arm64/fpsimd: Track the saved FPSIMD state type separately to TIF_SVE

When we save the state for the floating point registers this can be done
in the form visible through either the FPSIMD V registers or the SVE Z and
P registers. At present we track which format is currently used based on
TIF_SVE and the SME streaming mode state but particularly in the SVE case
this limits our options for optimising things, especially around syscalls.
Introduce a new enum which we place together with saved floating point
state in both thread_struct and the KVM guest state which explicitly
states which format is active and keep it up to date when we change it.

At present we do not use this state except to verify that it has the
expected value when loading the state, future patches will introduce
functional changes.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221115094640.112848-3-broonie@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>

1 files changed, 43 insertions, 15 deletions

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 549e11645e0f..aacd8e356084 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -125,6 +125,7 @@ struct fpsimd_last_state_struct {
 	u64 *svcr;
 	unsigned int sve_vl;
 	unsigned int sme_vl;
+	enum fp_type *fp_type;
 };
 
 static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
@@ -330,15 +331,6 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  *    The task can execute SVE instructions while in userspace without
  *    trapping to the kernel.
  *
- *    When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
- *    corresponding Zn), P0-P15 and FFR are encoded in
- *    task->thread.sve_state, formatted appropriately for vector
- *    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.
- *
  *    During any syscall, the kernel may optionally clear TIF_SVE and
  *    discard the vector state except for the FPSIMD subset.
  *
@@ -348,7 +340,15 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  *    do_sve_acc() to be called, which does some preparation and then
  *    sets TIF_SVE.
  *
- *    When stored, FPSIMD registers V0-V31 are encoded in
+ * During any syscall, the kernel may optionally clear TIF_SVE and
+ * discard the vector state except for the FPSIMD subset.
+ *
+ * The data will be stored in one of two formats:
+ *
+ *  * FPSIMD only - FP_STATE_FPSIMD:
+ *
+ *    When the FPSIMD only state stored task->thread.fp_type is set to
+ *    FP_STATE_FPSIMD, the FPSIMD registers V0-V31 are encoded in
  *    task->thread.uw.fpsimd_state; bits [max : 128] for each of Z0-Z31 are
  *    logically zero but not stored anywhere; P0-P15 and FFR are not
  *    stored and have unspecified values from userspace's point of
@@ -358,6 +358,19 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  *    task->thread.sve_state does not need to be non-NULL, valid or any
  *    particular size: it must not be dereferenced.
  *
+ *  * SVE state - FP_STATE_SVE:
+ *
+ *    When the full SVE state is stored task->thread.fp_type is set to
+ *    FP_STATE_SVE and 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 or, if SVCR.SM is set,
+ *    task->thread.sme_vl. The storage for the vector registers in
+ *    task->thread.uw.fpsimd_state should be ignored.
+ *
+ *    task->thread.sve_state must point to a valid buffer at least
+ *    sve_state_size(task) bytes in size.
+ *
  *  * FPSR and FPCR are always stored in task->thread.uw.fpsimd_state
  *    irrespective of whether TIF_SVE is clear or set, since these are
  *    not vector length dependent.
@@ -404,12 +417,15 @@ static void task_fpsimd_load(void)
 		}
 	}
 
-	if (restore_sve_regs)
+	if (restore_sve_regs) {
+		WARN_ON_ONCE(current->thread.fp_type != FP_STATE_SVE);
 		sve_load_state(sve_pffr(&current->thread),
 			       &current->thread.uw.fpsimd_state.fpsr,
 			       restore_ffr);
-	else
+	} else {
+		WARN_ON_ONCE(current->thread.fp_type != FP_STATE_FPSIMD);
 		fpsimd_load_state(&current->thread.uw.fpsimd_state);
+	}
 }
 
 /*
@@ -474,8 +490,10 @@ static void fpsimd_save(void)
 		sve_save_state((char *)last->sve_state +
 					sve_ffr_offset(vl),
 			       &last->st->fpsr, save_ffr);
+		*last->fp_type = FP_STATE_SVE;
 	} else {
 		fpsimd_save_state(last->st);
+		*last->fp_type = FP_STATE_FPSIMD;
 	}
 }
 
@@ -848,8 +866,10 @@ 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) ||
-	    thread_sm_enabled(&task->thread))
+	    thread_sm_enabled(&task->thread)) {
 		sve_to_fpsimd(task);
+		task->thread.fp_type = FP_STATE_FPSIMD;
+	}
 
 	if (system_supports_sme() && type == ARM64_VEC_SME) {
 		task->thread.svcr &= ~(SVCR_SM_MASK |
@@ -1368,6 +1388,7 @@ static void sve_init_regs(void)
 		fpsimd_bind_task_to_cpu();
 	} else {
 		fpsimd_to_sve(current);
+		current->thread.fp_type = FP_STATE_SVE;
 	}
 }
 
@@ -1596,6 +1617,8 @@ void fpsimd_flush_thread(void)
 		current->thread.svcr = 0;
 	}
 
+	current->thread.fp_type = FP_STATE_FPSIMD;
+
 	put_cpu_fpsimd_context();
 	kfree(sve_state);
 	kfree(za_state);
@@ -1644,8 +1667,10 @@ void fpsimd_kvm_prepare(void)
 	 */
 	get_cpu_fpsimd_context();
 
-	if (test_and_clear_thread_flag(TIF_SVE))
+	if (test_and_clear_thread_flag(TIF_SVE)) {
 		sve_to_fpsimd(current);
+		current->thread.fp_type = FP_STATE_FPSIMD;
+	}
 
 	put_cpu_fpsimd_context();
 }
@@ -1667,6 +1692,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	last->sve_vl = task_get_sve_vl(current);
 	last->sme_vl = task_get_sme_vl(current);
 	last->svcr = &current->thread.svcr;
+	last->fp_type = &current->thread.fp_type;
 	current->thread.fpsimd_cpu = smp_processor_id();
 
 	/*
@@ -1690,7 +1716,8 @@ 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, void *za_state,
-			      unsigned int sme_vl, u64 *svcr)
+			      unsigned int sme_vl, u64 *svcr,
+			      enum fp_type *type)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -1704,6 +1731,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 	last->za_state = za_state;
 	last->sve_vl = sve_vl;
 	last->sme_vl = sme_vl;
+	last->fp_type = type;
 }
 
 /*