[PATCH v7 18/37] arm64/sme: Implement SVCR context switching

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 v7 18/37] arm64/sme: Implement SVCR context switching
Date: Fri, 10 Dec 2021 18:41:14 +0000	[thread overview]
Message-ID: <20211210184133.320748-19-broonie@kernel.org> (raw)
In-Reply-To: <20211210184133.320748-1-broonie@kernel.org>

In SME the use of both streaming SVE mode and ZA are tracked through
PSTATE.SM and PSTATE.ZA, visible through the system register SVCR.  In
order to context switch the floating point state for SME we need to
context switch the contents of this register as part of context
switching the floating point state.

Since changing the vector length exits streaming SVE mode and disables
ZA we also make sure we update SVCR appropriately when setting vector
length, and similarly ensure that new threads have streaming SVE mode
and ZA disabled.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm64/include/asm/processor.h   |  1 +
 arch/arm64/include/asm/thread_info.h |  1 +
 arch/arm64/kernel/fpsimd.c           | 11 +++++++++++
 arch/arm64/kernel/process.c          |  2 ++
 4 files changed, 15 insertions(+)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 008a1767ebff..7e08a4d48c24 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -168,6 +168,7 @@ struct thread_struct {
 	u64			mte_ctrl;
 #endif
 	u64			sctlr_user;
+	u64			svcr;
 	u64			tpidr2_el0;
 };
 
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 4e6b58dcd6f9..848739c15de8 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -82,6 +82,7 @@ int arch_dup_task_struct(struct task_struct *dst,
 #define TIF_SVE_VL_INHERIT	24	/* Inherit SVE vl_onexec across exec */
 #define TIF_SSBD		25	/* Wants SSB mitigation */
 #define TIF_TAGGED_ADDR		26	/* Allow tagged user addresses */
+#define TIF_SME			27	/* SME in use */
 #define TIF_SME_VL_INHERIT	28	/* Inherit SME vl_onexec across exec */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 0af82c518979..d6e6bec6b490 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -355,6 +355,9 @@ static void task_fpsimd_load(void)
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
 
+	if (IS_ENABLED(CONFIG_ARM64_SME) && test_thread_flag(TIF_SME))
+		write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0);
+
 	if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) {
 		sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
 		sve_load_state(sve_pffr(&current->thread),
@@ -380,6 +383,10 @@ static void fpsimd_save(void)
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
 		return;
 
+	if (IS_ENABLED(CONFIG_ARM64_SME) &&
+	    test_thread_flag(TIF_SME))
+		current->thread.svcr = read_sysreg_s(SYS_SVCR_EL0);
+
 	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
 	    test_thread_flag(TIF_SVE)) {
 		if (WARN_ON(sve_get_vl() != last->sve_vl)) {
@@ -731,6 +738,10 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	if (test_and_clear_tsk_thread_flag(task, TIF_SVE))
 		sve_to_fpsimd(task);
 
+	if (system_supports_sme() && type == ARM64_VEC_SME)
+		task->thread.svcr &= ~(SYS_SVCR_EL0_SM_MASK |
+				       SYS_SVCR_EL0_ZA_MASK);
+
 	if (task == current)
 		put_cpu_fpsimd_context();
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 3adca0123943..eff50e02b4e2 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -309,6 +309,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	dst->thread.sve_state = NULL;
 	clear_tsk_thread_flag(dst, TIF_SVE);
 
+	dst->thread.svcr = 0;
+
 	/* clear any pending asynchronous tag fault raised by the parent */
 	clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
 
-- 
2.30.2

