| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <Zcuqd9e359L0SVPC@FVFF77S0Q05N.cambridge.arm.com>
Date: Tue, 13 Feb 2024 17:44:23 +0000
From: Mark Rutland <mark.rutland@....com>
To: Ryan Roberts <ryan.roberts@....com>
Cc: Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will@...nel.org>, Ard Biesheuvel <ardb@...nel.org>,
Marc Zyngier <maz@...nel.org>, James Morse <james.morse@....com>,
Andrey Ryabinin <ryabinin.a.a@...il.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Matthew Wilcox <willy@...radead.org>,
David Hildenbrand <david@...hat.com>,
Kefeng Wang <wangkefeng.wang@...wei.com>,
John Hubbard <jhubbard@...dia.com>, Zi Yan <ziy@...dia.com>,
Barry Song <21cnbao@...il.com>,
Alistair Popple <apopple@...dia.com>,
Yang Shi <shy828301@...il.com>, Nicholas Piggin <npiggin@...il.com>,
Christophe Leroy <christophe.leroy@...roup.eu>,
"Aneesh Kumar K.V" <aneesh.kumar@...nel.org>,
"Naveen N. Rao" <naveen.n.rao@...ux.ibm.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...ux.intel.com>,
"H. Peter Anvin" <hpa@...or.com>,
linux-arm-kernel@...ts.infradead.org, x86@...nel.org,
linuxppc-dev@...ts.ozlabs.org, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v5 25/25] arm64/mm: Automatically fold contpte mappings
On Fri, Feb 02, 2024 at 08:07:56AM +0000, Ryan Roberts wrote:
> There are situations where a change to a single PTE could cause the
> contpte block in which it resides to become foldable (i.e. could be
> repainted with the contiguous bit). Such situations arise, for example,
> when user space temporarily changes protections, via mprotect, for
> individual pages, such can be the case for certain garbage collectors.
>
> We would like to detect when such a PTE change occurs. However this can
> be expensive due to the amount of checking required. Therefore only
> perform the checks when an indiviual PTE is modified via mprotect
> (ptep_modify_prot_commit() -> set_pte_at() -> set_ptes(nr=1)) and only
> when we are setting the final PTE in a contpte-aligned block.
>
> Signed-off-by: Ryan Roberts <ryan.roberts@....com>
> ---
> arch/arm64/include/asm/pgtable.h | 26 +++++++++++++
> arch/arm64/mm/contpte.c | 64 ++++++++++++++++++++++++++++++++
> 2 files changed, 90 insertions(+)
>
> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
> index cdc310880a3b..d3357fe4eb89 100644
> --- a/arch/arm64/include/asm/pgtable.h
> +++ b/arch/arm64/include/asm/pgtable.h
> @@ -1192,6 +1192,8 @@ void vmemmap_update_pte(unsigned long addr, pte_t *ptep, pte_t pte);
> * where it is possible and makes sense to do so. The PTE_CONT bit is considered
> * a private implementation detail of the public ptep API (see below).
> */
> +extern void __contpte_try_fold(struct mm_struct *mm, unsigned long addr,
> + pte_t *ptep, pte_t pte);
> extern void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr,
> pte_t *ptep, pte_t pte);
> extern pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte);
> @@ -1213,6 +1215,29 @@ extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
> unsigned long addr, pte_t *ptep,
> pte_t entry, int dirty);
>
> +static __always_inline void contpte_try_fold(struct mm_struct *mm,
> + unsigned long addr, pte_t *ptep, pte_t pte)
> +{
> + /*
> + * Only bother trying if both the virtual and physical addresses are
> + * aligned and correspond to the last entry in a contig range. The core
> + * code mostly modifies ranges from low to high, so this is the likely
> + * the last modification in the contig range, so a good time to fold.
> + * We can't fold special mappings, because there is no associated folio.
> + */
> +
> + const unsigned long contmask = CONT_PTES - 1;
> + bool valign = ((addr >> PAGE_SHIFT) & contmask) == contmask;
> +
> + if (unlikely(valign)) {
> + bool palign = (pte_pfn(pte) & contmask) == contmask;
> +
> + if (unlikely(palign &&
> + pte_valid(pte) && !pte_cont(pte) && !pte_special(pte)))
> + __contpte_try_fold(mm, addr, ptep, pte);
> + }
> +}
> +
> static __always_inline void contpte_try_unfold(struct mm_struct *mm,
> unsigned long addr, pte_t *ptep, pte_t pte)
> {
> @@ -1287,6 +1312,7 @@ static __always_inline void set_ptes(struct mm_struct *mm, unsigned long addr,
> if (likely(nr == 1)) {
> contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
> __set_ptes(mm, addr, ptep, pte, 1);
> + contpte_try_fold(mm, addr, ptep, pte);
> } else {
> contpte_set_ptes(mm, addr, ptep, pte, nr);
> }
> diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
> index 80346108450b..2c7dafd0552a 100644
> --- a/arch/arm64/mm/contpte.c
> +++ b/arch/arm64/mm/contpte.c
> @@ -67,6 +67,70 @@ static void contpte_convert(struct mm_struct *mm, unsigned long addr,
> __set_ptes(mm, start_addr, start_ptep, pte, CONT_PTES);
> }
>
> +void __contpte_try_fold(struct mm_struct *mm, unsigned long addr,
> + pte_t *ptep, pte_t pte)
> +{
> + /*
> + * We have already checked that the virtual and pysical addresses are
> + * correctly aligned for a contpte mapping in contpte_try_fold() so the
> + * remaining checks are to ensure that the contpte range is fully
> + * covered by a single folio, and ensure that all the ptes are valid
> + * with contiguous PFNs and matching prots. We ignore the state of the
> + * access and dirty bits for the purpose of deciding if its a contiguous
> + * range; the folding process will generate a single contpte entry which
> + * has a single access and dirty bit. Those 2 bits are the logical OR of
> + * their respective bits in the constituent pte entries. In order to
> + * ensure the contpte range is covered by a single folio, we must
> + * recover the folio from the pfn, but special mappings don't have a
> + * folio backing them. Fortunately contpte_try_fold() already checked
> + * that the pte is not special - we never try to fold special mappings.
> + * Note we can't use vm_normal_page() for this since we don't have the
> + * vma.
> + */
> +
> + unsigned long folio_saddr, folio_eaddr;
> + unsigned long cont_saddr, cont_eaddr;
> + pte_t expected_pte, subpte;
> + struct folio *folio;
> + struct page *page;
> + unsigned long pfn;
> + pte_t *orig_ptep;
> + pgprot_t prot;
> +
> + int i;
> +
> + if (!mm_is_user(mm))
> + return;
> +
> + page = pte_page(pte);
> + folio = page_folio(page);
> + folio_saddr = addr - (page - &folio->page) * PAGE_SIZE;
> + folio_eaddr = folio_saddr + folio_nr_pages(folio) * PAGE_SIZE;
> + cont_saddr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
> + cont_eaddr = cont_saddr + CONT_PTE_SIZE;
I assume that the 's' in *_sddar is for "start", and the 'e' in *_eaddr is for
"end". Could we use "start" and "end" directly, e.g. folio_start, folio_end?
> +
> + if (folio_saddr > cont_saddr || folio_eaddr < cont_eaddr)
> + return;
> +
> + pfn = pte_pfn(pte) - ((addr - cont_saddr) >> PAGE_SHIFT);
IIUC this should be the same as:
pfn = ALIGN_DOWN(pte_pfn(pte), NR_CONT_PTES);
.. which would align with the way we generate 'cont_saddr' above.
Otherwise, this looks good to me.
Mark.
> + prot = pte_pgprot(pte_mkold(pte_mkclean(pte)));
> + expected_pte = pfn_pte(pfn, prot);
> + orig_ptep = ptep;
> + ptep = contpte_align_down(ptep);
> +
> + for (i = 0; i < CONT_PTES; i++) {
> + subpte = pte_mkold(pte_mkclean(__ptep_get(ptep)));
> + if (!pte_same(subpte, expected_pte))
> + return;
> + expected_pte = pte_advance_pfn(expected_pte, 1);
> + ptep++;
> + }
> +
> + pte = pte_mkcont(pte);
> + contpte_convert(mm, addr, orig_ptep, pte);
> +}
> +EXPORT_SYMBOL(__contpte_try_fold);
> +
> void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr,
> pte_t *ptep, pte_t pte)
> {
> --
> 2.25.1
>
Powered by blists - more mailing lists