Merge branch 'for-next/perf' into aarch64/for-next/core

Merge in ARM PMU and perf updates for 4.15:

  - Support for the Statistical Profiling Extension
  - Support for Hisilicon's SoC PMU

Signed-off-by: Will Deacon <will.deacon@arm.com>

4 files changed, 114 insertions, 22 deletions

diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 0fe7e43b7fbc..77651c49ef44 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -31,6 +31,8 @@
 #define dmb(opt)	asm volatile("dmb " #opt : : : "memory")
 #define dsb(opt)	asm volatile("dsb " #opt : : : "memory")
 
+#define psb_csync()	asm volatile("hint #17" : : : "memory")
+
 #define mb()		dsb(sy)
 #define rmb()		dsb(ld)
 #define wmb()		dsb(st)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 32f489ba952f..4dceb12f4596 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -172,6 +172,99 @@
 #define SYS_FAR_EL1			sys_reg(3, 0, 6, 0, 0)
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
 
+/*** Statistical Profiling Extension ***/
+/* ID registers */
+#define SYS_PMSIDR_EL1			sys_reg(3, 0, 9, 9, 7)
+#define SYS_PMSIDR_EL1_FE_SHIFT		0
+#define SYS_PMSIDR_EL1_FT_SHIFT		1
+#define SYS_PMSIDR_EL1_FL_SHIFT		2
+#define SYS_PMSIDR_EL1_ARCHINST_SHIFT	3
+#define SYS_PMSIDR_EL1_LDS_SHIFT	4
+#define SYS_PMSIDR_EL1_ERND_SHIFT	5
+#define SYS_PMSIDR_EL1_INTERVAL_SHIFT	8
+#define SYS_PMSIDR_EL1_INTERVAL_MASK	0xfUL
+#define SYS_PMSIDR_EL1_MAXSIZE_SHIFT	12
+#define SYS_PMSIDR_EL1_MAXSIZE_MASK	0xfUL
+#define SYS_PMSIDR_EL1_COUNTSIZE_SHIFT	16
+#define SYS_PMSIDR_EL1_COUNTSIZE_MASK	0xfUL
+
+#define SYS_PMBIDR_EL1			sys_reg(3, 0, 9, 10, 7)
+#define SYS_PMBIDR_EL1_ALIGN_SHIFT	0
+#define SYS_PMBIDR_EL1_ALIGN_MASK	0xfU
+#define SYS_PMBIDR_EL1_P_SHIFT		4
+#define SYS_PMBIDR_EL1_F_SHIFT		5
+
+/* Sampling controls */
+#define SYS_PMSCR_EL1			sys_reg(3, 0, 9, 9, 0)
+#define SYS_PMSCR_EL1_E0SPE_SHIFT	0
+#define SYS_PMSCR_EL1_E1SPE_SHIFT	1
+#define SYS_PMSCR_EL1_CX_SHIFT		3
+#define SYS_PMSCR_EL1_PA_SHIFT		4
+#define SYS_PMSCR_EL1_TS_SHIFT		5
+#define SYS_PMSCR_EL1_PCT_SHIFT		6
+
+#define SYS_PMSCR_EL2			sys_reg(3, 4, 9, 9, 0)
+#define SYS_PMSCR_EL2_E0HSPE_SHIFT	0
+#define SYS_PMSCR_EL2_E2SPE_SHIFT	1
+#define SYS_PMSCR_EL2_CX_SHIFT		3
+#define SYS_PMSCR_EL2_PA_SHIFT		4
+#define SYS_PMSCR_EL2_TS_SHIFT		5
+#define SYS_PMSCR_EL2_PCT_SHIFT		6
+
+#define SYS_PMSICR_EL1			sys_reg(3, 0, 9, 9, 2)
+
+#define SYS_PMSIRR_EL1			sys_reg(3, 0, 9, 9, 3)
+#define SYS_PMSIRR_EL1_RND_SHIFT	0
+#define SYS_PMSIRR_EL1_INTERVAL_SHIFT	8
+#define SYS_PMSIRR_EL1_INTERVAL_MASK	0xffffffUL
+
+/* Filtering controls */
+#define SYS_PMSFCR_EL1			sys_reg(3, 0, 9, 9, 4)
+#define SYS_PMSFCR_EL1_FE_SHIFT		0
+#define SYS_PMSFCR_EL1_FT_SHIFT		1
+#define SYS_PMSFCR_EL1_FL_SHIFT		2
+#define SYS_PMSFCR_EL1_B_SHIFT		16
+#define SYS_PMSFCR_EL1_LD_SHIFT		17
+#define SYS_PMSFCR_EL1_ST_SHIFT		18
+
+#define SYS_PMSEVFR_EL1			sys_reg(3, 0, 9, 9, 5)
+#define SYS_PMSEVFR_EL1_RES0		0x0000ffff00ff0f55UL
+
+#define SYS_PMSLATFR_EL1		sys_reg(3, 0, 9, 9, 6)
+#define SYS_PMSLATFR_EL1_MINLAT_SHIFT	0
+
+/* Buffer controls */
+#define SYS_PMBLIMITR_EL1		sys_reg(3, 0, 9, 10, 0)
+#define SYS_PMBLIMITR_EL1_E_SHIFT	0
+#define SYS_PMBLIMITR_EL1_FM_SHIFT	1
+#define SYS_PMBLIMITR_EL1_FM_MASK	0x3UL
+#define SYS_PMBLIMITR_EL1_FM_STOP_IRQ	(0 << SYS_PMBLIMITR_EL1_FM_SHIFT)
+
+#define SYS_PMBPTR_EL1			sys_reg(3, 0, 9, 10, 1)
+
+/* Buffer error reporting */
+#define SYS_PMBSR_EL1			sys_reg(3, 0, 9, 10, 3)
+#define SYS_PMBSR_EL1_COLL_SHIFT	16
+#define SYS_PMBSR_EL1_S_SHIFT		17
+#define SYS_PMBSR_EL1_EA_SHIFT		18
+#define SYS_PMBSR_EL1_DL_SHIFT		19
+#define SYS_PMBSR_EL1_EC_SHIFT		26
+#define SYS_PMBSR_EL1_EC_MASK		0x3fUL
+
+#define SYS_PMBSR_EL1_EC_BUF		(0x0UL << SYS_PMBSR_EL1_EC_SHIFT)
+#define SYS_PMBSR_EL1_EC_FAULT_S1	(0x24UL << SYS_PMBSR_EL1_EC_SHIFT)
+#define SYS_PMBSR_EL1_EC_FAULT_S2	(0x25UL << SYS_PMBSR_EL1_EC_SHIFT)
+
+#define SYS_PMBSR_EL1_FAULT_FSC_SHIFT	0
+#define SYS_PMBSR_EL1_FAULT_FSC_MASK	0x3fUL
+
+#define SYS_PMBSR_EL1_BUF_BSC_SHIFT	0
+#define SYS_PMBSR_EL1_BUF_BSC_MASK	0x3fUL
+
+#define SYS_PMBSR_EL1_BUF_BSC_FULL	(0x1UL << SYS_PMBSR_EL1_BUF_BSC_SHIFT)
+
+/*** End of Statistical Profiling Extension ***/
+
 #define SYS_PMINTENSET_EL1		sys_reg(3, 0, 9, 14, 1)
 #define SYS_PMINTENCLR_EL1		sys_reg(3, 0, 9, 14, 2)
 
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 0b243ecaf7ac..cfa90a43fbe7 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -480,14 +480,21 @@ set_hcr:
 
 	/* Statistical profiling */
 	ubfx	x0, x1, #32, #4			// Check ID_AA64DFR0_EL1 PMSVer
-	cbz	x0, 6f				// Skip if SPE not present
-	cbnz	x2, 5f				// VHE?
+	cbz	x0, 7f				// Skip if SPE not present
+	cbnz	x2, 6f				// VHE?
+	mrs_s	x4, SYS_PMBIDR_EL1		// If SPE available at EL2,
+	and	x4, x4, #(1 << SYS_PMBIDR_EL1_P_SHIFT)
+	cbnz	x4, 5f				// then permit sampling of physical
+	mov	x4, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \
+		      1 << SYS_PMSCR_EL2_PA_SHIFT)
+	msr_s	SYS_PMSCR_EL2, x4		// addresses and physical counter
+5:
 	mov	x1, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
 	orr	x3, x3, x1			// If we don't have VHE, then
-	b	6f				// use EL1&0 translation.
-5:						// For VHE, use EL2 translation
+	b	7f				// use EL1&0 translation.
+6:						// For VHE, use EL2 translation
 	orr	x3, x3, #MDCR_EL2_TPMS		// and disable access from EL1
-6:
+7:
 	msr	mdcr_el2, x3			// Configure debug traps
 
 	/* Stage-2 translation */
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
index f5154ed3da6c..321c9c05dd9e 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@@ -65,16 +65,6 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
-#define PMSCR_EL1		sys_reg(3, 0, 9, 9, 0)
-
-#define PMBLIMITR_EL1		sys_reg(3, 0, 9, 10, 0)
-#define PMBLIMITR_EL1_E		BIT(0)
-
-#define PMBIDR_EL1		sys_reg(3, 0, 9, 10, 7)
-#define PMBIDR_EL1_P		BIT(4)
-
-#define psb_csync()		asm volatile("hint #17")
-
 static void __hyp_text __debug_save_spe_vhe(u64 *pmscr_el1)
 {
 	/* The vcpu can run. but it can't hide. */
@@ -90,18 +80,18 @@ static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
 		return;
 
 	/* Yes; is it owned by EL3? */
-	reg = read_sysreg_s(PMBIDR_EL1);
-	if (reg & PMBIDR_EL1_P)
+	reg = read_sysreg_s(SYS_PMBIDR_EL1);
+	if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT))
 		return;
 
 	/* No; is the host actually using the thing? */
-	reg = read_sysreg_s(PMBLIMITR_EL1);
-	if (!(reg & PMBLIMITR_EL1_E))
+	reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
+	if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
 		return;
 
 	/* Yes; save the control register and disable data generation */
-	*pmscr_el1 = read_sysreg_s(PMSCR_EL1);
-	write_sysreg_s(0, PMSCR_EL1);
+	*pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
+	write_sysreg_s(0, SYS_PMSCR_EL1);
 	isb();
 
 	/* Now drain all buffered data to memory */
@@ -122,7 +112,7 @@ static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
 	isb();
 
 	/* Re-enable data generation */
-	write_sysreg_s(pmscr_el1, PMSCR_EL1);
+	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
 }
 
 void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,