summaryrefslogtreecommitdiff
path: root/arch/arm64/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/include')
-rw-r--r--arch/arm64/include/asm/fpsimd.h22
-rw-r--r--arch/arm64/include/asm/fpsimdmacros.h11
-rw-r--r--arch/arm64/include/asm/processor.h10
3 files changed, 41 insertions, 2 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);