kernel_optimize_test/include/linux/pagewalk.h
Steven Price e47690d756 x86: mm: avoid allocating struct mm_struct on the stack
struct mm_struct is quite large (~1664 bytes) and so allocating on the
stack may cause problems as the kernel stack size is small.

Since ptdump_walk_pgd_level_core() was only allocating the structure so
that it could modify the pgd argument we can instead introduce a pgd
override in struct mm_walk and pass this down the call stack to where it
is needed.

Since the correct mm_struct is now being passed down, it is now also
unnecessary to take the mmap_sem semaphore because ptdump_walk_pgd() will
now take the semaphore on the real mm.

[steven.price@arm.com: restore missed arm64 changes]
  Link: http://lkml.kernel.org/r/20200108145710.34314-1-steven.price@arm.com
Link: http://lkml.kernel.org/r/20200108145710.34314-1-steven.price@arm.com
Signed-off-by: Steven Price <steven.price@arm.com>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Burton <paul.burton@mips.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zong Li <zong.li@sifive.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 03:05:25 +00:00

109 lines
4.1 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PAGEWALK_H
#define _LINUX_PAGEWALK_H
#include <linux/mm.h>
struct mm_walk;
/**
* mm_walk_ops - callbacks for walk_page_range
* @pgd_entry: if set, called for each non-empty PGD (top-level) entry
* @p4d_entry: if set, called for each non-empty P4D entry
* @pud_entry: if set, called for each non-empty PUD entry
* @pmd_entry: if set, called for each non-empty PMD entry
* this handler is required to be able to handle
* pmd_trans_huge() pmds. They may simply choose to
* split_huge_page() instead of handling it explicitly.
* @pte_entry: if set, called for each non-empty PTE (lowest-level)
* entry
* @pte_hole: if set, called for each hole at all levels,
* depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD
* 4:PTE. Any folded depths (where PTRS_PER_P?D is equal
* to 1) are skipped.
* @hugetlb_entry: if set, called for each hugetlb entry
* @test_walk: caller specific callback function to determine whether
* we walk over the current vma or not. Returning 0 means
* "do page table walk over the current vma", returning
* a negative value means "abort current page table walk
* right now" and returning 1 means "skip the current vma"
* @pre_vma: if set, called before starting walk on a non-null vma.
* @post_vma: if set, called after a walk on a non-null vma, provided
* that @pre_vma and the vma walk succeeded.
*
* p?d_entry callbacks are called even if those levels are folded on a
* particular architecture/configuration.
*/
struct mm_walk_ops {
int (*pgd_entry)(pgd_t *pgd, unsigned long addr,
unsigned long next, struct mm_walk *walk);
int (*p4d_entry)(p4d_t *p4d, unsigned long addr,
unsigned long next, struct mm_walk *walk);
int (*pud_entry)(pud_t *pud, unsigned long addr,
unsigned long next, struct mm_walk *walk);
int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
unsigned long next, struct mm_walk *walk);
int (*pte_entry)(pte_t *pte, unsigned long addr,
unsigned long next, struct mm_walk *walk);
int (*pte_hole)(unsigned long addr, unsigned long next,
int depth, struct mm_walk *walk);
int (*hugetlb_entry)(pte_t *pte, unsigned long hmask,
unsigned long addr, unsigned long next,
struct mm_walk *walk);
int (*test_walk)(unsigned long addr, unsigned long next,
struct mm_walk *walk);
int (*pre_vma)(unsigned long start, unsigned long end,
struct mm_walk *walk);
void (*post_vma)(struct mm_walk *walk);
};
/*
* Action for pud_entry / pmd_entry callbacks.
* ACTION_SUBTREE is the default
*/
enum page_walk_action {
/* Descend to next level, splitting huge pages if needed and possible */
ACTION_SUBTREE = 0,
/* Continue to next entry at this level (ignoring any subtree) */
ACTION_CONTINUE = 1,
/* Call again for this entry */
ACTION_AGAIN = 2
};
/**
* mm_walk - walk_page_range data
* @ops: operation to call during the walk
* @mm: mm_struct representing the target process of page table walk
* @pgd: pointer to PGD; only valid with no_vma (otherwise set to NULL)
* @vma: vma currently walked (NULL if walking outside vmas)
* @action: next action to perform (see enum page_walk_action)
* @no_vma: walk ignoring vmas (vma will always be NULL)
* @private: private data for callbacks' usage
*
* (see the comment on walk_page_range() for more details)
*/
struct mm_walk {
const struct mm_walk_ops *ops;
struct mm_struct *mm;
pgd_t *pgd;
struct vm_area_struct *vma;
enum page_walk_action action;
bool no_vma;
void *private;
};
int walk_page_range(struct mm_struct *mm, unsigned long start,
unsigned long end, const struct mm_walk_ops *ops,
void *private);
int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
unsigned long end, const struct mm_walk_ops *ops,
pgd_t *pgd,
void *private);
int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
void *private);
int walk_page_mapping(struct address_space *mapping, pgoff_t first_index,
pgoff_t nr, const struct mm_walk_ops *ops,
void *private);
#endif /* _LINUX_PAGEWALK_H */