arm64/sme: Implement ptrace support for streaming mode SVE registers

The streaming mode SVE registers are represented using the same data
structures as for SVE but since the vector lengths supported and in use
may not be the same as SVE we represent them with a new type NT_ARM_SSVE.
Unfortunately we only have a single 16 bit reserved field available in
the header so there is no space to fit the current and maximum vector
length for both standard and streaming SVE mode without redefining the
structure in a way the creates a complicatd and fragile ABI. Since FFR
is not present in streaming mode it is read and written as zero.

Setting NT_ARM_SSVE registers will put the task into streaming mode,
similarly setting NT_ARM_SVE registers will exit it. Reads that do not
correspond to the current mode of the task will return the header with
no register data. For compatibility reasons on write setting no flag for
the register type will be interpreted as setting SVE registers, though
users can provide no register data as an alternative mechanism for doing
so.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20220419112247.711548-21-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/fpsimd.h

@@ -144,6 +144,7 @@ struct vl_info {
 extern void sve_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 fpsimd_force_sync_to_sve(struct task_struct *task);
 extern void sve_sync_to_fpsimd(struct task_struct *task);
 extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
 

arch/arm64/include/uapi/asm/ptrace.h

@@ -109,7 +109,7 @@ struct user_hwdebug_state {
 	}		dbg_regs[16];
 };
 
-/* SVE/FP/SIMD state (NT_ARM_SVE) */
+/* SVE/FP/SIMD state (NT_ARM_SVE & NT_ARM_SSVE) */
 
 struct user_sve_header {
 	__u32 size; /* total meaningful regset content in bytes */
@@ -220,6 +220,7 @@ struct user_sve_header {
 	(SVE_PT_SVE_PREG_OFFSET(vq, __SVE_NUM_PREGS) - \
 		SVE_PT_SVE_PREGS_OFFSET(vq))
 
+/* For streaming mode SVE (SSVE) FFR must be read and written as zero */
 #define SVE_PT_SVE_FFR_OFFSET(vq) \
 	(SVE_PT_REGS_OFFSET + __SVE_FFR_OFFSET(vq))
 
@@ -240,10 +241,12 @@ struct user_sve_header {
 			- SVE_PT_SVE_OFFSET + (__SVE_VQ_BYTES - 1))	\
 		/ __SVE_VQ_BYTES * __SVE_VQ_BYTES)
 
-#define SVE_PT_SIZE(vq, flags)						\
-	 (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ?		\
-		  SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags)	\
-		: SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags))
+#define SVE_PT_SIZE(vq, flags)						  \
+	 (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ?		  \
+		  SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags)	  \
+		: ((((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD ?  \
+		    SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags) \
+		  : SVE_PT_REGS_OFFSET)))
 
 /* pointer authentication masks (NT_ARM_PAC_MASK) */
 

arch/arm64/kernel/fpsimd.c

@@ -643,7 +643,7 @@ static void fpsimd_to_sve(struct task_struct *task)
 	if (!system_supports_sve())
 		return;
 
-	vq = sve_vq_from_vl(task_get_sve_vl(task));
+	vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
 	__fpsimd_to_sve(sst, fst, vq);
 }
 
@@ -660,7 +660,7 @@ static void fpsimd_to_sve(struct task_struct *task)
  */
 static void sve_to_fpsimd(struct task_struct *task)
 {
-	unsigned int vq;
+	unsigned int vq, vl;
 	void const *sst = task->thread.sve_state;
 	struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state;
 	unsigned int i;
@@ -669,7 +669,8 @@ static void sve_to_fpsimd(struct task_struct *task)
 	if (!system_supports_sve())
 		return;
 
-	vq = sve_vq_from_vl(task_get_sve_vl(task));
+	vl = thread_get_cur_vl(&task->thread);
+	vq = sve_vq_from_vl(vl);
 	for (i = 0; i < SVE_NUM_ZREGS; ++i) {
 		p = (__uint128_t const *)ZREG(sst, vq, i);
 		fst->vregs[i] = arm64_le128_to_cpu(*p);
@@ -717,6 +718,19 @@ void sve_alloc(struct task_struct *task)
 }
 
 
+/*
+ * Force the FPSIMD state shared with SVE to be updated in the SVE state
+ * even if the SVE state is the current active state.
+ *
+ * This should only be called by ptrace.  task must be non-runnable.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ */
+void fpsimd_force_sync_to_sve(struct task_struct *task)
+{
+	fpsimd_to_sve(task);
+}
+
 /*
  * Ensure that task->thread.sve_state is up to date with respect to
  * the user task, irrespective of when SVE is in use or not.
@@ -727,7 +741,8 @@ void sve_alloc(struct task_struct *task)
  */
 void fpsimd_sync_to_sve(struct task_struct *task)
 {
-	if (!test_tsk_thread_flag(task, TIF_SVE))
+	if (!test_tsk_thread_flag(task, TIF_SVE) &&
+	    !thread_sm_enabled(&task->thread))
 		fpsimd_to_sve(task);
 }
 
@@ -741,7 +756,8 @@ void fpsimd_sync_to_sve(struct task_struct *task)
  */
 void sve_sync_to_fpsimd(struct task_struct *task)
 {
-	if (test_tsk_thread_flag(task, TIF_SVE))
+	if (test_tsk_thread_flag(task, TIF_SVE) ||
+	    thread_sm_enabled(&task->thread))
 		sve_to_fpsimd(task);
 }
 
@@ -766,7 +782,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
 	if (!test_tsk_thread_flag(task, TIF_SVE))
 		return;
 
-	vq = sve_vq_from_vl(task_get_sve_vl(task));
+	vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
 
 	memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
 	__fpsimd_to_sve(sst, fst, vq);
@@ -810,8 +826,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	/*
 	 * To ensure the FPSIMD bits of the SVE vector registers are preserved,
 	 * write any live register state back to task_struct, and convert to a
-	 * regular FPSIMD thread.  Since the vector length can only be changed
-	 * with a syscall we can't be in streaming mode while reconfiguring.
+	 * regular FPSIMD thread.
 	 */
 	if (task == current) {
 		get_cpu_fpsimd_context();