RISC-V updates for v5.4-rc1

Add the following new features:
 
 - Generic CPU topology description support for DT-based platforms,
   including ARM64, ARM and RISC-V.
 
 - Sparsemem support
 
 - Perf callchain support
 
 - SiFive PLIC irqchip modifications, in preparation for M-mode Linux
 
 and clean up the code base:
 
 - Clean up chip-specific register (CSR) manipulation code, IPIs, TLB
   flushing, and the RISC-V CPU-local timer code
 
 - Kbuild cleanup from one of the Kbuild maintainers
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEElRDoIDdEz9/svf2Kx4+xDQu9KksFAl1/pGEACgkQx4+xDQu9
 Kkvkyw/9GulLK2yeXG8SoXiXWZAhrgUn487GM87BJXFwXkjDCRvYVk4RD8BKfOGt
 w1td6BXK5PjceH+d2m3kHa1aBQwT7sgsfQD0mBiHQ7TG+CMHMPV31eqjgIgnklEY
 f6bRl4JGokanPnLWE8tnQrMpu91kDI0XS2pnnQNNrAK3DbWocsdUIei14+auwygp
 Djbwssb8R/5RQdFO1dRa+0dWo1omzCJBgkMQBXipvD/z7u8BApioYdEUN1pEg6Yg
 YLdVtBUIF5gXIsq9jdqEZHWzvTPnq+5HZPy8pAYe/fPcnga89fCfgpWA9DfqjIEA
 bNFHJJKWc/lFAcMmXWWkYwgIbx8PUiktdv27S/DYLdyZ4SIX5YEtmdD6aK4ZStQT
 ZQcvCMDq9C3Y4s1PIwl9ORI8aVs3k1cI4Ee0xWS/x6D9h/84Ky1uBFgrPXai2G6q
 AUxnu0zWhllNahxp+rvUh0rnfHOMalaTG8eUb1GEoLzFcRhKYrKWLgFG/eBCAiit
 dofD24KpYSpZNrhZWgVUuE0Jcc58JSHp/LzDUloR2AcAvdxyQZ2Vd+vwE5BGGTzR
 t/V4zjSvndXUxFBVe28zHO2qrDzA+jUE8d+vO8w+lDGjbITYYZwIJPBL3f8Z0s6b
 wQWBwWlM4ZATqR662sBpz8P/t+RCcTMfLlatIV/07GRerjvPrd8=
 =N9WW
 -----END PGP SIGNATURE-----

Merge tag 'riscv/for-v5.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Paul Walmsley:
 "Add the following new features:

   - Generic CPU topology description support for DT-based platforms,
     including ARM64, ARM and RISC-V.

   - Sparsemem support

   - Perf callchain support

   - SiFive PLIC irqchip modifications, in preparation for M-mode Linux

  and clean up the code base:

   - Clean up chip-specific register (CSR) manipulation code, IPIs, TLB
     flushing, and the RISC-V CPU-local timer code

   - Kbuild cleanup from one of the Kbuild maintainers"

[ The CPU topology parts came in through the arm64 tree with a shared
  branch   - Linus ]

* tag 'riscv/for-v5.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  irqchip/sifive-plic: set max threshold for ignored handlers
  riscv: move the TLB flush logic out of line
  riscv: don't use the rdtime(h) pseudo-instructions
  riscv: cleanup riscv_cpuid_to_hartid_mask
  riscv: optimize send_ipi_single
  riscv: cleanup send_ipi_mask
  riscv: refactor the IPI code
  riscv: Add support for libdw
  riscv: Add support for perf registers sampling
  riscv: Add perf callchain support
  riscv: add arch/riscv/Kbuild
  RISC-V: Implement sparsemem
  riscv: Using CSR numbers to access CSRs

arch/riscv/Kbuild

@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-y += kernel/ mm/ net/

arch/riscv/Kconfig

@@ -35,6 +35,8 @@ config RISCV
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_SYSCALL_TRACEPOINTS
 	select IRQ_DOMAIN
 	select SPARSE_IRQ
@@ -55,6 +57,7 @@ config RISCV
 	select EDAC_SUPPORT
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
+	select SPARSEMEM_STATIC if 32BIT
 
 config MMU
 	def_bool y
@@ -63,12 +66,32 @@ config ZONE_DMA32
 	bool
 	default y if 64BIT
 
+config VA_BITS
+	int
+	default 32 if 32BIT
+	default 39 if 64BIT
+
+config PA_BITS
+	int
+	default 34 if 32BIT
+	default 56 if 64BIT
+
 config PAGE_OFFSET
 	hex
 	default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB
 	default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
 	default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
 
+config ARCH_FLATMEM_ENABLE
+	def_bool y
+
+config ARCH_SPARSEMEM_ENABLE
+	def_bool y
+	select SPARSEMEM_VMEMMAP_ENABLE
+
+config ARCH_SELECT_MEMORY_MODEL
+	def_bool ARCH_SPARSEMEM_ENABLE
+
 config ARCH_WANT_GENERAL_HUGETLB
 	def_bool y
 

arch/riscv/Makefile

@@ -54,6 +54,9 @@ endif
 ifeq ($(CONFIG_MODULE_SECTIONS),y)
 	KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/riscv/kernel/module.lds
 endif
+ifeq ($(CONFIG_PERF_EVENTS),y)
+        KBUILD_CFLAGS += -fno-omit-frame-pointer
+endif
 
 KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax)
 
@@ -72,7 +75,7 @@ KBUILD_IMAGE	:= $(boot)/Image.gz
 
 head-y := arch/riscv/kernel/head.o
 
-core-y += arch/riscv/kernel/ arch/riscv/mm/ arch/riscv/net/
+core-y += arch/riscv/
 
 libs-y += arch/riscv/lib/
 

arch/riscv/include/asm/page.h

@@ -110,8 +110,10 @@ extern unsigned long min_low_pfn;
 #define page_to_bus(page)	(page_to_phys(page))
 #define phys_to_page(paddr)	(pfn_to_page(phys_to_pfn(paddr)))
 
+#ifdef CONFIG_FLATMEM
 #define pfn_valid(pfn) \
 	(((pfn) >= pfn_base) && (((pfn)-pfn_base) < max_mapnr))
+#endif
 
 #define ARCH_PFN_OFFSET		(pfn_base)
 

arch/riscv/include/asm/pgtable.h

@@ -83,6 +83,19 @@ extern pgd_t swapper_pg_dir[];
 #define __S110	PAGE_SHARED_EXEC
 #define __S111	PAGE_SHARED_EXEC
 
+/*
+ * Roughly size the vmemmap space to be large enough to fit enough
+ * struct pages to map half the virtual address space. Then
+ * position vmemmap directly below the VMALLOC region.
+ */
+#define VMEMMAP_SHIFT \
+	(CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
+#define VMEMMAP_SIZE	BIT(VMEMMAP_SHIFT)
+#define VMEMMAP_END	(VMALLOC_START - 1)
+#define VMEMMAP_START	(VMALLOC_START - VMEMMAP_SIZE)
+
+#define vmemmap		((struct page *)VMEMMAP_START)
+
 /*
  * ZERO_PAGE is a global shared page that is always zero,
  * used for zero-mapped memory areas, etc.

arch/riscv/include/asm/smp.h

@@ -61,11 +61,5 @@ static inline unsigned long cpuid_to_hartid_map(int cpu)
 	return boot_cpu_hartid;
 }
 
-static inline void riscv_cpuid_to_hartid_mask(const struct cpumask *in,
-					      struct cpumask *out)
-{
-	cpumask_set_cpu(cpuid_to_hartid_map(0), out);
-}
-
 #endif /* CONFIG_SMP */
 #endif /* _ASM_RISCV_SMP_H */

arch/riscv/include/asm/sparsemem.h

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_SPARSEMEM_H
+#define __ASM_SPARSEMEM_H
+
+#ifdef CONFIG_SPARSEMEM
+#define MAX_PHYSMEM_BITS	CONFIG_PA_BITS
+#define SECTION_SIZE_BITS	27
+#endif /* CONFIG_SPARSEMEM */
+
+#endif /* __ASM_SPARSEMEM_H */

arch/riscv/include/asm/timex.h

@@ -6,43 +6,41 @@
 #ifndef _ASM_RISCV_TIMEX_H
 #define _ASM_RISCV_TIMEX_H
 
-#include <asm/param.h>
+#include <asm/csr.h>
 
 typedef unsigned long cycles_t;
 
-static inline cycles_t get_cycles_inline(void)
+static inline cycles_t get_cycles(void)
 {
-	cycles_t n;
-
-	__asm__ __volatile__ (
-		"rdtime %0"
-		: "=r" (n));
-	return n;
+	return csr_read(CSR_TIME);
 }
-#define get_cycles get_cycles_inline
+#define get_cycles get_cycles
 
 #ifdef CONFIG_64BIT
-static inline uint64_t get_cycles64(void)
+static inline u64 get_cycles64(void)
 {
-        return get_cycles();
+	return get_cycles();
 }
-#else
-static inline uint64_t get_cycles64(void)
+#else /* CONFIG_64BIT */
+static inline u32 get_cycles_hi(void)
 {
-	u32 lo, hi, tmp;
-	__asm__ __volatile__ (
-		"1:\n"
-		"rdtimeh %0\n"
-		"rdtime %1\n"
-		"rdtimeh %2\n"
-		"bne %0, %2, 1b"
-		: "=&r" (hi), "=&r" (lo), "=&r" (tmp));
+	return csr_read(CSR_TIMEH);
+}
+
+static inline u64 get_cycles64(void)
+{
+	u32 hi, lo;
+
+	do {
+		hi = get_cycles_hi();
+		lo = get_cycles();
+	} while (hi != get_cycles_hi());
+
 	return ((u64)hi << 32) | lo;
 }
-#endif
+#endif /* CONFIG_64BIT */
 
 #define ARCH_HAS_READ_CURRENT_TIMER
-
 static inline int read_current_timer(unsigned long *timer_val)
 {
 	*timer_val = get_cycles();

arch/riscv/include/asm/tlbflush.h

@@ -25,8 +25,13 @@ static inline void local_flush_tlb_page(unsigned long addr)
 	__asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory");
 }
 
-#ifndef CONFIG_SMP
-
+#ifdef CONFIG_SMP
+void flush_tlb_all(void);
+void flush_tlb_mm(struct mm_struct *mm);
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
+void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end);
+#else /* CONFIG_SMP */
 #define flush_tlb_all() local_flush_tlb_all()
 #define flush_tlb_page(vma, addr) local_flush_tlb_page(addr)
 
@@ -37,35 +42,6 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 }
 
 #define flush_tlb_mm(mm) flush_tlb_all()
-
-#else /* CONFIG_SMP */
-
-#include <asm/sbi.h>
-
-static inline void remote_sfence_vma(struct cpumask *cmask, unsigned long start,
-				     unsigned long size)
-{
-	struct cpumask hmask;
-
-	cpumask_clear(&hmask);
-	riscv_cpuid_to_hartid_mask(cmask, &hmask);
-	sbi_remote_sfence_vma(hmask.bits, start, size);
-}
-
-#define flush_tlb_all() sbi_remote_sfence_vma(NULL, 0, -1)
-
-#define flush_tlb_range(vma, start, end) \
-	remote_sfence_vma(mm_cpumask((vma)->vm_mm), start, (end) - (start))
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
-				  unsigned long addr)
-{
-	flush_tlb_range(vma, addr, addr + PAGE_SIZE);
-}
-
-#define flush_tlb_mm(mm)				\
-	remote_sfence_vma(mm_cpumask(mm), 0, -1)
-
 #endif /* CONFIG_SMP */
 
 /* Flush a range of kernel pages */

arch/riscv/include/uapi/asm/perf_regs.h

@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#ifndef _ASM_RISCV_PERF_REGS_H
+#define _ASM_RISCV_PERF_REGS_H
+
+enum perf_event_riscv_regs {
+	PERF_REG_RISCV_PC,
+	PERF_REG_RISCV_RA,
+	PERF_REG_RISCV_SP,
+	PERF_REG_RISCV_GP,
+	PERF_REG_RISCV_TP,
+	PERF_REG_RISCV_T0,
+	PERF_REG_RISCV_T1,
+	PERF_REG_RISCV_T2,
+	PERF_REG_RISCV_S0,
+	PERF_REG_RISCV_S1,
+	PERF_REG_RISCV_A0,
+	PERF_REG_RISCV_A1,
+	PERF_REG_RISCV_A2,
+	PERF_REG_RISCV_A3,
+	PERF_REG_RISCV_A4,
+	PERF_REG_RISCV_A5,
+	PERF_REG_RISCV_A6,
+	PERF_REG_RISCV_A7,
+	PERF_REG_RISCV_S2,
+	PERF_REG_RISCV_S3,
+	PERF_REG_RISCV_S4,
+	PERF_REG_RISCV_S5,
+	PERF_REG_RISCV_S6,
+	PERF_REG_RISCV_S7,
+	PERF_REG_RISCV_S8,
+	PERF_REG_RISCV_S9,
+	PERF_REG_RISCV_S10,
+	PERF_REG_RISCV_S11,
+	PERF_REG_RISCV_T3,
+	PERF_REG_RISCV_T4,
+	PERF_REG_RISCV_T5,
+	PERF_REG_RISCV_T6,
+	PERF_REG_RISCV_MAX,
+};
+#endif /* _ASM_RISCV_PERF_REGS_H */

arch/riscv/kernel/Makefile

@@ -38,6 +38,8 @@ obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= mcount-dyn.o
 
-obj-$(CONFIG_PERF_EVENTS)      += perf_event.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
+obj-$(CONFIG_HAVE_PERF_REGS)	+= perf_regs.o
 
 clean:

arch/riscv/kernel/entry.S

@@ -167,7 +167,7 @@ ENTRY(handle_exception)
 	tail do_IRQ
 1:
 	/* Exceptions run with interrupts enabled */
-	csrs sstatus, SR_SIE
+	csrs CSR_SSTATUS, SR_SIE
 
 	/* Handle syscalls */
 	li t0, EXC_SYSCALL
@@ -222,7 +222,7 @@ ret_from_syscall:
 
 ret_from_exception:
 	REG_L s0, PT_SSTATUS(sp)
-	csrc sstatus, SR_SIE
+	csrc CSR_SSTATUS, SR_SIE
 	andi s0, s0, SR_SPP
 	bnez s0, resume_kernel
 
@@ -265,7 +265,7 @@ work_pending:
 	bnez s1, work_resched
 work_notifysig:
 	/* Handle pending signals and notify-resume requests */
-	csrs sstatus, SR_SIE /* Enable interrupts for do_notify_resume() */
+	csrs CSR_SSTATUS, SR_SIE /* Enable interrupts for do_notify_resume() */
 	move a0, sp /* pt_regs */
 	move a1, s0 /* current_thread_info->flags */
 	tail do_notify_resume

arch/riscv/kernel/fpu.S

@@ -23,7 +23,7 @@ ENTRY(__fstate_save)
 	li  a2,  TASK_THREAD_F0
 	add a0, a0, a2
 	li t1, SR_FS
-	csrs sstatus, t1
+	csrs CSR_SSTATUS, t1
 	frcsr t0
 	fsd f0,  TASK_THREAD_F0_F0(a0)
 	fsd f1,  TASK_THREAD_F1_F0(a0)
@@ -58,7 +58,7 @@ ENTRY(__fstate_save)
 	fsd f30, TASK_THREAD_F30_F0(a0)
 	fsd f31, TASK_THREAD_F31_F0(a0)
 	sw t0, TASK_THREAD_FCSR_F0(a0)
-	csrc sstatus, t1
+	csrc CSR_SSTATUS, t1
 	ret
 ENDPROC(__fstate_save)
 
@@ -67,7 +67,7 @@ ENTRY(__fstate_restore)
 	add a0, a0, a2
 	li t1, SR_FS
 	lw t0, TASK_THREAD_FCSR_F0(a0)
-	csrs sstatus, t1
+	csrs CSR_SSTATUS, t1
 	fld f0,  TASK_THREAD_F0_F0(a0)
 	fld f1,  TASK_THREAD_F1_F0(a0)
 	fld f2,  TASK_THREAD_F2_F0(a0)
@@ -101,6 +101,6 @@ ENTRY(__fstate_restore)
 	fld f30, TASK_THREAD_F30_F0(a0)
 	fld f31, TASK_THREAD_F31_F0(a0)
 	fscsr t0
-	csrc sstatus, t1
+	csrc CSR_SSTATUS, t1
 	ret
 ENDPROC(__fstate_restore)

arch/riscv/kernel/head.S

@@ -61,7 +61,7 @@ _start_kernel:
 	 * floating point in kernel space
 	 */
 	li t0, SR_FS
-	csrc sstatus, t0
+	csrc CSR_SSTATUS, t0
 
 	/* Pick one hart to run the main boot sequence */
 	la a3, hart_lottery

arch/riscv/kernel/perf_callchain.c

@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+
+/* Kernel callchain */
+struct stackframe {
+	unsigned long fp;
+	unsigned long ra;
+};
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry,
+				    unsigned long fp, unsigned long reg_ra)
+{
+	struct stackframe buftail;
+	unsigned long ra = 0;
+	unsigned long *user_frame_tail =
+			(unsigned long *)(fp - sizeof(struct stackframe));
+
+	/* Check accessibility of one struct frame_tail beyond */
+	if (!access_ok(user_frame_tail, sizeof(buftail)))
+		return 0;
+	if (__copy_from_user_inatomic(&buftail, user_frame_tail,
+				      sizeof(buftail)))
+		return 0;
+
+	if (reg_ra != 0)
+		ra = reg_ra;
+	else
+		ra = buftail.ra;
+
+	fp = buftail.fp;
+	if (ra != 0)
+		perf_callchain_store(entry, ra);
+	else
+		return 0;
+
+	return fp;
+}
+
+/*
+ * This will be called when the target is in user mode
+ * This function will only be called when we use
+ * "PERF_SAMPLE_CALLCHAIN" in
+ * kernel/events/core.c:perf_prepare_sample()
+ *
+ * How to trigger perf_callchain_[user/kernel] :
+ * $ perf record -e cpu-clock --call-graph fp ./program
+ * $ perf report --call-graph
+ *
+ * On RISC-V platform, the program being sampled and the C library
+ * need to be compiled with -fno-omit-frame-pointer, otherwise
+ * the user stack will not contain function frame.
+ */
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
+			 struct pt_regs *regs)
+{
+	unsigned long fp = 0;
+
+	/* RISC-V does not support perf in guest mode. */
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
+		return;
+
+	fp = regs->s0;
+	perf_callchain_store(entry, regs->sepc);
+
+	fp = user_backtrace(entry, fp, regs->ra);
+	while (fp && !(fp & 0x3) && entry->nr < entry->max_stack)
+		fp = user_backtrace(entry, fp, 0);
+}
+
+bool fill_callchain(unsigned long pc, void *entry)
+{
+	return perf_callchain_store(entry, pc);
+}
+
+void notrace walk_stackframe(struct task_struct *task,
+	struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg);
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+			   struct pt_regs *regs)
+{
+	/* RISC-V does not support perf in guest mode. */
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		pr_warn("RISC-V does not support perf in guest mode!");
+		return;
+	}
+
+	walk_stackframe(NULL, regs, fill_callchain, entry);
+}

arch/riscv/kernel/perf_regs.c

@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_RISCV_MAX))
+		return 0;
+
+	return ((unsigned long *)regs)[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_RISCV_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+#if __riscv_xlen == 64
+	return PERF_SAMPLE_REGS_ABI_64;
+#else
+	return PERF_SAMPLE_REGS_ABI_32;
+#endif
+}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}

arch/riscv/kernel/smp.c

@@ -56,6 +56,7 @@ void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out)
 {
 	int cpu;
 
+	cpumask_clear(out);
 	for_each_cpu(cpu, in)
 		cpumask_set_cpu(cpuid_to_hartid_map(cpu), out);
 }
@@ -78,13 +79,42 @@ static void ipi_stop(void)
 		wait_for_interrupt();
 }
 
+static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op)
+{
+	struct cpumask hartid_mask;
+	int cpu;
+
+	smp_mb__before_atomic();
+	for_each_cpu(cpu, mask)
+		set_bit(op, &ipi_data[cpu].bits);
+	smp_mb__after_atomic();
+
+	riscv_cpuid_to_hartid_mask(mask, &hartid_mask);
+	sbi_send_ipi(cpumask_bits(&hartid_mask));
+}
+
+static void send_ipi_single(int cpu, enum ipi_message_type op)
+{
+	int hartid = cpuid_to_hartid_map(cpu);
+
+	smp_mb__before_atomic();
+	set_bit(op, &ipi_data[cpu].bits);
+	smp_mb__after_atomic();
+
+	sbi_send_ipi(cpumask_bits(cpumask_of(hartid)));
+}
+
+static inline void clear_ipi(void)
+{
+	csr_clear(CSR_SIP, SIE_SSIE);
+}
+
 void riscv_software_interrupt(void)
 {
 	unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
 	unsigned long *stats = ipi_data[smp_processor_id()].stats;
 
-	/* Clear pending IPI */
-	csr_clear(CSR_SIP, SIE_SSIE);
+	clear_ipi();
 
 	while (true) {
 		unsigned long ops;
@@ -118,23 +148,6 @@ void riscv_software_interrupt(void)
 	}
 }
 
-static void
-send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
-{
-	int cpuid, hartid;
-	struct cpumask hartid_mask;
-
-	cpumask_clear(&hartid_mask);
-	mb();
-	for_each_cpu(cpuid, to_whom) {
-		set_bit(operation, &ipi_data[cpuid].bits);
-		hartid = cpuid_to_hartid_map(cpuid);
-		cpumask_set_cpu(hartid, &hartid_mask);
-	}
-	mb();
-	sbi_send_ipi(cpumask_bits(&hartid_mask));
-}
-
 static const char * const ipi_names[] = {
 	[IPI_RESCHEDULE]	= "Rescheduling interrupts",
 	[IPI_CALL_FUNC]		= "Function call interrupts",
@@ -156,12 +169,12 @@ void show_ipi_stats(struct seq_file *p, int prec)
 
 void arch_send_call_function_ipi_mask(struct cpumask *mask)
 {
-	send_ipi_message(mask, IPI_CALL_FUNC);
+	send_ipi_mask(mask, IPI_CALL_FUNC);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
+	send_ipi_single(cpu, IPI_CALL_FUNC);
 }
 
 void smp_send_stop(void)
@@ -176,7 +189,7 @@ void smp_send_stop(void)
 
 		if (system_state <= SYSTEM_RUNNING)
 			pr_crit("SMP: stopping secondary CPUs\n");
-		send_ipi_message(&mask, IPI_CPU_STOP);
+		send_ipi_mask(&mask, IPI_CPU_STOP);
 	}
 
 	/* Wait up to one second for other CPUs to stop */
@@ -191,6 +204,5 @@ void smp_send_stop(void)
 
 void smp_send_reschedule(int cpu)
 {
-	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
+	send_ipi_single(cpu, IPI_RESCHEDULE);
 }
-

arch/riscv/kernel/stacktrace.c

@@ -19,8 +19,8 @@ struct stackframe {
 	unsigned long ra;
 };
 
-static void notrace walk_stackframe(struct task_struct *task,
-	struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
+void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
+			     bool (*fn)(unsigned long, void *), void *arg)
 {
 	unsigned long fp, sp, pc;
 

arch/riscv/lib/uaccess.S

@@ -18,7 +18,7 @@ ENTRY(__asm_copy_from_user)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
-	csrs sstatus, t6
+	csrs CSR_SSTATUS, t6
 
 	add a3, a1, a2
 	/* Use word-oriented copy only if low-order bits match */
@@ -47,7 +47,7 @@ ENTRY(__asm_copy_from_user)
 
 3:
 	/* Disable access to user memory */
-	csrc sstatus, t6
+	csrc CSR_SSTATUS, t6
 	li a0, 0
 	ret
 4: /* Edge case: unalignment */
@@ -72,7 +72,7 @@ ENTRY(__clear_user)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
-	csrs sstatus, t6
+	csrs CSR_SSTATUS, t6
 
 	add a3, a0, a1
 	addi t0, a0, SZREG-1
@@ -94,7 +94,7 @@ ENTRY(__clear_user)
 
 3:
 	/* Disable access to user memory */
-	csrc sstatus, t6
+	csrc CSR_SSTATUS, t6
 	li a0, 0
 	ret
 4: /* Edge case: unalignment */
@@ -114,11 +114,11 @@ ENDPROC(__clear_user)
 	/* Fixup code for __copy_user(10) and __clear_user(11) */
 10:
 	/* Disable access to user memory */
-	csrs sstatus, t6
+	csrs CSR_SSTATUS, t6
 	mv a0, a2
 	ret
 11:
-	csrs sstatus, t6
+	csrs CSR_SSTATUS, t6
 	mv a0, a1
 	ret
 	.previous

arch/riscv/mm/Makefile

@@ -13,4 +13,7 @@ obj-y += cacheflush.o
 obj-y += context.o
 obj-y += sifive_l2_cache.o
 
+ifeq ($(CONFIG_MMU),y)
+obj-$(CONFIG_SMP) += tlbflush.o
+endif
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o

arch/riscv/mm/cacheflush.c

@@ -47,7 +47,6 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 	cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
 	local |= cpumask_empty(&others);
 	if (mm != current->active_mm || !local) {
-		cpumask_clear(&hmask);
 		riscv_cpuid_to_hartid_mask(&others, &hmask);
 		sbi_remote_fence_i(hmask.bits);
 	} else {

arch/riscv/mm/context.c

@@ -57,12 +57,7 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	cpumask_clear_cpu(cpu, mm_cpumask(prev));
 	cpumask_set_cpu(cpu, mm_cpumask(next));
 
-	/*
-	 * Use the old spbtr name instead of using the current satp
-	 * name to support binutils 2.29 which doesn't know about the
-	 * privileged ISA 1.10 yet.
-	 */
-	csr_write(sptbr, virt_to_pfn(next->pgd) | SATP_MODE);
+	csr_write(CSR_SATP, virt_to_pfn(next->pgd) | SATP_MODE);
 	local_flush_tlb_all();
 
 	flush_icache_deferred(next);

arch/riscv/mm/init.c

@@ -435,13 +435,23 @@ static void __init setup_vm_final(void)
 	clear_fixmap(FIX_PMD);
 
 	/* Move to swapper page table */
-	csr_write(sptbr, PFN_DOWN(__pa(swapper_pg_dir)) | SATP_MODE);
+	csr_write(CSR_SATP, PFN_DOWN(__pa(swapper_pg_dir)) | SATP_MODE);
 	local_flush_tlb_all();
 }
 
 void __init paging_init(void)
 {
 	setup_vm_final();
+	memblocks_present();
+	sparse_init();
 	setup_zero_page();
 	zone_sizes_init();
 }
+
+#ifdef CONFIG_SPARSEMEM
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
+			       struct vmem_altmap *altmap)
+{
+	return vmemmap_populate_basepages(start, end, node);
+}
+#endif

arch/riscv/mm/tlbflush.c

@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <asm/sbi.h>
+
+void flush_tlb_all(void)
+{
+	sbi_remote_sfence_vma(NULL, 0, -1);
+}
+
+static void __sbi_tlb_flush_range(struct cpumask *cmask, unsigned long start,
+				  unsigned long size)
+{
+	struct cpumask hmask;
+
+	riscv_cpuid_to_hartid_mask(cmask, &hmask);
+	sbi_remote_sfence_vma(hmask.bits, start, size);
+}
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	__sbi_tlb_flush_range(mm_cpumask(mm), 0, -1);
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
+{
+	__sbi_tlb_flush_range(mm_cpumask(vma->vm_mm), addr, PAGE_SIZE);
+}
+
+void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end)
+{
+	__sbi_tlb_flush_range(mm_cpumask(vma->vm_mm), start, end - start);
+}

drivers/clocksource/timer-riscv.c

@@ -2,6 +2,10 @@
 /*
  * Copyright (C) 2012 Regents of the University of California
  * Copyright (C) 2017 SiFive
+ *
+ * All RISC-V systems have a timer attached to every hart.  These timers can be
+ * read from the "time" and "timeh" CSRs, and can use the SBI to setup
+ * events.
  */
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
@@ -12,19 +16,6 @@
 #include <asm/smp.h>
 #include <asm/sbi.h>
 
-/*
- * All RISC-V systems have a timer attached to every hart.  These timers can be
- * read by the 'rdcycle' pseudo instruction, and can use the SBI to setup
- * events.  In order to abstract the architecture-specific timer reading and
- * setting functions away from the clock event insertion code, we provide
- * function pointers to the clockevent subsystem that perform two basic
- * operations: rdtime() reads the timer on the current CPU, and
- * next_event(delta) sets the next timer event to 'delta' cycles in the future.
- * As the timers are inherently a per-cpu resource, these callbacks perform
- * operations on the current hart.  There is guaranteed to be exactly one timer
- * per hart on all RISC-V systems.
- */
-
 static int riscv_clock_next_event(unsigned long delta,
 		struct clock_event_device *ce)
 {

drivers/irqchip/irq-sifive-plic.c

@@ -244,6 +244,7 @@ static int __init plic_init(struct device_node *node,
 		struct plic_handler *handler;
 		irq_hw_number_t hwirq;
 		int cpu, hartid;
+		u32 threshold = 0;
 
 		if (of_irq_parse_one(node, i, &parent)) {
 			pr_err("failed to parse parent for context %d.\n", i);
@@ -266,10 +267,16 @@ static int __init plic_init(struct device_node *node,
 			continue;
 		}
 
+		/*
+		 * 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
+		 * little fragile.
+		 */
 		handler = per_cpu_ptr(&plic_handlers, cpu);
 		if (handler->present) {
 			pr_warn("handler already present for context %d.\n", i);
-			continue;
+			threshold = 0xffffffff;
+			goto done;
 		}
 
 		handler->present = true;
@@ -279,8 +286,9 @@ static int __init plic_init(struct device_node *node,
 		handler->enable_base =
 			plic_regs + ENABLE_BASE + i * ENABLE_PER_HART;
 
+done:
 		/* priority must be > threshold to trigger an interrupt */
-		writel(0, handler->hart_base + CONTEXT_THRESHOLD);
+		writel(threshold, handler->hart_base + CONTEXT_THRESHOLD);
 		for (hwirq = 1; hwirq <= nr_irqs; hwirq++)
 			plic_toggle(handler, hwirq, 0);
 		nr_handlers++;

tools/arch/riscv/include/uapi/asm/perf_regs.h

@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#ifndef _ASM_RISCV_PERF_REGS_H
+#define _ASM_RISCV_PERF_REGS_H
+
+enum perf_event_riscv_regs {
+	PERF_REG_RISCV_PC,
+	PERF_REG_RISCV_RA,
+	PERF_REG_RISCV_SP,
+	PERF_REG_RISCV_GP,
+	PERF_REG_RISCV_TP,
+	PERF_REG_RISCV_T0,
+	PERF_REG_RISCV_T1,
+	PERF_REG_RISCV_T2,
+	PERF_REG_RISCV_S0,
+	PERF_REG_RISCV_S1,
+	PERF_REG_RISCV_A0,
+	PERF_REG_RISCV_A1,
+	PERF_REG_RISCV_A2,
+	PERF_REG_RISCV_A3,
+	PERF_REG_RISCV_A4,
+	PERF_REG_RISCV_A5,
+	PERF_REG_RISCV_A6,
+	PERF_REG_RISCV_A7,
+	PERF_REG_RISCV_S2,
+	PERF_REG_RISCV_S3,
+	PERF_REG_RISCV_S4,
+	PERF_REG_RISCV_S5,
+	PERF_REG_RISCV_S6,
+	PERF_REG_RISCV_S7,
+	PERF_REG_RISCV_S8,
+	PERF_REG_RISCV_S9,
+	PERF_REG_RISCV_S10,
+	PERF_REG_RISCV_S11,
+	PERF_REG_RISCV_T3,
+	PERF_REG_RISCV_T4,
+	PERF_REG_RISCV_T5,
+	PERF_REG_RISCV_T6,
+	PERF_REG_RISCV_MAX,
+};
+#endif /* _ASM_RISCV_PERF_REGS_H */

tools/perf/Makefile.config

@@ -60,6 +60,10 @@ ifeq ($(SRCARCH),arm64)
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
+ifeq ($(SRCARCH),riscv)
+  NO_PERF_REGS := 0
+endif
+
 ifeq ($(SRCARCH),csky)
   NO_PERF_REGS := 0
 endif
@@ -82,7 +86,7 @@ endif
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
 # to the check.
-ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky riscv))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 

tools/perf/arch/riscv/Build

@@ -0,0 +1 @@
+perf-y += util/

tools/perf/arch/riscv/Makefile

@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+endif
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1

tools/perf/arch/riscv/include/perf_regs.h

@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+#define PERF_REGS_MASK	((1ULL << PERF_REG_RISCV_MAX) - 1)
+#define PERF_REGS_MAX	PERF_REG_RISCV_MAX
+#if __riscv_xlen == 64
+#define PERF_SAMPLE_REGS_ABI    PERF_SAMPLE_REGS_ABI_64
+#else
+#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32
+#endif
+
+#define PERF_REG_IP	PERF_REG_RISCV_PC
+#define PERF_REG_SP	PERF_REG_RISCV_SP
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_RISCV_PC:
+		return "pc";
+	case PERF_REG_RISCV_RA:
+		return "ra";
+	case PERF_REG_RISCV_SP:
+		return "sp";
+	case PERF_REG_RISCV_GP:
+		return "gp";
+	case PERF_REG_RISCV_TP:
+		return "tp";
+	case PERF_REG_RISCV_T0:
+		return "t0";
+	case PERF_REG_RISCV_T1:
+		return "t1";
+	case PERF_REG_RISCV_T2:
+		return "t2";
+	case PERF_REG_RISCV_S0:
+		return "s0";
+	case PERF_REG_RISCV_S1:
+		return "s1";
+	case PERF_REG_RISCV_A0:
+		return "a0";
+	case PERF_REG_RISCV_A1:
+		return "a1";
+	case PERF_REG_RISCV_A2:
+		return "a2";
+	case PERF_REG_RISCV_A3:
+		return "a3";
+	case PERF_REG_RISCV_A4:
+		return "a4";
+	case PERF_REG_RISCV_A5:
+		return "a5";
+	case PERF_REG_RISCV_A6:
+		return "a6";
+	case PERF_REG_RISCV_A7:
+		return "a7";
+	case PERF_REG_RISCV_S2:
+		return "s2";
+	case PERF_REG_RISCV_S3:
+		return "s3";
+	case PERF_REG_RISCV_S4:
+		return "s4";
+	case PERF_REG_RISCV_S5:
+		return "s5";
+	case PERF_REG_RISCV_S6:
+		return "s6";
+	case PERF_REG_RISCV_S7:
+		return "s7";
+	case PERF_REG_RISCV_S8:
+		return "s8";
+	case PERF_REG_RISCV_S9:
+		return "s9";
+	case PERF_REG_RISCV_S10:
+		return "s10";
+	case PERF_REG_RISCV_S11:
+		return "s11";
+	case PERF_REG_RISCV_T3:
+		return "t3";
+	case PERF_REG_RISCV_T4:
+		return "t4";
+	case PERF_REG_RISCV_T5:
+		return "t5";
+	case PERF_REG_RISCV_T6:
+		return "t6";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */

tools/perf/arch/riscv/util/Build

@@ -0,0 +1,2 @@
+perf-$(CONFIG_DWARF) += dwarf-regs.o
+perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o

tools/perf/arch/riscv/util/dwarf-regs.c

@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
+ * Mapping of DWARF debug register numbers into register names.
+ */
+
+#include <stddef.h>
+#include <errno.h> /* for EINVAL */
+#include <string.h> /* for strcmp */
+#include <dwarf-regs.h>
+
+struct pt_regs_dwarfnum {
+	const char *name;
+	unsigned int dwarfnum;
+};
+
+#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+
+struct pt_regs_dwarfnum riscv_dwarf_regs_table[] = {
+	REG_DWARFNUM_NAME("%zero", 0),
+	REG_DWARFNUM_NAME("%ra", 1),
+	REG_DWARFNUM_NAME("%sp", 2),
+	REG_DWARFNUM_NAME("%gp", 3),
+	REG_DWARFNUM_NAME("%tp", 4),
+	REG_DWARFNUM_NAME("%t0", 5),
+	REG_DWARFNUM_NAME("%t1", 6),
+	REG_DWARFNUM_NAME("%t2", 7),
+	REG_DWARFNUM_NAME("%s0", 8),
+	REG_DWARFNUM_NAME("%s1", 9),
+	REG_DWARFNUM_NAME("%a0", 10),
+	REG_DWARFNUM_NAME("%a1", 11),
+	REG_DWARFNUM_NAME("%a2", 12),
+	REG_DWARFNUM_NAME("%a3", 13),
+	REG_DWARFNUM_NAME("%a4", 14),
+	REG_DWARFNUM_NAME("%a5", 15),
+	REG_DWARFNUM_NAME("%a6", 16),
+	REG_DWARFNUM_NAME("%a7", 17),
+	REG_DWARFNUM_NAME("%s2", 18),
+	REG_DWARFNUM_NAME("%s3", 19),
+	REG_DWARFNUM_NAME("%s4", 20),
+	REG_DWARFNUM_NAME("%s5", 21),
+	REG_DWARFNUM_NAME("%s6", 22),
+	REG_DWARFNUM_NAME("%s7", 23),
+	REG_DWARFNUM_NAME("%s8", 24),
+	REG_DWARFNUM_NAME("%s9", 25),
+	REG_DWARFNUM_NAME("%s10", 26),
+	REG_DWARFNUM_NAME("%s11", 27),
+	REG_DWARFNUM_NAME("%t3", 28),
+	REG_DWARFNUM_NAME("%t4", 29),
+	REG_DWARFNUM_NAME("%t5", 30),
+	REG_DWARFNUM_NAME("%t6", 31),
+	REG_DWARFNUM_END,
+};
+
+#define RISCV_MAX_REGS ((sizeof(riscv_dwarf_regs_table) / \
+		 sizeof(riscv_dwarf_regs_table[0])) - 1)
+
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n < RISCV_MAX_REGS) ? riscv_dwarf_regs_table[n].name : NULL;
+}
+
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_dwarfnum *roff;
+
+	for (roff = riscv_dwarf_regs_table; roff->name; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->dwarfnum;
+	return -EINVAL;
+}

tools/perf/arch/riscv/util/unwind-libdw.c

@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+#include "../../util/event.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[32];
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_RISCV_##r);	\
+	val;							\
+})
+
+	dwarf_regs[0]  = 0;
+	dwarf_regs[1]  = REG(RA);
+	dwarf_regs[2]  = REG(SP);
+	dwarf_regs[3]  = REG(GP);
+	dwarf_regs[4]  = REG(TP);
+	dwarf_regs[5]  = REG(T0);
+	dwarf_regs[6]  = REG(T1);
+	dwarf_regs[7]  = REG(T2);
+	dwarf_regs[8]  = REG(S0);
+	dwarf_regs[9]  = REG(S1);
+	dwarf_regs[10] = REG(A0);
+	dwarf_regs[11] = REG(A1);
+	dwarf_regs[12] = REG(A2);
+	dwarf_regs[13] = REG(A3);
+	dwarf_regs[14] = REG(A4);
+	dwarf_regs[15] = REG(A5);
+	dwarf_regs[16] = REG(A6);
+	dwarf_regs[17] = REG(A7);
+	dwarf_regs[18] = REG(S2);
+	dwarf_regs[19] = REG(S3);
+	dwarf_regs[20] = REG(S4);
+	dwarf_regs[21] = REG(S5);
+	dwarf_regs[22] = REG(S6);
+	dwarf_regs[23] = REG(S7);
+	dwarf_regs[24] = REG(S8);
+	dwarf_regs[25] = REG(S9);
+	dwarf_regs[26] = REG(S10);
+	dwarf_regs[27] = REG(S11);
+	dwarf_regs[28] = REG(T3);
+	dwarf_regs[29] = REG(T4);
+	dwarf_regs[30] = REG(T5);
+	dwarf_regs[31] = REG(T6);
+	dwfl_thread_state_register_pc(thread, REG(PC));
+
+	return dwfl_thread_state_registers(thread, 0, PERF_REG_RISCV_MAX,
+					   dwarf_regs);
+}