linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Mark Brown <broonie@kernel.org>
To: Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Shuah Khan <shuah@kernel.org>
Cc: 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>,
	linux-arm-kernel@lists.infradead.org,
	linux-kselftest@vger.kernel.org, Mark Brown <broonie@kernel.org>
Subject: [PATCH v1 23/38] arm64/sme: Implement ZA context switching
Date: Thu, 30 Sep 2021 19:11:29 +0100	[thread overview]
Message-ID: <20210930181144.10029-24-broonie@kernel.org> (raw)
In-Reply-To: <20210930181144.10029-1-broonie@kernel.org>

Allocate space for storing ZA on first access to SME and use that to save
and restore ZA state when context switching. We do this by using the vector
form of the LDR and STR ZA instructions, these do not require streaming
mode and have implementation recommendations that they avoid contention
issues in shared SMCU implementations.

Since ZA is architecturally guaranteed to be zeroed when enabled we do not
need to explicitly zero ZA, either we will be restoring from a saved copy
or trapping on first use of SME so we know that ZA must be disabled.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm64/include/asm/fpsimd.h       |  5 ++++-
 arch/arm64/include/asm/fpsimdmacros.h | 22 ++++++++++++++++++++++
 arch/arm64/include/asm/processor.h    |  1 +
 arch/arm64/kernel/entry-fpsimd.S      | 22 ++++++++++++++++++++++
 arch/arm64/kernel/fpsimd.c            | 16 ++++++++++------
 arch/arm64/kvm/fpsimd.c               |  2 +-
 6 files changed, 60 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 43737ca91f1a..45f7153067bb 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -47,7 +47,7 @@ extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
 
 extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
 				     void *sve_state, unsigned int sve_vl,
-				     unsigned int sme_vl);
+				     void *za_state, unsigned int sme_vl);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
@@ -90,6 +90,8 @@ extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1);
 extern unsigned int sve_get_vl(void);
 extern void sve_set_vq(unsigned long vq_minus_1);
 extern void sme_set_vq(unsigned long vq_minus_1);
+extern void sme_save_state(void *state, unsigned int vq_minus_1);
+extern void sme_load_state(void const *state, unsigned int vq_minus_1);
 
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
@@ -119,6 +121,7 @@ static inline unsigned int __bit_to_vq(unsigned int bit)
 extern size_t sve_state_size(struct task_struct const *task);
 
 extern void sve_alloc(struct task_struct *task);
+extern void sme_alloc(struct task_struct *task);
 extern void fpsimd_release_task(struct task_struct *task);
 extern void fpsimd_sync_to_sve(struct task_struct *task);
 extern void sve_sync_to_fpsimd(struct task_struct *task);
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index c86fc2fc72e9..146f906e9a86 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -309,3 +309,25 @@
 		ldr		w\nxtmp, [\xpfpsr, #4]
 		msr		fpcr, x\nxtmp
 .endm
+
+.macro sme_save_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_str_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm
+
+.macro sme_load_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_ldr_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 338cb03811bd..e4688a58f365 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -153,6 +153,7 @@ struct thread_struct {
 
 	unsigned int		fpsimd_cpu;
 	void			*sve_state;	/* SVE registers, if any */
+	void			*za_state;	/* ZA register, if any */
 	unsigned int		vl[ARM64_VEC_MAX];	/* vector length */
 	unsigned int		vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */
 	unsigned long		fault_address;	/* fault info */
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 55eb45b3faa9..8ee5f32a81fd 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -94,4 +94,26 @@ SYM_FUNC_START(sme_set_vq)
 	ret
 SYM_FUNC_END(sme_set_vq)
 
+/*
+ * Save the SME state
+ *
+ * x0 - pointer to buffer for state
+ * x1 - Bytes per vector
+ */
+SYM_FUNC_START(sme_save_state)
+	sme_save_za 0, x1, 12
+	ret
+SYM_FUNC_END(sme_save_state)
+
+/*
+ * Load the SME state
+ *
+ * x0 - pointer to buffer for state
+ * x1 - bytes per vector
+ */
+SYM_FUNC_START(sme_load_state)
+	sme_load_za 0, x1, 12
+	ret
+SYM_FUNC_END(sme_load_state)
+
 #endif /* CONFIG_ARM64_SME */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 89b94e8c81fd..4ef95690b30e 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -117,6 +117,7 @@
 struct fpsimd_last_state_struct {
 	struct user_fpsimd_state *st;
 	void *sve_state;
+	void *za_state;
 	unsigned int sve_vl;
 	unsigned int sme_vl;
 };
@@ -387,6 +388,9 @@ static void task_fpsimd_load(void)
 
 		write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0);
 
+		if (thread_za_enabled(&current->thread))
+			sme_load_state(current->thread.za_state, sme_vl);
+
 		if (thread_sm_enabled(&current->thread)) {
 			restore_sve_regs = true;
 			restore_ffr = false;
@@ -434,11 +438,8 @@ static void fpsimd_save(void)
 					      SYS_SVCR_EL0_SM_MASK)))
 			clear_thread_flag(TIF_SME);
 
-		if (thread_za_enabled(&current->thread)) {
-			/* ZA state managment is not implemented yet */
-			force_signal_inject(SIGKILL, SI_KERNEL, 0, 0);
-			return;
-		}
+		if (thread_za_enabled(&current->thread))
+			sme_save_state(last->za_state, last->sme_vl);
 
 		/* If we are in streaming mode override regular SVE. */
 		if (thread_sm_enabled(&current->thread)) {
@@ -1476,6 +1477,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	WARN_ON(!system_supports_fpsimd());
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
+	last->za_state = current->thread.za_state;
 	last->sve_vl = task_get_sve_vl(current);
 	last->sme_vl = task_get_sme_vl(current);
 	current->thread.fpsimd_cpu = smp_processor_id();
@@ -1492,7 +1494,8 @@ static void fpsimd_bind_task_to_cpu(void)
 }
 
 void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
-			      unsigned int sve_vl, unsigned int sme_vl)
+			      unsigned int sve_vl, void *za_state,
+			      unsigned int sme_vl)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -1502,6 +1505,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 
 	last->st = st;
 	last->sve_state = sve_state;
+	last->za_state = za_state;
 	last->sve_vl = sve_vl;
 	last->sme_vl = sme_vl;
 }
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index d96871002081..007b2e8b9ae9 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -100,7 +100,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs,
 					 vcpu->arch.sve_state,
 					 vcpu->arch.sve_max_vl,
-					 0);
+					 NULL, 0);
 
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));
-- 
2.20.1


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

  parent reply	other threads:[~2021-09-30 18:34 UTC|newest]

Thread overview: 69+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-30 18:11 [PATCH v1 00/38] arm64/sme: Initial support for the Scalable Matrix Extension Mark Brown
2021-09-30 18:11 ` [PATCH v1 01/38] arm64/fp: Reindent fpsimd_save() Mark Brown
2021-10-11  9:39   ` Jonathan Cameron
2021-10-11 13:02     ` Mark Brown
2021-09-30 18:11 ` [PATCH v1 02/38] arm64/sve: Remove sve_load_from_fpsimd_state() Mark Brown
2021-09-30 18:11 ` [PATCH v1 03/38] arm64/sve: Make access to FFR optional Mark Brown
2021-09-30 18:11 ` [PATCH v1 04/38] arm64/sve: Rename find_supported_vector_length() Mark Brown
2021-09-30 18:11 ` [PATCH v1 05/38] arm64/sve: Use accessor functions for vector lengths in thread_struct Mark Brown
2021-09-30 18:11 ` [PATCH v1 06/38] arm64/sve: Put system wide vector length information into structs Mark Brown
2021-10-01  3:13   ` kernel test robot
2021-09-30 18:11 ` [PATCH v1 07/38] arm64/sve: Explicitly load vector length when restoring SVE state Mark Brown
2021-09-30 18:11 ` [PATCH v1 08/38] arm64/sve: Track vector lengths for tasks in an array Mark Brown
2021-10-11 10:20   ` Jonathan Cameron
2021-10-11 13:14     ` Mark Brown
2021-10-11 13:18       ` Jonathan Cameron
2021-09-30 18:11 ` [PATCH v1 09/38] arm64/sve: Make sysctl interface for SVE reusable by SME Mark Brown
2021-09-30 18:11 ` [PATCH v1 10/38] arm64/sve: Generalise vector length configuration prctl() for SME Mark Brown
2021-10-11 10:27   ` Jonathan Cameron
2021-10-11 13:18     ` Mark Brown
2021-09-30 18:11 ` [PATCH v1 11/38] selftests: arm64: Parameterise ptrace vector length information Mark Brown
2021-09-30 18:11 ` [PATCH v1 12/38] arm64/sme: Provide ABI documentation for SME Mark Brown
2021-10-08 14:11   ` Alan Hayward
2021-10-08 15:28     ` Mark Brown
2021-10-08 16:45       ` Alan Hayward
2021-10-08 17:04         ` Mark Brown
2021-10-11 11:15           ` Alan Hayward
2021-10-11 11:48             ` Mark Brown
2021-10-11 11:05   ` Jonathan Cameron
2021-10-11 13:20     ` Mark Brown
2021-10-11 13:17   ` Szabolcs Nagy
2021-10-11 13:23     ` Mark Brown
2021-10-11 14:19       ` Szabolcs Nagy
2021-10-11 20:10         ` Mark Brown
2021-10-12  8:23           ` Szabolcs Nagy
2021-10-13 18:37             ` Mark Brown
2021-10-14  9:57               ` Szabolcs Nagy
2021-09-30 18:11 ` [PATCH v1 13/38] arm64/sme: System register and exception syndrome definitions Mark Brown
2021-09-30 18:11 ` [PATCH v1 14/38] arm64/sme: Define macros for manually encoding SME instructions Mark Brown
2021-09-30 18:11 ` [PATCH v1 15/38] arm64/sme: Early CPU setup for SME Mark Brown
2021-09-30 18:11 ` [PATCH v1 16/38] arm64/sme: Basic enumeration support Mark Brown
2021-09-30 18:11 ` [PATCH v1 17/38] arm64/sme: Identify supported SME vector lengths at boot Mark Brown
2021-09-30 18:11 ` [PATCH v1 18/38] arm64/sme: Implement sysctl to set the default vector length Mark Brown
2021-09-30 18:11 ` [PATCH v1 19/38] arm64/sme: Implement vector length configuration prctl()s Mark Brown
2021-10-01  5:20   ` kernel test robot
2021-10-01 12:40     ` Mark Brown
2021-10-08  1:32       ` [kbuild-all] " Chen, Rong A
2021-10-01 16:38   ` kernel test robot
2021-09-30 18:11 ` [PATCH v1 20/38] arm64/sme: Implement support for TPIDR2 Mark Brown
2021-09-30 18:11 ` [PATCH v1 21/38] arm64/sme: Implement SVCR context switching Mark Brown
2021-10-11 12:15   ` Jonathan Cameron
2021-09-30 18:11 ` [PATCH v1 22/38] arm64/sme: Implement streaming SVE " Mark Brown
2021-09-30 18:11 ` Mark Brown [this message]
2021-10-11 12:27   ` [PATCH v1 23/38] arm64/sme: Implement ZA " Jonathan Cameron
2021-09-30 18:11 ` [PATCH v1 24/38] arm64/sme: Implement traps and syscall handling for SME Mark Brown
2021-10-11 12:37   ` Jonathan Cameron
2021-09-30 18:11 ` [PATCH v1 25/38] arm64/sme: Implement streaming SVE signal handling Mark Brown
2021-09-30 18:11 ` [PATCH v1 26/38] arm64/sme: Implement ZA " Mark Brown
2021-09-30 18:11 ` [PATCH v1 27/38] arm64/sme: Implement ptrace support for streaming mode SVE registers Mark Brown
2021-09-30 18:11 ` [PATCH v1 28/38] arm64/sme: Add ptrace support for ZA Mark Brown
2021-09-30 18:11 ` [PATCH v1 29/38] arm64/sme: Disable streaming mode and ZA when flushing CPU state Mark Brown
2021-09-30 18:11 ` [PATCH v1 30/38] arm64/sme: Save and restore streaming mode over EFI runtime calls Mark Brown
2021-09-30 18:11 ` [PATCH v1 31/38] arm64/sme: Provide Kconfig for SME Mark Brown
2021-09-30 18:11 ` [PATCH v1 32/38] kselftest/arm64: Add tests for TPIDR2 Mark Brown
2021-09-30 18:11 ` [PATCH v1 33/38] kselftest/arm64: Extend vector configuration API tests to cover SME Mark Brown
2021-09-30 18:11 ` [PATCH v1 34/38] kselftest/arm64: sme: Provide streaming mode SVE stress test Mark Brown
2021-09-30 18:11 ` [PATCH v1 35/38] kselftest/arm64: Add stress test for SME ZA context switching Mark Brown
2021-09-30 18:11 ` [PATCH v1 36/38] kselftest/arm64: signal: Add SME signal handling tests Mark Brown
2021-09-30 18:11 ` [PATCH v1 37/38] selftests: arm64: Add streaming SVE to SVE ptrace tests Mark Brown
2021-09-30 18:11 ` [PATCH v1 38/38] selftests: arm64: Add coverage for the ZA ptrace interface Mark Brown

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=20210930181144.10029-24-broonie@kernel.org \
    --to=broonie@kernel.org \
    --cc=Basant.KumarDwivedi@arm.com \
    --cc=Salil.Akerkar@arm.com \
    --cc=alan.hayward@arm.com \
    --cc=catalin.marinas@arm.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=luis.machado@arm.com \
    --cc=shuah@kernel.org \
    --cc=skhan@linuxfoundation.org \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).