Merge tag 'riscv-for-linus-6.6-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Support for the new "riscv,isa-extensions" and "riscv,isa-base"
   device tree interfaces for probing extensions

 - Support for userspace access to the performance counters

 - Support for more instructions in kprobes

 - Crash kernels can be allocated above 4GiB

 - Support for KCFI

 - Support for ELFs in !MMU configurations

 - ARCH_KMALLOC_MINALIGN has been reduced to 8

 - mmap() defaults to sv48-sized addresses, with longer addresses hidden
   behind a hint (similar to Arm and Intel)

 - Also various fixes and cleanups

* tag 'riscv-for-linus-6.6-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (51 commits)
  lib/Kconfig.debug: Restrict DEBUG_INFO_SPLIT for RISC-V
  riscv: support PREEMPT_DYNAMIC with static keys
  riscv: Move create_tmp_mapping() to init sections
  riscv: Mark KASAN tmp* page tables variables as static
  riscv: mm: use bitmap_zero() API
  riscv: enable DEBUG_FORCE_FUNCTION_ALIGN_64B
  riscv: remove redundant mv instructions
  RISC-V: mm: Document mmap changes
  RISC-V: mm: Update pgtable comment documentation
  RISC-V: mm: Add tests for RISC-V mm
  RISC-V: mm: Restrict address space for sv39,sv48,sv57
  riscv: enable DMA_BOUNCE_UNALIGNED_KMALLOC for !dma_coherent
  riscv: allow kmalloc() caches aligned to the smallest value
  riscv: support the elf-fdpic binfmt loader
  binfmt_elf_fdpic: support 64-bit systems
  riscv: Allow CONFIG_CFI_CLANG to be selected
  riscv/purgatory: Disable CFI
  riscv: Add CFI error handling
  riscv: Add ftrace_stub_graph
  riscv: Add types to indirectly called assembly functions
  ...

3 files changed, 328 insertions, 9 deletions

diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c
index 56897d4d4fd3..1f9a35f724f5 100644
--- a/drivers/perf/riscv_pmu.c
+++ b/drivers/perf/riscv_pmu.c
@@ -14,9 +14,81 @@
 #include <linux/perf/riscv_pmu.h>
 #include <linux/printk.h>
 #include <linux/smp.h>
+#include <linux/sched_clock.h>
 
 #include <asm/sbi.h>
 
+static bool riscv_perf_user_access(struct perf_event *event)
+{
+	return ((event->attr.type == PERF_TYPE_HARDWARE) ||
+		(event->attr.type == PERF_TYPE_HW_CACHE) ||
+		(event->attr.type == PERF_TYPE_RAW)) &&
+		!!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT);
+}
+
+void arch_perf_update_userpage(struct perf_event *event,
+			       struct perf_event_mmap_page *userpg, u64 now)
+{
+	struct clock_read_data *rd;
+	unsigned int seq;
+	u64 ns;
+
+	userpg->cap_user_time = 0;
+	userpg->cap_user_time_zero = 0;
+	userpg->cap_user_time_short = 0;
+	userpg->cap_user_rdpmc = riscv_perf_user_access(event);
+
+#ifdef CONFIG_RISCV_PMU
+	/*
+	 * The counters are 64-bit but the priv spec doesn't mandate all the
+	 * bits to be implemented: that's why, counter width can vary based on
+	 * the cpu vendor.
+	 */
+	if (userpg->cap_user_rdpmc)
+		userpg->pmc_width = to_riscv_pmu(event->pmu)->ctr_get_width(event->hw.idx) + 1;
+#endif
+
+	do {
+		rd = sched_clock_read_begin(&seq);
+
+		userpg->time_mult = rd->mult;
+		userpg->time_shift = rd->shift;
+		userpg->time_zero = rd->epoch_ns;
+		userpg->time_cycles = rd->epoch_cyc;
+		userpg->time_mask = rd->sched_clock_mask;
+
+		/*
+		 * Subtract the cycle base, such that software that
+		 * doesn't know about cap_user_time_short still 'works'
+		 * assuming no wraps.
+		 */
+		ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift);
+		userpg->time_zero -= ns;
+
+	} while (sched_clock_read_retry(seq));
+
+	userpg->time_offset = userpg->time_zero - now;
+
+	/*
+	 * time_shift is not expected to be greater than 31 due to
+	 * the original published conversion algorithm shifting a
+	 * 32-bit value (now specifies a 64-bit value) - refer
+	 * perf_event_mmap_page documentation in perf_event.h.
+	 */
+	if (userpg->time_shift == 32) {
+		userpg->time_shift = 31;
+		userpg->time_mult >>= 1;
+	}
+
+	/*
+	 * Internal timekeeping for enabled/running/stopped times
+	 * is always computed with the sched_clock.
+	 */
+	userpg->cap_user_time = 1;
+	userpg->cap_user_time_zero = 1;
+	userpg->cap_user_time_short = 1;
+}
+
 static unsigned long csr_read_num(int csr_num)
 {
 #define switchcase_csr_read(__csr_num, __val)		{\
@@ -171,6 +243,8 @@ int riscv_pmu_event_set_period(struct perf_event *event)
 
 	local64_set(&hwc->prev_count, (u64)-left);
 
+	perf_event_update_userpage(event);
+
 	return overflow;
 }
 
@@ -264,6 +338,9 @@ static int riscv_pmu_event_init(struct perf_event *event)
 	hwc->idx = -1;
 	hwc->event_base = mapped_event;
 
+	if (rvpmu->event_init)
+		rvpmu->event_init(event);
+
 	if (!is_sampling_event(event)) {
 		/*
 		 * For non-sampling runs, limit the sample_period to half
@@ -280,6 +357,39 @@ static int riscv_pmu_event_init(struct perf_event *event)
 	return 0;
 }
 
+static int riscv_pmu_event_idx(struct perf_event *event)
+{
+	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
+
+	if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT))
+		return 0;
+
+	if (rvpmu->csr_index)
+		return rvpmu->csr_index(event) + 1;
+
+	return 0;
+}
+
+static void riscv_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
+{
+	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
+
+	if (rvpmu->event_mapped) {
+		rvpmu->event_mapped(event, mm);
+		perf_event_update_userpage(event);
+	}
+}
+
+static void riscv_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
+{
+	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
+
+	if (rvpmu->event_unmapped) {
+		rvpmu->event_unmapped(event, mm);
+		perf_event_update_userpage(event);
+	}
+}
+
 struct riscv_pmu *riscv_pmu_alloc(void)
 {
 	struct riscv_pmu *pmu;
@@ -304,6 +414,9 @@ struct riscv_pmu *riscv_pmu_alloc(void)
 	}
 	pmu->pmu = (struct pmu) {
 		.event_init	= riscv_pmu_event_init,
+		.event_mapped	= riscv_pmu_event_mapped,
+		.event_unmapped	= riscv_pmu_event_unmapped,
+		.event_idx	= riscv_pmu_event_idx,
 		.add		= riscv_pmu_add,
 		.del		= riscv_pmu_del,
 		.start		= riscv_pmu_start,
diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c
index ca9e20bfc7ac..79fdd667922e 100644
--- a/drivers/perf/riscv_pmu_legacy.c
+++ b/drivers/perf/riscv_pmu_legacy.c
@@ -13,7 +13,7 @@
 #include <linux/platform_device.h>
 
 #define RISCV_PMU_LEGACY_CYCLE		0
-#define RISCV_PMU_LEGACY_INSTRET	1
+#define RISCV_PMU_LEGACY_INSTRET	2
 
 static bool pmu_init_done;
 
@@ -71,6 +71,29 @@ static void pmu_legacy_ctr_start(struct perf_event *event, u64 ival)
 	local64_set(&hwc->prev_count, initial_val);
 }
 
+static uint8_t pmu_legacy_csr_index(struct perf_event *event)
+{
+	return event->hw.idx;
+}
+
+static void pmu_legacy_event_mapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES &&
+	    event->attr.config != PERF_COUNT_HW_INSTRUCTIONS)
+		return;
+
+	event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT;
+}
+
+static void pmu_legacy_event_unmapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES &&
+	    event->attr.config != PERF_COUNT_HW_INSTRUCTIONS)
+		return;
+
+	event->hw.flags &= ~PERF_EVENT_FLAG_USER_READ_CNT;
+}
+
 /*
  * This is just a simple implementation to allow legacy implementations
  * compatible with new RISC-V PMU driver framework.
@@ -91,6 +114,9 @@ static void pmu_legacy_init(struct riscv_pmu *pmu)
 	pmu->ctr_get_width = NULL;
 	pmu->ctr_clear_idx = NULL;
 	pmu->ctr_read = pmu_legacy_read_ctr;
+	pmu->event_mapped = pmu_legacy_event_mapped;
+	pmu->event_unmapped = pmu_legacy_event_unmapped;
+	pmu->csr_index = pmu_legacy_csr_index;
 
 	perf_pmu_register(&pmu->pmu, "cpu", PERF_TYPE_RAW);
 }
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 4163ff517471..9a51053b1f99 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -24,6 +24,14 @@
 #include <asm/sbi.h>
 #include <asm/hwcap.h>
 
+#define SYSCTL_NO_USER_ACCESS	0
+#define SYSCTL_USER_ACCESS	1
+#define SYSCTL_LEGACY		2
+
+#define PERF_EVENT_FLAG_NO_USER_ACCESS	BIT(SYSCTL_NO_USER_ACCESS)
+#define PERF_EVENT_FLAG_USER_ACCESS	BIT(SYSCTL_USER_ACCESS)
+#define PERF_EVENT_FLAG_LEGACY		BIT(SYSCTL_LEGACY)
+
 PMU_FORMAT_ATTR(event, "config:0-47");
 PMU_FORMAT_ATTR(firmware, "config:63");
 
@@ -43,6 +51,9 @@ static const struct attribute_group *riscv_pmu_attr_groups[] = {
 	NULL,
 };
 
+/* Allow user mode access by default */
+static int sysctl_perf_user_access __read_mostly = SYSCTL_USER_ACCESS;
+
 /*
  * RISC-V doesn't have heterogeneous harts yet. This need to be part of
  * per_cpu in case of harts with different pmu counters
@@ -301,6 +312,11 @@ int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr)
 }
 EXPORT_SYMBOL_GPL(riscv_pmu_get_hpm_info);
 
+static uint8_t pmu_sbi_csr_index(struct perf_event *event)
+{
+	return pmu_ctr_list[event->hw.idx].csr - CSR_CYCLE;
+}
+
 static unsigned long pmu_sbi_get_filter_flags(struct perf_event *event)
 {
 	unsigned long cflags = 0;
@@ -329,18 +345,34 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(rvpmu->hw_events);
 	struct sbiret ret;
 	int idx;
-	uint64_t cbase = 0;
+	uint64_t cbase = 0, cmask = rvpmu->cmask;
 	unsigned long cflags = 0;
 
 	cflags = pmu_sbi_get_filter_flags(event);
+
+	/*
+	 * In legacy mode, we have to force the fixed counters for those events
+	 * but not in the user access mode as we want to use the other counters
+	 * that support sampling/filtering.
+	 */
+	if (hwc->flags & PERF_EVENT_FLAG_LEGACY) {
+		if (event->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
+			cflags |= SBI_PMU_CFG_FLAG_SKIP_MATCH;
+			cmask = 1;
+		} else if (event->attr.config == PERF_COUNT_HW_INSTRUCTIONS) {
+			cflags |= SBI_PMU_CFG_FLAG_SKIP_MATCH;
+			cmask = 1UL << (CSR_INSTRET - CSR_CYCLE);
+		}
+	}
+
 	/* retrieve the available counter index */
 #if defined(CONFIG_32BIT)
 	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase,
-			rvpmu->cmask, cflags, hwc->event_base, hwc->config,
+			cmask, cflags, hwc->event_base, hwc->config,
 			hwc->config >> 32);
 #else
 	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase,
-			rvpmu->cmask, cflags, hwc->event_base, hwc->config, 0);
+			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",
@@ -474,6 +506,22 @@ static u64 pmu_sbi_ctr_read(struct perf_event *event)
 	return val;
 }
 
+static void pmu_sbi_set_scounteren(void *arg)
+{
+	struct perf_event *event = (struct perf_event *)arg;
+
+	csr_write(CSR_SCOUNTEREN,
+		  csr_read(CSR_SCOUNTEREN) | (1 << pmu_sbi_csr_index(event)));
+}
+
+static void pmu_sbi_reset_scounteren(void *arg)
+{
+	struct perf_event *event = (struct perf_event *)arg;
+
+	csr_write(CSR_SCOUNTEREN,
+		  csr_read(CSR_SCOUNTEREN) & ~(1 << pmu_sbi_csr_index(event)));
+}
+
 static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival)
 {
 	struct sbiret ret;
@@ -490,6 +538,10 @@ static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival)
 	if (ret.error && (ret.error != SBI_ERR_ALREADY_STARTED))
 		pr_err("Starting counter idx %d failed with error %d\n",
 			hwc->idx, sbi_err_map_linux_errno(ret.error));
+
+	if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) &&
+	    (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT))
+		pmu_sbi_set_scounteren((void *)event);
 }
 
 static void pmu_sbi_ctr_stop(struct perf_event *event, unsigned long flag)
@@ -497,6 +549,10 @@ static void pmu_sbi_ctr_stop(struct perf_event *event, unsigned long flag)
 	struct sbiret ret;
 	struct hw_perf_event *hwc = &event->hw;
 
+	if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) &&
+	    (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT))
+		pmu_sbi_reset_scounteren((void *)event);
+
 	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, hwc->idx, 1, flag, 0, 0, 0);
 	if (ret.error && (ret.error != SBI_ERR_ALREADY_STOPPED) &&
 		flag != SBI_PMU_STOP_FLAG_RESET)
@@ -704,10 +760,13 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node)
 	struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events);
 
 	/*
-	 * Enable the access for CYCLE, TIME, and INSTRET CSRs from userspace,
-	 * as is necessary to maintain uABI compatibility.
+	 * We keep enabling userspace access to CYCLE, TIME and INSTRET via the
+	 * legacy option but that will be removed in the future.
 	 */
-	csr_write(CSR_SCOUNTEREN, 0x7);
+	if (sysctl_perf_user_access == SYSCTL_LEGACY)
+		csr_write(CSR_SCOUNTEREN, 0x7);
+	else
+		csr_write(CSR_SCOUNTEREN, 0x2);
 
 	/* Stop all the counters so that they can be enabled from perf */
 	pmu_sbi_stop_all(pmu);
@@ -838,6 +897,121 @@ static void riscv_pmu_destroy(struct riscv_pmu *pmu)
 	cpuhp_state_remove_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node);
 }
 
+static void pmu_sbi_event_init(struct perf_event *event)
+{
+	/*
+	 * The permissions are set at event_init so that we do not depend
+	 * on the sysctl value that can change.
+	 */
+	if (sysctl_perf_user_access == SYSCTL_NO_USER_ACCESS)
+		event->hw.flags |= PERF_EVENT_FLAG_NO_USER_ACCESS;
+	else if (sysctl_perf_user_access == SYSCTL_USER_ACCESS)
+		event->hw.flags |= PERF_EVENT_FLAG_USER_ACCESS;
+	else
+		event->hw.flags |= PERF_EVENT_FLAG_LEGACY;
+}
+
+static void pmu_sbi_event_mapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (event->hw.flags & PERF_EVENT_FLAG_NO_USER_ACCESS)
+		return;
+
+	if (event->hw.flags & PERF_EVENT_FLAG_LEGACY) {
+		if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES &&
+		    event->attr.config != PERF_COUNT_HW_INSTRUCTIONS) {
+			return;
+		}
+	}
+
+	/*
+	 * The user mmapped the event to directly access it: this is where
+	 * we determine based on sysctl_perf_user_access if we grant userspace
+	 * the direct access to this event. That means that within the same
+	 * task, some events may be directly accessible and some other may not,
+	 * if the user changes the value of sysctl_perf_user_accesss in the
+	 * meantime.
+	 */
+
+	event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT;
+
+	/*
+	 * We must enable userspace access *before* advertising in the user page
+	 * that it is possible to do so to avoid any race.
+	 * And we must notify all cpus here because threads that currently run
+	 * on other cpus will try to directly access the counter too without
+	 * calling pmu_sbi_ctr_start.
+	 */
+	if (event->hw.flags & PERF_EVENT_FLAG_USER_ACCESS)
+		on_each_cpu_mask(mm_cpumask(mm),
+				 pmu_sbi_set_scounteren, (void *)event, 1);
+}
+
+static void pmu_sbi_event_unmapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (event->hw.flags & PERF_EVENT_FLAG_NO_USER_ACCESS)
+		return;
+
+	if (event->hw.flags & PERF_EVENT_FLAG_LEGACY) {
+		if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES &&
+		    event->attr.config != PERF_COUNT_HW_INSTRUCTIONS) {
+			return;
+		}
+	}
+
+	/*
+	 * Here we can directly remove user access since the user does not have
+	 * access to the user page anymore so we avoid the racy window where the
+	 * user could have read cap_user_rdpmc to true right before we disable
+	 * it.
+	 */
+	event->hw.flags &= ~PERF_EVENT_FLAG_USER_READ_CNT;
+
+	if (event->hw.flags & PERF_EVENT_FLAG_USER_ACCESS)
+		on_each_cpu_mask(mm_cpumask(mm),
+				 pmu_sbi_reset_scounteren, (void *)event, 1);
+}
+
+static void riscv_pmu_update_counter_access(void *info)
+{
+	if (sysctl_perf_user_access == SYSCTL_LEGACY)
+		csr_write(CSR_SCOUNTEREN, 0x7);
+	else
+		csr_write(CSR_SCOUNTEREN, 0x2);
+}
+
+static int riscv_pmu_proc_user_access_handler(struct ctl_table *table,
+					      int write, void *buffer,
+					      size_t *lenp, loff_t *ppos)
+{
+	int prev = sysctl_perf_user_access;
+	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+	/*
+	 * Test against the previous value since we clear SCOUNTEREN when
+	 * sysctl_perf_user_access is set to SYSCTL_USER_ACCESS, but we should
+	 * not do that if that was already the case.
+	 */
+	if (ret || !write || prev == sysctl_perf_user_access)
+		return ret;
+
+	on_each_cpu(riscv_pmu_update_counter_access, NULL, 1);
+
+	return 0;
+}
+
+static struct ctl_table sbi_pmu_sysctl_table[] = {
+	{
+		.procname       = "perf_user_access",
+		.data		= &sysctl_perf_user_access,
+		.maxlen		= sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler	= riscv_pmu_proc_user_access_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_TWO,
+	},
+	{ }
+};
+
 static int pmu_sbi_device_probe(struct platform_device *pdev)
 {
 	struct riscv_pmu *pmu = NULL;
@@ -881,6 +1055,10 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	pmu->ctr_get_width = pmu_sbi_ctr_get_width;
 	pmu->ctr_clear_idx = pmu_sbi_ctr_clear_idx;
 	pmu->ctr_read = pmu_sbi_ctr_read;
+	pmu->event_init = pmu_sbi_event_init;
+	pmu->event_mapped = pmu_sbi_event_mapped;
+	pmu->event_unmapped = pmu_sbi_event_unmapped;
+	pmu->csr_index = pmu_sbi_csr_index;
 
 	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node);
 	if (ret)
@@ -894,6 +1072,8 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_unregister;
 
+	register_sysctl("kernel", sbi_pmu_sysctl_table);
+
 	return 0;
 
 out_unregister:
@@ -907,7 +1087,7 @@ out_free:
 static struct platform_driver pmu_sbi_driver = {
 	.probe		= pmu_sbi_device_probe,
 	.driver		= {
-		.name	= RISCV_PMU_PDEV_NAME,
+		.name	= RISCV_PMU_SBI_PDEV_NAME,
 	},
 };
 
@@ -934,7 +1114,7 @@ static int __init pmu_sbi_devinit(void)
 	if (ret)
 		return ret;
 
-	pdev = platform_device_register_simple(RISCV_PMU_PDEV_NAME, -1, NULL, 0);
+	pdev = platform_device_register_simple(RISCV_PMU_SBI_PDEV_NAME, -1, NULL, 0);
 	if (IS_ERR(pdev)) {
 		platform_driver_unregister(&pmu_sbi_driver);
 		return PTR_ERR(pdev);