All of lore.kernel.org
 help / color / mirror / Atom feed
From: Catalin Marinas <catalin.marinas@arm.com>
To: Mark Brown <broonie@kernel.org>
Cc: Will Deacon <will@kernel.org>, Marc Zyngier <maz@kernel.org>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Shuah Khan <shuah@kernel.org>,
	Alan Hayward <alan.hayward@arm.com>,
	Luis Machado <luis.machado@arm.com>,
	Salil Akerkar <Salil.Akerkar@arm.com>,
	Basant Kumar Dwivedi <Basant.KumarDwivedi@arm.com>,
	Szabolcs Nagy <szabolcs.nagy@arm.com>,
	James Morse <james.morse@arm.com>,
	Alexandru Elisei <alexandru.elisei@arm.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Luca Salabrino <luca.scalabrino@arm.com>,
	linux-arm-kernel@lists.infradead.org,
	linux-kselftest@vger.kernel.org, kvmarm@lists.cs.columbia.edu
Subject: Re: [PATCH v14 16/39] arm64/sme: Implement traps and syscall handling for SME
Date: Fri, 22 Apr 2022 17:28:02 +0100	[thread overview]
Message-ID: <YmLXkgwNv3n/zl9T@arm.com> (raw)
In-Reply-To: <20220419112247.711548-17-broonie@kernel.org>

On Tue, Apr 19, 2022 at 12:22:24PM +0100, Mark Brown wrote:
> By default all SME operations in userspace will trap.  When this happens
> we allocate storage space for the SME register state, set up the SVE
> registers and disable traps.  We do not need to initialize ZA since the
> architecture guarantees that it will be zeroed when enabled and when we
> trap ZA is disabled.
> 
> On syscall we exit streaming mode if we were previously in it and ensure
> that all but the lower 128 bits of the registers are zeroed while
> preserving the state of ZA. This follows the aarch64 PCS for SME, ZA
> state is preserved over a function call and streaming mode is exited.
> Since the traps for SME do not distinguish between streaming mode SVE
> and ZA usage if ZA is in use rather than reenabling traps we instead
> zero the parts of the SVE registers not shared with FPSIMD and leave SME
> enabled, this simplifies handling SME traps. If ZA is not in use then we
> reenable SME traps and fall through to normal handling of SVE.
> 
> Signed-off-by: Mark Brown <broonie@kernel.org>

Re-adding my reviewed-by following the update.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>

WARNING: multiple messages have this Message-ID (diff)
From: Catalin Marinas <catalin.marinas@arm.com>
To: Mark Brown <broonie@kernel.org>
Cc: Basant Kumar Dwivedi <Basant.KumarDwivedi@arm.com>,
	Will Deacon <will@kernel.org>,
	Luis Machado <luis.machado@arm.com>,
	Szabolcs Nagy <szabolcs.nagy@arm.com>,
	Marc Zyngier <maz@kernel.org>,
	Shuah Khan <skhan@linuxfoundation.org>,
	linux-arm-kernel@lists.infradead.org,
	linux-kselftest@vger.kernel.org,
	Alan Hayward <alan.hayward@arm.com>,
	Shuah Khan <shuah@kernel.org>,
	kvmarm@lists.cs.columbia.edu,
	Salil Akerkar <Salil.Akerkar@arm.com>,
	Luca Salabrino <luca.scalabrino@arm.com>
Subject: Re: [PATCH v14 16/39] arm64/sme: Implement traps and syscall handling for SME
Date: Fri, 22 Apr 2022 17:28:02 +0100	[thread overview]
Message-ID: <YmLXkgwNv3n/zl9T@arm.com> (raw)
In-Reply-To: <20220419112247.711548-17-broonie@kernel.org>

On Tue, Apr 19, 2022 at 12:22:24PM +0100, Mark Brown wrote:
> By default all SME operations in userspace will trap.  When this happens
> we allocate storage space for the SME register state, set up the SVE
> registers and disable traps.  We do not need to initialize ZA since the
> architecture guarantees that it will be zeroed when enabled and when we
> trap ZA is disabled.
> 
> On syscall we exit streaming mode if we were previously in it and ensure
> that all but the lower 128 bits of the registers are zeroed while
> preserving the state of ZA. This follows the aarch64 PCS for SME, ZA
> state is preserved over a function call and streaming mode is exited.
> Since the traps for SME do not distinguish between streaming mode SVE
> and ZA usage if ZA is in use rather than reenabling traps we instead
> zero the parts of the SVE registers not shared with FPSIMD and leave SME
> enabled, this simplifies handling SME traps. If ZA is not in use then we
> reenable SME traps and fall through to normal handling of SVE.
> 
> Signed-off-by: Mark Brown <broonie@kernel.org>

Re-adding my reviewed-by following the update.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

WARNING: multiple messages have this Message-ID (diff)
From: Catalin Marinas <catalin.marinas@arm.com>
To: Mark Brown <broonie@kernel.org>
Cc: Will Deacon <will@kernel.org>, Marc Zyngier <maz@kernel.org>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Shuah Khan <shuah@kernel.org>,
	Alan Hayward <alan.hayward@arm.com>,
	Luis Machado <luis.machado@arm.com>,
	Salil Akerkar <Salil.Akerkar@arm.com>,
	Basant Kumar Dwivedi <Basant.KumarDwivedi@arm.com>,
	Szabolcs Nagy <szabolcs.nagy@arm.com>,
	James Morse <james.morse@arm.com>,
	Alexandru Elisei <alexandru.elisei@arm.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Luca Salabrino <luca.scalabrino@arm.com>,
	linux-arm-kernel@lists.infradead.org,
	linux-kselftest@vger.kernel.org, kvmarm@lists.cs.columbia.edu
Subject: Re: [PATCH v14 16/39] arm64/sme: Implement traps and syscall handling for SME
Date: Fri, 22 Apr 2022 17:28:02 +0100	[thread overview]
Message-ID: <YmLXkgwNv3n/zl9T@arm.com> (raw)
In-Reply-To: <20220419112247.711548-17-broonie@kernel.org>

On Tue, Apr 19, 2022 at 12:22:24PM +0100, Mark Brown wrote:
> By default all SME operations in userspace will trap.  When this happens
> we allocate storage space for the SME register state, set up the SVE
> registers and disable traps.  We do not need to initialize ZA since the
> architecture guarantees that it will be zeroed when enabled and when we
> trap ZA is disabled.
> 
> On syscall we exit streaming mode if we were previously in it and ensure
> that all but the lower 128 bits of the registers are zeroed while
> preserving the state of ZA. This follows the aarch64 PCS for SME, ZA
> state is preserved over a function call and streaming mode is exited.
> Since the traps for SME do not distinguish between streaming mode SVE
> and ZA usage if ZA is in use rather than reenabling traps we instead
> zero the parts of the SVE registers not shared with FPSIMD and leave SME
> enabled, this simplifies handling SME traps. If ZA is not in use then we
> reenable SME traps and fall through to normal handling of SVE.
> 
> Signed-off-by: Mark Brown <broonie@kernel.org>

Re-adding my reviewed-by following the update.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>

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

  reply	other threads:[~2022-04-22 16:28 UTC|newest]

Thread overview: 177+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-19 11:22 [PATCH v14 00/39] arm64/sme: Initial support for the Scalable Matrix Extension Mark Brown
2022-04-19 11:22 ` Mark Brown
2022-04-19 11:22 ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 01/39] kselftest/arm64: Fix comment for ptrace_sve_get_fpsimd_data() Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 02/39] kselftest/arm64: Remove assumption that tasks start FPSIMD only Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 03/39] kselftest/arm64: Validate setting via FPSIMD and read via SVE regsets Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 04/39] arm64/sme: Provide ABI documentation for SME Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-28  9:19   ` Catalin Marinas
2022-04-28  9:19     ` Catalin Marinas
2022-04-28  9:19     ` Catalin Marinas
2022-05-03  8:13     ` Szabolcs Nagy
2022-05-03  8:13       ` Szabolcs Nagy
2022-05-03  8:13       ` Szabolcs Nagy
2022-04-19 11:22 ` [PATCH v14 05/39] arm64/sme: System register and exception syndrome definitions Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 06/39] arm64/sme: Manually encode SME instructions Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 07/39] arm64/sme: Early CPU setup for SME Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 08/39] arm64/sme: Basic enumeration support Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 09/39] arm64/sme: Identify supported SME vector lengths at boot Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 10/39] arm64/sme: Implement sysctl to set the default vector length Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 11/39] arm64/sme: Implement vector length configuration prctl()s Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 12/39] arm64/sme: Implement support for TPIDR2 Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 13/39] arm64/sme: Implement SVCR context switching Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 14/39] arm64/sme: Implement streaming SVE " Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 15/39] arm64/sme: Implement ZA " Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 16/39] arm64/sme: Implement traps and syscall handling for SME Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-22 16:28   ` Catalin Marinas [this message]
2022-04-22 16:28     ` Catalin Marinas
2022-04-22 16:28     ` Catalin Marinas
2022-12-07 14:00   ` Zenghui Yu
2022-12-07 14:00     ` Zenghui Yu
2022-12-07 14:00     ` Zenghui Yu
2022-12-07 14:16     ` Mark Brown
2022-12-07 14:16       ` Mark Brown
2022-12-07 14:16       ` Mark Brown
2022-12-08  2:15       ` Zenghui Yu
2022-12-08  2:15         ` Zenghui Yu
2022-12-08  2:15         ` Zenghui Yu
2022-04-19 11:22 ` [PATCH v14 17/39] arm64/sme: Disable ZA and streaming mode when handling signals Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 18/39] arm64/sme: Implement streaming SVE signal handling Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 19/39] arm64/sme: Implement ZA " Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 20/39] arm64/sme: Implement ptrace support for streaming mode SVE registers Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 21/39] arm64/sme: Add ptrace support for ZA Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 22/39] arm64/sme: Disable streaming mode and ZA when flushing CPU state Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 23/39] arm64/sme: Save and restore streaming mode over EFI runtime calls Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 24/39] KVM: arm64: Hide SME system registers from guests Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 25/39] KVM: arm64: Trap SME usage in guest Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 26/39] KVM: arm64: Handle SME host state when running guests Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 27/39] arm64/sme: Provide Kconfig for SME Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
     [not found]   ` <CGME20220426221433eucas1p253f6350eacf87d8cac2c05adc903656e@eucas1p2.samsung.com>
2022-04-26 22:14     ` Marek Szyprowski
2022-04-26 22:14       ` Marek Szyprowski
2022-04-26 22:14       ` Marek Szyprowski
2022-04-27 12:55       ` Mark Brown
2022-04-27 12:55         ` Mark Brown
2022-04-27 12:55         ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 28/39] kselftest/arm64: Add manual encodings for SME instructions Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 29/39] kselftest/arm64: sme: Add SME support to vlset Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 30/39] kselftest/arm64: Add tests for TPIDR2 Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 31/39] kselftest/arm64: Extend vector configuration API tests to cover SME Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 32/39] kselftest/arm64: sme: Provide streaming mode SVE stress test Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 33/39] kselftest/arm64: signal: Handle ZA signal context in core code Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 34/39] kselftest/arm64: Add stress test for SME ZA context switching Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 35/39] kselftest/arm64: signal: Add SME signal handling tests Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 36/39] kselftest/arm64: Add streaming SVE to SVE ptrace tests Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 37/39] kselftest/arm64: Add coverage for the ZA ptrace interface Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 38/39] kselftest/arm64: Add SME support to syscall ABI test Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22 ` [PATCH v14 39/39] selftests/arm64: Add a testcase for handling of ZA on clone() Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-19 11:22   ` Mark Brown
2022-04-22 17:10 ` [PATCH v14 00/39] arm64/sme: Initial support for the Scalable Matrix Extension Marc Zyngier
2022-04-22 17:10   ` Marc Zyngier
2022-04-22 17:10   ` Marc Zyngier
2022-04-22 18:35   ` Catalin Marinas
2022-04-22 18:35     ` Catalin Marinas
2022-04-22 18:35     ` Catalin Marinas
2022-04-22 18:26 ` (subset) " Catalin Marinas
2022-04-22 18:26   ` Catalin Marinas
2022-04-22 18:26   ` Catalin Marinas
2022-04-27 17:08 ` Qian Cai
2022-04-27 17:08   ` Qian Cai
2022-04-27 17:08   ` Qian Cai
2022-04-27 17:14   ` Mark Brown
2022-04-27 17:14     ` Mark Brown
2022-04-27 17:14     ` Mark Brown
2022-04-27 21:08     ` Qian Cai
2022-04-27 21:08       ` Qian Cai
2022-04-27 21:08       ` Qian Cai
2022-04-27 22:13       ` Mark Brown
2022-04-27 22:13         ` Mark Brown
2022-04-27 22:13         ` Mark Brown
2022-05-03 22:23 ` Qian Cai
2022-05-03 22:23   ` Qian Cai
2022-05-03 22:23   ` Qian Cai
2022-05-03 23:52   ` Mark Brown
2022-05-03 23:52     ` Mark Brown
2022-05-03 23:52     ` Mark Brown
2022-05-04  5:25     ` Naresh Kamboju
2022-05-04  5:25       ` Naresh Kamboju
2022-05-04  5:25       ` Naresh Kamboju
2022-05-04  7:49     ` Naresh Kamboju
2022-05-04  7:49       ` Naresh Kamboju
2022-05-04  7:49       ` Naresh Kamboju

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=YmLXkgwNv3n/zl9T@arm.com \
    --to=catalin.marinas@arm.com \
    --cc=Basant.KumarDwivedi@arm.com \
    --cc=Salil.Akerkar@arm.com \
    --cc=alan.hayward@arm.com \
    --cc=alexandru.elisei@arm.com \
    --cc=broonie@kernel.org \
    --cc=james.morse@arm.com \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=luca.scalabrino@arm.com \
    --cc=luis.machado@arm.com \
    --cc=maz@kernel.org \
    --cc=shuah@kernel.org \
    --cc=skhan@linuxfoundation.org \
    --cc=suzuki.poulose@arm.com \
    --cc=szabolcs.nagy@arm.com \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

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

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.