Re: [RFC PATCH 3/7] arm64: mm: use nGnRnE instead of nGnRE on Apple processors

From: Alexander Graf <graf@amazon.com>
To: Mohamed Mediouni <mohamed.mediouni@caramail.com>
Cc: Mark Rutland <mark.rutland@arm.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Hector Martin <marcan@marcan.st>,
	linux-kernel@vger.kernel.org, Marc Zyngier <maz@kernel.org>,
	Will Deacon <will@kernel.org>,
	linux-arm-kernel@lists.infradead.org,
	Stan Skowronek <stan@corellium.com>
Subject: Re: [RFC PATCH 3/7] arm64: mm: use nGnRnE instead of nGnRE on Apple processors
Date: Wed, 20 Jan 2021 19:10:33 +0100	[thread overview]
Message-ID: <6047872c-8a40-4159-aeb6-ea439bfafd82@amazon.com> (raw)
In-Reply-To: <17579DC5-13AF-48E1-9B72-91B14AB485FA@caramail.com>

On 20.01.21 19:06, Mohamed Mediouni wrote:
> 
>> On 20 Jan 2021, at 17:47, Alexander Graf <graf@amazon.com> wrote:
>>
>> On 20.01.21 14:27, Mohamed Mediouni wrote:
>>> Use nGnRnE instead of nGnRE on Apple SoCs to workaround a serious hardware quirk.
>>> On Apple processors, writes using the nGnRE device memory type get dropped in flight,
>>> getting to nowhere.
>>> Signed-off-by: Stan Skowronek <stan@corellium.com>
>>> Signed-off-by: Mohamed Mediouni <mohamed.mediouni@caramail.com>
>>> ---
>>>   arch/arm64/mm/proc.S | 26 ++++++++++++++++++++++++++
>>>   1 file changed, 26 insertions(+)
>>> diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
>>> index 1f7ee8c8b7b8..06436916f137 100644
>>> --- a/arch/arm64/mm/proc.S
>>> +++ b/arch/arm64/mm/proc.S
>>> @@ -51,6 +51,25 @@
>>>   #define TCR_KASAN_HW_FLAGS 0
>>>   #endif
>>> +#ifdef CONFIG_ARCH_APPLE
>>
>> Is there any particular reason for this #ifdef?
>>
>>
>> Alex
>>
> Not a particular reason, as we explicitly check for the implementer ID. However,
> without CONFIG_ARCH_APPLE, other parts of the support for Apple CPUs
> will not be available anyway.

The ifdef below for code looks ok to me, I'm explicitly wondering why 
you're guarding the #define :)

Alex

>>> +
>>> +/*
>>> + * Apple cores appear to black-hole writes done with nGnRE.
>>> + * We settled on a work-around that uses MAIR vs changing every single user of
>>> + * nGnRE across the arm64 code.
>>> + */
>>> +
>>> +#define MAIR_EL1_SET_APPLE                                          \
>>> +    (MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRnE, MT_DEVICE_nGnRnE) |      \
>>> +     MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRnE, MT_DEVICE_nGnRE) |       \
>>> +     MAIR_ATTRIDX(MAIR_ATTR_DEVICE_GRE, MT_DEVICE_GRE) |            \
>>> +     MAIR_ATTRIDX(MAIR_ATTR_NORMAL_NC, MT_NORMAL_NC) |              \
>>> +     MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) |                    \
>>> +     MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT) |              \
>>> +     MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL_TAGGED))
>>> +
>>> +#endif
>>> +
>>>   /*
>>>    * Default MAIR_EL1. MT_NORMAL_TAGGED is initially mapped as Normal memory and
>>>    * changed during __cpu_setup to Normal Tagged if the system supports MTE.
>>> @@ -432,6 +451,13 @@ SYM_FUNC_START(__cpu_setup)
>>>        * Memory region attributes
>>>        */
>>>       mov_q   x5, MAIR_EL1_SET
>>> +#ifdef CONFIG_ARCH_APPLE
>>> +    mrs     x0, MIDR_EL1
>>> +    lsr     w0, w0, #24
>>> +    mov_q   x1, MAIR_EL1_SET_APPLE
>>> +    cmp     x0, #0x61                       // 0x61 = Implementer: Apple
>>> +    csel    x5, x1, x5, eq
>>> +#endif
>>>   #ifdef CONFIG_ARM64_MTE
>>>       mte_tcr .req    x20
>>> --
>>> 2.29.2

Amazon Development Center Germany GmbH
Krausenstr. 38
10117 Berlin
Geschaeftsfuehrung: Christian Schlaeger, Jonathan Weiss
Eingetragen am Amtsgericht Charlottenburg unter HRB 149173 B
Sitz: Berlin
Ust-ID: DE 289 237 879

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel