f9bff0e318
Patch series "New page table range API", v6.
This patchset changes the API used by the MM to set up page table entries.
The four APIs are:
set_ptes(mm, addr, ptep, pte, nr)
update_mmu_cache_range(vma, addr, ptep, nr)
flush_dcache_folio(folio)
flush_icache_pages(vma, page, nr)
flush_dcache_folio() isn't technically new, but no architecture
implemented it, so I've done that for them. The old APIs remain around
but are mostly implemented by calling the new interfaces.
The new APIs are based around setting up N page table entries at once.
The N entries belong to the same PMD, the same folio and the same VMA, so
ptep++ is a legitimate operation, and locking is taken care of for you.
Some architectures can do a better job of it than just a loop, but I have
hesitated to make too deep a change to architectures I don't understand
well.
One thing I have changed in every architecture is that PG_arch_1 is now a
per-folio bit instead of a per-page bit when used for dcache clean/dirty
tracking. This was something that would have to happen eventually, and it
makes sense to do it now rather than iterate over every page involved in a
cache flush and figure out if it needs to happen.
The point of all this is better performance, and Fengwei Yin has measured
improvement on x86. I suspect you'll see improvement on your architecture
too. Try the new will-it-scale test mentioned here:
https://lore.kernel.org/linux-mm/20230206140639.538867-5-fengwei.yin@intel.com/
You'll need to run it on an XFS filesystem and have
CONFIG_TRANSPARENT_HUGEPAGE set.
This patchset is the basis for much of the anonymous large folio work
being done by Ryan, so it's received quite a lot of testing over the last
few months.
This patch (of 38):
Determine if a value lies within a range more efficiently (subtraction +
comparison vs two comparisons and an AND). It also has useful (under some
circumstances) behaviour if the range exceeds the maximum value of the
type. Convert all the conflicting definitions of in_range() within the
kernel; some can use the generic definition while others need their own
definition.
Link: https://lkml.kernel.org/r/20230802151406.3735276-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20230802151406.3735276-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
112 lines
2.6 KiB
C
112 lines
2.6 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Copyright (c) 2014, The Linux Foundation. All rights reserved.
|
|
*/
|
|
#include <linux/mm.h>
|
|
#include <linux/module.h>
|
|
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/set_memory.h>
|
|
|
|
struct page_change_data {
|
|
pgprot_t set_mask;
|
|
pgprot_t clear_mask;
|
|
};
|
|
|
|
static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
|
|
{
|
|
struct page_change_data *cdata = data;
|
|
pte_t pte = *ptep;
|
|
|
|
pte = clear_pte_bit(pte, cdata->clear_mask);
|
|
pte = set_pte_bit(pte, cdata->set_mask);
|
|
|
|
set_pte_ext(ptep, pte, 0);
|
|
return 0;
|
|
}
|
|
|
|
static bool range_in_range(unsigned long start, unsigned long size,
|
|
unsigned long range_start, unsigned long range_end)
|
|
{
|
|
return start >= range_start && start < range_end &&
|
|
size <= range_end - start;
|
|
}
|
|
|
|
/*
|
|
* This function assumes that the range is mapped with PAGE_SIZE pages.
|
|
*/
|
|
static int __change_memory_common(unsigned long start, unsigned long size,
|
|
pgprot_t set_mask, pgprot_t clear_mask)
|
|
{
|
|
struct page_change_data data;
|
|
int ret;
|
|
|
|
data.set_mask = set_mask;
|
|
data.clear_mask = clear_mask;
|
|
|
|
ret = apply_to_page_range(&init_mm, start, size, change_page_range,
|
|
&data);
|
|
|
|
flush_tlb_kernel_range(start, start + size);
|
|
return ret;
|
|
}
|
|
|
|
static int change_memory_common(unsigned long addr, int numpages,
|
|
pgprot_t set_mask, pgprot_t clear_mask)
|
|
{
|
|
unsigned long start = addr & PAGE_MASK;
|
|
unsigned long end = PAGE_ALIGN(addr) + numpages * PAGE_SIZE;
|
|
unsigned long size = end - start;
|
|
|
|
WARN_ON_ONCE(start != addr);
|
|
|
|
if (!size)
|
|
return 0;
|
|
|
|
if (!range_in_range(start, size, MODULES_VADDR, MODULES_END) &&
|
|
!range_in_range(start, size, VMALLOC_START, VMALLOC_END))
|
|
return -EINVAL;
|
|
|
|
return __change_memory_common(start, size, set_mask, clear_mask);
|
|
}
|
|
|
|
int set_memory_ro(unsigned long addr, int numpages)
|
|
{
|
|
return change_memory_common(addr, numpages,
|
|
__pgprot(L_PTE_RDONLY),
|
|
__pgprot(0));
|
|
}
|
|
|
|
int set_memory_rw(unsigned long addr, int numpages)
|
|
{
|
|
return change_memory_common(addr, numpages,
|
|
__pgprot(0),
|
|
__pgprot(L_PTE_RDONLY));
|
|
}
|
|
|
|
int set_memory_nx(unsigned long addr, int numpages)
|
|
{
|
|
return change_memory_common(addr, numpages,
|
|
__pgprot(L_PTE_XN),
|
|
__pgprot(0));
|
|
}
|
|
|
|
int set_memory_x(unsigned long addr, int numpages)
|
|
{
|
|
return change_memory_common(addr, numpages,
|
|
__pgprot(0),
|
|
__pgprot(L_PTE_XN));
|
|
}
|
|
|
|
int set_memory_valid(unsigned long addr, int numpages, int enable)
|
|
{
|
|
if (enable)
|
|
return __change_memory_common(addr, PAGE_SIZE * numpages,
|
|
__pgprot(L_PTE_VALID),
|
|
__pgprot(0));
|
|
else
|
|
return __change_memory_common(addr, PAGE_SIZE * numpages,
|
|
__pgprot(0),
|
|
__pgprot(L_PTE_VALID));
|
|
}
|