13 files changed, 243 insertions, 7 deletions

diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 76af908f87c1..78f670d70133 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -152,6 +152,3 @@ END(_start)
 __PAGE_ALIGNED_BSS
         /* Empty zero page */
         .balign PAGE_SIZE
-ENTRY(empty_zero_page)
-        .fill (empty_zero_page + PAGE_SIZE) - ., 1, 0x00
-END(empty_zero_page)
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
index 23cc81ec9e94..551734248748 100644
--- a/arch/riscv/kernel/riscv_ksyms.c
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -12,4 +12,7 @@
 /*
  * Assembly functions that may be used (directly or indirectly) by modules
  */
+EXPORT_SYMBOL(__clear_user);
 EXPORT_SYMBOL(__copy_user);
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memcpy);
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index de7db114c315..8fbb6749910d 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -58,7 +58,12 @@ static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
 #endif /* CONFIG_CMDLINE_BOOL */
 
 unsigned long va_pa_offset;
+EXPORT_SYMBOL(va_pa_offset);
 unsigned long pfn_base;
+EXPORT_SYMBOL(pfn_base);
+
+unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
+EXPORT_SYMBOL(empty_zero_page);
 
 /* The lucky hart to first increment this variable will boot the other cores */
 atomic_t hart_lottery;
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index b4a71ec5906f..6d3962435720 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -38,6 +38,13 @@ enum ipi_message_type {
         IPI_MAX
 };
 
+
+/* Unsupported */
+int setup_profiling_timer(unsigned int multiplier)
+{
+        return -EINVAL;
+}
+
 irqreturn_t handle_ipi(void)
 {
         unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
@@ -108,3 +115,51 @@ void smp_send_reschedule(int cpu)
 {
         send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
 }
+
+/*
+ * Performs an icache flush for the given MM context.  RISC-V has no direct
+ * mechanism for instruction cache shoot downs, so instead we send an IPI that
+ * informs the remote harts they need to flush their local instruction caches.
+ * To avoid pathologically slow behavior in a common case (a bunch of
+ * single-hart processes on a many-hart machine, ie 'make -j') we avoid the
+ * IPIs for harts that are not currently executing a MM context and instead
+ * schedule a deferred local instruction cache flush to be performed before
+ * execution resumes on each hart.
+ */
+void flush_icache_mm(struct mm_struct *mm, bool local)
+{
+        unsigned int cpu;
+        cpumask_t others, *mask;
+
+        preempt_disable();
+
+        /* Mark every hart's icache as needing a flush for this MM. */
+        mask = &mm->context.icache_stale_mask;
+        cpumask_setall(mask);
+        /* Flush this hart's I$ now, and mark it as flushed. */
+        cpu = smp_processor_id();
+        cpumask_clear_cpu(cpu, mask);
+        local_flush_icache_all();
+
+        /*
+         * Flush the I$ of other harts concurrently executing, and mark them as
+         * flushed.
+         */
+        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 {
+                /*
+                 * It's assumed that at least one strongly ordered operation is
+                 * performed on this hart between setting a hart's cpumask bit
+                 * and scheduling this MM context on that hart.  Sending an SBI
+                 * remote message will do this, but in the case where no
+                 * messages are sent we still need to order this hart's writes
+                 * with flush_icache_deferred().
+                 */
+                smp_mb();
+        }
+
+        preempt_enable();
+}
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 4351be7d0533..a2ae936a093e 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -14,8 +14,8 @@
  */
 
 #include <linux/syscalls.h>
-#include <asm/cmpxchg.h>
 #include <asm/unistd.h>
+#include <asm/cacheflush.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
                            unsigned long prot, unsigned long flags,
@@ -47,3 +47,34 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
         return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12);
 }
 #endif /* !CONFIG_64BIT */
+
+#ifdef CONFIG_SMP
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * sys_riscv_flush_icache() is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
+        uintptr_t, flags)
+{
+        struct mm_struct *mm = current->mm;
+        bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0;
+
+        /* Check the reserved flags. */
+        if (unlikely(flags & !SYS_RISCV_FLUSH_ICACHE_ALL))
+                return -EINVAL;
+
+        flush_icache_mm(mm, local);
+
+        return 0;
+}
+#endif
diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c
index 4e30dc5fb593..a5bd6401f95e 100644
--- a/arch/riscv/kernel/syscall_table.c
+++ b/arch/riscv/kernel/syscall_table.c
@@ -15,6 +15,7 @@
 #include <linux/linkage.h>
 #include <linux/syscalls.h>
 #include <asm-generic/syscalls.h>
+#include <asm/vdso.h>
 
 #undef __SYSCALL
 #define __SYSCALL(nr, call)     [nr] = (call),
@@ -22,4 +23,5 @@
 void *sys_call_table[__NR_syscalls] = {
         [0 ... __NR_syscalls - 1] = sys_ni_syscall,
 #include <asm/unistd.h>
+#include <asm/vdso-syscalls.h>
 };
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 523d0a8ac8db..324568d33921 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -1,7 +1,12 @@
 # Copied from arch/tile/kernel/vdso/Makefile
 
 # Symbols present in the vdso
-vdso-syms = rt_sigreturn
+vdso-syms  = rt_sigreturn
+vdso-syms += gettimeofday
+vdso-syms += clock_gettime
+vdso-syms += clock_getres
+vdso-syms += getcpu
+vdso-syms += flush_icache
 
 # Files to link into the vdso
 obj-vdso = $(patsubst %, %.o, $(vdso-syms))
diff --git a/arch/riscv/kernel/vdso/clock_getres.S b/arch/riscv/kernel/vdso/clock_getres.S
new file mode 100644
index 000000000000..edf7e2339648
--- /dev/null
+++ b/arch/riscv/kernel/vdso/clock_getres.S
@@ -0,0 +1,26 @@
+/*
+ * 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/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)
diff --git a/arch/riscv/kernel/vdso/clock_gettime.S b/arch/riscv/kernel/vdso/clock_gettime.S
new file mode 100644
index 000000000000..aac65676c6d5
--- /dev/null
+++ b/arch/riscv/kernel/vdso/clock_gettime.S
@@ -0,0 +1,26 @@
+/*
+ * 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/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)
diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S
new file mode 100644
index 000000000000..b0fbad74e873
--- /dev/null
+++ b/arch/riscv/kernel/vdso/flush_icache.S
@@ -0,0 +1,31 @@
+/*
+ * 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/unistd.h>
+#include <asm/vdso-syscalls.h>
+
+        .text
+/* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */
+ENTRY(__vdso_flush_icache)
+        .cfi_startproc
+#ifdef CONFIG_SMP
+        li a7, __NR_riscv_flush_icache
+        ecall
+#else
+        fence.i
+        li a0, 0
+#endif
+        ret
+        .cfi_endproc
+ENDPROC(__vdso_flush_icache)
diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S
new file mode 100644
index 000000000000..cc7e98924484
--- /dev/null
+++ b/arch/riscv/kernel/vdso/getcpu.S
@@ -0,0 +1,26 @@
+/*
+ * 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/unistd.h>
+
+        .text
+/* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */
+ENTRY(__vdso_getcpu)
+        .cfi_startproc
+        /* For now, just do the syscall. */
+        li a7, __NR_getcpu
+        ecall
+        ret
+        .cfi_endproc
+ENDPROC(__vdso_getcpu)
diff --git a/arch/riscv/kernel/vdso/gettimeofday.S b/arch/riscv/kernel/vdso/gettimeofday.S
new file mode 100644
index 000000000000..da85d33e8990
--- /dev/null
+++ b/arch/riscv/kernel/vdso/gettimeofday.S
@@ -0,0 +1,26 @@
+/*
+ * 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/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)
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index 8c9dce95c11d..cd1d47e0724b 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -70,8 +70,11 @@ VERSION
         LINUX_4.15 {
         global:
                 __vdso_rt_sigreturn;
-                __vdso_cmpxchg32;
-                __vdso_cmpxchg64;
+                __vdso_gettimeofday;
+                __vdso_clock_gettime;
+                __vdso_clock_getres;
+                __vdso_getcpu;
+                __vdso_flush_icache;
         local: *;
         };
 }