mirror of
https://github.com/torvalds/linux.git
synced 2026-05-28 09:04:39 +02:00
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>
90 lines
2.3 KiB
C
90 lines
2.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_X86_PAGE_H
|
|
#define _ASM_X86_PAGE_H
|
|
|
|
#include <linux/types.h>
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#include <asm/page_types.h>
|
|
|
|
#ifdef CONFIG_X86_64
|
|
#include <asm/page_64.h>
|
|
#else
|
|
#include <asm/page_32.h>
|
|
#endif /* CONFIG_X86_64 */
|
|
|
|
#ifndef __ASSEMBLER__
|
|
|
|
struct page;
|
|
|
|
#include <linux/range.h>
|
|
extern struct range pfn_mapped[];
|
|
extern int nr_pfn_mapped;
|
|
|
|
static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
|
|
struct page *topage)
|
|
{
|
|
copy_page(to, from);
|
|
}
|
|
|
|
#define vma_alloc_zeroed_movable_folio(vma, vaddr) \
|
|
vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr)
|
|
|
|
#ifndef __pa
|
|
#define __pa(x) __phys_addr((unsigned long)(x))
|
|
#endif
|
|
|
|
#define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x))
|
|
/* __pa_symbol should be used for C visible symbols.
|
|
This seems to be the official gcc blessed way to do such arithmetic. */
|
|
/*
|
|
* We need __phys_reloc_hide() here because gcc may assume that there is no
|
|
* overflow during __pa() calculation and can optimize it unexpectedly.
|
|
* Newer versions of gcc provide -fno-strict-overflow switch to handle this
|
|
* case properly. Once all supported versions of gcc understand it, we can
|
|
* remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated)
|
|
*/
|
|
#define __pa_symbol(x) \
|
|
__phys_addr_symbol(__phys_reloc_hide((unsigned long)(x)))
|
|
|
|
#ifndef __va
|
|
#define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET))
|
|
#endif
|
|
|
|
#define __boot_va(x) __va(x)
|
|
#define __boot_pa(x) __pa(x)
|
|
|
|
/*
|
|
* virt_to_page(kaddr) returns a valid pointer if and only if
|
|
* virt_addr_valid(kaddr) returns true.
|
|
*/
|
|
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
|
|
extern bool __virt_addr_valid(unsigned long kaddr);
|
|
#define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr))
|
|
|
|
static __always_inline void *pfn_to_kaddr(unsigned long pfn)
|
|
{
|
|
return __va(pfn << PAGE_SHIFT);
|
|
}
|
|
|
|
static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits)
|
|
{
|
|
return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
|
|
}
|
|
|
|
static __always_inline u64 __is_canonical_address(u64 vaddr, u8 vaddr_bits)
|
|
{
|
|
return __canonical_address(vaddr, vaddr_bits) == vaddr;
|
|
}
|
|
|
|
#endif /* __ASSEMBLER__ */
|
|
|
|
#include <asm-generic/memory_model.h>
|
|
#include <asm-generic/getorder.h>
|
|
|
|
#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif /* _ASM_X86_PAGE_H */
|