Merge tag 'riscv-for-linus-6.9-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Support for various vector-accelerated crypto routines

 - Hibernation is now enabled for portable kernel builds

 - mmap_rnd_bits_max is larger on systems with larger VAs

 - Support for fast GUP

 - Support for membarrier-based instruction cache synchronization

 - Support for the Andes hart-level interrupt controller and PMU

 - Some cleanups around unaligned access speed probing and Kconfig
   settings

 - Support for ACPI LPI and CPPC

 - Various cleanus related to barriers

 - A handful of fixes

* tag 'riscv-for-linus-6.9-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (66 commits)
  riscv: Fix syscall wrapper for >word-size arguments
  crypto: riscv - add vector crypto accelerated AES-CBC-CTS
  crypto: riscv - parallelize AES-CBC decryption
  riscv: Only flush the mm icache when setting an exec pte
  riscv: Use kcalloc() instead of kzalloc()
  riscv/barrier: Add missing space after ','
  riscv/barrier: Consolidate fence definitions
  riscv/barrier: Define RISCV_FULL_BARRIER
  riscv/barrier: Define __{mb,rmb,wmb}
  RISC-V: defconfig: Enable CONFIG_ACPI_CPPC_CPUFREQ
  cpufreq: Move CPPC configs to common Kconfig and add RISC-V
  ACPI: RISC-V: Add CPPC driver
  ACPI: Enable ACPI_PROCESSOR for RISC-V
  ACPI: RISC-V: Add LPI driver
  cpuidle: RISC-V: Move few functions to arch/riscv
  riscv: Introduce set_compat_task() in asm/compat.h
  riscv: Introduce is_compat_thread() into compat.h
  riscv: add compile-time test into is_compat_task()
  riscv: Replace direct thread flag check with is_compat_task()
  riscv: Improve arch_get_mmap_end() macro
  ...

2 files changed, 46 insertions, 5 deletions

diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index 54ff5cc17ccd..7526a9e714fa 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -96,6 +96,20 @@ config STARFIVE_STARLINK_PMU
 	   an L3 memory system. The L3 cache events are added into perf event
 	   subsystem, allowing monitoring of various L3 cache perf events.
 
+config ANDES_CUSTOM_PMU
+	bool "Andes custom PMU support"
+	depends on ARCH_RENESAS && RISCV_ALTERNATIVE && RISCV_PMU_SBI
+	default y
+	help
+	  The Andes cores implement the PMU overflow extension very
+	  similar to the standard Sscofpmf and Smcntrpmf extension.
+
+	  This will patch the overflow and pending CSRs and handle the
+	  non-standard behaviour via the regular SBI PMU driver and
+	  interface.
+
+	  If you don't know what to do here, say "Y".
+
 config ARM_PMU_ACPI
 	depends on ARM_PMU && ACPI
 	def_bool y
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 452aab49db1e..8cbe6e5f9c39 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -19,11 +19,33 @@
 #include <linux/of.h>
 #include <linux/cpu_pm.h>
 #include <linux/sched/clock.h>
+#include <linux/soc/andes/irq.h>
 
 #include <asm/errata_list.h>
 #include <asm/sbi.h>
 #include <asm/cpufeature.h>
 
+#define ALT_SBI_PMU_OVERFLOW(__ovl)					\
+asm volatile(ALTERNATIVE_2(						\
+	"csrr %0, " __stringify(CSR_SSCOUNTOVF),			\
+	"csrr %0, " __stringify(THEAD_C9XX_CSR_SCOUNTEROF),		\
+		THEAD_VENDOR_ID, ERRATA_THEAD_PMU,			\
+		CONFIG_ERRATA_THEAD_PMU,				\
+	"csrr %0, " __stringify(ANDES_CSR_SCOUNTEROF),			\
+		0, RISCV_ISA_EXT_XANDESPMU,				\
+		CONFIG_ANDES_CUSTOM_PMU)				\
+	: "=r" (__ovl) :						\
+	: "memory")
+
+#define ALT_SBI_PMU_OVF_CLEAR_PENDING(__irq_mask)			\
+asm volatile(ALTERNATIVE(						\
+	"csrc " __stringify(CSR_IP) ", %0\n\t",				\
+	"csrc " __stringify(ANDES_CSR_SLIP) ", %0\n\t",			\
+		0, RISCV_ISA_EXT_XANDESPMU,				\
+		CONFIG_ANDES_CUSTOM_PMU)				\
+	: : "r"(__irq_mask)						\
+	: "memory")
+
 #define SYSCTL_NO_USER_ACCESS	0
 #define SYSCTL_USER_ACCESS	1
 #define SYSCTL_LEGACY		2
@@ -61,6 +83,7 @@ static int sysctl_perf_user_access __read_mostly = SYSCTL_USER_ACCESS;
 static union sbi_pmu_ctr_info *pmu_ctr_list;
 static bool riscv_pmu_use_irq;
 static unsigned int riscv_pmu_irq_num;
+static unsigned int riscv_pmu_irq_mask;
 static unsigned int riscv_pmu_irq;
 
 /* Cache the available counters in a bitmask */
@@ -694,7 +717,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 
 	event = cpu_hw_evt->events[fidx];
 	if (!event) {
-		csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num));
+		ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask);
 		return IRQ_NONE;
 	}
 
@@ -708,7 +731,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 	 * Overflow interrupt pending bit should only be cleared after stopping
 	 * all the counters to avoid any race condition.
 	 */
-	csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num));
+	ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask);
 
 	/* No overflow bit is set */
 	if (!overflow)
@@ -780,8 +803,7 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node)
 
 	if (riscv_pmu_use_irq) {
 		cpu_hw_evt->irq = riscv_pmu_irq;
-		csr_clear(CSR_IP, BIT(riscv_pmu_irq_num));
-		csr_set(CSR_IE, BIT(riscv_pmu_irq_num));
+		ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask);
 		enable_percpu_irq(riscv_pmu_irq, IRQ_TYPE_NONE);
 	}
 
@@ -792,7 +814,6 @@ static int pmu_sbi_dying_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	if (riscv_pmu_use_irq) {
 		disable_percpu_irq(riscv_pmu_irq);
-		csr_clear(CSR_IE, BIT(riscv_pmu_irq_num));
 	}
 
 	/* Disable all counters access for user mode now */
@@ -816,8 +837,14 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde
 		   riscv_cached_mimpid(0) == 0) {
 		riscv_pmu_irq_num = THEAD_C9XX_RV_IRQ_PMU;
 		riscv_pmu_use_irq = true;
+	} else if (riscv_isa_extension_available(NULL, XANDESPMU) &&
+		   IS_ENABLED(CONFIG_ANDES_CUSTOM_PMU)) {
+		riscv_pmu_irq_num = ANDES_SLI_CAUSE_BASE + ANDES_RV_IRQ_PMOVI;
+		riscv_pmu_use_irq = true;
 	}
 
+	riscv_pmu_irq_mask = BIT(riscv_pmu_irq_num % BITS_PER_LONG);
+
 	if (!riscv_pmu_use_irq)
 		return -EOPNOTSUPP;