* [PATCH v2 2/3] arm64: mm: don't call page table ctors for init_mm
2019-02-18 23:13 ` [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables Yu Zhao
@ 2019-02-18 23:13 ` Yu Zhao
2019-02-26 15:13 ` Mark Rutland
2019-02-18 23:13 ` [PATCH v2 3/3] arm64: mm: enable per pmd page table lock Yu Zhao
` (3 subsequent siblings)
4 siblings, 1 reply; 38+ messages in thread
From: Yu Zhao @ 2019-02-18 23:13 UTC (permalink / raw)
To: Catalin Marinas, Will Deacon
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Mark Rutland,
Ard Biesheuvel, Chintan Pandya, Jun Yao, Laura Abbott,
linux-arm-kernel, linux-kernel, linux-arch, linux-mm, Yu Zhao
init_mm doesn't require page table lock to be initialized at
any level. Add a separate page table allocator for it, and the
new one skips page table ctors.
The ctors allocate memory when ALLOC_SPLIT_PTLOCKS is set. Not
calling them avoids memory leak in case we call pte_free_kernel()
on init_mm.
Signed-off-by: Yu Zhao <yuzhao@google.com>
---
arch/arm64/mm/mmu.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index fa7351877af3..e8bf8a6300e8 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -370,6 +370,16 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
} while (pgdp++, addr = next, addr != end);
}
+static phys_addr_t pgd_kernel_pgtable_alloc(int shift)
+{
+ void *ptr = (void *)__get_free_page(PGALLOC_GFP);
+ BUG_ON(!ptr);
+
+ /* Ensure the zeroed page is visible to the page table walker */
+ dsb(ishst);
+ return __pa(ptr);
+}
+
static phys_addr_t pgd_pgtable_alloc(int shift)
{
void *ptr = (void *)__get_free_page(PGALLOC_GFP);
@@ -591,7 +601,7 @@ static int __init map_entry_trampoline(void)
/* Map only the text into the trampoline page table */
memset(tramp_pg_dir, 0, PGD_SIZE);
__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
- prot, pgd_pgtable_alloc, 0);
+ prot, pgd_kernel_pgtable_alloc, 0);
/* Map both the text and data into the kernel page table */
__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
@@ -1067,7 +1077,8 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
- size, PAGE_KERNEL, pgd_pgtable_alloc, flags);
+ size, PAGE_KERNEL, pgd_kernel_pgtable_alloc,
+ flags);
return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
altmap, want_memblock);
--
2.21.0.rc0.258.g878e2cd30e-goog
^ permalink raw reply related [flat|nested] 38+ messages in thread
* Re: [PATCH v2 2/3] arm64: mm: don't call page table ctors for init_mm
2019-02-18 23:13 ` [PATCH v2 2/3] arm64: mm: don't call page table ctors for init_mm Yu Zhao
@ 2019-02-26 15:13 ` Mark Rutland
2019-03-09 3:52 ` Yu Zhao
0 siblings, 1 reply; 38+ messages in thread
From: Mark Rutland @ 2019-02-26 15:13 UTC (permalink / raw)
To: Yu Zhao
Cc: Catalin Marinas, Will Deacon, Aneesh Kumar K . V, Andrew Morton,
Nick Piggin, Peter Zijlstra, Joel Fernandes, Kirill A . Shutemov,
Ard Biesheuvel, Chintan Pandya, Jun Yao, Laura Abbott,
linux-arm-kernel, linux-kernel, linux-arch, linux-mm
Hi,
On Mon, Feb 18, 2019 at 04:13:18PM -0700, Yu Zhao wrote:
> init_mm doesn't require page table lock to be initialized at
> any level. Add a separate page table allocator for it, and the
> new one skips page table ctors.
Just to check, in a previous reply you mentioned we need to call the
ctors for our efi_mm, since we use apply_to_page_range() on that. Is
that only because apply_to_pte_range() tries to take the ptl for non
init_mm?
... or did I miss something else?
> The ctors allocate memory when ALLOC_SPLIT_PTLOCKS is set. Not
> calling them avoids memory leak in case we call pte_free_kernel()
> on init_mm.
>
> Signed-off-by: Yu Zhao <yuzhao@google.com>
Assuming that was all, this patch makes sense to me. FWIW:
Acked-by: Mark Rutland <mark.rutland@arm.com>
Thanks,
Mark.
> ---
> arch/arm64/mm/mmu.c | 15 +++++++++++++--
> 1 file changed, 13 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
> index fa7351877af3..e8bf8a6300e8 100644
> --- a/arch/arm64/mm/mmu.c
> +++ b/arch/arm64/mm/mmu.c
> @@ -370,6 +370,16 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
> } while (pgdp++, addr = next, addr != end);
> }
>
> +static phys_addr_t pgd_kernel_pgtable_alloc(int shift)
> +{
> + void *ptr = (void *)__get_free_page(PGALLOC_GFP);
> + BUG_ON(!ptr);
> +
> + /* Ensure the zeroed page is visible to the page table walker */
> + dsb(ishst);
> + return __pa(ptr);
> +}
> +
> static phys_addr_t pgd_pgtable_alloc(int shift)
> {
> void *ptr = (void *)__get_free_page(PGALLOC_GFP);
> @@ -591,7 +601,7 @@ static int __init map_entry_trampoline(void)
> /* Map only the text into the trampoline page table */
> memset(tramp_pg_dir, 0, PGD_SIZE);
> __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
> - prot, pgd_pgtable_alloc, 0);
> + prot, pgd_kernel_pgtable_alloc, 0);
>
> /* Map both the text and data into the kernel page table */
> __set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
> @@ -1067,7 +1077,8 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
> flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
>
> __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
> - size, PAGE_KERNEL, pgd_pgtable_alloc, flags);
> + size, PAGE_KERNEL, pgd_kernel_pgtable_alloc,
> + flags);
>
> return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
> altmap, want_memblock);
> --
> 2.21.0.rc0.258.g878e2cd30e-goog
>
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 2/3] arm64: mm: don't call page table ctors for init_mm
2019-02-26 15:13 ` Mark Rutland
@ 2019-03-09 3:52 ` Yu Zhao
0 siblings, 0 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-09 3:52 UTC (permalink / raw)
To: Mark Rutland
Cc: Catalin Marinas, Will Deacon, Aneesh Kumar K . V, Andrew Morton,
Nick Piggin, Peter Zijlstra, Joel Fernandes, Kirill A . Shutemov,
Ard Biesheuvel, Chintan Pandya, Jun Yao, Laura Abbott,
linux-arm-kernel, linux-kernel, linux-arch, linux-mm
On Tue, Feb 26, 2019 at 03:13:07PM +0000, Mark Rutland wrote:
> Hi,
>
> On Mon, Feb 18, 2019 at 04:13:18PM -0700, Yu Zhao wrote:
> > init_mm doesn't require page table lock to be initialized at
> > any level. Add a separate page table allocator for it, and the
> > new one skips page table ctors.
>
> Just to check, in a previous reply you mentioned we need to call the
> ctors for our efi_mm, since we use apply_to_page_range() on that. Is
> that only because apply_to_pte_range() tries to take the ptl for non
> init_mm?
Precisely.
> ... or did I miss something else?
>
> > The ctors allocate memory when ALLOC_SPLIT_PTLOCKS is set. Not
> > calling them avoids memory leak in case we call pte_free_kernel()
> > on init_mm.
> >
> > Signed-off-by: Yu Zhao <yuzhao@google.com>
>
> Assuming that was all, this patch makes sense to me. FWIW:
>
> Acked-by: Mark Rutland <mark.rutland@arm.com>
Thanks.
> Thanks,
> Mark.
>
> > ---
> > arch/arm64/mm/mmu.c | 15 +++++++++++++--
> > 1 file changed, 13 insertions(+), 2 deletions(-)
> >
> > diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
> > index fa7351877af3..e8bf8a6300e8 100644
> > --- a/arch/arm64/mm/mmu.c
> > +++ b/arch/arm64/mm/mmu.c
> > @@ -370,6 +370,16 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
> > } while (pgdp++, addr = next, addr != end);
> > }
> >
> > +static phys_addr_t pgd_kernel_pgtable_alloc(int shift)
> > +{
> > + void *ptr = (void *)__get_free_page(PGALLOC_GFP);
> > + BUG_ON(!ptr);
> > +
> > + /* Ensure the zeroed page is visible to the page table walker */
> > + dsb(ishst);
> > + return __pa(ptr);
> > +}
> > +
> > static phys_addr_t pgd_pgtable_alloc(int shift)
> > {
> > void *ptr = (void *)__get_free_page(PGALLOC_GFP);
> > @@ -591,7 +601,7 @@ static int __init map_entry_trampoline(void)
> > /* Map only the text into the trampoline page table */
> > memset(tramp_pg_dir, 0, PGD_SIZE);
> > __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
> > - prot, pgd_pgtable_alloc, 0);
> > + prot, pgd_kernel_pgtable_alloc, 0);
> >
> > /* Map both the text and data into the kernel page table */
> > __set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
> > @@ -1067,7 +1077,8 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
> > flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
> >
> > __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
> > - size, PAGE_KERNEL, pgd_pgtable_alloc, flags);
> > + size, PAGE_KERNEL, pgd_kernel_pgtable_alloc,
> > + flags);
> >
> > return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
> > altmap, want_memblock);
> > --
> > 2.21.0.rc0.258.g878e2cd30e-goog
> >
^ permalink raw reply [flat|nested] 38+ messages in thread
* [PATCH v2 3/3] arm64: mm: enable per pmd page table lock
2019-02-18 23:13 ` [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables Yu Zhao
2019-02-18 23:13 ` [PATCH v2 2/3] arm64: mm: don't call page table ctors for init_mm Yu Zhao
@ 2019-02-18 23:13 ` Yu Zhao
2019-02-19 4:21 ` [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables Anshuman Khandual
` (2 subsequent siblings)
4 siblings, 0 replies; 38+ messages in thread
From: Yu Zhao @ 2019-02-18 23:13 UTC (permalink / raw)
To: Catalin Marinas, Will Deacon
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Mark Rutland,
Ard Biesheuvel, Chintan Pandya, Jun Yao, Laura Abbott,
linux-arm-kernel, linux-kernel, linux-arch, linux-mm, Yu Zhao
Switch from per mm_struct to per pmd page table lock by enabling
ARCH_ENABLE_SPLIT_PMD_PTLOCK. This provides better granularity for
large system.
I'm not sure if there is contention on mm->page_table_lock. Given
the option comes at no cost (apart from initializing more spin
locks), why not enable it now.
Signed-off-by: Yu Zhao <yuzhao@google.com>
---
arch/arm64/Kconfig | 3 +++
arch/arm64/include/asm/pgalloc.h | 12 +++++++++++-
arch/arm64/include/asm/tlb.h | 5 ++++-
3 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a4168d366127..8dbfa49d926c 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -872,6 +872,9 @@ config ARCH_WANT_HUGE_PMD_SHARE
config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+ def_bool y if PGTABLE_LEVELS > 2
+
config SECCOMP
bool "Enable seccomp to safely compute untrusted bytecode"
---help---
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 52fa47c73bf0..dabba4b2c61f 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -33,12 +33,22 @@
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return (pmd_t *)__get_free_page(PGALLOC_GFP);
+ struct page *page;
+
+ page = alloc_page(PGALLOC_GFP);
+ if (!page)
+ return NULL;
+ if (!pgtable_pmd_page_ctor(page)) {
+ __free_page(page);
+ return NULL;
+ }
+ return page_address(page);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
{
BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
+ pgtable_pmd_page_dtor(virt_to_page(pmdp));
free_page((unsigned long)pmdp);
}
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 106fdc951b6e..4e3becfed387 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -62,7 +62,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
unsigned long addr)
{
- tlb_remove_table(tlb, virt_to_page(pmdp));
+ struct page *page = virt_to_page(pmdp);
+
+ pgtable_pmd_page_dtor(page);
+ tlb_remove_table(tlb, page);
}
#endif
--
2.21.0.rc0.258.g878e2cd30e-goog
^ permalink raw reply related [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-18 23:13 ` [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables Yu Zhao
2019-02-18 23:13 ` [PATCH v2 2/3] arm64: mm: don't call page table ctors for init_mm Yu Zhao
2019-02-18 23:13 ` [PATCH v2 3/3] arm64: mm: enable per pmd page table lock Yu Zhao
@ 2019-02-19 4:21 ` Anshuman Khandual
2019-02-19 5:32 ` Yu Zhao
2019-02-26 15:12 ` Mark Rutland
2019-03-10 1:19 ` [PATCH v3 " Yu Zhao
4 siblings, 1 reply; 38+ messages in thread
From: Anshuman Khandual @ 2019-02-19 4:21 UTC (permalink / raw)
To: Yu Zhao, Catalin Marinas, Will Deacon
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Mark Rutland,
Ard Biesheuvel, Chintan Pandya, Jun Yao, Laura Abbott,
linux-arm-kernel, linux-kernel, linux-arch, linux-mm
On 02/19/2019 04:43 AM, Yu Zhao wrote:
> For pte page, use pgtable_page_ctor(); for pmd page, use
> pgtable_pmd_page_ctor() if not folded; and for the rest (pud,
> p4d and pgd), don't use any.
pgtable_page_ctor()/dtor() is not optional for any level page table page
as it determines the struct page state and zone statistics. We should not
skip it for any page table page. As stated before pgtable_pmd_page_ctor()
is not a replacement for pgtable_page_ctor().
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-19 4:21 ` [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables Anshuman Khandual
@ 2019-02-19 5:32 ` Yu Zhao
2019-02-19 6:17 ` Anshuman Khandual
2019-02-20 21:03 ` Matthew Wilcox
0 siblings, 2 replies; 38+ messages in thread
From: Yu Zhao @ 2019-02-19 5:32 UTC (permalink / raw)
To: Anshuman Khandual
Cc: Catalin Marinas, Will Deacon, Aneesh Kumar K . V, Andrew Morton,
Nick Piggin, Peter Zijlstra, Joel Fernandes, Kirill A . Shutemov,
Mark Rutland, Ard Biesheuvel, Chintan Pandya, Jun Yao,
Laura Abbott, linux-arm-kernel, linux-kernel, linux-arch,
linux-mm
On Tue, Feb 19, 2019 at 09:51:01AM +0530, Anshuman Khandual wrote:
>
>
> On 02/19/2019 04:43 AM, Yu Zhao wrote:
> > For pte page, use pgtable_page_ctor(); for pmd page, use
> > pgtable_pmd_page_ctor() if not folded; and for the rest (pud,
> > p4d and pgd), don't use any.
> pgtable_page_ctor()/dtor() is not optional for any level page table page
> as it determines the struct page state and zone statistics.
This is not true. pgtable_page_ctor() is only meant for user pte
page. The name isn't perfect (we named it this way before we had
split pmd page table lock, and never bothered to change it).
The commit cccd843f54be ("mm: mark pages in use for page tables")
clearly states so:
Note that only pages currently accounted as NR_PAGETABLES are
tracked as PageTable; this does not include pgd/p4d/pud/pmd pages.
I'm sure if we go back further, we can find similar stories: we
don't set PageTable on page tables other than pte; and we don't
account page tables other than pte. I don't have any objection if
you want change these two. But please make sure they are consistent
across all archs.
> We should not skip it for any page table page.
In fact, calling it on pmd/pud/p4d is peculiar, and may even be
considered wrong. AFAIK, no other arch does so.
> As stated before pgtable_pmd_page_ctor() is not a replacement for
> pgtable_page_ctor().
pgtable_pmd_page_ctor() must be used on user pmd. For kernel pmd,
it's okay to use pgtable_page_ctor() instead only because kernel
doesn't have thp.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-19 5:32 ` Yu Zhao
@ 2019-02-19 6:17 ` Anshuman Khandual
2019-02-19 22:28 ` Yu Zhao
2019-02-20 1:34 ` Matthew Wilcox
2019-02-20 21:03 ` Matthew Wilcox
1 sibling, 2 replies; 38+ messages in thread
From: Anshuman Khandual @ 2019-02-19 6:17 UTC (permalink / raw)
To: Yu Zhao
Cc: Catalin Marinas, Will Deacon, Aneesh Kumar K . V, Andrew Morton,
Nick Piggin, Peter Zijlstra, Joel Fernandes, Kirill A . Shutemov,
Mark Rutland, Ard Biesheuvel, Chintan Pandya, Jun Yao,
Laura Abbott, linux-arm-kernel, linux-kernel, linux-arch,
linux-mm, Matthew Wilcox
+ Matthew Wilcox
On 02/19/2019 11:02 AM, Yu Zhao wrote:
> On Tue, Feb 19, 2019 at 09:51:01AM +0530, Anshuman Khandual wrote:
>>
>>
>> On 02/19/2019 04:43 AM, Yu Zhao wrote:
>>> For pte page, use pgtable_page_ctor(); for pmd page, use
>>> pgtable_pmd_page_ctor() if not folded; and for the rest (pud,
>>> p4d and pgd), don't use any.
>> pgtable_page_ctor()/dtor() is not optional for any level page table page
>> as it determines the struct page state and zone statistics.
>
> This is not true. pgtable_page_ctor() is only meant for user pte
> page. The name isn't perfect (we named it this way before we had
> split pmd page table lock, and never bothered to change it).
>
> The commit cccd843f54be ("mm: mark pages in use for page tables")
> clearly states so:
> Note that only pages currently accounted as NR_PAGETABLES are
> tracked as PageTable; this does not include pgd/p4d/pud/pmd pages.
I think the commit is the following one and it does say so. But what is
the rationale of tagging only PTE page as PageTable and updating the zone
stat but not doing so for higher level page table pages ? Are not they
used as page table pages ? Should not they count towards NR_PAGETABLE ?
1d40a5ea01d53251c ("mm: mark pages in use for page tables")
>
> I'm sure if we go back further, we can find similar stories: we
> don't set PageTable on page tables other than pte; and we don't
> account page tables other than pte. I don't have any objection if
> you want change these two. But please make sure they are consistent
> across all archs.
pgtable_page_ctor/dtor() use across arch is not consistent and there is a need
for generalization which has been already acknowledged earlier. But for now we
can atleast fix this on arm64.
https://lore.kernel.org/lkml/1547619692-7946-1-git-send-email-anshuman.khandual@arm.com/
>
>> We should not skip it for any page table page.
>
> In fact, calling it on pmd/pud/p4d is peculiar, and may even be
> considered wrong. AFAIK, no other arch does so.
Why would it be considered wrong ? IIUC archs have their own understanding
of this and there are different implementations. But doing something for
PTE page and skipping for others is plain inconsistent.
>
>> As stated before pgtable_pmd_page_ctor() is not a replacement for
>> pgtable_page_ctor().
>
> pgtable_pmd_page_ctor() must be used on user pmd. For kernel pmd,
> it's okay to use pgtable_page_ctor() instead only because kernel
> doesn't have thp.
The only extra thing to be done for THP is initializing page->pmd_huge_pte
apart from calling pgtable_page_ctor(). Right not it just works on arm64
may be because page->pmd_huge_pte never gets accessed before it's init and
no path checks for it when not THP. Its better to init/reset pmd_huge_pte.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-19 6:17 ` Anshuman Khandual
@ 2019-02-19 22:28 ` Yu Zhao
2019-02-20 10:27 ` Anshuman Khandual
2019-02-20 1:34 ` Matthew Wilcox
1 sibling, 1 reply; 38+ messages in thread
From: Yu Zhao @ 2019-02-19 22:28 UTC (permalink / raw)
To: Anshuman Khandual
Cc: Catalin Marinas, Will Deacon, Aneesh Kumar K . V, Andrew Morton,
Nick Piggin, Peter Zijlstra, Joel Fernandes, Kirill A . Shutemov,
Mark Rutland, Ard Biesheuvel, Chintan Pandya, Jun Yao,
Laura Abbott, linux-arm-kernel, linux-kernel, linux-arch,
linux-mm, Matthew Wilcox
On Tue, Feb 19, 2019 at 11:47:12AM +0530, Anshuman Khandual wrote:
> + Matthew Wilcox
>
> On 02/19/2019 11:02 AM, Yu Zhao wrote:
> > On Tue, Feb 19, 2019 at 09:51:01AM +0530, Anshuman Khandual wrote:
> >>
> >>
> >> On 02/19/2019 04:43 AM, Yu Zhao wrote:
> >>> For pte page, use pgtable_page_ctor(); for pmd page, use
> >>> pgtable_pmd_page_ctor() if not folded; and for the rest (pud,
> >>> p4d and pgd), don't use any.
> >> pgtable_page_ctor()/dtor() is not optional for any level page table page
> >> as it determines the struct page state and zone statistics.
> >
> > This is not true. pgtable_page_ctor() is only meant for user pte
> > page. The name isn't perfect (we named it this way before we had
> > split pmd page table lock, and never bothered to change it).
> >
> > The commit cccd843f54be ("mm: mark pages in use for page tables")
> > clearly states so:
> > Note that only pages currently accounted as NR_PAGETABLES are
> > tracked as PageTable; this does not include pgd/p4d/pud/pmd pages.
>
> I think the commit is the following one and it does say so. But what is
> the rationale of tagging only PTE page as PageTable and updating the zone
> stat but not doing so for higher level page table pages ? Are not they
> used as page table pages ? Should not they count towards NR_PAGETABLE ?
>
> 1d40a5ea01d53251c ("mm: mark pages in use for page tables")
Well, I was just trying to clarify how the ctor is meant to be used.
The rational behind it is probably another topic.
For starters, the number of pmd/pud/p4d/pgd is at least two orders
of magnitude less than the number of pte, which makes them almost
negligible. And some archs use kmem for them, so it's infeasible to
SetPageTable on or account them in the way the ctor does on those
archs.
But, as I said, it's not something can't be changed. It's just not
the concern of this patch.
> >
> > I'm sure if we go back further, we can find similar stories: we
> > don't set PageTable on page tables other than pte; and we don't
> > account page tables other than pte. I don't have any objection if
> > you want change these two. But please make sure they are consistent
> > across all archs.
>
> pgtable_page_ctor/dtor() use across arch is not consistent and there is a need
> for generalization which has been already acknowledged earlier. But for now we
> can atleast fix this on arm64.
>
> https://lore.kernel.org/lkml/1547619692-7946-1-git-send-email-anshuman.khandual@arm.com/
This is again not true. Please stop making claims not backed up by
facts. And the link is completely irrelevant to the ctor.
I just checked *all* arches. Only four arches call the ctor outside
pte_alloc_one(). They are arm, arm64, ppc and s390. The last two do
so not because they want to SetPageTable on or account pmd/pud/p4d/
pgd, but because they have to work around something, as arm/arm64
do.
>
> >
> >> We should not skip it for any page table page.
> >
> > In fact, calling it on pmd/pud/p4d is peculiar, and may even be
> > considered wrong. AFAIK, no other arch does so.
>
> Why would it be considered wrong ? IIUC archs have their own understanding
> of this and there are different implementations. But doing something for
> PTE page and skipping for others is plain inconsistent.
Allocating memory that will never be used is wrong. Please look into
the ctor and find out what exactly it does under different configs.
And why I said "may"? Because we know there is only negligible number
of pmd/pud/p4d, so the memory allocated may be considered negligible
as well.
>
> >
> >> As stated before pgtable_pmd_page_ctor() is not a replacement for
> >> pgtable_page_ctor().
> >
> > pgtable_pmd_page_ctor() must be used on user pmd. For kernel pmd,
> > it's okay to use pgtable_page_ctor() instead only because kernel
> > doesn't have thp.
>
> The only extra thing to be done for THP is initializing page->pmd_huge_pte
> apart from calling pgtable_page_ctor(). Right not it just works on arm64
> may be because page->pmd_huge_pte never gets accessed before it's init and
> no path checks for it when not THP. Its better to init/reset pmd_huge_pte.
This is not the reason. Arm64 gets by with calling
pgtable_page_ctor() on pmd because it only does so on efi_mm. efi_mm
is not user mm, therefore doesn't involve thp.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-19 22:28 ` Yu Zhao
@ 2019-02-20 10:27 ` Anshuman Khandual
2019-02-20 12:24 ` Matthew Wilcox
2019-02-20 20:22 ` Yu Zhao
0 siblings, 2 replies; 38+ messages in thread
From: Anshuman Khandual @ 2019-02-20 10:27 UTC (permalink / raw)
To: Yu Zhao
Cc: Catalin Marinas, Will Deacon, Aneesh Kumar K . V, Andrew Morton,
Nick Piggin, Peter Zijlstra, Joel Fernandes, Kirill A . Shutemov,
Mark Rutland, Ard Biesheuvel, Chintan Pandya, Jun Yao,
Laura Abbott, linux-arm-kernel, linux-kernel, linux-arch,
linux-mm, Matthew Wilcox
On 02/20/2019 03:58 AM, Yu Zhao wrote:
> On Tue, Feb 19, 2019 at 11:47:12AM +0530, Anshuman Khandual wrote:
>> + Matthew Wilcox
>>
>> On 02/19/2019 11:02 AM, Yu Zhao wrote:
>>> On Tue, Feb 19, 2019 at 09:51:01AM +0530, Anshuman Khandual wrote:
>>>>
>>>>
>>>> On 02/19/2019 04:43 AM, Yu Zhao wrote:
>>>>> For pte page, use pgtable_page_ctor(); for pmd page, use
>>>>> pgtable_pmd_page_ctor() if not folded; and for the rest (pud,
>>>>> p4d and pgd), don't use any.
>>>> pgtable_page_ctor()/dtor() is not optional for any level page table page
>>>> as it determines the struct page state and zone statistics.
>>>
>>> This is not true. pgtable_page_ctor() is only meant for user pte
>>> page. The name isn't perfect (we named it this way before we had
>>> split pmd page table lock, and never bothered to change it).
>>>
>>> The commit cccd843f54be ("mm: mark pages in use for page tables")
>>> clearly states so:
>>> Note that only pages currently accounted as NR_PAGETABLES are
>>> tracked as PageTable; this does not include pgd/p4d/pud/pmd pages.
>>
>> I think the commit is the following one and it does say so. But what is
>> the rationale of tagging only PTE page as PageTable and updating the zone
>> stat but not doing so for higher level page table pages ? Are not they
>> used as page table pages ? Should not they count towards NR_PAGETABLE ?
>>
>> 1d40a5ea01d53251c ("mm: mark pages in use for page tables")
>
> Well, I was just trying to clarify how the ctor is meant to be used.
> The rational behind it is probably another topic.
>
> For starters, the number of pmd/pud/p4d/pgd is at least two orders
> of magnitude less than the number of pte, which makes them almost
> negligible. And some archs use kmem for them, so it's infeasible to
> SetPageTable on or account them in the way the ctor does on those
> archs.
>
I understand the kmem cases which are definitely problematic and should
be fixed. IIRC there is a mechanism to custom init pages allocated for
slab cache with a ctor function which in turn can call pgtable_page_ctor().
But destructor helper support for slab has been dropped I guess.
> But, as I said, it's not something can't be changed. It's just not
> the concern of this patch.
Using pgtable_pmd_page_ctor() during PMD level pgtable page allocation
as suggested in the patch breaks pmd_alloc_one() changes as per the
previous proposal. Hence we all would need some agreement here.
https://www.spinics.net/lists/arm-kernel/msg701960.html
We can still accommodate the split PMD ptlock feature in pmd_alloc_one().
A possible solution can be like this above and over the previous series.
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a4168d366127..c02abb2a69f7 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -9,6 +9,7 @@ config ARM64
select ACPI_SPCR_TABLE if ACPI
select ACPI_PPTT if ACPI
select ARCH_CLOCKSOURCE_DATA
+ select ARCH_ENABLE_SPLIT_PMD_PTLOCK if HAVE_ARCH_TRANSPARENT_HUGEPAGE
select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_DMA_COHERENT_TO_PFN
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index a02a4d1d967d..258e09fb3ce2 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -37,13 +37,29 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte);
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return (pmd_t *)pte_alloc_one_virt(mm);
+ pgtable_t ptr;
+
+ ptr = pte_alloc_one(mm);
+ if (!ptr)
+ return 0;
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
+ ptr->pmd_huge_pte = NULL;
+#endif
+ return (pmd_t *)page_to_virt(ptr);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
{
+ struct page *page;
+
BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
- pte_free(mm, virt_to_page(pmdp));
+ page = virt_to_page(pmdp);
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
+ VM_BUG_ON_PAGE(page->pmd_huge_pte, page);
+#endif
+ pte_free(mm, page);
}
>
>>>
>>> I'm sure if we go back further, we can find similar stories: we
>>> don't set PageTable on page tables other than pte; and we don't
>>> account page tables other than pte. I don't have any objection if
>>> you want change these two. But please make sure they are consistent
>>> across all archs.
>>
>> pgtable_page_ctor/dtor() use across arch is not consistent and there is a need
>> for generalization which has been already acknowledged earlier. But for now we
>> can atleast fix this on arm64.
>>
>> https://lore.kernel.org/lkml/1547619692-7946-1-git-send-email-anshuman.khandual@arm.com/
>
> This is again not true. Please stop making claims not backed up by
> facts. And the link is completely irrelevant to the ctor.
>
> I just checked *all* arches. Only four arches call the ctor outside
> pte_alloc_one(). They are arm, arm64, ppc and s390. The last two do
> so not because they want to SetPageTable on or account pmd/pud/p4d/
> pgd, but because they have to work around something, as arm/arm64
> do.
That reaffirms the fact that pgtable_page_ctor()/dtor() are getting used
not in a consistent manner.
>
>>
>>>
>>>> We should not skip it for any page table page.
>>>
>>> In fact, calling it on pmd/pud/p4d is peculiar, and may even be
>>> considered wrong. AFAIK, no other arch does so.
>>
>> Why would it be considered wrong ? IIUC archs have their own understanding
>> of this and there are different implementations. But doing something for
>> PTE page and skipping for others is plain inconsistent.
>
> Allocating memory that will never be used is wrong. Please look into
> the ctor and find out what exactly it does under different configs.
Are you referring to ptlock_init() --> ptlock_alloc() triggered spinlock_t
allocations with USE_SPLIT_PTE_PTLOCKS and ALLOC_SPLIT_PTLOCKS.
>
> And why I said "may"? Because we know there is only negligible number
> of pmd/pud/p4d, so the memory allocated may be considered negligible
> as well.
Okay.
^ permalink raw reply related [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-20 10:27 ` Anshuman Khandual
@ 2019-02-20 12:24 ` Matthew Wilcox
2019-02-20 20:22 ` Yu Zhao
1 sibling, 0 replies; 38+ messages in thread
From: Matthew Wilcox @ 2019-02-20 12:24 UTC (permalink / raw)
To: Anshuman Khandual
Cc: Yu Zhao, Catalin Marinas, Will Deacon, Aneesh Kumar K . V,
Andrew Morton, Nick Piggin, Peter Zijlstra, Joel Fernandes,
Kirill A . Shutemov, Mark Rutland, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm
On Wed, Feb 20, 2019 at 03:57:59PM +0530, Anshuman Khandual wrote:
> On 02/20/2019 03:58 AM, Yu Zhao wrote:
> > On Tue, Feb 19, 2019 at 11:47:12AM +0530, Anshuman Khandual wrote:
> >> On 02/19/2019 11:02 AM, Yu Zhao wrote:
> >>> On Tue, Feb 19, 2019 at 09:51:01AM +0530, Anshuman Khandual wrote:
> >>>> On 02/19/2019 04:43 AM, Yu Zhao wrote:
> >>>>> For pte page, use pgtable_page_ctor(); for pmd page, use
> >>>>> pgtable_pmd_page_ctor() if not folded; and for the rest (pud,
> >>>>> p4d and pgd), don't use any.
> >>>> pgtable_page_ctor()/dtor() is not optional for any level page table page
> >>>> as it determines the struct page state and zone statistics.
> >>>
> >>> This is not true. pgtable_page_ctor() is only meant for user pte
> >>> page. The name isn't perfect (we named it this way before we had
> >>> split pmd page table lock, and never bothered to change it).
> >>>
> >>> The commit cccd843f54be ("mm: mark pages in use for page tables")
> >>> clearly states so:
> >>> Note that only pages currently accounted as NR_PAGETABLES are
> >>> tracked as PageTable; this does not include pgd/p4d/pud/pmd pages.
> >>
> >> I think the commit is the following one and it does say so. But what is
> >> the rationale of tagging only PTE page as PageTable and updating the zone
> >> stat but not doing so for higher level page table pages ? Are not they
> >> used as page table pages ? Should not they count towards NR_PAGETABLE ?
> >>
> >> 1d40a5ea01d53251c ("mm: mark pages in use for page tables")
> >
> > Well, I was just trying to clarify how the ctor is meant to be used.
> > The rational behind it is probably another topic.
> >
> > For starters, the number of pmd/pud/p4d/pgd is at least two orders
> > of magnitude less than the number of pte, which makes them almost
> > negligible. And some archs use kmem for them, so it's infeasible to
> > SetPageTable on or account them in the way the ctor does on those
> > archs.
>
> I understand the kmem cases which are definitely problematic and should
> be fixed. IIRC there is a mechanism to custom init pages allocated for
> slab cache with a ctor function which in turn can call pgtable_page_ctor().
> But destructor helper support for slab has been dropped I guess.
You can't put a spinlock in the struct page if the page is allocated
through slab. Slab uses basically all of struct page for its own
purposes. I tried to make that clear with the new layout of struct
page where everything's in a union discriminated by what the page is
allocated for.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-20 10:27 ` Anshuman Khandual
2019-02-20 12:24 ` Matthew Wilcox
@ 2019-02-20 20:22 ` Yu Zhao
2019-02-20 20:59 ` Matthew Wilcox
1 sibling, 1 reply; 38+ messages in thread
From: Yu Zhao @ 2019-02-20 20:22 UTC (permalink / raw)
To: Anshuman Khandual
Cc: Catalin Marinas, Will Deacon, Aneesh Kumar K . V, Andrew Morton,
Nick Piggin, Peter Zijlstra, Joel Fernandes, Kirill A . Shutemov,
Mark Rutland, Ard Biesheuvel, Chintan Pandya, Jun Yao,
Laura Abbott, linux-arm-kernel, linux-kernel, linux-arch,
linux-mm, Matthew Wilcox
On Wed, Feb 20, 2019 at 03:57:59PM +0530, Anshuman Khandual wrote:
>
>
> On 02/20/2019 03:58 AM, Yu Zhao wrote:
> > On Tue, Feb 19, 2019 at 11:47:12AM +0530, Anshuman Khandual wrote:
> >> + Matthew Wilcox
> >>
> >> On 02/19/2019 11:02 AM, Yu Zhao wrote:
> >>> On Tue, Feb 19, 2019 at 09:51:01AM +0530, Anshuman Khandual wrote:
> >>>>
> >>>>
> >>>> On 02/19/2019 04:43 AM, Yu Zhao wrote:
> >>>>> For pte page, use pgtable_page_ctor(); for pmd page, use
> >>>>> pgtable_pmd_page_ctor() if not folded; and for the rest (pud,
> >>>>> p4d and pgd), don't use any.
> >>>> pgtable_page_ctor()/dtor() is not optional for any level page table page
> >>>> as it determines the struct page state and zone statistics.
> >>>
> >>> This is not true. pgtable_page_ctor() is only meant for user pte
> >>> page. The name isn't perfect (we named it this way before we had
> >>> split pmd page table lock, and never bothered to change it).
> >>>
> >>> The commit cccd843f54be ("mm: mark pages in use for page tables")
> >>> clearly states so:
> >>> Note that only pages currently accounted as NR_PAGETABLES are
> >>> tracked as PageTable; this does not include pgd/p4d/pud/pmd pages.
> >>
> >> I think the commit is the following one and it does say so. But what is
> >> the rationale of tagging only PTE page as PageTable and updating the zone
> >> stat but not doing so for higher level page table pages ? Are not they
> >> used as page table pages ? Should not they count towards NR_PAGETABLE ?
> >>
> >> 1d40a5ea01d53251c ("mm: mark pages in use for page tables")
> >
> > Well, I was just trying to clarify how the ctor is meant to be used.
> > The rational behind it is probably another topic.
> >
> > For starters, the number of pmd/pud/p4d/pgd is at least two orders
> > of magnitude less than the number of pte, which makes them almost
> > negligible. And some archs use kmem for them, so it's infeasible to
> > SetPageTable on or account them in the way the ctor does on those
> > archs.
> >
>
> I understand the kmem cases which are definitely problematic and should
> be fixed. IIRC there is a mechanism to custom init pages allocated for
> slab cache with a ctor function which in turn can call pgtable_page_ctor().
> But destructor helper support for slab has been dropped I guess.
>
>
> > But, as I said, it's not something can't be changed. It's just not
> > the concern of this patch.
>
> Using pgtable_pmd_page_ctor() during PMD level pgtable page allocation
> as suggested in the patch breaks pmd_alloc_one() changes as per the
> previous proposal. Hence we all would need some agreement here.
>
> https://www.spinics.net/lists/arm-kernel/msg701960.html
A proposal that requires all page tables to go through a same set of
ctors on all archs is not only inefficient (for kernel page tables)
but also infeasible (for arches use kmem for page tables). I've
explained this clearly.
The generalized page table functions must recognize the differences
on different levels and between user and kernel page tables, and
provide unified api that is capable of handling the differences.
The change below is not helping at all.
>
> We can still accommodate the split PMD ptlock feature in pmd_alloc_one().
> A possible solution can be like this above and over the previous series.
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index a4168d366127..c02abb2a69f7 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -9,6 +9,7 @@ config ARM64
> select ACPI_SPCR_TABLE if ACPI
> select ACPI_PPTT if ACPI
> select ARCH_CLOCKSOURCE_DATA
> + select ARCH_ENABLE_SPLIT_PMD_PTLOCK if HAVE_ARCH_TRANSPARENT_HUGEPAGE
> select ARCH_HAS_DEBUG_VIRTUAL
> select ARCH_HAS_DEVMEM_IS_ALLOWED
> select ARCH_HAS_DMA_COHERENT_TO_PFN
> diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
> index a02a4d1d967d..258e09fb3ce2 100644
> --- a/arch/arm64/include/asm/pgalloc.h
> +++ b/arch/arm64/include/asm/pgalloc.h
> @@ -37,13 +37,29 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte);
>
> static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
> {
> - return (pmd_t *)pte_alloc_one_virt(mm);
> + pgtable_t ptr;
> +
> + ptr = pte_alloc_one(mm);
> + if (!ptr)
> + return 0;
> +
> +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
> + ptr->pmd_huge_pte = NULL;
> +#endif
> + return (pmd_t *)page_to_virt(ptr);
> }
>
> static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
> {
> + struct page *page;
> +
> BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
> - pte_free(mm, virt_to_page(pmdp));
> + page = virt_to_page(pmdp);
> +
> +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
> + VM_BUG_ON_PAGE(page->pmd_huge_pte, page);
> +#endif
> + pte_free(mm, page);
> }
>
>
> >
> >>>
> >>> I'm sure if we go back further, we can find similar stories: we
> >>> don't set PageTable on page tables other than pte; and we don't
> >>> account page tables other than pte. I don't have any objection if
> >>> you want change these two. But please make sure they are consistent
> >>> across all archs.
> >>
> >> pgtable_page_ctor/dtor() use across arch is not consistent and there is a need
> >> for generalization which has been already acknowledged earlier. But for now we
> >> can atleast fix this on arm64.
> >>
> >> https://lore.kernel.org/lkml/1547619692-7946-1-git-send-email-anshuman.khandual@arm.com/
> >
> > This is again not true. Please stop making claims not backed up by
> > facts. And the link is completely irrelevant to the ctor.
> >
> > I just checked *all* arches. Only four arches call the ctor outside
> > pte_alloc_one(). They are arm, arm64, ppc and s390. The last two do
> > so not because they want to SetPageTable on or account pmd/pud/p4d/
> > pgd, but because they have to work around something, as arm/arm64
> > do.
>
> That reaffirms the fact that pgtable_page_ctor()/dtor() are getting used
> not in a consistent manner.
Now it's getting absurd. I'll just stop before this turns into
complete nonsense.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-20 20:22 ` Yu Zhao
@ 2019-02-20 20:59 ` Matthew Wilcox
0 siblings, 0 replies; 38+ messages in thread
From: Matthew Wilcox @ 2019-02-20 20:59 UTC (permalink / raw)
To: Yu Zhao
Cc: Anshuman Khandual, Catalin Marinas, Will Deacon,
Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Mark Rutland,
Ard Biesheuvel, Chintan Pandya, Jun Yao, Laura Abbott,
linux-arm-kernel, linux-kernel, linux-arch, linux-mm
On Wed, Feb 20, 2019 at 01:22:44PM -0700, Yu Zhao wrote:
> On Wed, Feb 20, 2019 at 03:57:59PM +0530, Anshuman Khandual wrote:
> > Using pgtable_pmd_page_ctor() during PMD level pgtable page allocation
> > as suggested in the patch breaks pmd_alloc_one() changes as per the
> > previous proposal. Hence we all would need some agreement here.
> >
> > https://www.spinics.net/lists/arm-kernel/msg701960.html
>
> A proposal that requires all page tables to go through a same set of
> ctors on all archs is not only inefficient (for kernel page tables)
> but also infeasible (for arches use kmem for page tables). I've
> explained this clearly.
>
> The generalized page table functions must recognize the differences
> on different levels and between user and kernel page tables, and
> provide unified api that is capable of handling the differences.
The two architectures I'm aware of (s390 and power) which use sub-page
allocations for page tables do so by allocating entire pages and then
implementing their own allocators. It shouldn't be a huge problem to
use a ctor for the pages. We can probably even implement a dtor for them.
Oh, another corner-case I've just remembered is x86-32's PAE with four
8-byte entries in the PGD. That should also go away and be replaced
with a shared implementation of sub-page allocations which can also be
marked as PageTable.
Ideally PTEs, PMDs, etc, etc would all be accounted to the individual
processes causing them to be allocated. This isn't really feasible
with the x86 PGD; by definition there's only one per process. I'm OK
with failing to account this 32-byte allocation to the task though.
So maybe the pgd_cache can remain separate from the hypothetical unified
ppc/s390 code.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-19 6:17 ` Anshuman Khandual
2019-02-19 22:28 ` Yu Zhao
@ 2019-02-20 1:34 ` Matthew Wilcox
2019-02-20 3:20 ` Anshuman Khandual
1 sibling, 1 reply; 38+ messages in thread
From: Matthew Wilcox @ 2019-02-20 1:34 UTC (permalink / raw)
To: Anshuman Khandual
Cc: Yu Zhao, Catalin Marinas, Will Deacon, Aneesh Kumar K . V,
Andrew Morton, Nick Piggin, Peter Zijlstra, Joel Fernandes,
Kirill A . Shutemov, Mark Rutland, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm
On Tue, Feb 19, 2019 at 11:47:12AM +0530, Anshuman Khandual wrote:
> + Matthew Wilcox
> On 02/19/2019 11:02 AM, Yu Zhao wrote:
> > On Tue, Feb 19, 2019 at 09:51:01AM +0530, Anshuman Khandual wrote:
> >>
> >>
> >> On 02/19/2019 04:43 AM, Yu Zhao wrote:
> >>> For pte page, use pgtable_page_ctor(); for pmd page, use
> >>> pgtable_pmd_page_ctor() if not folded; and for the rest (pud,
> >>> p4d and pgd), don't use any.
> >> pgtable_page_ctor()/dtor() is not optional for any level page table page
> >> as it determines the struct page state and zone statistics.
> >
> > This is not true. pgtable_page_ctor() is only meant for user pte
> > page. The name isn't perfect (we named it this way before we had
> > split pmd page table lock, and never bothered to change it).
> >
> > The commit cccd843f54be ("mm: mark pages in use for page tables")
Where did you get that commit ID from? In Linus' tree, it's
1d40a5ea01d53251c23c7be541d3f4a656cfc537
> > clearly states so:
> > Note that only pages currently accounted as NR_PAGETABLES are
> > tracked as PageTable; this does not include pgd/p4d/pud/pmd pages.
>
> I think the commit is the following one and it does say so. But what is
> the rationale of tagging only PTE page as PageTable and updating the zone
> stat but not doing so for higher level page table pages ? Are not they
> used as page table pages ? Should not they count towards NR_PAGETABLE ?
>
> 1d40a5ea01d53251c ("mm: mark pages in use for page tables")
I think they should all be accounted towards NR_PAGETABLE and marked
as being PageTable. Somebody needs to make the case for that and
send the patches. That patch even says that there should be follow-up
patches to do that. I've been a little busy and haven't got back to it.
I thought you said you were going to do it.
> pgtable_page_ctor/dtor() use across arch is not consistent and there is a need
> for generalization which has been already acknowledged earlier. But for now we
> can atleast fix this on arm64.
>
> https://lore.kernel.org/lkml/1547619692-7946-1-git-send-email-anshuman.khandual@arm.com/
... were you not listening when you were told that was completely
inadequate?
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-20 1:34 ` Matthew Wilcox
@ 2019-02-20 3:20 ` Anshuman Khandual
0 siblings, 0 replies; 38+ messages in thread
From: Anshuman Khandual @ 2019-02-20 3:20 UTC (permalink / raw)
To: Matthew Wilcox
Cc: Yu Zhao, Catalin Marinas, Will Deacon, Aneesh Kumar K . V,
Andrew Morton, Nick Piggin, Peter Zijlstra, Joel Fernandes,
Kirill A . Shutemov, Mark Rutland, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm
On 02/20/2019 07:04 AM, Matthew Wilcox wrote:
> On Tue, Feb 19, 2019 at 11:47:12AM +0530, Anshuman Khandual wrote:
>> + Matthew Wilcox
>> On 02/19/2019 11:02 AM, Yu Zhao wrote:
>>> On Tue, Feb 19, 2019 at 09:51:01AM +0530, Anshuman Khandual wrote:
>>>>
>>>>
>>>> On 02/19/2019 04:43 AM, Yu Zhao wrote:
>>>>> For pte page, use pgtable_page_ctor(); for pmd page, use
>>>>> pgtable_pmd_page_ctor() if not folded; and for the rest (pud,
>>>>> p4d and pgd), don't use any.
>>>> pgtable_page_ctor()/dtor() is not optional for any level page table page
>>>> as it determines the struct page state and zone statistics.
>>>
>>> This is not true. pgtable_page_ctor() is only meant for user pte
>>> page. The name isn't perfect (we named it this way before we had
>>> split pmd page table lock, and never bothered to change it).
>>>
>>> The commit cccd843f54be ("mm: mark pages in use for page tables")
>
> Where did you get that commit ID from? In Linus' tree, it's
> 1d40a5ea01d53251c23c7be541d3f4a656cfc537
>
>>> clearly states so:
>>> Note that only pages currently accounted as NR_PAGETABLES are
>>> tracked as PageTable; this does not include pgd/p4d/pud/pmd pages.
>>
>> I think the commit is the following one and it does say so. But what is
>> the rationale of tagging only PTE page as PageTable and updating the zone
>> stat but not doing so for higher level page table pages ? Are not they
>> used as page table pages ? Should not they count towards NR_PAGETABLE ?
>>
>> 1d40a5ea01d53251c ("mm: mark pages in use for page tables")
>
> I think they should all be accounted towards NR_PAGETABLE and marked
> as being PageTable. Somebody needs to make the case for that and
Okay so we agree on the applicability part.
> send the patches. That patch even says that there should be follow-up
> patches to do that. I've been a little busy and haven't got back to it.
> I thought you said you were going to do it.
This is very much arch specific. pgtabe_page_ctor()/dtor() are not uniformly
called for all page table level allocations (user or kernel) across different
archs. Yes I am planning to make generic page table allocation functions for
all levels which archs can choose to use. But for now I have a series to fix
the situation on arm64.
>
>> pgtable_page_ctor/dtor() use across arch is not consistent and there is a need
>> for generalization which has been already acknowledged earlier. But for now we
>> can atleast fix this on arm64.
>>
>> https://lore.kernel.org/lkml/1547619692-7946-1-git-send-email-anshuman.khandual@arm.com/
>
> ... were you not listening when you were told that was completely
> inadequate?
Agreed. The discussion on the thread made it clear that the above patch was
inadequate. What I was trying to point out (probably not very clearly) that
there is a need for larger generalization/consolidation on page table page
allocation front including but might not be limited to allocation flag for
user/kernel page table, standard allocation functions etc. The very idea of
quoting the above URL here was to bring attention to the fact that different
archs are doing these allocations differently already.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-19 5:32 ` Yu Zhao
2019-02-19 6:17 ` Anshuman Khandual
@ 2019-02-20 21:03 ` Matthew Wilcox
1 sibling, 0 replies; 38+ messages in thread
From: Matthew Wilcox @ 2019-02-20 21:03 UTC (permalink / raw)
To: Yu Zhao
Cc: Anshuman Khandual, Catalin Marinas, Will Deacon,
Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Mark Rutland,
Ard Biesheuvel, Chintan Pandya, Jun Yao, Laura Abbott,
linux-arm-kernel, linux-kernel, linux-arch, linux-mm
On Mon, Feb 18, 2019 at 10:32:05PM -0700, Yu Zhao wrote:
> pgtable_pmd_page_ctor() must be used on user pmd. For kernel pmd,
> it's okay to use pgtable_page_ctor() instead only because kernel
> doesn't have thp.
I'm not sure that's true. I think you can create THPs in vmalloc
these days. See HAVE_ARCH_HUGE_VMAP which is supported by arm64.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-18 23:13 ` [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables Yu Zhao
` (2 preceding siblings ...)
2019-02-19 4:21 ` [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables Anshuman Khandual
@ 2019-02-26 15:12 ` Mark Rutland
2019-03-09 4:01 ` Yu Zhao
2019-03-10 1:19 ` [PATCH v3 " Yu Zhao
4 siblings, 1 reply; 38+ messages in thread
From: Mark Rutland @ 2019-02-26 15:12 UTC (permalink / raw)
To: Yu Zhao
Cc: Catalin Marinas, Will Deacon, Aneesh Kumar K . V, Andrew Morton,
Nick Piggin, Peter Zijlstra, Joel Fernandes, Kirill A . Shutemov,
Ard Biesheuvel, Chintan Pandya, Jun Yao, Laura Abbott,
linux-arm-kernel, linux-kernel, linux-arch, linux-mm
Hi,
On Mon, Feb 18, 2019 at 04:13:17PM -0700, Yu Zhao wrote:
> For pte page, use pgtable_page_ctor(); for pmd page, use
> pgtable_pmd_page_ctor() if not folded; and for the rest (pud,
> p4d and pgd), don't use any.
>
> Signed-off-by: Yu Zhao <yuzhao@google.com>
> ---
> arch/arm64/mm/mmu.c | 33 +++++++++++++++++++++------------
> 1 file changed, 21 insertions(+), 12 deletions(-)
[...]
> -static phys_addr_t pgd_pgtable_alloc(void)
> +static phys_addr_t pgd_pgtable_alloc(int shift)
> {
> void *ptr = (void *)__get_free_page(PGALLOC_GFP);
> - if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
> - BUG();
> + BUG_ON(!ptr);
> +
> + /*
> + * Initialize page table locks in case later we need to
> + * call core mm functions like apply_to_page_range() on
> + * this pre-allocated page table.
> + */
> + if (shift == PAGE_SHIFT)
> + BUG_ON(!pgtable_page_ctor(virt_to_page(ptr)));
> + else if (shift == PMD_SHIFT && PMD_SHIFT != PUD_SHIFT)
> + BUG_ON(!pgtable_pmd_page_ctor(virt_to_page(ptr)));
IIUC, this is for nopmd kernels, where we only have real PGD and PTE
levels of table. From my PoV, that would be clearer if we did:
else if (shift == PMD_SHIFT && !is_defined(__PAGETABLE_PMD_FOLDED))
... though IMO it would be a bit nicer if the generic
pgtable_pmd_page_ctor() were nop'd out for __PAGETABLE_PMD_FOLDED
builds, so that callers don't have to be aware of folding.
I couldn't think of a nicer way of distinguishing levels of table, and
having separate function pointers for each level seems over-the-top, so
otehr than that this looks good to me.
Assuming you're happy with the above change:
Acked-by: Mark Rutland <mark.rutland@arm.com>
Thanks,
Mark.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-26 15:12 ` Mark Rutland
@ 2019-03-09 4:01 ` Yu Zhao
0 siblings, 0 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-09 4:01 UTC (permalink / raw)
To: Mark Rutland
Cc: Catalin Marinas, Will Deacon, Aneesh Kumar K . V, Andrew Morton,
Nick Piggin, Peter Zijlstra, Joel Fernandes, Kirill A . Shutemov,
Ard Biesheuvel, Chintan Pandya, Jun Yao, Laura Abbott,
linux-arm-kernel, linux-kernel, linux-arch, linux-mm
On Tue, Feb 26, 2019 at 03:12:31PM +0000, Mark Rutland wrote:
> Hi,
>
> On Mon, Feb 18, 2019 at 04:13:17PM -0700, Yu Zhao wrote:
> > For pte page, use pgtable_page_ctor(); for pmd page, use
> > pgtable_pmd_page_ctor() if not folded; and for the rest (pud,
> > p4d and pgd), don't use any.
> >
> > Signed-off-by: Yu Zhao <yuzhao@google.com>
> > ---
> > arch/arm64/mm/mmu.c | 33 +++++++++++++++++++++------------
> > 1 file changed, 21 insertions(+), 12 deletions(-)
>
> [...]
>
> > -static phys_addr_t pgd_pgtable_alloc(void)
> > +static phys_addr_t pgd_pgtable_alloc(int shift)
> > {
> > void *ptr = (void *)__get_free_page(PGALLOC_GFP);
> > - if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
> > - BUG();
> > + BUG_ON(!ptr);
> > +
> > + /*
> > + * Initialize page table locks in case later we need to
> > + * call core mm functions like apply_to_page_range() on
> > + * this pre-allocated page table.
> > + */
> > + if (shift == PAGE_SHIFT)
> > + BUG_ON(!pgtable_page_ctor(virt_to_page(ptr)));
> > + else if (shift == PMD_SHIFT && PMD_SHIFT != PUD_SHIFT)
> > + BUG_ON(!pgtable_pmd_page_ctor(virt_to_page(ptr)));
>
> IIUC, this is for nopmd kernels, where we only have real PGD and PTE
> levels of table. From my PoV, that would be clearer if we did:
>
> else if (shift == PMD_SHIFT && !is_defined(__PAGETABLE_PMD_FOLDED))
>
> ... though IMO it would be a bit nicer if the generic
> pgtable_pmd_page_ctor() were nop'd out for __PAGETABLE_PMD_FOLDED
> builds, so that callers don't have to be aware of folding.
Agreed. Will make pgtable_pmd_page_ctor() nop when pmd is folded.
> I couldn't think of a nicer way of distinguishing levels of table, and
> having separate function pointers for each level seems over-the-top, so
> otehr than that this looks good to me.
>
> Assuming you're happy with the above change:
>
> Acked-by: Mark Rutland <mark.rutland@arm.com>
>
> Thanks,
> Mark.
^ permalink raw reply [flat|nested] 38+ messages in thread
* [PATCH v3 1/3] arm64: mm: use appropriate ctors for page tables
2019-02-18 23:13 ` [PATCH v2 1/3] arm64: mm: use appropriate ctors for page tables Yu Zhao
` (3 preceding siblings ...)
2019-02-26 15:12 ` Mark Rutland
@ 2019-03-10 1:19 ` Yu Zhao
2019-03-10 1:19 ` [PATCH v3 2/3] arm64: mm: don't call page table ctors for init_mm Yu Zhao
` (3 more replies)
4 siblings, 4 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-10 1:19 UTC (permalink / raw)
To: Catalin Marinas, Will Deacon, Mark Rutland
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm, Yu Zhao
For pte page, use pgtable_page_ctor(); for pmd page, use
pgtable_pmd_page_ctor(); and for the rest (pud, p4d and pgd),
don't use any.
For now, we don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK and
pgtable_pmd_page_ctor() is a nop. When we do in patch 3, we
make sure pmd is not folded so we won't mistakenly call
pgtable_pmd_page_ctor() on pud or p4d.
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Yu Zhao <yuzhao@google.com>
---
arch/arm64/mm/mmu.c | 36 ++++++++++++++++++++++++------------
1 file changed, 24 insertions(+), 12 deletions(-)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index b6f5aa52ac67..f704b291f2c5 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -98,7 +98,7 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
}
EXPORT_SYMBOL(phys_mem_access_prot);
-static phys_addr_t __init early_pgtable_alloc(void)
+static phys_addr_t __init early_pgtable_alloc(int shift)
{
phys_addr_t phys;
void *ptr;
@@ -173,7 +173,7 @@ static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long next;
@@ -183,7 +183,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
if (pmd_none(pmd)) {
phys_addr_t pte_phys;
BUG_ON(!pgtable_alloc);
- pte_phys = pgtable_alloc();
+ pte_phys = pgtable_alloc(PAGE_SHIFT);
__pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
pmd = READ_ONCE(*pmdp);
}
@@ -207,7 +207,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void), int flags)
+ phys_addr_t (*pgtable_alloc)(int), int flags)
{
unsigned long next;
pmd_t *pmdp;
@@ -245,7 +245,7 @@ static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void), int flags)
+ phys_addr_t (*pgtable_alloc)(int), int flags)
{
unsigned long next;
pud_t pud = READ_ONCE(*pudp);
@@ -257,7 +257,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
if (pud_none(pud)) {
phys_addr_t pmd_phys;
BUG_ON(!pgtable_alloc);
- pmd_phys = pgtable_alloc();
+ pmd_phys = pgtable_alloc(PMD_SHIFT);
__pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
pud = READ_ONCE(*pudp);
}
@@ -293,7 +293,7 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,
static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long next;
@@ -303,7 +303,7 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
if (pgd_none(pgd)) {
phys_addr_t pud_phys;
BUG_ON(!pgtable_alloc);
- pud_phys = pgtable_alloc();
+ pud_phys = pgtable_alloc(PUD_SHIFT);
__pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE);
pgd = READ_ONCE(*pgdp);
}
@@ -344,7 +344,7 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long addr, length, end, next;
@@ -370,11 +370,23 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
} while (pgdp++, addr = next, addr != end);
}
-static phys_addr_t pgd_pgtable_alloc(void)
+static phys_addr_t pgd_pgtable_alloc(int shift)
{
void *ptr = (void *)__get_free_page(PGALLOC_GFP);
- if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
- BUG();
+ BUG_ON(!ptr);
+
+ /*
+ * Call proper page table ctor in case later we need to
+ * call core mm functions like apply_to_page_range() on
+ * this pre-allocated page table.
+ *
+ * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is
+ * folded, and if so pgtable_pmd_page_ctor() becomes nop.
+ */
+ if (shift == PAGE_SHIFT)
+ BUG_ON(!pgtable_page_ctor(virt_to_page(ptr)));
+ else if (shift == PMD_SHIFT)
+ BUG_ON(!pgtable_pmd_page_ctor(virt_to_page(ptr)));
/* Ensure the zeroed page is visible to the page table walker */
dsb(ishst);
--
2.21.0.360.g471c308f928-goog
^ permalink raw reply related [flat|nested] 38+ messages in thread
* [PATCH v3 2/3] arm64: mm: don't call page table ctors for init_mm
2019-03-10 1:19 ` [PATCH v3 " Yu Zhao
@ 2019-03-10 1:19 ` Yu Zhao
2019-03-10 1:19 ` [PATCH v3 3/3] arm64: mm: enable per pmd page table lock Yu Zhao
` (2 subsequent siblings)
3 siblings, 0 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-10 1:19 UTC (permalink / raw)
To: Catalin Marinas, Will Deacon, Mark Rutland
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm, Yu Zhao
init_mm doesn't require page table lock to be initialized at
any level. Add a separate page table allocator for it, and the
new one skips page table ctors.
The ctors allocate memory when ALLOC_SPLIT_PTLOCKS is set. Not
calling them avoids memory leak in case we call pte_free_kernel()
on init_mm.
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Yu Zhao <yuzhao@google.com>
---
arch/arm64/mm/mmu.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index f704b291f2c5..d1dc2a2777aa 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -370,6 +370,16 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
} while (pgdp++, addr = next, addr != end);
}
+static phys_addr_t pgd_kernel_pgtable_alloc(int shift)
+{
+ void *ptr = (void *)__get_free_page(PGALLOC_GFP);
+ BUG_ON(!ptr);
+
+ /* Ensure the zeroed page is visible to the page table walker */
+ dsb(ishst);
+ return __pa(ptr);
+}
+
static phys_addr_t pgd_pgtable_alloc(int shift)
{
void *ptr = (void *)__get_free_page(PGALLOC_GFP);
@@ -594,7 +604,7 @@ static int __init map_entry_trampoline(void)
/* Map only the text into the trampoline page table */
memset(tramp_pg_dir, 0, PGD_SIZE);
__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
- prot, pgd_pgtable_alloc, 0);
+ prot, pgd_kernel_pgtable_alloc, 0);
/* Map both the text and data into the kernel page table */
__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
@@ -1070,7 +1080,8 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
- size, PAGE_KERNEL, pgd_pgtable_alloc, flags);
+ size, PAGE_KERNEL, pgd_kernel_pgtable_alloc,
+ flags);
return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
altmap, want_memblock);
--
2.21.0.360.g471c308f928-goog
^ permalink raw reply related [flat|nested] 38+ messages in thread
* [PATCH v3 3/3] arm64: mm: enable per pmd page table lock
2019-03-10 1:19 ` [PATCH v3 " Yu Zhao
2019-03-10 1:19 ` [PATCH v3 2/3] arm64: mm: don't call page table ctors for init_mm Yu Zhao
@ 2019-03-10 1:19 ` Yu Zhao
2019-03-11 8:28 ` Anshuman Khandual
2019-03-11 12:12 ` Mark Rutland
2019-03-11 7:45 ` [PATCH v3 1/3] arm64: mm: use appropriate ctors for page tables Anshuman Khandual
2019-03-12 0:57 ` [PATCH v4 1/4] " Yu Zhao
3 siblings, 2 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-10 1:19 UTC (permalink / raw)
To: Catalin Marinas, Will Deacon, Mark Rutland
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm, Yu Zhao
Switch from per mm_struct to per pmd page table lock by enabling
ARCH_ENABLE_SPLIT_PMD_PTLOCK. This provides better granularity for
large system.
I'm not sure if there is contention on mm->page_table_lock. Given
the option comes at no cost (apart from initializing more spin
locks), why not enable it now.
We only do so when pmd is not folded, so we don't mistakenly call
pgtable_pmd_page_ctor() on pud or p4d in pgd_pgtable_alloc(). (We
check shift against PMD_SHIFT, which is same as PUD_SHIFT when pmd
is folded).
Signed-off-by: Yu Zhao <yuzhao@google.com>
---
arch/arm64/Kconfig | 3 +++
arch/arm64/include/asm/pgalloc.h | 12 +++++++++++-
arch/arm64/include/asm/tlb.h | 5 ++++-
3 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index cfbf307d6dc4..a3b1b789f766 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -872,6 +872,9 @@ config ARCH_WANT_HUGE_PMD_SHARE
config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+ def_bool y if PGTABLE_LEVELS > 2
+
config SECCOMP
bool "Enable seccomp to safely compute untrusted bytecode"
---help---
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 52fa47c73bf0..dabba4b2c61f 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -33,12 +33,22 @@
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return (pmd_t *)__get_free_page(PGALLOC_GFP);
+ struct page *page;
+
+ page = alloc_page(PGALLOC_GFP);
+ if (!page)
+ return NULL;
+ if (!pgtable_pmd_page_ctor(page)) {
+ __free_page(page);
+ return NULL;
+ }
+ return page_address(page);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
{
BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
+ pgtable_pmd_page_dtor(virt_to_page(pmdp));
free_page((unsigned long)pmdp);
}
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 106fdc951b6e..4e3becfed387 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -62,7 +62,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
unsigned long addr)
{
- tlb_remove_table(tlb, virt_to_page(pmdp));
+ struct page *page = virt_to_page(pmdp);
+
+ pgtable_pmd_page_dtor(page);
+ tlb_remove_table(tlb, page);
}
#endif
--
2.21.0.360.g471c308f928-goog
^ permalink raw reply related [flat|nested] 38+ messages in thread
* Re: [PATCH v3 3/3] arm64: mm: enable per pmd page table lock
2019-03-10 1:19 ` [PATCH v3 3/3] arm64: mm: enable per pmd page table lock Yu Zhao
@ 2019-03-11 8:28 ` Anshuman Khandual
2019-03-11 23:10 ` Yu Zhao
2019-03-11 12:12 ` Mark Rutland
1 sibling, 1 reply; 38+ messages in thread
From: Anshuman Khandual @ 2019-03-11 8:28 UTC (permalink / raw)
To: Yu Zhao, Catalin Marinas, Will Deacon, Mark Rutland
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm
On 03/10/2019 06:49 AM, Yu Zhao wrote:
> Switch from per mm_struct to per pmd page table lock by enabling
> ARCH_ENABLE_SPLIT_PMD_PTLOCK. This provides better granularity for
> large system.
>
> I'm not sure if there is contention on mm->page_table_lock. Given
> the option comes at no cost (apart from initializing more spin
> locks), why not enable it now.
>
> We only do so when pmd is not folded, so we don't mistakenly call
> pgtable_pmd_page_ctor() on pud or p4d in pgd_pgtable_alloc(). (We
> check shift against PMD_SHIFT, which is same as PUD_SHIFT when pmd
> is folded).
>
> Signed-off-by: Yu Zhao <yuzhao@google.com>
> ---
> arch/arm64/Kconfig | 3 +++
> arch/arm64/include/asm/pgalloc.h | 12 +++++++++++-
> arch/arm64/include/asm/tlb.h | 5 ++++-
> 3 files changed, 18 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index cfbf307d6dc4..a3b1b789f766 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -872,6 +872,9 @@ config ARCH_WANT_HUGE_PMD_SHARE
> config ARCH_HAS_CACHE_LINE_SIZE
> def_bool y
>
> +config ARCH_ENABLE_SPLIT_PMD_PTLOCK
> + def_bool y if PGTABLE_LEVELS > 2
> +
> config SECCOMP
> bool "Enable seccomp to safely compute untrusted bytecode"
> ---help---
> diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
> index 52fa47c73bf0..dabba4b2c61f 100644
> --- a/arch/arm64/include/asm/pgalloc.h
> +++ b/arch/arm64/include/asm/pgalloc.h
> @@ -33,12 +33,22 @@
>
> static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
> {
> - return (pmd_t *)__get_free_page(PGALLOC_GFP);
> + struct page *page;
> +
> + page = alloc_page(PGALLOC_GFP);
> + if (!page)
> + return NULL;
> + if (!pgtable_pmd_page_ctor(page)) {
> + __free_page(page);
> + return NULL;
> + }
> + return page_address(page);
> }
>
> static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
> {
> BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
> + pgtable_pmd_page_dtor(virt_to_page(pmdp));
> free_page((unsigned long)pmdp);
> }
There is just one problem here. ARM KVM's stage2_pmd_free() calls into pmd_free() on a page
originally allocated with __get_free_page() and never went through pgtable_pmd_page_ctor().
So when ARCH_ENABLE_SPLIT_PMD_PTLOCK is enabled
stage2_pmd_free()
pgtable_pmd_page_dtor()
ptlock_free()
kmem_cache_free(page_ptl_cachep, page->ptl)
Though SLUB implementation for kmem_cache_free() seems to be handling NULL page->ptl (as the
page never got it's lock allocated or initialized) correctly I am not sure if it is a right
thing to do.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v3 3/3] arm64: mm: enable per pmd page table lock
2019-03-11 8:28 ` Anshuman Khandual
@ 2019-03-11 23:10 ` Yu Zhao
0 siblings, 0 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-11 23:10 UTC (permalink / raw)
To: Anshuman Khandual
Cc: Catalin Marinas, Will Deacon, Mark Rutland, Aneesh Kumar K . V,
Andrew Morton, Nick Piggin, Peter Zijlstra, Joel Fernandes,
Kirill A . Shutemov, Ard Biesheuvel, Chintan Pandya, Jun Yao,
Laura Abbott, linux-arm-kernel, linux-kernel, linux-arch,
linux-mm
On Mon, Mar 11, 2019 at 01:58:27PM +0530, Anshuman Khandual wrote:
> On 03/10/2019 06:49 AM, Yu Zhao wrote:
> > Switch from per mm_struct to per pmd page table lock by enabling
> > ARCH_ENABLE_SPLIT_PMD_PTLOCK. This provides better granularity for
> > large system.
> >
> > I'm not sure if there is contention on mm->page_table_lock. Given
> > the option comes at no cost (apart from initializing more spin
> > locks), why not enable it now.
> >
> > We only do so when pmd is not folded, so we don't mistakenly call
> > pgtable_pmd_page_ctor() on pud or p4d in pgd_pgtable_alloc(). (We
> > check shift against PMD_SHIFT, which is same as PUD_SHIFT when pmd
> > is folded).
> >
> > Signed-off-by: Yu Zhao <yuzhao@google.com>
> > ---
> > arch/arm64/Kconfig | 3 +++
> > arch/arm64/include/asm/pgalloc.h | 12 +++++++++++-
> > arch/arm64/include/asm/tlb.h | 5 ++++-
> > 3 files changed, 18 insertions(+), 2 deletions(-)
> >
> > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> > index cfbf307d6dc4..a3b1b789f766 100644
> > --- a/arch/arm64/Kconfig
> > +++ b/arch/arm64/Kconfig
> > @@ -872,6 +872,9 @@ config ARCH_WANT_HUGE_PMD_SHARE
> > config ARCH_HAS_CACHE_LINE_SIZE
> > def_bool y
> >
> > +config ARCH_ENABLE_SPLIT_PMD_PTLOCK
> > + def_bool y if PGTABLE_LEVELS > 2
> > +
> > config SECCOMP
> > bool "Enable seccomp to safely compute untrusted bytecode"
> > ---help---
> > diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
> > index 52fa47c73bf0..dabba4b2c61f 100644
> > --- a/arch/arm64/include/asm/pgalloc.h
> > +++ b/arch/arm64/include/asm/pgalloc.h
> > @@ -33,12 +33,22 @@
> >
> > static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
> > {
> > - return (pmd_t *)__get_free_page(PGALLOC_GFP);
> > + struct page *page;
> > +
> > + page = alloc_page(PGALLOC_GFP);
> > + if (!page)
> > + return NULL;
> > + if (!pgtable_pmd_page_ctor(page)) {
> > + __free_page(page);
> > + return NULL;
> > + }
> > + return page_address(page);
> > }
> >
> > static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
> > {
> > BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
> > + pgtable_pmd_page_dtor(virt_to_page(pmdp));
> > free_page((unsigned long)pmdp);
> > }
>
> There is just one problem here. ARM KVM's stage2_pmd_free() calls into pmd_free() on a page
> originally allocated with __get_free_page() and never went through pgtable_pmd_page_ctor().
> So when ARCH_ENABLE_SPLIT_PMD_PTLOCK is enabled
>
> stage2_pmd_free()
> pgtable_pmd_page_dtor()
> ptlock_free()
> kmem_cache_free(page_ptl_cachep, page->ptl)
>
> Though SLUB implementation for kmem_cache_free() seems to be handling NULL page->ptl (as the
> page never got it's lock allocated or initialized) correctly I am not sure if it is a right
> thing to do.
Thanks for reminding me. This should be fixed as well. Will do it
in a separate patch.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v3 3/3] arm64: mm: enable per pmd page table lock
2019-03-10 1:19 ` [PATCH v3 3/3] arm64: mm: enable per pmd page table lock Yu Zhao
2019-03-11 8:28 ` Anshuman Khandual
@ 2019-03-11 12:12 ` Mark Rutland
2019-03-11 12:57 ` Anshuman Khandual
2019-03-11 23:11 ` Yu Zhao
1 sibling, 2 replies; 38+ messages in thread
From: Mark Rutland @ 2019-03-11 12:12 UTC (permalink / raw)
To: Yu Zhao, Anshuman Khandual
Cc: Catalin Marinas, Will Deacon, Aneesh Kumar K . V, Andrew Morton,
Nick Piggin, Peter Zijlstra, Joel Fernandes, Kirill A . Shutemov,
Ard Biesheuvel, Chintan Pandya, Jun Yao, Laura Abbott,
linux-arm-kernel, linux-kernel, linux-arch, linux-mm
Hi,
On Sat, Mar 09, 2019 at 06:19:06PM -0700, Yu Zhao wrote:
> Switch from per mm_struct to per pmd page table lock by enabling
> ARCH_ENABLE_SPLIT_PMD_PTLOCK. This provides better granularity for
> large system.
>
> I'm not sure if there is contention on mm->page_table_lock. Given
> the option comes at no cost (apart from initializing more spin
> locks), why not enable it now.
>
> We only do so when pmd is not folded, so we don't mistakenly call
> pgtable_pmd_page_ctor() on pud or p4d in pgd_pgtable_alloc(). (We
> check shift against PMD_SHIFT, which is same as PUD_SHIFT when pmd
> is folded).
Just to check, I take it pgtable_pmd_page_ctor() is now a NOP when the
PMD is folded, and this last paragraph is stale?
> Signed-off-by: Yu Zhao <yuzhao@google.com>
> ---
> arch/arm64/Kconfig | 3 +++
> arch/arm64/include/asm/pgalloc.h | 12 +++++++++++-
> arch/arm64/include/asm/tlb.h | 5 ++++-
> 3 files changed, 18 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index cfbf307d6dc4..a3b1b789f766 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -872,6 +872,9 @@ config ARCH_WANT_HUGE_PMD_SHARE
> config ARCH_HAS_CACHE_LINE_SIZE
> def_bool y
>
> +config ARCH_ENABLE_SPLIT_PMD_PTLOCK
> + def_bool y if PGTABLE_LEVELS > 2
> +
> config SECCOMP
> bool "Enable seccomp to safely compute untrusted bytecode"
> ---help---
> diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
> index 52fa47c73bf0..dabba4b2c61f 100644
> --- a/arch/arm64/include/asm/pgalloc.h
> +++ b/arch/arm64/include/asm/pgalloc.h
> @@ -33,12 +33,22 @@
>
> static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
> {
> - return (pmd_t *)__get_free_page(PGALLOC_GFP);
> + struct page *page;
> +
> + page = alloc_page(PGALLOC_GFP);
> + if (!page)
> + return NULL;
> + if (!pgtable_pmd_page_ctor(page)) {
> + __free_page(page);
> + return NULL;
> + }
> + return page_address(page);
> }
>
> static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
> {
> BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
> + pgtable_pmd_page_dtor(virt_to_page(pmdp));
> free_page((unsigned long)pmdp);
> }
It looks like arm64's existing stage-2 code is inconsistent across
alloc/free, and IIUC this change might turn that into a real problem.
Currently we allocate all levels of stage-2 table with
__get_free_page(), but free them with p?d_free(). We always miss the
ctor and always use the dtor.
Other than that, this patch looks fine to me, but I'd feel more
comfortable if we could first fix the stage-2 code to free those stage-2
tables without invoking the dtor.
Anshuman, IIRC you had a patch to fix the stage-2 code to not invoke the
dtors. If so, could you please post that so that we could take it as a
preparatory patch for this series?
Thanks,
Mark.
> diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
> index 106fdc951b6e..4e3becfed387 100644
> --- a/arch/arm64/include/asm/tlb.h
> +++ b/arch/arm64/include/asm/tlb.h
> @@ -62,7 +62,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
> static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
> unsigned long addr)
> {
> - tlb_remove_table(tlb, virt_to_page(pmdp));
> + struct page *page = virt_to_page(pmdp);
> +
> + pgtable_pmd_page_dtor(page);
> + tlb_remove_table(tlb, page);
> }
> #endif
>
> --
> 2.21.0.360.g471c308f928-goog
>
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v3 3/3] arm64: mm: enable per pmd page table lock
2019-03-11 12:12 ` Mark Rutland
@ 2019-03-11 12:57 ` Anshuman Khandual
2019-03-11 23:11 ` Yu Zhao
1 sibling, 0 replies; 38+ messages in thread
From: Anshuman Khandual @ 2019-03-11 12:57 UTC (permalink / raw)
To: Mark Rutland, Yu Zhao
Cc: Catalin Marinas, Will Deacon, Aneesh Kumar K . V, Andrew Morton,
Nick Piggin, Peter Zijlstra, Joel Fernandes, Kirill A . Shutemov,
Ard Biesheuvel, Chintan Pandya, Jun Yao, Laura Abbott,
linux-arm-kernel, linux-kernel, linux-arch, linux-mm
On 03/11/2019 05:42 PM, Mark Rutland wrote:
> Hi,
>
> On Sat, Mar 09, 2019 at 06:19:06PM -0700, Yu Zhao wrote:
>> Switch from per mm_struct to per pmd page table lock by enabling
>> ARCH_ENABLE_SPLIT_PMD_PTLOCK. This provides better granularity for
>> large system.
>>
>> I'm not sure if there is contention on mm->page_table_lock. Given
>> the option comes at no cost (apart from initializing more spin
>> locks), why not enable it now.
>>
>> We only do so when pmd is not folded, so we don't mistakenly call
>> pgtable_pmd_page_ctor() on pud or p4d in pgd_pgtable_alloc(). (We
>> check shift against PMD_SHIFT, which is same as PUD_SHIFT when pmd
>> is folded).
>
> Just to check, I take it pgtable_pmd_page_ctor() is now a NOP when the
> PMD is folded, and this last paragraph is stale?
>
>> Signed-off-by: Yu Zhao <yuzhao@google.com>
>> ---
>> arch/arm64/Kconfig | 3 +++
>> arch/arm64/include/asm/pgalloc.h | 12 +++++++++++-
>> arch/arm64/include/asm/tlb.h | 5 ++++-
>> 3 files changed, 18 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
>> index cfbf307d6dc4..a3b1b789f766 100644
>> --- a/arch/arm64/Kconfig
>> +++ b/arch/arm64/Kconfig
>> @@ -872,6 +872,9 @@ config ARCH_WANT_HUGE_PMD_SHARE
>> config ARCH_HAS_CACHE_LINE_SIZE
>> def_bool y
>>
>> +config ARCH_ENABLE_SPLIT_PMD_PTLOCK
>> + def_bool y if PGTABLE_LEVELS > 2
>> +
>> config SECCOMP
>> bool "Enable seccomp to safely compute untrusted bytecode"
>> ---help---
>> diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
>> index 52fa47c73bf0..dabba4b2c61f 100644
>> --- a/arch/arm64/include/asm/pgalloc.h
>> +++ b/arch/arm64/include/asm/pgalloc.h
>> @@ -33,12 +33,22 @@
>>
>> static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
>> {
>> - return (pmd_t *)__get_free_page(PGALLOC_GFP);
>> + struct page *page;
>> +
>> + page = alloc_page(PGALLOC_GFP);
>> + if (!page)
>> + return NULL;
>> + if (!pgtable_pmd_page_ctor(page)) {
>> + __free_page(page);
>> + return NULL;
>> + }
>> + return page_address(page);
>> }
>>
>> static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
>> {
>> BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
>> + pgtable_pmd_page_dtor(virt_to_page(pmdp));
>> free_page((unsigned long)pmdp);
>> }
>
> It looks like arm64's existing stage-2 code is inconsistent across
> alloc/free, and IIUC this change might turn that into a real problem.
> Currently we allocate all levels of stage-2 table with
> __get_free_page(), but free them with p?d_free(). We always miss the
> ctor and always use the dtor.
>
> Other than that, this patch looks fine to me, but I'd feel more
> comfortable if we could first fix the stage-2 code to free those stage-2
> tables without invoking the dtor.
Thats right. I have already highlighted this problem.
>
> Anshuman, IIRC you had a patch to fix the stage-2 code to not invoke the
> dtors. If so, could you please post that so that we could take it as a
> preparatory patch for this series?
Sure I can after fixing PTE level pte_free_kernel/__free_page which I had
missed in V2.
https://www.spinics.net/lists/arm-kernel/msg710118.html
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v3 3/3] arm64: mm: enable per pmd page table lock
2019-03-11 12:12 ` Mark Rutland
2019-03-11 12:57 ` Anshuman Khandual
@ 2019-03-11 23:11 ` Yu Zhao
1 sibling, 0 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-11 23:11 UTC (permalink / raw)
To: Mark Rutland
Cc: Anshuman Khandual, Catalin Marinas, Will Deacon,
Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm
On Mon, Mar 11, 2019 at 12:12:28PM +0000, Mark Rutland wrote:
> Hi,
>
> On Sat, Mar 09, 2019 at 06:19:06PM -0700, Yu Zhao wrote:
> > Switch from per mm_struct to per pmd page table lock by enabling
> > ARCH_ENABLE_SPLIT_PMD_PTLOCK. This provides better granularity for
> > large system.
> >
> > I'm not sure if there is contention on mm->page_table_lock. Given
> > the option comes at no cost (apart from initializing more spin
> > locks), why not enable it now.
> >
> > We only do so when pmd is not folded, so we don't mistakenly call
> > pgtable_pmd_page_ctor() on pud or p4d in pgd_pgtable_alloc(). (We
> > check shift against PMD_SHIFT, which is same as PUD_SHIFT when pmd
> > is folded).
>
> Just to check, I take it pgtable_pmd_page_ctor() is now a NOP when the
> PMD is folded, and this last paragraph is stale?
Yes, and will remove it.
> > Signed-off-by: Yu Zhao <yuzhao@google.com>
> > ---
> > arch/arm64/Kconfig | 3 +++
> > arch/arm64/include/asm/pgalloc.h | 12 +++++++++++-
> > arch/arm64/include/asm/tlb.h | 5 ++++-
> > 3 files changed, 18 insertions(+), 2 deletions(-)
> >
> > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> > index cfbf307d6dc4..a3b1b789f766 100644
> > --- a/arch/arm64/Kconfig
> > +++ b/arch/arm64/Kconfig
> > @@ -872,6 +872,9 @@ config ARCH_WANT_HUGE_PMD_SHARE
> > config ARCH_HAS_CACHE_LINE_SIZE
> > def_bool y
> >
> > +config ARCH_ENABLE_SPLIT_PMD_PTLOCK
> > + def_bool y if PGTABLE_LEVELS > 2
> > +
> > config SECCOMP
> > bool "Enable seccomp to safely compute untrusted bytecode"
> > ---help---
> > diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
> > index 52fa47c73bf0..dabba4b2c61f 100644
> > --- a/arch/arm64/include/asm/pgalloc.h
> > +++ b/arch/arm64/include/asm/pgalloc.h
> > @@ -33,12 +33,22 @@
> >
> > static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
> > {
> > - return (pmd_t *)__get_free_page(PGALLOC_GFP);
> > + struct page *page;
> > +
> > + page = alloc_page(PGALLOC_GFP);
> > + if (!page)
> > + return NULL;
> > + if (!pgtable_pmd_page_ctor(page)) {
> > + __free_page(page);
> > + return NULL;
> > + }
> > + return page_address(page);
> > }
> >
> > static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
> > {
> > BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
> > + pgtable_pmd_page_dtor(virt_to_page(pmdp));
> > free_page((unsigned long)pmdp);
> > }
>
> It looks like arm64's existing stage-2 code is inconsistent across
> alloc/free, and IIUC this change might turn that into a real problem.
> Currently we allocate all levels of stage-2 table with
> __get_free_page(), but free them with p?d_free(). We always miss the
> ctor and always use the dtor.
>
> Other than that, this patch looks fine to me, but I'd feel more
> comfortable if we could first fix the stage-2 code to free those stage-2
> tables without invoking the dtor.
>
> Anshuman, IIRC you had a patch to fix the stage-2 code to not invoke the
> dtors. If so, could you please post that so that we could take it as a
> preparatory patch for this series?
Will do.
> Thanks,
> Mark.
>
> > diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
> > index 106fdc951b6e..4e3becfed387 100644
> > --- a/arch/arm64/include/asm/tlb.h
> > +++ b/arch/arm64/include/asm/tlb.h
> > @@ -62,7 +62,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
> > static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
> > unsigned long addr)
> > {
> > - tlb_remove_table(tlb, virt_to_page(pmdp));
> > + struct page *page = virt_to_page(pmdp);
> > +
> > + pgtable_pmd_page_dtor(page);
> > + tlb_remove_table(tlb, page);
> > }
> > #endif
> >
> > --
> > 2.21.0.360.g471c308f928-goog
> >
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v3 1/3] arm64: mm: use appropriate ctors for page tables
2019-03-10 1:19 ` [PATCH v3 " Yu Zhao
2019-03-10 1:19 ` [PATCH v3 2/3] arm64: mm: don't call page table ctors for init_mm Yu Zhao
2019-03-10 1:19 ` [PATCH v3 3/3] arm64: mm: enable per pmd page table lock Yu Zhao
@ 2019-03-11 7:45 ` Anshuman Khandual
2019-03-11 23:23 ` Yu Zhao
2019-03-12 0:57 ` [PATCH v4 1/4] " Yu Zhao
3 siblings, 1 reply; 38+ messages in thread
From: Anshuman Khandual @ 2019-03-11 7:45 UTC (permalink / raw)
To: Yu Zhao, Catalin Marinas, Will Deacon, Mark Rutland
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm
Hello Yu,
We had some disagreements over this series last time around after which I had
posted the following series [1] which tried to enable ARCH_ENABLE_SPLIT_PMD_PTLOCK
after doing some pgtable accounting changes. After some thoughts and deliberations
I figure that its better not to do pgtable alloc changes on arm64 creating a brand
new semantics which ideally should be first debated and agreed upon in generic MM.
Though I still see value in a changed generic pgtable page allocation semantics
for user and kernel space that should not stop us from enabling more granular
PMD level locks through ARCH_ENABLE_SPLIT_PMD_PTLOCK right now.
[1] https://www.spinics.net/lists/arm-kernel/msg709917.html
Having said that this series attempts to enable ARCH_ENABLE_SPLIT_PMD_PTLOCK with
some minimal changes to existing kernel pgtable page allocation code. Hence just
trying to re-evaluate the series in that isolation.
On 03/10/2019 06:49 AM, Yu Zhao wrote:
> For pte page, use pgtable_page_ctor(); for pmd page, use
> pgtable_pmd_page_ctor(); and for the rest (pud, p4d and pgd),
> don't use any.
This is semantics change. Hence the question is why ? Should not we wait until a
generic MM agreement in place in this regard ? Can we avoid this ? Is the change
really required to enable ARCH_ENABLE_SPLIT_PMD_PTLOCK for user space THP which
this series originally intended to achieve ?
>
> For now, we don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK and
> pgtable_pmd_page_ctor() is a nop. When we do in patch 3, we
> make sure pmd is not folded so we won't mistakenly call
> pgtable_pmd_page_ctor() on pud or p4d.
This makes sense from code perspective but I still dont understand the need to
change kernel pgtable page allocation semantics without any real benefit or fix at
the moment. Cant we keep kernel page table page allocation unchanged for now and
just enable ARCH_ENABLE_SPLIT_PMD_PTLOCK for user space THP benefits ? Do you see
any concern with that.
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [PATCH v3 1/3] arm64: mm: use appropriate ctors for page tables
2019-03-11 7:45 ` [PATCH v3 1/3] arm64: mm: use appropriate ctors for page tables Anshuman Khandual
@ 2019-03-11 23:23 ` Yu Zhao
0 siblings, 0 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-11 23:23 UTC (permalink / raw)
To: Anshuman Khandual
Cc: Catalin Marinas, Will Deacon, Mark Rutland, Aneesh Kumar K . V,
Andrew Morton, Nick Piggin, Peter Zijlstra, Joel Fernandes,
Kirill A . Shutemov, Ard Biesheuvel, Chintan Pandya, Jun Yao,
Laura Abbott, linux-arm-kernel, linux-kernel, linux-arch,
linux-mm
On Mon, Mar 11, 2019 at 01:15:55PM +0530, Anshuman Khandual wrote:
> Hello Yu,
>
> We had some disagreements over this series last time around after which I had
> posted the following series [1] which tried to enable ARCH_ENABLE_SPLIT_PMD_PTLOCK
> after doing some pgtable accounting changes. After some thoughts and deliberations
> I figure that its better not to do pgtable alloc changes on arm64 creating a brand
> new semantics which ideally should be first debated and agreed upon in generic MM.
>
> Though I still see value in a changed generic pgtable page allocation semantics
> for user and kernel space that should not stop us from enabling more granular
> PMD level locks through ARCH_ENABLE_SPLIT_PMD_PTLOCK right now.
>
> [1] https://www.spinics.net/lists/arm-kernel/msg709917.html
>
> Having said that this series attempts to enable ARCH_ENABLE_SPLIT_PMD_PTLOCK with
> some minimal changes to existing kernel pgtable page allocation code. Hence just
> trying to re-evaluate the series in that isolation.
>
> On 03/10/2019 06:49 AM, Yu Zhao wrote:
>
> > For pte page, use pgtable_page_ctor(); for pmd page, use
> > pgtable_pmd_page_ctor(); and for the rest (pud, p4d and pgd),
> > don't use any.
>
> This is semantics change. Hence the question is why ? Should not we wait until a
> generic MM agreement in place in this regard ? Can we avoid this ? Is the change
> really required to enable ARCH_ENABLE_SPLIT_PMD_PTLOCK for user space THP which
> this series originally intended to achieve ?
>
> >
> > For now, we don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK and
> > pgtable_pmd_page_ctor() is a nop. When we do in patch 3, we
> > make sure pmd is not folded so we won't mistakenly call
> > pgtable_pmd_page_ctor() on pud or p4d.
>
> This makes sense from code perspective but I still dont understand the need to
> change kernel pgtable page allocation semantics without any real benefit or fix at
> the moment. Cant we keep kernel page table page allocation unchanged for now and
> just enable ARCH_ENABLE_SPLIT_PMD_PTLOCK for user space THP benefits ? Do you see
> any concern with that.
This is not for kernel page tables (i.e. init_mm). This is to
accommodate pre-allocated efi_mm page tables because it uses
apply_to_page_range() which then calls pte_alloc_map_lock().
^ permalink raw reply [flat|nested] 38+ messages in thread
* [PATCH v4 1/4] arm64: mm: use appropriate ctors for page tables
2019-03-10 1:19 ` [PATCH v3 " Yu Zhao
` (2 preceding siblings ...)
2019-03-11 7:45 ` [PATCH v3 1/3] arm64: mm: use appropriate ctors for page tables Anshuman Khandual
@ 2019-03-12 0:57 ` Yu Zhao
2019-03-12 0:57 ` [PATCH v4 2/4] arm64: mm: don't call page table ctors for init_mm Yu Zhao
` (2 more replies)
3 siblings, 3 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-12 0:57 UTC (permalink / raw)
To: Catalin Marinas, Will Deacon, Mark Rutland
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm, Yu Zhao
For pte page, use pgtable_page_ctor(); for pmd page, use
pgtable_pmd_page_ctor(); and for the rest (pud, p4d and pgd),
don't use any.
For now, we don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK and
pgtable_pmd_page_ctor() is a nop. When we do in patch 3, we
make sure pmd is not folded so we won't mistakenly call
pgtable_pmd_page_ctor() on pud or p4d.
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Yu Zhao <yuzhao@google.com>
---
arch/arm64/mm/mmu.c | 36 ++++++++++++++++++++++++------------
1 file changed, 24 insertions(+), 12 deletions(-)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index b6f5aa52ac67..f704b291f2c5 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -98,7 +98,7 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
}
EXPORT_SYMBOL(phys_mem_access_prot);
-static phys_addr_t __init early_pgtable_alloc(void)
+static phys_addr_t __init early_pgtable_alloc(int shift)
{
phys_addr_t phys;
void *ptr;
@@ -173,7 +173,7 @@ static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long next;
@@ -183,7 +183,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
if (pmd_none(pmd)) {
phys_addr_t pte_phys;
BUG_ON(!pgtable_alloc);
- pte_phys = pgtable_alloc();
+ pte_phys = pgtable_alloc(PAGE_SHIFT);
__pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
pmd = READ_ONCE(*pmdp);
}
@@ -207,7 +207,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void), int flags)
+ phys_addr_t (*pgtable_alloc)(int), int flags)
{
unsigned long next;
pmd_t *pmdp;
@@ -245,7 +245,7 @@ static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void), int flags)
+ phys_addr_t (*pgtable_alloc)(int), int flags)
{
unsigned long next;
pud_t pud = READ_ONCE(*pudp);
@@ -257,7 +257,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
if (pud_none(pud)) {
phys_addr_t pmd_phys;
BUG_ON(!pgtable_alloc);
- pmd_phys = pgtable_alloc();
+ pmd_phys = pgtable_alloc(PMD_SHIFT);
__pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
pud = READ_ONCE(*pudp);
}
@@ -293,7 +293,7 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,
static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long next;
@@ -303,7 +303,7 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
if (pgd_none(pgd)) {
phys_addr_t pud_phys;
BUG_ON(!pgtable_alloc);
- pud_phys = pgtable_alloc();
+ pud_phys = pgtable_alloc(PUD_SHIFT);
__pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE);
pgd = READ_ONCE(*pgdp);
}
@@ -344,7 +344,7 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long addr, length, end, next;
@@ -370,11 +370,23 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
} while (pgdp++, addr = next, addr != end);
}
-static phys_addr_t pgd_pgtable_alloc(void)
+static phys_addr_t pgd_pgtable_alloc(int shift)
{
void *ptr = (void *)__get_free_page(PGALLOC_GFP);
- if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
- BUG();
+ BUG_ON(!ptr);
+
+ /*
+ * Call proper page table ctor in case later we need to
+ * call core mm functions like apply_to_page_range() on
+ * this pre-allocated page table.
+ *
+ * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is
+ * folded, and if so pgtable_pmd_page_ctor() becomes nop.
+ */
+ if (shift == PAGE_SHIFT)
+ BUG_ON(!pgtable_page_ctor(virt_to_page(ptr)));
+ else if (shift == PMD_SHIFT)
+ BUG_ON(!pgtable_pmd_page_ctor(virt_to_page(ptr)));
/* Ensure the zeroed page is visible to the page table walker */
dsb(ishst);
--
2.21.0.360.g471c308f928-goog
^ permalink raw reply related [flat|nested] 38+ messages in thread
* [PATCH v4 2/4] arm64: mm: don't call page table ctors for init_mm
2019-03-12 0:57 ` [PATCH v4 1/4] " Yu Zhao
@ 2019-03-12 0:57 ` Yu Zhao
2019-03-12 0:57 ` [PATCH v4 3/4] arm64: mm: call ctor for stage2 pmd page Yu Zhao
2019-03-12 0:57 ` [PATCH v4 4/4] arm64: mm: enable per pmd page table lock Yu Zhao
2 siblings, 0 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-12 0:57 UTC (permalink / raw)
To: Catalin Marinas, Will Deacon, Mark Rutland
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm, Yu Zhao
init_mm doesn't require page table lock to be initialized at
any level. Add a separate page table allocator for it, and the
new one skips page table ctors.
The ctors allocate memory when ALLOC_SPLIT_PTLOCKS is set. Not
calling them avoids memory leak in case we call pte_free_kernel()
on init_mm.
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Yu Zhao <yuzhao@google.com>
---
arch/arm64/mm/mmu.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index f704b291f2c5..d1dc2a2777aa 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -370,6 +370,16 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
} while (pgdp++, addr = next, addr != end);
}
+static phys_addr_t pgd_kernel_pgtable_alloc(int shift)
+{
+ void *ptr = (void *)__get_free_page(PGALLOC_GFP);
+ BUG_ON(!ptr);
+
+ /* Ensure the zeroed page is visible to the page table walker */
+ dsb(ishst);
+ return __pa(ptr);
+}
+
static phys_addr_t pgd_pgtable_alloc(int shift)
{
void *ptr = (void *)__get_free_page(PGALLOC_GFP);
@@ -594,7 +604,7 @@ static int __init map_entry_trampoline(void)
/* Map only the text into the trampoline page table */
memset(tramp_pg_dir, 0, PGD_SIZE);
__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
- prot, pgd_pgtable_alloc, 0);
+ prot, pgd_kernel_pgtable_alloc, 0);
/* Map both the text and data into the kernel page table */
__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
@@ -1070,7 +1080,8 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
- size, PAGE_KERNEL, pgd_pgtable_alloc, flags);
+ size, PAGE_KERNEL, pgd_kernel_pgtable_alloc,
+ flags);
return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
altmap, want_memblock);
--
2.21.0.360.g471c308f928-goog
^ permalink raw reply related [flat|nested] 38+ messages in thread
* [PATCH v4 3/4] arm64: mm: call ctor for stage2 pmd page
2019-03-12 0:57 ` [PATCH v4 1/4] " Yu Zhao
2019-03-12 0:57 ` [PATCH v4 2/4] arm64: mm: don't call page table ctors for init_mm Yu Zhao
@ 2019-03-12 0:57 ` Yu Zhao
2019-03-12 0:57 ` [PATCH v4 4/4] arm64: mm: enable per pmd page table lock Yu Zhao
2 siblings, 0 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-12 0:57 UTC (permalink / raw)
To: Catalin Marinas, Will Deacon, Mark Rutland
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm, Yu Zhao
Call pgtable_pmd_page_dtor() for pmd page allocated by
mmu_memory_cache_alloc() so kernel won't crash when it's freed
through stage2_pmd_free()->pmd_free()->pgtable_pmd_page_dtor().
This is needed if we are going to enable split pmd pt lock.
Signed-off-by: Yu Zhao <yuzhao@google.com>
---
arch/arm64/include/asm/stage2_pgtable.h | 15 ++++++++++++---
virt/kvm/arm/mmu.c | 13 +++++++++++--
2 files changed, 23 insertions(+), 5 deletions(-)
diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index 5412fa40825e..0d9207144257 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -174,10 +174,19 @@ static inline bool stage2_pud_present(struct kvm *kvm, pud_t pud)
return 1;
}
-static inline void stage2_pud_populate(struct kvm *kvm, pud_t *pud, pmd_t *pmd)
+static inline int stage2_pud_populate(struct kvm *kvm, pud_t *pud, pmd_t *pmd)
{
- if (kvm_stage2_has_pmd(kvm))
- pud_populate(NULL, pud, pmd);
+ if (!kvm_stage2_has_pmd(kvm))
+ return 0;
+
+ /* paired with pgtable_pmd_page_dtor() in pmd_free() below */
+ if (!pgtable_pmd_page_ctor(virt_to_page(pmd))) {
+ free_page((unsigned long)pmd);
+ return -ENOMEM;
+ }
+
+ pud_populate(NULL, pud, pmd);
+ return 0;
}
static inline pmd_t *stage2_pmd_offset(struct kvm *kvm,
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index e9d28a7ca673..11922d84be83 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1037,6 +1037,7 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr)
{
+ int ret;
pud_t *pud;
pmd_t *pmd;
@@ -1048,7 +1049,9 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
if (!cache)
return NULL;
pmd = mmu_memory_cache_alloc(cache);
- stage2_pud_populate(kvm, pud, pmd);
+ ret = stage2_pud_populate(kvm, pud, pmd);
+ if (ret)
+ return ERR_PTR(ret);
get_page(virt_to_page(pud));
}
@@ -1061,6 +1064,9 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
pmd_t *pmd, old_pmd;
pmd = stage2_get_pmd(kvm, cache, addr);
+ if (IS_ERR(pmd))
+ return PTR_ERR(pmd);
+
VM_BUG_ON(!pmd);
old_pmd = *pmd;
@@ -1198,6 +1204,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr, const pte_t *new_pte,
unsigned long flags)
{
+ int ret;
pud_t *pud;
pmd_t *pmd;
pte_t *pte, old_pte;
@@ -1227,7 +1234,9 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
if (!cache)
return 0; /* ignore calls from kvm_set_spte_hva */
pmd = mmu_memory_cache_alloc(cache);
- stage2_pud_populate(kvm, pud, pmd);
+ ret = stage2_pud_populate(kvm, pud, pmd);
+ if (ret)
+ return ret;
get_page(virt_to_page(pud));
}
--
2.21.0.360.g471c308f928-goog
^ permalink raw reply related [flat|nested] 38+ messages in thread
* [PATCH v4 4/4] arm64: mm: enable per pmd page table lock
2019-03-12 0:57 ` [PATCH v4 1/4] " Yu Zhao
2019-03-12 0:57 ` [PATCH v4 2/4] arm64: mm: don't call page table ctors for init_mm Yu Zhao
2019-03-12 0:57 ` [PATCH v4 3/4] arm64: mm: call ctor for stage2 pmd page Yu Zhao
@ 2019-03-12 0:57 ` Yu Zhao
2 siblings, 0 replies; 38+ messages in thread
From: Yu Zhao @ 2019-03-12 0:57 UTC (permalink / raw)
To: Catalin Marinas, Will Deacon, Mark Rutland
Cc: Aneesh Kumar K . V, Andrew Morton, Nick Piggin, Peter Zijlstra,
Joel Fernandes, Kirill A . Shutemov, Ard Biesheuvel,
Chintan Pandya, Jun Yao, Laura Abbott, linux-arm-kernel,
linux-kernel, linux-arch, linux-mm, Yu Zhao
Switch from per mm_struct to per pmd page table lock by enabling
ARCH_ENABLE_SPLIT_PMD_PTLOCK. This provides better granularity for
large system.
I'm not sure if there is contention on mm->page_table_lock. Given
the option comes at no cost (apart from initializing more spin
locks), why not enable it now.
We only do so when pmd is not folded, so we don't mistakenly call
pgtable_pmd_page_ctor() on pud or p4d in pgd_pgtable_alloc().
Signed-off-by: Yu Zhao <yuzhao@google.com>
---
arch/arm64/Kconfig | 3 +++
arch/arm64/include/asm/pgalloc.h | 12 +++++++++++-
arch/arm64/include/asm/tlb.h | 5 ++++-
3 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index cfbf307d6dc4..a3b1b789f766 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -872,6 +872,9 @@ config ARCH_WANT_HUGE_PMD_SHARE
config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+ def_bool y if PGTABLE_LEVELS > 2
+
config SECCOMP
bool "Enable seccomp to safely compute untrusted bytecode"
---help---
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 52fa47c73bf0..dabba4b2c61f 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -33,12 +33,22 @@
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return (pmd_t *)__get_free_page(PGALLOC_GFP);
+ struct page *page;
+
+ page = alloc_page(PGALLOC_GFP);
+ if (!page)
+ return NULL;
+ if (!pgtable_pmd_page_ctor(page)) {
+ __free_page(page);
+ return NULL;
+ }
+ return page_address(page);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
{
BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
+ pgtable_pmd_page_dtor(virt_to_page(pmdp));
free_page((unsigned long)pmdp);
}
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 106fdc951b6e..4e3becfed387 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -62,7 +62,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
unsigned long addr)
{
- tlb_remove_table(tlb, virt_to_page(pmdp));
+ struct page *page = virt_to_page(pmdp);
+
+ pgtable_pmd_page_dtor(page);
+ tlb_remove_table(tlb, page);
}
#endif
--
2.21.0.360.g471c308f928-goog
^ permalink raw reply related [flat|nested] 38+ messages in thread