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
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAK9=C2XEmFBDB6R5f+L9++7ojhWb8rJK-e-vgFrDmsi2=DMOBw@mail.gmail.com>
Date: Mon, 5 Feb 2024 15:25:59 +0530
From: Anup Patel <apatel@...tanamicro.com>
To: Alexandre Ghiti <alex@...ti.fr>
Cc: Palmer Dabbelt <palmer@...belt.com>, Paul Walmsley <paul.walmsley@...ive.com>, 
	Anup Patel <anup@...infault.org>, linux-kernel@...r.kernel.org, 
	Björn Töpel <bjorn@...nel.org>, 
	Atish Patra <atishp@...shpatra.org>, linux-riscv@...ts.infradead.org, 
	Andrew Jones <ajones@...tanamicro.com>
Subject: Re: [PATCH] RISC-V: Don't use IPIs in flush_icache_all() when
 patching text

On Mon, Feb 5, 2024 at 11:52 AM Alexandre Ghiti <alex@...ti.fr> wrote:
>
> Hi Anup,
>
> On 05/02/2024 05:29, Anup Patel wrote:
> > If some of the HARTs are parked by stop machine then IPI-based
> > flushing in flush_icache_all() will hang. This hang is observed
> > when text patching is invoked by various debug and BPF features.
> >
> > To avoid this hang, we force use of SBI-based icache flushing
> > when patching text.
> >
> > Fixes: 627922843235 ("RISC-V: Use IPIs for remote icache flush when possible")
> > Reported-by: Bjorn Topel <bjorn@...nel.org>
> > Closes: https://gist.github.com/bjoto/04a580568378f3b5483af07cd9d22501
> > Signed-off-by: Anup Patel <apatel@...tanamicro.com>
> > ---
> >   arch/riscv/include/asm/cacheflush.h | 7 ++++---
> >   arch/riscv/kernel/hibernate.c       | 2 +-
> >   arch/riscv/kernel/patch.c           | 4 ++--
> >   arch/riscv/mm/cacheflush.c          | 7 ++++---
> >   4 files changed, 11 insertions(+), 9 deletions(-)
> >
> > diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
> > index a129dac4521d..561e079f34af 100644
> > --- a/arch/riscv/include/asm/cacheflush.h
> > +++ b/arch/riscv/include/asm/cacheflush.h
> > @@ -32,7 +32,8 @@ static inline void flush_dcache_page(struct page *page)
> >    * RISC-V doesn't have an instruction to flush parts of the instruction cache,
> >    * so instead we just flush the whole thing.
> >    */
> > -#define flush_icache_range(start, end) flush_icache_all()
> > +#define flush_icache_range(start, end) flush_icache_all(true)
> > +#define flush_icache_patch_range(start, end) flush_icache_all(false)
> >   #define flush_icache_user_page(vma, pg, addr, len) \
> >       flush_icache_mm(vma->vm_mm, 0)
> >
> > @@ -43,12 +44,12 @@ static inline void flush_dcache_page(struct page *page)
> >
> >   #ifndef CONFIG_SMP
> >
> > -#define flush_icache_all() local_flush_icache_all()
> > +#define flush_icache_all(want_ipi) local_flush_icache_all()
> >   #define flush_icache_mm(mm, local) flush_icache_all()
> >
> >   #else /* CONFIG_SMP */
> >
> > -void flush_icache_all(void);
> > +void flush_icache_all(bool want_ipi);
> >   void flush_icache_mm(struct mm_struct *mm, bool local);
> >
> >   #endif /* CONFIG_SMP */
> > diff --git a/arch/riscv/kernel/hibernate.c b/arch/riscv/kernel/hibernate.c
> > index 671b686c0158..388f10e187ba 100644
> > --- a/arch/riscv/kernel/hibernate.c
> > +++ b/arch/riscv/kernel/hibernate.c
> > @@ -153,7 +153,7 @@ int swsusp_arch_suspend(void)
> >       } else {
> >               suspend_restore_csrs(hibernate_cpu_context);
> >               flush_tlb_all();
> > -             flush_icache_all();
> > +             flush_icache_all(true);
> >
> >               /*
> >                * Tell the hibernation core that we've just restored the memory.
> > diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
> > index 37e87fdcf6a0..721e144a7847 100644
> > --- a/arch/riscv/kernel/patch.c
> > +++ b/arch/riscv/kernel/patch.c
> > @@ -182,7 +182,7 @@ int patch_text_set_nosync(void *addr, u8 c, size_t len)
> >       ret = patch_insn_set(tp, c, len);
> >
> >       if (!ret)
> > -             flush_icache_range((uintptr_t)tp, (uintptr_t)tp + len);
> > +             flush_icache_patch_range((uintptr_t)tp, (uintptr_t)tp + len);
> >
> >       return ret;
> >   }
> > @@ -217,7 +217,7 @@ int patch_text_nosync(void *addr, const void *insns, size_t len)
> >       ret = patch_insn_write(tp, insns, len);
> >
> >       if (!ret)
> > -             flush_icache_range((uintptr_t) tp, (uintptr_t) tp + len);
> > +             flush_icache_patch_range((uintptr_t) tp, (uintptr_t) tp + len);
> >
> >       return ret;
> >   }
> > diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
> > index 55a34f2020a8..03cd3d4831ef 100644
> > --- a/arch/riscv/mm/cacheflush.c
> > +++ b/arch/riscv/mm/cacheflush.c
> > @@ -17,11 +17,12 @@ static void ipi_remote_fence_i(void *info)
> >       return local_flush_icache_all();
> >   }
> >
> > -void flush_icache_all(void)
> > +void flush_icache_all(bool want_ipi)
> >   {
> >       local_flush_icache_all();
> >
> > -     if (IS_ENABLED(CONFIG_RISCV_SBI) && !riscv_use_ipi_for_rfence())
> > +     if (IS_ENABLED(CONFIG_RISCV_SBI) &&
> > +         (!want_ipi || !riscv_use_ipi_for_rfence()))
> >               sbi_remote_fence_i(NULL);
> >       else
> >               on_each_cpu(ipi_remote_fence_i, NULL, 1);
> > @@ -87,7 +88,7 @@ void flush_icache_pte(pte_t pte)
> >       struct folio *folio = page_folio(pte_page(pte));
> >
> >       if (!test_bit(PG_dcache_clean, &folio->flags)) {
> > -             flush_icache_all();
> > +             flush_icache_all(true);
> >               set_bit(PG_dcache_clean, &folio->flags);
> >       }
> >   }
>
>
> Since patch_text_cb() is run on all cpus, couldn't we completely avoid
> any remote icache flush by slightly changing patch_text_cb() instead as
> follows?

Unfortunately patch_text_cb() is not the only user of patch_text_nosync
since patch_text_nosync() and patch_text_set_nosync() are called directly
from other places as well.

We have to update all users of patch_text_nosync() and
patch_text_set_nosync() to move to local icache flushes which
is a much bigger change.

Regards,
Anup

>
> diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
> index 37e87fdcf6a0..075c376ed528 100644
> --- a/arch/riscv/kernel/patch.c
> +++ b/arch/riscv/kernel/patch.c
> @@ -232,8 +232,8 @@ static int patch_text_cb(void *data)
>          if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) {
>                  for (i = 0; ret == 0 && i < patch->ninsns; i++) {
>                          len = GET_INSN_LENGTH(patch->insns[i]);
> -                       ret = patch_text_nosync(patch->addr + i * len,
> - &patch->insns[i], len);
> +                       ret = patch_insn_write((u32 *)(patch->addr + i *
> len),
> + &patch->insns[i], len);
>                  }
>                  atomic_inc(&patch->cpu_count);
>          } else {
> @@ -242,6 +242,8 @@ static int patch_text_cb(void *data)
>                  smp_mb();
>          }
>
> +       local_flush_icache_all();
> +
>          return ret;
>   }
>   NOKPROBE_SYMBOL(patch_text_cb);
>
>
>

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ