mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2026-08-09 06:14:34 +02:00
David HildenbrandandAndrew Morton
8e38607aa4
Patch series "mm: folio_zero_user: clear page ranges", v11.
This series adds clearing of contiguous page ranges for hugepages.
The series improves on the current discontiguous clearing approach in two
ways:
- clear pages in a contiguous fashion.
- use batched clearing via clear_pages() wherever exposed.
The first is useful because it allows us to make much better use of
hardware prefetchers.
The second, enables advertising the real extent to the processor. Where
specific instructions support it (ex. string instructions on x86; "mops"
on arm64 etc), a processor can optimize based on this because, instead of
seeing a sequence of 8-byte stores, or a sequence of 4KB pages, it sees a
larger unit being operated on.
For instance, AMD Zen uarchs (for extents larger than LLC-size) switch to
a mode where they start eliding cacheline allocation. This is helpful not
just because it results in higher bandwidth, but also because now the
cache is not evicting useful cachelines and replacing them with zeroes.
Demand faulting a 64GB region shows performance improvement:
$ perf bench mem mmap -p $pg-sz -f demand -s 64GB -l 5
baseline +series
(GBps +- %stdev) (GBps +- %stdev)
pg-sz=2MB 11.76 +- 1.10% 25.34 +- 1.18% [*] +115.47% preempt=*
pg-sz=1GB 24.85 +- 2.41% 39.22 +- 2.32% + 57.82% preempt=none|voluntary
pg-sz=1GB (similar) 52.73 +- 0.20% [#] +112.19% preempt=full|lazy
[*] This improvement is because switching to sequential clearing
allows the hardware prefetchers to do a much better job.
[#] For pg-sz=1GB a large part of the improvement is because of the
cacheline elision mentioned above. preempt=full|lazy improves upon
that because, not needing explicit invocations of cond_resched() to
ensure reasonable preemption latency, it can clear the full extent
as a single unit. In comparison the maximum extent used for
preempt=none|voluntary is PROCESS_PAGES_NON_PREEMPT_BATCH (32MB).
When provided the full extent the processor forgoes allocating
cachelines on this path almost entirely.
(The hope is that eventually, in the fullness of time, the lazy
preemption model will be able to do the same job that none or
voluntary models are used for, allowing us to do away with
cond_resched().)
Raghavendra also tested previous version of the series on AMD Genoa and
sees similar improvement [1] with preempt=lazy.
$ perf bench mem map -p $page-size -f populate -s 64GB -l 10
base patched change
pg-sz=2MB 12.731939 GB/sec 26.304263 GB/sec 106.6%
pg-sz=1GB 26.232423 GB/sec 61.174836 GB/sec 133.2%
This patch (of 8):
Let's drop all variants that effectively map to clear_page() and provide
it in a generic variant instead.
We'll use the macro clear_user_page to indicate whether an architecture
provides it's own variant.
Also, clear_user_page() is only called from the generic variant of
clear_user_highpage(), so define it only if the architecture does not
provide a clear_user_highpage(). And, for simplicity define it in
linux/highmem.h.
Note that for parisc, clear_page() and clear_user_page() map to
clear_page_asm(), so we can just get rid of the custom clear_user_page()
implementation. There is a clear_user_page_asm() function on parisc, that
seems to be unused. Not sure what's up with that.
Link: https://lkml.kernel.org/r/20260107072009.1615991-1-ankur.a.arora@oracle.com
Link: https://lkml.kernel.org/r/20260107072009.1615991-2-ankur.a.arora@oracle.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Co-developed-by: Ankur Arora <ankur.a.arora@oracle.com>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ankur Arora <ankur.a.arora@oracle.com>
Cc: "Borislav Petkov (AMD)" <bp@alien8.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Konrad Rzessutek Wilk <konrad.wilk@oracle.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Li Zhe <lizhe.67@bytedance.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Raghavendra K T <raghavendra.kt@amd.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
162 lines
4.6 KiB
C
162 lines
4.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _SPARC64_PAGE_H
|
|
#define _SPARC64_PAGE_H
|
|
|
|
#include <linux/const.h>
|
|
|
|
#include <vdso/page.h>
|
|
|
|
/* Flushing for D-cache alias handling is only needed if
|
|
* the page size is smaller than 16K.
|
|
*/
|
|
#if PAGE_SHIFT < 14
|
|
#define DCACHE_ALIASING_POSSIBLE
|
|
#endif
|
|
|
|
#define HPAGE_SHIFT 23
|
|
#define REAL_HPAGE_SHIFT 22
|
|
#define HPAGE_16GB_SHIFT 34
|
|
#define HPAGE_2GB_SHIFT 31
|
|
#define HPAGE_256MB_SHIFT 28
|
|
#define HPAGE_64K_SHIFT 16
|
|
#define REAL_HPAGE_SIZE (_AC(1,UL) << REAL_HPAGE_SHIFT)
|
|
|
|
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
|
|
#define HPAGE_SIZE (_AC(1,UL) << HPAGE_SHIFT)
|
|
#define HPAGE_MASK (~(HPAGE_SIZE - 1UL))
|
|
#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
|
|
#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
|
|
#define REAL_HPAGE_PER_HPAGE (_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
|
|
#define HUGE_MAX_HSTATE 5
|
|
#endif
|
|
|
|
#ifndef __ASSEMBLER__
|
|
|
|
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
|
|
struct pt_regs;
|
|
void hugetlb_setup(struct pt_regs *regs);
|
|
#endif
|
|
|
|
#define WANT_PAGE_VIRTUAL
|
|
|
|
void _clear_page(void *page);
|
|
#define clear_page(X) _clear_page((void *)(X))
|
|
struct page;
|
|
void clear_user_page(void *addr, unsigned long vaddr, struct page *page);
|
|
#define clear_user_page clear_user_page
|
|
#define copy_page(X,Y) memcpy((void *)(X), (void *)(Y), PAGE_SIZE)
|
|
void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage);
|
|
#define __HAVE_ARCH_COPY_USER_HIGHPAGE
|
|
struct vm_area_struct;
|
|
void copy_user_highpage(struct page *to, struct page *from,
|
|
unsigned long vaddr, struct vm_area_struct *vma);
|
|
#define __HAVE_ARCH_COPY_HIGHPAGE
|
|
void copy_highpage(struct page *to, struct page *from);
|
|
|
|
/* Unlike sparc32, sparc64's parameter passing API is more
|
|
* sane in that structures which as small enough are passed
|
|
* in registers instead of on the stack. Thus, setting
|
|
* STRICT_MM_TYPECHECKS does not generate worse code so
|
|
* let's enable it to get the type checking.
|
|
*/
|
|
|
|
#define STRICT_MM_TYPECHECKS
|
|
|
|
#ifdef STRICT_MM_TYPECHECKS
|
|
/* These are used to make use of C type-checking.. */
|
|
typedef struct { unsigned long pte; } pte_t;
|
|
typedef struct { unsigned long iopte; } iopte_t;
|
|
typedef struct { unsigned long pmd; } pmd_t;
|
|
typedef struct { unsigned long pud; } pud_t;
|
|
typedef struct { unsigned long pgd; } pgd_t;
|
|
typedef struct { unsigned long pgprot; } pgprot_t;
|
|
|
|
#define pte_val(x) ((x).pte)
|
|
#define iopte_val(x) ((x).iopte)
|
|
#define pmd_val(x) ((x).pmd)
|
|
#define pud_val(x) ((x).pud)
|
|
#define pgd_val(x) ((x).pgd)
|
|
#define pgprot_val(x) ((x).pgprot)
|
|
|
|
#define __pte(x) ((pte_t) { (x) } )
|
|
#define __iopte(x) ((iopte_t) { (x) } )
|
|
#define __pmd(x) ((pmd_t) { (x) } )
|
|
#define __pud(x) ((pud_t) { (x) } )
|
|
#define __pgd(x) ((pgd_t) { (x) } )
|
|
#define __pgprot(x) ((pgprot_t) { (x) } )
|
|
|
|
#else
|
|
/* .. while these make it easier on the compiler */
|
|
typedef unsigned long pte_t;
|
|
typedef unsigned long iopte_t;
|
|
typedef unsigned long pmd_t;
|
|
typedef unsigned long pud_t;
|
|
typedef unsigned long pgd_t;
|
|
typedef unsigned long pgprot_t;
|
|
|
|
#define pte_val(x) (x)
|
|
#define iopte_val(x) (x)
|
|
#define pmd_val(x) (x)
|
|
#define pud_val(x) (x)
|
|
#define pgd_val(x) (x)
|
|
#define pgprot_val(x) (x)
|
|
|
|
#define __pte(x) (x)
|
|
#define __iopte(x) (x)
|
|
#define __pmd(x) (x)
|
|
#define __pud(x) (x)
|
|
#define __pgd(x) (x)
|
|
#define __pgprot(x) (x)
|
|
|
|
#endif /* (STRICT_MM_TYPECHECKS) */
|
|
|
|
typedef pte_t *pgtable_t;
|
|
|
|
extern unsigned long sparc64_va_hole_top;
|
|
extern unsigned long sparc64_va_hole_bottom;
|
|
|
|
/* The next two defines specify the actual exclusion region we
|
|
* enforce, wherein we use a 4GB red zone on each side of the VA hole.
|
|
*/
|
|
#define VA_EXCLUDE_START (sparc64_va_hole_bottom - (1UL << 32UL))
|
|
#define VA_EXCLUDE_END (sparc64_va_hole_top + (1UL << 32UL))
|
|
|
|
#define TASK_UNMAPPED_BASE (test_thread_flag(TIF_32BIT) ? \
|
|
_AC(0x0000000070000000,UL) : \
|
|
VA_EXCLUDE_END)
|
|
|
|
#include <asm-generic/memory_model.h>
|
|
|
|
extern unsigned long PAGE_OFFSET;
|
|
|
|
#endif /* !(__ASSEMBLER__) */
|
|
|
|
/* The maximum number of physical memory address bits we support. The
|
|
* largest value we can support is whatever "KPGD_SHIFT + KPTE_BITS"
|
|
* evaluates to.
|
|
*/
|
|
#define MAX_PHYS_ADDRESS_BITS 53
|
|
|
|
#define ILOG2_4MB 22
|
|
#define ILOG2_256MB 28
|
|
|
|
#ifndef __ASSEMBLER__
|
|
|
|
#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET)
|
|
#define __va(x) ((void *)((unsigned long) (x) + PAGE_OFFSET))
|
|
|
|
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
|
|
|
|
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr)>>PAGE_SHIFT)
|
|
|
|
#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
|
|
|
|
#define virt_to_phys __pa
|
|
#define phys_to_virt __va
|
|
|
|
#endif /* !(__ASSEMBLER__) */
|
|
|
|
#include <asm-generic/getorder.h>
|
|
|
|
#endif /* _SPARC64_PAGE_H */
|