Merge tag 'riscv-for-linus-6.18-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V fixes from Paul Walmsley:

 - Close a race during boot between userspace vDSO usage and some
   late-initialized vDSO data

 - Improve performance on systems with non-CPU-cache-coherent
   DMA-capable peripherals by enabling write combining on
   pgprot_dmacoherent() allocations

 - Add human-readable detail for RISC-V IPI tracing

 - Provide more information to zsmalloc on 64-bit RISC-V to improve
   allocation

 - Silence useless boot messages about CPUs that have been disabled in
   DT

 - Resolve some compiler and smatch warnings and remove a redundant
   macro

* tag 'riscv-for-linus-6.18-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  riscv: hwprobe: avoid uninitialized variable use in hwprobe_arch_id()
  riscv: cpufeature: avoid uninitialized variable in has_thead_homogeneous_vlenb()
  riscv: hwprobe: Fix stale vDSO data for late-initialized keys at boot
  riscv: add a forward declaration for cpuinfo_op
  RISC-V: Don't print details of CPUs disabled in DT
  riscv: Remove the PER_CPU_OFFSET_SHIFT macro
  riscv: mm: Define MAX_POSSIBLE_PHYSMEM_BITS for zsmalloc
  riscv: Register IPI IRQs with unique names
  ACPI: RIMT: Fix unused function warnings when CONFIG_IOMMU_API is disabled
  RISC-V: Define pgprot_dmacoherent() for non-coherent devices

13 files changed, 168 insertions, 100 deletions

diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 8bd2a11382a3..ac28066bb564 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -84,15 +84,9 @@
 .endm
 
 #ifdef CONFIG_SMP
-#ifdef CONFIG_32BIT
-#define PER_CPU_OFFSET_SHIFT 2
-#else
-#define PER_CPU_OFFSET_SHIFT 3
-#endif
-
 .macro asm_per_cpu dst sym tmp
 	lw    \tmp, TASK_TI_CPU_NUM(tp)
-	slli  \tmp, \tmp, PER_CPU_OFFSET_SHIFT
+	slli  \tmp, \tmp, RISCV_LGPTR
 	la    \dst, __per_cpu_offset
 	add   \dst, \dst, \tmp
 	REG_L \tmp, 0(\dst)
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index fbd0e4306c93..62837fa981e8 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -31,6 +31,8 @@ struct riscv_isainfo {
 
 DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
 
+extern const struct seq_operations cpuinfo_op;
+
 /* Per-cpu ISA extensions. */
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index 948d2b34e94e..58f8dda73259 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -42,4 +42,11 @@ static inline bool riscv_hwprobe_pair_cmp(struct riscv_hwprobe *pair,
 	return pair->value == other_pair->value;
 }
 
+#ifdef CONFIG_MMU
+void riscv_hwprobe_register_async_probe(void);
+void riscv_hwprobe_complete_async_probe(void);
+#else
+static inline void riscv_hwprobe_register_async_probe(void) {}
+static inline void riscv_hwprobe_complete_async_probe(void) {}
+#endif
 #endif
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 1018d2216901..6e789fa58514 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -69,6 +69,8 @@ typedef struct {
 
 #define PTRS_PER_PMD    (PAGE_SIZE / sizeof(pmd_t))
 
+#define MAX_POSSIBLE_PHYSMEM_BITS 56
+
 /*
  * rv64 PTE format:
  * | 63 | 62 61 | 60 54 | 53  10 | 9             8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 29e994a9afb6..5a08eb5fe99f 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -654,6 +654,8 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
 	return __pgprot(prot);
 }
 
+#define pgprot_dmacoherent pgprot_writecombine
+
 /*
  * Both Svade and Svadu control the hardware behavior when the PTE A/D bits need to be set. By
  * default the M-mode firmware enables the hardware updating scheme when only Svadu is present in
diff --git a/arch/riscv/include/asm/vdso/arch_data.h b/arch/riscv/include/asm/vdso/arch_data.h
index da57a3786f7a..88b37af55175 100644
--- a/arch/riscv/include/asm/vdso/arch_data.h
+++ b/arch/riscv/include/asm/vdso/arch_data.h
@@ -12,6 +12,12 @@ struct vdso_arch_data {
 
 	/* Boolean indicating all CPUs have the same static hwprobe values. */
 	__u8 homogeneous_cpus;
+
+	/*
+	 * A gate to check and see if the hwprobe data is actually ready, as
+	 * probing is deferred to avoid boot slowdowns.
+	 */
+	__u8 ready;
 };
 
 #endif /* __RISCV_ASM_VDSO_ARCH_DATA_H */
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index f6b13e9f5e6c..3dbc8cc557dd 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -62,10 +62,8 @@ int __init riscv_early_of_processor_hartid(struct device_node *node, unsigned lo
 		return -ENODEV;
 	}
 
-	if (!of_device_is_available(node)) {
-		pr_info("CPU with hartid=%lu is not available\n", *hart);
+	if (!of_device_is_available(node))
 		return -ENODEV;
-	}
 
 	if (of_property_read_string(node, "riscv,isa-base", &isa))
 		goto old_interface;
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 67b59699357d..72ca768f4e91 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -932,9 +932,9 @@ static int has_thead_homogeneous_vlenb(void)
 {
 	int cpu;
 	u32 prev_vlenb = 0;
-	u32 vlenb;
+	u32 vlenb = 0;
 
-	/* Ignore thead,vlenb property if xtheavector is not enabled in the kernel */
+	/* Ignore thead,vlenb property if xtheadvector is not enabled in the kernel */
 	if (!IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR))
 		return 0;
 
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index e650dec44817..5ed5095320e6 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -40,6 +40,17 @@ enum ipi_message_type {
 	IPI_MAX
 };
 
+static const char * const ipi_names[] = {
+	[IPI_RESCHEDULE]	= "Rescheduling interrupts",
+	[IPI_CALL_FUNC]		= "Function call interrupts",
+	[IPI_CPU_STOP]		= "CPU stop interrupts",
+	[IPI_CPU_CRASH_STOP]	= "CPU stop (for crash dump) interrupts",
+	[IPI_IRQ_WORK]		= "IRQ work interrupts",
+	[IPI_TIMER]		= "Timer broadcast interrupts",
+	[IPI_CPU_BACKTRACE]     = "CPU backtrace interrupts",
+	[IPI_KGDB_ROUNDUP]	= "KGDB roundup interrupts",
+};
+
 unsigned long __cpuid_to_hartid_map[NR_CPUS] __ro_after_init = {
 	[0 ... NR_CPUS-1] = INVALID_HARTID
 };
@@ -199,7 +210,7 @@ void riscv_ipi_set_virq_range(int virq, int nr)
 	/* Request IPIs */
 	for (i = 0; i < nr_ipi; i++) {
 		err = request_percpu_irq(ipi_virq_base + i, handle_IPI,
-					 "IPI", &ipi_dummy_dev);
+					 ipi_names[i], &ipi_dummy_dev);
 		WARN_ON(err);
 
 		ipi_desc[i] = irq_to_desc(ipi_virq_base + i);
@@ -210,17 +221,6 @@ void riscv_ipi_set_virq_range(int virq, int nr)
 	riscv_ipi_enable();
 }
 
-static const char * const ipi_names[] = {
-	[IPI_RESCHEDULE]	= "Rescheduling interrupts",
-	[IPI_CALL_FUNC]		= "Function call interrupts",
-	[IPI_CPU_STOP]		= "CPU stop interrupts",
-	[IPI_CPU_CRASH_STOP]	= "CPU stop (for crash dump) interrupts",
-	[IPI_IRQ_WORK]		= "IRQ work interrupts",
-	[IPI_TIMER]		= "Timer broadcast interrupts",
-	[IPI_CPU_BACKTRACE]     = "CPU backtrace interrupts",
-	[IPI_KGDB_ROUNDUP]	= "KGDB roundup interrupts",
-};
-
 void show_ipi_stats(struct seq_file *p, int prec)
 {
 	unsigned int cpu, i;
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index 000f4451a9d8..199d13f86f31 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -5,6 +5,9 @@
  * more details.
  */
 #include <linux/syscalls.h>
+#include <linux/completion.h>
+#include <linux/atomic.h>
+#include <linux/once.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/hwprobe.h>
@@ -28,6 +31,11 @@ static void hwprobe_arch_id(struct riscv_hwprobe *pair,
 	bool first = true;
 	int cpu;
 
+	if (pair->key != RISCV_HWPROBE_KEY_MVENDORID &&
+	    pair->key != RISCV_HWPROBE_KEY_MIMPID &&
+	    pair->key != RISCV_HWPROBE_KEY_MARCHID)
+		goto out;
+
 	for_each_cpu(cpu, cpus) {
 		u64 cpu_id;
 
@@ -58,6 +66,7 @@ static void hwprobe_arch_id(struct riscv_hwprobe *pair,
 		}
 	}
 
+out:
 	pair->value = id;
 }
 
@@ -454,28 +463,32 @@ static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs,
 	return 0;
 }
 
-static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
-			    size_t pair_count, size_t cpusetsize,
-			    unsigned long __user *cpus_user,
-			    unsigned int flags)
-{
-	if (flags & RISCV_HWPROBE_WHICH_CPUS)
-		return hwprobe_get_cpus(pairs, pair_count, cpusetsize,
-					cpus_user, flags);
+#ifdef CONFIG_MMU
 
-	return hwprobe_get_values(pairs, pair_count, cpusetsize,
-				  cpus_user, flags);
+static DECLARE_COMPLETION(boot_probes_done);
+static atomic_t pending_boot_probes = ATOMIC_INIT(1);
+
+void riscv_hwprobe_register_async_probe(void)
+{
+	atomic_inc(&pending_boot_probes);
 }
 
-#ifdef CONFIG_MMU
+void riscv_hwprobe_complete_async_probe(void)
+{
+	if (atomic_dec_and_test(&pending_boot_probes))
+		complete(&boot_probes_done);
+}
 
-static int __init init_hwprobe_vdso_data(void)
+static int complete_hwprobe_vdso_data(void)
 {
 	struct vdso_arch_data *avd = vdso_k_arch_data;
 	u64 id_bitsmash = 0;
 	struct riscv_hwprobe pair;
 	int key;
 
+	if (unlikely(!atomic_dec_and_test(&pending_boot_probes)))
+		wait_for_completion(&boot_probes_done);
+
 	/*
 	 * Initialize vDSO data with the answers for the "all CPUs" case, to
 	 * save a syscall in the common case.
@@ -503,13 +516,52 @@ static int __init init_hwprobe_vdso_data(void)
 	 * vDSO should defer to the kernel for exotic cpu masks.
 	 */
 	avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1;
+
+	/*
+	 * Make sure all the VDSO values are visible before we look at them.
+	 * This pairs with the implicit "no speculativly visible accesses"
+	 * barrier in the VDSO hwprobe code.
+	 */
+	smp_wmb();
+	avd->ready = true;
+	return 0;
+}
+
+static int __init init_hwprobe_vdso_data(void)
+{
+	struct vdso_arch_data *avd = vdso_k_arch_data;
+
+	/*
+	 * Prevent the vDSO cached values from being used, as they're not ready
+	 * yet.
+	 */
+	avd->ready = false;
 	return 0;
 }
 
 arch_initcall_sync(init_hwprobe_vdso_data);
 
+#else
+
+static int complete_hwprobe_vdso_data(void) { return 0; }
+
 #endif /* CONFIG_MMU */
 
+static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
+			    size_t pair_count, size_t cpusetsize,
+			    unsigned long __user *cpus_user,
+			    unsigned int flags)
+{
+	DO_ONCE_SLEEPABLE(complete_hwprobe_vdso_data);
+
+	if (flags & RISCV_HWPROBE_WHICH_CPUS)
+		return hwprobe_get_cpus(pairs, pair_count, cpusetsize,
+					cpus_user, flags);
+
+	return hwprobe_get_values(pairs, pair_count, cpusetsize,
+				cpus_user, flags);
+}
+
 SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
 		size_t, pair_count, size_t, cpusetsize, unsigned long __user *,
 		cpus, unsigned int, flags)
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index ae2068425fbc..70b5e6927620 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -379,6 +379,7 @@ free:
 static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
 {
 	schedule_on_each_cpu(check_vector_unaligned_access);
+	riscv_hwprobe_complete_async_probe();
 
 	return 0;
 }
@@ -473,8 +474,12 @@ static int __init check_unaligned_access_all_cpus(void)
 			per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param;
 	} else if (!check_vector_unaligned_access_emulated_all_cpus() &&
 		   IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) {
-		kthread_run(vec_check_unaligned_access_speed_all_cpus,
-			    NULL, "vec_check_unaligned_access_speed_all_cpus");
+		riscv_hwprobe_register_async_probe();
+		if (IS_ERR(kthread_run(vec_check_unaligned_access_speed_all_cpus,
+				       NULL, "vec_check_unaligned_access_speed_all_cpus"))) {
+			pr_warn("Failed to create vec_unalign_check kthread\n");
+			riscv_hwprobe_complete_async_probe();
+		}
 	}
 
 	/*
diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c
index 2ddeba6c68dd..8f45500d0a6e 100644
--- a/arch/riscv/kernel/vdso/hwprobe.c
+++ b/arch/riscv/kernel/vdso/hwprobe.c
@@ -27,7 +27,7 @@ static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count,
 	 * homogeneous, then this function can handle requests for arbitrary
 	 * masks.
 	 */
-	if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus))
+	if (flags != 0 || (!all_cpus && !avd->homogeneous_cpus) || unlikely(!avd->ready))
 		return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags);
 
 	/* This is something we can handle, fill out the pairs. */
diff --git a/drivers/acpi/riscv/rimt.c b/drivers/acpi/riscv/rimt.c
index 683fcfe35c31..7f423405e5ef 100644
--- a/drivers/acpi/riscv/rimt.c
+++ b/drivers/acpi/riscv/rimt.c
@@ -61,30 +61,6 @@ static int rimt_set_fwnode(struct acpi_rimt_node *rimt_node,
 	return 0;
 }
 
-/**
- * rimt_get_fwnode() - Retrieve fwnode associated with an RIMT node
- *
- * @node: RIMT table node to be looked-up
- *
- * Returns: fwnode_handle pointer on success, NULL on failure
- */
-static struct fwnode_handle *rimt_get_fwnode(struct acpi_rimt_node *node)
-{
-	struct fwnode_handle *fwnode = NULL;
-	struct rimt_fwnode *curr;
-
-	spin_lock(&rimt_fwnode_lock);
-	list_for_each_entry(curr, &rimt_fwnode_list, list) {
-		if (curr->rimt_node == node) {
-			fwnode = curr->fwnode;
-			break;
-		}
-	}
-	spin_unlock(&rimt_fwnode_lock);
-
-	return fwnode;
-}
-
 static acpi_status rimt_match_node_callback(struct acpi_rimt_node *node,
 					    void *context)
 {
@@ -202,6 +178,67 @@ static struct acpi_rimt_node *rimt_scan_node(enum acpi_rimt_node_type type,
 	return NULL;
 }
 
+/*
+ * RISC-V supports IOMMU as a PCI device or a platform device.
+ * When it is a platform device, there should be a namespace device as
+ * well along with RIMT. To create the link between RIMT information and
+ * the platform device, the IOMMU driver should register itself with the
+ * RIMT module. This is true for PCI based IOMMU as well.
+ */
+int rimt_iommu_register(struct device *dev)
+{
+	struct fwnode_handle *rimt_fwnode;
+	struct acpi_rimt_node *node;
+
+	node = rimt_scan_node(ACPI_RIMT_NODE_TYPE_IOMMU, dev);
+	if (!node) {
+		pr_err("Could not find IOMMU node in RIMT\n");
+		return -ENODEV;
+	}
+
+	if (dev_is_pci(dev)) {
+		rimt_fwnode = acpi_alloc_fwnode_static();
+		if (!rimt_fwnode)
+			return -ENOMEM;
+
+		rimt_fwnode->dev = dev;
+		if (!dev->fwnode)
+			dev->fwnode = rimt_fwnode;
+
+		rimt_set_fwnode(node, rimt_fwnode);
+	} else {
+		rimt_set_fwnode(node, dev->fwnode);
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_IOMMU_API
+
+/**
+ * rimt_get_fwnode() - Retrieve fwnode associated with an RIMT node
+ *
+ * @node: RIMT table node to be looked-up
+ *
+ * Returns: fwnode_handle pointer on success, NULL on failure
+ */
+static struct fwnode_handle *rimt_get_fwnode(struct acpi_rimt_node *node)
+{
+	struct fwnode_handle *fwnode = NULL;
+	struct rimt_fwnode *curr;
+
+	spin_lock(&rimt_fwnode_lock);
+	list_for_each_entry(curr, &rimt_fwnode_list, list) {
+		if (curr->rimt_node == node) {
+			fwnode = curr->fwnode;
+			break;
+		}
+	}
+	spin_unlock(&rimt_fwnode_lock);
+
+	return fwnode;
+}
+
 static bool rimt_pcie_rc_supports_ats(struct acpi_rimt_node *node)
 {
 	struct acpi_rimt_pcie_rc *pci_rc;
@@ -290,43 +327,6 @@ static struct acpi_rimt_node *rimt_node_get_id(struct acpi_rimt_node *node,
 	return NULL;
 }
 
-/*
- * RISC-V supports IOMMU as a PCI device or a platform device.
- * When it is a platform device, there should be a namespace device as
- * well along with RIMT. To create the link between RIMT information and
- * the platform device, the IOMMU driver should register itself with the
- * RIMT module. This is true for PCI based IOMMU as well.
- */
-int rimt_iommu_register(struct device *dev)
-{
-	struct fwnode_handle *rimt_fwnode;
-	struct acpi_rimt_node *node;
-
-	node = rimt_scan_node(ACPI_RIMT_NODE_TYPE_IOMMU, dev);
-	if (!node) {
-		pr_err("Could not find IOMMU node in RIMT\n");
-		return -ENODEV;
-	}
-
-	if (dev_is_pci(dev)) {
-		rimt_fwnode = acpi_alloc_fwnode_static();
-		if (!rimt_fwnode)
-			return -ENOMEM;
-
-		rimt_fwnode->dev = dev;
-		if (!dev->fwnode)
-			dev->fwnode = rimt_fwnode;
-
-		rimt_set_fwnode(node, rimt_fwnode);
-	} else {
-		rimt_set_fwnode(node, dev->fwnode);
-	}
-
-	return 0;
-}
-
-#ifdef CONFIG_IOMMU_API
-
 static struct acpi_rimt_node *rimt_node_map_id(struct acpi_rimt_node *node,
 					       u32 id_in, u32 *id_out,
 					       u8 type_mask)