2007-04-30 14:30:56 +08:00
|
|
|
#ifndef _ASM_POWERPC_PGALLOC_64_H
|
|
|
|
#define _ASM_POWERPC_PGALLOC_64_H
|
|
|
|
/*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/cpumask.h>
|
|
|
|
#include <linux/percpu.h>
|
|
|
|
|
2010-04-22 00:21:03 +08:00
|
|
|
struct vmemmap_backing {
|
|
|
|
struct vmemmap_backing *list;
|
|
|
|
unsigned long phys;
|
|
|
|
unsigned long virt_addr;
|
|
|
|
};
|
2013-11-16 01:31:32 +08:00
|
|
|
extern struct vmemmap_backing *vmemmap_list;
|
2010-04-22 00:21:03 +08:00
|
|
|
|
2009-10-29 00:27:18 +08:00
|
|
|
/*
|
|
|
|
* Functions that deal with pagetables that could be at any level of
|
|
|
|
* the table need to be passed an "index_size" so they know how to
|
|
|
|
* handle allocation. For PTE pages (which are linked to a struct
|
|
|
|
* page for now, and drawn from the main get_free_pages() pool), the
|
|
|
|
* allocation size will be (2^index_size * sizeof(pointer)) and
|
|
|
|
* allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
|
|
|
|
*
|
|
|
|
* The maximum index size needs to be big enough to allow any
|
|
|
|
* pagetable sizes we need, but small enough to fit in the low bits of
|
|
|
|
* any page table pointer. In other words all pagetables, even tiny
|
|
|
|
* ones, must be aligned to allow at least enough low 0 bits to
|
|
|
|
* contain this value. This value is also used as a mask, so it must
|
|
|
|
* be one less than a power of two.
|
|
|
|
*/
|
|
|
|
#define MAX_PGTABLE_INDEX_SIZE 0xf
|
|
|
|
|
2007-04-30 14:30:56 +08:00
|
|
|
extern struct kmem_cache *pgtable_cache[];
|
2013-04-28 17:37:29 +08:00
|
|
|
#define PGT_CACHE(shift) ({ \
|
|
|
|
BUG_ON(!(shift)); \
|
|
|
|
pgtable_cache[(shift) - 1]; \
|
|
|
|
})
|
2007-04-30 14:30:56 +08:00
|
|
|
|
|
|
|
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
|
|
|
|
{
|
2009-10-29 00:27:18 +08:00
|
|
|
return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
|
2007-04-30 14:30:56 +08:00
|
|
|
}
|
|
|
|
|
2008-02-05 14:29:14 +08:00
|
|
|
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
|
2007-04-30 14:30:56 +08:00
|
|
|
{
|
2009-10-29 00:27:18 +08:00
|
|
|
kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
|
2007-04-30 14:30:56 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
#ifndef CONFIG_PPC_64K_PAGES
|
|
|
|
|
|
|
|
#define pgd_populate(MM, PGD, PUD) pgd_set(PGD, PUD)
|
|
|
|
|
|
|
|
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
|
|
|
|
{
|
2009-10-29 00:27:18 +08:00
|
|
|
return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
|
2007-04-30 14:30:56 +08:00
|
|
|
GFP_KERNEL|__GFP_REPEAT);
|
|
|
|
}
|
|
|
|
|
2008-02-05 14:29:14 +08:00
|
|
|
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
|
2007-04-30 14:30:56 +08:00
|
|
|
{
|
2009-10-29 00:27:18 +08:00
|
|
|
kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud);
|
2007-04-30 14:30:56 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
|
|
|
|
{
|
|
|
|
pud_set(pud, (unsigned long)pmd);
|
|
|
|
}
|
|
|
|
|
|
|
|
#define pmd_populate(mm, pmd, pte_page) \
|
|
|
|
pmd_populate_kernel(mm, pmd, page_address(pte_page))
|
|
|
|
#define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, (unsigned long)(pte))
|
2008-02-08 20:22:04 +08:00
|
|
|
#define pmd_pgtable(pmd) pmd_page(pmd)
|
2007-04-30 14:30:56 +08:00
|
|
|
|
2013-04-28 17:37:32 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
|
|
|
|
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);
|
2013-11-15 06:31:38 +08:00
|
|
|
if (!pgtable_page_ctor(page)) {
|
|
|
|
__free_page(page);
|
|
|
|
return NULL;
|
|
|
|
}
|
2013-04-28 17:37:32 +08:00
|
|
|
return page;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
|
|
|
|
{
|
|
|
|
free_page((unsigned long)pte);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
|
|
|
|
{
|
|
|
|
pgtable_page_dtor(ptepage);
|
|
|
|
__free_page(ptepage);
|
|
|
|
}
|
|
|
|
|
|
|
|
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)
|
|
|
|
{
|
|
|
|
tlb_flush_pgtable(tlb, address);
|
powerpc: Fix PTE page address mismatch in pgtable ctor/dtor
In pte_alloc_one(), pgtable_page_ctor() is passed an address that has
not been converted by page_address() to the newly allocated PTE page.
When the PTE is freed, __pte_free_tlb() calls pgtable_page_dtor()
with an address to the PTE page that has been converted by page_address().
The mismatch in the PTE's page address causes pgtable_page_dtor() to access
invalid memory, so resources for that PTE (such as the page lock) is not
properly cleaned up.
On PPC32, only SMP kernels are affected.
On PPC64, only SMP kernels with 4K page size are affected.
This bug was introduced by commit d614bb041209fd7cb5e4b35e11a7b2f6ee8f62b8
"powerpc: Move the pte free routines from common header".
On a preempt-rt kernel, a spinlock is dynamically allocated for each
PTE in pgtable_page_ctor(). When the PTE is freed, calling
pgtable_page_dtor() with a mismatched page address causes a memory leak,
as the pointer to the PTE's spinlock is bogus.
On mainline, there isn't any immediately obvious symptoms, but the
problem still exists here.
Fixes: d614bb041209fd7c "powerpc: Move the pte free routes from common header"
Cc: Paul Mackerras <paulus@samba.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linux-stable <stable@vger.kernel.org> # v3.10+
Signed-off-by: Hong H. Pham <hong.pham@windriver.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-12-07 22:06:33 +08:00
|
|
|
pgtable_page_dtor(table);
|
|
|
|
pgtable_free_tlb(tlb, page_address(table), 0);
|
2013-04-28 17:37:32 +08:00
|
|
|
}
|
2007-04-30 14:30:56 +08:00
|
|
|
|
2013-04-28 17:37:32 +08:00
|
|
|
#else /* if CONFIG_PPC_64K_PAGES */
|
2013-04-28 17:37:33 +08:00
|
|
|
/*
|
|
|
|
* 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
|
2007-04-30 14:30:56 +08:00
|
|
|
|
|
|
|
#define pud_populate(mm, pud, pmd) pud_set(pud, (unsigned long)pmd)
|
|
|
|
|
|
|
|
static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
|
|
|
|
pte_t *pte)
|
|
|
|
{
|
|
|
|
pmd_set(pmd, (unsigned long)pte);
|
|
|
|
}
|
|
|
|
|
2013-04-28 17:37:32 +08:00
|
|
|
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
|
|
|
|
pgtable_t pte_page)
|
2007-04-30 14:30:56 +08:00
|
|
|
{
|
2013-04-28 17:37:33 +08:00
|
|
|
pmd_set(pmd, (unsigned long)pte_page);
|
2007-04-30 14:30:56 +08:00
|
|
|
}
|
|
|
|
|
2013-04-28 17:37:32 +08:00
|
|
|
static inline pgtable_t pmd_pgtable(pmd_t pmd)
|
2007-04-30 14:30:56 +08:00
|
|
|
{
|
2013-05-12 06:33:19 +08:00
|
|
|
return (pgtable_t)(pmd_val(pmd) & ~PMD_MASKED_BITS);
|
2007-04-30 14:30:56 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
|
|
|
|
unsigned long address)
|
|
|
|
{
|
2013-04-28 17:37:33 +08:00
|
|
|
return (pte_t *)page_table_alloc(mm, address, 1);
|
2007-04-30 14:30:56 +08:00
|
|
|
}
|
|
|
|
|
2008-02-08 20:22:04 +08:00
|
|
|
static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
|
2013-04-28 17:37:33 +08:00
|
|
|
unsigned long address)
|
2007-04-30 14:30:56 +08:00
|
|
|
{
|
2013-04-28 17:37:33 +08:00
|
|
|
return (pgtable_t)page_table_alloc(mm, address, 0);
|
2007-04-30 14:30:56 +08:00
|
|
|
}
|
|
|
|
|
2013-04-28 17:37:32 +08:00
|
|
|
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
|
|
|
|
{
|
2013-04-28 17:37:33 +08:00
|
|
|
page_table_free(mm, (unsigned long *)pte, 1);
|
2013-04-28 17:37:32 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
|
|
|
|
{
|
2013-04-28 17:37:33 +08:00
|
|
|
page_table_free(mm, (unsigned long *)ptepage, 0);
|
2013-04-28 17:37:32 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
|
|
|
|
unsigned long address)
|
|
|
|
{
|
|
|
|
tlb_flush_pgtable(tlb, address);
|
2013-04-28 17:37:33 +08:00
|
|
|
pgtable_free_tlb(tlb, table, 0);
|
2013-04-28 17:37:32 +08:00
|
|
|
}
|
|
|
|
#endif /* CONFIG_PPC_64K_PAGES */
|
|
|
|
|
|
|
|
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
|
|
|
|
{
|
2013-06-20 17:00:14 +08:00
|
|
|
return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
|
2013-04-28 17:37:32 +08:00
|
|
|
GFP_KERNEL|__GFP_REPEAT);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
|
|
|
|
{
|
2013-06-20 17:00:14 +08:00
|
|
|
kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd);
|
2013-04-28 17:37:32 +08:00
|
|
|
}
|
|
|
|
|
2009-10-29 00:27:18 +08:00
|
|
|
#define __pmd_free_tlb(tlb, pmd, addr) \
|
2013-06-20 17:00:14 +08:00
|
|
|
pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX)
|
2007-04-30 14:30:56 +08:00
|
|
|
#ifndef CONFIG_PPC_64K_PAGES
|
mm: Pass virtual address to [__]p{te,ud,md}_free_tlb()
mm: Pass virtual address to [__]p{te,ud,md}_free_tlb()
Upcoming paches to support the new 64-bit "BookE" powerpc architecture
will need to have the virtual address corresponding to PTE page when
freeing it, due to the way the HW table walker works.
Basically, the TLB can be loaded with "large" pages that cover the whole
virtual space (well, sort-of, half of it actually) represented by a PTE
page, and which contain an "indirect" bit indicating that this TLB entry
RPN points to an array of PTEs from which the TLB can then create direct
entries. Thus, in order to invalidate those when PTE pages are deleted,
we need the virtual address to pass to tlbilx or tlbivax instructions.
The old trick of sticking it somewhere in the PTE page struct page sucks
too much, the address is almost readily available in all call sites and
almost everybody implemets these as macros, so we may as well add the
argument everywhere. I added it to the pmd and pud variants for consistency.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: David Howells <dhowells@redhat.com> [MN10300 & FRV]
Acked-by: Nick Piggin <npiggin@suse.de>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> [s390]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-07-22 13:44:28 +08:00
|
|
|
#define __pud_free_tlb(tlb, pud, addr) \
|
2009-10-29 00:27:18 +08:00
|
|
|
pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
|
|
|
|
|
2007-04-30 14:30:56 +08:00
|
|
|
#endif /* CONFIG_PPC_64K_PAGES */
|
|
|
|
|
|
|
|
#define check_pgt_cache() do { } while (0)
|
|
|
|
|
|
|
|
#endif /* _ASM_POWERPC_PGALLOC_64_H */
|