| 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: <7eeed961-c2c0-2aeb-ff8c-3717de09d605@csgroup.eu>
Date: Tue, 22 Aug 2023 09:38:47 +0000
From: Christophe Leroy <christophe.leroy@...roup.eu>
To: Kefeng Wang <wangkefeng.wang@...wei.com>,
Andrew Morton <akpm@...ux-foundation.org>,
"linux-mm@...ck.org" <linux-mm@...ck.org>
CC: "surenb@...gle.com" <surenb@...gle.com>,
"willy@...radead.org" <willy@...radead.org>,
Russell King <linux@...linux.org.uk>,
Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will@...nel.org>,
Huacai Chen <chenhuacai@...nel.org>,
WANG Xuerui <kernel@...0n.name>,
Michael Ellerman <mpe@...erman.id.au>,
Nicholas Piggin <npiggin@...il.com>,
Paul Walmsley <paul.walmsley@...ive.com>,
Palmer Dabbelt <palmer@...belt.com>,
Albert Ou <aou@...s.berkeley.edu>,
Alexander Gordeev <agordeev@...ux.ibm.com>,
Gerald Schaefer <gerald.schaefer@...ux.ibm.com>,
Heiko Carstens <hca@...ux.ibm.com>,
Vasily Gorbik <gor@...ux.ibm.com>,
Christian Borntraeger <borntraeger@...ux.ibm.com>,
Sven Schnelle <svens@...ux.ibm.com>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Andy Lutomirski <luto@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
"x86@...nel.org" <x86@...nel.org>,
"H . Peter Anvin" <hpa@...or.com>,
"linux-arm-kernel@...ts.infradead.org"
<linux-arm-kernel@...ts.infradead.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"loongarch@...ts.linux.dev" <loongarch@...ts.linux.dev>,
"linuxppc-dev@...ts.ozlabs.org" <linuxppc-dev@...ts.ozlabs.org>,
"linux-riscv@...ts.infradead.org" <linux-riscv@...ts.infradead.org>,
"linux-s390@...r.kernel.org" <linux-s390@...r.kernel.org>
Subject: Re: [PATCH rfc v2 05/10] powerpc: mm: use try_vma_locked_page_fault()
Le 21/08/2023 à 14:30, Kefeng Wang a écrit :
> Use new try_vma_locked_page_fault() helper to simplify code.
> No functional change intended.
Does it really simplifies code ? It's 32 insertions versus 34 deletions
so only removing 2 lines.
I don't like the struct vm_fault you are adding because when it was four
independant variables it was handled through local registers. Now that
it is a struct it has to go via the stack, leading to unnecessary memory
read and writes. And going back and forth between architecture code and
generic code may also be counter-performant.
Did you make any performance analysis ? Page faults are really a hot
path when dealling with minor faults.
Thanks
Christophe
>
> Signed-off-by: Kefeng Wang <wangkefeng.wang@...wei.com>
> ---
> arch/powerpc/mm/fault.c | 66 ++++++++++++++++++++---------------------
> 1 file changed, 32 insertions(+), 34 deletions(-)
>
> diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
> index b1723094d464..52f9546e020e 100644
> --- a/arch/powerpc/mm/fault.c
> +++ b/arch/powerpc/mm/fault.c
> @@ -391,6 +391,22 @@ static int page_fault_is_bad(unsigned long err)
> #define page_fault_is_bad(__err) ((__err) & DSISR_BAD_FAULT_32S)
> #endif
>
> +#ifdef CONFIG_PER_VMA_LOCK
> +bool arch_vma_access_error(struct vm_area_struct *vma, struct vm_fault *vmf)
> +{
> + int is_exec = TRAP(vmf->regs) == INTERRUPT_INST_STORAGE;
> + int is_write = page_fault_is_write(vmf->fault_code);
> +
> + if (unlikely(access_pkey_error(is_write, is_exec,
> + (vmf->fault_code & DSISR_KEYFAULT), vma)))
> + return true;
> +
> + if (unlikely(access_error(is_write, is_exec, vma)))
> + return true;
> + return false;
> +}
> +#endif
> +
> /*
> * For 600- and 800-family processors, the error_code parameter is DSISR
> * for a data fault, SRR1 for an instruction fault.
> @@ -407,12 +423,18 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
> {
> struct vm_area_struct * vma;
> struct mm_struct *mm = current->mm;
> - unsigned int flags = FAULT_FLAG_DEFAULT;
> int is_exec = TRAP(regs) == INTERRUPT_INST_STORAGE;
> int is_user = user_mode(regs);
> int is_write = page_fault_is_write(error_code);
> vm_fault_t fault, major = 0;
> bool kprobe_fault = kprobe_page_fault(regs, 11);
> + struct vm_fault vmf = {
> + .real_address = address,
> + .fault_code = error_code,
> + .regs = regs,
> + .flags = FAULT_FLAG_DEFAULT,
> + };
> +
>
> if (unlikely(debugger_fault_handler(regs) || kprobe_fault))
> return 0;
> @@ -463,45 +485,21 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
> * mmap_lock held
> */
> if (is_user)
> - flags |= FAULT_FLAG_USER;
> + vmf.flags |= FAULT_FLAG_USER;
> if (is_write)
> - flags |= FAULT_FLAG_WRITE;
> + vmf.flags |= FAULT_FLAG_WRITE;
> if (is_exec)
> - flags |= FAULT_FLAG_INSTRUCTION;
> + vmf.flags |= FAULT_FLAG_INSTRUCTION;
>
> - if (!(flags & FAULT_FLAG_USER))
> - goto lock_mmap;
> -
> - vma = lock_vma_under_rcu(mm, address);
> - if (!vma)
> - goto lock_mmap;
> -
> - if (unlikely(access_pkey_error(is_write, is_exec,
> - (error_code & DSISR_KEYFAULT), vma))) {
> - vma_end_read(vma);
> - goto lock_mmap;
> - }
> -
> - if (unlikely(access_error(is_write, is_exec, vma))) {
> - vma_end_read(vma);
> - goto lock_mmap;
> - }
> -
> - fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
> - if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
> - vma_end_read(vma);
> -
> - if (!(fault & VM_FAULT_RETRY)) {
> - count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
> + fault = try_vma_locked_page_fault(&vmf);
> + if (fault == VM_FAULT_NONE)
> + goto retry;
> + if (!(fault & VM_FAULT_RETRY))
> goto done;
> - }
> - count_vm_vma_lock_event(VMA_LOCK_RETRY);
>
> if (fault_signal_pending(fault, regs))
> return user_mode(regs) ? 0 : SIGBUS;
>
> -lock_mmap:
> -
> /* When running in the kernel we expect faults to occur only to
> * addresses in user space. All other faults represent errors in the
> * kernel and should generate an OOPS. Unfortunately, in the case of an
> @@ -528,7 +526,7 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
> * make sure we exit gracefully rather than endlessly redo
> * the fault.
> */
> - fault = handle_mm_fault(vma, address, flags, regs);
> + fault = handle_mm_fault(vma, address, vmf.flags, regs);
>
> major |= fault & VM_FAULT_MAJOR;
>
> @@ -544,7 +542,7 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
> * case.
> */
> if (unlikely(fault & VM_FAULT_RETRY)) {
> - flags |= FAULT_FLAG_TRIED;
> + vmf.flags |= FAULT_FLAG_TRIED;
> goto retry;
> }
>
Powered by blists - more mailing lists