From: Ryan Roberts <ryan.roberts@arm.com>
To: Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will@kernel.org>,
Pasha Tatashin <pasha.tatashin@soleen.com>,
Andrew Morton <akpm@linux-foundation.org>,
Uladzislau Rezki <urezki@gmail.com>,
Christoph Hellwig <hch@infradead.org>,
David Hildenbrand <david@redhat.com>,
"Matthew Wilcox (Oracle)" <willy@infradead.org>,
Mark Rutland <mark.rutland@arm.com>,
Anshuman Khandual <anshuman.khandual@arm.com>,
Alexandre Ghiti <alexghiti@rivosinc.com>,
Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>,
linux-arm-kernel@lists.infradead.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Subject: [PATCH v3 05/11] arm64: hugetlb: Use set_ptes_anysz() and ptep_get_and_clear_anysz()
Date: Tue, 4 Mar 2025 15:04:35 +0000 [thread overview]
Message-ID: <20250304150444.3788920-6-ryan.roberts@arm.com> (raw)
In-Reply-To: <20250304150444.3788920-1-ryan.roberts@arm.com>
Refactor the huge_pte helpers to use the new common set_ptes_anysz() and
ptep_get_and_clear_anysz() APIs.
This provides 2 benefits; First, when page_table_check=on, hugetlb is
now properly/fully checked. Previously only the first page of a hugetlb
folio was checked. Second, instead of having to call __set_ptes(nr=1)
for each pte in a loop, the whole contiguous batch can now be set in one
go, which enables some efficiencies and cleans up the code.
One detail to note is that huge_ptep_clear_flush() was previously
calling ptep_clear_flush() for a non-contiguous pte (i.e. a pud or pmd
block mapping). This has a couple of disadvantages; first
ptep_clear_flush() calls ptep_get_and_clear() which transparently
handles contpte. Given we only call for non-contiguous ptes, it would be
safe, but a waste of effort. It's preferable to go straight to the layer
below. However, more problematic is that ptep_get_and_clear() is for
PAGE_SIZE entries so it calls page_table_check_pte_clear() and would not
clear the whole hugetlb folio. So let's stop special-casing the non-cont
case and just rely on get_clear_contig_flush() to do the right thing for
non-cont entries.
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
arch/arm64/mm/hugetlbpage.c | 52 +++++++------------------------------
1 file changed, 10 insertions(+), 42 deletions(-)
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 065be8650aa5..efd18bd1eae3 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -159,12 +159,12 @@ static pte_t get_clear_contig(struct mm_struct *mm,
pte_t pte, tmp_pte;
bool present;
- pte = __ptep_get_and_clear(mm, addr, ptep);
+ pte = ptep_get_and_clear_anysz(mm, ptep, pgsize);
present = pte_present(pte);
while (--ncontig) {
ptep++;
addr += pgsize;
- tmp_pte = __ptep_get_and_clear(mm, addr, ptep);
+ tmp_pte = ptep_get_and_clear_anysz(mm, ptep, pgsize);
if (present) {
if (pte_dirty(tmp_pte))
pte = pte_mkdirty(pte);
@@ -208,7 +208,7 @@ static void clear_flush(struct mm_struct *mm,
unsigned long i, saddr = addr;
for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
- __ptep_get_and_clear(mm, addr, ptep);
+ ptep_get_and_clear_anysz(mm, ptep, pgsize);
__flush_hugetlb_tlb_range(&vma, saddr, addr, pgsize, true);
}
@@ -219,32 +219,20 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
size_t pgsize;
int i;
int ncontig;
- unsigned long pfn, dpfn;
- pgprot_t hugeprot;
ncontig = num_contig_ptes(sz, &pgsize);
if (!pte_present(pte)) {
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
- __set_ptes(mm, addr, ptep, pte, 1);
+ set_ptes_anysz(mm, ptep, pte, 1, pgsize);
return;
}
- if (!pte_cont(pte)) {
- __set_ptes(mm, addr, ptep, pte, 1);
- return;
- }
-
- pfn = pte_pfn(pte);
- dpfn = pgsize >> PAGE_SHIFT;
- hugeprot = pte_pgprot(pte);
-
/* Only need to "break" if transitioning valid -> valid. */
- if (pte_valid(__ptep_get(ptep)))
+ if (pte_cont(pte) && pte_valid(__ptep_get(ptep)))
clear_flush(mm, addr, ptep, pgsize, ncontig);
- for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
- __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
+ set_ptes_anysz(mm, ptep, pte, ncontig, pgsize);
}
pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -434,11 +422,9 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty)
{
- int ncontig, i;
+ int ncontig;
size_t pgsize = 0;
- unsigned long pfn = pte_pfn(pte), dpfn;
struct mm_struct *mm = vma->vm_mm;
- pgprot_t hugeprot;
pte_t orig_pte;
VM_WARN_ON(!pte_present(pte));
@@ -447,7 +433,6 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
return __ptep_set_access_flags(vma, addr, ptep, pte, dirty);
ncontig = num_contig_ptes(huge_page_size(hstate_vma(vma)), &pgsize);
- dpfn = pgsize >> PAGE_SHIFT;
if (!__cont_access_flags_changed(ptep, pte, ncontig))
return 0;
@@ -462,19 +447,14 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
if (pte_young(orig_pte))
pte = pte_mkyoung(pte);
- hugeprot = pte_pgprot(pte);
- for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
- __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
-
+ set_ptes_anysz(mm, ptep, pte, ncontig, pgsize);
return 1;
}
void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- unsigned long pfn, dpfn;
- pgprot_t hugeprot;
- int ncontig, i;
+ int ncontig;
size_t pgsize;
pte_t pte;
@@ -487,16 +467,11 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
}
ncontig = find_num_contig(mm, addr, ptep, &pgsize);
- dpfn = pgsize >> PAGE_SHIFT;
pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
pte = pte_wrprotect(pte);
- hugeprot = pte_pgprot(pte);
- pfn = pte_pfn(pte);
-
- for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
- __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
+ set_ptes_anysz(mm, ptep, pte, ncontig, pgsize);
}
pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
@@ -505,13 +480,6 @@ pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
struct mm_struct *mm = vma->vm_mm;
size_t pgsize;
int ncontig;
- pte_t pte;
-
- pte = __ptep_get(ptep);
- VM_WARN_ON(!pte_present(pte));
-
- if (!pte_cont(pte))
- return ptep_clear_flush(vma, addr, ptep);
ncontig = num_contig_ptes(huge_page_size(hstate_vma(vma)), &pgsize);
return get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
--
2.43.0
next prev parent reply other threads:[~2025-03-04 15:05 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-04 15:04 [PATCH v3 00/11] Perf improvements for hugetlb and vmalloc on arm64 Ryan Roberts
2025-03-04 15:04 ` [PATCH v3 01/11] arm64: hugetlb: Cleanup huge_pte size discovery mechanisms Ryan Roberts
2025-04-03 20:46 ` Catalin Marinas
2025-04-04 3:03 ` Anshuman Khandual
2025-03-04 15:04 ` [PATCH v3 02/11] arm64: hugetlb: Refine tlb maintenance scope Ryan Roberts
2025-04-03 20:47 ` Catalin Marinas
2025-04-04 3:50 ` Anshuman Khandual
2025-03-04 15:04 ` [PATCH v3 03/11] mm/page_table_check: Batch-check pmds/puds just like ptes Ryan Roberts
2025-03-26 14:48 ` Pasha Tatashin
2025-03-26 14:54 ` Ryan Roberts
2025-04-03 20:46 ` Catalin Marinas
2025-03-04 15:04 ` [PATCH v3 04/11] arm64/mm: Refactor __set_ptes() and __ptep_get_and_clear() Ryan Roberts
2025-03-06 5:08 ` kernel test robot
2025-03-06 11:54 ` Ryan Roberts
2025-04-14 16:25 ` Catalin Marinas
2025-03-04 15:04 ` Ryan Roberts [this message]
2025-03-05 16:00 ` [PATCH v3 05/11] arm64: hugetlb: Use set_ptes_anysz() and ptep_get_and_clear_anysz() kernel test robot
2025-03-05 16:32 ` Ryan Roberts
2025-04-03 20:47 ` Catalin Marinas
2025-03-04 15:04 ` [PATCH v3 06/11] arm64/mm: Hoist barriers out of set_ptes_anysz() loop Ryan Roberts
2025-04-03 20:46 ` Catalin Marinas
2025-04-04 4:11 ` Anshuman Khandual
2025-03-04 15:04 ` [PATCH v3 07/11] mm/vmalloc: Warn on improper use of vunmap_range() Ryan Roberts
2025-03-27 13:05 ` Uladzislau Rezki
2025-03-04 15:04 ` [PATCH v3 08/11] mm/vmalloc: Gracefully unmap huge ptes Ryan Roberts
2025-03-04 15:04 ` [PATCH v3 09/11] arm64/mm: Support huge pte-mapped pages in vmap Ryan Roberts
2025-03-04 15:04 ` [PATCH v3 10/11] mm/vmalloc: Enter lazy mmu mode while manipulating vmalloc ptes Ryan Roberts
2025-03-27 13:06 ` Uladzislau Rezki
2025-04-03 20:47 ` Catalin Marinas
2025-04-04 4:54 ` Anshuman Khandual
2025-03-04 15:04 ` [PATCH v3 11/11] arm64/mm: Batch barriers when updating kernel mappings Ryan Roberts
2025-04-04 6:02 ` Anshuman Khandual
2025-04-14 17:38 ` Catalin Marinas
2025-04-14 18:28 ` Ryan Roberts
2025-04-15 10:51 ` Catalin Marinas
2025-04-15 17:28 ` Ryan Roberts
2025-03-27 12:16 ` [PATCH v3 00/11] Perf improvements for hugetlb and vmalloc on arm64 Uladzislau Rezki
2025-03-27 13:46 ` Ryan Roberts
2025-04-14 13:56 ` Ryan Roberts
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250304150444.3788920-6-ryan.roberts@arm.com \
--to=ryan.roberts@arm.com \
--cc=akpm@linux-foundation.org \
--cc=alexghiti@rivosinc.com \
--cc=anshuman.khandual@arm.com \
--cc=catalin.marinas@arm.com \
--cc=david@redhat.com \
--cc=hch@infradead.org \
--cc=kevin.brodsky@arm.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mark.rutland@arm.com \
--cc=pasha.tatashin@soleen.com \
--cc=urezki@gmail.com \
--cc=will@kernel.org \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox