[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <8cf6c576-f0e2-9a52-6919-cb5e27d2ffb5@huawei.com>
Date: Wed, 25 Mar 2020 10:47:31 +0800
From: Zhenyu Ye <yezhenyu2@...wei.com>
To: Marc Zyngier <maz@...nel.org>
CC: <will@...nel.org>, <mark.rutland@....com>,
<catalin.marinas@....com>, <aneesh.kumar@...ux.ibm.com>,
<akpm@...ux-foundation.org>, <npiggin@...il.com>,
<peterz@...radead.org>, <arnd@...db.de>, <rostedt@...dmis.org>,
<suzuki.poulose@....com>, <tglx@...utronix.de>,
<yuzhao@...gle.com>, <Dave.Martin@....com>, <steven.price@....com>,
<broonie@...nel.org>, <guohanjun@...wei.com>,
<linux-arm-kernel@...ts.infradead.org>,
<linux-kernel@...r.kernel.org>, <linux-arch@...r.kernel.org>,
<linux-mm@...ck.org>, <arm@...nel.org>, <xiexiangyou@...wei.com>,
<prime.zeng@...ilicon.com>, <zhangshaokun@...ilicon.com>
Subject: Re: [RFC PATCH v4 3/6] arm64: Add level-hinted TLB invalidation
helper to tlbi_user
Hi Marc,
On 2020/3/24 22:19, Marc Zyngier wrote:
> On Tue, 24 Mar 2020 21:45:31 +0800
> Zhenyu Ye <yezhenyu2@...wei.com> wrote:
>
>> Add a level-hinted parameter to __tlbi_user, which only gets used
>> if ARMv8.4-TTL gets detected.
>>
>> ARMv8.4-TTL provides the TTL field in tlbi instruction to indicate
>> the level of translation table walk holding the leaf entry for the
>> address that is being invalidated.
>>
>> This patch set the default level value to 0.
>>
>> Signed-off-by: Zhenyu Ye <yezhenyu2@...wei.com>
>> ---
>> arch/arm64/include/asm/tlbflush.h | 42 ++++++++++++++++++++++++++-----
>> 1 file changed, 36 insertions(+), 6 deletions(-)
>>
>> diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
>> index a3f70778a325..d141c080e494 100644
>> --- a/arch/arm64/include/asm/tlbflush.h
>> +++ b/arch/arm64/include/asm/tlbflush.h
>> @@ -89,6 +89,36 @@
>> __tlbi(op, arg); \
>> } while(0)
>>
>> +#define __tlbi_user_level(op, addr, level) \
>> + do { \
>> + u64 arg = addr; \
>> + \
>> + if (!arm64_kernel_unmapped_at_el0()) \
>> + break; \
>> + \
>> + if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) && \
>> + level) { \
>> + u64 ttl = level; \
>> + \
>> + switch (PAGE_SIZE) { \
>> + case SZ_4K: \
>> + ttl |= 1 << 2; \
>> + break; \
>> + case SZ_16K: \
>> + ttl |= 2 << 2; \
>> + break; \
>> + case SZ_64K: \
>> + ttl |= 3 << 2; \
>> + break; \
>> + } \
>> + \
>> + arg &= ~TLBI_TTL_MASK; \
>> + arg |= FIELD_PREP(TLBI_TTL_MASK, ttl); \
>> + } \
>> + \
>> + __tlbi(op, (arg) | USER_ASID_FLAG);
>> \
>> + } while (0)
>> +
>
> Isn't this just:
>
> define __tlbi_user_level(op, addr, level) \
> do { \
> if (!arm64_kernel_unmapped_at_el0()) \
> break; \
> \
> __tlbi_level(op, addr | USER_ASID_FLAG, level); \
> } while (0)
>
> Thanks,
>
> M.
>
Yeah, your code is more clear! I will take it in next version. ;-)
Thanks,
zhenyu
Powered by blists - more mailing lists