mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
4981d01ead
According to intel CPU manual, every time PGD entry is changed in i386 PAE mode, we need do a full TLB flush. Current code follows this and there is comment for this too in the code. But current code misses the multi-threaded case. A changed page table might be used by several CPUs, every such CPU should flush TLB. Usually this isn't a problem, because we prepopulate all PGD entries at process fork. But when the process does munmap and follows new mmap, this issue will be triggered. When it happens, some CPUs keep doing page faults: http://marc.info/?l=linux-kernel&m=129915020508238&w=2 Reported-by: Yasunori Goto<y-goto@jp.fujitsu.com> Tested-by: Yasunori Goto<y-goto@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Shaohua Li<shaohua.li@intel.com> Cc: Mallick Asit K <asit.k.mallick@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: linux-mm <linux-mm@kvack.org> Cc: stable <stable@kernel.org> LKML-Reference: <1300246649.2337.95.camel@sli10-conroe> Signed-off-by: Ingo Molnar <mingo@elte.hu>
143 lines
3.8 KiB
C
143 lines
3.8 KiB
C
#ifndef _ASM_X86_PGTABLE_3LEVEL_H
|
|
#define _ASM_X86_PGTABLE_3LEVEL_H
|
|
|
|
/*
|
|
* Intel Physical Address Extension (PAE) Mode - three-level page
|
|
* tables on PPro+ CPUs.
|
|
*
|
|
* Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
|
|
*/
|
|
|
|
#define pte_ERROR(e) \
|
|
printk("%s:%d: bad pte %p(%08lx%08lx).\n", \
|
|
__FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
|
|
#define pmd_ERROR(e) \
|
|
printk("%s:%d: bad pmd %p(%016Lx).\n", \
|
|
__FILE__, __LINE__, &(e), pmd_val(e))
|
|
#define pgd_ERROR(e) \
|
|
printk("%s:%d: bad pgd %p(%016Lx).\n", \
|
|
__FILE__, __LINE__, &(e), pgd_val(e))
|
|
|
|
/* Rules for using set_pte: the pte being assigned *must* be
|
|
* either not present or in a state where the hardware will
|
|
* not attempt to update the pte. In places where this is
|
|
* not possible, use pte_get_and_clear to obtain the old pte
|
|
* value and then use set_pte to update it. -ben
|
|
*/
|
|
static inline void native_set_pte(pte_t *ptep, pte_t pte)
|
|
{
|
|
ptep->pte_high = pte.pte_high;
|
|
smp_wmb();
|
|
ptep->pte_low = pte.pte_low;
|
|
}
|
|
|
|
static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
|
|
{
|
|
set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
|
|
}
|
|
|
|
static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
|
|
{
|
|
set_64bit((unsigned long long *)(pmdp), native_pmd_val(pmd));
|
|
}
|
|
|
|
static inline void native_set_pud(pud_t *pudp, pud_t pud)
|
|
{
|
|
set_64bit((unsigned long long *)(pudp), native_pud_val(pud));
|
|
}
|
|
|
|
/*
|
|
* For PTEs and PDEs, we must clear the P-bit first when clearing a page table
|
|
* entry, so clear the bottom half first and enforce ordering with a compiler
|
|
* barrier.
|
|
*/
|
|
static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
|
|
pte_t *ptep)
|
|
{
|
|
ptep->pte_low = 0;
|
|
smp_wmb();
|
|
ptep->pte_high = 0;
|
|
}
|
|
|
|
static inline void native_pmd_clear(pmd_t *pmd)
|
|
{
|
|
u32 *tmp = (u32 *)pmd;
|
|
*tmp = 0;
|
|
smp_wmb();
|
|
*(tmp + 1) = 0;
|
|
}
|
|
|
|
static inline void pud_clear(pud_t *pudp)
|
|
{
|
|
set_pud(pudp, __pud(0));
|
|
|
|
/*
|
|
* According to Intel App note "TLBs, Paging-Structure Caches,
|
|
* and Their Invalidation", April 2007, document 317080-001,
|
|
* section 8.1: in PAE mode we explicitly have to flush the
|
|
* TLB via cr3 if the top-level pgd is changed...
|
|
*
|
|
* Currently all places where pud_clear() is called either have
|
|
* flush_tlb_mm() followed or don't need TLB flush (x86_64 code or
|
|
* pud_clear_bad()), so we don't need TLB flush here.
|
|
*/
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
|
|
{
|
|
pte_t res;
|
|
|
|
/* xchg acts as a barrier before the setting of the high bits */
|
|
res.pte_low = xchg(&ptep->pte_low, 0);
|
|
res.pte_high = ptep->pte_high;
|
|
ptep->pte_high = 0;
|
|
|
|
return res;
|
|
}
|
|
#else
|
|
#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
|
|
#endif
|
|
|
|
#ifdef CONFIG_SMP
|
|
union split_pmd {
|
|
struct {
|
|
u32 pmd_low;
|
|
u32 pmd_high;
|
|
};
|
|
pmd_t pmd;
|
|
};
|
|
static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
|
|
{
|
|
union split_pmd res, *orig = (union split_pmd *)pmdp;
|
|
|
|
/* xchg acts as a barrier before setting of the high bits */
|
|
res.pmd_low = xchg(&orig->pmd_low, 0);
|
|
res.pmd_high = orig->pmd_high;
|
|
orig->pmd_high = 0;
|
|
|
|
return res.pmd;
|
|
}
|
|
#else
|
|
#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
|
|
#endif
|
|
|
|
/*
|
|
* Bits 0, 6 and 7 are taken in the low part of the pte,
|
|
* put the 32 bits of offset into the high part.
|
|
*/
|
|
#define pte_to_pgoff(pte) ((pte).pte_high)
|
|
#define pgoff_to_pte(off) \
|
|
((pte_t) { { .pte_low = _PAGE_FILE, .pte_high = (off) } })
|
|
#define PTE_FILE_MAX_BITS 32
|
|
|
|
/* Encode and de-code a swap entry */
|
|
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5)
|
|
#define __swp_type(x) (((x).val) & 0x1f)
|
|
#define __swp_offset(x) ((x).val >> 5)
|
|
#define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << 5})
|
|
#define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high })
|
|
#define __swp_entry_to_pte(x) ((pte_t){ { .pte_high = (x).val } })
|
|
|
|
#endif /* _ASM_X86_PGTABLE_3LEVEL_H */
|