* RISC-V Linux Port v4
@ 2017-07-04 19:50 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Thanks to everyone who has participated in the review process so far. There
have only been a few changes since the v3 patch set:
* The cmpxchg64 syscall is no longer enabled on 32-bit systems. It's not
possible to provide this on SMP systems, and it's not necessary as glibc
knows not to call it.
* We provide a ELF_HWCAP so users can determine the ISA of the machine the
kernel is running on.
* The multi-line comments are in a better form.
* There were a handful of headers that could be replaced with the asm-generic
versions, and a few unnecessary definitions.
* We no longer use printk, but instead use pr_*.
* A few Kconfig and defconfig entries have been cleaned up.
Since things have really calmed down, I think it would be good to try and get
this into 4.13 (ie, during this merge window). This might let us get into the
upcoming glibc release as well. Does that seem possible?
Like last time, in case one gets eaten by the mailing list this is also
available as a git tree on our Git Hub
https://github.com/riscv/riscv-linux/tree/riscv-for-submission-arch-v4
This patch set just contains the arch code, we have various drivers that are
required to build and boot a RISC-V system. A tree that contains this patch
set merged with all our other patch sets lives at
https://github.com/riscv/riscv-linux/tree/riscv-for-submission-v4
a83d4bb70b76 pci: Add a generic, weakly-linked pcibios_fixup_bus
a3445d3b4ff1 pci: Add a generic, weakly-linked pcibios_align_resource
d97ac4f5bb1d Merge branch 'riscv-for-submission-arch-v4' into riscv-for-submission-v4
0705a31372d4 Merge branch 'riscv-for-submission-clk-v2' into riscv-for-submission-v4
a6c8eb9af199 Merge branch 'riscv-for-submission-irq-v2' into riscv-for-submission-v4
3e5b46967f66 Merge branch 'riscv-for-submission-lib-v2' into riscv-for-submission-v4
8ca3c2cdefed Merge branch 'riscv-for-submission-pci-v3' into riscv-for-submission-v4
e1aa9abddfa8 Merge branch 'riscv-for-submission-tty-v2' into riscv-for-submission-v4
If you're going to try to build or boot the kernel, I'd recommend using that.
Thanks to everyone who has helped review our port!
[PATCH 1/9] RISC-V: Init and Halt Code
[PATCH 2/9] RISC-V: Atomic and Locking Code
[PATCH 3/9] RISC-V: Generic library routines and assembly
[PATCH 4/9] RISC-V: ELF and module implementation
[PATCH 5/9] RISC-V: Task implementation
[PATCH 6/9] RISC-V: Device, timer, IRQs, and the SBI
[PATCH 7/9] RISC-V: Paging and MMU
[PATCH 8/9] RISC-V: User-facing API
[PATCH 9/9] RISC-V: Build Infastructure
^ permalink raw reply [flat|nested] 58+ messages in thread
* [PATCH 1/9] RISC-V: Init and Halt Code
2017-07-04 19:50 ` Palmer Dabbelt
(?)
@ 2017-07-04 19:50 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This contains the various __init C functions, the initial assembly
kernel entry point, and the code to reset the system. When a file was
init-related, it contains
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/bug.h | 88 +++++++++++++++
arch/riscv/include/asm/cache.h | 22 ++++
arch/riscv/include/asm/smp.h | 41 +++++++
arch/riscv/kernel/cacheinfo.c | 105 ++++++++++++++++++
arch/riscv/kernel/cpu.c | 89 +++++++++++++++
arch/riscv/kernel/head.S | 152 +++++++++++++++++++++++++
arch/riscv/kernel/irq.c | 20 ++++
arch/riscv/kernel/reset.c | 36 ++++++
arch/riscv/kernel/setup.c | 246 +++++++++++++++++++++++++++++++++++++++++
arch/riscv/kernel/smp.c | 110 ++++++++++++++++++
arch/riscv/kernel/smpboot.c | 114 +++++++++++++++++++
arch/riscv/kernel/time.c | 61 ++++++++++
arch/riscv/kernel/traps.c | 184 ++++++++++++++++++++++++++++++
arch/riscv/kernel/vdso.c | 125 +++++++++++++++++++++
arch/riscv/mm/init.c | 70 ++++++++++++
15 files changed, 1463 insertions(+)
create mode 100644 arch/riscv/include/asm/bug.h
create mode 100644 arch/riscv/include/asm/cache.h
create mode 100644 arch/riscv/include/asm/smp.h
create mode 100644 arch/riscv/kernel/cacheinfo.c
create mode 100644 arch/riscv/kernel/cpu.c
create mode 100644 arch/riscv/kernel/head.S
create mode 100644 arch/riscv/kernel/irq.c
create mode 100644 arch/riscv/kernel/reset.c
create mode 100644 arch/riscv/kernel/setup.c
create mode 100644 arch/riscv/kernel/smp.c
create mode 100644 arch/riscv/kernel/smpboot.c
create mode 100644 arch/riscv/kernel/time.c
create mode 100644 arch/riscv/kernel/traps.c
create mode 100644 arch/riscv/kernel/vdso.c
create mode 100644 arch/riscv/mm/init.c
diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h
new file mode 100644
index 000000000000..e2f690c20729
--- /dev/null
+++ b/arch/riscv/include/asm/bug.h
@@ -0,0 +1,88 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_BUG_H
+#define _ASM_RISCV_BUG_H
+
+#include <linux/compiler.h>
+#include <linux/const.h>
+#include <linux/types.h>
+
+#include <asm/asm.h>
+
+#ifdef CONFIG_GENERIC_BUG
+#define __BUG_INSN _AC(0x00100073, UL) /* sbreak */
+
+#ifndef __ASSEMBLY__
+typedef u32 bug_insn_t;
+
+#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+#define __BUG_ENTRY_ADDR INT " 1b - 2b"
+#define __BUG_ENTRY_FILE INT " %0 - 2b"
+#else
+#define __BUG_ENTRY_ADDR RISCV_PTR " 1b"
+#define __BUG_ENTRY_FILE RISCV_PTR " %0"
+#endif
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define __BUG_ENTRY \
+ __BUG_ENTRY_ADDR "\n\t" \
+ __BUG_ENTRY_FILE "\n\t" \
+ SHORT " %1"
+#else
+#define __BUG_ENTRY \
+ __BUG_ENTRY_ADDR
+#endif
+
+#define BUG() \
+do { \
+ __asm__ __volatile__ ( \
+ "1:\n\t" \
+ "sbreak\n" \
+ ".pushsection __bug_table,\"a\"\n\t" \
+ "2:\n\t" \
+ __BUG_ENTRY "\n\t" \
+ ".org 2b + %2\n\t" \
+ ".popsection" \
+ : \
+ : "i" (__FILE__), "i" (__LINE__), \
+ "i" (sizeof(struct bug_entry))); \
+ unreachable(); \
+} while (0)
+#endif /* !__ASSEMBLY__ */
+#else /* CONFIG_GENERIC_BUG */
+#ifndef __ASSEMBLY__
+#define BUG() \
+do { \
+ __asm__ __volatile__ ("sbreak\n"); \
+ unreachable(); \
+} while (0)
+#endif /* !__ASSEMBLY__ */
+#endif /* CONFIG_GENERIC_BUG */
+
+#define HAVE_ARCH_BUG
+
+#include <asm-generic/bug.h>
+
+#ifndef __ASSEMBLY__
+
+struct pt_regs;
+struct task_struct;
+
+extern void die(struct pt_regs *regs, const char *str);
+extern void do_trap(struct pt_regs *regs, int signo, int code,
+ unsigned long addr, struct task_struct *tsk);
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_BUG_H */
diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
new file mode 100644
index 000000000000..e8f0d1110d74
--- /dev/null
+++ b/arch/riscv/include/asm/cache.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2017 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_CACHE_H
+#define _ASM_RISCV_CACHE_H
+
+#define L1_CACHE_SHIFT 6
+
+#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
+
+#endif /* _ASM_RISCV_CACHE_H */
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
new file mode 100644
index 000000000000..f61f8c25f95b
--- /dev/null
+++ b/arch/riscv/include/asm/smp.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SMP_H
+#define _ASM_RISCV_SMP_H
+
+#include <linux/cpumask.h>
+#include <linux/irqreturn.h>
+
+#ifdef CONFIG_SMP
+
+/* SMP initialization hook for setup_arch */
+void __init init_clockevent(void);
+
+/* SMP initialization hook for setup_arch */
+void __init setup_smp(void);
+
+/* Hook for the generic smp_call_function_many() routine. */
+void arch_send_call_function_ipi_mask(struct cpumask *mask);
+
+/* Hook for the generic smp_call_function_single() routine. */
+void arch_send_call_function_single_ipi(int cpu);
+
+#define raw_smp_processor_id() (current_thread_info()->cpu)
+
+/* Interprocessor interrupt handler */
+irqreturn_t handle_ipi(void);
+
+#endif /* CONFIG_SMP */
+
+#endif /* _ASM_RISCV_SMP_H */
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
new file mode 100644
index 000000000000..10ed2749e246
--- /dev/null
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -0,0 +1,105 @@
+/*
+ * 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/cacheinfo.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+static void ci_leaf_init(struct cacheinfo *this_leaf,
+ struct device_node *node,
+ enum cache_type type, unsigned int level)
+{
+ this_leaf->of_node = node;
+ 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)
+{
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct device_node *np = of_cpu_device_node_get(cpu);
+ int levels = 0, leaves = 0, level;
+
+ if (of_property_read_bool(np, "cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "i-cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "d-cache-size"))
+ ++leaves;
+ if (leaves > 0)
+ levels = 1;
+
+ while ((np = of_find_next_cache_node(np))) {
+ if (!of_device_is_compatible(np, "cache"))
+ break;
+ if (of_property_read_u32(np, "cache-level", &level))
+ break;
+ if (level <= levels)
+ break;
+ if (of_property_read_bool(np, "cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "i-cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "d-cache-size"))
+ ++leaves;
+ levels = level;
+ }
+
+ this_cpu_ci->num_levels = levels;
+ this_cpu_ci->num_leaves = leaves;
+ return 0;
+}
+
+static int __populate_cache_leaves(unsigned int cpu)
+{
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+ struct device_node *np = of_cpu_device_node_get(cpu);
+ int levels = 1, level = 1;
+
+ if (of_property_read_bool(np, "cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level);
+ if (of_property_read_bool(np, "i-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level);
+ if (of_property_read_bool(np, "d-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level);
+
+ while ((np = of_find_next_cache_node(np))) {
+ if (!of_device_is_compatible(np, "cache"))
+ break;
+ if (of_property_read_u32(np, "cache-level", &level))
+ break;
+ if (level <= levels)
+ break;
+ if (of_property_read_bool(np, "cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level);
+ if (of_property_read_bool(np, "i-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level);
+ if (of_property_read_bool(np, "d-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level);
+ levels = level;
+ }
+
+ return 0;
+}
+
+DEFINE_SMP_CALL_CACHE_FUNCTION(init_cache_level)
+DEFINE_SMP_CALL_CACHE_FUNCTION(populate_cache_leaves)
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
new file mode 100644
index 000000000000..20004bd7a216
--- /dev/null
+++ b/arch/riscv/kernel/cpu.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/init.h>
+#include <linux/seq_file.h>
+#include <linux/of.h>
+
+/* Return -1 if not a valid hart */
+int riscv_of_processor_hart(struct device_node *node)
+{
+ const char *isa, *status;
+ u32 hart;
+
+ if (!of_device_is_compatible(node, "riscv"))
+ return -(ENODEV);
+ if (of_property_read_u32(node, "reg", &hart)
+ || hart >= NR_CPUS)
+ return -(ENODEV);
+ if (of_property_read_string(node, "status", &status)
+ || strcmp(status, "okay"))
+ return -(ENODEV);
+ if (of_property_read_string(node, "riscv,isa", &isa)
+ || isa[0] != 'r'
+ || isa[1] != 'v')
+ return -(ENODEV);
+
+ return hart;
+}
+
+#ifdef CONFIG_PROC_FS
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+ *pos = cpumask_next(*pos - 1, cpu_online_mask);
+ if ((*pos) < nr_cpu_ids)
+ return (void *)(uintptr_t)(1 + *pos);
+ return NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ (*pos)++;
+ return c_start(m, pos);
+}
+
+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);
+ 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);
+ if (!of_property_read_string(node, "compatible", &compat)
+ && strcmp(compat, "riscv"))
+ seq_printf(m, "uarch\t: %s\n", compat);
+ seq_puts(m, "\n");
+
+ return 0;
+}
+
+const struct seq_operations cpuinfo_op = {
+ .start = c_start,
+ .next = c_next,
+ .stop = c_stop,
+ .show = c_show
+};
+
+#endif /* CONFIG_PROC_FS */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
new file mode 100644
index 000000000000..504c368238c2
--- /dev/null
+++ b/arch/riscv/kernel/head.S
@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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 <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm/asm.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/csr.h>
+
+__INIT
+ENTRY(_start)
+ /* Mask all interrupts */
+ csrw sie, zero
+
+ /*
+ * Disable FPU to detect illegal usage of
+ * floating point in kernel space
+ */
+ li t0, SR_FS
+ csrc sstatus, t0
+
+#ifndef CONFIG_RV_PUM
+ /* Allow access to user memory */
+ li t0, SR_SUM
+ csrs sstatus, t0
+#endif
+
+#ifdef CONFIG_ISA_A
+ /* Pick one hart to run the main boot sequence */
+ la a3, hart_lottery
+ li a2, 1
+ amoadd.w a3, a2, (a3)
+ bnez a3, .Lsecondary_start
+#else
+ /*
+ * We don't have atomic support, so the boot hart must be picked
+ * staticly. Hart 0 is the only sane choice.
+ */
+ bnez a0, .Lsecondary_park
+#endif
+
+ /* Save hart ID and DTB physical address */
+ mv s0, a0
+ mv s1, a1
+
+ /* Initialize page tables and relocate to virtual addresses */
+ la sp, init_thread_union + THREAD_SIZE
+ call setup_vm
+ call relocate
+
+ /* Restore C environment */
+ la tp, init_task
+
+ la sp, init_thread_union
+ li a0, ASM_THREAD_SIZE
+ add sp, sp, a0
+
+ /* Start the kernel */
+ mv a0, s0
+ mv a1, s1
+ call sbi_save
+ tail start_kernel
+
+relocate:
+ /* Relocate return address */
+ li a1, PAGE_OFFSET
+ la a0, _start
+ sub a1, a1, a0
+ add ra, ra, a1
+
+ /* Point stvec to virtual address of intruction after sptbr write */
+ la a0, 1f
+ add a0, a0, a1
+ csrw stvec, a0
+
+ /* Compute sptbr for kernel page tables, but don't load it yet */
+ la a2, swapper_pg_dir
+ srl a2, a2, PAGE_SHIFT
+ li a1, SPTBR_MODE
+ or a2, a2, a1
+
+ /*
+ * Load trampoline page directory, which will cause us to trap to
+ * stvec if VA != PA, or simply fall through if VA == PA
+ */
+ la a0, trampoline_pg_dir
+ srl a0, a0, PAGE_SHIFT
+ or a0, a0, a1
+ sfence.vma
+ csrw sptbr, a0
+1:
+ /* Set trap vector to spin forever to help debug */
+ la a0, .Lsecondary_park
+ csrw stvec, a0
+
+ /* Load the global pointer */
+ la gp, __global_pointer$
+
+ /* Switch to kernel page tables */
+ csrw sptbr, a2
+
+ ret
+
+.Lsecondary_start:
+#ifdef CONFIG_SMP
+ li a1, CONFIG_NR_CPUS
+ bgeu a0, a1, .Lsecondary_park
+
+ la a1, __cpu_up_stack_pointer
+ slli a0, a0, LGREG
+ add a0, a0, a1
+
+.Lwait_for_cpu_up:
+ REG_L sp, (a0)
+ beqz sp, .Lwait_for_cpu_up
+ fence
+
+ /* Enable virtual memory and relocate to virtual address */
+ call relocate
+
+ /* Initialize task_struct pointer */
+ li tp, -THREAD_SIZE
+ add tp, tp, sp
+
+ tail smp_callin
+#endif
+
+.Lsecondary_park:
+ /* We lack SMP support or have too many harts, so park this hart */
+ wfi
+ j .Lsecondary_park
+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/irq.c b/arch/riscv/kernel/irq.c
new file mode 100644
index 000000000000..737d7cce2c6d
--- /dev/null
+++ b/arch/riscv/kernel/irq.c
@@ -0,0 +1,20 @@
+/*
+ * 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/irqchip.h>
+
+void __init init_IRQ(void)
+{
+ irqchip_init();
+}
diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c
new file mode 100644
index 000000000000..2a53d26ffdd6
--- /dev/null
+++ b/arch/riscv/kernel/reset.c
@@ -0,0 +1,36 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/reboot.h>
+#include <linux/export.h>
+#include <asm/sbi.h>
+
+void (*pm_power_off)(void) = machine_power_off;
+EXPORT_SYMBOL(pm_power_off);
+
+void machine_restart(char *cmd)
+{
+ do_kernel_restart(cmd);
+ while (1);
+}
+
+void machine_halt(void)
+{
+ machine_power_off();
+}
+
+void machine_power_off(void)
+{
+ sbi_shutdown();
+ while (1);
+}
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
new file mode 100644
index 000000000000..319fad96f537
--- /dev/null
+++ b/arch/riscv/kernel/setup.c
@@ -0,0 +1,246 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/sched.h>
+#include <linux/initrd.h>
+#include <linux/console.h>
+#include <linux/screen_info.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/sched/task.h>
+
+#include <asm/setup.h>
+#include <asm/sections.h>
+#include <asm/pgtable.h>
+#include <asm/smp.h>
+#include <asm/sbi.h>
+#include <asm/tlbflush.h>
+#include <asm/thread_info.h>
+
+#ifdef CONFIG_DUMMY_CONSOLE
+struct screen_info screen_info = {
+ .orig_video_lines = 30,
+ .orig_video_cols = 80,
+ .orig_video_mode = 0,
+ .orig_video_ega_bx = 0,
+ .orig_video_isVGA = 1,
+ .orig_video_points = 8
+};
+#endif
+
+#ifdef CONFIG_CMDLINE_BOOL
+static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
+#endif /* CONFIG_CMDLINE_BOOL */
+
+unsigned long va_pa_offset;
+unsigned long pfn_base;
+
+/* The lucky hart to first increment this variable will boot the other cores */
+atomic_t hart_lottery;
+
+#ifdef CONFIG_BLK_DEV_INITRD
+static void __init setup_initrd(void)
+{
+ extern char __initramfs_start[];
+ extern unsigned long __initramfs_size;
+ unsigned long size;
+
+ if (__initramfs_size > 0) {
+ initrd_start = (unsigned long)(&__initramfs_start);
+ initrd_end = initrd_start + __initramfs_size;
+ }
+
+ if (initrd_start >= initrd_end) {
+ printk(KERN_INFO "initrd not found or empty");
+ goto disable;
+ }
+ if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) {
+ printk(KERN_ERR "initrd extends beyond end of memory");
+ goto disable;
+ }
+
+ size = initrd_end - initrd_start;
+ memblock_reserve(__pa(initrd_start), size);
+ initrd_below_start_ok = 1;
+
+ printk(KERN_INFO "Initial ramdisk at: 0x%p (%lu bytes)\n",
+ (void *)(initrd_start), size);
+ return;
+disable:
+ pr_cont(" - disabling initrd\n");
+ initrd_start = 0;
+ initrd_end = 0;
+}
+#endif /* CONFIG_BLK_DEV_INITRD */
+
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
+pgd_t trampoline_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+
+#ifndef __PAGETABLE_PMD_FOLDED
+#define NUM_SWAPPER_PMDS ((uintptr_t)-PAGE_OFFSET >> PGDIR_SHIFT)
+pmd_t swapper_pmd[PTRS_PER_PMD*((-PAGE_OFFSET)/PGDIR_SIZE)] __page_aligned_bss;
+pmd_t trampoline_pmd[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+#endif
+
+asmlinkage void __init setup_vm(void)
+{
+ extern char _start;
+ uintptr_t i;
+ uintptr_t pa = (uintptr_t) &_start;
+ pgprot_t prot = __pgprot(pgprot_val(PAGE_KERNEL) | _PAGE_EXEC);
+
+ va_pa_offset = PAGE_OFFSET - pa;
+ pfn_base = PFN_DOWN(pa);
+
+ /* Sanity check alignment and size */
+ BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
+ BUG_ON((pa % (PAGE_SIZE * PTRS_PER_PTE)) != 0);
+
+#ifndef __PAGETABLE_PMD_FOLDED
+ trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
+ pfn_pgd(PFN_DOWN((uintptr_t)trampoline_pmd),
+ __pgprot(_PAGE_TABLE));
+ trampoline_pmd[0] = pfn_pmd(PFN_DOWN(pa), prot);
+
+ for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
+ size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
+ swapper_pg_dir[o] =
+ pfn_pgd(PFN_DOWN((uintptr_t)swapper_pmd) + i,
+ __pgprot(_PAGE_TABLE));
+ }
+ for (i = 0; i < ARRAY_SIZE(swapper_pmd); i++)
+ swapper_pmd[i] = pfn_pmd(PFN_DOWN(pa + i * PMD_SIZE), prot);
+#else
+ trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
+ pfn_pgd(PFN_DOWN(pa), prot);
+
+ for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
+ size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
+ swapper_pg_dir[o] =
+ pfn_pgd(PFN_DOWN(pa + i * PGDIR_SIZE), prot);
+ }
+#endif
+}
+
+void __init sbi_save(unsigned int hartid, void *dtb)
+{
+ early_init_dt_scan(__va(dtb));
+}
+
+/*
+ * Allow the user to manually add a memory region (in case DTS is broken);
+ * "mem_end=nn[KkMmGg]"
+ */
+static int __init mem_end_override(char *p)
+{
+ resource_size_t base, end;
+
+ if (!p)
+ return -EINVAL;
+ base = (uintptr_t) __pa(PAGE_OFFSET);
+ end = memparse(p, &p) & PMD_MASK;
+ if (end == 0)
+ return -EINVAL;
+ memblock_add(base, end - base);
+ return 0;
+}
+early_param("mem_end", mem_end_override);
+
+static void __init setup_bootmem(void)
+{
+ struct memblock_region *reg;
+ phys_addr_t mem_size = 0;
+
+ /* Find the memory region containing the kernel */
+ for_each_memblock(memory, reg) {
+ phys_addr_t vmlinux_end = __pa(_end);
+ phys_addr_t end = reg->base + reg->size;
+
+ if (reg->base <= vmlinux_end && vmlinux_end <= end) {
+ /*
+ * Reserve from the start of the region to the end of
+ * the kernel
+ */
+ memblock_reserve(reg->base, vmlinux_end - reg->base);
+ mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
+ }
+ }
+ BUG_ON(mem_size == 0);
+
+ set_max_mapnr(PFN_DOWN(mem_size));
+ max_low_pfn = pfn_base + PFN_DOWN(mem_size);
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ setup_initrd();
+#endif /* CONFIG_BLK_DEV_INITRD */
+
+ early_init_fdt_reserve_self();
+ early_init_fdt_scan_reserved_mem();
+ memblock_allow_resize();
+ memblock_dump_all();
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+ strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+ if (builtin_cmdline[0] != '\0') {
+ /* Append bootloader command line to built-in */
+ strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
+ strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+ strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+ }
+#endif /* CONFIG_CMDLINE_OVERRIDE */
+#endif /* CONFIG_CMDLINE_BOOL */
+ *cmdline_p = boot_command_line;
+
+ parse_early_param();
+
+ init_mm.start_code = (unsigned long) _stext;
+ init_mm.end_code = (unsigned long) _etext;
+ init_mm.end_data = (unsigned long) _edata;
+ init_mm.brk = (unsigned long) _end;
+
+ setup_bootmem();
+ paging_init();
+ unflatten_device_tree();
+
+#ifdef CONFIG_SMP
+ setup_smp();
+#endif
+
+#ifdef CONFIG_DUMMY_CONSOLE
+ conswitchp = &dummy_con;
+#endif
+
+ riscv_fill_hwcap();
+}
+
+static int __init riscv_device_init(void)
+{
+ return of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+}
+subsys_initcall_sync(riscv_device_init);
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
new file mode 100644
index 000000000000..b4a71ec5906f
--- /dev/null
+++ b/arch/riscv/kernel/smp.c
@@ -0,0 +1,110 @@
+/*
+ * SMP initialisation and IPI support
+ * Based on arch/arm64/kernel/smp.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+#include <linux/sched.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
+};
+
+irqreturn_t handle_ipi(void)
+{
+ unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
+
+ /* Clear pending IPI */
+ csr_clear(sip, SIE_SSIE);
+
+ while (true) {
+ unsigned long ops;
+
+ /* Order bit clearing and data access. */
+ mb();
+
+ ops = xchg(pending_ipis, 0);
+ if (ops == 0)
+ return IRQ_HANDLED;
+
+ if (ops & (1 << IPI_RESCHEDULE))
+ scheduler_ipi();
+
+ if (ops & (1 << IPI_CALL_FUNC))
+ generic_smp_call_function_interrupt();
+
+ BUG_ON((ops >> IPI_MAX) != 0);
+
+ /* Order data access and bit testing. */
+ mb();
+ }
+
+ return IRQ_HANDLED;
+}
+
+static void
+send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
+{
+ int i;
+
+ mb();
+ for_each_cpu(i, to_whom)
+ set_bit(operation, &ipi_data[i].bits);
+
+ mb();
+ sbi_send_ipi(cpumask_bits(to_whom));
+}
+
+void arch_send_call_function_ipi_mask(struct cpumask *mask)
+{
+ send_ipi_message(mask, IPI_CALL_FUNC);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+ send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
+}
+
+static void ipi_stop(void *unused)
+{
+ while (1)
+ wait_for_interrupt();
+}
+
+void smp_send_stop(void)
+{
+ on_each_cpu(ipi_stop, NULL, 1);
+}
+
+void smp_send_reschedule(int cpu)
+{
+ send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
+}
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
new file mode 100644
index 000000000000..e5c7f1aafda9
--- /dev/null
+++ b/arch/riscv/kernel/smpboot.c
@@ -0,0 +1,114 @@
+/*
+ * SMP initialisation and IPI support
+ * Based on arch/arm64/kernel/smp.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/kernel_stat.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/percpu.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/sched/task_stack.h>
+#include <asm/irq.h>
+#include <asm/mmu_context.h>
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/sbi.h>
+
+void *__cpu_up_stack_pointer[NR_CPUS];
+
+void __init smp_prepare_boot_cpu(void)
+{
+}
+
+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;
+
+ 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;
+ }
+ }
+ }
+
+ BUG_ON(!im_okay_therefore_i_am);
+}
+
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+ /* Signal cpu to start */
+ mb();
+ __cpu_up_stack_pointer[cpu] = task_stack_page(tidle) + THREAD_SIZE;
+
+ while (!cpu_online(cpu))
+ cpu_relax();
+
+ return 0;
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+/*
+ * C entry point for a secondary processor.
+ */
+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);
+ current->active_mm = mm;
+
+ trap_init();
+ init_clockevent();
+ notify_cpu_starting(smp_processor_id());
+ set_cpu_online(smp_processor_id(), 1);
+
+ /*
+ * Write SIE again now that this hart is online, to catch any IRQ
+ * enable/disable events that happened between trap_init() and
+ * set_cpu_online().
+ */
+ csr_write(sie,
+ SIE_SSIE | atomic_long_read(&per_cpu(riscv_early_sie, hart))
+ );
+
+ local_flush_tlb_all();
+ local_irq_enable();
+ preempt_disable();
+ cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
new file mode 100644
index 000000000000..6bba2e6f2a84
--- /dev/null
+++ b/arch/riscv/kernel/time.c
@@ -0,0 +1,61 @@
+/*
+ * 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/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/delay.h>
+#include <linux/timer_riscv.h>
+
+#include <asm/sbi.h>
+
+unsigned long riscv_timebase;
+
+static int next_event(unsigned long delta, struct clock_event_device *ce)
+{
+ BUG_ON(ce != timer_riscv_device(smp_processor_id()));
+ sbi_set_timer(get_cycles64() + delta);
+ return 0;
+}
+
+static unsigned long long rdtime(struct clocksource *cs)
+{
+ BUG_ON(cs != timer_riscv_source(smp_processor_id()));
+ return get_cycles64();
+}
+
+void riscv_timer_interrupt(void)
+{
+ int cpu = smp_processor_id();
+ struct clock_event_device *evdev = timer_riscv_device(cpu);
+
+ evdev->event_handler(evdev);
+}
+
+void __init time_init(void)
+{
+ struct device_node *cpu;
+ u32 prop;
+ int cpu_id = smp_processor_id();
+
+ cpu = of_find_node_by_path("/cpus");
+ if (!cpu || of_property_read_u32(cpu, "timebase-frequency", &prop))
+ panic(KERN_WARNING "RISC-V system with no 'timebase-frequency' in DTS\n");
+ riscv_timebase = prop;
+
+ lpj_fine = riscv_timebase / HZ;
+
+ timer_riscv_init(cpu_id, riscv_timebase, &rdtime, &next_event);
+
+ csr_set(sie, SIE_STIE);
+}
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
new file mode 100644
index 000000000000..2175a39bed1c
--- /dev/null
+++ b/arch/riscv/kernel/traps.c
@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/kernel.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
+#include <linux/signal.h>
+#include <linux/kdebug.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/csr.h>
+
+int show_unhandled_signals = 1;
+
+extern asmlinkage void handle_exception(void);
+
+static DEFINE_SPINLOCK(die_lock);
+
+void die(struct pt_regs *regs, const char *str)
+{
+ static int die_counter;
+ int ret;
+
+ oops_enter();
+
+ spin_lock_irq(&die_lock);
+ console_verbose();
+ bust_spinlocks(1);
+
+ pr_emerg("%s [#%d]\n", str, ++die_counter);
+ print_modules();
+ show_regs(regs);
+
+ ret = notify_die(DIE_OOPS, str, regs, 0, regs->scause, SIGSEGV);
+
+ bust_spinlocks(0);
+ add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
+ spin_unlock_irq(&die_lock);
+ oops_exit();
+
+ if (in_interrupt())
+ panic("Fatal exception in interrupt");
+ if (panic_on_oops)
+ panic("Fatal exception");
+ if (ret != NOTIFY_STOP)
+ do_exit(SIGSEGV);
+}
+
+static inline void do_trap_siginfo(int signo, int code,
+ unsigned long addr, struct task_struct *tsk)
+{
+ siginfo_t info;
+
+ info.si_signo = signo;
+ info.si_errno = 0;
+ info.si_code = code;
+ info.si_addr = (void __user *)addr;
+ force_sig_info(signo, &info, tsk);
+}
+
+void do_trap(struct pt_regs *regs, int signo, int code,
+ unsigned long addr, struct task_struct *tsk)
+{
+ if (show_unhandled_signals && unhandled_signal(tsk, signo)
+ && printk_ratelimit()) {
+ pr_info("%s[%d]: unhandled signal %d code 0x%x at 0x" REG_FMT,
+ tsk->comm, task_pid_nr(tsk), signo, code, addr);
+ print_vma_addr(KERN_CONT " in ", GET_IP(regs));
+ pr_cont("\n");
+ show_regs(regs);
+ }
+
+ do_trap_siginfo(signo, code, addr, tsk);
+}
+
+static void do_trap_error(struct pt_regs *regs, int signo, int code,
+ unsigned long addr, const char *str)
+{
+ if (user_mode(regs)) {
+ do_trap(regs, signo, code, addr, current);
+ } else {
+ if (!fixup_exception(regs))
+ die(regs, str);
+ }
+}
+
+#define DO_ERROR_INFO(name, signo, code, str) \
+asmlinkage void name(struct pt_regs *regs) \
+{ \
+ do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \
+}
+
+DO_ERROR_INFO(do_trap_unknown,
+ SIGILL, ILL_ILLTRP, "unknown exception");
+DO_ERROR_INFO(do_trap_insn_misaligned,
+ SIGBUS, BUS_ADRALN, "instruction address misaligned");
+DO_ERROR_INFO(do_trap_insn_fault,
+ SIGBUS, BUS_ADRALN, "instruction access fault");
+DO_ERROR_INFO(do_trap_insn_illegal,
+ SIGILL, ILL_ILLOPC, "illegal instruction");
+DO_ERROR_INFO(do_trap_load_misaligned,
+ SIGBUS, BUS_ADRALN, "load address misaligned");
+DO_ERROR_INFO(do_trap_load_fault,
+ SIGSEGV, SEGV_ACCERR, "load access fault");
+DO_ERROR_INFO(do_trap_store_misaligned,
+ SIGBUS, BUS_ADRALN, "store (or AMO) address misaligned");
+DO_ERROR_INFO(do_trap_store_fault,
+ SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
+DO_ERROR_INFO(do_trap_ecall_u,
+ SIGILL, ILL_ILLTRP, "environment call from U-mode");
+DO_ERROR_INFO(do_trap_ecall_s,
+ SIGILL, ILL_ILLTRP, "environment call from S-mode");
+DO_ERROR_INFO(do_trap_ecall_m,
+ SIGILL, ILL_ILLTRP, "environment call from M-mode");
+
+asmlinkage void do_trap_break(struct pt_regs *regs)
+{
+#ifdef CONFIG_GENERIC_BUG
+ if (!user_mode(regs)) {
+ enum bug_trap_type type;
+
+ type = report_bug(regs->sepc, regs);
+ switch (type) {
+ case BUG_TRAP_TYPE_NONE:
+ break;
+ case BUG_TRAP_TYPE_WARN:
+ regs->sepc += sizeof(bug_insn_t);
+ return;
+ case BUG_TRAP_TYPE_BUG:
+ die(regs, "Kernel BUG");
+ }
+ }
+#endif /* CONFIG_GENERIC_BUG */
+
+ do_trap_siginfo(SIGTRAP, TRAP_BRKPT, regs->sepc, current);
+ regs->sepc += 0x4;
+}
+
+#ifdef CONFIG_GENERIC_BUG
+int is_valid_bugaddr(unsigned long pc)
+{
+ bug_insn_t insn;
+
+ if (pc < PAGE_OFFSET)
+ return 0;
+ if (probe_kernel_address((bug_insn_t __user *)pc, insn))
+ return 0;
+ return (insn == __BUG_INSN);
+}
+#endif /* CONFIG_GENERIC_BUG */
+
+void __init trap_init(void)
+{
+ int hart = smp_processor_id();
+
+ /*
+ * Set sup0 scratch register to 0, indicating to exception vector
+ * that we are presently executing in the kernel
+ */
+ csr_write(sscratch, 0);
+ /* Set the exception vector address */
+ csr_write(stvec, &handle_exception);
+ /* Enable software interrupts and setup initial mask */
+ csr_write(sie,
+ SIE_SSIE | atomic_long_read(&per_cpu(riscv_early_sie, hart))
+ );
+}
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
new file mode 100644
index 000000000000..e8a178df8144
--- /dev/null
+++ b/arch/riscv/kernel/vdso.c
@@ -0,0 +1,125 @@
+/*
+ * Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
+ * <benh@kernel.crashing.org>
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/binfmts.h>
+#include <linux/err.h>
+
+#include <asm/vdso.h>
+
+extern char vdso_start[], vdso_end[];
+
+static unsigned int vdso_pages;
+static struct page **vdso_pagelist;
+
+/*
+ * The vDSO data page.
+ */
+static union {
+ struct vdso_data data;
+ u8 page[PAGE_SIZE];
+} vdso_data_store __page_aligned_data;
+struct vdso_data *vdso_data = &vdso_data_store.data;
+
+static int __init vdso_init(void)
+{
+ unsigned int i;
+
+ vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
+ vdso_pagelist =
+ kcalloc(vdso_pages + 1, sizeof(struct page *), GFP_KERNEL);
+ if (unlikely(vdso_pagelist == NULL)) {
+ pr_err("vdso: pagelist allocation failed\n");
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < vdso_pages; i++) {
+ struct page *pg;
+
+ pg = virt_to_page(vdso_start + (i << PAGE_SHIFT));
+ ClearPageReserved(pg);
+ vdso_pagelist[i] = pg;
+ }
+ vdso_pagelist[i] = virt_to_page(vdso_data);
+
+ return 0;
+}
+arch_initcall(vdso_init);
+
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp)
+{
+ struct mm_struct *mm = current->mm;
+ unsigned long vdso_base, vdso_len;
+ int ret;
+
+ vdso_len = (vdso_pages + 1) << PAGE_SHIFT;
+
+ down_write(&mm->mmap_sem);
+ vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0);
+ if (unlikely(IS_ERR_VALUE(vdso_base))) {
+ ret = vdso_base;
+ goto end;
+ }
+
+ /*
+ * Put vDSO base into mm struct. We need to do this before calling
+ * install_special_mapping or the perf counter mmap tracking code
+ * will fail to recognise it as a vDSO (since arch_vma_name fails).
+ */
+ mm->context.vdso = (void *)vdso_base;
+
+ ret = install_special_mapping(mm, vdso_base, vdso_len,
+ (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
+ vdso_pagelist);
+
+ if (unlikely(ret))
+ mm->context.vdso = NULL;
+
+end:
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+
+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]";
+ return NULL;
+}
+
+/*
+ * Function stubs to prevent linker errors when AT_SYSINFO_EHDR is defined
+ */
+
+int in_gate_area_no_mm(unsigned long addr)
+{
+ return 0;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
+{
+ return 0;
+}
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+ return NULL;
+}
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
new file mode 100644
index 000000000000..9f4bee5e51fd
--- /dev/null
+++ b/arch/riscv/mm/init.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/init.h>
+#include <linux/mm.h>
+#include <linux/bootmem.h>
+#include <linux/initrd.h>
+#include <linux/memblock.h>
+#include <linux/swap.h>
+
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/pgtable.h>
+#include <asm/io.h>
+
+static void __init zone_sizes_init(void)
+{
+ unsigned long zones_size[MAX_NR_ZONES];
+
+ memset(zones_size, 0, sizeof(zones_size));
+ zones_size[ZONE_NORMAL] = max_mapnr;
+ free_area_init_node(0, zones_size, pfn_base, NULL);
+}
+
+void setup_zero_page(void)
+{
+ memset((void *)empty_zero_page, 0, PAGE_SIZE);
+}
+
+void __init paging_init(void)
+{
+ init_mm.pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr));
+
+ setup_zero_page();
+ local_flush_tlb_all();
+ zone_sizes_init();
+}
+
+void __init mem_init(void)
+{
+#ifdef CONFIG_FLATMEM
+ BUG_ON(!mem_map);
+#endif /* CONFIG_FLATMEM */
+
+ high_memory = (void *)(__va(PFN_PHYS(max_low_pfn)));
+ free_all_bootmem();
+
+ mem_init_print_info(NULL);
+}
+
+void free_initmem(void)
+{
+ free_initmem_default(0);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+}
+#endif /* CONFIG_BLK_DEV_INITRD */
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 1/9] RISC-V: Init and Halt Code
2017-07-04 19:50 ` Palmer Dabbelt
@ 2017-07-04 19:50 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This contains the various __init C functions, the initial assembly
kernel entry point, and the code to reset the system. When a file was
init-related, it contains
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/bug.h | 88 +++++++++++++++
arch/riscv/include/asm/cache.h | 22 ++++
arch/riscv/include/asm/smp.h | 41 +++++++
arch/riscv/kernel/cacheinfo.c | 105 ++++++++++++++++++
arch/riscv/kernel/cpu.c | 89 +++++++++++++++
arch/riscv/kernel/head.S | 152 +++++++++++++++++++++++++
arch/riscv/kernel/irq.c | 20 ++++
arch/riscv/kernel/reset.c | 36 ++++++
arch/riscv/kernel/setup.c | 246 +++++++++++++++++++++++++++++++++++++++++
arch/riscv/kernel/smp.c | 110 ++++++++++++++++++
arch/riscv/kernel/smpboot.c | 114 +++++++++++++++++++
arch/riscv/kernel/time.c | 61 ++++++++++
arch/riscv/kernel/traps.c | 184 ++++++++++++++++++++++++++++++
arch/riscv/kernel/vdso.c | 125 +++++++++++++++++++++
arch/riscv/mm/init.c | 70 ++++++++++++
15 files changed, 1463 insertions(+)
create mode 100644 arch/riscv/include/asm/bug.h
create mode 100644 arch/riscv/include/asm/cache.h
create mode 100644 arch/riscv/include/asm/smp.h
create mode 100644 arch/riscv/kernel/cacheinfo.c
create mode 100644 arch/riscv/kernel/cpu.c
create mode 100644 arch/riscv/kernel/head.S
create mode 100644 arch/riscv/kernel/irq.c
create mode 100644 arch/riscv/kernel/reset.c
create mode 100644 arch/riscv/kernel/setup.c
create mode 100644 arch/riscv/kernel/smp.c
create mode 100644 arch/riscv/kernel/smpboot.c
create mode 100644 arch/riscv/kernel/time.c
create mode 100644 arch/riscv/kernel/traps.c
create mode 100644 arch/riscv/kernel/vdso.c
create mode 100644 arch/riscv/mm/init.c
diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h
new file mode 100644
index 000000000000..e2f690c20729
--- /dev/null
+++ b/arch/riscv/include/asm/bug.h
@@ -0,0 +1,88 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_BUG_H
+#define _ASM_RISCV_BUG_H
+
+#include <linux/compiler.h>
+#include <linux/const.h>
+#include <linux/types.h>
+
+#include <asm/asm.h>
+
+#ifdef CONFIG_GENERIC_BUG
+#define __BUG_INSN _AC(0x00100073, UL) /* sbreak */
+
+#ifndef __ASSEMBLY__
+typedef u32 bug_insn_t;
+
+#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+#define __BUG_ENTRY_ADDR INT " 1b - 2b"
+#define __BUG_ENTRY_FILE INT " %0 - 2b"
+#else
+#define __BUG_ENTRY_ADDR RISCV_PTR " 1b"
+#define __BUG_ENTRY_FILE RISCV_PTR " %0"
+#endif
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define __BUG_ENTRY \
+ __BUG_ENTRY_ADDR "\n\t" \
+ __BUG_ENTRY_FILE "\n\t" \
+ SHORT " %1"
+#else
+#define __BUG_ENTRY \
+ __BUG_ENTRY_ADDR
+#endif
+
+#define BUG() \
+do { \
+ __asm__ __volatile__ ( \
+ "1:\n\t" \
+ "sbreak\n" \
+ ".pushsection __bug_table,\"a\"\n\t" \
+ "2:\n\t" \
+ __BUG_ENTRY "\n\t" \
+ ".org 2b + %2\n\t" \
+ ".popsection" \
+ : \
+ : "i" (__FILE__), "i" (__LINE__), \
+ "i" (sizeof(struct bug_entry))); \
+ unreachable(); \
+} while (0)
+#endif /* !__ASSEMBLY__ */
+#else /* CONFIG_GENERIC_BUG */
+#ifndef __ASSEMBLY__
+#define BUG() \
+do { \
+ __asm__ __volatile__ ("sbreak\n"); \
+ unreachable(); \
+} while (0)
+#endif /* !__ASSEMBLY__ */
+#endif /* CONFIG_GENERIC_BUG */
+
+#define HAVE_ARCH_BUG
+
+#include <asm-generic/bug.h>
+
+#ifndef __ASSEMBLY__
+
+struct pt_regs;
+struct task_struct;
+
+extern void die(struct pt_regs *regs, const char *str);
+extern void do_trap(struct pt_regs *regs, int signo, int code,
+ unsigned long addr, struct task_struct *tsk);
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_BUG_H */
diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
new file mode 100644
index 000000000000..e8f0d1110d74
--- /dev/null
+++ b/arch/riscv/include/asm/cache.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2017 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_CACHE_H
+#define _ASM_RISCV_CACHE_H
+
+#define L1_CACHE_SHIFT 6
+
+#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
+
+#endif /* _ASM_RISCV_CACHE_H */
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
new file mode 100644
index 000000000000..f61f8c25f95b
--- /dev/null
+++ b/arch/riscv/include/asm/smp.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SMP_H
+#define _ASM_RISCV_SMP_H
+
+#include <linux/cpumask.h>
+#include <linux/irqreturn.h>
+
+#ifdef CONFIG_SMP
+
+/* SMP initialization hook for setup_arch */
+void __init init_clockevent(void);
+
+/* SMP initialization hook for setup_arch */
+void __init setup_smp(void);
+
+/* Hook for the generic smp_call_function_many() routine. */
+void arch_send_call_function_ipi_mask(struct cpumask *mask);
+
+/* Hook for the generic smp_call_function_single() routine. */
+void arch_send_call_function_single_ipi(int cpu);
+
+#define raw_smp_processor_id() (current_thread_info()->cpu)
+
+/* Interprocessor interrupt handler */
+irqreturn_t handle_ipi(void);
+
+#endif /* CONFIG_SMP */
+
+#endif /* _ASM_RISCV_SMP_H */
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
new file mode 100644
index 000000000000..10ed2749e246
--- /dev/null
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -0,0 +1,105 @@
+/*
+ * 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/cacheinfo.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+static void ci_leaf_init(struct cacheinfo *this_leaf,
+ struct device_node *node,
+ enum cache_type type, unsigned int level)
+{
+ this_leaf->of_node = node;
+ 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)
+{
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct device_node *np = of_cpu_device_node_get(cpu);
+ int levels = 0, leaves = 0, level;
+
+ if (of_property_read_bool(np, "cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "i-cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "d-cache-size"))
+ ++leaves;
+ if (leaves > 0)
+ levels = 1;
+
+ while ((np = of_find_next_cache_node(np))) {
+ if (!of_device_is_compatible(np, "cache"))
+ break;
+ if (of_property_read_u32(np, "cache-level", &level))
+ break;
+ if (level <= levels)
+ break;
+ if (of_property_read_bool(np, "cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "i-cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "d-cache-size"))
+ ++leaves;
+ levels = level;
+ }
+
+ this_cpu_ci->num_levels = levels;
+ this_cpu_ci->num_leaves = leaves;
+ return 0;
+}
+
+static int __populate_cache_leaves(unsigned int cpu)
+{
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+ struct device_node *np = of_cpu_device_node_get(cpu);
+ int levels = 1, level = 1;
+
+ if (of_property_read_bool(np, "cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level);
+ if (of_property_read_bool(np, "i-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level);
+ if (of_property_read_bool(np, "d-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level);
+
+ while ((np = of_find_next_cache_node(np))) {
+ if (!of_device_is_compatible(np, "cache"))
+ break;
+ if (of_property_read_u32(np, "cache-level", &level))
+ break;
+ if (level <= levels)
+ break;
+ if (of_property_read_bool(np, "cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level);
+ if (of_property_read_bool(np, "i-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level);
+ if (of_property_read_bool(np, "d-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level);
+ levels = level;
+ }
+
+ return 0;
+}
+
+DEFINE_SMP_CALL_CACHE_FUNCTION(init_cache_level)
+DEFINE_SMP_CALL_CACHE_FUNCTION(populate_cache_leaves)
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
new file mode 100644
index 000000000000..20004bd7a216
--- /dev/null
+++ b/arch/riscv/kernel/cpu.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/init.h>
+#include <linux/seq_file.h>
+#include <linux/of.h>
+
+/* Return -1 if not a valid hart */
+int riscv_of_processor_hart(struct device_node *node)
+{
+ const char *isa, *status;
+ u32 hart;
+
+ if (!of_device_is_compatible(node, "riscv"))
+ return -(ENODEV);
+ if (of_property_read_u32(node, "reg", &hart)
+ || hart >= NR_CPUS)
+ return -(ENODEV);
+ if (of_property_read_string(node, "status", &status)
+ || strcmp(status, "okay"))
+ return -(ENODEV);
+ if (of_property_read_string(node, "riscv,isa", &isa)
+ || isa[0] != 'r'
+ || isa[1] != 'v')
+ return -(ENODEV);
+
+ return hart;
+}
+
+#ifdef CONFIG_PROC_FS
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+ *pos = cpumask_next(*pos - 1, cpu_online_mask);
+ if ((*pos) < nr_cpu_ids)
+ return (void *)(uintptr_t)(1 + *pos);
+ return NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ (*pos)++;
+ return c_start(m, pos);
+}
+
+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);
+ 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);
+ if (!of_property_read_string(node, "compatible", &compat)
+ && strcmp(compat, "riscv"))
+ seq_printf(m, "uarch\t: %s\n", compat);
+ seq_puts(m, "\n");
+
+ return 0;
+}
+
+const struct seq_operations cpuinfo_op = {
+ .start = c_start,
+ .next = c_next,
+ .stop = c_stop,
+ .show = c_show
+};
+
+#endif /* CONFIG_PROC_FS */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
new file mode 100644
index 000000000000..504c368238c2
--- /dev/null
+++ b/arch/riscv/kernel/head.S
@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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 <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm/asm.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/csr.h>
+
+__INIT
+ENTRY(_start)
+ /* Mask all interrupts */
+ csrw sie, zero
+
+ /*
+ * Disable FPU to detect illegal usage of
+ * floating point in kernel space
+ */
+ li t0, SR_FS
+ csrc sstatus, t0
+
+#ifndef CONFIG_RV_PUM
+ /* Allow access to user memory */
+ li t0, SR_SUM
+ csrs sstatus, t0
+#endif
+
+#ifdef CONFIG_ISA_A
+ /* Pick one hart to run the main boot sequence */
+ la a3, hart_lottery
+ li a2, 1
+ amoadd.w a3, a2, (a3)
+ bnez a3, .Lsecondary_start
+#else
+ /*
+ * We don't have atomic support, so the boot hart must be picked
+ * staticly. Hart 0 is the only sane choice.
+ */
+ bnez a0, .Lsecondary_park
+#endif
+
+ /* Save hart ID and DTB physical address */
+ mv s0, a0
+ mv s1, a1
+
+ /* Initialize page tables and relocate to virtual addresses */
+ la sp, init_thread_union + THREAD_SIZE
+ call setup_vm
+ call relocate
+
+ /* Restore C environment */
+ la tp, init_task
+
+ la sp, init_thread_union
+ li a0, ASM_THREAD_SIZE
+ add sp, sp, a0
+
+ /* Start the kernel */
+ mv a0, s0
+ mv a1, s1
+ call sbi_save
+ tail start_kernel
+
+relocate:
+ /* Relocate return address */
+ li a1, PAGE_OFFSET
+ la a0, _start
+ sub a1, a1, a0
+ add ra, ra, a1
+
+ /* Point stvec to virtual address of intruction after sptbr write */
+ la a0, 1f
+ add a0, a0, a1
+ csrw stvec, a0
+
+ /* Compute sptbr for kernel page tables, but don't load it yet */
+ la a2, swapper_pg_dir
+ srl a2, a2, PAGE_SHIFT
+ li a1, SPTBR_MODE
+ or a2, a2, a1
+
+ /*
+ * Load trampoline page directory, which will cause us to trap to
+ * stvec if VA != PA, or simply fall through if VA == PA
+ */
+ la a0, trampoline_pg_dir
+ srl a0, a0, PAGE_SHIFT
+ or a0, a0, a1
+ sfence.vma
+ csrw sptbr, a0
+1:
+ /* Set trap vector to spin forever to help debug */
+ la a0, .Lsecondary_park
+ csrw stvec, a0
+
+ /* Load the global pointer */
+ la gp, __global_pointer$
+
+ /* Switch to kernel page tables */
+ csrw sptbr, a2
+
+ ret
+
+.Lsecondary_start:
+#ifdef CONFIG_SMP
+ li a1, CONFIG_NR_CPUS
+ bgeu a0, a1, .Lsecondary_park
+
+ la a1, __cpu_up_stack_pointer
+ slli a0, a0, LGREG
+ add a0, a0, a1
+
+.Lwait_for_cpu_up:
+ REG_L sp, (a0)
+ beqz sp, .Lwait_for_cpu_up
+ fence
+
+ /* Enable virtual memory and relocate to virtual address */
+ call relocate
+
+ /* Initialize task_struct pointer */
+ li tp, -THREAD_SIZE
+ add tp, tp, sp
+
+ tail smp_callin
+#endif
+
+.Lsecondary_park:
+ /* We lack SMP support or have too many harts, so park this hart */
+ wfi
+ j .Lsecondary_park
+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/irq.c b/arch/riscv/kernel/irq.c
new file mode 100644
index 000000000000..737d7cce2c6d
--- /dev/null
+++ b/arch/riscv/kernel/irq.c
@@ -0,0 +1,20 @@
+/*
+ * 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/irqchip.h>
+
+void __init init_IRQ(void)
+{
+ irqchip_init();
+}
diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c
new file mode 100644
index 000000000000..2a53d26ffdd6
--- /dev/null
+++ b/arch/riscv/kernel/reset.c
@@ -0,0 +1,36 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/reboot.h>
+#include <linux/export.h>
+#include <asm/sbi.h>
+
+void (*pm_power_off)(void) = machine_power_off;
+EXPORT_SYMBOL(pm_power_off);
+
+void machine_restart(char *cmd)
+{
+ do_kernel_restart(cmd);
+ while (1);
+}
+
+void machine_halt(void)
+{
+ machine_power_off();
+}
+
+void machine_power_off(void)
+{
+ sbi_shutdown();
+ while (1);
+}
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
new file mode 100644
index 000000000000..319fad96f537
--- /dev/null
+++ b/arch/riscv/kernel/setup.c
@@ -0,0 +1,246 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/sched.h>
+#include <linux/initrd.h>
+#include <linux/console.h>
+#include <linux/screen_info.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/sched/task.h>
+
+#include <asm/setup.h>
+#include <asm/sections.h>
+#include <asm/pgtable.h>
+#include <asm/smp.h>
+#include <asm/sbi.h>
+#include <asm/tlbflush.h>
+#include <asm/thread_info.h>
+
+#ifdef CONFIG_DUMMY_CONSOLE
+struct screen_info screen_info = {
+ .orig_video_lines = 30,
+ .orig_video_cols = 80,
+ .orig_video_mode = 0,
+ .orig_video_ega_bx = 0,
+ .orig_video_isVGA = 1,
+ .orig_video_points = 8
+};
+#endif
+
+#ifdef CONFIG_CMDLINE_BOOL
+static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
+#endif /* CONFIG_CMDLINE_BOOL */
+
+unsigned long va_pa_offset;
+unsigned long pfn_base;
+
+/* The lucky hart to first increment this variable will boot the other cores */
+atomic_t hart_lottery;
+
+#ifdef CONFIG_BLK_DEV_INITRD
+static void __init setup_initrd(void)
+{
+ extern char __initramfs_start[];
+ extern unsigned long __initramfs_size;
+ unsigned long size;
+
+ if (__initramfs_size > 0) {
+ initrd_start = (unsigned long)(&__initramfs_start);
+ initrd_end = initrd_start + __initramfs_size;
+ }
+
+ if (initrd_start >= initrd_end) {
+ printk(KERN_INFO "initrd not found or empty");
+ goto disable;
+ }
+ if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) {
+ printk(KERN_ERR "initrd extends beyond end of memory");
+ goto disable;
+ }
+
+ size = initrd_end - initrd_start;
+ memblock_reserve(__pa(initrd_start), size);
+ initrd_below_start_ok = 1;
+
+ printk(KERN_INFO "Initial ramdisk at: 0x%p (%lu bytes)\n",
+ (void *)(initrd_start), size);
+ return;
+disable:
+ pr_cont(" - disabling initrd\n");
+ initrd_start = 0;
+ initrd_end = 0;
+}
+#endif /* CONFIG_BLK_DEV_INITRD */
+
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
+pgd_t trampoline_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+
+#ifndef __PAGETABLE_PMD_FOLDED
+#define NUM_SWAPPER_PMDS ((uintptr_t)-PAGE_OFFSET >> PGDIR_SHIFT)
+pmd_t swapper_pmd[PTRS_PER_PMD*((-PAGE_OFFSET)/PGDIR_SIZE)] __page_aligned_bss;
+pmd_t trampoline_pmd[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+#endif
+
+asmlinkage void __init setup_vm(void)
+{
+ extern char _start;
+ uintptr_t i;
+ uintptr_t pa = (uintptr_t) &_start;
+ pgprot_t prot = __pgprot(pgprot_val(PAGE_KERNEL) | _PAGE_EXEC);
+
+ va_pa_offset = PAGE_OFFSET - pa;
+ pfn_base = PFN_DOWN(pa);
+
+ /* Sanity check alignment and size */
+ BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
+ BUG_ON((pa % (PAGE_SIZE * PTRS_PER_PTE)) != 0);
+
+#ifndef __PAGETABLE_PMD_FOLDED
+ trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
+ pfn_pgd(PFN_DOWN((uintptr_t)trampoline_pmd),
+ __pgprot(_PAGE_TABLE));
+ trampoline_pmd[0] = pfn_pmd(PFN_DOWN(pa), prot);
+
+ for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
+ size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
+ swapper_pg_dir[o] =
+ pfn_pgd(PFN_DOWN((uintptr_t)swapper_pmd) + i,
+ __pgprot(_PAGE_TABLE));
+ }
+ for (i = 0; i < ARRAY_SIZE(swapper_pmd); i++)
+ swapper_pmd[i] = pfn_pmd(PFN_DOWN(pa + i * PMD_SIZE), prot);
+#else
+ trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
+ pfn_pgd(PFN_DOWN(pa), prot);
+
+ for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
+ size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
+ swapper_pg_dir[o] =
+ pfn_pgd(PFN_DOWN(pa + i * PGDIR_SIZE), prot);
+ }
+#endif
+}
+
+void __init sbi_save(unsigned int hartid, void *dtb)
+{
+ early_init_dt_scan(__va(dtb));
+}
+
+/*
+ * Allow the user to manually add a memory region (in case DTS is broken);
+ * "mem_end=nn[KkMmGg]"
+ */
+static int __init mem_end_override(char *p)
+{
+ resource_size_t base, end;
+
+ if (!p)
+ return -EINVAL;
+ base = (uintptr_t) __pa(PAGE_OFFSET);
+ end = memparse(p, &p) & PMD_MASK;
+ if (end == 0)
+ return -EINVAL;
+ memblock_add(base, end - base);
+ return 0;
+}
+early_param("mem_end", mem_end_override);
+
+static void __init setup_bootmem(void)
+{
+ struct memblock_region *reg;
+ phys_addr_t mem_size = 0;
+
+ /* Find the memory region containing the kernel */
+ for_each_memblock(memory, reg) {
+ phys_addr_t vmlinux_end = __pa(_end);
+ phys_addr_t end = reg->base + reg->size;
+
+ if (reg->base <= vmlinux_end && vmlinux_end <= end) {
+ /*
+ * Reserve from the start of the region to the end of
+ * the kernel
+ */
+ memblock_reserve(reg->base, vmlinux_end - reg->base);
+ mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
+ }
+ }
+ BUG_ON(mem_size == 0);
+
+ set_max_mapnr(PFN_DOWN(mem_size));
+ max_low_pfn = pfn_base + PFN_DOWN(mem_size);
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ setup_initrd();
+#endif /* CONFIG_BLK_DEV_INITRD */
+
+ early_init_fdt_reserve_self();
+ early_init_fdt_scan_reserved_mem();
+ memblock_allow_resize();
+ memblock_dump_all();
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+ strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+ if (builtin_cmdline[0] != '\0') {
+ /* Append bootloader command line to built-in */
+ strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
+ strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+ strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+ }
+#endif /* CONFIG_CMDLINE_OVERRIDE */
+#endif /* CONFIG_CMDLINE_BOOL */
+ *cmdline_p = boot_command_line;
+
+ parse_early_param();
+
+ init_mm.start_code = (unsigned long) _stext;
+ init_mm.end_code = (unsigned long) _etext;
+ init_mm.end_data = (unsigned long) _edata;
+ init_mm.brk = (unsigned long) _end;
+
+ setup_bootmem();
+ paging_init();
+ unflatten_device_tree();
+
+#ifdef CONFIG_SMP
+ setup_smp();
+#endif
+
+#ifdef CONFIG_DUMMY_CONSOLE
+ conswitchp = &dummy_con;
+#endif
+
+ riscv_fill_hwcap();
+}
+
+static int __init riscv_device_init(void)
+{
+ return of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+}
+subsys_initcall_sync(riscv_device_init);
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
new file mode 100644
index 000000000000..b4a71ec5906f
--- /dev/null
+++ b/arch/riscv/kernel/smp.c
@@ -0,0 +1,110 @@
+/*
+ * SMP initialisation and IPI support
+ * Based on arch/arm64/kernel/smp.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+#include <linux/sched.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
+};
+
+irqreturn_t handle_ipi(void)
+{
+ unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
+
+ /* Clear pending IPI */
+ csr_clear(sip, SIE_SSIE);
+
+ while (true) {
+ unsigned long ops;
+
+ /* Order bit clearing and data access. */
+ mb();
+
+ ops = xchg(pending_ipis, 0);
+ if (ops == 0)
+ return IRQ_HANDLED;
+
+ if (ops & (1 << IPI_RESCHEDULE))
+ scheduler_ipi();
+
+ if (ops & (1 << IPI_CALL_FUNC))
+ generic_smp_call_function_interrupt();
+
+ BUG_ON((ops >> IPI_MAX) != 0);
+
+ /* Order data access and bit testing. */
+ mb();
+ }
+
+ return IRQ_HANDLED;
+}
+
+static void
+send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
+{
+ int i;
+
+ mb();
+ for_each_cpu(i, to_whom)
+ set_bit(operation, &ipi_data[i].bits);
+
+ mb();
+ sbi_send_ipi(cpumask_bits(to_whom));
+}
+
+void arch_send_call_function_ipi_mask(struct cpumask *mask)
+{
+ send_ipi_message(mask, IPI_CALL_FUNC);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+ send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
+}
+
+static void ipi_stop(void *unused)
+{
+ while (1)
+ wait_for_interrupt();
+}
+
+void smp_send_stop(void)
+{
+ on_each_cpu(ipi_stop, NULL, 1);
+}
+
+void smp_send_reschedule(int cpu)
+{
+ send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
+}
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
new file mode 100644
index 000000000000..e5c7f1aafda9
--- /dev/null
+++ b/arch/riscv/kernel/smpboot.c
@@ -0,0 +1,114 @@
+/*
+ * SMP initialisation and IPI support
+ * Based on arch/arm64/kernel/smp.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/kernel_stat.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/percpu.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/sched/task_stack.h>
+#include <asm/irq.h>
+#include <asm/mmu_context.h>
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/sbi.h>
+
+void *__cpu_up_stack_pointer[NR_CPUS];
+
+void __init smp_prepare_boot_cpu(void)
+{
+}
+
+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;
+
+ 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;
+ }
+ }
+ }
+
+ BUG_ON(!im_okay_therefore_i_am);
+}
+
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+ /* Signal cpu to start */
+ mb();
+ __cpu_up_stack_pointer[cpu] = task_stack_page(tidle) + THREAD_SIZE;
+
+ while (!cpu_online(cpu))
+ cpu_relax();
+
+ return 0;
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+/*
+ * C entry point for a secondary processor.
+ */
+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);
+ current->active_mm = mm;
+
+ trap_init();
+ init_clockevent();
+ notify_cpu_starting(smp_processor_id());
+ set_cpu_online(smp_processor_id(), 1);
+
+ /*
+ * Write SIE again now that this hart is online, to catch any IRQ
+ * enable/disable events that happened between trap_init() and
+ * set_cpu_online().
+ */
+ csr_write(sie,
+ SIE_SSIE | atomic_long_read(&per_cpu(riscv_early_sie, hart))
+ );
+
+ local_flush_tlb_all();
+ local_irq_enable();
+ preempt_disable();
+ cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
new file mode 100644
index 000000000000..6bba2e6f2a84
--- /dev/null
+++ b/arch/riscv/kernel/time.c
@@ -0,0 +1,61 @@
+/*
+ * 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/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/delay.h>
+#include <linux/timer_riscv.h>
+
+#include <asm/sbi.h>
+
+unsigned long riscv_timebase;
+
+static int next_event(unsigned long delta, struct clock_event_device *ce)
+{
+ BUG_ON(ce != timer_riscv_device(smp_processor_id()));
+ sbi_set_timer(get_cycles64() + delta);
+ return 0;
+}
+
+static unsigned long long rdtime(struct clocksource *cs)
+{
+ BUG_ON(cs != timer_riscv_source(smp_processor_id()));
+ return get_cycles64();
+}
+
+void riscv_timer_interrupt(void)
+{
+ int cpu = smp_processor_id();
+ struct clock_event_device *evdev = timer_riscv_device(cpu);
+
+ evdev->event_handler(evdev);
+}
+
+void __init time_init(void)
+{
+ struct device_node *cpu;
+ u32 prop;
+ int cpu_id = smp_processor_id();
+
+ cpu = of_find_node_by_path("/cpus");
+ if (!cpu || of_property_read_u32(cpu, "timebase-frequency", &prop))
+ panic(KERN_WARNING "RISC-V system with no 'timebase-frequency' in DTS\n");
+ riscv_timebase = prop;
+
+ lpj_fine = riscv_timebase / HZ;
+
+ timer_riscv_init(cpu_id, riscv_timebase, &rdtime, &next_event);
+
+ csr_set(sie, SIE_STIE);
+}
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
new file mode 100644
index 000000000000..2175a39bed1c
--- /dev/null
+++ b/arch/riscv/kernel/traps.c
@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/kernel.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
+#include <linux/signal.h>
+#include <linux/kdebug.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/csr.h>
+
+int show_unhandled_signals = 1;
+
+extern asmlinkage void handle_exception(void);
+
+static DEFINE_SPINLOCK(die_lock);
+
+void die(struct pt_regs *regs, const char *str)
+{
+ static int die_counter;
+ int ret;
+
+ oops_enter();
+
+ spin_lock_irq(&die_lock);
+ console_verbose();
+ bust_spinlocks(1);
+
+ pr_emerg("%s [#%d]\n", str, ++die_counter);
+ print_modules();
+ show_regs(regs);
+
+ ret = notify_die(DIE_OOPS, str, regs, 0, regs->scause, SIGSEGV);
+
+ bust_spinlocks(0);
+ add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
+ spin_unlock_irq(&die_lock);
+ oops_exit();
+
+ if (in_interrupt())
+ panic("Fatal exception in interrupt");
+ if (panic_on_oops)
+ panic("Fatal exception");
+ if (ret != NOTIFY_STOP)
+ do_exit(SIGSEGV);
+}
+
+static inline void do_trap_siginfo(int signo, int code,
+ unsigned long addr, struct task_struct *tsk)
+{
+ siginfo_t info;
+
+ info.si_signo = signo;
+ info.si_errno = 0;
+ info.si_code = code;
+ info.si_addr = (void __user *)addr;
+ force_sig_info(signo, &info, tsk);
+}
+
+void do_trap(struct pt_regs *regs, int signo, int code,
+ unsigned long addr, struct task_struct *tsk)
+{
+ if (show_unhandled_signals && unhandled_signal(tsk, signo)
+ && printk_ratelimit()) {
+ pr_info("%s[%d]: unhandled signal %d code 0x%x at 0x" REG_FMT,
+ tsk->comm, task_pid_nr(tsk), signo, code, addr);
+ print_vma_addr(KERN_CONT " in ", GET_IP(regs));
+ pr_cont("\n");
+ show_regs(regs);
+ }
+
+ do_trap_siginfo(signo, code, addr, tsk);
+}
+
+static void do_trap_error(struct pt_regs *regs, int signo, int code,
+ unsigned long addr, const char *str)
+{
+ if (user_mode(regs)) {
+ do_trap(regs, signo, code, addr, current);
+ } else {
+ if (!fixup_exception(regs))
+ die(regs, str);
+ }
+}
+
+#define DO_ERROR_INFO(name, signo, code, str) \
+asmlinkage void name(struct pt_regs *regs) \
+{ \
+ do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \
+}
+
+DO_ERROR_INFO(do_trap_unknown,
+ SIGILL, ILL_ILLTRP, "unknown exception");
+DO_ERROR_INFO(do_trap_insn_misaligned,
+ SIGBUS, BUS_ADRALN, "instruction address misaligned");
+DO_ERROR_INFO(do_trap_insn_fault,
+ SIGBUS, BUS_ADRALN, "instruction access fault");
+DO_ERROR_INFO(do_trap_insn_illegal,
+ SIGILL, ILL_ILLOPC, "illegal instruction");
+DO_ERROR_INFO(do_trap_load_misaligned,
+ SIGBUS, BUS_ADRALN, "load address misaligned");
+DO_ERROR_INFO(do_trap_load_fault,
+ SIGSEGV, SEGV_ACCERR, "load access fault");
+DO_ERROR_INFO(do_trap_store_misaligned,
+ SIGBUS, BUS_ADRALN, "store (or AMO) address misaligned");
+DO_ERROR_INFO(do_trap_store_fault,
+ SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
+DO_ERROR_INFO(do_trap_ecall_u,
+ SIGILL, ILL_ILLTRP, "environment call from U-mode");
+DO_ERROR_INFO(do_trap_ecall_s,
+ SIGILL, ILL_ILLTRP, "environment call from S-mode");
+DO_ERROR_INFO(do_trap_ecall_m,
+ SIGILL, ILL_ILLTRP, "environment call from M-mode");
+
+asmlinkage void do_trap_break(struct pt_regs *regs)
+{
+#ifdef CONFIG_GENERIC_BUG
+ if (!user_mode(regs)) {
+ enum bug_trap_type type;
+
+ type = report_bug(regs->sepc, regs);
+ switch (type) {
+ case BUG_TRAP_TYPE_NONE:
+ break;
+ case BUG_TRAP_TYPE_WARN:
+ regs->sepc += sizeof(bug_insn_t);
+ return;
+ case BUG_TRAP_TYPE_BUG:
+ die(regs, "Kernel BUG");
+ }
+ }
+#endif /* CONFIG_GENERIC_BUG */
+
+ do_trap_siginfo(SIGTRAP, TRAP_BRKPT, regs->sepc, current);
+ regs->sepc += 0x4;
+}
+
+#ifdef CONFIG_GENERIC_BUG
+int is_valid_bugaddr(unsigned long pc)
+{
+ bug_insn_t insn;
+
+ if (pc < PAGE_OFFSET)
+ return 0;
+ if (probe_kernel_address((bug_insn_t __user *)pc, insn))
+ return 0;
+ return (insn == __BUG_INSN);
+}
+#endif /* CONFIG_GENERIC_BUG */
+
+void __init trap_init(void)
+{
+ int hart = smp_processor_id();
+
+ /*
+ * Set sup0 scratch register to 0, indicating to exception vector
+ * that we are presently executing in the kernel
+ */
+ csr_write(sscratch, 0);
+ /* Set the exception vector address */
+ csr_write(stvec, &handle_exception);
+ /* Enable software interrupts and setup initial mask */
+ csr_write(sie,
+ SIE_SSIE | atomic_long_read(&per_cpu(riscv_early_sie, hart))
+ );
+}
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
new file mode 100644
index 000000000000..e8a178df8144
--- /dev/null
+++ b/arch/riscv/kernel/vdso.c
@@ -0,0 +1,125 @@
+/*
+ * Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
+ * <benh@kernel.crashing.org>
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/binfmts.h>
+#include <linux/err.h>
+
+#include <asm/vdso.h>
+
+extern char vdso_start[], vdso_end[];
+
+static unsigned int vdso_pages;
+static struct page **vdso_pagelist;
+
+/*
+ * The vDSO data page.
+ */
+static union {
+ struct vdso_data data;
+ u8 page[PAGE_SIZE];
+} vdso_data_store __page_aligned_data;
+struct vdso_data *vdso_data = &vdso_data_store.data;
+
+static int __init vdso_init(void)
+{
+ unsigned int i;
+
+ vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
+ vdso_pagelist =
+ kcalloc(vdso_pages + 1, sizeof(struct page *), GFP_KERNEL);
+ if (unlikely(vdso_pagelist == NULL)) {
+ pr_err("vdso: pagelist allocation failed\n");
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < vdso_pages; i++) {
+ struct page *pg;
+
+ pg = virt_to_page(vdso_start + (i << PAGE_SHIFT));
+ ClearPageReserved(pg);
+ vdso_pagelist[i] = pg;
+ }
+ vdso_pagelist[i] = virt_to_page(vdso_data);
+
+ return 0;
+}
+arch_initcall(vdso_init);
+
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp)
+{
+ struct mm_struct *mm = current->mm;
+ unsigned long vdso_base, vdso_len;
+ int ret;
+
+ vdso_len = (vdso_pages + 1) << PAGE_SHIFT;
+
+ down_write(&mm->mmap_sem);
+ vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0);
+ if (unlikely(IS_ERR_VALUE(vdso_base))) {
+ ret = vdso_base;
+ goto end;
+ }
+
+ /*
+ * Put vDSO base into mm struct. We need to do this before calling
+ * install_special_mapping or the perf counter mmap tracking code
+ * will fail to recognise it as a vDSO (since arch_vma_name fails).
+ */
+ mm->context.vdso = (void *)vdso_base;
+
+ ret = install_special_mapping(mm, vdso_base, vdso_len,
+ (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
+ vdso_pagelist);
+
+ if (unlikely(ret))
+ mm->context.vdso = NULL;
+
+end:
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+
+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]";
+ return NULL;
+}
+
+/*
+ * Function stubs to prevent linker errors when AT_SYSINFO_EHDR is defined
+ */
+
+int in_gate_area_no_mm(unsigned long addr)
+{
+ return 0;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
+{
+ return 0;
+}
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+ return NULL;
+}
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
new file mode 100644
index 000000000000..9f4bee5e51fd
--- /dev/null
+++ b/arch/riscv/mm/init.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/init.h>
+#include <linux/mm.h>
+#include <linux/bootmem.h>
+#include <linux/initrd.h>
+#include <linux/memblock.h>
+#include <linux/swap.h>
+
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/pgtable.h>
+#include <asm/io.h>
+
+static void __init zone_sizes_init(void)
+{
+ unsigned long zones_size[MAX_NR_ZONES];
+
+ memset(zones_size, 0, sizeof(zones_size));
+ zones_size[ZONE_NORMAL] = max_mapnr;
+ free_area_init_node(0, zones_size, pfn_base, NULL);
+}
+
+void setup_zero_page(void)
+{
+ memset((void *)empty_zero_page, 0, PAGE_SIZE);
+}
+
+void __init paging_init(void)
+{
+ init_mm.pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr));
+
+ setup_zero_page();
+ local_flush_tlb_all();
+ zone_sizes_init();
+}
+
+void __init mem_init(void)
+{
+#ifdef CONFIG_FLATMEM
+ BUG_ON(!mem_map);
+#endif /* CONFIG_FLATMEM */
+
+ high_memory = (void *)(__va(PFN_PHYS(max_low_pfn)));
+ free_all_bootmem();
+
+ mem_init_print_info(NULL);
+}
+
+void free_initmem(void)
+{
+ free_initmem_default(0);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+}
+#endif /* CONFIG_BLK_DEV_INITRD */
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 1/9] RISC-V: Init and Halt Code
@ 2017-07-04 19:50 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This contains the various __init C functions, the initial assembly
kernel entry point, and the code to reset the system. When a file was
init-related, it contains
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/bug.h | 88 +++++++++++++++
arch/riscv/include/asm/cache.h | 22 ++++
arch/riscv/include/asm/smp.h | 41 +++++++
arch/riscv/kernel/cacheinfo.c | 105 ++++++++++++++++++
arch/riscv/kernel/cpu.c | 89 +++++++++++++++
arch/riscv/kernel/head.S | 152 +++++++++++++++++++++++++
arch/riscv/kernel/irq.c | 20 ++++
arch/riscv/kernel/reset.c | 36 ++++++
arch/riscv/kernel/setup.c | 246 +++++++++++++++++++++++++++++++++++++++++
arch/riscv/kernel/smp.c | 110 ++++++++++++++++++
arch/riscv/kernel/smpboot.c | 114 +++++++++++++++++++
arch/riscv/kernel/time.c | 61 ++++++++++
arch/riscv/kernel/traps.c | 184 ++++++++++++++++++++++++++++++
arch/riscv/kernel/vdso.c | 125 +++++++++++++++++++++
arch/riscv/mm/init.c | 70 ++++++++++++
15 files changed, 1463 insertions(+)
create mode 100644 arch/riscv/include/asm/bug.h
create mode 100644 arch/riscv/include/asm/cache.h
create mode 100644 arch/riscv/include/asm/smp.h
create mode 100644 arch/riscv/kernel/cacheinfo.c
create mode 100644 arch/riscv/kernel/cpu.c
create mode 100644 arch/riscv/kernel/head.S
create mode 100644 arch/riscv/kernel/irq.c
create mode 100644 arch/riscv/kernel/reset.c
create mode 100644 arch/riscv/kernel/setup.c
create mode 100644 arch/riscv/kernel/smp.c
create mode 100644 arch/riscv/kernel/smpboot.c
create mode 100644 arch/riscv/kernel/time.c
create mode 100644 arch/riscv/kernel/traps.c
create mode 100644 arch/riscv/kernel/vdso.c
create mode 100644 arch/riscv/mm/init.c
diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h
new file mode 100644
index 000000000000..e2f690c20729
--- /dev/null
+++ b/arch/riscv/include/asm/bug.h
@@ -0,0 +1,88 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_BUG_H
+#define _ASM_RISCV_BUG_H
+
+#include <linux/compiler.h>
+#include <linux/const.h>
+#include <linux/types.h>
+
+#include <asm/asm.h>
+
+#ifdef CONFIG_GENERIC_BUG
+#define __BUG_INSN _AC(0x00100073, UL) /* sbreak */
+
+#ifndef __ASSEMBLY__
+typedef u32 bug_insn_t;
+
+#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+#define __BUG_ENTRY_ADDR INT " 1b - 2b"
+#define __BUG_ENTRY_FILE INT " %0 - 2b"
+#else
+#define __BUG_ENTRY_ADDR RISCV_PTR " 1b"
+#define __BUG_ENTRY_FILE RISCV_PTR " %0"
+#endif
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define __BUG_ENTRY \
+ __BUG_ENTRY_ADDR "\n\t" \
+ __BUG_ENTRY_FILE "\n\t" \
+ SHORT " %1"
+#else
+#define __BUG_ENTRY \
+ __BUG_ENTRY_ADDR
+#endif
+
+#define BUG() \
+do { \
+ __asm__ __volatile__ ( \
+ "1:\n\t" \
+ "sbreak\n" \
+ ".pushsection __bug_table,\"a\"\n\t" \
+ "2:\n\t" \
+ __BUG_ENTRY "\n\t" \
+ ".org 2b + %2\n\t" \
+ ".popsection" \
+ : \
+ : "i" (__FILE__), "i" (__LINE__), \
+ "i" (sizeof(struct bug_entry))); \
+ unreachable(); \
+} while (0)
+#endif /* !__ASSEMBLY__ */
+#else /* CONFIG_GENERIC_BUG */
+#ifndef __ASSEMBLY__
+#define BUG() \
+do { \
+ __asm__ __volatile__ ("sbreak\n"); \
+ unreachable(); \
+} while (0)
+#endif /* !__ASSEMBLY__ */
+#endif /* CONFIG_GENERIC_BUG */
+
+#define HAVE_ARCH_BUG
+
+#include <asm-generic/bug.h>
+
+#ifndef __ASSEMBLY__
+
+struct pt_regs;
+struct task_struct;
+
+extern void die(struct pt_regs *regs, const char *str);
+extern void do_trap(struct pt_regs *regs, int signo, int code,
+ unsigned long addr, struct task_struct *tsk);
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_BUG_H */
diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
new file mode 100644
index 000000000000..e8f0d1110d74
--- /dev/null
+++ b/arch/riscv/include/asm/cache.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2017 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_CACHE_H
+#define _ASM_RISCV_CACHE_H
+
+#define L1_CACHE_SHIFT 6
+
+#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
+
+#endif /* _ASM_RISCV_CACHE_H */
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
new file mode 100644
index 000000000000..f61f8c25f95b
--- /dev/null
+++ b/arch/riscv/include/asm/smp.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SMP_H
+#define _ASM_RISCV_SMP_H
+
+#include <linux/cpumask.h>
+#include <linux/irqreturn.h>
+
+#ifdef CONFIG_SMP
+
+/* SMP initialization hook for setup_arch */
+void __init init_clockevent(void);
+
+/* SMP initialization hook for setup_arch */
+void __init setup_smp(void);
+
+/* Hook for the generic smp_call_function_many() routine. */
+void arch_send_call_function_ipi_mask(struct cpumask *mask);
+
+/* Hook for the generic smp_call_function_single() routine. */
+void arch_send_call_function_single_ipi(int cpu);
+
+#define raw_smp_processor_id() (current_thread_info()->cpu)
+
+/* Interprocessor interrupt handler */
+irqreturn_t handle_ipi(void);
+
+#endif /* CONFIG_SMP */
+
+#endif /* _ASM_RISCV_SMP_H */
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
new file mode 100644
index 000000000000..10ed2749e246
--- /dev/null
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -0,0 +1,105 @@
+/*
+ * 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/cacheinfo.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+static void ci_leaf_init(struct cacheinfo *this_leaf,
+ struct device_node *node,
+ enum cache_type type, unsigned int level)
+{
+ this_leaf->of_node = node;
+ 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)
+{
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct device_node *np = of_cpu_device_node_get(cpu);
+ int levels = 0, leaves = 0, level;
+
+ if (of_property_read_bool(np, "cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "i-cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "d-cache-size"))
+ ++leaves;
+ if (leaves > 0)
+ levels = 1;
+
+ while ((np = of_find_next_cache_node(np))) {
+ if (!of_device_is_compatible(np, "cache"))
+ break;
+ if (of_property_read_u32(np, "cache-level", &level))
+ break;
+ if (level <= levels)
+ break;
+ if (of_property_read_bool(np, "cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "i-cache-size"))
+ ++leaves;
+ if (of_property_read_bool(np, "d-cache-size"))
+ ++leaves;
+ levels = level;
+ }
+
+ this_cpu_ci->num_levels = levels;
+ this_cpu_ci->num_leaves = leaves;
+ return 0;
+}
+
+static int __populate_cache_leaves(unsigned int cpu)
+{
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+ struct device_node *np = of_cpu_device_node_get(cpu);
+ int levels = 1, level = 1;
+
+ if (of_property_read_bool(np, "cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level);
+ if (of_property_read_bool(np, "i-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level);
+ if (of_property_read_bool(np, "d-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level);
+
+ while ((np = of_find_next_cache_node(np))) {
+ if (!of_device_is_compatible(np, "cache"))
+ break;
+ if (of_property_read_u32(np, "cache-level", &level))
+ break;
+ if (level <= levels)
+ break;
+ if (of_property_read_bool(np, "cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level);
+ if (of_property_read_bool(np, "i-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level);
+ if (of_property_read_bool(np, "d-cache-size"))
+ ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level);
+ levels = level;
+ }
+
+ return 0;
+}
+
+DEFINE_SMP_CALL_CACHE_FUNCTION(init_cache_level)
+DEFINE_SMP_CALL_CACHE_FUNCTION(populate_cache_leaves)
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
new file mode 100644
index 000000000000..20004bd7a216
--- /dev/null
+++ b/arch/riscv/kernel/cpu.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/init.h>
+#include <linux/seq_file.h>
+#include <linux/of.h>
+
+/* Return -1 if not a valid hart */
+int riscv_of_processor_hart(struct device_node *node)
+{
+ const char *isa, *status;
+ u32 hart;
+
+ if (!of_device_is_compatible(node, "riscv"))
+ return -(ENODEV);
+ if (of_property_read_u32(node, "reg", &hart)
+ || hart >= NR_CPUS)
+ return -(ENODEV);
+ if (of_property_read_string(node, "status", &status)
+ || strcmp(status, "okay"))
+ return -(ENODEV);
+ if (of_property_read_string(node, "riscv,isa", &isa)
+ || isa[0] != 'r'
+ || isa[1] != 'v')
+ return -(ENODEV);
+
+ return hart;
+}
+
+#ifdef CONFIG_PROC_FS
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+ *pos = cpumask_next(*pos - 1, cpu_online_mask);
+ if ((*pos) < nr_cpu_ids)
+ return (void *)(uintptr_t)(1 + *pos);
+ return NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ (*pos)++;
+ return c_start(m, pos);
+}
+
+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);
+ 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);
+ if (!of_property_read_string(node, "compatible", &compat)
+ && strcmp(compat, "riscv"))
+ seq_printf(m, "uarch\t: %s\n", compat);
+ seq_puts(m, "\n");
+
+ return 0;
+}
+
+const struct seq_operations cpuinfo_op = {
+ .start = c_start,
+ .next = c_next,
+ .stop = c_stop,
+ .show = c_show
+};
+
+#endif /* CONFIG_PROC_FS */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
new file mode 100644
index 000000000000..504c368238c2
--- /dev/null
+++ b/arch/riscv/kernel/head.S
@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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 <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm/asm.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/csr.h>
+
+__INIT
+ENTRY(_start)
+ /* Mask all interrupts */
+ csrw sie, zero
+
+ /*
+ * Disable FPU to detect illegal usage of
+ * floating point in kernel space
+ */
+ li t0, SR_FS
+ csrc sstatus, t0
+
+#ifndef CONFIG_RV_PUM
+ /* Allow access to user memory */
+ li t0, SR_SUM
+ csrs sstatus, t0
+#endif
+
+#ifdef CONFIG_ISA_A
+ /* Pick one hart to run the main boot sequence */
+ la a3, hart_lottery
+ li a2, 1
+ amoadd.w a3, a2, (a3)
+ bnez a3, .Lsecondary_start
+#else
+ /*
+ * We don't have atomic support, so the boot hart must be picked
+ * staticly. Hart 0 is the only sane choice.
+ */
+ bnez a0, .Lsecondary_park
+#endif
+
+ /* Save hart ID and DTB physical address */
+ mv s0, a0
+ mv s1, a1
+
+ /* Initialize page tables and relocate to virtual addresses */
+ la sp, init_thread_union + THREAD_SIZE
+ call setup_vm
+ call relocate
+
+ /* Restore C environment */
+ la tp, init_task
+
+ la sp, init_thread_union
+ li a0, ASM_THREAD_SIZE
+ add sp, sp, a0
+
+ /* Start the kernel */
+ mv a0, s0
+ mv a1, s1
+ call sbi_save
+ tail start_kernel
+
+relocate:
+ /* Relocate return address */
+ li a1, PAGE_OFFSET
+ la a0, _start
+ sub a1, a1, a0
+ add ra, ra, a1
+
+ /* Point stvec to virtual address of intruction after sptbr write */
+ la a0, 1f
+ add a0, a0, a1
+ csrw stvec, a0
+
+ /* Compute sptbr for kernel page tables, but don't load it yet */
+ la a2, swapper_pg_dir
+ srl a2, a2, PAGE_SHIFT
+ li a1, SPTBR_MODE
+ or a2, a2, a1
+
+ /*
+ * Load trampoline page directory, which will cause us to trap to
+ * stvec if VA != PA, or simply fall through if VA == PA
+ */
+ la a0, trampoline_pg_dir
+ srl a0, a0, PAGE_SHIFT
+ or a0, a0, a1
+ sfence.vma
+ csrw sptbr, a0
+1:
+ /* Set trap vector to spin forever to help debug */
+ la a0, .Lsecondary_park
+ csrw stvec, a0
+
+ /* Load the global pointer */
+ la gp, __global_pointer$
+
+ /* Switch to kernel page tables */
+ csrw sptbr, a2
+
+ ret
+
+.Lsecondary_start:
+#ifdef CONFIG_SMP
+ li a1, CONFIG_NR_CPUS
+ bgeu a0, a1, .Lsecondary_park
+
+ la a1, __cpu_up_stack_pointer
+ slli a0, a0, LGREG
+ add a0, a0, a1
+
+.Lwait_for_cpu_up:
+ REG_L sp, (a0)
+ beqz sp, .Lwait_for_cpu_up
+ fence
+
+ /* Enable virtual memory and relocate to virtual address */
+ call relocate
+
+ /* Initialize task_struct pointer */
+ li tp, -THREAD_SIZE
+ add tp, tp, sp
+
+ tail smp_callin
+#endif
+
+.Lsecondary_park:
+ /* We lack SMP support or have too many harts, so park this hart */
+ wfi
+ j .Lsecondary_park
+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/irq.c b/arch/riscv/kernel/irq.c
new file mode 100644
index 000000000000..737d7cce2c6d
--- /dev/null
+++ b/arch/riscv/kernel/irq.c
@@ -0,0 +1,20 @@
+/*
+ * 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/irqchip.h>
+
+void __init init_IRQ(void)
+{
+ irqchip_init();
+}
diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c
new file mode 100644
index 000000000000..2a53d26ffdd6
--- /dev/null
+++ b/arch/riscv/kernel/reset.c
@@ -0,0 +1,36 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/reboot.h>
+#include <linux/export.h>
+#include <asm/sbi.h>
+
+void (*pm_power_off)(void) = machine_power_off;
+EXPORT_SYMBOL(pm_power_off);
+
+void machine_restart(char *cmd)
+{
+ do_kernel_restart(cmd);
+ while (1);
+}
+
+void machine_halt(void)
+{
+ machine_power_off();
+}
+
+void machine_power_off(void)
+{
+ sbi_shutdown();
+ while (1);
+}
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
new file mode 100644
index 000000000000..319fad96f537
--- /dev/null
+++ b/arch/riscv/kernel/setup.c
@@ -0,0 +1,246 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/sched.h>
+#include <linux/initrd.h>
+#include <linux/console.h>
+#include <linux/screen_info.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/sched/task.h>
+
+#include <asm/setup.h>
+#include <asm/sections.h>
+#include <asm/pgtable.h>
+#include <asm/smp.h>
+#include <asm/sbi.h>
+#include <asm/tlbflush.h>
+#include <asm/thread_info.h>
+
+#ifdef CONFIG_DUMMY_CONSOLE
+struct screen_info screen_info = {
+ .orig_video_lines = 30,
+ .orig_video_cols = 80,
+ .orig_video_mode = 0,
+ .orig_video_ega_bx = 0,
+ .orig_video_isVGA = 1,
+ .orig_video_points = 8
+};
+#endif
+
+#ifdef CONFIG_CMDLINE_BOOL
+static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
+#endif /* CONFIG_CMDLINE_BOOL */
+
+unsigned long va_pa_offset;
+unsigned long pfn_base;
+
+/* The lucky hart to first increment this variable will boot the other cores */
+atomic_t hart_lottery;
+
+#ifdef CONFIG_BLK_DEV_INITRD
+static void __init setup_initrd(void)
+{
+ extern char __initramfs_start[];
+ extern unsigned long __initramfs_size;
+ unsigned long size;
+
+ if (__initramfs_size > 0) {
+ initrd_start = (unsigned long)(&__initramfs_start);
+ initrd_end = initrd_start + __initramfs_size;
+ }
+
+ if (initrd_start >= initrd_end) {
+ printk(KERN_INFO "initrd not found or empty");
+ goto disable;
+ }
+ if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) {
+ printk(KERN_ERR "initrd extends beyond end of memory");
+ goto disable;
+ }
+
+ size = initrd_end - initrd_start;
+ memblock_reserve(__pa(initrd_start), size);
+ initrd_below_start_ok = 1;
+
+ printk(KERN_INFO "Initial ramdisk at: 0x%p (%lu bytes)\n",
+ (void *)(initrd_start), size);
+ return;
+disable:
+ pr_cont(" - disabling initrd\n");
+ initrd_start = 0;
+ initrd_end = 0;
+}
+#endif /* CONFIG_BLK_DEV_INITRD */
+
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
+pgd_t trampoline_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+
+#ifndef __PAGETABLE_PMD_FOLDED
+#define NUM_SWAPPER_PMDS ((uintptr_t)-PAGE_OFFSET >> PGDIR_SHIFT)
+pmd_t swapper_pmd[PTRS_PER_PMD*((-PAGE_OFFSET)/PGDIR_SIZE)] __page_aligned_bss;
+pmd_t trampoline_pmd[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+#endif
+
+asmlinkage void __init setup_vm(void)
+{
+ extern char _start;
+ uintptr_t i;
+ uintptr_t pa = (uintptr_t) &_start;
+ pgprot_t prot = __pgprot(pgprot_val(PAGE_KERNEL) | _PAGE_EXEC);
+
+ va_pa_offset = PAGE_OFFSET - pa;
+ pfn_base = PFN_DOWN(pa);
+
+ /* Sanity check alignment and size */
+ BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
+ BUG_ON((pa % (PAGE_SIZE * PTRS_PER_PTE)) != 0);
+
+#ifndef __PAGETABLE_PMD_FOLDED
+ trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
+ pfn_pgd(PFN_DOWN((uintptr_t)trampoline_pmd),
+ __pgprot(_PAGE_TABLE));
+ trampoline_pmd[0] = pfn_pmd(PFN_DOWN(pa), prot);
+
+ for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
+ size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
+ swapper_pg_dir[o] =
+ pfn_pgd(PFN_DOWN((uintptr_t)swapper_pmd) + i,
+ __pgprot(_PAGE_TABLE));
+ }
+ for (i = 0; i < ARRAY_SIZE(swapper_pmd); i++)
+ swapper_pmd[i] = pfn_pmd(PFN_DOWN(pa + i * PMD_SIZE), prot);
+#else
+ trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
+ pfn_pgd(PFN_DOWN(pa), prot);
+
+ for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
+ size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
+ swapper_pg_dir[o] =
+ pfn_pgd(PFN_DOWN(pa + i * PGDIR_SIZE), prot);
+ }
+#endif
+}
+
+void __init sbi_save(unsigned int hartid, void *dtb)
+{
+ early_init_dt_scan(__va(dtb));
+}
+
+/*
+ * Allow the user to manually add a memory region (in case DTS is broken);
+ * "mem_end=nn[KkMmGg]"
+ */
+static int __init mem_end_override(char *p)
+{
+ resource_size_t base, end;
+
+ if (!p)
+ return -EINVAL;
+ base = (uintptr_t) __pa(PAGE_OFFSET);
+ end = memparse(p, &p) & PMD_MASK;
+ if (end == 0)
+ return -EINVAL;
+ memblock_add(base, end - base);
+ return 0;
+}
+early_param("mem_end", mem_end_override);
+
+static void __init setup_bootmem(void)
+{
+ struct memblock_region *reg;
+ phys_addr_t mem_size = 0;
+
+ /* Find the memory region containing the kernel */
+ for_each_memblock(memory, reg) {
+ phys_addr_t vmlinux_end = __pa(_end);
+ phys_addr_t end = reg->base + reg->size;
+
+ if (reg->base <= vmlinux_end && vmlinux_end <= end) {
+ /*
+ * Reserve from the start of the region to the end of
+ * the kernel
+ */
+ memblock_reserve(reg->base, vmlinux_end - reg->base);
+ mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
+ }
+ }
+ BUG_ON(mem_size == 0);
+
+ set_max_mapnr(PFN_DOWN(mem_size));
+ max_low_pfn = pfn_base + PFN_DOWN(mem_size);
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ setup_initrd();
+#endif /* CONFIG_BLK_DEV_INITRD */
+
+ early_init_fdt_reserve_self();
+ early_init_fdt_scan_reserved_mem();
+ memblock_allow_resize();
+ memblock_dump_all();
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+ strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+ if (builtin_cmdline[0] != '\0') {
+ /* Append bootloader command line to built-in */
+ strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
+ strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+ strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+ }
+#endif /* CONFIG_CMDLINE_OVERRIDE */
+#endif /* CONFIG_CMDLINE_BOOL */
+ *cmdline_p = boot_command_line;
+
+ parse_early_param();
+
+ init_mm.start_code = (unsigned long) _stext;
+ init_mm.end_code = (unsigned long) _etext;
+ init_mm.end_data = (unsigned long) _edata;
+ init_mm.brk = (unsigned long) _end;
+
+ setup_bootmem();
+ paging_init();
+ unflatten_device_tree();
+
+#ifdef CONFIG_SMP
+ setup_smp();
+#endif
+
+#ifdef CONFIG_DUMMY_CONSOLE
+ conswitchp = &dummy_con;
+#endif
+
+ riscv_fill_hwcap();
+}
+
+static int __init riscv_device_init(void)
+{
+ return of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+}
+subsys_initcall_sync(riscv_device_init);
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
new file mode 100644
index 000000000000..b4a71ec5906f
--- /dev/null
+++ b/arch/riscv/kernel/smp.c
@@ -0,0 +1,110 @@
+/*
+ * SMP initialisation and IPI support
+ * Based on arch/arm64/kernel/smp.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+#include <linux/sched.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
+};
+
+irqreturn_t handle_ipi(void)
+{
+ unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
+
+ /* Clear pending IPI */
+ csr_clear(sip, SIE_SSIE);
+
+ while (true) {
+ unsigned long ops;
+
+ /* Order bit clearing and data access. */
+ mb();
+
+ ops = xchg(pending_ipis, 0);
+ if (ops == 0)
+ return IRQ_HANDLED;
+
+ if (ops & (1 << IPI_RESCHEDULE))
+ scheduler_ipi();
+
+ if (ops & (1 << IPI_CALL_FUNC))
+ generic_smp_call_function_interrupt();
+
+ BUG_ON((ops >> IPI_MAX) != 0);
+
+ /* Order data access and bit testing. */
+ mb();
+ }
+
+ return IRQ_HANDLED;
+}
+
+static void
+send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
+{
+ int i;
+
+ mb();
+ for_each_cpu(i, to_whom)
+ set_bit(operation, &ipi_data[i].bits);
+
+ mb();
+ sbi_send_ipi(cpumask_bits(to_whom));
+}
+
+void arch_send_call_function_ipi_mask(struct cpumask *mask)
+{
+ send_ipi_message(mask, IPI_CALL_FUNC);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+ send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
+}
+
+static void ipi_stop(void *unused)
+{
+ while (1)
+ wait_for_interrupt();
+}
+
+void smp_send_stop(void)
+{
+ on_each_cpu(ipi_stop, NULL, 1);
+}
+
+void smp_send_reschedule(int cpu)
+{
+ send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
+}
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
new file mode 100644
index 000000000000..e5c7f1aafda9
--- /dev/null
+++ b/arch/riscv/kernel/smpboot.c
@@ -0,0 +1,114 @@
+/*
+ * SMP initialisation and IPI support
+ * Based on arch/arm64/kernel/smp.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/kernel_stat.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/percpu.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/sched/task_stack.h>
+#include <asm/irq.h>
+#include <asm/mmu_context.h>
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/sbi.h>
+
+void *__cpu_up_stack_pointer[NR_CPUS];
+
+void __init smp_prepare_boot_cpu(void)
+{
+}
+
+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;
+
+ 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;
+ }
+ }
+ }
+
+ BUG_ON(!im_okay_therefore_i_am);
+}
+
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+ /* Signal cpu to start */
+ mb();
+ __cpu_up_stack_pointer[cpu] = task_stack_page(tidle) + THREAD_SIZE;
+
+ while (!cpu_online(cpu))
+ cpu_relax();
+
+ return 0;
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+/*
+ * C entry point for a secondary processor.
+ */
+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);
+ current->active_mm = mm;
+
+ trap_init();
+ init_clockevent();
+ notify_cpu_starting(smp_processor_id());
+ set_cpu_online(smp_processor_id(), 1);
+
+ /*
+ * Write SIE again now that this hart is online, to catch any IRQ
+ * enable/disable events that happened between trap_init() and
+ * set_cpu_online().
+ */
+ csr_write(sie,
+ SIE_SSIE | atomic_long_read(&per_cpu(riscv_early_sie, hart))
+ );
+
+ local_flush_tlb_all();
+ local_irq_enable();
+ preempt_disable();
+ cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
new file mode 100644
index 000000000000..6bba2e6f2a84
--- /dev/null
+++ b/arch/riscv/kernel/time.c
@@ -0,0 +1,61 @@
+/*
+ * 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/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/delay.h>
+#include <linux/timer_riscv.h>
+
+#include <asm/sbi.h>
+
+unsigned long riscv_timebase;
+
+static int next_event(unsigned long delta, struct clock_event_device *ce)
+{
+ BUG_ON(ce != timer_riscv_device(smp_processor_id()));
+ sbi_set_timer(get_cycles64() + delta);
+ return 0;
+}
+
+static unsigned long long rdtime(struct clocksource *cs)
+{
+ BUG_ON(cs != timer_riscv_source(smp_processor_id()));
+ return get_cycles64();
+}
+
+void riscv_timer_interrupt(void)
+{
+ int cpu = smp_processor_id();
+ struct clock_event_device *evdev = timer_riscv_device(cpu);
+
+ evdev->event_handler(evdev);
+}
+
+void __init time_init(void)
+{
+ struct device_node *cpu;
+ u32 prop;
+ int cpu_id = smp_processor_id();
+
+ cpu = of_find_node_by_path("/cpus");
+ if (!cpu || of_property_read_u32(cpu, "timebase-frequency", &prop))
+ panic(KERN_WARNING "RISC-V system with no 'timebase-frequency' in DTS\n");
+ riscv_timebase = prop;
+
+ lpj_fine = riscv_timebase / HZ;
+
+ timer_riscv_init(cpu_id, riscv_timebase, &rdtime, &next_event);
+
+ csr_set(sie, SIE_STIE);
+}
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
new file mode 100644
index 000000000000..2175a39bed1c
--- /dev/null
+++ b/arch/riscv/kernel/traps.c
@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/kernel.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
+#include <linux/signal.h>
+#include <linux/kdebug.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/csr.h>
+
+int show_unhandled_signals = 1;
+
+extern asmlinkage void handle_exception(void);
+
+static DEFINE_SPINLOCK(die_lock);
+
+void die(struct pt_regs *regs, const char *str)
+{
+ static int die_counter;
+ int ret;
+
+ oops_enter();
+
+ spin_lock_irq(&die_lock);
+ console_verbose();
+ bust_spinlocks(1);
+
+ pr_emerg("%s [#%d]\n", str, ++die_counter);
+ print_modules();
+ show_regs(regs);
+
+ ret = notify_die(DIE_OOPS, str, regs, 0, regs->scause, SIGSEGV);
+
+ bust_spinlocks(0);
+ add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
+ spin_unlock_irq(&die_lock);
+ oops_exit();
+
+ if (in_interrupt())
+ panic("Fatal exception in interrupt");
+ if (panic_on_oops)
+ panic("Fatal exception");
+ if (ret != NOTIFY_STOP)
+ do_exit(SIGSEGV);
+}
+
+static inline void do_trap_siginfo(int signo, int code,
+ unsigned long addr, struct task_struct *tsk)
+{
+ siginfo_t info;
+
+ info.si_signo = signo;
+ info.si_errno = 0;
+ info.si_code = code;
+ info.si_addr = (void __user *)addr;
+ force_sig_info(signo, &info, tsk);
+}
+
+void do_trap(struct pt_regs *regs, int signo, int code,
+ unsigned long addr, struct task_struct *tsk)
+{
+ if (show_unhandled_signals && unhandled_signal(tsk, signo)
+ && printk_ratelimit()) {
+ pr_info("%s[%d]: unhandled signal %d code 0x%x at 0x" REG_FMT,
+ tsk->comm, task_pid_nr(tsk), signo, code, addr);
+ print_vma_addr(KERN_CONT " in ", GET_IP(regs));
+ pr_cont("\n");
+ show_regs(regs);
+ }
+
+ do_trap_siginfo(signo, code, addr, tsk);
+}
+
+static void do_trap_error(struct pt_regs *regs, int signo, int code,
+ unsigned long addr, const char *str)
+{
+ if (user_mode(regs)) {
+ do_trap(regs, signo, code, addr, current);
+ } else {
+ if (!fixup_exception(regs))
+ die(regs, str);
+ }
+}
+
+#define DO_ERROR_INFO(name, signo, code, str) \
+asmlinkage void name(struct pt_regs *regs) \
+{ \
+ do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \
+}
+
+DO_ERROR_INFO(do_trap_unknown,
+ SIGILL, ILL_ILLTRP, "unknown exception");
+DO_ERROR_INFO(do_trap_insn_misaligned,
+ SIGBUS, BUS_ADRALN, "instruction address misaligned");
+DO_ERROR_INFO(do_trap_insn_fault,
+ SIGBUS, BUS_ADRALN, "instruction access fault");
+DO_ERROR_INFO(do_trap_insn_illegal,
+ SIGILL, ILL_ILLOPC, "illegal instruction");
+DO_ERROR_INFO(do_trap_load_misaligned,
+ SIGBUS, BUS_ADRALN, "load address misaligned");
+DO_ERROR_INFO(do_trap_load_fault,
+ SIGSEGV, SEGV_ACCERR, "load access fault");
+DO_ERROR_INFO(do_trap_store_misaligned,
+ SIGBUS, BUS_ADRALN, "store (or AMO) address misaligned");
+DO_ERROR_INFO(do_trap_store_fault,
+ SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
+DO_ERROR_INFO(do_trap_ecall_u,
+ SIGILL, ILL_ILLTRP, "environment call from U-mode");
+DO_ERROR_INFO(do_trap_ecall_s,
+ SIGILL, ILL_ILLTRP, "environment call from S-mode");
+DO_ERROR_INFO(do_trap_ecall_m,
+ SIGILL, ILL_ILLTRP, "environment call from M-mode");
+
+asmlinkage void do_trap_break(struct pt_regs *regs)
+{
+#ifdef CONFIG_GENERIC_BUG
+ if (!user_mode(regs)) {
+ enum bug_trap_type type;
+
+ type = report_bug(regs->sepc, regs);
+ switch (type) {
+ case BUG_TRAP_TYPE_NONE:
+ break;
+ case BUG_TRAP_TYPE_WARN:
+ regs->sepc += sizeof(bug_insn_t);
+ return;
+ case BUG_TRAP_TYPE_BUG:
+ die(regs, "Kernel BUG");
+ }
+ }
+#endif /* CONFIG_GENERIC_BUG */
+
+ do_trap_siginfo(SIGTRAP, TRAP_BRKPT, regs->sepc, current);
+ regs->sepc += 0x4;
+}
+
+#ifdef CONFIG_GENERIC_BUG
+int is_valid_bugaddr(unsigned long pc)
+{
+ bug_insn_t insn;
+
+ if (pc < PAGE_OFFSET)
+ return 0;
+ if (probe_kernel_address((bug_insn_t __user *)pc, insn))
+ return 0;
+ return (insn == __BUG_INSN);
+}
+#endif /* CONFIG_GENERIC_BUG */
+
+void __init trap_init(void)
+{
+ int hart = smp_processor_id();
+
+ /*
+ * Set sup0 scratch register to 0, indicating to exception vector
+ * that we are presently executing in the kernel
+ */
+ csr_write(sscratch, 0);
+ /* Set the exception vector address */
+ csr_write(stvec, &handle_exception);
+ /* Enable software interrupts and setup initial mask */
+ csr_write(sie,
+ SIE_SSIE | atomic_long_read(&per_cpu(riscv_early_sie, hart))
+ );
+}
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
new file mode 100644
index 000000000000..e8a178df8144
--- /dev/null
+++ b/arch/riscv/kernel/vdso.c
@@ -0,0 +1,125 @@
+/*
+ * Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
+ * <benh@kernel.crashing.org>
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/binfmts.h>
+#include <linux/err.h>
+
+#include <asm/vdso.h>
+
+extern char vdso_start[], vdso_end[];
+
+static unsigned int vdso_pages;
+static struct page **vdso_pagelist;
+
+/*
+ * The vDSO data page.
+ */
+static union {
+ struct vdso_data data;
+ u8 page[PAGE_SIZE];
+} vdso_data_store __page_aligned_data;
+struct vdso_data *vdso_data = &vdso_data_store.data;
+
+static int __init vdso_init(void)
+{
+ unsigned int i;
+
+ vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
+ vdso_pagelist =
+ kcalloc(vdso_pages + 1, sizeof(struct page *), GFP_KERNEL);
+ if (unlikely(vdso_pagelist == NULL)) {
+ pr_err("vdso: pagelist allocation failed\n");
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < vdso_pages; i++) {
+ struct page *pg;
+
+ pg = virt_to_page(vdso_start + (i << PAGE_SHIFT));
+ ClearPageReserved(pg);
+ vdso_pagelist[i] = pg;
+ }
+ vdso_pagelist[i] = virt_to_page(vdso_data);
+
+ return 0;
+}
+arch_initcall(vdso_init);
+
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp)
+{
+ struct mm_struct *mm = current->mm;
+ unsigned long vdso_base, vdso_len;
+ int ret;
+
+ vdso_len = (vdso_pages + 1) << PAGE_SHIFT;
+
+ down_write(&mm->mmap_sem);
+ vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0);
+ if (unlikely(IS_ERR_VALUE(vdso_base))) {
+ ret = vdso_base;
+ goto end;
+ }
+
+ /*
+ * Put vDSO base into mm struct. We need to do this before calling
+ * install_special_mapping or the perf counter mmap tracking code
+ * will fail to recognise it as a vDSO (since arch_vma_name fails).
+ */
+ mm->context.vdso = (void *)vdso_base;
+
+ ret = install_special_mapping(mm, vdso_base, vdso_len,
+ (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
+ vdso_pagelist);
+
+ if (unlikely(ret))
+ mm->context.vdso = NULL;
+
+end:
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+
+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]";
+ return NULL;
+}
+
+/*
+ * Function stubs to prevent linker errors when AT_SYSINFO_EHDR is defined
+ */
+
+int in_gate_area_no_mm(unsigned long addr)
+{
+ return 0;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
+{
+ return 0;
+}
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+ return NULL;
+}
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
new file mode 100644
index 000000000000..9f4bee5e51fd
--- /dev/null
+++ b/arch/riscv/mm/init.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/init.h>
+#include <linux/mm.h>
+#include <linux/bootmem.h>
+#include <linux/initrd.h>
+#include <linux/memblock.h>
+#include <linux/swap.h>
+
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/pgtable.h>
+#include <asm/io.h>
+
+static void __init zone_sizes_init(void)
+{
+ unsigned long zones_size[MAX_NR_ZONES];
+
+ memset(zones_size, 0, sizeof(zones_size));
+ zones_size[ZONE_NORMAL] = max_mapnr;
+ free_area_init_node(0, zones_size, pfn_base, NULL);
+}
+
+void setup_zero_page(void)
+{
+ memset((void *)empty_zero_page, 0, PAGE_SIZE);
+}
+
+void __init paging_init(void)
+{
+ init_mm.pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr));
+
+ setup_zero_page();
+ local_flush_tlb_all();
+ zone_sizes_init();
+}
+
+void __init mem_init(void)
+{
+#ifdef CONFIG_FLATMEM
+ BUG_ON(!mem_map);
+#endif /* CONFIG_FLATMEM */
+
+ high_memory = (void *)(__va(PFN_PHYS(max_low_pfn)));
+ free_all_bootmem();
+
+ mem_init_print_info(NULL);
+}
+
+void free_initmem(void)
+{
+ free_initmem_default(0);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+}
+#endif /* CONFIG_BLK_DEV_INITRD */
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread[parent not found: <alpine.DEB.2.20.1707042224560.2131@nanos>]
* Re: [patches] Re: [PATCH 1/9] RISC-V: Init and Halt Code
[not found] ` <alpine.DEB.2.20.1707042224560.2131@nanos>
@ 2017-07-04 21:17 ` Karsten Merker
2017-07-05 6:39 ` Thomas Gleixner
0 siblings, 1 reply; 58+ messages in thread
From: Karsten Merker @ 2017-07-04 21:17 UTC (permalink / raw)
To: Palmer Dabbelt, Thomas Gleixner
Cc: patches, peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel,
rmk+kernel, msalter, tklauser, will.deacon, james.hogan,
paul.gortmaker, linux, linux-kernel, linux-arch, albert
On Tue, Jul 04, 2017 at 10:37:37PM +0200, Thomas Gleixner wrote:
> On Tue, 4 Jul 2017, Palmer Dabbelt wrote:
> > +unsigned long riscv_timebase;
> > +
> > +static int next_event(unsigned long delta, struct clock_event_device *ce)
> > +{
> > + BUG_ON(ce != timer_riscv_device(smp_processor_id()));
> > + sbi_set_timer(get_cycles64() + delta);
> > + return 0;
> > +}
> > +
> > +static unsigned long long rdtime(struct clocksource *cs)
> > +{
> > + BUG_ON(cs != timer_riscv_source(smp_processor_id()));
> > + return get_cycles64();
> > +}
> > +
> > +void riscv_timer_interrupt(void)
> > +{
> > + int cpu = smp_processor_id();
> > + struct clock_event_device *evdev = timer_riscv_device(cpu);
> > +
> > + evdev->event_handler(evdev);
> > +}
> > +
> > +void __init time_init(void)
> > +{
> > + struct device_node *cpu;
> > + u32 prop;
> > + int cpu_id = smp_processor_id();
> > +
> > + cpu = of_find_node_by_path("/cpus");
> > + if (!cpu || of_property_read_u32(cpu, "timebase-frequency", &prop))
> > + panic(KERN_WARNING "RISC-V system with no 'timebase-frequency' in DTS\n");
> > + riscv_timebase = prop;
> > +
> > + lpj_fine = riscv_timebase / HZ;
> > +
> > + timer_riscv_init(cpu_id, riscv_timebase, &rdtime, &next_event);
>
> This function is nowhere.... Neither can I find the header file.
It is part of the RISC-V clock driver patchset, please cf.
https://github.com/riscv/riscv-linux/commit/0705a31372d4714e54c5104e02021441785c1fd5
https://github.com/riscv/riscv-linux/commits/riscv-for-submission-v4
has the various RISC-V-related driver patchsets merged in (in
addition to this arch patchset).
Regards,
Karsten
--
Gem. Par. 28 Abs. 4 Bundesdatenschutzgesetz widerspreche ich der Nutzung
sowie der Weitergabe meiner personenbezogenen Daten für Zwecke der
Werbung sowie der Markt- oder Meinungsforschung.
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [patches] Re: [PATCH 1/9] RISC-V: Init and Halt Code
2017-07-04 21:17 ` [patches] " Karsten Merker
@ 2017-07-05 6:39 ` Thomas Gleixner
0 siblings, 0 replies; 58+ messages in thread
From: Thomas Gleixner @ 2017-07-05 6:39 UTC (permalink / raw)
To: Karsten Merker
Cc: Palmer Dabbelt, patches, peterz, mingo, mcgrof, viro, sfr,
nicolas.dichtel, rmk+kernel, msalter, tklauser, will.deacon,
james.hogan, paul.gortmaker, linux, linux-kernel, linux-arch,
albert
On Tue, 4 Jul 2017, Karsten Merker wrote:
> On Tue, Jul 04, 2017 at 10:37:37PM +0200, Thomas Gleixner wrote:
> > > + timer_riscv_init(cpu_id, riscv_timebase, &rdtime, &next_event);
> >
> > This function is nowhere.... Neither can I find the header file.
>
> It is part of the RISC-V clock driver patchset, please cf.
> https://github.com/riscv/riscv-linux/commit/0705a31372d4714e54c5104e02021441785c1fd5
>
> https://github.com/riscv/riscv-linux/commits/riscv-for-submission-v4
> has the various RISC-V-related driver patchsets merged in (in
> addition to this arch patchset).
Well, then please move that timer stuff to the clock driver patchset, so
the combo can be reviewed. Having half functional patches with missing
references here and there makes review a PITA.
Thanks,
tglx
^ permalink raw reply [flat|nested] 58+ messages in thread
* Re: [patches] [PATCH 1/9] RISC-V: Init and Halt Code
2017-07-04 19:50 ` Palmer Dabbelt
(?)
(?)
@ 2017-07-04 21:54 ` Jonathan Neuschäfer
2017-07-06 22:34 ` Palmer Dabbelt
-1 siblings, 1 reply; 58+ messages in thread
From: Jonathan Neuschäfer @ 2017-07-04 21:54 UTC (permalink / raw)
To: patches
Cc: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, Palmer Dabbelt
[-- Attachment #1: Type: text/plain, Size: 1969 bytes --]
Hi, below are some small comments.
On Tue, Jul 04, 2017 at 12:50:54PM -0700, Palmer Dabbelt wrote:
> This contains the various __init C functions, the initial assembly
> kernel entry point, and the code to reset the system. When a file was
> init-related, it contains
It contains what?
> Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
[...]
> +#ifdef CONFIG_GENERIC_BUG
> +#define __BUG_INSN _AC(0x00100073, UL) /* sbreak */
This should be ebreak, not sbreak, in Priv Spec 1.10, AFAICT.
I guess binutils still understands sbreak, but it's nicer to stick to
the spec, IMHO.
> +#define BUG() \
> +do { \
> + __asm__ __volatile__ ( \
> + "1:\n\t" \
> + "sbreak\n" \
ebreak
> + ".pushsection __bug_table,\"a\"\n\t" \
> + "2:\n\t" \
> + __BUG_ENTRY "\n\t" \
> + ".org 2b + %2\n\t" \
> + ".popsection" \
> + : \
> + : "i" (__FILE__), "i" (__LINE__), \
> + "i" (sizeof(struct bug_entry))); \
> + unreachable(); \
> +} while (0)
> +#endif /* !__ASSEMBLY__ */
> +#else /* CONFIG_GENERIC_BUG */
> +#ifndef __ASSEMBLY__
> +#define BUG() \
> +do { \
> + __asm__ __volatile__ ("sbreak\n"); \
ebreak
> + unreachable(); \
> +} while (0)
> +#endif /* !__ASSEMBLY__ */
> +#endif /* CONFIG_GENERIC_BUG */
[...]
> +#define DO_ERROR_INFO(name, signo, code, str) \
> +asmlinkage void name(struct pt_regs *regs) \
> +{ \
> + do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \
> +}
> +
> +DO_ERROR_INFO(do_trap_unknown,
> + SIGILL, ILL_ILLTRP, "unknown exception");
> +DO_ERROR_INFO(do_trap_insn_misaligned,
> + SIGBUS, BUS_ADRALN, "instruction address misaligned");
> +DO_ERROR_INFO(do_trap_insn_fault,
> + SIGBUS, BUS_ADRALN, "instruction access fault");
For a general instruction access fault, BUS_ADRALN seems wrong. A
variant of SIGSEGV seems more appropriate, IMHO.
Jonathan Neuschäfer
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [patches] [PATCH 1/9] RISC-V: Init and Halt Code
2017-07-04 21:54 ` [patches] " Jonathan Neuschäfer
@ 2017-07-06 22:34 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-06 22:34 UTC (permalink / raw)
To: j.neuschaefer
Cc: patches, peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel,
rmk+kernel, msalter, tklauser, will.deacon, james.hogan,
paul.gortmaker, linux, linux-kernel, linux-arch, albert
On Tue, 04 Jul 2017 14:54:01 PDT (-0700), j.neuschaefer@gmx.net wrote:
> Hi, below are some small comments.
>
> On Tue, Jul 04, 2017 at 12:50:54PM -0700, Palmer Dabbelt wrote:
>> This contains the various __init C functions, the initial assembly
>> kernel entry point, and the code to reset the system. When a file was
>> init-related, it contains
>
> It contains what?
>
>> Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
> [...]
>
>> +#ifdef CONFIG_GENERIC_BUG
>> +#define __BUG_INSN _AC(0x00100073, UL) /* sbreak */
>
> This should be ebreak, not sbreak, in Priv Spec 1.10, AFAICT.
> I guess binutils still understands sbreak, but it's nicer to stick to
> the spec, IMHO.
I agree. IIRC they're the same instruction, we just alias sbreak->ebreak in
binutils (like scall->ecall).
>> +#define BUG() \
>> +do { \
>> + __asm__ __volatile__ ( \
>> + "1:\n\t" \
>> + "sbreak\n" \
>
> ebreak
>
>> + ".pushsection __bug_table,\"a\"\n\t" \
>> + "2:\n\t" \
>> + __BUG_ENTRY "\n\t" \
>> + ".org 2b + %2\n\t" \
>> + ".popsection" \
>> + : \
>> + : "i" (__FILE__), "i" (__LINE__), \
>> + "i" (sizeof(struct bug_entry))); \
>> + unreachable(); \
>> +} while (0)
>> +#endif /* !__ASSEMBLY__ */
>> +#else /* CONFIG_GENERIC_BUG */
>> +#ifndef __ASSEMBLY__
>> +#define BUG() \
>> +do { \
>> + __asm__ __volatile__ ("sbreak\n"); \
>
> ebreak
>
>> + unreachable(); \
>> +} while (0)
>> +#endif /* !__ASSEMBLY__ */
>> +#endif /* CONFIG_GENERIC_BUG */
> [...]
>
>> +#define DO_ERROR_INFO(name, signo, code, str) \
>> +asmlinkage void name(struct pt_regs *regs) \
>> +{ \
>> + do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \
>> +}
>> +
>> +DO_ERROR_INFO(do_trap_unknown,
>> + SIGILL, ILL_ILLTRP, "unknown exception");
>> +DO_ERROR_INFO(do_trap_insn_misaligned,
>> + SIGBUS, BUS_ADRALN, "instruction address misaligned");
>> +DO_ERROR_INFO(do_trap_insn_fault,
>> + SIGBUS, BUS_ADRALN, "instruction access fault");
>
> For a general instruction access fault, BUS_ADRALN seems wrong. A
> variant of SIGSEGV seems more appropriate, IMHO.
How does this look?
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 4c693b5b9980..3ce9ac6e736e 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -112,7 +112,7 @@ DO_ERROR_INFO(do_trap_unknown,
DO_ERROR_INFO(do_trap_insn_misaligned,
SIGBUS, BUS_ADRALN, "instruction address misaligned");
DO_ERROR_INFO(do_trap_insn_fault,
- SIGBUS, BUS_ADRALN, "instruction access fault");
+ SIGBUS, SEGV_ACCERR, "instruction access fault");
DO_ERROR_INFO(do_trap_insn_illegal,
SIGILL, ILL_ILLOPC, "illegal instruction");
DO_ERROR_INFO(do_trap_load_misaligned,
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [patches] [PATCH 1/9] RISC-V: Init and Halt Code
@ 2017-07-06 22:34 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-06 22:34 UTC (permalink / raw)
To: j.neuschaefer
Cc: patches, peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel,
rmk+kernel, msalter, tklauser, will.deacon, james.hogan,
paul.gortmaker, linux, linux-kernel, linux-arch, albert
On Tue, 04 Jul 2017 14:54:01 PDT (-0700), j.neuschaefer@gmx.net wrote:
> Hi, below are some small comments.
>
> On Tue, Jul 04, 2017 at 12:50:54PM -0700, Palmer Dabbelt wrote:
>> This contains the various __init C functions, the initial assembly
>> kernel entry point, and the code to reset the system. When a file was
>> init-related, it contains
>
> It contains what?
>
>> Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
> [...]
>
>> +#ifdef CONFIG_GENERIC_BUG
>> +#define __BUG_INSN _AC(0x00100073, UL) /* sbreak */
>
> This should be ebreak, not sbreak, in Priv Spec 1.10, AFAICT.
> I guess binutils still understands sbreak, but it's nicer to stick to
> the spec, IMHO.
I agree. IIRC they're the same instruction, we just alias sbreak->ebreak in
binutils (like scall->ecall).
>> +#define BUG() \
>> +do { \
>> + __asm__ __volatile__ ( \
>> + "1:\n\t" \
>> + "sbreak\n" \
>
> ebreak
>
>> + ".pushsection __bug_table,\"a\"\n\t" \
>> + "2:\n\t" \
>> + __BUG_ENTRY "\n\t" \
>> + ".org 2b + %2\n\t" \
>> + ".popsection" \
>> + : \
>> + : "i" (__FILE__), "i" (__LINE__), \
>> + "i" (sizeof(struct bug_entry))); \
>> + unreachable(); \
>> +} while (0)
>> +#endif /* !__ASSEMBLY__ */
>> +#else /* CONFIG_GENERIC_BUG */
>> +#ifndef __ASSEMBLY__
>> +#define BUG() \
>> +do { \
>> + __asm__ __volatile__ ("sbreak\n"); \
>
> ebreak
>
>> + unreachable(); \
>> +} while (0)
>> +#endif /* !__ASSEMBLY__ */
>> +#endif /* CONFIG_GENERIC_BUG */
> [...]
>
>> +#define DO_ERROR_INFO(name, signo, code, str) \
>> +asmlinkage void name(struct pt_regs *regs) \
>> +{ \
>> + do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \
>> +}
>> +
>> +DO_ERROR_INFO(do_trap_unknown,
>> + SIGILL, ILL_ILLTRP, "unknown exception");
>> +DO_ERROR_INFO(do_trap_insn_misaligned,
>> + SIGBUS, BUS_ADRALN, "instruction address misaligned");
>> +DO_ERROR_INFO(do_trap_insn_fault,
>> + SIGBUS, BUS_ADRALN, "instruction access fault");
>
> For a general instruction access fault, BUS_ADRALN seems wrong. A
> variant of SIGSEGV seems more appropriate, IMHO.
How does this look?
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 4c693b5b9980..3ce9ac6e736e 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -112,7 +112,7 @@ DO_ERROR_INFO(do_trap_unknown,
DO_ERROR_INFO(do_trap_insn_misaligned,
SIGBUS, BUS_ADRALN, "instruction address misaligned");
DO_ERROR_INFO(do_trap_insn_fault,
- SIGBUS, BUS_ADRALN, "instruction access fault");
+ SIGBUS, SEGV_ACCERR, "instruction access fault");
DO_ERROR_INFO(do_trap_insn_illegal,
SIGILL, ILL_ILLOPC, "illegal instruction");
DO_ERROR_INFO(do_trap_load_misaligned,
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [patches] [PATCH 1/9] RISC-V: Init and Halt Code
2017-07-06 22:34 ` Palmer Dabbelt
(?)
@ 2017-07-07 12:58 ` Jonathan Neuschäfer
2017-07-10 20:39 ` Palmer Dabbelt
-1 siblings, 1 reply; 58+ messages in thread
From: Jonathan Neuschäfer @ 2017-07-07 12:58 UTC (permalink / raw)
To: Palmer Dabbelt
Cc: j.neuschaefer, patches, peterz, mingo, mcgrof, viro, sfr,
nicolas.dichtel, rmk+kernel, msalter, tklauser, will.deacon,
james.hogan, paul.gortmaker, linux, linux-kernel, linux-arch,
albert
[-- Attachment #1: Type: text/plain, Size: 1834 bytes --]
On Thu, Jul 06, 2017 at 03:34:39PM -0700, Palmer Dabbelt wrote:
> On Tue, 04 Jul 2017 14:54:01 PDT (-0700), j.neuschaefer@gmx.net wrote:
[...]
> >> +#define DO_ERROR_INFO(name, signo, code, str) \
> >> +asmlinkage void name(struct pt_regs *regs) \
> >> +{ \
> >> + do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \
> >> +}
> >> +
> >> +DO_ERROR_INFO(do_trap_unknown,
> >> + SIGILL, ILL_ILLTRP, "unknown exception");
> >> +DO_ERROR_INFO(do_trap_insn_misaligned,
> >> + SIGBUS, BUS_ADRALN, "instruction address misaligned");
> >> +DO_ERROR_INFO(do_trap_insn_fault,
> >> + SIGBUS, BUS_ADRALN, "instruction access fault");
> >
> > For a general instruction access fault, BUS_ADRALN seems wrong. A
> > variant of SIGSEGV seems more appropriate, IMHO.
>
> How does this look?
>
> diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
> index 4c693b5b9980..3ce9ac6e736e 100644
> --- a/arch/riscv/kernel/traps.c
> +++ b/arch/riscv/kernel/traps.c
> @@ -112,7 +112,7 @@ DO_ERROR_INFO(do_trap_unknown,
> DO_ERROR_INFO(do_trap_insn_misaligned,
> SIGBUS, BUS_ADRALN, "instruction address misaligned");
> DO_ERROR_INFO(do_trap_insn_fault,
> - SIGBUS, BUS_ADRALN, "instruction access fault");
> + SIGBUS, SEGV_ACCERR, "instruction access fault");
> DO_ERROR_INFO(do_trap_insn_illegal,
> SIGILL, ILL_ILLOPC, "illegal instruction");
> DO_ERROR_INFO(do_trap_load_misaligned,
I'm not familiar with the trap handling infrastructure, but looking at
include/uapi/asm-generic/siginfo.h, SEGV_ACCERR would alias to
BUS_ADRERR (both are defined as (__SI_FAULT|2)). So if you use SEGV_*,
you need to use SIGSEGV, too.
With DO_ERROR_INFO(..., SIGSEGV, SEGV_ACCERR, ...); it looks good to me.
Jonathan Neuschäfer
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [patches] [PATCH 1/9] RISC-V: Init and Halt Code
2017-07-07 12:58 ` Jonathan Neuschäfer
@ 2017-07-10 20:39 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-10 20:39 UTC (permalink / raw)
To: j.neuschaefer
Cc: j.neuschaefer, patches, peterz, mingo, mcgrof, viro, sfr,
nicolas.dichtel, rmk+kernel, msalter, tklauser, will.deacon,
james.hogan, paul.gortmaker, linux, linux-kernel, linux-arch,
albert
On Fri, 07 Jul 2017 05:58:55 PDT (-0700), j.neuschaefer@gmx.net wrote:
> On Thu, Jul 06, 2017 at 03:34:39PM -0700, Palmer Dabbelt wrote:
>> On Tue, 04 Jul 2017 14:54:01 PDT (-0700), j.neuschaefer@gmx.net wrote:
> [...]
>> >> +#define DO_ERROR_INFO(name, signo, code, str) \
>> >> +asmlinkage void name(struct pt_regs *regs) \
>> >> +{ \
>> >> + do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \
>> >> +}
>> >> +
>> >> +DO_ERROR_INFO(do_trap_unknown,
>> >> + SIGILL, ILL_ILLTRP, "unknown exception");
>> >> +DO_ERROR_INFO(do_trap_insn_misaligned,
>> >> + SIGBUS, BUS_ADRALN, "instruction address misaligned");
>> >> +DO_ERROR_INFO(do_trap_insn_fault,
>> >> + SIGBUS, BUS_ADRALN, "instruction access fault");
>> >
>> > For a general instruction access fault, BUS_ADRALN seems wrong. A
>> > variant of SIGSEGV seems more appropriate, IMHO.
>>
>> How does this look?
>>
>> diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
>> index 4c693b5b9980..3ce9ac6e736e 100644
>> --- a/arch/riscv/kernel/traps.c
>> +++ b/arch/riscv/kernel/traps.c
>> @@ -112,7 +112,7 @@ DO_ERROR_INFO(do_trap_unknown,
>> DO_ERROR_INFO(do_trap_insn_misaligned,
>> SIGBUS, BUS_ADRALN, "instruction address misaligned");
>> DO_ERROR_INFO(do_trap_insn_fault,
>> - SIGBUS, BUS_ADRALN, "instruction access fault");
>> + SIGBUS, SEGV_ACCERR, "instruction access fault");
>> DO_ERROR_INFO(do_trap_insn_illegal,
>> SIGILL, ILL_ILLOPC, "illegal instruction");
>> DO_ERROR_INFO(do_trap_load_misaligned,
>
> I'm not familiar with the trap handling infrastructure, but looking at
> include/uapi/asm-generic/siginfo.h, SEGV_ACCERR would alias to
> BUS_ADRERR (both are defined as (__SI_FAULT|2)). So if you use SEGV_*,
> you need to use SIGSEGV, too.
>
> With DO_ERROR_INFO(..., SIGSEGV, SEGV_ACCERR, ...); it looks good to me.
Oh, sorry, I wasn't paying attention. It should be fixed now.
Thanks!
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [patches] [PATCH 1/9] RISC-V: Init and Halt Code
@ 2017-07-10 20:39 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-10 20:39 UTC (permalink / raw)
Cc: j.neuschaefer, patches, peterz, mingo, mcgrof, viro, sfr,
nicolas.dichtel, rmk+kernel, msalter, tklauser, will.deacon,
james.hogan, paul.gortmaker, linux, linux-kernel, linux-arch,
albert
On Fri, 07 Jul 2017 05:58:55 PDT (-0700), j.neuschaefer@gmx.net wrote:
> On Thu, Jul 06, 2017 at 03:34:39PM -0700, Palmer Dabbelt wrote:
>> On Tue, 04 Jul 2017 14:54:01 PDT (-0700), j.neuschaefer@gmx.net wrote:
> [...]
>> >> +#define DO_ERROR_INFO(name, signo, code, str) \
>> >> +asmlinkage void name(struct pt_regs *regs) \
>> >> +{ \
>> >> + do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \
>> >> +}
>> >> +
>> >> +DO_ERROR_INFO(do_trap_unknown,
>> >> + SIGILL, ILL_ILLTRP, "unknown exception");
>> >> +DO_ERROR_INFO(do_trap_insn_misaligned,
>> >> + SIGBUS, BUS_ADRALN, "instruction address misaligned");
>> >> +DO_ERROR_INFO(do_trap_insn_fault,
>> >> + SIGBUS, BUS_ADRALN, "instruction access fault");
>> >
>> > For a general instruction access fault, BUS_ADRALN seems wrong. A
>> > variant of SIGSEGV seems more appropriate, IMHO.
>>
>> How does this look?
>>
>> diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
>> index 4c693b5b9980..3ce9ac6e736e 100644
>> --- a/arch/riscv/kernel/traps.c
>> +++ b/arch/riscv/kernel/traps.c
>> @@ -112,7 +112,7 @@ DO_ERROR_INFO(do_trap_unknown,
>> DO_ERROR_INFO(do_trap_insn_misaligned,
>> SIGBUS, BUS_ADRALN, "instruction address misaligned");
>> DO_ERROR_INFO(do_trap_insn_fault,
>> - SIGBUS, BUS_ADRALN, "instruction access fault");
>> + SIGBUS, SEGV_ACCERR, "instruction access fault");
>> DO_ERROR_INFO(do_trap_insn_illegal,
>> SIGILL, ILL_ILLOPC, "illegal instruction");
>> DO_ERROR_INFO(do_trap_load_misaligned,
>
> I'm not familiar with the trap handling infrastructure, but looking at
> include/uapi/asm-generic/siginfo.h, SEGV_ACCERR would alias to
> BUS_ADRERR (both are defined as (__SI_FAULT|2)). So if you use SEGV_*,
> you need to use SIGSEGV, too.
>
> With DO_ERROR_INFO(..., SIGSEGV, SEGV_ACCERR, ...); it looks good to me.
Oh, sorry, I wasn't paying attention. It should be fixed now.
Thanks!
^ permalink raw reply [flat|nested] 58+ messages in thread
* [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-04 19:50 ` Palmer Dabbelt
@ 2017-07-04 19:50 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This contains all the code that directly interfaces with the RISC-V
memory model. While this code corforms to the current RISC-V ISA
specifications (user 2.2 and priv 1.10), the memory model is somewhat
underspecified in those documents. There is a working group that hopes
to produce a formal memory model by the end of the year, but my
understanding is that the basic definitions we're relying on here won't
change significantly.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/atomic.h | 337 ++++++++++++++++++++++++++++++++
arch/riscv/include/asm/barrier.h | 143 ++++++++++++++
arch/riscv/include/asm/bitops.h | 228 +++++++++++++++++++++
arch/riscv/include/asm/cacheflush.h | 39 ++++
arch/riscv/include/asm/cmpxchg.h | 138 +++++++++++++
arch/riscv/include/asm/io.h | 180 +++++++++++++++++
arch/riscv/include/asm/spinlock.h | 167 ++++++++++++++++
arch/riscv/include/asm/spinlock_types.h | 33 ++++
arch/riscv/include/asm/tlb.h | 24 +++
arch/riscv/include/asm/tlbflush.h | 64 ++++++
10 files changed, 1353 insertions(+)
create mode 100644 arch/riscv/include/asm/atomic.h
create mode 100644 arch/riscv/include/asm/barrier.h
create mode 100644 arch/riscv/include/asm/bitops.h
create mode 100644 arch/riscv/include/asm/cacheflush.h
create mode 100644 arch/riscv/include/asm/cmpxchg.h
create mode 100644 arch/riscv/include/asm/io.h
create mode 100644 arch/riscv/include/asm/spinlock.h
create mode 100644 arch/riscv/include/asm/spinlock_types.h
create mode 100644 arch/riscv/include/asm/tlb.h
create mode 100644 arch/riscv/include/asm/tlbflush.h
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
new file mode 100644
index 000000000000..e5a12cfa405a
--- /dev/null
+++ b/arch/riscv/include/asm/atomic.h
@@ -0,0 +1,337 @@
+/*
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _ASM_RISCV_ATOMIC_H
+#define _ASM_RISCV_ATOMIC_H
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+# include <asm-generic/atomic64.h>
+#else
+# if (__riscv_xlen < 64)
+# error "64-bit atomics require XLEN to be at least 64"
+# endif
+#endif
+
+#ifdef CONFIG_ISA_A
+
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+
+#define ATOMIC_INIT(i) { (i) }
+static __always_inline int atomic_read(const atomic_t *v)
+{
+ return READ_ONCE(v->counter);
+}
+static __always_inline void atomic_set(atomic_t *v, int i)
+{
+ WRITE_ONCE(v->counter, i);
+}
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC64_INIT(i) { (i) }
+static __always_inline int atomic64_read(const atomic64_t *v)
+{
+ return READ_ONCE(v->counter);
+}
+static __always_inline void atomic64_set(atomic64_t *v, int i)
+{
+ WRITE_ONCE(v->counter, i);
+}
+#endif
+
+/*
+ * First, the atomic ops that have no ordering constraints and therefor don't
+ * have the AQ or RL bits set. These don't return anything, so there's only
+ * one version to worry about.
+ */
+#define ATOMIC_OP(op, asm_op, c_op, I, asm_type, c_type, prefix) \
+static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
+{ \
+ __asm__ __volatile__ ( \
+ "amo" #asm_op "." #asm_type " zero, %1, %0" \
+ : "+A" (v->counter) \
+ : "r" (I)); \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, w, int, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, w, int, ) \
+ ATOMIC_OP (op, asm_op, c_op, I, d, long, 64)
+#endif
+
+ATOMIC_OPS(add, add, +, i)
+ATOMIC_OPS(sub, add, +, -i)
+/*
+ * FIXME: I could only find documentation that atomic_{add,sub,inc,dec} are
+ * barrier-free. I'm assuming that and/or/xor have the same constraints as the
+ * others.
+ */
+ATOMIC_OPS(and, and, &, i)
+ATOMIC_OPS( or, or, |, i)
+ATOMIC_OPS(xor, xor, ^, i)
+
+#undef ATOMIC_OP
+#undef ATOMIC_OPS
+
+/*
+ * Atomic ops that have ordered, relaxed, acquire, and relese variants.
+ * There's two flavors of these: the arithmatic ops have both fetch and return
+ * versions, while the logical ops only have fetch versions.
+ */
+#define ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix) \
+static __always_inline c_type atomic##prefix##_fetch_##op##c_or(c_type i, atomic##prefix##_t *v) \
+{ \
+ register c_type ret; \
+ __asm__ __volatile__ ( \
+ "amo" #asm_op "." #asm_type #asm_or " %2, %1, %0" \
+ : "+A" (v->counter), "=r" (ret) \
+ : "r" (I)); \
+ return ret; \
+}
+
+#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix) \
+static __always_inline c_type atomic##prefix##_##op##_return##c_or(int i, atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_fetch_##op##c_or(i, v) c_op I; \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w, int, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, d, long, 64) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#endif
+
+ATOMIC_OPS(add, add, +, i, , _relaxed)
+ATOMIC_OPS(add, add, +, i, .aq , _acquire)
+ATOMIC_OPS(add, add, +, i, .rl , _release)
+ATOMIC_OPS(add, add, +, i, .aqrl, )
+
+ATOMIC_OPS(sub, add, +, -i, , _relaxed)
+ATOMIC_OPS(sub, add, +, -i, .aq , _acquire)
+ATOMIC_OPS(sub, add, +, -i, .rl , _release)
+ATOMIC_OPS(sub, add, +, -i, .aqrl, )
+
+#undef ATOMIC_OPS
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w, int, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#endif
+
+ATOMIC_OPS(and, and, &, i, , _relaxed)
+ATOMIC_OPS(and, and, &, i, .aq , _acquire)
+ATOMIC_OPS(and, and, &, i, .rl , _release)
+ATOMIC_OPS(and, and, &, i, .aqrl, )
+
+ATOMIC_OPS( or, or, |, i, , _relaxed)
+ATOMIC_OPS( or, or, |, i, .aq , _acquire)
+ATOMIC_OPS( or, or, |, i, .rl , _release)
+ATOMIC_OPS( or, or, |, i, .aqrl, )
+
+ATOMIC_OPS(xor, xor, ^, i, , _relaxed)
+ATOMIC_OPS(xor, xor, ^, i, .aq , _acquire)
+ATOMIC_OPS(xor, xor, ^, i, .rl , _release)
+ATOMIC_OPS(xor, xor, ^, i, .aqrl, )
+
+#undef ATOMIC_OPS
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+
+/*
+ * The extra atomic operations that are constructed from one of the core
+ * AMO-based operations above (aside from sub, which is easier to fit above).
+ * These are required to perform a barrier, but they're OK this way because
+ * atomic_*_return is also required to perform a barrier.
+ */
+#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix) \
+static __always_inline bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_##func_op##_return(i, v) comp_op I; \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, func_op, comp_op, I) \
+ ATOMIC_OP (op, func_op, comp_op, I, int, )
+#else
+#define ATOMIC_OPS(op, func_op, comp_op, I) \
+ ATOMIC_OP (op, func_op, comp_op, I, int, ) \
+ ATOMIC_OP (op, func_op, comp_op, I, long, 64)
+#endif
+
+ATOMIC_OPS(add_and_test, add, ==, 0)
+ATOMIC_OPS(sub_and_test, sub, ==, 0)
+ATOMIC_OPS(add_negative, add, <, 0)
+
+#undef ATOMIC_OP
+#undef ATOMIC_OPS
+
+#define ATOMIC_OP(op, func_op, c_op, I, prefix) \
+static __always_inline void atomic##prefix##_##op(atomic##prefix##_t *v) \
+{ \
+ atomic##prefix##_##func_op(I, v); \
+}
+
+#define ATOMIC_FETCH_OP(op, func_op, c_op, I, prefix) \
+static __always_inline int atomic##prefix##_fetch_##op(atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_fetch_##func_op(I, v); \
+}
+
+#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, prefix) \
+static __always_inline int atomic##prefix##_##op##_return(atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_fetch_##op(v) c_op I; \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, ) \
+ ATOMIC_OP (op, asm_op, c_op, I, 64) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, 64) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, 64)
+#endif
+
+ATOMIC_OPS(inc, add, +, 1)
+ATOMIC_OPS(dec, add, +, -1)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+
+#define ATOMIC_OP(op, func_op, comp_op, I, prefix) \
+static __always_inline bool atomic##prefix##_##op(atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_##func_op##_return(v) comp_op I; \
+}
+
+ATOMIC_OP(inc_and_test, inc, ==, 0, )
+ATOMIC_OP(dec_and_test, dec, ==, 0, )
+#ifndef CONFIG_GENERIC_ATOMIC64
+ATOMIC_OP(inc_and_test, inc, ==, 0, 64)
+ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
+#endif
+
+#undef ATOMIC_OP
+
+/* This is required to provide a barrier on success. */
+static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+ register int prev, rc;
+
+ __asm__ __volatile__ (
+ "0:\n\t"
+ "lr.w.aqrl %0, %2\n\t"
+ "beq %0, %4, 1f\n\t"
+ "add %1, %0, %3\n\t"
+ "sc.w.aqrl %1, %1, %2\n\t"
+ "bnez %1, 0b\n\t"
+ "1:"
+ : "=&r" (prev), "=&r" (rc), "+A" (v->counter)
+ : "r" (a), "r" (u));
+ return prev;
+}
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+static __always_inline long atomic64_add_unless(atomic64_t *v, long a, long u)
+{
+ register long prev, rc;
+
+ __asm__ __volatile__ (
+ "0:\n\t"
+ "lr.d.aqrl %0, %2\n\t"
+ "beq %0, %4, 1f\n\t"
+ "add %1, %0, %3\n\t"
+ "sc.d.aqrl %1, %1, %2\n\t"
+ "bnez %1, 0b\n\t"
+ "1:"
+ : "=&r" (prev), "=&r" (rc), "+A" (v->counter)
+ : "r" (a), "r" (u));
+ return prev;
+}
+#endif
+
+/*
+ * The extra atomic operations that are constructed from one of the core
+ * LR/SC-based operations above.
+ */
+static __always_inline int atomic_inc_not_zero(atomic_t *v)
+{
+ return __atomic_add_unless(v, 1, 0);
+}
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+static __always_inline int atomic64_inc_not_zero(atomic64_t *v)
+{
+ return atomic64_add_unless(v, 1, 0);
+}
+#endif
+
+/*
+ * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
+ * {cmp,}xchg and the operations that return, so they need a barrier. We just
+ * use the other implementations directly.
+ */
+#define ATOMIC_OP(c_t, prefix, c_or, size, asm_or) \
+static __always_inline c_t atomic##prefix##_cmpxchg##c_or(atomic##prefix##_t *v, c_t o, c_t n) \
+{ \
+ return __cmpxchg(&(v->counter), o, n, size, asm_or, asm_or); \
+} \
+static __always_inline c_t atomic##prefix##_xchg##c_or(atomic##prefix##_t *v, c_t n) \
+{ \
+ return __xchg(n, &(v->counter), size, asm_or); \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(c_or, asm_or) \
+ ATOMIC_OP( int, , c_or, 4, asm_or)
+#else
+#define ATOMIC_OPS(c_or, asm_or) \
+ ATOMIC_OP( int, , c_or, 4, asm_or) \
+ ATOMIC_OP(long, 64, c_or, 8, asm_or)
+#endif
+
+ATOMIC_OPS( , .aqrl)
+ATOMIC_OPS(_acquire, .aq)
+ATOMIC_OPS(_release, .rl)
+ATOMIC_OPS(_relaxed, )
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP
+
+#else /* !CONFIG_ISA_A */
+
+#include <asm-generic/atomic.h>
+
+#endif /* CONFIG_ISA_A */
+
+#endif /* _ASM_RISCV_ATOMIC_H */
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
new file mode 100644
index 000000000000..cbe7bc5c506e
--- /dev/null
+++ b/arch/riscv/include/asm/barrier.h
@@ -0,0 +1,143 @@
+/*
+ * Based on arch/arm/include/asm/barrier.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2013 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ASM_RISCV_BARRIER_H
+#define _ASM_RISCV_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#define nop() __asm__ __volatile__ ("nop")
+
+#define RISCV_FENCE(p, s) \
+ __asm__ __volatile__ ("fence " #p "," #s : : : "memory")
+
+/* These barries need to enforce ordering on both devices or memory. */
+#define mb() RISCV_FENCE(iorw,iorw)
+#define rmb() RISCV_FENCE(ir,ir)
+#define wmb() RISCV_FENCE(ow,ow)
+
+/* These barries do not need to enforce ordering on devices, just memory. */
+#define smp_mb() RISCV_FENCE(rw,rw)
+#define smp_rmb() RISCV_FENCE(r,r)
+#define smp_wmb() RISCV_FENCE(w,w)
+
+/*
+ * Our atomic operations set the AQ and RL bits and therefor we don't need to
+ * fence around atomics.
+ */
+#define __smb_mb__before_atomic() barrier()
+#define __smb_mb__after_atomic() barrier()
+
+/*
+ * These barries are meant to prevent memory operations inside a spinlock from
+ * moving outside of that spinlock. Since we set the AQ and RL bits when
+ * entering or leaving spinlocks, no additional fence needs to be performed.
+ */
+#define smb_mb__before_spinlock() barrier()
+#define smb_mb__after_spinlock() barrier()
+
+/* FIXME: I don't think RISC-V is allowed to perform a speculative load. */
+#define smp_acquire__after_ctrl_dep() barrier()
+
+/*
+ * The RISC-V ISA doesn't support byte or half-word AMOs, so we fall back to a
+ * regular store and a fence here. Otherwise we emit an AMO with an AQ or RL
+ * bit set and allow the microarchitecture to avoid the other half of the AMO.
+ */
+#define __smp_store_release(p, v) \
+do { \
+ union { typeof(*p) __val; char __c[1]; } __u = \
+ { .__val = (__force typeof(*p)) (v) }; \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 1: \
+ case 2: \
+ smb_mb(); \
+ WRITE_ONCE(*p, __u.__val); \
+ break; \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "amoswap.w.rl zero, %1, %0" \
+ : "+A" (*p), "r" (__u.__val) \
+ : \
+ : "memory"); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "amoswap.d.rl zero, %1, %0" \
+ : "+A" (*p), "r" (__u.__val) \
+ : \
+ : "memory"); \
+ break; \
+ } \
+} while (0)
+
+#define __smp_load_acquire(p) \
+do { \
+ union { typeof(*p) __val; char __c[1]; } __u = \
+ { .__val = (__force typeof(*p)) (v) }; \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 1: \
+ case 2: \
+ __u.__val = READ_ONCE(*p); \
+ smb_mb(); \
+ break; \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "amoor.w.aq %1, zero, %0" \
+ : "+A" (*p) \
+ : "=r" (__u.__val) \
+ : "memory"); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "amoor.d.aq %1, zero, %0" \
+ : "+A" (*p) \
+ : "=r" (__u.__val) \
+ : "memory"); \
+ break; \
+ } \
+ __u.__val; \
+} while (0)
+
+/*
+ * The default implementation of this uses READ_ONCE and
+ * smp_acquire__after_ctrl_dep, but since we can directly do an ACQUIRE load we
+ * can avoid the extra barrier.
+ */
+#define smp_cond_load_acquire(ptr, cond_expr) ({ \
+ typeof(ptr) __PTR = (ptr); \
+ typeof(*ptr) VAL; \
+ for (;;) { \
+ VAL = __smp_load_acquire(__PTR); \
+ if (cond_expr) \
+ break; \
+ cpu_relax(); \
+ } \
+ smp_acquire__after_ctrl_dep(); \
+ VAL; \
+})
+
+#include <asm-generic/barrier.h>
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_BARRIER_H */
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
new file mode 100644
index 000000000000..27e47858c6b1
--- /dev/null
+++ b/arch/riscv/include/asm/bitops.h
@@ -0,0 +1,228 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_BITOPS_H
+#define _ASM_RISCV_BITOPS_H
+
+#ifndef _LINUX_BITOPS_H
+#error "Only <linux/bitops.h> can be included directly"
+#endif /* _LINUX_BITOPS_H */
+
+#ifdef __KERNEL__
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <asm/barrier.h>
+#include <asm/bitsperlong.h>
+
+#ifdef CONFIG_ISA_A
+
+#ifndef smp_mb__before_clear_bit
+#define smp_mb__before_clear_bit() smp_mb()
+#define smp_mb__after_clear_bit() smp_mb()
+#endif /* smp_mb__before_clear_bit */
+
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/ffs.h>
+
+#include <asm-generic/bitops/hweight.h>
+
+#if (BITS_PER_LONG == 64)
+#define __AMO(op) "amo" #op ".d"
+#elif (BITS_PER_LONG == 32)
+#define __AMO(op) "amo" #op ".w"
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+#define __test_and_op_bit(op, mod, nr, addr) \
+({ \
+ unsigned long __res, __mask; \
+ __mask = BIT_MASK(nr); \
+ __asm__ __volatile__ ( \
+ __AMO(op) " %0, %2, %1" \
+ : "=r" (__res), "+A" (addr[BIT_WORD(nr)]) \
+ : "r" (mod(__mask))); \
+ ((__res & __mask) != 0); \
+})
+
+#define __op_bit(op, mod, nr, addr) \
+ __asm__ __volatile__ ( \
+ __AMO(op) " zero, %1, %0" \
+ : "+A" (addr[BIT_WORD(nr)]) \
+ : "r" (mod(BIT_MASK(nr))))
+
+/* Bitmask modifiers */
+#define __NOP(x) (x)
+#define __NOT(x) (~(x))
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It may be reordered on other architectures than x86.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+ return __test_and_op_bit(or, __NOP, nr, addr);
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It can be reordered on other architectures other than x86.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+ return __test_and_op_bit(and, __NOT, nr, addr);
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+ return __test_and_op_bit(xor, __NOP, nr, addr);
+}
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered. See __set_bit()
+ * if you do not require the atomic guarantees.
+ *
+ * Note: there are no guarantees that this function will not be reordered
+ * on non x86 architectures, so if you are writing portable code,
+ * make sure not to rely on its reordering guarantees.
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void set_bit(int nr, volatile unsigned long *addr)
+{
+ __op_bit(or, __NOP, nr, addr);
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and may not be reordered. However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * in order to ensure changes are visible on other processors.
+ */
+static inline void clear_bit(int nr, volatile unsigned long *addr)
+{
+ __op_bit(and, __NOT, nr, addr);
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered. It may be
+ * reordered on other architectures than x86.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void change_bit(int nr, volatile unsigned long *addr)
+{
+ __op_bit(xor, __NOP, nr, addr);
+}
+
+/**
+ * test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and provides acquire barrier semantics.
+ * It can be used to implement bit locks.
+ */
+static inline int test_and_set_bit_lock(
+ unsigned long nr, volatile unsigned long *addr)
+{
+ return test_and_set_bit(nr, addr);
+}
+
+/**
+ * clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ */
+static inline void clear_bit_unlock(
+ unsigned long nr, volatile unsigned long *addr)
+{
+ clear_bit(nr, addr);
+}
+
+/**
+ * __clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is like clear_bit_unlock, however it is not atomic.
+ * It does provide release barrier semantics so it can be used to unlock
+ * a bit lock, however it would only be used if no other CPU can modify
+ * any bits in the memory until the lock is released (a good example is
+ * if the bit lock itself protects access to the other bits in the word).
+ */
+static inline void __clear_bit_unlock(
+ unsigned long nr, volatile unsigned long *addr)
+{
+ clear_bit(nr, addr);
+}
+
+#undef __test_and_op_bit
+#undef __op_bit
+#undef __NOP
+#undef __NOT
+#undef __AMO
+
+#include <asm-generic/bitops/non-atomic.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic.h>
+
+#else /* !CONFIG_ISA_A */
+
+#include <asm-generic/bitops.h>
+
+#endif /* CONFIG_ISA_A */
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_RISCV_BITOPS_H */
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
new file mode 100644
index 000000000000..0595585013b0
--- /dev/null
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -0,0 +1,39 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_CACHEFLUSH_H
+#define _ASM_RISCV_CACHEFLUSH_H
+
+#include <asm-generic/cacheflush.h>
+
+#undef flush_icache_range
+#undef flush_icache_user_range
+
+static inline void local_flush_icache_all(void)
+{
+ asm volatile ("fence.i" ::: "memory");
+}
+
+#ifndef CONFIG_SMP
+
+#define flush_icache_range(start, end) local_flush_icache_all()
+#define flush_icache_user_range(vma, pg, addr, len) local_flush_icache_all()
+
+#else /* CONFIG_SMP */
+
+#define flush_icache_range(start, end) sbi_remote_fence_i(0)
+#define flush_icache_user_range(vma, pg, addr, len) sbi_remote_fence_i(0)
+
+#endif /* CONFIG_SMP */
+
+#endif /* _ASM_RISCV_CACHEFLUSH_H */
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..81025c056412
--- /dev/null
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -0,0 +1,138 @@
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_CMPXCHG_H
+#define _ASM_RISCV_CMPXCHG_H
+
+#include <linux/bug.h>
+
+#ifdef CONFIG_ISA_A
+
+#include <asm/barrier.h>
+
+#define __xchg(new, ptr, size, asm_or) \
+({ \
+ __typeof__(ptr) __ptr = (ptr); \
+ __typeof__(new) __new = (new); \
+ __typeof__(*(ptr)) __ret; \
+ switch (size) { \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "amoswap.w" #asm_or " %0, %2, %1" \
+ : "=r" (__ret), "+A" (*__ptr) \
+ : "r" (__new)); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "amoswap.d" #asm_or " %0, %2, %1" \
+ : "=r" (__ret), "+A" (*__ptr) \
+ : "r" (__new)); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ __ret; \
+})
+
+#define xchg(ptr, x) (__xchg((x), (ptr), sizeof(*(ptr)), .aqrl))
+
+#define xchg32(ptr, x) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
+ xchg((ptr), (x)); \
+})
+
+#define xchg64(ptr, x) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ xchg((ptr), (x)); \
+})
+
+/*
+ * Atomic compare and exchange. Compare OLD with MEM, if identical,
+ * store NEW in MEM. Return the initial value in MEM. Success is
+ * indicated by comparing RETURN with OLD.
+ */
+#define __cmpxchg(ptr, old, new, size, lrb, scb) \
+({ \
+ __typeof__(ptr) __ptr = (ptr); \
+ __typeof__(old) __old = (old); \
+ __typeof__(new) __new = (new); \
+ __typeof__(*(ptr)) __ret; \
+ register unsigned int __rc; \
+ switch (size) { \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "0:" \
+ "lr.w" #scb " %0, %2\n" \
+ "bne %0, %z3, 1f\n" \
+ "sc.w" #lrb " %1, %z4, %2\n" \
+ "bnez %1, 0b\n" \
+ "1:" \
+ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
+ : "rJ" (__old), "rJ" (__new)); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "0:" \
+ "lr.d" #scb " %0, %2\n" \
+ "bne %0, %z3, 1f\n" \
+ "sc.d" #lrb " %1, %z4, %2\n" \
+ "bnez %1, 0b\n" \
+ "1:" \
+ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
+ : "rJ" (__old), "rJ" (__new)); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ __ret; \
+})
+
+#define cmpxchg(ptr, o, n) \
+ (__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), .aqrl, .aqrl))
+
+#define cmpxchg_local(ptr, o, n) \
+ (__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), , ))
+
+#define cmpxchg32(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
+ cmpxchg((ptr), (o), (n)); \
+})
+
+#define cmpxchg32_local(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
+ cmpxchg_local((ptr), (o), (n)); \
+})
+
+#define cmpxchg64(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ cmpxchg((ptr), (o), (n)); \
+})
+
+#define cmpxchg64_local(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ cmpxchg_local((ptr), (o), (n)); \
+})
+
+#else /* !CONFIG_ISA_A */
+
+#include <asm-generic/cmpxchg.h>
+
+#endif /* CONFIG_ISA_A */
+
+#endif /* _ASM_RISCV_CMPXCHG_H */
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
new file mode 100644
index 000000000000..c47177cb6660
--- /dev/null
+++ b/arch/riscv/include/asm/io.h
@@ -0,0 +1,180 @@
+/*
+ * {read,write}{b,w,l,q} based on arch/arm64/include/asm/io.h
+ * which was based on arch/arm/include/io.h
+ *
+ * Copyright (C) 1996-2000 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_IO_H
+#define _ASM_RISCV_IO_H
+
+#ifdef CONFIG_MMU
+
+extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
+
+/*
+ * The RISC-V ISA doesn't yet specify how to query of modify PMAs, so we can't
+ * change the properties of memory regions. This should be fixed by the
+ * upcoming platform spec.
+ */
+#define ioremap_nocache(addr, size) ioremap((addr), (size))
+#define ioremap_wc(addr, size) ioremap((addr), (size))
+#define ioremap_wt(addr, size) ioremap((addr), (size))
+
+extern void iounmap(void __iomem *addr);
+
+#endif /* CONFIG_MMU */
+
+/* Generic IO read/write. These perform native-endian accesses. */
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
+{
+ asm volatile("sb %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 val, volatile void __iomem *addr)
+{
+ asm volatile("sh %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 val, volatile void __iomem *addr)
+{
+ asm volatile("sw %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#ifdef __riscv64
+#define __raw_writeq __raw_writeq
+static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
+{
+ asm volatile("sd %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+#endif
+
+#define __raw_readb __raw_readb
+static inline u8 __raw_readb(const volatile void __iomem *addr)
+{
+ u8 val;
+
+ asm volatile("lb %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+
+#define __raw_readw __raw_readw
+static inline u16 __raw_readw(const volatile void __iomem *addr)
+{
+ u16 val;
+
+ asm volatile("lh %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+
+#define __raw_readl __raw_readl
+static inline u32 __raw_readl(const volatile void __iomem *addr)
+{
+ u32 val;
+
+ asm volatile("lw %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+
+#ifdef __riscv64
+#define __raw_readq __raw_readq
+static inline u64 __raw_readq(const volatile void __iomem *addr)
+{
+ u64 val;
+
+ asm volatile("ld %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+#endif
+
+/*
+ * FIXME: I'm flip-flopping on whether or not we should keep this or enforce
+ * the ordering with I/O on spinlocks. The worry is that drivers won't get
+ * this correct, but I also don't want to introduce a fence into the lock code
+ * that otherwise only uses AMOs and LR/SC. For now I'm leaving this here:
+ * "w,o" is sufficient to ensure that all writes to the device has completed
+ * before the write to the spinlock is allowed to commit. I surmised this from
+ * reading "ACQUIRES VS I/O ACCESSES" in memory-barries.txt.
+ */
+#define mmiowb() __asm__ __volatile__ ("fence o,w" : : : "memory");
+
+/*
+ * Unordered I/O memory access primitives. These are even more relaxed than
+ * the relaxed versions, as they don't even order accesses between successive
+ * operations to the I/O regions.
+ */
+#define readb_cpu(c) ({ u8 __r = __raw_readb(c); __r; })
+#define readw_cpu(c) ({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; })
+#define readl_cpu(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
+#define readq_cpu(c) ({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; })
+
+#define writeb_cpu(v,c) ((void)__raw_writeb((v),(c)))
+#define writew_cpu(v,c) ((void)__raw_writew((__force u16)cpu_to_le16(v),(c)))
+#define writel_cpu(v,c) ((void)__raw_writel((__force u32)cpu_to_le32(v),(c)))
+#define writeq_cpu(v,c) ((void)__raw_writeq((__force u64)cpu_to_le64(v),(c)))
+
+/*
+ * Relaxed I/O memory access primitives. These follow the Device memory
+ * ordering rules but do not guarantee any ordering relative to Normal memory
+ * accesses. The memory barries here are necessary as RISC-V doesn't define
+ * any ordering constraints on accesses to the device I/O space. These are
+ * defined to order the indicated access (either a read or write) with all
+ * other I/O memory accesses.
+ */
+/*
+ * FIXME: The platform spec will define the default Linux-capable platform to
+ * have some extra IO ordering constraints that will make these fences
+ * unnecessary.
+ */
+#define __iorrmb() __asm__ __volatile__ ("fence i,io" : : : "memory");
+#define __iorwmb() __asm__ __volatile__ ("fence io,o" : : : "memory");
+
+#define readb_relaxed(c) ({ u8 __v = readb_cpu(c); __iorrmb(); __v; })
+#define readw_relaxed(c) ({ u16 __v = readw_cpu(c); __iorrmb(); __v; })
+#define readl_relaxed(c) ({ u32 __v = readl_cpu(c); __iorrmb(); __v; })
+#define readq_relaxed(c) ({ u64 __v = readq_cpu(c); __iorrmb(); __v; })
+
+#define writeb_relaxed(v,c) ({ __iorwmb(); writeb_cpu((v),(c)); })
+#define writew_relaxed(v,c) ({ __iorwmb(); writew_cpu((v),(c)); })
+#define writel_relaxed(v,c) ({ __iorwmb(); writel_cpu((v),(c)); })
+#define writeq_relaxed(v,c) ({ __iorwmb(); writeq_cpu((v),(c)); })
+
+/*
+ * I/O memory access primitives. Reads are ordered relative to any
+ * following Normal memory access. Writes are ordered relative to any prior
+ * Normal memory access. The memory barriers here are necessary as RISC-V
+ * doesn't define any ordering between the memory space and the I/O space.
+ * They may be stronger than necessary ("i,r" and "w,o" might be sufficient),
+ * but I feel kind of queasy making these weaker in any manner than the relaxed
+ * versions above.
+ */
+#define __iormb() __asm__ __volatile__ ("fence i,ior" : : : "memory");
+#define __iowmb() __asm__ __volatile__ ("fence iow,o" : : : "memory");
+
+#define readb(c) ({ u8 __v = readb_cpu(c); __iormb(); __v; })
+#define readw(c) ({ u16 __v = readw_cpu(c); __iormb(); __v; })
+#define readl(c) ({ u32 __v = readl_cpu(c); __iormb(); __v; })
+#define readq(c) ({ u64 __v = readq_cpu(c); __iormb(); __v; })
+
+#define writeb(v,c) ({ __iowmb(); writeb_cpu((v),(c)); })
+#define writew(v,c) ({ __iowmb(); writew_cpu((v),(c)); })
+#define writel(v,c) ({ __iowmb(); writel_cpu((v),(c)); })
+#define writeq(v,c) ({ __iowmb(); writeq_cpu((v),(c)); })
+
+#include <asm-generic/io.h>
+
+#endif /* _ASM_RISCV_IO_H */
diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
new file mode 100644
index 000000000000..54ed73bfa972
--- /dev/null
+++ b/arch/riscv/include/asm/spinlock.h
@@ -0,0 +1,167 @@
+/*
+ * Copyright (C) 2015 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.
+ */
+
+#ifndef _ASM_RISCV_SPINLOCK_H
+#define _ASM_RISCV_SPINLOCK_H
+
+#include <linux/kernel.h>
+#include <asm/current.h>
+
+/*
+ * Simple spin lock operations. These provide no fairness guarantees.
+ */
+
+/* FIXME: Replace this with a ticket lock, like MIPS. */
+
+#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
+#define arch_spin_is_locked(x) ((x)->lock != 0)
+#define arch_spin_unlock_wait(x) \
+ do { cpu_relax(); } while ((x)->lock)
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+ __asm__ __volatile__ (
+ "amoswap.w.rl x0, x0, %0"
+ : "=A" (lock->lock)
+ :: "memory");
+}
+
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+ int tmp = 1, busy;
+
+ __asm__ __volatile__ (
+ "amoswap.w.aq %0, %2, %1"
+ : "=r" (busy), "+A" (lock->lock)
+ : "r" (tmp)
+ : "memory");
+
+ return !busy;
+}
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+ while (1) {
+ if (arch_spin_is_locked(lock))
+ continue;
+
+ if (arch_spin_trylock(lock))
+ break;
+ }
+}
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+ smp_rmb();
+ do {
+ cpu_relax();
+ } while (arch_spin_is_locked(lock));
+ smp_acquire__after_ctrl_dep();
+}
+
+/***********************************************************/
+
+static inline int arch_read_can_lock(arch_rwlock_t *lock)
+{
+ return lock->lock >= 0;
+}
+
+static inline int arch_write_can_lock(arch_rwlock_t *lock)
+{
+ return lock->lock == 0;
+}
+
+static inline void arch_read_lock(arch_rwlock_t *lock)
+{
+ int tmp;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bltz %1, 1b\n"
+ " addi %1, %1, 1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ : "+A" (lock->lock), "=&r" (tmp)
+ :: "memory");
+}
+
+static inline void arch_write_lock(arch_rwlock_t *lock)
+{
+ int tmp;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bnez %1, 1b\n"
+ " li %1, -1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ : "+A" (lock->lock), "=&r" (tmp)
+ :: "memory");
+}
+
+static inline int arch_read_trylock(arch_rwlock_t *lock)
+{
+ int busy;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bltz %1, 1f\n"
+ " addi %1, %1, 1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ "1:\n"
+ : "+A" (lock->lock), "=&r" (busy)
+ :: "memory");
+
+ return !busy;
+}
+
+static inline int arch_write_trylock(arch_rwlock_t *lock)
+{
+ int busy;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bnez %1, 1f\n"
+ " li %1, -1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ "1:\n"
+ : "+A" (lock->lock), "=&r" (busy)
+ :: "memory");
+
+ return !busy;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *lock)
+{
+ __asm__ __volatile__(
+ "amoadd.w.rl x0, %1, %0"
+ : "+A" (lock->lock)
+ : "r" (-1)
+ : "memory");
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *lock)
+{
+ __asm__ __volatile__ (
+ "amoswap.w.rl x0, x0, %0"
+ : "=A" (lock->lock)
+ :: "memory");
+}
+
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
+#endif /* _ASM_RISCV_SPINLOCK_H */
diff --git a/arch/riscv/include/asm/spinlock_types.h b/arch/riscv/include/asm/spinlock_types.h
new file mode 100644
index 000000000000..83ac4ac9e2ac
--- /dev/null
+++ b/arch/riscv/include/asm/spinlock_types.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SPINLOCK_TYPES_H
+#define _ASM_RISCV_SPINLOCK_TYPES_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+# error "please don't include this file directly"
+#endif
+
+typedef struct {
+ volatile unsigned int lock;
+} arch_spinlock_t;
+
+#define __ARCH_SPIN_LOCK_UNLOCKED { 0 }
+
+typedef struct {
+ volatile unsigned int lock;
+} arch_rwlock_t;
+
+#define __ARCH_RW_LOCK_UNLOCKED { 0 }
+
+#endif
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
new file mode 100644
index 000000000000..c229509288ea
--- /dev/null
+++ b/arch/riscv/include/asm/tlb.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_TLB_H
+#define _ASM_RISCV_TLB_H
+
+#include <asm-generic/tlb.h>
+
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+ flush_tlb_mm(tlb->mm);
+}
+
+#endif /* _ASM_RISCV_TLB_H */
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
new file mode 100644
index 000000000000..5ee4ae370b5e
--- /dev/null
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_TLBFLUSH_H
+#define _ASM_RISCV_TLBFLUSH_H
+
+#ifdef CONFIG_MMU
+
+/* Flush entire local TLB */
+static inline void local_flush_tlb_all(void)
+{
+ __asm__ __volatile__ ("sfence.vma" : : : "memory");
+}
+
+/* Flush one page from local TLB */
+static inline void local_flush_tlb_page(unsigned long addr)
+{
+ __asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory");
+}
+
+#ifndef CONFIG_SMP
+
+#define flush_tlb_all() local_flush_tlb_all()
+#define flush_tlb_page(vma, addr) local_flush_tlb_page(addr)
+#define flush_tlb_range(vma, start, end) local_flush_tlb_all()
+
+#else /* CONFIG_SMP */
+
+#include <asm/sbi.h>
+
+#define flush_tlb_all() sbi_remote_sfence_vma(0, 0, -1)
+#define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0)
+#define flush_tlb_range(vma, start, end) \
+ sbi_remote_sfence_vma(0, start, (end) - (start))
+
+#endif /* CONFIG_SMP */
+
+/* Flush the TLB entries of the specified mm context */
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+ flush_tlb_all();
+}
+
+/* Flush a range of kernel pages */
+static inline void flush_tlb_kernel_range(unsigned long start,
+ unsigned long end)
+{
+ flush_tlb_all();
+}
+
+#endif /* CONFIG_MMU */
+
+#endif /* _ASM_RISCV_TLBFLUSH_H */
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 2/9] RISC-V: Atomic and Locking Code
@ 2017-07-04 19:50 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This contains all the code that directly interfaces with the RISC-V
memory model. While this code corforms to the current RISC-V ISA
specifications (user 2.2 and priv 1.10), the memory model is somewhat
underspecified in those documents. There is a working group that hopes
to produce a formal memory model by the end of the year, but my
understanding is that the basic definitions we're relying on here won't
change significantly.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/atomic.h | 337 ++++++++++++++++++++++++++++++++
arch/riscv/include/asm/barrier.h | 143 ++++++++++++++
arch/riscv/include/asm/bitops.h | 228 +++++++++++++++++++++
arch/riscv/include/asm/cacheflush.h | 39 ++++
arch/riscv/include/asm/cmpxchg.h | 138 +++++++++++++
arch/riscv/include/asm/io.h | 180 +++++++++++++++++
arch/riscv/include/asm/spinlock.h | 167 ++++++++++++++++
arch/riscv/include/asm/spinlock_types.h | 33 ++++
arch/riscv/include/asm/tlb.h | 24 +++
arch/riscv/include/asm/tlbflush.h | 64 ++++++
10 files changed, 1353 insertions(+)
create mode 100644 arch/riscv/include/asm/atomic.h
create mode 100644 arch/riscv/include/asm/barrier.h
create mode 100644 arch/riscv/include/asm/bitops.h
create mode 100644 arch/riscv/include/asm/cacheflush.h
create mode 100644 arch/riscv/include/asm/cmpxchg.h
create mode 100644 arch/riscv/include/asm/io.h
create mode 100644 arch/riscv/include/asm/spinlock.h
create mode 100644 arch/riscv/include/asm/spinlock_types.h
create mode 100644 arch/riscv/include/asm/tlb.h
create mode 100644 arch/riscv/include/asm/tlbflush.h
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
new file mode 100644
index 000000000000..e5a12cfa405a
--- /dev/null
+++ b/arch/riscv/include/asm/atomic.h
@@ -0,0 +1,337 @@
+/*
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _ASM_RISCV_ATOMIC_H
+#define _ASM_RISCV_ATOMIC_H
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+# include <asm-generic/atomic64.h>
+#else
+# if (__riscv_xlen < 64)
+# error "64-bit atomics require XLEN to be at least 64"
+# endif
+#endif
+
+#ifdef CONFIG_ISA_A
+
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+
+#define ATOMIC_INIT(i) { (i) }
+static __always_inline int atomic_read(const atomic_t *v)
+{
+ return READ_ONCE(v->counter);
+}
+static __always_inline void atomic_set(atomic_t *v, int i)
+{
+ WRITE_ONCE(v->counter, i);
+}
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC64_INIT(i) { (i) }
+static __always_inline int atomic64_read(const atomic64_t *v)
+{
+ return READ_ONCE(v->counter);
+}
+static __always_inline void atomic64_set(atomic64_t *v, int i)
+{
+ WRITE_ONCE(v->counter, i);
+}
+#endif
+
+/*
+ * First, the atomic ops that have no ordering constraints and therefor don't
+ * have the AQ or RL bits set. These don't return anything, so there's only
+ * one version to worry about.
+ */
+#define ATOMIC_OP(op, asm_op, c_op, I, asm_type, c_type, prefix) \
+static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
+{ \
+ __asm__ __volatile__ ( \
+ "amo" #asm_op "." #asm_type " zero, %1, %0" \
+ : "+A" (v->counter) \
+ : "r" (I)); \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, w, int, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, w, int, ) \
+ ATOMIC_OP (op, asm_op, c_op, I, d, long, 64)
+#endif
+
+ATOMIC_OPS(add, add, +, i)
+ATOMIC_OPS(sub, add, +, -i)
+/*
+ * FIXME: I could only find documentation that atomic_{add,sub,inc,dec} are
+ * barrier-free. I'm assuming that and/or/xor have the same constraints as the
+ * others.
+ */
+ATOMIC_OPS(and, and, &, i)
+ATOMIC_OPS( or, or, |, i)
+ATOMIC_OPS(xor, xor, ^, i)
+
+#undef ATOMIC_OP
+#undef ATOMIC_OPS
+
+/*
+ * Atomic ops that have ordered, relaxed, acquire, and relese variants.
+ * There's two flavors of these: the arithmatic ops have both fetch and return
+ * versions, while the logical ops only have fetch versions.
+ */
+#define ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix) \
+static __always_inline c_type atomic##prefix##_fetch_##op##c_or(c_type i, atomic##prefix##_t *v) \
+{ \
+ register c_type ret; \
+ __asm__ __volatile__ ( \
+ "amo" #asm_op "." #asm_type #asm_or " %2, %1, %0" \
+ : "+A" (v->counter), "=r" (ret) \
+ : "r" (I)); \
+ return ret; \
+}
+
+#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix) \
+static __always_inline c_type atomic##prefix##_##op##_return##c_or(int i, atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_fetch_##op##c_or(i, v) c_op I; \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w, int, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, d, long, 64) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#endif
+
+ATOMIC_OPS(add, add, +, i, , _relaxed)
+ATOMIC_OPS(add, add, +, i, .aq , _acquire)
+ATOMIC_OPS(add, add, +, i, .rl , _release)
+ATOMIC_OPS(add, add, +, i, .aqrl, )
+
+ATOMIC_OPS(sub, add, +, -i, , _relaxed)
+ATOMIC_OPS(sub, add, +, -i, .aq , _acquire)
+ATOMIC_OPS(sub, add, +, -i, .rl , _release)
+ATOMIC_OPS(sub, add, +, -i, .aqrl, )
+
+#undef ATOMIC_OPS
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w, int, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#endif
+
+ATOMIC_OPS(and, and, &, i, , _relaxed)
+ATOMIC_OPS(and, and, &, i, .aq , _acquire)
+ATOMIC_OPS(and, and, &, i, .rl , _release)
+ATOMIC_OPS(and, and, &, i, .aqrl, )
+
+ATOMIC_OPS( or, or, |, i, , _relaxed)
+ATOMIC_OPS( or, or, |, i, .aq , _acquire)
+ATOMIC_OPS( or, or, |, i, .rl , _release)
+ATOMIC_OPS( or, or, |, i, .aqrl, )
+
+ATOMIC_OPS(xor, xor, ^, i, , _relaxed)
+ATOMIC_OPS(xor, xor, ^, i, .aq , _acquire)
+ATOMIC_OPS(xor, xor, ^, i, .rl , _release)
+ATOMIC_OPS(xor, xor, ^, i, .aqrl, )
+
+#undef ATOMIC_OPS
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+
+/*
+ * The extra atomic operations that are constructed from one of the core
+ * AMO-based operations above (aside from sub, which is easier to fit above).
+ * These are required to perform a barrier, but they're OK this way because
+ * atomic_*_return is also required to perform a barrier.
+ */
+#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix) \
+static __always_inline bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_##func_op##_return(i, v) comp_op I; \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, func_op, comp_op, I) \
+ ATOMIC_OP (op, func_op, comp_op, I, int, )
+#else
+#define ATOMIC_OPS(op, func_op, comp_op, I) \
+ ATOMIC_OP (op, func_op, comp_op, I, int, ) \
+ ATOMIC_OP (op, func_op, comp_op, I, long, 64)
+#endif
+
+ATOMIC_OPS(add_and_test, add, ==, 0)
+ATOMIC_OPS(sub_and_test, sub, ==, 0)
+ATOMIC_OPS(add_negative, add, <, 0)
+
+#undef ATOMIC_OP
+#undef ATOMIC_OPS
+
+#define ATOMIC_OP(op, func_op, c_op, I, prefix) \
+static __always_inline void atomic##prefix##_##op(atomic##prefix##_t *v) \
+{ \
+ atomic##prefix##_##func_op(I, v); \
+}
+
+#define ATOMIC_FETCH_OP(op, func_op, c_op, I, prefix) \
+static __always_inline int atomic##prefix##_fetch_##op(atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_fetch_##func_op(I, v); \
+}
+
+#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, prefix) \
+static __always_inline int atomic##prefix##_##op##_return(atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_fetch_##op(v) c_op I; \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, ) \
+ ATOMIC_OP (op, asm_op, c_op, I, 64) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, 64) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, 64)
+#endif
+
+ATOMIC_OPS(inc, add, +, 1)
+ATOMIC_OPS(dec, add, +, -1)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+
+#define ATOMIC_OP(op, func_op, comp_op, I, prefix) \
+static __always_inline bool atomic##prefix##_##op(atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_##func_op##_return(v) comp_op I; \
+}
+
+ATOMIC_OP(inc_and_test, inc, ==, 0, )
+ATOMIC_OP(dec_and_test, dec, ==, 0, )
+#ifndef CONFIG_GENERIC_ATOMIC64
+ATOMIC_OP(inc_and_test, inc, ==, 0, 64)
+ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
+#endif
+
+#undef ATOMIC_OP
+
+/* This is required to provide a barrier on success. */
+static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+ register int prev, rc;
+
+ __asm__ __volatile__ (
+ "0:\n\t"
+ "lr.w.aqrl %0, %2\n\t"
+ "beq %0, %4, 1f\n\t"
+ "add %1, %0, %3\n\t"
+ "sc.w.aqrl %1, %1, %2\n\t"
+ "bnez %1, 0b\n\t"
+ "1:"
+ : "=&r" (prev), "=&r" (rc), "+A" (v->counter)
+ : "r" (a), "r" (u));
+ return prev;
+}
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+static __always_inline long atomic64_add_unless(atomic64_t *v, long a, long u)
+{
+ register long prev, rc;
+
+ __asm__ __volatile__ (
+ "0:\n\t"
+ "lr.d.aqrl %0, %2\n\t"
+ "beq %0, %4, 1f\n\t"
+ "add %1, %0, %3\n\t"
+ "sc.d.aqrl %1, %1, %2\n\t"
+ "bnez %1, 0b\n\t"
+ "1:"
+ : "=&r" (prev), "=&r" (rc), "+A" (v->counter)
+ : "r" (a), "r" (u));
+ return prev;
+}
+#endif
+
+/*
+ * The extra atomic operations that are constructed from one of the core
+ * LR/SC-based operations above.
+ */
+static __always_inline int atomic_inc_not_zero(atomic_t *v)
+{
+ return __atomic_add_unless(v, 1, 0);
+}
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+static __always_inline int atomic64_inc_not_zero(atomic64_t *v)
+{
+ return atomic64_add_unless(v, 1, 0);
+}
+#endif
+
+/*
+ * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
+ * {cmp,}xchg and the operations that return, so they need a barrier. We just
+ * use the other implementations directly.
+ */
+#define ATOMIC_OP(c_t, prefix, c_or, size, asm_or) \
+static __always_inline c_t atomic##prefix##_cmpxchg##c_or(atomic##prefix##_t *v, c_t o, c_t n) \
+{ \
+ return __cmpxchg(&(v->counter), o, n, size, asm_or, asm_or); \
+} \
+static __always_inline c_t atomic##prefix##_xchg##c_or(atomic##prefix##_t *v, c_t n) \
+{ \
+ return __xchg(n, &(v->counter), size, asm_or); \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(c_or, asm_or) \
+ ATOMIC_OP( int, , c_or, 4, asm_or)
+#else
+#define ATOMIC_OPS(c_or, asm_or) \
+ ATOMIC_OP( int, , c_or, 4, asm_or) \
+ ATOMIC_OP(long, 64, c_or, 8, asm_or)
+#endif
+
+ATOMIC_OPS( , .aqrl)
+ATOMIC_OPS(_acquire, .aq)
+ATOMIC_OPS(_release, .rl)
+ATOMIC_OPS(_relaxed, )
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP
+
+#else /* !CONFIG_ISA_A */
+
+#include <asm-generic/atomic.h>
+
+#endif /* CONFIG_ISA_A */
+
+#endif /* _ASM_RISCV_ATOMIC_H */
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
new file mode 100644
index 000000000000..cbe7bc5c506e
--- /dev/null
+++ b/arch/riscv/include/asm/barrier.h
@@ -0,0 +1,143 @@
+/*
+ * Based on arch/arm/include/asm/barrier.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2013 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ASM_RISCV_BARRIER_H
+#define _ASM_RISCV_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#define nop() __asm__ __volatile__ ("nop")
+
+#define RISCV_FENCE(p, s) \
+ __asm__ __volatile__ ("fence " #p "," #s : : : "memory")
+
+/* These barries need to enforce ordering on both devices or memory. */
+#define mb() RISCV_FENCE(iorw,iorw)
+#define rmb() RISCV_FENCE(ir,ir)
+#define wmb() RISCV_FENCE(ow,ow)
+
+/* These barries do not need to enforce ordering on devices, just memory. */
+#define smp_mb() RISCV_FENCE(rw,rw)
+#define smp_rmb() RISCV_FENCE(r,r)
+#define smp_wmb() RISCV_FENCE(w,w)
+
+/*
+ * Our atomic operations set the AQ and RL bits and therefor we don't need to
+ * fence around atomics.
+ */
+#define __smb_mb__before_atomic() barrier()
+#define __smb_mb__after_atomic() barrier()
+
+/*
+ * These barries are meant to prevent memory operations inside a spinlock from
+ * moving outside of that spinlock. Since we set the AQ and RL bits when
+ * entering or leaving spinlocks, no additional fence needs to be performed.
+ */
+#define smb_mb__before_spinlock() barrier()
+#define smb_mb__after_spinlock() barrier()
+
+/* FIXME: I don't think RISC-V is allowed to perform a speculative load. */
+#define smp_acquire__after_ctrl_dep() barrier()
+
+/*
+ * The RISC-V ISA doesn't support byte or half-word AMOs, so we fall back to a
+ * regular store and a fence here. Otherwise we emit an AMO with an AQ or RL
+ * bit set and allow the microarchitecture to avoid the other half of the AMO.
+ */
+#define __smp_store_release(p, v) \
+do { \
+ union { typeof(*p) __val; char __c[1]; } __u = \
+ { .__val = (__force typeof(*p)) (v) }; \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 1: \
+ case 2: \
+ smb_mb(); \
+ WRITE_ONCE(*p, __u.__val); \
+ break; \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "amoswap.w.rl zero, %1, %0" \
+ : "+A" (*p), "r" (__u.__val) \
+ : \
+ : "memory"); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "amoswap.d.rl zero, %1, %0" \
+ : "+A" (*p), "r" (__u.__val) \
+ : \
+ : "memory"); \
+ break; \
+ } \
+} while (0)
+
+#define __smp_load_acquire(p) \
+do { \
+ union { typeof(*p) __val; char __c[1]; } __u = \
+ { .__val = (__force typeof(*p)) (v) }; \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 1: \
+ case 2: \
+ __u.__val = READ_ONCE(*p); \
+ smb_mb(); \
+ break; \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "amoor.w.aq %1, zero, %0" \
+ : "+A" (*p) \
+ : "=r" (__u.__val) \
+ : "memory"); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "amoor.d.aq %1, zero, %0" \
+ : "+A" (*p) \
+ : "=r" (__u.__val) \
+ : "memory"); \
+ break; \
+ } \
+ __u.__val; \
+} while (0)
+
+/*
+ * The default implementation of this uses READ_ONCE and
+ * smp_acquire__after_ctrl_dep, but since we can directly do an ACQUIRE load we
+ * can avoid the extra barrier.
+ */
+#define smp_cond_load_acquire(ptr, cond_expr) ({ \
+ typeof(ptr) __PTR = (ptr); \
+ typeof(*ptr) VAL; \
+ for (;;) { \
+ VAL = __smp_load_acquire(__PTR); \
+ if (cond_expr) \
+ break; \
+ cpu_relax(); \
+ } \
+ smp_acquire__after_ctrl_dep(); \
+ VAL; \
+})
+
+#include <asm-generic/barrier.h>
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_BARRIER_H */
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
new file mode 100644
index 000000000000..27e47858c6b1
--- /dev/null
+++ b/arch/riscv/include/asm/bitops.h
@@ -0,0 +1,228 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_BITOPS_H
+#define _ASM_RISCV_BITOPS_H
+
+#ifndef _LINUX_BITOPS_H
+#error "Only <linux/bitops.h> can be included directly"
+#endif /* _LINUX_BITOPS_H */
+
+#ifdef __KERNEL__
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <asm/barrier.h>
+#include <asm/bitsperlong.h>
+
+#ifdef CONFIG_ISA_A
+
+#ifndef smp_mb__before_clear_bit
+#define smp_mb__before_clear_bit() smp_mb()
+#define smp_mb__after_clear_bit() smp_mb()
+#endif /* smp_mb__before_clear_bit */
+
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/ffs.h>
+
+#include <asm-generic/bitops/hweight.h>
+
+#if (BITS_PER_LONG == 64)
+#define __AMO(op) "amo" #op ".d"
+#elif (BITS_PER_LONG == 32)
+#define __AMO(op) "amo" #op ".w"
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+#define __test_and_op_bit(op, mod, nr, addr) \
+({ \
+ unsigned long __res, __mask; \
+ __mask = BIT_MASK(nr); \
+ __asm__ __volatile__ ( \
+ __AMO(op) " %0, %2, %1" \
+ : "=r" (__res), "+A" (addr[BIT_WORD(nr)]) \
+ : "r" (mod(__mask))); \
+ ((__res & __mask) != 0); \
+})
+
+#define __op_bit(op, mod, nr, addr) \
+ __asm__ __volatile__ ( \
+ __AMO(op) " zero, %1, %0" \
+ : "+A" (addr[BIT_WORD(nr)]) \
+ : "r" (mod(BIT_MASK(nr))))
+
+/* Bitmask modifiers */
+#define __NOP(x) (x)
+#define __NOT(x) (~(x))
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It may be reordered on other architectures than x86.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+ return __test_and_op_bit(or, __NOP, nr, addr);
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It can be reordered on other architectures other than x86.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+ return __test_and_op_bit(and, __NOT, nr, addr);
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+ return __test_and_op_bit(xor, __NOP, nr, addr);
+}
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered. See __set_bit()
+ * if you do not require the atomic guarantees.
+ *
+ * Note: there are no guarantees that this function will not be reordered
+ * on non x86 architectures, so if you are writing portable code,
+ * make sure not to rely on its reordering guarantees.
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void set_bit(int nr, volatile unsigned long *addr)
+{
+ __op_bit(or, __NOP, nr, addr);
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and may not be reordered. However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * in order to ensure changes are visible on other processors.
+ */
+static inline void clear_bit(int nr, volatile unsigned long *addr)
+{
+ __op_bit(and, __NOT, nr, addr);
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered. It may be
+ * reordered on other architectures than x86.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void change_bit(int nr, volatile unsigned long *addr)
+{
+ __op_bit(xor, __NOP, nr, addr);
+}
+
+/**
+ * test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and provides acquire barrier semantics.
+ * It can be used to implement bit locks.
+ */
+static inline int test_and_set_bit_lock(
+ unsigned long nr, volatile unsigned long *addr)
+{
+ return test_and_set_bit(nr, addr);
+}
+
+/**
+ * clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ */
+static inline void clear_bit_unlock(
+ unsigned long nr, volatile unsigned long *addr)
+{
+ clear_bit(nr, addr);
+}
+
+/**
+ * __clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is like clear_bit_unlock, however it is not atomic.
+ * It does provide release barrier semantics so it can be used to unlock
+ * a bit lock, however it would only be used if no other CPU can modify
+ * any bits in the memory until the lock is released (a good example is
+ * if the bit lock itself protects access to the other bits in the word).
+ */
+static inline void __clear_bit_unlock(
+ unsigned long nr, volatile unsigned long *addr)
+{
+ clear_bit(nr, addr);
+}
+
+#undef __test_and_op_bit
+#undef __op_bit
+#undef __NOP
+#undef __NOT
+#undef __AMO
+
+#include <asm-generic/bitops/non-atomic.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic.h>
+
+#else /* !CONFIG_ISA_A */
+
+#include <asm-generic/bitops.h>
+
+#endif /* CONFIG_ISA_A */
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_RISCV_BITOPS_H */
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
new file mode 100644
index 000000000000..0595585013b0
--- /dev/null
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -0,0 +1,39 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_CACHEFLUSH_H
+#define _ASM_RISCV_CACHEFLUSH_H
+
+#include <asm-generic/cacheflush.h>
+
+#undef flush_icache_range
+#undef flush_icache_user_range
+
+static inline void local_flush_icache_all(void)
+{
+ asm volatile ("fence.i" ::: "memory");
+}
+
+#ifndef CONFIG_SMP
+
+#define flush_icache_range(start, end) local_flush_icache_all()
+#define flush_icache_user_range(vma, pg, addr, len) local_flush_icache_all()
+
+#else /* CONFIG_SMP */
+
+#define flush_icache_range(start, end) sbi_remote_fence_i(0)
+#define flush_icache_user_range(vma, pg, addr, len) sbi_remote_fence_i(0)
+
+#endif /* CONFIG_SMP */
+
+#endif /* _ASM_RISCV_CACHEFLUSH_H */
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..81025c056412
--- /dev/null
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -0,0 +1,138 @@
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_CMPXCHG_H
+#define _ASM_RISCV_CMPXCHG_H
+
+#include <linux/bug.h>
+
+#ifdef CONFIG_ISA_A
+
+#include <asm/barrier.h>
+
+#define __xchg(new, ptr, size, asm_or) \
+({ \
+ __typeof__(ptr) __ptr = (ptr); \
+ __typeof__(new) __new = (new); \
+ __typeof__(*(ptr)) __ret; \
+ switch (size) { \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "amoswap.w" #asm_or " %0, %2, %1" \
+ : "=r" (__ret), "+A" (*__ptr) \
+ : "r" (__new)); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "amoswap.d" #asm_or " %0, %2, %1" \
+ : "=r" (__ret), "+A" (*__ptr) \
+ : "r" (__new)); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ __ret; \
+})
+
+#define xchg(ptr, x) (__xchg((x), (ptr), sizeof(*(ptr)), .aqrl))
+
+#define xchg32(ptr, x) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
+ xchg((ptr), (x)); \
+})
+
+#define xchg64(ptr, x) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ xchg((ptr), (x)); \
+})
+
+/*
+ * Atomic compare and exchange. Compare OLD with MEM, if identical,
+ * store NEW in MEM. Return the initial value in MEM. Success is
+ * indicated by comparing RETURN with OLD.
+ */
+#define __cmpxchg(ptr, old, new, size, lrb, scb) \
+({ \
+ __typeof__(ptr) __ptr = (ptr); \
+ __typeof__(old) __old = (old); \
+ __typeof__(new) __new = (new); \
+ __typeof__(*(ptr)) __ret; \
+ register unsigned int __rc; \
+ switch (size) { \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "0:" \
+ "lr.w" #scb " %0, %2\n" \
+ "bne %0, %z3, 1f\n" \
+ "sc.w" #lrb " %1, %z4, %2\n" \
+ "bnez %1, 0b\n" \
+ "1:" \
+ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
+ : "rJ" (__old), "rJ" (__new)); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "0:" \
+ "lr.d" #scb " %0, %2\n" \
+ "bne %0, %z3, 1f\n" \
+ "sc.d" #lrb " %1, %z4, %2\n" \
+ "bnez %1, 0b\n" \
+ "1:" \
+ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
+ : "rJ" (__old), "rJ" (__new)); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ __ret; \
+})
+
+#define cmpxchg(ptr, o, n) \
+ (__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), .aqrl, .aqrl))
+
+#define cmpxchg_local(ptr, o, n) \
+ (__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), , ))
+
+#define cmpxchg32(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
+ cmpxchg((ptr), (o), (n)); \
+})
+
+#define cmpxchg32_local(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
+ cmpxchg_local((ptr), (o), (n)); \
+})
+
+#define cmpxchg64(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ cmpxchg((ptr), (o), (n)); \
+})
+
+#define cmpxchg64_local(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ cmpxchg_local((ptr), (o), (n)); \
+})
+
+#else /* !CONFIG_ISA_A */
+
+#include <asm-generic/cmpxchg.h>
+
+#endif /* CONFIG_ISA_A */
+
+#endif /* _ASM_RISCV_CMPXCHG_H */
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
new file mode 100644
index 000000000000..c47177cb6660
--- /dev/null
+++ b/arch/riscv/include/asm/io.h
@@ -0,0 +1,180 @@
+/*
+ * {read,write}{b,w,l,q} based on arch/arm64/include/asm/io.h
+ * which was based on arch/arm/include/io.h
+ *
+ * Copyright (C) 1996-2000 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_IO_H
+#define _ASM_RISCV_IO_H
+
+#ifdef CONFIG_MMU
+
+extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
+
+/*
+ * The RISC-V ISA doesn't yet specify how to query of modify PMAs, so we can't
+ * change the properties of memory regions. This should be fixed by the
+ * upcoming platform spec.
+ */
+#define ioremap_nocache(addr, size) ioremap((addr), (size))
+#define ioremap_wc(addr, size) ioremap((addr), (size))
+#define ioremap_wt(addr, size) ioremap((addr), (size))
+
+extern void iounmap(void __iomem *addr);
+
+#endif /* CONFIG_MMU */
+
+/* Generic IO read/write. These perform native-endian accesses. */
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
+{
+ asm volatile("sb %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 val, volatile void __iomem *addr)
+{
+ asm volatile("sh %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 val, volatile void __iomem *addr)
+{
+ asm volatile("sw %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#ifdef __riscv64
+#define __raw_writeq __raw_writeq
+static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
+{
+ asm volatile("sd %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+#endif
+
+#define __raw_readb __raw_readb
+static inline u8 __raw_readb(const volatile void __iomem *addr)
+{
+ u8 val;
+
+ asm volatile("lb %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+
+#define __raw_readw __raw_readw
+static inline u16 __raw_readw(const volatile void __iomem *addr)
+{
+ u16 val;
+
+ asm volatile("lh %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+
+#define __raw_readl __raw_readl
+static inline u32 __raw_readl(const volatile void __iomem *addr)
+{
+ u32 val;
+
+ asm volatile("lw %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+
+#ifdef __riscv64
+#define __raw_readq __raw_readq
+static inline u64 __raw_readq(const volatile void __iomem *addr)
+{
+ u64 val;
+
+ asm volatile("ld %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+#endif
+
+/*
+ * FIXME: I'm flip-flopping on whether or not we should keep this or enforce
+ * the ordering with I/O on spinlocks. The worry is that drivers won't get
+ * this correct, but I also don't want to introduce a fence into the lock code
+ * that otherwise only uses AMOs and LR/SC. For now I'm leaving this here:
+ * "w,o" is sufficient to ensure that all writes to the device has completed
+ * before the write to the spinlock is allowed to commit. I surmised this from
+ * reading "ACQUIRES VS I/O ACCESSES" in memory-barries.txt.
+ */
+#define mmiowb() __asm__ __volatile__ ("fence o,w" : : : "memory");
+
+/*
+ * Unordered I/O memory access primitives. These are even more relaxed than
+ * the relaxed versions, as they don't even order accesses between successive
+ * operations to the I/O regions.
+ */
+#define readb_cpu(c) ({ u8 __r = __raw_readb(c); __r; })
+#define readw_cpu(c) ({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; })
+#define readl_cpu(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
+#define readq_cpu(c) ({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; })
+
+#define writeb_cpu(v,c) ((void)__raw_writeb((v),(c)))
+#define writew_cpu(v,c) ((void)__raw_writew((__force u16)cpu_to_le16(v),(c)))
+#define writel_cpu(v,c) ((void)__raw_writel((__force u32)cpu_to_le32(v),(c)))
+#define writeq_cpu(v,c) ((void)__raw_writeq((__force u64)cpu_to_le64(v),(c)))
+
+/*
+ * Relaxed I/O memory access primitives. These follow the Device memory
+ * ordering rules but do not guarantee any ordering relative to Normal memory
+ * accesses. The memory barries here are necessary as RISC-V doesn't define
+ * any ordering constraints on accesses to the device I/O space. These are
+ * defined to order the indicated access (either a read or write) with all
+ * other I/O memory accesses.
+ */
+/*
+ * FIXME: The platform spec will define the default Linux-capable platform to
+ * have some extra IO ordering constraints that will make these fences
+ * unnecessary.
+ */
+#define __iorrmb() __asm__ __volatile__ ("fence i,io" : : : "memory");
+#define __iorwmb() __asm__ __volatile__ ("fence io,o" : : : "memory");
+
+#define readb_relaxed(c) ({ u8 __v = readb_cpu(c); __iorrmb(); __v; })
+#define readw_relaxed(c) ({ u16 __v = readw_cpu(c); __iorrmb(); __v; })
+#define readl_relaxed(c) ({ u32 __v = readl_cpu(c); __iorrmb(); __v; })
+#define readq_relaxed(c) ({ u64 __v = readq_cpu(c); __iorrmb(); __v; })
+
+#define writeb_relaxed(v,c) ({ __iorwmb(); writeb_cpu((v),(c)); })
+#define writew_relaxed(v,c) ({ __iorwmb(); writew_cpu((v),(c)); })
+#define writel_relaxed(v,c) ({ __iorwmb(); writel_cpu((v),(c)); })
+#define writeq_relaxed(v,c) ({ __iorwmb(); writeq_cpu((v),(c)); })
+
+/*
+ * I/O memory access primitives. Reads are ordered relative to any
+ * following Normal memory access. Writes are ordered relative to any prior
+ * Normal memory access. The memory barriers here are necessary as RISC-V
+ * doesn't define any ordering between the memory space and the I/O space.
+ * They may be stronger than necessary ("i,r" and "w,o" might be sufficient),
+ * but I feel kind of queasy making these weaker in any manner than the relaxed
+ * versions above.
+ */
+#define __iormb() __asm__ __volatile__ ("fence i,ior" : : : "memory");
+#define __iowmb() __asm__ __volatile__ ("fence iow,o" : : : "memory");
+
+#define readb(c) ({ u8 __v = readb_cpu(c); __iormb(); __v; })
+#define readw(c) ({ u16 __v = readw_cpu(c); __iormb(); __v; })
+#define readl(c) ({ u32 __v = readl_cpu(c); __iormb(); __v; })
+#define readq(c) ({ u64 __v = readq_cpu(c); __iormb(); __v; })
+
+#define writeb(v,c) ({ __iowmb(); writeb_cpu((v),(c)); })
+#define writew(v,c) ({ __iowmb(); writew_cpu((v),(c)); })
+#define writel(v,c) ({ __iowmb(); writel_cpu((v),(c)); })
+#define writeq(v,c) ({ __iowmb(); writeq_cpu((v),(c)); })
+
+#include <asm-generic/io.h>
+
+#endif /* _ASM_RISCV_IO_H */
diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
new file mode 100644
index 000000000000..54ed73bfa972
--- /dev/null
+++ b/arch/riscv/include/asm/spinlock.h
@@ -0,0 +1,167 @@
+/*
+ * Copyright (C) 2015 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.
+ */
+
+#ifndef _ASM_RISCV_SPINLOCK_H
+#define _ASM_RISCV_SPINLOCK_H
+
+#include <linux/kernel.h>
+#include <asm/current.h>
+
+/*
+ * Simple spin lock operations. These provide no fairness guarantees.
+ */
+
+/* FIXME: Replace this with a ticket lock, like MIPS. */
+
+#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
+#define arch_spin_is_locked(x) ((x)->lock != 0)
+#define arch_spin_unlock_wait(x) \
+ do { cpu_relax(); } while ((x)->lock)
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+ __asm__ __volatile__ (
+ "amoswap.w.rl x0, x0, %0"
+ : "=A" (lock->lock)
+ :: "memory");
+}
+
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+ int tmp = 1, busy;
+
+ __asm__ __volatile__ (
+ "amoswap.w.aq %0, %2, %1"
+ : "=r" (busy), "+A" (lock->lock)
+ : "r" (tmp)
+ : "memory");
+
+ return !busy;
+}
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+ while (1) {
+ if (arch_spin_is_locked(lock))
+ continue;
+
+ if (arch_spin_trylock(lock))
+ break;
+ }
+}
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+ smp_rmb();
+ do {
+ cpu_relax();
+ } while (arch_spin_is_locked(lock));
+ smp_acquire__after_ctrl_dep();
+}
+
+/***********************************************************/
+
+static inline int arch_read_can_lock(arch_rwlock_t *lock)
+{
+ return lock->lock >= 0;
+}
+
+static inline int arch_write_can_lock(arch_rwlock_t *lock)
+{
+ return lock->lock == 0;
+}
+
+static inline void arch_read_lock(arch_rwlock_t *lock)
+{
+ int tmp;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bltz %1, 1b\n"
+ " addi %1, %1, 1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ : "+A" (lock->lock), "=&r" (tmp)
+ :: "memory");
+}
+
+static inline void arch_write_lock(arch_rwlock_t *lock)
+{
+ int tmp;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bnez %1, 1b\n"
+ " li %1, -1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ : "+A" (lock->lock), "=&r" (tmp)
+ :: "memory");
+}
+
+static inline int arch_read_trylock(arch_rwlock_t *lock)
+{
+ int busy;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bltz %1, 1f\n"
+ " addi %1, %1, 1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ "1:\n"
+ : "+A" (lock->lock), "=&r" (busy)
+ :: "memory");
+
+ return !busy;
+}
+
+static inline int arch_write_trylock(arch_rwlock_t *lock)
+{
+ int busy;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bnez %1, 1f\n"
+ " li %1, -1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ "1:\n"
+ : "+A" (lock->lock), "=&r" (busy)
+ :: "memory");
+
+ return !busy;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *lock)
+{
+ __asm__ __volatile__(
+ "amoadd.w.rl x0, %1, %0"
+ : "+A" (lock->lock)
+ : "r" (-1)
+ : "memory");
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *lock)
+{
+ __asm__ __volatile__ (
+ "amoswap.w.rl x0, x0, %0"
+ : "=A" (lock->lock)
+ :: "memory");
+}
+
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
+#endif /* _ASM_RISCV_SPINLOCK_H */
diff --git a/arch/riscv/include/asm/spinlock_types.h b/arch/riscv/include/asm/spinlock_types.h
new file mode 100644
index 000000000000..83ac4ac9e2ac
--- /dev/null
+++ b/arch/riscv/include/asm/spinlock_types.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SPINLOCK_TYPES_H
+#define _ASM_RISCV_SPINLOCK_TYPES_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+# error "please don't include this file directly"
+#endif
+
+typedef struct {
+ volatile unsigned int lock;
+} arch_spinlock_t;
+
+#define __ARCH_SPIN_LOCK_UNLOCKED { 0 }
+
+typedef struct {
+ volatile unsigned int lock;
+} arch_rwlock_t;
+
+#define __ARCH_RW_LOCK_UNLOCKED { 0 }
+
+#endif
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
new file mode 100644
index 000000000000..c229509288ea
--- /dev/null
+++ b/arch/riscv/include/asm/tlb.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_TLB_H
+#define _ASM_RISCV_TLB_H
+
+#include <asm-generic/tlb.h>
+
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+ flush_tlb_mm(tlb->mm);
+}
+
+#endif /* _ASM_RISCV_TLB_H */
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
new file mode 100644
index 000000000000..5ee4ae370b5e
--- /dev/null
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_TLBFLUSH_H
+#define _ASM_RISCV_TLBFLUSH_H
+
+#ifdef CONFIG_MMU
+
+/* Flush entire local TLB */
+static inline void local_flush_tlb_all(void)
+{
+ __asm__ __volatile__ ("sfence.vma" : : : "memory");
+}
+
+/* Flush one page from local TLB */
+static inline void local_flush_tlb_page(unsigned long addr)
+{
+ __asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory");
+}
+
+#ifndef CONFIG_SMP
+
+#define flush_tlb_all() local_flush_tlb_all()
+#define flush_tlb_page(vma, addr) local_flush_tlb_page(addr)
+#define flush_tlb_range(vma, start, end) local_flush_tlb_all()
+
+#else /* CONFIG_SMP */
+
+#include <asm/sbi.h>
+
+#define flush_tlb_all() sbi_remote_sfence_vma(0, 0, -1)
+#define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0)
+#define flush_tlb_range(vma, start, end) \
+ sbi_remote_sfence_vma(0, start, (end) - (start))
+
+#endif /* CONFIG_SMP */
+
+/* Flush the TLB entries of the specified mm context */
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+ flush_tlb_all();
+}
+
+/* Flush a range of kernel pages */
+static inline void flush_tlb_kernel_range(unsigned long start,
+ unsigned long end)
+{
+ flush_tlb_all();
+}
+
+#endif /* CONFIG_MMU */
+
+#endif /* _ASM_RISCV_TLBFLUSH_H */
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* Re: [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-04 19:50 ` Palmer Dabbelt
(?)
@ 2017-07-05 8:43 ` Peter Zijlstra
2017-07-06 11:08 ` Boqun Feng
2017-07-07 1:04 ` Palmer Dabbelt
-1 siblings, 2 replies; 58+ messages in thread
From: Peter Zijlstra @ 2017-07-05 8:43 UTC (permalink / raw)
To: Palmer Dabbelt
Cc: mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel, msalter,
tklauser, will.deacon, james.hogan, paul.gortmaker, linux,
linux-kernel, linux-arch, albert, patches
On Tue, Jul 04, 2017 at 12:50:55PM -0700, Palmer Dabbelt wrote:
> +/*
> + * FIXME: I could only find documentation that atomic_{add,sub,inc,dec} are
> + * barrier-free. I'm assuming that and/or/xor have the same constraints as the
> + * others.
> + */
Yes.. we have new documentation in the work to which I would post a link
but for some reason copy/paste stopped working again (Konsole does that
at times and is #$%#$%#4# annoying).
Ha, found it using google...
https://marc.info/?l=linux-kernel&m=14972790112580
> +
> +/*
> + * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
> + * {cmp,}xchg and the operations that return, so they need a barrier. We just
> + * use the other implementations directly.
> + */
cmpxchg triggers an extra rule; all conditional operations only need to
imply barriers on success. So a cmpxchg that fails, need not imply any
ordering what so ever.
> +/*
> + * Our atomic operations set the AQ and RL bits and therefor we don't need to
> + * fence around atomics.
> + */
> +#define __smb_mb__before_atomic() barrier()
> +#define __smb_mb__after_atomic() barrier()
Ah, not quite... you need full barriers here. Because your regular
atomic ops imply no ordering what so ever.
> +/*
> + * These barries are meant to prevent memory operations inside a spinlock from
> + * moving outside of that spinlock. Since we set the AQ and RL bits when
> + * entering or leaving spinlocks, no additional fence needs to be performed.
> + */
> +#define smb_mb__before_spinlock() barrier()
> +#define smb_mb__after_spinlock() barrier()
Also probably not true. I _think_ you want a full barrier here, but
given the total lack of documentation on your end and the fact I've not
yet read the spinlock (which I suppose is below) I cannot yet state
more.
> +
> +/* FIXME: I don't think RISC-V is allowed to perform a speculative load. */
> +#define smp_acquire__after_ctrl_dep() barrier()
That would be a very weird thing to disallow... speculative loads are
teh awesome ;-) Note you can get the very same effect from caches when
your stores are not globally atomic.
> +/*
> + * The RISC-V ISA doesn't support byte or half-word AMOs, so we fall back to a
> + * regular store and a fence here. Otherwise we emit an AMO with an AQ or RL
> + * bit set and allow the microarchitecture to avoid the other half of the AMO.
> + */
> +#define __smp_store_release(p, v) \
> +do { \
> + union { typeof(*p) __val; char __c[1]; } __u = \
> + { .__val = (__force typeof(*p)) (v) }; \
> + compiletime_assert_atomic_type(*p); \
> + switch (sizeof(*p)) { \
> + case 1: \
> + case 2: \
> + smb_mb(); \
> + WRITE_ONCE(*p, __u.__val); \
> + break; \
> + case 4: \
> + __asm__ __volatile__ ( \
> + "amoswap.w.rl zero, %1, %0" \
> + : "+A" (*p), "r" (__u.__val) \
> + : \
> + : "memory"); \
> + break; \
> + case 8: \
> + __asm__ __volatile__ ( \
> + "amoswap.d.rl zero, %1, %0" \
> + : "+A" (*p), "r" (__u.__val) \
> + : \
> + : "memory"); \
> + break; \
> + } \
> +} while (0)
> +
> +#define __smp_load_acquire(p) \
> +do { \
> + union { typeof(*p) __val; char __c[1]; } __u = \
> + { .__val = (__force typeof(*p)) (v) }; \
> + compiletime_assert_atomic_type(*p); \
> + switch (sizeof(*p)) { \
> + case 1: \
> + case 2: \
> + __u.__val = READ_ONCE(*p); \
> + smb_mb(); \
> + break; \
> + case 4: \
> + __asm__ __volatile__ ( \
> + "amoor.w.aq %1, zero, %0" \
> + : "+A" (*p) \
> + : "=r" (__u.__val) \
> + : "memory"); \
> + break; \
> + case 8: \
> + __asm__ __volatile__ ( \
> + "amoor.d.aq %1, zero, %0" \
> + : "+A" (*p) \
> + : "=r" (__u.__val) \
> + : "memory"); \
> + break; \
> + } \
> + __u.__val; \
> +} while (0)
'creative' use of amoswap and amoor :-)
You should really look at a normal load with ordering instruction
though, that amoor.aq is a rmw and will promote the cacheline to
exclusive (and dirty it).
> +/*
> + * Simple spin lock operations. These provide no fairness guarantees.
> + */
> +
> +/* FIXME: Replace this with a ticket lock, like MIPS. */
> +
> +#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
> +#define arch_spin_is_locked(x) ((x)->lock != 0)
> +#define arch_spin_unlock_wait(x) \
> + do { cpu_relax(); } while ((x)->lock)
> +
> +static inline void arch_spin_unlock(arch_spinlock_t *lock)
> +{
> + __asm__ __volatile__ (
> + "amoswap.w.rl x0, x0, %0"
> + : "=A" (lock->lock)
> + :: "memory");
> +}
> +
> +static inline int arch_spin_trylock(arch_spinlock_t *lock)
> +{
> + int tmp = 1, busy;
> +
> + __asm__ __volatile__ (
> + "amoswap.w.aq %0, %2, %1"
> + : "=r" (busy), "+A" (lock->lock)
> + : "r" (tmp)
> + : "memory");
> +
> + return !busy;
> +}
> +
> +static inline void arch_spin_lock(arch_spinlock_t *lock)
> +{
> + while (1) {
> + if (arch_spin_is_locked(lock))
> + continue;
> +
> + if (arch_spin_trylock(lock))
> + break;
> + }
> +}
OK, so back to smp_mb__{before,after}_spinlock(), that wants to order
things like:
wakeup: block:
COND = 1; p->state = UNINTERRUPTIBLE;
smp_mb();
smp_mb__before_spinlock();
spin_lock(&lock); if (!COND)
schedule()
if (p->state & state)
goto out;
And here it is important that the COND store not happen _after_ the
p->state load.
Now, your spin_lock() only implies the AQ thing, which should only
constraint later load/stores but does nothing for the prior load/stores.
So our COND store can drop into the lock and even happen after the
p->state load.
So you very much want your smp_mb__{before,after}_spinlock thingies to
be full barriers.
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-05 8:43 ` Peter Zijlstra
@ 2017-07-06 11:08 ` Boqun Feng
2017-07-06 7:26 ` Peter Zijlstra
2017-07-07 1:04 ` Palmer Dabbelt
1 sibling, 1 reply; 58+ messages in thread
From: Boqun Feng @ 2017-07-06 11:08 UTC (permalink / raw)
To: Peter Zijlstra
Cc: Palmer Dabbelt, mingo, mcgrof, viro, sfr, nicolas.dichtel,
rmk+kernel, msalter, tklauser, will.deacon, james.hogan,
paul.gortmaker, linux, linux-kernel, linux-arch, albert, patches
[-- Attachment #1: Type: text/plain, Size: 754 bytes --]
On Wed, Jul 05, 2017 at 10:43:21AM +0200, Peter Zijlstra wrote:
> On Tue, Jul 04, 2017 at 12:50:55PM -0700, Palmer Dabbelt wrote:
> > +/*
> > + * FIXME: I could only find documentation that atomic_{add,sub,inc,dec} are
> > + * barrier-free. I'm assuming that and/or/xor have the same constraints as the
> > + * others.
> > + */
>
> Yes.. we have new documentation in the work to which I would post a link
> but for some reason copy/paste stopped working again (Konsole does that
> at times and is #$%#$%#4# annoying).
>
> Ha, found it using google...
>
> https://marc.info/?l=linux-kernel&m=14972790112580
>
The link is broken, you miss a tailing 1 ;-)
https://marc.info/?l=linux-kernel&m=149727901125801
Regards,
Boqun
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-06 11:08 ` Boqun Feng
@ 2017-07-06 7:26 ` Peter Zijlstra
0 siblings, 0 replies; 58+ messages in thread
From: Peter Zijlstra @ 2017-07-06 7:26 UTC (permalink / raw)
To: Boqun Feng
Cc: Palmer Dabbelt, mingo, mcgrof, viro, sfr, nicolas.dichtel,
rmk+kernel, msalter, tklauser, will.deacon, james.hogan,
paul.gortmaker, linux, linux-kernel, linux-arch, albert, patches
On Thu, Jul 06, 2017 at 07:08:33PM +0800, Boqun Feng wrote:
> On Wed, Jul 05, 2017 at 10:43:21AM +0200, Peter Zijlstra wrote:
> > On Tue, Jul 04, 2017 at 12:50:55PM -0700, Palmer Dabbelt wrote:
> > > +/*
> > > + * FIXME: I could only find documentation that atomic_{add,sub,inc,dec} are
> > > + * barrier-free. I'm assuming that and/or/xor have the same constraints as the
> > > + * others.
> > > + */
> >
> > Yes.. we have new documentation in the work to which I would post a link
> > but for some reason copy/paste stopped working again (Konsole does that
> > at times and is #$%#$%#4# annoying).
> >
> > Ha, found it using google...
> >
> > https://marc.info/?l=linux-kernel&m=14972790112580
> >
>
> The link is broken, you miss a tailing 1 ;-)
>
> https://marc.info/?l=linux-kernel&m=149727901125801
>
Argh... thanks for fixing that!
^ permalink raw reply [flat|nested] 58+ messages in thread
* Re: [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-05 8:43 ` Peter Zijlstra
@ 2017-07-07 1:04 ` Palmer Dabbelt
2017-07-07 1:04 ` Palmer Dabbelt
1 sibling, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-07 1:04 UTC (permalink / raw)
To: peterz
Cc: mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel, msalter,
tklauser, will.deacon, james.hogan, paul.gortmaker, linux,
linux-kernel, linux-arch, albert, patches
On Wed, 05 Jul 2017 01:43:21 PDT (-0700), peterz@infradead.org wrote:
> On Tue, Jul 04, 2017 at 12:50:55PM -0700, Palmer Dabbelt wrote:
>> +/*
>> + * FIXME: I could only find documentation that atomic_{add,sub,inc,dec} are
>> + * barrier-free. I'm assuming that and/or/xor have the same constraints as the
>> + * others.
>> + */
>
> Yes.. we have new documentation in the work to which I would post a link
> but for some reason copy/paste stopped working again (Konsole does that
> at times and is #$%#$%#4# annoying).
>
> Ha, found it using google...
>
> https://marc.info/?l=linux-kernel&m=149727901125801
Thanks.
>> +/*
>> + * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
>> + * {cmp,}xchg and the operations that return, so they need a barrier. We just
>> + * use the other implementations directly.
>> + */
>
> cmpxchg triggers an extra rule; all conditional operations only need to
> imply barriers on success. So a cmpxchg that fails, need not imply any
> ordering what so ever.
>
>> +/*
>> + * Our atomic operations set the AQ and RL bits and therefor we don't need to
>> + * fence around atomics.
>> + */
>> +#define __smb_mb__before_atomic() barrier()
>> +#define __smb_mb__after_atomic() barrier()
>
> Ah, not quite... you need full barriers here. Because your regular
> atomic ops imply no ordering what so ever.
The new documentation helps here, too. Thanks!
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index 82a0092a86d0..a480c0fb85e5 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -39,11 +39,19 @@
#define smp_wmb() RISCV_FENCE(w,w)
/*
- * Our atomic operations set the AQ and RL bits and therefor we don't need to
- * fence around atomics.
+ * These fences exist to enforce ordering around the relaxed AMOs. The
+ * documentation defines that
+ * "
+ * atomic_fetch_add();
+ * is equivalent to:
+ * smp_mb__before_atomic();
+ * atomic_fetch_add_relaxed();
+ * smp_mb__after_atomic();
+ * "
+ * So we emit full fences on both sides.
*/
-#define __smb_mb__before_atomic() barrier()
-#define __smb_mb__after_atomic() barrier()
+#define __smb_mb__before_atomic() smp_mb()
+#define __smb_mb__after_atomic() smp_mb()
/*
* These barries are meant to prevent memory operations inside a spinlock from
>> +/*
>> + * These barries are meant to prevent memory operations inside a spinlock from
>> + * moving outside of that spinlock. Since we set the AQ and RL bits when
>> + * entering or leaving spinlocks, no additional fence needs to be performed.
>> + */
>> +#define smb_mb__before_spinlock() barrier()
>> +#define smb_mb__after_spinlock() barrier()
>
> Also probably not true. I _think_ you want a full barrier here, but
> given the total lack of documentation on your end and the fact I've not
> yet read the spinlock (which I suppose is below) I cannot yet state
> more.
Ya, sorry about that -- we're waiting on a proper memory model spec. Is there
any other documentation I should produce?
More below.
>> +
>> +/* FIXME: I don't think RISC-V is allowed to perform a speculative load. */
>> +#define smp_acquire__after_ctrl_dep() barrier()
>
> That would be a very weird thing to disallow... speculative loads are
> teh awesome ;-) Note you can get the very same effect from caches when
> your stores are not globally atomic.
OK -- I guess generally the user ISA spec is written disregarding
microarchitecture, so I assumed this would be illegal. We'll wait for the
memory model spec.
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index a4e54f4c17eb..c039333d4a5d 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -61,8 +61,12 @@
#define smb_mb__before_spinlock() smp_mb()
#define smb_mb__after_spinlock() smp_mb()
-/* FIXME: I don't think RISC-V is allowed to perform a speculative load. */
-#define smp_acquire__after_ctrl_dep() barrier()
+/*
+ * TODO_RISCV_MEMORY_MODEL: I don't think RISC-V is allowed to perform a
+ * speculative load, but we're going to wait on a formal memory model in order
+ * to ensure this is safe to elide.
+ */
+#define smp_acquire__after_ctrl_dep() smp_mb()
/*
* The RISC-V ISA doesn't support byte or half-word AMOs, so we fall back to a
@@ -137,24 +141,6 @@
__u.__val; \
})
-/*
- * The default implementation of this uses READ_ONCE and
- * smp_acquire__after_ctrl_dep, but since we can directly do an ACQUIRE load we
- * can avoid the extra barrier.
- */
-#define smp_cond_load_acquire(ptr, cond_expr) ({ \
- typeof(ptr) __PTR = (ptr); \
- typeof(*ptr) VAL; \
- for (;;) { \
- VAL = __smp_load_acquire(__PTR); \
- if (cond_expr) \
- break; \
- cpu_relax(); \
- } \
- smp_acquire__after_ctrl_dep(); \
- VAL; \
-})
-
#include <asm-generic/barrier.h>
#endif /* __ASSEMBLY__ */
>> +/*
>> + * The RISC-V ISA doesn't support byte or half-word AMOs, so we fall back to a
>> + * regular store and a fence here. Otherwise we emit an AMO with an AQ or RL
>> + * bit set and allow the microarchitecture to avoid the other half of the AMO.
>> + */
>> +#define __smp_store_release(p, v) \
>> +do { \
>> + union { typeof(*p) __val; char __c[1]; } __u = \
>> + { .__val = (__force typeof(*p)) (v) }; \
>> + compiletime_assert_atomic_type(*p); \
>> + switch (sizeof(*p)) { \
>> + case 1: \
>> + case 2: \
>> + smb_mb(); \
>> + WRITE_ONCE(*p, __u.__val); \
>> + break; \
>> + case 4: \
>> + __asm__ __volatile__ ( \
>> + "amoswap.w.rl zero, %1, %0" \
>> + : "+A" (*p), "r" (__u.__val) \
>> + : \
>> + : "memory"); \
>> + break; \
>> + case 8: \
>> + __asm__ __volatile__ ( \
>> + "amoswap.d.rl zero, %1, %0" \
>> + : "+A" (*p), "r" (__u.__val) \
>> + : \
>> + : "memory"); \
>> + break; \
>> + } \
>> +} while (0)
>> +
>> +#define __smp_load_acquire(p) \
>> +do { \
>> + union { typeof(*p) __val; char __c[1]; } __u = \
>> + { .__val = (__force typeof(*p)) (v) }; \
>> + compiletime_assert_atomic_type(*p); \
>> + switch (sizeof(*p)) { \
>> + case 1: \
>> + case 2: \
>> + __u.__val = READ_ONCE(*p); \
>> + smb_mb(); \
>> + break; \
>> + case 4: \
>> + __asm__ __volatile__ ( \
>> + "amoor.w.aq %1, zero, %0" \
>> + : "+A" (*p) \
>> + : "=r" (__u.__val) \
>> + : "memory"); \
>> + break; \
>> + case 8: \
>> + __asm__ __volatile__ ( \
>> + "amoor.d.aq %1, zero, %0" \
>> + : "+A" (*p) \
>> + : "=r" (__u.__val) \
>> + : "memory"); \
>> + break; \
>> + } \
>> + __u.__val; \
>> +} while (0)
>
> 'creative' use of amoswap and amoor :-)
>
> You should really look at a normal load with ordering instruction
> though, that amoor.aq is a rmw and will promote the cacheline to
> exclusive (and dirty it).
The thought here was that implementations could elide the MW by pattern
matching the "zero" (x0, the architectural zero register) forms of AMOs where
it's interesting. I talked to one of our microarchitecture guys, and while he
agrees that's easy he points out that eliding half the AMO may wreak havoc on
the consistency model. Since we're not sure what the memory model is actually
going to look like, we thought it'd be best to just write the simplest code
here
/*
* TODO_RISCV_MEMORY_MODEL: While we could emit AMOs for the W and D sized
* accesses here, it's questionable if that actually helps or not: the lack of
* offsets in the AMOs means they're usually preceded by an addi, so they
* probably won't save code space. For now we'll just emit the fence.
*/
#define __smp_store_release(p, v) \
({ \
compiletime_assert_atomic_type(*p); \
smp_mb(); \
WRITE_ONCE(*p, v); \
})
#define __smp_load_acquire(p) \
({ \
union{typeof(*p) __p; long __l;} __u; \
compiletime_assert_atomic_type(*p); \
__u.__l = READ_ONCE(*p); \
smp_mb(); \
__u.__p; \
})
>> +/*
>> + * Simple spin lock operations. These provide no fairness guarantees.
>> + */
>> +
>> +/* FIXME: Replace this with a ticket lock, like MIPS. */
>> +
>> +#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
>> +#define arch_spin_is_locked(x) ((x)->lock != 0)
>> +#define arch_spin_unlock_wait(x) \
>> + do { cpu_relax(); } while ((x)->lock)
>> +
>> +static inline void arch_spin_unlock(arch_spinlock_t *lock)
>> +{
>> + __asm__ __volatile__ (
>> + "amoswap.w.rl x0, x0, %0"
>> + : "=A" (lock->lock)
>> + :: "memory");
>> +}
>> +
>> +static inline int arch_spin_trylock(arch_spinlock_t *lock)
>> +{
>> + int tmp = 1, busy;
>> +
>> + __asm__ __volatile__ (
>> + "amoswap.w.aq %0, %2, %1"
>> + : "=r" (busy), "+A" (lock->lock)
>> + : "r" (tmp)
>> + : "memory");
>> +
>> + return !busy;
>> +}
>> +
>> +static inline void arch_spin_lock(arch_spinlock_t *lock)
>> +{
>> + while (1) {
>> + if (arch_spin_is_locked(lock))
>> + continue;
>> +
>> + if (arch_spin_trylock(lock))
>> + break;
>> + }
>> +}
>
> OK, so back to smp_mb__{before,after}_spinlock(), that wants to order
> things like:
>
> wakeup: block:
>
> COND = 1; p->state = UNINTERRUPTIBLE;
> smp_mb();
> smp_mb__before_spinlock();
> spin_lock(&lock); if (!COND)
> schedule()
> if (p->state & state)
> goto out;
>
>
> And here it is important that the COND store not happen _after_ the
> p->state load.
>
> Now, your spin_lock() only implies the AQ thing, which should only
> constraint later load/stores but does nothing for the prior load/stores.
> So our COND store can drop into the lock and even happen after the
> p->state load.
>
> So you very much want your smp_mb__{before,after}_spinlock thingies to
> be full barriers.
OK, thanks! I just had the movement direction backwards. This makes much more
sense.
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index a480c0fb85e5..a4e54f4c17eb 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -54,12 +54,12 @@
#define __smb_mb__after_atomic() smp_mb()
/*
- * These barries are meant to prevent memory operations inside a spinlock from
- * moving outside of that spinlock. Since we set the AQ and RL bits when
- * entering or leaving spinlocks, no additional fence needs to be performed.
+ * These barries prevent accesses performed outside a spinlock from being moved
+ * inside a spinlock. Since RISC-V sets the aq/rl bits on our spinlock only
+ * enforce release consistency, we need full fences here.
*/
-#define smb_mb__before_spinlock() barrier()
-#define smb_mb__after_spinlock() barrier()
+#define smb_mb__before_spinlock() smp_mb()
+#define smb_mb__after_spinlock() smp_mb()
/* FIXME: I don't think RISC-V is allowed to perform a speculative load. */
#define smp_acquire__after_ctrl_dep() barrier()
Thanks for all the help!
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [PATCH 2/9] RISC-V: Atomic and Locking Code
@ 2017-07-07 1:04 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-07 1:04 UTC (permalink / raw)
To: peterz
Cc: mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel, msalter,
tklauser, will.deacon, james.hogan, paul.gortmaker, linux,
linux-kernel, linux-arch, albert, patches
On Wed, 05 Jul 2017 01:43:21 PDT (-0700), peterz@infradead.org wrote:
> On Tue, Jul 04, 2017 at 12:50:55PM -0700, Palmer Dabbelt wrote:
>> +/*
>> + * FIXME: I could only find documentation that atomic_{add,sub,inc,dec} are
>> + * barrier-free. I'm assuming that and/or/xor have the same constraints as the
>> + * others.
>> + */
>
> Yes.. we have new documentation in the work to which I would post a link
> but for some reason copy/paste stopped working again (Konsole does that
> at times and is #$%#$%#4# annoying).
>
> Ha, found it using google...
>
> https://marc.info/?l=linux-kernel&m=149727901125801
Thanks.
>> +/*
>> + * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
>> + * {cmp,}xchg and the operations that return, so they need a barrier. We just
>> + * use the other implementations directly.
>> + */
>
> cmpxchg triggers an extra rule; all conditional operations only need to
> imply barriers on success. So a cmpxchg that fails, need not imply any
> ordering what so ever.
>
>> +/*
>> + * Our atomic operations set the AQ and RL bits and therefor we don't need to
>> + * fence around atomics.
>> + */
>> +#define __smb_mb__before_atomic() barrier()
>> +#define __smb_mb__after_atomic() barrier()
>
> Ah, not quite... you need full barriers here. Because your regular
> atomic ops imply no ordering what so ever.
The new documentation helps here, too. Thanks!
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index 82a0092a86d0..a480c0fb85e5 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -39,11 +39,19 @@
#define smp_wmb() RISCV_FENCE(w,w)
/*
- * Our atomic operations set the AQ and RL bits and therefor we don't need to
- * fence around atomics.
+ * These fences exist to enforce ordering around the relaxed AMOs. The
+ * documentation defines that
+ * "
+ * atomic_fetch_add();
+ * is equivalent to:
+ * smp_mb__before_atomic();
+ * atomic_fetch_add_relaxed();
+ * smp_mb__after_atomic();
+ * "
+ * So we emit full fences on both sides.
*/
-#define __smb_mb__before_atomic() barrier()
-#define __smb_mb__after_atomic() barrier()
+#define __smb_mb__before_atomic() smp_mb()
+#define __smb_mb__after_atomic() smp_mb()
/*
* These barries are meant to prevent memory operations inside a spinlock from
>> +/*
>> + * These barries are meant to prevent memory operations inside a spinlock from
>> + * moving outside of that spinlock. Since we set the AQ and RL bits when
>> + * entering or leaving spinlocks, no additional fence needs to be performed.
>> + */
>> +#define smb_mb__before_spinlock() barrier()
>> +#define smb_mb__after_spinlock() barrier()
>
> Also probably not true. I _think_ you want a full barrier here, but
> given the total lack of documentation on your end and the fact I've not
> yet read the spinlock (which I suppose is below) I cannot yet state
> more.
Ya, sorry about that -- we're waiting on a proper memory model spec. Is there
any other documentation I should produce?
More below.
>> +
>> +/* FIXME: I don't think RISC-V is allowed to perform a speculative load. */
>> +#define smp_acquire__after_ctrl_dep() barrier()
>
> That would be a very weird thing to disallow... speculative loads are
> teh awesome ;-) Note you can get the very same effect from caches when
> your stores are not globally atomic.
OK -- I guess generally the user ISA spec is written disregarding
microarchitecture, so I assumed this would be illegal. We'll wait for the
memory model spec.
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index a4e54f4c17eb..c039333d4a5d 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -61,8 +61,12 @@
#define smb_mb__before_spinlock() smp_mb()
#define smb_mb__after_spinlock() smp_mb()
-/* FIXME: I don't think RISC-V is allowed to perform a speculative load. */
-#define smp_acquire__after_ctrl_dep() barrier()
+/*
+ * TODO_RISCV_MEMORY_MODEL: I don't think RISC-V is allowed to perform a
+ * speculative load, but we're going to wait on a formal memory model in order
+ * to ensure this is safe to elide.
+ */
+#define smp_acquire__after_ctrl_dep() smp_mb()
/*
* The RISC-V ISA doesn't support byte or half-word AMOs, so we fall back to a
@@ -137,24 +141,6 @@
__u.__val; \
})
-/*
- * The default implementation of this uses READ_ONCE and
- * smp_acquire__after_ctrl_dep, but since we can directly do an ACQUIRE load we
- * can avoid the extra barrier.
- */
-#define smp_cond_load_acquire(ptr, cond_expr) ({ \
- typeof(ptr) __PTR = (ptr); \
- typeof(*ptr) VAL; \
- for (;;) { \
- VAL = __smp_load_acquire(__PTR); \
- if (cond_expr) \
- break; \
- cpu_relax(); \
- } \
- smp_acquire__after_ctrl_dep(); \
- VAL; \
-})
-
#include <asm-generic/barrier.h>
#endif /* __ASSEMBLY__ */
>> +/*
>> + * The RISC-V ISA doesn't support byte or half-word AMOs, so we fall back to a
>> + * regular store and a fence here. Otherwise we emit an AMO with an AQ or RL
>> + * bit set and allow the microarchitecture to avoid the other half of the AMO.
>> + */
>> +#define __smp_store_release(p, v) \
>> +do { \
>> + union { typeof(*p) __val; char __c[1]; } __u = \
>> + { .__val = (__force typeof(*p)) (v) }; \
>> + compiletime_assert_atomic_type(*p); \
>> + switch (sizeof(*p)) { \
>> + case 1: \
>> + case 2: \
>> + smb_mb(); \
>> + WRITE_ONCE(*p, __u.__val); \
>> + break; \
>> + case 4: \
>> + __asm__ __volatile__ ( \
>> + "amoswap.w.rl zero, %1, %0" \
>> + : "+A" (*p), "r" (__u.__val) \
>> + : \
>> + : "memory"); \
>> + break; \
>> + case 8: \
>> + __asm__ __volatile__ ( \
>> + "amoswap.d.rl zero, %1, %0" \
>> + : "+A" (*p), "r" (__u.__val) \
>> + : \
>> + : "memory"); \
>> + break; \
>> + } \
>> +} while (0)
>> +
>> +#define __smp_load_acquire(p) \
>> +do { \
>> + union { typeof(*p) __val; char __c[1]; } __u = \
>> + { .__val = (__force typeof(*p)) (v) }; \
>> + compiletime_assert_atomic_type(*p); \
>> + switch (sizeof(*p)) { \
>> + case 1: \
>> + case 2: \
>> + __u.__val = READ_ONCE(*p); \
>> + smb_mb(); \
>> + break; \
>> + case 4: \
>> + __asm__ __volatile__ ( \
>> + "amoor.w.aq %1, zero, %0" \
>> + : "+A" (*p) \
>> + : "=r" (__u.__val) \
>> + : "memory"); \
>> + break; \
>> + case 8: \
>> + __asm__ __volatile__ ( \
>> + "amoor.d.aq %1, zero, %0" \
>> + : "+A" (*p) \
>> + : "=r" (__u.__val) \
>> + : "memory"); \
>> + break; \
>> + } \
>> + __u.__val; \
>> +} while (0)
>
> 'creative' use of amoswap and amoor :-)
>
> You should really look at a normal load with ordering instruction
> though, that amoor.aq is a rmw and will promote the cacheline to
> exclusive (and dirty it).
The thought here was that implementations could elide the MW by pattern
matching the "zero" (x0, the architectural zero register) forms of AMOs where
it's interesting. I talked to one of our microarchitecture guys, and while he
agrees that's easy he points out that eliding half the AMO may wreak havoc on
the consistency model. Since we're not sure what the memory model is actually
going to look like, we thought it'd be best to just write the simplest code
here
/*
* TODO_RISCV_MEMORY_MODEL: While we could emit AMOs for the W and D sized
* accesses here, it's questionable if that actually helps or not: the lack of
* offsets in the AMOs means they're usually preceded by an addi, so they
* probably won't save code space. For now we'll just emit the fence.
*/
#define __smp_store_release(p, v) \
({ \
compiletime_assert_atomic_type(*p); \
smp_mb(); \
WRITE_ONCE(*p, v); \
})
#define __smp_load_acquire(p) \
({ \
union{typeof(*p) __p; long __l;} __u; \
compiletime_assert_atomic_type(*p); \
__u.__l = READ_ONCE(*p); \
smp_mb(); \
__u.__p; \
})
>> +/*
>> + * Simple spin lock operations. These provide no fairness guarantees.
>> + */
>> +
>> +/* FIXME: Replace this with a ticket lock, like MIPS. */
>> +
>> +#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
>> +#define arch_spin_is_locked(x) ((x)->lock != 0)
>> +#define arch_spin_unlock_wait(x) \
>> + do { cpu_relax(); } while ((x)->lock)
>> +
>> +static inline void arch_spin_unlock(arch_spinlock_t *lock)
>> +{
>> + __asm__ __volatile__ (
>> + "amoswap.w.rl x0, x0, %0"
>> + : "=A" (lock->lock)
>> + :: "memory");
>> +}
>> +
>> +static inline int arch_spin_trylock(arch_spinlock_t *lock)
>> +{
>> + int tmp = 1, busy;
>> +
>> + __asm__ __volatile__ (
>> + "amoswap.w.aq %0, %2, %1"
>> + : "=r" (busy), "+A" (lock->lock)
>> + : "r" (tmp)
>> + : "memory");
>> +
>> + return !busy;
>> +}
>> +
>> +static inline void arch_spin_lock(arch_spinlock_t *lock)
>> +{
>> + while (1) {
>> + if (arch_spin_is_locked(lock))
>> + continue;
>> +
>> + if (arch_spin_trylock(lock))
>> + break;
>> + }
>> +}
>
> OK, so back to smp_mb__{before,after}_spinlock(), that wants to order
> things like:
>
> wakeup: block:
>
> COND = 1; p->state = UNINTERRUPTIBLE;
> smp_mb();
> smp_mb__before_spinlock();
> spin_lock(&lock); if (!COND)
> schedule()
> if (p->state & state)
> goto out;
>
>
> And here it is important that the COND store not happen _after_ the
> p->state load.
>
> Now, your spin_lock() only implies the AQ thing, which should only
> constraint later load/stores but does nothing for the prior load/stores.
> So our COND store can drop into the lock and even happen after the
> p->state load.
>
> So you very much want your smp_mb__{before,after}_spinlock thingies to
> be full barriers.
OK, thanks! I just had the movement direction backwards. This makes much more
sense.
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index a480c0fb85e5..a4e54f4c17eb 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -54,12 +54,12 @@
#define __smb_mb__after_atomic() smp_mb()
/*
- * These barries are meant to prevent memory operations inside a spinlock from
- * moving outside of that spinlock. Since we set the AQ and RL bits when
- * entering or leaving spinlocks, no additional fence needs to be performed.
+ * These barries prevent accesses performed outside a spinlock from being moved
+ * inside a spinlock. Since RISC-V sets the aq/rl bits on our spinlock only
+ * enforce release consistency, we need full fences here.
*/
-#define smb_mb__before_spinlock() barrier()
-#define smb_mb__after_spinlock() barrier()
+#define smb_mb__before_spinlock() smp_mb()
+#define smb_mb__after_spinlock() smp_mb()
/* FIXME: I don't think RISC-V is allowed to perform a speculative load. */
#define smp_acquire__after_ctrl_dep() barrier()
Thanks for all the help!
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-07 1:04 ` Palmer Dabbelt
(?)
@ 2017-07-07 2:14 ` Boqun Feng
2017-07-10 20:39 ` Palmer Dabbelt
-1 siblings, 1 reply; 58+ messages in thread
From: Boqun Feng @ 2017-07-07 2:14 UTC (permalink / raw)
To: Palmer Dabbelt
Cc: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
[-- Attachment #1: Type: text/plain, Size: 3392 bytes --]
On Thu, Jul 06, 2017 at 06:04:13PM -0700, Palmer Dabbelt wrote:
[...]
> >> +#define __smp_load_acquire(p) \
> >> +do { \
> >> + union { typeof(*p) __val; char __c[1]; } __u = \
> >> + { .__val = (__force typeof(*p)) (v) }; \
> >> + compiletime_assert_atomic_type(*p); \
> >> + switch (sizeof(*p)) { \
> >> + case 1: \
> >> + case 2: \
> >> + __u.__val = READ_ONCE(*p); \
> >> + smb_mb(); \
> >> + break; \
> >> + case 4: \
> >> + __asm__ __volatile__ ( \
> >> + "amoor.w.aq %1, zero, %0" \
> >> + : "+A" (*p) \
> >> + : "=r" (__u.__val) \
> >> + : "memory"); \
> >> + break; \
> >> + case 8: \
> >> + __asm__ __volatile__ ( \
> >> + "amoor.d.aq %1, zero, %0" \
> >> + : "+A" (*p) \
> >> + : "=r" (__u.__val) \
> >> + : "memory"); \
> >> + break; \
> >> + } \
> >> + __u.__val; \
> >> +} while (0)
> >
> > 'creative' use of amoswap and amoor :-)
> >
> > You should really look at a normal load with ordering instruction
> > though, that amoor.aq is a rmw and will promote the cacheline to
> > exclusive (and dirty it).
>
> The thought here was that implementations could elide the MW by pattern
> matching the "zero" (x0, the architectural zero register) forms of AMOs where
> it's interesting. I talked to one of our microarchitecture guys, and while he
> agrees that's easy he points out that eliding half the AMO may wreak havoc on
> the consistency model. Since we're not sure what the memory model is actually
> going to look like, we thought it'd be best to just write the simplest code
> here
>
> /*
> * TODO_RISCV_MEMORY_MODEL: While we could emit AMOs for the W and D sized
> * accesses here, it's questionable if that actually helps or not: the lack of
> * offsets in the AMOs means they're usually preceded by an addi, so they
> * probably won't save code space. For now we'll just emit the fence.
> */
> #define __smp_store_release(p, v) \
> ({ \
> compiletime_assert_atomic_type(*p); \
> smp_mb(); \
> WRITE_ONCE(*p, v); \
> })
>
> #define __smp_load_acquire(p) \
> ({ \
> union{typeof(*p) __p; long __l;} __u; \
AFAICT, there seems to be an endian issue if you do this. No?
Let us assume typeof(*p) is char and *p == 1, and on a big endian 32bit
platform:
> compiletime_assert_atomic_type(*p); \
> __u.__l = READ_ONCE(*p); \
READ_ONCE(*p) is 1 so
__u.__l is 0x00 00 00 01 now
> smp_mb(); \
> __u.__p; \
__u.__p is then 0x00.
Am I missing something here?
Even so why not use the simple definition as in include/asm-generic/barrier.h?
Regards,
Boqun
> })
>
[...]
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-07 2:14 ` Boqun Feng
@ 2017-07-10 20:39 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-10 20:39 UTC (permalink / raw)
To: boqun.feng
Cc: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
On Thu, 06 Jul 2017 19:14:25 PDT (-0700), boqun.feng@gmail.com wrote:
> On Thu, Jul 06, 2017 at 06:04:13PM -0700, Palmer Dabbelt wrote:
> [...]
>> >> +#define __smp_load_acquire(p) \
>> >> +do { \
>> >> + union { typeof(*p) __val; char __c[1]; } __u = \
>> >> + { .__val = (__force typeof(*p)) (v) }; \
>> >> + compiletime_assert_atomic_type(*p); \
>> >> + switch (sizeof(*p)) { \
>> >> + case 1: \
>> >> + case 2: \
>> >> + __u.__val = READ_ONCE(*p); \
>> >> + smb_mb(); \
>> >> + break; \
>> >> + case 4: \
>> >> + __asm__ __volatile__ ( \
>> >> + "amoor.w.aq %1, zero, %0" \
>> >> + : "+A" (*p) \
>> >> + : "=r" (__u.__val) \
>> >> + : "memory"); \
>> >> + break; \
>> >> + case 8: \
>> >> + __asm__ __volatile__ ( \
>> >> + "amoor.d.aq %1, zero, %0" \
>> >> + : "+A" (*p) \
>> >> + : "=r" (__u.__val) \
>> >> + : "memory"); \
>> >> + break; \
>> >> + } \
>> >> + __u.__val; \
>> >> +} while (0)
>> >
>> > 'creative' use of amoswap and amoor :-)
>> >
>> > You should really look at a normal load with ordering instruction
>> > though, that amoor.aq is a rmw and will promote the cacheline to
>> > exclusive (and dirty it).
>>
>> The thought here was that implementations could elide the MW by pattern
>> matching the "zero" (x0, the architectural zero register) forms of AMOs where
>> it's interesting. I talked to one of our microarchitecture guys, and while he
>> agrees that's easy he points out that eliding half the AMO may wreak havoc on
>> the consistency model. Since we're not sure what the memory model is actually
>> going to look like, we thought it'd be best to just write the simplest code
>> here
>>
>> /*
>> * TODO_RISCV_MEMORY_MODEL: While we could emit AMOs for the W and D sized
>> * accesses here, it's questionable if that actually helps or not: the lack of
>> * offsets in the AMOs means they're usually preceded by an addi, so they
>> * probably won't save code space. For now we'll just emit the fence.
>> */
>> #define __smp_store_release(p, v) \
>> ({ \
>> compiletime_assert_atomic_type(*p); \
>> smp_mb(); \
>> WRITE_ONCE(*p, v); \
>> })
>>
>> #define __smp_load_acquire(p) \
>> ({ \
>> union{typeof(*p) __p; long __l;} __u; \
>
> AFAICT, there seems to be an endian issue if you do this. No?
>
> Let us assume typeof(*p) is char and *p == 1, and on a big endian 32bit
> platform:
>
>> compiletime_assert_atomic_type(*p); \
>> __u.__l = READ_ONCE(*p); \
>
> READ_ONCE(*p) is 1 so
> __u.__l is 0x00 00 00 01 now
>
>> smp_mb(); \
>> __u.__p; \
>
> __u.__p is then 0x00.
>
> Am I missing something here?
We're little endian (though I might have still screwed it up). I didn't really
bother looking because...
> Even so why not use the simple definition as in include/asm-generic/barrier.h?
...that's much better -- I forgot there were generic versions, as we used to
have a much more complicated one.
https://github.com/riscv/riscv-linux/commit/910d2bf4c3c349b670a1d839462e32e122ac70a5
Thanks!
^ permalink raw reply [flat|nested] 58+ messages in thread
* Re: [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-07 1:04 ` Palmer Dabbelt
(?)
(?)
@ 2017-07-07 8:08 ` Peter Zijlstra
2017-07-10 20:39 ` Palmer Dabbelt
-1 siblings, 1 reply; 58+ messages in thread
From: Peter Zijlstra @ 2017-07-07 8:08 UTC (permalink / raw)
To: Palmer Dabbelt
Cc: mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel, msalter,
tklauser, will.deacon, james.hogan, paul.gortmaker, linux,
linux-kernel, linux-arch, albert, patches
On Thu, Jul 06, 2017 at 06:04:13PM -0700, Palmer Dabbelt wrote:
> > Also probably not true. I _think_ you want a full barrier here, but
> > given the total lack of documentation on your end and the fact I've not
> > yet read the spinlock (which I suppose is below) I cannot yet state
> > more.
>
> Ya, sorry about that -- we're waiting on a proper memory model spec. Is there
> any other documentation I should produce?
Nah, I'll wait for your shiny new document.
> +/*
> + * TODO_RISCV_MEMORY_MODEL: I don't think RISC-V is allowed to perform a
> + * speculative load, but we're going to wait on a formal memory model in order
> + * to ensure this is safe to elide.
> + */
> +#define smp_acquire__after_ctrl_dep() smp_mb()
So typically a control dependency already provides read->write ordering,
by virtue of speculative writes being BAD.
So a control dependency only needs to provide read->read ordering in
addition to the existing read->write ordering and hence this barrier is
typically a smp_rmb().
See the definition in asm-generic/barrier.h.
Having to use a full barrier here would imply your architecture does not
respect control dependencies, which would be BAD because we actually
rely on them.
So either the normal definition is good and you don't need to do
anything, or you prohibit read speculation in which case you have a
special case like TILE does.
> >> +#define __smp_load_acquire(p) \
> >> +do { \
> >> + union { typeof(*p) __val; char __c[1]; } __u = \
> >> + { .__val = (__force typeof(*p)) (v) }; \
> >> + compiletime_assert_atomic_type(*p); \
> >> + switch (sizeof(*p)) { \
> >> + case 1: \
> >> + case 2: \
> >> + __u.__val = READ_ONCE(*p); \
> >> + smb_mb(); \
> >> + break; \
> >> + case 4: \
> >> + __asm__ __volatile__ ( \
> >> + "amoor.w.aq %1, zero, %0" \
> >> + : "+A" (*p) \
> >> + : "=r" (__u.__val) \
> >> + : "memory"); \
> >> + break; \
> >> + case 8: \
> >> + __asm__ __volatile__ ( \
> >> + "amoor.d.aq %1, zero, %0" \
> >> + : "+A" (*p) \
> >> + : "=r" (__u.__val) \
> >> + : "memory"); \
> >> + break; \
> >> + } \
> >> + __u.__val; \
> >> +} while (0)
> >
> > 'creative' use of amoswap and amoor :-)
> >
> > You should really look at a normal load with ordering instruction
> > though, that amoor.aq is a rmw and will promote the cacheline to
> > exclusive (and dirty it).
>
> The thought here was that implementations could elide the MW by pattern
> matching the "zero" (x0, the architectural zero register) forms of AMOs where
> it's interesting. I talked to one of our microarchitecture guys, and while he
> agrees that's easy he points out that eliding half the AMO may wreak havoc on
> the consistency model. Since we're not sure what the memory model is actually
> going to look like, we thought it'd be best to just write the simplest code
> here
>
> /*
> * TODO_RISCV_MEMORY_MODEL: While we could emit AMOs for the W and D sized
> * accesses here, it's questionable if that actually helps or not: the lack of
> * offsets in the AMOs means they're usually preceded by an addi, so they
> * probably won't save code space. For now we'll just emit the fence.
> */
> #define __smp_store_release(p, v) \
> ({ \
> compiletime_assert_atomic_type(*p); \
> smp_mb(); \
> WRITE_ONCE(*p, v); \
> })
>
> #define __smp_load_acquire(p) \
> ({ \
> union{typeof(*p) __p; long __l;} __u; \
> compiletime_assert_atomic_type(*p); \
> __u.__l = READ_ONCE(*p); \
> smp_mb(); \
> __u.__p; \
> })
Fair enough, that works.
> > OK, so back to smp_mb__{before,after}_spinlock(), that wants to order
> > things like:
> >
> > wakeup: block:
> >
> > COND = 1; p->state = UNINTERRUPTIBLE;
> > smp_mb();
> > smp_mb__before_spinlock();
> > spin_lock(&lock); if (!COND)
> > schedule()
> > if (p->state & state)
> > goto out;
> >
> >
> > And here it is important that the COND store not happen _after_ the
> > p->state load.
> >
> > Now, your spin_lock() only implies the AQ thing, which should only
> > constraint later load/stores but does nothing for the prior load/stores.
> > So our COND store can drop into the lock and even happen after the
> > p->state load.
> >
> > So you very much want your smp_mb__{before,after}_spinlock thingies to
> > be full barriers.
>
> OK, thanks! I just had the movement direction backwards. This makes much more
> sense.
>
> diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
> index a480c0fb85e5..a4e54f4c17eb 100644
> --- a/arch/riscv/include/asm/barrier.h
> +++ b/arch/riscv/include/asm/barrier.h
> @@ -54,12 +54,12 @@
> #define __smb_mb__after_atomic() smp_mb()
>
> /*
> - * These barries are meant to prevent memory operations inside a spinlock from
> - * moving outside of that spinlock. Since we set the AQ and RL bits when
> - * entering or leaving spinlocks, no additional fence needs to be performed.
> + * These barries prevent accesses performed outside a spinlock from being moved
> + * inside a spinlock. Since RISC-V sets the aq/rl bits on our spinlock only
> + * enforce release consistency, we need full fences here.
> */
> -#define smb_mb__before_spinlock() barrier()
> -#define smb_mb__after_spinlock() barrier()
> +#define smb_mb__before_spinlock() smp_mb()
> +#define smb_mb__after_spinlock() smp_mb()
>
Most excellent. Thanks!
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-07 8:08 ` Peter Zijlstra
@ 2017-07-10 20:39 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-10 20:39 UTC (permalink / raw)
To: peterz
Cc: mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel, msalter,
tklauser, will.deacon, james.hogan, paul.gortmaker, linux,
linux-kernel, linux-arch, albert, patches
On Fri, 07 Jul 2017 01:08:19 PDT (-0700), peterz@infradead.org wrote:
> On Thu, Jul 06, 2017 at 06:04:13PM -0700, Palmer Dabbelt wrote:
>> +/*
>> + * TODO_RISCV_MEMORY_MODEL: I don't think RISC-V is allowed to perform a
>> + * speculative load, but we're going to wait on a formal memory model in order
>> + * to ensure this is safe to elide.
>> + */
>> +#define smp_acquire__after_ctrl_dep() smp_mb()
>
> So typically a control dependency already provides read->write ordering,
> by virtue of speculative writes being BAD.
>
> So a control dependency only needs to provide read->read ordering in
> addition to the existing read->write ordering and hence this barrier is
> typically a smp_rmb().
>
> See the definition in asm-generic/barrier.h.
>
> Having to use a full barrier here would imply your architecture does not
> respect control dependencies, which would be BAD because we actually
> rely on them.
>
> So either the normal definition is good and you don't need to do
> anything, or you prohibit read speculation in which case you have a
> special case like TILE does.
I'd be very surprised (and very unhappy) if we ended up with speculative
writes, as that would be a huge mess.
Thanks!
^ permalink raw reply [flat|nested] 58+ messages in thread
* Re: [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-04 19:50 ` Palmer Dabbelt
(?)
(?)
@ 2017-07-06 10:33 ` Boqun Feng
-1 siblings, 0 replies; 58+ messages in thread
From: Boqun Feng @ 2017-07-06 10:33 UTC (permalink / raw)
To: Palmer Dabbelt
Cc: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
[-- Attachment #1: Type: text/plain, Size: 4668 bytes --]
On Tue, Jul 04, 2017 at 12:50:55PM -0700, Palmer Dabbelt wrote:
[...]
> diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
> new file mode 100644
> index 000000000000..81025c056412
> --- /dev/null
> +++ b/arch/riscv/include/asm/cmpxchg.h
> @@ -0,0 +1,138 @@
> +/*
> + * Copyright (C) 2014 Regents of the University of California
> + *
> + * 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.
> + */
> +
> +#ifndef _ASM_RISCV_CMPXCHG_H
> +#define _ASM_RISCV_CMPXCHG_H
> +
> +#include <linux/bug.h>
> +
> +#ifdef CONFIG_ISA_A
> +
> +#include <asm/barrier.h>
> +
> +#define __xchg(new, ptr, size, asm_or) \
> +({ \
> + __typeof__(ptr) __ptr = (ptr); \
> + __typeof__(new) __new = (new); \
> + __typeof__(*(ptr)) __ret; \
> + switch (size) { \
> + case 4: \
> + __asm__ __volatile__ ( \
> + "amoswap.w" #asm_or " %0, %2, %1" \
> + : "=r" (__ret), "+A" (*__ptr) \
> + : "r" (__new)); \
It seems that you miss the "memmory" clobber here, so as for cmpxchg(),
did you do this on purpose? AFAIK, without this clobber, compilers are
within their right to reorder operations preceding and following this
operation, which makes it unordered.
> + break; \
> + case 8: \
> + __asm__ __volatile__ ( \
> + "amoswap.d" #asm_or " %0, %2, %1" \
> + : "=r" (__ret), "+A" (*__ptr) \
> + : "r" (__new)); \
> + break; \
> + default: \
> + BUILD_BUG(); \
> + } \
> + __ret; \
> +})
> +
> +#define xchg(ptr, x) (__xchg((x), (ptr), sizeof(*(ptr)), .aqrl))
> +
> +#define xchg32(ptr, x) \
> +({ \
> + BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
> + xchg((ptr), (x)); \
> +})
> +
> +#define xchg64(ptr, x) \
> +({ \
> + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
> + xchg((ptr), (x)); \
> +})
> +
> +/*
> + * Atomic compare and exchange. Compare OLD with MEM, if identical,
> + * store NEW in MEM. Return the initial value in MEM. Success is
> + * indicated by comparing RETURN with OLD.
> + */
> +#define __cmpxchg(ptr, old, new, size, lrb, scb) \
> +({ \
> + __typeof__(ptr) __ptr = (ptr); \
> + __typeof__(old) __old = (old); \
> + __typeof__(new) __new = (new); \
Better write those two lines as:
__typeof__(*(ptr)) __old = (old); \
__typeof__(*(ptr)) __new = (new); \
? I'm thinking the case where @old and @new are int and ptr is "long *",
could the asm below do the implicitly converting right, i.e. keep the
sign bit?
Regards,
Boqun
> + __typeof__(*(ptr)) __ret; \
> + register unsigned int __rc; \
> + switch (size) { \
> + case 4: \
> + __asm__ __volatile__ ( \
> + "0:" \
> + "lr.w" #scb " %0, %2\n" \
> + "bne %0, %z3, 1f\n" \
> + "sc.w" #lrb " %1, %z4, %2\n" \
> + "bnez %1, 0b\n" \
> + "1:" \
> + : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
> + : "rJ" (__old), "rJ" (__new)); \
> + break; \
> + case 8: \
> + __asm__ __volatile__ ( \
> + "0:" \
> + "lr.d" #scb " %0, %2\n" \
> + "bne %0, %z3, 1f\n" \
> + "sc.d" #lrb " %1, %z4, %2\n" \
> + "bnez %1, 0b\n" \
> + "1:" \
> + : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
> + : "rJ" (__old), "rJ" (__new)); \
> + break; \
> + default: \
> + BUILD_BUG(); \
> + } \
> + __ret; \
> +})
> +
> +#define cmpxchg(ptr, o, n) \
> + (__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), .aqrl, .aqrl))
> +
> +#define cmpxchg_local(ptr, o, n) \
> + (__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), , ))
> +
> +#define cmpxchg32(ptr, o, n) \
> +({ \
> + BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
> + cmpxchg((ptr), (o), (n)); \
> +})
> +
> +#define cmpxchg32_local(ptr, o, n) \
> +({ \
> + BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
> + cmpxchg_local((ptr), (o), (n)); \
> +})
> +
> +#define cmpxchg64(ptr, o, n) \
> +({ \
> + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
> + cmpxchg((ptr), (o), (n)); \
> +})
> +
> +#define cmpxchg64_local(ptr, o, n) \
> +({ \
> + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
> + cmpxchg_local((ptr), (o), (n)); \
> +})
> +
> +#else /* !CONFIG_ISA_A */
> +
> +#include <asm-generic/cmpxchg.h>
> +
> +#endif /* CONFIG_ISA_A */
> +
[...]
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [patches] [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-04 19:50 ` Palmer Dabbelt
` (2 preceding siblings ...)
(?)
@ 2017-07-07 13:16 ` Jonathan Neuschäfer
2017-07-10 20:39 ` Palmer Dabbelt
-1 siblings, 1 reply; 58+ messages in thread
From: Jonathan Neuschäfer @ 2017-07-07 13:16 UTC (permalink / raw)
To: patches
Cc: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, Palmer Dabbelt
[-- Attachment #1: Type: text/plain, Size: 233 bytes --]
On Tue, Jul 04, 2017 at 12:50:55PM -0700, Palmer Dabbelt wrote:
[...]
> +/* These barries need to enforce ordering on both devices or memory. */
Very minor nit: s/barries/barriers/ (in several places)
Jonathan Neuschäfer
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [patches] [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-07 13:16 ` [patches] " Jonathan Neuschäfer
@ 2017-07-10 20:39 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-10 20:39 UTC (permalink / raw)
To: j.neuschaefer
Cc: patches, peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel,
rmk+kernel, msalter, tklauser, will.deacon, james.hogan,
paul.gortmaker, linux, linux-kernel, linux-arch, albert
On Fri, 07 Jul 2017 06:16:07 PDT (-0700), j.neuschaefer@gmx.net wrote:
> On Tue, Jul 04, 2017 at 12:50:55PM -0700, Palmer Dabbelt wrote:
> [...]
>> +/* These barries need to enforce ordering on both devices or memory. */
>
> Very minor nit: s/barries/barriers/ (in several places)
I think this should do it
https://github.com/riscv/riscv-linux/commit/b356e7a2223b5e21df424ea7e9900e5bf408762f
Thanks!
^ permalink raw reply [flat|nested] 58+ messages in thread
* [PATCH 2/9] RISC-V: Atomic and Locking Code
2017-07-04 19:50 ` Palmer Dabbelt
` (3 preceding siblings ...)
(?)
@ 2017-07-04 19:50 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This contains all the code that directly interfaces with the RISC-V
memory model. While this code corforms to the current RISC-V ISA
specifications (user 2.2 and priv 1.10), the memory model is somewhat
underspecified in those documents. There is a working group that hopes
to produce a formal memory model by the end of the year, but my
understanding is that the basic definitions we're relying on here won't
change significantly.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/atomic.h | 337 ++++++++++++++++++++++++++++++++
arch/riscv/include/asm/barrier.h | 143 ++++++++++++++
arch/riscv/include/asm/bitops.h | 228 +++++++++++++++++++++
arch/riscv/include/asm/cacheflush.h | 39 ++++
arch/riscv/include/asm/cmpxchg.h | 138 +++++++++++++
arch/riscv/include/asm/io.h | 180 +++++++++++++++++
arch/riscv/include/asm/spinlock.h | 167 ++++++++++++++++
arch/riscv/include/asm/spinlock_types.h | 33 ++++
arch/riscv/include/asm/tlb.h | 24 +++
arch/riscv/include/asm/tlbflush.h | 64 ++++++
10 files changed, 1353 insertions(+)
create mode 100644 arch/riscv/include/asm/atomic.h
create mode 100644 arch/riscv/include/asm/barrier.h
create mode 100644 arch/riscv/include/asm/bitops.h
create mode 100644 arch/riscv/include/asm/cacheflush.h
create mode 100644 arch/riscv/include/asm/cmpxchg.h
create mode 100644 arch/riscv/include/asm/io.h
create mode 100644 arch/riscv/include/asm/spinlock.h
create mode 100644 arch/riscv/include/asm/spinlock_types.h
create mode 100644 arch/riscv/include/asm/tlb.h
create mode 100644 arch/riscv/include/asm/tlbflush.h
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
new file mode 100644
index 000000000000..e5a12cfa405a
--- /dev/null
+++ b/arch/riscv/include/asm/atomic.h
@@ -0,0 +1,337 @@
+/*
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _ASM_RISCV_ATOMIC_H
+#define _ASM_RISCV_ATOMIC_H
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+# include <asm-generic/atomic64.h>
+#else
+# if (__riscv_xlen < 64)
+# error "64-bit atomics require XLEN to be at least 64"
+# endif
+#endif
+
+#ifdef CONFIG_ISA_A
+
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+
+#define ATOMIC_INIT(i) { (i) }
+static __always_inline int atomic_read(const atomic_t *v)
+{
+ return READ_ONCE(v->counter);
+}
+static __always_inline void atomic_set(atomic_t *v, int i)
+{
+ WRITE_ONCE(v->counter, i);
+}
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC64_INIT(i) { (i) }
+static __always_inline int atomic64_read(const atomic64_t *v)
+{
+ return READ_ONCE(v->counter);
+}
+static __always_inline void atomic64_set(atomic64_t *v, int i)
+{
+ WRITE_ONCE(v->counter, i);
+}
+#endif
+
+/*
+ * First, the atomic ops that have no ordering constraints and therefor don't
+ * have the AQ or RL bits set. These don't return anything, so there's only
+ * one version to worry about.
+ */
+#define ATOMIC_OP(op, asm_op, c_op, I, asm_type, c_type, prefix) \
+static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
+{ \
+ __asm__ __volatile__ ( \
+ "amo" #asm_op "." #asm_type " zero, %1, %0" \
+ : "+A" (v->counter) \
+ : "r" (I)); \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, w, int, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, w, int, ) \
+ ATOMIC_OP (op, asm_op, c_op, I, d, long, 64)
+#endif
+
+ATOMIC_OPS(add, add, +, i)
+ATOMIC_OPS(sub, add, +, -i)
+/*
+ * FIXME: I could only find documentation that atomic_{add,sub,inc,dec} are
+ * barrier-free. I'm assuming that and/or/xor have the same constraints as the
+ * others.
+ */
+ATOMIC_OPS(and, and, &, i)
+ATOMIC_OPS( or, or, |, i)
+ATOMIC_OPS(xor, xor, ^, i)
+
+#undef ATOMIC_OP
+#undef ATOMIC_OPS
+
+/*
+ * Atomic ops that have ordered, relaxed, acquire, and relese variants.
+ * There's two flavors of these: the arithmatic ops have both fetch and return
+ * versions, while the logical ops only have fetch versions.
+ */
+#define ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix) \
+static __always_inline c_type atomic##prefix##_fetch_##op##c_or(c_type i, atomic##prefix##_t *v) \
+{ \
+ register c_type ret; \
+ __asm__ __volatile__ ( \
+ "amo" #asm_op "." #asm_type #asm_or " %2, %1, %0" \
+ : "+A" (v->counter), "=r" (ret) \
+ : "r" (I)); \
+ return ret; \
+}
+
+#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix) \
+static __always_inline c_type atomic##prefix##_##op##_return##c_or(int i, atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_fetch_##op##c_or(i, v) c_op I; \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w, int, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, d, long, 64) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#endif
+
+ATOMIC_OPS(add, add, +, i, , _relaxed)
+ATOMIC_OPS(add, add, +, i, .aq , _acquire)
+ATOMIC_OPS(add, add, +, i, .rl , _release)
+ATOMIC_OPS(add, add, +, i, .aqrl, )
+
+ATOMIC_OPS(sub, add, +, -i, , _relaxed)
+ATOMIC_OPS(sub, add, +, -i, .aq , _acquire)
+ATOMIC_OPS(sub, add, +, -i, .rl , _release)
+ATOMIC_OPS(sub, add, +, -i, .aqrl, )
+
+#undef ATOMIC_OPS
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w, int, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or) \
+ ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w, int, ) \
+ ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#endif
+
+ATOMIC_OPS(and, and, &, i, , _relaxed)
+ATOMIC_OPS(and, and, &, i, .aq , _acquire)
+ATOMIC_OPS(and, and, &, i, .rl , _release)
+ATOMIC_OPS(and, and, &, i, .aqrl, )
+
+ATOMIC_OPS( or, or, |, i, , _relaxed)
+ATOMIC_OPS( or, or, |, i, .aq , _acquire)
+ATOMIC_OPS( or, or, |, i, .rl , _release)
+ATOMIC_OPS( or, or, |, i, .aqrl, )
+
+ATOMIC_OPS(xor, xor, ^, i, , _relaxed)
+ATOMIC_OPS(xor, xor, ^, i, .aq , _acquire)
+ATOMIC_OPS(xor, xor, ^, i, .rl , _release)
+ATOMIC_OPS(xor, xor, ^, i, .aqrl, )
+
+#undef ATOMIC_OPS
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+
+/*
+ * The extra atomic operations that are constructed from one of the core
+ * AMO-based operations above (aside from sub, which is easier to fit above).
+ * These are required to perform a barrier, but they're OK this way because
+ * atomic_*_return is also required to perform a barrier.
+ */
+#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix) \
+static __always_inline bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_##func_op##_return(i, v) comp_op I; \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, func_op, comp_op, I) \
+ ATOMIC_OP (op, func_op, comp_op, I, int, )
+#else
+#define ATOMIC_OPS(op, func_op, comp_op, I) \
+ ATOMIC_OP (op, func_op, comp_op, I, int, ) \
+ ATOMIC_OP (op, func_op, comp_op, I, long, 64)
+#endif
+
+ATOMIC_OPS(add_and_test, add, ==, 0)
+ATOMIC_OPS(sub_and_test, sub, ==, 0)
+ATOMIC_OPS(add_negative, add, <, 0)
+
+#undef ATOMIC_OP
+#undef ATOMIC_OPS
+
+#define ATOMIC_OP(op, func_op, c_op, I, prefix) \
+static __always_inline void atomic##prefix##_##op(atomic##prefix##_t *v) \
+{ \
+ atomic##prefix##_##func_op(I, v); \
+}
+
+#define ATOMIC_FETCH_OP(op, func_op, c_op, I, prefix) \
+static __always_inline int atomic##prefix##_fetch_##op(atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_fetch_##func_op(I, v); \
+}
+
+#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, prefix) \
+static __always_inline int atomic##prefix##_##op##_return(atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_fetch_##op(v) c_op I; \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, )
+#else
+#define ATOMIC_OPS(op, asm_op, c_op, I) \
+ ATOMIC_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, ) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, ) \
+ ATOMIC_OP (op, asm_op, c_op, I, 64) \
+ ATOMIC_FETCH_OP (op, asm_op, c_op, I, 64) \
+ ATOMIC_OP_RETURN(op, asm_op, c_op, I, 64)
+#endif
+
+ATOMIC_OPS(inc, add, +, 1)
+ATOMIC_OPS(dec, add, +, -1)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+
+#define ATOMIC_OP(op, func_op, comp_op, I, prefix) \
+static __always_inline bool atomic##prefix##_##op(atomic##prefix##_t *v) \
+{ \
+ return atomic##prefix##_##func_op##_return(v) comp_op I; \
+}
+
+ATOMIC_OP(inc_and_test, inc, ==, 0, )
+ATOMIC_OP(dec_and_test, dec, ==, 0, )
+#ifndef CONFIG_GENERIC_ATOMIC64
+ATOMIC_OP(inc_and_test, inc, ==, 0, 64)
+ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
+#endif
+
+#undef ATOMIC_OP
+
+/* This is required to provide a barrier on success. */
+static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+ register int prev, rc;
+
+ __asm__ __volatile__ (
+ "0:\n\t"
+ "lr.w.aqrl %0, %2\n\t"
+ "beq %0, %4, 1f\n\t"
+ "add %1, %0, %3\n\t"
+ "sc.w.aqrl %1, %1, %2\n\t"
+ "bnez %1, 0b\n\t"
+ "1:"
+ : "=&r" (prev), "=&r" (rc), "+A" (v->counter)
+ : "r" (a), "r" (u));
+ return prev;
+}
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+static __always_inline long atomic64_add_unless(atomic64_t *v, long a, long u)
+{
+ register long prev, rc;
+
+ __asm__ __volatile__ (
+ "0:\n\t"
+ "lr.d.aqrl %0, %2\n\t"
+ "beq %0, %4, 1f\n\t"
+ "add %1, %0, %3\n\t"
+ "sc.d.aqrl %1, %1, %2\n\t"
+ "bnez %1, 0b\n\t"
+ "1:"
+ : "=&r" (prev), "=&r" (rc), "+A" (v->counter)
+ : "r" (a), "r" (u));
+ return prev;
+}
+#endif
+
+/*
+ * The extra atomic operations that are constructed from one of the core
+ * LR/SC-based operations above.
+ */
+static __always_inline int atomic_inc_not_zero(atomic_t *v)
+{
+ return __atomic_add_unless(v, 1, 0);
+}
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+static __always_inline int atomic64_inc_not_zero(atomic64_t *v)
+{
+ return atomic64_add_unless(v, 1, 0);
+}
+#endif
+
+/*
+ * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
+ * {cmp,}xchg and the operations that return, so they need a barrier. We just
+ * use the other implementations directly.
+ */
+#define ATOMIC_OP(c_t, prefix, c_or, size, asm_or) \
+static __always_inline c_t atomic##prefix##_cmpxchg##c_or(atomic##prefix##_t *v, c_t o, c_t n) \
+{ \
+ return __cmpxchg(&(v->counter), o, n, size, asm_or, asm_or); \
+} \
+static __always_inline c_t atomic##prefix##_xchg##c_or(atomic##prefix##_t *v, c_t n) \
+{ \
+ return __xchg(n, &(v->counter), size, asm_or); \
+}
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#define ATOMIC_OPS(c_or, asm_or) \
+ ATOMIC_OP( int, , c_or, 4, asm_or)
+#else
+#define ATOMIC_OPS(c_or, asm_or) \
+ ATOMIC_OP( int, , c_or, 4, asm_or) \
+ ATOMIC_OP(long, 64, c_or, 8, asm_or)
+#endif
+
+ATOMIC_OPS( , .aqrl)
+ATOMIC_OPS(_acquire, .aq)
+ATOMIC_OPS(_release, .rl)
+ATOMIC_OPS(_relaxed, )
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP
+
+#else /* !CONFIG_ISA_A */
+
+#include <asm-generic/atomic.h>
+
+#endif /* CONFIG_ISA_A */
+
+#endif /* _ASM_RISCV_ATOMIC_H */
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
new file mode 100644
index 000000000000..cbe7bc5c506e
--- /dev/null
+++ b/arch/riscv/include/asm/barrier.h
@@ -0,0 +1,143 @@
+/*
+ * Based on arch/arm/include/asm/barrier.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2013 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ASM_RISCV_BARRIER_H
+#define _ASM_RISCV_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#define nop() __asm__ __volatile__ ("nop")
+
+#define RISCV_FENCE(p, s) \
+ __asm__ __volatile__ ("fence " #p "," #s : : : "memory")
+
+/* These barries need to enforce ordering on both devices or memory. */
+#define mb() RISCV_FENCE(iorw,iorw)
+#define rmb() RISCV_FENCE(ir,ir)
+#define wmb() RISCV_FENCE(ow,ow)
+
+/* These barries do not need to enforce ordering on devices, just memory. */
+#define smp_mb() RISCV_FENCE(rw,rw)
+#define smp_rmb() RISCV_FENCE(r,r)
+#define smp_wmb() RISCV_FENCE(w,w)
+
+/*
+ * Our atomic operations set the AQ and RL bits and therefor we don't need to
+ * fence around atomics.
+ */
+#define __smb_mb__before_atomic() barrier()
+#define __smb_mb__after_atomic() barrier()
+
+/*
+ * These barries are meant to prevent memory operations inside a spinlock from
+ * moving outside of that spinlock. Since we set the AQ and RL bits when
+ * entering or leaving spinlocks, no additional fence needs to be performed.
+ */
+#define smb_mb__before_spinlock() barrier()
+#define smb_mb__after_spinlock() barrier()
+
+/* FIXME: I don't think RISC-V is allowed to perform a speculative load. */
+#define smp_acquire__after_ctrl_dep() barrier()
+
+/*
+ * The RISC-V ISA doesn't support byte or half-word AMOs, so we fall back to a
+ * regular store and a fence here. Otherwise we emit an AMO with an AQ or RL
+ * bit set and allow the microarchitecture to avoid the other half of the AMO.
+ */
+#define __smp_store_release(p, v) \
+do { \
+ union { typeof(*p) __val; char __c[1]; } __u = \
+ { .__val = (__force typeof(*p)) (v) }; \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 1: \
+ case 2: \
+ smb_mb(); \
+ WRITE_ONCE(*p, __u.__val); \
+ break; \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "amoswap.w.rl zero, %1, %0" \
+ : "+A" (*p), "r" (__u.__val) \
+ : \
+ : "memory"); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "amoswap.d.rl zero, %1, %0" \
+ : "+A" (*p), "r" (__u.__val) \
+ : \
+ : "memory"); \
+ break; \
+ } \
+} while (0)
+
+#define __smp_load_acquire(p) \
+do { \
+ union { typeof(*p) __val; char __c[1]; } __u = \
+ { .__val = (__force typeof(*p)) (v) }; \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 1: \
+ case 2: \
+ __u.__val = READ_ONCE(*p); \
+ smb_mb(); \
+ break; \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "amoor.w.aq %1, zero, %0" \
+ : "+A" (*p) \
+ : "=r" (__u.__val) \
+ : "memory"); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "amoor.d.aq %1, zero, %0" \
+ : "+A" (*p) \
+ : "=r" (__u.__val) \
+ : "memory"); \
+ break; \
+ } \
+ __u.__val; \
+} while (0)
+
+/*
+ * The default implementation of this uses READ_ONCE and
+ * smp_acquire__after_ctrl_dep, but since we can directly do an ACQUIRE load we
+ * can avoid the extra barrier.
+ */
+#define smp_cond_load_acquire(ptr, cond_expr) ({ \
+ typeof(ptr) __PTR = (ptr); \
+ typeof(*ptr) VAL; \
+ for (;;) { \
+ VAL = __smp_load_acquire(__PTR); \
+ if (cond_expr) \
+ break; \
+ cpu_relax(); \
+ } \
+ smp_acquire__after_ctrl_dep(); \
+ VAL; \
+})
+
+#include <asm-generic/barrier.h>
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_BARRIER_H */
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
new file mode 100644
index 000000000000..27e47858c6b1
--- /dev/null
+++ b/arch/riscv/include/asm/bitops.h
@@ -0,0 +1,228 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_BITOPS_H
+#define _ASM_RISCV_BITOPS_H
+
+#ifndef _LINUX_BITOPS_H
+#error "Only <linux/bitops.h> can be included directly"
+#endif /* _LINUX_BITOPS_H */
+
+#ifdef __KERNEL__
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <asm/barrier.h>
+#include <asm/bitsperlong.h>
+
+#ifdef CONFIG_ISA_A
+
+#ifndef smp_mb__before_clear_bit
+#define smp_mb__before_clear_bit() smp_mb()
+#define smp_mb__after_clear_bit() smp_mb()
+#endif /* smp_mb__before_clear_bit */
+
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/ffs.h>
+
+#include <asm-generic/bitops/hweight.h>
+
+#if (BITS_PER_LONG == 64)
+#define __AMO(op) "amo" #op ".d"
+#elif (BITS_PER_LONG == 32)
+#define __AMO(op) "amo" #op ".w"
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+#define __test_and_op_bit(op, mod, nr, addr) \
+({ \
+ unsigned long __res, __mask; \
+ __mask = BIT_MASK(nr); \
+ __asm__ __volatile__ ( \
+ __AMO(op) " %0, %2, %1" \
+ : "=r" (__res), "+A" (addr[BIT_WORD(nr)]) \
+ : "r" (mod(__mask))); \
+ ((__res & __mask) != 0); \
+})
+
+#define __op_bit(op, mod, nr, addr) \
+ __asm__ __volatile__ ( \
+ __AMO(op) " zero, %1, %0" \
+ : "+A" (addr[BIT_WORD(nr)]) \
+ : "r" (mod(BIT_MASK(nr))))
+
+/* Bitmask modifiers */
+#define __NOP(x) (x)
+#define __NOT(x) (~(x))
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It may be reordered on other architectures than x86.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+ return __test_and_op_bit(or, __NOP, nr, addr);
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It can be reordered on other architectures other than x86.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+ return __test_and_op_bit(and, __NOT, nr, addr);
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+ return __test_and_op_bit(xor, __NOP, nr, addr);
+}
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered. See __set_bit()
+ * if you do not require the atomic guarantees.
+ *
+ * Note: there are no guarantees that this function will not be reordered
+ * on non x86 architectures, so if you are writing portable code,
+ * make sure not to rely on its reordering guarantees.
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void set_bit(int nr, volatile unsigned long *addr)
+{
+ __op_bit(or, __NOP, nr, addr);
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and may not be reordered. However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * in order to ensure changes are visible on other processors.
+ */
+static inline void clear_bit(int nr, volatile unsigned long *addr)
+{
+ __op_bit(and, __NOT, nr, addr);
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered. It may be
+ * reordered on other architectures than x86.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void change_bit(int nr, volatile unsigned long *addr)
+{
+ __op_bit(xor, __NOP, nr, addr);
+}
+
+/**
+ * test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and provides acquire barrier semantics.
+ * It can be used to implement bit locks.
+ */
+static inline int test_and_set_bit_lock(
+ unsigned long nr, volatile unsigned long *addr)
+{
+ return test_and_set_bit(nr, addr);
+}
+
+/**
+ * clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ */
+static inline void clear_bit_unlock(
+ unsigned long nr, volatile unsigned long *addr)
+{
+ clear_bit(nr, addr);
+}
+
+/**
+ * __clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is like clear_bit_unlock, however it is not atomic.
+ * It does provide release barrier semantics so it can be used to unlock
+ * a bit lock, however it would only be used if no other CPU can modify
+ * any bits in the memory until the lock is released (a good example is
+ * if the bit lock itself protects access to the other bits in the word).
+ */
+static inline void __clear_bit_unlock(
+ unsigned long nr, volatile unsigned long *addr)
+{
+ clear_bit(nr, addr);
+}
+
+#undef __test_and_op_bit
+#undef __op_bit
+#undef __NOP
+#undef __NOT
+#undef __AMO
+
+#include <asm-generic/bitops/non-atomic.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic.h>
+
+#else /* !CONFIG_ISA_A */
+
+#include <asm-generic/bitops.h>
+
+#endif /* CONFIG_ISA_A */
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_RISCV_BITOPS_H */
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
new file mode 100644
index 000000000000..0595585013b0
--- /dev/null
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -0,0 +1,39 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_CACHEFLUSH_H
+#define _ASM_RISCV_CACHEFLUSH_H
+
+#include <asm-generic/cacheflush.h>
+
+#undef flush_icache_range
+#undef flush_icache_user_range
+
+static inline void local_flush_icache_all(void)
+{
+ asm volatile ("fence.i" ::: "memory");
+}
+
+#ifndef CONFIG_SMP
+
+#define flush_icache_range(start, end) local_flush_icache_all()
+#define flush_icache_user_range(vma, pg, addr, len) local_flush_icache_all()
+
+#else /* CONFIG_SMP */
+
+#define flush_icache_range(start, end) sbi_remote_fence_i(0)
+#define flush_icache_user_range(vma, pg, addr, len) sbi_remote_fence_i(0)
+
+#endif /* CONFIG_SMP */
+
+#endif /* _ASM_RISCV_CACHEFLUSH_H */
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..81025c056412
--- /dev/null
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -0,0 +1,138 @@
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_CMPXCHG_H
+#define _ASM_RISCV_CMPXCHG_H
+
+#include <linux/bug.h>
+
+#ifdef CONFIG_ISA_A
+
+#include <asm/barrier.h>
+
+#define __xchg(new, ptr, size, asm_or) \
+({ \
+ __typeof__(ptr) __ptr = (ptr); \
+ __typeof__(new) __new = (new); \
+ __typeof__(*(ptr)) __ret; \
+ switch (size) { \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "amoswap.w" #asm_or " %0, %2, %1" \
+ : "=r" (__ret), "+A" (*__ptr) \
+ : "r" (__new)); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "amoswap.d" #asm_or " %0, %2, %1" \
+ : "=r" (__ret), "+A" (*__ptr) \
+ : "r" (__new)); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ __ret; \
+})
+
+#define xchg(ptr, x) (__xchg((x), (ptr), sizeof(*(ptr)), .aqrl))
+
+#define xchg32(ptr, x) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
+ xchg((ptr), (x)); \
+})
+
+#define xchg64(ptr, x) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ xchg((ptr), (x)); \
+})
+
+/*
+ * Atomic compare and exchange. Compare OLD with MEM, if identical,
+ * store NEW in MEM. Return the initial value in MEM. Success is
+ * indicated by comparing RETURN with OLD.
+ */
+#define __cmpxchg(ptr, old, new, size, lrb, scb) \
+({ \
+ __typeof__(ptr) __ptr = (ptr); \
+ __typeof__(old) __old = (old); \
+ __typeof__(new) __new = (new); \
+ __typeof__(*(ptr)) __ret; \
+ register unsigned int __rc; \
+ switch (size) { \
+ case 4: \
+ __asm__ __volatile__ ( \
+ "0:" \
+ "lr.w" #scb " %0, %2\n" \
+ "bne %0, %z3, 1f\n" \
+ "sc.w" #lrb " %1, %z4, %2\n" \
+ "bnez %1, 0b\n" \
+ "1:" \
+ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
+ : "rJ" (__old), "rJ" (__new)); \
+ break; \
+ case 8: \
+ __asm__ __volatile__ ( \
+ "0:" \
+ "lr.d" #scb " %0, %2\n" \
+ "bne %0, %z3, 1f\n" \
+ "sc.d" #lrb " %1, %z4, %2\n" \
+ "bnez %1, 0b\n" \
+ "1:" \
+ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
+ : "rJ" (__old), "rJ" (__new)); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ __ret; \
+})
+
+#define cmpxchg(ptr, o, n) \
+ (__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), .aqrl, .aqrl))
+
+#define cmpxchg_local(ptr, o, n) \
+ (__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), , ))
+
+#define cmpxchg32(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
+ cmpxchg((ptr), (o), (n)); \
+})
+
+#define cmpxchg32_local(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
+ cmpxchg_local((ptr), (o), (n)); \
+})
+
+#define cmpxchg64(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ cmpxchg((ptr), (o), (n)); \
+})
+
+#define cmpxchg64_local(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ cmpxchg_local((ptr), (o), (n)); \
+})
+
+#else /* !CONFIG_ISA_A */
+
+#include <asm-generic/cmpxchg.h>
+
+#endif /* CONFIG_ISA_A */
+
+#endif /* _ASM_RISCV_CMPXCHG_H */
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
new file mode 100644
index 000000000000..c47177cb6660
--- /dev/null
+++ b/arch/riscv/include/asm/io.h
@@ -0,0 +1,180 @@
+/*
+ * {read,write}{b,w,l,q} based on arch/arm64/include/asm/io.h
+ * which was based on arch/arm/include/io.h
+ *
+ * Copyright (C) 1996-2000 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_IO_H
+#define _ASM_RISCV_IO_H
+
+#ifdef CONFIG_MMU
+
+extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
+
+/*
+ * The RISC-V ISA doesn't yet specify how to query of modify PMAs, so we can't
+ * change the properties of memory regions. This should be fixed by the
+ * upcoming platform spec.
+ */
+#define ioremap_nocache(addr, size) ioremap((addr), (size))
+#define ioremap_wc(addr, size) ioremap((addr), (size))
+#define ioremap_wt(addr, size) ioremap((addr), (size))
+
+extern void iounmap(void __iomem *addr);
+
+#endif /* CONFIG_MMU */
+
+/* Generic IO read/write. These perform native-endian accesses. */
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
+{
+ asm volatile("sb %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 val, volatile void __iomem *addr)
+{
+ asm volatile("sh %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 val, volatile void __iomem *addr)
+{
+ asm volatile("sw %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+
+#ifdef __riscv64
+#define __raw_writeq __raw_writeq
+static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
+{
+ asm volatile("sd %0, 0(%1)" : : "r" (val), "r" (addr));
+}
+#endif
+
+#define __raw_readb __raw_readb
+static inline u8 __raw_readb(const volatile void __iomem *addr)
+{
+ u8 val;
+
+ asm volatile("lb %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+
+#define __raw_readw __raw_readw
+static inline u16 __raw_readw(const volatile void __iomem *addr)
+{
+ u16 val;
+
+ asm volatile("lh %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+
+#define __raw_readl __raw_readl
+static inline u32 __raw_readl(const volatile void __iomem *addr)
+{
+ u32 val;
+
+ asm volatile("lw %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+
+#ifdef __riscv64
+#define __raw_readq __raw_readq
+static inline u64 __raw_readq(const volatile void __iomem *addr)
+{
+ u64 val;
+
+ asm volatile("ld %0, 0(%1)" : "=r" (val) : "r" (addr));
+ return val;
+}
+#endif
+
+/*
+ * FIXME: I'm flip-flopping on whether or not we should keep this or enforce
+ * the ordering with I/O on spinlocks. The worry is that drivers won't get
+ * this correct, but I also don't want to introduce a fence into the lock code
+ * that otherwise only uses AMOs and LR/SC. For now I'm leaving this here:
+ * "w,o" is sufficient to ensure that all writes to the device has completed
+ * before the write to the spinlock is allowed to commit. I surmised this from
+ * reading "ACQUIRES VS I/O ACCESSES" in memory-barries.txt.
+ */
+#define mmiowb() __asm__ __volatile__ ("fence o,w" : : : "memory");
+
+/*
+ * Unordered I/O memory access primitives. These are even more relaxed than
+ * the relaxed versions, as they don't even order accesses between successive
+ * operations to the I/O regions.
+ */
+#define readb_cpu(c) ({ u8 __r = __raw_readb(c); __r; })
+#define readw_cpu(c) ({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; })
+#define readl_cpu(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
+#define readq_cpu(c) ({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; })
+
+#define writeb_cpu(v,c) ((void)__raw_writeb((v),(c)))
+#define writew_cpu(v,c) ((void)__raw_writew((__force u16)cpu_to_le16(v),(c)))
+#define writel_cpu(v,c) ((void)__raw_writel((__force u32)cpu_to_le32(v),(c)))
+#define writeq_cpu(v,c) ((void)__raw_writeq((__force u64)cpu_to_le64(v),(c)))
+
+/*
+ * Relaxed I/O memory access primitives. These follow the Device memory
+ * ordering rules but do not guarantee any ordering relative to Normal memory
+ * accesses. The memory barries here are necessary as RISC-V doesn't define
+ * any ordering constraints on accesses to the device I/O space. These are
+ * defined to order the indicated access (either a read or write) with all
+ * other I/O memory accesses.
+ */
+/*
+ * FIXME: The platform spec will define the default Linux-capable platform to
+ * have some extra IO ordering constraints that will make these fences
+ * unnecessary.
+ */
+#define __iorrmb() __asm__ __volatile__ ("fence i,io" : : : "memory");
+#define __iorwmb() __asm__ __volatile__ ("fence io,o" : : : "memory");
+
+#define readb_relaxed(c) ({ u8 __v = readb_cpu(c); __iorrmb(); __v; })
+#define readw_relaxed(c) ({ u16 __v = readw_cpu(c); __iorrmb(); __v; })
+#define readl_relaxed(c) ({ u32 __v = readl_cpu(c); __iorrmb(); __v; })
+#define readq_relaxed(c) ({ u64 __v = readq_cpu(c); __iorrmb(); __v; })
+
+#define writeb_relaxed(v,c) ({ __iorwmb(); writeb_cpu((v),(c)); })
+#define writew_relaxed(v,c) ({ __iorwmb(); writew_cpu((v),(c)); })
+#define writel_relaxed(v,c) ({ __iorwmb(); writel_cpu((v),(c)); })
+#define writeq_relaxed(v,c) ({ __iorwmb(); writeq_cpu((v),(c)); })
+
+/*
+ * I/O memory access primitives. Reads are ordered relative to any
+ * following Normal memory access. Writes are ordered relative to any prior
+ * Normal memory access. The memory barriers here are necessary as RISC-V
+ * doesn't define any ordering between the memory space and the I/O space.
+ * They may be stronger than necessary ("i,r" and "w,o" might be sufficient),
+ * but I feel kind of queasy making these weaker in any manner than the relaxed
+ * versions above.
+ */
+#define __iormb() __asm__ __volatile__ ("fence i,ior" : : : "memory");
+#define __iowmb() __asm__ __volatile__ ("fence iow,o" : : : "memory");
+
+#define readb(c) ({ u8 __v = readb_cpu(c); __iormb(); __v; })
+#define readw(c) ({ u16 __v = readw_cpu(c); __iormb(); __v; })
+#define readl(c) ({ u32 __v = readl_cpu(c); __iormb(); __v; })
+#define readq(c) ({ u64 __v = readq_cpu(c); __iormb(); __v; })
+
+#define writeb(v,c) ({ __iowmb(); writeb_cpu((v),(c)); })
+#define writew(v,c) ({ __iowmb(); writew_cpu((v),(c)); })
+#define writel(v,c) ({ __iowmb(); writel_cpu((v),(c)); })
+#define writeq(v,c) ({ __iowmb(); writeq_cpu((v),(c)); })
+
+#include <asm-generic/io.h>
+
+#endif /* _ASM_RISCV_IO_H */
diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
new file mode 100644
index 000000000000..54ed73bfa972
--- /dev/null
+++ b/arch/riscv/include/asm/spinlock.h
@@ -0,0 +1,167 @@
+/*
+ * Copyright (C) 2015 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.
+ */
+
+#ifndef _ASM_RISCV_SPINLOCK_H
+#define _ASM_RISCV_SPINLOCK_H
+
+#include <linux/kernel.h>
+#include <asm/current.h>
+
+/*
+ * Simple spin lock operations. These provide no fairness guarantees.
+ */
+
+/* FIXME: Replace this with a ticket lock, like MIPS. */
+
+#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
+#define arch_spin_is_locked(x) ((x)->lock != 0)
+#define arch_spin_unlock_wait(x) \
+ do { cpu_relax(); } while ((x)->lock)
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+ __asm__ __volatile__ (
+ "amoswap.w.rl x0, x0, %0"
+ : "=A" (lock->lock)
+ :: "memory");
+}
+
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+ int tmp = 1, busy;
+
+ __asm__ __volatile__ (
+ "amoswap.w.aq %0, %2, %1"
+ : "=r" (busy), "+A" (lock->lock)
+ : "r" (tmp)
+ : "memory");
+
+ return !busy;
+}
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+ while (1) {
+ if (arch_spin_is_locked(lock))
+ continue;
+
+ if (arch_spin_trylock(lock))
+ break;
+ }
+}
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+ smp_rmb();
+ do {
+ cpu_relax();
+ } while (arch_spin_is_locked(lock));
+ smp_acquire__after_ctrl_dep();
+}
+
+/***********************************************************/
+
+static inline int arch_read_can_lock(arch_rwlock_t *lock)
+{
+ return lock->lock >= 0;
+}
+
+static inline int arch_write_can_lock(arch_rwlock_t *lock)
+{
+ return lock->lock == 0;
+}
+
+static inline void arch_read_lock(arch_rwlock_t *lock)
+{
+ int tmp;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bltz %1, 1b\n"
+ " addi %1, %1, 1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ : "+A" (lock->lock), "=&r" (tmp)
+ :: "memory");
+}
+
+static inline void arch_write_lock(arch_rwlock_t *lock)
+{
+ int tmp;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bnez %1, 1b\n"
+ " li %1, -1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ : "+A" (lock->lock), "=&r" (tmp)
+ :: "memory");
+}
+
+static inline int arch_read_trylock(arch_rwlock_t *lock)
+{
+ int busy;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bltz %1, 1f\n"
+ " addi %1, %1, 1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ "1:\n"
+ : "+A" (lock->lock), "=&r" (busy)
+ :: "memory");
+
+ return !busy;
+}
+
+static inline int arch_write_trylock(arch_rwlock_t *lock)
+{
+ int busy;
+
+ __asm__ __volatile__(
+ "1: lr.w %1, %0\n"
+ " bnez %1, 1f\n"
+ " li %1, -1\n"
+ " sc.w.aq %1, %1, %0\n"
+ " bnez %1, 1b\n"
+ "1:\n"
+ : "+A" (lock->lock), "=&r" (busy)
+ :: "memory");
+
+ return !busy;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *lock)
+{
+ __asm__ __volatile__(
+ "amoadd.w.rl x0, %1, %0"
+ : "+A" (lock->lock)
+ : "r" (-1)
+ : "memory");
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *lock)
+{
+ __asm__ __volatile__ (
+ "amoswap.w.rl x0, x0, %0"
+ : "=A" (lock->lock)
+ :: "memory");
+}
+
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
+#endif /* _ASM_RISCV_SPINLOCK_H */
diff --git a/arch/riscv/include/asm/spinlock_types.h b/arch/riscv/include/asm/spinlock_types.h
new file mode 100644
index 000000000000..83ac4ac9e2ac
--- /dev/null
+++ b/arch/riscv/include/asm/spinlock_types.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SPINLOCK_TYPES_H
+#define _ASM_RISCV_SPINLOCK_TYPES_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+# error "please don't include this file directly"
+#endif
+
+typedef struct {
+ volatile unsigned int lock;
+} arch_spinlock_t;
+
+#define __ARCH_SPIN_LOCK_UNLOCKED { 0 }
+
+typedef struct {
+ volatile unsigned int lock;
+} arch_rwlock_t;
+
+#define __ARCH_RW_LOCK_UNLOCKED { 0 }
+
+#endif
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
new file mode 100644
index 000000000000..c229509288ea
--- /dev/null
+++ b/arch/riscv/include/asm/tlb.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_TLB_H
+#define _ASM_RISCV_TLB_H
+
+#include <asm-generic/tlb.h>
+
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+ flush_tlb_mm(tlb->mm);
+}
+
+#endif /* _ASM_RISCV_TLB_H */
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
new file mode 100644
index 000000000000..5ee4ae370b5e
--- /dev/null
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_TLBFLUSH_H
+#define _ASM_RISCV_TLBFLUSH_H
+
+#ifdef CONFIG_MMU
+
+/* Flush entire local TLB */
+static inline void local_flush_tlb_all(void)
+{
+ __asm__ __volatile__ ("sfence.vma" : : : "memory");
+}
+
+/* Flush one page from local TLB */
+static inline void local_flush_tlb_page(unsigned long addr)
+{
+ __asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory");
+}
+
+#ifndef CONFIG_SMP
+
+#define flush_tlb_all() local_flush_tlb_all()
+#define flush_tlb_page(vma, addr) local_flush_tlb_page(addr)
+#define flush_tlb_range(vma, start, end) local_flush_tlb_all()
+
+#else /* CONFIG_SMP */
+
+#include <asm/sbi.h>
+
+#define flush_tlb_all() sbi_remote_sfence_vma(0, 0, -1)
+#define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0)
+#define flush_tlb_range(vma, start, end) \
+ sbi_remote_sfence_vma(0, start, (end) - (start))
+
+#endif /* CONFIG_SMP */
+
+/* Flush the TLB entries of the specified mm context */
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+ flush_tlb_all();
+}
+
+/* Flush a range of kernel pages */
+static inline void flush_tlb_kernel_range(unsigned long start,
+ unsigned long end)
+{
+ flush_tlb_all();
+}
+
+#endif /* CONFIG_MMU */
+
+#endif /* _ASM_RISCV_TLBFLUSH_H */
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 3/9] RISC-V: Generic library routines and assembly
2017-07-04 19:50 ` Palmer Dabbelt
@ 2017-07-04 19:50 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains code that is more specific to the RISC-V ISA than it
is to Linux. It contains string and math operations, C wrappers for
various assembly instructions, stack walking code, and uaccess.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/asm.h | 76 ++++++
arch/riscv/include/asm/bitops.h | 4 -
arch/riscv/include/asm/csr.h | 125 +++++++++
arch/riscv/include/asm/linkage.h | 20 ++
arch/riscv/include/asm/string.h | 26 ++
arch/riscv/include/asm/uaccess.h | 441 ++++++++++++++++++++++++++++++++
arch/riscv/include/asm/word-at-a-time.h | 55 ++++
arch/riscv/kernel/stacktrace.c | 177 +++++++++++++
arch/riscv/lib/memcpy.S | 100 ++++++++
arch/riscv/lib/memset.S | 120 +++++++++
arch/riscv/lib/uaccess.S | 127 +++++++++
arch/riscv/lib/udivdi3.S | 38 +++
12 files changed, 1305 insertions(+), 4 deletions(-)
create mode 100644 arch/riscv/include/asm/asm.h
create mode 100644 arch/riscv/include/asm/csr.h
create mode 100644 arch/riscv/include/asm/linkage.h
create mode 100644 arch/riscv/include/asm/string.h
create mode 100644 arch/riscv/include/asm/uaccess.h
create mode 100644 arch/riscv/include/asm/word-at-a-time.h
create mode 100644 arch/riscv/kernel/stacktrace.c
create mode 100644 arch/riscv/lib/memcpy.S
create mode 100644 arch/riscv/lib/memset.S
create mode 100644 arch/riscv/lib/uaccess.S
create mode 100644 arch/riscv/lib/udivdi3.S
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
new file mode 100644
index 000000000000..6cbbb6a68d76
--- /dev/null
+++ b/arch/riscv/include/asm/asm.h
@@ -0,0 +1,76 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_ASM_H
+#define _ASM_RISCV_ASM_H
+
+#ifdef __ASSEMBLY__
+#define __ASM_STR(x) x
+#else
+#define __ASM_STR(x) #x
+#endif
+
+#if __riscv_xlen == 64
+#define __REG_SEL(a, b) __ASM_STR(a)
+#elif __riscv_xlen == 32
+#define __REG_SEL(a, b) __ASM_STR(b)
+#else
+#error "Unexpected __riscv_xlen"
+#endif
+
+#define REG_L __REG_SEL(ld, lw)
+#define REG_S __REG_SEL(sd, sw)
+#define SZREG __REG_SEL(8, 4)
+#define LGREG __REG_SEL(3, 2)
+
+#if __SIZEOF_POINTER__ == 8
+#ifdef __ASSEMBLY__
+#define RISCV_PTR .dword
+#define RISCV_SZPTR 8
+#define RISCV_LGPTR 3
+#else
+#define RISCV_PTR ".dword"
+#define RISCV_SZPTR "8"
+#define RISCV_LGPTR "3"
+#endif
+#elif __SIZEOF_POINTER__ == 4
+#ifdef __ASSEMBLY__
+#define RISCV_PTR .word
+#define RISCV_SZPTR 4
+#define RISCV_LGPTR 2
+#else
+#define RISCV_PTR ".word"
+#define RISCV_SZPTR "4"
+#define RISCV_LGPTR "2"
+#endif
+#else
+#error "Unexpected __SIZEOF_POINTER__"
+#endif
+
+#if (__SIZEOF_INT__ == 4)
+#define INT __ASM_STR(.word)
+#define SZINT __ASM_STR(4)
+#define LGINT __ASM_STR(2)
+#else
+#error "Unexpected __SIZEOF_INT__"
+#endif
+
+#if (__SIZEOF_SHORT__ == 2)
+#define SHORT __ASM_STR(.half)
+#define SZSHORT __ASM_STR(2)
+#define LGSHORT __ASM_STR(1)
+#else
+#error "Unexpected __SIZEOF_SHORT__"
+#endif
+
+#endif /* _ASM_RISCV_ASM_H */
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 27e47858c6b1..d4f1c9c66e4d 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -18,8 +18,6 @@
#error "Only <linux/bitops.h> can be included directly"
#endif /* _LINUX_BITOPS_H */
-#ifdef __KERNEL__
-
#include <linux/compiler.h>
#include <linux/irqflags.h>
#include <asm/barrier.h>
@@ -223,6 +221,4 @@ static inline void __clear_bit_unlock(
#endif /* CONFIG_ISA_A */
-#endif /* __KERNEL__ */
-
#endif /* _ASM_RISCV_BITOPS_H */
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
new file mode 100644
index 000000000000..387d0dbf0073
--- /dev/null
+++ b/arch/riscv/include/asm/csr.h
@@ -0,0 +1,125 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_CSR_H
+#define _ASM_RISCV_CSR_H
+
+#include <linux/const.h>
+
+/* Status register flags */
+#define SR_IE _AC(0x00000002, UL) /* Interrupt Enable */
+#define SR_PIE _AC(0x00000020, UL) /* Previous IE */
+#define SR_PS _AC(0x00000100, UL) /* Previously Supervisor */
+#define SR_SUM _AC(0x00040000, UL) /* Supervisor may access User Memory */
+
+#define SR_FS _AC(0x00006000, UL) /* Floating-point Status */
+#define SR_FS_OFF _AC(0x00000000, UL)
+#define SR_FS_INITIAL _AC(0x00002000, UL)
+#define SR_FS_CLEAN _AC(0x00004000, UL)
+#define SR_FS_DIRTY _AC(0x00006000, UL)
+
+#define SR_XS _AC(0x00018000, UL) /* Extension Status */
+#define SR_XS_OFF _AC(0x00000000, UL)
+#define SR_XS_INITIAL _AC(0x00008000, UL)
+#define SR_XS_CLEAN _AC(0x00010000, UL)
+#define SR_XS_DIRTY _AC(0x00018000, UL)
+
+#ifndef CONFIG_64BIT
+#define SR_SD _AC(0x80000000, UL) /* FS/XS dirty */
+#else
+#define SR_SD _AC(0x8000000000000000, UL) /* FS/XS dirty */
+#endif
+
+/* SPTBR flags */
+#if __riscv_xlen == 32
+#define SPTBR_PPN _AC(0x003FFFFF, UL)
+#define SPTBR_MODE_32 _AC(0x80000000, UL)
+#define SPTBR_MODE SPTBR_MODE_32
+#else
+#define SPTBR_PPN _AC(0x00000FFFFFFFFFFF, UL)
+#define SPTBR_MODE_39 _AC(0x8000000000000000, UL)
+#define SPTBR_MODE SPTBR_MODE_39
+#endif
+
+/* Interrupt Enable and Interrupt Pending flags */
+#define SIE_SSIE _AC(0x00000002, UL) /* Software Interrupt Enable */
+#define SIE_STIE _AC(0x00000020, UL) /* Timer Interrupt Enable */
+
+#define EXC_INST_MISALIGNED 0
+#define EXC_INST_ACCESS 1
+#define EXC_BREAKPOINT 3
+#define EXC_LOAD_ACCESS 5
+#define EXC_STORE_ACCESS 7
+#define EXC_SYSCALL 8
+#define EXC_INST_PAGE_FAULT 12
+#define EXC_LOAD_PAGE_FAULT 13
+#define EXC_STORE_PAGE_FAULT 15
+
+#ifndef __ASSEMBLY__
+
+#define csr_swap(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrrw %0, " #csr ", %1" \
+ : "=r" (__v) : "rK" (__v)); \
+ __v; \
+})
+
+#define csr_read(csr) \
+({ \
+ register unsigned long __v; \
+ __asm__ __volatile__ ("csrr %0, " #csr \
+ : "=r" (__v)); \
+ __v; \
+})
+
+#define csr_write(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrw " #csr ", %0" \
+ : : "rK" (__v)); \
+})
+
+#define csr_read_set(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrrs %0, " #csr ", %1" \
+ : "=r" (__v) : "rK" (__v)); \
+ __v; \
+})
+
+#define csr_set(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrs " #csr ", %0" \
+ : : "rK" (__v)); \
+})
+
+#define csr_read_clear(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrrc %0, " #csr ", %1" \
+ : "=r" (__v) : "rK" (__v)); \
+ __v; \
+})
+
+#define csr_clear(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrc " #csr ", %0" \
+ : : "rK" (__v)); \
+})
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_CSR_H */
diff --git a/arch/riscv/include/asm/linkage.h b/arch/riscv/include/asm/linkage.h
new file mode 100644
index 000000000000..b7b304ca89c4
--- /dev/null
+++ b/arch/riscv/include/asm/linkage.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_LINKAGE_H
+#define _ASM_RISCV_LINKAGE_H
+
+#define __ALIGN .balign 4
+#define __ALIGN_STR ".balign 4"
+
+#endif /* _ASM_RISCV_LINKAGE_H */
diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h
new file mode 100644
index 000000000000..9210fcf4ff52
--- /dev/null
+++ b/arch/riscv/include/asm/string.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2013 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_STRING_H
+#define _ASM_RISCV_STRING_H
+
+#include <linux/types.h>
+#include <linux/linkage.h>
+
+#define __HAVE_ARCH_MEMSET
+extern asmlinkage void *memset(void *, int, size_t);
+
+#define __HAVE_ARCH_MEMCPY
+extern asmlinkage void *memcpy(void *, const void *, size_t);
+
+#endif /* _ASM_RISCV_STRING_H */
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
new file mode 100644
index 000000000000..647a060090f1
--- /dev/null
+++ b/arch/riscv/include/asm/uaccess.h
@@ -0,0 +1,441 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ *
+ * This file was copied from include/asm-generic/uaccess.h
+ */
+
+#ifndef _ASM_RISCV_UACCESS_H
+#define _ASM_RISCV_UACCESS_H
+
+/*
+ * User space memory access functions
+ */
+#include <linux/errno.h>
+#include <linux/compiler.h>
+#include <linux/thread_info.h>
+#include <asm/byteorder.h>
+#include <asm/asm.h>
+
+#ifdef CONFIG_RV_PUM
+#define __enable_user_access() \
+ __asm__ __volatile__ ("csrs sstatus, %0" : : "r" (SR_SUM) : "memory")
+#define __disable_user_access() \
+ __asm__ __volatile__ ("csrc sstatus, %0" : : "r" (SR_SUM) : "memory")
+#else
+#define __enable_user_access()
+#define __disable_user_access()
+#endif
+
+/*
+ * The fs value determines whether argument validity checking should be
+ * performed or not. If get_fs() == USER_DS, checking is performed, with
+ * get_fs() == KERNEL_DS, checking is bypassed.
+ *
+ * For historical reasons, these macros are grossly misnamed.
+ */
+
+#define KERNEL_DS (~0UL)
+#define USER_DS (TASK_SIZE)
+
+#define get_ds() (KERNEL_DS)
+#define get_fs() (current_thread_info()->addr_limit)
+
+static inline void set_fs(mm_segment_t fs)
+{
+ current_thread_info()->addr_limit = fs;
+}
+
+#define segment_eq(a, b) ((a) == (b))
+
+#define user_addr_max() (get_fs())
+
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+/**
+ * access_ok: - Checks if a user space pointer is valid
+ * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE. Note that
+ * %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe
+ * to write to a block, it is always safe to read from it.
+ * @addr: User space pointer to start of block to check
+ * @size: Size of block to check
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * Checks if a pointer to a block of memory in user space is valid.
+ *
+ * Returns true (nonzero) if the memory block may be valid, false (zero)
+ * if it is definitely invalid.
+ *
+ * Note that, depending on architecture, this function probably just
+ * checks that the pointer is in the user space range - after calling
+ * this function, memory access functions may still return -EFAULT.
+ */
+#define access_ok(type, addr, size) ({ \
+ __chk_user_ptr(addr); \
+ likely(__access_ok((unsigned long __force)(addr), (size))); \
+})
+
+/*
+ * Ensure that the range [addr, addr+size) is within the process's
+ * address space
+ */
+static inline int __access_ok(unsigned long addr, unsigned long size)
+{
+ const mm_segment_t fs = get_fs();
+
+ return (size <= fs) && (addr <= (fs - size));
+}
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue. No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path. This means when everything is well,
+ * we don't even have to jump over them. Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry {
+ unsigned long insn, fixup;
+};
+
+extern int fixup_exception(struct pt_regs *state);
+
+#if defined(__LITTLE_ENDIAN)
+#define __MSW 1
+#define __LSW 0
+#elif defined(__BIG_ENDIAN)
+#define __MSW 0
+#define __LSW 1
+#else
+#error "Unknown endianness"
+#endif
+
+/*
+ * The "__xxx" versions of the user access functions do not verify the address
+ * space - it must have been done previously with a separate "access_ok()"
+ * call.
+ */
+
+#ifdef CONFIG_MMU
+#define __get_user_asm(insn, x, ptr, err) \
+do { \
+ uintptr_t __tmp; \
+ __typeof__(x) __x; \
+ __enable_user_access(); \
+ __asm__ __volatile__ ( \
+ "1:\n" \
+ " " insn " %1, %3\n" \
+ "2:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .balign 4\n" \
+ "3:\n" \
+ " li %0, %4\n" \
+ " li %1, 0\n" \
+ " jump 2b, %2\n" \
+ " .previous\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .balign " RISCV_SZPTR "\n" \
+ " " RISCV_PTR " 1b, 3b\n" \
+ " .previous" \
+ : "+r" (err), "=&r" (__x), "=r" (__tmp) \
+ : "m" (*(ptr)), "i" (-EFAULT)); \
+ __disable_user_access(); \
+ (x) = __x; \
+} while (0)
+#endif /* CONFIG_MMU */
+
+#ifdef CONFIG_64BIT
+#define __get_user_8(x, ptr, err) \
+ __get_user_asm("ld", x, ptr, err)
+#else /* !CONFIG_64BIT */
+#ifdef CONFIG_MMU
+#define __get_user_8(x, ptr, err) \
+do { \
+ u32 __user *__ptr = (u32 __user *)(ptr); \
+ u32 __lo, __hi; \
+ uintptr_t __tmp; \
+ __enable_user_access(); \
+ __asm__ __volatile__ ( \
+ "1:\n" \
+ " lw %1, %4\n" \
+ "2:\n" \
+ " lw %2, %5\n" \
+ "3:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .balign 4\n" \
+ "4:\n" \
+ " li %0, %6\n" \
+ " li %1, 0\n" \
+ " li %2, 0\n" \
+ " jump 3b, %3\n" \
+ " .previous\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .balign " RISCV_SZPTR "\n" \
+ " " RISCV_PTR " 1b, 4b\n" \
+ " " RISCV_PTR " 2b, 4b\n" \
+ " .previous" \
+ : "+r" (err), "=&r" (__lo), "=r" (__hi), \
+ "=r" (__tmp) \
+ : "m" (__ptr[__LSW]), "m" (__ptr[__MSW]), \
+ "i" (-EFAULT)); \
+ __disable_user_access(); \
+ (x) = (__typeof__(x))((__typeof__((x)-(x)))( \
+ (((u64)__hi << 32) | __lo))); \
+} while (0)
+#endif /* CONFIG_MMU */
+#endif /* CONFIG_64BIT */
+
+
+/**
+ * __get_user: - Get a simple variable from user space, with less checking.
+ * @x: Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space. It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+#define __get_user(x, ptr) \
+({ \
+ register long __gu_err = 0; \
+ const __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
+ __chk_user_ptr(__gu_ptr); \
+ switch (sizeof(*__gu_ptr)) { \
+ case 1: \
+ __get_user_asm("lb", (x), __gu_ptr, __gu_err); \
+ break; \
+ case 2: \
+ __get_user_asm("lh", (x), __gu_ptr, __gu_err); \
+ break; \
+ case 4: \
+ __get_user_asm("lw", (x), __gu_ptr, __gu_err); \
+ break; \
+ case 8: \
+ __get_user_8((x), __gu_ptr, __gu_err); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ __gu_err; \
+})
+
+/**
+ * get_user: - Get a simple variable from user space.
+ * @x: Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space. It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+#define get_user(x, ptr) \
+({ \
+ const __typeof__(*(ptr)) __user *__p = (ptr); \
+ might_fault(); \
+ access_ok(VERIFY_READ, __p, sizeof(*__p)) ? \
+ __get_user((x), __p) : \
+ ((x) = 0, -EFAULT); \
+})
+
+
+#ifdef CONFIG_MMU
+#define __put_user_asm(insn, x, ptr, err) \
+do { \
+ uintptr_t __tmp; \
+ __typeof__(*(ptr)) __x = x; \
+ __enable_user_access(); \
+ __asm__ __volatile__ ( \
+ "1:\n" \
+ " " insn " %z3, %2\n" \
+ "2:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .balign 4\n" \
+ "3:\n" \
+ " li %0, %4\n" \
+ " jump 2b, %1\n" \
+ " .previous\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .balign " RISCV_SZPTR "\n" \
+ " " RISCV_PTR " 1b, 3b\n" \
+ " .previous" \
+ : "+r" (err), "=r" (__tmp), "=m" (*(ptr)) \
+ : "rJ" (__x), "i" (-EFAULT)); \
+ __disable_user_access(); \
+} while (0)
+#endif /* CONFIG_MMU */
+
+
+#ifdef CONFIG_64BIT
+#define __put_user_8(x, ptr, err) \
+ __put_user_asm("sd", x, ptr, err)
+#else /* !CONFIG_64BIT */
+#ifdef CONFIG_MMU
+#define __put_user_8(x, ptr, err) \
+do { \
+ u32 __user *__ptr = (u32 __user *)(ptr); \
+ u64 __x = (__typeof__((x)-(x)))(x); \
+ uintptr_t __tmp; \
+ __enable_user_access(); \
+ __asm__ __volatile__ ( \
+ "1:\n" \
+ " sw %z4, %2\n" \
+ "2:\n" \
+ " sw %z5, %3\n" \
+ "3:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .balign 4\n" \
+ "4:\n" \
+ " li %0, %6\n" \
+ " jump 2b, %1\n" \
+ " .previous\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .balign " RISCV_SZPTR "\n" \
+ " " RISCV_PTR " 1b, 4b\n" \
+ " " RISCV_PTR " 2b, 4b\n" \
+ " .previous" \
+ : "+r" (err), "=r" (__tmp), \
+ "=m" (__ptr[__LSW]), \
+ "=m" (__ptr[__MSW]) \
+ : "rJ" (__x), "rJ" (__x >> 32), "i" (-EFAULT)); \
+ __disable_user_access(); \
+} while (0)
+#endif /* CONFIG_MMU */
+#endif /* CONFIG_64BIT */
+
+
+/**
+ * __put_user: - Write a simple value into user space, with less checking.
+ * @x: Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space. It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+#define __put_user(x, ptr) \
+({ \
+ register long __pu_err = 0; \
+ __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
+ __chk_user_ptr(__gu_ptr); \
+ switch (sizeof(*__gu_ptr)) { \
+ case 1: \
+ __put_user_asm("sb", (x), __gu_ptr, __pu_err); \
+ break; \
+ case 2: \
+ __put_user_asm("sh", (x), __gu_ptr, __pu_err); \
+ break; \
+ case 4: \
+ __put_user_asm("sw", (x), __gu_ptr, __pu_err); \
+ break; \
+ case 8: \
+ __put_user_8((x), __gu_ptr, __pu_err); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ __pu_err; \
+})
+
+/**
+ * put_user: - Write a simple value into user space.
+ * @x: Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space. It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+#define put_user(x, ptr) \
+({ \
+ __typeof__(*(ptr)) __user *__p = (ptr); \
+ might_fault(); \
+ access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ? \
+ __put_user((x), __p) : \
+ -EFAULT; \
+})
+
+
+extern unsigned long __must_check __copy_user(void __user *to,
+ const void __user *from, unsigned long n);
+
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ return __copy_user(to, from, n);
+}
+
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ return __copy_user(to, from, n);
+}
+
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+
+extern long __must_check strlen_user(const char __user *str);
+extern long __must_check strnlen_user(const char __user *str, long n);
+
+extern
+unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
+
+static inline
+unsigned long __must_check clear_user(void __user *to, unsigned long n)
+{
+ might_fault();
+ return access_ok(VERIFY_WRITE, to, n) ?
+ __clear_user(to, n) : n;
+}
+
+#endif /* _ASM_RISCV_UACCESS_H */
diff --git a/arch/riscv/include/asm/word-at-a-time.h b/arch/riscv/include/asm/word-at-a-time.h
new file mode 100644
index 000000000000..aa6238791d3e
--- /dev/null
+++ b/arch/riscv/include/asm/word-at-a-time.h
@@ -0,0 +1,55 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ * Derived from arch/x86/include/asm/word-at-a-time.h
+ */
+
+#ifndef _ASM_RISCV_WORD_AT_A_TIME_H
+#define _ASM_RISCV_WORD_AT_A_TIME_H
+
+
+#include <linux/kernel.h>
+
+struct word_at_a_time {
+ const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+static inline unsigned long has_zero(unsigned long val,
+ unsigned long *bits, const struct word_at_a_time *c)
+{
+ unsigned long mask = ((val - c->one_bits) & ~val) & c->high_bits;
+ *bits = mask;
+ return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long val,
+ unsigned long bits, const struct word_at_a_time *c)
+{
+ return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+ bits = (bits - 1) & ~bits;
+ return bits >> 7;
+}
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+ return fls64(mask) >> 3;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+#endif /* _ASM_RISCV_WORD_AT_A_TIME_H */
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
new file mode 100644
index 000000000000..559aae781154
--- /dev/null
+++ b/arch/riscv/kernel/stacktrace.c
@@ -0,0 +1,177 @@
+/*
+ * Copyright (C) 2008 ARM Limited
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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/export.h>
+#include <linux/kallsyms.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
+#include <linux/stacktrace.h>
+
+#ifdef CONFIG_FRAME_POINTER
+
+struct stackframe {
+ unsigned long fp;
+ unsigned long ra;
+};
+
+static void notrace walk_stackframe(struct task_struct *task,
+ struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
+{
+ unsigned long fp, sp, pc;
+
+ if (regs) {
+ fp = GET_FP(regs);
+ sp = GET_USP(regs);
+ pc = GET_IP(regs);
+ } else if (task == NULL || task == current) {
+ const register unsigned long current_sp __asm__ ("sp");
+ fp = (unsigned long)__builtin_frame_address(0);
+ sp = current_sp;
+ pc = (unsigned long)walk_stackframe;
+ } else {
+ /* task blocked in __switch_to */
+ fp = task->thread.s[0];
+ sp = task->thread.sp;
+ pc = task->thread.ra;
+ }
+
+ for (;;) {
+ unsigned long low, high;
+ struct stackframe *frame;
+
+ if (unlikely(!__kernel_text_address(pc) || fn(pc, arg)))
+ break;
+
+ /* Validate frame pointer */
+ low = sp + sizeof(struct stackframe);
+ high = ALIGN(sp, THREAD_SIZE);
+ if (unlikely(fp < low || fp > high || fp & 0x7))
+ break;
+ /* Unwind stack frame */
+ frame = (struct stackframe *)fp - 1;
+ sp = fp;
+ fp = frame->fp;
+ pc = frame->ra - 0x4;
+ }
+}
+
+#else /* !CONFIG_FRAME_POINTER */
+
+static void notrace walk_stackframe(struct task_struct *task,
+ struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
+{
+ unsigned long sp, pc;
+ unsigned long *ksp;
+
+ if (regs) {
+ sp = GET_USP(regs);
+ pc = GET_IP(regs);
+ } else if (task == NULL || task == current) {
+ const register unsigned long current_sp __asm__ ("sp");
+ sp = current_sp;
+ pc = (unsigned long)walk_stackframe;
+ } else {
+ /* task blocked in __switch_to */
+ sp = task->thread.sp;
+ pc = task->thread.ra;
+ }
+
+ if (unlikely(sp & 0x7))
+ return;
+
+ ksp = (unsigned long *)sp;
+ while (!kstack_end(ksp)) {
+ if (__kernel_text_address(pc) && unlikely(fn(pc, arg)))
+ break;
+ pc = (*ksp++) - 0x4;
+ }
+}
+
+#endif /* CONFIG_FRAME_POINTER */
+
+
+static bool print_trace_address(unsigned long pc, void *arg)
+{
+ print_ip_sym(pc);
+ return false;
+}
+
+void show_stack(struct task_struct *task, unsigned long *sp)
+{
+ pr_cont("Call Trace:\n");
+ walk_stackframe(task, NULL, print_trace_address, NULL);
+}
+
+
+static bool save_wchan(unsigned long pc, void *arg)
+{
+ if (!in_sched_functions(pc)) {
+ unsigned long *p = arg;
+ *p = pc;
+ return true;
+ }
+ return false;
+}
+
+unsigned long get_wchan(struct task_struct *task)
+{
+ unsigned long pc = 0;
+
+ if (likely(task && task != current && task->state != TASK_RUNNING))
+ walk_stackframe(task, NULL, save_wchan, &pc);
+ return pc;
+}
+
+
+#ifdef CONFIG_STACKTRACE
+
+static bool __save_trace(unsigned long pc, void *arg, bool nosched)
+{
+ struct stack_trace *trace = arg;
+
+ if (unlikely(nosched && in_sched_functions(pc)))
+ return false;
+ if (unlikely(trace->skip > 0)) {
+ trace->skip--;
+ return false;
+ }
+
+ trace->entries[trace->nr_entries++] = pc;
+ return (trace->nr_entries >= trace->max_entries);
+}
+
+static bool save_trace(unsigned long pc, void *arg)
+{
+ return __save_trace(pc, arg, false);
+}
+
+/*
+ * Save stack-backtrace addresses into a stack_trace buffer.
+ */
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+ walk_stackframe(tsk, NULL, save_trace, trace);
+ if (trace->nr_entries < trace->max_entries)
+ trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+void save_stack_trace(struct stack_trace *trace)
+{
+ save_stack_trace_tsk(NULL, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+#endif /* CONFIG_STACKTRACE */
diff --git a/arch/riscv/lib/memcpy.S b/arch/riscv/lib/memcpy.S
new file mode 100644
index 000000000000..3605b55c68fa
--- /dev/null
+++ b/arch/riscv/lib/memcpy.S
@@ -0,0 +1,100 @@
+/*
+ * Copyright (C) 2013 Regents of the University of California
+ *
+ * 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>
+
+/* void *memcpy(void *, const void *, size_t) */
+ENTRY(memcpy)
+ move t6, a0 /* Preserve return value */
+
+ /* Defer to byte-oriented copy for small sizes */
+ sltiu a3, a2, 128
+ bnez a3, 4f
+ /* Use word-oriented copy only if low-order bits match */
+ andi a3, t6, SZREG-1
+ andi a4, a1, SZREG-1
+ bne a3, a4, 4f
+
+ beqz a3, 2f /* Skip if already aligned */
+ /*
+ * Round to nearest double word-aligned address
+ * greater than or equal to start address
+ */
+ andi a3, a1, ~(SZREG-1)
+ addi a3, a3, SZREG
+ /* Handle initial misalignment */
+ sub a4, a3, a1
+1:
+ lb a5, 0(a1)
+ addi a1, a1, 1
+ sb a5, 0(t6)
+ addi t6, t6, 1
+ bltu a1, a3, 1b
+ sub a2, a2, a4 /* Update count */
+
+2:
+ andi a4, a2, ~((16*SZREG)-1)
+ beqz a4, 4f
+ add a3, a1, a4
+3:
+ REG_L a4, 0(a1)
+ REG_L a5, SZREG(a1)
+ REG_L a6, 2*SZREG(a1)
+ REG_L a7, 3*SZREG(a1)
+ REG_L t0, 4*SZREG(a1)
+ REG_L t1, 5*SZREG(a1)
+ REG_L t2, 6*SZREG(a1)
+ REG_L t3, 7*SZREG(a1)
+ REG_L t4, 8*SZREG(a1)
+ REG_L t5, 9*SZREG(a1)
+ REG_S a4, 0(t6)
+ REG_S a5, SZREG(t6)
+ REG_S a6, 2*SZREG(t6)
+ REG_S a7, 3*SZREG(t6)
+ REG_S t0, 4*SZREG(t6)
+ REG_S t1, 5*SZREG(t6)
+ REG_S t2, 6*SZREG(t6)
+ REG_S t3, 7*SZREG(t6)
+ REG_S t4, 8*SZREG(t6)
+ REG_S t5, 9*SZREG(t6)
+ REG_L a4, 10*SZREG(a1)
+ REG_L a5, 11*SZREG(a1)
+ REG_L a6, 12*SZREG(a1)
+ REG_L a7, 13*SZREG(a1)
+ REG_L t0, 14*SZREG(a1)
+ REG_L t1, 15*SZREG(a1)
+ addi a1, a1, 16*SZREG
+ REG_S a4, 10*SZREG(t6)
+ REG_S a5, 11*SZREG(t6)
+ REG_S a6, 12*SZREG(t6)
+ REG_S a7, 13*SZREG(t6)
+ REG_S t0, 14*SZREG(t6)
+ REG_S t1, 15*SZREG(t6)
+ addi t6, t6, 16*SZREG
+ bltu a1, a3, 3b
+ andi a2, a2, (16*SZREG)-1 /* Update count */
+
+4:
+ /* Handle trailing misalignment */
+ beqz a2, 6f
+ add a3, a1, a2
+5:
+ lb a4, 0(a1)
+ addi a1, a1, 1
+ sb a4, 0(t6)
+ addi t6, t6, 1
+ bltu a1, a3, 5b
+6:
+ ret
+END(memcpy)
diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S
new file mode 100644
index 000000000000..a790107cf4c9
--- /dev/null
+++ b/arch/riscv/lib/memset.S
@@ -0,0 +1,120 @@
+/*
+ * Copyright (C) 2013 Regents of the University of California
+ *
+ * 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>
+
+/* void *memset(void *, int, size_t) */
+ENTRY(memset)
+ move t0, a0 /* Preserve return value */
+
+ /* Defer to byte-oriented fill for small sizes */
+ sltiu a3, a2, 16
+ bnez a3, 4f
+
+ /*
+ * Round to nearest XLEN-aligned address
+ * greater than or equal to start address
+ */
+ addi a3, t0, SZREG-1
+ andi a3, a3, ~(SZREG-1)
+ beq a3, t0, 2f /* Skip if already aligned */
+ /* Handle initial misalignment */
+ sub a4, a3, t0
+1:
+ sb a1, 0(t0)
+ addi t0, t0, 1
+ bltu t0, a3, 1b
+ sub a2, a2, a4 /* Update count */
+
+2: /* Duff's device with 32 XLEN stores per iteration */
+ /* Broadcast value into all bytes */
+ andi a1, a1, 0xff
+ slli a3, a1, 8
+ or a1, a3, a1
+ slli a3, a1, 16
+ or a1, a3, a1
+#ifdef CONFIG_64BIT
+ slli a3, a1, 32
+ or a1, a3, a1
+#endif
+
+ /* Calculate end address */
+ andi a4, a2, ~(SZREG-1)
+ add a3, t0, a4
+
+ andi a4, a4, 31*SZREG /* Calculate remainder */
+ beqz a4, 3f /* Shortcut if no remainder */
+ neg a4, a4
+ addi a4, a4, 32*SZREG /* Calculate initial offset */
+
+ /* Adjust start address with offset */
+ sub t0, t0, a4
+
+ /* Jump into loop body */
+ /* Assumes 32-bit instruction lengths */
+ la a5, 3f
+#ifdef CONFIG_64BIT
+ srli a4, a4, 1
+#endif
+ add a5, a5, a4
+ jr a5
+3:
+ REG_S a1, 0(t0)
+ REG_S a1, SZREG(t0)
+ REG_S a1, 2*SZREG(t0)
+ REG_S a1, 3*SZREG(t0)
+ REG_S a1, 4*SZREG(t0)
+ REG_S a1, 5*SZREG(t0)
+ REG_S a1, 6*SZREG(t0)
+ REG_S a1, 7*SZREG(t0)
+ REG_S a1, 8*SZREG(t0)
+ REG_S a1, 9*SZREG(t0)
+ REG_S a1, 10*SZREG(t0)
+ REG_S a1, 11*SZREG(t0)
+ REG_S a1, 12*SZREG(t0)
+ REG_S a1, 13*SZREG(t0)
+ REG_S a1, 14*SZREG(t0)
+ REG_S a1, 15*SZREG(t0)
+ REG_S a1, 16*SZREG(t0)
+ REG_S a1, 17*SZREG(t0)
+ REG_S a1, 18*SZREG(t0)
+ REG_S a1, 19*SZREG(t0)
+ REG_S a1, 20*SZREG(t0)
+ REG_S a1, 21*SZREG(t0)
+ REG_S a1, 22*SZREG(t0)
+ REG_S a1, 23*SZREG(t0)
+ REG_S a1, 24*SZREG(t0)
+ REG_S a1, 25*SZREG(t0)
+ REG_S a1, 26*SZREG(t0)
+ REG_S a1, 27*SZREG(t0)
+ REG_S a1, 28*SZREG(t0)
+ REG_S a1, 29*SZREG(t0)
+ REG_S a1, 30*SZREG(t0)
+ REG_S a1, 31*SZREG(t0)
+ addi t0, t0, 32*SZREG
+ bltu t0, a3, 3b
+ andi a2, a2, SZREG-1 /* Update count */
+
+4:
+ /* Handle trailing misalignment */
+ beqz a2, 6f
+ add a3, t0, a2
+5:
+ sb a1, 0(t0)
+ addi t0, t0, 1
+ bltu t0, a3, 5b
+6:
+ ret
+END(memset)
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
new file mode 100644
index 000000000000..c36917fcd33d
--- /dev/null
+++ b/arch/riscv/lib/uaccess.S
@@ -0,0 +1,127 @@
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/csr.h>
+
+ .altmacro
+ .macro fixup op reg addr lbl
+ LOCAL _epc
+_epc:
+ \op \reg, \addr
+ .section __ex_table,"a"
+ .balign RISCV_SZPTR
+ RISCV_PTR _epc, \lbl
+ .previous
+ .endm
+
+ENTRY(__copy_user)
+
+#ifdef CONFIG_RV_PUM
+ /* Enable access to user memory */
+ li t6, SR_SUM
+ csrs sstatus, t6
+#endif
+
+ add a3, a1, a2
+ /* Use word-oriented copy only if low-order bits match */
+ andi t0, a0, SZREG-1
+ andi t1, a1, SZREG-1
+ bne t0, t1, 2f
+
+ addi t0, a1, SZREG-1
+ andi t1, a3, ~(SZREG-1)
+ andi t0, t0, ~(SZREG-1)
+ /*
+ * a3: terminal address of source region
+ * t0: lowest XLEN-aligned address in source
+ * t1: highest XLEN-aligned address in source
+ */
+ bgeu t0, t1, 2f
+ bltu a1, t0, 4f
+1:
+ fixup REG_L, t2, (a1), 10f
+ fixup REG_S, t2, (a0), 10f
+ addi a1, a1, SZREG
+ addi a0, a0, SZREG
+ bltu a1, t1, 1b
+2:
+ bltu a1, a3, 5f
+
+3:
+#ifdef CONFIG_RV_PUM
+ /* Disable access to user memory */
+ csrc sstatus, t6
+#endif
+ li a0, 0
+ ret
+4: /* Edge case: unalignment */
+ fixup lbu, t2, (a1), 10f
+ fixup sb, t2, (a0), 10f
+ addi a1, a1, 1
+ addi a0, a0, 1
+ bltu a1, t0, 4b
+ j 1b
+5: /* Edge case: remainder */
+ fixup lbu, t2, (a1), 10f
+ fixup sb, t2, (a0), 10f
+ addi a1, a1, 1
+ addi a0, a0, 1
+ bltu a1, a3, 5b
+ j 3b
+ENDPROC(__copy_user)
+
+
+ENTRY(__clear_user)
+
+#ifdef CONFIG_RV_PUM
+ /* Enable access to user memory */
+ li t6, SR_SUM
+ csrs sstatus, t6
+#endif
+
+ add a3, a0, a1
+ addi t0, a0, SZREG-1
+ andi t1, a3, ~(SZREG-1)
+ andi t0, t0, ~(SZREG-1)
+ /*
+ * a3: terminal address of target region
+ * t0: lowest doubleword-aligned address in target region
+ * t1: highest doubleword-aligned address in target region
+ */
+ bgeu t0, t1, 2f
+ bltu a0, t0, 4f
+1:
+ fixup REG_S, zero, (a0), 10f
+ addi a0, a0, SZREG
+ bltu a0, t1, 1b
+2:
+ bltu a0, a3, 5f
+
+3:
+#ifdef CONFIG_RV_PUM
+ /* Disable access to user memory */
+ csrc sstatus, t6
+#endif
+ li a0, 0
+ ret
+4: /* Edge case: unalignment */
+ fixup sb, zero, (a0), 10f
+ addi a0, a0, 1
+ bltu a0, t0, 4b
+ j 1b
+5: /* Edge case: remainder */
+ fixup sb, zero, (a0), 10f
+ addi a0, a0, 1
+ bltu a0, a3, 5b
+ j 3b
+ENDPROC(__clear_user)
+
+ .section .fixup,"ax"
+ .balign 4
+10:
+#ifdef CONFIG_RV_PUM
+ /* Disable access to user memory */
+ csrs sstatus, t6
+#endif
+ sub a0, a3, a0
+ ret
+ .previous
diff --git a/arch/riscv/lib/udivdi3.S b/arch/riscv/lib/udivdi3.S
new file mode 100644
index 000000000000..cb01ae5b181a
--- /dev/null
+++ b/arch/riscv/lib/udivdi3.S
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2016-2017 Free Software Foundation, Inc.
+ *
+ * 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.
+ */
+
+ .globl __udivdi3
+__udivdi3:
+ mv a2, a1
+ mv a1, a0
+ li a0, -1
+ beqz a2, .L5
+ li a3, 1
+ bgeu a2, a1, .L2
+.L1:
+ blez a2, .L2
+ slli a2, a2, 1
+ slli a3, a3, 1
+ bgtu a1, a2, .L1
+.L2:
+ li a0, 0
+.L3:
+ bltu a1, a2, .L4
+ sub a1, a1, a2
+ or a0, a0, a3
+.L4:
+ srli a3, a3, 1
+ srli a2, a2, 1
+ bnez a3, .L3
+.L5:
+ ret
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 3/9] RISC-V: Generic library routines and assembly
@ 2017-07-04 19:50 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains code that is more specific to the RISC-V ISA than it
is to Linux. It contains string and math operations, C wrappers for
various assembly instructions, stack walking code, and uaccess.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/asm.h | 76 ++++++
arch/riscv/include/asm/bitops.h | 4 -
arch/riscv/include/asm/csr.h | 125 +++++++++
arch/riscv/include/asm/linkage.h | 20 ++
arch/riscv/include/asm/string.h | 26 ++
arch/riscv/include/asm/uaccess.h | 441 ++++++++++++++++++++++++++++++++
arch/riscv/include/asm/word-at-a-time.h | 55 ++++
arch/riscv/kernel/stacktrace.c | 177 +++++++++++++
arch/riscv/lib/memcpy.S | 100 ++++++++
arch/riscv/lib/memset.S | 120 +++++++++
arch/riscv/lib/uaccess.S | 127 +++++++++
arch/riscv/lib/udivdi3.S | 38 +++
12 files changed, 1305 insertions(+), 4 deletions(-)
create mode 100644 arch/riscv/include/asm/asm.h
create mode 100644 arch/riscv/include/asm/csr.h
create mode 100644 arch/riscv/include/asm/linkage.h
create mode 100644 arch/riscv/include/asm/string.h
create mode 100644 arch/riscv/include/asm/uaccess.h
create mode 100644 arch/riscv/include/asm/word-at-a-time.h
create mode 100644 arch/riscv/kernel/stacktrace.c
create mode 100644 arch/riscv/lib/memcpy.S
create mode 100644 arch/riscv/lib/memset.S
create mode 100644 arch/riscv/lib/uaccess.S
create mode 100644 arch/riscv/lib/udivdi3.S
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
new file mode 100644
index 000000000000..6cbbb6a68d76
--- /dev/null
+++ b/arch/riscv/include/asm/asm.h
@@ -0,0 +1,76 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_ASM_H
+#define _ASM_RISCV_ASM_H
+
+#ifdef __ASSEMBLY__
+#define __ASM_STR(x) x
+#else
+#define __ASM_STR(x) #x
+#endif
+
+#if __riscv_xlen == 64
+#define __REG_SEL(a, b) __ASM_STR(a)
+#elif __riscv_xlen == 32
+#define __REG_SEL(a, b) __ASM_STR(b)
+#else
+#error "Unexpected __riscv_xlen"
+#endif
+
+#define REG_L __REG_SEL(ld, lw)
+#define REG_S __REG_SEL(sd, sw)
+#define SZREG __REG_SEL(8, 4)
+#define LGREG __REG_SEL(3, 2)
+
+#if __SIZEOF_POINTER__ == 8
+#ifdef __ASSEMBLY__
+#define RISCV_PTR .dword
+#define RISCV_SZPTR 8
+#define RISCV_LGPTR 3
+#else
+#define RISCV_PTR ".dword"
+#define RISCV_SZPTR "8"
+#define RISCV_LGPTR "3"
+#endif
+#elif __SIZEOF_POINTER__ == 4
+#ifdef __ASSEMBLY__
+#define RISCV_PTR .word
+#define RISCV_SZPTR 4
+#define RISCV_LGPTR 2
+#else
+#define RISCV_PTR ".word"
+#define RISCV_SZPTR "4"
+#define RISCV_LGPTR "2"
+#endif
+#else
+#error "Unexpected __SIZEOF_POINTER__"
+#endif
+
+#if (__SIZEOF_INT__ == 4)
+#define INT __ASM_STR(.word)
+#define SZINT __ASM_STR(4)
+#define LGINT __ASM_STR(2)
+#else
+#error "Unexpected __SIZEOF_INT__"
+#endif
+
+#if (__SIZEOF_SHORT__ == 2)
+#define SHORT __ASM_STR(.half)
+#define SZSHORT __ASM_STR(2)
+#define LGSHORT __ASM_STR(1)
+#else
+#error "Unexpected __SIZEOF_SHORT__"
+#endif
+
+#endif /* _ASM_RISCV_ASM_H */
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 27e47858c6b1..d4f1c9c66e4d 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -18,8 +18,6 @@
#error "Only <linux/bitops.h> can be included directly"
#endif /* _LINUX_BITOPS_H */
-#ifdef __KERNEL__
-
#include <linux/compiler.h>
#include <linux/irqflags.h>
#include <asm/barrier.h>
@@ -223,6 +221,4 @@ static inline void __clear_bit_unlock(
#endif /* CONFIG_ISA_A */
-#endif /* __KERNEL__ */
-
#endif /* _ASM_RISCV_BITOPS_H */
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
new file mode 100644
index 000000000000..387d0dbf0073
--- /dev/null
+++ b/arch/riscv/include/asm/csr.h
@@ -0,0 +1,125 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_CSR_H
+#define _ASM_RISCV_CSR_H
+
+#include <linux/const.h>
+
+/* Status register flags */
+#define SR_IE _AC(0x00000002, UL) /* Interrupt Enable */
+#define SR_PIE _AC(0x00000020, UL) /* Previous IE */
+#define SR_PS _AC(0x00000100, UL) /* Previously Supervisor */
+#define SR_SUM _AC(0x00040000, UL) /* Supervisor may access User Memory */
+
+#define SR_FS _AC(0x00006000, UL) /* Floating-point Status */
+#define SR_FS_OFF _AC(0x00000000, UL)
+#define SR_FS_INITIAL _AC(0x00002000, UL)
+#define SR_FS_CLEAN _AC(0x00004000, UL)
+#define SR_FS_DIRTY _AC(0x00006000, UL)
+
+#define SR_XS _AC(0x00018000, UL) /* Extension Status */
+#define SR_XS_OFF _AC(0x00000000, UL)
+#define SR_XS_INITIAL _AC(0x00008000, UL)
+#define SR_XS_CLEAN _AC(0x00010000, UL)
+#define SR_XS_DIRTY _AC(0x00018000, UL)
+
+#ifndef CONFIG_64BIT
+#define SR_SD _AC(0x80000000, UL) /* FS/XS dirty */
+#else
+#define SR_SD _AC(0x8000000000000000, UL) /* FS/XS dirty */
+#endif
+
+/* SPTBR flags */
+#if __riscv_xlen == 32
+#define SPTBR_PPN _AC(0x003FFFFF, UL)
+#define SPTBR_MODE_32 _AC(0x80000000, UL)
+#define SPTBR_MODE SPTBR_MODE_32
+#else
+#define SPTBR_PPN _AC(0x00000FFFFFFFFFFF, UL)
+#define SPTBR_MODE_39 _AC(0x8000000000000000, UL)
+#define SPTBR_MODE SPTBR_MODE_39
+#endif
+
+/* Interrupt Enable and Interrupt Pending flags */
+#define SIE_SSIE _AC(0x00000002, UL) /* Software Interrupt Enable */
+#define SIE_STIE _AC(0x00000020, UL) /* Timer Interrupt Enable */
+
+#define EXC_INST_MISALIGNED 0
+#define EXC_INST_ACCESS 1
+#define EXC_BREAKPOINT 3
+#define EXC_LOAD_ACCESS 5
+#define EXC_STORE_ACCESS 7
+#define EXC_SYSCALL 8
+#define EXC_INST_PAGE_FAULT 12
+#define EXC_LOAD_PAGE_FAULT 13
+#define EXC_STORE_PAGE_FAULT 15
+
+#ifndef __ASSEMBLY__
+
+#define csr_swap(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrrw %0, " #csr ", %1" \
+ : "=r" (__v) : "rK" (__v)); \
+ __v; \
+})
+
+#define csr_read(csr) \
+({ \
+ register unsigned long __v; \
+ __asm__ __volatile__ ("csrr %0, " #csr \
+ : "=r" (__v)); \
+ __v; \
+})
+
+#define csr_write(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrw " #csr ", %0" \
+ : : "rK" (__v)); \
+})
+
+#define csr_read_set(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrrs %0, " #csr ", %1" \
+ : "=r" (__v) : "rK" (__v)); \
+ __v; \
+})
+
+#define csr_set(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrs " #csr ", %0" \
+ : : "rK" (__v)); \
+})
+
+#define csr_read_clear(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrrc %0, " #csr ", %1" \
+ : "=r" (__v) : "rK" (__v)); \
+ __v; \
+})
+
+#define csr_clear(csr, val) \
+({ \
+ unsigned long __v = (unsigned long)(val); \
+ __asm__ __volatile__ ("csrc " #csr ", %0" \
+ : : "rK" (__v)); \
+})
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_CSR_H */
diff --git a/arch/riscv/include/asm/linkage.h b/arch/riscv/include/asm/linkage.h
new file mode 100644
index 000000000000..b7b304ca89c4
--- /dev/null
+++ b/arch/riscv/include/asm/linkage.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_LINKAGE_H
+#define _ASM_RISCV_LINKAGE_H
+
+#define __ALIGN .balign 4
+#define __ALIGN_STR ".balign 4"
+
+#endif /* _ASM_RISCV_LINKAGE_H */
diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h
new file mode 100644
index 000000000000..9210fcf4ff52
--- /dev/null
+++ b/arch/riscv/include/asm/string.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2013 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_STRING_H
+#define _ASM_RISCV_STRING_H
+
+#include <linux/types.h>
+#include <linux/linkage.h>
+
+#define __HAVE_ARCH_MEMSET
+extern asmlinkage void *memset(void *, int, size_t);
+
+#define __HAVE_ARCH_MEMCPY
+extern asmlinkage void *memcpy(void *, const void *, size_t);
+
+#endif /* _ASM_RISCV_STRING_H */
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
new file mode 100644
index 000000000000..647a060090f1
--- /dev/null
+++ b/arch/riscv/include/asm/uaccess.h
@@ -0,0 +1,441 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ *
+ * This file was copied from include/asm-generic/uaccess.h
+ */
+
+#ifndef _ASM_RISCV_UACCESS_H
+#define _ASM_RISCV_UACCESS_H
+
+/*
+ * User space memory access functions
+ */
+#include <linux/errno.h>
+#include <linux/compiler.h>
+#include <linux/thread_info.h>
+#include <asm/byteorder.h>
+#include <asm/asm.h>
+
+#ifdef CONFIG_RV_PUM
+#define __enable_user_access() \
+ __asm__ __volatile__ ("csrs sstatus, %0" : : "r" (SR_SUM) : "memory")
+#define __disable_user_access() \
+ __asm__ __volatile__ ("csrc sstatus, %0" : : "r" (SR_SUM) : "memory")
+#else
+#define __enable_user_access()
+#define __disable_user_access()
+#endif
+
+/*
+ * The fs value determines whether argument validity checking should be
+ * performed or not. If get_fs() == USER_DS, checking is performed, with
+ * get_fs() == KERNEL_DS, checking is bypassed.
+ *
+ * For historical reasons, these macros are grossly misnamed.
+ */
+
+#define KERNEL_DS (~0UL)
+#define USER_DS (TASK_SIZE)
+
+#define get_ds() (KERNEL_DS)
+#define get_fs() (current_thread_info()->addr_limit)
+
+static inline void set_fs(mm_segment_t fs)
+{
+ current_thread_info()->addr_limit = fs;
+}
+
+#define segment_eq(a, b) ((a) == (b))
+
+#define user_addr_max() (get_fs())
+
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+/**
+ * access_ok: - Checks if a user space pointer is valid
+ * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE. Note that
+ * %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe
+ * to write to a block, it is always safe to read from it.
+ * @addr: User space pointer to start of block to check
+ * @size: Size of block to check
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * Checks if a pointer to a block of memory in user space is valid.
+ *
+ * Returns true (nonzero) if the memory block may be valid, false (zero)
+ * if it is definitely invalid.
+ *
+ * Note that, depending on architecture, this function probably just
+ * checks that the pointer is in the user space range - after calling
+ * this function, memory access functions may still return -EFAULT.
+ */
+#define access_ok(type, addr, size) ({ \
+ __chk_user_ptr(addr); \
+ likely(__access_ok((unsigned long __force)(addr), (size))); \
+})
+
+/*
+ * Ensure that the range [addr, addr+size) is within the process's
+ * address space
+ */
+static inline int __access_ok(unsigned long addr, unsigned long size)
+{
+ const mm_segment_t fs = get_fs();
+
+ return (size <= fs) && (addr <= (fs - size));
+}
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue. No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path. This means when everything is well,
+ * we don't even have to jump over them. Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry {
+ unsigned long insn, fixup;
+};
+
+extern int fixup_exception(struct pt_regs *state);
+
+#if defined(__LITTLE_ENDIAN)
+#define __MSW 1
+#define __LSW 0
+#elif defined(__BIG_ENDIAN)
+#define __MSW 0
+#define __LSW 1
+#else
+#error "Unknown endianness"
+#endif
+
+/*
+ * The "__xxx" versions of the user access functions do not verify the address
+ * space - it must have been done previously with a separate "access_ok()"
+ * call.
+ */
+
+#ifdef CONFIG_MMU
+#define __get_user_asm(insn, x, ptr, err) \
+do { \
+ uintptr_t __tmp; \
+ __typeof__(x) __x; \
+ __enable_user_access(); \
+ __asm__ __volatile__ ( \
+ "1:\n" \
+ " " insn " %1, %3\n" \
+ "2:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .balign 4\n" \
+ "3:\n" \
+ " li %0, %4\n" \
+ " li %1, 0\n" \
+ " jump 2b, %2\n" \
+ " .previous\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .balign " RISCV_SZPTR "\n" \
+ " " RISCV_PTR " 1b, 3b\n" \
+ " .previous" \
+ : "+r" (err), "=&r" (__x), "=r" (__tmp) \
+ : "m" (*(ptr)), "i" (-EFAULT)); \
+ __disable_user_access(); \
+ (x) = __x; \
+} while (0)
+#endif /* CONFIG_MMU */
+
+#ifdef CONFIG_64BIT
+#define __get_user_8(x, ptr, err) \
+ __get_user_asm("ld", x, ptr, err)
+#else /* !CONFIG_64BIT */
+#ifdef CONFIG_MMU
+#define __get_user_8(x, ptr, err) \
+do { \
+ u32 __user *__ptr = (u32 __user *)(ptr); \
+ u32 __lo, __hi; \
+ uintptr_t __tmp; \
+ __enable_user_access(); \
+ __asm__ __volatile__ ( \
+ "1:\n" \
+ " lw %1, %4\n" \
+ "2:\n" \
+ " lw %2, %5\n" \
+ "3:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .balign 4\n" \
+ "4:\n" \
+ " li %0, %6\n" \
+ " li %1, 0\n" \
+ " li %2, 0\n" \
+ " jump 3b, %3\n" \
+ " .previous\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .balign " RISCV_SZPTR "\n" \
+ " " RISCV_PTR " 1b, 4b\n" \
+ " " RISCV_PTR " 2b, 4b\n" \
+ " .previous" \
+ : "+r" (err), "=&r" (__lo), "=r" (__hi), \
+ "=r" (__tmp) \
+ : "m" (__ptr[__LSW]), "m" (__ptr[__MSW]), \
+ "i" (-EFAULT)); \
+ __disable_user_access(); \
+ (x) = (__typeof__(x))((__typeof__((x)-(x)))( \
+ (((u64)__hi << 32) | __lo))); \
+} while (0)
+#endif /* CONFIG_MMU */
+#endif /* CONFIG_64BIT */
+
+
+/**
+ * __get_user: - Get a simple variable from user space, with less checking.
+ * @x: Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space. It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+#define __get_user(x, ptr) \
+({ \
+ register long __gu_err = 0; \
+ const __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
+ __chk_user_ptr(__gu_ptr); \
+ switch (sizeof(*__gu_ptr)) { \
+ case 1: \
+ __get_user_asm("lb", (x), __gu_ptr, __gu_err); \
+ break; \
+ case 2: \
+ __get_user_asm("lh", (x), __gu_ptr, __gu_err); \
+ break; \
+ case 4: \
+ __get_user_asm("lw", (x), __gu_ptr, __gu_err); \
+ break; \
+ case 8: \
+ __get_user_8((x), __gu_ptr, __gu_err); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ __gu_err; \
+})
+
+/**
+ * get_user: - Get a simple variable from user space.
+ * @x: Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space. It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+#define get_user(x, ptr) \
+({ \
+ const __typeof__(*(ptr)) __user *__p = (ptr); \
+ might_fault(); \
+ access_ok(VERIFY_READ, __p, sizeof(*__p)) ? \
+ __get_user((x), __p) : \
+ ((x) = 0, -EFAULT); \
+})
+
+
+#ifdef CONFIG_MMU
+#define __put_user_asm(insn, x, ptr, err) \
+do { \
+ uintptr_t __tmp; \
+ __typeof__(*(ptr)) __x = x; \
+ __enable_user_access(); \
+ __asm__ __volatile__ ( \
+ "1:\n" \
+ " " insn " %z3, %2\n" \
+ "2:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .balign 4\n" \
+ "3:\n" \
+ " li %0, %4\n" \
+ " jump 2b, %1\n" \
+ " .previous\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .balign " RISCV_SZPTR "\n" \
+ " " RISCV_PTR " 1b, 3b\n" \
+ " .previous" \
+ : "+r" (err), "=r" (__tmp), "=m" (*(ptr)) \
+ : "rJ" (__x), "i" (-EFAULT)); \
+ __disable_user_access(); \
+} while (0)
+#endif /* CONFIG_MMU */
+
+
+#ifdef CONFIG_64BIT
+#define __put_user_8(x, ptr, err) \
+ __put_user_asm("sd", x, ptr, err)
+#else /* !CONFIG_64BIT */
+#ifdef CONFIG_MMU
+#define __put_user_8(x, ptr, err) \
+do { \
+ u32 __user *__ptr = (u32 __user *)(ptr); \
+ u64 __x = (__typeof__((x)-(x)))(x); \
+ uintptr_t __tmp; \
+ __enable_user_access(); \
+ __asm__ __volatile__ ( \
+ "1:\n" \
+ " sw %z4, %2\n" \
+ "2:\n" \
+ " sw %z5, %3\n" \
+ "3:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .balign 4\n" \
+ "4:\n" \
+ " li %0, %6\n" \
+ " jump 2b, %1\n" \
+ " .previous\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .balign " RISCV_SZPTR "\n" \
+ " " RISCV_PTR " 1b, 4b\n" \
+ " " RISCV_PTR " 2b, 4b\n" \
+ " .previous" \
+ : "+r" (err), "=r" (__tmp), \
+ "=m" (__ptr[__LSW]), \
+ "=m" (__ptr[__MSW]) \
+ : "rJ" (__x), "rJ" (__x >> 32), "i" (-EFAULT)); \
+ __disable_user_access(); \
+} while (0)
+#endif /* CONFIG_MMU */
+#endif /* CONFIG_64BIT */
+
+
+/**
+ * __put_user: - Write a simple value into user space, with less checking.
+ * @x: Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space. It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+#define __put_user(x, ptr) \
+({ \
+ register long __pu_err = 0; \
+ __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
+ __chk_user_ptr(__gu_ptr); \
+ switch (sizeof(*__gu_ptr)) { \
+ case 1: \
+ __put_user_asm("sb", (x), __gu_ptr, __pu_err); \
+ break; \
+ case 2: \
+ __put_user_asm("sh", (x), __gu_ptr, __pu_err); \
+ break; \
+ case 4: \
+ __put_user_asm("sw", (x), __gu_ptr, __pu_err); \
+ break; \
+ case 8: \
+ __put_user_8((x), __gu_ptr, __pu_err); \
+ break; \
+ default: \
+ BUILD_BUG(); \
+ } \
+ __pu_err; \
+})
+
+/**
+ * put_user: - Write a simple value into user space.
+ * @x: Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space. It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+#define put_user(x, ptr) \
+({ \
+ __typeof__(*(ptr)) __user *__p = (ptr); \
+ might_fault(); \
+ access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ? \
+ __put_user((x), __p) : \
+ -EFAULT; \
+})
+
+
+extern unsigned long __must_check __copy_user(void __user *to,
+ const void __user *from, unsigned long n);
+
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ return __copy_user(to, from, n);
+}
+
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ return __copy_user(to, from, n);
+}
+
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+
+extern long __must_check strlen_user(const char __user *str);
+extern long __must_check strnlen_user(const char __user *str, long n);
+
+extern
+unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
+
+static inline
+unsigned long __must_check clear_user(void __user *to, unsigned long n)
+{
+ might_fault();
+ return access_ok(VERIFY_WRITE, to, n) ?
+ __clear_user(to, n) : n;
+}
+
+#endif /* _ASM_RISCV_UACCESS_H */
diff --git a/arch/riscv/include/asm/word-at-a-time.h b/arch/riscv/include/asm/word-at-a-time.h
new file mode 100644
index 000000000000..aa6238791d3e
--- /dev/null
+++ b/arch/riscv/include/asm/word-at-a-time.h
@@ -0,0 +1,55 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ * Derived from arch/x86/include/asm/word-at-a-time.h
+ */
+
+#ifndef _ASM_RISCV_WORD_AT_A_TIME_H
+#define _ASM_RISCV_WORD_AT_A_TIME_H
+
+
+#include <linux/kernel.h>
+
+struct word_at_a_time {
+ const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+static inline unsigned long has_zero(unsigned long val,
+ unsigned long *bits, const struct word_at_a_time *c)
+{
+ unsigned long mask = ((val - c->one_bits) & ~val) & c->high_bits;
+ *bits = mask;
+ return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long val,
+ unsigned long bits, const struct word_at_a_time *c)
+{
+ return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+ bits = (bits - 1) & ~bits;
+ return bits >> 7;
+}
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+ return fls64(mask) >> 3;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+#endif /* _ASM_RISCV_WORD_AT_A_TIME_H */
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
new file mode 100644
index 000000000000..559aae781154
--- /dev/null
+++ b/arch/riscv/kernel/stacktrace.c
@@ -0,0 +1,177 @@
+/*
+ * Copyright (C) 2008 ARM Limited
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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/export.h>
+#include <linux/kallsyms.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
+#include <linux/stacktrace.h>
+
+#ifdef CONFIG_FRAME_POINTER
+
+struct stackframe {
+ unsigned long fp;
+ unsigned long ra;
+};
+
+static void notrace walk_stackframe(struct task_struct *task,
+ struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
+{
+ unsigned long fp, sp, pc;
+
+ if (regs) {
+ fp = GET_FP(regs);
+ sp = GET_USP(regs);
+ pc = GET_IP(regs);
+ } else if (task == NULL || task == current) {
+ const register unsigned long current_sp __asm__ ("sp");
+ fp = (unsigned long)__builtin_frame_address(0);
+ sp = current_sp;
+ pc = (unsigned long)walk_stackframe;
+ } else {
+ /* task blocked in __switch_to */
+ fp = task->thread.s[0];
+ sp = task->thread.sp;
+ pc = task->thread.ra;
+ }
+
+ for (;;) {
+ unsigned long low, high;
+ struct stackframe *frame;
+
+ if (unlikely(!__kernel_text_address(pc) || fn(pc, arg)))
+ break;
+
+ /* Validate frame pointer */
+ low = sp + sizeof(struct stackframe);
+ high = ALIGN(sp, THREAD_SIZE);
+ if (unlikely(fp < low || fp > high || fp & 0x7))
+ break;
+ /* Unwind stack frame */
+ frame = (struct stackframe *)fp - 1;
+ sp = fp;
+ fp = frame->fp;
+ pc = frame->ra - 0x4;
+ }
+}
+
+#else /* !CONFIG_FRAME_POINTER */
+
+static void notrace walk_stackframe(struct task_struct *task,
+ struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
+{
+ unsigned long sp, pc;
+ unsigned long *ksp;
+
+ if (regs) {
+ sp = GET_USP(regs);
+ pc = GET_IP(regs);
+ } else if (task == NULL || task == current) {
+ const register unsigned long current_sp __asm__ ("sp");
+ sp = current_sp;
+ pc = (unsigned long)walk_stackframe;
+ } else {
+ /* task blocked in __switch_to */
+ sp = task->thread.sp;
+ pc = task->thread.ra;
+ }
+
+ if (unlikely(sp & 0x7))
+ return;
+
+ ksp = (unsigned long *)sp;
+ while (!kstack_end(ksp)) {
+ if (__kernel_text_address(pc) && unlikely(fn(pc, arg)))
+ break;
+ pc = (*ksp++) - 0x4;
+ }
+}
+
+#endif /* CONFIG_FRAME_POINTER */
+
+
+static bool print_trace_address(unsigned long pc, void *arg)
+{
+ print_ip_sym(pc);
+ return false;
+}
+
+void show_stack(struct task_struct *task, unsigned long *sp)
+{
+ pr_cont("Call Trace:\n");
+ walk_stackframe(task, NULL, print_trace_address, NULL);
+}
+
+
+static bool save_wchan(unsigned long pc, void *arg)
+{
+ if (!in_sched_functions(pc)) {
+ unsigned long *p = arg;
+ *p = pc;
+ return true;
+ }
+ return false;
+}
+
+unsigned long get_wchan(struct task_struct *task)
+{
+ unsigned long pc = 0;
+
+ if (likely(task && task != current && task->state != TASK_RUNNING))
+ walk_stackframe(task, NULL, save_wchan, &pc);
+ return pc;
+}
+
+
+#ifdef CONFIG_STACKTRACE
+
+static bool __save_trace(unsigned long pc, void *arg, bool nosched)
+{
+ struct stack_trace *trace = arg;
+
+ if (unlikely(nosched && in_sched_functions(pc)))
+ return false;
+ if (unlikely(trace->skip > 0)) {
+ trace->skip--;
+ return false;
+ }
+
+ trace->entries[trace->nr_entries++] = pc;
+ return (trace->nr_entries >= trace->max_entries);
+}
+
+static bool save_trace(unsigned long pc, void *arg)
+{
+ return __save_trace(pc, arg, false);
+}
+
+/*
+ * Save stack-backtrace addresses into a stack_trace buffer.
+ */
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+ walk_stackframe(tsk, NULL, save_trace, trace);
+ if (trace->nr_entries < trace->max_entries)
+ trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+void save_stack_trace(struct stack_trace *trace)
+{
+ save_stack_trace_tsk(NULL, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+#endif /* CONFIG_STACKTRACE */
diff --git a/arch/riscv/lib/memcpy.S b/arch/riscv/lib/memcpy.S
new file mode 100644
index 000000000000..3605b55c68fa
--- /dev/null
+++ b/arch/riscv/lib/memcpy.S
@@ -0,0 +1,100 @@
+/*
+ * Copyright (C) 2013 Regents of the University of California
+ *
+ * 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>
+
+/* void *memcpy(void *, const void *, size_t) */
+ENTRY(memcpy)
+ move t6, a0 /* Preserve return value */
+
+ /* Defer to byte-oriented copy for small sizes */
+ sltiu a3, a2, 128
+ bnez a3, 4f
+ /* Use word-oriented copy only if low-order bits match */
+ andi a3, t6, SZREG-1
+ andi a4, a1, SZREG-1
+ bne a3, a4, 4f
+
+ beqz a3, 2f /* Skip if already aligned */
+ /*
+ * Round to nearest double word-aligned address
+ * greater than or equal to start address
+ */
+ andi a3, a1, ~(SZREG-1)
+ addi a3, a3, SZREG
+ /* Handle initial misalignment */
+ sub a4, a3, a1
+1:
+ lb a5, 0(a1)
+ addi a1, a1, 1
+ sb a5, 0(t6)
+ addi t6, t6, 1
+ bltu a1, a3, 1b
+ sub a2, a2, a4 /* Update count */
+
+2:
+ andi a4, a2, ~((16*SZREG)-1)
+ beqz a4, 4f
+ add a3, a1, a4
+3:
+ REG_L a4, 0(a1)
+ REG_L a5, SZREG(a1)
+ REG_L a6, 2*SZREG(a1)
+ REG_L a7, 3*SZREG(a1)
+ REG_L t0, 4*SZREG(a1)
+ REG_L t1, 5*SZREG(a1)
+ REG_L t2, 6*SZREG(a1)
+ REG_L t3, 7*SZREG(a1)
+ REG_L t4, 8*SZREG(a1)
+ REG_L t5, 9*SZREG(a1)
+ REG_S a4, 0(t6)
+ REG_S a5, SZREG(t6)
+ REG_S a6, 2*SZREG(t6)
+ REG_S a7, 3*SZREG(t6)
+ REG_S t0, 4*SZREG(t6)
+ REG_S t1, 5*SZREG(t6)
+ REG_S t2, 6*SZREG(t6)
+ REG_S t3, 7*SZREG(t6)
+ REG_S t4, 8*SZREG(t6)
+ REG_S t5, 9*SZREG(t6)
+ REG_L a4, 10*SZREG(a1)
+ REG_L a5, 11*SZREG(a1)
+ REG_L a6, 12*SZREG(a1)
+ REG_L a7, 13*SZREG(a1)
+ REG_L t0, 14*SZREG(a1)
+ REG_L t1, 15*SZREG(a1)
+ addi a1, a1, 16*SZREG
+ REG_S a4, 10*SZREG(t6)
+ REG_S a5, 11*SZREG(t6)
+ REG_S a6, 12*SZREG(t6)
+ REG_S a7, 13*SZREG(t6)
+ REG_S t0, 14*SZREG(t6)
+ REG_S t1, 15*SZREG(t6)
+ addi t6, t6, 16*SZREG
+ bltu a1, a3, 3b
+ andi a2, a2, (16*SZREG)-1 /* Update count */
+
+4:
+ /* Handle trailing misalignment */
+ beqz a2, 6f
+ add a3, a1, a2
+5:
+ lb a4, 0(a1)
+ addi a1, a1, 1
+ sb a4, 0(t6)
+ addi t6, t6, 1
+ bltu a1, a3, 5b
+6:
+ ret
+END(memcpy)
diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S
new file mode 100644
index 000000000000..a790107cf4c9
--- /dev/null
+++ b/arch/riscv/lib/memset.S
@@ -0,0 +1,120 @@
+/*
+ * Copyright (C) 2013 Regents of the University of California
+ *
+ * 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>
+
+/* void *memset(void *, int, size_t) */
+ENTRY(memset)
+ move t0, a0 /* Preserve return value */
+
+ /* Defer to byte-oriented fill for small sizes */
+ sltiu a3, a2, 16
+ bnez a3, 4f
+
+ /*
+ * Round to nearest XLEN-aligned address
+ * greater than or equal to start address
+ */
+ addi a3, t0, SZREG-1
+ andi a3, a3, ~(SZREG-1)
+ beq a3, t0, 2f /* Skip if already aligned */
+ /* Handle initial misalignment */
+ sub a4, a3, t0
+1:
+ sb a1, 0(t0)
+ addi t0, t0, 1
+ bltu t0, a3, 1b
+ sub a2, a2, a4 /* Update count */
+
+2: /* Duff's device with 32 XLEN stores per iteration */
+ /* Broadcast value into all bytes */
+ andi a1, a1, 0xff
+ slli a3, a1, 8
+ or a1, a3, a1
+ slli a3, a1, 16
+ or a1, a3, a1
+#ifdef CONFIG_64BIT
+ slli a3, a1, 32
+ or a1, a3, a1
+#endif
+
+ /* Calculate end address */
+ andi a4, a2, ~(SZREG-1)
+ add a3, t0, a4
+
+ andi a4, a4, 31*SZREG /* Calculate remainder */
+ beqz a4, 3f /* Shortcut if no remainder */
+ neg a4, a4
+ addi a4, a4, 32*SZREG /* Calculate initial offset */
+
+ /* Adjust start address with offset */
+ sub t0, t0, a4
+
+ /* Jump into loop body */
+ /* Assumes 32-bit instruction lengths */
+ la a5, 3f
+#ifdef CONFIG_64BIT
+ srli a4, a4, 1
+#endif
+ add a5, a5, a4
+ jr a5
+3:
+ REG_S a1, 0(t0)
+ REG_S a1, SZREG(t0)
+ REG_S a1, 2*SZREG(t0)
+ REG_S a1, 3*SZREG(t0)
+ REG_S a1, 4*SZREG(t0)
+ REG_S a1, 5*SZREG(t0)
+ REG_S a1, 6*SZREG(t0)
+ REG_S a1, 7*SZREG(t0)
+ REG_S a1, 8*SZREG(t0)
+ REG_S a1, 9*SZREG(t0)
+ REG_S a1, 10*SZREG(t0)
+ REG_S a1, 11*SZREG(t0)
+ REG_S a1, 12*SZREG(t0)
+ REG_S a1, 13*SZREG(t0)
+ REG_S a1, 14*SZREG(t0)
+ REG_S a1, 15*SZREG(t0)
+ REG_S a1, 16*SZREG(t0)
+ REG_S a1, 17*SZREG(t0)
+ REG_S a1, 18*SZREG(t0)
+ REG_S a1, 19*SZREG(t0)
+ REG_S a1, 20*SZREG(t0)
+ REG_S a1, 21*SZREG(t0)
+ REG_S a1, 22*SZREG(t0)
+ REG_S a1, 23*SZREG(t0)
+ REG_S a1, 24*SZREG(t0)
+ REG_S a1, 25*SZREG(t0)
+ REG_S a1, 26*SZREG(t0)
+ REG_S a1, 27*SZREG(t0)
+ REG_S a1, 28*SZREG(t0)
+ REG_S a1, 29*SZREG(t0)
+ REG_S a1, 30*SZREG(t0)
+ REG_S a1, 31*SZREG(t0)
+ addi t0, t0, 32*SZREG
+ bltu t0, a3, 3b
+ andi a2, a2, SZREG-1 /* Update count */
+
+4:
+ /* Handle trailing misalignment */
+ beqz a2, 6f
+ add a3, t0, a2
+5:
+ sb a1, 0(t0)
+ addi t0, t0, 1
+ bltu t0, a3, 5b
+6:
+ ret
+END(memset)
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
new file mode 100644
index 000000000000..c36917fcd33d
--- /dev/null
+++ b/arch/riscv/lib/uaccess.S
@@ -0,0 +1,127 @@
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/csr.h>
+
+ .altmacro
+ .macro fixup op reg addr lbl
+ LOCAL _epc
+_epc:
+ \op \reg, \addr
+ .section __ex_table,"a"
+ .balign RISCV_SZPTR
+ RISCV_PTR _epc, \lbl
+ .previous
+ .endm
+
+ENTRY(__copy_user)
+
+#ifdef CONFIG_RV_PUM
+ /* Enable access to user memory */
+ li t6, SR_SUM
+ csrs sstatus, t6
+#endif
+
+ add a3, a1, a2
+ /* Use word-oriented copy only if low-order bits match */
+ andi t0, a0, SZREG-1
+ andi t1, a1, SZREG-1
+ bne t0, t1, 2f
+
+ addi t0, a1, SZREG-1
+ andi t1, a3, ~(SZREG-1)
+ andi t0, t0, ~(SZREG-1)
+ /*
+ * a3: terminal address of source region
+ * t0: lowest XLEN-aligned address in source
+ * t1: highest XLEN-aligned address in source
+ */
+ bgeu t0, t1, 2f
+ bltu a1, t0, 4f
+1:
+ fixup REG_L, t2, (a1), 10f
+ fixup REG_S, t2, (a0), 10f
+ addi a1, a1, SZREG
+ addi a0, a0, SZREG
+ bltu a1, t1, 1b
+2:
+ bltu a1, a3, 5f
+
+3:
+#ifdef CONFIG_RV_PUM
+ /* Disable access to user memory */
+ csrc sstatus, t6
+#endif
+ li a0, 0
+ ret
+4: /* Edge case: unalignment */
+ fixup lbu, t2, (a1), 10f
+ fixup sb, t2, (a0), 10f
+ addi a1, a1, 1
+ addi a0, a0, 1
+ bltu a1, t0, 4b
+ j 1b
+5: /* Edge case: remainder */
+ fixup lbu, t2, (a1), 10f
+ fixup sb, t2, (a0), 10f
+ addi a1, a1, 1
+ addi a0, a0, 1
+ bltu a1, a3, 5b
+ j 3b
+ENDPROC(__copy_user)
+
+
+ENTRY(__clear_user)
+
+#ifdef CONFIG_RV_PUM
+ /* Enable access to user memory */
+ li t6, SR_SUM
+ csrs sstatus, t6
+#endif
+
+ add a3, a0, a1
+ addi t0, a0, SZREG-1
+ andi t1, a3, ~(SZREG-1)
+ andi t0, t0, ~(SZREG-1)
+ /*
+ * a3: terminal address of target region
+ * t0: lowest doubleword-aligned address in target region
+ * t1: highest doubleword-aligned address in target region
+ */
+ bgeu t0, t1, 2f
+ bltu a0, t0, 4f
+1:
+ fixup REG_S, zero, (a0), 10f
+ addi a0, a0, SZREG
+ bltu a0, t1, 1b
+2:
+ bltu a0, a3, 5f
+
+3:
+#ifdef CONFIG_RV_PUM
+ /* Disable access to user memory */
+ csrc sstatus, t6
+#endif
+ li a0, 0
+ ret
+4: /* Edge case: unalignment */
+ fixup sb, zero, (a0), 10f
+ addi a0, a0, 1
+ bltu a0, t0, 4b
+ j 1b
+5: /* Edge case: remainder */
+ fixup sb, zero, (a0), 10f
+ addi a0, a0, 1
+ bltu a0, a3, 5b
+ j 3b
+ENDPROC(__clear_user)
+
+ .section .fixup,"ax"
+ .balign 4
+10:
+#ifdef CONFIG_RV_PUM
+ /* Disable access to user memory */
+ csrs sstatus, t6
+#endif
+ sub a0, a3, a0
+ ret
+ .previous
diff --git a/arch/riscv/lib/udivdi3.S b/arch/riscv/lib/udivdi3.S
new file mode 100644
index 000000000000..cb01ae5b181a
--- /dev/null
+++ b/arch/riscv/lib/udivdi3.S
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2016-2017 Free Software Foundation, Inc.
+ *
+ * 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.
+ */
+
+ .globl __udivdi3
+__udivdi3:
+ mv a2, a1
+ mv a1, a0
+ li a0, -1
+ beqz a2, .L5
+ li a3, 1
+ bgeu a2, a1, .L2
+.L1:
+ blez a2, .L2
+ slli a2, a2, 1
+ slli a3, a3, 1
+ bgtu a1, a2, .L1
+.L2:
+ li a0, 0
+.L3:
+ bltu a1, a2, .L4
+ sub a1, a1, a2
+ or a0, a0, a3
+.L4:
+ srli a3, a3, 1
+ srli a2, a2, 1
+ bnez a3, .L3
+.L5:
+ ret
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread
* [PATCH 4/9] RISC-V: ELF and module implementation
2017-07-04 19:50 ` Palmer Dabbelt
@ 2017-07-04 19:50 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains the code that interfaces with ELF objects on RISC-V
systems, the vast majority of which is present to load kernel modules.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/compat.h | 29 ++++++++++++++
arch/riscv/include/asm/elf.h | 83 +++++++++++++++++++++++++++++++++++++++++
arch/riscv/include/asm/hwcap.h | 37 ++++++++++++++++++
arch/riscv/mm/extable.c | 37 ++++++++++++++++++
4 files changed, 186 insertions(+)
create mode 100644 arch/riscv/include/asm/compat.h
create mode 100644 arch/riscv/include/asm/elf.h
create mode 100644 arch/riscv/include/asm/hwcap.h
create mode 100644 arch/riscv/mm/extable.c
diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h
new file mode 100644
index 000000000000..044aecff8854
--- /dev/null
+++ b/arch/riscv/include/asm/compat.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_COMPAT_H
+#define __ASM_COMPAT_H
+#ifdef CONFIG_COMPAT
+
+#if defined(CONFIG_64BIT)
+#define COMPAT_UTS_MACHINE "riscv64\0\0"
+#elif defined(CONFIG_32BIT)
+#define COMPAT_UTS_MACHINE "riscv32\0\0"
+#else
+#error "Unknown RISC-V base ISA"
+#endif
+
+#endif /*CONFIG_COMPAT*/
+#endif /*__ASM_COMPAT_H*/
diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
new file mode 100644
index 000000000000..5ded3f6f83ea
--- /dev/null
+++ b/arch/riscv/include/asm/elf.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
+ * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _ASM_RISCV_ELF_H
+#define _ASM_RISCV_ELF_H
+
+#include <uapi/asm/elf.h>
+#include <asm/auxvec.h>
+#include <asm/byteorder.h>
+
+/* TODO: Move definition into include/uapi/linux/elf-em.h */
+#define EM_RISCV 0xF3
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_ARCH EM_RISCV
+
+#ifdef CONFIG_64BIT
+#define ELF_CLASS ELFCLASS64
+#else
+#define ELF_CLASS ELFCLASS32
+#endif
+
+#if defined(__LITTLE_ENDIAN)
+#define ELF_DATA ELFDATA2LSB
+#elif defined(__BIG_ENDIAN)
+#define ELF_DATA ELFDATA2MSB
+#else
+#error "Unknown endianness"
+#endif
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) ((x)->e_machine == EM_RISCV)
+
+#define CORE_DUMP_USE_REGSET
+#define ELF_EXEC_PAGESIZE (PAGE_SIZE)
+
+/*
+ * This is the location that an ET_DYN program is loaded if exec'ed. Typical
+ * use of this is to invoke "./ld.so someprog" to test out a new version of
+ * the loader. We need to make sure that it is out of the way of the program
+ * that it will "exec", and that there is sufficient room for the brk.
+ */
+#define ELF_ET_DYN_BASE ((TASK_SIZE / 3) * 2)
+
+/*
+ * This yields a mask that user programs can use to figure out what
+ * instruction set this CPU supports. This could be done in user space,
+ * but it's not easy, and we've already done it here.
+ */
+#define ELF_HWCAP (0)
+
+/*
+ * This yields a string that ld.so will use to load implementation
+ * specific libraries for optimization. This is more specific in
+ * intent than poking at uname or /proc/cpuinfo.
+ */
+#define ELF_PLATFORM (NULL)
+
+#define ARCH_DLINFO \
+do { \
+ NEW_AUX_ENT(AT_SYSINFO_EHDR, \
+ (elf_addr_t)current->mm->context.vdso); \
+} while (0)
+
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp);
+
+#endif /* _ASM_RISCV_ELF_H */
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
new file mode 100644
index 000000000000..8a4ed7bbcbea
--- /dev/null
+++ b/arch/riscv/include/asm/hwcap.h
@@ -0,0 +1,37 @@
+/*
+ * Copied from arch/arm64/include/asm/hwcap.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_HWCAP_H
+#define __ASM_HWCAP_H
+
+#include <uapi/asm/hwcap.h>
+
+#ifndef __ASSEMBLY__
+/*
+ * This yields a mask that user programs can use to figure out what
+ * instruction set this cpu supports.
+ */
+#define ELF_HWCAP (elf_hwcap)
+
+enum {
+ CAP_HWCAP = 1,
+};
+
+extern unsigned long elf_hwcap;
+#endif
+#endif
diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c
new file mode 100644
index 000000000000..11bb9417123b
--- /dev/null
+++ b/arch/riscv/mm/extable.c
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2013 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+
+#include <linux/extable.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+int fixup_exception(struct pt_regs *regs)
+{
+ const struct exception_table_entry *fixup;
+
+ fixup = search_exception_tables(regs->sepc);
+ if (fixup) {
+ regs->sepc = fixup->fixup;
+ return 1;
+ }
+ return 0;
+}
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 4/9] RISC-V: ELF and module implementation
@ 2017-07-04 19:50 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains the code that interfaces with ELF objects on RISC-V
systems, the vast majority of which is present to load kernel modules.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/compat.h | 29 ++++++++++++++
arch/riscv/include/asm/elf.h | 83 +++++++++++++++++++++++++++++++++++++++++
arch/riscv/include/asm/hwcap.h | 37 ++++++++++++++++++
arch/riscv/mm/extable.c | 37 ++++++++++++++++++
4 files changed, 186 insertions(+)
create mode 100644 arch/riscv/include/asm/compat.h
create mode 100644 arch/riscv/include/asm/elf.h
create mode 100644 arch/riscv/include/asm/hwcap.h
create mode 100644 arch/riscv/mm/extable.c
diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h
new file mode 100644
index 000000000000..044aecff8854
--- /dev/null
+++ b/arch/riscv/include/asm/compat.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_COMPAT_H
+#define __ASM_COMPAT_H
+#ifdef CONFIG_COMPAT
+
+#if defined(CONFIG_64BIT)
+#define COMPAT_UTS_MACHINE "riscv64\0\0"
+#elif defined(CONFIG_32BIT)
+#define COMPAT_UTS_MACHINE "riscv32\0\0"
+#else
+#error "Unknown RISC-V base ISA"
+#endif
+
+#endif /*CONFIG_COMPAT*/
+#endif /*__ASM_COMPAT_H*/
diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
new file mode 100644
index 000000000000..5ded3f6f83ea
--- /dev/null
+++ b/arch/riscv/include/asm/elf.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
+ * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _ASM_RISCV_ELF_H
+#define _ASM_RISCV_ELF_H
+
+#include <uapi/asm/elf.h>
+#include <asm/auxvec.h>
+#include <asm/byteorder.h>
+
+/* TODO: Move definition into include/uapi/linux/elf-em.h */
+#define EM_RISCV 0xF3
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_ARCH EM_RISCV
+
+#ifdef CONFIG_64BIT
+#define ELF_CLASS ELFCLASS64
+#else
+#define ELF_CLASS ELFCLASS32
+#endif
+
+#if defined(__LITTLE_ENDIAN)
+#define ELF_DATA ELFDATA2LSB
+#elif defined(__BIG_ENDIAN)
+#define ELF_DATA ELFDATA2MSB
+#else
+#error "Unknown endianness"
+#endif
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) ((x)->e_machine == EM_RISCV)
+
+#define CORE_DUMP_USE_REGSET
+#define ELF_EXEC_PAGESIZE (PAGE_SIZE)
+
+/*
+ * This is the location that an ET_DYN program is loaded if exec'ed. Typical
+ * use of this is to invoke "./ld.so someprog" to test out a new version of
+ * the loader. We need to make sure that it is out of the way of the program
+ * that it will "exec", and that there is sufficient room for the brk.
+ */
+#define ELF_ET_DYN_BASE ((TASK_SIZE / 3) * 2)
+
+/*
+ * This yields a mask that user programs can use to figure out what
+ * instruction set this CPU supports. This could be done in user space,
+ * but it's not easy, and we've already done it here.
+ */
+#define ELF_HWCAP (0)
+
+/*
+ * This yields a string that ld.so will use to load implementation
+ * specific libraries for optimization. This is more specific in
+ * intent than poking at uname or /proc/cpuinfo.
+ */
+#define ELF_PLATFORM (NULL)
+
+#define ARCH_DLINFO \
+do { \
+ NEW_AUX_ENT(AT_SYSINFO_EHDR, \
+ (elf_addr_t)current->mm->context.vdso); \
+} while (0)
+
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp);
+
+#endif /* _ASM_RISCV_ELF_H */
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
new file mode 100644
index 000000000000..8a4ed7bbcbea
--- /dev/null
+++ b/arch/riscv/include/asm/hwcap.h
@@ -0,0 +1,37 @@
+/*
+ * Copied from arch/arm64/include/asm/hwcap.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_HWCAP_H
+#define __ASM_HWCAP_H
+
+#include <uapi/asm/hwcap.h>
+
+#ifndef __ASSEMBLY__
+/*
+ * This yields a mask that user programs can use to figure out what
+ * instruction set this cpu supports.
+ */
+#define ELF_HWCAP (elf_hwcap)
+
+enum {
+ CAP_HWCAP = 1,
+};
+
+extern unsigned long elf_hwcap;
+#endif
+#endif
diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c
new file mode 100644
index 000000000000..11bb9417123b
--- /dev/null
+++ b/arch/riscv/mm/extable.c
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2013 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+
+#include <linux/extable.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+int fixup_exception(struct pt_regs *regs)
+{
+ const struct exception_table_entry *fixup;
+
+ fixup = search_exception_tables(regs->sepc);
+ if (fixup) {
+ regs->sepc = fixup->fixup;
+ return 1;
+ }
+ return 0;
+}
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread
* [PATCH 5/9] RISC-V: Task implementation
2017-07-04 19:50 ` Palmer Dabbelt
@ 2017-07-04 19:50 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains the implementation of tasks on RISC-V, most of which
is involved in task switching.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/asm-offsets.h | 1 +
arch/riscv/include/asm/current.h | 44 ++++
arch/riscv/include/asm/kprobes.h | 22 ++
arch/riscv/include/asm/processor.h | 97 ++++++++
arch/riscv/include/asm/switch_to.h | 69 ++++++
arch/riscv/include/asm/thread_info.h | 93 ++++++++
arch/riscv/kernel/asm-offsets.c | 318 +++++++++++++++++++++++++
arch/riscv/kernel/entry.S | 450 +++++++++++++++++++++++++++++++++++
arch/riscv/kernel/process.c | 132 ++++++++++
9 files changed, 1226 insertions(+)
create mode 100644 arch/riscv/include/asm/asm-offsets.h
create mode 100644 arch/riscv/include/asm/current.h
create mode 100644 arch/riscv/include/asm/kprobes.h
create mode 100644 arch/riscv/include/asm/processor.h
create mode 100644 arch/riscv/include/asm/switch_to.h
create mode 100644 arch/riscv/include/asm/thread_info.h
create mode 100644 arch/riscv/kernel/asm-offsets.c
create mode 100644 arch/riscv/kernel/entry.S
create mode 100644 arch/riscv/kernel/process.c
diff --git a/arch/riscv/include/asm/asm-offsets.h b/arch/riscv/include/asm/asm-offsets.h
new file mode 100644
index 000000000000..d370ee36a182
--- /dev/null
+++ b/arch/riscv/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/riscv/include/asm/current.h b/arch/riscv/include/asm/current.h
new file mode 100644
index 000000000000..353a7c9f3c9e
--- /dev/null
+++ b/arch/riscv/include/asm/current.h
@@ -0,0 +1,44 @@
+/*
+ * Based on arm/arm64/include/asm/current.h
+ *
+ * Copyright (C) 2016 ARM
+ * 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.
+ */
+
+
+#ifndef __ASM_CURRENT_H
+#define __ASM_CURRENT_H
+
+#include <linux/compiler.h>
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+/*
+ * This only works because "struct thread_info" is at offset 0 from "struct
+ * task_struct". This constraint seems to be necessary on other architectures
+ * as well, but __switch_to enforces it. We can't check TASK_TI here because
+ * <asm/asm-offsets.h> includes this, and I can't get the definition of "struct
+ * task_struct" here due to some header ordering problems.
+ */
+static __always_inline struct task_struct *get_current(void)
+{
+ register struct task_struct *tp __asm__("tp");
+ return tp;
+}
+
+#define current get_current()
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_CURRENT_H */
diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h
new file mode 100644
index 000000000000..c7eb010d1528
--- /dev/null
+++ b/arch/riscv/include/asm/kprobes.h
@@ -0,0 +1,22 @@
+/*
+ * Copied from arch/arm64/include/asm/kprobes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ */
+
+#ifndef _RISCV_KPROBES_H
+#define _RISCV_KPROBES_H
+
+#include <asm-generic/kprobes.h>
+
+#endif /* _RISCV_KPROBES_H */
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
new file mode 100644
index 000000000000..3fe4af8147d2
--- /dev/null
+++ b/arch/riscv/include/asm/processor.h
@@ -0,0 +1,97 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PROCESSOR_H
+#define _ASM_RISCV_PROCESSOR_H
+
+#include <linux/const.h>
+
+#include <asm/ptrace.h>
+
+/*
+ * This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE >> 1)
+
+#define STACK_TOP TASK_SIZE
+#define STACK_TOP_MAX STACK_TOP
+#define STACK_ALIGN 16
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+struct pt_regs;
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ __label__ _l; _l: &&_l; })
+
+/* CPU-specific state of a task */
+struct thread_struct {
+ /* Callee-saved registers */
+ unsigned long ra;
+ unsigned long sp; /* Kernel mode stack */
+ unsigned long s[12]; /* s[0]: frame pointer */
+ struct __riscv_d_ext_state fstate;
+};
+
+#define INIT_THREAD { \
+ .sp = sizeof(init_stack) + (long)&init_stack, \
+}
+
+#define task_pt_regs(tsk) \
+ ((struct pt_regs *)(task_stack_page(tsk) + THREAD_SIZE \
+ - ALIGN(sizeof(struct pt_regs), STACK_ALIGN)))
+
+#define KSTK_EIP(tsk) (task_pt_regs(tsk)->sepc)
+#define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp)
+
+
+/* Do necessary setup to start up a newly executed thread. */
+extern void start_thread(struct pt_regs *regs,
+ unsigned long pc, unsigned long sp);
+
+/* Free all resources held by a thread. */
+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");
+}
+
+struct device_node;
+extern int riscv_of_processor_hart(struct device_node *node);
+
+extern void riscv_fill_hwcap(void);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
new file mode 100644
index 000000000000..dd6b05bff75b
--- /dev/null
+++ b/arch/riscv/include/asm/switch_to.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SWITCH_TO_H
+#define _ASM_RISCV_SWITCH_TO_H
+
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/csr.h>
+
+extern void __fstate_save(struct task_struct *save_to);
+extern void __fstate_restore(struct task_struct *restore_from);
+
+static inline void __fstate_clean(struct pt_regs *regs)
+{
+ regs->sstatus |= (regs->sstatus & ~(SR_FS)) | SR_FS_CLEAN;
+}
+
+static inline void fstate_save(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ if ((regs->sstatus & SR_FS) == SR_FS_DIRTY) {
+ __fstate_save(task);
+ __fstate_clean(regs);
+ }
+}
+
+static inline void fstate_restore(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ if ((regs->sstatus & SR_FS) != SR_FS_OFF) {
+ __fstate_restore(task);
+ __fstate_clean(regs);
+ }
+}
+
+static inline void __switch_to_aux(struct task_struct *prev,
+ struct task_struct *next)
+{
+ struct pt_regs *regs;
+
+ regs = task_pt_regs(prev);
+ if (unlikely(regs->sstatus & SR_SD))
+ fstate_save(prev, regs);
+ fstate_restore(next, task_pt_regs(next));
+}
+
+extern struct task_struct *__switch_to(struct task_struct *,
+ struct task_struct *);
+
+#define switch_to(prev, next, last) \
+do { \
+ struct task_struct *__prev = (prev); \
+ struct task_struct *__next = (next); \
+ __switch_to_aux(__prev, __next); \
+ ((last) = __switch_to(__prev, __next)); \
+} while (0)
+
+#endif /* _ASM_RISCV_SWITCH_TO_H */
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
new file mode 100644
index 000000000000..ad13bea17b5d
--- /dev/null
+++ b/arch/riscv/include/asm/thread_info.h
@@ -0,0 +1,93 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_THREAD_INFO_H
+#define _ASM_RISCV_THREAD_INFO_H
+
+#include <asm/page.h>
+#include <linux/const.h>
+
+/* thread information allocation */
+#define THREAD_SIZE_ORDER (1)
+#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/processor.h>
+#include <asm/csr.h>
+
+typedef unsigned long mm_segment_t;
+
+/*
+ * low level task data that entry.S needs immediate access to
+ * - this struct should fit entirely inside of one cache line
+ * - if the members of this struct changes, the assembly constants
+ * in asm-offsets.c must be updated accordingly
+ * - thread_info is included in task_struct at an offset of 0. This means that
+ * tp points to both thread_info and task_struct.
+ */
+struct thread_info {
+ unsigned long flags; /* low level flags */
+ int preempt_count; /* 0=>preemptible, <0=>BUG */
+ mm_segment_t addr_limit;
+ /*
+ * These stack pointers are overwritten on every system call or
+ * exception. SP is also saved to the stack it can be recovered when
+ * overwritten.
+ */
+ long kernel_sp; /* Kernel stack pointer */
+ long user_sp; /* User stack pointer */
+};
+
+/*
+ * macros/functions for gaining access to the thread information structure
+ *
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#define INIT_THREAD_INFO(tsk) \
+{ \
+ .flags = 0, \
+ .preempt_count = INIT_PREEMPT_COUNT, \
+ .addr_limit = KERNEL_DS, \
+}
+
+#define init_stack (init_thread_union.stack)
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * thread information flags
+ * - these are process state flags that various assembly files may need to
+ * access
+ * - pending work-to-be-done flags are in lowest half-word
+ * - other flags in upper half-word(s)
+ */
+#define TIF_SYSCALL_TRACE 0 /* syscall trace active */
+#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */
+#define TIF_SIGPENDING 2 /* signal pending */
+#define TIF_NEED_RESCHED 3 /* rescheduling necessary */
+#define TIF_RESTORE_SIGMASK 4 /* restore signal mask in do_signal() */
+#define TIF_MEMDIE 5 /* is terminating due to OOM killer */
+#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
+
+#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
+#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
+#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
+
+#define _TIF_WORK_MASK \
+ (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED)
+
+#endif /* _ASM_RISCV_THREAD_INFO_H */
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
new file mode 100644
index 000000000000..3dc7f9d52cb1
--- /dev/null
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -0,0 +1,318 @@
+/*
+ * 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/kbuild.h>
+#include <linux/sched.h>
+#include <asm/thread_info.h>
+#include <asm/ptrace.h>
+
+void asm_offsets(void)
+{
+ OFFSET(TASK_THREAD_RA, task_struct, thread.ra);
+ OFFSET(TASK_THREAD_SP, task_struct, thread.sp);
+ OFFSET(TASK_THREAD_S0, task_struct, thread.s[0]);
+ OFFSET(TASK_THREAD_S1, task_struct, thread.s[1]);
+ OFFSET(TASK_THREAD_S2, task_struct, thread.s[2]);
+ OFFSET(TASK_THREAD_S3, task_struct, thread.s[3]);
+ OFFSET(TASK_THREAD_S4, task_struct, thread.s[4]);
+ OFFSET(TASK_THREAD_S5, task_struct, thread.s[5]);
+ OFFSET(TASK_THREAD_S6, task_struct, thread.s[6]);
+ OFFSET(TASK_THREAD_S7, task_struct, thread.s[7]);
+ OFFSET(TASK_THREAD_S8, task_struct, thread.s[8]);
+ OFFSET(TASK_THREAD_S9, task_struct, thread.s[9]);
+ OFFSET(TASK_THREAD_S10, task_struct, thread.s[10]);
+ OFFSET(TASK_THREAD_S11, task_struct, thread.s[11]);
+ OFFSET(TASK_THREAD_SP, task_struct, thread.sp);
+ OFFSET(TASK_STACK, task_struct, stack);
+ OFFSET(TASK_TI, task_struct, thread_info);
+ OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags);
+ OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
+ OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
+
+ OFFSET(TASK_THREAD_F0, task_struct, thread.fstate.f[0]);
+ OFFSET(TASK_THREAD_F1, task_struct, thread.fstate.f[1]);
+ OFFSET(TASK_THREAD_F2, task_struct, thread.fstate.f[2]);
+ OFFSET(TASK_THREAD_F3, task_struct, thread.fstate.f[3]);
+ OFFSET(TASK_THREAD_F4, task_struct, thread.fstate.f[4]);
+ OFFSET(TASK_THREAD_F5, task_struct, thread.fstate.f[5]);
+ OFFSET(TASK_THREAD_F6, task_struct, thread.fstate.f[6]);
+ OFFSET(TASK_THREAD_F7, task_struct, thread.fstate.f[7]);
+ OFFSET(TASK_THREAD_F8, task_struct, thread.fstate.f[8]);
+ OFFSET(TASK_THREAD_F9, task_struct, thread.fstate.f[9]);
+ OFFSET(TASK_THREAD_F10, task_struct, thread.fstate.f[10]);
+ OFFSET(TASK_THREAD_F11, task_struct, thread.fstate.f[11]);
+ OFFSET(TASK_THREAD_F12, task_struct, thread.fstate.f[12]);
+ OFFSET(TASK_THREAD_F13, task_struct, thread.fstate.f[13]);
+ OFFSET(TASK_THREAD_F14, task_struct, thread.fstate.f[14]);
+ OFFSET(TASK_THREAD_F15, task_struct, thread.fstate.f[15]);
+ OFFSET(TASK_THREAD_F16, task_struct, thread.fstate.f[16]);
+ OFFSET(TASK_THREAD_F17, task_struct, thread.fstate.f[17]);
+ OFFSET(TASK_THREAD_F18, task_struct, thread.fstate.f[18]);
+ OFFSET(TASK_THREAD_F19, task_struct, thread.fstate.f[19]);
+ OFFSET(TASK_THREAD_F20, task_struct, thread.fstate.f[20]);
+ OFFSET(TASK_THREAD_F21, task_struct, thread.fstate.f[21]);
+ OFFSET(TASK_THREAD_F22, task_struct, thread.fstate.f[22]);
+ OFFSET(TASK_THREAD_F23, task_struct, thread.fstate.f[23]);
+ OFFSET(TASK_THREAD_F24, task_struct, thread.fstate.f[24]);
+ OFFSET(TASK_THREAD_F25, task_struct, thread.fstate.f[25]);
+ OFFSET(TASK_THREAD_F26, task_struct, thread.fstate.f[26]);
+ OFFSET(TASK_THREAD_F27, task_struct, thread.fstate.f[27]);
+ OFFSET(TASK_THREAD_F28, task_struct, thread.fstate.f[28]);
+ OFFSET(TASK_THREAD_F29, task_struct, thread.fstate.f[29]);
+ OFFSET(TASK_THREAD_F30, task_struct, thread.fstate.f[30]);
+ OFFSET(TASK_THREAD_F31, task_struct, thread.fstate.f[31]);
+ OFFSET(TASK_THREAD_FCSR, task_struct, thread.fstate.fcsr);
+
+ DEFINE(PT_SIZE, sizeof(struct pt_regs));
+ OFFSET(PT_SEPC, pt_regs, sepc);
+ OFFSET(PT_RA, pt_regs, ra);
+ OFFSET(PT_FP, pt_regs, s0);
+ OFFSET(PT_S0, pt_regs, s0);
+ OFFSET(PT_S1, pt_regs, s1);
+ OFFSET(PT_S2, pt_regs, s2);
+ OFFSET(PT_S3, pt_regs, s3);
+ OFFSET(PT_S4, pt_regs, s4);
+ OFFSET(PT_S5, pt_regs, s5);
+ OFFSET(PT_S6, pt_regs, s6);
+ OFFSET(PT_S7, pt_regs, s7);
+ OFFSET(PT_S8, pt_regs, s8);
+ OFFSET(PT_S9, pt_regs, s9);
+ OFFSET(PT_S10, pt_regs, s10);
+ OFFSET(PT_S11, pt_regs, s11);
+ OFFSET(PT_SP, pt_regs, sp);
+ OFFSET(PT_TP, pt_regs, tp);
+ OFFSET(PT_A0, pt_regs, a0);
+ OFFSET(PT_A1, pt_regs, a1);
+ OFFSET(PT_A2, pt_regs, a2);
+ OFFSET(PT_A3, pt_regs, a3);
+ OFFSET(PT_A4, pt_regs, a4);
+ OFFSET(PT_A5, pt_regs, a5);
+ OFFSET(PT_A6, pt_regs, a6);
+ OFFSET(PT_A7, pt_regs, a7);
+ OFFSET(PT_T0, pt_regs, t0);
+ OFFSET(PT_T1, pt_regs, t1);
+ OFFSET(PT_T2, pt_regs, t2);
+ OFFSET(PT_T3, pt_regs, t3);
+ OFFSET(PT_T4, pt_regs, t4);
+ OFFSET(PT_T5, pt_regs, t5);
+ OFFSET(PT_T6, pt_regs, t6);
+ OFFSET(PT_GP, pt_regs, gp);
+ OFFSET(PT_SSTATUS, pt_regs, sstatus);
+ OFFSET(PT_SBADADDR, pt_regs, sbadaddr);
+ OFFSET(PT_SCAUSE, pt_regs, scause);
+
+ /*
+ * THREAD_{F,X}* might be larger than a S-type offset can handle, but
+ * these are used in performance-sensitive assembly so we can't resort
+ * to loading the long immediate every time.
+ */
+ DEFINE(TASK_THREAD_RA_RA,
+ offsetof(struct task_struct, thread.ra)
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_SP_RA,
+ offsetof(struct task_struct, thread.sp)
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S0_RA,
+ offsetof(struct task_struct, thread.s[0])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S1_RA,
+ offsetof(struct task_struct, thread.s[1])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S2_RA,
+ offsetof(struct task_struct, thread.s[2])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S3_RA,
+ offsetof(struct task_struct, thread.s[3])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S4_RA,
+ offsetof(struct task_struct, thread.s[4])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S5_RA,
+ offsetof(struct task_struct, thread.s[5])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S6_RA,
+ offsetof(struct task_struct, thread.s[6])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S7_RA,
+ offsetof(struct task_struct, thread.s[7])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S8_RA,
+ offsetof(struct task_struct, thread.s[8])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S9_RA,
+ offsetof(struct task_struct, thread.s[9])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S10_RA,
+ offsetof(struct task_struct, thread.s[10])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S11_RA,
+ offsetof(struct task_struct, thread.s[11])
+ - offsetof(struct task_struct, thread.ra)
+ );
+
+ DEFINE(TASK_THREAD_F0_F0,
+ offsetof(struct task_struct, thread.fstate.f[0])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F1_F0,
+ offsetof(struct task_struct, thread.fstate.f[1])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F2_F0,
+ offsetof(struct task_struct, thread.fstate.f[2])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F3_F0,
+ offsetof(struct task_struct, thread.fstate.f[3])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F4_F0,
+ offsetof(struct task_struct, thread.fstate.f[4])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F5_F0,
+ offsetof(struct task_struct, thread.fstate.f[5])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F6_F0,
+ offsetof(struct task_struct, thread.fstate.f[6])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F7_F0,
+ offsetof(struct task_struct, thread.fstate.f[7])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F8_F0,
+ offsetof(struct task_struct, thread.fstate.f[8])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F9_F0,
+ offsetof(struct task_struct, thread.fstate.f[9])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F10_F0,
+ offsetof(struct task_struct, thread.fstate.f[10])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F11_F0,
+ offsetof(struct task_struct, thread.fstate.f[11])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F12_F0,
+ offsetof(struct task_struct, thread.fstate.f[12])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F13_F0,
+ offsetof(struct task_struct, thread.fstate.f[13])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F14_F0,
+ offsetof(struct task_struct, thread.fstate.f[14])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F15_F0,
+ offsetof(struct task_struct, thread.fstate.f[15])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F16_F0,
+ offsetof(struct task_struct, thread.fstate.f[16])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F17_F0,
+ offsetof(struct task_struct, thread.fstate.f[17])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F18_F0,
+ offsetof(struct task_struct, thread.fstate.f[18])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F19_F0,
+ offsetof(struct task_struct, thread.fstate.f[19])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F20_F0,
+ offsetof(struct task_struct, thread.fstate.f[20])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F21_F0,
+ offsetof(struct task_struct, thread.fstate.f[21])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F22_F0,
+ offsetof(struct task_struct, thread.fstate.f[22])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F23_F0,
+ offsetof(struct task_struct, thread.fstate.f[23])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F24_F0,
+ offsetof(struct task_struct, thread.fstate.f[24])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F25_F0,
+ offsetof(struct task_struct, thread.fstate.f[25])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F26_F0,
+ offsetof(struct task_struct, thread.fstate.f[26])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F27_F0,
+ offsetof(struct task_struct, thread.fstate.f[27])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F28_F0,
+ offsetof(struct task_struct, thread.fstate.f[28])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F29_F0,
+ offsetof(struct task_struct, thread.fstate.f[29])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F30_F0,
+ offsetof(struct task_struct, thread.fstate.f[30])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F31_F0,
+ offsetof(struct task_struct, thread.fstate.f[31])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_FCSR_F0,
+ offsetof(struct task_struct, thread.fstate.fcsr)
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+
+ /* The assembler needs access to THREAD_SIZE as well. */
+ DEFINE(ASM_THREAD_SIZE, THREAD_SIZE);
+
+ /*
+ * We allocate a pt_regs on the stack when entering the kernel. This
+ * ensures the alignment is sane.
+ */
+ DEFINE(PT_SIZE_ON_STACK, ALIGN(sizeof(struct pt_regs), STACK_ALIGN));
+}
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
new file mode 100644
index 000000000000..7208fcec0cf4
--- /dev/null
+++ b/arch/riscv/kernel/entry.S
@@ -0,0 +1,450 @@
+/*
+ * 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/init.h>
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+
+ .text
+ .altmacro
+
+/*
+ * Prepares to enter a system call or exception by saving all registers to the
+ * stack.
+ */
+ .macro SAVE_ALL
+ LOCAL _restore_kernel_tpsp
+ LOCAL _save_context
+
+ /*
+ * If coming from userspace, preserve the user thread pointer and load
+ * the kernel thread pointer. If we came from the kernel, sscratch
+ * will contain 0, and we should continue on the current TP.
+ */
+ csrrw tp, sscratch, tp
+ bnez tp, _save_context
+
+_restore_kernel_tpsp:
+ csrr tp, sscratch
+ REG_S sp, TASK_TI_KERNEL_SP(tp)
+_save_context:
+ REG_S sp, TASK_TI_USER_SP(tp)
+ REG_L sp, TASK_TI_KERNEL_SP(tp)
+ addi sp, sp, -(PT_SIZE_ON_STACK)
+ REG_S x1, PT_RA(sp)
+ REG_S x3, PT_GP(sp)
+ REG_S x5, PT_T0(sp)
+ REG_S x6, PT_T1(sp)
+ REG_S x7, PT_T2(sp)
+ REG_S x8, PT_S0(sp)
+ REG_S x9, PT_S1(sp)
+ REG_S x10, PT_A0(sp)
+ REG_S x11, PT_A1(sp)
+ REG_S x12, PT_A2(sp)
+ REG_S x13, PT_A3(sp)
+ REG_S x14, PT_A4(sp)
+ REG_S x15, PT_A5(sp)
+ REG_S x16, PT_A6(sp)
+ REG_S x17, PT_A7(sp)
+ REG_S x18, PT_S2(sp)
+ REG_S x19, PT_S3(sp)
+ REG_S x20, PT_S4(sp)
+ REG_S x21, PT_S5(sp)
+ REG_S x22, PT_S6(sp)
+ REG_S x23, PT_S7(sp)
+ REG_S x24, PT_S8(sp)
+ REG_S x25, PT_S9(sp)
+ REG_S x26, PT_S10(sp)
+ REG_S x27, PT_S11(sp)
+ REG_S x28, PT_T3(sp)
+ REG_S x29, PT_T4(sp)
+ REG_S x30, PT_T5(sp)
+ REG_S x31, PT_T6(sp)
+
+ /*
+ * Disable FPU to detect illegal usage of
+ * floating point in kernel space
+ */
+ li t0, SR_FS
+
+ REG_L s0, TASK_TI_USER_SP(tp)
+ csrrc s1, sstatus, t0
+ csrr s2, sepc
+ csrr s3, sbadaddr
+ csrr s4, scause
+ csrr s5, sscratch
+ REG_S s0, PT_SP(sp)
+ REG_S s1, PT_SSTATUS(sp)
+ REG_S s2, PT_SEPC(sp)
+ REG_S s3, PT_SBADADDR(sp)
+ REG_S s4, PT_SCAUSE(sp)
+ REG_S s5, PT_TP(sp)
+ .endm
+
+/*
+ * Prepares to return from a system call or exception by restoring all
+ * registers from the stack.
+ */
+ .macro RESTORE_ALL
+ REG_L a0, PT_SSTATUS(sp)
+ REG_L a2, PT_SEPC(sp)
+ csrw sstatus, a0
+ csrw sepc, a2
+
+ REG_L x1, PT_RA(sp)
+ REG_L x3, PT_GP(sp)
+ REG_L x4, PT_TP(sp)
+ REG_L x5, PT_T0(sp)
+ REG_L x6, PT_T1(sp)
+ REG_L x7, PT_T2(sp)
+ REG_L x8, PT_S0(sp)
+ REG_L x9, PT_S1(sp)
+ REG_L x10, PT_A0(sp)
+ REG_L x11, PT_A1(sp)
+ REG_L x12, PT_A2(sp)
+ REG_L x13, PT_A3(sp)
+ REG_L x14, PT_A4(sp)
+ REG_L x15, PT_A5(sp)
+ REG_L x16, PT_A6(sp)
+ REG_L x17, PT_A7(sp)
+ REG_L x18, PT_S2(sp)
+ REG_L x19, PT_S3(sp)
+ REG_L x20, PT_S4(sp)
+ REG_L x21, PT_S5(sp)
+ REG_L x22, PT_S6(sp)
+ REG_L x23, PT_S7(sp)
+ REG_L x24, PT_S8(sp)
+ REG_L x25, PT_S9(sp)
+ REG_L x26, PT_S10(sp)
+ REG_L x27, PT_S11(sp)
+ REG_L x28, PT_T3(sp)
+ REG_L x29, PT_T4(sp)
+ REG_L x30, PT_T5(sp)
+ REG_L x31, PT_T6(sp)
+
+ REG_L x2, PT_SP(sp)
+ .endm
+
+ENTRY(handle_exception)
+ SAVE_ALL
+
+ /*
+ * Set sscratch register to 0, so that if a recursive exception
+ * occurs, the exception vector knows it came from the kernel
+ */
+ csrw sscratch, x0
+
+ la gp, __global_pointer$
+
+ la ra, ret_from_exception
+ /*
+ * MSB of cause differentiates between
+ * interrupts and exceptions
+ */
+ bge s4, zero, 1f
+
+ /* Handle interrupts */
+ slli a0, s4, 1
+ srli a0, a0, 1
+ move a1, sp /* pt_regs */
+ tail do_IRQ
+1:
+ /* Handle syscalls */
+ li t0, EXC_SYSCALL
+ beq s4, t0, handle_syscall
+
+ /* Handle other exceptions */
+ slli t0, s4, RISCV_LGPTR
+ la t1, excp_vect_table
+ la t2, excp_vect_table_end
+ move a0, sp /* pt_regs */
+ add t0, t1, t0
+ /* Check if exception code lies within bounds */
+ bgeu t0, t2, 1f
+ REG_L t0, 0(t0)
+ jr t0
+1:
+ tail do_trap_unknown
+
+handle_syscall:
+ /*
+ * Advance SEPC to avoid executing the original
+ * scall instruction on sret
+ */
+ addi s2, s2, 0x4
+ REG_S s2, PT_SEPC(sp)
+ /* System calls run with interrupts enabled */
+ csrs sstatus, SR_IE
+ /* Trace syscalls, but only if requested by the user. */
+ REG_L t0, TASK_TI_FLAGS(tp)
+ andi t0, t0, _TIF_SYSCALL_TRACE
+ bnez t0, handle_syscall_trace_enter
+check_syscall_nr:
+ /* Check to make sure we don't jump to a bogus syscall number. */
+ li t0, __NR_syscalls
+ la s0, sys_ni_syscall
+ /* Syscall number held in a7 */
+ bgeu a7, t0, 1f
+ la s0, sys_call_table
+ slli t0, a7, RISCV_LGPTR
+ add s0, s0, t0
+ REG_L s0, 0(s0)
+1:
+ jalr s0
+
+ret_from_syscall:
+ /* Set user a0 to kernel a0 */
+ REG_S a0, PT_A0(sp)
+ /* Trace syscalls, but only if requested by the user. */
+ REG_L t0, TASK_TI_FLAGS(tp)
+ andi t0, t0, _TIF_SYSCALL_TRACE
+ bnez t0, handle_syscall_trace_exit
+
+ret_from_exception:
+ REG_L s0, PT_SSTATUS(sp)
+ csrc sstatus, SR_IE
+ andi s0, s0, SR_PS
+ bnez s0, restore_all
+
+resume_userspace:
+ /* Interrupts must be disabled here so flags are checked atomically */
+ REG_L s0, TASK_TI_FLAGS(tp) /* current_thread_info->flags */
+ andi s1, s0, _TIF_WORK_MASK
+ bnez s1, work_pending
+
+ /* Save unwound kernel stack pointer in thread_info */
+ addi s0, sp, PT_SIZE_ON_STACK
+ REG_S s0, TASK_TI_KERNEL_SP(tp)
+
+ /*
+ * Save TP into sscratch, so we can find the kernel data structures
+ * again.
+ */
+ csrw sscratch, tp
+
+restore_all:
+ RESTORE_ALL
+ sret
+
+work_pending:
+ /* Enter slow path for supplementary processing */
+ la ra, ret_from_exception
+ andi s1, s0, _TIF_NEED_RESCHED
+ bnez s1, work_resched
+work_notifysig:
+ /* Handle pending signals and notify-resume requests */
+ csrs sstatus, SR_IE /* Enable interrupts for do_notify_resume() */
+ move a0, sp /* pt_regs */
+ move a1, s0 /* current_thread_info->flags */
+ tail do_notify_resume
+work_resched:
+ tail schedule
+
+/* Slow paths for ptrace. */
+handle_syscall_trace_enter:
+ move a0, sp
+ call do_syscall_trace_enter
+ REG_L a0, PT_A0(sp)
+ REG_L a1, PT_A1(sp)
+ REG_L a2, PT_A2(sp)
+ REG_L a3, PT_A3(sp)
+ REG_L a4, PT_A4(sp)
+ REG_L a5, PT_A5(sp)
+ REG_L a6, PT_A6(sp)
+ REG_L a7, PT_A7(sp)
+ j check_syscall_nr
+handle_syscall_trace_exit:
+ move a0, sp
+ call do_syscall_trace_exit
+ j ret_from_exception
+
+END(handle_exception)
+
+ENTRY(ret_from_fork)
+ la ra, ret_from_exception
+ tail schedule_tail
+ENDPROC(ret_from_fork)
+
+ENTRY(ret_from_kernel_thread)
+ call schedule_tail
+ /* Call fn(arg) */
+ la ra, ret_from_exception
+ move a0, s1
+ jr s0
+ENDPROC(ret_from_kernel_thread)
+
+
+/*
+ * Integer register context switch
+ * The callee-saved registers must be saved and restored.
+ *
+ * a0: previous task_struct (must be preserved across the switch)
+ * a1: next task_struct
+ */
+ENTRY(__switch_to)
+ /* Save context into prev->thread */
+ li a2, TASK_THREAD_RA
+ add a0, a0, a2
+ add a2, a1, a2
+ REG_S ra, TASK_THREAD_RA_RA(a0)
+ REG_S sp, TASK_THREAD_SP_RA(a0)
+ REG_S s0, TASK_THREAD_S0_RA(a0)
+ REG_S s1, TASK_THREAD_S1_RA(a0)
+ REG_S s2, TASK_THREAD_S2_RA(a0)
+ REG_S s3, TASK_THREAD_S3_RA(a0)
+ REG_S s4, TASK_THREAD_S4_RA(a0)
+ REG_S s5, TASK_THREAD_S5_RA(a0)
+ REG_S s6, TASK_THREAD_S6_RA(a0)
+ REG_S s7, TASK_THREAD_S7_RA(a0)
+ REG_S s8, TASK_THREAD_S8_RA(a0)
+ REG_S s9, TASK_THREAD_S9_RA(a0)
+ REG_S s10, TASK_THREAD_S10_RA(a0)
+ REG_S s11, TASK_THREAD_S11_RA(a0)
+ /* Restore context from next->thread */
+ REG_L ra, TASK_THREAD_RA_RA(a2)
+ REG_L sp, TASK_THREAD_SP_RA(a2)
+ REG_L s0, TASK_THREAD_S0_RA(a2)
+ REG_L s1, TASK_THREAD_S1_RA(a2)
+ REG_L s2, TASK_THREAD_S2_RA(a2)
+ REG_L s3, TASK_THREAD_S3_RA(a2)
+ REG_L s4, TASK_THREAD_S4_RA(a2)
+ REG_L s5, TASK_THREAD_S5_RA(a2)
+ REG_L s6, TASK_THREAD_S6_RA(a2)
+ REG_L s7, TASK_THREAD_S7_RA(a2)
+ REG_L s8, TASK_THREAD_S8_RA(a2)
+ REG_L s9, TASK_THREAD_S9_RA(a2)
+ REG_L s10, TASK_THREAD_S10_RA(a2)
+ REG_L s11, TASK_THREAD_S11_RA(a2)
+#if TASK_TI != 0
+#error "TASK_TI != 0: tp will contain a 'struct thread_info', not a 'struct task_struct' so get_current() won't work."
+ addi tp, a1, TASK_TI
+#else
+ move tp, a1
+#endif
+ 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)
+ RISCV_PTR do_trap_insn_misaligned
+ RISCV_PTR do_trap_insn_fault
+ RISCV_PTR do_trap_insn_illegal
+ RISCV_PTR do_trap_break
+ RISCV_PTR do_trap_load_misaligned
+ RISCV_PTR do_trap_load_fault
+ RISCV_PTR do_trap_store_misaligned
+ RISCV_PTR do_trap_store_fault
+ RISCV_PTR do_trap_ecall_u /* system call, gets intercepted */
+ RISCV_PTR do_trap_ecall_s
+ RISCV_PTR do_trap_unknown
+ RISCV_PTR do_trap_ecall_m
+ RISCV_PTR do_page_fault /* instruction page fault */
+ RISCV_PTR do_page_fault /* load page fault */
+ RISCV_PTR do_trap_unknown
+ RISCV_PTR do_page_fault /* store page fault */
+excp_vect_table_end:
+END(excp_vect_table)
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
new file mode 100644
index 000000000000..7d539d64bf1a
--- /dev/null
+++ b/arch/riscv/kernel/process.c
@@ -0,0 +1,132 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/tick.h>
+#include <linux/ptrace.h>
+
+#include <asm/unistd.h>
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+#include <asm/csr.h>
+#include <asm/string.h>
+#include <asm/switch_to.h>
+
+extern asmlinkage void ret_from_fork(void);
+extern asmlinkage void ret_from_kernel_thread(void);
+
+void arch_cpu_idle(void)
+{
+ wait_for_interrupt();
+ local_irq_enable();
+}
+
+void show_regs(struct pt_regs *regs)
+{
+ show_regs_print_info(KERN_DEFAULT);
+
+ pr_cont("sepc: " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n",
+ regs->sepc, regs->ra, regs->sp);
+ pr_cont(" gp : " REG_FMT " tp : " REG_FMT " t0 : " REG_FMT "\n",
+ regs->gp, regs->tp, regs->t0);
+ pr_cont(" t1 : " REG_FMT " t2 : " REG_FMT " s0 : " REG_FMT "\n",
+ regs->t1, regs->t2, regs->s0);
+ pr_cont(" s1 : " REG_FMT " a0 : " REG_FMT " a1 : " REG_FMT "\n",
+ regs->s1, regs->a0, regs->a1);
+ pr_cont(" a2 : " REG_FMT " a3 : " REG_FMT " a4 : " REG_FMT "\n",
+ regs->a2, regs->a3, regs->a4);
+ pr_cont(" a5 : " REG_FMT " a6 : " REG_FMT " a7 : " REG_FMT "\n",
+ regs->a5, regs->a6, regs->a7);
+ pr_cont(" s2 : " REG_FMT " s3 : " REG_FMT " s4 : " REG_FMT "\n",
+ regs->s2, regs->s3, regs->s4);
+ pr_cont(" s5 : " REG_FMT " s6 : " REG_FMT " s7 : " REG_FMT "\n",
+ regs->s5, regs->s6, regs->s7);
+ pr_cont(" s8 : " REG_FMT " s9 : " REG_FMT " s10: " REG_FMT "\n",
+ regs->s8, regs->s9, regs->s10);
+ pr_cont(" s11: " REG_FMT " t3 : " REG_FMT " t4 : " REG_FMT "\n",
+ regs->s11, regs->t3, regs->t4);
+ pr_cont(" t5 : " REG_FMT " t6 : " REG_FMT "\n",
+ regs->t5, regs->t6);
+
+ pr_cont("sstatus: " REG_FMT " sbadaddr: " REG_FMT " scause: " REG_FMT "\n",
+ regs->sstatus, regs->sbadaddr, regs->scause);
+}
+
+void start_thread(struct pt_regs *regs, unsigned long pc,
+ unsigned long sp)
+{
+ regs->sstatus = SR_PIE /* User mode, irqs on */ | SR_FS_INITIAL;
+#ifndef CONFIG_RV_PUM
+ regs->sstatus |= SR_SUM;
+#endif
+ regs->sepc = pc;
+ regs->sp = sp;
+ set_fs(USER_DS);
+}
+
+void flush_thread(void)
+{
+ /*
+ * Reset FPU context
+ * frm: round to nearest, ties to even (IEEE default)
+ * fflags: accrued exceptions cleared
+ */
+ memset(¤t->thread.fstate, 0, sizeof(current->thread.fstate));
+}
+
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+ fstate_save(src, task_pt_regs(src));
+ *dst = *src;
+ return 0;
+}
+
+int copy_thread(unsigned long clone_flags, unsigned long usp,
+ unsigned long arg, struct task_struct *p)
+{
+ struct pt_regs *childregs = task_pt_regs(p);
+
+ /* p->thread holds context to be restored by __switch_to() */
+ if (unlikely(p->flags & PF_KTHREAD)) {
+ /* Kernel thread */
+ const register unsigned long gp __asm__ ("gp");
+ memset(childregs, 0, sizeof(struct pt_regs));
+ childregs->gp = gp;
+ childregs->sstatus = SR_PS | SR_PIE; /* Supervisor, irqs on */
+
+ p->thread.ra = (unsigned long)ret_from_kernel_thread;
+ p->thread.s[0] = usp; /* fn */
+ p->thread.s[1] = arg;
+ } else {
+ *childregs = *(current_pt_regs());
+ if (usp) /* User fork */
+ childregs->sp = usp;
+ if (clone_flags & CLONE_SETTLS)
+ childregs->tp = childregs->a5;
+ childregs->a0 = 0; /* Return value of fork() */
+ p->thread.ra = (unsigned long)ret_from_fork;
+ }
+ p->thread.sp = (unsigned long)childregs; /* kernel sp */
+ return 0;
+}
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 5/9] RISC-V: Task implementation
@ 2017-07-04 19:50 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains the implementation of tasks on RISC-V, most of which
is involved in task switching.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/asm-offsets.h | 1 +
arch/riscv/include/asm/current.h | 44 ++++
arch/riscv/include/asm/kprobes.h | 22 ++
arch/riscv/include/asm/processor.h | 97 ++++++++
arch/riscv/include/asm/switch_to.h | 69 ++++++
arch/riscv/include/asm/thread_info.h | 93 ++++++++
arch/riscv/kernel/asm-offsets.c | 318 +++++++++++++++++++++++++
arch/riscv/kernel/entry.S | 450 +++++++++++++++++++++++++++++++++++
arch/riscv/kernel/process.c | 132 ++++++++++
9 files changed, 1226 insertions(+)
create mode 100644 arch/riscv/include/asm/asm-offsets.h
create mode 100644 arch/riscv/include/asm/current.h
create mode 100644 arch/riscv/include/asm/kprobes.h
create mode 100644 arch/riscv/include/asm/processor.h
create mode 100644 arch/riscv/include/asm/switch_to.h
create mode 100644 arch/riscv/include/asm/thread_info.h
create mode 100644 arch/riscv/kernel/asm-offsets.c
create mode 100644 arch/riscv/kernel/entry.S
create mode 100644 arch/riscv/kernel/process.c
diff --git a/arch/riscv/include/asm/asm-offsets.h b/arch/riscv/include/asm/asm-offsets.h
new file mode 100644
index 000000000000..d370ee36a182
--- /dev/null
+++ b/arch/riscv/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/riscv/include/asm/current.h b/arch/riscv/include/asm/current.h
new file mode 100644
index 000000000000..353a7c9f3c9e
--- /dev/null
+++ b/arch/riscv/include/asm/current.h
@@ -0,0 +1,44 @@
+/*
+ * Based on arm/arm64/include/asm/current.h
+ *
+ * Copyright (C) 2016 ARM
+ * 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.
+ */
+
+
+#ifndef __ASM_CURRENT_H
+#define __ASM_CURRENT_H
+
+#include <linux/compiler.h>
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+/*
+ * This only works because "struct thread_info" is at offset 0 from "struct
+ * task_struct". This constraint seems to be necessary on other architectures
+ * as well, but __switch_to enforces it. We can't check TASK_TI here because
+ * <asm/asm-offsets.h> includes this, and I can't get the definition of "struct
+ * task_struct" here due to some header ordering problems.
+ */
+static __always_inline struct task_struct *get_current(void)
+{
+ register struct task_struct *tp __asm__("tp");
+ return tp;
+}
+
+#define current get_current()
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_CURRENT_H */
diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h
new file mode 100644
index 000000000000..c7eb010d1528
--- /dev/null
+++ b/arch/riscv/include/asm/kprobes.h
@@ -0,0 +1,22 @@
+/*
+ * Copied from arch/arm64/include/asm/kprobes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ */
+
+#ifndef _RISCV_KPROBES_H
+#define _RISCV_KPROBES_H
+
+#include <asm-generic/kprobes.h>
+
+#endif /* _RISCV_KPROBES_H */
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
new file mode 100644
index 000000000000..3fe4af8147d2
--- /dev/null
+++ b/arch/riscv/include/asm/processor.h
@@ -0,0 +1,97 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PROCESSOR_H
+#define _ASM_RISCV_PROCESSOR_H
+
+#include <linux/const.h>
+
+#include <asm/ptrace.h>
+
+/*
+ * This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE >> 1)
+
+#define STACK_TOP TASK_SIZE
+#define STACK_TOP_MAX STACK_TOP
+#define STACK_ALIGN 16
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+struct pt_regs;
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ __label__ _l; _l: &&_l; })
+
+/* CPU-specific state of a task */
+struct thread_struct {
+ /* Callee-saved registers */
+ unsigned long ra;
+ unsigned long sp; /* Kernel mode stack */
+ unsigned long s[12]; /* s[0]: frame pointer */
+ struct __riscv_d_ext_state fstate;
+};
+
+#define INIT_THREAD { \
+ .sp = sizeof(init_stack) + (long)&init_stack, \
+}
+
+#define task_pt_regs(tsk) \
+ ((struct pt_regs *)(task_stack_page(tsk) + THREAD_SIZE \
+ - ALIGN(sizeof(struct pt_regs), STACK_ALIGN)))
+
+#define KSTK_EIP(tsk) (task_pt_regs(tsk)->sepc)
+#define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp)
+
+
+/* Do necessary setup to start up a newly executed thread. */
+extern void start_thread(struct pt_regs *regs,
+ unsigned long pc, unsigned long sp);
+
+/* Free all resources held by a thread. */
+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");
+}
+
+struct device_node;
+extern int riscv_of_processor_hart(struct device_node *node);
+
+extern void riscv_fill_hwcap(void);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
new file mode 100644
index 000000000000..dd6b05bff75b
--- /dev/null
+++ b/arch/riscv/include/asm/switch_to.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SWITCH_TO_H
+#define _ASM_RISCV_SWITCH_TO_H
+
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/csr.h>
+
+extern void __fstate_save(struct task_struct *save_to);
+extern void __fstate_restore(struct task_struct *restore_from);
+
+static inline void __fstate_clean(struct pt_regs *regs)
+{
+ regs->sstatus |= (regs->sstatus & ~(SR_FS)) | SR_FS_CLEAN;
+}
+
+static inline void fstate_save(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ if ((regs->sstatus & SR_FS) == SR_FS_DIRTY) {
+ __fstate_save(task);
+ __fstate_clean(regs);
+ }
+}
+
+static inline void fstate_restore(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ if ((regs->sstatus & SR_FS) != SR_FS_OFF) {
+ __fstate_restore(task);
+ __fstate_clean(regs);
+ }
+}
+
+static inline void __switch_to_aux(struct task_struct *prev,
+ struct task_struct *next)
+{
+ struct pt_regs *regs;
+
+ regs = task_pt_regs(prev);
+ if (unlikely(regs->sstatus & SR_SD))
+ fstate_save(prev, regs);
+ fstate_restore(next, task_pt_regs(next));
+}
+
+extern struct task_struct *__switch_to(struct task_struct *,
+ struct task_struct *);
+
+#define switch_to(prev, next, last) \
+do { \
+ struct task_struct *__prev = (prev); \
+ struct task_struct *__next = (next); \
+ __switch_to_aux(__prev, __next); \
+ ((last) = __switch_to(__prev, __next)); \
+} while (0)
+
+#endif /* _ASM_RISCV_SWITCH_TO_H */
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
new file mode 100644
index 000000000000..ad13bea17b5d
--- /dev/null
+++ b/arch/riscv/include/asm/thread_info.h
@@ -0,0 +1,93 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_THREAD_INFO_H
+#define _ASM_RISCV_THREAD_INFO_H
+
+#include <asm/page.h>
+#include <linux/const.h>
+
+/* thread information allocation */
+#define THREAD_SIZE_ORDER (1)
+#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/processor.h>
+#include <asm/csr.h>
+
+typedef unsigned long mm_segment_t;
+
+/*
+ * low level task data that entry.S needs immediate access to
+ * - this struct should fit entirely inside of one cache line
+ * - if the members of this struct changes, the assembly constants
+ * in asm-offsets.c must be updated accordingly
+ * - thread_info is included in task_struct at an offset of 0. This means that
+ * tp points to both thread_info and task_struct.
+ */
+struct thread_info {
+ unsigned long flags; /* low level flags */
+ int preempt_count; /* 0=>preemptible, <0=>BUG */
+ mm_segment_t addr_limit;
+ /*
+ * These stack pointers are overwritten on every system call or
+ * exception. SP is also saved to the stack it can be recovered when
+ * overwritten.
+ */
+ long kernel_sp; /* Kernel stack pointer */
+ long user_sp; /* User stack pointer */
+};
+
+/*
+ * macros/functions for gaining access to the thread information structure
+ *
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#define INIT_THREAD_INFO(tsk) \
+{ \
+ .flags = 0, \
+ .preempt_count = INIT_PREEMPT_COUNT, \
+ .addr_limit = KERNEL_DS, \
+}
+
+#define init_stack (init_thread_union.stack)
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * thread information flags
+ * - these are process state flags that various assembly files may need to
+ * access
+ * - pending work-to-be-done flags are in lowest half-word
+ * - other flags in upper half-word(s)
+ */
+#define TIF_SYSCALL_TRACE 0 /* syscall trace active */
+#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */
+#define TIF_SIGPENDING 2 /* signal pending */
+#define TIF_NEED_RESCHED 3 /* rescheduling necessary */
+#define TIF_RESTORE_SIGMASK 4 /* restore signal mask in do_signal() */
+#define TIF_MEMDIE 5 /* is terminating due to OOM killer */
+#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
+
+#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
+#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
+#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
+
+#define _TIF_WORK_MASK \
+ (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED)
+
+#endif /* _ASM_RISCV_THREAD_INFO_H */
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
new file mode 100644
index 000000000000..3dc7f9d52cb1
--- /dev/null
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -0,0 +1,318 @@
+/*
+ * 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/kbuild.h>
+#include <linux/sched.h>
+#include <asm/thread_info.h>
+#include <asm/ptrace.h>
+
+void asm_offsets(void)
+{
+ OFFSET(TASK_THREAD_RA, task_struct, thread.ra);
+ OFFSET(TASK_THREAD_SP, task_struct, thread.sp);
+ OFFSET(TASK_THREAD_S0, task_struct, thread.s[0]);
+ OFFSET(TASK_THREAD_S1, task_struct, thread.s[1]);
+ OFFSET(TASK_THREAD_S2, task_struct, thread.s[2]);
+ OFFSET(TASK_THREAD_S3, task_struct, thread.s[3]);
+ OFFSET(TASK_THREAD_S4, task_struct, thread.s[4]);
+ OFFSET(TASK_THREAD_S5, task_struct, thread.s[5]);
+ OFFSET(TASK_THREAD_S6, task_struct, thread.s[6]);
+ OFFSET(TASK_THREAD_S7, task_struct, thread.s[7]);
+ OFFSET(TASK_THREAD_S8, task_struct, thread.s[8]);
+ OFFSET(TASK_THREAD_S9, task_struct, thread.s[9]);
+ OFFSET(TASK_THREAD_S10, task_struct, thread.s[10]);
+ OFFSET(TASK_THREAD_S11, task_struct, thread.s[11]);
+ OFFSET(TASK_THREAD_SP, task_struct, thread.sp);
+ OFFSET(TASK_STACK, task_struct, stack);
+ OFFSET(TASK_TI, task_struct, thread_info);
+ OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags);
+ OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
+ OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
+
+ OFFSET(TASK_THREAD_F0, task_struct, thread.fstate.f[0]);
+ OFFSET(TASK_THREAD_F1, task_struct, thread.fstate.f[1]);
+ OFFSET(TASK_THREAD_F2, task_struct, thread.fstate.f[2]);
+ OFFSET(TASK_THREAD_F3, task_struct, thread.fstate.f[3]);
+ OFFSET(TASK_THREAD_F4, task_struct, thread.fstate.f[4]);
+ OFFSET(TASK_THREAD_F5, task_struct, thread.fstate.f[5]);
+ OFFSET(TASK_THREAD_F6, task_struct, thread.fstate.f[6]);
+ OFFSET(TASK_THREAD_F7, task_struct, thread.fstate.f[7]);
+ OFFSET(TASK_THREAD_F8, task_struct, thread.fstate.f[8]);
+ OFFSET(TASK_THREAD_F9, task_struct, thread.fstate.f[9]);
+ OFFSET(TASK_THREAD_F10, task_struct, thread.fstate.f[10]);
+ OFFSET(TASK_THREAD_F11, task_struct, thread.fstate.f[11]);
+ OFFSET(TASK_THREAD_F12, task_struct, thread.fstate.f[12]);
+ OFFSET(TASK_THREAD_F13, task_struct, thread.fstate.f[13]);
+ OFFSET(TASK_THREAD_F14, task_struct, thread.fstate.f[14]);
+ OFFSET(TASK_THREAD_F15, task_struct, thread.fstate.f[15]);
+ OFFSET(TASK_THREAD_F16, task_struct, thread.fstate.f[16]);
+ OFFSET(TASK_THREAD_F17, task_struct, thread.fstate.f[17]);
+ OFFSET(TASK_THREAD_F18, task_struct, thread.fstate.f[18]);
+ OFFSET(TASK_THREAD_F19, task_struct, thread.fstate.f[19]);
+ OFFSET(TASK_THREAD_F20, task_struct, thread.fstate.f[20]);
+ OFFSET(TASK_THREAD_F21, task_struct, thread.fstate.f[21]);
+ OFFSET(TASK_THREAD_F22, task_struct, thread.fstate.f[22]);
+ OFFSET(TASK_THREAD_F23, task_struct, thread.fstate.f[23]);
+ OFFSET(TASK_THREAD_F24, task_struct, thread.fstate.f[24]);
+ OFFSET(TASK_THREAD_F25, task_struct, thread.fstate.f[25]);
+ OFFSET(TASK_THREAD_F26, task_struct, thread.fstate.f[26]);
+ OFFSET(TASK_THREAD_F27, task_struct, thread.fstate.f[27]);
+ OFFSET(TASK_THREAD_F28, task_struct, thread.fstate.f[28]);
+ OFFSET(TASK_THREAD_F29, task_struct, thread.fstate.f[29]);
+ OFFSET(TASK_THREAD_F30, task_struct, thread.fstate.f[30]);
+ OFFSET(TASK_THREAD_F31, task_struct, thread.fstate.f[31]);
+ OFFSET(TASK_THREAD_FCSR, task_struct, thread.fstate.fcsr);
+
+ DEFINE(PT_SIZE, sizeof(struct pt_regs));
+ OFFSET(PT_SEPC, pt_regs, sepc);
+ OFFSET(PT_RA, pt_regs, ra);
+ OFFSET(PT_FP, pt_regs, s0);
+ OFFSET(PT_S0, pt_regs, s0);
+ OFFSET(PT_S1, pt_regs, s1);
+ OFFSET(PT_S2, pt_regs, s2);
+ OFFSET(PT_S3, pt_regs, s3);
+ OFFSET(PT_S4, pt_regs, s4);
+ OFFSET(PT_S5, pt_regs, s5);
+ OFFSET(PT_S6, pt_regs, s6);
+ OFFSET(PT_S7, pt_regs, s7);
+ OFFSET(PT_S8, pt_regs, s8);
+ OFFSET(PT_S9, pt_regs, s9);
+ OFFSET(PT_S10, pt_regs, s10);
+ OFFSET(PT_S11, pt_regs, s11);
+ OFFSET(PT_SP, pt_regs, sp);
+ OFFSET(PT_TP, pt_regs, tp);
+ OFFSET(PT_A0, pt_regs, a0);
+ OFFSET(PT_A1, pt_regs, a1);
+ OFFSET(PT_A2, pt_regs, a2);
+ OFFSET(PT_A3, pt_regs, a3);
+ OFFSET(PT_A4, pt_regs, a4);
+ OFFSET(PT_A5, pt_regs, a5);
+ OFFSET(PT_A6, pt_regs, a6);
+ OFFSET(PT_A7, pt_regs, a7);
+ OFFSET(PT_T0, pt_regs, t0);
+ OFFSET(PT_T1, pt_regs, t1);
+ OFFSET(PT_T2, pt_regs, t2);
+ OFFSET(PT_T3, pt_regs, t3);
+ OFFSET(PT_T4, pt_regs, t4);
+ OFFSET(PT_T5, pt_regs, t5);
+ OFFSET(PT_T6, pt_regs, t6);
+ OFFSET(PT_GP, pt_regs, gp);
+ OFFSET(PT_SSTATUS, pt_regs, sstatus);
+ OFFSET(PT_SBADADDR, pt_regs, sbadaddr);
+ OFFSET(PT_SCAUSE, pt_regs, scause);
+
+ /*
+ * THREAD_{F,X}* might be larger than a S-type offset can handle, but
+ * these are used in performance-sensitive assembly so we can't resort
+ * to loading the long immediate every time.
+ */
+ DEFINE(TASK_THREAD_RA_RA,
+ offsetof(struct task_struct, thread.ra)
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_SP_RA,
+ offsetof(struct task_struct, thread.sp)
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S0_RA,
+ offsetof(struct task_struct, thread.s[0])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S1_RA,
+ offsetof(struct task_struct, thread.s[1])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S2_RA,
+ offsetof(struct task_struct, thread.s[2])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S3_RA,
+ offsetof(struct task_struct, thread.s[3])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S4_RA,
+ offsetof(struct task_struct, thread.s[4])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S5_RA,
+ offsetof(struct task_struct, thread.s[5])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S6_RA,
+ offsetof(struct task_struct, thread.s[6])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S7_RA,
+ offsetof(struct task_struct, thread.s[7])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S8_RA,
+ offsetof(struct task_struct, thread.s[8])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S9_RA,
+ offsetof(struct task_struct, thread.s[9])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S10_RA,
+ offsetof(struct task_struct, thread.s[10])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S11_RA,
+ offsetof(struct task_struct, thread.s[11])
+ - offsetof(struct task_struct, thread.ra)
+ );
+
+ DEFINE(TASK_THREAD_F0_F0,
+ offsetof(struct task_struct, thread.fstate.f[0])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F1_F0,
+ offsetof(struct task_struct, thread.fstate.f[1])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F2_F0,
+ offsetof(struct task_struct, thread.fstate.f[2])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F3_F0,
+ offsetof(struct task_struct, thread.fstate.f[3])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F4_F0,
+ offsetof(struct task_struct, thread.fstate.f[4])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F5_F0,
+ offsetof(struct task_struct, thread.fstate.f[5])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F6_F0,
+ offsetof(struct task_struct, thread.fstate.f[6])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F7_F0,
+ offsetof(struct task_struct, thread.fstate.f[7])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F8_F0,
+ offsetof(struct task_struct, thread.fstate.f[8])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F9_F0,
+ offsetof(struct task_struct, thread.fstate.f[9])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F10_F0,
+ offsetof(struct task_struct, thread.fstate.f[10])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F11_F0,
+ offsetof(struct task_struct, thread.fstate.f[11])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F12_F0,
+ offsetof(struct task_struct, thread.fstate.f[12])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F13_F0,
+ offsetof(struct task_struct, thread.fstate.f[13])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F14_F0,
+ offsetof(struct task_struct, thread.fstate.f[14])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F15_F0,
+ offsetof(struct task_struct, thread.fstate.f[15])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F16_F0,
+ offsetof(struct task_struct, thread.fstate.f[16])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F17_F0,
+ offsetof(struct task_struct, thread.fstate.f[17])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F18_F0,
+ offsetof(struct task_struct, thread.fstate.f[18])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F19_F0,
+ offsetof(struct task_struct, thread.fstate.f[19])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F20_F0,
+ offsetof(struct task_struct, thread.fstate.f[20])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F21_F0,
+ offsetof(struct task_struct, thread.fstate.f[21])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F22_F0,
+ offsetof(struct task_struct, thread.fstate.f[22])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F23_F0,
+ offsetof(struct task_struct, thread.fstate.f[23])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F24_F0,
+ offsetof(struct task_struct, thread.fstate.f[24])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F25_F0,
+ offsetof(struct task_struct, thread.fstate.f[25])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F26_F0,
+ offsetof(struct task_struct, thread.fstate.f[26])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F27_F0,
+ offsetof(struct task_struct, thread.fstate.f[27])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F28_F0,
+ offsetof(struct task_struct, thread.fstate.f[28])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F29_F0,
+ offsetof(struct task_struct, thread.fstate.f[29])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F30_F0,
+ offsetof(struct task_struct, thread.fstate.f[30])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F31_F0,
+ offsetof(struct task_struct, thread.fstate.f[31])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_FCSR_F0,
+ offsetof(struct task_struct, thread.fstate.fcsr)
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+
+ /* The assembler needs access to THREAD_SIZE as well. */
+ DEFINE(ASM_THREAD_SIZE, THREAD_SIZE);
+
+ /*
+ * We allocate a pt_regs on the stack when entering the kernel. This
+ * ensures the alignment is sane.
+ */
+ DEFINE(PT_SIZE_ON_STACK, ALIGN(sizeof(struct pt_regs), STACK_ALIGN));
+}
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
new file mode 100644
index 000000000000..7208fcec0cf4
--- /dev/null
+++ b/arch/riscv/kernel/entry.S
@@ -0,0 +1,450 @@
+/*
+ * 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/init.h>
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+
+ .text
+ .altmacro
+
+/*
+ * Prepares to enter a system call or exception by saving all registers to the
+ * stack.
+ */
+ .macro SAVE_ALL
+ LOCAL _restore_kernel_tpsp
+ LOCAL _save_context
+
+ /*
+ * If coming from userspace, preserve the user thread pointer and load
+ * the kernel thread pointer. If we came from the kernel, sscratch
+ * will contain 0, and we should continue on the current TP.
+ */
+ csrrw tp, sscratch, tp
+ bnez tp, _save_context
+
+_restore_kernel_tpsp:
+ csrr tp, sscratch
+ REG_S sp, TASK_TI_KERNEL_SP(tp)
+_save_context:
+ REG_S sp, TASK_TI_USER_SP(tp)
+ REG_L sp, TASK_TI_KERNEL_SP(tp)
+ addi sp, sp, -(PT_SIZE_ON_STACK)
+ REG_S x1, PT_RA(sp)
+ REG_S x3, PT_GP(sp)
+ REG_S x5, PT_T0(sp)
+ REG_S x6, PT_T1(sp)
+ REG_S x7, PT_T2(sp)
+ REG_S x8, PT_S0(sp)
+ REG_S x9, PT_S1(sp)
+ REG_S x10, PT_A0(sp)
+ REG_S x11, PT_A1(sp)
+ REG_S x12, PT_A2(sp)
+ REG_S x13, PT_A3(sp)
+ REG_S x14, PT_A4(sp)
+ REG_S x15, PT_A5(sp)
+ REG_S x16, PT_A6(sp)
+ REG_S x17, PT_A7(sp)
+ REG_S x18, PT_S2(sp)
+ REG_S x19, PT_S3(sp)
+ REG_S x20, PT_S4(sp)
+ REG_S x21, PT_S5(sp)
+ REG_S x22, PT_S6(sp)
+ REG_S x23, PT_S7(sp)
+ REG_S x24, PT_S8(sp)
+ REG_S x25, PT_S9(sp)
+ REG_S x26, PT_S10(sp)
+ REG_S x27, PT_S11(sp)
+ REG_S x28, PT_T3(sp)
+ REG_S x29, PT_T4(sp)
+ REG_S x30, PT_T5(sp)
+ REG_S x31, PT_T6(sp)
+
+ /*
+ * Disable FPU to detect illegal usage of
+ * floating point in kernel space
+ */
+ li t0, SR_FS
+
+ REG_L s0, TASK_TI_USER_SP(tp)
+ csrrc s1, sstatus, t0
+ csrr s2, sepc
+ csrr s3, sbadaddr
+ csrr s4, scause
+ csrr s5, sscratch
+ REG_S s0, PT_SP(sp)
+ REG_S s1, PT_SSTATUS(sp)
+ REG_S s2, PT_SEPC(sp)
+ REG_S s3, PT_SBADADDR(sp)
+ REG_S s4, PT_SCAUSE(sp)
+ REG_S s5, PT_TP(sp)
+ .endm
+
+/*
+ * Prepares to return from a system call or exception by restoring all
+ * registers from the stack.
+ */
+ .macro RESTORE_ALL
+ REG_L a0, PT_SSTATUS(sp)
+ REG_L a2, PT_SEPC(sp)
+ csrw sstatus, a0
+ csrw sepc, a2
+
+ REG_L x1, PT_RA(sp)
+ REG_L x3, PT_GP(sp)
+ REG_L x4, PT_TP(sp)
+ REG_L x5, PT_T0(sp)
+ REG_L x6, PT_T1(sp)
+ REG_L x7, PT_T2(sp)
+ REG_L x8, PT_S0(sp)
+ REG_L x9, PT_S1(sp)
+ REG_L x10, PT_A0(sp)
+ REG_L x11, PT_A1(sp)
+ REG_L x12, PT_A2(sp)
+ REG_L x13, PT_A3(sp)
+ REG_L x14, PT_A4(sp)
+ REG_L x15, PT_A5(sp)
+ REG_L x16, PT_A6(sp)
+ REG_L x17, PT_A7(sp)
+ REG_L x18, PT_S2(sp)
+ REG_L x19, PT_S3(sp)
+ REG_L x20, PT_S4(sp)
+ REG_L x21, PT_S5(sp)
+ REG_L x22, PT_S6(sp)
+ REG_L x23, PT_S7(sp)
+ REG_L x24, PT_S8(sp)
+ REG_L x25, PT_S9(sp)
+ REG_L x26, PT_S10(sp)
+ REG_L x27, PT_S11(sp)
+ REG_L x28, PT_T3(sp)
+ REG_L x29, PT_T4(sp)
+ REG_L x30, PT_T5(sp)
+ REG_L x31, PT_T6(sp)
+
+ REG_L x2, PT_SP(sp)
+ .endm
+
+ENTRY(handle_exception)
+ SAVE_ALL
+
+ /*
+ * Set sscratch register to 0, so that if a recursive exception
+ * occurs, the exception vector knows it came from the kernel
+ */
+ csrw sscratch, x0
+
+ la gp, __global_pointer$
+
+ la ra, ret_from_exception
+ /*
+ * MSB of cause differentiates between
+ * interrupts and exceptions
+ */
+ bge s4, zero, 1f
+
+ /* Handle interrupts */
+ slli a0, s4, 1
+ srli a0, a0, 1
+ move a1, sp /* pt_regs */
+ tail do_IRQ
+1:
+ /* Handle syscalls */
+ li t0, EXC_SYSCALL
+ beq s4, t0, handle_syscall
+
+ /* Handle other exceptions */
+ slli t0, s4, RISCV_LGPTR
+ la t1, excp_vect_table
+ la t2, excp_vect_table_end
+ move a0, sp /* pt_regs */
+ add t0, t1, t0
+ /* Check if exception code lies within bounds */
+ bgeu t0, t2, 1f
+ REG_L t0, 0(t0)
+ jr t0
+1:
+ tail do_trap_unknown
+
+handle_syscall:
+ /*
+ * Advance SEPC to avoid executing the original
+ * scall instruction on sret
+ */
+ addi s2, s2, 0x4
+ REG_S s2, PT_SEPC(sp)
+ /* System calls run with interrupts enabled */
+ csrs sstatus, SR_IE
+ /* Trace syscalls, but only if requested by the user. */
+ REG_L t0, TASK_TI_FLAGS(tp)
+ andi t0, t0, _TIF_SYSCALL_TRACE
+ bnez t0, handle_syscall_trace_enter
+check_syscall_nr:
+ /* Check to make sure we don't jump to a bogus syscall number. */
+ li t0, __NR_syscalls
+ la s0, sys_ni_syscall
+ /* Syscall number held in a7 */
+ bgeu a7, t0, 1f
+ la s0, sys_call_table
+ slli t0, a7, RISCV_LGPTR
+ add s0, s0, t0
+ REG_L s0, 0(s0)
+1:
+ jalr s0
+
+ret_from_syscall:
+ /* Set user a0 to kernel a0 */
+ REG_S a0, PT_A0(sp)
+ /* Trace syscalls, but only if requested by the user. */
+ REG_L t0, TASK_TI_FLAGS(tp)
+ andi t0, t0, _TIF_SYSCALL_TRACE
+ bnez t0, handle_syscall_trace_exit
+
+ret_from_exception:
+ REG_L s0, PT_SSTATUS(sp)
+ csrc sstatus, SR_IE
+ andi s0, s0, SR_PS
+ bnez s0, restore_all
+
+resume_userspace:
+ /* Interrupts must be disabled here so flags are checked atomically */
+ REG_L s0, TASK_TI_FLAGS(tp) /* current_thread_info->flags */
+ andi s1, s0, _TIF_WORK_MASK
+ bnez s1, work_pending
+
+ /* Save unwound kernel stack pointer in thread_info */
+ addi s0, sp, PT_SIZE_ON_STACK
+ REG_S s0, TASK_TI_KERNEL_SP(tp)
+
+ /*
+ * Save TP into sscratch, so we can find the kernel data structures
+ * again.
+ */
+ csrw sscratch, tp
+
+restore_all:
+ RESTORE_ALL
+ sret
+
+work_pending:
+ /* Enter slow path for supplementary processing */
+ la ra, ret_from_exception
+ andi s1, s0, _TIF_NEED_RESCHED
+ bnez s1, work_resched
+work_notifysig:
+ /* Handle pending signals and notify-resume requests */
+ csrs sstatus, SR_IE /* Enable interrupts for do_notify_resume() */
+ move a0, sp /* pt_regs */
+ move a1, s0 /* current_thread_info->flags */
+ tail do_notify_resume
+work_resched:
+ tail schedule
+
+/* Slow paths for ptrace. */
+handle_syscall_trace_enter:
+ move a0, sp
+ call do_syscall_trace_enter
+ REG_L a0, PT_A0(sp)
+ REG_L a1, PT_A1(sp)
+ REG_L a2, PT_A2(sp)
+ REG_L a3, PT_A3(sp)
+ REG_L a4, PT_A4(sp)
+ REG_L a5, PT_A5(sp)
+ REG_L a6, PT_A6(sp)
+ REG_L a7, PT_A7(sp)
+ j check_syscall_nr
+handle_syscall_trace_exit:
+ move a0, sp
+ call do_syscall_trace_exit
+ j ret_from_exception
+
+END(handle_exception)
+
+ENTRY(ret_from_fork)
+ la ra, ret_from_exception
+ tail schedule_tail
+ENDPROC(ret_from_fork)
+
+ENTRY(ret_from_kernel_thread)
+ call schedule_tail
+ /* Call fn(arg) */
+ la ra, ret_from_exception
+ move a0, s1
+ jr s0
+ENDPROC(ret_from_kernel_thread)
+
+
+/*
+ * Integer register context switch
+ * The callee-saved registers must be saved and restored.
+ *
+ * a0: previous task_struct (must be preserved across the switch)
+ * a1: next task_struct
+ */
+ENTRY(__switch_to)
+ /* Save context into prev->thread */
+ li a2, TASK_THREAD_RA
+ add a0, a0, a2
+ add a2, a1, a2
+ REG_S ra, TASK_THREAD_RA_RA(a0)
+ REG_S sp, TASK_THREAD_SP_RA(a0)
+ REG_S s0, TASK_THREAD_S0_RA(a0)
+ REG_S s1, TASK_THREAD_S1_RA(a0)
+ REG_S s2, TASK_THREAD_S2_RA(a0)
+ REG_S s3, TASK_THREAD_S3_RA(a0)
+ REG_S s4, TASK_THREAD_S4_RA(a0)
+ REG_S s5, TASK_THREAD_S5_RA(a0)
+ REG_S s6, TASK_THREAD_S6_RA(a0)
+ REG_S s7, TASK_THREAD_S7_RA(a0)
+ REG_S s8, TASK_THREAD_S8_RA(a0)
+ REG_S s9, TASK_THREAD_S9_RA(a0)
+ REG_S s10, TASK_THREAD_S10_RA(a0)
+ REG_S s11, TASK_THREAD_S11_RA(a0)
+ /* Restore context from next->thread */
+ REG_L ra, TASK_THREAD_RA_RA(a2)
+ REG_L sp, TASK_THREAD_SP_RA(a2)
+ REG_L s0, TASK_THREAD_S0_RA(a2)
+ REG_L s1, TASK_THREAD_S1_RA(a2)
+ REG_L s2, TASK_THREAD_S2_RA(a2)
+ REG_L s3, TASK_THREAD_S3_RA(a2)
+ REG_L s4, TASK_THREAD_S4_RA(a2)
+ REG_L s5, TASK_THREAD_S5_RA(a2)
+ REG_L s6, TASK_THREAD_S6_RA(a2)
+ REG_L s7, TASK_THREAD_S7_RA(a2)
+ REG_L s8, TASK_THREAD_S8_RA(a2)
+ REG_L s9, TASK_THREAD_S9_RA(a2)
+ REG_L s10, TASK_THREAD_S10_RA(a2)
+ REG_L s11, TASK_THREAD_S11_RA(a2)
+#if TASK_TI != 0
+#error "TASK_TI != 0: tp will contain a 'struct thread_info', not a 'struct task_struct' so get_current() won't work."
+ addi tp, a1, TASK_TI
+#else
+ move tp, a1
+#endif
+ 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)
+ RISCV_PTR do_trap_insn_misaligned
+ RISCV_PTR do_trap_insn_fault
+ RISCV_PTR do_trap_insn_illegal
+ RISCV_PTR do_trap_break
+ RISCV_PTR do_trap_load_misaligned
+ RISCV_PTR do_trap_load_fault
+ RISCV_PTR do_trap_store_misaligned
+ RISCV_PTR do_trap_store_fault
+ RISCV_PTR do_trap_ecall_u /* system call, gets intercepted */
+ RISCV_PTR do_trap_ecall_s
+ RISCV_PTR do_trap_unknown
+ RISCV_PTR do_trap_ecall_m
+ RISCV_PTR do_page_fault /* instruction page fault */
+ RISCV_PTR do_page_fault /* load page fault */
+ RISCV_PTR do_trap_unknown
+ RISCV_PTR do_page_fault /* store page fault */
+excp_vect_table_end:
+END(excp_vect_table)
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
new file mode 100644
index 000000000000..7d539d64bf1a
--- /dev/null
+++ b/arch/riscv/kernel/process.c
@@ -0,0 +1,132 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/tick.h>
+#include <linux/ptrace.h>
+
+#include <asm/unistd.h>
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+#include <asm/csr.h>
+#include <asm/string.h>
+#include <asm/switch_to.h>
+
+extern asmlinkage void ret_from_fork(void);
+extern asmlinkage void ret_from_kernel_thread(void);
+
+void arch_cpu_idle(void)
+{
+ wait_for_interrupt();
+ local_irq_enable();
+}
+
+void show_regs(struct pt_regs *regs)
+{
+ show_regs_print_info(KERN_DEFAULT);
+
+ pr_cont("sepc: " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n",
+ regs->sepc, regs->ra, regs->sp);
+ pr_cont(" gp : " REG_FMT " tp : " REG_FMT " t0 : " REG_FMT "\n",
+ regs->gp, regs->tp, regs->t0);
+ pr_cont(" t1 : " REG_FMT " t2 : " REG_FMT " s0 : " REG_FMT "\n",
+ regs->t1, regs->t2, regs->s0);
+ pr_cont(" s1 : " REG_FMT " a0 : " REG_FMT " a1 : " REG_FMT "\n",
+ regs->s1, regs->a0, regs->a1);
+ pr_cont(" a2 : " REG_FMT " a3 : " REG_FMT " a4 : " REG_FMT "\n",
+ regs->a2, regs->a3, regs->a4);
+ pr_cont(" a5 : " REG_FMT " a6 : " REG_FMT " a7 : " REG_FMT "\n",
+ regs->a5, regs->a6, regs->a7);
+ pr_cont(" s2 : " REG_FMT " s3 : " REG_FMT " s4 : " REG_FMT "\n",
+ regs->s2, regs->s3, regs->s4);
+ pr_cont(" s5 : " REG_FMT " s6 : " REG_FMT " s7 : " REG_FMT "\n",
+ regs->s5, regs->s6, regs->s7);
+ pr_cont(" s8 : " REG_FMT " s9 : " REG_FMT " s10: " REG_FMT "\n",
+ regs->s8, regs->s9, regs->s10);
+ pr_cont(" s11: " REG_FMT " t3 : " REG_FMT " t4 : " REG_FMT "\n",
+ regs->s11, regs->t3, regs->t4);
+ pr_cont(" t5 : " REG_FMT " t6 : " REG_FMT "\n",
+ regs->t5, regs->t6);
+
+ pr_cont("sstatus: " REG_FMT " sbadaddr: " REG_FMT " scause: " REG_FMT "\n",
+ regs->sstatus, regs->sbadaddr, regs->scause);
+}
+
+void start_thread(struct pt_regs *regs, unsigned long pc,
+ unsigned long sp)
+{
+ regs->sstatus = SR_PIE /* User mode, irqs on */ | SR_FS_INITIAL;
+#ifndef CONFIG_RV_PUM
+ regs->sstatus |= SR_SUM;
+#endif
+ regs->sepc = pc;
+ regs->sp = sp;
+ set_fs(USER_DS);
+}
+
+void flush_thread(void)
+{
+ /*
+ * Reset FPU context
+ * frm: round to nearest, ties to even (IEEE default)
+ * fflags: accrued exceptions cleared
+ */
+ memset(¤t->thread.fstate, 0, sizeof(current->thread.fstate));
+}
+
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+ fstate_save(src, task_pt_regs(src));
+ *dst = *src;
+ return 0;
+}
+
+int copy_thread(unsigned long clone_flags, unsigned long usp,
+ unsigned long arg, struct task_struct *p)
+{
+ struct pt_regs *childregs = task_pt_regs(p);
+
+ /* p->thread holds context to be restored by __switch_to() */
+ if (unlikely(p->flags & PF_KTHREAD)) {
+ /* Kernel thread */
+ const register unsigned long gp __asm__ ("gp");
+ memset(childregs, 0, sizeof(struct pt_regs));
+ childregs->gp = gp;
+ childregs->sstatus = SR_PS | SR_PIE; /* Supervisor, irqs on */
+
+ p->thread.ra = (unsigned long)ret_from_kernel_thread;
+ p->thread.s[0] = usp; /* fn */
+ p->thread.s[1] = arg;
+ } else {
+ *childregs = *(current_pt_regs());
+ if (usp) /* User fork */
+ childregs->sp = usp;
+ if (clone_flags & CLONE_SETTLS)
+ childregs->tp = childregs->a5;
+ childregs->a0 = 0; /* Return value of fork() */
+ p->thread.ra = (unsigned long)ret_from_fork;
+ }
+ p->thread.sp = (unsigned long)childregs; /* kernel sp */
+ return 0;
+}
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread
* [PATCH 5/9] RISC-V: Task implementation
2017-07-04 19:50 ` Palmer Dabbelt
` (7 preceding siblings ...)
(?)
@ 2017-07-04 19:50 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains the implementation of tasks on RISC-V, most of which
is involved in task switching.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/asm-offsets.h | 1 +
arch/riscv/include/asm/current.h | 44 ++++
arch/riscv/include/asm/kprobes.h | 22 ++
arch/riscv/include/asm/processor.h | 97 ++++++++
arch/riscv/include/asm/switch_to.h | 69 ++++++
arch/riscv/include/asm/thread_info.h | 93 ++++++++
arch/riscv/kernel/asm-offsets.c | 318 +++++++++++++++++++++++++
arch/riscv/kernel/entry.S | 450 +++++++++++++++++++++++++++++++++++
arch/riscv/kernel/process.c | 132 ++++++++++
9 files changed, 1226 insertions(+)
create mode 100644 arch/riscv/include/asm/asm-offsets.h
create mode 100644 arch/riscv/include/asm/current.h
create mode 100644 arch/riscv/include/asm/kprobes.h
create mode 100644 arch/riscv/include/asm/processor.h
create mode 100644 arch/riscv/include/asm/switch_to.h
create mode 100644 arch/riscv/include/asm/thread_info.h
create mode 100644 arch/riscv/kernel/asm-offsets.c
create mode 100644 arch/riscv/kernel/entry.S
create mode 100644 arch/riscv/kernel/process.c
diff --git a/arch/riscv/include/asm/asm-offsets.h b/arch/riscv/include/asm/asm-offsets.h
new file mode 100644
index 000000000000..d370ee36a182
--- /dev/null
+++ b/arch/riscv/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/riscv/include/asm/current.h b/arch/riscv/include/asm/current.h
new file mode 100644
index 000000000000..353a7c9f3c9e
--- /dev/null
+++ b/arch/riscv/include/asm/current.h
@@ -0,0 +1,44 @@
+/*
+ * Based on arm/arm64/include/asm/current.h
+ *
+ * Copyright (C) 2016 ARM
+ * 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.
+ */
+
+
+#ifndef __ASM_CURRENT_H
+#define __ASM_CURRENT_H
+
+#include <linux/compiler.h>
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+/*
+ * This only works because "struct thread_info" is at offset 0 from "struct
+ * task_struct". This constraint seems to be necessary on other architectures
+ * as well, but __switch_to enforces it. We can't check TASK_TI here because
+ * <asm/asm-offsets.h> includes this, and I can't get the definition of "struct
+ * task_struct" here due to some header ordering problems.
+ */
+static __always_inline struct task_struct *get_current(void)
+{
+ register struct task_struct *tp __asm__("tp");
+ return tp;
+}
+
+#define current get_current()
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_CURRENT_H */
diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h
new file mode 100644
index 000000000000..c7eb010d1528
--- /dev/null
+++ b/arch/riscv/include/asm/kprobes.h
@@ -0,0 +1,22 @@
+/*
+ * Copied from arch/arm64/include/asm/kprobes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ */
+
+#ifndef _RISCV_KPROBES_H
+#define _RISCV_KPROBES_H
+
+#include <asm-generic/kprobes.h>
+
+#endif /* _RISCV_KPROBES_H */
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
new file mode 100644
index 000000000000..3fe4af8147d2
--- /dev/null
+++ b/arch/riscv/include/asm/processor.h
@@ -0,0 +1,97 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PROCESSOR_H
+#define _ASM_RISCV_PROCESSOR_H
+
+#include <linux/const.h>
+
+#include <asm/ptrace.h>
+
+/*
+ * This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE >> 1)
+
+#define STACK_TOP TASK_SIZE
+#define STACK_TOP_MAX STACK_TOP
+#define STACK_ALIGN 16
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+struct pt_regs;
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ __label__ _l; _l: &&_l; })
+
+/* CPU-specific state of a task */
+struct thread_struct {
+ /* Callee-saved registers */
+ unsigned long ra;
+ unsigned long sp; /* Kernel mode stack */
+ unsigned long s[12]; /* s[0]: frame pointer */
+ struct __riscv_d_ext_state fstate;
+};
+
+#define INIT_THREAD { \
+ .sp = sizeof(init_stack) + (long)&init_stack, \
+}
+
+#define task_pt_regs(tsk) \
+ ((struct pt_regs *)(task_stack_page(tsk) + THREAD_SIZE \
+ - ALIGN(sizeof(struct pt_regs), STACK_ALIGN)))
+
+#define KSTK_EIP(tsk) (task_pt_regs(tsk)->sepc)
+#define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp)
+
+
+/* Do necessary setup to start up a newly executed thread. */
+extern void start_thread(struct pt_regs *regs,
+ unsigned long pc, unsigned long sp);
+
+/* Free all resources held by a thread. */
+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");
+}
+
+struct device_node;
+extern int riscv_of_processor_hart(struct device_node *node);
+
+extern void riscv_fill_hwcap(void);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
new file mode 100644
index 000000000000..dd6b05bff75b
--- /dev/null
+++ b/arch/riscv/include/asm/switch_to.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SWITCH_TO_H
+#define _ASM_RISCV_SWITCH_TO_H
+
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/csr.h>
+
+extern void __fstate_save(struct task_struct *save_to);
+extern void __fstate_restore(struct task_struct *restore_from);
+
+static inline void __fstate_clean(struct pt_regs *regs)
+{
+ regs->sstatus |= (regs->sstatus & ~(SR_FS)) | SR_FS_CLEAN;
+}
+
+static inline void fstate_save(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ if ((regs->sstatus & SR_FS) == SR_FS_DIRTY) {
+ __fstate_save(task);
+ __fstate_clean(regs);
+ }
+}
+
+static inline void fstate_restore(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ if ((regs->sstatus & SR_FS) != SR_FS_OFF) {
+ __fstate_restore(task);
+ __fstate_clean(regs);
+ }
+}
+
+static inline void __switch_to_aux(struct task_struct *prev,
+ struct task_struct *next)
+{
+ struct pt_regs *regs;
+
+ regs = task_pt_regs(prev);
+ if (unlikely(regs->sstatus & SR_SD))
+ fstate_save(prev, regs);
+ fstate_restore(next, task_pt_regs(next));
+}
+
+extern struct task_struct *__switch_to(struct task_struct *,
+ struct task_struct *);
+
+#define switch_to(prev, next, last) \
+do { \
+ struct task_struct *__prev = (prev); \
+ struct task_struct *__next = (next); \
+ __switch_to_aux(__prev, __next); \
+ ((last) = __switch_to(__prev, __next)); \
+} while (0)
+
+#endif /* _ASM_RISCV_SWITCH_TO_H */
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
new file mode 100644
index 000000000000..ad13bea17b5d
--- /dev/null
+++ b/arch/riscv/include/asm/thread_info.h
@@ -0,0 +1,93 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_THREAD_INFO_H
+#define _ASM_RISCV_THREAD_INFO_H
+
+#include <asm/page.h>
+#include <linux/const.h>
+
+/* thread information allocation */
+#define THREAD_SIZE_ORDER (1)
+#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/processor.h>
+#include <asm/csr.h>
+
+typedef unsigned long mm_segment_t;
+
+/*
+ * low level task data that entry.S needs immediate access to
+ * - this struct should fit entirely inside of one cache line
+ * - if the members of this struct changes, the assembly constants
+ * in asm-offsets.c must be updated accordingly
+ * - thread_info is included in task_struct at an offset of 0. This means that
+ * tp points to both thread_info and task_struct.
+ */
+struct thread_info {
+ unsigned long flags; /* low level flags */
+ int preempt_count; /* 0=>preemptible, <0=>BUG */
+ mm_segment_t addr_limit;
+ /*
+ * These stack pointers are overwritten on every system call or
+ * exception. SP is also saved to the stack it can be recovered when
+ * overwritten.
+ */
+ long kernel_sp; /* Kernel stack pointer */
+ long user_sp; /* User stack pointer */
+};
+
+/*
+ * macros/functions for gaining access to the thread information structure
+ *
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#define INIT_THREAD_INFO(tsk) \
+{ \
+ .flags = 0, \
+ .preempt_count = INIT_PREEMPT_COUNT, \
+ .addr_limit = KERNEL_DS, \
+}
+
+#define init_stack (init_thread_union.stack)
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * thread information flags
+ * - these are process state flags that various assembly files may need to
+ * access
+ * - pending work-to-be-done flags are in lowest half-word
+ * - other flags in upper half-word(s)
+ */
+#define TIF_SYSCALL_TRACE 0 /* syscall trace active */
+#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */
+#define TIF_SIGPENDING 2 /* signal pending */
+#define TIF_NEED_RESCHED 3 /* rescheduling necessary */
+#define TIF_RESTORE_SIGMASK 4 /* restore signal mask in do_signal() */
+#define TIF_MEMDIE 5 /* is terminating due to OOM killer */
+#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
+
+#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
+#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
+#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
+
+#define _TIF_WORK_MASK \
+ (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED)
+
+#endif /* _ASM_RISCV_THREAD_INFO_H */
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
new file mode 100644
index 000000000000..3dc7f9d52cb1
--- /dev/null
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -0,0 +1,318 @@
+/*
+ * 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/kbuild.h>
+#include <linux/sched.h>
+#include <asm/thread_info.h>
+#include <asm/ptrace.h>
+
+void asm_offsets(void)
+{
+ OFFSET(TASK_THREAD_RA, task_struct, thread.ra);
+ OFFSET(TASK_THREAD_SP, task_struct, thread.sp);
+ OFFSET(TASK_THREAD_S0, task_struct, thread.s[0]);
+ OFFSET(TASK_THREAD_S1, task_struct, thread.s[1]);
+ OFFSET(TASK_THREAD_S2, task_struct, thread.s[2]);
+ OFFSET(TASK_THREAD_S3, task_struct, thread.s[3]);
+ OFFSET(TASK_THREAD_S4, task_struct, thread.s[4]);
+ OFFSET(TASK_THREAD_S5, task_struct, thread.s[5]);
+ OFFSET(TASK_THREAD_S6, task_struct, thread.s[6]);
+ OFFSET(TASK_THREAD_S7, task_struct, thread.s[7]);
+ OFFSET(TASK_THREAD_S8, task_struct, thread.s[8]);
+ OFFSET(TASK_THREAD_S9, task_struct, thread.s[9]);
+ OFFSET(TASK_THREAD_S10, task_struct, thread.s[10]);
+ OFFSET(TASK_THREAD_S11, task_struct, thread.s[11]);
+ OFFSET(TASK_THREAD_SP, task_struct, thread.sp);
+ OFFSET(TASK_STACK, task_struct, stack);
+ OFFSET(TASK_TI, task_struct, thread_info);
+ OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags);
+ OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
+ OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
+
+ OFFSET(TASK_THREAD_F0, task_struct, thread.fstate.f[0]);
+ OFFSET(TASK_THREAD_F1, task_struct, thread.fstate.f[1]);
+ OFFSET(TASK_THREAD_F2, task_struct, thread.fstate.f[2]);
+ OFFSET(TASK_THREAD_F3, task_struct, thread.fstate.f[3]);
+ OFFSET(TASK_THREAD_F4, task_struct, thread.fstate.f[4]);
+ OFFSET(TASK_THREAD_F5, task_struct, thread.fstate.f[5]);
+ OFFSET(TASK_THREAD_F6, task_struct, thread.fstate.f[6]);
+ OFFSET(TASK_THREAD_F7, task_struct, thread.fstate.f[7]);
+ OFFSET(TASK_THREAD_F8, task_struct, thread.fstate.f[8]);
+ OFFSET(TASK_THREAD_F9, task_struct, thread.fstate.f[9]);
+ OFFSET(TASK_THREAD_F10, task_struct, thread.fstate.f[10]);
+ OFFSET(TASK_THREAD_F11, task_struct, thread.fstate.f[11]);
+ OFFSET(TASK_THREAD_F12, task_struct, thread.fstate.f[12]);
+ OFFSET(TASK_THREAD_F13, task_struct, thread.fstate.f[13]);
+ OFFSET(TASK_THREAD_F14, task_struct, thread.fstate.f[14]);
+ OFFSET(TASK_THREAD_F15, task_struct, thread.fstate.f[15]);
+ OFFSET(TASK_THREAD_F16, task_struct, thread.fstate.f[16]);
+ OFFSET(TASK_THREAD_F17, task_struct, thread.fstate.f[17]);
+ OFFSET(TASK_THREAD_F18, task_struct, thread.fstate.f[18]);
+ OFFSET(TASK_THREAD_F19, task_struct, thread.fstate.f[19]);
+ OFFSET(TASK_THREAD_F20, task_struct, thread.fstate.f[20]);
+ OFFSET(TASK_THREAD_F21, task_struct, thread.fstate.f[21]);
+ OFFSET(TASK_THREAD_F22, task_struct, thread.fstate.f[22]);
+ OFFSET(TASK_THREAD_F23, task_struct, thread.fstate.f[23]);
+ OFFSET(TASK_THREAD_F24, task_struct, thread.fstate.f[24]);
+ OFFSET(TASK_THREAD_F25, task_struct, thread.fstate.f[25]);
+ OFFSET(TASK_THREAD_F26, task_struct, thread.fstate.f[26]);
+ OFFSET(TASK_THREAD_F27, task_struct, thread.fstate.f[27]);
+ OFFSET(TASK_THREAD_F28, task_struct, thread.fstate.f[28]);
+ OFFSET(TASK_THREAD_F29, task_struct, thread.fstate.f[29]);
+ OFFSET(TASK_THREAD_F30, task_struct, thread.fstate.f[30]);
+ OFFSET(TASK_THREAD_F31, task_struct, thread.fstate.f[31]);
+ OFFSET(TASK_THREAD_FCSR, task_struct, thread.fstate.fcsr);
+
+ DEFINE(PT_SIZE, sizeof(struct pt_regs));
+ OFFSET(PT_SEPC, pt_regs, sepc);
+ OFFSET(PT_RA, pt_regs, ra);
+ OFFSET(PT_FP, pt_regs, s0);
+ OFFSET(PT_S0, pt_regs, s0);
+ OFFSET(PT_S1, pt_regs, s1);
+ OFFSET(PT_S2, pt_regs, s2);
+ OFFSET(PT_S3, pt_regs, s3);
+ OFFSET(PT_S4, pt_regs, s4);
+ OFFSET(PT_S5, pt_regs, s5);
+ OFFSET(PT_S6, pt_regs, s6);
+ OFFSET(PT_S7, pt_regs, s7);
+ OFFSET(PT_S8, pt_regs, s8);
+ OFFSET(PT_S9, pt_regs, s9);
+ OFFSET(PT_S10, pt_regs, s10);
+ OFFSET(PT_S11, pt_regs, s11);
+ OFFSET(PT_SP, pt_regs, sp);
+ OFFSET(PT_TP, pt_regs, tp);
+ OFFSET(PT_A0, pt_regs, a0);
+ OFFSET(PT_A1, pt_regs, a1);
+ OFFSET(PT_A2, pt_regs, a2);
+ OFFSET(PT_A3, pt_regs, a3);
+ OFFSET(PT_A4, pt_regs, a4);
+ OFFSET(PT_A5, pt_regs, a5);
+ OFFSET(PT_A6, pt_regs, a6);
+ OFFSET(PT_A7, pt_regs, a7);
+ OFFSET(PT_T0, pt_regs, t0);
+ OFFSET(PT_T1, pt_regs, t1);
+ OFFSET(PT_T2, pt_regs, t2);
+ OFFSET(PT_T3, pt_regs, t3);
+ OFFSET(PT_T4, pt_regs, t4);
+ OFFSET(PT_T5, pt_regs, t5);
+ OFFSET(PT_T6, pt_regs, t6);
+ OFFSET(PT_GP, pt_regs, gp);
+ OFFSET(PT_SSTATUS, pt_regs, sstatus);
+ OFFSET(PT_SBADADDR, pt_regs, sbadaddr);
+ OFFSET(PT_SCAUSE, pt_regs, scause);
+
+ /*
+ * THREAD_{F,X}* might be larger than a S-type offset can handle, but
+ * these are used in performance-sensitive assembly so we can't resort
+ * to loading the long immediate every time.
+ */
+ DEFINE(TASK_THREAD_RA_RA,
+ offsetof(struct task_struct, thread.ra)
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_SP_RA,
+ offsetof(struct task_struct, thread.sp)
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S0_RA,
+ offsetof(struct task_struct, thread.s[0])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S1_RA,
+ offsetof(struct task_struct, thread.s[1])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S2_RA,
+ offsetof(struct task_struct, thread.s[2])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S3_RA,
+ offsetof(struct task_struct, thread.s[3])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S4_RA,
+ offsetof(struct task_struct, thread.s[4])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S5_RA,
+ offsetof(struct task_struct, thread.s[5])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S6_RA,
+ offsetof(struct task_struct, thread.s[6])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S7_RA,
+ offsetof(struct task_struct, thread.s[7])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S8_RA,
+ offsetof(struct task_struct, thread.s[8])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S9_RA,
+ offsetof(struct task_struct, thread.s[9])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S10_RA,
+ offsetof(struct task_struct, thread.s[10])
+ - offsetof(struct task_struct, thread.ra)
+ );
+ DEFINE(TASK_THREAD_S11_RA,
+ offsetof(struct task_struct, thread.s[11])
+ - offsetof(struct task_struct, thread.ra)
+ );
+
+ DEFINE(TASK_THREAD_F0_F0,
+ offsetof(struct task_struct, thread.fstate.f[0])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F1_F0,
+ offsetof(struct task_struct, thread.fstate.f[1])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F2_F0,
+ offsetof(struct task_struct, thread.fstate.f[2])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F3_F0,
+ offsetof(struct task_struct, thread.fstate.f[3])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F4_F0,
+ offsetof(struct task_struct, thread.fstate.f[4])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F5_F0,
+ offsetof(struct task_struct, thread.fstate.f[5])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F6_F0,
+ offsetof(struct task_struct, thread.fstate.f[6])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F7_F0,
+ offsetof(struct task_struct, thread.fstate.f[7])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F8_F0,
+ offsetof(struct task_struct, thread.fstate.f[8])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F9_F0,
+ offsetof(struct task_struct, thread.fstate.f[9])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F10_F0,
+ offsetof(struct task_struct, thread.fstate.f[10])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F11_F0,
+ offsetof(struct task_struct, thread.fstate.f[11])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F12_F0,
+ offsetof(struct task_struct, thread.fstate.f[12])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F13_F0,
+ offsetof(struct task_struct, thread.fstate.f[13])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F14_F0,
+ offsetof(struct task_struct, thread.fstate.f[14])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F15_F0,
+ offsetof(struct task_struct, thread.fstate.f[15])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F16_F0,
+ offsetof(struct task_struct, thread.fstate.f[16])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F17_F0,
+ offsetof(struct task_struct, thread.fstate.f[17])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F18_F0,
+ offsetof(struct task_struct, thread.fstate.f[18])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F19_F0,
+ offsetof(struct task_struct, thread.fstate.f[19])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F20_F0,
+ offsetof(struct task_struct, thread.fstate.f[20])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F21_F0,
+ offsetof(struct task_struct, thread.fstate.f[21])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F22_F0,
+ offsetof(struct task_struct, thread.fstate.f[22])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F23_F0,
+ offsetof(struct task_struct, thread.fstate.f[23])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F24_F0,
+ offsetof(struct task_struct, thread.fstate.f[24])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F25_F0,
+ offsetof(struct task_struct, thread.fstate.f[25])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F26_F0,
+ offsetof(struct task_struct, thread.fstate.f[26])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F27_F0,
+ offsetof(struct task_struct, thread.fstate.f[27])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F28_F0,
+ offsetof(struct task_struct, thread.fstate.f[28])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F29_F0,
+ offsetof(struct task_struct, thread.fstate.f[29])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F30_F0,
+ offsetof(struct task_struct, thread.fstate.f[30])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_F31_F0,
+ offsetof(struct task_struct, thread.fstate.f[31])
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+ DEFINE(TASK_THREAD_FCSR_F0,
+ offsetof(struct task_struct, thread.fstate.fcsr)
+ - offsetof(struct task_struct, thread.fstate.f[0])
+ );
+
+ /* The assembler needs access to THREAD_SIZE as well. */
+ DEFINE(ASM_THREAD_SIZE, THREAD_SIZE);
+
+ /*
+ * We allocate a pt_regs on the stack when entering the kernel. This
+ * ensures the alignment is sane.
+ */
+ DEFINE(PT_SIZE_ON_STACK, ALIGN(sizeof(struct pt_regs), STACK_ALIGN));
+}
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
new file mode 100644
index 000000000000..7208fcec0cf4
--- /dev/null
+++ b/arch/riscv/kernel/entry.S
@@ -0,0 +1,450 @@
+/*
+ * 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/init.h>
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+
+ .text
+ .altmacro
+
+/*
+ * Prepares to enter a system call or exception by saving all registers to the
+ * stack.
+ */
+ .macro SAVE_ALL
+ LOCAL _restore_kernel_tpsp
+ LOCAL _save_context
+
+ /*
+ * If coming from userspace, preserve the user thread pointer and load
+ * the kernel thread pointer. If we came from the kernel, sscratch
+ * will contain 0, and we should continue on the current TP.
+ */
+ csrrw tp, sscratch, tp
+ bnez tp, _save_context
+
+_restore_kernel_tpsp:
+ csrr tp, sscratch
+ REG_S sp, TASK_TI_KERNEL_SP(tp)
+_save_context:
+ REG_S sp, TASK_TI_USER_SP(tp)
+ REG_L sp, TASK_TI_KERNEL_SP(tp)
+ addi sp, sp, -(PT_SIZE_ON_STACK)
+ REG_S x1, PT_RA(sp)
+ REG_S x3, PT_GP(sp)
+ REG_S x5, PT_T0(sp)
+ REG_S x6, PT_T1(sp)
+ REG_S x7, PT_T2(sp)
+ REG_S x8, PT_S0(sp)
+ REG_S x9, PT_S1(sp)
+ REG_S x10, PT_A0(sp)
+ REG_S x11, PT_A1(sp)
+ REG_S x12, PT_A2(sp)
+ REG_S x13, PT_A3(sp)
+ REG_S x14, PT_A4(sp)
+ REG_S x15, PT_A5(sp)
+ REG_S x16, PT_A6(sp)
+ REG_S x17, PT_A7(sp)
+ REG_S x18, PT_S2(sp)
+ REG_S x19, PT_S3(sp)
+ REG_S x20, PT_S4(sp)
+ REG_S x21, PT_S5(sp)
+ REG_S x22, PT_S6(sp)
+ REG_S x23, PT_S7(sp)
+ REG_S x24, PT_S8(sp)
+ REG_S x25, PT_S9(sp)
+ REG_S x26, PT_S10(sp)
+ REG_S x27, PT_S11(sp)
+ REG_S x28, PT_T3(sp)
+ REG_S x29, PT_T4(sp)
+ REG_S x30, PT_T5(sp)
+ REG_S x31, PT_T6(sp)
+
+ /*
+ * Disable FPU to detect illegal usage of
+ * floating point in kernel space
+ */
+ li t0, SR_FS
+
+ REG_L s0, TASK_TI_USER_SP(tp)
+ csrrc s1, sstatus, t0
+ csrr s2, sepc
+ csrr s3, sbadaddr
+ csrr s4, scause
+ csrr s5, sscratch
+ REG_S s0, PT_SP(sp)
+ REG_S s1, PT_SSTATUS(sp)
+ REG_S s2, PT_SEPC(sp)
+ REG_S s3, PT_SBADADDR(sp)
+ REG_S s4, PT_SCAUSE(sp)
+ REG_S s5, PT_TP(sp)
+ .endm
+
+/*
+ * Prepares to return from a system call or exception by restoring all
+ * registers from the stack.
+ */
+ .macro RESTORE_ALL
+ REG_L a0, PT_SSTATUS(sp)
+ REG_L a2, PT_SEPC(sp)
+ csrw sstatus, a0
+ csrw sepc, a2
+
+ REG_L x1, PT_RA(sp)
+ REG_L x3, PT_GP(sp)
+ REG_L x4, PT_TP(sp)
+ REG_L x5, PT_T0(sp)
+ REG_L x6, PT_T1(sp)
+ REG_L x7, PT_T2(sp)
+ REG_L x8, PT_S0(sp)
+ REG_L x9, PT_S1(sp)
+ REG_L x10, PT_A0(sp)
+ REG_L x11, PT_A1(sp)
+ REG_L x12, PT_A2(sp)
+ REG_L x13, PT_A3(sp)
+ REG_L x14, PT_A4(sp)
+ REG_L x15, PT_A5(sp)
+ REG_L x16, PT_A6(sp)
+ REG_L x17, PT_A7(sp)
+ REG_L x18, PT_S2(sp)
+ REG_L x19, PT_S3(sp)
+ REG_L x20, PT_S4(sp)
+ REG_L x21, PT_S5(sp)
+ REG_L x22, PT_S6(sp)
+ REG_L x23, PT_S7(sp)
+ REG_L x24, PT_S8(sp)
+ REG_L x25, PT_S9(sp)
+ REG_L x26, PT_S10(sp)
+ REG_L x27, PT_S11(sp)
+ REG_L x28, PT_T3(sp)
+ REG_L x29, PT_T4(sp)
+ REG_L x30, PT_T5(sp)
+ REG_L x31, PT_T6(sp)
+
+ REG_L x2, PT_SP(sp)
+ .endm
+
+ENTRY(handle_exception)
+ SAVE_ALL
+
+ /*
+ * Set sscratch register to 0, so that if a recursive exception
+ * occurs, the exception vector knows it came from the kernel
+ */
+ csrw sscratch, x0
+
+ la gp, __global_pointer$
+
+ la ra, ret_from_exception
+ /*
+ * MSB of cause differentiates between
+ * interrupts and exceptions
+ */
+ bge s4, zero, 1f
+
+ /* Handle interrupts */
+ slli a0, s4, 1
+ srli a0, a0, 1
+ move a1, sp /* pt_regs */
+ tail do_IRQ
+1:
+ /* Handle syscalls */
+ li t0, EXC_SYSCALL
+ beq s4, t0, handle_syscall
+
+ /* Handle other exceptions */
+ slli t0, s4, RISCV_LGPTR
+ la t1, excp_vect_table
+ la t2, excp_vect_table_end
+ move a0, sp /* pt_regs */
+ add t0, t1, t0
+ /* Check if exception code lies within bounds */
+ bgeu t0, t2, 1f
+ REG_L t0, 0(t0)
+ jr t0
+1:
+ tail do_trap_unknown
+
+handle_syscall:
+ /*
+ * Advance SEPC to avoid executing the original
+ * scall instruction on sret
+ */
+ addi s2, s2, 0x4
+ REG_S s2, PT_SEPC(sp)
+ /* System calls run with interrupts enabled */
+ csrs sstatus, SR_IE
+ /* Trace syscalls, but only if requested by the user. */
+ REG_L t0, TASK_TI_FLAGS(tp)
+ andi t0, t0, _TIF_SYSCALL_TRACE
+ bnez t0, handle_syscall_trace_enter
+check_syscall_nr:
+ /* Check to make sure we don't jump to a bogus syscall number. */
+ li t0, __NR_syscalls
+ la s0, sys_ni_syscall
+ /* Syscall number held in a7 */
+ bgeu a7, t0, 1f
+ la s0, sys_call_table
+ slli t0, a7, RISCV_LGPTR
+ add s0, s0, t0
+ REG_L s0, 0(s0)
+1:
+ jalr s0
+
+ret_from_syscall:
+ /* Set user a0 to kernel a0 */
+ REG_S a0, PT_A0(sp)
+ /* Trace syscalls, but only if requested by the user. */
+ REG_L t0, TASK_TI_FLAGS(tp)
+ andi t0, t0, _TIF_SYSCALL_TRACE
+ bnez t0, handle_syscall_trace_exit
+
+ret_from_exception:
+ REG_L s0, PT_SSTATUS(sp)
+ csrc sstatus, SR_IE
+ andi s0, s0, SR_PS
+ bnez s0, restore_all
+
+resume_userspace:
+ /* Interrupts must be disabled here so flags are checked atomically */
+ REG_L s0, TASK_TI_FLAGS(tp) /* current_thread_info->flags */
+ andi s1, s0, _TIF_WORK_MASK
+ bnez s1, work_pending
+
+ /* Save unwound kernel stack pointer in thread_info */
+ addi s0, sp, PT_SIZE_ON_STACK
+ REG_S s0, TASK_TI_KERNEL_SP(tp)
+
+ /*
+ * Save TP into sscratch, so we can find the kernel data structures
+ * again.
+ */
+ csrw sscratch, tp
+
+restore_all:
+ RESTORE_ALL
+ sret
+
+work_pending:
+ /* Enter slow path for supplementary processing */
+ la ra, ret_from_exception
+ andi s1, s0, _TIF_NEED_RESCHED
+ bnez s1, work_resched
+work_notifysig:
+ /* Handle pending signals and notify-resume requests */
+ csrs sstatus, SR_IE /* Enable interrupts for do_notify_resume() */
+ move a0, sp /* pt_regs */
+ move a1, s0 /* current_thread_info->flags */
+ tail do_notify_resume
+work_resched:
+ tail schedule
+
+/* Slow paths for ptrace. */
+handle_syscall_trace_enter:
+ move a0, sp
+ call do_syscall_trace_enter
+ REG_L a0, PT_A0(sp)
+ REG_L a1, PT_A1(sp)
+ REG_L a2, PT_A2(sp)
+ REG_L a3, PT_A3(sp)
+ REG_L a4, PT_A4(sp)
+ REG_L a5, PT_A5(sp)
+ REG_L a6, PT_A6(sp)
+ REG_L a7, PT_A7(sp)
+ j check_syscall_nr
+handle_syscall_trace_exit:
+ move a0, sp
+ call do_syscall_trace_exit
+ j ret_from_exception
+
+END(handle_exception)
+
+ENTRY(ret_from_fork)
+ la ra, ret_from_exception
+ tail schedule_tail
+ENDPROC(ret_from_fork)
+
+ENTRY(ret_from_kernel_thread)
+ call schedule_tail
+ /* Call fn(arg) */
+ la ra, ret_from_exception
+ move a0, s1
+ jr s0
+ENDPROC(ret_from_kernel_thread)
+
+
+/*
+ * Integer register context switch
+ * The callee-saved registers must be saved and restored.
+ *
+ * a0: previous task_struct (must be preserved across the switch)
+ * a1: next task_struct
+ */
+ENTRY(__switch_to)
+ /* Save context into prev->thread */
+ li a2, TASK_THREAD_RA
+ add a0, a0, a2
+ add a2, a1, a2
+ REG_S ra, TASK_THREAD_RA_RA(a0)
+ REG_S sp, TASK_THREAD_SP_RA(a0)
+ REG_S s0, TASK_THREAD_S0_RA(a0)
+ REG_S s1, TASK_THREAD_S1_RA(a0)
+ REG_S s2, TASK_THREAD_S2_RA(a0)
+ REG_S s3, TASK_THREAD_S3_RA(a0)
+ REG_S s4, TASK_THREAD_S4_RA(a0)
+ REG_S s5, TASK_THREAD_S5_RA(a0)
+ REG_S s6, TASK_THREAD_S6_RA(a0)
+ REG_S s7, TASK_THREAD_S7_RA(a0)
+ REG_S s8, TASK_THREAD_S8_RA(a0)
+ REG_S s9, TASK_THREAD_S9_RA(a0)
+ REG_S s10, TASK_THREAD_S10_RA(a0)
+ REG_S s11, TASK_THREAD_S11_RA(a0)
+ /* Restore context from next->thread */
+ REG_L ra, TASK_THREAD_RA_RA(a2)
+ REG_L sp, TASK_THREAD_SP_RA(a2)
+ REG_L s0, TASK_THREAD_S0_RA(a2)
+ REG_L s1, TASK_THREAD_S1_RA(a2)
+ REG_L s2, TASK_THREAD_S2_RA(a2)
+ REG_L s3, TASK_THREAD_S3_RA(a2)
+ REG_L s4, TASK_THREAD_S4_RA(a2)
+ REG_L s5, TASK_THREAD_S5_RA(a2)
+ REG_L s6, TASK_THREAD_S6_RA(a2)
+ REG_L s7, TASK_THREAD_S7_RA(a2)
+ REG_L s8, TASK_THREAD_S8_RA(a2)
+ REG_L s9, TASK_THREAD_S9_RA(a2)
+ REG_L s10, TASK_THREAD_S10_RA(a2)
+ REG_L s11, TASK_THREAD_S11_RA(a2)
+#if TASK_TI != 0
+#error "TASK_TI != 0: tp will contain a 'struct thread_info', not a 'struct task_struct' so get_current() won't work."
+ addi tp, a1, TASK_TI
+#else
+ move tp, a1
+#endif
+ 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)
+ RISCV_PTR do_trap_insn_misaligned
+ RISCV_PTR do_trap_insn_fault
+ RISCV_PTR do_trap_insn_illegal
+ RISCV_PTR do_trap_break
+ RISCV_PTR do_trap_load_misaligned
+ RISCV_PTR do_trap_load_fault
+ RISCV_PTR do_trap_store_misaligned
+ RISCV_PTR do_trap_store_fault
+ RISCV_PTR do_trap_ecall_u /* system call, gets intercepted */
+ RISCV_PTR do_trap_ecall_s
+ RISCV_PTR do_trap_unknown
+ RISCV_PTR do_trap_ecall_m
+ RISCV_PTR do_page_fault /* instruction page fault */
+ RISCV_PTR do_page_fault /* load page fault */
+ RISCV_PTR do_trap_unknown
+ RISCV_PTR do_page_fault /* store page fault */
+excp_vect_table_end:
+END(excp_vect_table)
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
new file mode 100644
index 000000000000..7d539d64bf1a
--- /dev/null
+++ b/arch/riscv/kernel/process.c
@@ -0,0 +1,132 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/tick.h>
+#include <linux/ptrace.h>
+
+#include <asm/unistd.h>
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+#include <asm/csr.h>
+#include <asm/string.h>
+#include <asm/switch_to.h>
+
+extern asmlinkage void ret_from_fork(void);
+extern asmlinkage void ret_from_kernel_thread(void);
+
+void arch_cpu_idle(void)
+{
+ wait_for_interrupt();
+ local_irq_enable();
+}
+
+void show_regs(struct pt_regs *regs)
+{
+ show_regs_print_info(KERN_DEFAULT);
+
+ pr_cont("sepc: " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n",
+ regs->sepc, regs->ra, regs->sp);
+ pr_cont(" gp : " REG_FMT " tp : " REG_FMT " t0 : " REG_FMT "\n",
+ regs->gp, regs->tp, regs->t0);
+ pr_cont(" t1 : " REG_FMT " t2 : " REG_FMT " s0 : " REG_FMT "\n",
+ regs->t1, regs->t2, regs->s0);
+ pr_cont(" s1 : " REG_FMT " a0 : " REG_FMT " a1 : " REG_FMT "\n",
+ regs->s1, regs->a0, regs->a1);
+ pr_cont(" a2 : " REG_FMT " a3 : " REG_FMT " a4 : " REG_FMT "\n",
+ regs->a2, regs->a3, regs->a4);
+ pr_cont(" a5 : " REG_FMT " a6 : " REG_FMT " a7 : " REG_FMT "\n",
+ regs->a5, regs->a6, regs->a7);
+ pr_cont(" s2 : " REG_FMT " s3 : " REG_FMT " s4 : " REG_FMT "\n",
+ regs->s2, regs->s3, regs->s4);
+ pr_cont(" s5 : " REG_FMT " s6 : " REG_FMT " s7 : " REG_FMT "\n",
+ regs->s5, regs->s6, regs->s7);
+ pr_cont(" s8 : " REG_FMT " s9 : " REG_FMT " s10: " REG_FMT "\n",
+ regs->s8, regs->s9, regs->s10);
+ pr_cont(" s11: " REG_FMT " t3 : " REG_FMT " t4 : " REG_FMT "\n",
+ regs->s11, regs->t3, regs->t4);
+ pr_cont(" t5 : " REG_FMT " t6 : " REG_FMT "\n",
+ regs->t5, regs->t6);
+
+ pr_cont("sstatus: " REG_FMT " sbadaddr: " REG_FMT " scause: " REG_FMT "\n",
+ regs->sstatus, regs->sbadaddr, regs->scause);
+}
+
+void start_thread(struct pt_regs *regs, unsigned long pc,
+ unsigned long sp)
+{
+ regs->sstatus = SR_PIE /* User mode, irqs on */ | SR_FS_INITIAL;
+#ifndef CONFIG_RV_PUM
+ regs->sstatus |= SR_SUM;
+#endif
+ regs->sepc = pc;
+ regs->sp = sp;
+ set_fs(USER_DS);
+}
+
+void flush_thread(void)
+{
+ /*
+ * Reset FPU context
+ * frm: round to nearest, ties to even (IEEE default)
+ * fflags: accrued exceptions cleared
+ */
+ memset(¤t->thread.fstate, 0, sizeof(current->thread.fstate));
+}
+
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+ fstate_save(src, task_pt_regs(src));
+ *dst = *src;
+ return 0;
+}
+
+int copy_thread(unsigned long clone_flags, unsigned long usp,
+ unsigned long arg, struct task_struct *p)
+{
+ struct pt_regs *childregs = task_pt_regs(p);
+
+ /* p->thread holds context to be restored by __switch_to() */
+ if (unlikely(p->flags & PF_KTHREAD)) {
+ /* Kernel thread */
+ const register unsigned long gp __asm__ ("gp");
+ memset(childregs, 0, sizeof(struct pt_regs));
+ childregs->gp = gp;
+ childregs->sstatus = SR_PS | SR_PIE; /* Supervisor, irqs on */
+
+ p->thread.ra = (unsigned long)ret_from_kernel_thread;
+ p->thread.s[0] = usp; /* fn */
+ p->thread.s[1] = arg;
+ } else {
+ *childregs = *(current_pt_regs());
+ if (usp) /* User fork */
+ childregs->sp = usp;
+ if (clone_flags & CLONE_SETTLS)
+ childregs->tp = childregs->a5;
+ childregs->a0 = 0; /* Return value of fork() */
+ p->thread.ra = (unsigned long)ret_from_fork;
+ }
+ p->thread.sp = (unsigned long)childregs; /* kernel sp */
+ return 0;
+}
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 6/9] RISC-V: Device, timer, IRQs, and the SBI
2017-07-04 19:50 ` Palmer Dabbelt
@ 2017-07-04 19:50 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains code that interfaces with devices that are mandated
by the RISC-V supervisor specification and that don't have explicit
drivers anywhere else in the tree. This includes the staticly defined
interrupts, the CSR-mapped timer, and virtualized SBI devices.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/delay.h | 28 +++++++++
arch/riscv/include/asm/dma-mapping.h | 38 ++++++++++++
arch/riscv/include/asm/irq.h | 31 ++++++++++
arch/riscv/include/asm/irqflags.h | 63 ++++++++++++++++++++
arch/riscv/include/asm/pci.h | 48 +++++++++++++++
arch/riscv/include/asm/sbi.h | 100 +++++++++++++++++++++++++++++++
arch/riscv/include/asm/timex.h | 59 +++++++++++++++++++
arch/riscv/lib/delay.c | 110 +++++++++++++++++++++++++++++++++++
arch/riscv/mm/ioremap.c | 92 +++++++++++++++++++++++++++++
9 files changed, 569 insertions(+)
create mode 100644 arch/riscv/include/asm/delay.h
create mode 100644 arch/riscv/include/asm/dma-mapping.h
create mode 100644 arch/riscv/include/asm/irq.h
create mode 100644 arch/riscv/include/asm/irqflags.h
create mode 100644 arch/riscv/include/asm/pci.h
create mode 100644 arch/riscv/include/asm/sbi.h
create mode 100644 arch/riscv/include/asm/timex.h
create mode 100644 arch/riscv/lib/delay.c
create mode 100644 arch/riscv/mm/ioremap.c
diff --git a/arch/riscv/include/asm/delay.h b/arch/riscv/include/asm/delay.h
new file mode 100644
index 000000000000..cbb0c9eb96cb
--- /dev/null
+++ b/arch/riscv/include/asm/delay.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2016 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_DELAY_H
+#define _ASM_RISCV_DELAY_H
+
+extern unsigned long riscv_timebase;
+
+#define udelay udelay
+extern void udelay(unsigned long usecs);
+
+#define ndelay ndelay
+extern void ndelay(unsigned long nsecs);
+
+extern void __delay(unsigned long cycles);
+
+#endif /* _ASM_RISCV_DELAY_H */
diff --git a/arch/riscv/include/asm/dma-mapping.h b/arch/riscv/include/asm/dma-mapping.h
new file mode 100644
index 000000000000..3eec1000196d
--- /dev/null
+++ b/arch/riscv/include/asm/dma-mapping.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2003-2004 Hewlett-Packard Co
+ * David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2016 SiFive, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_RISCV_DMA_MAPPING_H
+#define __ASM_RISCV_DMA_MAPPING_H
+
+/* Use ops->dma_mapping_error (if it exists) or assume success */
+// #undef DMA_ERROR_CODE
+
+static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
+{
+ return &dma_noop_ops;
+}
+
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+ if (!dev->dma_mask)
+ return false;
+
+ return addr + size - 1 <= *dev->dma_mask;
+}
+
+#endif /* __ASM_RISCV_DMA_MAPPING_H */
diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h
new file mode 100644
index 000000000000..e64c61e89f76
--- /dev/null
+++ b/arch/riscv/include/asm/irq.h
@@ -0,0 +1,31 @@
+/*
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_IRQ_H
+#define _ASM_RISCV_IRQ_H
+
+#define NR_IRQS 0
+
+#define INTERRUPT_CAUSE_SOFTWARE 1
+#define INTERRUPT_CAUSE_TIMER 5
+#define INTERRUPT_CAUSE_EXTERNAL 9
+
+void riscv_timer_interrupt(void);
+
+#include <asm-generic/irq.h>
+
+/* The value of csr sie before init_traps runs (core is up) */
+DECLARE_PER_CPU(atomic_long_t, riscv_early_sie);
+
+#endif /* _ASM_RISCV_IRQ_H */
diff --git a/arch/riscv/include/asm/irqflags.h b/arch/riscv/include/asm/irqflags.h
new file mode 100644
index 000000000000..6fdc860d7f84
--- /dev/null
+++ b/arch/riscv/include/asm/irqflags.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+
+#ifndef _ASM_RISCV_IRQFLAGS_H
+#define _ASM_RISCV_IRQFLAGS_H
+
+#include <asm/processor.h>
+#include <asm/csr.h>
+
+/* read interrupt enabled status */
+static inline unsigned long arch_local_save_flags(void)
+{
+ return csr_read(sstatus);
+}
+
+/* unconditionally enable interrupts */
+static inline void arch_local_irq_enable(void)
+{
+ csr_set(sstatus, SR_IE);
+}
+
+/* unconditionally disable interrupts */
+static inline void arch_local_irq_disable(void)
+{
+ csr_clear(sstatus, SR_IE);
+}
+
+/* get status and disable interrupts */
+static inline unsigned long arch_local_irq_save(void)
+{
+ return csr_read_clear(sstatus, SR_IE);
+}
+
+/* test flags */
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+ return !(flags & SR_IE);
+}
+
+/* test hardware interrupt enable bit */
+static inline int arch_irqs_disabled(void)
+{
+ return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+/* set interrupt enabled status */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+ csr_set(sstatus, flags & SR_IE);
+}
+
+#endif /* _ASM_RISCV_IRQFLAGS_H */
diff --git a/arch/riscv/include/asm/pci.h b/arch/riscv/include/asm/pci.h
new file mode 100644
index 000000000000..285747fa2ef0
--- /dev/null
+++ b/arch/riscv/include/asm/pci.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 2016 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.
+ */
+
+#ifndef __ASM_RISCV_PCI_H
+#define __ASM_RISCV_PCI_H
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/io.h>
+
+#define PCIBIOS_MIN_IO 0
+#define PCIBIOS_MIN_MEM 0
+
+/* RISC-V shim does not initialize PCI bus */
+#define pcibios_assign_all_busses() 1
+
+/* RISC-V TileLink and PCIe share the share address space */
+#define PCI_DMA_BUS_IS_PHYS 1
+
+extern int isa_dma_bridge_buggy;
+
+#ifdef CONFIG_PCI
+static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
+{
+ /* no legacy IRQ on risc-v */
+ return -ENODEV;
+}
+
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+ /* always show the domain in /proc */
+ return 1;
+}
+#endif /* CONFIG_PCI */
+
+#endif /* __ASM_PCI_H */
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
new file mode 100644
index 000000000000..b6bb10b92fe2
--- /dev/null
+++ b/arch/riscv/include/asm/sbi.h
@@ -0,0 +1,100 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SBI_H
+#define _ASM_RISCV_SBI_H
+
+#include <linux/types.h>
+
+#define SBI_SET_TIMER 0
+#define SBI_CONSOLE_PUTCHAR 1
+#define SBI_CONSOLE_GETCHAR 2
+#define SBI_CLEAR_IPI 3
+#define SBI_SEND_IPI 4
+#define SBI_REMOTE_FENCE_I 5
+#define SBI_REMOTE_SFENCE_VMA 6
+#define SBI_REMOTE_SFENCE_VMA_ASID 7
+#define SBI_SHUTDOWN 8
+
+#define SBI_CALL(which, arg0, arg1, arg2) ({ \
+ register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0); \
+ register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1); \
+ register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2); \
+ register uintptr_t a7 asm ("a7") = (uintptr_t)(which); \
+ asm volatile ("ecall" \
+ : "+r" (a0) \
+ : "r" (a1), "r" (a2), "r" (a7) \
+ : "memory"); \
+ a0; \
+})
+
+/* Lazy implementations until SBI is finalized */
+#define SBI_CALL_0(which) SBI_CALL(which, 0, 0, 0)
+#define SBI_CALL_1(which, arg0) SBI_CALL(which, arg0, 0, 0)
+#define SBI_CALL_2(which, arg0, arg1) SBI_CALL(which, arg0, arg1, 0)
+
+static inline void sbi_console_putchar(int ch)
+{
+ SBI_CALL_1(SBI_CONSOLE_PUTCHAR, ch);
+}
+
+static inline int sbi_console_getchar(void)
+{
+ return SBI_CALL_0(SBI_CONSOLE_GETCHAR);
+}
+
+static inline void sbi_set_timer(uint64_t stime_value)
+{
+#if __riscv_xlen == 32
+ SBI_CALL_2(SBI_SET_TIMER, stime_value, stime_value >> 32);
+#else
+ SBI_CALL_1(SBI_SET_TIMER, stime_value);
+#endif
+}
+
+static inline void sbi_shutdown(void)
+{
+ SBI_CALL_0(SBI_SHUTDOWN);
+}
+
+static inline void sbi_clear_ipi(void)
+{
+ SBI_CALL_0(SBI_CLEAR_IPI);
+}
+
+static inline void sbi_send_ipi(const unsigned long *hart_mask)
+{
+ SBI_CALL_1(SBI_SEND_IPI, hart_mask);
+}
+
+static inline void sbi_remote_fence_i(const unsigned long *hart_mask)
+{
+ SBI_CALL_1(SBI_REMOTE_FENCE_I, hart_mask);
+}
+
+static inline void sbi_remote_sfence_vma(const unsigned long *hart_mask,
+ unsigned long start,
+ unsigned long size)
+{
+ SBI_CALL_1(SBI_REMOTE_SFENCE_VMA, hart_mask);
+}
+
+static inline void sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
+ unsigned long start,
+ unsigned long size,
+ unsigned long asid)
+{
+ SBI_CALL_1(SBI_REMOTE_SFENCE_VMA_ASID, hart_mask);
+}
+
+#endif
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
new file mode 100644
index 000000000000..3df4932d8964
--- /dev/null
+++ b/arch/riscv/include/asm/timex.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_TIMEX_H
+#define _ASM_RISCV_TIMEX_H
+
+#include <asm/param.h>
+
+typedef unsigned long cycles_t;
+
+static inline cycles_t get_cycles(void)
+{
+ cycles_t n;
+
+ __asm__ __volatile__ (
+ "rdtime %0"
+ : "=r" (n));
+ return n;
+}
+
+#ifdef CONFIG_64BIT
+static inline uint64_t get_cycles64(void)
+{
+ return get_cycles();
+}
+#else
+static inline uint64_t get_cycles64(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 ((u64)hi << 32) | lo;
+}
+#endif
+
+#define ARCH_HAS_READ_CURRENT_TIMER
+
+static inline int read_current_timer(unsigned long *timer_val)
+{
+ *timer_val = get_cycles();
+ return 0;
+}
+
+#endif /* _ASM_RISCV_TIMEX_H */
diff --git a/arch/riscv/lib/delay.c b/arch/riscv/lib/delay.c
new file mode 100644
index 000000000000..1cc4ac3964b4
--- /dev/null
+++ b/arch/riscv/lib/delay.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/delay.h>
+#include <linux/param.h>
+#include <linux/timex.h>
+#include <linux/export.h>
+
+/*
+ * This is copies from arch/arm/include/asm/delay.h
+ *
+ * Loop (or tick) based delay:
+ *
+ * loops = loops_per_jiffy * jiffies_per_sec * delay_us / us_per_sec
+ *
+ * where:
+ *
+ * jiffies_per_sec = HZ
+ * us_per_sec = 1000000
+ *
+ * Therefore the constant part is HZ / 1000000 which is a small
+ * fractional number. To make this usable with integer math, we
+ * scale up this constant by 2^31, perform the actual multiplication,
+ * and scale the result back down by 2^31 with a simple shift:
+ *
+ * loops = (loops_per_jiffy * delay_us * UDELAY_MULT) >> 31
+ *
+ * where:
+ *
+ * UDELAY_MULT = 2^31 * HZ / 1000000
+ * = (2^31 / 1000000) * HZ
+ * = 2147.483648 * HZ
+ * = 2147 * HZ + 483648 * HZ / 1000000
+ *
+ * 31 is the biggest scale shift value that won't overflow 32 bits for
+ * delay_us * UDELAY_MULT assuming HZ <= 1000 and delay_us <= 2000.
+ */
+#define MAX_UDELAY_US 2000
+#define MAX_UDELAY_HZ 1000
+#define UDELAY_MULT (2147UL * HZ + 483648UL * HZ / 1000000UL)
+#define UDELAY_SHIFT 31
+
+#if HZ > MAX_UDELAY_HZ
+#error "HZ > MAX_UDELAY_HZ"
+#endif
+
+/*
+ * RISC-V supports both UDELAY and NDELAY. This is largely the same as above,
+ * but with different constants. I added 10 bits to the shift to get this, but
+ * the result is that I need a 64-bit multiply, which is slow on 32-bit
+ * platforms.
+ *
+ * NDELAY_MULT = 2^41 * HZ / 1000000000
+ * = (2^41 / 1000000000) * HZ
+ * = 2199.02325555 * HZ
+ * = 2199 * HZ + 23255550 * HZ / 1000000000
+ *
+ * The maximum here is to avoid 64-bit overflow, but it isn't checked as it
+ * won't happen.
+ */
+#define MAX_NDELAY_NS (1ULL << 42)
+#define MAX_NDELAY_HZ MAX_UDELAY_HZ
+#define NDELAY_MULT ((unsigned long long)(2199ULL * HZ + 23255550ULL * HZ / 1000000000ULL))
+#define NDELAY_SHIFT 41
+
+#if HZ > MAX_NDELAY_HZ
+#error "HZ > MAX_NDELAY_HZ"
+#endif
+
+void __delay(unsigned long cycles)
+{
+ u64 t0 = get_cycles();
+
+ while ((unsigned long)(get_cycles() - t0) < cycles)
+ cpu_relax();
+}
+
+void udelay(unsigned long usecs)
+{
+ unsigned long ucycles = usecs * lpj_fine * UDELAY_MULT;
+
+ if (unlikely(usecs > MAX_UDELAY_US)) {
+ __delay((u64)usecs * riscv_timebase / 1000000ULL);
+ return;
+ }
+
+ __delay(ucycles >> UDELAY_SHIFT);
+}
+EXPORT_SYMBOL(udelay);
+
+void ndelay(unsigned long nsecs)
+{
+ /*
+ * This doesn't bother checking for overflow, as it won't happen (it's
+ * an hour) of delay.
+ */
+ unsigned long long ncycles = nsecs * lpj_fine * NDELAY_MULT;
+ __delay(ncycles >> NDELAY_SHIFT);
+}
+EXPORT_SYMBOL(ndelay);
diff --git a/arch/riscv/mm/ioremap.c b/arch/riscv/mm/ioremap.c
new file mode 100644
index 000000000000..e99194a4077e
--- /dev/null
+++ b/arch/riscv/mm/ioremap.c
@@ -0,0 +1,92 @@
+/*
+ * (C) Copyright 1995 1996 Linus Torvalds
+ * (C) Copyright 2012 Regents of the University of California
+ *
+ * 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/export.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/io.h>
+
+#include <asm/pgtable.h>
+
+/*
+ * Remap an arbitrary physical address space into the kernel virtual
+ * address space. Needed when the kernel wants to access high addresses
+ * directly.
+ *
+ * NOTE! We need to allow non-page-aligned mappings too: we will obviously
+ * have to convert them into an offset in a page-aligned mapping, but the
+ * caller shouldn't need to know that small detail.
+ */
+static void __iomem *__ioremap_caller(phys_addr_t addr, size_t size,
+ pgprot_t prot, void *caller)
+{
+ phys_addr_t last_addr;
+ unsigned long offset, vaddr;
+ struct vm_struct *area;
+
+ /* Disallow wrap-around or zero size */
+ last_addr = addr + size - 1;
+ if (!size || last_addr < addr)
+ return NULL;
+
+ /* Page-align mappings */
+ offset = addr & (~PAGE_MASK);
+ addr &= PAGE_MASK;
+ size = PAGE_ALIGN(size + offset);
+
+ area = get_vm_area_caller(size, VM_IOREMAP, caller);
+ if (!area)
+ return NULL;
+ vaddr = (unsigned long)area->addr;
+
+ if (ioremap_page_range(vaddr, vaddr + size, addr, prot)) {
+ free_vm_area(area);
+ return NULL;
+ }
+
+ return (void __iomem *)(vaddr + offset);
+}
+
+/*
+ * ioremap - map bus memory into CPU space
+ * @offset: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * ioremap performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap(phys_addr_t offset, unsigned long size)
+{
+ return __ioremap_caller(offset, size, PAGE_KERNEL,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap);
+
+
+/**
+ * iounmap - Free a IO remapping
+ * @addr: virtual address from ioremap_*
+ *
+ * Caller must ensure there is only one unmapping for the same pointer.
+ */
+void iounmap(void __iomem *addr)
+{
+ vunmap((void *)((unsigned long)addr & PAGE_MASK));
+}
+EXPORT_SYMBOL(iounmap);
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 6/9] RISC-V: Device, timer, IRQs, and the SBI
@ 2017-07-04 19:50 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:50 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains code that interfaces with devices that are mandated
by the RISC-V supervisor specification and that don't have explicit
drivers anywhere else in the tree. This includes the staticly defined
interrupts, the CSR-mapped timer, and virtualized SBI devices.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/delay.h | 28 +++++++++
arch/riscv/include/asm/dma-mapping.h | 38 ++++++++++++
arch/riscv/include/asm/irq.h | 31 ++++++++++
arch/riscv/include/asm/irqflags.h | 63 ++++++++++++++++++++
arch/riscv/include/asm/pci.h | 48 +++++++++++++++
arch/riscv/include/asm/sbi.h | 100 +++++++++++++++++++++++++++++++
arch/riscv/include/asm/timex.h | 59 +++++++++++++++++++
arch/riscv/lib/delay.c | 110 +++++++++++++++++++++++++++++++++++
arch/riscv/mm/ioremap.c | 92 +++++++++++++++++++++++++++++
9 files changed, 569 insertions(+)
create mode 100644 arch/riscv/include/asm/delay.h
create mode 100644 arch/riscv/include/asm/dma-mapping.h
create mode 100644 arch/riscv/include/asm/irq.h
create mode 100644 arch/riscv/include/asm/irqflags.h
create mode 100644 arch/riscv/include/asm/pci.h
create mode 100644 arch/riscv/include/asm/sbi.h
create mode 100644 arch/riscv/include/asm/timex.h
create mode 100644 arch/riscv/lib/delay.c
create mode 100644 arch/riscv/mm/ioremap.c
diff --git a/arch/riscv/include/asm/delay.h b/arch/riscv/include/asm/delay.h
new file mode 100644
index 000000000000..cbb0c9eb96cb
--- /dev/null
+++ b/arch/riscv/include/asm/delay.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2016 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_DELAY_H
+#define _ASM_RISCV_DELAY_H
+
+extern unsigned long riscv_timebase;
+
+#define udelay udelay
+extern void udelay(unsigned long usecs);
+
+#define ndelay ndelay
+extern void ndelay(unsigned long nsecs);
+
+extern void __delay(unsigned long cycles);
+
+#endif /* _ASM_RISCV_DELAY_H */
diff --git a/arch/riscv/include/asm/dma-mapping.h b/arch/riscv/include/asm/dma-mapping.h
new file mode 100644
index 000000000000..3eec1000196d
--- /dev/null
+++ b/arch/riscv/include/asm/dma-mapping.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2003-2004 Hewlett-Packard Co
+ * David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2016 SiFive, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_RISCV_DMA_MAPPING_H
+#define __ASM_RISCV_DMA_MAPPING_H
+
+/* Use ops->dma_mapping_error (if it exists) or assume success */
+// #undef DMA_ERROR_CODE
+
+static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
+{
+ return &dma_noop_ops;
+}
+
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+ if (!dev->dma_mask)
+ return false;
+
+ return addr + size - 1 <= *dev->dma_mask;
+}
+
+#endif /* __ASM_RISCV_DMA_MAPPING_H */
diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h
new file mode 100644
index 000000000000..e64c61e89f76
--- /dev/null
+++ b/arch/riscv/include/asm/irq.h
@@ -0,0 +1,31 @@
+/*
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_IRQ_H
+#define _ASM_RISCV_IRQ_H
+
+#define NR_IRQS 0
+
+#define INTERRUPT_CAUSE_SOFTWARE 1
+#define INTERRUPT_CAUSE_TIMER 5
+#define INTERRUPT_CAUSE_EXTERNAL 9
+
+void riscv_timer_interrupt(void);
+
+#include <asm-generic/irq.h>
+
+/* The value of csr sie before init_traps runs (core is up) */
+DECLARE_PER_CPU(atomic_long_t, riscv_early_sie);
+
+#endif /* _ASM_RISCV_IRQ_H */
diff --git a/arch/riscv/include/asm/irqflags.h b/arch/riscv/include/asm/irqflags.h
new file mode 100644
index 000000000000..6fdc860d7f84
--- /dev/null
+++ b/arch/riscv/include/asm/irqflags.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+
+#ifndef _ASM_RISCV_IRQFLAGS_H
+#define _ASM_RISCV_IRQFLAGS_H
+
+#include <asm/processor.h>
+#include <asm/csr.h>
+
+/* read interrupt enabled status */
+static inline unsigned long arch_local_save_flags(void)
+{
+ return csr_read(sstatus);
+}
+
+/* unconditionally enable interrupts */
+static inline void arch_local_irq_enable(void)
+{
+ csr_set(sstatus, SR_IE);
+}
+
+/* unconditionally disable interrupts */
+static inline void arch_local_irq_disable(void)
+{
+ csr_clear(sstatus, SR_IE);
+}
+
+/* get status and disable interrupts */
+static inline unsigned long arch_local_irq_save(void)
+{
+ return csr_read_clear(sstatus, SR_IE);
+}
+
+/* test flags */
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+ return !(flags & SR_IE);
+}
+
+/* test hardware interrupt enable bit */
+static inline int arch_irqs_disabled(void)
+{
+ return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+/* set interrupt enabled status */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+ csr_set(sstatus, flags & SR_IE);
+}
+
+#endif /* _ASM_RISCV_IRQFLAGS_H */
diff --git a/arch/riscv/include/asm/pci.h b/arch/riscv/include/asm/pci.h
new file mode 100644
index 000000000000..285747fa2ef0
--- /dev/null
+++ b/arch/riscv/include/asm/pci.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 2016 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.
+ */
+
+#ifndef __ASM_RISCV_PCI_H
+#define __ASM_RISCV_PCI_H
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/io.h>
+
+#define PCIBIOS_MIN_IO 0
+#define PCIBIOS_MIN_MEM 0
+
+/* RISC-V shim does not initialize PCI bus */
+#define pcibios_assign_all_busses() 1
+
+/* RISC-V TileLink and PCIe share the share address space */
+#define PCI_DMA_BUS_IS_PHYS 1
+
+extern int isa_dma_bridge_buggy;
+
+#ifdef CONFIG_PCI
+static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
+{
+ /* no legacy IRQ on risc-v */
+ return -ENODEV;
+}
+
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+ /* always show the domain in /proc */
+ return 1;
+}
+#endif /* CONFIG_PCI */
+
+#endif /* __ASM_PCI_H */
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
new file mode 100644
index 000000000000..b6bb10b92fe2
--- /dev/null
+++ b/arch/riscv/include/asm/sbi.h
@@ -0,0 +1,100 @@
+/*
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SBI_H
+#define _ASM_RISCV_SBI_H
+
+#include <linux/types.h>
+
+#define SBI_SET_TIMER 0
+#define SBI_CONSOLE_PUTCHAR 1
+#define SBI_CONSOLE_GETCHAR 2
+#define SBI_CLEAR_IPI 3
+#define SBI_SEND_IPI 4
+#define SBI_REMOTE_FENCE_I 5
+#define SBI_REMOTE_SFENCE_VMA 6
+#define SBI_REMOTE_SFENCE_VMA_ASID 7
+#define SBI_SHUTDOWN 8
+
+#define SBI_CALL(which, arg0, arg1, arg2) ({ \
+ register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0); \
+ register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1); \
+ register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2); \
+ register uintptr_t a7 asm ("a7") = (uintptr_t)(which); \
+ asm volatile ("ecall" \
+ : "+r" (a0) \
+ : "r" (a1), "r" (a2), "r" (a7) \
+ : "memory"); \
+ a0; \
+})
+
+/* Lazy implementations until SBI is finalized */
+#define SBI_CALL_0(which) SBI_CALL(which, 0, 0, 0)
+#define SBI_CALL_1(which, arg0) SBI_CALL(which, arg0, 0, 0)
+#define SBI_CALL_2(which, arg0, arg1) SBI_CALL(which, arg0, arg1, 0)
+
+static inline void sbi_console_putchar(int ch)
+{
+ SBI_CALL_1(SBI_CONSOLE_PUTCHAR, ch);
+}
+
+static inline int sbi_console_getchar(void)
+{
+ return SBI_CALL_0(SBI_CONSOLE_GETCHAR);
+}
+
+static inline void sbi_set_timer(uint64_t stime_value)
+{
+#if __riscv_xlen == 32
+ SBI_CALL_2(SBI_SET_TIMER, stime_value, stime_value >> 32);
+#else
+ SBI_CALL_1(SBI_SET_TIMER, stime_value);
+#endif
+}
+
+static inline void sbi_shutdown(void)
+{
+ SBI_CALL_0(SBI_SHUTDOWN);
+}
+
+static inline void sbi_clear_ipi(void)
+{
+ SBI_CALL_0(SBI_CLEAR_IPI);
+}
+
+static inline void sbi_send_ipi(const unsigned long *hart_mask)
+{
+ SBI_CALL_1(SBI_SEND_IPI, hart_mask);
+}
+
+static inline void sbi_remote_fence_i(const unsigned long *hart_mask)
+{
+ SBI_CALL_1(SBI_REMOTE_FENCE_I, hart_mask);
+}
+
+static inline void sbi_remote_sfence_vma(const unsigned long *hart_mask,
+ unsigned long start,
+ unsigned long size)
+{
+ SBI_CALL_1(SBI_REMOTE_SFENCE_VMA, hart_mask);
+}
+
+static inline void sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
+ unsigned long start,
+ unsigned long size,
+ unsigned long asid)
+{
+ SBI_CALL_1(SBI_REMOTE_SFENCE_VMA_ASID, hart_mask);
+}
+
+#endif
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
new file mode 100644
index 000000000000..3df4932d8964
--- /dev/null
+++ b/arch/riscv/include/asm/timex.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_TIMEX_H
+#define _ASM_RISCV_TIMEX_H
+
+#include <asm/param.h>
+
+typedef unsigned long cycles_t;
+
+static inline cycles_t get_cycles(void)
+{
+ cycles_t n;
+
+ __asm__ __volatile__ (
+ "rdtime %0"
+ : "=r" (n));
+ return n;
+}
+
+#ifdef CONFIG_64BIT
+static inline uint64_t get_cycles64(void)
+{
+ return get_cycles();
+}
+#else
+static inline uint64_t get_cycles64(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 ((u64)hi << 32) | lo;
+}
+#endif
+
+#define ARCH_HAS_READ_CURRENT_TIMER
+
+static inline int read_current_timer(unsigned long *timer_val)
+{
+ *timer_val = get_cycles();
+ return 0;
+}
+
+#endif /* _ASM_RISCV_TIMEX_H */
diff --git a/arch/riscv/lib/delay.c b/arch/riscv/lib/delay.c
new file mode 100644
index 000000000000..1cc4ac3964b4
--- /dev/null
+++ b/arch/riscv/lib/delay.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/delay.h>
+#include <linux/param.h>
+#include <linux/timex.h>
+#include <linux/export.h>
+
+/*
+ * This is copies from arch/arm/include/asm/delay.h
+ *
+ * Loop (or tick) based delay:
+ *
+ * loops = loops_per_jiffy * jiffies_per_sec * delay_us / us_per_sec
+ *
+ * where:
+ *
+ * jiffies_per_sec = HZ
+ * us_per_sec = 1000000
+ *
+ * Therefore the constant part is HZ / 1000000 which is a small
+ * fractional number. To make this usable with integer math, we
+ * scale up this constant by 2^31, perform the actual multiplication,
+ * and scale the result back down by 2^31 with a simple shift:
+ *
+ * loops = (loops_per_jiffy * delay_us * UDELAY_MULT) >> 31
+ *
+ * where:
+ *
+ * UDELAY_MULT = 2^31 * HZ / 1000000
+ * = (2^31 / 1000000) * HZ
+ * = 2147.483648 * HZ
+ * = 2147 * HZ + 483648 * HZ / 1000000
+ *
+ * 31 is the biggest scale shift value that won't overflow 32 bits for
+ * delay_us * UDELAY_MULT assuming HZ <= 1000 and delay_us <= 2000.
+ */
+#define MAX_UDELAY_US 2000
+#define MAX_UDELAY_HZ 1000
+#define UDELAY_MULT (2147UL * HZ + 483648UL * HZ / 1000000UL)
+#define UDELAY_SHIFT 31
+
+#if HZ > MAX_UDELAY_HZ
+#error "HZ > MAX_UDELAY_HZ"
+#endif
+
+/*
+ * RISC-V supports both UDELAY and NDELAY. This is largely the same as above,
+ * but with different constants. I added 10 bits to the shift to get this, but
+ * the result is that I need a 64-bit multiply, which is slow on 32-bit
+ * platforms.
+ *
+ * NDELAY_MULT = 2^41 * HZ / 1000000000
+ * = (2^41 / 1000000000) * HZ
+ * = 2199.02325555 * HZ
+ * = 2199 * HZ + 23255550 * HZ / 1000000000
+ *
+ * The maximum here is to avoid 64-bit overflow, but it isn't checked as it
+ * won't happen.
+ */
+#define MAX_NDELAY_NS (1ULL << 42)
+#define MAX_NDELAY_HZ MAX_UDELAY_HZ
+#define NDELAY_MULT ((unsigned long long)(2199ULL * HZ + 23255550ULL * HZ / 1000000000ULL))
+#define NDELAY_SHIFT 41
+
+#if HZ > MAX_NDELAY_HZ
+#error "HZ > MAX_NDELAY_HZ"
+#endif
+
+void __delay(unsigned long cycles)
+{
+ u64 t0 = get_cycles();
+
+ while ((unsigned long)(get_cycles() - t0) < cycles)
+ cpu_relax();
+}
+
+void udelay(unsigned long usecs)
+{
+ unsigned long ucycles = usecs * lpj_fine * UDELAY_MULT;
+
+ if (unlikely(usecs > MAX_UDELAY_US)) {
+ __delay((u64)usecs * riscv_timebase / 1000000ULL);
+ return;
+ }
+
+ __delay(ucycles >> UDELAY_SHIFT);
+}
+EXPORT_SYMBOL(udelay);
+
+void ndelay(unsigned long nsecs)
+{
+ /*
+ * This doesn't bother checking for overflow, as it won't happen (it's
+ * an hour) of delay.
+ */
+ unsigned long long ncycles = nsecs * lpj_fine * NDELAY_MULT;
+ __delay(ncycles >> NDELAY_SHIFT);
+}
+EXPORT_SYMBOL(ndelay);
diff --git a/arch/riscv/mm/ioremap.c b/arch/riscv/mm/ioremap.c
new file mode 100644
index 000000000000..e99194a4077e
--- /dev/null
+++ b/arch/riscv/mm/ioremap.c
@@ -0,0 +1,92 @@
+/*
+ * (C) Copyright 1995 1996 Linus Torvalds
+ * (C) Copyright 2012 Regents of the University of California
+ *
+ * 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/export.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/io.h>
+
+#include <asm/pgtable.h>
+
+/*
+ * Remap an arbitrary physical address space into the kernel virtual
+ * address space. Needed when the kernel wants to access high addresses
+ * directly.
+ *
+ * NOTE! We need to allow non-page-aligned mappings too: we will obviously
+ * have to convert them into an offset in a page-aligned mapping, but the
+ * caller shouldn't need to know that small detail.
+ */
+static void __iomem *__ioremap_caller(phys_addr_t addr, size_t size,
+ pgprot_t prot, void *caller)
+{
+ phys_addr_t last_addr;
+ unsigned long offset, vaddr;
+ struct vm_struct *area;
+
+ /* Disallow wrap-around or zero size */
+ last_addr = addr + size - 1;
+ if (!size || last_addr < addr)
+ return NULL;
+
+ /* Page-align mappings */
+ offset = addr & (~PAGE_MASK);
+ addr &= PAGE_MASK;
+ size = PAGE_ALIGN(size + offset);
+
+ area = get_vm_area_caller(size, VM_IOREMAP, caller);
+ if (!area)
+ return NULL;
+ vaddr = (unsigned long)area->addr;
+
+ if (ioremap_page_range(vaddr, vaddr + size, addr, prot)) {
+ free_vm_area(area);
+ return NULL;
+ }
+
+ return (void __iomem *)(vaddr + offset);
+}
+
+/*
+ * ioremap - map bus memory into CPU space
+ * @offset: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * ioremap performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap(phys_addr_t offset, unsigned long size)
+{
+ return __ioremap_caller(offset, size, PAGE_KERNEL,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap);
+
+
+/**
+ * iounmap - Free a IO remapping
+ * @addr: virtual address from ioremap_*
+ *
+ * Caller must ensure there is only one unmapping for the same pointer.
+ */
+void iounmap(void __iomem *addr)
+{
+ vunmap((void *)((unsigned long)addr & PAGE_MASK));
+}
+EXPORT_SYMBOL(iounmap);
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread
* [PATCH 7/9] RISC-V: Paging and MMU
2017-07-04 19:50 ` Palmer Dabbelt
@ 2017-07-04 19:51 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:51 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains code to manage the RISC-V MMU, including definitions
of the page tables and the page walking code.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/mmu_context.h | 69 ++++++
arch/riscv/include/asm/page.h | 134 +++++++++++
arch/riscv/include/asm/pgalloc.h | 124 ++++++++++
arch/riscv/include/asm/pgtable-32.h | 25 ++
arch/riscv/include/asm/pgtable-64.h | 84 +++++++
arch/riscv/include/asm/pgtable-bits.h | 48 ++++
arch/riscv/include/asm/pgtable.h | 430 ++++++++++++++++++++++++++++++++++
arch/riscv/mm/fault.c | 282 ++++++++++++++++++++++
8 files changed, 1196 insertions(+)
create mode 100644 arch/riscv/include/asm/mmu_context.h
create mode 100644 arch/riscv/include/asm/page.h
create mode 100644 arch/riscv/include/asm/pgalloc.h
create mode 100644 arch/riscv/include/asm/pgtable-32.h
create mode 100644 arch/riscv/include/asm/pgtable-64.h
create mode 100644 arch/riscv/include/asm/pgtable-bits.h
create mode 100644 arch/riscv/include/asm/pgtable.h
create mode 100644 arch/riscv/mm/fault.c
diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
new file mode 100644
index 000000000000..de1fc1631fc4
--- /dev/null
+++ b/arch/riscv/include/asm/mmu_context.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_MMU_CONTEXT_H
+#define _ASM_RISCV_MMU_CONTEXT_H
+
+#include <asm-generic/mm_hooks.h>
+
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <asm/tlbflush.h>
+
+static inline void enter_lazy_tlb(struct mm_struct *mm,
+ struct task_struct *task)
+{
+}
+
+/* Initialize context-related info for a new mm_struct */
+static inline int init_new_context(struct task_struct *task,
+ struct mm_struct *mm)
+{
+ return 0;
+}
+
+static inline void destroy_context(struct mm_struct *mm)
+{
+}
+
+static inline pgd_t *current_pgdir(void)
+{
+ return pfn_to_virt(csr_read(sptbr) & SPTBR_PPN);
+}
+
+static inline void set_pgdir(pgd_t *pgd)
+{
+ csr_write(sptbr, virt_to_pfn(pgd) | SPTBR_MODE);
+}
+
+static inline void switch_mm(struct mm_struct *prev,
+ struct mm_struct *next, struct task_struct *task)
+{
+ if (likely(prev != next)) {
+ set_pgdir(next->pgd);
+ local_flush_tlb_all();
+ }
+}
+
+static inline void activate_mm(struct mm_struct *prev,
+ struct mm_struct *next)
+{
+ switch_mm(prev, next, NULL);
+}
+
+static inline void deactivate_mm(struct task_struct *task,
+ struct mm_struct *mm)
+{
+}
+
+#endif /* _ASM_RISCV_MMU_CONTEXT_H */
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
new file mode 100644
index 000000000000..5bbbff2d5a60
--- /dev/null
+++ b/arch/riscv/include/asm/page.h
@@ -0,0 +1,134 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ * Copyright (C) 2017 XiaojingZhu <zhuxiaoj@ict.ac.cn>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PAGE_H
+#define _ASM_RISCV_PAGE_H
+
+#include <linux/pfn.h>
+#include <linux/const.h>
+
+#define PAGE_SHIFT (12)
+#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE - 1))
+
+/*
+ * PAGE_OFFSET -- the first address of the first page of memory.
+ * When not using MMU this corresponds to the first free page in
+ * physical memory (aligned on a page boundary).
+ */
+#ifdef CONFIG_64BIT
+#define PAGE_OFFSET _AC(0xffffffff80000000, UL)
+#else
+#define PAGE_OFFSET _AC(0xc0000000, UL)
+#endif
+
+#define KERN_VIRT_SIZE (-PAGE_OFFSET)
+
+#ifndef __ASSEMBLY__
+
+#define PAGE_UP(addr) (((addr)+((PAGE_SIZE)-1))&(~((PAGE_SIZE)-1)))
+#define PAGE_DOWN(addr) ((addr)&(~((PAGE_SIZE)-1)))
+
+/* align addr on a size boundary - adjust address up/down if needed */
+#define _ALIGN_UP(addr, size) (((addr)+((size)-1))&(~((size)-1)))
+#define _ALIGN_DOWN(addr, size) ((addr)&(~((size)-1)))
+
+/* align addr on a size boundary - adjust address up if needed */
+#define _ALIGN(addr, size) _ALIGN_UP(addr, size)
+
+#define clear_page(pgaddr) memset((pgaddr), 0, PAGE_SIZE)
+#define copy_page(to, from) memcpy((to), (from), PAGE_SIZE)
+
+#define clear_user_page(pgaddr, vaddr, page) memset((pgaddr), 0, PAGE_SIZE)
+#define copy_user_page(vto, vfrom, vaddr, topg) \
+ memcpy((vto), (vfrom), PAGE_SIZE)
+
+/*
+ * Use struct definitions to apply C type checking
+ */
+
+/* Page Global Directory entry */
+typedef struct {
+ unsigned long pgd;
+} pgd_t;
+
+/* Page Table entry */
+typedef struct {
+ unsigned long pte;
+} pte_t;
+
+typedef struct {
+ unsigned long pgprot;
+} pgprot_t;
+
+typedef struct page *pgtable_t;
+
+#define pte_val(x) ((x).pte)
+#define pgd_val(x) ((x).pgd)
+#define pgprot_val(x) ((x).pgprot)
+
+#define __pte(x) ((pte_t) { (x) })
+#define __pgd(x) ((pgd_t) { (x) })
+#define __pgprot(x) ((pgprot_t) { (x) })
+
+#ifdef CONFIG_64BITS
+#define PTE_FMT "%016lx"
+#else
+#define PTE_FMT "%08lx"
+#endif
+
+extern unsigned long va_pa_offset;
+extern unsigned long pfn_base;
+
+extern unsigned long max_low_pfn;
+extern unsigned long min_low_pfn;
+
+#define __pa(x) ((unsigned long)(x) - va_pa_offset)
+#define __va(x) ((void *)((unsigned long) (x) + va_pa_offset))
+
+#define phys_to_pfn(phys) (PFN_DOWN(phys))
+#define pfn_to_phys(pfn) (PFN_PHYS(pfn))
+
+#define virt_to_pfn(vaddr) (phys_to_pfn(__pa(vaddr)))
+#define pfn_to_virt(pfn) (__va(pfn_to_phys(pfn)))
+
+#define virt_to_page(vaddr) (pfn_to_page(virt_to_pfn(vaddr)))
+#define page_to_virt(page) (pfn_to_virt(page_to_pfn(page)))
+
+#define page_to_phys(page) (pfn_to_phys(page_to_pfn(page)))
+#define page_to_bus(page) (page_to_phys(page))
+#define phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr)))
+
+#define pfn_valid(pfn) \
+ (((pfn) >= pfn_base) && (((pfn)-pfn_base) < max_mapnr))
+
+#define ARCH_PFN_OFFSET (pfn_base)
+
+#endif /* __ASSEMBLY__ */
+
+#define virt_addr_valid(vaddr) (pfn_valid(virt_to_pfn(vaddr)))
+
+#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/getorder.h>
+
+/* vDSO support */
+/* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
+#define __HAVE_ARCH_GATE_AREA
+
+#endif /* _ASM_RISCV_PAGE_H */
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
new file mode 100644
index 000000000000..b40074bcb164
--- /dev/null
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGALLOC_H
+#define _ASM_RISCV_PGALLOC_H
+
+#include <linux/mm.h>
+#include <asm/tlb.h>
+
+static inline void pmd_populate_kernel(struct mm_struct *mm,
+ pmd_t *pmd, pte_t *pte)
+{
+ unsigned long pfn = virt_to_pfn(pte);
+
+ set_pmd(pmd, __pmd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+
+static inline void pmd_populate(struct mm_struct *mm,
+ pmd_t *pmd, pgtable_t pte)
+{
+ unsigned long pfn = virt_to_pfn(page_address(pte));
+
+ set_pmd(pmd, __pmd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+
+#ifndef __PAGETABLE_PMD_FOLDED
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+ unsigned long pfn = virt_to_pfn(pmd);
+
+ set_pud(pud, __pud((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+ pgd_t *pgd;
+
+ pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
+ if (likely(pgd != NULL)) {
+ memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
+ /* Copy kernel mappings */
+ memcpy(pgd + USER_PTRS_PER_PGD,
+ init_mm.pgd + USER_PTRS_PER_PGD,
+ (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+ }
+ return pgd;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+ free_page((unsigned long)pgd);
+}
+
+#ifndef __PAGETABLE_PMD_FOLDED
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+ return (pmd_t *)__get_free_page(
+ GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+ free_page((unsigned long)pmd);
+}
+
+#define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd)
+
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+ unsigned long address)
+{
+ return (pte_t *)__get_free_page(
+ GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+}
+
+static inline struct page *pte_alloc_one(struct mm_struct *mm,
+ unsigned long address)
+{
+ struct page *pte;
+
+ pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+ if (likely(pte != NULL))
+ pgtable_page_ctor(pte);
+ return pte;
+}
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+ free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
+{
+ pgtable_page_dtor(pte);
+ __free_page(pte);
+}
+
+#define __pte_free_tlb(tlb, pte, buf) \
+do { \
+ pgtable_page_dtor(pte); \
+ tlb_remove_page((tlb), pte); \
+} while (0)
+
+static inline void check_pgt_cache(void)
+{
+}
+
+#endif /* _ASM_RISCV_PGALLOC_H */
diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h
new file mode 100644
index 000000000000..d61974b74182
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-32.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_32_H
+#define _ASM_RISCV_PGTABLE_32_H
+
+#include <asm-generic/pgtable-nopmd.h>
+#include <linux/const.h>
+
+/* Size of region mapped by a page global directory */
+#define PGDIR_SHIFT 22
+#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE - 1))
+
+#endif /* _ASM_RISCV_PGTABLE_32_H */
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
new file mode 100644
index 000000000000..7aa0ea9bd8bb
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -0,0 +1,84 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_64_H
+#define _ASM_RISCV_PGTABLE_64_H
+
+#include <linux/const.h>
+
+#define PGDIR_SHIFT 30
+/* Size of region mapped by a page global directory */
+#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE - 1))
+
+#define PMD_SHIFT 21
+/* Size of region mapped by a page middle directory */
+#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE - 1))
+
+/* Page Middle Directory entry */
+typedef struct {
+ unsigned long pmd;
+} pmd_t;
+
+#define pmd_val(x) ((x).pmd)
+#define __pmd(x) ((pmd_t) { (x) })
+
+#define PTRS_PER_PMD (PAGE_SIZE / sizeof(pmd_t))
+
+static inline int pud_present(pud_t pud)
+{
+ return (pud_val(pud) & _PAGE_PRESENT);
+}
+
+static inline int pud_none(pud_t pud)
+{
+ return (pud_val(pud) == 0);
+}
+
+static inline int pud_bad(pud_t pud)
+{
+ return !pud_present(pud);
+}
+
+static inline void set_pud(pud_t *pudp, pud_t pud)
+{
+ *pudp = pud;
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+ set_pud(pudp, __pud(0));
+}
+
+static inline unsigned long pud_page_vaddr(pud_t pud)
+{
+ return (unsigned long)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT);
+}
+
+#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+ return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+}
+
+static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot)
+{
+ return __pmd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+#define pmd_ERROR(e) \
+ pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
+
+#endif /* _ASM_RISCV_PGTABLE_64_H */
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
new file mode 100644
index 000000000000..997ddbb1d370
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_BITS_H
+#define _ASM_RISCV_PGTABLE_BITS_H
+
+/*
+ * PTE format:
+ * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0
+ * PFN reserved for SW D A G U X W R V
+ */
+
+#define _PAGE_ACCESSED_OFFSET 6
+
+#define _PAGE_PRESENT (1 << 0)
+#define _PAGE_READ (1 << 1) /* Readable */
+#define _PAGE_WRITE (1 << 2) /* Writable */
+#define _PAGE_EXEC (1 << 3) /* Executable */
+#define _PAGE_USER (1 << 4) /* User */
+#define _PAGE_GLOBAL (1 << 5) /* Global */
+#define _PAGE_ACCESSED (1 << 6) /* Set by hardware on any access */
+#define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */
+#define _PAGE_SOFT (1 << 8) /* Reserved for software */
+
+#define _PAGE_SPECIAL _PAGE_SOFT
+#define _PAGE_TABLE _PAGE_PRESENT
+
+#define _PAGE_PFN_SHIFT 10
+
+/* Set of bits to preserve across pte_modify() */
+#define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \
+ _PAGE_WRITE | _PAGE_EXEC | \
+ _PAGE_USER | _PAGE_GLOBAL))
+
+/* Advertise support for _PAGE_SPECIAL */
+#define __HAVE_ARCH_PTE_SPECIAL
+
+#endif /* _ASM_RISCV_PGTABLE_BITS_H */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
new file mode 100644
index 000000000000..3399257780b2
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable.h
@@ -0,0 +1,430 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_H
+#define _ASM_RISCV_PGTABLE_H
+
+#include <linux/mmzone.h>
+
+#include <asm/pgtable-bits.h>
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_MMU
+
+/* Page Upper Directory not used in RISC-V */
+#include <asm-generic/pgtable-nopud.h>
+#include <asm/page.h>
+#include <asm/tlbflush.h>
+#include <linux/mm_types.h>
+
+#ifdef CONFIG_64BIT
+#include <asm/pgtable-64.h>
+#else
+#include <asm/pgtable-32.h>
+#endif /* CONFIG_64BIT */
+
+/* Number of entries in the page global directory */
+#define PTRS_PER_PGD (PAGE_SIZE / sizeof(pgd_t))
+/* Number of entries in the page table */
+#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t))
+
+/* Number of PGD entries that a user-mode program can use */
+#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)
+#define FIRST_USER_ADDRESS 0
+
+/* Page protection bits */
+#define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER)
+
+#define PAGE_NONE __pgprot(0)
+#define PAGE_READ __pgprot(_PAGE_BASE | _PAGE_READ)
+#define PAGE_WRITE __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE)
+#define PAGE_EXEC __pgprot(_PAGE_BASE | _PAGE_EXEC)
+#define PAGE_READ_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC)
+#define PAGE_WRITE_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | \
+ _PAGE_EXEC | _PAGE_WRITE)
+
+#define PAGE_COPY PAGE_READ
+#define PAGE_COPY_EXEC PAGE_EXEC
+#define PAGE_COPY_READ_EXEC PAGE_READ_EXEC
+#define PAGE_SHARED PAGE_WRITE
+#define PAGE_SHARED_EXEC PAGE_WRITE_EXEC
+
+#define _PAGE_KERNEL (_PAGE_READ \
+ | _PAGE_WRITE \
+ | _PAGE_PRESENT \
+ | _PAGE_ACCESSED \
+ | _PAGE_DIRTY)
+
+#define PAGE_KERNEL __pgprot(_PAGE_KERNEL)
+#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC)
+
+extern pgd_t swapper_pg_dir[];
+
+/* MAP_PRIVATE permissions: xwr (copy-on-write) */
+#define __P000 PAGE_NONE
+#define __P001 PAGE_READ
+#define __P010 PAGE_COPY
+#define __P011 PAGE_COPY
+#define __P100 PAGE_EXEC
+#define __P101 PAGE_READ_EXEC
+#define __P110 PAGE_COPY_EXEC
+#define __P111 PAGE_COPY_READ_EXEC
+
+/* MAP_SHARED permissions: xwr */
+#define __S000 PAGE_NONE
+#define __S001 PAGE_READ
+#define __S010 PAGE_SHARED
+#define __S011 PAGE_SHARED
+#define __S100 PAGE_EXEC
+#define __S101 PAGE_READ_EXEC
+#define __S110 PAGE_SHARED_EXEC
+#define __S111 PAGE_SHARED_EXEC
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero,
+ * used for zero-mapped memory areas, etc.
+ */
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+static inline int pmd_present(pmd_t pmd)
+{
+ return (pmd_val(pmd) & _PAGE_PRESENT);
+}
+
+static inline int pmd_none(pmd_t pmd)
+{
+ return (pmd_val(pmd) == 0);
+}
+
+static inline int pmd_bad(pmd_t pmd)
+{
+ return !pmd_present(pmd);
+}
+
+static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+ *pmdp = pmd;
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+ set_pmd(pmdp, __pmd(0));
+}
+
+
+static inline pgd_t pfn_pgd(unsigned long pfn, pgprot_t prot)
+{
+ return __pgd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+#define pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
+
+/* Locate an entry in the page global directory */
+static inline pgd_t *pgd_offset(const struct mm_struct *mm, unsigned long addr)
+{
+ return mm->pgd + pgd_index(addr);
+}
+/* Locate an entry in the kernel page global directory */
+#define pgd_offset_k(addr) pgd_offset(&init_mm, (addr))
+
+static inline struct page *pmd_page(pmd_t pmd)
+{
+ return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT);
+}
+
+static inline unsigned long pmd_page_vaddr(pmd_t pmd)
+{
+ return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT);
+}
+
+/* Yields the page frame number (PFN) of a page table entry */
+static inline unsigned long pte_pfn(pte_t pte)
+{
+ return (pte_val(pte) >> _PAGE_PFN_SHIFT);
+}
+
+#define pte_page(x) pfn_to_page(pte_pfn(x))
+
+/* Constructs a page table entry */
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
+{
+ return __pte((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+static inline pte_t mk_pte(struct page *page, pgprot_t prot)
+{
+ return pfn_pte(page_to_pfn(page), prot);
+}
+
+#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+
+static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr)
+{
+ return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(addr);
+}
+
+#define pte_offset_map(dir, addr) pte_offset_kernel((dir), (addr))
+#define pte_unmap(pte) ((void)(pte))
+
+/*
+ * Certain architectures need to do special things when PTEs within
+ * a page table are directly modified. Thus, the following hook is
+ * made available.
+ */
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+ *ptep = pteval;
+}
+
+static inline void set_pte_at(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep, pte_t pteval)
+{
+ set_pte(ptep, pteval);
+}
+
+static inline void pte_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ set_pte_at(mm, addr, ptep, __pte(0));
+}
+
+static inline int pte_present(pte_t pte)
+{
+ return (pte_val(pte) & _PAGE_PRESENT);
+}
+
+static inline int pte_none(pte_t pte)
+{
+ return (pte_val(pte) == 0);
+}
+
+/* static inline int pte_read(pte_t pte) */
+
+static inline int pte_write(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_WRITE;
+}
+
+static inline int pte_huge(pte_t pte)
+{
+ return pte_present(pte)
+ && (pte_val(pte) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
+}
+
+/* static inline int pte_exec(pte_t pte) */
+
+static inline int pte_dirty(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_DIRTY;
+}
+
+static inline int pte_young(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_ACCESSED;
+}
+
+static inline int pte_special(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_SPECIAL;
+}
+
+/* static inline pte_t pte_rdprotect(pte_t pte) */
+
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+ return __pte(pte_val(pte) & ~(_PAGE_WRITE));
+}
+
+/* static inline pte_t pte_mkread(pte_t pte) */
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_WRITE);
+}
+
+/* static inline pte_t pte_mkexec(pte_t pte) */
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+ return __pte(pte_val(pte) & ~(_PAGE_DIRTY));
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+ return __pte(pte_val(pte) & ~(_PAGE_ACCESSED));
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_SPECIAL);
+}
+
+/* Modify page protection bits */
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+ return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+}
+
+#define pgd_ERROR(e) \
+ pr_err("%s:%d: bad pgd " PTE_FMT ".\n", __FILE__, __LINE__, pgd_val(e))
+
+
+/* Commit new configuration to MMU hardware */
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep)
+{
+ /*
+ * The kernel assumes that TLBs don't cache invalid entries, but
+ * in RISC-V, SFENCE.VMA specifies an ordering constraint, not a
+ * cache flush; it is necessary even after writing invalid entries.
+ * Relying on flush_tlb_fix_spurious_fault would suffice, but
+ * the extra traps reduce performance. So, eagerly SFENCE.VMA.
+ */
+ local_flush_tlb_page(address);
+}
+
+#define __HAVE_ARCH_PTE_SAME
+static inline int pte_same(pte_t pte_a, pte_t pte_b)
+{
+ return pte_val(pte_a) == pte_val(pte_b);
+}
+
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+static inline int ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep,
+ pte_t entry, int dirty)
+{
+ if (!pte_same(*ptep, entry))
+ set_pte_at(vma->vm_mm, address, ptep, entry);
+ /*
+ * update_mmu_cache will unconditionally execute, handling both
+ * the case that the PTE changed and the spurious fault case.
+ */
+ return true;
+}
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long address, pte_t *ptep)
+{
+ return __pte(atomic_long_xchg((atomic_long_t *)ptep, 0));
+}
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+ unsigned long address,
+ pte_t *ptep)
+{
+ if (!pte_young(*ptep))
+ return 0;
+ return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm,
+ unsigned long address, pte_t *ptep)
+{
+ atomic_long_and(~(unsigned long)_PAGE_WRITE, (atomic_long_t *)ptep);
+}
+
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep)
+{
+ /*
+ * This comment is borrowed from x86, but applies equally to RISC-V:
+ *
+ * Clearing the accessed bit without a TLB flush
+ * doesn't cause data corruption. [ It could cause incorrect
+ * page aging and the (mistaken) reclaim of hot pages, but the
+ * chance of that should be relatively low. ]
+ *
+ * So as a performance optimization don't flush the TLB when
+ * clearing the accessed bit, it will eventually be flushed by
+ * a context switch or a VM operation anyway. [ In the rare
+ * event of it not getting flushed for a long time the delay
+ * shouldn't really matter because there's no real memory
+ * pressure for swapout to react to. ]
+ */
+ return ptep_test_and_clear_young(vma, address, ptep);
+}
+
+/*
+ * Encode and decode a swap entry
+ *
+ * Format of swap PTE:
+ * bit 0: _PAGE_PRESENT (zero)
+ * bit 1: reserved for future use (zero)
+ * bits 2 to 6: swap type
+ * bits 7 to XLEN-1: swap offset
+ */
+#define __SWP_TYPE_SHIFT 2
+#define __SWP_TYPE_BITS 5
+#define __SWP_TYPE_MASK ((1UL << __SWP_TYPE_BITS) - 1)
+#define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
+
+#define MAX_SWAPFILES_CHECK() \
+ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
+
+#define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
+#define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT)
+#define __swp_entry(type, offset) ((swp_entry_t) \
+ { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
+
+#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
+
+#ifdef CONFIG_FLATMEM
+#define kern_addr_valid(addr) (1) /* FIXME */
+#endif
+
+extern void paging_init(void);
+
+static inline void pgtable_cache_init(void)
+{
+ /* No page table caches to initialize */
+}
+
+#endif /* CONFIG_MMU */
+
+#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1)
+#define VMALLOC_END (PAGE_OFFSET - 1)
+#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE)
+
+/*
+ * Task size is 0x40000000000 for RV64 or 0xb800000 for RV32.
+ * Note that PGDIR_SIZE must evenly divide TASK_SIZE.
+ */
+#ifdef CONFIG_64BIT
+#define TASK_SIZE (PGDIR_SIZE * PTRS_PER_PGD / 2)
+#else
+#define TASK_SIZE VMALLOC_START
+#endif
+
+#include <asm-generic/pgtable.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PGTABLE_H */
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
new file mode 100644
index 000000000000..df2ca3c65048
--- /dev/null
+++ b/arch/riscv/mm/fault.c
@@ -0,0 +1,282 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+
+#include <linux/mm.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/perf_event.h>
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+
+#include <asm/pgalloc.h>
+#include <asm/ptrace.h>
+#include <asm/uaccess.h>
+
+/*
+ * This routine handles page faults. It determines the address and the
+ * problem, and then passes it off to one of the appropriate routines.
+ */
+asmlinkage void do_page_fault(struct pt_regs *regs)
+{
+ struct task_struct *tsk;
+ struct vm_area_struct *vma;
+ struct mm_struct *mm;
+ unsigned long addr, cause;
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ int fault, code = SEGV_MAPERR;
+
+ cause = regs->scause;
+ addr = regs->sbadaddr;
+
+ tsk = current;
+ mm = tsk->mm;
+
+ /*
+ * Fault-in kernel-space virtual memory on-demand.
+ * The 'reference' page table is init_mm.pgd.
+ *
+ * NOTE! We MUST NOT take any locks for this case. We may
+ * be in an interrupt or a critical region, and should
+ * only copy the information from the master page table,
+ * nothing more.
+ */
+ if (unlikely((addr >= VMALLOC_START) && (addr <= VMALLOC_END)))
+ goto vmalloc_fault;
+
+ /* Enable interrupts if they were enabled in the parent context. */
+ if (likely(regs->sstatus & SR_PIE))
+ local_irq_enable();
+
+ /*
+ * If we're in an interrupt, have no user context, or are running
+ * in an atomic region, then we must not take the fault.
+ */
+ if (unlikely(faulthandler_disabled() || !mm))
+ goto no_context;
+
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
+retry:
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, addr);
+ if (unlikely(!vma))
+ goto bad_area;
+ if (likely(vma->vm_start <= addr))
+ goto good_area;
+ if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
+ goto bad_area;
+ if (unlikely(expand_stack(vma, addr)))
+ goto bad_area;
+
+ /*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it.
+ */
+good_area:
+ code = SEGV_ACCERR;
+
+ switch (cause) {
+ case EXC_INST_PAGE_FAULT:
+ if (!(vma->vm_flags & VM_EXEC))
+ goto bad_area;
+ break;
+ case EXC_LOAD_PAGE_FAULT:
+ if (!(vma->vm_flags & VM_READ))
+ goto bad_area;
+ break;
+ case EXC_STORE_PAGE_FAULT:
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
+ break;
+ default:
+ panic("%s: unhandled cause %lu", __func__, cause);
+ }
+
+ /*
+ * If for any reason at all we could not handle the fault,
+ * make sure we exit gracefully rather than endlessly redo
+ * the fault.
+ */
+ fault = handle_mm_fault(vma, addr, flags);
+
+ /*
+ * If we need to retry but a fatal signal is pending, handle the
+ * signal first. We do not need to release the mmap_sem because it
+ * would already be released in __lock_page_or_retry in mm/filemap.c.
+ */
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(tsk))
+ return;
+
+ if (unlikely(fault & VM_FAULT_ERROR)) {
+ if (fault & VM_FAULT_OOM)
+ goto out_of_memory;
+ else if (fault & VM_FAULT_SIGBUS)
+ goto do_sigbus;
+ BUG();
+ }
+
+ /*
+ * Major/minor page fault accounting is only done on the
+ * initial attempt. If we go through a retry, it is extremely
+ * likely that the page will be found in page cache at that point.
+ */
+ if (flags & FAULT_FLAG_ALLOW_RETRY) {
+ if (fault & VM_FAULT_MAJOR) {
+ tsk->maj_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
+ 1, regs, addr);
+ } else {
+ tsk->min_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
+ 1, regs, addr);
+ }
+ if (fault & VM_FAULT_RETRY) {
+ /*
+ * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+ * of starvation.
+ */
+ flags &= ~(FAULT_FLAG_ALLOW_RETRY);
+ flags |= FAULT_FLAG_TRIED;
+
+ /*
+ * No need to up_read(&mm->mmap_sem) as we would
+ * have already released it in __lock_page_or_retry
+ * in mm/filemap.c.
+ */
+ goto retry;
+ }
+ }
+
+ up_read(&mm->mmap_sem);
+ return;
+
+ /*
+ * Something tried to access memory that isn't in our memory map.
+ * Fix it, but check if it's kernel or user first.
+ */
+bad_area:
+ up_read(&mm->mmap_sem);
+ /* User mode accesses just cause a SIGSEGV */
+ if (user_mode(regs)) {
+ do_trap(regs, SIGSEGV, code, addr, tsk);
+ return;
+ }
+
+no_context:
+ /* Are we prepared to handle this kernel fault? */
+ if (fixup_exception(regs))
+ return;
+
+ /*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+ bust_spinlocks(1);
+ pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n",
+ (addr < PAGE_SIZE) ? "NULL pointer dereference" :
+ "paging request", addr);
+ die(regs, "Oops");
+ do_exit(SIGKILL);
+
+ /*
+ * We ran out of memory, call the OOM killer, and return the userspace
+ * (which will retry the fault, or kill us if we got oom-killed).
+ */
+out_of_memory:
+ up_read(&mm->mmap_sem);
+ if (!user_mode(regs))
+ goto no_context;
+ pagefault_out_of_memory();
+ return;
+
+do_sigbus:
+ up_read(&mm->mmap_sem);
+ /* Kernel mode? Handle exceptions or die */
+ if (!user_mode(regs))
+ goto no_context;
+ do_trap(regs, SIGBUS, BUS_ADRERR, addr, tsk);
+ return;
+
+vmalloc_fault:
+ {
+ pgd_t *pgd, *pgd_k;
+ pud_t *pud, *pud_k;
+ p4d_t *p4d, *p4d_k;
+ pmd_t *pmd, *pmd_k;
+ pte_t *pte_k;
+ int index;
+
+ if (user_mode(regs))
+ goto bad_area;
+
+ /*
+ * Synchronize this task's top level page-table
+ * with the 'reference' page table.
+ *
+ * Do _not_ use "tsk->active_mm->pgd" here.
+ * We might be inside an interrupt in the middle
+ * of a task switch.
+ */
+ index = pgd_index(addr);
+ pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr)) + index;
+ pgd_k = init_mm.pgd + index;
+
+ if (!pgd_present(*pgd_k))
+ goto no_context;
+ set_pgd(pgd, *pgd_k);
+
+ p4d = p4d_offset(pgd, addr);
+ p4d_k = p4d_offset(pgd_k, addr);
+ if (!p4d_present(*p4d_k))
+ goto no_context;
+
+ pud = pud_offset(p4d, addr);
+ pud_k = pud_offset(p4d_k, addr);
+ if (!pud_present(*pud_k))
+ goto no_context;
+
+ /*
+ * Since the vmalloc area is global, it is unnecessary
+ * to copy individual PTEs
+ */
+ pmd = pmd_offset(pud, addr);
+ pmd_k = pmd_offset(pud_k, addr);
+ if (!pmd_present(*pmd_k))
+ goto no_context;
+ set_pmd(pmd, *pmd_k);
+
+ /*
+ * Make sure the actual PTE exists as well to
+ * catch kernel vmalloc-area accesses to non-mapped
+ * addresses. If we don't do this, this will just
+ * silently loop forever.
+ */
+ pte_k = pte_offset_kernel(pmd_k, addr);
+ if (!pte_present(*pte_k))
+ goto no_context;
+ return;
+ }
+}
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 7/9] RISC-V: Paging and MMU
@ 2017-07-04 19:51 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:51 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains code to manage the RISC-V MMU, including definitions
of the page tables and the page walking code.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/mmu_context.h | 69 ++++++
arch/riscv/include/asm/page.h | 134 +++++++++++
arch/riscv/include/asm/pgalloc.h | 124 ++++++++++
arch/riscv/include/asm/pgtable-32.h | 25 ++
arch/riscv/include/asm/pgtable-64.h | 84 +++++++
arch/riscv/include/asm/pgtable-bits.h | 48 ++++
arch/riscv/include/asm/pgtable.h | 430 ++++++++++++++++++++++++++++++++++
arch/riscv/mm/fault.c | 282 ++++++++++++++++++++++
8 files changed, 1196 insertions(+)
create mode 100644 arch/riscv/include/asm/mmu_context.h
create mode 100644 arch/riscv/include/asm/page.h
create mode 100644 arch/riscv/include/asm/pgalloc.h
create mode 100644 arch/riscv/include/asm/pgtable-32.h
create mode 100644 arch/riscv/include/asm/pgtable-64.h
create mode 100644 arch/riscv/include/asm/pgtable-bits.h
create mode 100644 arch/riscv/include/asm/pgtable.h
create mode 100644 arch/riscv/mm/fault.c
diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
new file mode 100644
index 000000000000..de1fc1631fc4
--- /dev/null
+++ b/arch/riscv/include/asm/mmu_context.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_MMU_CONTEXT_H
+#define _ASM_RISCV_MMU_CONTEXT_H
+
+#include <asm-generic/mm_hooks.h>
+
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <asm/tlbflush.h>
+
+static inline void enter_lazy_tlb(struct mm_struct *mm,
+ struct task_struct *task)
+{
+}
+
+/* Initialize context-related info for a new mm_struct */
+static inline int init_new_context(struct task_struct *task,
+ struct mm_struct *mm)
+{
+ return 0;
+}
+
+static inline void destroy_context(struct mm_struct *mm)
+{
+}
+
+static inline pgd_t *current_pgdir(void)
+{
+ return pfn_to_virt(csr_read(sptbr) & SPTBR_PPN);
+}
+
+static inline void set_pgdir(pgd_t *pgd)
+{
+ csr_write(sptbr, virt_to_pfn(pgd) | SPTBR_MODE);
+}
+
+static inline void switch_mm(struct mm_struct *prev,
+ struct mm_struct *next, struct task_struct *task)
+{
+ if (likely(prev != next)) {
+ set_pgdir(next->pgd);
+ local_flush_tlb_all();
+ }
+}
+
+static inline void activate_mm(struct mm_struct *prev,
+ struct mm_struct *next)
+{
+ switch_mm(prev, next, NULL);
+}
+
+static inline void deactivate_mm(struct task_struct *task,
+ struct mm_struct *mm)
+{
+}
+
+#endif /* _ASM_RISCV_MMU_CONTEXT_H */
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
new file mode 100644
index 000000000000..5bbbff2d5a60
--- /dev/null
+++ b/arch/riscv/include/asm/page.h
@@ -0,0 +1,134 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ * Copyright (C) 2017 XiaojingZhu <zhuxiaoj@ict.ac.cn>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PAGE_H
+#define _ASM_RISCV_PAGE_H
+
+#include <linux/pfn.h>
+#include <linux/const.h>
+
+#define PAGE_SHIFT (12)
+#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE - 1))
+
+/*
+ * PAGE_OFFSET -- the first address of the first page of memory.
+ * When not using MMU this corresponds to the first free page in
+ * physical memory (aligned on a page boundary).
+ */
+#ifdef CONFIG_64BIT
+#define PAGE_OFFSET _AC(0xffffffff80000000, UL)
+#else
+#define PAGE_OFFSET _AC(0xc0000000, UL)
+#endif
+
+#define KERN_VIRT_SIZE (-PAGE_OFFSET)
+
+#ifndef __ASSEMBLY__
+
+#define PAGE_UP(addr) (((addr)+((PAGE_SIZE)-1))&(~((PAGE_SIZE)-1)))
+#define PAGE_DOWN(addr) ((addr)&(~((PAGE_SIZE)-1)))
+
+/* align addr on a size boundary - adjust address up/down if needed */
+#define _ALIGN_UP(addr, size) (((addr)+((size)-1))&(~((size)-1)))
+#define _ALIGN_DOWN(addr, size) ((addr)&(~((size)-1)))
+
+/* align addr on a size boundary - adjust address up if needed */
+#define _ALIGN(addr, size) _ALIGN_UP(addr, size)
+
+#define clear_page(pgaddr) memset((pgaddr), 0, PAGE_SIZE)
+#define copy_page(to, from) memcpy((to), (from), PAGE_SIZE)
+
+#define clear_user_page(pgaddr, vaddr, page) memset((pgaddr), 0, PAGE_SIZE)
+#define copy_user_page(vto, vfrom, vaddr, topg) \
+ memcpy((vto), (vfrom), PAGE_SIZE)
+
+/*
+ * Use struct definitions to apply C type checking
+ */
+
+/* Page Global Directory entry */
+typedef struct {
+ unsigned long pgd;
+} pgd_t;
+
+/* Page Table entry */
+typedef struct {
+ unsigned long pte;
+} pte_t;
+
+typedef struct {
+ unsigned long pgprot;
+} pgprot_t;
+
+typedef struct page *pgtable_t;
+
+#define pte_val(x) ((x).pte)
+#define pgd_val(x) ((x).pgd)
+#define pgprot_val(x) ((x).pgprot)
+
+#define __pte(x) ((pte_t) { (x) })
+#define __pgd(x) ((pgd_t) { (x) })
+#define __pgprot(x) ((pgprot_t) { (x) })
+
+#ifdef CONFIG_64BITS
+#define PTE_FMT "%016lx"
+#else
+#define PTE_FMT "%08lx"
+#endif
+
+extern unsigned long va_pa_offset;
+extern unsigned long pfn_base;
+
+extern unsigned long max_low_pfn;
+extern unsigned long min_low_pfn;
+
+#define __pa(x) ((unsigned long)(x) - va_pa_offset)
+#define __va(x) ((void *)((unsigned long) (x) + va_pa_offset))
+
+#define phys_to_pfn(phys) (PFN_DOWN(phys))
+#define pfn_to_phys(pfn) (PFN_PHYS(pfn))
+
+#define virt_to_pfn(vaddr) (phys_to_pfn(__pa(vaddr)))
+#define pfn_to_virt(pfn) (__va(pfn_to_phys(pfn)))
+
+#define virt_to_page(vaddr) (pfn_to_page(virt_to_pfn(vaddr)))
+#define page_to_virt(page) (pfn_to_virt(page_to_pfn(page)))
+
+#define page_to_phys(page) (pfn_to_phys(page_to_pfn(page)))
+#define page_to_bus(page) (page_to_phys(page))
+#define phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr)))
+
+#define pfn_valid(pfn) \
+ (((pfn) >= pfn_base) && (((pfn)-pfn_base) < max_mapnr))
+
+#define ARCH_PFN_OFFSET (pfn_base)
+
+#endif /* __ASSEMBLY__ */
+
+#define virt_addr_valid(vaddr) (pfn_valid(virt_to_pfn(vaddr)))
+
+#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/getorder.h>
+
+/* vDSO support */
+/* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
+#define __HAVE_ARCH_GATE_AREA
+
+#endif /* _ASM_RISCV_PAGE_H */
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
new file mode 100644
index 000000000000..b40074bcb164
--- /dev/null
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGALLOC_H
+#define _ASM_RISCV_PGALLOC_H
+
+#include <linux/mm.h>
+#include <asm/tlb.h>
+
+static inline void pmd_populate_kernel(struct mm_struct *mm,
+ pmd_t *pmd, pte_t *pte)
+{
+ unsigned long pfn = virt_to_pfn(pte);
+
+ set_pmd(pmd, __pmd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+
+static inline void pmd_populate(struct mm_struct *mm,
+ pmd_t *pmd, pgtable_t pte)
+{
+ unsigned long pfn = virt_to_pfn(page_address(pte));
+
+ set_pmd(pmd, __pmd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+
+#ifndef __PAGETABLE_PMD_FOLDED
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+ unsigned long pfn = virt_to_pfn(pmd);
+
+ set_pud(pud, __pud((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+ pgd_t *pgd;
+
+ pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
+ if (likely(pgd != NULL)) {
+ memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
+ /* Copy kernel mappings */
+ memcpy(pgd + USER_PTRS_PER_PGD,
+ init_mm.pgd + USER_PTRS_PER_PGD,
+ (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+ }
+ return pgd;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+ free_page((unsigned long)pgd);
+}
+
+#ifndef __PAGETABLE_PMD_FOLDED
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+ return (pmd_t *)__get_free_page(
+ GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+ free_page((unsigned long)pmd);
+}
+
+#define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd)
+
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+ unsigned long address)
+{
+ return (pte_t *)__get_free_page(
+ GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+}
+
+static inline struct page *pte_alloc_one(struct mm_struct *mm,
+ unsigned long address)
+{
+ struct page *pte;
+
+ pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+ if (likely(pte != NULL))
+ pgtable_page_ctor(pte);
+ return pte;
+}
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+ free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
+{
+ pgtable_page_dtor(pte);
+ __free_page(pte);
+}
+
+#define __pte_free_tlb(tlb, pte, buf) \
+do { \
+ pgtable_page_dtor(pte); \
+ tlb_remove_page((tlb), pte); \
+} while (0)
+
+static inline void check_pgt_cache(void)
+{
+}
+
+#endif /* _ASM_RISCV_PGALLOC_H */
diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h
new file mode 100644
index 000000000000..d61974b74182
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-32.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_32_H
+#define _ASM_RISCV_PGTABLE_32_H
+
+#include <asm-generic/pgtable-nopmd.h>
+#include <linux/const.h>
+
+/* Size of region mapped by a page global directory */
+#define PGDIR_SHIFT 22
+#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE - 1))
+
+#endif /* _ASM_RISCV_PGTABLE_32_H */
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
new file mode 100644
index 000000000000..7aa0ea9bd8bb
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -0,0 +1,84 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_64_H
+#define _ASM_RISCV_PGTABLE_64_H
+
+#include <linux/const.h>
+
+#define PGDIR_SHIFT 30
+/* Size of region mapped by a page global directory */
+#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE - 1))
+
+#define PMD_SHIFT 21
+/* Size of region mapped by a page middle directory */
+#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE - 1))
+
+/* Page Middle Directory entry */
+typedef struct {
+ unsigned long pmd;
+} pmd_t;
+
+#define pmd_val(x) ((x).pmd)
+#define __pmd(x) ((pmd_t) { (x) })
+
+#define PTRS_PER_PMD (PAGE_SIZE / sizeof(pmd_t))
+
+static inline int pud_present(pud_t pud)
+{
+ return (pud_val(pud) & _PAGE_PRESENT);
+}
+
+static inline int pud_none(pud_t pud)
+{
+ return (pud_val(pud) == 0);
+}
+
+static inline int pud_bad(pud_t pud)
+{
+ return !pud_present(pud);
+}
+
+static inline void set_pud(pud_t *pudp, pud_t pud)
+{
+ *pudp = pud;
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+ set_pud(pudp, __pud(0));
+}
+
+static inline unsigned long pud_page_vaddr(pud_t pud)
+{
+ return (unsigned long)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT);
+}
+
+#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+ return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+}
+
+static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot)
+{
+ return __pmd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+#define pmd_ERROR(e) \
+ pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
+
+#endif /* _ASM_RISCV_PGTABLE_64_H */
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
new file mode 100644
index 000000000000..997ddbb1d370
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_BITS_H
+#define _ASM_RISCV_PGTABLE_BITS_H
+
+/*
+ * PTE format:
+ * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0
+ * PFN reserved for SW D A G U X W R V
+ */
+
+#define _PAGE_ACCESSED_OFFSET 6
+
+#define _PAGE_PRESENT (1 << 0)
+#define _PAGE_READ (1 << 1) /* Readable */
+#define _PAGE_WRITE (1 << 2) /* Writable */
+#define _PAGE_EXEC (1 << 3) /* Executable */
+#define _PAGE_USER (1 << 4) /* User */
+#define _PAGE_GLOBAL (1 << 5) /* Global */
+#define _PAGE_ACCESSED (1 << 6) /* Set by hardware on any access */
+#define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */
+#define _PAGE_SOFT (1 << 8) /* Reserved for software */
+
+#define _PAGE_SPECIAL _PAGE_SOFT
+#define _PAGE_TABLE _PAGE_PRESENT
+
+#define _PAGE_PFN_SHIFT 10
+
+/* Set of bits to preserve across pte_modify() */
+#define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \
+ _PAGE_WRITE | _PAGE_EXEC | \
+ _PAGE_USER | _PAGE_GLOBAL))
+
+/* Advertise support for _PAGE_SPECIAL */
+#define __HAVE_ARCH_PTE_SPECIAL
+
+#endif /* _ASM_RISCV_PGTABLE_BITS_H */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
new file mode 100644
index 000000000000..3399257780b2
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable.h
@@ -0,0 +1,430 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_H
+#define _ASM_RISCV_PGTABLE_H
+
+#include <linux/mmzone.h>
+
+#include <asm/pgtable-bits.h>
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_MMU
+
+/* Page Upper Directory not used in RISC-V */
+#include <asm-generic/pgtable-nopud.h>
+#include <asm/page.h>
+#include <asm/tlbflush.h>
+#include <linux/mm_types.h>
+
+#ifdef CONFIG_64BIT
+#include <asm/pgtable-64.h>
+#else
+#include <asm/pgtable-32.h>
+#endif /* CONFIG_64BIT */
+
+/* Number of entries in the page global directory */
+#define PTRS_PER_PGD (PAGE_SIZE / sizeof(pgd_t))
+/* Number of entries in the page table */
+#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t))
+
+/* Number of PGD entries that a user-mode program can use */
+#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)
+#define FIRST_USER_ADDRESS 0
+
+/* Page protection bits */
+#define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER)
+
+#define PAGE_NONE __pgprot(0)
+#define PAGE_READ __pgprot(_PAGE_BASE | _PAGE_READ)
+#define PAGE_WRITE __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE)
+#define PAGE_EXEC __pgprot(_PAGE_BASE | _PAGE_EXEC)
+#define PAGE_READ_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC)
+#define PAGE_WRITE_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | \
+ _PAGE_EXEC | _PAGE_WRITE)
+
+#define PAGE_COPY PAGE_READ
+#define PAGE_COPY_EXEC PAGE_EXEC
+#define PAGE_COPY_READ_EXEC PAGE_READ_EXEC
+#define PAGE_SHARED PAGE_WRITE
+#define PAGE_SHARED_EXEC PAGE_WRITE_EXEC
+
+#define _PAGE_KERNEL (_PAGE_READ \
+ | _PAGE_WRITE \
+ | _PAGE_PRESENT \
+ | _PAGE_ACCESSED \
+ | _PAGE_DIRTY)
+
+#define PAGE_KERNEL __pgprot(_PAGE_KERNEL)
+#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC)
+
+extern pgd_t swapper_pg_dir[];
+
+/* MAP_PRIVATE permissions: xwr (copy-on-write) */
+#define __P000 PAGE_NONE
+#define __P001 PAGE_READ
+#define __P010 PAGE_COPY
+#define __P011 PAGE_COPY
+#define __P100 PAGE_EXEC
+#define __P101 PAGE_READ_EXEC
+#define __P110 PAGE_COPY_EXEC
+#define __P111 PAGE_COPY_READ_EXEC
+
+/* MAP_SHARED permissions: xwr */
+#define __S000 PAGE_NONE
+#define __S001 PAGE_READ
+#define __S010 PAGE_SHARED
+#define __S011 PAGE_SHARED
+#define __S100 PAGE_EXEC
+#define __S101 PAGE_READ_EXEC
+#define __S110 PAGE_SHARED_EXEC
+#define __S111 PAGE_SHARED_EXEC
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero,
+ * used for zero-mapped memory areas, etc.
+ */
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+static inline int pmd_present(pmd_t pmd)
+{
+ return (pmd_val(pmd) & _PAGE_PRESENT);
+}
+
+static inline int pmd_none(pmd_t pmd)
+{
+ return (pmd_val(pmd) == 0);
+}
+
+static inline int pmd_bad(pmd_t pmd)
+{
+ return !pmd_present(pmd);
+}
+
+static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+ *pmdp = pmd;
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+ set_pmd(pmdp, __pmd(0));
+}
+
+
+static inline pgd_t pfn_pgd(unsigned long pfn, pgprot_t prot)
+{
+ return __pgd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+#define pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
+
+/* Locate an entry in the page global directory */
+static inline pgd_t *pgd_offset(const struct mm_struct *mm, unsigned long addr)
+{
+ return mm->pgd + pgd_index(addr);
+}
+/* Locate an entry in the kernel page global directory */
+#define pgd_offset_k(addr) pgd_offset(&init_mm, (addr))
+
+static inline struct page *pmd_page(pmd_t pmd)
+{
+ return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT);
+}
+
+static inline unsigned long pmd_page_vaddr(pmd_t pmd)
+{
+ return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT);
+}
+
+/* Yields the page frame number (PFN) of a page table entry */
+static inline unsigned long pte_pfn(pte_t pte)
+{
+ return (pte_val(pte) >> _PAGE_PFN_SHIFT);
+}
+
+#define pte_page(x) pfn_to_page(pte_pfn(x))
+
+/* Constructs a page table entry */
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
+{
+ return __pte((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+static inline pte_t mk_pte(struct page *page, pgprot_t prot)
+{
+ return pfn_pte(page_to_pfn(page), prot);
+}
+
+#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+
+static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr)
+{
+ return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(addr);
+}
+
+#define pte_offset_map(dir, addr) pte_offset_kernel((dir), (addr))
+#define pte_unmap(pte) ((void)(pte))
+
+/*
+ * Certain architectures need to do special things when PTEs within
+ * a page table are directly modified. Thus, the following hook is
+ * made available.
+ */
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+ *ptep = pteval;
+}
+
+static inline void set_pte_at(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep, pte_t pteval)
+{
+ set_pte(ptep, pteval);
+}
+
+static inline void pte_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ set_pte_at(mm, addr, ptep, __pte(0));
+}
+
+static inline int pte_present(pte_t pte)
+{
+ return (pte_val(pte) & _PAGE_PRESENT);
+}
+
+static inline int pte_none(pte_t pte)
+{
+ return (pte_val(pte) == 0);
+}
+
+/* static inline int pte_read(pte_t pte) */
+
+static inline int pte_write(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_WRITE;
+}
+
+static inline int pte_huge(pte_t pte)
+{
+ return pte_present(pte)
+ && (pte_val(pte) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
+}
+
+/* static inline int pte_exec(pte_t pte) */
+
+static inline int pte_dirty(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_DIRTY;
+}
+
+static inline int pte_young(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_ACCESSED;
+}
+
+static inline int pte_special(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_SPECIAL;
+}
+
+/* static inline pte_t pte_rdprotect(pte_t pte) */
+
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+ return __pte(pte_val(pte) & ~(_PAGE_WRITE));
+}
+
+/* static inline pte_t pte_mkread(pte_t pte) */
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_WRITE);
+}
+
+/* static inline pte_t pte_mkexec(pte_t pte) */
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+ return __pte(pte_val(pte) & ~(_PAGE_DIRTY));
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+ return __pte(pte_val(pte) & ~(_PAGE_ACCESSED));
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_SPECIAL);
+}
+
+/* Modify page protection bits */
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+ return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+}
+
+#define pgd_ERROR(e) \
+ pr_err("%s:%d: bad pgd " PTE_FMT ".\n", __FILE__, __LINE__, pgd_val(e))
+
+
+/* Commit new configuration to MMU hardware */
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep)
+{
+ /*
+ * The kernel assumes that TLBs don't cache invalid entries, but
+ * in RISC-V, SFENCE.VMA specifies an ordering constraint, not a
+ * cache flush; it is necessary even after writing invalid entries.
+ * Relying on flush_tlb_fix_spurious_fault would suffice, but
+ * the extra traps reduce performance. So, eagerly SFENCE.VMA.
+ */
+ local_flush_tlb_page(address);
+}
+
+#define __HAVE_ARCH_PTE_SAME
+static inline int pte_same(pte_t pte_a, pte_t pte_b)
+{
+ return pte_val(pte_a) == pte_val(pte_b);
+}
+
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+static inline int ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep,
+ pte_t entry, int dirty)
+{
+ if (!pte_same(*ptep, entry))
+ set_pte_at(vma->vm_mm, address, ptep, entry);
+ /*
+ * update_mmu_cache will unconditionally execute, handling both
+ * the case that the PTE changed and the spurious fault case.
+ */
+ return true;
+}
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long address, pte_t *ptep)
+{
+ return __pte(atomic_long_xchg((atomic_long_t *)ptep, 0));
+}
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+ unsigned long address,
+ pte_t *ptep)
+{
+ if (!pte_young(*ptep))
+ return 0;
+ return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm,
+ unsigned long address, pte_t *ptep)
+{
+ atomic_long_and(~(unsigned long)_PAGE_WRITE, (atomic_long_t *)ptep);
+}
+
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep)
+{
+ /*
+ * This comment is borrowed from x86, but applies equally to RISC-V:
+ *
+ * Clearing the accessed bit without a TLB flush
+ * doesn't cause data corruption. [ It could cause incorrect
+ * page aging and the (mistaken) reclaim of hot pages, but the
+ * chance of that should be relatively low. ]
+ *
+ * So as a performance optimization don't flush the TLB when
+ * clearing the accessed bit, it will eventually be flushed by
+ * a context switch or a VM operation anyway. [ In the rare
+ * event of it not getting flushed for a long time the delay
+ * shouldn't really matter because there's no real memory
+ * pressure for swapout to react to. ]
+ */
+ return ptep_test_and_clear_young(vma, address, ptep);
+}
+
+/*
+ * Encode and decode a swap entry
+ *
+ * Format of swap PTE:
+ * bit 0: _PAGE_PRESENT (zero)
+ * bit 1: reserved for future use (zero)
+ * bits 2 to 6: swap type
+ * bits 7 to XLEN-1: swap offset
+ */
+#define __SWP_TYPE_SHIFT 2
+#define __SWP_TYPE_BITS 5
+#define __SWP_TYPE_MASK ((1UL << __SWP_TYPE_BITS) - 1)
+#define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
+
+#define MAX_SWAPFILES_CHECK() \
+ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
+
+#define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
+#define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT)
+#define __swp_entry(type, offset) ((swp_entry_t) \
+ { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
+
+#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
+
+#ifdef CONFIG_FLATMEM
+#define kern_addr_valid(addr) (1) /* FIXME */
+#endif
+
+extern void paging_init(void);
+
+static inline void pgtable_cache_init(void)
+{
+ /* No page table caches to initialize */
+}
+
+#endif /* CONFIG_MMU */
+
+#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1)
+#define VMALLOC_END (PAGE_OFFSET - 1)
+#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE)
+
+/*
+ * Task size is 0x40000000000 for RV64 or 0xb800000 for RV32.
+ * Note that PGDIR_SIZE must evenly divide TASK_SIZE.
+ */
+#ifdef CONFIG_64BIT
+#define TASK_SIZE (PGDIR_SIZE * PTRS_PER_PGD / 2)
+#else
+#define TASK_SIZE VMALLOC_START
+#endif
+
+#include <asm-generic/pgtable.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PGTABLE_H */
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
new file mode 100644
index 000000000000..df2ca3c65048
--- /dev/null
+++ b/arch/riscv/mm/fault.c
@@ -0,0 +1,282 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+
+#include <linux/mm.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/perf_event.h>
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+
+#include <asm/pgalloc.h>
+#include <asm/ptrace.h>
+#include <asm/uaccess.h>
+
+/*
+ * This routine handles page faults. It determines the address and the
+ * problem, and then passes it off to one of the appropriate routines.
+ */
+asmlinkage void do_page_fault(struct pt_regs *regs)
+{
+ struct task_struct *tsk;
+ struct vm_area_struct *vma;
+ struct mm_struct *mm;
+ unsigned long addr, cause;
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ int fault, code = SEGV_MAPERR;
+
+ cause = regs->scause;
+ addr = regs->sbadaddr;
+
+ tsk = current;
+ mm = tsk->mm;
+
+ /*
+ * Fault-in kernel-space virtual memory on-demand.
+ * The 'reference' page table is init_mm.pgd.
+ *
+ * NOTE! We MUST NOT take any locks for this case. We may
+ * be in an interrupt or a critical region, and should
+ * only copy the information from the master page table,
+ * nothing more.
+ */
+ if (unlikely((addr >= VMALLOC_START) && (addr <= VMALLOC_END)))
+ goto vmalloc_fault;
+
+ /* Enable interrupts if they were enabled in the parent context. */
+ if (likely(regs->sstatus & SR_PIE))
+ local_irq_enable();
+
+ /*
+ * If we're in an interrupt, have no user context, or are running
+ * in an atomic region, then we must not take the fault.
+ */
+ if (unlikely(faulthandler_disabled() || !mm))
+ goto no_context;
+
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
+retry:
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, addr);
+ if (unlikely(!vma))
+ goto bad_area;
+ if (likely(vma->vm_start <= addr))
+ goto good_area;
+ if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
+ goto bad_area;
+ if (unlikely(expand_stack(vma, addr)))
+ goto bad_area;
+
+ /*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it.
+ */
+good_area:
+ code = SEGV_ACCERR;
+
+ switch (cause) {
+ case EXC_INST_PAGE_FAULT:
+ if (!(vma->vm_flags & VM_EXEC))
+ goto bad_area;
+ break;
+ case EXC_LOAD_PAGE_FAULT:
+ if (!(vma->vm_flags & VM_READ))
+ goto bad_area;
+ break;
+ case EXC_STORE_PAGE_FAULT:
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
+ break;
+ default:
+ panic("%s: unhandled cause %lu", __func__, cause);
+ }
+
+ /*
+ * If for any reason at all we could not handle the fault,
+ * make sure we exit gracefully rather than endlessly redo
+ * the fault.
+ */
+ fault = handle_mm_fault(vma, addr, flags);
+
+ /*
+ * If we need to retry but a fatal signal is pending, handle the
+ * signal first. We do not need to release the mmap_sem because it
+ * would already be released in __lock_page_or_retry in mm/filemap.c.
+ */
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(tsk))
+ return;
+
+ if (unlikely(fault & VM_FAULT_ERROR)) {
+ if (fault & VM_FAULT_OOM)
+ goto out_of_memory;
+ else if (fault & VM_FAULT_SIGBUS)
+ goto do_sigbus;
+ BUG();
+ }
+
+ /*
+ * Major/minor page fault accounting is only done on the
+ * initial attempt. If we go through a retry, it is extremely
+ * likely that the page will be found in page cache at that point.
+ */
+ if (flags & FAULT_FLAG_ALLOW_RETRY) {
+ if (fault & VM_FAULT_MAJOR) {
+ tsk->maj_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
+ 1, regs, addr);
+ } else {
+ tsk->min_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
+ 1, regs, addr);
+ }
+ if (fault & VM_FAULT_RETRY) {
+ /*
+ * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+ * of starvation.
+ */
+ flags &= ~(FAULT_FLAG_ALLOW_RETRY);
+ flags |= FAULT_FLAG_TRIED;
+
+ /*
+ * No need to up_read(&mm->mmap_sem) as we would
+ * have already released it in __lock_page_or_retry
+ * in mm/filemap.c.
+ */
+ goto retry;
+ }
+ }
+
+ up_read(&mm->mmap_sem);
+ return;
+
+ /*
+ * Something tried to access memory that isn't in our memory map.
+ * Fix it, but check if it's kernel or user first.
+ */
+bad_area:
+ up_read(&mm->mmap_sem);
+ /* User mode accesses just cause a SIGSEGV */
+ if (user_mode(regs)) {
+ do_trap(regs, SIGSEGV, code, addr, tsk);
+ return;
+ }
+
+no_context:
+ /* Are we prepared to handle this kernel fault? */
+ if (fixup_exception(regs))
+ return;
+
+ /*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+ bust_spinlocks(1);
+ pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n",
+ (addr < PAGE_SIZE) ? "NULL pointer dereference" :
+ "paging request", addr);
+ die(regs, "Oops");
+ do_exit(SIGKILL);
+
+ /*
+ * We ran out of memory, call the OOM killer, and return the userspace
+ * (which will retry the fault, or kill us if we got oom-killed).
+ */
+out_of_memory:
+ up_read(&mm->mmap_sem);
+ if (!user_mode(regs))
+ goto no_context;
+ pagefault_out_of_memory();
+ return;
+
+do_sigbus:
+ up_read(&mm->mmap_sem);
+ /* Kernel mode? Handle exceptions or die */
+ if (!user_mode(regs))
+ goto no_context;
+ do_trap(regs, SIGBUS, BUS_ADRERR, addr, tsk);
+ return;
+
+vmalloc_fault:
+ {
+ pgd_t *pgd, *pgd_k;
+ pud_t *pud, *pud_k;
+ p4d_t *p4d, *p4d_k;
+ pmd_t *pmd, *pmd_k;
+ pte_t *pte_k;
+ int index;
+
+ if (user_mode(regs))
+ goto bad_area;
+
+ /*
+ * Synchronize this task's top level page-table
+ * with the 'reference' page table.
+ *
+ * Do _not_ use "tsk->active_mm->pgd" here.
+ * We might be inside an interrupt in the middle
+ * of a task switch.
+ */
+ index = pgd_index(addr);
+ pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr)) + index;
+ pgd_k = init_mm.pgd + index;
+
+ if (!pgd_present(*pgd_k))
+ goto no_context;
+ set_pgd(pgd, *pgd_k);
+
+ p4d = p4d_offset(pgd, addr);
+ p4d_k = p4d_offset(pgd_k, addr);
+ if (!p4d_present(*p4d_k))
+ goto no_context;
+
+ pud = pud_offset(p4d, addr);
+ pud_k = pud_offset(p4d_k, addr);
+ if (!pud_present(*pud_k))
+ goto no_context;
+
+ /*
+ * Since the vmalloc area is global, it is unnecessary
+ * to copy individual PTEs
+ */
+ pmd = pmd_offset(pud, addr);
+ pmd_k = pmd_offset(pud_k, addr);
+ if (!pmd_present(*pmd_k))
+ goto no_context;
+ set_pmd(pmd, *pmd_k);
+
+ /*
+ * Make sure the actual PTE exists as well to
+ * catch kernel vmalloc-area accesses to non-mapped
+ * addresses. If we don't do this, this will just
+ * silently loop forever.
+ */
+ pte_k = pte_offset_kernel(pmd_k, addr);
+ if (!pte_present(*pte_k))
+ goto no_context;
+ return;
+ }
+}
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread
* [PATCH 7/9] RISC-V: Paging and MMU
2017-07-04 19:50 ` Palmer Dabbelt
` (10 preceding siblings ...)
(?)
@ 2017-07-04 19:51 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:51 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains code to manage the RISC-V MMU, including definitions
of the page tables and the page walking code.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/mmu_context.h | 69 ++++++
arch/riscv/include/asm/page.h | 134 +++++++++++
arch/riscv/include/asm/pgalloc.h | 124 ++++++++++
arch/riscv/include/asm/pgtable-32.h | 25 ++
arch/riscv/include/asm/pgtable-64.h | 84 +++++++
arch/riscv/include/asm/pgtable-bits.h | 48 ++++
arch/riscv/include/asm/pgtable.h | 430 ++++++++++++++++++++++++++++++++++
arch/riscv/mm/fault.c | 282 ++++++++++++++++++++++
8 files changed, 1196 insertions(+)
create mode 100644 arch/riscv/include/asm/mmu_context.h
create mode 100644 arch/riscv/include/asm/page.h
create mode 100644 arch/riscv/include/asm/pgalloc.h
create mode 100644 arch/riscv/include/asm/pgtable-32.h
create mode 100644 arch/riscv/include/asm/pgtable-64.h
create mode 100644 arch/riscv/include/asm/pgtable-bits.h
create mode 100644 arch/riscv/include/asm/pgtable.h
create mode 100644 arch/riscv/mm/fault.c
diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
new file mode 100644
index 000000000000..de1fc1631fc4
--- /dev/null
+++ b/arch/riscv/include/asm/mmu_context.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_MMU_CONTEXT_H
+#define _ASM_RISCV_MMU_CONTEXT_H
+
+#include <asm-generic/mm_hooks.h>
+
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <asm/tlbflush.h>
+
+static inline void enter_lazy_tlb(struct mm_struct *mm,
+ struct task_struct *task)
+{
+}
+
+/* Initialize context-related info for a new mm_struct */
+static inline int init_new_context(struct task_struct *task,
+ struct mm_struct *mm)
+{
+ return 0;
+}
+
+static inline void destroy_context(struct mm_struct *mm)
+{
+}
+
+static inline pgd_t *current_pgdir(void)
+{
+ return pfn_to_virt(csr_read(sptbr) & SPTBR_PPN);
+}
+
+static inline void set_pgdir(pgd_t *pgd)
+{
+ csr_write(sptbr, virt_to_pfn(pgd) | SPTBR_MODE);
+}
+
+static inline void switch_mm(struct mm_struct *prev,
+ struct mm_struct *next, struct task_struct *task)
+{
+ if (likely(prev != next)) {
+ set_pgdir(next->pgd);
+ local_flush_tlb_all();
+ }
+}
+
+static inline void activate_mm(struct mm_struct *prev,
+ struct mm_struct *next)
+{
+ switch_mm(prev, next, NULL);
+}
+
+static inline void deactivate_mm(struct task_struct *task,
+ struct mm_struct *mm)
+{
+}
+
+#endif /* _ASM_RISCV_MMU_CONTEXT_H */
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
new file mode 100644
index 000000000000..5bbbff2d5a60
--- /dev/null
+++ b/arch/riscv/include/asm/page.h
@@ -0,0 +1,134 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ * Copyright (C) 2017 XiaojingZhu <zhuxiaoj@ict.ac.cn>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PAGE_H
+#define _ASM_RISCV_PAGE_H
+
+#include <linux/pfn.h>
+#include <linux/const.h>
+
+#define PAGE_SHIFT (12)
+#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE - 1))
+
+/*
+ * PAGE_OFFSET -- the first address of the first page of memory.
+ * When not using MMU this corresponds to the first free page in
+ * physical memory (aligned on a page boundary).
+ */
+#ifdef CONFIG_64BIT
+#define PAGE_OFFSET _AC(0xffffffff80000000, UL)
+#else
+#define PAGE_OFFSET _AC(0xc0000000, UL)
+#endif
+
+#define KERN_VIRT_SIZE (-PAGE_OFFSET)
+
+#ifndef __ASSEMBLY__
+
+#define PAGE_UP(addr) (((addr)+((PAGE_SIZE)-1))&(~((PAGE_SIZE)-1)))
+#define PAGE_DOWN(addr) ((addr)&(~((PAGE_SIZE)-1)))
+
+/* align addr on a size boundary - adjust address up/down if needed */
+#define _ALIGN_UP(addr, size) (((addr)+((size)-1))&(~((size)-1)))
+#define _ALIGN_DOWN(addr, size) ((addr)&(~((size)-1)))
+
+/* align addr on a size boundary - adjust address up if needed */
+#define _ALIGN(addr, size) _ALIGN_UP(addr, size)
+
+#define clear_page(pgaddr) memset((pgaddr), 0, PAGE_SIZE)
+#define copy_page(to, from) memcpy((to), (from), PAGE_SIZE)
+
+#define clear_user_page(pgaddr, vaddr, page) memset((pgaddr), 0, PAGE_SIZE)
+#define copy_user_page(vto, vfrom, vaddr, topg) \
+ memcpy((vto), (vfrom), PAGE_SIZE)
+
+/*
+ * Use struct definitions to apply C type checking
+ */
+
+/* Page Global Directory entry */
+typedef struct {
+ unsigned long pgd;
+} pgd_t;
+
+/* Page Table entry */
+typedef struct {
+ unsigned long pte;
+} pte_t;
+
+typedef struct {
+ unsigned long pgprot;
+} pgprot_t;
+
+typedef struct page *pgtable_t;
+
+#define pte_val(x) ((x).pte)
+#define pgd_val(x) ((x).pgd)
+#define pgprot_val(x) ((x).pgprot)
+
+#define __pte(x) ((pte_t) { (x) })
+#define __pgd(x) ((pgd_t) { (x) })
+#define __pgprot(x) ((pgprot_t) { (x) })
+
+#ifdef CONFIG_64BITS
+#define PTE_FMT "%016lx"
+#else
+#define PTE_FMT "%08lx"
+#endif
+
+extern unsigned long va_pa_offset;
+extern unsigned long pfn_base;
+
+extern unsigned long max_low_pfn;
+extern unsigned long min_low_pfn;
+
+#define __pa(x) ((unsigned long)(x) - va_pa_offset)
+#define __va(x) ((void *)((unsigned long) (x) + va_pa_offset))
+
+#define phys_to_pfn(phys) (PFN_DOWN(phys))
+#define pfn_to_phys(pfn) (PFN_PHYS(pfn))
+
+#define virt_to_pfn(vaddr) (phys_to_pfn(__pa(vaddr)))
+#define pfn_to_virt(pfn) (__va(pfn_to_phys(pfn)))
+
+#define virt_to_page(vaddr) (pfn_to_page(virt_to_pfn(vaddr)))
+#define page_to_virt(page) (pfn_to_virt(page_to_pfn(page)))
+
+#define page_to_phys(page) (pfn_to_phys(page_to_pfn(page)))
+#define page_to_bus(page) (page_to_phys(page))
+#define phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr)))
+
+#define pfn_valid(pfn) \
+ (((pfn) >= pfn_base) && (((pfn)-pfn_base) < max_mapnr))
+
+#define ARCH_PFN_OFFSET (pfn_base)
+
+#endif /* __ASSEMBLY__ */
+
+#define virt_addr_valid(vaddr) (pfn_valid(virt_to_pfn(vaddr)))
+
+#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/getorder.h>
+
+/* vDSO support */
+/* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
+#define __HAVE_ARCH_GATE_AREA
+
+#endif /* _ASM_RISCV_PAGE_H */
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
new file mode 100644
index 000000000000..b40074bcb164
--- /dev/null
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2009 Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGALLOC_H
+#define _ASM_RISCV_PGALLOC_H
+
+#include <linux/mm.h>
+#include <asm/tlb.h>
+
+static inline void pmd_populate_kernel(struct mm_struct *mm,
+ pmd_t *pmd, pte_t *pte)
+{
+ unsigned long pfn = virt_to_pfn(pte);
+
+ set_pmd(pmd, __pmd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+
+static inline void pmd_populate(struct mm_struct *mm,
+ pmd_t *pmd, pgtable_t pte)
+{
+ unsigned long pfn = virt_to_pfn(page_address(pte));
+
+ set_pmd(pmd, __pmd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+
+#ifndef __PAGETABLE_PMD_FOLDED
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+ unsigned long pfn = virt_to_pfn(pmd);
+
+ set_pud(pud, __pud((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+}
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+ pgd_t *pgd;
+
+ pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
+ if (likely(pgd != NULL)) {
+ memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
+ /* Copy kernel mappings */
+ memcpy(pgd + USER_PTRS_PER_PGD,
+ init_mm.pgd + USER_PTRS_PER_PGD,
+ (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+ }
+ return pgd;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+ free_page((unsigned long)pgd);
+}
+
+#ifndef __PAGETABLE_PMD_FOLDED
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+ return (pmd_t *)__get_free_page(
+ GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+ free_page((unsigned long)pmd);
+}
+
+#define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd)
+
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+ unsigned long address)
+{
+ return (pte_t *)__get_free_page(
+ GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+}
+
+static inline struct page *pte_alloc_one(struct mm_struct *mm,
+ unsigned long address)
+{
+ struct page *pte;
+
+ pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+ if (likely(pte != NULL))
+ pgtable_page_ctor(pte);
+ return pte;
+}
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+ free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
+{
+ pgtable_page_dtor(pte);
+ __free_page(pte);
+}
+
+#define __pte_free_tlb(tlb, pte, buf) \
+do { \
+ pgtable_page_dtor(pte); \
+ tlb_remove_page((tlb), pte); \
+} while (0)
+
+static inline void check_pgt_cache(void)
+{
+}
+
+#endif /* _ASM_RISCV_PGALLOC_H */
diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h
new file mode 100644
index 000000000000..d61974b74182
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-32.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_32_H
+#define _ASM_RISCV_PGTABLE_32_H
+
+#include <asm-generic/pgtable-nopmd.h>
+#include <linux/const.h>
+
+/* Size of region mapped by a page global directory */
+#define PGDIR_SHIFT 22
+#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE - 1))
+
+#endif /* _ASM_RISCV_PGTABLE_32_H */
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
new file mode 100644
index 000000000000..7aa0ea9bd8bb
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -0,0 +1,84 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_64_H
+#define _ASM_RISCV_PGTABLE_64_H
+
+#include <linux/const.h>
+
+#define PGDIR_SHIFT 30
+/* Size of region mapped by a page global directory */
+#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE - 1))
+
+#define PMD_SHIFT 21
+/* Size of region mapped by a page middle directory */
+#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE - 1))
+
+/* Page Middle Directory entry */
+typedef struct {
+ unsigned long pmd;
+} pmd_t;
+
+#define pmd_val(x) ((x).pmd)
+#define __pmd(x) ((pmd_t) { (x) })
+
+#define PTRS_PER_PMD (PAGE_SIZE / sizeof(pmd_t))
+
+static inline int pud_present(pud_t pud)
+{
+ return (pud_val(pud) & _PAGE_PRESENT);
+}
+
+static inline int pud_none(pud_t pud)
+{
+ return (pud_val(pud) == 0);
+}
+
+static inline int pud_bad(pud_t pud)
+{
+ return !pud_present(pud);
+}
+
+static inline void set_pud(pud_t *pudp, pud_t pud)
+{
+ *pudp = pud;
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+ set_pud(pudp, __pud(0));
+}
+
+static inline unsigned long pud_page_vaddr(pud_t pud)
+{
+ return (unsigned long)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT);
+}
+
+#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+ return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+}
+
+static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot)
+{
+ return __pmd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+#define pmd_ERROR(e) \
+ pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
+
+#endif /* _ASM_RISCV_PGTABLE_64_H */
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
new file mode 100644
index 000000000000..997ddbb1d370
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_BITS_H
+#define _ASM_RISCV_PGTABLE_BITS_H
+
+/*
+ * PTE format:
+ * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0
+ * PFN reserved for SW D A G U X W R V
+ */
+
+#define _PAGE_ACCESSED_OFFSET 6
+
+#define _PAGE_PRESENT (1 << 0)
+#define _PAGE_READ (1 << 1) /* Readable */
+#define _PAGE_WRITE (1 << 2) /* Writable */
+#define _PAGE_EXEC (1 << 3) /* Executable */
+#define _PAGE_USER (1 << 4) /* User */
+#define _PAGE_GLOBAL (1 << 5) /* Global */
+#define _PAGE_ACCESSED (1 << 6) /* Set by hardware on any access */
+#define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */
+#define _PAGE_SOFT (1 << 8) /* Reserved for software */
+
+#define _PAGE_SPECIAL _PAGE_SOFT
+#define _PAGE_TABLE _PAGE_PRESENT
+
+#define _PAGE_PFN_SHIFT 10
+
+/* Set of bits to preserve across pte_modify() */
+#define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \
+ _PAGE_WRITE | _PAGE_EXEC | \
+ _PAGE_USER | _PAGE_GLOBAL))
+
+/* Advertise support for _PAGE_SPECIAL */
+#define __HAVE_ARCH_PTE_SPECIAL
+
+#endif /* _ASM_RISCV_PGTABLE_BITS_H */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
new file mode 100644
index 000000000000..3399257780b2
--- /dev/null
+++ b/arch/riscv/include/asm/pgtable.h
@@ -0,0 +1,430 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PGTABLE_H
+#define _ASM_RISCV_PGTABLE_H
+
+#include <linux/mmzone.h>
+
+#include <asm/pgtable-bits.h>
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_MMU
+
+/* Page Upper Directory not used in RISC-V */
+#include <asm-generic/pgtable-nopud.h>
+#include <asm/page.h>
+#include <asm/tlbflush.h>
+#include <linux/mm_types.h>
+
+#ifdef CONFIG_64BIT
+#include <asm/pgtable-64.h>
+#else
+#include <asm/pgtable-32.h>
+#endif /* CONFIG_64BIT */
+
+/* Number of entries in the page global directory */
+#define PTRS_PER_PGD (PAGE_SIZE / sizeof(pgd_t))
+/* Number of entries in the page table */
+#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t))
+
+/* Number of PGD entries that a user-mode program can use */
+#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)
+#define FIRST_USER_ADDRESS 0
+
+/* Page protection bits */
+#define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER)
+
+#define PAGE_NONE __pgprot(0)
+#define PAGE_READ __pgprot(_PAGE_BASE | _PAGE_READ)
+#define PAGE_WRITE __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE)
+#define PAGE_EXEC __pgprot(_PAGE_BASE | _PAGE_EXEC)
+#define PAGE_READ_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC)
+#define PAGE_WRITE_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | \
+ _PAGE_EXEC | _PAGE_WRITE)
+
+#define PAGE_COPY PAGE_READ
+#define PAGE_COPY_EXEC PAGE_EXEC
+#define PAGE_COPY_READ_EXEC PAGE_READ_EXEC
+#define PAGE_SHARED PAGE_WRITE
+#define PAGE_SHARED_EXEC PAGE_WRITE_EXEC
+
+#define _PAGE_KERNEL (_PAGE_READ \
+ | _PAGE_WRITE \
+ | _PAGE_PRESENT \
+ | _PAGE_ACCESSED \
+ | _PAGE_DIRTY)
+
+#define PAGE_KERNEL __pgprot(_PAGE_KERNEL)
+#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC)
+
+extern pgd_t swapper_pg_dir[];
+
+/* MAP_PRIVATE permissions: xwr (copy-on-write) */
+#define __P000 PAGE_NONE
+#define __P001 PAGE_READ
+#define __P010 PAGE_COPY
+#define __P011 PAGE_COPY
+#define __P100 PAGE_EXEC
+#define __P101 PAGE_READ_EXEC
+#define __P110 PAGE_COPY_EXEC
+#define __P111 PAGE_COPY_READ_EXEC
+
+/* MAP_SHARED permissions: xwr */
+#define __S000 PAGE_NONE
+#define __S001 PAGE_READ
+#define __S010 PAGE_SHARED
+#define __S011 PAGE_SHARED
+#define __S100 PAGE_EXEC
+#define __S101 PAGE_READ_EXEC
+#define __S110 PAGE_SHARED_EXEC
+#define __S111 PAGE_SHARED_EXEC
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero,
+ * used for zero-mapped memory areas, etc.
+ */
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+static inline int pmd_present(pmd_t pmd)
+{
+ return (pmd_val(pmd) & _PAGE_PRESENT);
+}
+
+static inline int pmd_none(pmd_t pmd)
+{
+ return (pmd_val(pmd) == 0);
+}
+
+static inline int pmd_bad(pmd_t pmd)
+{
+ return !pmd_present(pmd);
+}
+
+static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+ *pmdp = pmd;
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+ set_pmd(pmdp, __pmd(0));
+}
+
+
+static inline pgd_t pfn_pgd(unsigned long pfn, pgprot_t prot)
+{
+ return __pgd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+#define pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
+
+/* Locate an entry in the page global directory */
+static inline pgd_t *pgd_offset(const struct mm_struct *mm, unsigned long addr)
+{
+ return mm->pgd + pgd_index(addr);
+}
+/* Locate an entry in the kernel page global directory */
+#define pgd_offset_k(addr) pgd_offset(&init_mm, (addr))
+
+static inline struct page *pmd_page(pmd_t pmd)
+{
+ return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT);
+}
+
+static inline unsigned long pmd_page_vaddr(pmd_t pmd)
+{
+ return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT);
+}
+
+/* Yields the page frame number (PFN) of a page table entry */
+static inline unsigned long pte_pfn(pte_t pte)
+{
+ return (pte_val(pte) >> _PAGE_PFN_SHIFT);
+}
+
+#define pte_page(x) pfn_to_page(pte_pfn(x))
+
+/* Constructs a page table entry */
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
+{
+ return __pte((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+static inline pte_t mk_pte(struct page *page, pgprot_t prot)
+{
+ return pfn_pte(page_to_pfn(page), prot);
+}
+
+#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+
+static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr)
+{
+ return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(addr);
+}
+
+#define pte_offset_map(dir, addr) pte_offset_kernel((dir), (addr))
+#define pte_unmap(pte) ((void)(pte))
+
+/*
+ * Certain architectures need to do special things when PTEs within
+ * a page table are directly modified. Thus, the following hook is
+ * made available.
+ */
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+ *ptep = pteval;
+}
+
+static inline void set_pte_at(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep, pte_t pteval)
+{
+ set_pte(ptep, pteval);
+}
+
+static inline void pte_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ set_pte_at(mm, addr, ptep, __pte(0));
+}
+
+static inline int pte_present(pte_t pte)
+{
+ return (pte_val(pte) & _PAGE_PRESENT);
+}
+
+static inline int pte_none(pte_t pte)
+{
+ return (pte_val(pte) == 0);
+}
+
+/* static inline int pte_read(pte_t pte) */
+
+static inline int pte_write(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_WRITE;
+}
+
+static inline int pte_huge(pte_t pte)
+{
+ return pte_present(pte)
+ && (pte_val(pte) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
+}
+
+/* static inline int pte_exec(pte_t pte) */
+
+static inline int pte_dirty(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_DIRTY;
+}
+
+static inline int pte_young(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_ACCESSED;
+}
+
+static inline int pte_special(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_SPECIAL;
+}
+
+/* static inline pte_t pte_rdprotect(pte_t pte) */
+
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+ return __pte(pte_val(pte) & ~(_PAGE_WRITE));
+}
+
+/* static inline pte_t pte_mkread(pte_t pte) */
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_WRITE);
+}
+
+/* static inline pte_t pte_mkexec(pte_t pte) */
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+ return __pte(pte_val(pte) & ~(_PAGE_DIRTY));
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+ return __pte(pte_val(pte) & ~(_PAGE_ACCESSED));
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_SPECIAL);
+}
+
+/* Modify page protection bits */
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+ return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+}
+
+#define pgd_ERROR(e) \
+ pr_err("%s:%d: bad pgd " PTE_FMT ".\n", __FILE__, __LINE__, pgd_val(e))
+
+
+/* Commit new configuration to MMU hardware */
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep)
+{
+ /*
+ * The kernel assumes that TLBs don't cache invalid entries, but
+ * in RISC-V, SFENCE.VMA specifies an ordering constraint, not a
+ * cache flush; it is necessary even after writing invalid entries.
+ * Relying on flush_tlb_fix_spurious_fault would suffice, but
+ * the extra traps reduce performance. So, eagerly SFENCE.VMA.
+ */
+ local_flush_tlb_page(address);
+}
+
+#define __HAVE_ARCH_PTE_SAME
+static inline int pte_same(pte_t pte_a, pte_t pte_b)
+{
+ return pte_val(pte_a) == pte_val(pte_b);
+}
+
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+static inline int ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep,
+ pte_t entry, int dirty)
+{
+ if (!pte_same(*ptep, entry))
+ set_pte_at(vma->vm_mm, address, ptep, entry);
+ /*
+ * update_mmu_cache will unconditionally execute, handling both
+ * the case that the PTE changed and the spurious fault case.
+ */
+ return true;
+}
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long address, pte_t *ptep)
+{
+ return __pte(atomic_long_xchg((atomic_long_t *)ptep, 0));
+}
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+ unsigned long address,
+ pte_t *ptep)
+{
+ if (!pte_young(*ptep))
+ return 0;
+ return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm,
+ unsigned long address, pte_t *ptep)
+{
+ atomic_long_and(~(unsigned long)_PAGE_WRITE, (atomic_long_t *)ptep);
+}
+
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep)
+{
+ /*
+ * This comment is borrowed from x86, but applies equally to RISC-V:
+ *
+ * Clearing the accessed bit without a TLB flush
+ * doesn't cause data corruption. [ It could cause incorrect
+ * page aging and the (mistaken) reclaim of hot pages, but the
+ * chance of that should be relatively low. ]
+ *
+ * So as a performance optimization don't flush the TLB when
+ * clearing the accessed bit, it will eventually be flushed by
+ * a context switch or a VM operation anyway. [ In the rare
+ * event of it not getting flushed for a long time the delay
+ * shouldn't really matter because there's no real memory
+ * pressure for swapout to react to. ]
+ */
+ return ptep_test_and_clear_young(vma, address, ptep);
+}
+
+/*
+ * Encode and decode a swap entry
+ *
+ * Format of swap PTE:
+ * bit 0: _PAGE_PRESENT (zero)
+ * bit 1: reserved for future use (zero)
+ * bits 2 to 6: swap type
+ * bits 7 to XLEN-1: swap offset
+ */
+#define __SWP_TYPE_SHIFT 2
+#define __SWP_TYPE_BITS 5
+#define __SWP_TYPE_MASK ((1UL << __SWP_TYPE_BITS) - 1)
+#define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
+
+#define MAX_SWAPFILES_CHECK() \
+ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
+
+#define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
+#define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT)
+#define __swp_entry(type, offset) ((swp_entry_t) \
+ { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
+
+#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
+
+#ifdef CONFIG_FLATMEM
+#define kern_addr_valid(addr) (1) /* FIXME */
+#endif
+
+extern void paging_init(void);
+
+static inline void pgtable_cache_init(void)
+{
+ /* No page table caches to initialize */
+}
+
+#endif /* CONFIG_MMU */
+
+#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1)
+#define VMALLOC_END (PAGE_OFFSET - 1)
+#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE)
+
+/*
+ * Task size is 0x40000000000 for RV64 or 0xb800000 for RV32.
+ * Note that PGDIR_SIZE must evenly divide TASK_SIZE.
+ */
+#ifdef CONFIG_64BIT
+#define TASK_SIZE (PGDIR_SIZE * PTRS_PER_PGD / 2)
+#else
+#define TASK_SIZE VMALLOC_START
+#endif
+
+#include <asm-generic/pgtable.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PGTABLE_H */
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
new file mode 100644
index 000000000000..df2ca3c65048
--- /dev/null
+++ b/arch/riscv/mm/fault.c
@@ -0,0 +1,282 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+
+#include <linux/mm.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/perf_event.h>
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+
+#include <asm/pgalloc.h>
+#include <asm/ptrace.h>
+#include <asm/uaccess.h>
+
+/*
+ * This routine handles page faults. It determines the address and the
+ * problem, and then passes it off to one of the appropriate routines.
+ */
+asmlinkage void do_page_fault(struct pt_regs *regs)
+{
+ struct task_struct *tsk;
+ struct vm_area_struct *vma;
+ struct mm_struct *mm;
+ unsigned long addr, cause;
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ int fault, code = SEGV_MAPERR;
+
+ cause = regs->scause;
+ addr = regs->sbadaddr;
+
+ tsk = current;
+ mm = tsk->mm;
+
+ /*
+ * Fault-in kernel-space virtual memory on-demand.
+ * The 'reference' page table is init_mm.pgd.
+ *
+ * NOTE! We MUST NOT take any locks for this case. We may
+ * be in an interrupt or a critical region, and should
+ * only copy the information from the master page table,
+ * nothing more.
+ */
+ if (unlikely((addr >= VMALLOC_START) && (addr <= VMALLOC_END)))
+ goto vmalloc_fault;
+
+ /* Enable interrupts if they were enabled in the parent context. */
+ if (likely(regs->sstatus & SR_PIE))
+ local_irq_enable();
+
+ /*
+ * If we're in an interrupt, have no user context, or are running
+ * in an atomic region, then we must not take the fault.
+ */
+ if (unlikely(faulthandler_disabled() || !mm))
+ goto no_context;
+
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
+retry:
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, addr);
+ if (unlikely(!vma))
+ goto bad_area;
+ if (likely(vma->vm_start <= addr))
+ goto good_area;
+ if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
+ goto bad_area;
+ if (unlikely(expand_stack(vma, addr)))
+ goto bad_area;
+
+ /*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it.
+ */
+good_area:
+ code = SEGV_ACCERR;
+
+ switch (cause) {
+ case EXC_INST_PAGE_FAULT:
+ if (!(vma->vm_flags & VM_EXEC))
+ goto bad_area;
+ break;
+ case EXC_LOAD_PAGE_FAULT:
+ if (!(vma->vm_flags & VM_READ))
+ goto bad_area;
+ break;
+ case EXC_STORE_PAGE_FAULT:
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
+ break;
+ default:
+ panic("%s: unhandled cause %lu", __func__, cause);
+ }
+
+ /*
+ * If for any reason at all we could not handle the fault,
+ * make sure we exit gracefully rather than endlessly redo
+ * the fault.
+ */
+ fault = handle_mm_fault(vma, addr, flags);
+
+ /*
+ * If we need to retry but a fatal signal is pending, handle the
+ * signal first. We do not need to release the mmap_sem because it
+ * would already be released in __lock_page_or_retry in mm/filemap.c.
+ */
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(tsk))
+ return;
+
+ if (unlikely(fault & VM_FAULT_ERROR)) {
+ if (fault & VM_FAULT_OOM)
+ goto out_of_memory;
+ else if (fault & VM_FAULT_SIGBUS)
+ goto do_sigbus;
+ BUG();
+ }
+
+ /*
+ * Major/minor page fault accounting is only done on the
+ * initial attempt. If we go through a retry, it is extremely
+ * likely that the page will be found in page cache at that point.
+ */
+ if (flags & FAULT_FLAG_ALLOW_RETRY) {
+ if (fault & VM_FAULT_MAJOR) {
+ tsk->maj_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
+ 1, regs, addr);
+ } else {
+ tsk->min_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
+ 1, regs, addr);
+ }
+ if (fault & VM_FAULT_RETRY) {
+ /*
+ * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+ * of starvation.
+ */
+ flags &= ~(FAULT_FLAG_ALLOW_RETRY);
+ flags |= FAULT_FLAG_TRIED;
+
+ /*
+ * No need to up_read(&mm->mmap_sem) as we would
+ * have already released it in __lock_page_or_retry
+ * in mm/filemap.c.
+ */
+ goto retry;
+ }
+ }
+
+ up_read(&mm->mmap_sem);
+ return;
+
+ /*
+ * Something tried to access memory that isn't in our memory map.
+ * Fix it, but check if it's kernel or user first.
+ */
+bad_area:
+ up_read(&mm->mmap_sem);
+ /* User mode accesses just cause a SIGSEGV */
+ if (user_mode(regs)) {
+ do_trap(regs, SIGSEGV, code, addr, tsk);
+ return;
+ }
+
+no_context:
+ /* Are we prepared to handle this kernel fault? */
+ if (fixup_exception(regs))
+ return;
+
+ /*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+ bust_spinlocks(1);
+ pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n",
+ (addr < PAGE_SIZE) ? "NULL pointer dereference" :
+ "paging request", addr);
+ die(regs, "Oops");
+ do_exit(SIGKILL);
+
+ /*
+ * We ran out of memory, call the OOM killer, and return the userspace
+ * (which will retry the fault, or kill us if we got oom-killed).
+ */
+out_of_memory:
+ up_read(&mm->mmap_sem);
+ if (!user_mode(regs))
+ goto no_context;
+ pagefault_out_of_memory();
+ return;
+
+do_sigbus:
+ up_read(&mm->mmap_sem);
+ /* Kernel mode? Handle exceptions or die */
+ if (!user_mode(regs))
+ goto no_context;
+ do_trap(regs, SIGBUS, BUS_ADRERR, addr, tsk);
+ return;
+
+vmalloc_fault:
+ {
+ pgd_t *pgd, *pgd_k;
+ pud_t *pud, *pud_k;
+ p4d_t *p4d, *p4d_k;
+ pmd_t *pmd, *pmd_k;
+ pte_t *pte_k;
+ int index;
+
+ if (user_mode(regs))
+ goto bad_area;
+
+ /*
+ * Synchronize this task's top level page-table
+ * with the 'reference' page table.
+ *
+ * Do _not_ use "tsk->active_mm->pgd" here.
+ * We might be inside an interrupt in the middle
+ * of a task switch.
+ */
+ index = pgd_index(addr);
+ pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr)) + index;
+ pgd_k = init_mm.pgd + index;
+
+ if (!pgd_present(*pgd_k))
+ goto no_context;
+ set_pgd(pgd, *pgd_k);
+
+ p4d = p4d_offset(pgd, addr);
+ p4d_k = p4d_offset(pgd_k, addr);
+ if (!p4d_present(*p4d_k))
+ goto no_context;
+
+ pud = pud_offset(p4d, addr);
+ pud_k = pud_offset(p4d_k, addr);
+ if (!pud_present(*pud_k))
+ goto no_context;
+
+ /*
+ * Since the vmalloc area is global, it is unnecessary
+ * to copy individual PTEs
+ */
+ pmd = pmd_offset(pud, addr);
+ pmd_k = pmd_offset(pud_k, addr);
+ if (!pmd_present(*pmd_k))
+ goto no_context;
+ set_pmd(pmd, *pmd_k);
+
+ /*
+ * Make sure the actual PTE exists as well to
+ * catch kernel vmalloc-area accesses to non-mapped
+ * addresses. If we don't do this, this will just
+ * silently loop forever.
+ */
+ pte_k = pte_offset_kernel(pmd_k, addr);
+ if (!pte_present(*pte_k))
+ goto no_context;
+ return;
+ }
+}
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 8/9] RISC-V: User-facing API
2017-07-04 19:50 ` Palmer Dabbelt
@ 2017-07-04 19:51 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:51 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains code that is in some way visible to the user:
including via system calls, the VDSO, module loading and signal
handling. It also contains some generic code that is ABI visible.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/elf.h | 3 +-
arch/riscv/include/asm/mmu.h | 26 +++
arch/riscv/include/asm/ptrace.h | 116 ++++++++++++
arch/riscv/include/asm/syscall.h | 90 ++++++++++
arch/riscv/include/asm/syscalls.h | 25 +++
arch/riscv/include/asm/unistd.h | 16 ++
arch/riscv/include/asm/vdso.h | 32 ++++
arch/riscv/include/uapi/asm/auxvec.h | 24 +++
arch/riscv/include/uapi/asm/bitsperlong.h | 25 +++
arch/riscv/include/uapi/asm/byteorder.h | 23 +++
arch/riscv/include/uapi/asm/elf.h | 83 +++++++++
arch/riscv/include/uapi/asm/hwcap.h | 36 ++++
arch/riscv/include/uapi/asm/ptrace.h | 90 ++++++++++
arch/riscv/include/uapi/asm/sigcontext.h | 30 ++++
arch/riscv/include/uapi/asm/siginfo.h | 24 +++
arch/riscv/include/uapi/asm/ucontext.h | 35 ++++
arch/riscv/include/uapi/asm/unistd.h | 23 +++
arch/riscv/kernel/cpufeature.c | 61 +++++++
arch/riscv/kernel/module.c | 217 ++++++++++++++++++++++
arch/riscv/kernel/ptrace.c | 138 ++++++++++++++
arch/riscv/kernel/riscv_ksyms.c | 15 ++
arch/riscv/kernel/signal.c | 289 ++++++++++++++++++++++++++++++
arch/riscv/kernel/sys_riscv.c | 90 ++++++++++
arch/riscv/kernel/syscall_table.c | 25 +++
arch/riscv/kernel/vdso/.gitignore | 1 +
arch/riscv/kernel/vdso/cmpxchg32.S | 40 +++++
arch/riscv/kernel/vdso/cmpxchg64.S | 40 +++++
arch/riscv/kernel/vdso/sigreturn.S | 24 +++
arch/riscv/kernel/vdso/vdso.S | 27 +++
29 files changed, 1667 insertions(+), 1 deletion(-)
create mode 100644 arch/riscv/include/asm/mmu.h
create mode 100644 arch/riscv/include/asm/ptrace.h
create mode 100644 arch/riscv/include/asm/syscall.h
create mode 100644 arch/riscv/include/asm/syscalls.h
create mode 100644 arch/riscv/include/asm/unistd.h
create mode 100644 arch/riscv/include/asm/vdso.h
create mode 100644 arch/riscv/include/uapi/asm/auxvec.h
create mode 100644 arch/riscv/include/uapi/asm/bitsperlong.h
create mode 100644 arch/riscv/include/uapi/asm/byteorder.h
create mode 100644 arch/riscv/include/uapi/asm/elf.h
create mode 100644 arch/riscv/include/uapi/asm/hwcap.h
create mode 100644 arch/riscv/include/uapi/asm/ptrace.h
create mode 100644 arch/riscv/include/uapi/asm/sigcontext.h
create mode 100644 arch/riscv/include/uapi/asm/siginfo.h
create mode 100644 arch/riscv/include/uapi/asm/ucontext.h
create mode 100644 arch/riscv/include/uapi/asm/unistd.h
create mode 100644 arch/riscv/kernel/cpufeature.c
create mode 100644 arch/riscv/kernel/module.c
create mode 100644 arch/riscv/kernel/ptrace.c
create mode 100644 arch/riscv/kernel/riscv_ksyms.c
create mode 100644 arch/riscv/kernel/signal.c
create mode 100644 arch/riscv/kernel/sys_riscv.c
create mode 100644 arch/riscv/kernel/syscall_table.c
create mode 100644 arch/riscv/kernel/vdso/.gitignore
create mode 100644 arch/riscv/kernel/vdso/cmpxchg32.S
create mode 100644 arch/riscv/kernel/vdso/cmpxchg64.S
create mode 100644 arch/riscv/kernel/vdso/sigreturn.S
create mode 100644 arch/riscv/kernel/vdso/vdso.S
diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
index 5ded3f6f83ea..a1ef503d616e 100644
--- a/arch/riscv/include/asm/elf.h
+++ b/arch/riscv/include/asm/elf.h
@@ -59,7 +59,8 @@
* instruction set this CPU supports. This could be done in user space,
* but it's not easy, and we've already done it here.
*/
-#define ELF_HWCAP (0)
+#define ELF_HWCAP (elf_hwcap)
+extern unsigned long elf_hwcap;
/*
* This yields a string that ld.so will use to load implementation
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
new file mode 100644
index 000000000000..66805cba9a27
--- /dev/null
+++ b/arch/riscv/include/asm/mmu.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+
+#ifndef _ASM_RISCV_MMU_H
+#define _ASM_RISCV_MMU_H
+
+#ifndef __ASSEMBLY__
+
+typedef struct {
+ void *vdso;
+} mm_context_t;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_MMU_H */
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
new file mode 100644
index 000000000000..340201868842
--- /dev/null
+++ b/arch/riscv/include/asm/ptrace.h
@@ -0,0 +1,116 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PTRACE_H
+#define _ASM_RISCV_PTRACE_H
+
+#include <uapi/asm/ptrace.h>
+#include <asm/csr.h>
+
+#ifndef __ASSEMBLY__
+
+struct pt_regs {
+ unsigned long sepc;
+ unsigned long ra;
+ unsigned long sp;
+ unsigned long gp;
+ unsigned long tp;
+ unsigned long t0;
+ unsigned long t1;
+ unsigned long t2;
+ unsigned long s0;
+ unsigned long s1;
+ unsigned long a0;
+ unsigned long a1;
+ unsigned long a2;
+ unsigned long a3;
+ unsigned long a4;
+ unsigned long a5;
+ unsigned long a6;
+ unsigned long a7;
+ unsigned long s2;
+ unsigned long s3;
+ unsigned long s4;
+ unsigned long s5;
+ unsigned long s6;
+ unsigned long s7;
+ unsigned long s8;
+ unsigned long s9;
+ unsigned long s10;
+ unsigned long s11;
+ unsigned long t3;
+ unsigned long t4;
+ unsigned long t5;
+ unsigned long t6;
+ /* Supervisor CSRs */
+ unsigned long sstatus;
+ unsigned long sbadaddr;
+ unsigned long scause;
+};
+
+#ifdef CONFIG_64BIT
+#define REG_FMT "%016lx"
+#else
+#define REG_FMT "%08lx"
+#endif
+
+#define user_mode(regs) (((regs)->sstatus & SR_PS) == 0)
+
+
+/* Helpers for working with the instruction pointer */
+#define GET_IP(regs) ((regs)->sepc)
+#define SET_IP(regs, val) (GET_IP(regs) = (val))
+
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+ return GET_IP(regs);
+}
+static inline void instruction_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ SET_IP(regs, val);
+}
+
+#define profile_pc(regs) instruction_pointer(regs)
+
+/* Helpers for working with the user stack pointer */
+#define GET_USP(regs) ((regs)->sp)
+#define SET_USP(regs, val) (GET_USP(regs) = (val))
+
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+ return GET_USP(regs);
+}
+static inline void user_stack_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ SET_USP(regs, val);
+}
+
+/* Helpers for working with the frame pointer */
+#define GET_FP(regs) ((regs)->s0)
+#define SET_FP(regs, val) (GET_FP(regs) = (val))
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+ return GET_FP(regs);
+}
+static inline void frame_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ SET_FP(regs, val);
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
new file mode 100644
index 000000000000..c70f0e7a06b8
--- /dev/null
+++ b/arch/riscv/include/asm/syscall.h
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved.
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2015 Regents of the University of California, Berkeley
+ *
+ * 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.
+ *
+ * See asm-generic/syscall.h for descriptions of what we must do here.
+ */
+
+#ifndef _ASM_RISCV_SYSCALL_H
+#define _ASM_RISCV_SYSCALL_H
+
+#include <linux/sched.h>
+#include <linux/err.h>
+
+/* The array of function pointers for syscalls. */
+extern void *sys_call_table[];
+
+/*
+ * Only the low 32 bits of orig_r0 are meaningful, so we return int.
+ * This importantly ignores the high bits on 64-bit, so comparisons
+ * sign-extend the low 32 bits.
+ */
+static inline int syscall_get_nr(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->a7;
+}
+
+static inline void syscall_set_nr(struct task_struct *task,
+ struct pt_regs *regs,
+ int sysno)
+{
+ regs->a7 = sysno;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ /* FIXME: We can't do this... */
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ unsigned long error = regs->a0;
+
+ return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->a0;
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+ struct pt_regs *regs,
+ int error, long val)
+{
+ regs->a0 = (long) error ?: val;
+}
+
+static inline void syscall_get_arguments(struct task_struct *task,
+ struct pt_regs *regs,
+ unsigned int i, unsigned int n,
+ unsigned long *args)
+{
+ BUG_ON(i + n > 6);
+ memcpy(args, ®s->a0 + i * sizeof(regs->a0), n * sizeof(args[0]));
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+ struct pt_regs *regs,
+ unsigned int i, unsigned int n,
+ const unsigned long *args)
+{
+ BUG_ON(i + n > 6);
+ memcpy(®s->a0 + i * sizeof(regs->a0), args, n * sizeof(regs->a0));
+}
+
+#endif /* _ASM_TILE_SYSCALL_H */
diff --git a/arch/riscv/include/asm/syscalls.h b/arch/riscv/include/asm/syscalls.h
new file mode 100644
index 000000000000..6490274fbb76
--- /dev/null
+++ b/arch/riscv/include/asm/syscalls.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2014 Darius Rad <darius@bluespec.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SYSCALLS_H
+#define _ASM_RISCV_SYSCALLS_H
+
+#include <linux/linkage.h>
+
+#include <asm-generic/syscalls.h>
+
+/* kernel/sys_riscv.c */
+asmlinkage long sys_sysriscv_cmpxchg32(u32 __user * ptr, u32 new, u32 old);
+asmlinkage long sys_sysriscv_cmpxchg64(u64 __user * ptr, u64 new, u64 old);
+
+#endif /* _ASM_RISCV_SYSCALLS_H */
diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h
new file mode 100644
index 000000000000..9f250ed007cd
--- /dev/null
+++ b/arch/riscv/include/asm/unistd.h
@@ -0,0 +1,16 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#define __ARCH_HAVE_MMU
+#define __ARCH_WANT_SYS_CLONE
+#include <uapi/asm/unistd.h>
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
new file mode 100644
index 000000000000..95768a3810a7
--- /dev/null
+++ b/arch/riscv/include/asm/vdso.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ASM_RISCV_VDSO_H
+#define _ASM_RISCV_VDSO_H
+
+#include <linux/types.h>
+
+struct vdso_data {
+};
+
+#define VDSO_SYMBOL(base, name) \
+({ \
+ extern const char __vdso_##name[]; \
+ (void __user *)((unsigned long)(base) + __vdso_##name); \
+})
+
+#endif /* _ASM_RISCV_VDSO_H */
diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h
new file mode 100644
index 000000000000..1376515547cd
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/auxvec.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _UAPI_ASM_RISCV_AUXVEC_H
+#define _UAPI_ASM_RISCV_AUXVEC_H
+
+/* vDSO location */
+#define AT_SYSINFO_EHDR 33
+
+#endif /* _UAPI_ASM_RISCV_AUXVEC_H */
diff --git a/arch/riscv/include/uapi/asm/bitsperlong.h b/arch/riscv/include/uapi/asm/bitsperlong.h
new file mode 100644
index 000000000000..0b3cb52fd29d
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _UAPI_ASM_RISCV_BITSPERLONG_H
+#define _UAPI_ASM_RISCV_BITSPERLONG_H
+
+#define __BITS_PER_LONG (__SIZEOF_POINTER__ * 8)
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* _UAPI_ASM_RISCV_BITSPERLONG_H */
diff --git a/arch/riscv/include/uapi/asm/byteorder.h b/arch/riscv/include/uapi/asm/byteorder.h
new file mode 100644
index 000000000000..4ca38af2cd32
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/byteorder.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _UAPI_ASM_RISCV_BYTEORDER_H
+#define _UAPI_ASM_RISCV_BYTEORDER_H
+
+#include <linux/byteorder/little_endian.h>
+
+#endif /* _UAPI_ASM_RISCV_BYTEORDER_H */
diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h
new file mode 100644
index 000000000000..a510edfa8226
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/elf.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
+ * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _UAPI_ASM_ELF_H
+#define _UAPI_ASM_ELF_H
+
+#include <asm/ptrace.h>
+
+/* ELF register definitions */
+typedef unsigned long elf_greg_t;
+typedef struct user_regs_struct elf_gregset_t;
+#define ELF_NGREG (sizeof(elf_gregset_t) / sizeof(elf_greg_t))
+
+typedef union __riscv_fp_state elf_fpregset_t;
+
+#define ELF_RISCV_R_SYM(r_info) ((r_info) >> 32)
+#define ELF_RISCV_R_TYPE(r_info) ((r_info) & 0xffffffff)
+
+/*
+ * RISC-V relocation types
+ */
+
+/* Relocation types used by the dynamic linker */
+#define R_RISCV_NONE 0
+#define R_RISCV_32 1
+#define R_RISCV_64 2
+#define R_RISCV_RELATIVE 3
+#define R_RISCV_COPY 4
+#define R_RISCV_JUMP_SLOT 5
+#define R_RISCV_TLS_DTPMOD32 6
+#define R_RISCV_TLS_DTPMOD64 7
+#define R_RISCV_TLS_DTPREL32 8
+#define R_RISCV_TLS_DTPREL64 9
+#define R_RISCV_TLS_TPREL32 10
+#define R_RISCV_TLS_TPREL64 11
+
+/* Relocation types not used by the dynamic linker */
+#define R_RISCV_BRANCH 16
+#define R_RISCV_JAL 17
+#define R_RISCV_CALL 18
+#define R_RISCV_CALL_PLT 19
+#define R_RISCV_GOT_HI20 20
+#define R_RISCV_TLS_GOT_HI20 21
+#define R_RISCV_TLS_GD_HI20 22
+#define R_RISCV_PCREL_HI20 23
+#define R_RISCV_PCREL_LO12_I 24
+#define R_RISCV_PCREL_LO12_S 25
+#define R_RISCV_HI20 26
+#define R_RISCV_LO12_I 27
+#define R_RISCV_LO12_S 28
+#define R_RISCV_TPREL_HI20 29
+#define R_RISCV_TPREL_LO12_I 30
+#define R_RISCV_TPREL_LO12_S 31
+#define R_RISCV_TPREL_ADD 32
+#define R_RISCV_ADD8 33
+#define R_RISCV_ADD16 34
+#define R_RISCV_ADD32 35
+#define R_RISCV_ADD64 36
+#define R_RISCV_SUB8 37
+#define R_RISCV_SUB16 38
+#define R_RISCV_SUB32 39
+#define R_RISCV_SUB64 40
+#define R_RISCV_GNU_VTINHERIT 41
+#define R_RISCV_GNU_VTENTRY 42
+#define R_RISCV_ALIGN 43
+#define R_RISCV_RVC_BRANCH 44
+#define R_RISCV_RVC_JUMP 45
+#define R_RISCV_LUI 46
+#define R_RISCV_GPREL_I 47
+#define R_RISCV_GPREL_S 48
+#define R_RISCV_TPREL_I 49
+#define R_RISCV_TPREL_S 50
+#define R_RISCV_RELAX 51
+
+#endif /* _UAPI_ASM_ELF_H */
diff --git a/arch/riscv/include/uapi/asm/hwcap.h b/arch/riscv/include/uapi/asm/hwcap.h
new file mode 100644
index 000000000000..f333221c9ab2
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/hwcap.h
@@ -0,0 +1,36 @@
+/*
+ * Copied from arch/arm64/include/asm/hwcap.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __UAPI_ASM_HWCAP_H
+#define __UAPI_ASM_HWCAP_H
+
+/*
+ * Linux saves the floating-point registers according to the ISA Linux is
+ * executing on, as opposed to the ISA the user program is compiled for. This
+ * is necessary for a handful of esoteric use cases: for example, userpsace
+ * threading libraries must be able to examine the actual machine state in
+ * order to fully reconstruct the state of a thread.
+ */
+#define COMPAT_HWCAP_ISA_I (1 << ('I' - 'A'))
+#define COMPAT_HWCAP_ISA_M (1 << ('M' - 'A'))
+#define COMPAT_HWCAP_ISA_A (1 << ('A' - 'A'))
+#define COMPAT_HWCAP_ISA_F (1 << ('F' - 'A'))
+#define COMPAT_HWCAP_ISA_D (1 << ('D' - 'A'))
+#define COMPAT_HWCAP_ISA_C (1 << ('C' - 'A'))
+
+#endif
diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
new file mode 100644
index 000000000000..1a9e4cdd37e2
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _UAPI_ASM_RISCV_PTRACE_H
+#define _UAPI_ASM_RISCV_PTRACE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * User-mode register state for core dumps, ptrace, sigcontext
+ *
+ * This decouples struct pt_regs from the userspace ABI.
+ * struct user_regs_struct must form a prefix of struct pt_regs.
+ */
+struct user_regs_struct {
+ unsigned long pc;
+ unsigned long ra;
+ unsigned long sp;
+ unsigned long gp;
+ unsigned long tp;
+ unsigned long t0;
+ unsigned long t1;
+ unsigned long t2;
+ unsigned long s0;
+ unsigned long s1;
+ unsigned long a0;
+ unsigned long a1;
+ unsigned long a2;
+ unsigned long a3;
+ unsigned long a4;
+ unsigned long a5;
+ unsigned long a6;
+ unsigned long a7;
+ unsigned long s2;
+ unsigned long s3;
+ unsigned long s4;
+ unsigned long s5;
+ unsigned long s6;
+ unsigned long s7;
+ unsigned long s8;
+ unsigned long s9;
+ unsigned long s10;
+ unsigned long s11;
+ unsigned long t3;
+ unsigned long t4;
+ unsigned long t5;
+ unsigned long t6;
+};
+
+struct __riscv_f_ext_state {
+ __u32 f[32];
+ __u32 fcsr;
+};
+
+struct __riscv_d_ext_state {
+ __u64 f[32];
+ __u32 fcsr;
+};
+
+struct __riscv_q_ext_state {
+ __u64 f[64] __attribute__((aligned(16)));
+ __u32 fcsr;
+ /*
+ * Reserved for expansion of sigcontext structure. Currently zeroed
+ * upon signal, and must be zero upon sigreturn.
+ */
+ __u32 reserved[3];
+};
+
+union __riscv_fp_state {
+ struct __riscv_f_ext_state f;
+ struct __riscv_d_ext_state d;
+ struct __riscv_q_ext_state q;
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h
new file mode 100644
index 000000000000..ed7372b277fa
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/sigcontext.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _UAPI_ASM_RISCV_SIGCONTEXT_H
+#define _UAPI_ASM_RISCV_SIGCONTEXT_H
+
+#include <asm/ptrace.h>
+
+/*
+ * Signal context structure
+ *
+ * This contains the context saved before a signal handler is invoked;
+ * it is restored by sys_sigreturn / sys_rt_sigreturn.
+ */
+struct sigcontext {
+ struct user_regs_struct sc_regs;
+ union __riscv_fp_state sc_fpregs;
+};
+
+#endif /* _UAPI_ASM_RISCV_SIGCONTEXT_H */
diff --git a/arch/riscv/include/uapi/asm/siginfo.h b/arch/riscv/include/uapi/asm/siginfo.h
new file mode 100644
index 000000000000..f96849aac662
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/siginfo.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2016 SiFive, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_SIGINFO_H
+#define __ASM_SIGINFO_H
+
+#define __ARCH_SI_PREAMBLE_SIZE (__SIZEOF_POINTER__ == 4 ? 12 : 16)
+
+#include <asm-generic/siginfo.h>
+
+#endif
diff --git a/arch/riscv/include/uapi/asm/ucontext.h b/arch/riscv/include/uapi/asm/ucontext.h
new file mode 100644
index 000000000000..52eff9febcfd
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/ucontext.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2017 SiFive, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file was copied from arch/arm64/include/uapi/asm/ucontext.h
+ */
+#ifndef _UAPI__ASM_UCONTEXT_H
+#define _UAPI__ASM_UCONTEXT_H
+
+#include <linux/types.h>
+
+struct ucontext {
+ unsigned long uc_flags;
+ struct ucontext *uc_link;
+ stack_t uc_stack;
+ sigset_t uc_sigmask;
+ /* glibc uses a 1024-bit sigset_t */
+ __u8 __unused[1024 / 8 - sizeof(sigset_t)];
+ /* last for future expansion */
+ struct sigcontext uc_mcontext;
+};
+
+#endif /* _UAPI__ASM_UCONTEXT_H */
diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..37a5429cc896
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/unistd.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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 <asm-generic/unistd.h>
+
+/*
+ * These system calls add support for AMOs on RISC-V systems without support
+ * for the A extension.
+ */
+#define __NR_sysriscv_cmpxchg32 (__NR_arch_specific_syscall + 0)
+__SYSCALL(__NR_sysriscv_cmpxchg32, sys_sysriscv_cmpxchg32)
+#define __NR_sysriscv_cmpxchg64 (__NR_arch_specific_syscall + 1)
+__SYSCALL(__NR_sysriscv_cmpxchg64, sys_sysriscv_cmpxchg64)
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
new file mode 100644
index 000000000000..3ced896cfce1
--- /dev/null
+++ b/arch/riscv/kernel/cpufeature.c
@@ -0,0 +1,61 @@
+/*
+ * Copied from arch/arm64/kernel/cpufeature.c
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ * 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/of.h>
+#include <asm/processor.h>
+#include <asm/hwcap.h>
+
+unsigned long elf_hwcap __read_mostly;
+
+void riscv_fill_hwcap(void)
+{
+ struct device_node *node;
+ const char *isa;
+ size_t i;
+ static unsigned long isa2hwcap[256] = {0};
+
+ isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I;
+ isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M;
+ isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A;
+ isa2hwcap['f'] = isa2hwcap['F'] = COMPAT_HWCAP_ISA_F;
+ isa2hwcap['d'] = isa2hwcap['D'] = COMPAT_HWCAP_ISA_D;
+ isa2hwcap['c'] = isa2hwcap['C'] = COMPAT_HWCAP_ISA_C;
+
+ elf_hwcap = 0;
+
+ /*
+ * We don't support running Linux on hertergenous ISA systems. For
+ * now, we just check the ISA of the first processor.
+ */
+ node = of_find_node_by_type(NULL, "cpu");
+ if (!node) {
+ pr_warning("Unable to find \"cpu\" devicetree entry");
+ return;
+ }
+
+ if (of_property_read_string(node, "riscv,isa", &isa)) {
+ pr_warning("Unable to find \"riscv,isa\" devicetree entry");
+ return;
+ }
+
+ for (i = 0; i < strlen(isa); ++i)
+ elf_hwcap |= isa2hwcap[(unsigned char)(isa[i])];
+
+ pr_info("elf_hwcap is 0x%lx", elf_hwcap);
+}
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
new file mode 100644
index 000000000000..e0f05034fc21
--- /dev/null
+++ b/arch/riscv/kernel/module.c
@@ -0,0 +1,217 @@
+/*
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * Copyright (C) 2017 Zihao Yu
+ */
+
+#include <linux/elf.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/moduleloader.h>
+
+static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v)
+{
+ *(u64 *)location = v;
+ return 0;
+}
+
+static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ u32 imm12 = (offset & 0x1000) << (31 - 12);
+ u32 imm11 = (offset & 0x800) >> (11 - 7);
+ u32 imm10_5 = (offset & 0x7e0) << (30 - 10);
+ u32 imm4_1 = (offset & 0x1e) << (11 - 4);
+
+ *location = (*location & 0x1fff07f) | imm12 | imm11 | imm10_5 | imm4_1;
+ return 0;
+}
+
+static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ u32 imm20 = (offset & 0x100000) << (31 - 20);
+ u32 imm19_12 = (offset & 0xff000);
+ u32 imm11 = (offset & 0x800) << (20 - 11);
+ u32 imm10_1 = (offset & 0x7fe) << (30 - 10);
+
+ *location = (*location & 0xfff) | imm20 | imm19_12 | imm11 | imm10_1;
+ return 0;
+}
+
+static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ s32 hi20;
+
+ if (offset != (s32)offset) {
+ pr_err(
+ "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+ me->name, v, location);
+ return -EINVAL;
+ }
+
+ hi20 = (offset + 0x800) & 0xfffff000;
+ *location = (*location & 0xfff) | hi20;
+ return 0;
+}
+
+static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ /*
+ * v is the lo12 value to fill. It is calculated before calling this
+ * handler.
+ */
+ *location = (*location & 0xfffff) | ((v & 0xfff) << 20);
+ return 0;
+}
+
+static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ /*
+ * v is the lo12 value to fill. It is calculated before calling this
+ * handler.
+ */
+ u32 imm11_5 = (v & 0xfe0) << (31 - 11);
+ u32 imm4_0 = (v & 0x1f) << (11 - 4);
+
+ *location = (*location & 0x1fff07f) | imm11_5 | imm4_0;
+ return 0;
+}
+
+static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ s32 fill_v = offset;
+ u32 hi20, lo12;
+
+ if (offset != fill_v) {
+ pr_err(
+ "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+ me->name, v, location);
+ return -EINVAL;
+ }
+
+ hi20 = (offset + 0x800) & 0xfffff000;
+ lo12 = (offset - hi20) & 0xfff;
+ *location = (*location & 0xfff) | hi20;
+ *(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20);
+ return 0;
+}
+
+static int apply_r_riscv_relax_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ return 0;
+}
+
+static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
+ Elf_Addr v) = {
+ [R_RISCV_64] = apply_r_riscv_64_rela,
+ [R_RISCV_BRANCH] = apply_r_riscv_branch_rela,
+ [R_RISCV_JAL] = apply_r_riscv_jal_rela,
+ [R_RISCV_PCREL_HI20] = apply_r_riscv_pcrel_hi20_rela,
+ [R_RISCV_PCREL_LO12_I] = apply_r_riscv_pcrel_lo12_i_rela,
+ [R_RISCV_PCREL_LO12_S] = apply_r_riscv_pcrel_lo12_s_rela,
+ [R_RISCV_CALL_PLT] = apply_r_riscv_call_plt_rela,
+ [R_RISCV_RELAX] = apply_r_riscv_relax_rela,
+};
+
+int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
+ unsigned int symindex, unsigned int relsec,
+ struct module *me)
+{
+ Elf_Rela *rel = (void *) sechdrs[relsec].sh_addr;
+ int (*handler)(struct module *me, u32 *location, Elf_Addr v);
+ Elf_Sym *sym;
+ u32 *location;
+ unsigned int i, type;
+ Elf_Addr v;
+ int res;
+
+ pr_debug("Applying relocate section %u to %u\n", relsec,
+ sechdrs[relsec].sh_info);
+
+ for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
+ /* This is where to make the change */
+ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+ + rel[i].r_offset;
+ /* This is the symbol it is referring to */
+ sym = (Elf_Sym *)sechdrs[symindex].sh_addr
+ + ELF_RISCV_R_SYM(rel[i].r_info);
+ if (IS_ERR_VALUE(sym->st_value)) {
+ /* Ignore unresolved weak symbol */
+ if (ELF_ST_BIND(sym->st_info) == STB_WEAK)
+ continue;
+ pr_warning("%s: Unknown symbol %s\n",
+ me->name, strtab + sym->st_name);
+ return -ENOENT;
+ }
+
+ type = ELF_RISCV_R_TYPE(rel[i].r_info);
+
+ if (type < ARRAY_SIZE(reloc_handlers_rela))
+ handler = reloc_handlers_rela[type];
+ else
+ handler = NULL;
+
+ if (!handler) {
+ pr_err("%s: Unknown relocation type %u\n",
+ me->name, type);
+ return -EINVAL;
+ }
+
+ v = sym->st_value + rel[i].r_addend;
+
+ if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) {
+ unsigned int j;
+
+ for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
+ u64 hi20_loc =
+ sechdrs[sechdrs[relsec].sh_info].sh_addr
+ + rel[j].r_offset;
+ /* Find the corresponding HI20 PC-relative relocation entry */
+ if (hi20_loc == sym->st_value) {
+ Elf_Sym *hi20_sym =
+ (Elf_Sym *)sechdrs[symindex].sh_addr
+ + ELF_RISCV_R_SYM(rel[j].r_info);
+ u64 hi20_sym_val =
+ hi20_sym->st_value
+ + rel[j].r_addend;
+ /* Calculate lo12 */
+ s64 offset = hi20_sym_val - hi20_loc;
+ s32 hi20 = (offset + 0x800) & 0xfffff000;
+ s32 lo12 = offset - hi20;
+ v = lo12;
+ break;
+ }
+ }
+ if (j == sechdrs[relsec].sh_size / sizeof(*rel)) {
+ pr_err(
+ "%s: Can not find HI20 PC-relative relocation information\n",
+ me->name);
+ return -EINVAL;
+ }
+ }
+
+ res = handler(me, location, v);
+ if (res)
+ return res;
+ }
+
+ return 0;
+}
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
new file mode 100644
index 000000000000..2720d5e97354
--- /dev/null
+++ b/arch/riscv/kernel/ptrace.c
@@ -0,0 +1,138 @@
+/*
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2015 Regents of the University of California
+ * Copyright 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.
+ *
+ * Copied from arch/tile/kernel/ptrace.c
+ */
+
+#include <asm/ptrace.h>
+#include <asm/syscall.h>
+#include <asm/thread_info.h>
+#include <linux/ptrace.h>
+#include <linux/elf.h>
+#include <linux/regset.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/tracehook.h>
+#include <trace/events/syscalls.h>
+
+enum riscv_regset {
+ REGSET_X,
+};
+
+/* Put registers back to task. */
+static void putregs(struct task_struct *child, struct pt_regs *uregs)
+{
+ struct pt_regs *regs = task_pt_regs(child);
+ *regs = *uregs;
+}
+
+static int riscv_gpr_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct pt_regs *regs;
+
+ regs = task_pt_regs(target);
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf, regs, 0,
+ sizeof(*regs));
+}
+
+static int riscv_gpr_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 pt_regs regs;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®s, 0,
+ sizeof(regs));
+ if (ret)
+ return ret;
+
+ putregs(target, ®s);
+
+ return 0;
+}
+
+
+static const struct user_regset riscv_user_regset[] = {
+ [REGSET_X] = {
+ .core_note_type = NT_PRSTATUS,
+ .n = ELF_NGREG,
+ .size = sizeof(elf_greg_t),
+ .align = sizeof(elf_greg_t),
+ .get = &riscv_gpr_get,
+ .set = &riscv_gpr_set,
+ },
+};
+
+static const struct user_regset_view riscv_user_native_view = {
+ .name = "riscv",
+ .e_machine = EM_RISCV,
+ .regsets = riscv_user_regset,
+ .n = ARRAY_SIZE(riscv_user_regset),
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+ return &riscv_user_native_view;
+}
+
+void ptrace_disable(struct task_struct *child)
+{
+ clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+ unsigned long addr, unsigned long data)
+{
+ long ret = -EIO;
+
+ switch (request) {
+ default:
+ ret = ptrace_request(child, request, addr, data);
+ break;
+ }
+
+ return ret;
+}
+
+/*
+ * Allows PTRACE_SYSCALL to work. These are called from entry.S in
+ * {handle,ret_from}_syscall.
+ */
+void do_syscall_trace_enter(struct pt_regs *regs)
+{
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ if (tracehook_report_syscall_entry(regs))
+ syscall_set_nr(current, regs, -1);
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+ if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+ trace_sys_enter(regs, syscall_get_nr(current, regs));
+#endif
+}
+
+void do_syscall_trace_exit(struct pt_regs *regs)
+{
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ tracehook_report_syscall_exit(regs, 0);
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+ if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+ trace_sys_exit(regs, regs->regs[0]);
+#endif
+}
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
new file mode 100644
index 000000000000..23cc81ec9e94
--- /dev/null
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -0,0 +1,15 @@
+/*
+ * Copyright (C) 2017 Zihao Yu
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/export.h>
+#include <linux/uaccess.h>
+
+/*
+ * Assembly functions that may be used (directly or indirectly) by modules
+ */
+EXPORT_SYMBOL(__copy_user);
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
new file mode 100644
index 000000000000..e0a1b89583ef
--- /dev/null
+++ b/arch/riscv/kernel/signal.c
@@ -0,0 +1,289 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/tracehook.h>
+#include <linux/linkage.h>
+
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+#include <asm/switch_to.h>
+#include <asm/csr.h>
+
+#define DEBUG_SIG 0
+
+struct rt_sigframe {
+ struct siginfo info;
+ struct ucontext uc;
+};
+
+static long restore_d_state(struct pt_regs *regs,
+ struct __riscv_d_ext_state __user *state)
+{
+ long err;
+ err = __copy_from_user(¤t->thread.fstate, state, sizeof(*state));
+ if (likely(!err))
+ fstate_restore(current, regs);
+ return err;
+}
+
+static long save_d_state(struct pt_regs *regs,
+ struct __riscv_d_ext_state __user *state)
+{
+ fstate_save(current, regs);
+ return __copy_to_user(state, ¤t->thread.fstate, sizeof(*state));
+}
+
+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;
+ }
+ return err;
+}
+
+SYSCALL_DEFINE0(rt_sigreturn)
+{
+ struct pt_regs *regs = current_pt_regs();
+ struct rt_sigframe __user *frame;
+ struct task_struct *task;
+ sigset_t set;
+
+ /* Always make any pending restarted system calls return -EINTR */
+ current->restart_block.fn = do_no_restart_syscall;
+
+ frame = (struct rt_sigframe __user *)regs->sp;
+
+ if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+
+ if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+ goto badframe;
+
+ set_current_blocked(&set);
+
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+ goto badframe;
+
+ if (restore_altstack(&frame->uc.uc_stack))
+ goto badframe;
+
+ return regs->a0;
+
+badframe:
+ task = current;
+ if (show_unhandled_signals) {
+ pr_info_ratelimited(
+ "%s[%d]: bad frame in %s: frame=%p pc=%p sp=%p\n",
+ task->comm, task_pid_nr(task), __func__,
+ frame, (void *)regs->sepc, (void *)regs->sp);
+ }
+ force_sig(SIGSEGV, task);
+ return 0;
+}
+
+static long setup_sigcontext(struct rt_sigframe __user *frame,
+ struct pt_regs *regs)
+{
+ 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]);
+ return err;
+}
+
+static inline void __user *get_sigframe(struct ksignal *ksig,
+ struct pt_regs *regs, size_t framesize)
+{
+ unsigned long sp;
+ /* Default to using normal stack */
+ sp = regs->sp;
+
+ /*
+ * If we are on the alternate signal stack and would overflow it, don't.
+ * Return an always-bogus address instead so we will die with SIGSEGV.
+ */
+ if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize)))
+ return (void __user __force *)(-1UL);
+
+ /* This is the X/Open sanctioned signal stack switching. */
+ sp = sigsp(sp, ksig) - framesize;
+
+ /* Align the stack frame. */
+ sp &= ~0xfUL;
+
+ return (void __user *)sp;
+}
+
+
+static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
+ struct pt_regs *regs)
+{
+ struct rt_sigframe __user *frame;
+ long err = 0;
+
+ frame = get_sigframe(ksig, regs, sizeof(*frame));
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ return -EFAULT;
+
+ err |= copy_siginfo_to_user(&frame->info, &ksig->info);
+
+ /* Create the ucontext. */
+ err |= __put_user(0, &frame->uc.uc_flags);
+ err |= __put_user(NULL, &frame->uc.uc_link);
+ err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+ err |= setup_sigcontext(frame, regs);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+ if (err)
+ return -EFAULT;
+
+ /* Set up to return from userspace. */
+ regs->ra = (unsigned long)VDSO_SYMBOL(
+ current->mm->context.vdso, rt_sigreturn);
+
+ /*
+ * Set up registers for signal handler.
+ * Registers that we don't modify keep the value they had from
+ * user-space at the time we took the signal.
+ * We always pass siginfo and mcontext, regardless of SA_SIGINFO,
+ * since some things rely on this (e.g. glibc's debug/segfault.c).
+ */
+ regs->sepc = (unsigned long)ksig->ka.sa.sa_handler;
+ regs->sp = (unsigned long)frame;
+ regs->a0 = ksig->sig; /* a0: signal number */
+ regs->a1 = (unsigned long)(&frame->info); /* a1: siginfo pointer */
+ regs->a2 = (unsigned long)(&frame->uc); /* a2: ucontext pointer */
+
+#if DEBUG_SIG
+ pr_info("SIG deliver (%s:%d): sig=%d pc=%p ra=%p sp=%p\n",
+ current->comm, task_pid_nr(current), ksig->sig,
+ (void *)regs->sepc, (void *)regs->ra, frame);
+#endif
+
+ return 0;
+}
+
+static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
+{
+ sigset_t *oldset = sigmask_to_save();
+ int ret;
+
+ /* Are we from a system call? */
+ if (regs->scause == EXC_SYSCALL) {
+ /* If so, check system call restarting.. */
+ switch (regs->a0) {
+ case -ERESTART_RESTARTBLOCK:
+ case -ERESTARTNOHAND:
+ regs->a0 = -EINTR;
+ break;
+
+ case -ERESTARTSYS:
+ if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
+ regs->a0 = -EINTR;
+ break;
+ }
+ /* fallthrough */
+ case -ERESTARTNOINTR:
+ regs->sepc -= 0x4;
+ break;
+ }
+ }
+
+ /* Set up the stack frame */
+ ret = setup_rt_frame(ksig, oldset, regs);
+
+ signal_setup_done(ret, ksig, 0);
+}
+
+static void do_signal(struct pt_regs *regs)
+{
+ struct ksignal ksig;
+
+ if (get_signal(&ksig)) {
+ /* Actually deliver the signal */
+ handle_signal(&ksig, regs);
+ return;
+ }
+
+ /* Did we come from a system call? */
+ if (regs->scause == EXC_SYSCALL) {
+ /* Restart the system call - no handlers present */
+ switch (regs->a0) {
+ case -ERESTARTNOHAND:
+ case -ERESTARTSYS:
+ case -ERESTARTNOINTR:
+ regs->sepc -= 0x4;
+ break;
+ case -ERESTART_RESTARTBLOCK:
+ regs->a7 = __NR_restart_syscall;
+ regs->sepc -= 0x4;
+ break;
+ }
+ }
+
+ /*
+ * If there is no signal to deliver, we just put the saved
+ * sigmask back.
+ */
+ restore_saved_sigmask();
+}
+
+/*
+ * notification of userspace execution resumption
+ * - triggered by the _TIF_WORK_MASK flags
+ */
+asmlinkage void do_notify_resume(struct pt_regs *regs,
+ unsigned long thread_info_flags)
+{
+ /* Handle pending signal delivery */
+ if (thread_info_flags & _TIF_SIGPENDING)
+ do_signal(regs);
+
+ if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+ clear_thread_flag(TIF_NOTIFY_RESUME);
+ tracehook_notify_resume(regs);
+ }
+}
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
new file mode 100644
index 000000000000..4419604ff46c
--- /dev/null
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2014 Darius Rad <darius@bluespec.com>
+ * 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/syscalls.h>
+#include <asm/cmpxchg.h>
+#include <asm/unistd.h>
+
+#ifdef CONFIG_64BIT
+SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, off_t, offset)
+{
+ if (unlikely(offset & (~PAGE_MASK)))
+ return -EINVAL;
+ return sys_mmap_pgoff(addr, len, prot, flags, fd, offset >> PAGE_SHIFT);
+}
+#else
+SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, off_t, offset)
+{
+ /*
+ * Note that the shift for mmap2 is constant (12),
+ * regardless of PAGE_SIZE
+ */
+ if (unlikely(offset & (~PAGE_MASK >> 12)))
+ return -EINVAL;
+ return sys_mmap_pgoff(addr, len, prot, flags, fd,
+ offset >> (PAGE_SHIFT - 12));
+}
+#endif /* !CONFIG_64BIT */
+
+SYSCALL_DEFINE3(sysriscv_cmpxchg32, u32 __user *, ptr, u32, new, u32, old)
+{
+ u32 prev;
+ unsigned int err;
+
+ if (!access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)))
+ return -EFAULT;
+
+#ifdef CONFIG_ISA_A
+ err = 0;
+ prev = cmpxchg32(ptr, old, new);
+#else
+ preempt_disable();
+ err = __get_user(prev, ptr);
+ if (likely(!err && prev == old))
+ err = __put_user(new, ptr);
+ preempt_enable();
+#endif
+
+ return unlikely(err) ? err : prev;
+}
+
+SYSCALL_DEFINE3(sysriscv_cmpxchg64, u64 __user *, ptr, u64, new, u64, old)
+{
+#ifdef CONFIG_64BIT
+ u64 prev;
+ unsigned int err;
+
+ if (!access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)))
+ return -EFAULT;
+
+#ifdef CONFIG_ISA_A
+ err = 0;
+ prev = cmpxchg64(ptr, old, new);
+#else
+ preempt_disable();
+ err = __get_user(prev, ptr);
+ if (likely(!err && prev == old))
+ err = __put_user(new, ptr);
+ preempt_enable();
+#endif
+ return unlikely(err) ? err : prev;
+#else
+ return -ENOTSUPP;
+#endif
+}
diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c
new file mode 100644
index 000000000000..8fa239b67cbc
--- /dev/null
+++ b/arch/riscv/kernel/syscall_table.c
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2009 Arnd Bergmann <arnd@arndb.de>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/syscalls.h>
+
+#include <asm/syscalls.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call) [nr] = (call),
+
+void *sys_call_table[__NR_syscalls] = {
+ [0 ... __NR_syscalls - 1] = sys_ni_syscall,
+#include <asm/unistd.h>
+};
diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore
new file mode 100644
index 000000000000..f8b69d84238e
--- /dev/null
+++ b/arch/riscv/kernel/vdso/.gitignore
@@ -0,0 +1 @@
+vdso.lds
diff --git a/arch/riscv/kernel/vdso/cmpxchg32.S b/arch/riscv/kernel/vdso/cmpxchg32.S
new file mode 100644
index 000000000000..387deb4e852c
--- /dev/null
+++ b/arch/riscv/kernel/vdso/cmpxchg32.S
@@ -0,0 +1,40 @@
+/*
+ * 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
+ENTRY(__vdso_cmpxchg32)
+ .cfi_startproc
+#ifdef CONFIG_ISA_A
+/*
+ * a0: ptr
+ * a1: compare value
+ * a2: exchange value
+ */
+0:
+ lr.w.aqrl t0, 0(a0)
+ bne t0, a1, 1f
+ sc.w.aqrl t1, a2, 0(a0)
+ bnez t1, 0b
+1:
+ mv a0, t0
+ ret
+#else
+ li a7, __NR_sysriscv_cmpxchg32
+ scall
+ ret
+#endif
+ .cfi_endproc
+ENDPROC(__vdso_cmpxchg32)
diff --git a/arch/riscv/kernel/vdso/cmpxchg64.S b/arch/riscv/kernel/vdso/cmpxchg64.S
new file mode 100644
index 000000000000..6286842f78c0
--- /dev/null
+++ b/arch/riscv/kernel/vdso/cmpxchg64.S
@@ -0,0 +1,40 @@
+/*
+ * 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
+ENTRY(__vdso_cmpxchg64)
+ .cfi_startproc
+#ifdef CONFIG_ISA_A
+/*
+ * a0: ptr
+ * a1: compare value
+ * a2: exchange value
+ */
+0:
+ lr.d.aqrl t0, 0(a0)
+ bne t0, a1, 1f
+ sc.d.aqrl t1, a2, 0(a0)
+ bnez t1, 0b
+1:
+ mv a0, t0
+ ret
+#else
+ li a7, __NR_sysriscv_cmpxchg64
+ scall
+ ret
+#endif
+ .cfi_endproc
+ENDPROC(__vdso_cmpxchg64)
diff --git a/arch/riscv/kernel/vdso/sigreturn.S b/arch/riscv/kernel/vdso/sigreturn.S
new file mode 100644
index 000000000000..f5aa3d72acfb
--- /dev/null
+++ b/arch/riscv/kernel/vdso/sigreturn.S
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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
+ENTRY(__vdso_rt_sigreturn)
+ .cfi_startproc
+ .cfi_signal_frame
+ li a7, __NR_rt_sigreturn
+ scall
+ .cfi_endproc
+ENDPROC(__vdso_rt_sigreturn)
diff --git a/arch/riscv/kernel/vdso/vdso.S b/arch/riscv/kernel/vdso/vdso.S
new file mode 100644
index 000000000000..7055de5f9174
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vdso.S
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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/init.h>
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+ __PAGE_ALIGNED_DATA
+
+ .globl vdso_start, vdso_end
+ .balign PAGE_SIZE
+vdso_start:
+ .incbin "arch/riscv/kernel/vdso/vdso.so"
+ .balign PAGE_SIZE
+vdso_end:
+
+ .previous
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 8/9] RISC-V: User-facing API
@ 2017-07-04 19:51 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:51 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains code that is in some way visible to the user:
including via system calls, the VDSO, module loading and signal
handling. It also contains some generic code that is ABI visible.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/elf.h | 3 +-
arch/riscv/include/asm/mmu.h | 26 +++
arch/riscv/include/asm/ptrace.h | 116 ++++++++++++
arch/riscv/include/asm/syscall.h | 90 ++++++++++
arch/riscv/include/asm/syscalls.h | 25 +++
arch/riscv/include/asm/unistd.h | 16 ++
arch/riscv/include/asm/vdso.h | 32 ++++
arch/riscv/include/uapi/asm/auxvec.h | 24 +++
arch/riscv/include/uapi/asm/bitsperlong.h | 25 +++
arch/riscv/include/uapi/asm/byteorder.h | 23 +++
arch/riscv/include/uapi/asm/elf.h | 83 +++++++++
arch/riscv/include/uapi/asm/hwcap.h | 36 ++++
arch/riscv/include/uapi/asm/ptrace.h | 90 ++++++++++
arch/riscv/include/uapi/asm/sigcontext.h | 30 ++++
arch/riscv/include/uapi/asm/siginfo.h | 24 +++
arch/riscv/include/uapi/asm/ucontext.h | 35 ++++
arch/riscv/include/uapi/asm/unistd.h | 23 +++
arch/riscv/kernel/cpufeature.c | 61 +++++++
arch/riscv/kernel/module.c | 217 ++++++++++++++++++++++
arch/riscv/kernel/ptrace.c | 138 ++++++++++++++
arch/riscv/kernel/riscv_ksyms.c | 15 ++
arch/riscv/kernel/signal.c | 289 ++++++++++++++++++++++++++++++
arch/riscv/kernel/sys_riscv.c | 90 ++++++++++
arch/riscv/kernel/syscall_table.c | 25 +++
arch/riscv/kernel/vdso/.gitignore | 1 +
arch/riscv/kernel/vdso/cmpxchg32.S | 40 +++++
arch/riscv/kernel/vdso/cmpxchg64.S | 40 +++++
arch/riscv/kernel/vdso/sigreturn.S | 24 +++
arch/riscv/kernel/vdso/vdso.S | 27 +++
29 files changed, 1667 insertions(+), 1 deletion(-)
create mode 100644 arch/riscv/include/asm/mmu.h
create mode 100644 arch/riscv/include/asm/ptrace.h
create mode 100644 arch/riscv/include/asm/syscall.h
create mode 100644 arch/riscv/include/asm/syscalls.h
create mode 100644 arch/riscv/include/asm/unistd.h
create mode 100644 arch/riscv/include/asm/vdso.h
create mode 100644 arch/riscv/include/uapi/asm/auxvec.h
create mode 100644 arch/riscv/include/uapi/asm/bitsperlong.h
create mode 100644 arch/riscv/include/uapi/asm/byteorder.h
create mode 100644 arch/riscv/include/uapi/asm/elf.h
create mode 100644 arch/riscv/include/uapi/asm/hwcap.h
create mode 100644 arch/riscv/include/uapi/asm/ptrace.h
create mode 100644 arch/riscv/include/uapi/asm/sigcontext.h
create mode 100644 arch/riscv/include/uapi/asm/siginfo.h
create mode 100644 arch/riscv/include/uapi/asm/ucontext.h
create mode 100644 arch/riscv/include/uapi/asm/unistd.h
create mode 100644 arch/riscv/kernel/cpufeature.c
create mode 100644 arch/riscv/kernel/module.c
create mode 100644 arch/riscv/kernel/ptrace.c
create mode 100644 arch/riscv/kernel/riscv_ksyms.c
create mode 100644 arch/riscv/kernel/signal.c
create mode 100644 arch/riscv/kernel/sys_riscv.c
create mode 100644 arch/riscv/kernel/syscall_table.c
create mode 100644 arch/riscv/kernel/vdso/.gitignore
create mode 100644 arch/riscv/kernel/vdso/cmpxchg32.S
create mode 100644 arch/riscv/kernel/vdso/cmpxchg64.S
create mode 100644 arch/riscv/kernel/vdso/sigreturn.S
create mode 100644 arch/riscv/kernel/vdso/vdso.S
diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
index 5ded3f6f83ea..a1ef503d616e 100644
--- a/arch/riscv/include/asm/elf.h
+++ b/arch/riscv/include/asm/elf.h
@@ -59,7 +59,8 @@
* instruction set this CPU supports. This could be done in user space,
* but it's not easy, and we've already done it here.
*/
-#define ELF_HWCAP (0)
+#define ELF_HWCAP (elf_hwcap)
+extern unsigned long elf_hwcap;
/*
* This yields a string that ld.so will use to load implementation
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
new file mode 100644
index 000000000000..66805cba9a27
--- /dev/null
+++ b/arch/riscv/include/asm/mmu.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+
+#ifndef _ASM_RISCV_MMU_H
+#define _ASM_RISCV_MMU_H
+
+#ifndef __ASSEMBLY__
+
+typedef struct {
+ void *vdso;
+} mm_context_t;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_MMU_H */
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
new file mode 100644
index 000000000000..340201868842
--- /dev/null
+++ b/arch/riscv/include/asm/ptrace.h
@@ -0,0 +1,116 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PTRACE_H
+#define _ASM_RISCV_PTRACE_H
+
+#include <uapi/asm/ptrace.h>
+#include <asm/csr.h>
+
+#ifndef __ASSEMBLY__
+
+struct pt_regs {
+ unsigned long sepc;
+ unsigned long ra;
+ unsigned long sp;
+ unsigned long gp;
+ unsigned long tp;
+ unsigned long t0;
+ unsigned long t1;
+ unsigned long t2;
+ unsigned long s0;
+ unsigned long s1;
+ unsigned long a0;
+ unsigned long a1;
+ unsigned long a2;
+ unsigned long a3;
+ unsigned long a4;
+ unsigned long a5;
+ unsigned long a6;
+ unsigned long a7;
+ unsigned long s2;
+ unsigned long s3;
+ unsigned long s4;
+ unsigned long s5;
+ unsigned long s6;
+ unsigned long s7;
+ unsigned long s8;
+ unsigned long s9;
+ unsigned long s10;
+ unsigned long s11;
+ unsigned long t3;
+ unsigned long t4;
+ unsigned long t5;
+ unsigned long t6;
+ /* Supervisor CSRs */
+ unsigned long sstatus;
+ unsigned long sbadaddr;
+ unsigned long scause;
+};
+
+#ifdef CONFIG_64BIT
+#define REG_FMT "%016lx"
+#else
+#define REG_FMT "%08lx"
+#endif
+
+#define user_mode(regs) (((regs)->sstatus & SR_PS) == 0)
+
+
+/* Helpers for working with the instruction pointer */
+#define GET_IP(regs) ((regs)->sepc)
+#define SET_IP(regs, val) (GET_IP(regs) = (val))
+
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+ return GET_IP(regs);
+}
+static inline void instruction_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ SET_IP(regs, val);
+}
+
+#define profile_pc(regs) instruction_pointer(regs)
+
+/* Helpers for working with the user stack pointer */
+#define GET_USP(regs) ((regs)->sp)
+#define SET_USP(regs, val) (GET_USP(regs) = (val))
+
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+ return GET_USP(regs);
+}
+static inline void user_stack_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ SET_USP(regs, val);
+}
+
+/* Helpers for working with the frame pointer */
+#define GET_FP(regs) ((regs)->s0)
+#define SET_FP(regs, val) (GET_FP(regs) = (val))
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+ return GET_FP(regs);
+}
+static inline void frame_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ SET_FP(regs, val);
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
new file mode 100644
index 000000000000..c70f0e7a06b8
--- /dev/null
+++ b/arch/riscv/include/asm/syscall.h
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved.
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2015 Regents of the University of California, Berkeley
+ *
+ * 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.
+ *
+ * See asm-generic/syscall.h for descriptions of what we must do here.
+ */
+
+#ifndef _ASM_RISCV_SYSCALL_H
+#define _ASM_RISCV_SYSCALL_H
+
+#include <linux/sched.h>
+#include <linux/err.h>
+
+/* The array of function pointers for syscalls. */
+extern void *sys_call_table[];
+
+/*
+ * Only the low 32 bits of orig_r0 are meaningful, so we return int.
+ * This importantly ignores the high bits on 64-bit, so comparisons
+ * sign-extend the low 32 bits.
+ */
+static inline int syscall_get_nr(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->a7;
+}
+
+static inline void syscall_set_nr(struct task_struct *task,
+ struct pt_regs *regs,
+ int sysno)
+{
+ regs->a7 = sysno;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ /* FIXME: We can't do this... */
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ unsigned long error = regs->a0;
+
+ return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->a0;
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+ struct pt_regs *regs,
+ int error, long val)
+{
+ regs->a0 = (long) error ?: val;
+}
+
+static inline void syscall_get_arguments(struct task_struct *task,
+ struct pt_regs *regs,
+ unsigned int i, unsigned int n,
+ unsigned long *args)
+{
+ BUG_ON(i + n > 6);
+ memcpy(args, ®s->a0 + i * sizeof(regs->a0), n * sizeof(args[0]));
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+ struct pt_regs *regs,
+ unsigned int i, unsigned int n,
+ const unsigned long *args)
+{
+ BUG_ON(i + n > 6);
+ memcpy(®s->a0 + i * sizeof(regs->a0), args, n * sizeof(regs->a0));
+}
+
+#endif /* _ASM_TILE_SYSCALL_H */
diff --git a/arch/riscv/include/asm/syscalls.h b/arch/riscv/include/asm/syscalls.h
new file mode 100644
index 000000000000..6490274fbb76
--- /dev/null
+++ b/arch/riscv/include/asm/syscalls.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2014 Darius Rad <darius@bluespec.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SYSCALLS_H
+#define _ASM_RISCV_SYSCALLS_H
+
+#include <linux/linkage.h>
+
+#include <asm-generic/syscalls.h>
+
+/* kernel/sys_riscv.c */
+asmlinkage long sys_sysriscv_cmpxchg32(u32 __user * ptr, u32 new, u32 old);
+asmlinkage long sys_sysriscv_cmpxchg64(u64 __user * ptr, u64 new, u64 old);
+
+#endif /* _ASM_RISCV_SYSCALLS_H */
diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h
new file mode 100644
index 000000000000..9f250ed007cd
--- /dev/null
+++ b/arch/riscv/include/asm/unistd.h
@@ -0,0 +1,16 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#define __ARCH_HAVE_MMU
+#define __ARCH_WANT_SYS_CLONE
+#include <uapi/asm/unistd.h>
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
new file mode 100644
index 000000000000..95768a3810a7
--- /dev/null
+++ b/arch/riscv/include/asm/vdso.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ASM_RISCV_VDSO_H
+#define _ASM_RISCV_VDSO_H
+
+#include <linux/types.h>
+
+struct vdso_data {
+};
+
+#define VDSO_SYMBOL(base, name) \
+({ \
+ extern const char __vdso_##name[]; \
+ (void __user *)((unsigned long)(base) + __vdso_##name); \
+})
+
+#endif /* _ASM_RISCV_VDSO_H */
diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h
new file mode 100644
index 000000000000..1376515547cd
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/auxvec.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _UAPI_ASM_RISCV_AUXVEC_H
+#define _UAPI_ASM_RISCV_AUXVEC_H
+
+/* vDSO location */
+#define AT_SYSINFO_EHDR 33
+
+#endif /* _UAPI_ASM_RISCV_AUXVEC_H */
diff --git a/arch/riscv/include/uapi/asm/bitsperlong.h b/arch/riscv/include/uapi/asm/bitsperlong.h
new file mode 100644
index 000000000000..0b3cb52fd29d
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _UAPI_ASM_RISCV_BITSPERLONG_H
+#define _UAPI_ASM_RISCV_BITSPERLONG_H
+
+#define __BITS_PER_LONG (__SIZEOF_POINTER__ * 8)
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* _UAPI_ASM_RISCV_BITSPERLONG_H */
diff --git a/arch/riscv/include/uapi/asm/byteorder.h b/arch/riscv/include/uapi/asm/byteorder.h
new file mode 100644
index 000000000000..4ca38af2cd32
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/byteorder.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _UAPI_ASM_RISCV_BYTEORDER_H
+#define _UAPI_ASM_RISCV_BYTEORDER_H
+
+#include <linux/byteorder/little_endian.h>
+
+#endif /* _UAPI_ASM_RISCV_BYTEORDER_H */
diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h
new file mode 100644
index 000000000000..a510edfa8226
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/elf.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
+ * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _UAPI_ASM_ELF_H
+#define _UAPI_ASM_ELF_H
+
+#include <asm/ptrace.h>
+
+/* ELF register definitions */
+typedef unsigned long elf_greg_t;
+typedef struct user_regs_struct elf_gregset_t;
+#define ELF_NGREG (sizeof(elf_gregset_t) / sizeof(elf_greg_t))
+
+typedef union __riscv_fp_state elf_fpregset_t;
+
+#define ELF_RISCV_R_SYM(r_info) ((r_info) >> 32)
+#define ELF_RISCV_R_TYPE(r_info) ((r_info) & 0xffffffff)
+
+/*
+ * RISC-V relocation types
+ */
+
+/* Relocation types used by the dynamic linker */
+#define R_RISCV_NONE 0
+#define R_RISCV_32 1
+#define R_RISCV_64 2
+#define R_RISCV_RELATIVE 3
+#define R_RISCV_COPY 4
+#define R_RISCV_JUMP_SLOT 5
+#define R_RISCV_TLS_DTPMOD32 6
+#define R_RISCV_TLS_DTPMOD64 7
+#define R_RISCV_TLS_DTPREL32 8
+#define R_RISCV_TLS_DTPREL64 9
+#define R_RISCV_TLS_TPREL32 10
+#define R_RISCV_TLS_TPREL64 11
+
+/* Relocation types not used by the dynamic linker */
+#define R_RISCV_BRANCH 16
+#define R_RISCV_JAL 17
+#define R_RISCV_CALL 18
+#define R_RISCV_CALL_PLT 19
+#define R_RISCV_GOT_HI20 20
+#define R_RISCV_TLS_GOT_HI20 21
+#define R_RISCV_TLS_GD_HI20 22
+#define R_RISCV_PCREL_HI20 23
+#define R_RISCV_PCREL_LO12_I 24
+#define R_RISCV_PCREL_LO12_S 25
+#define R_RISCV_HI20 26
+#define R_RISCV_LO12_I 27
+#define R_RISCV_LO12_S 28
+#define R_RISCV_TPREL_HI20 29
+#define R_RISCV_TPREL_LO12_I 30
+#define R_RISCV_TPREL_LO12_S 31
+#define R_RISCV_TPREL_ADD 32
+#define R_RISCV_ADD8 33
+#define R_RISCV_ADD16 34
+#define R_RISCV_ADD32 35
+#define R_RISCV_ADD64 36
+#define R_RISCV_SUB8 37
+#define R_RISCV_SUB16 38
+#define R_RISCV_SUB32 39
+#define R_RISCV_SUB64 40
+#define R_RISCV_GNU_VTINHERIT 41
+#define R_RISCV_GNU_VTENTRY 42
+#define R_RISCV_ALIGN 43
+#define R_RISCV_RVC_BRANCH 44
+#define R_RISCV_RVC_JUMP 45
+#define R_RISCV_LUI 46
+#define R_RISCV_GPREL_I 47
+#define R_RISCV_GPREL_S 48
+#define R_RISCV_TPREL_I 49
+#define R_RISCV_TPREL_S 50
+#define R_RISCV_RELAX 51
+
+#endif /* _UAPI_ASM_ELF_H */
diff --git a/arch/riscv/include/uapi/asm/hwcap.h b/arch/riscv/include/uapi/asm/hwcap.h
new file mode 100644
index 000000000000..f333221c9ab2
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/hwcap.h
@@ -0,0 +1,36 @@
+/*
+ * Copied from arch/arm64/include/asm/hwcap.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __UAPI_ASM_HWCAP_H
+#define __UAPI_ASM_HWCAP_H
+
+/*
+ * Linux saves the floating-point registers according to the ISA Linux is
+ * executing on, as opposed to the ISA the user program is compiled for. This
+ * is necessary for a handful of esoteric use cases: for example, userpsace
+ * threading libraries must be able to examine the actual machine state in
+ * order to fully reconstruct the state of a thread.
+ */
+#define COMPAT_HWCAP_ISA_I (1 << ('I' - 'A'))
+#define COMPAT_HWCAP_ISA_M (1 << ('M' - 'A'))
+#define COMPAT_HWCAP_ISA_A (1 << ('A' - 'A'))
+#define COMPAT_HWCAP_ISA_F (1 << ('F' - 'A'))
+#define COMPAT_HWCAP_ISA_D (1 << ('D' - 'A'))
+#define COMPAT_HWCAP_ISA_C (1 << ('C' - 'A'))
+
+#endif
diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
new file mode 100644
index 000000000000..1a9e4cdd37e2
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _UAPI_ASM_RISCV_PTRACE_H
+#define _UAPI_ASM_RISCV_PTRACE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * User-mode register state for core dumps, ptrace, sigcontext
+ *
+ * This decouples struct pt_regs from the userspace ABI.
+ * struct user_regs_struct must form a prefix of struct pt_regs.
+ */
+struct user_regs_struct {
+ unsigned long pc;
+ unsigned long ra;
+ unsigned long sp;
+ unsigned long gp;
+ unsigned long tp;
+ unsigned long t0;
+ unsigned long t1;
+ unsigned long t2;
+ unsigned long s0;
+ unsigned long s1;
+ unsigned long a0;
+ unsigned long a1;
+ unsigned long a2;
+ unsigned long a3;
+ unsigned long a4;
+ unsigned long a5;
+ unsigned long a6;
+ unsigned long a7;
+ unsigned long s2;
+ unsigned long s3;
+ unsigned long s4;
+ unsigned long s5;
+ unsigned long s6;
+ unsigned long s7;
+ unsigned long s8;
+ unsigned long s9;
+ unsigned long s10;
+ unsigned long s11;
+ unsigned long t3;
+ unsigned long t4;
+ unsigned long t5;
+ unsigned long t6;
+};
+
+struct __riscv_f_ext_state {
+ __u32 f[32];
+ __u32 fcsr;
+};
+
+struct __riscv_d_ext_state {
+ __u64 f[32];
+ __u32 fcsr;
+};
+
+struct __riscv_q_ext_state {
+ __u64 f[64] __attribute__((aligned(16)));
+ __u32 fcsr;
+ /*
+ * Reserved for expansion of sigcontext structure. Currently zeroed
+ * upon signal, and must be zero upon sigreturn.
+ */
+ __u32 reserved[3];
+};
+
+union __riscv_fp_state {
+ struct __riscv_f_ext_state f;
+ struct __riscv_d_ext_state d;
+ struct __riscv_q_ext_state q;
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h
new file mode 100644
index 000000000000..ed7372b277fa
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/sigcontext.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _UAPI_ASM_RISCV_SIGCONTEXT_H
+#define _UAPI_ASM_RISCV_SIGCONTEXT_H
+
+#include <asm/ptrace.h>
+
+/*
+ * Signal context structure
+ *
+ * This contains the context saved before a signal handler is invoked;
+ * it is restored by sys_sigreturn / sys_rt_sigreturn.
+ */
+struct sigcontext {
+ struct user_regs_struct sc_regs;
+ union __riscv_fp_state sc_fpregs;
+};
+
+#endif /* _UAPI_ASM_RISCV_SIGCONTEXT_H */
diff --git a/arch/riscv/include/uapi/asm/siginfo.h b/arch/riscv/include/uapi/asm/siginfo.h
new file mode 100644
index 000000000000..f96849aac662
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/siginfo.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2016 SiFive, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_SIGINFO_H
+#define __ASM_SIGINFO_H
+
+#define __ARCH_SI_PREAMBLE_SIZE (__SIZEOF_POINTER__ == 4 ? 12 : 16)
+
+#include <asm-generic/siginfo.h>
+
+#endif
diff --git a/arch/riscv/include/uapi/asm/ucontext.h b/arch/riscv/include/uapi/asm/ucontext.h
new file mode 100644
index 000000000000..52eff9febcfd
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/ucontext.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2017 SiFive, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file was copied from arch/arm64/include/uapi/asm/ucontext.h
+ */
+#ifndef _UAPI__ASM_UCONTEXT_H
+#define _UAPI__ASM_UCONTEXT_H
+
+#include <linux/types.h>
+
+struct ucontext {
+ unsigned long uc_flags;
+ struct ucontext *uc_link;
+ stack_t uc_stack;
+ sigset_t uc_sigmask;
+ /* glibc uses a 1024-bit sigset_t */
+ __u8 __unused[1024 / 8 - sizeof(sigset_t)];
+ /* last for future expansion */
+ struct sigcontext uc_mcontext;
+};
+
+#endif /* _UAPI__ASM_UCONTEXT_H */
diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..37a5429cc896
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/unistd.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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 <asm-generic/unistd.h>
+
+/*
+ * These system calls add support for AMOs on RISC-V systems without support
+ * for the A extension.
+ */
+#define __NR_sysriscv_cmpxchg32 (__NR_arch_specific_syscall + 0)
+__SYSCALL(__NR_sysriscv_cmpxchg32, sys_sysriscv_cmpxchg32)
+#define __NR_sysriscv_cmpxchg64 (__NR_arch_specific_syscall + 1)
+__SYSCALL(__NR_sysriscv_cmpxchg64, sys_sysriscv_cmpxchg64)
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
new file mode 100644
index 000000000000..3ced896cfce1
--- /dev/null
+++ b/arch/riscv/kernel/cpufeature.c
@@ -0,0 +1,61 @@
+/*
+ * Copied from arch/arm64/kernel/cpufeature.c
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ * 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/of.h>
+#include <asm/processor.h>
+#include <asm/hwcap.h>
+
+unsigned long elf_hwcap __read_mostly;
+
+void riscv_fill_hwcap(void)
+{
+ struct device_node *node;
+ const char *isa;
+ size_t i;
+ static unsigned long isa2hwcap[256] = {0};
+
+ isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I;
+ isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M;
+ isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A;
+ isa2hwcap['f'] = isa2hwcap['F'] = COMPAT_HWCAP_ISA_F;
+ isa2hwcap['d'] = isa2hwcap['D'] = COMPAT_HWCAP_ISA_D;
+ isa2hwcap['c'] = isa2hwcap['C'] = COMPAT_HWCAP_ISA_C;
+
+ elf_hwcap = 0;
+
+ /*
+ * We don't support running Linux on hertergenous ISA systems. For
+ * now, we just check the ISA of the first processor.
+ */
+ node = of_find_node_by_type(NULL, "cpu");
+ if (!node) {
+ pr_warning("Unable to find \"cpu\" devicetree entry");
+ return;
+ }
+
+ if (of_property_read_string(node, "riscv,isa", &isa)) {
+ pr_warning("Unable to find \"riscv,isa\" devicetree entry");
+ return;
+ }
+
+ for (i = 0; i < strlen(isa); ++i)
+ elf_hwcap |= isa2hwcap[(unsigned char)(isa[i])];
+
+ pr_info("elf_hwcap is 0x%lx", elf_hwcap);
+}
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
new file mode 100644
index 000000000000..e0f05034fc21
--- /dev/null
+++ b/arch/riscv/kernel/module.c
@@ -0,0 +1,217 @@
+/*
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * Copyright (C) 2017 Zihao Yu
+ */
+
+#include <linux/elf.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/moduleloader.h>
+
+static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v)
+{
+ *(u64 *)location = v;
+ return 0;
+}
+
+static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ u32 imm12 = (offset & 0x1000) << (31 - 12);
+ u32 imm11 = (offset & 0x800) >> (11 - 7);
+ u32 imm10_5 = (offset & 0x7e0) << (30 - 10);
+ u32 imm4_1 = (offset & 0x1e) << (11 - 4);
+
+ *location = (*location & 0x1fff07f) | imm12 | imm11 | imm10_5 | imm4_1;
+ return 0;
+}
+
+static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ u32 imm20 = (offset & 0x100000) << (31 - 20);
+ u32 imm19_12 = (offset & 0xff000);
+ u32 imm11 = (offset & 0x800) << (20 - 11);
+ u32 imm10_1 = (offset & 0x7fe) << (30 - 10);
+
+ *location = (*location & 0xfff) | imm20 | imm19_12 | imm11 | imm10_1;
+ return 0;
+}
+
+static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ s32 hi20;
+
+ if (offset != (s32)offset) {
+ pr_err(
+ "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+ me->name, v, location);
+ return -EINVAL;
+ }
+
+ hi20 = (offset + 0x800) & 0xfffff000;
+ *location = (*location & 0xfff) | hi20;
+ return 0;
+}
+
+static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ /*
+ * v is the lo12 value to fill. It is calculated before calling this
+ * handler.
+ */
+ *location = (*location & 0xfffff) | ((v & 0xfff) << 20);
+ return 0;
+}
+
+static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ /*
+ * v is the lo12 value to fill. It is calculated before calling this
+ * handler.
+ */
+ u32 imm11_5 = (v & 0xfe0) << (31 - 11);
+ u32 imm4_0 = (v & 0x1f) << (11 - 4);
+
+ *location = (*location & 0x1fff07f) | imm11_5 | imm4_0;
+ return 0;
+}
+
+static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ s32 fill_v = offset;
+ u32 hi20, lo12;
+
+ if (offset != fill_v) {
+ pr_err(
+ "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+ me->name, v, location);
+ return -EINVAL;
+ }
+
+ hi20 = (offset + 0x800) & 0xfffff000;
+ lo12 = (offset - hi20) & 0xfff;
+ *location = (*location & 0xfff) | hi20;
+ *(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20);
+ return 0;
+}
+
+static int apply_r_riscv_relax_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ return 0;
+}
+
+static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
+ Elf_Addr v) = {
+ [R_RISCV_64] = apply_r_riscv_64_rela,
+ [R_RISCV_BRANCH] = apply_r_riscv_branch_rela,
+ [R_RISCV_JAL] = apply_r_riscv_jal_rela,
+ [R_RISCV_PCREL_HI20] = apply_r_riscv_pcrel_hi20_rela,
+ [R_RISCV_PCREL_LO12_I] = apply_r_riscv_pcrel_lo12_i_rela,
+ [R_RISCV_PCREL_LO12_S] = apply_r_riscv_pcrel_lo12_s_rela,
+ [R_RISCV_CALL_PLT] = apply_r_riscv_call_plt_rela,
+ [R_RISCV_RELAX] = apply_r_riscv_relax_rela,
+};
+
+int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
+ unsigned int symindex, unsigned int relsec,
+ struct module *me)
+{
+ Elf_Rela *rel = (void *) sechdrs[relsec].sh_addr;
+ int (*handler)(struct module *me, u32 *location, Elf_Addr v);
+ Elf_Sym *sym;
+ u32 *location;
+ unsigned int i, type;
+ Elf_Addr v;
+ int res;
+
+ pr_debug("Applying relocate section %u to %u\n", relsec,
+ sechdrs[relsec].sh_info);
+
+ for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
+ /* This is where to make the change */
+ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+ + rel[i].r_offset;
+ /* This is the symbol it is referring to */
+ sym = (Elf_Sym *)sechdrs[symindex].sh_addr
+ + ELF_RISCV_R_SYM(rel[i].r_info);
+ if (IS_ERR_VALUE(sym->st_value)) {
+ /* Ignore unresolved weak symbol */
+ if (ELF_ST_BIND(sym->st_info) == STB_WEAK)
+ continue;
+ pr_warning("%s: Unknown symbol %s\n",
+ me->name, strtab + sym->st_name);
+ return -ENOENT;
+ }
+
+ type = ELF_RISCV_R_TYPE(rel[i].r_info);
+
+ if (type < ARRAY_SIZE(reloc_handlers_rela))
+ handler = reloc_handlers_rela[type];
+ else
+ handler = NULL;
+
+ if (!handler) {
+ pr_err("%s: Unknown relocation type %u\n",
+ me->name, type);
+ return -EINVAL;
+ }
+
+ v = sym->st_value + rel[i].r_addend;
+
+ if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) {
+ unsigned int j;
+
+ for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
+ u64 hi20_loc =
+ sechdrs[sechdrs[relsec].sh_info].sh_addr
+ + rel[j].r_offset;
+ /* Find the corresponding HI20 PC-relative relocation entry */
+ if (hi20_loc == sym->st_value) {
+ Elf_Sym *hi20_sym =
+ (Elf_Sym *)sechdrs[symindex].sh_addr
+ + ELF_RISCV_R_SYM(rel[j].r_info);
+ u64 hi20_sym_val =
+ hi20_sym->st_value
+ + rel[j].r_addend;
+ /* Calculate lo12 */
+ s64 offset = hi20_sym_val - hi20_loc;
+ s32 hi20 = (offset + 0x800) & 0xfffff000;
+ s32 lo12 = offset - hi20;
+ v = lo12;
+ break;
+ }
+ }
+ if (j == sechdrs[relsec].sh_size / sizeof(*rel)) {
+ pr_err(
+ "%s: Can not find HI20 PC-relative relocation information\n",
+ me->name);
+ return -EINVAL;
+ }
+ }
+
+ res = handler(me, location, v);
+ if (res)
+ return res;
+ }
+
+ return 0;
+}
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
new file mode 100644
index 000000000000..2720d5e97354
--- /dev/null
+++ b/arch/riscv/kernel/ptrace.c
@@ -0,0 +1,138 @@
+/*
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2015 Regents of the University of California
+ * Copyright 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.
+ *
+ * Copied from arch/tile/kernel/ptrace.c
+ */
+
+#include <asm/ptrace.h>
+#include <asm/syscall.h>
+#include <asm/thread_info.h>
+#include <linux/ptrace.h>
+#include <linux/elf.h>
+#include <linux/regset.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/tracehook.h>
+#include <trace/events/syscalls.h>
+
+enum riscv_regset {
+ REGSET_X,
+};
+
+/* Put registers back to task. */
+static void putregs(struct task_struct *child, struct pt_regs *uregs)
+{
+ struct pt_regs *regs = task_pt_regs(child);
+ *regs = *uregs;
+}
+
+static int riscv_gpr_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct pt_regs *regs;
+
+ regs = task_pt_regs(target);
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf, regs, 0,
+ sizeof(*regs));
+}
+
+static int riscv_gpr_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 pt_regs regs;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®s, 0,
+ sizeof(regs));
+ if (ret)
+ return ret;
+
+ putregs(target, ®s);
+
+ return 0;
+}
+
+
+static const struct user_regset riscv_user_regset[] = {
+ [REGSET_X] = {
+ .core_note_type = NT_PRSTATUS,
+ .n = ELF_NGREG,
+ .size = sizeof(elf_greg_t),
+ .align = sizeof(elf_greg_t),
+ .get = &riscv_gpr_get,
+ .set = &riscv_gpr_set,
+ },
+};
+
+static const struct user_regset_view riscv_user_native_view = {
+ .name = "riscv",
+ .e_machine = EM_RISCV,
+ .regsets = riscv_user_regset,
+ .n = ARRAY_SIZE(riscv_user_regset),
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+ return &riscv_user_native_view;
+}
+
+void ptrace_disable(struct task_struct *child)
+{
+ clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+ unsigned long addr, unsigned long data)
+{
+ long ret = -EIO;
+
+ switch (request) {
+ default:
+ ret = ptrace_request(child, request, addr, data);
+ break;
+ }
+
+ return ret;
+}
+
+/*
+ * Allows PTRACE_SYSCALL to work. These are called from entry.S in
+ * {handle,ret_from}_syscall.
+ */
+void do_syscall_trace_enter(struct pt_regs *regs)
+{
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ if (tracehook_report_syscall_entry(regs))
+ syscall_set_nr(current, regs, -1);
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+ if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+ trace_sys_enter(regs, syscall_get_nr(current, regs));
+#endif
+}
+
+void do_syscall_trace_exit(struct pt_regs *regs)
+{
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ tracehook_report_syscall_exit(regs, 0);
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+ if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+ trace_sys_exit(regs, regs->regs[0]);
+#endif
+}
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
new file mode 100644
index 000000000000..23cc81ec9e94
--- /dev/null
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -0,0 +1,15 @@
+/*
+ * Copyright (C) 2017 Zihao Yu
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/export.h>
+#include <linux/uaccess.h>
+
+/*
+ * Assembly functions that may be used (directly or indirectly) by modules
+ */
+EXPORT_SYMBOL(__copy_user);
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
new file mode 100644
index 000000000000..e0a1b89583ef
--- /dev/null
+++ b/arch/riscv/kernel/signal.c
@@ -0,0 +1,289 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/tracehook.h>
+#include <linux/linkage.h>
+
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+#include <asm/switch_to.h>
+#include <asm/csr.h>
+
+#define DEBUG_SIG 0
+
+struct rt_sigframe {
+ struct siginfo info;
+ struct ucontext uc;
+};
+
+static long restore_d_state(struct pt_regs *regs,
+ struct __riscv_d_ext_state __user *state)
+{
+ long err;
+ err = __copy_from_user(¤t->thread.fstate, state, sizeof(*state));
+ if (likely(!err))
+ fstate_restore(current, regs);
+ return err;
+}
+
+static long save_d_state(struct pt_regs *regs,
+ struct __riscv_d_ext_state __user *state)
+{
+ fstate_save(current, regs);
+ return __copy_to_user(state, ¤t->thread.fstate, sizeof(*state));
+}
+
+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;
+ }
+ return err;
+}
+
+SYSCALL_DEFINE0(rt_sigreturn)
+{
+ struct pt_regs *regs = current_pt_regs();
+ struct rt_sigframe __user *frame;
+ struct task_struct *task;
+ sigset_t set;
+
+ /* Always make any pending restarted system calls return -EINTR */
+ current->restart_block.fn = do_no_restart_syscall;
+
+ frame = (struct rt_sigframe __user *)regs->sp;
+
+ if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+
+ if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+ goto badframe;
+
+ set_current_blocked(&set);
+
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+ goto badframe;
+
+ if (restore_altstack(&frame->uc.uc_stack))
+ goto badframe;
+
+ return regs->a0;
+
+badframe:
+ task = current;
+ if (show_unhandled_signals) {
+ pr_info_ratelimited(
+ "%s[%d]: bad frame in %s: frame=%p pc=%p sp=%p\n",
+ task->comm, task_pid_nr(task), __func__,
+ frame, (void *)regs->sepc, (void *)regs->sp);
+ }
+ force_sig(SIGSEGV, task);
+ return 0;
+}
+
+static long setup_sigcontext(struct rt_sigframe __user *frame,
+ struct pt_regs *regs)
+{
+ 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]);
+ return err;
+}
+
+static inline void __user *get_sigframe(struct ksignal *ksig,
+ struct pt_regs *regs, size_t framesize)
+{
+ unsigned long sp;
+ /* Default to using normal stack */
+ sp = regs->sp;
+
+ /*
+ * If we are on the alternate signal stack and would overflow it, don't.
+ * Return an always-bogus address instead so we will die with SIGSEGV.
+ */
+ if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize)))
+ return (void __user __force *)(-1UL);
+
+ /* This is the X/Open sanctioned signal stack switching. */
+ sp = sigsp(sp, ksig) - framesize;
+
+ /* Align the stack frame. */
+ sp &= ~0xfUL;
+
+ return (void __user *)sp;
+}
+
+
+static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
+ struct pt_regs *regs)
+{
+ struct rt_sigframe __user *frame;
+ long err = 0;
+
+ frame = get_sigframe(ksig, regs, sizeof(*frame));
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ return -EFAULT;
+
+ err |= copy_siginfo_to_user(&frame->info, &ksig->info);
+
+ /* Create the ucontext. */
+ err |= __put_user(0, &frame->uc.uc_flags);
+ err |= __put_user(NULL, &frame->uc.uc_link);
+ err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+ err |= setup_sigcontext(frame, regs);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+ if (err)
+ return -EFAULT;
+
+ /* Set up to return from userspace. */
+ regs->ra = (unsigned long)VDSO_SYMBOL(
+ current->mm->context.vdso, rt_sigreturn);
+
+ /*
+ * Set up registers for signal handler.
+ * Registers that we don't modify keep the value they had from
+ * user-space at the time we took the signal.
+ * We always pass siginfo and mcontext, regardless of SA_SIGINFO,
+ * since some things rely on this (e.g. glibc's debug/segfault.c).
+ */
+ regs->sepc = (unsigned long)ksig->ka.sa.sa_handler;
+ regs->sp = (unsigned long)frame;
+ regs->a0 = ksig->sig; /* a0: signal number */
+ regs->a1 = (unsigned long)(&frame->info); /* a1: siginfo pointer */
+ regs->a2 = (unsigned long)(&frame->uc); /* a2: ucontext pointer */
+
+#if DEBUG_SIG
+ pr_info("SIG deliver (%s:%d): sig=%d pc=%p ra=%p sp=%p\n",
+ current->comm, task_pid_nr(current), ksig->sig,
+ (void *)regs->sepc, (void *)regs->ra, frame);
+#endif
+
+ return 0;
+}
+
+static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
+{
+ sigset_t *oldset = sigmask_to_save();
+ int ret;
+
+ /* Are we from a system call? */
+ if (regs->scause == EXC_SYSCALL) {
+ /* If so, check system call restarting.. */
+ switch (regs->a0) {
+ case -ERESTART_RESTARTBLOCK:
+ case -ERESTARTNOHAND:
+ regs->a0 = -EINTR;
+ break;
+
+ case -ERESTARTSYS:
+ if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
+ regs->a0 = -EINTR;
+ break;
+ }
+ /* fallthrough */
+ case -ERESTARTNOINTR:
+ regs->sepc -= 0x4;
+ break;
+ }
+ }
+
+ /* Set up the stack frame */
+ ret = setup_rt_frame(ksig, oldset, regs);
+
+ signal_setup_done(ret, ksig, 0);
+}
+
+static void do_signal(struct pt_regs *regs)
+{
+ struct ksignal ksig;
+
+ if (get_signal(&ksig)) {
+ /* Actually deliver the signal */
+ handle_signal(&ksig, regs);
+ return;
+ }
+
+ /* Did we come from a system call? */
+ if (regs->scause == EXC_SYSCALL) {
+ /* Restart the system call - no handlers present */
+ switch (regs->a0) {
+ case -ERESTARTNOHAND:
+ case -ERESTARTSYS:
+ case -ERESTARTNOINTR:
+ regs->sepc -= 0x4;
+ break;
+ case -ERESTART_RESTARTBLOCK:
+ regs->a7 = __NR_restart_syscall;
+ regs->sepc -= 0x4;
+ break;
+ }
+ }
+
+ /*
+ * If there is no signal to deliver, we just put the saved
+ * sigmask back.
+ */
+ restore_saved_sigmask();
+}
+
+/*
+ * notification of userspace execution resumption
+ * - triggered by the _TIF_WORK_MASK flags
+ */
+asmlinkage void do_notify_resume(struct pt_regs *regs,
+ unsigned long thread_info_flags)
+{
+ /* Handle pending signal delivery */
+ if (thread_info_flags & _TIF_SIGPENDING)
+ do_signal(regs);
+
+ if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+ clear_thread_flag(TIF_NOTIFY_RESUME);
+ tracehook_notify_resume(regs);
+ }
+}
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
new file mode 100644
index 000000000000..4419604ff46c
--- /dev/null
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2014 Darius Rad <darius@bluespec.com>
+ * 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/syscalls.h>
+#include <asm/cmpxchg.h>
+#include <asm/unistd.h>
+
+#ifdef CONFIG_64BIT
+SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, off_t, offset)
+{
+ if (unlikely(offset & (~PAGE_MASK)))
+ return -EINVAL;
+ return sys_mmap_pgoff(addr, len, prot, flags, fd, offset >> PAGE_SHIFT);
+}
+#else
+SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, off_t, offset)
+{
+ /*
+ * Note that the shift for mmap2 is constant (12),
+ * regardless of PAGE_SIZE
+ */
+ if (unlikely(offset & (~PAGE_MASK >> 12)))
+ return -EINVAL;
+ return sys_mmap_pgoff(addr, len, prot, flags, fd,
+ offset >> (PAGE_SHIFT - 12));
+}
+#endif /* !CONFIG_64BIT */
+
+SYSCALL_DEFINE3(sysriscv_cmpxchg32, u32 __user *, ptr, u32, new, u32, old)
+{
+ u32 prev;
+ unsigned int err;
+
+ if (!access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)))
+ return -EFAULT;
+
+#ifdef CONFIG_ISA_A
+ err = 0;
+ prev = cmpxchg32(ptr, old, new);
+#else
+ preempt_disable();
+ err = __get_user(prev, ptr);
+ if (likely(!err && prev == old))
+ err = __put_user(new, ptr);
+ preempt_enable();
+#endif
+
+ return unlikely(err) ? err : prev;
+}
+
+SYSCALL_DEFINE3(sysriscv_cmpxchg64, u64 __user *, ptr, u64, new, u64, old)
+{
+#ifdef CONFIG_64BIT
+ u64 prev;
+ unsigned int err;
+
+ if (!access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)))
+ return -EFAULT;
+
+#ifdef CONFIG_ISA_A
+ err = 0;
+ prev = cmpxchg64(ptr, old, new);
+#else
+ preempt_disable();
+ err = __get_user(prev, ptr);
+ if (likely(!err && prev == old))
+ err = __put_user(new, ptr);
+ preempt_enable();
+#endif
+ return unlikely(err) ? err : prev;
+#else
+ return -ENOTSUPP;
+#endif
+}
diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c
new file mode 100644
index 000000000000..8fa239b67cbc
--- /dev/null
+++ b/arch/riscv/kernel/syscall_table.c
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2009 Arnd Bergmann <arnd@arndb.de>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/syscalls.h>
+
+#include <asm/syscalls.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call) [nr] = (call),
+
+void *sys_call_table[__NR_syscalls] = {
+ [0 ... __NR_syscalls - 1] = sys_ni_syscall,
+#include <asm/unistd.h>
+};
diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore
new file mode 100644
index 000000000000..f8b69d84238e
--- /dev/null
+++ b/arch/riscv/kernel/vdso/.gitignore
@@ -0,0 +1 @@
+vdso.lds
diff --git a/arch/riscv/kernel/vdso/cmpxchg32.S b/arch/riscv/kernel/vdso/cmpxchg32.S
new file mode 100644
index 000000000000..387deb4e852c
--- /dev/null
+++ b/arch/riscv/kernel/vdso/cmpxchg32.S
@@ -0,0 +1,40 @@
+/*
+ * 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
+ENTRY(__vdso_cmpxchg32)
+ .cfi_startproc
+#ifdef CONFIG_ISA_A
+/*
+ * a0: ptr
+ * a1: compare value
+ * a2: exchange value
+ */
+0:
+ lr.w.aqrl t0, 0(a0)
+ bne t0, a1, 1f
+ sc.w.aqrl t1, a2, 0(a0)
+ bnez t1, 0b
+1:
+ mv a0, t0
+ ret
+#else
+ li a7, __NR_sysriscv_cmpxchg32
+ scall
+ ret
+#endif
+ .cfi_endproc
+ENDPROC(__vdso_cmpxchg32)
diff --git a/arch/riscv/kernel/vdso/cmpxchg64.S b/arch/riscv/kernel/vdso/cmpxchg64.S
new file mode 100644
index 000000000000..6286842f78c0
--- /dev/null
+++ b/arch/riscv/kernel/vdso/cmpxchg64.S
@@ -0,0 +1,40 @@
+/*
+ * 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
+ENTRY(__vdso_cmpxchg64)
+ .cfi_startproc
+#ifdef CONFIG_ISA_A
+/*
+ * a0: ptr
+ * a1: compare value
+ * a2: exchange value
+ */
+0:
+ lr.d.aqrl t0, 0(a0)
+ bne t0, a1, 1f
+ sc.d.aqrl t1, a2, 0(a0)
+ bnez t1, 0b
+1:
+ mv a0, t0
+ ret
+#else
+ li a7, __NR_sysriscv_cmpxchg64
+ scall
+ ret
+#endif
+ .cfi_endproc
+ENDPROC(__vdso_cmpxchg64)
diff --git a/arch/riscv/kernel/vdso/sigreturn.S b/arch/riscv/kernel/vdso/sigreturn.S
new file mode 100644
index 000000000000..f5aa3d72acfb
--- /dev/null
+++ b/arch/riscv/kernel/vdso/sigreturn.S
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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
+ENTRY(__vdso_rt_sigreturn)
+ .cfi_startproc
+ .cfi_signal_frame
+ li a7, __NR_rt_sigreturn
+ scall
+ .cfi_endproc
+ENDPROC(__vdso_rt_sigreturn)
diff --git a/arch/riscv/kernel/vdso/vdso.S b/arch/riscv/kernel/vdso/vdso.S
new file mode 100644
index 000000000000..7055de5f9174
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vdso.S
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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/init.h>
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+ __PAGE_ALIGNED_DATA
+
+ .globl vdso_start, vdso_end
+ .balign PAGE_SIZE
+vdso_start:
+ .incbin "arch/riscv/kernel/vdso/vdso.so"
+ .balign PAGE_SIZE
+vdso_end:
+
+ .previous
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* Re: [PATCH 8/9] RISC-V: User-facing API
2017-07-04 19:51 ` Palmer Dabbelt
@ 2017-07-05 10:24 ` James Hogan
-1 siblings, 0 replies; 58+ messages in thread
From: James Hogan @ 2017-07-05 10:24 UTC (permalink / raw)
To: Palmer Dabbelt
Cc: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, paul.gortmaker, linux,
linux-kernel, linux-arch, albert, patches
[-- Attachment #1: Type: text/plain, Size: 4358 bytes --]
On Tue, Jul 04, 2017 at 12:51:01PM -0700, Palmer Dabbelt wrote:
> diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
> new file mode 100644
> index 000000000000..2720d5e97354
> --- /dev/null
> +++ b/arch/riscv/kernel/ptrace.c
> @@ -0,0 +1,138 @@
> +/* Put registers back to task. */
> +static void putregs(struct task_struct *child, struct pt_regs *uregs)
> +{
> + struct pt_regs *regs = task_pt_regs(child);
> + *regs = *uregs;
> +}
> +
> +static int riscv_gpr_get(struct task_struct *target,
> + const struct user_regset *regset,
> + unsigned int pos, unsigned int count,
> + void *kbuf, void __user *ubuf)
> +{
> + struct pt_regs *regs;
> +
> + regs = task_pt_regs(target);
> + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, regs, 0,
> + sizeof(*regs));
sizeof(struct pt_regs) > sizeof(struct user_regs_struct), which allows
supervisor registers to be copied too. I think you should be using
sizeof(struct user_regs_struct) instead.
> +}
> +
> +static int riscv_gpr_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 pt_regs regs;
> +
> + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®s, 0,
> + sizeof(regs));
same
> + if (ret)
> + return ret;
> +
> + putregs(target, ®s);
you're still copying via the stack without initialising the non-written
fields. If userland does a short PTRACE_SETREGSET the remaining fields
will be copied from the uninitialised kernel stack and accessible to
userland via PTRACE_GETREGSET.
Even if the user does a full sizeof(struct user_regs_struct) (not
pt_regs) PTRACE_SETREGSET the supervisor registers will be overwritten
with uninitialised stack content.
> diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
> new file mode 100644
> index 000000000000..4419604ff46c
> --- /dev/null
> +++ b/arch/riscv/kernel/sys_riscv.c
> +SYSCALL_DEFINE3(sysriscv_cmpxchg32, u32 __user *, ptr, u32, new, u32, old)
> +{
> + u32 prev;
> + unsigned int err;
> +
> + if (!access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)))
> + return -EFAULT;
> +
> +#ifdef CONFIG_ISA_A
> + err = 0;
> + prev = cmpxchg32(ptr, old, new);
I think this needs a special version of cmpxchg (or for cmpxchg to be
modified) with fixup protection to return -EFAULT in case the page isn't
mapped or is paged out/read only.
> +#else
> + preempt_disable();
> + err = __get_user(prev, ptr);
> + if (likely(!err && prev == old))
> + err = __put_user(new, ptr);
> + preempt_enable();
> +#endif
> +
> + return unlikely(err) ? err : prev;
> +}
> +
> +SYSCALL_DEFINE3(sysriscv_cmpxchg64, u64 __user *, ptr, u64, new, u64, old)
> +{
> +#ifdef CONFIG_64BIT
> + u64 prev;
> + unsigned int err;
> +
> + if (!access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)))
> + return -EFAULT;
> +
> +#ifdef CONFIG_ISA_A
> + err = 0;
> + prev = cmpxchg64(ptr, old, new);
Likewise
> +#else
> + preempt_disable();
> + err = __get_user(prev, ptr);
> + if (likely(!err && prev == old))
> + err = __put_user(new, ptr);
> + preempt_enable();
> +#endif
> + return unlikely(err) ? err : prev;
> +#else
> + return -ENOTSUPP;
I think -ENOSYS is more standard for missing/unimplemented system calls.
A better way IMO would be to #ifdef the definitions in unistd.h, then
the __NR_* definitions could also be more accurately extracted from the
kernel headers, and you could just ifdef CONFIG_64BIT the whole syscall
implementation, i.e.:
> diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h
> new file mode 100644
> index 000000000000..37a5429cc896
> --- /dev/null
> +++ b/arch/riscv/include/uapi/asm/unistd.h
> @@ -0,0 +1,23 @@
> +/*
> + * These system calls add support for AMOs on RISC-V systems without support
> + * for the A extension.
> + */
> +#define __NR_sysriscv_cmpxchg32 (__NR_arch_specific_syscall + 0)
> +__SYSCALL(__NR_sysriscv_cmpxchg32, sys_sysriscv_cmpxchg32)
+ifdef WHATEVER_BUILTIN_GCC_DEFINES_FOR_64BIT_RISCV_ABI
In case its helpful the following should list builtin preprocessor
defines for given CFLAGS:
${CROSS_COMPILE}gcc ${CFLAGS} -dM -E -</dev/null
> +#define __NR_sysriscv_cmpxchg64 (__NR_arch_specific_syscall + 1)
> +__SYSCALL(__NR_sysriscv_cmpxchg64, sys_sysriscv_cmpxchg64)
+endif
Cheers
James
[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply [flat|nested] 58+ messages in thread* Re: [PATCH 8/9] RISC-V: User-facing API
@ 2017-07-05 10:24 ` James Hogan
0 siblings, 0 replies; 58+ messages in thread
From: James Hogan @ 2017-07-05 10:24 UTC (permalink / raw)
To: Palmer Dabbelt
Cc: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, paul.gortmaker, linux,
linux-kernel, linux-arch, albert, patches
[-- Attachment #1: Type: text/plain, Size: 4358 bytes --]
On Tue, Jul 04, 2017 at 12:51:01PM -0700, Palmer Dabbelt wrote:
> diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
> new file mode 100644
> index 000000000000..2720d5e97354
> --- /dev/null
> +++ b/arch/riscv/kernel/ptrace.c
> @@ -0,0 +1,138 @@
> +/* Put registers back to task. */
> +static void putregs(struct task_struct *child, struct pt_regs *uregs)
> +{
> + struct pt_regs *regs = task_pt_regs(child);
> + *regs = *uregs;
> +}
> +
> +static int riscv_gpr_get(struct task_struct *target,
> + const struct user_regset *regset,
> + unsigned int pos, unsigned int count,
> + void *kbuf, void __user *ubuf)
> +{
> + struct pt_regs *regs;
> +
> + regs = task_pt_regs(target);
> + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, regs, 0,
> + sizeof(*regs));
sizeof(struct pt_regs) > sizeof(struct user_regs_struct), which allows
supervisor registers to be copied too. I think you should be using
sizeof(struct user_regs_struct) instead.
> +}
> +
> +static int riscv_gpr_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 pt_regs regs;
> +
> + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®s, 0,
> + sizeof(regs));
same
> + if (ret)
> + return ret;
> +
> + putregs(target, ®s);
you're still copying via the stack without initialising the non-written
fields. If userland does a short PTRACE_SETREGSET the remaining fields
will be copied from the uninitialised kernel stack and accessible to
userland via PTRACE_GETREGSET.
Even if the user does a full sizeof(struct user_regs_struct) (not
pt_regs) PTRACE_SETREGSET the supervisor registers will be overwritten
with uninitialised stack content.
> diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
> new file mode 100644
> index 000000000000..4419604ff46c
> --- /dev/null
> +++ b/arch/riscv/kernel/sys_riscv.c
> +SYSCALL_DEFINE3(sysriscv_cmpxchg32, u32 __user *, ptr, u32, new, u32, old)
> +{
> + u32 prev;
> + unsigned int err;
> +
> + if (!access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)))
> + return -EFAULT;
> +
> +#ifdef CONFIG_ISA_A
> + err = 0;
> + prev = cmpxchg32(ptr, old, new);
I think this needs a special version of cmpxchg (or for cmpxchg to be
modified) with fixup protection to return -EFAULT in case the page isn't
mapped or is paged out/read only.
> +#else
> + preempt_disable();
> + err = __get_user(prev, ptr);
> + if (likely(!err && prev == old))
> + err = __put_user(new, ptr);
> + preempt_enable();
> +#endif
> +
> + return unlikely(err) ? err : prev;
> +}
> +
> +SYSCALL_DEFINE3(sysriscv_cmpxchg64, u64 __user *, ptr, u64, new, u64, old)
> +{
> +#ifdef CONFIG_64BIT
> + u64 prev;
> + unsigned int err;
> +
> + if (!access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)))
> + return -EFAULT;
> +
> +#ifdef CONFIG_ISA_A
> + err = 0;
> + prev = cmpxchg64(ptr, old, new);
Likewise
> +#else
> + preempt_disable();
> + err = __get_user(prev, ptr);
> + if (likely(!err && prev == old))
> + err = __put_user(new, ptr);
> + preempt_enable();
> +#endif
> + return unlikely(err) ? err : prev;
> +#else
> + return -ENOTSUPP;
I think -ENOSYS is more standard for missing/unimplemented system calls.
A better way IMO would be to #ifdef the definitions in unistd.h, then
the __NR_* definitions could also be more accurately extracted from the
kernel headers, and you could just ifdef CONFIG_64BIT the whole syscall
implementation, i.e.:
> diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h
> new file mode 100644
> index 000000000000..37a5429cc896
> --- /dev/null
> +++ b/arch/riscv/include/uapi/asm/unistd.h
> @@ -0,0 +1,23 @@
> +/*
> + * These system calls add support for AMOs on RISC-V systems without support
> + * for the A extension.
> + */
> +#define __NR_sysriscv_cmpxchg32 (__NR_arch_specific_syscall + 0)
> +__SYSCALL(__NR_sysriscv_cmpxchg32, sys_sysriscv_cmpxchg32)
+ifdef WHATEVER_BUILTIN_GCC_DEFINES_FOR_64BIT_RISCV_ABI
In case its helpful the following should list builtin preprocessor
defines for given CFLAGS:
${CROSS_COMPILE}gcc ${CFLAGS} -dM -E -</dev/null
> +#define __NR_sysriscv_cmpxchg64 (__NR_arch_specific_syscall + 1)
> +__SYSCALL(__NR_sysriscv_cmpxchg64, sys_sysriscv_cmpxchg64)
+endif
Cheers
James
[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply [flat|nested] 58+ messages in thread
* Re: [PATCH 8/9] RISC-V: User-facing API
2017-07-04 19:51 ` Palmer Dabbelt
(?)
(?)
@ 2017-07-06 2:01 ` Christoph Hellwig
2017-07-06 8:55 ` Will Deacon
-1 siblings, 1 reply; 58+ messages in thread
From: Christoph Hellwig @ 2017-07-06 2:01 UTC (permalink / raw)
To: Palmer Dabbelt
Cc: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
I'm a bit concerned about these cmpxchg syscalls, and I'd like to
understand if my concerns are justified.
For a new instruction set that starts out in the 201x years we really
should have cmpxchg as a mandatory instruction - if not in the CPU
it should be in the Linux ABI so that we don't have to deal with a mess
where programs will either need an indirection for CPUs that have
cmpxchg capabilities vs those that don't, and we don't need to worry
if given binaries work on all CPUs.
What keeps from from declaring that the RISV-A extension is mandatory
for Linux?
^ permalink raw reply [flat|nested] 58+ messages in thread
* Re: [PATCH 8/9] RISC-V: User-facing API
2017-07-06 2:01 ` Christoph Hellwig
@ 2017-07-06 8:55 ` Will Deacon
2017-07-06 15:34 ` Christoph Hellwig
0 siblings, 1 reply; 58+ messages in thread
From: Will Deacon @ 2017-07-06 8:55 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Palmer Dabbelt, peterz, mingo, mcgrof, viro, sfr,
nicolas.dichtel, rmk+kernel, msalter, tklauser, james.hogan,
paul.gortmaker, linux, linux-kernel, linux-arch, albert, patches,
mathieu.desnoyers
On Wed, Jul 05, 2017 at 07:01:41PM -0700, Christoph Hellwig wrote:
> I'm a bit concerned about these cmpxchg syscalls, and I'd like to
> understand if my concerns are justified.
>
> For a new instruction set that starts out in the 201x years we really
> should have cmpxchg as a mandatory instruction - if not in the CPU
> it should be in the Linux ABI so that we don't have to deal with a mess
> where programs will either need an indirection for CPUs that have
> cmpxchg capabilities vs those that don't, and we don't need to worry
> if given binaries work on all CPUs.
Agreed on the indirection; it feels like this is something that should be in
the vDSO, which could use the cmpxchg instruction if it's available, or
otherwise just uses plain loads and stores. In the latter case, the kernel
can then detect if you're preempted in the vdso critical region and restart
the cmpxchg (we do something similar for arch/arm/, but it's slightly
simpler with the vectors page (see entry-armv.S).
Alternatively, we could revisit the restartable sequences work from Mathieu,
but I think that's stalled pending real-world performance data.
> What keeps from from declaring that the RISV-A extension is mandatory
> for Linux?
Or that!
Will
^ permalink raw reply [flat|nested] 58+ messages in thread
* Re: [PATCH 8/9] RISC-V: User-facing API
2017-07-06 8:55 ` Will Deacon
@ 2017-07-06 15:34 ` Christoph Hellwig
2017-07-06 15:45 ` Will Deacon
0 siblings, 1 reply; 58+ messages in thread
From: Christoph Hellwig @ 2017-07-06 15:34 UTC (permalink / raw)
To: Will Deacon
Cc: Christoph Hellwig, Palmer Dabbelt, peterz, mingo, mcgrof, viro,
sfr, nicolas.dichtel, rmk+kernel, msalter, tklauser, james.hogan,
paul.gortmaker, linux, linux-kernel, linux-arch, albert, patches,
mathieu.desnoyers
On Thu, Jul 06, 2017 at 09:55:03AM +0100, Will Deacon wrote:
> Agreed on the indirection; it feels like this is something that should be in
> the vDSO, which could use the cmpxchg instruction if it's available, or
> otherwise just uses plain loads and stores.
Even that seems like a lot of indirection for something that is in
the critical fast path for synchronization. I really can't understand
how a new ISA / ABI could even come up with an idea as stupid as making
essential synchronization primitives optional.
^ permalink raw reply [flat|nested] 58+ messages in thread
* Re: [PATCH 8/9] RISC-V: User-facing API
2017-07-06 15:34 ` Christoph Hellwig
@ 2017-07-06 15:45 ` Will Deacon
[not found] ` <mhng-f92ef7c4-049a-4a71-be12-c600d1d7858b@palmer-si-x1c4>
0 siblings, 1 reply; 58+ messages in thread
From: Will Deacon @ 2017-07-06 15:45 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Palmer Dabbelt, peterz, mingo, mcgrof, viro, sfr,
nicolas.dichtel, rmk+kernel, msalter, tklauser, james.hogan,
paul.gortmaker, linux, linux-kernel, linux-arch, albert, patches,
mathieu.desnoyers
On Thu, Jul 06, 2017 at 08:34:27AM -0700, Christoph Hellwig wrote:
> On Thu, Jul 06, 2017 at 09:55:03AM +0100, Will Deacon wrote:
> > Agreed on the indirection; it feels like this is something that should be in
> > the vDSO, which could use the cmpxchg instruction if it's available, or
> > otherwise just uses plain loads and stores.
>
> Even that seems like a lot of indirection for something that is in
> the critical fast path for synchronization. I really can't understand
> how a new ISA / ABI could even come up with an idea as stupid as making
> essential synchronization primitives optional.
No disagreement there!
Will
^ permalink raw reply [flat|nested] 58+ messages in thread
* Re: [PATCH 8/9] RISC-V: User-facing API
2017-07-04 19:51 ` Palmer Dabbelt
` (2 preceding siblings ...)
(?)
@ 2017-07-06 15:34 ` Dave P Martin
-1 siblings, 0 replies; 58+ messages in thread
From: Dave P Martin @ 2017-07-06 15:34 UTC (permalink / raw)
To: Palmer Dabbelt
Cc: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
On Wed, Jul 05, 2017 at 09:49:36AM -0700, Palmer Dabbelt wrote:
> On Mon, 03 Jul 2017 16:06:39 PDT (-0700), james.hogan@imgtec.com wrote:
> > On Thu, Jun 29, 2017 at 02:42:38PM -0700, Palmer Dabbelt wrote:
> >> On Wed, 28 Jun 2017 15:42:37 PDT (-0700), james.hogan@imgtec.com wrote:
> >> > On Wed, Jun 28, 2017 at 11:55:37AM -0700, Palmer Dabbelt wrote:
> >> >> diff --git a/arch/riscv/include/uapi/asm/ucontext.h b/arch/riscv/include/uapi/asm/ucontext.h
> >> >> new file mode 100644
> >> >> index 000000000000..52eff9febcfd
> >> >> --- /dev/null
> >> >> +++ b/arch/riscv/include/uapi/asm/ucontext.h
> >> > ...
> >> >> +struct ucontext {
> >> >> + unsigned long uc_flags;
> >> >> + struct ucontext *uc_link;
> >> >> + stack_t uc_stack;
> >> >> + sigset_t uc_sigmask;
> >> >> + /* glibc uses a 1024-bit sigset_t */
> >> >> + __u8 __unused[1024 / 8 - sizeof(sigset_t)];
> >> >> + /* last for future expansion */
> >> >> + struct sigcontext uc_mcontext;
> >> >> +};
> >> >
> >> > Any particular reason not to use the asm-generic ucontext?
> >>
> >> In the generic ucontext, 'uc_sigmask' is at the end of the structure so it can
> >> be expanded. Since we want our mcontext to be expandable as well, we
> >> pre-allocate some expandable space for sigmask and then put mcontext at the
> >> end.
> >>
> >> We stole this idea from arm64.
> >
> > Curious. __unused seems like overkill to be honest given that expanding
> > the number of signals up to 128 causes other issues (as discovered on
> > MIPS e.g. the waitpid() status, with stopsig not fitting below the exit
> > code (shift 8) and core dump flag (bit 7)), but perhaps it could be
> > carefully expanded by splitting the stopsig field.
>
> Sorry, I don't understand the intricacies of this in the slightest. In general
> we try to avoid surprises in software land in RISC-V, so whenever we do
> something we go look at the most popular architectures (Intel and ARM) and try
> to ensure we don't paint ourselves into any corners that they didn't.
I think Catalin was concerned that putting uc_sigmask at the end breaks
extensibility of sigcontext.
[Catalin, please comment if I'm misquoting you ;) ]
Generic ucontext seems broken in any case, when kernel/user sigset_t
sizes differ:
sigset_t oldmask, newmask;
void handler(int n, siginfo_t *si, void *uc_)
{
ucontext_t *uc = uc_;
oldmask = uc->uc_sigmask; uc->uc_sigmask = newmask;
}
With generic ucontext, this can overrun and corrupt memory if the user/
kernel sigset_t sizes differ. The only fix is to reserve space in
ucontext for the larger of the two sigset sizes, which generic ucontext
does not do.
There's also the problem you comment on where only 7 bits of signal
number are available in wait() status values: with 0x7f being magic and
0 not a valid signal number, that probably allows up to 126 signals.
An arch could possibly have its own definitions to get beyond this, but
it's all done by magic numbers and open-coding in core code today.
i.e., the "extensibility" in generic ucontext may be bogus.
So, you can commit to a sane maximum number of signals (say, 64) in
your ABI, but this means that your libc sigset_t size probably needs to
match and you can never grow beyond that without an ABI break.
Or you can reserve enough space in ucontext for the userspace sigset_t.
Using generic signal.h and ucontext.h effectively commits you to max 64
signals AFAICT. The extra space may be permanently wasted, but that's
preferable to memory corruption.
(Note, I don't know myself where the "1024" comes from. Are there any
POSIXish systems implementing anywhere near that number of signals? Is
there a real usecase for it? Maybe it's just overzealous
futureproofing?)
> > Looks harmless here I suppose so I defer to others. If it is the
> > preferred approach does it make sense to make it the "default" for new
> > architectures at some point?
>
> Again, this isn't really my thing, but we chose this because we thought it was
> the sane way to do it. Unless we're doing something silly, I don't see why it
> wouldn't be a reasonable default. This is predicated on having expandable
> architectural state, otherwise putting sigmask at the end seems sane.
Note, the contents of sigcontext are nonportable but are nonetheless
ABI, and some userspace software does expect to be able to poke about in
there, modify the signal return state, etc.
Additionally the whole signal frame cannot safely exceed MINSIGSTKSZ in
size (which looks like 2K if you're relying on generic signal.h -- not
a big number when compared against upcoming vector architectures).
Going beyond MINSIGSTKSZ is a user ABI break, as is any non-probeable
change to the contents of struct sigcontext, including changes to its
size.
We are burned by this on arm64 with SVE: arm64 has its own MINSIGSTKSZ
(5K), which is not enough for the biggest possible SVE implemetations
(over 8K for the SVE state alone). I have some proposals to mitigate
this [1], but a complete solution is not possible.
Without any flags, size or version field or some kind of extensible
list structure, you would likely have trouble extending your sigcontext
without ABI breaks.
The ucontext API is unfortunately fundamentally broken, especially with
regard to extensibility. It's debatable whether the context argument
to sigaction handlers should have been ucontext_t, but we seem to be
stuck with it. POSIX no longer attempts to specify most of the de
facto ucontext API behaviour, but it persists because there are things
that userspace can't do any other way.
In principle we could cook up a new signal interface, and a new arch
could avoid the current and legacy interfaces entirely.
For example, the signal context could be made properly extensible, and
a cookie could be registered for each handler so that libc can wrap
signal handlers without the need for runtime-generated trampolines.
Then a POSIX compatibilty interface could be implemented in libc.
Could be a tough sell though -- and there's a fair risk we'd come up
with something that is still broken.
Cheers
---Dave
[1] [RFC PATCH v2 0/6] Signal frame expansion support
http://lists.infradead.org/pipermail/linux-arm-kernel/2017-April/501163.html
(Now merged, except for the AT_MINSIGSTKSZ auxv entry to report the
signal frame size -- since we won't need this until later and it could
benefit from more discussion and it would be good to build some
consensus around it if possible. I plan to talk about this and
related topics at Plumbers.)
^ permalink raw reply [flat|nested] 58+ messages in thread
* [PATCH 8/9] RISC-V: User-facing API
2017-07-04 19:50 ` Palmer Dabbelt
` (12 preceding siblings ...)
(?)
@ 2017-07-04 19:51 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:51 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains code that is in some way visible to the user:
including via system calls, the VDSO, module loading and signal
handling. It also contains some generic code that is ABI visible.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
arch/riscv/include/asm/elf.h | 3 +-
arch/riscv/include/asm/mmu.h | 26 +++
arch/riscv/include/asm/ptrace.h | 116 ++++++++++++
arch/riscv/include/asm/syscall.h | 90 ++++++++++
arch/riscv/include/asm/syscalls.h | 25 +++
arch/riscv/include/asm/unistd.h | 16 ++
arch/riscv/include/asm/vdso.h | 32 ++++
arch/riscv/include/uapi/asm/auxvec.h | 24 +++
arch/riscv/include/uapi/asm/bitsperlong.h | 25 +++
arch/riscv/include/uapi/asm/byteorder.h | 23 +++
arch/riscv/include/uapi/asm/elf.h | 83 +++++++++
arch/riscv/include/uapi/asm/hwcap.h | 36 ++++
arch/riscv/include/uapi/asm/ptrace.h | 90 ++++++++++
arch/riscv/include/uapi/asm/sigcontext.h | 30 ++++
arch/riscv/include/uapi/asm/siginfo.h | 24 +++
arch/riscv/include/uapi/asm/ucontext.h | 35 ++++
arch/riscv/include/uapi/asm/unistd.h | 23 +++
arch/riscv/kernel/cpufeature.c | 61 +++++++
arch/riscv/kernel/module.c | 217 ++++++++++++++++++++++
arch/riscv/kernel/ptrace.c | 138 ++++++++++++++
arch/riscv/kernel/riscv_ksyms.c | 15 ++
arch/riscv/kernel/signal.c | 289 ++++++++++++++++++++++++++++++
arch/riscv/kernel/sys_riscv.c | 90 ++++++++++
arch/riscv/kernel/syscall_table.c | 25 +++
arch/riscv/kernel/vdso/.gitignore | 1 +
arch/riscv/kernel/vdso/cmpxchg32.S | 40 +++++
arch/riscv/kernel/vdso/cmpxchg64.S | 40 +++++
arch/riscv/kernel/vdso/sigreturn.S | 24 +++
arch/riscv/kernel/vdso/vdso.S | 27 +++
29 files changed, 1667 insertions(+), 1 deletion(-)
create mode 100644 arch/riscv/include/asm/mmu.h
create mode 100644 arch/riscv/include/asm/ptrace.h
create mode 100644 arch/riscv/include/asm/syscall.h
create mode 100644 arch/riscv/include/asm/syscalls.h
create mode 100644 arch/riscv/include/asm/unistd.h
create mode 100644 arch/riscv/include/asm/vdso.h
create mode 100644 arch/riscv/include/uapi/asm/auxvec.h
create mode 100644 arch/riscv/include/uapi/asm/bitsperlong.h
create mode 100644 arch/riscv/include/uapi/asm/byteorder.h
create mode 100644 arch/riscv/include/uapi/asm/elf.h
create mode 100644 arch/riscv/include/uapi/asm/hwcap.h
create mode 100644 arch/riscv/include/uapi/asm/ptrace.h
create mode 100644 arch/riscv/include/uapi/asm/sigcontext.h
create mode 100644 arch/riscv/include/uapi/asm/siginfo.h
create mode 100644 arch/riscv/include/uapi/asm/ucontext.h
create mode 100644 arch/riscv/include/uapi/asm/unistd.h
create mode 100644 arch/riscv/kernel/cpufeature.c
create mode 100644 arch/riscv/kernel/module.c
create mode 100644 arch/riscv/kernel/ptrace.c
create mode 100644 arch/riscv/kernel/riscv_ksyms.c
create mode 100644 arch/riscv/kernel/signal.c
create mode 100644 arch/riscv/kernel/sys_riscv.c
create mode 100644 arch/riscv/kernel/syscall_table.c
create mode 100644 arch/riscv/kernel/vdso/.gitignore
create mode 100644 arch/riscv/kernel/vdso/cmpxchg32.S
create mode 100644 arch/riscv/kernel/vdso/cmpxchg64.S
create mode 100644 arch/riscv/kernel/vdso/sigreturn.S
create mode 100644 arch/riscv/kernel/vdso/vdso.S
diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
index 5ded3f6f83ea..a1ef503d616e 100644
--- a/arch/riscv/include/asm/elf.h
+++ b/arch/riscv/include/asm/elf.h
@@ -59,7 +59,8 @@
* instruction set this CPU supports. This could be done in user space,
* but it's not easy, and we've already done it here.
*/
-#define ELF_HWCAP (0)
+#define ELF_HWCAP (elf_hwcap)
+extern unsigned long elf_hwcap;
/*
* This yields a string that ld.so will use to load implementation
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
new file mode 100644
index 000000000000..66805cba9a27
--- /dev/null
+++ b/arch/riscv/include/asm/mmu.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+
+#ifndef _ASM_RISCV_MMU_H
+#define _ASM_RISCV_MMU_H
+
+#ifndef __ASSEMBLY__
+
+typedef struct {
+ void *vdso;
+} mm_context_t;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_MMU_H */
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
new file mode 100644
index 000000000000..340201868842
--- /dev/null
+++ b/arch/riscv/include/asm/ptrace.h
@@ -0,0 +1,116 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_PTRACE_H
+#define _ASM_RISCV_PTRACE_H
+
+#include <uapi/asm/ptrace.h>
+#include <asm/csr.h>
+
+#ifndef __ASSEMBLY__
+
+struct pt_regs {
+ unsigned long sepc;
+ unsigned long ra;
+ unsigned long sp;
+ unsigned long gp;
+ unsigned long tp;
+ unsigned long t0;
+ unsigned long t1;
+ unsigned long t2;
+ unsigned long s0;
+ unsigned long s1;
+ unsigned long a0;
+ unsigned long a1;
+ unsigned long a2;
+ unsigned long a3;
+ unsigned long a4;
+ unsigned long a5;
+ unsigned long a6;
+ unsigned long a7;
+ unsigned long s2;
+ unsigned long s3;
+ unsigned long s4;
+ unsigned long s5;
+ unsigned long s6;
+ unsigned long s7;
+ unsigned long s8;
+ unsigned long s9;
+ unsigned long s10;
+ unsigned long s11;
+ unsigned long t3;
+ unsigned long t4;
+ unsigned long t5;
+ unsigned long t6;
+ /* Supervisor CSRs */
+ unsigned long sstatus;
+ unsigned long sbadaddr;
+ unsigned long scause;
+};
+
+#ifdef CONFIG_64BIT
+#define REG_FMT "%016lx"
+#else
+#define REG_FMT "%08lx"
+#endif
+
+#define user_mode(regs) (((regs)->sstatus & SR_PS) == 0)
+
+
+/* Helpers for working with the instruction pointer */
+#define GET_IP(regs) ((regs)->sepc)
+#define SET_IP(regs, val) (GET_IP(regs) = (val))
+
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+ return GET_IP(regs);
+}
+static inline void instruction_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ SET_IP(regs, val);
+}
+
+#define profile_pc(regs) instruction_pointer(regs)
+
+/* Helpers for working with the user stack pointer */
+#define GET_USP(regs) ((regs)->sp)
+#define SET_USP(regs, val) (GET_USP(regs) = (val))
+
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+ return GET_USP(regs);
+}
+static inline void user_stack_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ SET_USP(regs, val);
+}
+
+/* Helpers for working with the frame pointer */
+#define GET_FP(regs) ((regs)->s0)
+#define SET_FP(regs, val) (GET_FP(regs) = (val))
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+ return GET_FP(regs);
+}
+static inline void frame_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ SET_FP(regs, val);
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
new file mode 100644
index 000000000000..c70f0e7a06b8
--- /dev/null
+++ b/arch/riscv/include/asm/syscall.h
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved.
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2015 Regents of the University of California, Berkeley
+ *
+ * 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.
+ *
+ * See asm-generic/syscall.h for descriptions of what we must do here.
+ */
+
+#ifndef _ASM_RISCV_SYSCALL_H
+#define _ASM_RISCV_SYSCALL_H
+
+#include <linux/sched.h>
+#include <linux/err.h>
+
+/* The array of function pointers for syscalls. */
+extern void *sys_call_table[];
+
+/*
+ * Only the low 32 bits of orig_r0 are meaningful, so we return int.
+ * This importantly ignores the high bits on 64-bit, so comparisons
+ * sign-extend the low 32 bits.
+ */
+static inline int syscall_get_nr(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->a7;
+}
+
+static inline void syscall_set_nr(struct task_struct *task,
+ struct pt_regs *regs,
+ int sysno)
+{
+ regs->a7 = sysno;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ /* FIXME: We can't do this... */
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ unsigned long error = regs->a0;
+
+ return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->a0;
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+ struct pt_regs *regs,
+ int error, long val)
+{
+ regs->a0 = (long) error ?: val;
+}
+
+static inline void syscall_get_arguments(struct task_struct *task,
+ struct pt_regs *regs,
+ unsigned int i, unsigned int n,
+ unsigned long *args)
+{
+ BUG_ON(i + n > 6);
+ memcpy(args, ®s->a0 + i * sizeof(regs->a0), n * sizeof(args[0]));
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+ struct pt_regs *regs,
+ unsigned int i, unsigned int n,
+ const unsigned long *args)
+{
+ BUG_ON(i + n > 6);
+ memcpy(®s->a0 + i * sizeof(regs->a0), args, n * sizeof(regs->a0));
+}
+
+#endif /* _ASM_TILE_SYSCALL_H */
diff --git a/arch/riscv/include/asm/syscalls.h b/arch/riscv/include/asm/syscalls.h
new file mode 100644
index 000000000000..6490274fbb76
--- /dev/null
+++ b/arch/riscv/include/asm/syscalls.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2014 Darius Rad <darius@bluespec.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_RISCV_SYSCALLS_H
+#define _ASM_RISCV_SYSCALLS_H
+
+#include <linux/linkage.h>
+
+#include <asm-generic/syscalls.h>
+
+/* kernel/sys_riscv.c */
+asmlinkage long sys_sysriscv_cmpxchg32(u32 __user * ptr, u32 new, u32 old);
+asmlinkage long sys_sysriscv_cmpxchg64(u64 __user * ptr, u64 new, u64 old);
+
+#endif /* _ASM_RISCV_SYSCALLS_H */
diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h
new file mode 100644
index 000000000000..9f250ed007cd
--- /dev/null
+++ b/arch/riscv/include/asm/unistd.h
@@ -0,0 +1,16 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#define __ARCH_HAVE_MMU
+#define __ARCH_WANT_SYS_CLONE
+#include <uapi/asm/unistd.h>
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
new file mode 100644
index 000000000000..95768a3810a7
--- /dev/null
+++ b/arch/riscv/include/asm/vdso.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ASM_RISCV_VDSO_H
+#define _ASM_RISCV_VDSO_H
+
+#include <linux/types.h>
+
+struct vdso_data {
+};
+
+#define VDSO_SYMBOL(base, name) \
+({ \
+ extern const char __vdso_##name[]; \
+ (void __user *)((unsigned long)(base) + __vdso_##name); \
+})
+
+#endif /* _ASM_RISCV_VDSO_H */
diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h
new file mode 100644
index 000000000000..1376515547cd
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/auxvec.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _UAPI_ASM_RISCV_AUXVEC_H
+#define _UAPI_ASM_RISCV_AUXVEC_H
+
+/* vDSO location */
+#define AT_SYSINFO_EHDR 33
+
+#endif /* _UAPI_ASM_RISCV_AUXVEC_H */
diff --git a/arch/riscv/include/uapi/asm/bitsperlong.h b/arch/riscv/include/uapi/asm/bitsperlong.h
new file mode 100644
index 000000000000..0b3cb52fd29d
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _UAPI_ASM_RISCV_BITSPERLONG_H
+#define _UAPI_ASM_RISCV_BITSPERLONG_H
+
+#define __BITS_PER_LONG (__SIZEOF_POINTER__ * 8)
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* _UAPI_ASM_RISCV_BITSPERLONG_H */
diff --git a/arch/riscv/include/uapi/asm/byteorder.h b/arch/riscv/include/uapi/asm/byteorder.h
new file mode 100644
index 000000000000..4ca38af2cd32
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/byteorder.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _UAPI_ASM_RISCV_BYTEORDER_H
+#define _UAPI_ASM_RISCV_BYTEORDER_H
+
+#include <linux/byteorder/little_endian.h>
+
+#endif /* _UAPI_ASM_RISCV_BYTEORDER_H */
diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h
new file mode 100644
index 000000000000..a510edfa8226
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/elf.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
+ * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _UAPI_ASM_ELF_H
+#define _UAPI_ASM_ELF_H
+
+#include <asm/ptrace.h>
+
+/* ELF register definitions */
+typedef unsigned long elf_greg_t;
+typedef struct user_regs_struct elf_gregset_t;
+#define ELF_NGREG (sizeof(elf_gregset_t) / sizeof(elf_greg_t))
+
+typedef union __riscv_fp_state elf_fpregset_t;
+
+#define ELF_RISCV_R_SYM(r_info) ((r_info) >> 32)
+#define ELF_RISCV_R_TYPE(r_info) ((r_info) & 0xffffffff)
+
+/*
+ * RISC-V relocation types
+ */
+
+/* Relocation types used by the dynamic linker */
+#define R_RISCV_NONE 0
+#define R_RISCV_32 1
+#define R_RISCV_64 2
+#define R_RISCV_RELATIVE 3
+#define R_RISCV_COPY 4
+#define R_RISCV_JUMP_SLOT 5
+#define R_RISCV_TLS_DTPMOD32 6
+#define R_RISCV_TLS_DTPMOD64 7
+#define R_RISCV_TLS_DTPREL32 8
+#define R_RISCV_TLS_DTPREL64 9
+#define R_RISCV_TLS_TPREL32 10
+#define R_RISCV_TLS_TPREL64 11
+
+/* Relocation types not used by the dynamic linker */
+#define R_RISCV_BRANCH 16
+#define R_RISCV_JAL 17
+#define R_RISCV_CALL 18
+#define R_RISCV_CALL_PLT 19
+#define R_RISCV_GOT_HI20 20
+#define R_RISCV_TLS_GOT_HI20 21
+#define R_RISCV_TLS_GD_HI20 22
+#define R_RISCV_PCREL_HI20 23
+#define R_RISCV_PCREL_LO12_I 24
+#define R_RISCV_PCREL_LO12_S 25
+#define R_RISCV_HI20 26
+#define R_RISCV_LO12_I 27
+#define R_RISCV_LO12_S 28
+#define R_RISCV_TPREL_HI20 29
+#define R_RISCV_TPREL_LO12_I 30
+#define R_RISCV_TPREL_LO12_S 31
+#define R_RISCV_TPREL_ADD 32
+#define R_RISCV_ADD8 33
+#define R_RISCV_ADD16 34
+#define R_RISCV_ADD32 35
+#define R_RISCV_ADD64 36
+#define R_RISCV_SUB8 37
+#define R_RISCV_SUB16 38
+#define R_RISCV_SUB32 39
+#define R_RISCV_SUB64 40
+#define R_RISCV_GNU_VTINHERIT 41
+#define R_RISCV_GNU_VTENTRY 42
+#define R_RISCV_ALIGN 43
+#define R_RISCV_RVC_BRANCH 44
+#define R_RISCV_RVC_JUMP 45
+#define R_RISCV_LUI 46
+#define R_RISCV_GPREL_I 47
+#define R_RISCV_GPREL_S 48
+#define R_RISCV_TPREL_I 49
+#define R_RISCV_TPREL_S 50
+#define R_RISCV_RELAX 51
+
+#endif /* _UAPI_ASM_ELF_H */
diff --git a/arch/riscv/include/uapi/asm/hwcap.h b/arch/riscv/include/uapi/asm/hwcap.h
new file mode 100644
index 000000000000..f333221c9ab2
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/hwcap.h
@@ -0,0 +1,36 @@
+/*
+ * Copied from arch/arm64/include/asm/hwcap.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __UAPI_ASM_HWCAP_H
+#define __UAPI_ASM_HWCAP_H
+
+/*
+ * Linux saves the floating-point registers according to the ISA Linux is
+ * executing on, as opposed to the ISA the user program is compiled for. This
+ * is necessary for a handful of esoteric use cases: for example, userpsace
+ * threading libraries must be able to examine the actual machine state in
+ * order to fully reconstruct the state of a thread.
+ */
+#define COMPAT_HWCAP_ISA_I (1 << ('I' - 'A'))
+#define COMPAT_HWCAP_ISA_M (1 << ('M' - 'A'))
+#define COMPAT_HWCAP_ISA_A (1 << ('A' - 'A'))
+#define COMPAT_HWCAP_ISA_F (1 << ('F' - 'A'))
+#define COMPAT_HWCAP_ISA_D (1 << ('D' - 'A'))
+#define COMPAT_HWCAP_ISA_C (1 << ('C' - 'A'))
+
+#endif
diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
new file mode 100644
index 000000000000..1a9e4cdd37e2
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _UAPI_ASM_RISCV_PTRACE_H
+#define _UAPI_ASM_RISCV_PTRACE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * User-mode register state for core dumps, ptrace, sigcontext
+ *
+ * This decouples struct pt_regs from the userspace ABI.
+ * struct user_regs_struct must form a prefix of struct pt_regs.
+ */
+struct user_regs_struct {
+ unsigned long pc;
+ unsigned long ra;
+ unsigned long sp;
+ unsigned long gp;
+ unsigned long tp;
+ unsigned long t0;
+ unsigned long t1;
+ unsigned long t2;
+ unsigned long s0;
+ unsigned long s1;
+ unsigned long a0;
+ unsigned long a1;
+ unsigned long a2;
+ unsigned long a3;
+ unsigned long a4;
+ unsigned long a5;
+ unsigned long a6;
+ unsigned long a7;
+ unsigned long s2;
+ unsigned long s3;
+ unsigned long s4;
+ unsigned long s5;
+ unsigned long s6;
+ unsigned long s7;
+ unsigned long s8;
+ unsigned long s9;
+ unsigned long s10;
+ unsigned long s11;
+ unsigned long t3;
+ unsigned long t4;
+ unsigned long t5;
+ unsigned long t6;
+};
+
+struct __riscv_f_ext_state {
+ __u32 f[32];
+ __u32 fcsr;
+};
+
+struct __riscv_d_ext_state {
+ __u64 f[32];
+ __u32 fcsr;
+};
+
+struct __riscv_q_ext_state {
+ __u64 f[64] __attribute__((aligned(16)));
+ __u32 fcsr;
+ /*
+ * Reserved for expansion of sigcontext structure. Currently zeroed
+ * upon signal, and must be zero upon sigreturn.
+ */
+ __u32 reserved[3];
+};
+
+union __riscv_fp_state {
+ struct __riscv_f_ext_state f;
+ struct __riscv_d_ext_state d;
+ struct __riscv_q_ext_state q;
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h
new file mode 100644
index 000000000000..ed7372b277fa
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/sigcontext.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+#ifndef _UAPI_ASM_RISCV_SIGCONTEXT_H
+#define _UAPI_ASM_RISCV_SIGCONTEXT_H
+
+#include <asm/ptrace.h>
+
+/*
+ * Signal context structure
+ *
+ * This contains the context saved before a signal handler is invoked;
+ * it is restored by sys_sigreturn / sys_rt_sigreturn.
+ */
+struct sigcontext {
+ struct user_regs_struct sc_regs;
+ union __riscv_fp_state sc_fpregs;
+};
+
+#endif /* _UAPI_ASM_RISCV_SIGCONTEXT_H */
diff --git a/arch/riscv/include/uapi/asm/siginfo.h b/arch/riscv/include/uapi/asm/siginfo.h
new file mode 100644
index 000000000000..f96849aac662
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/siginfo.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2016 SiFive, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_SIGINFO_H
+#define __ASM_SIGINFO_H
+
+#define __ARCH_SI_PREAMBLE_SIZE (__SIZEOF_POINTER__ == 4 ? 12 : 16)
+
+#include <asm-generic/siginfo.h>
+
+#endif
diff --git a/arch/riscv/include/uapi/asm/ucontext.h b/arch/riscv/include/uapi/asm/ucontext.h
new file mode 100644
index 000000000000..52eff9febcfd
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/ucontext.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2017 SiFive, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file was copied from arch/arm64/include/uapi/asm/ucontext.h
+ */
+#ifndef _UAPI__ASM_UCONTEXT_H
+#define _UAPI__ASM_UCONTEXT_H
+
+#include <linux/types.h>
+
+struct ucontext {
+ unsigned long uc_flags;
+ struct ucontext *uc_link;
+ stack_t uc_stack;
+ sigset_t uc_sigmask;
+ /* glibc uses a 1024-bit sigset_t */
+ __u8 __unused[1024 / 8 - sizeof(sigset_t)];
+ /* last for future expansion */
+ struct sigcontext uc_mcontext;
+};
+
+#endif /* _UAPI__ASM_UCONTEXT_H */
diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..37a5429cc896
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/unistd.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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 <asm-generic/unistd.h>
+
+/*
+ * These system calls add support for AMOs on RISC-V systems without support
+ * for the A extension.
+ */
+#define __NR_sysriscv_cmpxchg32 (__NR_arch_specific_syscall + 0)
+__SYSCALL(__NR_sysriscv_cmpxchg32, sys_sysriscv_cmpxchg32)
+#define __NR_sysriscv_cmpxchg64 (__NR_arch_specific_syscall + 1)
+__SYSCALL(__NR_sysriscv_cmpxchg64, sys_sysriscv_cmpxchg64)
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
new file mode 100644
index 000000000000..3ced896cfce1
--- /dev/null
+++ b/arch/riscv/kernel/cpufeature.c
@@ -0,0 +1,61 @@
+/*
+ * Copied from arch/arm64/kernel/cpufeature.c
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ * 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/of.h>
+#include <asm/processor.h>
+#include <asm/hwcap.h>
+
+unsigned long elf_hwcap __read_mostly;
+
+void riscv_fill_hwcap(void)
+{
+ struct device_node *node;
+ const char *isa;
+ size_t i;
+ static unsigned long isa2hwcap[256] = {0};
+
+ isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I;
+ isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M;
+ isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A;
+ isa2hwcap['f'] = isa2hwcap['F'] = COMPAT_HWCAP_ISA_F;
+ isa2hwcap['d'] = isa2hwcap['D'] = COMPAT_HWCAP_ISA_D;
+ isa2hwcap['c'] = isa2hwcap['C'] = COMPAT_HWCAP_ISA_C;
+
+ elf_hwcap = 0;
+
+ /*
+ * We don't support running Linux on hertergenous ISA systems. For
+ * now, we just check the ISA of the first processor.
+ */
+ node = of_find_node_by_type(NULL, "cpu");
+ if (!node) {
+ pr_warning("Unable to find \"cpu\" devicetree entry");
+ return;
+ }
+
+ if (of_property_read_string(node, "riscv,isa", &isa)) {
+ pr_warning("Unable to find \"riscv,isa\" devicetree entry");
+ return;
+ }
+
+ for (i = 0; i < strlen(isa); ++i)
+ elf_hwcap |= isa2hwcap[(unsigned char)(isa[i])];
+
+ pr_info("elf_hwcap is 0x%lx", elf_hwcap);
+}
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
new file mode 100644
index 000000000000..e0f05034fc21
--- /dev/null
+++ b/arch/riscv/kernel/module.c
@@ -0,0 +1,217 @@
+/*
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * Copyright (C) 2017 Zihao Yu
+ */
+
+#include <linux/elf.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/moduleloader.h>
+
+static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v)
+{
+ *(u64 *)location = v;
+ return 0;
+}
+
+static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ u32 imm12 = (offset & 0x1000) << (31 - 12);
+ u32 imm11 = (offset & 0x800) >> (11 - 7);
+ u32 imm10_5 = (offset & 0x7e0) << (30 - 10);
+ u32 imm4_1 = (offset & 0x1e) << (11 - 4);
+
+ *location = (*location & 0x1fff07f) | imm12 | imm11 | imm10_5 | imm4_1;
+ return 0;
+}
+
+static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ u32 imm20 = (offset & 0x100000) << (31 - 20);
+ u32 imm19_12 = (offset & 0xff000);
+ u32 imm11 = (offset & 0x800) << (20 - 11);
+ u32 imm10_1 = (offset & 0x7fe) << (30 - 10);
+
+ *location = (*location & 0xfff) | imm20 | imm19_12 | imm11 | imm10_1;
+ return 0;
+}
+
+static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ s32 hi20;
+
+ if (offset != (s32)offset) {
+ pr_err(
+ "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+ me->name, v, location);
+ return -EINVAL;
+ }
+
+ hi20 = (offset + 0x800) & 0xfffff000;
+ *location = (*location & 0xfff) | hi20;
+ return 0;
+}
+
+static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ /*
+ * v is the lo12 value to fill. It is calculated before calling this
+ * handler.
+ */
+ *location = (*location & 0xfffff) | ((v & 0xfff) << 20);
+ return 0;
+}
+
+static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ /*
+ * v is the lo12 value to fill. It is calculated before calling this
+ * handler.
+ */
+ u32 imm11_5 = (v & 0xfe0) << (31 - 11);
+ u32 imm4_0 = (v & 0x1f) << (11 - 4);
+
+ *location = (*location & 0x1fff07f) | imm11_5 | imm4_0;
+ return 0;
+}
+
+static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ s64 offset = (void *)v - (void *)location;
+ s32 fill_v = offset;
+ u32 hi20, lo12;
+
+ if (offset != fill_v) {
+ pr_err(
+ "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+ me->name, v, location);
+ return -EINVAL;
+ }
+
+ hi20 = (offset + 0x800) & 0xfffff000;
+ lo12 = (offset - hi20) & 0xfff;
+ *location = (*location & 0xfff) | hi20;
+ *(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20);
+ return 0;
+}
+
+static int apply_r_riscv_relax_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ return 0;
+}
+
+static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
+ Elf_Addr v) = {
+ [R_RISCV_64] = apply_r_riscv_64_rela,
+ [R_RISCV_BRANCH] = apply_r_riscv_branch_rela,
+ [R_RISCV_JAL] = apply_r_riscv_jal_rela,
+ [R_RISCV_PCREL_HI20] = apply_r_riscv_pcrel_hi20_rela,
+ [R_RISCV_PCREL_LO12_I] = apply_r_riscv_pcrel_lo12_i_rela,
+ [R_RISCV_PCREL_LO12_S] = apply_r_riscv_pcrel_lo12_s_rela,
+ [R_RISCV_CALL_PLT] = apply_r_riscv_call_plt_rela,
+ [R_RISCV_RELAX] = apply_r_riscv_relax_rela,
+};
+
+int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
+ unsigned int symindex, unsigned int relsec,
+ struct module *me)
+{
+ Elf_Rela *rel = (void *) sechdrs[relsec].sh_addr;
+ int (*handler)(struct module *me, u32 *location, Elf_Addr v);
+ Elf_Sym *sym;
+ u32 *location;
+ unsigned int i, type;
+ Elf_Addr v;
+ int res;
+
+ pr_debug("Applying relocate section %u to %u\n", relsec,
+ sechdrs[relsec].sh_info);
+
+ for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
+ /* This is where to make the change */
+ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+ + rel[i].r_offset;
+ /* This is the symbol it is referring to */
+ sym = (Elf_Sym *)sechdrs[symindex].sh_addr
+ + ELF_RISCV_R_SYM(rel[i].r_info);
+ if (IS_ERR_VALUE(sym->st_value)) {
+ /* Ignore unresolved weak symbol */
+ if (ELF_ST_BIND(sym->st_info) == STB_WEAK)
+ continue;
+ pr_warning("%s: Unknown symbol %s\n",
+ me->name, strtab + sym->st_name);
+ return -ENOENT;
+ }
+
+ type = ELF_RISCV_R_TYPE(rel[i].r_info);
+
+ if (type < ARRAY_SIZE(reloc_handlers_rela))
+ handler = reloc_handlers_rela[type];
+ else
+ handler = NULL;
+
+ if (!handler) {
+ pr_err("%s: Unknown relocation type %u\n",
+ me->name, type);
+ return -EINVAL;
+ }
+
+ v = sym->st_value + rel[i].r_addend;
+
+ if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) {
+ unsigned int j;
+
+ for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
+ u64 hi20_loc =
+ sechdrs[sechdrs[relsec].sh_info].sh_addr
+ + rel[j].r_offset;
+ /* Find the corresponding HI20 PC-relative relocation entry */
+ if (hi20_loc == sym->st_value) {
+ Elf_Sym *hi20_sym =
+ (Elf_Sym *)sechdrs[symindex].sh_addr
+ + ELF_RISCV_R_SYM(rel[j].r_info);
+ u64 hi20_sym_val =
+ hi20_sym->st_value
+ + rel[j].r_addend;
+ /* Calculate lo12 */
+ s64 offset = hi20_sym_val - hi20_loc;
+ s32 hi20 = (offset + 0x800) & 0xfffff000;
+ s32 lo12 = offset - hi20;
+ v = lo12;
+ break;
+ }
+ }
+ if (j == sechdrs[relsec].sh_size / sizeof(*rel)) {
+ pr_err(
+ "%s: Can not find HI20 PC-relative relocation information\n",
+ me->name);
+ return -EINVAL;
+ }
+ }
+
+ res = handler(me, location, v);
+ if (res)
+ return res;
+ }
+
+ return 0;
+}
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
new file mode 100644
index 000000000000..2720d5e97354
--- /dev/null
+++ b/arch/riscv/kernel/ptrace.c
@@ -0,0 +1,138 @@
+/*
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2015 Regents of the University of California
+ * Copyright 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.
+ *
+ * Copied from arch/tile/kernel/ptrace.c
+ */
+
+#include <asm/ptrace.h>
+#include <asm/syscall.h>
+#include <asm/thread_info.h>
+#include <linux/ptrace.h>
+#include <linux/elf.h>
+#include <linux/regset.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/tracehook.h>
+#include <trace/events/syscalls.h>
+
+enum riscv_regset {
+ REGSET_X,
+};
+
+/* Put registers back to task. */
+static void putregs(struct task_struct *child, struct pt_regs *uregs)
+{
+ struct pt_regs *regs = task_pt_regs(child);
+ *regs = *uregs;
+}
+
+static int riscv_gpr_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct pt_regs *regs;
+
+ regs = task_pt_regs(target);
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf, regs, 0,
+ sizeof(*regs));
+}
+
+static int riscv_gpr_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 pt_regs regs;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®s, 0,
+ sizeof(regs));
+ if (ret)
+ return ret;
+
+ putregs(target, ®s);
+
+ return 0;
+}
+
+
+static const struct user_regset riscv_user_regset[] = {
+ [REGSET_X] = {
+ .core_note_type = NT_PRSTATUS,
+ .n = ELF_NGREG,
+ .size = sizeof(elf_greg_t),
+ .align = sizeof(elf_greg_t),
+ .get = &riscv_gpr_get,
+ .set = &riscv_gpr_set,
+ },
+};
+
+static const struct user_regset_view riscv_user_native_view = {
+ .name = "riscv",
+ .e_machine = EM_RISCV,
+ .regsets = riscv_user_regset,
+ .n = ARRAY_SIZE(riscv_user_regset),
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+ return &riscv_user_native_view;
+}
+
+void ptrace_disable(struct task_struct *child)
+{
+ clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+ unsigned long addr, unsigned long data)
+{
+ long ret = -EIO;
+
+ switch (request) {
+ default:
+ ret = ptrace_request(child, request, addr, data);
+ break;
+ }
+
+ return ret;
+}
+
+/*
+ * Allows PTRACE_SYSCALL to work. These are called from entry.S in
+ * {handle,ret_from}_syscall.
+ */
+void do_syscall_trace_enter(struct pt_regs *regs)
+{
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ if (tracehook_report_syscall_entry(regs))
+ syscall_set_nr(current, regs, -1);
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+ if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+ trace_sys_enter(regs, syscall_get_nr(current, regs));
+#endif
+}
+
+void do_syscall_trace_exit(struct pt_regs *regs)
+{
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ tracehook_report_syscall_exit(regs, 0);
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+ if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+ trace_sys_exit(regs, regs->regs[0]);
+#endif
+}
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
new file mode 100644
index 000000000000..23cc81ec9e94
--- /dev/null
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -0,0 +1,15 @@
+/*
+ * Copyright (C) 2017 Zihao Yu
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/export.h>
+#include <linux/uaccess.h>
+
+/*
+ * Assembly functions that may be used (directly or indirectly) by modules
+ */
+EXPORT_SYMBOL(__copy_user);
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
new file mode 100644
index 000000000000..e0a1b89583ef
--- /dev/null
+++ b/arch/riscv/kernel/signal.c
@@ -0,0 +1,289 @@
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see the file COPYING, or write
+ * to the Free Software Foundation, Inc.,
+ */
+
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/tracehook.h>
+#include <linux/linkage.h>
+
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+#include <asm/switch_to.h>
+#include <asm/csr.h>
+
+#define DEBUG_SIG 0
+
+struct rt_sigframe {
+ struct siginfo info;
+ struct ucontext uc;
+};
+
+static long restore_d_state(struct pt_regs *regs,
+ struct __riscv_d_ext_state __user *state)
+{
+ long err;
+ err = __copy_from_user(¤t->thread.fstate, state, sizeof(*state));
+ if (likely(!err))
+ fstate_restore(current, regs);
+ return err;
+}
+
+static long save_d_state(struct pt_regs *regs,
+ struct __riscv_d_ext_state __user *state)
+{
+ fstate_save(current, regs);
+ return __copy_to_user(state, ¤t->thread.fstate, sizeof(*state));
+}
+
+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;
+ }
+ return err;
+}
+
+SYSCALL_DEFINE0(rt_sigreturn)
+{
+ struct pt_regs *regs = current_pt_regs();
+ struct rt_sigframe __user *frame;
+ struct task_struct *task;
+ sigset_t set;
+
+ /* Always make any pending restarted system calls return -EINTR */
+ current->restart_block.fn = do_no_restart_syscall;
+
+ frame = (struct rt_sigframe __user *)regs->sp;
+
+ if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+
+ if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+ goto badframe;
+
+ set_current_blocked(&set);
+
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+ goto badframe;
+
+ if (restore_altstack(&frame->uc.uc_stack))
+ goto badframe;
+
+ return regs->a0;
+
+badframe:
+ task = current;
+ if (show_unhandled_signals) {
+ pr_info_ratelimited(
+ "%s[%d]: bad frame in %s: frame=%p pc=%p sp=%p\n",
+ task->comm, task_pid_nr(task), __func__,
+ frame, (void *)regs->sepc, (void *)regs->sp);
+ }
+ force_sig(SIGSEGV, task);
+ return 0;
+}
+
+static long setup_sigcontext(struct rt_sigframe __user *frame,
+ struct pt_regs *regs)
+{
+ 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]);
+ return err;
+}
+
+static inline void __user *get_sigframe(struct ksignal *ksig,
+ struct pt_regs *regs, size_t framesize)
+{
+ unsigned long sp;
+ /* Default to using normal stack */
+ sp = regs->sp;
+
+ /*
+ * If we are on the alternate signal stack and would overflow it, don't.
+ * Return an always-bogus address instead so we will die with SIGSEGV.
+ */
+ if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize)))
+ return (void __user __force *)(-1UL);
+
+ /* This is the X/Open sanctioned signal stack switching. */
+ sp = sigsp(sp, ksig) - framesize;
+
+ /* Align the stack frame. */
+ sp &= ~0xfUL;
+
+ return (void __user *)sp;
+}
+
+
+static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
+ struct pt_regs *regs)
+{
+ struct rt_sigframe __user *frame;
+ long err = 0;
+
+ frame = get_sigframe(ksig, regs, sizeof(*frame));
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ return -EFAULT;
+
+ err |= copy_siginfo_to_user(&frame->info, &ksig->info);
+
+ /* Create the ucontext. */
+ err |= __put_user(0, &frame->uc.uc_flags);
+ err |= __put_user(NULL, &frame->uc.uc_link);
+ err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+ err |= setup_sigcontext(frame, regs);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+ if (err)
+ return -EFAULT;
+
+ /* Set up to return from userspace. */
+ regs->ra = (unsigned long)VDSO_SYMBOL(
+ current->mm->context.vdso, rt_sigreturn);
+
+ /*
+ * Set up registers for signal handler.
+ * Registers that we don't modify keep the value they had from
+ * user-space at the time we took the signal.
+ * We always pass siginfo and mcontext, regardless of SA_SIGINFO,
+ * since some things rely on this (e.g. glibc's debug/segfault.c).
+ */
+ regs->sepc = (unsigned long)ksig->ka.sa.sa_handler;
+ regs->sp = (unsigned long)frame;
+ regs->a0 = ksig->sig; /* a0: signal number */
+ regs->a1 = (unsigned long)(&frame->info); /* a1: siginfo pointer */
+ regs->a2 = (unsigned long)(&frame->uc); /* a2: ucontext pointer */
+
+#if DEBUG_SIG
+ pr_info("SIG deliver (%s:%d): sig=%d pc=%p ra=%p sp=%p\n",
+ current->comm, task_pid_nr(current), ksig->sig,
+ (void *)regs->sepc, (void *)regs->ra, frame);
+#endif
+
+ return 0;
+}
+
+static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
+{
+ sigset_t *oldset = sigmask_to_save();
+ int ret;
+
+ /* Are we from a system call? */
+ if (regs->scause == EXC_SYSCALL) {
+ /* If so, check system call restarting.. */
+ switch (regs->a0) {
+ case -ERESTART_RESTARTBLOCK:
+ case -ERESTARTNOHAND:
+ regs->a0 = -EINTR;
+ break;
+
+ case -ERESTARTSYS:
+ if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
+ regs->a0 = -EINTR;
+ break;
+ }
+ /* fallthrough */
+ case -ERESTARTNOINTR:
+ regs->sepc -= 0x4;
+ break;
+ }
+ }
+
+ /* Set up the stack frame */
+ ret = setup_rt_frame(ksig, oldset, regs);
+
+ signal_setup_done(ret, ksig, 0);
+}
+
+static void do_signal(struct pt_regs *regs)
+{
+ struct ksignal ksig;
+
+ if (get_signal(&ksig)) {
+ /* Actually deliver the signal */
+ handle_signal(&ksig, regs);
+ return;
+ }
+
+ /* Did we come from a system call? */
+ if (regs->scause == EXC_SYSCALL) {
+ /* Restart the system call - no handlers present */
+ switch (regs->a0) {
+ case -ERESTARTNOHAND:
+ case -ERESTARTSYS:
+ case -ERESTARTNOINTR:
+ regs->sepc -= 0x4;
+ break;
+ case -ERESTART_RESTARTBLOCK:
+ regs->a7 = __NR_restart_syscall;
+ regs->sepc -= 0x4;
+ break;
+ }
+ }
+
+ /*
+ * If there is no signal to deliver, we just put the saved
+ * sigmask back.
+ */
+ restore_saved_sigmask();
+}
+
+/*
+ * notification of userspace execution resumption
+ * - triggered by the _TIF_WORK_MASK flags
+ */
+asmlinkage void do_notify_resume(struct pt_regs *regs,
+ unsigned long thread_info_flags)
+{
+ /* Handle pending signal delivery */
+ if (thread_info_flags & _TIF_SIGPENDING)
+ do_signal(regs);
+
+ if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+ clear_thread_flag(TIF_NOTIFY_RESUME);
+ tracehook_notify_resume(regs);
+ }
+}
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
new file mode 100644
index 000000000000..4419604ff46c
--- /dev/null
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2014 Darius Rad <darius@bluespec.com>
+ * 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/syscalls.h>
+#include <asm/cmpxchg.h>
+#include <asm/unistd.h>
+
+#ifdef CONFIG_64BIT
+SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, off_t, offset)
+{
+ if (unlikely(offset & (~PAGE_MASK)))
+ return -EINVAL;
+ return sys_mmap_pgoff(addr, len, prot, flags, fd, offset >> PAGE_SHIFT);
+}
+#else
+SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, off_t, offset)
+{
+ /*
+ * Note that the shift for mmap2 is constant (12),
+ * regardless of PAGE_SIZE
+ */
+ if (unlikely(offset & (~PAGE_MASK >> 12)))
+ return -EINVAL;
+ return sys_mmap_pgoff(addr, len, prot, flags, fd,
+ offset >> (PAGE_SHIFT - 12));
+}
+#endif /* !CONFIG_64BIT */
+
+SYSCALL_DEFINE3(sysriscv_cmpxchg32, u32 __user *, ptr, u32, new, u32, old)
+{
+ u32 prev;
+ unsigned int err;
+
+ if (!access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)))
+ return -EFAULT;
+
+#ifdef CONFIG_ISA_A
+ err = 0;
+ prev = cmpxchg32(ptr, old, new);
+#else
+ preempt_disable();
+ err = __get_user(prev, ptr);
+ if (likely(!err && prev == old))
+ err = __put_user(new, ptr);
+ preempt_enable();
+#endif
+
+ return unlikely(err) ? err : prev;
+}
+
+SYSCALL_DEFINE3(sysriscv_cmpxchg64, u64 __user *, ptr, u64, new, u64, old)
+{
+#ifdef CONFIG_64BIT
+ u64 prev;
+ unsigned int err;
+
+ if (!access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)))
+ return -EFAULT;
+
+#ifdef CONFIG_ISA_A
+ err = 0;
+ prev = cmpxchg64(ptr, old, new);
+#else
+ preempt_disable();
+ err = __get_user(prev, ptr);
+ if (likely(!err && prev == old))
+ err = __put_user(new, ptr);
+ preempt_enable();
+#endif
+ return unlikely(err) ? err : prev;
+#else
+ return -ENOTSUPP;
+#endif
+}
diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c
new file mode 100644
index 000000000000..8fa239b67cbc
--- /dev/null
+++ b/arch/riscv/kernel/syscall_table.c
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2009 Arnd Bergmann <arnd@arndb.de>
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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/syscalls.h>
+
+#include <asm/syscalls.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call) [nr] = (call),
+
+void *sys_call_table[__NR_syscalls] = {
+ [0 ... __NR_syscalls - 1] = sys_ni_syscall,
+#include <asm/unistd.h>
+};
diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore
new file mode 100644
index 000000000000..f8b69d84238e
--- /dev/null
+++ b/arch/riscv/kernel/vdso/.gitignore
@@ -0,0 +1 @@
+vdso.lds
diff --git a/arch/riscv/kernel/vdso/cmpxchg32.S b/arch/riscv/kernel/vdso/cmpxchg32.S
new file mode 100644
index 000000000000..387deb4e852c
--- /dev/null
+++ b/arch/riscv/kernel/vdso/cmpxchg32.S
@@ -0,0 +1,40 @@
+/*
+ * 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
+ENTRY(__vdso_cmpxchg32)
+ .cfi_startproc
+#ifdef CONFIG_ISA_A
+/*
+ * a0: ptr
+ * a1: compare value
+ * a2: exchange value
+ */
+0:
+ lr.w.aqrl t0, 0(a0)
+ bne t0, a1, 1f
+ sc.w.aqrl t1, a2, 0(a0)
+ bnez t1, 0b
+1:
+ mv a0, t0
+ ret
+#else
+ li a7, __NR_sysriscv_cmpxchg32
+ scall
+ ret
+#endif
+ .cfi_endproc
+ENDPROC(__vdso_cmpxchg32)
diff --git a/arch/riscv/kernel/vdso/cmpxchg64.S b/arch/riscv/kernel/vdso/cmpxchg64.S
new file mode 100644
index 000000000000..6286842f78c0
--- /dev/null
+++ b/arch/riscv/kernel/vdso/cmpxchg64.S
@@ -0,0 +1,40 @@
+/*
+ * 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
+ENTRY(__vdso_cmpxchg64)
+ .cfi_startproc
+#ifdef CONFIG_ISA_A
+/*
+ * a0: ptr
+ * a1: compare value
+ * a2: exchange value
+ */
+0:
+ lr.d.aqrl t0, 0(a0)
+ bne t0, a1, 1f
+ sc.d.aqrl t1, a2, 0(a0)
+ bnez t1, 0b
+1:
+ mv a0, t0
+ ret
+#else
+ li a7, __NR_sysriscv_cmpxchg64
+ scall
+ ret
+#endif
+ .cfi_endproc
+ENDPROC(__vdso_cmpxchg64)
diff --git a/arch/riscv/kernel/vdso/sigreturn.S b/arch/riscv/kernel/vdso/sigreturn.S
new file mode 100644
index 000000000000..f5aa3d72acfb
--- /dev/null
+++ b/arch/riscv/kernel/vdso/sigreturn.S
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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
+ENTRY(__vdso_rt_sigreturn)
+ .cfi_startproc
+ .cfi_signal_frame
+ li a7, __NR_rt_sigreturn
+ scall
+ .cfi_endproc
+ENDPROC(__vdso_rt_sigreturn)
diff --git a/arch/riscv/kernel/vdso/vdso.S b/arch/riscv/kernel/vdso/vdso.S
new file mode 100644
index 000000000000..7055de5f9174
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vdso.S
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ *
+ * 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/init.h>
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+ __PAGE_ALIGNED_DATA
+
+ .globl vdso_start, vdso_end
+ .balign PAGE_SIZE
+vdso_start:
+ .incbin "arch/riscv/kernel/vdso/vdso.so"
+ .balign PAGE_SIZE
+vdso_end:
+
+ .previous
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 9/9] RISC-V: Build Infastructure
2017-07-04 19:50 ` Palmer Dabbelt
@ 2017-07-04 19:51 ` Palmer Dabbelt
-1 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:51 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains all the build infastructure that actually enables
the RISC-V port. This includes Makefiles, linker scripts, and Kconfig
files. It also contains the only top-level change, which adds RISC-V to
the list of architectures that need a sed run to produce the ARCH
variable when building locally.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
Makefile | 3 +-
arch/riscv/Kconfig | 304 ++++++++++++++++++++++++++++++
arch/riscv/Makefile | 64 +++++++
arch/riscv/configs/freedom-u500_defconfig | 52 +++++
arch/riscv/configs/spike32_defconfig | 50 +++++
arch/riscv/configs/spike64_defconfig | 46 +++++
arch/riscv/include/asm/Kbuild | 61 ++++++
arch/riscv/include/uapi/asm/Kbuild | 4 +
arch/riscv/kernel/.gitignore | 1 +
arch/riscv/kernel/Makefile | 33 ++++
arch/riscv/kernel/vdso/Makefile | 61 ++++++
arch/riscv/kernel/vdso/vdso.lds.S | 77 ++++++++
arch/riscv/kernel/vmlinux.lds.S | 92 +++++++++
arch/riscv/lib/Makefile | 6 +
arch/riscv/mm/Makefile | 4 +
15 files changed, 857 insertions(+), 1 deletion(-)
create mode 100644 arch/riscv/Kconfig
create mode 100644 arch/riscv/Makefile
create mode 100644 arch/riscv/configs/freedom-u500_defconfig
create mode 100644 arch/riscv/configs/spike32_defconfig
create mode 100644 arch/riscv/configs/spike64_defconfig
create mode 100644 arch/riscv/include/asm/Kbuild
create mode 100644 arch/riscv/include/uapi/asm/Kbuild
create mode 100644 arch/riscv/kernel/.gitignore
create mode 100644 arch/riscv/kernel/Makefile
create mode 100644 arch/riscv/kernel/vdso/Makefile
create mode 100644 arch/riscv/kernel/vdso/vdso.lds.S
create mode 100644 arch/riscv/kernel/vmlinux.lds.S
create mode 100644 arch/riscv/lib/Makefile
create mode 100644 arch/riscv/mm/Makefile
diff --git a/Makefile b/Makefile
index 283c6236438e..a7c77b6586b9 100644
--- a/Makefile
+++ b/Makefile
@@ -232,7 +232,8 @@ SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
-e s/arm.*/arm/ -e s/sa110/arm/ \
-e s/s390x/s390/ -e s/parisc64/parisc/ \
-e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
- -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ )
+ -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
+ -e s/riscv.*/riscv/)
# Cross compiling and selecting different set of gcc/bin-utils
# ---------------------------------------------------------------------------
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
new file mode 100644
index 000000000000..9f587af28910
--- /dev/null
+++ b/arch/riscv/Kconfig
@@ -0,0 +1,304 @@
+#
+# For a description of the syntax of this configuration file,
+# see Documentation/kbuild/kconfig-language.txt.
+#
+
+config RISCV
+ def_bool y
+ select OF
+ select OF_EARLY_FLATTREE
+ select OF_IRQ
+ select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+ select ARCH_WANT_FRAME_POINTERS
+ select CLONE_BACKWARDS
+ select COMMON_CLK
+ select GENERIC_CLOCKEVENTS
+ select GENERIC_CPU_DEVICES
+ select GENERIC_IRQ_SHOW
+ select GENERIC_PCI_IOMAP
+ select GENERIC_STRNCPY_FROM_USER
+ select GENERIC_STRNLEN_USER
+ select GENERIC_SMP_IDLE_THREAD
+ select GENERIC_ATOMIC64 if !64BIT || !ISA_A
+ select ARCH_WANT_OPTIONAL_GPIOLIB
+ select HAVE_MEMBLOCK
+ select HAVE_DMA_API_DEBUG
+ select HAVE_DMA_CONTIGUOUS
+ select HAVE_GENERIC_DMA_COHERENT
+ select IRQ_DOMAIN
+ select NO_BOOTMEM
+ select ISA_A if SMP
+ select SYSRISCV_ATOMIC if !ISA_A
+ select SPARSE_IRQ
+ select SYSCTL_EXCEPTION_TRACE
+ select HAVE_ARCH_TRACEHOOK
+ select MODULES_USE_ELF_RELA if MODULES
+ select THREAD_INFO_IN_TASK
+ select RISCV_IRQ_INTC
+ select RISCV_TIMER
+
+config MMU
+ def_bool y
+
+# even on 32-bit, physical (and DMA) addresses are > 32-bits
+config ARCH_PHYS_ADDR_T_64BIT
+ def_bool y
+
+config ARCH_DMA_ADDR_T_64BIT
+ def_bool y
+
+config STACKTRACE_SUPPORT
+ def_bool y
+
+config RWSEM_GENERIC_SPINLOCK
+ def_bool y
+
+config GENERIC_BUG
+ def_bool y
+ depends on BUG
+ select GENERIC_BUG_RELATIVE_POINTERS if 64BIT
+
+config GENERIC_BUG_RELATIVE_POINTERS
+ bool
+
+config GENERIC_CALIBRATE_DELAY
+ def_bool y
+
+config GENERIC_CSUM
+ def_bool y
+
+config GENERIC_HWEIGHT
+ def_bool y
+
+config PGTABLE_LEVELS
+ int
+ default 3 if 64BIT
+ default 2
+
+config HAVE_KPROBES
+ def_bool n
+
+config DMA_NOOP_OPS
+ def_bool y
+
+menu "Platform type"
+
+config SMP
+ bool "Symmetric Multi-Processing"
+ help
+ This enables support for systems with more than one CPU. If
+ you say N here, the kernel will run on single and
+ multiprocessor machines, but will use only one CPU of a
+ multiprocessor machine. If you say Y here, the kernel will run
+ on many, but not all, single processor machines. On a single
+ processor machine, the kernel will run faster if you say N
+ here.
+
+ If you don't know what to do here, say N.
+
+config NR_CPUS
+ int "Maximum number of CPUs (2-32)"
+ range 2 32
+ depends on SMP
+ default "8"
+
+config CPU_SUPPORTS_32BIT_KERNEL
+ bool
+config CPU_SUPPORTS_64BIT_KERNEL
+ bool
+
+choice
+ prompt "Base ISA"
+ default ARCH_RV64I
+
+config ARCH_RV32I
+ bool "RV32I"
+ select CPU_SUPPORTS_32BIT_KERNEL
+ select 32BIT
+ select GENERIC_ASHLDI3
+ select GENERIC_ASHRDI3
+ select GENERIC_LSHRDI3
+
+config ARCH_RV64I
+ bool "RV64I"
+ select CPU_SUPPORTS_64BIT_KERNEL
+ select 64BIT
+
+endchoice
+
+choice
+ prompt "CPU Tuning"
+ default TUNE_GENERIC
+
+config TUNE_GENERIC
+ bool "generic"
+
+endchoice
+
+config ISA_C
+ bool "Emit compressed instructions when building Linux"
+ default n
+ help
+ Adds "C" to the ISA subsets that the toolchain is allowed to emit
+ when building Linux, which results in compressed instructions in the
+ Linux binary.
+
+ If you don't know what to do here, say Y.
+
+config ISA_A
+ bool "Emit atomic instructions when building Linux"
+ default y
+ help
+ Adds "A" to the ISA subsets that the toolchain is allowed to emit
+ when building Linux, which results in atomic instructions in the
+ Linux binary.
+
+ If you don't know what to do here, say Y.
+
+config RV_PUM
+ def_bool y
+ prompt "Protect User Memory" if EXPERT
+ ---help---
+ Protect User Memory (PUM) prevents the kernel from inadvertently
+ accessing user-space memory. There is a small performance cost
+ and kernel size increase if this is enabled.
+
+ If unsure, say Y.
+
+endmenu
+
+menu "Kernel type"
+
+choice
+ prompt "Kernel code model"
+ default 64BIT
+
+config 32BIT
+ bool "32-bit kernel"
+ depends on CPU_SUPPORTS_32BIT_KERNEL
+ help
+ Select this option to build a 32-bit kernel.
+
+config 64BIT
+ bool "64-bit kernel"
+ depends on CPU_SUPPORTS_64BIT_KERNEL
+ help
+ Select this option to build a 64-bit kernel.
+
+endchoice
+
+source "mm/Kconfig"
+
+source "kernel/Kconfig.preempt"
+
+source "kernel/Kconfig.hz"
+
+endmenu
+
+menu "Bus support"
+
+config PCI
+ bool "PCI support"
+ select PCI_MSI
+ help
+ This feature enables support for PCI bus system. If you say Y
+ here, the kernel will include drivers and infrastructure code
+ to support PCI bus devices.
+
+ If you don't know what to do here, say Y.
+
+config PCI_DOMAINS
+ def_bool PCI
+
+config PCI_DOMAINS_GENERIC
+ def_bool PCI
+
+source "drivers/pci/Kconfig"
+
+endmenu
+
+source "init/Kconfig"
+
+source "kernel/Kconfig.freezer"
+
+menu "Executable file formats"
+
+source "fs/Kconfig.binfmt"
+
+endmenu
+
+menu "Power management options"
+
+source kernel/power/Kconfig
+
+endmenu
+
+source "net/Kconfig"
+
+source "drivers/Kconfig"
+
+source "fs/Kconfig"
+
+menu "Kernel hacking"
+
+config CMDLINE_BOOL
+ bool "Built-in kernel command line"
+ default n
+ help
+ For most platforms, it is firmware or second stage bootloader
+ that by default specifies the kernel command line options.
+ However, it might be necessary or advantageous to either override
+ the default kernel command line or add a few extra options to it.
+ For such cases, this option allows hardcoding command line options
+ directly into the kernel.
+
+ For that, choose 'Y' here and fill in the extra boot parameters
+ in CONFIG_CMDLINE.
+
+ The built-in options will be concatenated to the default command
+ line if CMDLINE_OVERRIDE is set to 'N'. Otherwise, the default
+ command line will be ignored and replaced by the built-in string.
+
+config CMDLINE
+ string "Built-in kernel command string"
+ depends on CMDLINE_BOOL
+ default ""
+ help
+ Supply command-line options at build time by entering them here.
+
+config CMDLINE_OVERRIDE
+ bool "Built-in command line overrides bootloader arguments"
+ default n
+ depends on CMDLINE_BOOL
+ help
+ Set this option to 'Y' to have the kernel ignore the bootloader
+ or firmware command line. Instead, the built-in command line
+ will be used exclusively.
+
+ If you don't know what to do here, say N.
+
+config EARLY_PRINTK
+ bool "Early printk"
+ default n
+ help
+ This option enables special console drivers which allow the kernel
+ to print messages very early in the bootup process.
+
+ This is useful for kernel debugging when your machine crashes very
+ early before the console code is initialized. For normal operation
+ it is not recommended because it looks ugly and doesn't cooperate
+ with klogd/syslogd or the X server. You should normally N here,
+ unless you want to debug such a crash.
+
+
+source "lib/Kconfig.debug"
+
+config CMDLINE_BOOL
+ bool
+endmenu
+
+source "security/Kconfig"
+
+source "crypto/Kconfig"
+
+source "lib/Kconfig"
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
new file mode 100644
index 000000000000..66c4a5e383f9
--- /dev/null
+++ b/arch/riscv/Makefile
@@ -0,0 +1,64 @@
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies. Remember to do have actions
+# for "archclean" and "archdep" for cleaning up and making dependencies for
+# this architecture
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+
+LDFLAGS :=
+OBJCOPYFLAGS := -O binary
+LDFLAGS_vmlinux :=
+KBUILD_AFLAGS_MODULE += -fPIC
+KBUILD_CFLAGS_MODULE += -fPIC
+
+KBUILD_DEFCONFIG = spike64_defconfig
+
+export BITS
+ifeq ($(CONFIG_ARCH_RV64I),y)
+ BITS := 64
+ UTS_MACHINE := riscv64
+
+ KBUILD_CFLAGS += -mabi=lp64
+ KBUILD_AFLAGS += -mabi=lp64
+ KBUILD_MARCH = rv64im
+ LDFLAGS += -melf64lriscv
+else
+ BITS := 32
+ UTS_MACHINE := riscv32
+
+ KBUILD_CFLAGS += -mabi=ilp32
+ KBUILD_AFLAGS += -mabi=ilp32
+ KBUILD_MARCH = rv32im
+ LDFLAGS += -melf32lriscv
+endif
+
+KBUILD_CFLAGS += -Wall
+
+ifeq ($(CONFIG_ISA_A),y)
+ KBUILD_ARCH_A = a
+endif
+ifeq ($(CONFIG_ISA_C),y)
+ KBUILD_ARCH_C = c
+endif
+
+KBUILD_AFLAGS += -march=$(KBUILD_MARCH)$(KBUILD_ARCH_A)fd$(KBUILD_ARCH_C)
+
+KBUILD_CFLAGS += -march=$(KBUILD_MARCH)$(KBUILD_ARCH_A)$(KBUILD_ARCH_C)
+KBUILD_CFLAGS += -mno-save-restore
+
+# GCC versions that support the "-mstrict-align" option default to allowing
+# unaligned accesses. While unaligned accesses are explicitly allowed in the
+# RISC-V ISA, they're emulated by machine mode traps on all extant
+# architectures. It's faster to have GCC emit only aligned accesses.
+KBUILD_CFLAGS += $(call cc-option,-mstrict-align)
+
+head-y := arch/riscv/kernel/head.o
+
+core-y += arch/riscv/kernel/ arch/riscv/mm/
+
+libs-y += arch/riscv/lib/
+
+all: vmlinux
diff --git a/arch/riscv/configs/freedom-u500_defconfig b/arch/riscv/configs/freedom-u500_defconfig
new file mode 100644
index 000000000000..b580dc5c8feb
--- /dev/null
+++ b/arch/riscv/configs/freedom-u500_defconfig
@@ -0,0 +1,52 @@
+CONFIG_DEFAULT_HOSTNAME="ucbvax"
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+# CONFIG_FHANDLE is not set
+CONFIG_NAMESPACES=y
+# CONFIG_SGETMASK_SYSCALL is not set
+CONFIG_EMBEDDED=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_EFI_PARTITION is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_COMPACTION is not set
+CONFIG_HZ_100=y
+CONFIG_PCI_MSI=y
+CONFIG_NET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_OF=y
+# CONFIG_BLK_DEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_VT is not set
+CONFIG_DEVKMEM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_PROC_PAGE_MONITOR is not set
+# CONFIG_SYSFS is not set
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_PRINTK_TIME=y
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_SECTION_MISMATCH=y
+# CONFIG_FRAME_POINTER is not set
+# CONFIG_EARLY_PRINTK is not set
+# CONFIG_CRYPTO_HW is not set
+CONFIG_TTY=y
diff --git a/arch/riscv/configs/spike32_defconfig b/arch/riscv/configs/spike32_defconfig
new file mode 100644
index 000000000000..cf3431e94311
--- /dev/null
+++ b/arch/riscv/configs/spike32_defconfig
@@ -0,0 +1,50 @@
+CONFIG_64BIT=n
+CONFIG_32BIT=y
+CONFIG_ARCH_RV64I=n
+CONFIG_ARCH_RV32I=y
+CONFIG_PCI=y
+CONFIG_DEFAULT_HOSTNAME="ucbvax"
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+# CONFIG_FHANDLE is not set
+CONFIG_NAMESPACES=y
+CONFIG_EMBEDDED=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_EFI_PARTITION is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+CONFIG_NET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_VT is not set
+CONFIG_DEVKMEM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_PROC_PAGE_MONITOR is not set
+# CONFIG_SYSFS is not set
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
+# CONFIG_FRAME_POINTER is not set
+# CONFIG_CRYPTO_HW is not set
+CONFIG_TTY=y
diff --git a/arch/riscv/configs/spike64_defconfig b/arch/riscv/configs/spike64_defconfig
new file mode 100644
index 000000000000..5ad6644df541
--- /dev/null
+++ b/arch/riscv/configs/spike64_defconfig
@@ -0,0 +1,46 @@
+CONFIG_PCI=y
+CONFIG_DEFAULT_HOSTNAME="ucbvax"
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+# CONFIG_FHANDLE is not set
+CONFIG_NAMESPACES=y
+CONFIG_EMBEDDED=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_EFI_PARTITION is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+CONFIG_NET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_VT is not set
+CONFIG_DEVKMEM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_PROC_PAGE_MONITOR is not set
+# CONFIG_SYSFS is not set
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
+# CONFIG_FRAME_POINTER is not set
+# CONFIG_CRYPTO_HW is not set
+CONFIG_TTY=y
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
new file mode 100644
index 000000000000..18158be62a2b
--- /dev/null
+++ b/arch/riscv/include/asm/Kbuild
@@ -0,0 +1,61 @@
+generic-y += bugs.h
+generic-y += cacheflush.h
+generic-y += checksum.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += device.h
+generic-y += div64.h
+generic-y += dma.h
+generic-y += dma-contiguous.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += exec.h
+generic-y += fb.h
+generic-y += fcntl.h
+generic-y += ftrace.h
+generic-y += futex.h
+generic-y += hardirq.h
+generic-y += hash.h
+generic-y += hw_irq.h
+generic-y += ioctl.h
+generic-y += ioctls.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += irq_work.h
+generic-y += kdebug.h
+generic-y += kmap_types.h
+generic-y += kvm_para.h
+generic-y += local.h
+generic-y += mm-arch-hooks.h
+generic-y += mman.h
+generic-y += module.h
+generic-y += msgbuf.h
+generic-y += mutex.h
+generic-y += param.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += posix_types.h
+generic-y += preempt.h
+generic-y += resource.h
+generic-y += scatterlist.h
+generic-y += sections.h
+generic-y += sembuf.h
+generic-y += setup.h
+generic-y += shmbuf.h
+generic-y += shmparam.h
+generic-y += signal.h
+generic-y += socket.h
+generic-y += sockios.h
+generic-y += stat.h
+generic-y += statfs.h
+generic-y += swab.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += topology.h
+generic-y += trace_clock.h
+generic-y += types.h
+generic-y += unaligned.h
+generic-y += user.h
+generic-y += vga.h
+generic-y += vmlinux.lds.h
+generic-y += xor.h
diff --git a/arch/riscv/include/uapi/asm/Kbuild b/arch/riscv/include/uapi/asm/Kbuild
new file mode 100644
index 000000000000..0727570a49b2
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/Kbuild
@@ -0,0 +1,4 @@
+# UAPI Header export list
+include include/uapi/asm-generic/Kbuild.asm
+
+generic-y += setup.h
diff --git a/arch/riscv/kernel/.gitignore b/arch/riscv/kernel/.gitignore
new file mode 100644
index 000000000000..b51634f6a7cd
--- /dev/null
+++ b/arch/riscv/kernel/.gitignore
@@ -0,0 +1 @@
+/vmlinux.lds
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
new file mode 100644
index 000000000000..ab8baf7bd142
--- /dev/null
+++ b/arch/riscv/kernel/Makefile
@@ -0,0 +1,33 @@
+#
+# Makefile for the RISC-V Linux kernel
+#
+
+extra-y += head.o
+extra-y += vmlinux.lds
+
+obj-y += cpu.o
+obj-y += cpufeature.o
+obj-y += entry.o
+obj-y += irq.o
+obj-y += process.o
+obj-y += ptrace.o
+obj-y += reset.o
+obj-y += setup.o
+obj-y += signal.o
+obj-y += syscall_table.o
+obj-y += sys_riscv.o
+obj-y += time.o
+obj-y += traps.o
+obj-y += riscv_ksyms.o
+obj-y += stacktrace.o
+obj-y += vdso.o
+obj-y += cacheinfo.o
+obj-y += vdso/
+
+CFLAGS_setup.o := -mcmodel=medany
+
+obj-$(CONFIG_SMP) += smpboot.o
+obj-$(CONFIG_SMP) += smp.o
+obj-$(CONFIG_MODULES) += module.o
+
+clean:
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
new file mode 100644
index 000000000000..1f272425e889
--- /dev/null
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -0,0 +1,61 @@
+# Derived from arch/{arm64,tile}/kernel/vdso/Makefile
+
+obj-vdso := sigreturn.o cmpxchg32.o cmpxchg64.o
+
+# Build rules
+targets := $(obj-vdso) vdso.so vdso.so.dbg
+obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
+
+#ccflags-y := -shared -fno-common -fno-builtin
+#ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
+ $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+
+CFLAGS_vdso.so = $(c_flags)
+CFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
+ $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+CFLAGS_vdso_syms.o = -r
+
+obj-y += vdso.o
+
+# We also create a special relocatable object that should mirror the symbol
+# table and layout of the linked DSO. With ld -R we can then refer to
+# these symbols in the kernel code rather than hand-coded addresses.
+extra-y += vdso.lds vdso-syms.o
+$(obj)/built-in.o: $(obj)/vdso-syms.o
+$(obj)/built-in.o: ld_flags += -R $(obj)/vdso-syms.o
+
+CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+
+# Force dependency
+$(obj)/vdso.o : $(obj)/vdso.so
+
+# Link rule for the *.so file; *.lds must be first
+$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso)
+ $(call if_changed,vdsold)
+$(obj)/vdso-syms.o: $(src)/vdso.lds $(obj-vdso)
+ $(call if_changed,vdsold)
+
+# Strip rule for the *.so file
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+ $(call if_changed,objcopy)
+
+# Assembly rules for the *.S files
+$(obj-vdso): %.o: %.S
+ $(call if_changed_dep,vdsoas)
+
+# Actual build commands
+quiet_cmd_vdsold = VDSOLD $@
+ cmd_vdsold = $(CC) $(c_flags) -nostdlib $(CFLAGS_$(@F)) -Wl,-n -Wl,-T $^ -o $@
+quiet_cmd_vdsoas = VDSOAS $@
+ cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
+
+# Install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+
+vdso.so: $(obj)/vdso.so.dbg
+ @mkdir -p $(MODLIB)/vdso
+ $(call cmd,vdso_install)
+
+vdso_install: vdso.so
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
new file mode 100644
index 000000000000..7142e1aafc30
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -0,0 +1,77 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+OUTPUT_ARCH(riscv)
+
+SECTIONS
+{
+ . = SIZEOF_HEADERS;
+
+ .hash : { *(.hash) } :text
+ .gnu.hash : { *(.gnu.hash) }
+ .dynsym : { *(.dynsym) }
+ .dynstr : { *(.dynstr) }
+ .gnu.version : { *(.gnu.version) }
+ .gnu.version_d : { *(.gnu.version_d) }
+ .gnu.version_r : { *(.gnu.version_r) }
+
+ .note : { *(.note.*) } :text :note
+ .dynamic : { *(.dynamic) } :text :dynamic
+
+ .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
+ .eh_frame : { KEEP (*(.eh_frame)) } :text
+
+ .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+
+ /*
+ * This linker script is used both with -r and with -shared.
+ * For the layouts to match, we need to skip more than enough
+ * space for the dynamic symbol table, etc. If this amount is
+ * insufficient, ld -shared will error; simply increase it here.
+ */
+ . = 0x800;
+ .text : { *(.text .text.*) } :text
+
+ .data : {
+ *(.got.plt) *(.got)
+ *(.data .data.* .gnu.linkonce.d.*)
+ *(.dynbss)
+ *(.bss .bss.* .gnu.linkonce.b.*)
+ }
+}
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+ text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
+ dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
+ note PT_NOTE FLAGS(4); /* PF_R */
+ eh_frame_hdr PT_GNU_EH_FRAME;
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+ LINUX_2.6 {
+ global:
+ __vdso_rt_sigreturn;
+ __vdso_cmpxchg32;
+ __vdso_cmpxchg64;
+ local: *;
+ };
+}
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
new file mode 100644
index 000000000000..ece84991609c
--- /dev/null
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -0,0 +1,92 @@
+/*
+ * 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.
+ */
+
+#define LOAD_OFFSET PAGE_OFFSET
+#include <asm/vmlinux.lds.h>
+#include <asm/page.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+
+OUTPUT_ARCH(riscv)
+ENTRY(_start)
+
+jiffies = jiffies_64;
+
+SECTIONS
+{
+ /* Beginning of code and text segment */
+ . = LOAD_OFFSET;
+ _start = .;
+ __init_begin = .;
+ HEAD_TEXT_SECTION
+ INIT_TEXT_SECTION(PAGE_SIZE)
+ INIT_DATA_SECTION(16)
+ /* we have to discard exit text and such at runtime, not link time */
+ .exit.text :
+ {
+ EXIT_TEXT
+ }
+ .exit.data :
+ {
+ EXIT_DATA
+ }
+ PERCPU_SECTION(L1_CACHE_BYTES)
+ __init_end = .;
+
+ .text : {
+ _text = .;
+ _stext = .;
+ TEXT_TEXT
+ SCHED_TEXT
+ CPUIDLE_TEXT
+ LOCK_TEXT
+ KPROBES_TEXT
+ ENTRY_TEXT
+ IRQENTRY_TEXT
+ *(.fixup)
+ _etext = .;
+ }
+
+ /* Start of data section */
+ _sdata = .;
+ RO_DATA_SECTION(L1_CACHE_BYTES)
+ .srodata : {
+ *(.srodata*)
+ }
+
+ RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+ .sdata : {
+ __global_pointer$ = . + 0x800;
+ *(.sdata*)
+ /* End of data section */
+ _edata = .;
+ *(.sbss*)
+ }
+
+ BSS_SECTION(0, 0, 0)
+
+ EXCEPTION_TABLE(0x10)
+ NOTES
+
+ .rel.dyn : {
+ *(.rel.dyn*)
+ }
+
+ _end = .;
+
+ STABS_DEBUG
+ DWARF_DEBUG
+
+ DISCARDS
+}
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
new file mode 100644
index 000000000000..596c2ca40d63
--- /dev/null
+++ b/arch/riscv/lib/Makefile
@@ -0,0 +1,6 @@
+lib-y += delay.o
+lib-y += memcpy.o
+lib-y += memset.o
+lib-y += uaccess.o
+
+lib-$(CONFIG_32BIT) += udivdi3.o
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
new file mode 100644
index 000000000000..81f7d9ce6d88
--- /dev/null
+++ b/arch/riscv/mm/Makefile
@@ -0,0 +1,4 @@
+obj-y += init.o
+obj-y += fault.o
+obj-y += extable.o
+obj-y += ioremap.o
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread* [PATCH 9/9] RISC-V: Build Infastructure
@ 2017-07-04 19:51 ` Palmer Dabbelt
0 siblings, 0 replies; 58+ messages in thread
From: Palmer Dabbelt @ 2017-07-04 19:51 UTC (permalink / raw)
To: peterz, mingo, mcgrof, viro, sfr, nicolas.dichtel, rmk+kernel,
msalter, tklauser, will.deacon, james.hogan, paul.gortmaker,
linux, linux-kernel, linux-arch, albert, patches
Cc: Palmer Dabbelt
This patch contains all the build infastructure that actually enables
the RISC-V port. This includes Makefiles, linker scripts, and Kconfig
files. It also contains the only top-level change, which adds RISC-V to
the list of architectures that need a sed run to produce the ARCH
variable when building locally.
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
Makefile | 3 +-
arch/riscv/Kconfig | 304 ++++++++++++++++++++++++++++++
arch/riscv/Makefile | 64 +++++++
arch/riscv/configs/freedom-u500_defconfig | 52 +++++
arch/riscv/configs/spike32_defconfig | 50 +++++
arch/riscv/configs/spike64_defconfig | 46 +++++
arch/riscv/include/asm/Kbuild | 61 ++++++
arch/riscv/include/uapi/asm/Kbuild | 4 +
arch/riscv/kernel/.gitignore | 1 +
arch/riscv/kernel/Makefile | 33 ++++
arch/riscv/kernel/vdso/Makefile | 61 ++++++
arch/riscv/kernel/vdso/vdso.lds.S | 77 ++++++++
arch/riscv/kernel/vmlinux.lds.S | 92 +++++++++
arch/riscv/lib/Makefile | 6 +
arch/riscv/mm/Makefile | 4 +
15 files changed, 857 insertions(+), 1 deletion(-)
create mode 100644 arch/riscv/Kconfig
create mode 100644 arch/riscv/Makefile
create mode 100644 arch/riscv/configs/freedom-u500_defconfig
create mode 100644 arch/riscv/configs/spike32_defconfig
create mode 100644 arch/riscv/configs/spike64_defconfig
create mode 100644 arch/riscv/include/asm/Kbuild
create mode 100644 arch/riscv/include/uapi/asm/Kbuild
create mode 100644 arch/riscv/kernel/.gitignore
create mode 100644 arch/riscv/kernel/Makefile
create mode 100644 arch/riscv/kernel/vdso/Makefile
create mode 100644 arch/riscv/kernel/vdso/vdso.lds.S
create mode 100644 arch/riscv/kernel/vmlinux.lds.S
create mode 100644 arch/riscv/lib/Makefile
create mode 100644 arch/riscv/mm/Makefile
diff --git a/Makefile b/Makefile
index 283c6236438e..a7c77b6586b9 100644
--- a/Makefile
+++ b/Makefile
@@ -232,7 +232,8 @@ SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
-e s/arm.*/arm/ -e s/sa110/arm/ \
-e s/s390x/s390/ -e s/parisc64/parisc/ \
-e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
- -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ )
+ -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
+ -e s/riscv.*/riscv/)
# Cross compiling and selecting different set of gcc/bin-utils
# ---------------------------------------------------------------------------
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
new file mode 100644
index 000000000000..9f587af28910
--- /dev/null
+++ b/arch/riscv/Kconfig
@@ -0,0 +1,304 @@
+#
+# For a description of the syntax of this configuration file,
+# see Documentation/kbuild/kconfig-language.txt.
+#
+
+config RISCV
+ def_bool y
+ select OF
+ select OF_EARLY_FLATTREE
+ select OF_IRQ
+ select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+ select ARCH_WANT_FRAME_POINTERS
+ select CLONE_BACKWARDS
+ select COMMON_CLK
+ select GENERIC_CLOCKEVENTS
+ select GENERIC_CPU_DEVICES
+ select GENERIC_IRQ_SHOW
+ select GENERIC_PCI_IOMAP
+ select GENERIC_STRNCPY_FROM_USER
+ select GENERIC_STRNLEN_USER
+ select GENERIC_SMP_IDLE_THREAD
+ select GENERIC_ATOMIC64 if !64BIT || !ISA_A
+ select ARCH_WANT_OPTIONAL_GPIOLIB
+ select HAVE_MEMBLOCK
+ select HAVE_DMA_API_DEBUG
+ select HAVE_DMA_CONTIGUOUS
+ select HAVE_GENERIC_DMA_COHERENT
+ select IRQ_DOMAIN
+ select NO_BOOTMEM
+ select ISA_A if SMP
+ select SYSRISCV_ATOMIC if !ISA_A
+ select SPARSE_IRQ
+ select SYSCTL_EXCEPTION_TRACE
+ select HAVE_ARCH_TRACEHOOK
+ select MODULES_USE_ELF_RELA if MODULES
+ select THREAD_INFO_IN_TASK
+ select RISCV_IRQ_INTC
+ select RISCV_TIMER
+
+config MMU
+ def_bool y
+
+# even on 32-bit, physical (and DMA) addresses are > 32-bits
+config ARCH_PHYS_ADDR_T_64BIT
+ def_bool y
+
+config ARCH_DMA_ADDR_T_64BIT
+ def_bool y
+
+config STACKTRACE_SUPPORT
+ def_bool y
+
+config RWSEM_GENERIC_SPINLOCK
+ def_bool y
+
+config GENERIC_BUG
+ def_bool y
+ depends on BUG
+ select GENERIC_BUG_RELATIVE_POINTERS if 64BIT
+
+config GENERIC_BUG_RELATIVE_POINTERS
+ bool
+
+config GENERIC_CALIBRATE_DELAY
+ def_bool y
+
+config GENERIC_CSUM
+ def_bool y
+
+config GENERIC_HWEIGHT
+ def_bool y
+
+config PGTABLE_LEVELS
+ int
+ default 3 if 64BIT
+ default 2
+
+config HAVE_KPROBES
+ def_bool n
+
+config DMA_NOOP_OPS
+ def_bool y
+
+menu "Platform type"
+
+config SMP
+ bool "Symmetric Multi-Processing"
+ help
+ This enables support for systems with more than one CPU. If
+ you say N here, the kernel will run on single and
+ multiprocessor machines, but will use only one CPU of a
+ multiprocessor machine. If you say Y here, the kernel will run
+ on many, but not all, single processor machines. On a single
+ processor machine, the kernel will run faster if you say N
+ here.
+
+ If you don't know what to do here, say N.
+
+config NR_CPUS
+ int "Maximum number of CPUs (2-32)"
+ range 2 32
+ depends on SMP
+ default "8"
+
+config CPU_SUPPORTS_32BIT_KERNEL
+ bool
+config CPU_SUPPORTS_64BIT_KERNEL
+ bool
+
+choice
+ prompt "Base ISA"
+ default ARCH_RV64I
+
+config ARCH_RV32I
+ bool "RV32I"
+ select CPU_SUPPORTS_32BIT_KERNEL
+ select 32BIT
+ select GENERIC_ASHLDI3
+ select GENERIC_ASHRDI3
+ select GENERIC_LSHRDI3
+
+config ARCH_RV64I
+ bool "RV64I"
+ select CPU_SUPPORTS_64BIT_KERNEL
+ select 64BIT
+
+endchoice
+
+choice
+ prompt "CPU Tuning"
+ default TUNE_GENERIC
+
+config TUNE_GENERIC
+ bool "generic"
+
+endchoice
+
+config ISA_C
+ bool "Emit compressed instructions when building Linux"
+ default n
+ help
+ Adds "C" to the ISA subsets that the toolchain is allowed to emit
+ when building Linux, which results in compressed instructions in the
+ Linux binary.
+
+ If you don't know what to do here, say Y.
+
+config ISA_A
+ bool "Emit atomic instructions when building Linux"
+ default y
+ help
+ Adds "A" to the ISA subsets that the toolchain is allowed to emit
+ when building Linux, which results in atomic instructions in the
+ Linux binary.
+
+ If you don't know what to do here, say Y.
+
+config RV_PUM
+ def_bool y
+ prompt "Protect User Memory" if EXPERT
+ ---help---
+ Protect User Memory (PUM) prevents the kernel from inadvertently
+ accessing user-space memory. There is a small performance cost
+ and kernel size increase if this is enabled.
+
+ If unsure, say Y.
+
+endmenu
+
+menu "Kernel type"
+
+choice
+ prompt "Kernel code model"
+ default 64BIT
+
+config 32BIT
+ bool "32-bit kernel"
+ depends on CPU_SUPPORTS_32BIT_KERNEL
+ help
+ Select this option to build a 32-bit kernel.
+
+config 64BIT
+ bool "64-bit kernel"
+ depends on CPU_SUPPORTS_64BIT_KERNEL
+ help
+ Select this option to build a 64-bit kernel.
+
+endchoice
+
+source "mm/Kconfig"
+
+source "kernel/Kconfig.preempt"
+
+source "kernel/Kconfig.hz"
+
+endmenu
+
+menu "Bus support"
+
+config PCI
+ bool "PCI support"
+ select PCI_MSI
+ help
+ This feature enables support for PCI bus system. If you say Y
+ here, the kernel will include drivers and infrastructure code
+ to support PCI bus devices.
+
+ If you don't know what to do here, say Y.
+
+config PCI_DOMAINS
+ def_bool PCI
+
+config PCI_DOMAINS_GENERIC
+ def_bool PCI
+
+source "drivers/pci/Kconfig"
+
+endmenu
+
+source "init/Kconfig"
+
+source "kernel/Kconfig.freezer"
+
+menu "Executable file formats"
+
+source "fs/Kconfig.binfmt"
+
+endmenu
+
+menu "Power management options"
+
+source kernel/power/Kconfig
+
+endmenu
+
+source "net/Kconfig"
+
+source "drivers/Kconfig"
+
+source "fs/Kconfig"
+
+menu "Kernel hacking"
+
+config CMDLINE_BOOL
+ bool "Built-in kernel command line"
+ default n
+ help
+ For most platforms, it is firmware or second stage bootloader
+ that by default specifies the kernel command line options.
+ However, it might be necessary or advantageous to either override
+ the default kernel command line or add a few extra options to it.
+ For such cases, this option allows hardcoding command line options
+ directly into the kernel.
+
+ For that, choose 'Y' here and fill in the extra boot parameters
+ in CONFIG_CMDLINE.
+
+ The built-in options will be concatenated to the default command
+ line if CMDLINE_OVERRIDE is set to 'N'. Otherwise, the default
+ command line will be ignored and replaced by the built-in string.
+
+config CMDLINE
+ string "Built-in kernel command string"
+ depends on CMDLINE_BOOL
+ default ""
+ help
+ Supply command-line options at build time by entering them here.
+
+config CMDLINE_OVERRIDE
+ bool "Built-in command line overrides bootloader arguments"
+ default n
+ depends on CMDLINE_BOOL
+ help
+ Set this option to 'Y' to have the kernel ignore the bootloader
+ or firmware command line. Instead, the built-in command line
+ will be used exclusively.
+
+ If you don't know what to do here, say N.
+
+config EARLY_PRINTK
+ bool "Early printk"
+ default n
+ help
+ This option enables special console drivers which allow the kernel
+ to print messages very early in the bootup process.
+
+ This is useful for kernel debugging when your machine crashes very
+ early before the console code is initialized. For normal operation
+ it is not recommended because it looks ugly and doesn't cooperate
+ with klogd/syslogd or the X server. You should normally N here,
+ unless you want to debug such a crash.
+
+
+source "lib/Kconfig.debug"
+
+config CMDLINE_BOOL
+ bool
+endmenu
+
+source "security/Kconfig"
+
+source "crypto/Kconfig"
+
+source "lib/Kconfig"
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
new file mode 100644
index 000000000000..66c4a5e383f9
--- /dev/null
+++ b/arch/riscv/Makefile
@@ -0,0 +1,64 @@
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies. Remember to do have actions
+# for "archclean" and "archdep" for cleaning up and making dependencies for
+# this architecture
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+
+LDFLAGS :=
+OBJCOPYFLAGS := -O binary
+LDFLAGS_vmlinux :=
+KBUILD_AFLAGS_MODULE += -fPIC
+KBUILD_CFLAGS_MODULE += -fPIC
+
+KBUILD_DEFCONFIG = spike64_defconfig
+
+export BITS
+ifeq ($(CONFIG_ARCH_RV64I),y)
+ BITS := 64
+ UTS_MACHINE := riscv64
+
+ KBUILD_CFLAGS += -mabi=lp64
+ KBUILD_AFLAGS += -mabi=lp64
+ KBUILD_MARCH = rv64im
+ LDFLAGS += -melf64lriscv
+else
+ BITS := 32
+ UTS_MACHINE := riscv32
+
+ KBUILD_CFLAGS += -mabi=ilp32
+ KBUILD_AFLAGS += -mabi=ilp32
+ KBUILD_MARCH = rv32im
+ LDFLAGS += -melf32lriscv
+endif
+
+KBUILD_CFLAGS += -Wall
+
+ifeq ($(CONFIG_ISA_A),y)
+ KBUILD_ARCH_A = a
+endif
+ifeq ($(CONFIG_ISA_C),y)
+ KBUILD_ARCH_C = c
+endif
+
+KBUILD_AFLAGS += -march=$(KBUILD_MARCH)$(KBUILD_ARCH_A)fd$(KBUILD_ARCH_C)
+
+KBUILD_CFLAGS += -march=$(KBUILD_MARCH)$(KBUILD_ARCH_A)$(KBUILD_ARCH_C)
+KBUILD_CFLAGS += -mno-save-restore
+
+# GCC versions that support the "-mstrict-align" option default to allowing
+# unaligned accesses. While unaligned accesses are explicitly allowed in the
+# RISC-V ISA, they're emulated by machine mode traps on all extant
+# architectures. It's faster to have GCC emit only aligned accesses.
+KBUILD_CFLAGS += $(call cc-option,-mstrict-align)
+
+head-y := arch/riscv/kernel/head.o
+
+core-y += arch/riscv/kernel/ arch/riscv/mm/
+
+libs-y += arch/riscv/lib/
+
+all: vmlinux
diff --git a/arch/riscv/configs/freedom-u500_defconfig b/arch/riscv/configs/freedom-u500_defconfig
new file mode 100644
index 000000000000..b580dc5c8feb
--- /dev/null
+++ b/arch/riscv/configs/freedom-u500_defconfig
@@ -0,0 +1,52 @@
+CONFIG_DEFAULT_HOSTNAME="ucbvax"
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+# CONFIG_FHANDLE is not set
+CONFIG_NAMESPACES=y
+# CONFIG_SGETMASK_SYSCALL is not set
+CONFIG_EMBEDDED=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_EFI_PARTITION is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_COMPACTION is not set
+CONFIG_HZ_100=y
+CONFIG_PCI_MSI=y
+CONFIG_NET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_OF=y
+# CONFIG_BLK_DEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_VT is not set
+CONFIG_DEVKMEM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_PROC_PAGE_MONITOR is not set
+# CONFIG_SYSFS is not set
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_PRINTK_TIME=y
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_SECTION_MISMATCH=y
+# CONFIG_FRAME_POINTER is not set
+# CONFIG_EARLY_PRINTK is not set
+# CONFIG_CRYPTO_HW is not set
+CONFIG_TTY=y
diff --git a/arch/riscv/configs/spike32_defconfig b/arch/riscv/configs/spike32_defconfig
new file mode 100644
index 000000000000..cf3431e94311
--- /dev/null
+++ b/arch/riscv/configs/spike32_defconfig
@@ -0,0 +1,50 @@
+CONFIG_64BIT=n
+CONFIG_32BIT=y
+CONFIG_ARCH_RV64I=n
+CONFIG_ARCH_RV32I=y
+CONFIG_PCI=y
+CONFIG_DEFAULT_HOSTNAME="ucbvax"
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+# CONFIG_FHANDLE is not set
+CONFIG_NAMESPACES=y
+CONFIG_EMBEDDED=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_EFI_PARTITION is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+CONFIG_NET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_VT is not set
+CONFIG_DEVKMEM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_PROC_PAGE_MONITOR is not set
+# CONFIG_SYSFS is not set
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
+# CONFIG_FRAME_POINTER is not set
+# CONFIG_CRYPTO_HW is not set
+CONFIG_TTY=y
diff --git a/arch/riscv/configs/spike64_defconfig b/arch/riscv/configs/spike64_defconfig
new file mode 100644
index 000000000000..5ad6644df541
--- /dev/null
+++ b/arch/riscv/configs/spike64_defconfig
@@ -0,0 +1,46 @@
+CONFIG_PCI=y
+CONFIG_DEFAULT_HOSTNAME="ucbvax"
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+# CONFIG_FHANDLE is not set
+CONFIG_NAMESPACES=y
+CONFIG_EMBEDDED=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_EFI_PARTITION is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+CONFIG_NET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+# CONFIG_BLK_DEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_VT is not set
+CONFIG_DEVKMEM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_PROC_PAGE_MONITOR is not set
+# CONFIG_SYSFS is not set
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
+# CONFIG_FRAME_POINTER is not set
+# CONFIG_CRYPTO_HW is not set
+CONFIG_TTY=y
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
new file mode 100644
index 000000000000..18158be62a2b
--- /dev/null
+++ b/arch/riscv/include/asm/Kbuild
@@ -0,0 +1,61 @@
+generic-y += bugs.h
+generic-y += cacheflush.h
+generic-y += checksum.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += device.h
+generic-y += div64.h
+generic-y += dma.h
+generic-y += dma-contiguous.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += exec.h
+generic-y += fb.h
+generic-y += fcntl.h
+generic-y += ftrace.h
+generic-y += futex.h
+generic-y += hardirq.h
+generic-y += hash.h
+generic-y += hw_irq.h
+generic-y += ioctl.h
+generic-y += ioctls.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += irq_work.h
+generic-y += kdebug.h
+generic-y += kmap_types.h
+generic-y += kvm_para.h
+generic-y += local.h
+generic-y += mm-arch-hooks.h
+generic-y += mman.h
+generic-y += module.h
+generic-y += msgbuf.h
+generic-y += mutex.h
+generic-y += param.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += posix_types.h
+generic-y += preempt.h
+generic-y += resource.h
+generic-y += scatterlist.h
+generic-y += sections.h
+generic-y += sembuf.h
+generic-y += setup.h
+generic-y += shmbuf.h
+generic-y += shmparam.h
+generic-y += signal.h
+generic-y += socket.h
+generic-y += sockios.h
+generic-y += stat.h
+generic-y += statfs.h
+generic-y += swab.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += topology.h
+generic-y += trace_clock.h
+generic-y += types.h
+generic-y += unaligned.h
+generic-y += user.h
+generic-y += vga.h
+generic-y += vmlinux.lds.h
+generic-y += xor.h
diff --git a/arch/riscv/include/uapi/asm/Kbuild b/arch/riscv/include/uapi/asm/Kbuild
new file mode 100644
index 000000000000..0727570a49b2
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/Kbuild
@@ -0,0 +1,4 @@
+# UAPI Header export list
+include include/uapi/asm-generic/Kbuild.asm
+
+generic-y += setup.h
diff --git a/arch/riscv/kernel/.gitignore b/arch/riscv/kernel/.gitignore
new file mode 100644
index 000000000000..b51634f6a7cd
--- /dev/null
+++ b/arch/riscv/kernel/.gitignore
@@ -0,0 +1 @@
+/vmlinux.lds
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
new file mode 100644
index 000000000000..ab8baf7bd142
--- /dev/null
+++ b/arch/riscv/kernel/Makefile
@@ -0,0 +1,33 @@
+#
+# Makefile for the RISC-V Linux kernel
+#
+
+extra-y += head.o
+extra-y += vmlinux.lds
+
+obj-y += cpu.o
+obj-y += cpufeature.o
+obj-y += entry.o
+obj-y += irq.o
+obj-y += process.o
+obj-y += ptrace.o
+obj-y += reset.o
+obj-y += setup.o
+obj-y += signal.o
+obj-y += syscall_table.o
+obj-y += sys_riscv.o
+obj-y += time.o
+obj-y += traps.o
+obj-y += riscv_ksyms.o
+obj-y += stacktrace.o
+obj-y += vdso.o
+obj-y += cacheinfo.o
+obj-y += vdso/
+
+CFLAGS_setup.o := -mcmodel=medany
+
+obj-$(CONFIG_SMP) += smpboot.o
+obj-$(CONFIG_SMP) += smp.o
+obj-$(CONFIG_MODULES) += module.o
+
+clean:
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
new file mode 100644
index 000000000000..1f272425e889
--- /dev/null
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -0,0 +1,61 @@
+# Derived from arch/{arm64,tile}/kernel/vdso/Makefile
+
+obj-vdso := sigreturn.o cmpxchg32.o cmpxchg64.o
+
+# Build rules
+targets := $(obj-vdso) vdso.so vdso.so.dbg
+obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
+
+#ccflags-y := -shared -fno-common -fno-builtin
+#ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
+ $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+
+CFLAGS_vdso.so = $(c_flags)
+CFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
+ $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+CFLAGS_vdso_syms.o = -r
+
+obj-y += vdso.o
+
+# We also create a special relocatable object that should mirror the symbol
+# table and layout of the linked DSO. With ld -R we can then refer to
+# these symbols in the kernel code rather than hand-coded addresses.
+extra-y += vdso.lds vdso-syms.o
+$(obj)/built-in.o: $(obj)/vdso-syms.o
+$(obj)/built-in.o: ld_flags += -R $(obj)/vdso-syms.o
+
+CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+
+# Force dependency
+$(obj)/vdso.o : $(obj)/vdso.so
+
+# Link rule for the *.so file; *.lds must be first
+$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso)
+ $(call if_changed,vdsold)
+$(obj)/vdso-syms.o: $(src)/vdso.lds $(obj-vdso)
+ $(call if_changed,vdsold)
+
+# Strip rule for the *.so file
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+ $(call if_changed,objcopy)
+
+# Assembly rules for the *.S files
+$(obj-vdso): %.o: %.S
+ $(call if_changed_dep,vdsoas)
+
+# Actual build commands
+quiet_cmd_vdsold = VDSOLD $@
+ cmd_vdsold = $(CC) $(c_flags) -nostdlib $(CFLAGS_$(@F)) -Wl,-n -Wl,-T $^ -o $@
+quiet_cmd_vdsoas = VDSOAS $@
+ cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
+
+# Install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+
+vdso.so: $(obj)/vdso.so.dbg
+ @mkdir -p $(MODLIB)/vdso
+ $(call cmd,vdso_install)
+
+vdso_install: vdso.so
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
new file mode 100644
index 000000000000..7142e1aafc30
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -0,0 +1,77 @@
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ *
+ * 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.
+ */
+
+OUTPUT_ARCH(riscv)
+
+SECTIONS
+{
+ . = SIZEOF_HEADERS;
+
+ .hash : { *(.hash) } :text
+ .gnu.hash : { *(.gnu.hash) }
+ .dynsym : { *(.dynsym) }
+ .dynstr : { *(.dynstr) }
+ .gnu.version : { *(.gnu.version) }
+ .gnu.version_d : { *(.gnu.version_d) }
+ .gnu.version_r : { *(.gnu.version_r) }
+
+ .note : { *(.note.*) } :text :note
+ .dynamic : { *(.dynamic) } :text :dynamic
+
+ .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
+ .eh_frame : { KEEP (*(.eh_frame)) } :text
+
+ .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+
+ /*
+ * This linker script is used both with -r and with -shared.
+ * For the layouts to match, we need to skip more than enough
+ * space for the dynamic symbol table, etc. If this amount is
+ * insufficient, ld -shared will error; simply increase it here.
+ */
+ . = 0x800;
+ .text : { *(.text .text.*) } :text
+
+ .data : {
+ *(.got.plt) *(.got)
+ *(.data .data.* .gnu.linkonce.d.*)
+ *(.dynbss)
+ *(.bss .bss.* .gnu.linkonce.b.*)
+ }
+}
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+ text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
+ dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
+ note PT_NOTE FLAGS(4); /* PF_R */
+ eh_frame_hdr PT_GNU_EH_FRAME;
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+ LINUX_2.6 {
+ global:
+ __vdso_rt_sigreturn;
+ __vdso_cmpxchg32;
+ __vdso_cmpxchg64;
+ local: *;
+ };
+}
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
new file mode 100644
index 000000000000..ece84991609c
--- /dev/null
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -0,0 +1,92 @@
+/*
+ * 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.
+ */
+
+#define LOAD_OFFSET PAGE_OFFSET
+#include <asm/vmlinux.lds.h>
+#include <asm/page.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+
+OUTPUT_ARCH(riscv)
+ENTRY(_start)
+
+jiffies = jiffies_64;
+
+SECTIONS
+{
+ /* Beginning of code and text segment */
+ . = LOAD_OFFSET;
+ _start = .;
+ __init_begin = .;
+ HEAD_TEXT_SECTION
+ INIT_TEXT_SECTION(PAGE_SIZE)
+ INIT_DATA_SECTION(16)
+ /* we have to discard exit text and such at runtime, not link time */
+ .exit.text :
+ {
+ EXIT_TEXT
+ }
+ .exit.data :
+ {
+ EXIT_DATA
+ }
+ PERCPU_SECTION(L1_CACHE_BYTES)
+ __init_end = .;
+
+ .text : {
+ _text = .;
+ _stext = .;
+ TEXT_TEXT
+ SCHED_TEXT
+ CPUIDLE_TEXT
+ LOCK_TEXT
+ KPROBES_TEXT
+ ENTRY_TEXT
+ IRQENTRY_TEXT
+ *(.fixup)
+ _etext = .;
+ }
+
+ /* Start of data section */
+ _sdata = .;
+ RO_DATA_SECTION(L1_CACHE_BYTES)
+ .srodata : {
+ *(.srodata*)
+ }
+
+ RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+ .sdata : {
+ __global_pointer$ = . + 0x800;
+ *(.sdata*)
+ /* End of data section */
+ _edata = .;
+ *(.sbss*)
+ }
+
+ BSS_SECTION(0, 0, 0)
+
+ EXCEPTION_TABLE(0x10)
+ NOTES
+
+ .rel.dyn : {
+ *(.rel.dyn*)
+ }
+
+ _end = .;
+
+ STABS_DEBUG
+ DWARF_DEBUG
+
+ DISCARDS
+}
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
new file mode 100644
index 000000000000..596c2ca40d63
--- /dev/null
+++ b/arch/riscv/lib/Makefile
@@ -0,0 +1,6 @@
+lib-y += delay.o
+lib-y += memcpy.o
+lib-y += memset.o
+lib-y += uaccess.o
+
+lib-$(CONFIG_32BIT) += udivdi3.o
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
new file mode 100644
index 000000000000..81f7d9ce6d88
--- /dev/null
+++ b/arch/riscv/mm/Makefile
@@ -0,0 +1,4 @@
+obj-y += init.o
+obj-y += fault.o
+obj-y += extable.o
+obj-y += ioremap.o
--
2.13.0
^ permalink raw reply related [flat|nested] 58+ messages in thread