PWN-Hunter/android_kernel_xiaomi_sdm845
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
e7eec2fc27
android_kernel_xiaomi_sdm845/arch/powerpc/include/asm/pgtable-ppc64.h
Benjamin Herrenschmidt 8d30c14cab powerpc/mm: Rework I$/D$ coherency (v3) 
This patch reworks the way we do I and D cache coherency on PowerPC.

The "old" way was split in 3 different parts depending on the processor type:

   - Hash with per-page exec support (64-bit and >= POWER4 only) does it
at hashing time, by preventing exec on unclean pages and cleaning pages
on exec faults.

   - Everything without per-page exec support (32-bit hash, 8xx, and
64-bit < POWER4) does it for all page going to user space in update_mmu_cache().

   - Embedded with per-page exec support does it from do_page_fault() on
exec faults, in a way similar to what the hash code does.

That leads to confusion, and bugs. For example, the method using update_mmu_cache()
is racy on SMP where another processor can see the new PTE and hash it in before
we have cleaned the cache, and then blow trying to execute. This is hard to hit but
I think it has bitten us in the past.

Also, it's inefficient for embedded where we always end up having to do at least
one more page fault.

This reworks the whole thing by moving the cache sync into two main call sites,
though we keep different behaviours depending on the HW capability. The call
sites are set_pte_at() which is now made out of line, and ptep_set_access_flags()
which joins the former in pgtable.c

The base idea for Embedded with per-page exec support, is that we now do the
flush at set_pte_at() time when coming from an exec fault, which allows us
to avoid the double fault problem completely (we can even improve the situation
more by implementing TLB preload in update_mmu_cache() but that's for later).

If for some reason we didn't do it there and we try to execute, we'll hit
the page fault, which will do a minor fault, which will hit ptep_set_access_flags()
to do things like update _PAGE_ACCESSED or _PAGE_DIRTY if needed, we just make
this guys also perform the I/D cache sync for exec faults now. This second path
is the catch all for things that weren't cleaned at set_pte_at() time.

For cpus without per-pag exec support, we always do the sync at set_pte_at(),
thus guaranteeing that when the PTE is visible to other processors, the cache
is clean.

For the 64-bit hash with per-page exec support case, we keep the old mechanism
for now. I'll look into changing it later, once I've reworked a bit how we
use _PAGE_EXEC.

This is also a first step for adding _PAGE_EXEC support for embedded platforms

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-02-11 16:00:10 +11:00

439 lines
14 KiB
C
Raw Blame History

#ifndef _ASM_POWERPC_PGTABLE_PPC64_H_
#define _ASM_POWERPC_PGTABLE_PPC64_H_
/*
* This file contains the functions and defines necessary to modify and use
* the ppc64 hashed page table.
*/
#ifndef __ASSEMBLY__
#include <linux/stddef.h>
#include <asm/tlbflush.h>
#endif /* __ASSEMBLY__ */
#ifdef CONFIG_PPC_64K_PAGES
#include <asm/pgtable-64k.h>
#else
#include <asm/pgtable-4k.h>
#endif
#define FIRST_USER_ADDRESS 0
/*
* Size of EA range mapped by our pagetables.
*/
#define PGTABLE_EADDR_SIZE (PTE_INDEX_SIZE + PMD_INDEX_SIZE + \
PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
#define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE)
#if TASK_SIZE_USER64 > PGTABLE_RANGE
#error TASK_SIZE_USER64 exceeds pagetable range
#endif
#if TASK_SIZE_USER64 > (1UL << (USER_ESID_BITS + SID_SHIFT))
#error TASK_SIZE_USER64 exceeds user VSID range
#endif
/*
* Define the address range of the vmalloc VM area.
*/
#define VMALLOC_START ASM_CONST(0xD000000000000000)
#define VMALLOC_SIZE (PGTABLE_RANGE >> 1)
#define VMALLOC_END (VMALLOC_START + VMALLOC_SIZE)
/*
* Define the address ranges for MMIO and IO space :
*
* ISA_IO_BASE = VMALLOC_END, 64K reserved area
* PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces
* IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE
*/
#define FULL_IO_SIZE 0x80000000ul
#define ISA_IO_BASE (VMALLOC_END)
#define ISA_IO_END (VMALLOC_END + 0x10000ul)
#define PHB_IO_BASE (ISA_IO_END)
#define PHB_IO_END (VMALLOC_END + FULL_IO_SIZE)
#define IOREMAP_BASE (PHB_IO_END)
#define IOREMAP_END (VMALLOC_START + PGTABLE_RANGE)
/*
* Region IDs
*/
#define REGION_SHIFT 60UL
#define REGION_MASK (0xfUL << REGION_SHIFT)
#define REGION_ID(ea) (((unsigned long)(ea)) >> REGION_SHIFT)
#define VMALLOC_REGION_ID (REGION_ID(VMALLOC_START))
#define KERNEL_REGION_ID (REGION_ID(PAGE_OFFSET))
#define VMEMMAP_REGION_ID (0xfUL)
#define USER_REGION_ID (0UL)
/*
* Defines the address of the vmemap area, in its own region
*/
#define VMEMMAP_BASE (VMEMMAP_REGION_ID << REGION_SHIFT)
#define vmemmap ((struct page *)VMEMMAP_BASE)
/*
* Common bits in a linux-style PTE. These match the bits in the
* (hardware-defined) PowerPC PTE as closely as possible. Additional
* bits may be defined in pgtable-*.h
*/
#define _PAGE_PRESENT 0x0001 /* software: pte contains a translation */
#define _PAGE_USER 0x0002 /* matches one of the PP bits */
#define _PAGE_FILE 0x0002 /* (!present only) software: pte holds file offset */
#define _PAGE_EXEC 0x0004 /* No execute on POWER4 and newer (we invert) */
#define _PAGE_GUARDED 0x0008
#define _PAGE_COHERENT 0x0010 /* M: enforce memory coherence (SMP systems) */
#define _PAGE_NO_CACHE 0x0020 /* I: cache inhibit */
#define _PAGE_WRITETHRU 0x0040 /* W: cache write-through */
#define _PAGE_DIRTY 0x0080 /* C: page changed */
#define _PAGE_ACCESSED 0x0100 /* R: page referenced */
#define _PAGE_RW 0x0200 /* software: user write access allowed */
#define _PAGE_BUSY 0x0800 /* software: PTE & hash are busy */
/* Strong Access Ordering */
#define _PAGE_SAO (_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT)
#define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_COHERENT)
#define _PAGE_WRENABLE (_PAGE_RW | _PAGE_DIRTY)
/* __pgprot defined in arch/powerpc/include/asm/page.h */
#define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_ACCESSED)
#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_USER)
#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_USER | _PAGE_EXEC)
#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER)
#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER)
#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
#define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_WRENABLE)
#define PAGE_KERNEL_CI __pgprot(_PAGE_PRESENT | _PAGE_ACCESSED | \
_PAGE_WRENABLE | _PAGE_NO_CACHE | _PAGE_GUARDED)
#define PAGE_KERNEL_EXEC __pgprot(_PAGE_BASE | _PAGE_WRENABLE | _PAGE_EXEC)
#define PAGE_AGP __pgprot(_PAGE_BASE | _PAGE_WRENABLE | _PAGE_NO_CACHE)
#define HAVE_PAGE_AGP
#define PAGE_PROT_BITS (_PAGE_GUARDED | _PAGE_COHERENT | \
_PAGE_NO_CACHE | _PAGE_WRITETHRU | \
_PAGE_4K_PFN | _PAGE_RW | _PAGE_USER | \
_PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_EXEC)
/* PTEIDX nibble */
#define _PTEIDX_SECONDARY 0x8
#define _PTEIDX_GROUP_IX 0x7
/* To make some generic powerpc code happy */
#define _PAGE_HWEXEC 0
/*
* POWER4 and newer have per page execute protection, older chips can only
* do this on a segment (256MB) basis.
*
* Also, write permissions imply read permissions.
* This is the closest we can get..
*
* Note due to the way vm flags are laid out, the bits are XWR
*/
#define __P000 PAGE_NONE
#define __P001 PAGE_READONLY
#define __P010 PAGE_COPY
#define __P011 PAGE_COPY
#define __P100 PAGE_READONLY_X
#define __P101 PAGE_READONLY_X
#define __P110 PAGE_COPY_X
#define __P111 PAGE_COPY_X
#define __S000 PAGE_NONE
#define __S001 PAGE_READONLY
#define __S010 PAGE_SHARED
#define __S011 PAGE_SHARED
#define __S100 PAGE_READONLY_X
#define __S101 PAGE_READONLY_X
#define __S110 PAGE_SHARED_X
#define __S111 PAGE_SHARED_X
#ifdef CONFIG_PPC_MM_SLICES
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
#endif /* CONFIG_PPC_MM_SLICES */
#ifndef __ASSEMBLY__
/*
* Conversion functions: convert a page and protection to a page entry,
* and a page entry and page directory to the page they refer to.
*
* mk_pte takes a (struct page *) as input
*/
#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
{
pte_t pte;
pte_val(pte) = (pfn << PTE_RPN_SHIFT) | pgprot_val(pgprot);
return pte;
}
#define pte_modify(_pte, newprot) \
(__pte((pte_val(_pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)))
#define pte_none(pte) ((pte_val(pte) & ~_PAGE_HPTEFLAGS) == 0)
#define pte_present(pte) (pte_val(pte) & _PAGE_PRESENT)
/* pte_clear moved to later in this file */
#define pte_pfn(x) ((unsigned long)((pte_val(x)>>PTE_RPN_SHIFT)))
#define pte_page(x) pfn_to_page(pte_pfn(x))
#define PMD_BAD_BITS (PTE_TABLE_SIZE-1)
#define PUD_BAD_BITS (PMD_TABLE_SIZE-1)
#define pmd_set(pmdp, pmdval) (pmd_val(*(pmdp)) = (pmdval))
#define pmd_none(pmd) (!pmd_val(pmd))
#define pmd_bad(pmd) (!is_kernel_addr(pmd_val(pmd)) \
|| (pmd_val(pmd) & PMD_BAD_BITS))
#define pmd_present(pmd) (pmd_val(pmd) != 0)
#define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0)
#define pmd_page_vaddr(pmd) (pmd_val(pmd) & ~PMD_MASKED_BITS)
#define pmd_page(pmd) virt_to_page(pmd_page_vaddr(pmd))
#define pud_set(pudp, pudval) (pud_val(*(pudp)) = (pudval))
#define pud_none(pud) (!pud_val(pud))
#define pud_bad(pud) (!is_kernel_addr(pud_val(pud)) \
|| (pud_val(pud) & PUD_BAD_BITS))
#define pud_present(pud) (pud_val(pud) != 0)
#define pud_clear(pudp) (pud_val(*(pudp)) = 0)
#define pud_page_vaddr(pud) (pud_val(pud) & ~PUD_MASKED_BITS)
#define pud_page(pud) virt_to_page(pud_page_vaddr(pud))
#define pgd_set(pgdp, pudp) ({pgd_val(*(pgdp)) = (unsigned long)(pudp);})
/*
* Find an entry in a page-table-directory. We combine the address region
* (the high order N bits) and the pgd portion of the address.
*/
/* to avoid overflow in free_pgtables we don't use PTRS_PER_PGD here */
#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & 0x1ff)
#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address))
#define pmd_offset(pudp,addr) \
(((pmd_t *) pud_page_vaddr(*(pudp))) + (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)))
#define pte_offset_kernel(dir,addr) \
(((pte_t *) pmd_page_vaddr(*(dir))) + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)))
#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr))
#define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir), (addr))
#define pte_unmap(pte) do { } while(0)
#define pte_unmap_nested(pte) do { } while(0)
/* to find an entry in a kernel page-table-directory */
/* This now only contains the vmalloc pages */
#define pgd_offset_k(address) pgd_offset(&init_mm, address)
/*
* The following only work if pte_present() is true.
* Undefined behaviour if not..
*/
static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_RW;}
static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY;}
static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED;}
static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE;}
static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; }
static inline pte_t pte_wrprotect(pte_t pte) {
pte_val(pte) &= ~(_PAGE_RW); return pte; }
static inline pte_t pte_mkclean(pte_t pte) {
pte_val(pte) &= ~(_PAGE_DIRTY); return pte; }
static inline pte_t pte_mkold(pte_t pte) {
pte_val(pte) &= ~_PAGE_ACCESSED; return pte; }
static inline pte_t pte_mkwrite(pte_t pte) {
pte_val(pte) |= _PAGE_RW; return pte; }
static inline pte_t pte_mkdirty(pte_t pte) {
pte_val(pte) |= _PAGE_DIRTY; return pte; }
static inline pte_t pte_mkyoung(pte_t pte) {
pte_val(pte) |= _PAGE_ACCESSED; return pte; }
static inline pte_t pte_mkhuge(pte_t pte) {
return pte; }
static inline pte_t pte_mkspecial(pte_t pte) {
pte_val(pte) |= _PAGE_SPECIAL; return pte; }
static inline pgprot_t pte_pgprot(pte_t pte)
{
return __pgprot(pte_val(pte) & PAGE_PROT_BITS);
}
/* Atomic PTE updates */
static inline unsigned long pte_update(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep, unsigned long clr,
int huge)
{
unsigned long old, tmp;
__asm__ __volatile__(
"1: ldarx %0,0,%3 # pte_update\n\
andi. %1,%0,%6\n\
bne- 1b \n\
andc %1,%0,%4 \n\
stdcx. %1,0,%3 \n\
bne- 1b"
: "=&r" (old), "=&r" (tmp), "=m" (*ptep)
: "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY)
: "cc" );
/* huge pages use the old page table lock */
if (!huge)
assert_pte_locked(mm, addr);
if (old & _PAGE_HASHPTE)
hpte_need_flush(mm, addr, ptep, old, huge);
return old;
}
static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
unsigned long old;
if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
return 0;
old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0);
return (old & _PAGE_ACCESSED) != 0;
}
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
#define ptep_test_and_clear_young(__vma, __addr, __ptep) \
({ \
int __r; \
__r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \
__r; \
})
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
unsigned long old;
if ((pte_val(*ptep) & _PAGE_RW) == 0)
return;
old = pte_update(mm, addr, ptep, _PAGE_RW, 0);
}
static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
unsigned long old;
if ((pte_val(*ptep) & _PAGE_RW) == 0)
return;
old = pte_update(mm, addr, ptep, _PAGE_RW, 1);
}
/*
* We currently remove entries from the hashtable regardless of whether
* the entry was young or dirty. The generic routines only flush if the
* entry was young or dirty which is not good enough.
*
* We should be more intelligent about this but for the moment we override
* these functions and force a tlb flush unconditionally
*/
#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
#define ptep_clear_flush_young(__vma, __address, __ptep) \
({ \
int __young = __ptep_test_and_clear_young((__vma)->vm_mm, __address, \
__ptep); \
__young; \
})
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0);
return __pte(old);
}
static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t * ptep)
{
pte_update(mm, addr, ptep, ~0UL, 0);
}
/* Set the dirty and/or accessed bits atomically in a linux PTE, this
* function doesn't need to flush the hash entry
*/
static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
{
unsigned long bits = pte_val(entry) &
(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
unsigned long old, tmp;
__asm__ __volatile__(
"1: ldarx %0,0,%4\n\
andi. %1,%0,%6\n\
bne- 1b \n\
or %0,%3,%0\n\
stdcx. %0,0,%4\n\
bne- 1b"
:"=&r" (old), "=&r" (tmp), "=m" (*ptep)
:"r" (bits), "r" (ptep), "m" (*ptep), "i" (_PAGE_BUSY)
:"cc");
}
#define __HAVE_ARCH_PTE_SAME
#define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)
#define pte_ERROR(e) \
printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
#define pmd_ERROR(e) \
printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
#define pgd_ERROR(e) \
printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
/* Encode and de-code a swap entry */
#define __swp_type(entry) (((entry).val >> 1) & 0x3f)
#define __swp_offset(entry) ((entry).val >> 8)
#define __swp_entry(type, offset) ((swp_entry_t){((type)<< 1)|((offset)<<8)})
#define __pte_to_swp_entry(pte) ((swp_entry_t){pte_val(pte) >> PTE_RPN_SHIFT})
#define __swp_entry_to_pte(x) ((pte_t) { (x).val << PTE_RPN_SHIFT })
#define pte_to_pgoff(pte) (pte_val(pte) >> PTE_RPN_SHIFT)
#define pgoff_to_pte(off) ((pte_t) {((off) << PTE_RPN_SHIFT)|_PAGE_FILE})
#define PTE_FILE_MAX_BITS (BITS_PER_LONG - PTE_RPN_SHIFT)
void pgtable_cache_init(void);
/*
* find_linux_pte returns the address of a linux pte for a given
* effective address and directory. If not found, it returns zero.
*/static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea)
{
pgd_t *pg;
pud_t *pu;
pmd_t *pm;
pte_t *pt = NULL;
pg = pgdir + pgd_index(ea);
if (!pgd_none(*pg)) {
pu = pud_offset(pg, ea);
if (!pud_none(*pu)) {
pm = pmd_offset(pu, ea);
if (pmd_present(*pm))
pt = pte_offset_kernel(pm, ea);
}
}
return pt;
}
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long address);
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */
Reference in New Issue View Git Blame Copy Permalink