RISC-V Patches for the 5.8 Merge Window, Part 2

* Select statements are now sorted alphanumerically.
 * Our first-level interrupts are now handled via a full irqchip driver.
 * CPU hotplug is fixed.
 * Our vDSO calls now use the common vDSO infrastructure.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEKzw3R0RoQ7JKlDp6LhMZ81+7GIkFAl7hq3QTHHBhbG1lckBk
 YWJiZWx0LmNvbQAKCRAuExnzX7sYiRcXD/9dEmZ/UgKNGE1BYlQoLbS4o3u4dt6K
 aZkl4AvadpgxlmCl5OAqv/8+UIsMmzhJ4y8bQL1FOdPhRQfModFlQFwzDiUbPguU
 Fgh+wXF+/iDywtfA2fVm7OaMBKpftzTBF+YKRsZHdrUF1l3es9f99mxfelcZWx2h
 nMrOdKFjmEeqhPlkF17Wr30elKGO7NqT3caBam9X/do1bgGnJ9sLfehr4b7dXdzk
 QWm6cp8xmSM7A2jKUT8l7WKmZn3a8DDTDws/yKDuFr+2UxfXspPtc+XzN36zRSAd
 DkL3Zwp+egld4y43019BaK2yY4sQ59HzJYRD+4Z0BiRltBs2gexVqkFy2k8kGemh
 X4kLe2opNQdsh9tcAM+s2VnBuwuiKPXc6AtNXaQKzeuZ6286axweYlCcYufTgzXP
 oEu1haDMjsZz9/mXNiQhvGIPMU/obXSRdJYvryhIwpDOqR3cvbpeQTtC/16raNwd
 OjE0qFE7AtI9pa7+oCQPfcJurjm6cPkv25b+L2SQ+dW9WkE6QzIP5ynMuxdhxg2m
 OxKbuV0mZ3MgbdK+nEc72gUtbUjdb3t/1a9GwoNNLW78eKER3uXl4vxAyIqSKgf7
 RViL0/CzEPqU97S/3qVPC27KhsBbqvXwM7gE1MVnm1HiEUiKnlZkLjzFqkorLUMz
 emv+mW+kdjZ1aQ==
 =FQnf
 -----END PGP SIGNATURE-----

Merge tag 'riscv-for-linus-5.8-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull more RISC-V updates from Palmer Dabbelt:

 - Kconfig select statements are now sorted alphanumerically

 - first-level interrupts are now handled via a full irqchip driver

 - CPU hotplug is fixed

 - vDSO calls now use the common vDSO infrastructure

* tag 'riscv-for-linus-5.8-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  riscv: set the permission of vdso_data to read-only
  riscv: use vDSO common flow to reduce the latency of the time-related functions
  riscv: fix build warning of missing prototypes
  RISC-V: Don't mark init section as non-executable
  RISC-V: Force select RISCV_INTC for CONFIG_RISCV
  RISC-V: Remove do_IRQ() function
  clocksource/drivers/timer-riscv: Use per-CPU timer interrupt
  irqchip: RISC-V per-HART local interrupt controller driver
  RISC-V: Rename and move plic_find_hart_id() to arch directory
  RISC-V: self-contained IPI handling routine
  RISC-V: Sort select statements alphanumerically

arch/riscv/Kconfig

@@ -12,64 +12,70 @@ config 32BIT
 
 config RISCV
 	def_bool y
-	select OF
+	select ARCH_CLOCKSOURCE_INIT
-	select OF_EARLY_FLATTREE
-	select OF_IRQ
 	select ARCH_HAS_BINFMT_FLAT
+	select ARCH_HAS_DEBUG_VIRTUAL if MMU
 	select ARCH_HAS_DEBUG_WX
+	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_GIGANTIC_PAGE
+	select ARCH_HAS_MMIOWB
+	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_SET_DIRECT_MAP
+	select ARCH_HAS_SET_MEMORY
+	select ARCH_HAS_STRICT_KERNEL_RWX if MMU
+	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_FRAME_POINTERS
+	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
+	select EDAC_SUPPORT
+	select GENERIC_ARCH_TOPOLOGY if SMP
+	select GENERIC_ATOMIC64 if !64BIT
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_GETTIMEOFDAY if HAVE_GENERIC_VDSO
+	select GENERIC_IOREMAP
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
+	select GENERIC_PTDUMP if MMU
 	select GENERIC_SCHED_CLOCK
+	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_STRNCPY_FROM_USER if MMU
 	select GENERIC_STRNLEN_USER if MMU
-	select GENERIC_SMP_IDLE_THREAD
+	select GENERIC_TIME_VSYSCALL if MMU && 64BIT
-	select GENERIC_ATOMIC64 if !64BIT
+	select HANDLE_DOMAIN_IRQ
-	select GENERIC_IOREMAP
-	select GENERIC_PTDUMP if MMU
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_KASAN if MMU && 64BIT
+	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_KGDB_QXFER_PKT
+	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ASM_MODVERSIONS
+	select HAVE_COPY_THREAD_TLS
 	select HAVE_DMA_CONTIGUOUS if MMU
+	select HAVE_EBPF_JIT if MMU
 	select HAVE_FUTEX_CMPXCHG if FUTEX
+	select HAVE_GENERIC_VDSO if MMU && 64BIT
+	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_SYSCALL_TRACEPOINTS
 	select IRQ_DOMAIN
-	select SPARSE_IRQ
-	select SYSCTL_EXCEPTION_TRACE
-	select HAVE_ARCH_TRACEHOOK
-	select HAVE_PCI
 	select MODULES_USE_ELF_RELA if MODULES
 	select MODULE_SECTIONS if MODULES
-	select THREAD_INFO_IN_TASK
+	select OF
+	select OF_EARLY_FLATTREE
+	select OF_IRQ
 	select PCI_DOMAINS_GENERIC if PCI
 	select PCI_MSI if PCI
+	select RISCV_INTC
 	select RISCV_TIMER
-	select GENERIC_IRQ_MULTI_HANDLER
-	select GENERIC_ARCH_TOPOLOGY if SMP
-	select ARCH_HAS_PTE_SPECIAL
-	select ARCH_HAS_MMIOWB
-	select ARCH_HAS_DEBUG_VIRTUAL if MMU
-	select HAVE_EBPF_JIT if MMU
-	select EDAC_SUPPORT
-	select ARCH_HAS_GIGANTIC_PAGE
-	select ARCH_HAS_SET_DIRECT_MAP
-	select ARCH_HAS_SET_MEMORY
-	select ARCH_HAS_STRICT_KERNEL_RWX if MMU
-	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select SPARSEMEM_STATIC if 32BIT
-	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
+	select SPARSE_IRQ
-	select HAVE_ARCH_MMAP_RND_BITS if MMU
+	select SYSCTL_EXCEPTION_TRACE
-	select ARCH_HAS_GCOV_PROFILE_ALL
+	select THREAD_INFO_IN_TASK
-	select HAVE_COPY_THREAD_TLS
-	select HAVE_ARCH_KASAN if MMU && 64BIT
-	select HAVE_ARCH_KGDB
-	select HAVE_ARCH_KGDB_QXFER_PKT
 
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
@@ -196,11 +202,11 @@ config ARCH_RV64I
 	bool "RV64I"
 	select 64BIT
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && GCC_VERSION >= 50000
-	select HAVE_FUNCTION_TRACER
-	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE if MMU
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_TRACER
 	select SWIOTLB if MMU
 
 endchoice

arch/riscv/include/asm/clocksource.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_CLOCKSOURCE_H
+#define _ASM_CLOCKSOURCE_H
+
+#include <asm/vdso/clocksource.h>
+
+#endif

arch/riscv/include/asm/irq.h

@@ -10,11 +10,6 @@
 #include <linux/interrupt.h>
 #include <linux/linkage.h>
 
-#define NR_IRQS         0
-
-void riscv_timer_interrupt(void);
-void riscv_software_interrupt(void);
-
 #include <asm-generic/irq.h>
 
 #endif /* _ASM_RISCV_IRQ_H */

arch/riscv/include/asm/processor.h

@@ -8,6 +8,8 @@
 
 #include <linux/const.h>
 
+#include <vdso/processor.h>
+
 #include <asm/ptrace.h>
 
 /*
@@ -58,16 +60,6 @@ static inline void release_thread(struct task_struct *dead_task)
 extern unsigned long get_wchan(struct task_struct *p);
 
 
-static inline void cpu_relax(void)
-{
-#ifdef __riscv_muldiv
-	int dummy;
-	/* In lieu of a halt instruction, induce a long-latency stall. */
-	__asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
-#endif
-	barrier();
-}
-
 static inline void wait_for_interrupt(void)
 {
 	__asm__ __volatile__ ("wfi");
@@ -75,6 +67,7 @@ static inline void wait_for_interrupt(void)
 
 struct device_node;
 int riscv_of_processor_hartid(struct device_node *node);
+int riscv_of_parent_hartid(struct device_node *node);
 
 extern void riscv_fill_hwcap(void);
 

arch/riscv/include/asm/smp.h

@@ -28,6 +28,9 @@ void show_ipi_stats(struct seq_file *p, int prec);
 /* SMP initialization hook for setup_arch */
 void __init setup_smp(void);
 
+/* Called from C code, this handles an IPI. */
+void handle_IPI(struct pt_regs *regs);
+
 /* Hook for the generic smp_call_function_many() routine. */
 void arch_send_call_function_ipi_mask(struct cpumask *mask);
 

arch/riscv/include/asm/vdso.h

@@ -10,8 +10,10 @@
 
 #include <linux/types.h>
 
+#ifndef GENERIC_TIME_VSYSCALL
 struct vdso_data {
 };
+#endif
 
 /*
  * The VDSO symbols are mapped into Linux so we can just use regular symbol

arch/riscv/include/asm/vdso/clocksource.h

@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSOCLOCKSOURCE_H
+#define __ASM_VDSOCLOCKSOURCE_H
+
+#define VDSO_ARCH_CLOCKMODES	\
+	VDSO_CLOCKMODE_ARCHTIMER
+
+#endif

arch/riscv/include/asm/vdso/gettimeofday.h

@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/unistd.h>
+#include <asm/csr.h>
+#include <uapi/linux/time.h>
+
+#define VDSO_HAS_CLOCK_GETRES	1
+
+static __always_inline
+int gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+			  struct timezone *_tz)
+{
+	register struct __kernel_old_timeval *tv asm("a0") = _tv;
+	register struct timezone *tz asm("a1") = _tz;
+	register long ret asm("a0");
+	register long nr asm("a7") = __NR_gettimeofday;
+
+	asm volatile ("ecall\n"
+		      : "=r" (ret)
+		      : "r"(tv), "r"(tz), "r"(nr)
+		      : "memory");
+
+	return ret;
+}
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register clockid_t clkid asm("a0") = _clkid;
+	register struct __kernel_timespec *ts asm("a1") = _ts;
+	register long ret asm("a0");
+	register long nr asm("a7") = __NR_clock_gettime;
+
+	asm volatile ("ecall\n"
+		      : "=r" (ret)
+		      : "r"(clkid), "r"(ts), "r"(nr)
+		      : "memory");
+
+	return ret;
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register clockid_t clkid asm("a0") = _clkid;
+	register struct __kernel_timespec *ts asm("a1") = _ts;
+	register long ret asm("a0");
+	register long nr asm("a7") = __NR_clock_getres;
+
+	asm volatile ("ecall\n"
+		      : "=r" (ret)
+		      : "r"(clkid), "r"(ts), "r"(nr)
+		      : "memory");
+
+	return ret;
+}
+
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
+{
+	/*
+	 * The purpose of csr_read(CSR_TIME) is to trap the system into
+	 * M-mode to obtain the value of CSR_TIME. Hence, unlike other
+	 * architecture, no fence instructions surround the csr_read()
+	 */
+	return csr_read(CSR_TIME);
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+	return _vdso_data;
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */

arch/riscv/include/asm/vdso/processor.h

@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_VDSO_PROCESSOR_H
+#define __ASM_VDSO_PROCESSOR_H
+
+#ifndef __ASSEMBLY__
+
+static inline void cpu_relax(void)
+{
+#ifdef __riscv_muldiv
+	int dummy;
+	/* In lieu of a halt instruction, induce a long-latency stall. */
+	__asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
+#endif
+	barrier();
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_PROCESSOR_H */

arch/riscv/include/asm/vdso/vsyscall.h

@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_VSYSCALL_H
+#define __ASM_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/timekeeper_internal.h>
+#include <vdso/datapage.h>
+
+extern struct vdso_data *vdso_data;
+
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+static __always_inline struct vdso_data *__riscv_get_k_vdso_data(void)
+{
+	return vdso_data;
+}
+
+#define __arch_get_k_vdso_data __riscv_get_k_vdso_data
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_VSYSCALL_H */

arch/riscv/kernel/cpu.c

@@ -44,6 +44,22 @@ int riscv_of_processor_hartid(struct device_node *node)
 	return hart;
 }
 
+/*
+ * Find hart ID of the CPU DT node under which given DT node falls.
+ *
+ * To achieve this, we walk up the DT tree until we find an active
+ * RISC-V core (HART) node and extract the cpuid from it.
+ */
+int riscv_of_parent_hartid(struct device_node *node)
+{
+	for (; node; node = node->parent) {
+		if (of_device_is_compatible(node, "riscv"))
+			return riscv_of_processor_hartid(node);
+	}
+
+	return -1;
+}
+
 #ifdef CONFIG_PROC_FS
 
 static void print_isa(struct seq_file *f, const char *isa)

arch/riscv/kernel/entry.S

@@ -106,7 +106,9 @@ _save_context:
 
 	/* Handle interrupts */
 	move a0, sp /* pt_regs */
-	tail do_IRQ
+	la a1, handle_arch_irq
+	REG_L a1, (a1)
+	jr a1
 1:
 	/*
 	 * Exceptions run with interrupts enabled or disabled depending on the

arch/riscv/kernel/irq.c

@@ -7,7 +7,6 @@
 
 #include <linux/interrupt.h>
 #include <linux/irqchip.h>
-#include <linux/irqdomain.h>
 #include <linux/seq_file.h>
 #include <asm/smp.h>
 
@@ -17,37 +16,9 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	return 0;
 }
 
-asmlinkage __visible void __irq_entry do_IRQ(struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-
-	irq_enter();
-	switch (regs->cause & ~CAUSE_IRQ_FLAG) {
-	case RV_IRQ_TIMER:
-		riscv_timer_interrupt();
-		break;
-#ifdef CONFIG_SMP
-	case RV_IRQ_SOFT:
-		/*
-		 * We only use software interrupts to pass IPIs, so if a non-SMP
-		 * system gets one, then we don't know what to do.
-		 */
-		riscv_software_interrupt();
-		break;
-#endif
-	case RV_IRQ_EXT:
-		handle_arch_irq(regs);
-		break;
-	default:
-		pr_alert("unexpected interrupt cause 0x%lx", regs->cause);
-		BUG();
-	}
-	irq_exit();
-
-	set_irq_regs(old_regs);
-}
-
 void __init init_IRQ(void)
 {
 	irqchip_init();
+	if (!handle_arch_irq)
+		panic("No interrupt controller found.");
 }

arch/riscv/kernel/patch.c

@@ -11,6 +11,7 @@
 #include <asm/kprobes.h>
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
+#include <asm/patch.h>
 
 struct patch_insn {
 	void *addr;

arch/riscv/kernel/smp.c

@@ -123,11 +123,14 @@ static inline void clear_ipi(void)
 		clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id()));
 }
 
-void riscv_software_interrupt(void)
+void handle_IPI(struct pt_regs *regs)
 {
+	struct pt_regs *old_regs = set_irq_regs(regs);
 	unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
 	unsigned long *stats = ipi_data[smp_processor_id()].stats;
 
+	irq_enter();
+
 	clear_ipi();
 
 	while (true) {
@@ -138,7 +141,7 @@ void riscv_software_interrupt(void)
 
 		ops = xchg(pending_ipis, 0);
 		if (ops == 0)
-			return;
+			goto done;
 
 		if (ops & (1 << IPI_RESCHEDULE)) {
 			stats[IPI_RESCHEDULE]++;
@@ -160,6 +163,10 @@ void riscv_software_interrupt(void)
 		/* Order data access and bit testing. */
 		mb();
 	}
+
+done:
+	irq_exit();
+	set_irq_regs(old_regs);
 }
 
 static const char * const ipi_names[] = {

arch/riscv/kernel/time.c

@@ -26,3 +26,12 @@ void __init time_init(void)
 	lpj_fine = riscv_timebase / HZ;
 	timer_probe();
 }
+
+void clocksource_arch_init(struct clocksource *cs)
+{
+#ifdef CONFIG_GENERIC_GETTIMEOFDAY
+	cs->vdso_clock_mode = VDSO_CLOCKMODE_ARCHTIMER;
+#else
+	cs->vdso_clock_mode = VDSO_CLOCKMODE_NONE;
+#endif
+}

arch/riscv/kernel/traps.c

@@ -183,6 +183,4 @@ void trap_init(void)
 	csr_write(CSR_SCRATCH, 0);
 	/* Set the exception vector address */
 	csr_write(CSR_TVEC, &handle_exception);
-	/* Enable interrupts */
-	csr_write(CSR_IE, IE_SIE);
 }

arch/riscv/kernel/vdso.c

@@ -11,8 +11,12 @@
 #include <linux/slab.h>
 #include <linux/binfmts.h>
 #include <linux/err.h>
-
+#include <asm/page.h>
+#ifdef GENERIC_TIME_VSYSCALL
+#include <vdso/datapage.h>
+#else
 #include <asm/vdso.h>
+#endif
 
 extern char vdso_start[], vdso_end[];
 
@@ -26,7 +30,7 @@ static union {
 	struct vdso_data	data;
 	u8			page[PAGE_SIZE];
 } vdso_data_store __page_aligned_data;
-static struct vdso_data *vdso_data = &vdso_data_store.data;
+struct vdso_data *vdso_data = &vdso_data_store.data;
 
 static int __init vdso_init(void)
 {
@@ -75,13 +79,22 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 	 */
 	mm->context.vdso = (void *)vdso_base;
 
-	ret = install_special_mapping(mm, vdso_base, vdso_len,
+	ret =
+	   install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
 		(VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
 		vdso_pagelist);
 
+	if (unlikely(ret)) {
+		mm->context.vdso = NULL;
+		goto end;
+	}
+
+	vdso_base += (vdso_pages << PAGE_SHIFT);
+	ret = install_special_mapping(mm, vdso_base, PAGE_SIZE,
+		(VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]);
+
 	if (unlikely(ret))
 		mm->context.vdso = NULL;
-
 end:
 	mmap_write_unlock(mm);
 	return ret;
@@ -91,5 +104,8 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 {
 	if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso))
 		return "[vdso]";
+	if (vma->vm_mm && (vma->vm_start ==
+			   (long)vma->vm_mm->context.vdso + PAGE_SIZE))
+		return "[vdso_data]";
 	return NULL;
 }

arch/riscv/kernel/vdso/Makefile

@@ -1,12 +1,14 @@
 # SPDX-License-Identifier: GPL-2.0-only
 # Copied from arch/tile/kernel/vdso/Makefile
 
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_RISCV_32|R_RISCV_64|R_RISCV_JUMP_SLOT
+include $(srctree)/lib/vdso/Makefile
 # Symbols present in the vdso
 vdso-syms  = rt_sigreturn
 ifdef CONFIG_64BIT
-vdso-syms += gettimeofday
+vdso-syms += vgettimeofday
-vdso-syms += clock_gettime
-vdso-syms += clock_getres
 endif
 vdso-syms += getcpu
 vdso-syms += flush_icache
@@ -14,6 +16,10 @@ vdso-syms += flush_icache
 # Files to link into the vdso
 obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
 
+ifneq ($(c-gettimeofday-y),)
+  CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+endif
+
 # Build rules
 targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-dummy.o
 obj-vdso := $(addprefix $(obj)/, $(obj-vdso))

arch/riscv/kernel/vdso/clock_getres.S

@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2017 SiFive
- */
-
-#include <linux/linkage.h>
-#include <asm/unistd.h>
-
-	.text
-/* int __vdso_clock_getres(clockid_t clock_id, struct timespec *res); */
-ENTRY(__vdso_clock_getres)
-	.cfi_startproc
-	/* For now, just do the syscall. */
-	li a7, __NR_clock_getres
-	ecall
-	ret
-	.cfi_endproc
-ENDPROC(__vdso_clock_getres)

arch/riscv/kernel/vdso/clock_gettime.S

@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2017 SiFive
- */
-
-#include <linux/linkage.h>
-#include <asm/unistd.h>
-
-	.text
-/* int __vdso_clock_gettime(clockid_t clock_id, struct timespec *tp); */
-ENTRY(__vdso_clock_gettime)
-	.cfi_startproc
-	/* For now, just do the syscall. */
-	li a7, __NR_clock_gettime
-	ecall
-	ret
-	.cfi_endproc
-ENDPROC(__vdso_clock_gettime)

arch/riscv/kernel/vdso/gettimeofday.S

@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2017 SiFive
- */
-
-#include <linux/linkage.h>
-#include <asm/unistd.h>
-
-	.text
-/* int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); */
-ENTRY(__vdso_gettimeofday)
-	.cfi_startproc
-	/* For now, just do the syscall. */
-	li a7, __NR_gettimeofday
-	ecall
-	ret
-	.cfi_endproc
-ENDPROC(__vdso_gettimeofday)

arch/riscv/kernel/vdso/vdso.lds.S

@@ -2,11 +2,13 @@
 /*
  * Copyright (C) 2012 Regents of the University of California
  */
+#include <asm/page.h>
 
 OUTPUT_ARCH(riscv)
 
 SECTIONS
 {
+	PROVIDE(_vdso_data = . + PAGE_SIZE);
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text

arch/riscv/kernel/vdso/vgettimeofday.c

@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copied from arch/arm64/kernel/vdso/vgettimeofday.c
+ *
+ * Copyright (C) 2018 ARM Ltd.
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/time.h>
+#include <linux/types.h>
+
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_gettime(clock, ts);
+}
+
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
+{
+	return __cvdso_gettimeofday(tv, tz);
+}
+
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
+{
+	return __cvdso_clock_getres(clock_id, res);
+}

arch/riscv/mm/init.c

@@ -480,17 +480,6 @@ static void __init setup_vm_final(void)
 	csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | SATP_MODE);
 	local_flush_tlb_all();
 }
-
-void free_initmem(void)
-{
-	unsigned long init_begin = (unsigned long)__init_begin;
-	unsigned long init_end = (unsigned long)__init_end;
-
-	/* Make the region as non-execuatble. */
-	set_memory_nx(init_begin, (init_end - init_begin) >> PAGE_SHIFT);
-	free_initmem_default(POISON_FREE_INITMEM);
-}
-
 #else
 asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 {

drivers/clocksource/timer-riscv.c

@@ -12,8 +12,11 @@
 #include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
+#include <linux/irqdomain.h>
 #include <linux/sched_clock.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/interrupt.h>
+#include <linux/of_irq.h>
 #include <asm/smp.h>
 #include <asm/sbi.h>
 
@@ -39,6 +42,7 @@ static int riscv_clock_next_event(unsigned long delta,
 	return 0;
 }
 
+static unsigned int riscv_clock_event_irq;
 static DEFINE_PER_CPU(struct clock_event_device, riscv_clock_event) = {
 	.name			= "riscv_timer_clockevent",
 	.features		= CLOCK_EVT_FEAT_ONESHOT,
@@ -74,30 +78,36 @@ static int riscv_timer_starting_cpu(unsigned int cpu)
 	struct clock_event_device *ce = per_cpu_ptr(&riscv_clock_event, cpu);
 
 	ce->cpumask = cpumask_of(cpu);
+	ce->irq = riscv_clock_event_irq;
 	clockevents_config_and_register(ce, riscv_timebase, 100, 0x7fffffff);
 
-	csr_set(CSR_IE, IE_TIE);
+	enable_percpu_irq(riscv_clock_event_irq,
+			  irq_get_trigger_type(riscv_clock_event_irq));
 	return 0;
 }
 
 static int riscv_timer_dying_cpu(unsigned int cpu)
 {
-	csr_clear(CSR_IE, IE_TIE);
+	disable_percpu_irq(riscv_clock_event_irq);
 	return 0;
 }
 
 /* called directly from the low-level interrupt handler */
-void riscv_timer_interrupt(void)
+static irqreturn_t riscv_timer_interrupt(int irq, void *dev_id)
 {
 	struct clock_event_device *evdev = this_cpu_ptr(&riscv_clock_event);
 
 	csr_clear(CSR_IE, IE_TIE);
 	evdev->event_handler(evdev);
+
+	return IRQ_HANDLED;
 }
 
 static int __init riscv_timer_init_dt(struct device_node *n)
 {
 	int cpuid, hartid, error;
+	struct device_node *child;
+	struct irq_domain *domain;
 
 	hartid = riscv_of_processor_hartid(n);
 	if (hartid < 0) {
@@ -115,6 +125,25 @@ static int __init riscv_timer_init_dt(struct device_node *n)
 	if (cpuid != smp_processor_id())
 		return 0;
 
+	domain = NULL;
+	child = of_get_compatible_child(n, "riscv,cpu-intc");
+	if (!child) {
+		pr_err("Failed to find INTC node [%pOF]\n", n);
+		return -ENODEV;
+	}
+	domain = irq_find_host(child);
+	of_node_put(child);
+	if (!domain) {
+		pr_err("Failed to find IRQ domain for node [%pOF]\n", n);
+		return -ENODEV;
+	}
+
+	riscv_clock_event_irq = irq_create_mapping(domain, RV_IRQ_TIMER);
+	if (!riscv_clock_event_irq) {
+		pr_err("Failed to map timer interrupt for node [%pOF]\n", n);
+		return -ENODEV;
+	}
+
 	pr_info("%s: Registering clocksource cpuid [%d] hartid [%d]\n",
 	       __func__, cpuid, hartid);
 	error = clocksource_register_hz(&riscv_clocksource, riscv_timebase);
@@ -126,6 +155,14 @@ static int __init riscv_timer_init_dt(struct device_node *n)
 
 	sched_clock_register(riscv_sched_clock, 64, riscv_timebase);
 
+	error = request_percpu_irq(riscv_clock_event_irq,
+				    riscv_timer_interrupt,
+				    "riscv-timer", &riscv_clock_event);
+	if (error) {
+		pr_err("registering percpu irq failed [%d]\n", error);
+		return error;
+	}
+
 	error = cpuhp_setup_state(CPUHP_AP_RISCV_TIMER_STARTING,
 			 "clockevents/riscv/timer:starting",
 			 riscv_timer_starting_cpu, riscv_timer_dying_cpu);

drivers/irqchip/Kconfig

@@ -493,6 +493,19 @@ config TI_SCI_INTA_IRQCHIP
 	  If you wish to use interrupt aggregator irq resources managed by the
 	  TI System Controller, say Y here. Otherwise, say N.
 
+config RISCV_INTC
+	bool "RISC-V Local Interrupt Controller"
+	depends on RISCV
+	default y
+	help
+	   This enables support for the per-HART local interrupt controller
+	   found in standard RISC-V systems.  The per-HART local interrupt
+	   controller handles timer interrupts, software interrupts, and
+	   hardware interrupts. Without a per-HART local interrupt controller,
+	   a RISC-V system will be unable to handle any interrupts.
+
+	   If you don't know what to do here, say Y.
+
 config SIFIVE_PLIC
 	bool "SiFive Platform-Level Interrupt Controller"
 	depends on RISCV

drivers/irqchip/Makefile

@@ -98,6 +98,7 @@ obj-$(CONFIG_NDS32)			+= irq-ativic32.o
 obj-$(CONFIG_QCOM_PDC)			+= qcom-pdc.o
 obj-$(CONFIG_CSKY_MPINTC)		+= irq-csky-mpintc.o
 obj-$(CONFIG_CSKY_APB_INTC)		+= irq-csky-apb-intc.o
+obj-$(CONFIG_RISCV_INTC)		+= irq-riscv-intc.o
 obj-$(CONFIG_SIFIVE_PLIC)		+= irq-sifive-plic.o
 obj-$(CONFIG_IMX_IRQSTEER)		+= irq-imx-irqsteer.o
 obj-$(CONFIG_IMX_INTMUX)		+= irq-imx-intmux.o

drivers/irqchip/irq-riscv-intc.c

@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017-2018 SiFive
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#define pr_fmt(fmt) "riscv-intc: " fmt
+#include <linux/atomic.h>
+#include <linux/bits.h>
+#include <linux/cpu.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/smp.h>
+
+static struct irq_domain *intc_domain;
+
+static asmlinkage void riscv_intc_irq(struct pt_regs *regs)
+{
+	unsigned long cause = regs->cause & ~CAUSE_IRQ_FLAG;
+
+	if (unlikely(cause >= BITS_PER_LONG))
+		panic("unexpected interrupt cause");
+
+	switch (cause) {
+#ifdef CONFIG_SMP
+	case RV_IRQ_SOFT:
+		/*
+		 * We only use software interrupts to pass IPIs, so if a
+		 * non-SMP system gets one, then we don't know what to do.
+		 */
+		handle_IPI(regs);
+		break;
+#endif
+	default:
+		handle_domain_irq(intc_domain, cause, regs);
+		break;
+	}
+}
+
+/*
+ * On RISC-V systems local interrupts are masked or unmasked by writing
+ * the SIE (Supervisor Interrupt Enable) CSR.  As CSRs can only be written
+ * on the local hart, these functions can only be called on the hart that
+ * corresponds to the IRQ chip.
+ */
+
+static void riscv_intc_irq_mask(struct irq_data *d)
+{
+	csr_clear(CSR_IE, BIT(d->hwirq));
+}
+
+static void riscv_intc_irq_unmask(struct irq_data *d)
+{
+	csr_set(CSR_IE, BIT(d->hwirq));
+}
+
+static int riscv_intc_cpu_starting(unsigned int cpu)
+{
+	csr_set(CSR_IE, BIT(RV_IRQ_SOFT));
+	return 0;
+}
+
+static int riscv_intc_cpu_dying(unsigned int cpu)
+{
+	csr_clear(CSR_IE, BIT(RV_IRQ_SOFT));
+	return 0;
+}
+
+static struct irq_chip riscv_intc_chip = {
+	.name = "RISC-V INTC",
+	.irq_mask = riscv_intc_irq_mask,
+	.irq_unmask = riscv_intc_irq_unmask,
+};
+
+static int riscv_intc_domain_map(struct irq_domain *d, unsigned int irq,
+				 irq_hw_number_t hwirq)
+{
+	irq_set_percpu_devid(irq);
+	irq_domain_set_info(d, irq, hwirq, &riscv_intc_chip, d->host_data,
+			    handle_percpu_devid_irq, NULL, NULL);
+
+	return 0;
+}
+
+static const struct irq_domain_ops riscv_intc_domain_ops = {
+	.map	= riscv_intc_domain_map,
+	.xlate	= irq_domain_xlate_onecell,
+};
+
+static int __init riscv_intc_init(struct device_node *node,
+				  struct device_node *parent)
+{
+	int rc, hartid;
+
+	hartid = riscv_of_parent_hartid(node);
+	if (hartid < 0) {
+		pr_warn("unable to fine hart id for %pOF\n", node);
+		return 0;
+	}
+
+	/*
+	 * The DT will have one INTC DT node under each CPU (or HART)
+	 * DT node so riscv_intc_init() function will be called once
+	 * for each INTC DT node. We only need to do INTC initialization
+	 * for the INTC DT node belonging to boot CPU (or boot HART).
+	 */
+	if (riscv_hartid_to_cpuid(hartid) != smp_processor_id())
+		return 0;
+
+	intc_domain = irq_domain_add_linear(node, BITS_PER_LONG,
+					    &riscv_intc_domain_ops, NULL);
+	if (!intc_domain) {
+		pr_err("unable to add IRQ domain\n");
+		return -ENXIO;
+	}
+
+	rc = set_handle_irq(&riscv_intc_irq);
+	if (rc) {
+		pr_err("failed to set irq handler\n");
+		return rc;
+	}
+
+	cpuhp_setup_state(CPUHP_AP_IRQ_RISCV_STARTING,
+			  "irqchip/riscv/intc:starting",
+			  riscv_intc_cpu_starting,
+			  riscv_intc_cpu_dying);
+
+	pr_info("%d local interrupts mapped\n", BITS_PER_LONG);
+
+	return 0;
+}
+
+IRQCHIP_DECLARE(riscv, "riscv,cpu-intc", riscv_intc_init);

drivers/irqchip/irq-sifive-plic.c

@@ -9,6 +9,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -76,6 +77,7 @@ struct plic_handler {
 	void __iomem		*enable_base;
 	struct plic_priv	*priv;
 };
+static int plic_parent_irq;
 static bool plic_cpuhp_setup_done;
 static DEFINE_PER_CPU(struct plic_handler, plic_handlers);
 
@@ -219,15 +221,17 @@ static const struct irq_domain_ops plic_irqdomain_ops = {
  * that source ID back to the same claim register.  This automatically enables
  * and disables the interrupt, so there's nothing else to do.
  */
-static void plic_handle_irq(struct pt_regs *regs)
+static void plic_handle_irq(struct irq_desc *desc)
 {
 	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 	void __iomem *claim = handler->hart_base + CONTEXT_CLAIM;
 	irq_hw_number_t hwirq;
 
 	WARN_ON_ONCE(!handler->present);
 
-	csr_clear(CSR_IE, IE_EIE);
+	chained_irq_enter(chip, desc);
+
 	while ((hwirq = readl(claim))) {
 		int irq = irq_find_mapping(handler->priv->irqdomain, hwirq);
 
@@ -237,21 +241,8 @@ static void plic_handle_irq(struct pt_regs *regs)
 		else
 			generic_handle_irq(irq);
 	}
-	csr_set(CSR_IE, IE_EIE);
-}
 
-/*
+	chained_irq_exit(chip, desc);
- * Walk up the DT tree until we find an active RISC-V core (HART) node and
- * extract the cpuid from it.
- */
-static int plic_find_hart_id(struct device_node *node)
-{
-	for (; node; node = node->parent) {
-		if (of_device_is_compatible(node, "riscv"))
-			return riscv_of_processor_hartid(node);
-	}
-
-	return -1;
 }
 
 static void plic_set_threshold(struct plic_handler *handler, u32 threshold)
@@ -262,10 +253,8 @@ static void plic_set_threshold(struct plic_handler *handler, u32 threshold)
 
 static int plic_dying_cpu(unsigned int cpu)
 {
-	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
+	if (plic_parent_irq)
-
+		disable_percpu_irq(plic_parent_irq);
-	csr_clear(CSR_IE, IE_EIE);
-	plic_set_threshold(handler, PLIC_DISABLE_THRESHOLD);
 
 	return 0;
 }
@@ -274,7 +263,11 @@ static int plic_starting_cpu(unsigned int cpu)
 {
 	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
 
-	csr_set(CSR_IE, IE_EIE);
+	if (plic_parent_irq)
+		enable_percpu_irq(plic_parent_irq,
+				  irq_get_trigger_type(plic_parent_irq));
+	else
+		pr_warn("cpu%d: parent irq not available\n", cpu);
 	plic_set_threshold(handler, PLIC_ENABLE_THRESHOLD);
 
 	return 0;
@@ -330,7 +323,7 @@ static int __init plic_init(struct device_node *node,
 		if (parent.args[0] != RV_IRQ_EXT)
 			continue;
 
-		hartid = plic_find_hart_id(parent.np);
+		hartid = riscv_of_parent_hartid(parent.np);
 		if (hartid < 0) {
 			pr_warn("failed to parse hart ID for context %d.\n", i);
 			continue;
@@ -342,6 +335,14 @@ static int __init plic_init(struct device_node *node,
 			continue;
 		}
 
+		/* Find parent domain and register chained handler */
+		if (!plic_parent_irq && irq_find_host(parent.np)) {
+			plic_parent_irq = irq_of_parse_and_map(node, i);
+			if (plic_parent_irq)
+				irq_set_chained_handler(plic_parent_irq,
+							plic_handle_irq);
+		}
+
 		/*
 		 * When running in M-mode we need to ignore the S-mode handler.
 		 * Here we assume it always comes later, but that might be a
@@ -382,7 +383,6 @@ done:
 
 	pr_info("%pOFP: mapped %d interrupts with %d handlers for"
 		" %d contexts.\n", node, nr_irqs, nr_handlers, nr_contexts);
-	set_handle_irq(plic_handle_irq);
 	return 0;
 
 out_iounmap:

include/linux/cpuhotplug.h

@@ -102,6 +102,7 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_IRQ_MIPS_GIC_STARTING,
+	CPUHP_AP_IRQ_RISCV_STARTING,
 	CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
 	CPUHP_AP_MICROCODE_LOADER,