Merge tag 'riscv-for-linus-6.1-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Improvements to the CPU topology subsystem, which fix some issues
   where RISC-V would report bad topology information.

 - The default NR_CPUS has increased to XLEN, and the maximum
   configurable value is 512.

 - The CD-ROM filesystems have been enabled in the defconfig.

 - Support for THP_SWAP has been added for rv64 systems.

There are also a handful of cleanups and fixes throughout the tree.

* tag 'riscv-for-linus-6.1-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  riscv: enable THP_SWAP for RV64
  RISC-V: Print SSTC in canonical order
  riscv: compat: s/failed/unsupported if compat mode isn't supported
  RISC-V: Increase range and default value of NR_CPUS
  cpuidle: riscv-sbi: Fix CPU_PM_CPU_IDLE_ENTER_xyz() macro usage
  perf: RISC-V: throttle perf events
  perf: RISC-V: exclude invalid pmu counters from SBI calls
  riscv: enable CD-ROM file systems in defconfig
  riscv: topology: fix default topology reporting
  arm64: topology: move store_cpu_topology() to shared code

11 files changed, 63 insertions, 62 deletions

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 44ebf5b2fc4b7f..817d788cd86669 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -22,46 +22,6 @@
 #include <asm/cputype.h>
 #include <asm/topology.h>
 
-void store_cpu_topology(unsigned int cpuid)
-{
-	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
-	u64 mpidr;
-
-	if (cpuid_topo->package_id != -1)
-		goto topology_populated;
-
-	mpidr = read_cpuid_mpidr();
-
-	/* Uniprocessor systems can rely on default topology values */
-	if (mpidr & MPIDR_UP_BITMASK)
-		return;
-
-	/*
-	 * This would be the place to create cpu topology based on MPIDR.
-	 *
-	 * However, it cannot be trusted to depict the actual topology; some
-	 * pieces of the architecture enforce an artificial cap on Aff0 values
-	 * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an
-	 * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up
-	 * having absolutely no relationship to the actual underlying system
-	 * topology, and cannot be reasonably used as core / package ID.
-	 *
-	 * If the MT bit is set, Aff0 *could* be used to define a thread ID, but
-	 * we still wouldn't be able to obtain a sane core ID. This means we
-	 * need to entirely ignore MPIDR for any topology deduction.
-	 */
-	cpuid_topo->thread_id  = -1;
-	cpuid_topo->core_id    = cpuid;
-	cpuid_topo->package_id = cpu_to_node(cpuid);
-
-	pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n",
-		 cpuid, cpuid_topo->package_id, cpuid_topo->core_id,
-		 cpuid_topo->thread_id, mpidr);
-
-topology_populated:
-	update_siblings_masks(cpuid);
-}
-
 #ifdef CONFIG_ACPI
 static bool __init acpi_cpu_is_threaded(int cpu)
 {
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 59d18881f35be4..e84f2742b6bba9 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -45,6 +45,7 @@ config RISCV
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_GENERAL_HUGETLB
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
+	select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
 	select BUILDTIME_TABLE_SORT if MMU
 	select CLONE_BACKWARDS
@@ -52,7 +53,7 @@ config RISCV
 	select COMMON_CLK
 	select CPU_PM if CPU_IDLE
 	select EDAC_SUPPORT
-	select GENERIC_ARCH_TOPOLOGY if SMP
+	select GENERIC_ARCH_TOPOLOGY
 	select GENERIC_ATOMIC64 if !64BIT
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
 	select GENERIC_EARLY_IOREMAP
@@ -309,10 +310,13 @@ config SMP
 	  If you don't know what to do here, say N.
 
 config NR_CPUS
-	int "Maximum number of CPUs (2-32)"
-	range 2 32
+	int "Maximum number of CPUs (2-512)"
 	depends on SMP
-	default "8"
+	range 2 512 if !SBI_V01
+	range 2 32 if SBI_V01 && 32BIT
+	range 2 64 if SBI_V01 && 64BIT
+	default "32" if 32BIT
+	default "64" if 64BIT
 
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index aed332a9d4ea21..05fd5fcf24f9bf 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -166,6 +166,9 @@ CONFIG_BTRFS_FS=m
 CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_AUTOFS4_FS=y
 CONFIG_OVERLAY_FS=m
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index 0be8a2403212d4..87455d12970f3c 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -92,10 +92,10 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid)
  */
 static struct riscv_isa_ext_data isa_ext_arr[] = {
 	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
+	__RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
 	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
 	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
-	__RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
 	__RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX),
 };
 
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index ceb9ebab6558cb..b0c63e8e867ef6 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -105,7 +105,7 @@ static int __init compat_mode_detect(void)
 	csr_write(CSR_STATUS, tmp);
 
 	pr_info("riscv: ELF compat mode %s",
-			compat_mode_supported ? "supported" : "failed");
+			compat_mode_supported ? "supported" : "unsupported");
 
 	return 0;
 }
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index a752c7b416838a..3373df413c8820 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -49,6 +49,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	unsigned int curr_cpuid;
 
 	curr_cpuid = smp_processor_id();
+	store_cpu_topology(curr_cpuid);
 	numa_store_cpu_info(curr_cpuid);
 	numa_add_cpu(curr_cpuid);
 
@@ -162,9 +163,9 @@ asmlinkage __visible void smp_callin(void)
 	mmgrab(mm);
 	current->active_mm = mm;
 
+	store_cpu_topology(curr_cpuid);
 	notify_cpu_starting(curr_cpuid);
 	numa_add_cpu(curr_cpuid);
-	update_siblings_masks(curr_cpuid);
 	set_cpu_online(curr_cpuid, 1);
 
 	/*
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index dd90591e51ba17..e7d6e6657ffa04 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -841,4 +841,23 @@ void __init init_cpu_topology(void)
 		return;
 	}
 }
+
+void store_cpu_topology(unsigned int cpuid)
+{
+	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
+
+	if (cpuid_topo->package_id != -1)
+		goto topology_populated;
+
+	cpuid_topo->thread_id = -1;
+	cpuid_topo->core_id = cpuid;
+	cpuid_topo->package_id = cpu_to_node(cpuid);
+
+	pr_debug("CPU%u: package %d core %d thread %d\n",
+		 cpuid, cpuid_topo->package_id, cpuid_topo->core_id,
+		 cpuid_topo->thread_id);
+
+topology_populated:
+	update_siblings_masks(cpuid);
+}
 #endif
diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c
index 862a2876f1c9df..05fe2902df9a78 100644
--- a/drivers/cpuidle/cpuidle-riscv-sbi.c
+++ b/drivers/cpuidle/cpuidle-riscv-sbi.c
@@ -97,8 +97,13 @@ static int sbi_cpuidle_enter_state(struct cpuidle_device *dev,
 				   struct cpuidle_driver *drv, int idx)
 {
 	u32 *states = __this_cpu_read(sbi_cpuidle_data.states);
+	u32 state = states[idx];
 
-	return CPU_PM_CPU_IDLE_ENTER_PARAM(sbi_suspend, idx, states[idx]);
+	if (state & SBI_HSM_SUSP_NON_RET_BIT)
+		return CPU_PM_CPU_IDLE_ENTER_PARAM(sbi_suspend, idx, state);
+	else
+		return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(sbi_suspend,
+							     idx, state);
 }
 
 static int __sbi_enter_domain_idle_state(struct cpuidle_device *dev,
diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c
index 2c20b0de8cb094..ca9e20bfc7acae 100644
--- a/drivers/perf/riscv_pmu_legacy.c
+++ b/drivers/perf/riscv_pmu_legacy.c
@@ -14,7 +14,6 @@
 
 #define RISCV_PMU_LEGACY_CYCLE		0
 #define RISCV_PMU_LEGACY_INSTRET	1
-#define RISCV_PMU_LEGACY_NUM_CTR	2
 
 static bool pmu_init_done;
 
@@ -83,7 +82,8 @@ static void pmu_legacy_init(struct riscv_pmu *pmu)
 {
 	pr_info("Legacy PMU implementation is available\n");
 
-	pmu->num_counters = RISCV_PMU_LEGACY_NUM_CTR;
+	pmu->cmask = BIT(RISCV_PMU_LEGACY_CYCLE) |
+		BIT(RISCV_PMU_LEGACY_INSTRET);
 	pmu->ctr_start = pmu_legacy_ctr_start;
 	pmu->ctr_stop = NULL;
 	pmu->event_map = pmu_legacy_event_map;
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 8de4ca2fef2101..15e5a47be7d59c 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -18,6 +18,7 @@
 #include <linux/of_irq.h>
 #include <linux/of.h>
 #include <linux/cpu_pm.h>
+#include <linux/sched/clock.h>
 
 #include <asm/sbi.h>
 #include <asm/hwcap.h>
@@ -271,7 +272,6 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event)
 	struct sbiret ret;
 	int idx;
 	uint64_t cbase = 0;
-	uint64_t cmask = GENMASK_ULL(rvpmu->num_counters - 1, 0);
 	unsigned long cflags = 0;
 
 	if (event->attr.exclude_kernel)
@@ -281,11 +281,12 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event)
 
 	/* retrieve the available counter index */
 #if defined(CONFIG_32BIT)
-	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, cmask,
-			cflags, hwc->event_base, hwc->config, hwc->config >> 32);
+	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase,
+			rvpmu->cmask, cflags, hwc->event_base, hwc->config,
+			hwc->config >> 32);
 #else
-	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, cmask,
-			cflags, hwc->event_base, hwc->config, 0);
+	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase,
+			rvpmu->cmask, cflags, hwc->event_base, hwc->config, 0);
 #endif
 	if (ret.error) {
 		pr_debug("Not able to find a counter for event %lx config %llx\n",
@@ -294,7 +295,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event)
 	}
 
 	idx = ret.value;
-	if (idx >= rvpmu->num_counters || !pmu_ctr_list[idx].value)
+	if (!test_bit(idx, &rvpmu->cmask) || !pmu_ctr_list[idx].value)
 		return -ENOENT;
 
 	/* Additional sanity check for the counter id */
@@ -463,7 +464,7 @@ static int pmu_sbi_find_num_ctrs(void)
 		return sbi_err_map_linux_errno(ret.error);
 }
 
-static int pmu_sbi_get_ctrinfo(int nctr)
+static int pmu_sbi_get_ctrinfo(int nctr, unsigned long *mask)
 {
 	struct sbiret ret;
 	int i, num_hw_ctr = 0, num_fw_ctr = 0;
@@ -478,6 +479,9 @@ static int pmu_sbi_get_ctrinfo(int nctr)
 		if (ret.error)
 			/* The logical counter ids are not expected to be contiguous */
 			continue;
+
+		*mask |= BIT(i);
+
 		cinfo.value = ret.value;
 		if (cinfo.type == SBI_PMU_CTR_TYPE_FW)
 			num_fw_ctr++;
@@ -498,7 +502,7 @@ static inline void pmu_sbi_stop_all(struct riscv_pmu *pmu)
 	 * which may include counters that are not enabled yet.
 	 */
 	sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP,
-		  0, GENMASK_ULL(pmu->num_counters - 1, 0), 0, 0, 0, 0);
+		  0, pmu->cmask, 0, 0, 0, 0);
 }
 
 static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu)
@@ -567,6 +571,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 	unsigned long overflow;
 	unsigned long overflowed_ctrs = 0;
 	struct cpu_hw_events *cpu_hw_evt = dev;
+	u64 start_clock = sched_clock();
 
 	if (WARN_ON_ONCE(!cpu_hw_evt))
 		return IRQ_NONE;
@@ -635,7 +640,9 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 			perf_event_overflow(event, &data, regs);
 		}
 	}
+
 	pmu_sbi_start_overflow_mask(pmu, overflowed_ctrs);
+	perf_sample_event_took(sched_clock() - start_clock);
 
 	return IRQ_HANDLED;
 }
@@ -788,8 +795,9 @@ static void riscv_pmu_destroy(struct riscv_pmu *pmu)
 static int pmu_sbi_device_probe(struct platform_device *pdev)
 {
 	struct riscv_pmu *pmu = NULL;
-	int num_counters;
+	unsigned long cmask = 0;
 	int ret = -ENODEV;
+	int num_counters;
 
 	pr_info("SBI PMU extension is available\n");
 	pmu = riscv_pmu_alloc();
@@ -803,7 +811,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	}
 
 	/* cache all the information about counters now */
-	if (pmu_sbi_get_ctrinfo(num_counters))
+	if (pmu_sbi_get_ctrinfo(num_counters, &cmask))
 		goto out_free;
 
 	ret = pmu_sbi_setup_irqs(pmu, pdev);
@@ -812,8 +820,9 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 		pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 		pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE;
 	}
+
 	pmu->pmu.attr_groups = riscv_pmu_attr_groups;
-	pmu->num_counters = num_counters;
+	pmu->cmask = cmask;
 	pmu->ctr_start = pmu_sbi_ctr_start;
 	pmu->ctr_stop = pmu_sbi_ctr_stop;
 	pmu->event_map = pmu_sbi_event_map;
diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h
index bf66fe011fa81d..e17e86ad6f3a24 100644
--- a/include/linux/perf/riscv_pmu.h
+++ b/include/linux/perf/riscv_pmu.h
@@ -45,7 +45,7 @@ struct riscv_pmu {
 
 	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
 
-	int		num_counters;
+	unsigned long	cmask;
 	u64		(*ctr_read)(struct perf_event *event);
 	int		(*ctr_get_idx)(struct perf_event *event);
 	int		(*ctr_get_width)(int idx);