linux-kernel - Re: [PATCH AUTOSEL 5.10 2/8] parisc: Disable debug code regarding cache flushes in handle_nadtlb

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: <786f58e8-aa61-d439-c9bb-4a27599d2aa5@gmx.de>
Date:   Tue, 24 May 2022 18:44:59 +0200
From:   Helge Deller <deller@....de>
To:     Sasha Levin <sashal@...nel.org>, linux-kernel@...r.kernel.org,
        stable@...r.kernel.org
Cc:     John David Anglin <dave.anglin@...l.net>,
        James.Bottomley@...senPartnership.com, akpm@...ux-foundation.org,
        zhengqi.arch@...edance.com, linux-parisc@...r.kernel.org
Subject: Re: [PATCH AUTOSEL 5.10 2/8] parisc: Disable debug code regarding
 cache flushes in handle_nadtlb_fault()

Hello Sascha,

On 5/24/22 18:00, Sasha Levin wrote:
> From: John David Anglin <dave.anglin@...l.net>
>
> [ Upstream commit 67c35a3b646cc68598ff0bb28de5f8bd7b2e81b3 ]
>
> Change the "BUG" to "WARNING" and disable the message because it triggers
> occasionally in spite of the check in flush_cache_page_if_present.

Please drop this patch from the backporting-queue (v5.10, v5.15 and v5.17).
It's not necessary since the warning will only trigger on v5.18 on machines
with PA8800/PA8900 processors.

Thanks.
Helge


> The pte value extracted for the "from" page in copy_user_highpage is racy and
> occasionally the pte is cleared before the flush is complete.  I assume that
> the page is simultaneously flushed by flush_cache_mm before the pte is cleared
> as nullifying the fdc doesn't seem to cause problems.
>
> I investigated various locking scenarios but I wasn't able to find a way to
> sequence the flushes.  This code is called for every COW break and locks impact
> performance.
>
> This patch is related to the bigger cache flush patch because we need the pte
> on PA8800/PA8900 to flush using the vma context.
> I have also seen this from copy_to_user_page and copy_from_user_page.
>
> The messages appear infrequently when enabled.
>
> Signed-off-by: John David Anglin <dave.anglin@...l.net>
> Signed-off-by: Helge Deller <deller@....de>
> Signed-off-by: Sasha Levin <sashal@...nel.org>
> ---
>  arch/parisc/mm/fault.c | 6 ++++--
>  1 file changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
> index 5faa3cff4738..2472780d4039 100644
> --- a/arch/parisc/mm/fault.c
> +++ b/arch/parisc/mm/fault.c
> @@ -22,6 +22,8 @@
>
>  #include <asm/traps.h>
>
> +#define DEBUG_NATLB 0
> +
>  /* Various important other fields */
>  #define bit22set(x)		(x & 0x00000200)
>  #define bits23_25set(x)		(x & 0x000001c0)
> @@ -449,8 +451,8 @@ handle_nadtlb_fault(struct pt_regs *regs)
>  		fallthrough;
>  	case 0x380:
>  		/* PDC and FIC instructions */
> -		if (printk_ratelimit()) {
> -			pr_warn("BUG: nullifying cache flush/purge instruction\n");
> +		if (DEBUG_NATLB && printk_ratelimit()) {
> +			pr_warn("WARNING: nullifying cache flush/purge instruction\n");
>  			show_regs(regs);
>  		}
>  		if (insn & 0x20) {