mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-03-22 07:27:12 +08:00
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>
115 lines
3.0 KiB
C
115 lines
3.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (C) 2020-2022 Loongson Technology Corporation Limited
|
|
*/
|
|
#ifndef _ASM_PAGE_H
|
|
#define _ASM_PAGE_H
|
|
|
|
#include <linux/const.h>
|
|
#include <asm/addrspace.h>
|
|
|
|
#include <vdso/page.h>
|
|
|
|
#define HPAGE_SHIFT (PAGE_SHIFT + PAGE_SHIFT - PTRLOG)
|
|
#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT)
|
|
#define HPAGE_MASK (~(HPAGE_SIZE - 1))
|
|
#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
|
|
|
|
#ifndef __ASSEMBLER__
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/pfn.h>
|
|
|
|
/*
|
|
* It's normally defined only for FLATMEM config but it's
|
|
* used in our early mem init code for all memory models.
|
|
* So always define it.
|
|
*/
|
|
#define ARCH_PFN_OFFSET PFN_UP(PHYS_OFFSET)
|
|
|
|
extern void clear_page(void *page);
|
|
extern void copy_page(void *to, void *from);
|
|
|
|
#define copy_user_page(to, from, vaddr, pg) copy_page(to, from)
|
|
|
|
extern unsigned long shm_align_mask;
|
|
|
|
struct page;
|
|
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_USER_HIGHPAGE
|
|
|
|
typedef struct { unsigned long pte; } pte_t;
|
|
#define pte_val(x) ((x).pte)
|
|
#define __pte(x) ((pte_t) { (x) })
|
|
typedef struct page *pgtable_t;
|
|
|
|
typedef struct { unsigned long pgd; } pgd_t;
|
|
#define pgd_val(x) ((x).pgd)
|
|
#define __pgd(x) ((pgd_t) { (x) })
|
|
|
|
/*
|
|
* Manipulate page protection bits
|
|
*/
|
|
typedef struct { unsigned long pgprot; } pgprot_t;
|
|
#define pgprot_val(x) ((x).pgprot)
|
|
#define __pgprot(x) ((pgprot_t) { (x) })
|
|
#define pte_pgprot(x) __pgprot(pte_val(x) & ~_PFN_MASK)
|
|
|
|
#define ptep_buddy(x) ((pte_t *)((unsigned long)(x) ^ sizeof(pte_t)))
|
|
|
|
/*
|
|
* __pa()/__va() should be used only during mem init.
|
|
*/
|
|
#define __pa(x) PHYSADDR(x)
|
|
#define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET - PHYS_OFFSET))
|
|
|
|
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
|
|
#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x))
|
|
|
|
struct page *dmw_virt_to_page(unsigned long kaddr);
|
|
struct page *tlb_virt_to_page(unsigned long kaddr);
|
|
|
|
#define pfn_to_phys(pfn) __pfn_to_phys(pfn)
|
|
#define phys_to_pfn(paddr) __phys_to_pfn(paddr)
|
|
|
|
#ifndef CONFIG_KFENCE
|
|
|
|
#define page_to_virt(page) __va(page_to_phys(page))
|
|
#define virt_to_page(kaddr) phys_to_page(__pa(kaddr))
|
|
|
|
#else
|
|
|
|
#define WANT_PAGE_VIRTUAL
|
|
|
|
#define page_to_virt(page) \
|
|
({ \
|
|
extern char *__kfence_pool; \
|
|
(__kfence_pool == NULL) ? __va(page_to_phys(page)) : page_address(page); \
|
|
})
|
|
|
|
#define virt_to_page(kaddr) \
|
|
({ \
|
|
(likely((unsigned long)kaddr < vm_map_base)) ? \
|
|
dmw_virt_to_page((unsigned long)kaddr) : tlb_virt_to_page((unsigned long)kaddr);\
|
|
})
|
|
|
|
#endif
|
|
|
|
#define pfn_to_virt(pfn) page_to_virt(pfn_to_page(pfn))
|
|
#define virt_to_pfn(kaddr) page_to_pfn(virt_to_page(kaddr))
|
|
|
|
extern int __virt_addr_valid(volatile void *kaddr);
|
|
#define virt_addr_valid(kaddr) __virt_addr_valid((volatile void *)(kaddr))
|
|
|
|
#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC
|
|
|
|
#include <asm-generic/memory_model.h>
|
|
#include <asm-generic/getorder.h>
|
|
|
|
#endif /* !__ASSEMBLER__ */
|
|
|
|
#endif /* _ASM_PAGE_H */
|