Add set_ptes(), update_mmu_cache_range() and flush_dcache_folio().
Change the PG_arch_1 (aka PG_dcache_dirty) flag from being per-page to
per-folio.
Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: Nicholas Piggin <[email protected]>
Cc: Christophe Leroy <[email protected]>
Cc: [email protected]
---
arch/powerpc/include/asm/book3s/pgtable.h | 10 +----
arch/powerpc/include/asm/cacheflush.h | 14 +++++--
arch/powerpc/include/asm/kvm_ppc.h | 10 ++---
arch/powerpc/include/asm/nohash/pgtable.h | 13 ++----
arch/powerpc/include/asm/pgtable.h | 6 +++
arch/powerpc/mm/book3s64/hash_utils.c | 11 ++---
arch/powerpc/mm/cacheflush.c | 40 ++++++------------
arch/powerpc/mm/nohash/e500_hugetlbpage.c | 3 +-
arch/powerpc/mm/pgtable.c | 51 +++++++++++++----------
9 files changed, 77 insertions(+), 81 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h
index d18b748ea3ae..c2ef811505b0 100644
--- a/arch/powerpc/include/asm/book3s/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/pgtable.h
@@ -9,13 +9,6 @@
#endif
#ifndef __ASSEMBLY__
-/* Insert a PTE, top-level function is out of line. It uses an inline
- * low level function in the respective pgtable-* files
- */
-extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
- pte_t pte);
-
-
#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep, pte_t entry, int dirty);
@@ -36,7 +29,8 @@ void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t
* corresponding HPTE into the hash table ahead of time, instead of
* waiting for the inevitable extra hash-table miss exception.
*/
-static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
+static inline void update_mmu_cache_range(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep, unsigned int nr)
{
if (IS_ENABLED(CONFIG_PPC32) && !mmu_has_feature(MMU_FTR_HPTE_TABLE))
return;
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index 7564dd4fd12b..ef7d2de33b89 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -35,13 +35,19 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
* It just marks the page as not i-cache clean. We do the i-cache
* flush later when the page is given to a user process, if necessary.
*/
-static inline void flush_dcache_page(struct page *page)
+static inline void flush_dcache_folio(struct folio *folio)
{
if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
return;
/* avoid an atomic op if possible */
- if (test_bit(PG_dcache_clean, &page->flags))
- clear_bit(PG_dcache_clean, &page->flags);
+ if (test_bit(PG_dcache_clean, &folio->flags))
+ clear_bit(PG_dcache_clean, &folio->flags);
+}
+#define flush_dcache_folio flush_dcache_folio
+
+static inline void flush_dcache_page(struct page *page)
+{
+ flush_dcache_folio(page_folio(page));
}
void flush_icache_range(unsigned long start, unsigned long stop);
@@ -51,7 +57,7 @@ void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
unsigned long addr, int len);
#define flush_icache_user_page flush_icache_user_page
-void flush_dcache_icache_page(struct page *page);
+void flush_dcache_icache_folio(struct folio *folio);
/**
* flush_dcache_range(): Write any modified data cache blocks out to memory and
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 6bef23d6d0e3..e91dd8e88bb7 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -868,7 +868,7 @@ void kvmppc_init_lpid(unsigned long nr_lpids);
static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn)
{
- struct page *page;
+ struct folio *folio;
/*
* We can only access pages that the kernel maps
* as memory. Bail out for unmapped ones.
@@ -877,10 +877,10 @@ static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn)
return;
/* Clear i-cache for new pages */
- page = pfn_to_page(pfn);
- if (!test_bit(PG_dcache_clean, &page->flags)) {
- flush_dcache_icache_page(page);
- set_bit(PG_dcache_clean, &page->flags);
+ folio = page_folio(pfn_to_page(pfn));
+ if (!test_bit(PG_dcache_clean, &folio->flags)) {
+ flush_dcache_icache_folio(folio);
+ set_bit(PG_dcache_clean, &folio->flags);
}
}
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index a6caaaab6f92..69a7dd47a9f0 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -166,12 +166,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE);
}
-/* Insert a PTE, top-level function is out of line. It uses an inline
- * low level function in the respective pgtable-* files
- */
-extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
- pte_t pte);
-
/* This low level function performs the actual PTE insertion
* Setting the PTE depends on the MMU type and other factors. It's
* an horrible mess that I'm not going to try to clean up now but
@@ -282,10 +276,11 @@ static inline int pud_huge(pud_t pud)
* for the page which has just been mapped in.
*/
#if defined(CONFIG_PPC_E500) && defined(CONFIG_HUGETLB_PAGE)
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep);
+void update_mmu_cache_range(struct vm_area_struct *vma, unsigned long address,
+ pte_t *ptep, unsigned int nr);
#else
-static inline
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) {}
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep, unsigned int nr) {}
#endif
#endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 9972626ddaf6..656ecf2b10cd 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -41,6 +41,12 @@ struct mm_struct;
#ifndef __ASSEMBLY__
+void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+ pte_t pte, unsigned int nr);
+#define set_ptes set_ptes
+#define update_mmu_cache(vma, addr, ptep) \
+ update_mmu_cache_range(vma, addr, ptep, 1)
+
#ifndef MAX_PTRS_PER_PGD
#define MAX_PTRS_PER_PGD PTRS_PER_PGD
#endif
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index fedffe3ae136..ad2afa08e62e 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1307,18 +1307,19 @@ void hash__early_init_mmu_secondary(void)
*/
unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
{
- struct page *page;
+ struct folio *folio;
if (!pfn_valid(pte_pfn(pte)))
return pp;
- page = pte_page(pte);
+ folio = page_folio(pte_page(pte));
/* page is dirty */
- if (!test_bit(PG_dcache_clean, &page->flags) && !PageReserved(page)) {
+ if (!test_bit(PG_dcache_clean, &folio->flags) &&
+ !folio_test_reserved(folio)) {
if (trap == INTERRUPT_INST_STORAGE) {
- flush_dcache_icache_page(page);
- set_bit(PG_dcache_clean, &page->flags);
+ flush_dcache_icache_folio(folio);
+ set_bit(PG_dcache_clean, &folio->flags);
} else
pp |= HPTE_R_N;
}
diff --git a/arch/powerpc/mm/cacheflush.c b/arch/powerpc/mm/cacheflush.c
index 0e9b4879c0f9..8760d2223abe 100644
--- a/arch/powerpc/mm/cacheflush.c
+++ b/arch/powerpc/mm/cacheflush.c
@@ -148,44 +148,30 @@ static void __flush_dcache_icache(void *p)
invalidate_icache_range(addr, addr + PAGE_SIZE);
}
-static void flush_dcache_icache_hugepage(struct page *page)
+void flush_dcache_icache_folio(struct folio *folio)
{
- int i;
- int nr = compound_nr(page);
+ unsigned int i, nr = folio_nr_pages(folio);
- if (!PageHighMem(page)) {
+ if (flush_coherent_icache())
+ return;
+
+ if (!folio_test_highmem(folio)) {
+ void *addr = folio_address(folio);
for (i = 0; i < nr; i++)
- __flush_dcache_icache(lowmem_page_address(page + i));
- } else {
+ __flush_dcache_icache(addr + i * PAGE_SIZE);
+ } else if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) {
for (i = 0; i < nr; i++) {
- void *start = kmap_local_page(page + i);
+ void *start = kmap_local_folio(folio, i * PAGE_SIZE);
__flush_dcache_icache(start);
kunmap_local(start);
}
- }
-}
-
-void flush_dcache_icache_page(struct page *page)
-{
- if (flush_coherent_icache())
- return;
-
- if (PageCompound(page))
- return flush_dcache_icache_hugepage(page);
-
- if (!PageHighMem(page)) {
- __flush_dcache_icache(lowmem_page_address(page));
- } else if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) {
- void *start = kmap_local_page(page);
-
- __flush_dcache_icache(start);
- kunmap_local(start);
} else {
- flush_dcache_icache_phys(page_to_phys(page));
+ unsigned long pfn = folio_pfn(folio);
+ for (i = 0; i < nr; i++)
+ flush_dcache_icache_phys((pfn + i) * PAGE_SIZE);
}
}
-EXPORT_SYMBOL(flush_dcache_icache_page);
void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
{
diff --git a/arch/powerpc/mm/nohash/e500_hugetlbpage.c b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
index 58c8d9849cb1..f3cb91107a47 100644
--- a/arch/powerpc/mm/nohash/e500_hugetlbpage.c
+++ b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
@@ -178,7 +178,8 @@ book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte)
*
* This must always be called with the pte lock held.
*/
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
+ pte_t *ptep, unsigned int nr)
{
if (is_vm_hugetlb_page(vma))
book3e_hugetlb_preload(vma, address, *ptep);
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index cb2dcdb18f8e..b3c7b874a7a2 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -58,7 +58,7 @@ static inline int pte_looks_normal(pte_t pte)
return 0;
}
-static struct page *maybe_pte_to_page(pte_t pte)
+static struct folio *maybe_pte_to_folio(pte_t pte)
{
unsigned long pfn = pte_pfn(pte);
struct page *page;
@@ -68,7 +68,7 @@ static struct page *maybe_pte_to_page(pte_t pte)
page = pfn_to_page(pfn);
if (PageReserved(page))
return NULL;
- return page;
+ return page_folio(page);
}
#ifdef CONFIG_PPC_BOOK3S
@@ -84,12 +84,12 @@ static pte_t set_pte_filter_hash(pte_t pte)
pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) ||
cpu_has_feature(CPU_FTR_NOEXECUTE))) {
- struct page *pg = maybe_pte_to_page(pte);
- if (!pg)
+ struct folio *folio = maybe_pte_to_folio(pte);
+ if (!folio)
return pte;
- if (!test_bit(PG_dcache_clean, &pg->flags)) {
- flush_dcache_icache_page(pg);
- set_bit(PG_dcache_clean, &pg->flags);
+ if (!test_bit(PG_dcache_clean, &folio->flags)) {
+ flush_dcache_icache_folio(folio);
+ set_bit(PG_dcache_clean, &folio->flags);
}
}
return pte;
@@ -107,7 +107,7 @@ static pte_t set_pte_filter_hash(pte_t pte) { return pte; }
*/
static inline pte_t set_pte_filter(pte_t pte)
{
- struct page *pg;
+ struct folio *folio;
if (radix_enabled())
return pte;
@@ -120,18 +120,18 @@ static inline pte_t set_pte_filter(pte_t pte)
return pte;
/* If you set _PAGE_EXEC on weird pages you're on your own */
- pg = maybe_pte_to_page(pte);
- if (unlikely(!pg))
+ folio = maybe_pte_to_folio(pte);
+ if (unlikely(!folio))
return pte;
/* If the page clean, we move on */
- if (test_bit(PG_dcache_clean, &pg->flags))
+ if (test_bit(PG_dcache_clean, &folio->flags))
return pte;
/* If it's an exec fault, we flush the cache and make it clean */
if (is_exec_fault()) {
- flush_dcache_icache_page(pg);
- set_bit(PG_dcache_clean, &pg->flags);
+ flush_dcache_icache_folio(folio);
+ set_bit(PG_dcache_clean, &folio->flags);
return pte;
}
@@ -142,7 +142,7 @@ static inline pte_t set_pte_filter(pte_t pte)
static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
int dirty)
{
- struct page *pg;
+ struct folio *folio;
if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
return pte;
@@ -168,17 +168,17 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
#endif /* CONFIG_DEBUG_VM */
/* If you set _PAGE_EXEC on weird pages you're on your own */
- pg = maybe_pte_to_page(pte);
- if (unlikely(!pg))
+ folio = maybe_pte_to_folio(pte);
+ if (unlikely(!folio))
goto bail;
/* If the page is already clean, we move on */
- if (test_bit(PG_dcache_clean, &pg->flags))
+ if (test_bit(PG_dcache_clean, &folio->flags))
goto bail;
/* Clean the page and set PG_dcache_clean */
- flush_dcache_icache_page(pg);
- set_bit(PG_dcache_clean, &pg->flags);
+ flush_dcache_icache_folio(folio);
+ set_bit(PG_dcache_clean, &folio->flags);
bail:
return pte_mkexec(pte);
@@ -187,8 +187,8 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
/*
* set_pte stores a linux PTE into the linux page table.
*/
-void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
- pte_t pte)
+void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+ pte_t pte, unsigned int nr)
{
/*
* Make sure hardware valid bit is not set. We don't do
@@ -203,7 +203,14 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
pte = set_pte_filter(pte);
/* Perform the setting of the PTE */
- __set_pte_at(mm, addr, ptep, pte, 0);
+ for (;;) {
+ __set_pte_at(mm, addr, ptep, pte, 0);
+ if (--nr == 0)
+ break;
+ ptep++;
+ pte = __pte(pte_val(pte) + PAGE_SIZE);
+ addr += PAGE_SIZE;
+ }
}
void unmap_kernel_page(unsigned long va)
--
2.39.2
Le 15/03/2023 à 06:14, Matthew Wilcox (Oracle) a écrit :
> Add set_ptes(), update_mmu_cache_range() and flush_dcache_folio().
> Change the PG_arch_1 (aka PG_dcache_dirty) flag from being per-page to
> per-folio.
>
> Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
> Cc: Michael Ellerman <[email protected]>
> Cc: Nicholas Piggin <[email protected]>
> Cc: Christophe Leroy <[email protected]>
> Cc: [email protected]
> ---
> arch/powerpc/include/asm/book3s/pgtable.h | 10 +----
> arch/powerpc/include/asm/cacheflush.h | 14 +++++--
> arch/powerpc/include/asm/kvm_ppc.h | 10 ++---
> arch/powerpc/include/asm/nohash/pgtable.h | 13 ++----
> arch/powerpc/include/asm/pgtable.h | 6 +++
> arch/powerpc/mm/book3s64/hash_utils.c | 11 ++---
> arch/powerpc/mm/cacheflush.c | 40 ++++++------------
> arch/powerpc/mm/nohash/e500_hugetlbpage.c | 3 +-
> arch/powerpc/mm/pgtable.c | 51 +++++++++++++----------
> 9 files changed, 77 insertions(+), 81 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h
> index d18b748ea3ae..c2ef811505b0 100644
> --- a/arch/powerpc/include/asm/book3s/pgtable.h
> +++ b/arch/powerpc/include/asm/book3s/pgtable.h
> @@ -9,13 +9,6 @@
> #endif
>
> #ifndef __ASSEMBLY__
> -/* Insert a PTE, top-level function is out of line. It uses an inline
> - * low level function in the respective pgtable-* files
> - */
> -extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> - pte_t pte);
> -
> -
> #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
> extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
> pte_t *ptep, pte_t entry, int dirty);
> @@ -36,7 +29,8 @@ void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t
> * corresponding HPTE into the hash table ahead of time, instead of
> * waiting for the inevitable extra hash-table miss exception.
> */
> -static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
> +static inline void update_mmu_cache_range(struct vm_area_struct *vma,
> + unsigned long address, pte_t *ptep, unsigned int nr)
> {
> if (IS_ENABLED(CONFIG_PPC32) && !mmu_has_feature(MMU_FTR_HPTE_TABLE))
> return;
> diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
> index 7564dd4fd12b..ef7d2de33b89 100644
> --- a/arch/powerpc/include/asm/cacheflush.h
> +++ b/arch/powerpc/include/asm/cacheflush.h
> @@ -35,13 +35,19 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
> * It just marks the page as not i-cache clean. We do the i-cache
> * flush later when the page is given to a user process, if necessary.
> */
> -static inline void flush_dcache_page(struct page *page)
> +static inline void flush_dcache_folio(struct folio *folio)
> {
> if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
> return;
> /* avoid an atomic op if possible */
> - if (test_bit(PG_dcache_clean, &page->flags))
> - clear_bit(PG_dcache_clean, &page->flags);
> + if (test_bit(PG_dcache_clean, &folio->flags))
> + clear_bit(PG_dcache_clean, &folio->flags);
> +}
> +#define flush_dcache_folio flush_dcache_folio
> +
> +static inline void flush_dcache_page(struct page *page)
> +{
> + flush_dcache_folio(page_folio(page));
> }
>
> void flush_icache_range(unsigned long start, unsigned long stop);
> @@ -51,7 +57,7 @@ void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
> unsigned long addr, int len);
> #define flush_icache_user_page flush_icache_user_page
>
> -void flush_dcache_icache_page(struct page *page);
> +void flush_dcache_icache_folio(struct folio *folio);
>
> /**
> * flush_dcache_range(): Write any modified data cache blocks out to memory and
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
> index 6bef23d6d0e3..e91dd8e88bb7 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -868,7 +868,7 @@ void kvmppc_init_lpid(unsigned long nr_lpids);
>
> static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn)
> {
> - struct page *page;
> + struct folio *folio;
> /*
> * We can only access pages that the kernel maps
> * as memory. Bail out for unmapped ones.
> @@ -877,10 +877,10 @@ static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn)
> return;
>
> /* Clear i-cache for new pages */
> - page = pfn_to_page(pfn);
> - if (!test_bit(PG_dcache_clean, &page->flags)) {
> - flush_dcache_icache_page(page);
> - set_bit(PG_dcache_clean, &page->flags);
> + folio = page_folio(pfn_to_page(pfn));
> + if (!test_bit(PG_dcache_clean, &folio->flags)) {
> + flush_dcache_icache_folio(folio);
> + set_bit(PG_dcache_clean, &folio->flags);
> }
> }
>
> diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
> index a6caaaab6f92..69a7dd47a9f0 100644
> --- a/arch/powerpc/include/asm/nohash/pgtable.h
> +++ b/arch/powerpc/include/asm/nohash/pgtable.h
> @@ -166,12 +166,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
> return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE);
> }
>
> -/* Insert a PTE, top-level function is out of line. It uses an inline
> - * low level function in the respective pgtable-* files
> - */
> -extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> - pte_t pte);
> -
> /* This low level function performs the actual PTE insertion
> * Setting the PTE depends on the MMU type and other factors. It's
> * an horrible mess that I'm not going to try to clean up now but
> @@ -282,10 +276,11 @@ static inline int pud_huge(pud_t pud)
> * for the page which has just been mapped in.
> */
> #if defined(CONFIG_PPC_E500) && defined(CONFIG_HUGETLB_PAGE)
> -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep);
> +void update_mmu_cache_range(struct vm_area_struct *vma, unsigned long address,
> + pte_t *ptep, unsigned int nr);
> #else
> -static inline
> -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) {}
> +static inline void update_mmu_cache(struct vm_area_struct *vma,
> + unsigned long address, pte_t *ptep, unsigned int nr) {}
Do you mean update_mmu_cache_range() ?
> #endif
>
> #endif /* __ASSEMBLY__ */
> diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
> index 9972626ddaf6..656ecf2b10cd 100644
> --- a/arch/powerpc/include/asm/pgtable.h
> +++ b/arch/powerpc/include/asm/pgtable.h
> @@ -41,6 +41,12 @@ struct mm_struct;
>
> #ifndef __ASSEMBLY__
>
> +void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> + pte_t pte, unsigned int nr);
> +#define set_ptes set_ptes
> +#define update_mmu_cache(vma, addr, ptep) \
> + update_mmu_cache_range(vma, addr, ptep, 1)
> +
> #ifndef MAX_PTRS_PER_PGD
> #define MAX_PTRS_PER_PGD PTRS_PER_PGD
> #endif
> diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
> index fedffe3ae136..ad2afa08e62e 100644
> --- a/arch/powerpc/mm/book3s64/hash_utils.c
> +++ b/arch/powerpc/mm/book3s64/hash_utils.c
> @@ -1307,18 +1307,19 @@ void hash__early_init_mmu_secondary(void)
> */
> unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
> {
> - struct page *page;
> + struct folio *folio;
>
> if (!pfn_valid(pte_pfn(pte)))
> return pp;
>
> - page = pte_page(pte);
> + folio = page_folio(pte_page(pte));
>
> /* page is dirty */
> - if (!test_bit(PG_dcache_clean, &page->flags) && !PageReserved(page)) {
> + if (!test_bit(PG_dcache_clean, &folio->flags) &&
> + !folio_test_reserved(folio)) {
> if (trap == INTERRUPT_INST_STORAGE) {
> - flush_dcache_icache_page(page);
> - set_bit(PG_dcache_clean, &page->flags);
> + flush_dcache_icache_folio(folio);
> + set_bit(PG_dcache_clean, &folio->flags);
> } else
> pp |= HPTE_R_N;
> }
> diff --git a/arch/powerpc/mm/cacheflush.c b/arch/powerpc/mm/cacheflush.c
> index 0e9b4879c0f9..8760d2223abe 100644
> --- a/arch/powerpc/mm/cacheflush.c
> +++ b/arch/powerpc/mm/cacheflush.c
> @@ -148,44 +148,30 @@ static void __flush_dcache_icache(void *p)
> invalidate_icache_range(addr, addr + PAGE_SIZE);
> }
>
> -static void flush_dcache_icache_hugepage(struct page *page)
> +void flush_dcache_icache_folio(struct folio *folio)
> {
> - int i;
> - int nr = compound_nr(page);
> + unsigned int i, nr = folio_nr_pages(folio);
>
> - if (!PageHighMem(page)) {
> + if (flush_coherent_icache())
> + return;
> +
> + if (!folio_test_highmem(folio)) {
> + void *addr = folio_address(folio);
Should be a blank line here ?
> for (i = 0; i < nr; i++)
> - __flush_dcache_icache(lowmem_page_address(page + i));
> - } else {
> + __flush_dcache_icache(addr + i * PAGE_SIZE);
> + } else if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) {
> for (i = 0; i < nr; i++) {
> - void *start = kmap_local_page(page + i);
> + void *start = kmap_local_folio(folio, i * PAGE_SIZE);
>
> __flush_dcache_icache(start);
> kunmap_local(start);
> }
> - }
> -}
> -
> -void flush_dcache_icache_page(struct page *page)
> -{
> - if (flush_coherent_icache())
> - return;
> -
> - if (PageCompound(page))
> - return flush_dcache_icache_hugepage(page);
> -
> - if (!PageHighMem(page)) {
> - __flush_dcache_icache(lowmem_page_address(page));
> - } else if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) {
> - void *start = kmap_local_page(page);
> -
> - __flush_dcache_icache(start);
> - kunmap_local(start);
> } else {
> - flush_dcache_icache_phys(page_to_phys(page));
> + unsigned long pfn = folio_pfn(folio);
Blank line ?
> + for (i = 0; i < nr; i++)
> + flush_dcache_icache_phys((pfn + i) * PAGE_SIZE);
Use PFN_PHYS(pfn + i) ?
> }
> }
> -EXPORT_SYMBOL(flush_dcache_icache_page);
>
> void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
> {
> diff --git a/arch/powerpc/mm/nohash/e500_hugetlbpage.c b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
> index 58c8d9849cb1..f3cb91107a47 100644
> --- a/arch/powerpc/mm/nohash/e500_hugetlbpage.c
> +++ b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
> @@ -178,7 +178,8 @@ book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte)
> *
> * This must always be called with the pte lock held.
> */
> -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
> +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
> + pte_t *ptep, unsigned int nr)
update_mmu_cache_range() ?
> {
> if (is_vm_hugetlb_page(vma))
> book3e_hugetlb_preload(vma, address, *ptep);
> diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
> index cb2dcdb18f8e..b3c7b874a7a2 100644
> --- a/arch/powerpc/mm/pgtable.c
> +++ b/arch/powerpc/mm/pgtable.c
> @@ -58,7 +58,7 @@ static inline int pte_looks_normal(pte_t pte)
> return 0;
> }
>
> -static struct page *maybe_pte_to_page(pte_t pte)
> +static struct folio *maybe_pte_to_folio(pte_t pte)
> {
> unsigned long pfn = pte_pfn(pte);
> struct page *page;
> @@ -68,7 +68,7 @@ static struct page *maybe_pte_to_page(pte_t pte)
> page = pfn_to_page(pfn);
> if (PageReserved(page))
> return NULL;
> - return page;
> + return page_folio(page);
> }
>
> #ifdef CONFIG_PPC_BOOK3S
> @@ -84,12 +84,12 @@ static pte_t set_pte_filter_hash(pte_t pte)
> pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
> if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) ||
> cpu_has_feature(CPU_FTR_NOEXECUTE))) {
> - struct page *pg = maybe_pte_to_page(pte);
> - if (!pg)
> + struct folio *folio = maybe_pte_to_folio(pte);
> + if (!folio)
> return pte;
> - if (!test_bit(PG_dcache_clean, &pg->flags)) {
> - flush_dcache_icache_page(pg);
> - set_bit(PG_dcache_clean, &pg->flags);
> + if (!test_bit(PG_dcache_clean, &folio->flags)) {
> + flush_dcache_icache_folio(folio);
> + set_bit(PG_dcache_clean, &folio->flags);
> }
> }
> return pte;
> @@ -107,7 +107,7 @@ static pte_t set_pte_filter_hash(pte_t pte) { return pte; }
> */
> static inline pte_t set_pte_filter(pte_t pte)
> {
> - struct page *pg;
> + struct folio *folio;
>
> if (radix_enabled())
> return pte;
> @@ -120,18 +120,18 @@ static inline pte_t set_pte_filter(pte_t pte)
> return pte;
>
> /* If you set _PAGE_EXEC on weird pages you're on your own */
> - pg = maybe_pte_to_page(pte);
> - if (unlikely(!pg))
> + folio = maybe_pte_to_folio(pte);
> + if (unlikely(!folio))
> return pte;
>
> /* If the page clean, we move on */
> - if (test_bit(PG_dcache_clean, &pg->flags))
> + if (test_bit(PG_dcache_clean, &folio->flags))
> return pte;
>
> /* If it's an exec fault, we flush the cache and make it clean */
> if (is_exec_fault()) {
> - flush_dcache_icache_page(pg);
> - set_bit(PG_dcache_clean, &pg->flags);
> + flush_dcache_icache_folio(folio);
> + set_bit(PG_dcache_clean, &folio->flags);
> return pte;
> }
>
> @@ -142,7 +142,7 @@ static inline pte_t set_pte_filter(pte_t pte)
> static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
> int dirty)
> {
> - struct page *pg;
> + struct folio *folio;
>
> if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
> return pte;
> @@ -168,17 +168,17 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
> #endif /* CONFIG_DEBUG_VM */
>
> /* If you set _PAGE_EXEC on weird pages you're on your own */
> - pg = maybe_pte_to_page(pte);
> - if (unlikely(!pg))
> + folio = maybe_pte_to_folio(pte);
> + if (unlikely(!folio))
> goto bail;
>
> /* If the page is already clean, we move on */
> - if (test_bit(PG_dcache_clean, &pg->flags))
> + if (test_bit(PG_dcache_clean, &folio->flags))
> goto bail;
>
> /* Clean the page and set PG_dcache_clean */
> - flush_dcache_icache_page(pg);
> - set_bit(PG_dcache_clean, &pg->flags);
> + flush_dcache_icache_folio(folio);
> + set_bit(PG_dcache_clean, &folio->flags);
>
> bail:
> return pte_mkexec(pte);
> @@ -187,8 +187,8 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
> /*
> * set_pte stores a linux PTE into the linux page table.
> */
> -void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> - pte_t pte)
> +void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> + pte_t pte, unsigned int nr)
> {
> /*
> * Make sure hardware valid bit is not set. We don't do
> @@ -203,7 +203,14 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> pte = set_pte_filter(pte);
>
> /* Perform the setting of the PTE */
> - __set_pte_at(mm, addr, ptep, pte, 0);
> + for (;;) {
> + __set_pte_at(mm, addr, ptep, pte, 0);
> + if (--nr == 0)
> + break;
> + ptep++;
> + pte = __pte(pte_val(pte) + PAGE_SIZE);
I don't like that math too much, but I have no better idea at the moment.
Maybe set_ptes() should take a pgprot_t and rebuild the pte with
mk_pte() or similar ?
> + addr += PAGE_SIZE;
> + }
> }
>
> void unmap_kernel_page(unsigned long va)
On Wed, Mar 15, 2023 at 05:14:28AM +0000, Matthew Wilcox (Oracle) wrote:
> Add set_ptes(), update_mmu_cache_range() and flush_dcache_folio().
> Change the PG_arch_1 (aka PG_dcache_dirty) flag from being per-page to
> per-folio.
>
> Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
> Cc: Michael Ellerman <[email protected]>
> Cc: Nicholas Piggin <[email protected]>
> Cc: Christophe Leroy <[email protected]>
> Cc: [email protected]
Acked-by: Mike Rapoport (IBM) <[email protected]>
> ---
> arch/powerpc/include/asm/book3s/pgtable.h | 10 +----
> arch/powerpc/include/asm/cacheflush.h | 14 +++++--
> arch/powerpc/include/asm/kvm_ppc.h | 10 ++---
> arch/powerpc/include/asm/nohash/pgtable.h | 13 ++----
> arch/powerpc/include/asm/pgtable.h | 6 +++
> arch/powerpc/mm/book3s64/hash_utils.c | 11 ++---
> arch/powerpc/mm/cacheflush.c | 40 ++++++------------
> arch/powerpc/mm/nohash/e500_hugetlbpage.c | 3 +-
> arch/powerpc/mm/pgtable.c | 51 +++++++++++++----------
> 9 files changed, 77 insertions(+), 81 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h
> index d18b748ea3ae..c2ef811505b0 100644
> --- a/arch/powerpc/include/asm/book3s/pgtable.h
> +++ b/arch/powerpc/include/asm/book3s/pgtable.h
> @@ -9,13 +9,6 @@
> #endif
>
> #ifndef __ASSEMBLY__
> -/* Insert a PTE, top-level function is out of line. It uses an inline
> - * low level function in the respective pgtable-* files
> - */
> -extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> - pte_t pte);
> -
> -
> #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
> extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
> pte_t *ptep, pte_t entry, int dirty);
> @@ -36,7 +29,8 @@ void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t
> * corresponding HPTE into the hash table ahead of time, instead of
> * waiting for the inevitable extra hash-table miss exception.
> */
> -static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
> +static inline void update_mmu_cache_range(struct vm_area_struct *vma,
> + unsigned long address, pte_t *ptep, unsigned int nr)
> {
> if (IS_ENABLED(CONFIG_PPC32) && !mmu_has_feature(MMU_FTR_HPTE_TABLE))
> return;
> diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
> index 7564dd4fd12b..ef7d2de33b89 100644
> --- a/arch/powerpc/include/asm/cacheflush.h
> +++ b/arch/powerpc/include/asm/cacheflush.h
> @@ -35,13 +35,19 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
> * It just marks the page as not i-cache clean. We do the i-cache
> * flush later when the page is given to a user process, if necessary.
> */
> -static inline void flush_dcache_page(struct page *page)
> +static inline void flush_dcache_folio(struct folio *folio)
> {
> if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
> return;
> /* avoid an atomic op if possible */
> - if (test_bit(PG_dcache_clean, &page->flags))
> - clear_bit(PG_dcache_clean, &page->flags);
> + if (test_bit(PG_dcache_clean, &folio->flags))
> + clear_bit(PG_dcache_clean, &folio->flags);
> +}
> +#define flush_dcache_folio flush_dcache_folio
> +
> +static inline void flush_dcache_page(struct page *page)
> +{
> + flush_dcache_folio(page_folio(page));
> }
>
> void flush_icache_range(unsigned long start, unsigned long stop);
> @@ -51,7 +57,7 @@ void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
> unsigned long addr, int len);
> #define flush_icache_user_page flush_icache_user_page
>
> -void flush_dcache_icache_page(struct page *page);
> +void flush_dcache_icache_folio(struct folio *folio);
>
> /**
> * flush_dcache_range(): Write any modified data cache blocks out to memory and
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
> index 6bef23d6d0e3..e91dd8e88bb7 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -868,7 +868,7 @@ void kvmppc_init_lpid(unsigned long nr_lpids);
>
> static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn)
> {
> - struct page *page;
> + struct folio *folio;
> /*
> * We can only access pages that the kernel maps
> * as memory. Bail out for unmapped ones.
> @@ -877,10 +877,10 @@ static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn)
> return;
>
> /* Clear i-cache for new pages */
> - page = pfn_to_page(pfn);
> - if (!test_bit(PG_dcache_clean, &page->flags)) {
> - flush_dcache_icache_page(page);
> - set_bit(PG_dcache_clean, &page->flags);
> + folio = page_folio(pfn_to_page(pfn));
> + if (!test_bit(PG_dcache_clean, &folio->flags)) {
> + flush_dcache_icache_folio(folio);
> + set_bit(PG_dcache_clean, &folio->flags);
> }
> }
>
> diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
> index a6caaaab6f92..69a7dd47a9f0 100644
> --- a/arch/powerpc/include/asm/nohash/pgtable.h
> +++ b/arch/powerpc/include/asm/nohash/pgtable.h
> @@ -166,12 +166,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
> return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE);
> }
>
> -/* Insert a PTE, top-level function is out of line. It uses an inline
> - * low level function in the respective pgtable-* files
> - */
> -extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> - pte_t pte);
> -
> /* This low level function performs the actual PTE insertion
> * Setting the PTE depends on the MMU type and other factors. It's
> * an horrible mess that I'm not going to try to clean up now but
> @@ -282,10 +276,11 @@ static inline int pud_huge(pud_t pud)
> * for the page which has just been mapped in.
> */
> #if defined(CONFIG_PPC_E500) && defined(CONFIG_HUGETLB_PAGE)
> -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep);
> +void update_mmu_cache_range(struct vm_area_struct *vma, unsigned long address,
> + pte_t *ptep, unsigned int nr);
> #else
> -static inline
> -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) {}
> +static inline void update_mmu_cache(struct vm_area_struct *vma,
> + unsigned long address, pte_t *ptep, unsigned int nr) {}
> #endif
>
> #endif /* __ASSEMBLY__ */
> diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
> index 9972626ddaf6..656ecf2b10cd 100644
> --- a/arch/powerpc/include/asm/pgtable.h
> +++ b/arch/powerpc/include/asm/pgtable.h
> @@ -41,6 +41,12 @@ struct mm_struct;
>
> #ifndef __ASSEMBLY__
>
> +void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> + pte_t pte, unsigned int nr);
> +#define set_ptes set_ptes
> +#define update_mmu_cache(vma, addr, ptep) \
> + update_mmu_cache_range(vma, addr, ptep, 1)
> +
> #ifndef MAX_PTRS_PER_PGD
> #define MAX_PTRS_PER_PGD PTRS_PER_PGD
> #endif
> diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
> index fedffe3ae136..ad2afa08e62e 100644
> --- a/arch/powerpc/mm/book3s64/hash_utils.c
> +++ b/arch/powerpc/mm/book3s64/hash_utils.c
> @@ -1307,18 +1307,19 @@ void hash__early_init_mmu_secondary(void)
> */
> unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
> {
> - struct page *page;
> + struct folio *folio;
>
> if (!pfn_valid(pte_pfn(pte)))
> return pp;
>
> - page = pte_page(pte);
> + folio = page_folio(pte_page(pte));
>
> /* page is dirty */
> - if (!test_bit(PG_dcache_clean, &page->flags) && !PageReserved(page)) {
> + if (!test_bit(PG_dcache_clean, &folio->flags) &&
> + !folio_test_reserved(folio)) {
> if (trap == INTERRUPT_INST_STORAGE) {
> - flush_dcache_icache_page(page);
> - set_bit(PG_dcache_clean, &page->flags);
> + flush_dcache_icache_folio(folio);
> + set_bit(PG_dcache_clean, &folio->flags);
> } else
> pp |= HPTE_R_N;
> }
> diff --git a/arch/powerpc/mm/cacheflush.c b/arch/powerpc/mm/cacheflush.c
> index 0e9b4879c0f9..8760d2223abe 100644
> --- a/arch/powerpc/mm/cacheflush.c
> +++ b/arch/powerpc/mm/cacheflush.c
> @@ -148,44 +148,30 @@ static void __flush_dcache_icache(void *p)
> invalidate_icache_range(addr, addr + PAGE_SIZE);
> }
>
> -static void flush_dcache_icache_hugepage(struct page *page)
> +void flush_dcache_icache_folio(struct folio *folio)
> {
> - int i;
> - int nr = compound_nr(page);
> + unsigned int i, nr = folio_nr_pages(folio);
>
> - if (!PageHighMem(page)) {
> + if (flush_coherent_icache())
> + return;
> +
> + if (!folio_test_highmem(folio)) {
> + void *addr = folio_address(folio);
> for (i = 0; i < nr; i++)
> - __flush_dcache_icache(lowmem_page_address(page + i));
> - } else {
> + __flush_dcache_icache(addr + i * PAGE_SIZE);
> + } else if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) {
> for (i = 0; i < nr; i++) {
> - void *start = kmap_local_page(page + i);
> + void *start = kmap_local_folio(folio, i * PAGE_SIZE);
>
> __flush_dcache_icache(start);
> kunmap_local(start);
> }
> - }
> -}
> -
> -void flush_dcache_icache_page(struct page *page)
> -{
> - if (flush_coherent_icache())
> - return;
> -
> - if (PageCompound(page))
> - return flush_dcache_icache_hugepage(page);
> -
> - if (!PageHighMem(page)) {
> - __flush_dcache_icache(lowmem_page_address(page));
> - } else if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) {
> - void *start = kmap_local_page(page);
> -
> - __flush_dcache_icache(start);
> - kunmap_local(start);
> } else {
> - flush_dcache_icache_phys(page_to_phys(page));
> + unsigned long pfn = folio_pfn(folio);
> + for (i = 0; i < nr; i++)
> + flush_dcache_icache_phys((pfn + i) * PAGE_SIZE);
> }
> }
> -EXPORT_SYMBOL(flush_dcache_icache_page);
>
> void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
> {
> diff --git a/arch/powerpc/mm/nohash/e500_hugetlbpage.c b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
> index 58c8d9849cb1..f3cb91107a47 100644
> --- a/arch/powerpc/mm/nohash/e500_hugetlbpage.c
> +++ b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
> @@ -178,7 +178,8 @@ book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte)
> *
> * This must always be called with the pte lock held.
> */
> -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
> +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
> + pte_t *ptep, unsigned int nr)
> {
> if (is_vm_hugetlb_page(vma))
> book3e_hugetlb_preload(vma, address, *ptep);
> diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
> index cb2dcdb18f8e..b3c7b874a7a2 100644
> --- a/arch/powerpc/mm/pgtable.c
> +++ b/arch/powerpc/mm/pgtable.c
> @@ -58,7 +58,7 @@ static inline int pte_looks_normal(pte_t pte)
> return 0;
> }
>
> -static struct page *maybe_pte_to_page(pte_t pte)
> +static struct folio *maybe_pte_to_folio(pte_t pte)
> {
> unsigned long pfn = pte_pfn(pte);
> struct page *page;
> @@ -68,7 +68,7 @@ static struct page *maybe_pte_to_page(pte_t pte)
> page = pfn_to_page(pfn);
> if (PageReserved(page))
> return NULL;
> - return page;
> + return page_folio(page);
> }
>
> #ifdef CONFIG_PPC_BOOK3S
> @@ -84,12 +84,12 @@ static pte_t set_pte_filter_hash(pte_t pte)
> pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
> if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) ||
> cpu_has_feature(CPU_FTR_NOEXECUTE))) {
> - struct page *pg = maybe_pte_to_page(pte);
> - if (!pg)
> + struct folio *folio = maybe_pte_to_folio(pte);
> + if (!folio)
> return pte;
> - if (!test_bit(PG_dcache_clean, &pg->flags)) {
> - flush_dcache_icache_page(pg);
> - set_bit(PG_dcache_clean, &pg->flags);
> + if (!test_bit(PG_dcache_clean, &folio->flags)) {
> + flush_dcache_icache_folio(folio);
> + set_bit(PG_dcache_clean, &folio->flags);
> }
> }
> return pte;
> @@ -107,7 +107,7 @@ static pte_t set_pte_filter_hash(pte_t pte) { return pte; }
> */
> static inline pte_t set_pte_filter(pte_t pte)
> {
> - struct page *pg;
> + struct folio *folio;
>
> if (radix_enabled())
> return pte;
> @@ -120,18 +120,18 @@ static inline pte_t set_pte_filter(pte_t pte)
> return pte;
>
> /* If you set _PAGE_EXEC on weird pages you're on your own */
> - pg = maybe_pte_to_page(pte);
> - if (unlikely(!pg))
> + folio = maybe_pte_to_folio(pte);
> + if (unlikely(!folio))
> return pte;
>
> /* If the page clean, we move on */
> - if (test_bit(PG_dcache_clean, &pg->flags))
> + if (test_bit(PG_dcache_clean, &folio->flags))
> return pte;
>
> /* If it's an exec fault, we flush the cache and make it clean */
> if (is_exec_fault()) {
> - flush_dcache_icache_page(pg);
> - set_bit(PG_dcache_clean, &pg->flags);
> + flush_dcache_icache_folio(folio);
> + set_bit(PG_dcache_clean, &folio->flags);
> return pte;
> }
>
> @@ -142,7 +142,7 @@ static inline pte_t set_pte_filter(pte_t pte)
> static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
> int dirty)
> {
> - struct page *pg;
> + struct folio *folio;
>
> if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
> return pte;
> @@ -168,17 +168,17 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
> #endif /* CONFIG_DEBUG_VM */
>
> /* If you set _PAGE_EXEC on weird pages you're on your own */
> - pg = maybe_pte_to_page(pte);
> - if (unlikely(!pg))
> + folio = maybe_pte_to_folio(pte);
> + if (unlikely(!folio))
> goto bail;
>
> /* If the page is already clean, we move on */
> - if (test_bit(PG_dcache_clean, &pg->flags))
> + if (test_bit(PG_dcache_clean, &folio->flags))
> goto bail;
>
> /* Clean the page and set PG_dcache_clean */
> - flush_dcache_icache_page(pg);
> - set_bit(PG_dcache_clean, &pg->flags);
> + flush_dcache_icache_folio(folio);
> + set_bit(PG_dcache_clean, &folio->flags);
>
> bail:
> return pte_mkexec(pte);
> @@ -187,8 +187,8 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
> /*
> * set_pte stores a linux PTE into the linux page table.
> */
> -void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> - pte_t pte)
> +void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> + pte_t pte, unsigned int nr)
> {
> /*
> * Make sure hardware valid bit is not set. We don't do
> @@ -203,7 +203,14 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> pte = set_pte_filter(pte);
>
> /* Perform the setting of the PTE */
> - __set_pte_at(mm, addr, ptep, pte, 0);
> + for (;;) {
> + __set_pte_at(mm, addr, ptep, pte, 0);
> + if (--nr == 0)
> + break;
> + ptep++;
> + pte = __pte(pte_val(pte) + PAGE_SIZE);
> + addr += PAGE_SIZE;
> + }
> }
>
> void unmap_kernel_page(unsigned long va)
> --
> 2.39.2
>
>
--
Sincerely yours,
Mike.
Le 15/03/2023 à 10:43, Christophe Leroy a écrit :
>
>
> Le 15/03/2023 à 06:14, Matthew Wilcox (Oracle) a écrit :
>> Add set_ptes(), update_mmu_cache_range() and flush_dcache_folio().
>> Change the PG_arch_1 (aka PG_dcache_dirty) flag from being per-page to
>> per-folio.
>>
>> Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
>> Cc: Michael Ellerman <[email protected]>
>> Cc: Nicholas Piggin <[email protected]>
>> Cc: Christophe Leroy <[email protected]>
>> Cc: [email protected]
>> ---
>> @@ -203,7 +203,14 @@ void set_pte_at(struct mm_struct *mm, unsigned
>> long addr, pte_t *ptep,
>> pte = set_pte_filter(pte);
>> /* Perform the setting of the PTE */
>> - __set_pte_at(mm, addr, ptep, pte, 0);
>> + for (;;) {
>> + __set_pte_at(mm, addr, ptep, pte, 0);
>> + if (--nr == 0)
>> + break;
>> + ptep++;
>> + pte = __pte(pte_val(pte) + PAGE_SIZE);
>
> I don't like that math too much, but I have no better idea at the moment.
>
> Maybe set_ptes() should take a pgprot_t and rebuild the pte with
> mk_pte() or similar ?
>
>> + addr += PAGE_SIZE;
>> + }
>> }
>> void unmap_kernel_page(unsigned long va)
I investigated a bit further and can confirm now that the above won't
always work, see comment
https://elixir.bootlin.com/linux/v6.3-rc2/source/arch/powerpc/include/asm/nohash/32/pgtable.h#L147
And then you see
https://elixir.bootlin.com/linux/v6.3-rc2/source/arch/powerpc/include/asm/nohash/pte-e500.h#L63
Christophe
On Wed, Mar 15, 2023 at 10:18:22AM +0000, Christophe Leroy wrote:
> I investigated a bit further and can confirm now that the above won't
> always work, see comment
> https://elixir.bootlin.com/linux/v6.3-rc2/source/arch/powerpc/include/asm/nohash/32/pgtable.h#L147
>
> And then you see
> https://elixir.bootlin.com/linux/v6.3-rc2/source/arch/powerpc/include/asm/nohash/pte-e500.h#L63
Got it. Here's what I intend to fold in for the next version:
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 7bf1fe7297c6..5f12b9382909 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -462,11 +462,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
pgprot_val(pgprot));
}
-static inline unsigned long pte_pfn(pte_t pte)
-{
- return pte_val(pte) >> PTE_RPN_SHIFT;
-}
-
/* Generic modifiers for PTE bits */
static inline pte_t pte_wrprotect(pte_t pte)
{
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 4acc9690f599..c5baa3082a5a 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -104,6 +104,7 @@
* and every thing below PAGE_SHIFT;
*/
#define PTE_RPN_MASK (((1UL << _PAGE_PA_MAX) - 1) & (PAGE_MASK))
+#define PTE_RPN_SHIFT PAGE_SHIFT
/*
* set of bits not changed in pmd_modify. Even though we have hash specific bits
* in here, on radix we expect them to be zero.
@@ -569,11 +570,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot) | _PAGE_PTE);
}
-static inline unsigned long pte_pfn(pte_t pte)
-{
- return (pte_val(pte) & PTE_RPN_MASK) >> PAGE_SHIFT;
-}
-
/* Generic modifiers for PTE bits */
static inline pte_t pte_wrprotect(pte_t pte)
{
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 69a7dd47a9f0..03be8b22aaea 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -101,8 +101,6 @@ static inline bool pte_access_permitted(pte_t pte, bool write)
static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) {
return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
pgprot_val(pgprot)); }
-static inline unsigned long pte_pfn(pte_t pte) {
- return pte_val(pte) >> PTE_RPN_SHIFT; }
/* Generic modifiers for PTE bits */
static inline pte_t pte_exprotect(pte_t pte)
@@ -279,7 +277,7 @@ static inline int pud_huge(pud_t pud)
void update_mmu_cache_range(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep, unsigned int nr);
#else
-static inline void update_mmu_cache(struct vm_area_struct *vma,
+static inline void update_mmu_cache_range(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep, unsigned int nr) {}
#endif
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 656ecf2b10cd..491a2720f835 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -54,6 +54,12 @@ void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
/* Keep these as a macros to avoid include dependency mess */
#define pte_page(x) pfn_to_page(pte_pfn(x))
#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+ return (pte_val(pte) & PTE_RPN_MASK) >> PTE_RPN_SHIFT;
+}
+
/*
* Select all bits except the pfn
*/
diff --git a/arch/powerpc/mm/nohash/e500_hugetlbpage.c b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
index f3cb91107a47..583b3098763f 100644
--- a/arch/powerpc/mm/nohash/e500_hugetlbpage.c
+++ b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
@@ -178,7 +178,7 @@ book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte)
*
* This must always be called with the pte lock held.
*/
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
+void update_mmu_cache_range(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep, unsigned int nr)
{
if (is_vm_hugetlb_page(vma))
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index b3c7b874a7a2..db236b494845 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -208,7 +208,7 @@ void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
if (--nr == 0)
break;
ptep++;
- pte = __pte(pte_val(pte) + PAGE_SIZE);
+ pte = __pte(pte_val(pte) + (1UL << PTE_RPN_SHIFT));
addr += PAGE_SIZE;
}
}
Le 17/03/2023 à 04:47, Matthew Wilcox a écrit :
> On Wed, Mar 15, 2023 at 10:18:22AM +0000, Christophe Leroy wrote:
>> I investigated a bit further and can confirm now that the above won't
>> always work, see comment
>> https://elixir.bootlin.com/linux/v6.3-rc2/source/arch/powerpc/include/asm/nohash/32/pgtable.h#L147
>>
>> And then you see
>> https://elixir.bootlin.com/linux/v6.3-rc2/source/arch/powerpc/include/asm/nohash/pte-e500.h#L63
>
> Got it. Here's what I intend to fold in for the next version:
>
> diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
> index 7bf1fe7297c6..5f12b9382909 100644
> --- a/arch/powerpc/include/asm/book3s/32/pgtable.h
> +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
> @@ -462,11 +462,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
> pgprot_val(pgprot));
> }
>
> -static inline unsigned long pte_pfn(pte_t pte)
> -{
> - return pte_val(pte) >> PTE_RPN_SHIFT;
> -}
> -
> /* Generic modifiers for PTE bits */
> static inline pte_t pte_wrprotect(pte_t pte)
> {
> diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
> index 4acc9690f599..c5baa3082a5a 100644
> --- a/arch/powerpc/include/asm/book3s/64/pgtable.h
> +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
> @@ -104,6 +104,7 @@
> * and every thing below PAGE_SHIFT;
> */
> #define PTE_RPN_MASK (((1UL << _PAGE_PA_MAX) - 1) & (PAGE_MASK))
> +#define PTE_RPN_SHIFT PAGE_SHIFT
> /*
> * set of bits not changed in pmd_modify. Even though we have hash specific bits
> * in here, on radix we expect them to be zero.
> @@ -569,11 +570,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
> return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot) | _PAGE_PTE);
> }
>
> -static inline unsigned long pte_pfn(pte_t pte)
> -{
> - return (pte_val(pte) & PTE_RPN_MASK) >> PAGE_SHIFT;
> -}
> -
> /* Generic modifiers for PTE bits */
> static inline pte_t pte_wrprotect(pte_t pte)
> {
> diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
> index 69a7dd47a9f0..03be8b22aaea 100644
> --- a/arch/powerpc/include/asm/nohash/pgtable.h
> +++ b/arch/powerpc/include/asm/nohash/pgtable.h
> @@ -101,8 +101,6 @@ static inline bool pte_access_permitted(pte_t pte, bool write)
> static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) {
> return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
> pgprot_val(pgprot)); }
> -static inline unsigned long pte_pfn(pte_t pte) {
> - return pte_val(pte) >> PTE_RPN_SHIFT; }
>
> /* Generic modifiers for PTE bits */
> static inline pte_t pte_exprotect(pte_t pte)
> @@ -279,7 +277,7 @@ static inline int pud_huge(pud_t pud)
> void update_mmu_cache_range(struct vm_area_struct *vma, unsigned long address,
> pte_t *ptep, unsigned int nr);
> #else
> -static inline void update_mmu_cache(struct vm_area_struct *vma,
> +static inline void update_mmu_cache_range(struct vm_area_struct *vma,
> unsigned long address, pte_t *ptep, unsigned int nr) {}
> #endif
>
> diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
> index 656ecf2b10cd..491a2720f835 100644
> --- a/arch/powerpc/include/asm/pgtable.h
> +++ b/arch/powerpc/include/asm/pgtable.h
> @@ -54,6 +54,12 @@ void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> /* Keep these as a macros to avoid include dependency mess */
> #define pte_page(x) pfn_to_page(pte_pfn(x))
> #define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
> +
> +static inline unsigned long pte_pfn(pte_t pte)
> +{
> + return (pte_val(pte) & PTE_RPN_MASK) >> PTE_RPN_SHIFT;
> +}
> +
> /*
> * Select all bits except the pfn
> */
> diff --git a/arch/powerpc/mm/nohash/e500_hugetlbpage.c b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
> index f3cb91107a47..583b3098763f 100644
> --- a/arch/powerpc/mm/nohash/e500_hugetlbpage.c
> +++ b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
> @@ -178,7 +178,7 @@ book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte)
> *
> * This must always be called with the pte lock held.
> */
> -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
> +void update_mmu_cache_range(struct vm_area_struct *vma, unsigned long address,
> pte_t *ptep, unsigned int nr)
> {
> if (is_vm_hugetlb_page(vma))
> diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
> index b3c7b874a7a2..db236b494845 100644
> --- a/arch/powerpc/mm/pgtable.c
> +++ b/arch/powerpc/mm/pgtable.c
> @@ -208,7 +208,7 @@ void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> if (--nr == 0)
> break;
> ptep++;
> - pte = __pte(pte_val(pte) + PAGE_SIZE);
> + pte = __pte(pte_val(pte) + (1UL << PTE_RPN_SHIFT));
> addr += PAGE_SIZE;
> }
> }
What about:
void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
pte_t pte, unsigned int nr)
{
pgprot_t prot;
unsigned long pfn;
/*
* Make sure hardware valid bit is not set. We don't do
* tlb flush for this update.
*/
VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
/* Note: mm->context.id might not yet have been assigned as
* this context might not have been activated yet when this
* is called.
*/
pte = set_pte_filter(pte);
prot = pte_pgprot(pte);
pfn = pte_pfn(pte);
/* Perform the setting of the PTE */
for (;;) {
__set_pte_at(mm, addr, ptep, pfn_pte(pfn, prot), 0);
if (--nr == 0)
break;
ptep++;
pfn++;
addr += PAGE_SIZE;
}
}
Christophe
On Sat, Mar 18, 2023 at 09:19:04AM +0000, Christophe Leroy wrote:
> void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> pte_t pte, unsigned int nr)
> {
> pgprot_t prot;
> unsigned long pfn;
> /*
> * Make sure hardware valid bit is not set. We don't do
> * tlb flush for this update.
> */
> VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
>
> /* Note: mm->context.id might not yet have been assigned as
> * this context might not have been activated yet when this
> * is called.
> */
> pte = set_pte_filter(pte);
>
> prot = pte_pgprot(pte);
> pfn = pte_pfn(pte);
> /* Perform the setting of the PTE */
> for (;;) {
> __set_pte_at(mm, addr, ptep, pfn_pte(pfn, prot), 0);
> if (--nr == 0)
> break;
> ptep++;
> pfn++;
> addr += PAGE_SIZE;
> }
> }
I'd rather the per-arch code were as similar to each other and the
generic implementation as possible. Fewer bugs that way and easier
for other people to make changes that have to touch every architecture
in the future.
Le 10/07/2023 à 22:24, Matthew Wilcox a écrit :
> On Sat, Mar 18, 2023 at 09:19:04AM +0000, Christophe Leroy wrote:
>> void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
>> pte_t pte, unsigned int nr)
>> {
>> pgprot_t prot;
>> unsigned long pfn;
>> /*
>> * Make sure hardware valid bit is not set. We don't do
>> * tlb flush for this update.
>> */
>> VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
>>
>> /* Note: mm->context.id might not yet have been assigned as
>> * this context might not have been activated yet when this
>> * is called.
>> */
>> pte = set_pte_filter(pte);
>>
>> prot = pte_pgprot(pte);
>> pfn = pte_pfn(pte);
>> /* Perform the setting of the PTE */
>> for (;;) {
>> __set_pte_at(mm, addr, ptep, pfn_pte(pfn, prot), 0);
>> if (--nr == 0)
>> break;
>> ptep++;
>> pfn++;
>> addr += PAGE_SIZE;
>> }
>> }
>
> I'd rather the per-arch code were as similar to each other and the
> generic implementation as possible. Fewer bugs that way and easier
> for other people to make changes that have to touch every architecture
> in the future.
I understand your point but I dislike the idea of open coding pte
manipulations when you have helpers for that. If you had used helpers
from the begining you wouldn't have had the mishap you had in v4.