public inbox for linux-arm-kernel@lists.infradead.org 
 help / color / mirror / Atom feed
From: rokhanna@nvidia•com (Rohit Khanna)
To: linux-arm-kernel@lists•infradead.org
Subject: [PATCH] arm64: alternative:flush cache with unpatched code
Date: Thu, 31 May 2018 17:45:11 +0000	[thread overview]
Message-ID: <1527788750049.85185@nvidia.com> (raw)
In-Reply-To: <20180530090044.GA2452@arm.com>

Will, thanks for the comments.
I will push a new patch set.
We want to avoid using __flush_icache_all as much as possible and hence trying to flush cache by range.

Thanks
Rohit
________________________________________
From: Will Deacon <will.deacon@arm•com>
Sent: Wednesday, May 30, 2018 2:00 AM
To: Rohit Khanna
Cc: catalin.marinas at arm.com; robin.murphy at arm.com; mark.rutland at arm.com; Suzuki.Poulose at arm.com; Bo Yan; Alexander Van Brunt; linux-arm-kernel at lists.infradead.org
Subject: Re: [PATCH] arm64: alternative:flush cache with unpatched code

Hi Rohit,

Please keep me on cc for future versions of this patch. Comments inline.

On Tue, May 29, 2018 at 11:11:28AM -0700, Rohit Khanna wrote:
> In the current implementation,  __apply_alternatives patches
> flush_icache_range and then executes it without invalidating the icache.
> Thus, icache can contain some of the old instructions for
> flush_icache_range. This can cause unpredictable behavior as during
> execution we can get a mix of old and new instructions for
> flush_icache_range.
>
> This patch :
> 1. Adds a new function flush_cache_kernel_range for flushing kernel
> memory range. This function uses non hot-patched code and can be
> safely used to flush cache during code patching.
>
> 2. Modifies __apply_alternatives so that it uses
> flush_cache_kernel_range to flush the cache range after patching code.
>
> Signed-off-by: Rohit Khanna <rokhanna@nvidia•com>
> ---
>  arch/arm64/kernel/alternative.c | 31 +++++++++++++++++++++++++++++--
>  1 file changed, 29 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
> index 5c4bce4ac381..e93cfd26a314 100644
> --- a/arch/arm64/kernel/alternative.c
> +++ b/arch/arm64/kernel/alternative.c
> @@ -122,6 +122,33 @@ static void patch_alternative(struct alt_instr *alt,
>       }
>  }
>
> +/* This is used for flushing kernel memory range after
> + * __apply_alternatives has patched kernel code
> + */
> +static void flush_cache_kernel_range(void *start, void *end)
> +{

How about something like clean_dcache_range_nopatch instead?

> +     u64 d_start, i_start, d_size, i_size;
> +
> +     /* use sanitized value of ctr_el0 rather than raw value from CPU */
> +     d_size = 4 << ((arm64_ftr_reg_ctrel0.sys_val >> 0x10) & 0xF); /* bytes */
> +     i_size = 4 << (arm64_ftr_reg_ctrel0.sys_val & 0xF); /* bytes */

You should be able to use read_sanitised_ftr_reg() and
cpuid_feature_extract_unsigned_field() here.

> +     d_start = (u64)start & ~(d_size - 1);
> +     while (d_start <= (u64)end) {

Please add a comment about the A53 erratum this is handling by using
clean+inv.

> +             asm volatile("dc civac, %0" : : "r" (d_start));
> +             d_start += d_size;
> +     }
> +     dsb(ish);
> +
> +     i_start = (u64)start & ~(i_size - 1);
> +     while (i_start <= (u64)end) {
> +             asm volatile("ic ivau, %0" : : "r" (i_start));
> +             i_start += i_size;
> +     }
> +     dsb(ish);
> +     isb();

As I mentioned before, I think it would be simpler just to avoid doing the
I-cache invalidation by range and instead call __flush_icache_all once we've
exiting the loop in __apply_alternatives.

Will

  reply	other threads:[~2018-05-31 17:45 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-29 18:11 [PATCH] arm64: alternative:flush cache with unpatched code Rohit Khanna
2018-05-30  9:00 ` Will Deacon
2018-05-31 17:45   ` Rohit Khanna [this message]
2018-06-04  9:16     ` Will Deacon
2018-06-04 19:34       ` Alexander Van Brunt
2018-06-05 16:55         ` Will Deacon
2018-06-05 17:07           ` Alexander Van Brunt
2018-06-06 15:44             ` Will Deacon
2018-06-06 16:16               ` Alexander Van Brunt
  -- strict thread matches above, loose matches on Subject: below --
2018-06-02  0:39 Rohit Khanna
2018-05-31 20:37 Rohit Khanna
2018-06-01  9:03 ` Mark Rutland
2018-06-01 19:52   ` Rohit Khanna
2018-06-01 21:43     ` Rohit Khanna
2018-06-04  9:01     ` Mark Rutland
2018-05-22 18:07 Rohit Khanna
2018-05-23  9:06 ` Will Deacon
2018-05-22  1:27 Rohit Khanna
2018-05-22 15:09 ` Suzuki K Poulose
2018-05-22 18:08   ` Rohit Khanna

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=1527788750049.85185@nvidia.com \
    --to=rokhanna@nvidia$(echo .)com \
    --cc=linux-arm-kernel@lists$(echo .)infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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