The patch titled
Subject: parisc: implement the new page table range API
has been added to the -mm mm-unstable branch. Its filename is
parisc-implement-the-new-page-table-range-api.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/parisc-implement-the-new-page-table-range-api.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
Subject: parisc: implement the new page table range API
Date: Wed, 2 Aug 2023 16:13:48 +0100
Add set_ptes(), update_mmu_cache_range(), flush_dcache_folio() and
flush_icache_pages(). Change the PG_arch_1 (aka PG_dcache_dirty) flag
from being per-page to per-folio.
Link: https://lkml.kernel.org/r/20230802151406.3735276-21-willy@xxxxxxxxxxxxx
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Acked-by: Mike Rapoport (IBM) <rppt@xxxxxxxxxx>
Cc: "James E.J. Bottomley" <James.Bottomley@xxxxxxxxxxxxxxxxxxxxx>
Cc: Helge Deller <deller@xxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/parisc/include/asm/cacheflush.h | 14 ++-
arch/parisc/include/asm/pgtable.h | 37 +++++---
arch/parisc/kernel/cache.c | 107 +++++++++++++++++--------
3 files changed, 105 insertions(+), 53 deletions(-)
--- a/arch/parisc/include/asm/cacheflush.h~parisc-implement-the-new-page-table-range-api
+++ a/arch/parisc/include/asm/cacheflush.h
@@ -43,8 +43,13 @@ void invalidate_kernel_vmap_range(void *
#define flush_cache_vmap(start, end) flush_cache_all()
#define flush_cache_vunmap(start, end) flush_cache_all()
+void flush_dcache_folio(struct folio *folio);
+#define flush_dcache_folio flush_dcache_folio
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-void flush_dcache_page(struct page *page);
+static inline void flush_dcache_page(struct page *page)
+{
+ flush_dcache_folio(page_folio(page));
+}
#define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages)
#define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages)
@@ -53,10 +58,9 @@ void flush_dcache_page(struct page *page
#define flush_dcache_mmap_unlock_irqrestore(mapping, flags) \
xa_unlock_irqrestore(&mapping->i_pages, flags)
-#define flush_icache_page(vma,page) do { \
- flush_kernel_dcache_page_addr(page_address(page)); \
- flush_kernel_icache_page(page_address(page)); \
-} while (0)
+void flush_icache_pages(struct vm_area_struct *vma, struct page *page,
+ unsigned int nr);
+#define flush_icache_page(vma, page) flush_icache_pages(vma, page, 1)
#define flush_icache_range(s,e) do { \
flush_kernel_dcache_range_asm(s,e); \
--- a/arch/parisc/include/asm/pgtable.h~parisc-implement-the-new-page-table-range-api
+++ a/arch/parisc/include/asm/pgtable.h
@@ -73,15 +73,6 @@ extern void __update_cache(pte_t pte);
mb(); \
} while(0)
-#define set_pte_at(mm, addr, pteptr, pteval) \
- do { \
- if (pte_present(pteval) && \
- pte_user(pteval)) \
- __update_cache(pteval); \
- *(pteptr) = (pteval); \
- purge_tlb_entries(mm, addr); \
- } while (0)
-
#endif /* !__ASSEMBLY__ */
#define pte_ERROR(e) \
@@ -285,7 +276,7 @@ extern unsigned long *empty_zero_page;
#define pte_none(x) (pte_val(x) == 0)
#define pte_present(x) (pte_val(x) & _PAGE_PRESENT)
#define pte_user(x) (pte_val(x) & _PAGE_USER)
-#define pte_clear(mm, addr, xp) set_pte_at(mm, addr, xp, __pte(0))
+#define pte_clear(mm, addr, xp) set_pte(xp, __pte(0))
#define pmd_flag(x) (pmd_val(x) & PxD_FLAG_MASK)
#define pmd_address(x) ((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
@@ -391,11 +382,29 @@ static inline unsigned long pmd_page_vad
extern void paging_init (void);
+static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned int nr)
+{
+ if (pte_present(pte) && pte_user(pte))
+ __update_cache(pte);
+ for (;;) {
+ *ptep = pte;
+ purge_tlb_entries(mm, addr);
+ if (--nr == 0)
+ break;
+ ptep++;
+ pte_val(pte) += 1 << PFN_PTE_SHIFT;
+ addr += PAGE_SIZE;
+ }
+}
+#define set_ptes set_ptes
+
/* Used for deferring calls to flush_dcache_page() */
#define PG_dcache_dirty PG_arch_1
-#define update_mmu_cache(vms,addr,ptep) __update_cache(*ptep)
+#define update_mmu_cache_range(vmf, vma, addr, ptep, nr) __update_cache(*ptep)
+#define update_mmu_cache(vma, addr, ptep) __update_cache(*ptep)
/*
* Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
@@ -450,7 +459,7 @@ static inline int ptep_test_and_clear_yo
if (!pte_young(pte)) {
return 0;
}
- set_pte_at(vma->vm_mm, addr, ptep, pte_mkold(pte));
+ set_pte(ptep, pte_mkold(pte));
return 1;
}
@@ -460,14 +469,14 @@ static inline pte_t ptep_get_and_clear(s
pte_t old_pte;
old_pte = *ptep;
- set_pte_at(mm, addr, ptep, __pte(0));
+ set_pte(ptep, __pte(0));
return old_pte;
}
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
- set_pte_at(mm, addr, ptep, pte_wrprotect(*ptep));
+ set_pte(ptep, pte_wrprotect(*ptep));
}
#define pte_same(A,B) (pte_val(A) == pte_val(B))
--- a/arch/parisc/kernel/cache.c~parisc-implement-the-new-page-table-range-api
+++ a/arch/parisc/kernel/cache.c
@@ -94,11 +94,11 @@ static inline void flush_data_cache(void
/* Kernel virtual address of pfn. */
#define pfn_va(pfn) __va(PFN_PHYS(pfn))
-void
-__update_cache(pte_t pte)
+void __update_cache(pte_t pte)
{
unsigned long pfn = pte_pfn(pte);
- struct page *page;
+ struct folio *folio;
+ unsigned int nr;
/* We don't have pte special. As a result, we can be called with
an invalid pfn and we don't need to flush the kernel dcache page.
@@ -106,13 +106,17 @@ __update_cache(pte_t pte)
if (!pfn_valid(pfn))
return;
- page = pfn_to_page(pfn);
- if (page_mapping_file(page) &&
- test_bit(PG_dcache_dirty, &page->flags)) {
- flush_kernel_dcache_page_addr(pfn_va(pfn));
- clear_bit(PG_dcache_dirty, &page->flags);
+ folio = page_folio(pfn_to_page(pfn));
+ pfn = folio_pfn(folio);
+ nr = folio_nr_pages(folio);
+ if (folio_flush_mapping(folio) &&
+ test_bit(PG_dcache_dirty, &folio->flags)) {
+ while (nr--)
+ flush_kernel_dcache_page_addr(pfn_va(pfn + nr));
+ clear_bit(PG_dcache_dirty, &folio->flags);
} else if (parisc_requires_coherency())
- flush_kernel_dcache_page_addr(pfn_va(pfn));
+ while (nr--)
+ flush_kernel_dcache_page_addr(pfn_va(pfn + nr));
}
void
@@ -366,6 +370,20 @@ static void flush_user_cache_page(struct
preempt_enable();
}
+void flush_icache_pages(struct vm_area_struct *vma, struct page *page,
+ unsigned int nr)
+{
+ void *kaddr = page_address(page);
+
+ for (;;) {
+ flush_kernel_dcache_page_addr(kaddr);
+ flush_kernel_icache_page(kaddr);
+ if (--nr == 0)
+ break;
+ kaddr += PAGE_SIZE;
+ }
+}
+
static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr)
{
pte_t *ptep = NULL;
@@ -394,27 +412,30 @@ static inline bool pte_needs_flush(pte_t
== (_PAGE_PRESENT | _PAGE_ACCESSED);
}
-void flush_dcache_page(struct page *page)
+void flush_dcache_folio(struct folio *folio)
{
- struct address_space *mapping = page_mapping_file(page);
- struct vm_area_struct *mpnt;
- unsigned long offset;
+ struct address_space *mapping = folio_flush_mapping(folio);
+ struct vm_area_struct *vma;
unsigned long addr, old_addr = 0;
+ void *kaddr;
unsigned long count = 0;
- unsigned long flags;
+ unsigned long i, nr, flags;
pgoff_t pgoff;
if (mapping && !mapping_mapped(mapping)) {
- set_bit(PG_dcache_dirty, &page->flags);
+ set_bit(PG_dcache_dirty, &folio->flags);
return;
}
- flush_kernel_dcache_page_addr(page_address(page));
+ nr = folio_nr_pages(folio);
+ kaddr = folio_address(folio);
+ for (i = 0; i < nr; i++)
+ flush_kernel_dcache_page_addr(kaddr + i * PAGE_SIZE);
if (!mapping)
return;
- pgoff = page->index;
+ pgoff = folio->index;
/*
* We have carefully arranged in arch_get_unmapped_area() that
@@ -424,20 +445,33 @@ void flush_dcache_page(struct page *page
* on machines that support equivalent aliasing
*/
flush_dcache_mmap_lock_irqsave(mapping, flags);
- vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
- offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
- addr = mpnt->vm_start + offset;
- if (parisc_requires_coherency()) {
- bool needs_flush = false;
- pte_t *ptep;
+ vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff + nr - 1) {
+ unsigned long offset = pgoff - vma->vm_pgoff;
+ unsigned long pfn = folio_pfn(folio);
+
+ addr = vma->vm_start;
+ nr = folio_nr_pages(folio);
+ if (offset > -nr) {
+ pfn -= offset;
+ nr += offset;
+ } else {
+ addr += offset * PAGE_SIZE;
+ }
+ if (addr + nr * PAGE_SIZE > vma->vm_end)
+ nr = (vma->vm_end - addr) / PAGE_SIZE;
- ptep = get_ptep(mpnt->vm_mm, addr);
- if (ptep) {
- needs_flush = pte_needs_flush(*ptep);
+ if (parisc_requires_coherency()) {
+ for (i = 0; i < nr; i++) {
+ pte_t *ptep = get_ptep(vma->vm_mm,
+ addr + i * PAGE_SIZE);
+ if (!ptep)
+ continue;
+ if (pte_needs_flush(*ptep))
+ flush_user_cache_page(vma,
+ addr + i * PAGE_SIZE);
+ /* Optimise accesses to the same table? */
pte_unmap(ptep);
}
- if (needs_flush)
- flush_user_cache_page(mpnt, addr);
} else {
/*
* The TLB is the engine of coherence on parisc:
@@ -450,27 +484,32 @@ void flush_dcache_page(struct page *page
* in (until the user or kernel specifically
* accesses it, of course)
*/
- flush_tlb_page(mpnt, addr);
+ for (i = 0; i < nr; i++)
+ flush_tlb_page(vma, addr + i * PAGE_SIZE);
if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1))
!= (addr & (SHM_COLOUR - 1))) {
- __flush_cache_page(mpnt, addr, page_to_phys(page));
+ for (i = 0; i < nr; i++)
+ __flush_cache_page(vma,
+ addr + i * PAGE_SIZE,
+ (pfn + i) * PAGE_SIZE);
/*
* Software is allowed to have any number
* of private mappings to a page.
*/
- if (!(mpnt->vm_flags & VM_SHARED))
+ if (!(vma->vm_flags & VM_SHARED))
continue;
if (old_addr)
pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n",
- old_addr, addr, mpnt->vm_file);
- old_addr = addr;
+ old_addr, addr, vma->vm_file);
+ if (nr == folio_nr_pages(folio))
+ old_addr = addr;
}
}
WARN_ON(++count == 4096);
}
flush_dcache_mmap_unlock_irqrestore(mapping, flags);
}
-EXPORT_SYMBOL(flush_dcache_page);
+EXPORT_SYMBOL(flush_dcache_folio);
/* Defined in arch/parisc/kernel/pacache.S */
EXPORT_SYMBOL(flush_kernel_dcache_range_asm);
_
Patches currently in -mm which might be from willy@xxxxxxxxxxxxx are
mm-drop-per-vma-lock-when-returning-vm_fault_retry-or-vm_fault_completed-fix.patch
rmap-pass-the-folio-to-__page_check_anon_rmap.patch
highmem-add-memcpy_to_folio-and-memcpy_from_folio.patch
affs-convert-affs_symlink_read_folio-to-use-the-folio.patch
affs-convert-data-read-and-write-to-use-folios.patch
migrate-use-folio_set_bh-instead-of-set_bh_page.patch
ntfs3-convert-ntfs_get_block_vbo-to-use-a-folio.patch
jbd2-use-a-folio-in-jbd2_journal_write_metadata_buffer.patch
buffer-remove-set_bh_page.patch
zswap-make-zswap_store-take-a-folio.patch
memcg-convert-get_obj_cgroup_from_page-to-get_obj_cgroup_from_folio.patch
swap-remove-some-calls-to-compound_head-in-swap_readpage.patch
zswap-make-zswap_load-take-a-folio.patch
mm-remove-config_per_vma_lock-ifdefs.patch
mm-allow-per-vma-locks-on-file-backed-vmas.patch
mm-move-fault_flag_vma_lock-check-from-handle_mm_fault.patch
mm-handle-pud-faults-under-the-vma-lock.patch
mm-handle-some-pmd-faults-under-the-vma-lock.patch
mm-move-fault_flag_vma_lock-check-down-in-handle_pte_fault.patch
mm-move-fault_flag_vma_lock-check-down-from-do_fault.patch
mm-run-the-fault-around-code-under-the-vma-lock.patch
mm-handle-swap-and-numa-pte-faults-under-the-vma-lock.patch
mm-handle-faults-that-merely-update-the-accessed-bit-under-the-vma-lock.patch
mm-handle-faults-that-merely-update-the-accessed-bit-under-the-vma-lock-fix.patch
mm-improve-the-comment-in-isolate_migratepages_block.patch
minmax-add-in_range-macro.patch
mm-convert-page_table_check_pte_set-to-page_table_check_ptes_set.patch
mm-add-generic-flush_icache_pages-and-documentation.patch
mm-add-folio_flush_mapping.patch
mm-remove-arch_implements_flush_dcache_folio.patch
mm-add-default-definition-of-set_ptes.patch
alpha-implement-the-new-page-table-range-api.patch
arc-implement-the-new-page-table-range-api.patch
arm-implement-the-new-page-table-range-api.patch
arm64-implement-the-new-page-table-range-api.patch
csky-implement-the-new-page-table-range-api.patch
hexagon-implement-the-new-page-table-range-api.patch
ia64-implement-the-new-page-table-range-api.patch
loongarch-implement-the-new-page-table-range-api.patch
m68k-implement-the-new-page-table-range-api.patch
microblaze-implement-the-new-page-table-range-api.patch
mips-implement-the-new-page-table-range-api.patch
nios2-implement-the-new-page-table-range-api.patch
openrisc-implement-the-new-page-table-range-api.patch
parisc-implement-the-new-page-table-range-api.patch
powerpc-implement-the-new-page-table-range-api.patch
riscv-implement-the-new-page-table-range-api.patch
s390-implement-the-new-page-table-range-api.patch
sh-implement-the-new-page-table-range-api.patch
sparc32-implement-the-new-page-table-range-api.patch
sparc64-implement-the-new-page-table-range-api.patch
um-implement-the-new-page-table-range-api.patch
x86-implement-the-new-page-table-range-api.patch
xtensa-implement-the-new-page-table-range-api.patch
mm-remove-page_mapping_file.patch
mm-rationalise-flush_icache_pages-and-flush_icache_page.patch
mm-tidy-up-set_ptes-definition.patch
mm-use-flush_icache_pages-in-do_set_pmd.patch
mm-call-update_mmu_cache_range-in-more-page-fault-handling-paths.patch
