[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH] x86: use alternative_input() in cache_flush()
- To: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
- From: Jan Beulich <jbeulich@xxxxxxxx>
- Date: Mon, 30 Sep 2024 17:39:26 +0200
- Autocrypt: addr=jbeulich@xxxxxxxx; keydata= xsDiBFk3nEQRBADAEaSw6zC/EJkiwGPXbWtPxl2xCdSoeepS07jW8UgcHNurfHvUzogEq5xk hu507c3BarVjyWCJOylMNR98Yd8VqD9UfmX0Hb8/BrA+Hl6/DB/eqGptrf4BSRwcZQM32aZK 7Pj2XbGWIUrZrd70x1eAP9QE3P79Y2oLrsCgbZJfEwCgvz9JjGmQqQkRiTVzlZVCJYcyGGsD /0tbFCzD2h20ahe8rC1gbb3K3qk+LpBtvjBu1RY9drYk0NymiGbJWZgab6t1jM7sk2vuf0Py O9Hf9XBmK0uE9IgMaiCpc32XV9oASz6UJebwkX+zF2jG5I1BfnO9g7KlotcA/v5ClMjgo6Gl MDY4HxoSRu3i1cqqSDtVlt+AOVBJBACrZcnHAUSuCXBPy0jOlBhxPqRWv6ND4c9PH1xjQ3NP nxJuMBS8rnNg22uyfAgmBKNLpLgAGVRMZGaGoJObGf72s6TeIqKJo/LtggAS9qAUiuKVnygo 3wjfkS9A3DRO+SpU7JqWdsveeIQyeyEJ/8PTowmSQLakF+3fote9ybzd880fSmFuIEJldWxp Y2ggPGpiZXVsaWNoQHN1c2UuY29tPsJgBBMRAgAgBQJZN5xEAhsDBgsJCAcDAgQVAggDBBYC AwECHgECF4AACgkQoDSui/t3IH4J+wCfQ5jHdEjCRHj23O/5ttg9r9OIruwAn3103WUITZee e7Sbg12UgcQ5lv7SzsFNBFk3nEQQCACCuTjCjFOUdi5Nm244F+78kLghRcin/awv+IrTcIWF hUpSs1Y91iQQ7KItirz5uwCPlwejSJDQJLIS+QtJHaXDXeV6NI0Uef1hP20+y8qydDiVkv6l IreXjTb7DvksRgJNvCkWtYnlS3mYvQ9NzS9PhyALWbXnH6sIJd2O9lKS1Mrfq+y0IXCP10eS FFGg+Av3IQeFatkJAyju0PPthyTqxSI4lZYuJVPknzgaeuJv/2NccrPvmeDg6Coe7ZIeQ8Yj t0ARxu2xytAkkLCel1Lz1WLmwLstV30g80nkgZf/wr+/BXJW/oIvRlonUkxv+IbBM3dX2OV8 AmRv1ySWPTP7AAMFB/9PQK/VtlNUJvg8GXj9ootzrteGfVZVVT4XBJkfwBcpC/XcPzldjv+3 HYudvpdNK3lLujXeA5fLOH+Z/G9WBc5pFVSMocI71I8bT8lIAzreg0WvkWg5V2WZsUMlnDL9 mpwIGFhlbM3gfDMs7MPMu8YQRFVdUvtSpaAs8OFfGQ0ia3LGZcjA6Ik2+xcqscEJzNH+qh8V m5jjp28yZgaqTaRbg3M/+MTbMpicpZuqF4rnB0AQD12/3BNWDR6bmh+EkYSMcEIpQmBM51qM EKYTQGybRCjpnKHGOxG0rfFY1085mBDZCH5Kx0cl0HVJuQKC+dV2ZY5AqjcKwAxpE75MLFkr wkkEGBECAAkFAlk3nEQCGwwACgkQoDSui/t3IH7nnwCfcJWUDUFKdCsBH/E5d+0ZnMQi+G0A nAuWpQkjM1ASeQwSHEeAWPgskBQL
- Cc: Roger Pau Monné <roger.pau@xxxxxxxxxx>, "xen-devel@xxxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxxx>
- Delivery-date: Mon, 30 Sep 2024 15:39:39 +0000
- List-id: Xen developer discussion <xen-devel.lists.xenproject.org>
On 30.09.2024 17:27, Andrew Cooper wrote:
> On 30/09/2024 4:09 pm, Jan Beulich wrote:
>> There's no point using alternative_io() when there are no outputs.
>>
>> No functional change.
>>
>> Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
>>
>> --- a/xen/arch/x86/flushtlb.c
>> +++ b/xen/arch/x86/flushtlb.c
>> @@ -286,11 +286,10 @@ void cache_flush(const void *addr, unsig
>> * + prefix than a clflush + nop, and hence the prefix is added
>> instead
>> * of letting the alternative framework fill the gap by appending
>> nops.
>> */
>> - alternative_io("ds; clflush %[p]",
>> - "data16 clflush %[p]", /* clflushopt */
>> - X86_FEATURE_CLFLUSHOPT,
>> - /* no outputs */,
>> - [p] "m" (*(const char *)(addr)));
>> + alternative_input("ds; clflush %[p]",
>
> Drop the ; as you're altering the line anyway?
Oh, sure.
> Acked-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Thanks.
> However, switching to ds ds will avoid a trailing nop, so will be
> marginally better.
I don't think I understand, which may or may not be due to me not being
sure whether "ds ds" is a typo. What trailing NOP are you seeing? The
"ds" that's there already covers for the sole trailing NOP that would
otherwise result due to the "data16" prefix.
Jan
|
