linux/arch/s390/include/asm/pgalloc.h
Qi Zheng db6b435d73 mm: pgtable: introduce pagetable_dtor()
The pagetable_p*_dtor() are exactly the same except for the handling of
ptlock.  If we make ptlock_free() handle the case where ptdesc->ptl is
NULL and remove VM_BUG_ON_PAGE() from pmd_ptlock_free(), we can unify
pagetable_p*_dtor() into one function.  Let's introduce pagetable_dtor()
to do this.

Later, pagetable_dtor() will be moved to tlb_remove_ptdesc(), so that
ptlock and page table pages can be freed together (regardless of whether
RCU is used).  This prevents the use-after-free problem where the ptlock
is freed immediately but the page table pages is freed later via RCU.

Link: https://lkml.kernel.org/r/47f44fff9dc68d9d9e9a0d6c036df275f820598a.1736317725.git.zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Originally-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kevin Brodsky <kevin.brodsky@arm.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>	[s390]
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2025-01-25 20:22:22 -08:00

169 lines
4.3 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* S390 version
* Copyright IBM Corp. 1999, 2000
* Author(s): Hartmut Penner (hp@de.ibm.com)
* Martin Schwidefsky (schwidefsky@de.ibm.com)
*
* Derived from "include/asm-i386/pgalloc.h"
* Copyright (C) 1994 Linus Torvalds
*/
#ifndef _S390_PGALLOC_H
#define _S390_PGALLOC_H
#include <linux/threads.h>
#include <linux/string.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#define CRST_ALLOC_ORDER 2
unsigned long *crst_table_alloc(struct mm_struct *);
void crst_table_free(struct mm_struct *, unsigned long *);
unsigned long *page_table_alloc(struct mm_struct *);
struct ptdesc *page_table_alloc_pgste(struct mm_struct *mm);
void page_table_free(struct mm_struct *, unsigned long *);
void page_table_free_pgste(struct ptdesc *ptdesc);
extern int page_table_allocate_pgste;
static inline void crst_table_init(unsigned long *crst, unsigned long entry)
{
memset64((u64 *)crst, entry, _CRST_ENTRIES);
}
int crst_table_upgrade(struct mm_struct *mm, unsigned long limit);
static inline unsigned long check_asce_limit(struct mm_struct *mm, unsigned long addr,
unsigned long len)
{
int rc;
if (addr + len > mm->context.asce_limit &&
addr + len <= TASK_SIZE) {
rc = crst_table_upgrade(mm, addr + len);
if (rc)
return (unsigned long) rc;
}
return addr;
}
static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address)
{
unsigned long *table = crst_table_alloc(mm);
if (!table)
return NULL;
crst_table_init(table, _REGION2_ENTRY_EMPTY);
pagetable_p4d_ctor(virt_to_ptdesc(table));
return (p4d_t *) table;
}
static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
{
if (mm_p4d_folded(mm))
return;
pagetable_dtor(virt_to_ptdesc(p4d));
crst_table_free(mm, (unsigned long *) p4d);
}
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
{
unsigned long *table = crst_table_alloc(mm);
if (!table)
return NULL;
crst_table_init(table, _REGION3_ENTRY_EMPTY);
pagetable_pud_ctor(virt_to_ptdesc(table));
return (pud_t *) table;
}
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
{
if (mm_pud_folded(mm))
return;
pagetable_dtor(virt_to_ptdesc(pud));
crst_table_free(mm, (unsigned long *) pud);
}
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
{
unsigned long *table = crst_table_alloc(mm);
if (!table)
return NULL;
crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
if (!pagetable_pmd_ctor(virt_to_ptdesc(table))) {
crst_table_free(mm, table);
return NULL;
}
return (pmd_t *) table;
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
{
if (mm_pmd_folded(mm))
return;
pagetable_dtor(virt_to_ptdesc(pmd));
crst_table_free(mm, (unsigned long *) pmd);
}
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
{
set_pgd(pgd, __pgd(_REGION1_ENTRY | __pa(p4d)));
}
static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud)
{
set_p4d(p4d, __p4d(_REGION2_ENTRY | __pa(pud)));
}
static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
{
set_pud(pud, __pud(_REGION3_ENTRY | __pa(pmd)));
}
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
return (pgd_t *) crst_table_alloc(mm);
}
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
crst_table_free(mm, (unsigned long *) pgd);
}
static inline void pmd_populate(struct mm_struct *mm,
pmd_t *pmd, pgtable_t pte)
{
set_pmd(pmd, __pmd(_SEGMENT_ENTRY | __pa(pte)));
}
#define pmd_populate_kernel(mm, pmd, pte) pmd_populate(mm, pmd, pte)
/*
* page table entry allocation/free routines.
*/
#define pte_alloc_one_kernel(mm) ((pte_t *)page_table_alloc(mm))
#define pte_alloc_one(mm) ((pte_t *)page_table_alloc(mm))
#define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
#define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)
/* arch use pte_free_defer() implementation in arch/s390/mm/pgalloc.c */
#define pte_free_defer pte_free_defer
void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable);
void vmem_map_init(void);
void *vmem_crst_alloc(unsigned long val);
pte_t *vmem_pte_alloc(void);
unsigned long base_asce_alloc(unsigned long addr, unsigned long num_pages);
void base_asce_free(unsigned long asce);
#endif /* _S390_PGALLOC_H */