
*/
#define PTE_FRAG_SIZE_SHIFT 12
#define PTE_FRAG_SIZE (2 * PTRS_PER_PTE * sizeof(pte_t))
extern pte_t *page_table_alloc(struct mm_struct *, unsigned long, int);
extern void page_table_free(struct mm_struct *, unsigned long *, int);
extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
#ifdef CONFIG_SMP
extern void __tlb_remove_table(void *_table);
#endif
#define pud_populate(mm, pud, pmd) pud_set(pud, (unsigned long)pmd)
@ -164,90 +181,42 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
pgtable_t pte_page)
{
pmd_populate_kernel(mm, pmd, page_address(pte_page));
pmd_set(pmd, (unsigned long)pte_page);
}
static inline pgtable_t pmd_pgtable(pmd_t pmd)
{
return pmd_page(pmd);
return (pgtable_t)(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE);
}
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
return (pte_t *)page_table_alloc(mm, address, 1);
}
static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
unsigned long address)
unsigned long address)
{
struct page *page;
pte_t *pte;
pte = pte_alloc_one_kernel(mm, address);
if (!pte)
return NULL;
page = virt_to_page(pte);
pgtable_page_ctor(page);
return page;
return (pgtable_t)page_table_alloc(mm, address, 0);
}
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
{
free_page((unsigned long)pte);
page_table_free(mm, (unsigned long *)pte, 1);
}
static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
{
pgtable_page_dtor(ptepage);
__free_page(ptepage);
page_table_free(mm, (unsigned long *)ptepage, 0);
}
static inline void pgtable_free(void *table, unsigned index_size)
{
if (!index_size)
free_page((unsigned long)table);
else {
BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
kmem_cache_free(PGT_CACHE(index_size), table);
}
}
#ifdef CONFIG_SMP
static inline void pgtable_free_tlb(struct mmu_gather *tlb,
void *table, int shift)
{
unsigned long pgf = (unsigned long)table;
BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
pgf |= shift;
tlb_remove_table(tlb, (void *)pgf);
}
static inline void __tlb_remove_table(void *_table)
{
void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
pgtable_free(table, shift);
}
#else /* !CONFIG_SMP */
static inline void pgtable_free_tlb(struct mmu_gather *tlb,
void *table, int shift)
{
pgtable_free(table, shift);
}
#endif /* CONFIG_SMP */
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
struct page *page = page_address(table);
tlb_flush_pgtable(tlb, address);
pgtable_page_dtor(page);
pgtable_free_tlb(tlb, page, 0);
pgtable_free_tlb(tlb, table, 0);
}
#endif /* CONFIG_PPC_64K_PAGES */
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
@ -261,7 +230,6 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
}
#define __pmd_free_tlb(tlb, pmd, addr) \
pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
#ifndef CONFIG_PPC_64K_PAGES

4
arch/powerpc/kernel/setup_64.c
View File

@ -583,7 +583,9 @@ void __init setup_arch(char **cmdline_p)
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = klimit;
#ifdef CONFIG_PPC_64K_PAGES
init_mm.context.pte_frag = NULL;
#endif
irqstack_early_init();
exc_lvl_early_init();
emergency_stack_init();

37
arch/powerpc/mm/mmu_context_hash64.c
View File

@ -23,6 +23,7 @@
#include <linux/slab.h>
#include <asm/mmu_context.h>
#include <asm/pgalloc.h>
#include "icswx.h"
@ -85,6 +86,9 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
spin_lock_init(mm->context.cop_lockp);
#endif /* CONFIG_PPC_ICSWX */
#ifdef CONFIG_PPC_64K_PAGES
mm->context.pte_frag = NULL;
#endif
return 0;
}
@ -96,13 +100,46 @@ void __destroy_context(int context_id)
}
EXPORT_SYMBOL_GPL(__destroy_context);
#ifdef CONFIG_PPC_64K_PAGES
static void destroy_pagetable_page(struct mm_struct *mm)
{
int count;
void *pte_frag;
struct page *page;
pte_frag = mm->context.pte_frag;
if (!pte_frag)
return;
page = virt_to_page(pte_frag);
/* drop all the pending references */
count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT;
/* We allow PTE_FRAG_NR fragments from a PTE page */
count = atomic_sub_return(PTE_FRAG_NR - count, &page->_count);
if (!count) {
pgtable_page_dtor(page);
free_hot_cold_page(page, 0);
}
}
#else
static inline void destroy_pagetable_page(struct mm_struct *mm)
{
return;
}
#endif
void destroy_context(struct mm_struct *mm)
{
#ifdef CONFIG_PPC_ICSWX
drop_cop(mm->context.acop, mm);
kfree(mm->context.cop_lockp);
mm->context.cop_lockp = NULL;
#endif /* CONFIG_PPC_ICSWX */
destroy_pagetable_page(mm);
__destroy_context(mm->context.id);
subpage_prot_free(mm);
mm->context.id = MMU_NO_CONTEXT;

118
arch/powerpc/mm/pgtable_64.c
View File

@ -337,3 +337,121 @@ EXPORT_SYMBOL(__ioremap_at);
EXPORT_SYMBOL(iounmap);
EXPORT_SYMBOL(__iounmap);
EXPORT_SYMBOL(__iounmap_at);
#ifdef CONFIG_PPC_64K_PAGES
static pte_t *get_from_cache(struct mm_struct *mm)
{
void *pte_frag, *ret;
spin_lock(&mm->page_table_lock);
ret = mm->context.pte_frag;
if (ret) {
pte_frag = ret + PTE_FRAG_SIZE;
/*
* If we have taken up all the fragments mark PTE page NULL
*/
if (((unsigned long)pte_frag & ~PAGE_MASK) == 0)
pte_frag = NULL;
mm->context.pte_frag = pte_frag;
}
spin_unlock(&mm->page_table_lock);
return (pte_t *)ret;
}
static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
{
void *ret = NULL;
struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
__GFP_REPEAT | __GFP_ZERO);
if (!page)
return NULL;
ret = page_address(page);
spin_lock(&mm->page_table_lock);
/*
* If we find pgtable_page set, we return
* the allocated page with single fragement
* count.
*/
if (likely(!mm->context.pte_frag)) {
atomic_set(&page->_count, PTE_FRAG_NR);
mm->context.pte_frag = ret + PTE_FRAG_SIZE;
}
spin_unlock(&mm->page_table_lock);
if (!kernel)
pgtable_page_ctor(page);
return (pte_t *)ret;
}
pte_t *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel)
{
pte_t *pte;
pte = get_from_cache(mm);
if (pte)
return pte;
return __alloc_for_cache(mm, kernel);
}
void page_table_free(struct mm_struct *mm, unsigned long *table, int kernel)
{
struct page *page = virt_to_page(table);
if (put_page_testzero(page)) {
if (!kernel)
pgtable_page_dtor(page);
free_hot_cold_page(page, 0);
}
}
#ifdef CONFIG_SMP
static void page_table_free_rcu(void *table)
{
struct page *page = virt_to_page(table);
if (put_page_testzero(page)) {
pgtable_page_dtor(page);
free_hot_cold_page(page, 0);
}
}
void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
{
unsigned long pgf = (unsigned long)table;
BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
pgf |= shift;
tlb_remove_table(tlb, (void *)pgf);
}
void __tlb_remove_table(void *_table)
{
void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
if (!shift)
/* PTE page needs special handling */
page_table_free_rcu(table);
else {
BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
kmem_cache_free(PGT_CACHE(shift), table);
}
}
#else
void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
{
if (!shift) {
/* PTE page needs special handling */
struct page *page = virt_to_page(table);
if (put_page_testzero(page)) {
pgtable_page_dtor(page);
free_hot_cold_page(page, 0);
}
} else {
BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
kmem_cache_free(PGT_CACHE(shift), table);
}
}
#endif
#endif /* CONFIG_PPC_64K_PAGES */