All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mark Brown <broonie@kernel.org>
To: Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>, Marc Zyngier <maz@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>,
	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,
	Mark Brown <broonie@kernel.org>
Subject: [PATCH v14 14/39] arm64/sme: Implement streaming SVE context switching
Date: Tue, 19 Apr 2022 12:22:22 +0100	[thread overview]
Message-ID: <20220419112247.711548-15-broonie@kernel.org> (raw)
In-Reply-To: <20220419112247.711548-1-broonie@kernel.org>

When in streaming mode we need to save and restore the streaming mode
SVE register state rather than the regular SVE register state. This uses
the streaming mode vector length and omits FFR but is otherwise identical,
if TIF_SVE is enabled when we are in streaming mode then streaming mode
takes precedence.

This does not handle use of streaming SVE state with KVM, ptrace or
signals. This will be updated in further patches.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h       |  22 +++++-
 arch/arm64/include/asm/fpsimdmacros.h |  11 +++
 arch/arm64/include/asm/processor.h    |  10 +++
 arch/arm64/kernel/entry-fpsimd.S      |   5 ++
 arch/arm64/kernel/fpsimd.c            | 109 +++++++++++++++++++++-----
 arch/arm64/kvm/fpsimd.c               |   2 +-
 6 files changed, 136 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 821d270980da..cd94f5c5b516 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -47,11 +47,21 @@ 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,
-				     u64 *svcr);
+				     unsigned int sme_vl, u64 *svcr);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
 
+static inline bool thread_sm_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK);
+}
+
+static inline bool thread_za_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_ZA_MASK);
+}
+
 /* Maximum VL that SVE/SME VL-agnostic software can transparently support */
 #define VL_ARCH_MAX 0x100
 
@@ -63,7 +73,14 @@ static inline size_t sve_ffr_offset(int vl)
 
 static inline void *sve_pffr(struct thread_struct *thread)
 {
-	return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread));
+	unsigned int vl;
+
+	if (system_supports_sme() && thread_sm_enabled(thread))
+		vl = thread_get_sme_vl(thread);
+	else
+		vl = thread_get_sve_vl(thread);
+
+	return (char *)thread->sve_state + sve_ffr_offset(vl);
 }
 
 extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
@@ -72,6 +89,7 @@ extern void sve_load_state(void const *state, u32 const *pfpsr,
 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);
 
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index 2e9a33155081..f6ab36e0cd8d 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -262,6 +262,17 @@
 921:
 .endm
 
+/* Update SMCR_EL1.LEN with the new VQ */
+.macro sme_load_vq xvqminus1, xtmp, xtmp2
+		mrs_s		\xtmp, SYS_SMCR_EL1
+		bic		\xtmp2, \xtmp, SMCR_ELx_LEN_MASK
+		orr		\xtmp2, \xtmp2, \xvqminus1
+		cmp		\xtmp2, \xtmp
+		b.eq		921f
+		msr_s		SYS_SMCR_EL1, \xtmp2	//self-synchronising
+921:
+.endm
+
 /* Preserve the first 128-bits of Znz and zero the rest. */
 .macro _sve_flush_z nz
 	_sve_check_zreg \nz
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 22cd11e86854..7542310b4e6b 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -184,6 +184,11 @@ static inline unsigned int thread_get_sve_vl(struct thread_struct *thread)
 	return thread_get_vl(thread, ARM64_VEC_SVE);
 }
 
+static inline unsigned int thread_get_sme_vl(struct thread_struct *thread)
+{
+	return thread_get_vl(thread, ARM64_VEC_SME);
+}
+
 unsigned int task_get_vl(const struct task_struct *task, enum vec_type type);
 void task_set_vl(struct task_struct *task, enum vec_type type,
 		 unsigned long vl);
@@ -197,6 +202,11 @@ static inline unsigned int task_get_sve_vl(const struct task_struct *task)
 	return task_get_vl(task, ARM64_VEC_SVE);
 }
 
+static inline unsigned int task_get_sme_vl(const struct task_struct *task)
+{
+	return task_get_vl(task, ARM64_VEC_SME);
+}
+
 static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl)
 {
 	task_set_vl(task, ARM64_VEC_SVE, vl);
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index deee5f01462e..6f88c0f86d50 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -94,4 +94,9 @@ SYM_FUNC_START(sme_get_vl)
 	ret
 SYM_FUNC_END(sme_get_vl)
 
+SYM_FUNC_START(sme_set_vq)
+	sme_load_vq x0, x1, x2
+	ret
+SYM_FUNC_END(sme_set_vq)
+
 #endif /* CONFIG_ARM64_SME */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 1c113349f6cc..f8506a875eb2 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -123,6 +123,7 @@ struct fpsimd_last_state_struct {
 	void *sve_state;
 	u64 *svcr;
 	unsigned int sve_vl;
+	unsigned int sme_vl;
 };
 
 static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
@@ -301,17 +302,28 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
 	task->thread.vl_onexec[type] = vl;
 }
 
+/*
+ * TIF_SME controls whether a task can use SME without trapping while
+ * in userspace, when TIF_SME is set then we must have storage
+ * alocated in sve_state and za_state to store the contents of both ZA
+ * and the SVE registers for both streaming and non-streaming modes.
+ *
+ * If both SVCR.ZA and SVCR.SM are disabled then at any point we
+ * may disable TIF_SME and reenable traps.
+ */
+
+
 /*
  * TIF_SVE controls whether a task can use SVE without trapping while
- * in userspace, and also the way a task's FPSIMD/SVE state is stored
- * in thread_struct.
+ * in userspace, and also (together with TIF_SME) the way a task's
+ * FPSIMD/SVE state is stored in thread_struct.
  *
  * The kernel uses this flag to track whether a user task is actively
  * using SVE, and therefore whether full SVE register state needs to
  * be tracked.  If not, the cheaper FPSIMD context handling code can
  * be used instead of the more costly SVE equivalents.
  *
- *  * TIF_SVE set:
+ *  * TIF_SVE or SVCR.SM set:
  *
  *    The task can execute SVE instructions while in userspace without
  *    trapping to the kernel.
@@ -319,7 +331,8 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  *    When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
  *    corresponding Zn), P0-P15 and FFR are encoded in in
  *    task->thread.sve_state, formatted appropriately for vector
- *    length task->thread.sve_vl.
+ *    length task->thread.sve_vl or, if SVCR.SM is set,
+ *    task->thread.sme_vl.
  *
  *    task->thread.sve_state must point to a valid buffer at least
  *    sve_state_size(task) bytes in size.
@@ -357,19 +370,40 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  */
 static void task_fpsimd_load(void)
 {
+	bool restore_sve_regs = false;
+	bool restore_ffr;
+
 	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);
-
+	/* Check if we should restore SVE first */
 	if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) {
 		sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
+		restore_sve_regs = true;
+		restore_ffr = true;
+	}
+
+	/* Restore SME, override SVE register configuration if needed */
+	if (system_supports_sme()) {
+		unsigned long sme_vl = task_get_sme_vl(current);
+
+		if (test_thread_flag(TIF_SME))
+			sme_set_vq(sve_vq_from_vl(sme_vl) - 1);
+
+		write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0);
+
+		if (thread_sm_enabled(&current->thread)) {
+			restore_sve_regs = true;
+			restore_ffr = system_supports_fa64();
+		}
+	}
+
+	if (restore_sve_regs)
 		sve_load_state(sve_pffr(&current->thread),
-			       &current->thread.uw.fpsimd_state.fpsr, true);
-	} else {
+			       &current->thread.uw.fpsimd_state.fpsr,
+			       restore_ffr);
+	else
 		fpsimd_load_state(&current->thread.uw.fpsimd_state);
-	}
 }
 
 /*
@@ -387,6 +421,9 @@ static void fpsimd_save(void)
 	struct fpsimd_last_state_struct const *last =
 		this_cpu_ptr(&fpsimd_last_state);
 	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
+	bool save_sve_regs = false;
+	bool save_ffr;
+	unsigned int vl;
 
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
@@ -394,15 +431,33 @@ static void fpsimd_save(void)
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
 		return;
 
-	if (IS_ENABLED(CONFIG_ARM64_SME) &&
-	    test_thread_flag(TIF_SME)) {
+	if (test_thread_flag(TIF_SVE)) {
+		save_sve_regs = true;
+		save_ffr = true;
+		vl = last->sve_vl;
+	}
+
+	if (system_supports_sme()) {
 		u64 *svcr = last->svcr;
 		*svcr = read_sysreg_s(SYS_SVCR_EL0);
+
+		if (thread_za_enabled(&current->thread)) {
+			/* ZA state managment is not implemented yet */
+			force_signal_inject(SIGKILL, SI_KERNEL, 0, 0);
+			return;
+		}
+
+		/* If we are in streaming mode override regular SVE. */
+		if (*svcr & SYS_SVCR_EL0_SM_MASK) {
+			save_sve_regs = true;
+			save_ffr = system_supports_fa64();
+			vl = last->sme_vl;
+		}
 	}
 
-	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
-	    test_thread_flag(TIF_SVE)) {
-		if (WARN_ON(sve_get_vl() != last->sve_vl)) {
+	if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) {
+		/* Get the configured VL from RDVL, will account for SM */
+		if (WARN_ON(sve_get_vl() != vl)) {
 			/*
 			 * Can't save the user regs, so current would
 			 * re-enter user with corrupt state.
@@ -413,8 +468,8 @@ static void fpsimd_save(void)
 		}
 
 		sve_save_state((char *)last->sve_state +
-					sve_ffr_offset(last->sve_vl),
-			       &last->st->fpsr, true);
+					sve_ffr_offset(vl),
+			       &last->st->fpsr, save_ffr);
 	} else {
 		fpsimd_save_state(last->st);
 	}
@@ -619,7 +674,14 @@ static void sve_to_fpsimd(struct task_struct *task)
  */
 static size_t sve_state_size(struct task_struct const *task)
 {
-	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task_get_sve_vl(task)));
+	unsigned int vl = 0;
+
+	if (system_supports_sve())
+		vl = task_get_sve_vl(task);
+	if (system_supports_sme())
+		vl = max(vl, task_get_sme_vl(task));
+
+	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl));
 }
 
 /*
@@ -748,7 +810,8 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	}
 
 	fpsimd_flush_task_state(task);
-	if (test_and_clear_tsk_thread_flag(task, TIF_SVE))
+	if (test_and_clear_tsk_thread_flag(task, TIF_SVE) ||
+	    thread_sm_enabled(&task->thread))
 		sve_to_fpsimd(task);
 
 	if (system_supports_sme() && type == ARM64_VEC_SME)
@@ -1375,6 +1438,9 @@ void fpsimd_flush_thread(void)
 		fpsimd_flush_thread_vl(ARM64_VEC_SVE);
 	}
 
+	if (system_supports_sme())
+		fpsimd_flush_thread_vl(ARM64_VEC_SME);
+
 	put_cpu_fpsimd_context();
 }
 
@@ -1418,6 +1484,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
 	last->sve_vl = task_get_sve_vl(current);
+	last->sme_vl = task_get_sme_vl(current);
 	last->svcr = &current->thread.svcr;
 	current->thread.fpsimd_cpu = smp_processor_id();
 
@@ -1433,7 +1500,8 @@ 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, u64 *svcr)
+			      unsigned int sve_vl, unsigned int sme_vl,
+			      u64 *svcr)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -1445,6 +1513,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 	last->svcr = svcr;
 	last->sve_state = sve_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 ac09f1f682ff..394e583bb73e 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -116,7 +116,7 @@ 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,
-					 NULL);
+					 0, NULL);
 
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));
-- 
2.30.2


WARNING: multiple messages have this Message-ID (diff)
From: Mark Brown <broonie@kernel.org>
To: Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>, Marc Zyngier <maz@kernel.org>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Shuah Khan <shuah@kernel.org>
Cc: Basant Kumar Dwivedi <Basant.KumarDwivedi@arm.com>,
	Luis Machado <luis.machado@arm.com>,
	Szabolcs Nagy <szabolcs.nagy@arm.com>,
	Mark Brown <broonie@kernel.org>,
	linux-arm-kernel@lists.infradead.org,
	linux-kselftest@vger.kernel.org,
	Alan Hayward <alan.hayward@arm.com>,
	kvmarm@lists.cs.columbia.edu,
	Salil Akerkar <Salil.Akerkar@arm.com>,
	Luca Salabrino <luca.scalabrino@arm.com>
Subject: [PATCH v14 14/39] arm64/sme: Implement streaming SVE context switching
Date: Tue, 19 Apr 2022 12:22:22 +0100	[thread overview]
Message-ID: <20220419112247.711548-15-broonie@kernel.org> (raw)
In-Reply-To: <20220419112247.711548-1-broonie@kernel.org>

When in streaming mode we need to save and restore the streaming mode
SVE register state rather than the regular SVE register state. This uses
the streaming mode vector length and omits FFR but is otherwise identical,
if TIF_SVE is enabled when we are in streaming mode then streaming mode
takes precedence.

This does not handle use of streaming SVE state with KVM, ptrace or
signals. This will be updated in further patches.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h       |  22 +++++-
 arch/arm64/include/asm/fpsimdmacros.h |  11 +++
 arch/arm64/include/asm/processor.h    |  10 +++
 arch/arm64/kernel/entry-fpsimd.S      |   5 ++
 arch/arm64/kernel/fpsimd.c            | 109 +++++++++++++++++++++-----
 arch/arm64/kvm/fpsimd.c               |   2 +-
 6 files changed, 136 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 821d270980da..cd94f5c5b516 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -47,11 +47,21 @@ 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,
-				     u64 *svcr);
+				     unsigned int sme_vl, u64 *svcr);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
 
+static inline bool thread_sm_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK);
+}
+
+static inline bool thread_za_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_ZA_MASK);
+}
+
 /* Maximum VL that SVE/SME VL-agnostic software can transparently support */
 #define VL_ARCH_MAX 0x100
 
@@ -63,7 +73,14 @@ static inline size_t sve_ffr_offset(int vl)
 
 static inline void *sve_pffr(struct thread_struct *thread)
 {
-	return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread));
+	unsigned int vl;
+
+	if (system_supports_sme() && thread_sm_enabled(thread))
+		vl = thread_get_sme_vl(thread);
+	else
+		vl = thread_get_sve_vl(thread);
+
+	return (char *)thread->sve_state + sve_ffr_offset(vl);
 }
 
 extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
@@ -72,6 +89,7 @@ extern void sve_load_state(void const *state, u32 const *pfpsr,
 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);
 
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index 2e9a33155081..f6ab36e0cd8d 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -262,6 +262,17 @@
 921:
 .endm
 
+/* Update SMCR_EL1.LEN with the new VQ */
+.macro sme_load_vq xvqminus1, xtmp, xtmp2
+		mrs_s		\xtmp, SYS_SMCR_EL1
+		bic		\xtmp2, \xtmp, SMCR_ELx_LEN_MASK
+		orr		\xtmp2, \xtmp2, \xvqminus1
+		cmp		\xtmp2, \xtmp
+		b.eq		921f
+		msr_s		SYS_SMCR_EL1, \xtmp2	//self-synchronising
+921:
+.endm
+
 /* Preserve the first 128-bits of Znz and zero the rest. */
 .macro _sve_flush_z nz
 	_sve_check_zreg \nz
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 22cd11e86854..7542310b4e6b 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -184,6 +184,11 @@ static inline unsigned int thread_get_sve_vl(struct thread_struct *thread)
 	return thread_get_vl(thread, ARM64_VEC_SVE);
 }
 
+static inline unsigned int thread_get_sme_vl(struct thread_struct *thread)
+{
+	return thread_get_vl(thread, ARM64_VEC_SME);
+}
+
 unsigned int task_get_vl(const struct task_struct *task, enum vec_type type);
 void task_set_vl(struct task_struct *task, enum vec_type type,
 		 unsigned long vl);
@@ -197,6 +202,11 @@ static inline unsigned int task_get_sve_vl(const struct task_struct *task)
 	return task_get_vl(task, ARM64_VEC_SVE);
 }
 
+static inline unsigned int task_get_sme_vl(const struct task_struct *task)
+{
+	return task_get_vl(task, ARM64_VEC_SME);
+}
+
 static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl)
 {
 	task_set_vl(task, ARM64_VEC_SVE, vl);
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index deee5f01462e..6f88c0f86d50 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -94,4 +94,9 @@ SYM_FUNC_START(sme_get_vl)
 	ret
 SYM_FUNC_END(sme_get_vl)
 
+SYM_FUNC_START(sme_set_vq)
+	sme_load_vq x0, x1, x2
+	ret
+SYM_FUNC_END(sme_set_vq)
+
 #endif /* CONFIG_ARM64_SME */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 1c113349f6cc..f8506a875eb2 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -123,6 +123,7 @@ struct fpsimd_last_state_struct {
 	void *sve_state;
 	u64 *svcr;
 	unsigned int sve_vl;
+	unsigned int sme_vl;
 };
 
 static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
@@ -301,17 +302,28 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
 	task->thread.vl_onexec[type] = vl;
 }
 
+/*
+ * TIF_SME controls whether a task can use SME without trapping while
+ * in userspace, when TIF_SME is set then we must have storage
+ * alocated in sve_state and za_state to store the contents of both ZA
+ * and the SVE registers for both streaming and non-streaming modes.
+ *
+ * If both SVCR.ZA and SVCR.SM are disabled then at any point we
+ * may disable TIF_SME and reenable traps.
+ */
+
+
 /*
  * TIF_SVE controls whether a task can use SVE without trapping while
- * in userspace, and also the way a task's FPSIMD/SVE state is stored
- * in thread_struct.
+ * in userspace, and also (together with TIF_SME) the way a task's
+ * FPSIMD/SVE state is stored in thread_struct.
  *
  * The kernel uses this flag to track whether a user task is actively
  * using SVE, and therefore whether full SVE register state needs to
  * be tracked.  If not, the cheaper FPSIMD context handling code can
  * be used instead of the more costly SVE equivalents.
  *
- *  * TIF_SVE set:
+ *  * TIF_SVE or SVCR.SM set:
  *
  *    The task can execute SVE instructions while in userspace without
  *    trapping to the kernel.
@@ -319,7 +331,8 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  *    When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
  *    corresponding Zn), P0-P15 and FFR are encoded in in
  *    task->thread.sve_state, formatted appropriately for vector
- *    length task->thread.sve_vl.
+ *    length task->thread.sve_vl or, if SVCR.SM is set,
+ *    task->thread.sme_vl.
  *
  *    task->thread.sve_state must point to a valid buffer at least
  *    sve_state_size(task) bytes in size.
@@ -357,19 +370,40 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  */
 static void task_fpsimd_load(void)
 {
+	bool restore_sve_regs = false;
+	bool restore_ffr;
+
 	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);
-
+	/* Check if we should restore SVE first */
 	if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) {
 		sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
+		restore_sve_regs = true;
+		restore_ffr = true;
+	}
+
+	/* Restore SME, override SVE register configuration if needed */
+	if (system_supports_sme()) {
+		unsigned long sme_vl = task_get_sme_vl(current);
+
+		if (test_thread_flag(TIF_SME))
+			sme_set_vq(sve_vq_from_vl(sme_vl) - 1);
+
+		write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0);
+
+		if (thread_sm_enabled(&current->thread)) {
+			restore_sve_regs = true;
+			restore_ffr = system_supports_fa64();
+		}
+	}
+
+	if (restore_sve_regs)
 		sve_load_state(sve_pffr(&current->thread),
-			       &current->thread.uw.fpsimd_state.fpsr, true);
-	} else {
+			       &current->thread.uw.fpsimd_state.fpsr,
+			       restore_ffr);
+	else
 		fpsimd_load_state(&current->thread.uw.fpsimd_state);
-	}
 }
 
 /*
@@ -387,6 +421,9 @@ static void fpsimd_save(void)
 	struct fpsimd_last_state_struct const *last =
 		this_cpu_ptr(&fpsimd_last_state);
 	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
+	bool save_sve_regs = false;
+	bool save_ffr;
+	unsigned int vl;
 
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
@@ -394,15 +431,33 @@ static void fpsimd_save(void)
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
 		return;
 
-	if (IS_ENABLED(CONFIG_ARM64_SME) &&
-	    test_thread_flag(TIF_SME)) {
+	if (test_thread_flag(TIF_SVE)) {
+		save_sve_regs = true;
+		save_ffr = true;
+		vl = last->sve_vl;
+	}
+
+	if (system_supports_sme()) {
 		u64 *svcr = last->svcr;
 		*svcr = read_sysreg_s(SYS_SVCR_EL0);
+
+		if (thread_za_enabled(&current->thread)) {
+			/* ZA state managment is not implemented yet */
+			force_signal_inject(SIGKILL, SI_KERNEL, 0, 0);
+			return;
+		}
+
+		/* If we are in streaming mode override regular SVE. */
+		if (*svcr & SYS_SVCR_EL0_SM_MASK) {
+			save_sve_regs = true;
+			save_ffr = system_supports_fa64();
+			vl = last->sme_vl;
+		}
 	}
 
-	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
-	    test_thread_flag(TIF_SVE)) {
-		if (WARN_ON(sve_get_vl() != last->sve_vl)) {
+	if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) {
+		/* Get the configured VL from RDVL, will account for SM */
+		if (WARN_ON(sve_get_vl() != vl)) {
 			/*
 			 * Can't save the user regs, so current would
 			 * re-enter user with corrupt state.
@@ -413,8 +468,8 @@ static void fpsimd_save(void)
 		}
 
 		sve_save_state((char *)last->sve_state +
-					sve_ffr_offset(last->sve_vl),
-			       &last->st->fpsr, true);
+					sve_ffr_offset(vl),
+			       &last->st->fpsr, save_ffr);
 	} else {
 		fpsimd_save_state(last->st);
 	}
@@ -619,7 +674,14 @@ static void sve_to_fpsimd(struct task_struct *task)
  */
 static size_t sve_state_size(struct task_struct const *task)
 {
-	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task_get_sve_vl(task)));
+	unsigned int vl = 0;
+
+	if (system_supports_sve())
+		vl = task_get_sve_vl(task);
+	if (system_supports_sme())
+		vl = max(vl, task_get_sme_vl(task));
+
+	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl));
 }
 
 /*
@@ -748,7 +810,8 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	}
 
 	fpsimd_flush_task_state(task);
-	if (test_and_clear_tsk_thread_flag(task, TIF_SVE))
+	if (test_and_clear_tsk_thread_flag(task, TIF_SVE) ||
+	    thread_sm_enabled(&task->thread))
 		sve_to_fpsimd(task);
 
 	if (system_supports_sme() && type == ARM64_VEC_SME)
@@ -1375,6 +1438,9 @@ void fpsimd_flush_thread(void)
 		fpsimd_flush_thread_vl(ARM64_VEC_SVE);
 	}
 
+	if (system_supports_sme())
+		fpsimd_flush_thread_vl(ARM64_VEC_SME);
+
 	put_cpu_fpsimd_context();
 }
 
@@ -1418,6 +1484,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
 	last->sve_vl = task_get_sve_vl(current);
+	last->sme_vl = task_get_sme_vl(current);
 	last->svcr = &current->thread.svcr;
 	current->thread.fpsimd_cpu = smp_processor_id();
 
@@ -1433,7 +1500,8 @@ 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, u64 *svcr)
+			      unsigned int sve_vl, unsigned int sme_vl,
+			      u64 *svcr)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -1445,6 +1513,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 	last->svcr = svcr;
 	last->sve_state = sve_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 ac09f1f682ff..394e583bb73e 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -116,7 +116,7 @@ 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,
-					 NULL);
+					 0, NULL);
 
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));
-- 
2.30.2

_______________________________________________
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: Mark Brown <broonie@kernel.org>
To: Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>, Marc Zyngier <maz@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>,
	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,
	Mark Brown <broonie@kernel.org>
Subject: [PATCH v14 14/39] arm64/sme: Implement streaming SVE context switching
Date: Tue, 19 Apr 2022 12:22:22 +0100	[thread overview]
Message-ID: <20220419112247.711548-15-broonie@kernel.org> (raw)
In-Reply-To: <20220419112247.711548-1-broonie@kernel.org>

When in streaming mode we need to save and restore the streaming mode
SVE register state rather than the regular SVE register state. This uses
the streaming mode vector length and omits FFR but is otherwise identical,
if TIF_SVE is enabled when we are in streaming mode then streaming mode
takes precedence.

This does not handle use of streaming SVE state with KVM, ptrace or
signals. This will be updated in further patches.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h       |  22 +++++-
 arch/arm64/include/asm/fpsimdmacros.h |  11 +++
 arch/arm64/include/asm/processor.h    |  10 +++
 arch/arm64/kernel/entry-fpsimd.S      |   5 ++
 arch/arm64/kernel/fpsimd.c            | 109 +++++++++++++++++++++-----
 arch/arm64/kvm/fpsimd.c               |   2 +-
 6 files changed, 136 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 821d270980da..cd94f5c5b516 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -47,11 +47,21 @@ 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,
-				     u64 *svcr);
+				     unsigned int sme_vl, u64 *svcr);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
 
+static inline bool thread_sm_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK);
+}
+
+static inline bool thread_za_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_ZA_MASK);
+}
+
 /* Maximum VL that SVE/SME VL-agnostic software can transparently support */
 #define VL_ARCH_MAX 0x100
 
@@ -63,7 +73,14 @@ static inline size_t sve_ffr_offset(int vl)
 
 static inline void *sve_pffr(struct thread_struct *thread)
 {
-	return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread));
+	unsigned int vl;
+
+	if (system_supports_sme() && thread_sm_enabled(thread))
+		vl = thread_get_sme_vl(thread);
+	else
+		vl = thread_get_sve_vl(thread);
+
+	return (char *)thread->sve_state + sve_ffr_offset(vl);
 }
 
 extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
@@ -72,6 +89,7 @@ extern void sve_load_state(void const *state, u32 const *pfpsr,
 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);
 
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index 2e9a33155081..f6ab36e0cd8d 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -262,6 +262,17 @@
 921:
 .endm
 
+/* Update SMCR_EL1.LEN with the new VQ */
+.macro sme_load_vq xvqminus1, xtmp, xtmp2
+		mrs_s		\xtmp, SYS_SMCR_EL1
+		bic		\xtmp2, \xtmp, SMCR_ELx_LEN_MASK
+		orr		\xtmp2, \xtmp2, \xvqminus1
+		cmp		\xtmp2, \xtmp
+		b.eq		921f
+		msr_s		SYS_SMCR_EL1, \xtmp2	//self-synchronising
+921:
+.endm
+
 /* Preserve the first 128-bits of Znz and zero the rest. */
 .macro _sve_flush_z nz
 	_sve_check_zreg \nz
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 22cd11e86854..7542310b4e6b 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -184,6 +184,11 @@ static inline unsigned int thread_get_sve_vl(struct thread_struct *thread)
 	return thread_get_vl(thread, ARM64_VEC_SVE);
 }
 
+static inline unsigned int thread_get_sme_vl(struct thread_struct *thread)
+{
+	return thread_get_vl(thread, ARM64_VEC_SME);
+}
+
 unsigned int task_get_vl(const struct task_struct *task, enum vec_type type);
 void task_set_vl(struct task_struct *task, enum vec_type type,
 		 unsigned long vl);
@@ -197,6 +202,11 @@ static inline unsigned int task_get_sve_vl(const struct task_struct *task)
 	return task_get_vl(task, ARM64_VEC_SVE);
 }
 
+static inline unsigned int task_get_sme_vl(const struct task_struct *task)
+{
+	return task_get_vl(task, ARM64_VEC_SME);
+}
+
 static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl)
 {
 	task_set_vl(task, ARM64_VEC_SVE, vl);
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index deee5f01462e..6f88c0f86d50 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -94,4 +94,9 @@ SYM_FUNC_START(sme_get_vl)
 	ret
 SYM_FUNC_END(sme_get_vl)
 
+SYM_FUNC_START(sme_set_vq)
+	sme_load_vq x0, x1, x2
+	ret
+SYM_FUNC_END(sme_set_vq)
+
 #endif /* CONFIG_ARM64_SME */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 1c113349f6cc..f8506a875eb2 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -123,6 +123,7 @@ struct fpsimd_last_state_struct {
 	void *sve_state;
 	u64 *svcr;
 	unsigned int sve_vl;
+	unsigned int sme_vl;
 };
 
 static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
@@ -301,17 +302,28 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
 	task->thread.vl_onexec[type] = vl;
 }
 
+/*
+ * TIF_SME controls whether a task can use SME without trapping while
+ * in userspace, when TIF_SME is set then we must have storage
+ * alocated in sve_state and za_state to store the contents of both ZA
+ * and the SVE registers for both streaming and non-streaming modes.
+ *
+ * If both SVCR.ZA and SVCR.SM are disabled then at any point we
+ * may disable TIF_SME and reenable traps.
+ */
+
+
 /*
  * TIF_SVE controls whether a task can use SVE without trapping while
- * in userspace, and also the way a task's FPSIMD/SVE state is stored
- * in thread_struct.
+ * in userspace, and also (together with TIF_SME) the way a task's
+ * FPSIMD/SVE state is stored in thread_struct.
  *
  * The kernel uses this flag to track whether a user task is actively
  * using SVE, and therefore whether full SVE register state needs to
  * be tracked.  If not, the cheaper FPSIMD context handling code can
  * be used instead of the more costly SVE equivalents.
  *
- *  * TIF_SVE set:
+ *  * TIF_SVE or SVCR.SM set:
  *
  *    The task can execute SVE instructions while in userspace without
  *    trapping to the kernel.
@@ -319,7 +331,8 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  *    When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
  *    corresponding Zn), P0-P15 and FFR are encoded in in
  *    task->thread.sve_state, formatted appropriately for vector
- *    length task->thread.sve_vl.
+ *    length task->thread.sve_vl or, if SVCR.SM is set,
+ *    task->thread.sme_vl.
  *
  *    task->thread.sve_state must point to a valid buffer at least
  *    sve_state_size(task) bytes in size.
@@ -357,19 +370,40 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  */
 static void task_fpsimd_load(void)
 {
+	bool restore_sve_regs = false;
+	bool restore_ffr;
+
 	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);
-
+	/* Check if we should restore SVE first */
 	if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) {
 		sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
+		restore_sve_regs = true;
+		restore_ffr = true;
+	}
+
+	/* Restore SME, override SVE register configuration if needed */
+	if (system_supports_sme()) {
+		unsigned long sme_vl = task_get_sme_vl(current);
+
+		if (test_thread_flag(TIF_SME))
+			sme_set_vq(sve_vq_from_vl(sme_vl) - 1);
+
+		write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0);
+
+		if (thread_sm_enabled(&current->thread)) {
+			restore_sve_regs = true;
+			restore_ffr = system_supports_fa64();
+		}
+	}
+
+	if (restore_sve_regs)
 		sve_load_state(sve_pffr(&current->thread),
-			       &current->thread.uw.fpsimd_state.fpsr, true);
-	} else {
+			       &current->thread.uw.fpsimd_state.fpsr,
+			       restore_ffr);
+	else
 		fpsimd_load_state(&current->thread.uw.fpsimd_state);
-	}
 }
 
 /*
@@ -387,6 +421,9 @@ static void fpsimd_save(void)
 	struct fpsimd_last_state_struct const *last =
 		this_cpu_ptr(&fpsimd_last_state);
 	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
+	bool save_sve_regs = false;
+	bool save_ffr;
+	unsigned int vl;
 
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
@@ -394,15 +431,33 @@ static void fpsimd_save(void)
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
 		return;
 
-	if (IS_ENABLED(CONFIG_ARM64_SME) &&
-	    test_thread_flag(TIF_SME)) {
+	if (test_thread_flag(TIF_SVE)) {
+		save_sve_regs = true;
+		save_ffr = true;
+		vl = last->sve_vl;
+	}
+
+	if (system_supports_sme()) {
 		u64 *svcr = last->svcr;
 		*svcr = read_sysreg_s(SYS_SVCR_EL0);
+
+		if (thread_za_enabled(&current->thread)) {
+			/* ZA state managment is not implemented yet */
+			force_signal_inject(SIGKILL, SI_KERNEL, 0, 0);
+			return;
+		}
+
+		/* If we are in streaming mode override regular SVE. */
+		if (*svcr & SYS_SVCR_EL0_SM_MASK) {
+			save_sve_regs = true;
+			save_ffr = system_supports_fa64();
+			vl = last->sme_vl;
+		}
 	}
 
-	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
-	    test_thread_flag(TIF_SVE)) {
-		if (WARN_ON(sve_get_vl() != last->sve_vl)) {
+	if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) {
+		/* Get the configured VL from RDVL, will account for SM */
+		if (WARN_ON(sve_get_vl() != vl)) {
 			/*
 			 * Can't save the user regs, so current would
 			 * re-enter user with corrupt state.
@@ -413,8 +468,8 @@ static void fpsimd_save(void)
 		}
 
 		sve_save_state((char *)last->sve_state +
-					sve_ffr_offset(last->sve_vl),
-			       &last->st->fpsr, true);
+					sve_ffr_offset(vl),
+			       &last->st->fpsr, save_ffr);
 	} else {
 		fpsimd_save_state(last->st);
 	}
@@ -619,7 +674,14 @@ static void sve_to_fpsimd(struct task_struct *task)
  */
 static size_t sve_state_size(struct task_struct const *task)
 {
-	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task_get_sve_vl(task)));
+	unsigned int vl = 0;
+
+	if (system_supports_sve())
+		vl = task_get_sve_vl(task);
+	if (system_supports_sme())
+		vl = max(vl, task_get_sme_vl(task));
+
+	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl));
 }
 
 /*
@@ -748,7 +810,8 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	}
 
 	fpsimd_flush_task_state(task);
-	if (test_and_clear_tsk_thread_flag(task, TIF_SVE))
+	if (test_and_clear_tsk_thread_flag(task, TIF_SVE) ||
+	    thread_sm_enabled(&task->thread))
 		sve_to_fpsimd(task);
 
 	if (system_supports_sme() && type == ARM64_VEC_SME)
@@ -1375,6 +1438,9 @@ void fpsimd_flush_thread(void)
 		fpsimd_flush_thread_vl(ARM64_VEC_SVE);
 	}
 
+	if (system_supports_sme())
+		fpsimd_flush_thread_vl(ARM64_VEC_SME);
+
 	put_cpu_fpsimd_context();
 }
 
@@ -1418,6 +1484,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
 	last->sve_vl = task_get_sve_vl(current);
+	last->sme_vl = task_get_sme_vl(current);
 	last->svcr = &current->thread.svcr;
 	current->thread.fpsimd_cpu = smp_processor_id();
 
@@ -1433,7 +1500,8 @@ 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, u64 *svcr)
+			      unsigned int sve_vl, unsigned int sme_vl,
+			      u64 *svcr)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -1445,6 +1513,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 	last->svcr = svcr;
 	last->sve_state = sve_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 ac09f1f682ff..394e583bb73e 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -116,7 +116,7 @@ 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,
-					 NULL);
+					 0, NULL);
 
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));
-- 
2.30.2


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

  parent reply	other threads:[~2022-04-19 11:24 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 ` Mark Brown [this message]
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 ` [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
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=20220419112247.711548-15-broonie@kernel.org \
    --to=broonie@kernel.org \
    --cc=Basant.KumarDwivedi@arm.com \
    --cc=Salil.Akerkar@arm.com \
    --cc=alan.hayward@arm.com \
    --cc=alexandru.elisei@arm.com \
    --cc=catalin.marinas@arm.com \
    --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.