arm64/sve: Make access to FFR optional

SME introduces streaming SVE mode in which FFR is not present and the
instructions for accessing it UNDEF. In preparation for handling this
update the low level SVE state access functions to take a flag specifying
if FFR should be handled. When saving the register state we store a zero
for FFR to guard against uninitialized data being read. No behaviour change
should be introduced by this patch.

Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>

Author: broonie

arch/arm64/include/asm/fpsimd.h

@@ -65,10 +65,10 @@ static inline void *sve_pffr(struct thread_struct *thread)
 	return (char *)thread->sve_state + sve_ffr_offset(thread->sve_vl);
 }
 
-extern void sve_save_state(void *state, u32 *pfpsr);
+extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
 extern void sve_load_state(void const *state, u32 const *pfpsr,
-			   unsigned long vq_minus_1);
-extern void sve_flush_live(unsigned long vq_minus_1);
+			   int restore_ffr, unsigned long vq_minus_1);
+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);
 

arch/arm64/include/asm/fpsimdmacros.h

@@ -217,28 +217,36 @@
 .macro sve_flush_z
  _for n, 0, 31, _sve_flush_z	\n
 .endm
-.macro sve_flush_p_ffr
+.macro sve_flush_p
  _for n, 0, 15, _sve_pfalse	\n
+.endm
+.macro sve_flush_ffr
 		_sve_wrffr	0
 .endm
 
-.macro sve_save nxbase, xpfpsr, nxtmp
+.macro sve_save nxbase, xpfpsr, save_ffr, nxtmp
  _for n, 0, 31,	_sve_str_v	\n, \nxbase, \n - 34
  _for n, 0, 15,	_sve_str_p	\n, \nxbase, \n - 16
+		cbz		\save_ffr, 921f
 		_sve_rdffr	0
 		_sve_str_p	0, \nxbase
 		_sve_ldr_p	0, \nxbase, -16
-
+		b		922f
+921:
+		str		xzr, [x\nxbase]		// Zero out FFR
+922:
 		mrs		x\nxtmp, fpsr
 		str		w\nxtmp, [\xpfpsr]
 		mrs		x\nxtmp, fpcr
 		str		w\nxtmp, [\xpfpsr, #4]
 .endm
 
-.macro __sve_load nxbase, xpfpsr, nxtmp
+.macro __sve_load nxbase, xpfpsr, restore_ffr, nxtmp
  _for n, 0, 31,	_sve_ldr_v	\n, \nxbase, \n - 34
+		cbz		\restore_ffr, 921f
 		_sve_ldr_p	0, \nxbase
 		_sve_wrffr	0
+921:
  _for n, 0, 15,	_sve_ldr_p	\n, \nxbase, \n - 16
 
 		ldr		w\nxtmp, [\xpfpsr]
@@ -247,7 +255,7 @@
 		msr		fpcr, x\nxtmp
 .endm
 
-.macro sve_load nxbase, xpfpsr, xvqminus1, nxtmp, xtmp2
+.macro sve_load nxbase, xpfpsr, restore_ffr, xvqminus1, nxtmp, xtmp2
 		sve_load_vq	\xvqminus1, x\nxtmp, \xtmp2
-		__sve_load	\nxbase, \xpfpsr, \nxtmp
+		__sve_load	\nxbase, \xpfpsr, \restore_ffr, \nxtmp
 .endm

arch/arm64/kernel/entry-fpsimd.S

@@ -38,9 +38,10 @@ SYM_FUNC_END(fpsimd_load_state)
  *
  * x0 - pointer to buffer for state
  * x1 - pointer to storage for FPSR
+ * x2 - Save FFR if non-zero
  */
 SYM_FUNC_START(sve_save_state)
-	sve_save 0, x1, 2
+	sve_save 0, x1, x2, 3
 	ret
 SYM_FUNC_END(sve_save_state)
 
@@ -49,10 +50,11 @@ SYM_FUNC_END(sve_save_state)
  *
  * x0 - pointer to buffer for state
  * x1 - pointer to storage for FPSR
- * x2 - VQ-1
+ * x2 - Restore FFR if non-zero
+ * x3 - VQ-1
  */
 SYM_FUNC_START(sve_load_state)
-	sve_load 0, x1, x2, 3, x4
+	sve_load 0, x1, x2, x3, 4, x5
 	ret
 SYM_FUNC_END(sve_load_state)
 
@@ -72,13 +74,16 @@ SYM_FUNC_END(sve_set_vq)
  * VQ must already be configured by caller, any further updates of VQ
  * will need to ensure that the register state remains valid.
  *
- * x0 = VQ - 1
+ * x0 = include FFR?
+ * x1 = VQ - 1
  */
 SYM_FUNC_START(sve_flush_live)
-	cbz		x0, 1f	// A VQ-1 of 0 is 128 bits so no extra Z state
+	cbz		x1, 1f	// A VQ-1 of 0 is 128 bits so no extra Z state
 	sve_flush_z
-1:	sve_flush_p_ffr
-	ret
+1:	sve_flush_p
+	tbz		x0, #0, 2f
+	sve_flush_ffr
+2:	ret
 SYM_FUNC_END(sve_flush_live)
 
 #endif /* CONFIG_ARM64_SVE */

arch/arm64/kernel/fpsimd.c

@@ -289,7 +289,7 @@ static void task_fpsimd_load(void)
 
 	if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE))
 		sve_load_state(sve_pffr(&current->thread),
-			       &current->thread.uw.fpsimd_state.fpsr,
+			       &current->thread.uw.fpsimd_state.fpsr, true,
 			       sve_vq_from_vl(current->thread.sve_vl) - 1);
 	else
 		fpsimd_load_state(&current->thread.uw.fpsimd_state);
@@ -325,7 +325,7 @@ static void fpsimd_save(void)
 
 		sve_save_state((char *)last->sve_state +
 					sve_ffr_offset(last->sve_vl),
-			       &last->st->fpsr);
+			       &last->st->fpsr, true);
 	} else {
 		fpsimd_save_state(last->st);
 	}
@@ -962,7 +962,7 @@ void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 		unsigned long vq_minus_one =
 			sve_vq_from_vl(current->thread.sve_vl) - 1;
 		sve_set_vq(vq_minus_one);
-		sve_flush_live(vq_minus_one);
+		sve_flush_live(true, vq_minus_one);
 		fpsimd_bind_task_to_cpu();
 	} else {
 		fpsimd_to_sve(current);
@@ -1356,7 +1356,8 @@ void __efi_fpsimd_begin(void)
 			__this_cpu_write(efi_sve_state_used, true);
 
 			sve_save_state(sve_state + sve_ffr_offset(sve_max_vl),
-				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr);
+				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
+				       true);
 		} else {
 			fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
 		}
@@ -1382,6 +1383,7 @@ void __efi_fpsimd_end(void)
 
 			sve_load_state(sve_state + sve_ffr_offset(sve_max_vl),
 				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
+				       true,
 				       sve_vq_from_vl(sve_get_vl()) - 1);
 
 			__this_cpu_write(efi_sve_state_used, false);

arch/arm64/kvm/hyp/fpsimd.S

@@ -21,11 +21,13 @@ SYM_FUNC_START(__fpsimd_restore_state)
 SYM_FUNC_END(__fpsimd_restore_state)
 
 SYM_FUNC_START(__sve_restore_state)
-	__sve_load 0, x1, 2
+	mov	x2, #1
+	__sve_load 0, x1, x2, 3
 	ret
 SYM_FUNC_END(__sve_restore_state)
 
 SYM_FUNC_START(__sve_save_state)
-	sve_save 0, x1, 2
+	mov	x2, #1
+	sve_save 0, x1, x2, 3
 	ret
 SYM_FUNC_END(__sve_save_state)