Merge tag 'riscv-for-linus-4.20-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux

Pull RISC-V updates from Palmer Dabbelt:
 "This patch set contains a lot (at least, for me) of improvements to
  the RISC-V kernel port:

   - The removal of some cacheinfo values that were bogus.

   - On systems with F but without D the kernel will not show the F
     extension to userspace, as it isn't actually supported.

   - Support for futexes.

   - Removal of some unused code.

   - Cleanup of some menuconfig entries.

   - Support for systems without a floating-point unit, and for building
     kernels that will never use the floating-point unit.

   - More fixes to the RV32I port, which regressed again. It's really
     time to get this into a regression test somewhere so I stop
     breaking it. Thanks to Zong for resurrecting it again!

   - Various fixes that resulted from a year old review of our original
     patch set that I finally got around to.

   - Various improvements to SMP support, largely based around having
     switched to logical hart numbering, as well as some interrupt
     improvements. This one is in the same patch set as above, thanks to
     Atish for sheparding everything though as my patch set was a bit of
     a mess.

  I'm pretty sure this is our largest patch set since the original
  kernel contribution, and it's certainly the one with the most
  contributors. While I don't have anything else I know I'm going to
  submit for the merge window, I would be somewhat surprised if I didn't
  screw anything up.

  Thanks for the help, everyone!"

* tag 'riscv-for-linus-4.20-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux: (31 commits)
  RISC-V: Cosmetic menuconfig changes
  riscv: move GCC version check for ARCH_SUPPORTS_INT128 to Kconfig
  RISC-V: remove the unused return_to_handler export
  RISC-V: Add futex support.
  RISC-V: Add FP register ptrace support for gdb.
  RISC-V: Mask out the F extension on systems without D
  RISC-V: Don't set cacheinfo.{physical_line_partition,attributes}
  RISC-V: Show IPI stats
  RISC-V: Show CPU ID and Hart ID separately in /proc/cpuinfo
  RISC-V: Use Linux logical CPU number instead of hartid
  RISC-V: Add logical CPU indexing for RISC-V
  RISC-V: Use WRITE_ONCE instead of direct access
  RISC-V: Use mmgrab()
  RISC-V: Rename im_okay_therefore_i_am to found_boot_cpu
  RISC-V: Rename riscv_of_processor_hart to riscv_of_processor_hartid
  RISC-V: Provide a cleaner raw_smp_processor_id()
  RISC-V: Disable preemption before enabling interrupts
  RISC-V: Comment on the TLB flush in smp_callin()
  RISC-V: Filter ISA and MMU values in cpuinfo
  RISC-V: Don't set cacheinfo.{physical_line_partition,attributes}
  ...

15 files changed, 425 insertions, 170 deletions

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index e1274fc03af4..f13f7f276639 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -31,6 +31,7 @@ obj-y	+= vdso/
 
 CFLAGS_setup.o := -mcmodel=medany
 
+obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_MODULES)		+= module.o
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index 0bc86e5f8f3f..cb35ffd8ec6b 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -22,13 +22,6 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,
 {
 	this_leaf->level = level;
 	this_leaf->type = type;
-	/* not a sector cache */
-	this_leaf->physical_line_partition = 1;
-	/* TODO: Add to DTS */
-	this_leaf->attributes =
-		CACHE_WRITE_BACK
-		| CACHE_READ_ALLOCATE
-		| CACHE_WRITE_ALLOCATE;
 }
 
 static int __init_cache_level(unsigned int cpu)
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index ca6c81e54e37..3a5a2ee31547 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -14,9 +14,13 @@
 #include <linux/init.h>
 #include <linux/seq_file.h>
 #include <linux/of.h>
+#include <asm/smp.h>
 
-/* Return -1 if not a valid hart */
-int riscv_of_processor_hart(struct device_node *node)
+/*
+ * Returns the hart ID of the given device tree node, or -1 if the device tree
+ * node isn't a RISC-V hart.
+ */
+int riscv_of_processor_hartid(struct device_node *node)
 {
 	const char *isa, *status;
 	u32 hart;
@@ -58,6 +62,64 @@ int riscv_of_processor_hart(struct device_node *node)
 
 #ifdef CONFIG_PROC_FS
 
+static void print_isa(struct seq_file *f, const char *orig_isa)
+{
+	static const char *ext = "mafdc";
+	const char *isa = orig_isa;
+	const char *e;
+
+	/*
+	 * Linux doesn't support rv32e or rv128i, and we only support booting
+	 * kernels on harts with the same ISA that the kernel is compiled for.
+	 */
+#if defined(CONFIG_32BIT)
+	if (strncmp(isa, "rv32i", 5) != 0)
+		return;
+#elif defined(CONFIG_64BIT)
+	if (strncmp(isa, "rv64i", 5) != 0)
+		return;
+#endif
+
+	/* Print the base ISA, as we already know it's legal. */
+	seq_puts(f, "isa\t\t: ");
+	seq_write(f, isa, 5);
+	isa += 5;
+
+	/*
+	 * Check the rest of the ISA string for valid extensions, printing those
+	 * we find.  RISC-V ISA strings define an order, so we only print the
+	 * extension bits when they're in order.
+	 */
+	for (e = ext; *e != '\0'; ++e) {
+		if (isa[0] == e[0]) {
+			seq_write(f, isa, 1);
+			isa++;
+		}
+	}
+	seq_puts(f, "\n");
+
+	/*
+	 * If we were given an unsupported ISA in the device tree then print
+	 * a bit of info describing what went wrong.
+	 */
+	if (isa[0] != '\0')
+		pr_info("unsupported ISA \"%s\" in device tree", orig_isa);
+}
+
+static void print_mmu(struct seq_file *f, const char *mmu_type)
+{
+#if defined(CONFIG_32BIT)
+	if (strcmp(mmu_type, "riscv,sv32") != 0)
+		return;
+#elif defined(CONFIG_64BIT)
+	if (strcmp(mmu_type, "riscv,sv39") != 0 &&
+	    strcmp(mmu_type, "riscv,sv48") != 0)
+		return;
+#endif
+
+	seq_printf(f, "mmu\t\t: %s\n", mmu_type+6);
+}
+
 static void *c_start(struct seq_file *m, loff_t *pos)
 {
 	*pos = cpumask_next(*pos - 1, cpu_online_mask);
@@ -78,21 +140,20 @@ static void c_stop(struct seq_file *m, void *v)
 
 static int c_show(struct seq_file *m, void *v)
 {
-	unsigned long hart_id = (unsigned long)v - 1;
-	struct device_node *node = of_get_cpu_node(hart_id, NULL);
+	unsigned long cpu_id = (unsigned long)v - 1;
+	struct device_node *node = of_get_cpu_node(cpuid_to_hartid_map(cpu_id),
+						   NULL);
 	const char *compat, *isa, *mmu;
 
-	seq_printf(m, "hart\t: %lu\n", hart_id);
-	if (!of_property_read_string(node, "riscv,isa", &isa)
-	    && isa[0] == 'r'
-	    && isa[1] == 'v')
-		seq_printf(m, "isa\t: %s\n", isa);
-	if (!of_property_read_string(node, "mmu-type", &mmu)
-	    && !strncmp(mmu, "riscv,", 6))
-		seq_printf(m, "mmu\t: %s\n", mmu+6);
+	seq_printf(m, "processor\t: %lu\n", cpu_id);
+	seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id));
+	if (!of_property_read_string(node, "riscv,isa", &isa))
+		print_isa(m, isa);
+	if (!of_property_read_string(node, "mmu-type", &mmu))
+		print_mmu(m, mmu);
 	if (!of_property_read_string(node, "compatible", &compat)
 	    && strcmp(compat, "riscv"))
-		seq_printf(m, "uarch\t: %s\n", compat);
+		seq_printf(m, "uarch\t\t: %s\n", compat);
 	seq_puts(m, "\n");
 
 	return 0;
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 17011a870044..5493f3228704 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -22,6 +22,9 @@
 #include <asm/hwcap.h>
 
 unsigned long elf_hwcap __read_mostly;
+#ifdef CONFIG_FPU
+bool has_fpu __read_mostly;
+#endif
 
 void riscv_fill_hwcap(void)
 {
@@ -57,5 +60,17 @@ void riscv_fill_hwcap(void)
 	for (i = 0; i < strlen(isa); ++i)
 		elf_hwcap |= isa2hwcap[(unsigned char)(isa[i])];
 
+	/* We don't support systems with F but without D, so mask those out
+	 * here. */
+	if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) {
+		pr_info("This kernel does not support systems with F but not D");
+		elf_hwcap &= ~COMPAT_HWCAP_ISA_F;
+	}
+
 	pr_info("elf_hwcap is 0x%lx", elf_hwcap);
+
+#ifdef CONFIG_FPU
+	if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D))
+		has_fpu = true;
+#endif
 }
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index fa2c08e3c05e..13d4826ab2a1 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -168,7 +168,6 @@ ENTRY(handle_exception)
 
 	/* Handle interrupts */
 	move a0, sp /* pt_regs */
-	move a1, s4 /* scause */
 	tail do_IRQ
 1:
 	/* Exceptions run with interrupts enabled */
@@ -357,93 +356,6 @@ ENTRY(__switch_to)
 	ret
 ENDPROC(__switch_to)
 
-ENTRY(__fstate_save)
-	li  a2,  TASK_THREAD_F0
-	add a0, a0, a2
-	li t1, SR_FS
-	csrs sstatus, t1
-	frcsr t0
-	fsd f0,  TASK_THREAD_F0_F0(a0)
-	fsd f1,  TASK_THREAD_F1_F0(a0)
-	fsd f2,  TASK_THREAD_F2_F0(a0)
-	fsd f3,  TASK_THREAD_F3_F0(a0)
-	fsd f4,  TASK_THREAD_F4_F0(a0)
-	fsd f5,  TASK_THREAD_F5_F0(a0)
-	fsd f6,  TASK_THREAD_F6_F0(a0)
-	fsd f7,  TASK_THREAD_F7_F0(a0)
-	fsd f8,  TASK_THREAD_F8_F0(a0)
-	fsd f9,  TASK_THREAD_F9_F0(a0)
-	fsd f10, TASK_THREAD_F10_F0(a0)
-	fsd f11, TASK_THREAD_F11_F0(a0)
-	fsd f12, TASK_THREAD_F12_F0(a0)
-	fsd f13, TASK_THREAD_F13_F0(a0)
-	fsd f14, TASK_THREAD_F14_F0(a0)
-	fsd f15, TASK_THREAD_F15_F0(a0)
-	fsd f16, TASK_THREAD_F16_F0(a0)
-	fsd f17, TASK_THREAD_F17_F0(a0)
-	fsd f18, TASK_THREAD_F18_F0(a0)
-	fsd f19, TASK_THREAD_F19_F0(a0)
-	fsd f20, TASK_THREAD_F20_F0(a0)
-	fsd f21, TASK_THREAD_F21_F0(a0)
-	fsd f22, TASK_THREAD_F22_F0(a0)
-	fsd f23, TASK_THREAD_F23_F0(a0)
-	fsd f24, TASK_THREAD_F24_F0(a0)
-	fsd f25, TASK_THREAD_F25_F0(a0)
-	fsd f26, TASK_THREAD_F26_F0(a0)
-	fsd f27, TASK_THREAD_F27_F0(a0)
-	fsd f28, TASK_THREAD_F28_F0(a0)
-	fsd f29, TASK_THREAD_F29_F0(a0)
-	fsd f30, TASK_THREAD_F30_F0(a0)
-	fsd f31, TASK_THREAD_F31_F0(a0)
-	sw t0, TASK_THREAD_FCSR_F0(a0)
-	csrc sstatus, t1
-	ret
-ENDPROC(__fstate_save)
-
-ENTRY(__fstate_restore)
-	li  a2,  TASK_THREAD_F0
-	add a0, a0, a2
-	li t1, SR_FS
-	lw t0, TASK_THREAD_FCSR_F0(a0)
-	csrs sstatus, t1
-	fld f0,  TASK_THREAD_F0_F0(a0)
-	fld f1,  TASK_THREAD_F1_F0(a0)
-	fld f2,  TASK_THREAD_F2_F0(a0)
-	fld f3,  TASK_THREAD_F3_F0(a0)
-	fld f4,  TASK_THREAD_F4_F0(a0)
-	fld f5,  TASK_THREAD_F5_F0(a0)
-	fld f6,  TASK_THREAD_F6_F0(a0)
-	fld f7,  TASK_THREAD_F7_F0(a0)
-	fld f8,  TASK_THREAD_F8_F0(a0)
-	fld f9,  TASK_THREAD_F9_F0(a0)
-	fld f10, TASK_THREAD_F10_F0(a0)
-	fld f11, TASK_THREAD_F11_F0(a0)
-	fld f12, TASK_THREAD_F12_F0(a0)
-	fld f13, TASK_THREAD_F13_F0(a0)
-	fld f14, TASK_THREAD_F14_F0(a0)
-	fld f15, TASK_THREAD_F15_F0(a0)
-	fld f16, TASK_THREAD_F16_F0(a0)
-	fld f17, TASK_THREAD_F17_F0(a0)
-	fld f18, TASK_THREAD_F18_F0(a0)
-	fld f19, TASK_THREAD_F19_F0(a0)
-	fld f20, TASK_THREAD_F20_F0(a0)
-	fld f21, TASK_THREAD_F21_F0(a0)
-	fld f22, TASK_THREAD_F22_F0(a0)
-	fld f23, TASK_THREAD_F23_F0(a0)
-	fld f24, TASK_THREAD_F24_F0(a0)
-	fld f25, TASK_THREAD_F25_F0(a0)
-	fld f26, TASK_THREAD_F26_F0(a0)
-	fld f27, TASK_THREAD_F27_F0(a0)
-	fld f28, TASK_THREAD_F28_F0(a0)
-	fld f29, TASK_THREAD_F29_F0(a0)
-	fld f30, TASK_THREAD_F30_F0(a0)
-	fld f31, TASK_THREAD_F31_F0(a0)
-	fscsr t0
-	csrc sstatus, t1
-	ret
-ENDPROC(__fstate_restore)
-
-
 	.section ".rodata"
 	/* Exception vector table */
 ENTRY(excp_vect_table)
diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S
new file mode 100644
index 000000000000..1defb0618aff
--- /dev/null
+++ b/arch/riscv/kernel/fpu.S
@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/asm-offsets.h>
+
+ENTRY(__fstate_save)
+	li  a2,  TASK_THREAD_F0
+	add a0, a0, a2
+	li t1, SR_FS
+	csrs sstatus, t1
+	frcsr t0
+	fsd f0,  TASK_THREAD_F0_F0(a0)
+	fsd f1,  TASK_THREAD_F1_F0(a0)
+	fsd f2,  TASK_THREAD_F2_F0(a0)
+	fsd f3,  TASK_THREAD_F3_F0(a0)
+	fsd f4,  TASK_THREAD_F4_F0(a0)
+	fsd f5,  TASK_THREAD_F5_F0(a0)
+	fsd f6,  TASK_THREAD_F6_F0(a0)
+	fsd f7,  TASK_THREAD_F7_F0(a0)
+	fsd f8,  TASK_THREAD_F8_F0(a0)
+	fsd f9,  TASK_THREAD_F9_F0(a0)
+	fsd f10, TASK_THREAD_F10_F0(a0)
+	fsd f11, TASK_THREAD_F11_F0(a0)
+	fsd f12, TASK_THREAD_F12_F0(a0)
+	fsd f13, TASK_THREAD_F13_F0(a0)
+	fsd f14, TASK_THREAD_F14_F0(a0)
+	fsd f15, TASK_THREAD_F15_F0(a0)
+	fsd f16, TASK_THREAD_F16_F0(a0)
+	fsd f17, TASK_THREAD_F17_F0(a0)
+	fsd f18, TASK_THREAD_F18_F0(a0)
+	fsd f19, TASK_THREAD_F19_F0(a0)
+	fsd f20, TASK_THREAD_F20_F0(a0)
+	fsd f21, TASK_THREAD_F21_F0(a0)
+	fsd f22, TASK_THREAD_F22_F0(a0)
+	fsd f23, TASK_THREAD_F23_F0(a0)
+	fsd f24, TASK_THREAD_F24_F0(a0)
+	fsd f25, TASK_THREAD_F25_F0(a0)
+	fsd f26, TASK_THREAD_F26_F0(a0)
+	fsd f27, TASK_THREAD_F27_F0(a0)
+	fsd f28, TASK_THREAD_F28_F0(a0)
+	fsd f29, TASK_THREAD_F29_F0(a0)
+	fsd f30, TASK_THREAD_F30_F0(a0)
+	fsd f31, TASK_THREAD_F31_F0(a0)
+	sw t0, TASK_THREAD_FCSR_F0(a0)
+	csrc sstatus, t1
+	ret
+ENDPROC(__fstate_save)
+
+ENTRY(__fstate_restore)
+	li  a2,  TASK_THREAD_F0
+	add a0, a0, a2
+	li t1, SR_FS
+	lw t0, TASK_THREAD_FCSR_F0(a0)
+	csrs sstatus, t1
+	fld f0,  TASK_THREAD_F0_F0(a0)
+	fld f1,  TASK_THREAD_F1_F0(a0)
+	fld f2,  TASK_THREAD_F2_F0(a0)
+	fld f3,  TASK_THREAD_F3_F0(a0)
+	fld f4,  TASK_THREAD_F4_F0(a0)
+	fld f5,  TASK_THREAD_F5_F0(a0)
+	fld f6,  TASK_THREAD_F6_F0(a0)
+	fld f7,  TASK_THREAD_F7_F0(a0)
+	fld f8,  TASK_THREAD_F8_F0(a0)
+	fld f9,  TASK_THREAD_F9_F0(a0)
+	fld f10, TASK_THREAD_F10_F0(a0)
+	fld f11, TASK_THREAD_F11_F0(a0)
+	fld f12, TASK_THREAD_F12_F0(a0)
+	fld f13, TASK_THREAD_F13_F0(a0)
+	fld f14, TASK_THREAD_F14_F0(a0)
+	fld f15, TASK_THREAD_F15_F0(a0)
+	fld f16, TASK_THREAD_F16_F0(a0)
+	fld f17, TASK_THREAD_F17_F0(a0)
+	fld f18, TASK_THREAD_F18_F0(a0)
+	fld f19, TASK_THREAD_F19_F0(a0)
+	fld f20, TASK_THREAD_F20_F0(a0)
+	fld f21, TASK_THREAD_F21_F0(a0)
+	fld f22, TASK_THREAD_F22_F0(a0)
+	fld f23, TASK_THREAD_F23_F0(a0)
+	fld f24, TASK_THREAD_F24_F0(a0)
+	fld f25, TASK_THREAD_F25_F0(a0)
+	fld f26, TASK_THREAD_F26_F0(a0)
+	fld f27, TASK_THREAD_F27_F0(a0)
+	fld f28, TASK_THREAD_F28_F0(a0)
+	fld f29, TASK_THREAD_F29_F0(a0)
+	fld f30, TASK_THREAD_F30_F0(a0)
+	fld f31, TASK_THREAD_F31_F0(a0)
+	fscsr t0
+	csrc sstatus, t1
+	ret
+ENDPROC(__fstate_restore)
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index c4d2c63f9a29..711190d473d4 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -47,6 +47,8 @@ ENTRY(_start)
 	/* Save hart ID and DTB physical address */
 	mv s0, a0
 	mv s1, a1
+	la a2, boot_cpu_hartid
+	REG_S a0, (a2)
 
 	/* Initialize page tables and relocate to virtual addresses */
 	la sp, init_thread_union + THREAD_SIZE
@@ -55,7 +57,7 @@ ENTRY(_start)
 
 	/* Restore C environment */
 	la tp, init_task
-	sw s0, TASK_TI_CPU(tp)
+	sw zero, TASK_TI_CPU(tp)
 
 	la sp, init_thread_union
 	li a0, ASM_THREAD_SIZE
diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c
index 0cfac48a1272..48e6b7db83a1 100644
--- a/arch/riscv/kernel/irq.c
+++ b/arch/riscv/kernel/irq.c
@@ -8,6 +8,8 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
+#include <linux/seq_file.h>
+#include <asm/smp.h>
 
 /*
  * Possible interrupt causes:
@@ -24,12 +26,18 @@
  */
 #define INTERRUPT_CAUSE_FLAG	(1UL << (__riscv_xlen - 1))
 
-asmlinkage void __irq_entry do_IRQ(struct pt_regs *regs, unsigned long cause)
+int arch_show_interrupts(struct seq_file *p, int prec)
+{
+	show_ipi_stats(p, prec);
+	return 0;
+}
+
+asmlinkage void __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	irq_enter();
-	switch (cause & ~INTERRUPT_CAUSE_FLAG) {
+	switch (regs->scause & ~INTERRUPT_CAUSE_FLAG) {
 	case INTERRUPT_CAUSE_TIMER:
 		riscv_timer_interrupt();
 		break;
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index 5721624886a1..8a5593ff9ff3 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -75,7 +75,6 @@ ENTRY(return_to_handler)
 	RESTORE_RET_ABI_STATE
 	jalr	a1
 ENDPROC(return_to_handler)
-EXPORT_SYMBOL(return_to_handler)
 #endif
 
 #ifndef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index d7c6ca7c95ae..bef19993ea92 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -76,7 +76,9 @@ void show_regs(struct pt_regs *regs)
 void start_thread(struct pt_regs *regs, unsigned long pc,
 	unsigned long sp)
 {
-	regs->sstatus = SR_SPIE /* User mode, irqs on */ | SR_FS_INITIAL;
+	regs->sstatus = SR_SPIE;
+	if (has_fpu)
+		regs->sstatus |= SR_FS_INITIAL;
 	regs->sepc = pc;
 	regs->sp = sp;
 	set_fs(USER_DS);
@@ -84,12 +86,14 @@ void start_thread(struct pt_regs *regs, unsigned long pc,
 
 void flush_thread(void)
 {
+#ifdef CONFIG_FPU
 	/*
 	 * Reset FPU context
 	 *	frm: round to nearest, ties to even (IEEE default)
 	 *	fflags: accrued exceptions cleared
 	 */
 	memset(&current->thread.fstate, 0, sizeof(current->thread.fstate));
+#endif
 }
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 9f82a7e34c64..60f1e02eed36 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -28,6 +28,9 @@
 
 enum riscv_regset {
 	REGSET_X,
+#ifdef CONFIG_FPU
+	REGSET_F,
+#endif
 };
 
 static int riscv_gpr_get(struct task_struct *target,
@@ -54,6 +57,45 @@ static int riscv_gpr_set(struct task_struct *target,
 	return ret;
 }
 
+#ifdef CONFIG_FPU
+static int riscv_fpr_get(struct task_struct *target,
+			 const struct user_regset *regset,
+			 unsigned int pos, unsigned int count,
+			 void *kbuf, void __user *ubuf)
+{
+	int ret;
+	struct __riscv_d_ext_state *fstate = &target->thread.fstate;
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, fstate, 0,
+				  offsetof(struct __riscv_d_ext_state, fcsr));
+	if (!ret) {
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, fstate, 0,
+					  offsetof(struct __riscv_d_ext_state, fcsr) +
+					  sizeof(fstate->fcsr));
+	}
+
+	return ret;
+}
+
+static int riscv_fpr_set(struct task_struct *target,
+			 const struct user_regset *regset,
+			 unsigned int pos, unsigned int count,
+			 const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	struct __riscv_d_ext_state *fstate = &target->thread.fstate;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, fstate, 0,
+				 offsetof(struct __riscv_d_ext_state, fcsr));
+	if (!ret) {
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, fstate, 0,
+					 offsetof(struct __riscv_d_ext_state, fcsr) +
+					 sizeof(fstate->fcsr));
+	}
+
+	return ret;
+}
+#endif
 
 static const struct user_regset riscv_user_regset[] = {
 	[REGSET_X] = {
@@ -64,6 +106,16 @@ static const struct user_regset riscv_user_regset[] = {
 		.get = &riscv_gpr_get,
 		.set = &riscv_gpr_set,
 	},
+#ifdef CONFIG_FPU
+	[REGSET_F] = {
+		.core_note_type = NT_PRFPREG,
+		.n = ELF_NFPREG,
+		.size = sizeof(elf_fpreg_t),
+		.align = sizeof(elf_fpreg_t),
+		.get = &riscv_fpr_get,
+		.set = &riscv_fpr_set,
+	},
+#endif
 };
 
 static const struct user_regset_view riscv_user_native_view = {
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index b2d26d9d8489..2c290e6aaa6e 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -81,6 +81,16 @@ EXPORT_SYMBOL(empty_zero_page);
 
 /* The lucky hart to first increment this variable will boot the other cores */
 atomic_t hart_lottery;
+unsigned long boot_cpu_hartid;
+
+unsigned long __cpuid_to_hartid_map[NR_CPUS] = {
+	[0 ... NR_CPUS-1] = INVALID_HARTID
+};
+
+void __init smp_setup_processor_id(void)
+{
+	cpuid_to_hartid_map(0) = boot_cpu_hartid;
+}
 
 #ifdef CONFIG_BLK_DEV_INITRD
 static void __init setup_initrd(void)
@@ -227,7 +237,10 @@ void __init setup_arch(char **cmdline_p)
 	setup_bootmem();
 	paging_init();
 	unflatten_device_tree();
+
+#ifdef CONFIG_SWIOTLB
 	swiotlb_init(1);
+#endif
 
 #ifdef CONFIG_SMP
 	setup_smp();
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 718d0c984ef0..f9b5e7e352ef 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -37,45 +37,69 @@ struct rt_sigframe {
 	struct ucontext uc;
 };
 
-static long restore_d_state(struct pt_regs *regs,
-	struct __riscv_d_ext_state __user *state)
+#ifdef CONFIG_FPU
+static long restore_fp_state(struct pt_regs *regs,
+			     union __riscv_fp_state *sc_fpregs)
 {
 	long err;
+	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
+	size_t i;
+
 	err = __copy_from_user(&current->thread.fstate, state, sizeof(*state));
-	if (likely(!err))
-		fstate_restore(current, regs);
+	if (unlikely(err))
+		return err;
+
+	fstate_restore(current, regs);
+
+	/* We support no other extension state at this time. */
+	for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) {
+		u32 value;
+
+		err = __get_user(value, &sc_fpregs->q.reserved[i]);
+		if (unlikely(err))
+			break;
+		if (value != 0)
+			return -EINVAL;
+	}
+
 	return err;
 }
 
-static long save_d_state(struct pt_regs *regs,
-	struct __riscv_d_ext_state __user *state)
+static long save_fp_state(struct pt_regs *regs,
+			  union __riscv_fp_state *sc_fpregs)
 {
+	long err;
+	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
+	size_t i;
+
 	fstate_save(current, regs);
-	return __copy_to_user(state, &current->thread.fstate, sizeof(*state));
+	err = __copy_to_user(state, &current->thread.fstate, sizeof(*state));
+	if (unlikely(err))
+		return err;
+
+	/* We support no other extension state at this time. */
+	for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) {
+		err = __put_user(0, &sc_fpregs->q.reserved[i]);
+		if (unlikely(err))
+			break;
+	}
+
+	return err;
 }
+#else
+#define save_fp_state(task, regs) (0)
+#define restore_fp_state(task, regs) (0)
+#endif
 
 static long restore_sigcontext(struct pt_regs *regs,
 	struct sigcontext __user *sc)
 {
 	long err;
-	size_t i;
 	/* sc_regs is structured the same as the start of pt_regs */
 	err = __copy_from_user(regs, &sc->sc_regs, sizeof(sc->sc_regs));
-	if (unlikely(err))
-		return err;
 	/* Restore the floating-point state. */
-	err = restore_d_state(regs, &sc->sc_fpregs.d);
-	if (unlikely(err))
-		return err;
-	/* We support no other extension state at this time. */
-	for (i = 0; i < ARRAY_SIZE(sc->sc_fpregs.q.reserved); i++) {
-		u32 value;
-		err = __get_user(value, &sc->sc_fpregs.q.reserved[i]);
-		if (unlikely(err))
-			break;
-		if (value != 0)
-			return -EINVAL;
-	}
+	if (has_fpu)
+		err |= restore_fp_state(regs, &sc->sc_fpregs);
 	return err;
 }
 
@@ -124,14 +148,11 @@ static long setup_sigcontext(struct rt_sigframe __user *frame,
 {
 	struct sigcontext __user *sc = &frame->uc.uc_mcontext;
 	long err;
-	size_t i;
 	/* sc_regs is structured the same as the start of pt_regs */
 	err = __copy_to_user(&sc->sc_regs, regs, sizeof(sc->sc_regs));
 	/* Save the floating-point state. */
-	err |= save_d_state(regs, &sc->sc_fpregs.d);
-	/* We support no other extension state at this time. */
-	for (i = 0; i < ARRAY_SIZE(sc->sc_fpregs.q.reserved); i++)
-		err |= __put_user(0, &sc->sc_fpregs.q.reserved[i]);
+	if (has_fpu)
+		err |= save_fp_state(regs, &sc->sc_fpregs);
 	return err;
 }
 
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 906fe21ea21b..57b1383e5ef7 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -22,23 +22,44 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
+#include <linux/seq_file.h>
 
 #include <asm/sbi.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 
-/* A collection of single bit ipi messages.  */
-static struct {
-	unsigned long bits ____cacheline_aligned;
-} ipi_data[NR_CPUS] __cacheline_aligned;
-
 enum ipi_message_type {
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
 	IPI_MAX
 };
 
+/* A collection of single bit ipi messages.  */
+static struct {
+	unsigned long stats[IPI_MAX] ____cacheline_aligned;
+	unsigned long bits ____cacheline_aligned;
+} ipi_data[NR_CPUS] __cacheline_aligned;
+
+int riscv_hartid_to_cpuid(int hartid)
+{
+	int i = -1;
+
+	for (i = 0; i < NR_CPUS; i++)
+		if (cpuid_to_hartid_map(i) == hartid)
+			return i;
 
+	pr_err("Couldn't find cpu id for hartid [%d]\n", hartid);
+	BUG();
+	return i;
+}
+
+void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out)
+{
+	int cpu;
+
+	for_each_cpu(cpu, in)
+		cpumask_set_cpu(cpuid_to_hartid_map(cpu), out);
+}
 /* Unsupported */
 int setup_profiling_timer(unsigned int multiplier)
 {
@@ -48,6 +69,7 @@ int setup_profiling_timer(unsigned int multiplier)
 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(sip, SIE_SSIE);
@@ -62,11 +84,15 @@ void riscv_software_interrupt(void)
 		if (ops == 0)
 			return;
 
-		if (ops & (1 << IPI_RESCHEDULE))
+		if (ops & (1 << IPI_RESCHEDULE)) {
+			stats[IPI_RESCHEDULE]++;
 			scheduler_ipi();
+		}
 
-		if (ops & (1 << IPI_CALL_FUNC))
+		if (ops & (1 << IPI_CALL_FUNC)) {
+			stats[IPI_CALL_FUNC]++;
 			generic_smp_call_function_interrupt();
+		}
 
 		BUG_ON((ops >> IPI_MAX) != 0);
 
@@ -78,14 +104,36 @@ void riscv_software_interrupt(void)
 static void
 send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
 {
-	int i;
+	int cpuid, hartid;
+	struct cpumask hartid_mask;
 
+	cpumask_clear(&hartid_mask);
 	mb();
-	for_each_cpu(i, to_whom)
-		set_bit(operation, &ipi_data[i].bits);
-
+	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(to_whom));
+	sbi_send_ipi(cpumask_bits(&hartid_mask));
+}
+
+static const char * const ipi_names[] = {
+	[IPI_RESCHEDULE]	= "Rescheduling interrupts",
+	[IPI_CALL_FUNC]		= "Function call interrupts",
+};
+
+void show_ipi_stats(struct seq_file *p, int prec)
+{
+	unsigned int cpu, i;
+
+	for (i = 0; i < IPI_MAX; i++) {
+		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
+			   prec >= 4 ? " " : "");
+		for_each_online_cpu(cpu)
+			seq_printf(p, "%10lu ", ipi_data[cpu].stats[i]);
+		seq_printf(p, " %s\n", ipi_names[i]);
+	}
 }
 
 void arch_send_call_function_ipi_mask(struct cpumask *mask)
@@ -127,7 +175,7 @@ void smp_send_reschedule(int cpu)
 void flush_icache_mm(struct mm_struct *mm, bool local)
 {
 	unsigned int cpu;
-	cpumask_t others, *mask;
+	cpumask_t others, hmask, *mask;
 
 	preempt_disable();
 
@@ -145,9 +193,11 @@ 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)
-		sbi_remote_fence_i(others.bits);
-	else {
+	if (mm != current->active_mm || !local) {
+		cpumask_clear(&hmask);
+		riscv_cpuid_to_hartid_mask(&others, &hmask);
+		sbi_remote_fence_i(hmask.bits);
+	} else {
 		/*
 		 * It's assumed that at least one strongly ordered operation is
 		 * performed on this hart between setting a hart's cpumask bit
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 56abab6a9812..18cda0e8cf94 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -30,6 +30,7 @@
 #include <linux/irq.h>
 #include <linux/of.h>
 #include <linux/sched/task_stack.h>
+#include <linux/sched/mm.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
@@ -50,25 +51,33 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 void __init setup_smp(void)
 {
 	struct device_node *dn = NULL;
-	int hart, im_okay_therefore_i_am = 0;
+	int hart;
+	bool found_boot_cpu = false;
+	int cpuid = 1;
 
 	while ((dn = of_find_node_by_type(dn, "cpu"))) {
-		hart = riscv_of_processor_hart(dn);
-		if (hart >= 0) {
-			set_cpu_possible(hart, true);
-			set_cpu_present(hart, true);
-			if (hart == smp_processor_id()) {
-				BUG_ON(im_okay_therefore_i_am);
-				im_okay_therefore_i_am = 1;
-			}
+		hart = riscv_of_processor_hartid(dn);
+		if (hart < 0)
+			continue;
+
+		if (hart == cpuid_to_hartid_map(0)) {
+			BUG_ON(found_boot_cpu);
+			found_boot_cpu = 1;
+			continue;
 		}
+
+		cpuid_to_hartid_map(cpuid) = hart;
+		set_cpu_possible(cpuid, true);
+		set_cpu_present(cpuid, true);
+		cpuid++;
 	}
 
-	BUG_ON(!im_okay_therefore_i_am);
+	BUG_ON(!found_boot_cpu);
 }
 
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
+	int hartid = cpuid_to_hartid_map(cpu);
 	tidle->thread_info.cpu = cpu;
 
 	/*
@@ -79,8 +88,9 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	 * the spinning harts that they can continue the boot process.
 	 */
 	smp_mb();
-	__cpu_up_stack_pointer[cpu] = task_stack_page(tidle) + THREAD_SIZE;
-	__cpu_up_task_pointer[cpu] = tidle;
+	WRITE_ONCE(__cpu_up_stack_pointer[hartid],
+		  task_stack_page(tidle) + THREAD_SIZE);
+	WRITE_ONCE(__cpu_up_task_pointer[hartid], tidle);
 
 	while (!cpu_online(cpu))
 		cpu_relax();
@@ -100,14 +110,22 @@ asmlinkage void __init smp_callin(void)
 	struct mm_struct *mm = &init_mm;
 
 	/* All kernel threads share the same mm context.  */
-	atomic_inc(&mm->mm_count);
+	mmgrab(mm);
 	current->active_mm = mm;
 
 	trap_init();
 	notify_cpu_starting(smp_processor_id());
 	set_cpu_online(smp_processor_id(), 1);
+	/*
+	 * Remote TLB flushes are ignored while the CPU is offline, so emit
+	 * a local TLB flush right now just in case.
+	 */
 	local_flush_tlb_all();
-	local_irq_enable();
+	/*
+	 * Disable preemption before enabling interrupts, so we don't try to
+	 * schedule a CPU that hasn't actually started yet.
+	 */
 	preempt_disable();
+	local_irq_enable();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }