Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/riscv/kernel/.gitignore b/arch/riscv/kernel/.gitignore
index b51634f..e052ed3 100644
--- a/arch/riscv/kernel/.gitignore
+++ b/arch/riscv/kernel/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
/vmlinux.lds
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 696020f..bc49d5f 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -4,12 +4,15 @@
#
ifdef CONFIG_FTRACE
-CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE)
endif
extra-y += head.o
extra-y += vmlinux.lds
+obj-y += soc.o
obj-y += cpu.o
obj-y += cpufeature.o
obj-y += entry.o
@@ -25,21 +28,36 @@
obj-y += traps.o
obj-y += riscv_ksyms.o
obj-y += stacktrace.o
-obj-y += vdso.o
obj-y += cacheinfo.o
-obj-y += vdso/
+obj-y += patch.o
+obj-$(CONFIG_MMU) += vdso.o vdso/
+obj-$(CONFIG_RISCV_M_MODE) += traps_misaligned.o
obj-$(CONFIG_FPU) += fpu.o
obj-$(CONFIG_SMP) += smpboot.o
obj-$(CONFIG_SMP) += smp.o
+obj-$(CONFIG_SMP) += cpu_ops.o
+obj-$(CONFIG_SMP) += cpu_ops_spinwait.o
obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o
obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o
obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o
-obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+obj-$(CONFIG_TRACE_IRQFLAGS) += trace_irq.o
+
+obj-$(CONFIG_RISCV_BASE_PMU) += perf_event.o
obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o
obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o
+obj-$(CONFIG_RISCV_SBI) += sbi.o
+ifeq ($(CONFIG_RISCV_SBI), y)
+obj-$(CONFIG_SMP) += cpu_ops_sbi.o
+endif
+obj-$(CONFIG_HOTPLUG_CPU) += cpu-hotplug.o
+obj-$(CONFIG_KGDB) += kgdb.o
+
+obj-$(CONFIG_JUMP_LABEL) += jump_label.o
+
+obj-$(CONFIG_EFI) += efi.o
clean:
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index 9f5628c..db20344 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -27,9 +27,6 @@
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_PREEMPT_COUNT, task_struct, thread_info.preempt_count);
OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
@@ -71,7 +68,7 @@
OFFSET(TASK_THREAD_FCSR, task_struct, thread.fstate.fcsr);
DEFINE(PT_SIZE, sizeof(struct pt_regs));
- OFFSET(PT_SEPC, pt_regs, sepc);
+ OFFSET(PT_EPC, pt_regs, epc);
OFFSET(PT_RA, pt_regs, ra);
OFFSET(PT_FP, pt_regs, s0);
OFFSET(PT_S0, pt_regs, s0);
@@ -105,9 +102,9 @@
OFFSET(PT_T6, pt_regs, t6);
OFFSET(PT_GP, pt_regs, gp);
OFFSET(PT_ORIG_A0, pt_regs, orig_a0);
- OFFSET(PT_SSTATUS, pt_regs, sstatus);
- OFFSET(PT_SBADADDR, pt_regs, sbadaddr);
- OFFSET(PT_SCAUSE, pt_regs, scause);
+ OFFSET(PT_STATUS, pt_regs, status);
+ OFFSET(PT_BADADDR, pt_regs, badaddr);
+ OFFSET(PT_CAUSE, pt_regs, cause);
/*
* THREAD_{F,X}* might be larger than a S-type offset can handle, but
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index 4c90c07..90deabf 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -3,20 +3,117 @@
* Copyright (C) 2017 SiFive
*/
-#include <linux/cacheinfo.h>
#include <linux/cpu.h>
#include <linux/of.h>
#include <linux/of_device.h>
+#include <asm/cacheinfo.h>
-static void ci_leaf_init(struct cacheinfo *this_leaf,
- struct device_node *node,
- enum cache_type type, unsigned int level)
+static struct riscv_cacheinfo_ops *rv_cache_ops;
+
+void riscv_set_cacheinfo_ops(struct riscv_cacheinfo_ops *ops)
+{
+ rv_cache_ops = ops;
+}
+EXPORT_SYMBOL_GPL(riscv_set_cacheinfo_ops);
+
+const struct attribute_group *
+cache_get_priv_group(struct cacheinfo *this_leaf)
+{
+ if (rv_cache_ops && rv_cache_ops->get_priv_group)
+ return rv_cache_ops->get_priv_group(this_leaf);
+ return NULL;
+}
+
+static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type)
+{
+ /*
+ * Using raw_smp_processor_id() elides a preemptability check, but this
+ * is really indicative of a larger problem: the cacheinfo UABI assumes
+ * that cores have a homonogenous view of the cache hierarchy. That
+ * happens to be the case for the current set of RISC-V systems, but
+ * likely won't be true in general. Since there's no way to provide
+ * correct information for these systems via the current UABI we're
+ * just eliding the check for now.
+ */
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id());
+ struct cacheinfo *this_leaf;
+ int index;
+
+ for (index = 0; index < this_cpu_ci->num_leaves; index++) {
+ this_leaf = this_cpu_ci->info_list + index;
+ if (this_leaf->level == level && this_leaf->type == type)
+ return this_leaf;
+ }
+
+ return NULL;
+}
+
+uintptr_t get_cache_size(u32 level, enum cache_type type)
+{
+ struct cacheinfo *this_leaf = get_cacheinfo(level, type);
+
+ return this_leaf ? this_leaf->size : 0;
+}
+
+uintptr_t get_cache_geometry(u32 level, enum cache_type type)
+{
+ struct cacheinfo *this_leaf = get_cacheinfo(level, type);
+
+ return this_leaf ? (this_leaf->ways_of_associativity << 16 |
+ this_leaf->coherency_line_size) :
+ 0;
+}
+
+static void ci_leaf_init(struct cacheinfo *this_leaf, enum cache_type type,
+ unsigned int level, unsigned int size,
+ unsigned int sets, unsigned int line_size)
{
this_leaf->level = level;
this_leaf->type = type;
+ this_leaf->size = size;
+ this_leaf->number_of_sets = sets;
+ this_leaf->coherency_line_size = line_size;
+
+ /*
+ * If the cache is fully associative, there is no need to
+ * check the other properties.
+ */
+ if (sets == 1)
+ return;
+
+ /*
+ * Set the ways number for n-ways associative, make sure
+ * all properties are big than zero.
+ */
+ if (sets > 0 && size > 0 && line_size > 0)
+ this_leaf->ways_of_associativity = (size / sets) / line_size;
}
-static int __init_cache_level(unsigned int cpu)
+static void fill_cacheinfo(struct cacheinfo **this_leaf,
+ struct device_node *node, unsigned int level)
+{
+ unsigned int size, sets, line_size;
+
+ if (!of_property_read_u32(node, "cache-size", &size) &&
+ !of_property_read_u32(node, "cache-block-size", &line_size) &&
+ !of_property_read_u32(node, "cache-sets", &sets)) {
+ ci_leaf_init((*this_leaf)++, CACHE_TYPE_UNIFIED, level, size, sets, line_size);
+ }
+
+ if (!of_property_read_u32(node, "i-cache-size", &size) &&
+ !of_property_read_u32(node, "i-cache-sets", &sets) &&
+ !of_property_read_u32(node, "i-cache-block-size", &line_size)) {
+ ci_leaf_init((*this_leaf)++, CACHE_TYPE_INST, level, size, sets, line_size);
+ }
+
+ if (!of_property_read_u32(node, "d-cache-size", &size) &&
+ !of_property_read_u32(node, "d-cache-sets", &sets) &&
+ !of_property_read_u32(node, "d-cache-block-size", &line_size)) {
+ ci_leaf_init((*this_leaf)++, CACHE_TYPE_DATA, level, size, sets, line_size);
+ }
+}
+
+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);
@@ -58,7 +155,7 @@
return 0;
}
-static int __populate_cache_leaves(unsigned int cpu)
+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;
@@ -66,35 +163,27 @@
struct device_node *prev = NULL;
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);
+ /* Level 1 caches in cpu node */
+ fill_cacheinfo(&this_leaf, np, level);
+ /* Next level caches in cache nodes */
prev = np;
while ((np = of_find_next_cache_node(np))) {
of_node_put(prev);
prev = 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);
+
+ fill_cacheinfo(&this_leaf, np, level);
+
levels = level;
}
of_node_put(np);
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-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c
new file mode 100644
index 0000000..df84e0c
--- /dev/null
+++ b/arch/riscv/kernel/cpu-hotplug.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/cpu.h>
+#include <linux/sched/hotplug.h>
+#include <asm/irq.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+
+void cpu_stop(void);
+void arch_cpu_idle_dead(void)
+{
+ cpu_stop();
+}
+
+bool cpu_has_hotplug(unsigned int cpu)
+{
+ if (cpu_ops[cpu]->cpu_stop)
+ return true;
+
+ return false;
+}
+
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpu_disable(void)
+{
+ int ret = 0;
+ unsigned int cpu = smp_processor_id();
+
+ if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_stop)
+ return -EOPNOTSUPP;
+
+ if (cpu_ops[cpu]->cpu_disable)
+ ret = cpu_ops[cpu]->cpu_disable(cpu);
+
+ if (ret)
+ return ret;
+
+ remove_cpu_topology(cpu);
+ set_cpu_online(cpu, false);
+ irq_migrate_all_off_this_cpu();
+
+ return ret;
+}
+
+/*
+ * Called on the thread which is asking for a CPU to be shutdown.
+ */
+void __cpu_die(unsigned int cpu)
+{
+ int ret = 0;
+
+ if (!cpu_wait_death(cpu, 5)) {
+ pr_err("CPU %u: didn't die\n", cpu);
+ return;
+ }
+ pr_notice("CPU%u: off\n", cpu);
+
+ /* Verify from the firmware if the cpu is really stopped*/
+ if (cpu_ops[cpu]->cpu_is_stopped)
+ ret = cpu_ops[cpu]->cpu_is_stopped(cpu);
+ if (ret)
+ pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
+}
+
+/*
+ * Called from the idle thread for the CPU which has been shutdown.
+ */
+void cpu_stop(void)
+{
+ idle_task_exit();
+
+ (void)cpu_report_death();
+
+ cpu_ops[smp_processor_id()]->cpu_stop();
+ /* It should never reach here */
+ BUG();
+}
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index 7da3c6a..6d59e69 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -44,53 +44,30 @@
return hart;
}
+/*
+ * Find hart ID of the CPU DT node under which given DT node falls.
+ *
+ * To achieve this, we walk up the DT tree until we find an active
+ * RISC-V core (HART) node and extract the cpuid from it.
+ */
+int riscv_of_parent_hartid(struct device_node *node)
+{
+ for (; node; node = node->parent) {
+ if (of_device_is_compatible(node, "riscv"))
+ return riscv_of_processor_hartid(node);
+ }
+
+ return -1;
+}
+
#ifdef CONFIG_PROC_FS
-static void print_isa(struct seq_file *f, const char *orig_isa)
+static void print_isa(struct seq_file *f, const char *isa)
{
- static const char *ext = "mafdcsu";
- const char *isa = orig_isa;
- const char *e;
-
- /*
- * Linux doesn't support rv32e or rv128i, and we only support booting
- * kernels on harts with the same ISA that the kernel is compiled for.
- */
-#if defined(CONFIG_32BIT)
- if (strncmp(isa, "rv32i", 5) != 0)
- return;
-#elif defined(CONFIG_64BIT)
- if (strncmp(isa, "rv64i", 5) != 0)
- return;
-#endif
-
- /* Print the base ISA, as we already know it's legal. */
+ /* Print the entire ISA as it is */
seq_puts(f, "isa\t\t: ");
- seq_write(f, isa, 5);
- isa += 5;
-
- /*
- * Check the rest of the ISA string for valid extensions, printing those
- * we find. RISC-V ISA strings define an order, so we only print the
- * extension bits when they're in order. Hide the supervisor (S)
- * extension from userspace as it's not accessible from there.
- */
- for (e = ext; *e != '\0'; ++e) {
- if (isa[0] == e[0]) {
- if (isa[0] != 's')
- seq_write(f, isa, 1);
-
- isa++;
- }
- }
+ seq_write(f, isa, strlen(isa));
seq_puts(f, "\n");
-
- /*
- * If we were given an unsupported ISA in the device tree then print
- * a bit of info describing what went wrong.
- */
- if (isa[0] != '\0')
- pr_info("unsupported ISA \"%s\" in device tree\n", orig_isa);
}
static void print_mmu(struct seq_file *f, const char *mmu_type)
diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c
new file mode 100644
index 0000000..1985884
--- /dev/null
+++ b/arch/riscv/kernel/cpu_ops.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
+
+void *__cpu_up_stack_pointer[NR_CPUS] __section(".data");
+void *__cpu_up_task_pointer[NR_CPUS] __section(".data");
+
+extern const struct cpu_operations cpu_ops_sbi;
+extern const struct cpu_operations cpu_ops_spinwait;
+
+void cpu_update_secondary_bootdata(unsigned int cpuid,
+ struct task_struct *tidle)
+{
+ int hartid = cpuid_to_hartid_map(cpuid);
+
+ /* Make sure tidle is updated */
+ smp_mb();
+ WRITE_ONCE(__cpu_up_stack_pointer[hartid],
+ task_stack_page(tidle) + THREAD_SIZE);
+ WRITE_ONCE(__cpu_up_task_pointer[hartid], tidle);
+}
+
+void __init cpu_set_ops(int cpuid)
+{
+#if IS_ENABLED(CONFIG_RISCV_SBI)
+ if (sbi_probe_extension(SBI_EXT_HSM) > 0) {
+ if (!cpuid)
+ pr_info("SBI v0.2 HSM extension detected\n");
+ cpu_ops[cpuid] = &cpu_ops_sbi;
+ } else
+#endif
+ cpu_ops[cpuid] = &cpu_ops_spinwait;
+}
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
new file mode 100644
index 0000000..685fae7
--- /dev/null
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * HSM extension and cpu_ops implementation.
+ *
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+extern char secondary_start_sbi[];
+const struct cpu_operations cpu_ops_sbi;
+
+static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
+ unsigned long priv)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_START,
+ hartid, saddr, priv, 0, 0, 0);
+ if (ret.error)
+ return sbi_err_map_linux_errno(ret.error);
+ else
+ return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int sbi_hsm_hart_stop(void)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STOP, 0, 0, 0, 0, 0, 0);
+
+ if (ret.error)
+ return sbi_err_map_linux_errno(ret.error);
+ else
+ return 0;
+}
+
+static int sbi_hsm_hart_get_status(unsigned long hartid)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STATUS,
+ hartid, 0, 0, 0, 0, 0);
+ if (ret.error)
+ return sbi_err_map_linux_errno(ret.error);
+ else
+ return ret.value;
+}
+#endif
+
+static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
+{
+ int rc;
+ unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
+ int hartid = cpuid_to_hartid_map(cpuid);
+
+ cpu_update_secondary_bootdata(cpuid, tidle);
+ rc = sbi_hsm_hart_start(hartid, boot_addr, 0);
+
+ return rc;
+}
+
+static int sbi_cpu_prepare(unsigned int cpuid)
+{
+ if (!cpu_ops_sbi.cpu_start) {
+ pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
+ return -ENODEV;
+ }
+ return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int sbi_cpu_disable(unsigned int cpuid)
+{
+ if (!cpu_ops_sbi.cpu_stop)
+ return -EOPNOTSUPP;
+ return 0;
+}
+
+static void sbi_cpu_stop(void)
+{
+ int ret;
+
+ ret = sbi_hsm_hart_stop();
+ pr_crit("Unable to stop the cpu %u (%d)\n", smp_processor_id(), ret);
+}
+
+static int sbi_cpu_is_stopped(unsigned int cpuid)
+{
+ int rc;
+ int hartid = cpuid_to_hartid_map(cpuid);
+
+ rc = sbi_hsm_hart_get_status(hartid);
+
+ if (rc == SBI_HSM_HART_STATUS_STOPPED)
+ return 0;
+ return rc;
+}
+#endif
+
+const struct cpu_operations cpu_ops_sbi = {
+ .name = "sbi",
+ .cpu_prepare = sbi_cpu_prepare,
+ .cpu_start = sbi_cpu_start,
+#ifdef CONFIG_HOTPLUG_CPU
+ .cpu_disable = sbi_cpu_disable,
+ .cpu_stop = sbi_cpu_stop,
+ .cpu_is_stopped = sbi_cpu_is_stopped,
+#endif
+};
diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c
new file mode 100644
index 0000000..b2c957b
--- /dev/null
+++ b/arch/riscv/kernel/cpu_ops_spinwait.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+const struct cpu_operations cpu_ops_spinwait;
+
+static int spinwait_cpu_prepare(unsigned int cpuid)
+{
+ if (!cpu_ops_spinwait.cpu_start) {
+ pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
+ return -ENODEV;
+ }
+ return 0;
+}
+
+static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
+{
+ /*
+ * In this protocol, all cpus boot on their own accord. _start
+ * selects the first cpu to boot the kernel and causes the remainder
+ * of the cpus to spin in a loop waiting for their stack pointer to be
+ * setup by that main cpu. Writing to bootdata
+ * (i.e __cpu_up_stack_pointer) signals to the spinning cpus that they
+ * can continue the boot process.
+ */
+ cpu_update_secondary_bootdata(cpuid, tidle);
+
+ return 0;
+}
+
+const struct cpu_operations cpu_ops_spinwait = {
+ .name = "spinwait",
+ .cpu_prepare = spinwait_cpu_prepare,
+ .cpu_start = spinwait_cpu_start,
+};
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index a5ad000..ac202f4 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -6,6 +6,7 @@
* Copyright (C) 2017 SiFive
*/
+#include <linux/bitmap.h>
#include <linux/of.h>
#include <asm/processor.h>
#include <asm/hwcap.h>
@@ -13,15 +14,57 @@
#include <asm/switch_to.h>
unsigned long elf_hwcap __read_mostly;
+
+/* Host ISA bitmap */
+static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
+
#ifdef CONFIG_FPU
bool has_fpu __read_mostly;
#endif
+/**
+ * riscv_isa_extension_base() - Get base extension word
+ *
+ * @isa_bitmap: ISA bitmap to use
+ * Return: base extension word as unsigned long value
+ *
+ * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
+ */
+unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap)
+{
+ if (!isa_bitmap)
+ return riscv_isa[0];
+ return isa_bitmap[0];
+}
+EXPORT_SYMBOL_GPL(riscv_isa_extension_base);
+
+/**
+ * __riscv_isa_extension_available() - Check whether given extension
+ * is available or not
+ *
+ * @isa_bitmap: ISA bitmap to use
+ * @bit: bit position of the desired extension
+ * Return: true or false
+ *
+ * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
+ */
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit)
+{
+ const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa;
+
+ if (bit >= RISCV_ISA_EXT_MAX)
+ return false;
+
+ return test_bit(bit, bmap) ? true : false;
+}
+EXPORT_SYMBOL_GPL(__riscv_isa_extension_available);
+
void riscv_fill_hwcap(void)
{
struct device_node *node;
const char *isa;
- size_t i;
+ char print_str[BITS_PER_LONG + 1];
+ size_t i, j, isa_len;
static unsigned long isa2hwcap[256] = {0};
isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I;
@@ -33,8 +76,11 @@
elf_hwcap = 0;
+ bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX);
+
for_each_of_cpu_node(node) {
unsigned long this_hwcap = 0;
+ unsigned long this_isa = 0;
if (riscv_of_processor_hartid(node) < 0)
continue;
@@ -44,8 +90,24 @@
continue;
}
- for (i = 0; i < strlen(isa); ++i)
+ i = 0;
+ isa_len = strlen(isa);
+#if IS_ENABLED(CONFIG_32BIT)
+ if (!strncmp(isa, "rv32", 4))
+ i += 4;
+#elif IS_ENABLED(CONFIG_64BIT)
+ if (!strncmp(isa, "rv64", 4))
+ i += 4;
+#endif
+ for (; i < isa_len; ++i) {
this_hwcap |= isa2hwcap[(unsigned char)(isa[i])];
+ /*
+ * TODO: X, Y and Z extension parsing for Host ISA
+ * bitmap will be added in-future.
+ */
+ if ('a' <= isa[i] && isa[i] < 'x')
+ this_isa |= (1UL << (isa[i] - 'a'));
+ }
/*
* All "okay" hart should have same isa. Set HWCAP based on
@@ -56,6 +118,11 @@
elf_hwcap &= this_hwcap;
else
elf_hwcap = this_hwcap;
+
+ if (riscv_isa[0])
+ riscv_isa[0] &= this_isa;
+ else
+ riscv_isa[0] = this_isa;
}
/* We don't support systems with F but without D, so mask those out
@@ -65,7 +132,17 @@
elf_hwcap &= ~COMPAT_HWCAP_ISA_F;
}
- pr_info("elf_hwcap is 0x%lx\n", elf_hwcap);
+ memset(print_str, 0, sizeof(print_str));
+ for (i = 0, j = 0; i < BITS_PER_LONG; i++)
+ if (riscv_isa[0] & BIT_MASK(i))
+ print_str[j++] = (char)('a' + i);
+ pr_info("riscv: ISA extensions %s\n", print_str);
+
+ memset(print_str, 0, sizeof(print_str));
+ for (i = 0, j = 0; i < BITS_PER_LONG; i++)
+ if (elf_hwcap & BIT_MASK(i))
+ print_str[j++] = (char)('a' + i);
+ pr_info("riscv: ELF capabilities %s\n", print_str);
#ifdef CONFIG_FPU
if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D))
diff --git a/arch/riscv/kernel/efi-header.S b/arch/riscv/kernel/efi-header.S
new file mode 100644
index 0000000..8e733aa
--- /dev/null
+++ b/arch/riscv/kernel/efi-header.S
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ * Adapted from arch/arm64/kernel/efi-header.S
+ */
+
+#include <linux/pe.h>
+#include <linux/sizes.h>
+
+ .macro __EFI_PE_HEADER
+ .long PE_MAGIC
+coff_header:
+#ifdef CONFIG_64BIT
+ .short IMAGE_FILE_MACHINE_RISCV64 // Machine
+#else
+ .short IMAGE_FILE_MACHINE_RISCV32 // Machine
+#endif
+ .short section_count // NumberOfSections
+ .long 0 // TimeDateStamp
+ .long 0 // PointerToSymbolTable
+ .long 0 // NumberOfSymbols
+ .short section_table - optional_header // SizeOfOptionalHeader
+ .short IMAGE_FILE_DEBUG_STRIPPED | \
+ IMAGE_FILE_EXECUTABLE_IMAGE | \
+ IMAGE_FILE_LINE_NUMS_STRIPPED // Characteristics
+
+optional_header:
+#ifdef CONFIG_64BIT
+ .short PE_OPT_MAGIC_PE32PLUS // PE32+ format
+#else
+ .short PE_OPT_MAGIC_PE32 // PE32 format
+#endif
+ .byte 0x02 // MajorLinkerVersion
+ .byte 0x14 // MinorLinkerVersion
+ .long __pecoff_text_end - efi_header_end // SizeOfCode
+ .long __pecoff_data_virt_size // SizeOfInitializedData
+ .long 0 // SizeOfUninitializedData
+ .long __efistub_efi_pe_entry - _start // AddressOfEntryPoint
+ .long efi_header_end - _start // BaseOfCode
+#ifdef CONFIG_32BIT
+ .long __pecoff_text_end - _start // BaseOfData
+#endif
+
+extra_header_fields:
+ .quad 0 // ImageBase
+ .long PECOFF_SECTION_ALIGNMENT // SectionAlignment
+ .long PECOFF_FILE_ALIGNMENT // FileAlignment
+ .short 0 // MajorOperatingSystemVersion
+ .short 0 // MinorOperatingSystemVersion
+ .short LINUX_EFISTUB_MAJOR_VERSION // MajorImageVersion
+ .short LINUX_EFISTUB_MINOR_VERSION // MinorImageVersion
+ .short 0 // MajorSubsystemVersion
+ .short 0 // MinorSubsystemVersion
+ .long 0 // Win32VersionValue
+
+ .long _end - _start // SizeOfImage
+
+ // Everything before the kernel image is considered part of the header
+ .long efi_header_end - _start // SizeOfHeaders
+ .long 0 // CheckSum
+ .short IMAGE_SUBSYSTEM_EFI_APPLICATION // Subsystem
+ .short 0 // DllCharacteristics
+ .quad 0 // SizeOfStackReserve
+ .quad 0 // SizeOfStackCommit
+ .quad 0 // SizeOfHeapReserve
+ .quad 0 // SizeOfHeapCommit
+ .long 0 // LoaderFlags
+ .long (section_table - .) / 8 // NumberOfRvaAndSizes
+
+ .quad 0 // ExportTable
+ .quad 0 // ImportTable
+ .quad 0 // ResourceTable
+ .quad 0 // ExceptionTable
+ .quad 0 // CertificationTable
+ .quad 0 // BaseRelocationTable
+
+ // Section table
+section_table:
+ .ascii ".text\0\0\0"
+ .long __pecoff_text_end - efi_header_end // VirtualSize
+ .long efi_header_end - _start // VirtualAddress
+ .long __pecoff_text_end - efi_header_end // SizeOfRawData
+ .long efi_header_end - _start // PointerToRawData
+
+ .long 0 // PointerToRelocations
+ .long 0 // PointerToLineNumbers
+ .short 0 // NumberOfRelocations
+ .short 0 // NumberOfLineNumbers
+ .long IMAGE_SCN_CNT_CODE | \
+ IMAGE_SCN_MEM_READ | \
+ IMAGE_SCN_MEM_EXECUTE // Characteristics
+
+ .ascii ".data\0\0\0"
+ .long __pecoff_data_virt_size // VirtualSize
+ .long __pecoff_text_end - _start // VirtualAddress
+ .long __pecoff_data_raw_size // SizeOfRawData
+ .long __pecoff_text_end - _start // PointerToRawData
+
+ .long 0 // PointerToRelocations
+ .long 0 // PointerToLineNumbers
+ .short 0 // NumberOfRelocations
+ .short 0 // NumberOfLineNumbers
+ .long IMAGE_SCN_CNT_INITIALIZED_DATA | \
+ IMAGE_SCN_MEM_READ | \
+ IMAGE_SCN_MEM_WRITE // Characteristics
+
+ .set section_count, (. - section_table) / 40
+
+ .balign 0x1000
+efi_header_end:
+ .endm
diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c
new file mode 100644
index 0000000..0241592
--- /dev/null
+++ b/arch/riscv/kernel/efi.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ * Adapted from arch/arm64/kernel/efi.c
+ */
+
+#include <linux/efi.h>
+#include <linux/init.h>
+
+#include <asm/efi.h>
+#include <asm/pgtable.h>
+#include <asm/pgtable-bits.h>
+
+/*
+ * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be
+ * executable, everything else can be mapped with the XN bits
+ * set. Also take the new (optional) RO/XP bits into account.
+ */
+static __init pgprot_t efimem_to_pgprot_map(efi_memory_desc_t *md)
+{
+ u64 attr = md->attribute;
+ u32 type = md->type;
+
+ if (type == EFI_MEMORY_MAPPED_IO)
+ return PAGE_KERNEL;
+
+ /* R-- */
+ if ((attr & (EFI_MEMORY_XP | EFI_MEMORY_RO)) ==
+ (EFI_MEMORY_XP | EFI_MEMORY_RO))
+ return PAGE_KERNEL_READ;
+
+ /* R-X */
+ if (attr & EFI_MEMORY_RO)
+ return PAGE_KERNEL_READ_EXEC;
+
+ /* RW- */
+ if (((attr & (EFI_MEMORY_RP | EFI_MEMORY_WP | EFI_MEMORY_XP)) ==
+ EFI_MEMORY_XP) ||
+ type != EFI_RUNTIME_SERVICES_CODE)
+ return PAGE_KERNEL;
+
+ /* RWX */
+ return PAGE_KERNEL_EXEC;
+}
+
+int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
+{
+ pgprot_t prot = __pgprot(pgprot_val(efimem_to_pgprot_map(md)) &
+ ~(_PAGE_GLOBAL));
+ int i;
+
+ /* RISC-V maps one page at a time */
+ for (i = 0; i < md->num_pages; i++)
+ create_pgd_mapping(mm->pgd, md->virt_addr + i * PAGE_SIZE,
+ md->phys_addr + i * PAGE_SIZE,
+ PAGE_SIZE, prot);
+ return 0;
+}
+
+static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
+{
+ efi_memory_desc_t *md = data;
+ pte_t pte = READ_ONCE(*ptep);
+ unsigned long val;
+
+ if (md->attribute & EFI_MEMORY_RO) {
+ val = pte_val(pte) & ~_PAGE_WRITE;
+ val = pte_val(pte) | _PAGE_READ;
+ pte = __pte(val);
+ }
+ if (md->attribute & EFI_MEMORY_XP) {
+ val = pte_val(pte) & ~_PAGE_EXEC;
+ pte = __pte(val);
+ }
+ set_pte(ptep, pte);
+
+ return 0;
+}
+
+int __init efi_set_mapping_permissions(struct mm_struct *mm,
+ efi_memory_desc_t *md)
+{
+ BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE &&
+ md->type != EFI_RUNTIME_SERVICES_DATA);
+
+ /*
+ * Calling apply_to_page_range() is only safe on regions that are
+ * guaranteed to be mapped down to pages. Since we are only called
+ * for regions that have been mapped using efi_create_mapping() above
+ * (and this is checked by the generic Memory Attributes table parsing
+ * routines), there is no need to check that again here.
+ */
+ return apply_to_page_range(mm, md->virt_addr,
+ md->num_pages << EFI_PAGE_SHIFT,
+ set_permissions, md);
+}
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 9c87ae7..5214c57 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -13,27 +13,21 @@
#include <asm/thread_info.h>
#include <asm/asm-offsets.h>
- .text
- .altmacro
+#if !IS_ENABLED(CONFIG_PREEMPTION)
+.set resume_kernel, restore_all
+#endif
-/*
- * 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
-
+ENTRY(handle_exception)
/*
* 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.
+ * the kernel thread pointer. If we came from the kernel, the scratch
+ * register will contain 0, and we should continue on the current TP.
*/
- csrrw tp, CSR_SSCRATCH, tp
+ csrrw tp, CSR_SCRATCH, tp
bnez tp, _save_context
_restore_kernel_tpsp:
- csrr tp, CSR_SSCRATCH
+ csrr tp, CSR_SCRATCH
REG_S sp, TASK_TI_KERNEL_SP(tp)
_save_context:
REG_S sp, TASK_TI_USER_SP(tp)
@@ -79,25 +73,198 @@
li t0, SR_SUM | SR_FS
REG_L s0, TASK_TI_USER_SP(tp)
- csrrc s1, CSR_SSTATUS, t0
- csrr s2, CSR_SEPC
- csrr s3, CSR_STVAL
- csrr s4, CSR_SCAUSE
- csrr s5, CSR_SSCRATCH
+ csrrc s1, CSR_STATUS, t0
+ csrr s2, CSR_EPC
+ csrr s3, CSR_TVAL
+ csrr s4, CSR_CAUSE
+ csrr s5, CSR_SCRATCH
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 s1, PT_STATUS(sp)
+ REG_S s2, PT_EPC(sp)
+ REG_S s3, PT_BADADDR(sp)
+ REG_S s4, PT_CAUSE(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)
+ /*
+ * Set the scratch register to 0, so that if a recursive exception
+ * occurs, the exception vector knows it came from the kernel
+ */
+ csrw CSR_SCRATCH, x0
+
+ /* Load the global pointer */
+.option push
+.option norelax
+ la gp, __global_pointer$
+.option pop
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+ call __trace_hardirqs_off
+#endif
+
+#ifdef CONFIG_CONTEXT_TRACKING
+ /* If previous state is in user mode, call context_tracking_user_exit. */
+ li a0, SR_PP
+ and a0, s1, a0
+ bnez a0, skip_context_tracking
+ call context_tracking_user_exit
+skip_context_tracking:
+#endif
+
+ /*
+ * MSB of cause differentiates between
+ * interrupts and exceptions
+ */
+ bge s4, zero, 1f
+
+ la ra, ret_from_exception
+
+ /* Handle interrupts */
+ move a0, sp /* pt_regs */
+ la a1, handle_arch_irq
+ REG_L a1, (a1)
+ jr a1
+1:
+ /*
+ * Exceptions run with interrupts enabled or disabled depending on the
+ * state of SR_PIE in m/sstatus.
+ */
+ andi t0, s1, SR_PIE
+ beqz t0, 1f
+#ifdef CONFIG_TRACE_IRQFLAGS
+ call __trace_hardirqs_on
+#endif
+ csrs CSR_STATUS, SR_IE
+
+1:
+ la ra, ret_from_exception
+ /* 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:
+#ifdef CONFIG_RISCV_M_MODE
+ /*
+ * When running is M-Mode (no MMU config), MPIE does not get set.
+ * As a result, we need to force enable interrupts here because
+ * handle_exception did not do set SR_IE as it always sees SR_PIE
+ * being cleared.
+ */
+ csrs CSR_STATUS, SR_IE
+#endif
+#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
+ /* Recover a0 - a7 for system calls */
+ 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)
+#endif
+ /* save the initial A0 value (needed in signal handlers) */
+ REG_S a0, PT_ORIG_A0(sp)
+ /*
+ * Advance SEPC to avoid executing the original
+ * scall instruction on sret
+ */
+ addi s2, s2, 0x4
+ REG_S s2, PT_EPC(sp)
+ /* Trace syscalls, but only if requested by the user. */
+ REG_L t0, TASK_TI_FLAGS(tp)
+ andi t0, t0, _TIF_SYSCALL_WORK
+ 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.
+ * If syscall number is above allowed value, redirect to ni_syscall.
+ */
+ bgeu a7, t0, 1f
+ /* Call syscall */
+ 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)
+ /*
+ * We didn't execute the actual syscall.
+ * Seccomp already set return value for the current task pt_regs.
+ * (If it was configured with SECCOMP_RET_ERRNO/TRACE)
+ */
+ret_from_syscall_rejected:
+ /* Trace syscalls, but only if requested by the user. */
+ REG_L t0, TASK_TI_FLAGS(tp)
+ andi t0, t0, _TIF_SYSCALL_WORK
+ bnez t0, handle_syscall_trace_exit
+
+ret_from_exception:
+ REG_L s0, PT_STATUS(sp)
+ csrc CSR_STATUS, SR_IE
+#ifdef CONFIG_TRACE_IRQFLAGS
+ call __trace_hardirqs_off
+#endif
+#ifdef CONFIG_RISCV_M_MODE
+ /* the MPP value is too large to be used as an immediate arg for addi */
+ li t0, SR_MPP
+ and s0, s0, t0
+#else
+ andi s0, s0, SR_SPP
+#endif
+ bnez s0, resume_kernel
+
+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
+
+#ifdef CONFIG_CONTEXT_TRACKING
+ call context_tracking_user_enter
+#endif
+
+ /* 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 the scratch register , so we can find the kernel data
+ * structures again.
+ */
+ csrw CSR_SCRATCH, tp
+
+restore_all:
+#ifdef CONFIG_TRACE_IRQFLAGS
+ REG_L s1, PT_STATUS(sp)
+ andi t0, s1, SR_PIE
+ beqz t0, 1f
+ call __trace_hardirqs_on
+ j 2f
+1:
+ call __trace_hardirqs_off
+2:
+#endif
+ REG_L a0, PT_STATUS(sp)
/*
* The current load reservation is effectively part of the processor's
* state, in the sense that load reservations cannot be shared between
@@ -115,11 +282,11 @@
* completes, implementations are allowed to expand reservations to be
* arbitrarily large.
*/
- REG_L a2, PT_SEPC(sp)
- REG_SC x0, a2, PT_SEPC(sp)
+ REG_L a2, PT_EPC(sp)
+ REG_SC x0, a2, PT_EPC(sp)
- csrw CSR_SSTATUS, a0
- csrw CSR_SEPC, a2
+ csrw CSR_STATUS, a0
+ csrw CSR_EPC, a2
REG_L x1, PT_RA(sp)
REG_L x3, PT_GP(sp)
@@ -153,123 +320,14 @@
REG_L x31, PT_T6(sp)
REG_L x2, PT_SP(sp)
- .endm
-#if !IS_ENABLED(CONFIG_PREEMPT)
-.set resume_kernel, restore_all
+#ifdef CONFIG_RISCV_M_MODE
+ mret
+#else
+ sret
#endif
-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 CSR_SSCRATCH, x0
-
- /* Load the global pointer */
-.option push
-.option norelax
- la gp, __global_pointer$
-.option pop
-
- la ra, ret_from_exception
- /*
- * MSB of cause differentiates between
- * interrupts and exceptions
- */
- bge s4, zero, 1f
-
- /* Handle interrupts */
- move a0, sp /* pt_regs */
- tail do_IRQ
-1:
- /* Exceptions run with interrupts enabled or disabled
- depending on the state of sstatus.SR_SPIE */
- andi t0, s1, SR_SPIE
- beqz t0, 1f
- csrs CSR_SSTATUS, SR_SIE
-
-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:
- /* save the initial A0 value (needed in signal handlers) */
- REG_S a0, PT_ORIG_A0(sp)
- /*
- * Advance SEPC to avoid executing the original
- * scall instruction on sret
- */
- addi s2, s2, 0x4
- REG_S s2, PT_SEPC(sp)
- /* Trace syscalls, but only if requested by the user. */
- REG_L t0, TASK_TI_FLAGS(tp)
- andi t0, t0, _TIF_SYSCALL_WORK
- 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_WORK
- bnez t0, handle_syscall_trace_exit
-
-ret_from_exception:
- REG_L s0, PT_SSTATUS(sp)
- csrc CSR_SSTATUS, SR_SIE
- andi s0, s0, SR_SPP
- bnez s0, resume_kernel
-
-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 CSR_SSCRATCH, tp
-
-restore_all:
- RESTORE_ALL
- sret
-
-#if IS_ENABLED(CONFIG_PREEMPT)
+#if IS_ENABLED(CONFIG_PREEMPTION)
resume_kernel:
REG_L s0, TASK_TI_PREEMPT_COUNT(tp)
bnez s0, restore_all
@@ -287,7 +345,7 @@
bnez s1, work_resched
work_notifysig:
/* Handle pending signals and notify-resume requests */
- csrs CSR_SSTATUS, SR_SIE /* Enable interrupts for do_notify_resume() */
+ csrs CSR_STATUS, SR_IE /* Enable interrupts for do_notify_resume() */
move a0, sp /* pt_regs */
move a1, s0 /* current_thread_info->flags */
tail do_notify_resume
@@ -298,6 +356,7 @@
handle_syscall_trace_enter:
move a0, sp
call do_syscall_trace_enter
+ move t0, a0
REG_L a0, PT_A0(sp)
REG_L a1, PT_A1(sp)
REG_L a2, PT_A2(sp)
@@ -306,6 +365,7 @@
REG_L a5, PT_A5(sp)
REG_L a6, PT_A6(sp)
REG_L a7, PT_A7(sp)
+ bnez t0, ret_from_syscall_rejected
j check_syscall_nr
handle_syscall_trace_exit:
move a0, sp
@@ -377,15 +437,15 @@
lw a4, TASK_TI_CPU(a1)
sw a3, TASK_TI_CPU(a1)
sw a4, TASK_TI_CPU(a0)
-#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
+ /* The offset of thread_info in task_struct is zero. */
move tp, a1
-#endif
ret
ENDPROC(__switch_to)
+#ifndef CONFIG_MMU
+#define do_page_fault do_trap_unknown
+#endif
+
.section ".rodata"
.align LGREG
/* Exception vector table */
@@ -408,3 +468,10 @@
RISCV_PTR do_page_fault /* store page fault */
excp_vect_table_end:
END(excp_vect_table)
+
+#ifndef CONFIG_MMU
+ENTRY(__user_rt_sigreturn)
+ li a7, __NR_rt_sigreturn
+ scall
+END(__user_rt_sigreturn)
+#endif
diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S
index 631d315..dd22054 100644
--- a/arch/riscv/kernel/fpu.S
+++ b/arch/riscv/kernel/fpu.S
@@ -23,7 +23,7 @@
li a2, TASK_THREAD_F0
add a0, a0, a2
li t1, SR_FS
- csrs CSR_SSTATUS, t1
+ csrs CSR_STATUS, t1
frcsr t0
fsd f0, TASK_THREAD_F0_F0(a0)
fsd f1, TASK_THREAD_F1_F0(a0)
@@ -58,7 +58,7 @@
fsd f30, TASK_THREAD_F30_F0(a0)
fsd f31, TASK_THREAD_F31_F0(a0)
sw t0, TASK_THREAD_FCSR_F0(a0)
- csrc CSR_SSTATUS, t1
+ csrc CSR_STATUS, t1
ret
ENDPROC(__fstate_save)
@@ -67,7 +67,7 @@
add a0, a0, a2
li t1, SR_FS
lw t0, TASK_THREAD_FCSR_F0(a0)
- csrs CSR_SSTATUS, t1
+ csrs CSR_STATUS, t1
fld f0, TASK_THREAD_F0_F0(a0)
fld f1, TASK_THREAD_F1_F0(a0)
fld f2, TASK_THREAD_F2_F0(a0)
@@ -101,6 +101,6 @@
fld f30, TASK_THREAD_F30_F0(a0)
fld f31, TASK_THREAD_F31_F0(a0)
fscsr t0
- csrc CSR_SSTATUS, t1
+ csrc CSR_STATUS, t1
ret
ENDPROC(__fstate_restore)
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 291c579..765b624 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2013 Linaro Limited
* Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
@@ -7,9 +7,23 @@
#include <linux/ftrace.h>
#include <linux/uaccess.h>
+#include <linux/memory.h>
#include <asm/cacheflush.h>
+#include <asm/patch.h>
#ifdef CONFIG_DYNAMIC_FTRACE
+int ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex)
+{
+ mutex_lock(&text_mutex);
+ return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void) __releases(&text_mutex)
+{
+ mutex_unlock(&text_mutex);
+ return 0;
+}
+
static int ftrace_check_current_call(unsigned long hook_pos,
unsigned int *expected)
{
@@ -24,7 +38,8 @@
* Read the text we want to modify;
* return must be -EFAULT on read error
*/
- if (probe_kernel_read(replaced, (void *)hook_pos, MCOUNT_INSN_SIZE))
+ if (copy_from_kernel_nofault(replaced, (void *)hook_pos,
+ MCOUNT_INSN_SIZE))
return -EFAULT;
/*
@@ -46,20 +61,14 @@
{
unsigned int call[2];
unsigned int nops[2] = {NOP4, NOP4};
- int ret = 0;
make_call(hook_pos, target, call);
- /* replace the auipc-jalr pair at once */
- ret = probe_kernel_write((void *)hook_pos, enable ? call : nops,
- MCOUNT_INSN_SIZE);
- /* return must be -EPERM on write error */
- if (ret)
+ /* Replace the auipc-jalr pair at once. Return -EPERM on write error. */
+ if (patch_text_nosync
+ ((void *)hook_pos, enable ? call : nops, MCOUNT_INSN_SIZE))
return -EPERM;
- smp_mb();
- flush_icache_range((void *)hook_pos, (void *)hook_pos + MCOUNT_INSN_SIZE);
-
return 0;
}
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 3447931..1a819c1 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -3,7 +3,6 @@
* Copyright (C) 2012 Regents of the University of California
*/
-#include <asm/thread_info.h>
#include <asm/asm-offsets.h>
#include <asm/asm.h>
#include <linux/init.h>
@@ -11,9 +10,11 @@
#include <asm/thread_info.h>
#include <asm/page.h>
#include <asm/csr.h>
+#include <asm/hwcap.h>
#include <asm/image.h>
+#include "efi-header.S"
-__INIT
+__HEAD
ENTRY(_start)
/*
* Image header expected by Linux boot-loaders. The image header data
@@ -21,10 +22,18 @@
* Do not modify it without modifying the structure and all bootloaders
* that expects this header format!!
*/
+#ifdef CONFIG_EFI
+ /*
+ * This instruction decodes to "MZ" ASCII required by UEFI.
+ */
+ c.li s4,-13
+ j _start_kernel
+#else
/* jump to start kernel */
j _start_kernel
/* reserved */
.word 0
+#endif
.balign 8
#ifdef CONFIG_RISCV_M_MODE
/* Image load offset (0MB) from start of RAM for M-mode */
@@ -47,13 +56,167 @@
.ascii RISCV_IMAGE_MAGIC
.balign 4
.ascii RISCV_IMAGE_MAGIC2
- .word 0
+#ifdef CONFIG_EFI
+ .word pe_head_start - _start
+pe_head_start:
-.global _start_kernel
-_start_kernel:
+ __EFI_PE_HEADER
+#else
+ .word 0
+#endif
+
+.align 2
+#ifdef CONFIG_MMU
+relocate:
+ /* Relocate return address */
+ li a1, PAGE_OFFSET
+ la a2, _start
+ sub a1, a1, a2
+ add ra, ra, a1
+
+ /* Point stvec to virtual address of intruction after satp write */
+ la a2, 1f
+ add a2, a2, a1
+ csrw CSR_TVEC, a2
+
+ /* Compute satp for kernel page tables, but don't load it yet */
+ srl a2, a0, PAGE_SHIFT
+ li a1, SATP_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. We need a
+ * full fence here because setup_vm() just wrote these PTEs and we need
+ * to ensure the new translations are in use.
+ */
+ la a0, trampoline_pg_dir
+ srl a0, a0, PAGE_SHIFT
+ or a0, a0, a1
+ sfence.vma
+ csrw CSR_SATP, a0
+.align 2
+1:
+ /* Set trap vector to spin forever to help debug */
+ la a0, .Lsecondary_park
+ csrw CSR_TVEC, a0
+
+ /* Reload the global pointer */
+.option push
+.option norelax
+ la gp, __global_pointer$
+.option pop
+
+ /*
+ * Switch to kernel page tables. A full fence is necessary in order to
+ * avoid using the trampoline translations, which are only correct for
+ * the first superpage. Fetching the fence is guarnteed to work
+ * because that first superpage is translated the same way.
+ */
+ csrw CSR_SATP, a2
+ sfence.vma
+
+ ret
+#endif /* CONFIG_MMU */
+#ifdef CONFIG_SMP
+ .global secondary_start_sbi
+secondary_start_sbi:
/* Mask all interrupts */
- csrw CSR_SIE, zero
- csrw CSR_SIP, zero
+ csrw CSR_IE, zero
+ csrw CSR_IP, zero
+
+ /* Load the global pointer */
+ .option push
+ .option norelax
+ la gp, __global_pointer$
+ .option pop
+
+ /*
+ * Disable FPU to detect illegal usage of
+ * floating point in kernel space
+ */
+ li t0, SR_FS
+ csrc CSR_STATUS, t0
+
+ /* Set trap vector to spin forever to help debug */
+ la a3, .Lsecondary_park
+ csrw CSR_TVEC, a3
+
+ slli a3, a0, LGREG
+ la a4, __cpu_up_stack_pointer
+ la a5, __cpu_up_task_pointer
+ add a4, a3, a4
+ add a5, a3, a5
+ REG_L sp, (a4)
+ REG_L tp, (a5)
+
+ .global secondary_start_common
+secondary_start_common:
+
+#ifdef CONFIG_MMU
+ /* Enable virtual memory and relocate to virtual address */
+ la a0, swapper_pg_dir
+ call relocate
+#endif
+ call setup_trap_vector
+ tail smp_callin
+#endif /* CONFIG_SMP */
+
+.align 2
+setup_trap_vector:
+ /* Set trap vector to exception handler */
+ la a0, handle_exception
+ csrw CSR_TVEC, a0
+
+ /*
+ * Set sup0 scratch register to 0, indicating to exception vector that
+ * we are presently executing in kernel.
+ */
+ csrw CSR_SCRATCH, zero
+ ret
+
+.align 2
+.Lsecondary_park:
+ /* We lack SMP support or have too many harts, so park this hart */
+ wfi
+ j .Lsecondary_park
+
+END(_start)
+
+ __INIT
+ENTRY(_start_kernel)
+ /* Mask all interrupts */
+ csrw CSR_IE, zero
+ csrw CSR_IP, zero
+
+#ifdef CONFIG_RISCV_M_MODE
+ /* flush the instruction cache */
+ fence.i
+
+ /* Reset all registers except ra, a0, a1 */
+ call reset_regs
+
+ /*
+ * Setup a PMP to permit access to all of memory. Some machines may
+ * not implement PMPs, so we set up a quick trap handler to just skip
+ * touching the PMPs on any trap.
+ */
+ la a0, pmp_done
+ csrw CSR_TVEC, a0
+
+ li a0, -1
+ csrw CSR_PMPADDR0, a0
+ li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X)
+ csrw CSR_PMPCFG0, a0
+.align 2
+pmp_done:
+
+ /*
+ * The hartid in a0 is expected later on, and we have no firmware
+ * to hand it to us.
+ */
+ csrr a0, CSR_MHARTID
+#endif /* CONFIG_RISCV_M_MODE */
/* Load the global pointer */
.option push
@@ -66,11 +229,13 @@
* floating point in kernel space
*/
li t0, SR_FS
- csrc CSR_SSTATUS, t0
+ csrc CSR_STATUS, t0
#ifdef CONFIG_SMP
li t0, CONFIG_NR_CPUS
- bgeu a0, t0, .Lsecondary_park
+ blt a0, t0, .Lgood_cores
+ tail .Lsecondary_park
+.Lgood_cores:
#endif
/* Pick one hart to run the main boot sequence */
@@ -99,74 +264,29 @@
la sp, init_thread_union + THREAD_SIZE
mv a0, s1
call setup_vm
+#ifdef CONFIG_MMU
la a0, early_pg_dir
call relocate
+#endif /* CONFIG_MMU */
+ call setup_trap_vector
/* Restore C environment */
la tp, init_task
sw zero, TASK_TI_CPU(tp)
la sp, init_thread_union + THREAD_SIZE
+#ifdef CONFIG_KASAN
+ call kasan_early_init
+#endif
/* Start the kernel */
- call parse_dtb
+ call soc_early_init
tail start_kernel
-relocate:
- /* Relocate return address */
- li a1, PAGE_OFFSET
- la a2, _start
- sub a1, a1, a2
- add ra, ra, a1
-
- /* Point stvec to virtual address of intruction after satp write */
- la a2, 1f
- add a2, a2, a1
- csrw CSR_STVEC, a2
-
- /* Compute satp for kernel page tables, but don't load it yet */
- srl a2, a0, PAGE_SHIFT
- li a1, SATP_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. We need a
- * full fence here because setup_vm() just wrote these PTEs and we need
- * to ensure the new translations are in use.
- */
- la a0, trampoline_pg_dir
- srl a0, a0, PAGE_SHIFT
- or a0, a0, a1
- sfence.vma
- csrw CSR_SATP, a0
-.align 2
-1:
- /* Set trap vector to spin forever to help debug */
- la a0, .Lsecondary_park
- csrw CSR_STVEC, a0
-
- /* Reload the global pointer */
-.option push
-.option norelax
- la gp, __global_pointer$
-.option pop
-
- /*
- * Switch to kernel page tables. A full fence is necessary in order to
- * avoid using the trampoline translations, which are only correct for
- * the first superpage. Fetching the fence is guarnteed to work
- * because that first superpage is translated the same way.
- */
- csrw CSR_SATP, a2
- sfence.vma
-
- ret
-
.Lsecondary_start:
#ifdef CONFIG_SMP
/* Set trap vector to spin forever to help debug */
la a3, .Lsecondary_park
- csrw CSR_STVEC, a3
+ csrw CSR_TVEC, a3
slli a3, a0, LGREG
la a1, __cpu_up_stack_pointer
@@ -186,19 +306,89 @@
beqz tp, .Lwait_for_cpu_up
fence
- /* Enable virtual memory and relocate to virtual address */
- la a0, swapper_pg_dir
- call relocate
-
- tail smp_callin
+ tail secondary_start_common
#endif
-.align 2
-.Lsecondary_park:
- /* We lack SMP support or have too many harts, so park this hart */
- wfi
- j .Lsecondary_park
-END(_start)
+END(_start_kernel)
+
+#ifdef CONFIG_RISCV_M_MODE
+ENTRY(reset_regs)
+ li sp, 0
+ li gp, 0
+ li tp, 0
+ li t0, 0
+ li t1, 0
+ li t2, 0
+ li s0, 0
+ li s1, 0
+ li a2, 0
+ li a3, 0
+ li a4, 0
+ li a5, 0
+ li a6, 0
+ li a7, 0
+ li s2, 0
+ li s3, 0
+ li s4, 0
+ li s5, 0
+ li s6, 0
+ li s7, 0
+ li s8, 0
+ li s9, 0
+ li s10, 0
+ li s11, 0
+ li t3, 0
+ li t4, 0
+ li t5, 0
+ li t6, 0
+ csrw CSR_SCRATCH, 0
+
+#ifdef CONFIG_FPU
+ csrr t0, CSR_MISA
+ andi t0, t0, (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D)
+ beqz t0, .Lreset_regs_done
+
+ li t1, SR_FS
+ csrs CSR_STATUS, t1
+ fmv.s.x f0, zero
+ fmv.s.x f1, zero
+ fmv.s.x f2, zero
+ fmv.s.x f3, zero
+ fmv.s.x f4, zero
+ fmv.s.x f5, zero
+ fmv.s.x f6, zero
+ fmv.s.x f7, zero
+ fmv.s.x f8, zero
+ fmv.s.x f9, zero
+ fmv.s.x f10, zero
+ fmv.s.x f11, zero
+ fmv.s.x f12, zero
+ fmv.s.x f13, zero
+ fmv.s.x f14, zero
+ fmv.s.x f15, zero
+ fmv.s.x f16, zero
+ fmv.s.x f17, zero
+ fmv.s.x f18, zero
+ fmv.s.x f19, zero
+ fmv.s.x f20, zero
+ fmv.s.x f21, zero
+ fmv.s.x f22, zero
+ fmv.s.x f23, zero
+ fmv.s.x f24, zero
+ fmv.s.x f25, zero
+ fmv.s.x f26, zero
+ fmv.s.x f27, zero
+ fmv.s.x f28, zero
+ fmv.s.x f29, zero
+ fmv.s.x f30, zero
+ fmv.s.x f31, zero
+ csrw fcsr, 0
+ /* note that the caller must clear SR_FS */
+#endif /* CONFIG_FPU */
+.Lreset_regs_done:
+ ret
+END(reset_regs)
+#endif /* CONFIG_RISCV_M_MODE */
__PAGE_ALIGNED_BSS
/* Empty zero page */
diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h
index 105fb04..b48dda3 100644
--- a/arch/riscv/kernel/head.h
+++ b/arch/riscv/kernel/head.h
@@ -16,6 +16,4 @@
extern void *__cpu_up_stack_pointer[];
extern void *__cpu_up_task_pointer[];
-void __init parse_dtb(void);
-
#endif /* __ASM_HEAD_H */
diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h
new file mode 100644
index 0000000..8c212ef
--- /dev/null
+++ b/arch/riscv/kernel/image-vars.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ * Linker script variables to be set after section resolution, as
+ * ld.lld does not like variables assigned before SECTIONS is processed.
+ * Based on arch/arm64/kerne/image-vars.h
+ */
+#ifndef __RISCV_KERNEL_IMAGE_VARS_H
+#define __RISCV_KERNEL_IMAGE_VARS_H
+
+#ifndef LINKER_SCRIPT
+#error This file should only be included in vmlinux.lds.S
+#endif
+
+#ifdef CONFIG_EFI
+
+/*
+ * The EFI stub has its own symbol namespace prefixed by __efistub_, to
+ * isolate it from the kernel proper. The following symbols are legally
+ * accessed by the stub, so provide some aliases to make them accessible.
+ * Only include data symbols here, or text symbols of functions that are
+ * guaranteed to be safe when executed at another offset than they were
+ * linked at. The routines below are all implemented in assembler in a
+ * position independent manner
+ */
+__efistub_memcmp = memcmp;
+__efistub_memchr = memchr;
+__efistub_memcpy = memcpy;
+__efistub_memmove = memmove;
+__efistub_memset = memset;
+__efistub_strlen = strlen;
+__efistub_strnlen = strnlen;
+__efistub_strcmp = strcmp;
+__efistub_strncmp = strncmp;
+__efistub_strrchr = strrchr;
+
+#ifdef CONFIG_KASAN
+__efistub___memcpy = memcpy;
+__efistub___memmove = memmove;
+__efistub___memset = memset;
+#endif
+
+__efistub__start = _start;
+__efistub__start_kernel = _start_kernel;
+__efistub__end = _end;
+__efistub__edata = _edata;
+__efistub_screen_info = screen_info;
+
+#endif
+
+#endif /* __RISCV_KERNEL_IMAGE_VARS_H */
diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c
index fffac6d..7207fa0 100644
--- a/arch/riscv/kernel/irq.c
+++ b/arch/riscv/kernel/irq.c
@@ -7,54 +7,18 @@
#include <linux/interrupt.h>
#include <linux/irqchip.h>
-#include <linux/irqdomain.h>
#include <linux/seq_file.h>
#include <asm/smp.h>
-/*
- * Possible interrupt causes:
- */
-#define INTERRUPT_CAUSE_SOFTWARE IRQ_S_SOFT
-#define INTERRUPT_CAUSE_TIMER IRQ_S_TIMER
-#define INTERRUPT_CAUSE_EXTERNAL IRQ_S_EXT
-
int arch_show_interrupts(struct seq_file *p, int prec)
{
show_ipi_stats(p, prec);
return 0;
}
-asmlinkage __visible void __irq_entry do_IRQ(struct pt_regs *regs)
-{
- struct pt_regs *old_regs = set_irq_regs(regs);
-
- irq_enter();
- switch (regs->scause & ~SCAUSE_IRQ_FLAG) {
- case INTERRUPT_CAUSE_TIMER:
- riscv_timer_interrupt();
- break;
-#ifdef CONFIG_SMP
- case INTERRUPT_CAUSE_SOFTWARE:
- /*
- * We only use software interrupts to pass IPIs, so if a non-SMP
- * system gets one, then we don't know what to do.
- */
- riscv_software_interrupt();
- break;
-#endif
- case INTERRUPT_CAUSE_EXTERNAL:
- handle_arch_irq(regs);
- break;
- default:
- pr_alert("unexpected interrupt cause 0x%lx", regs->scause);
- BUG();
- }
- irq_exit();
-
- set_irq_regs(old_regs);
-}
-
void __init init_IRQ(void)
{
irqchip_init();
+ if (!handle_arch_irq)
+ panic("No interrupt controller found.");
}
diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c
new file mode 100644
index 0000000..20e0905
--- /dev/null
+++ b/arch/riscv/kernel/jump_label.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Emil Renner Berthing
+ *
+ * Based on arch/arm64/kernel/jump_label.c
+ */
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/memory.h>
+#include <linux/mutex.h>
+#include <asm/bug.h>
+#include <asm/patch.h>
+
+#define RISCV_INSN_NOP 0x00000013U
+#define RISCV_INSN_JAL 0x0000006fU
+
+void arch_jump_label_transform(struct jump_entry *entry,
+ enum jump_label_type type)
+{
+ void *addr = (void *)jump_entry_code(entry);
+ u32 insn;
+
+ if (type == JUMP_LABEL_JMP) {
+ long offset = jump_entry_target(entry) - jump_entry_code(entry);
+
+ if (WARN_ON(offset & 1 || offset < -524288 || offset >= 524288))
+ return;
+
+ insn = RISCV_INSN_JAL |
+ (((u32)offset & GENMASK(19, 12)) << (12 - 12)) |
+ (((u32)offset & GENMASK(11, 11)) << (20 - 11)) |
+ (((u32)offset & GENMASK(10, 1)) << (21 - 1)) |
+ (((u32)offset & GENMASK(20, 20)) << (31 - 20));
+ } else {
+ insn = RISCV_INSN_NOP;
+ }
+
+ mutex_lock(&text_mutex);
+ patch_text_nosync(addr, &insn, sizeof(insn));
+ mutex_unlock(&text_mutex);
+}
+
+void arch_jump_label_transform_static(struct jump_entry *entry,
+ enum jump_label_type type)
+{
+ /*
+ * We use the same instructions in the arch_static_branch and
+ * arch_static_branch_jump inline functions, so there's no
+ * need to patch them up here.
+ * The core will call arch_jump_label_transform when those
+ * instructions need to be replaced.
+ */
+}
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
new file mode 100644
index 0000000..963ed7e
--- /dev/null
+++ b/arch/riscv/kernel/kgdb.c
@@ -0,0 +1,390 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/ptrace.h>
+#include <linux/kdebug.h>
+#include <linux/bug.h>
+#include <linux/kgdb.h>
+#include <linux/irqflags.h>
+#include <linux/string.h>
+#include <asm/cacheflush.h>
+#include <asm/gdb_xml.h>
+#include <asm/parse_asm.h>
+
+enum {
+ NOT_KGDB_BREAK = 0,
+ KGDB_SW_BREAK,
+ KGDB_COMPILED_BREAK,
+ KGDB_SW_SINGLE_STEP
+};
+
+static unsigned long stepped_address;
+static unsigned int stepped_opcode;
+
+#if __riscv_xlen == 32
+/* C.JAL is an RV32C-only instruction */
+DECLARE_INSN(c_jal, MATCH_C_JAL, MASK_C_JAL)
+#else
+#define is_c_jal_insn(opcode) 0
+#endif
+DECLARE_INSN(jalr, MATCH_JALR, MASK_JALR)
+DECLARE_INSN(jal, MATCH_JAL, MASK_JAL)
+DECLARE_INSN(c_jr, MATCH_C_JR, MASK_C_JR)
+DECLARE_INSN(c_jalr, MATCH_C_JALR, MASK_C_JALR)
+DECLARE_INSN(c_j, MATCH_C_J, MASK_C_J)
+DECLARE_INSN(beq, MATCH_BEQ, MASK_BEQ)
+DECLARE_INSN(bne, MATCH_BNE, MASK_BNE)
+DECLARE_INSN(blt, MATCH_BLT, MASK_BLT)
+DECLARE_INSN(bge, MATCH_BGE, MASK_BGE)
+DECLARE_INSN(bltu, MATCH_BLTU, MASK_BLTU)
+DECLARE_INSN(bgeu, MATCH_BGEU, MASK_BGEU)
+DECLARE_INSN(c_beqz, MATCH_C_BEQZ, MASK_C_BEQZ)
+DECLARE_INSN(c_bnez, MATCH_C_BNEZ, MASK_C_BNEZ)
+DECLARE_INSN(sret, MATCH_SRET, MASK_SRET)
+
+static int decode_register_index(unsigned long opcode, int offset)
+{
+ return (opcode >> offset) & 0x1F;
+}
+
+static int decode_register_index_short(unsigned long opcode, int offset)
+{
+ return ((opcode >> offset) & 0x7) + 8;
+}
+
+/* Calculate the new address for after a step */
+static int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
+{
+ unsigned long pc = regs->epc;
+ unsigned long *regs_ptr = (unsigned long *)regs;
+ unsigned int rs1_num, rs2_num;
+ int op_code;
+
+ if (get_kernel_nofault(op_code, (void *)pc))
+ return -EINVAL;
+ if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) {
+ if (is_c_jalr_insn(op_code) || is_c_jr_insn(op_code)) {
+ rs1_num = decode_register_index(op_code, RVC_C2_RS1_OPOFF);
+ *next_addr = regs_ptr[rs1_num];
+ } else if (is_c_j_insn(op_code) || is_c_jal_insn(op_code)) {
+ *next_addr = EXTRACT_RVC_J_IMM(op_code) + pc;
+ } else if (is_c_beqz_insn(op_code)) {
+ rs1_num = decode_register_index_short(op_code,
+ RVC_C1_RS1_OPOFF);
+ if (!rs1_num || regs_ptr[rs1_num] == 0)
+ *next_addr = EXTRACT_RVC_B_IMM(op_code) + pc;
+ else
+ *next_addr = pc + 2;
+ } else if (is_c_bnez_insn(op_code)) {
+ rs1_num =
+ decode_register_index_short(op_code, RVC_C1_RS1_OPOFF);
+ if (rs1_num && regs_ptr[rs1_num] != 0)
+ *next_addr = EXTRACT_RVC_B_IMM(op_code) + pc;
+ else
+ *next_addr = pc + 2;
+ } else {
+ *next_addr = pc + 2;
+ }
+ } else {
+ if ((op_code & __INSN_OPCODE_MASK) == __INSN_BRANCH_OPCODE) {
+ bool result = false;
+ long imm = EXTRACT_BTYPE_IMM(op_code);
+ unsigned long rs1_val = 0, rs2_val = 0;
+
+ rs1_num = decode_register_index(op_code, RVG_RS1_OPOFF);
+ rs2_num = decode_register_index(op_code, RVG_RS2_OPOFF);
+ if (rs1_num)
+ rs1_val = regs_ptr[rs1_num];
+ if (rs2_num)
+ rs2_val = regs_ptr[rs2_num];
+
+ if (is_beq_insn(op_code))
+ result = (rs1_val == rs2_val) ? true : false;
+ else if (is_bne_insn(op_code))
+ result = (rs1_val != rs2_val) ? true : false;
+ else if (is_blt_insn(op_code))
+ result =
+ ((long)rs1_val <
+ (long)rs2_val) ? true : false;
+ else if (is_bge_insn(op_code))
+ result =
+ ((long)rs1_val >=
+ (long)rs2_val) ? true : false;
+ else if (is_bltu_insn(op_code))
+ result = (rs1_val < rs2_val) ? true : false;
+ else if (is_bgeu_insn(op_code))
+ result = (rs1_val >= rs2_val) ? true : false;
+ if (result)
+ *next_addr = imm + pc;
+ else
+ *next_addr = pc + 4;
+ } else if (is_jal_insn(op_code)) {
+ *next_addr = EXTRACT_JTYPE_IMM(op_code) + pc;
+ } else if (is_jalr_insn(op_code)) {
+ rs1_num = decode_register_index(op_code, RVG_RS1_OPOFF);
+ if (rs1_num)
+ *next_addr = ((unsigned long *)regs)[rs1_num];
+ *next_addr += EXTRACT_ITYPE_IMM(op_code);
+ } else if (is_sret_insn(op_code)) {
+ *next_addr = pc;
+ } else {
+ *next_addr = pc + 4;
+ }
+ }
+ return 0;
+}
+
+static int do_single_step(struct pt_regs *regs)
+{
+ /* Determine where the target instruction will send us to */
+ unsigned long addr = 0;
+ int error = get_step_address(regs, &addr);
+
+ if (error)
+ return error;
+
+ /* Store the op code in the stepped address */
+ error = get_kernel_nofault(stepped_opcode, (void *)addr);
+ if (error)
+ return error;
+
+ stepped_address = addr;
+
+ /* Replace the op code with the break instruction */
+ error = copy_to_kernel_nofault((void *)stepped_address,
+ arch_kgdb_ops.gdb_bpt_instr,
+ BREAK_INSTR_SIZE);
+ /* Flush and return */
+ if (!error) {
+ flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
+ kgdb_single_step = 1;
+ atomic_set(&kgdb_cpu_doing_single_step,
+ raw_smp_processor_id());
+ } else {
+ stepped_address = 0;
+ stepped_opcode = 0;
+ }
+ return error;
+}
+
+/* Undo a single step */
+static void undo_single_step(struct pt_regs *regs)
+{
+ if (stepped_opcode != 0) {
+ copy_to_kernel_nofault((void *)stepped_address,
+ (void *)&stepped_opcode, BREAK_INSTR_SIZE);
+ flush_icache_range(stepped_address,
+ stepped_address + BREAK_INSTR_SIZE);
+ }
+ stepped_address = 0;
+ stepped_opcode = 0;
+ kgdb_single_step = 0;
+ atomic_set(&kgdb_cpu_doing_single_step, -1);
+}
+
+struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
+ {DBG_REG_ZERO, GDB_SIZEOF_REG, -1},
+ {DBG_REG_RA, GDB_SIZEOF_REG, offsetof(struct pt_regs, ra)},
+ {DBG_REG_SP, GDB_SIZEOF_REG, offsetof(struct pt_regs, sp)},
+ {DBG_REG_GP, GDB_SIZEOF_REG, offsetof(struct pt_regs, gp)},
+ {DBG_REG_TP, GDB_SIZEOF_REG, offsetof(struct pt_regs, tp)},
+ {DBG_REG_T0, GDB_SIZEOF_REG, offsetof(struct pt_regs, t0)},
+ {DBG_REG_T1, GDB_SIZEOF_REG, offsetof(struct pt_regs, t1)},
+ {DBG_REG_T2, GDB_SIZEOF_REG, offsetof(struct pt_regs, t2)},
+ {DBG_REG_FP, GDB_SIZEOF_REG, offsetof(struct pt_regs, s0)},
+ {DBG_REG_S1, GDB_SIZEOF_REG, offsetof(struct pt_regs, a1)},
+ {DBG_REG_A0, GDB_SIZEOF_REG, offsetof(struct pt_regs, a0)},
+ {DBG_REG_A1, GDB_SIZEOF_REG, offsetof(struct pt_regs, a1)},
+ {DBG_REG_A2, GDB_SIZEOF_REG, offsetof(struct pt_regs, a2)},
+ {DBG_REG_A3, GDB_SIZEOF_REG, offsetof(struct pt_regs, a3)},
+ {DBG_REG_A4, GDB_SIZEOF_REG, offsetof(struct pt_regs, a4)},
+ {DBG_REG_A5, GDB_SIZEOF_REG, offsetof(struct pt_regs, a5)},
+ {DBG_REG_A6, GDB_SIZEOF_REG, offsetof(struct pt_regs, a6)},
+ {DBG_REG_A7, GDB_SIZEOF_REG, offsetof(struct pt_regs, a7)},
+ {DBG_REG_S2, GDB_SIZEOF_REG, offsetof(struct pt_regs, s2)},
+ {DBG_REG_S3, GDB_SIZEOF_REG, offsetof(struct pt_regs, s3)},
+ {DBG_REG_S4, GDB_SIZEOF_REG, offsetof(struct pt_regs, s4)},
+ {DBG_REG_S5, GDB_SIZEOF_REG, offsetof(struct pt_regs, s5)},
+ {DBG_REG_S6, GDB_SIZEOF_REG, offsetof(struct pt_regs, s6)},
+ {DBG_REG_S7, GDB_SIZEOF_REG, offsetof(struct pt_regs, s7)},
+ {DBG_REG_S8, GDB_SIZEOF_REG, offsetof(struct pt_regs, s8)},
+ {DBG_REG_S9, GDB_SIZEOF_REG, offsetof(struct pt_regs, s9)},
+ {DBG_REG_S10, GDB_SIZEOF_REG, offsetof(struct pt_regs, s10)},
+ {DBG_REG_S11, GDB_SIZEOF_REG, offsetof(struct pt_regs, s11)},
+ {DBG_REG_T3, GDB_SIZEOF_REG, offsetof(struct pt_regs, t3)},
+ {DBG_REG_T4, GDB_SIZEOF_REG, offsetof(struct pt_regs, t4)},
+ {DBG_REG_T5, GDB_SIZEOF_REG, offsetof(struct pt_regs, t5)},
+ {DBG_REG_T6, GDB_SIZEOF_REG, offsetof(struct pt_regs, t6)},
+ {DBG_REG_EPC, GDB_SIZEOF_REG, offsetof(struct pt_regs, epc)},
+ {DBG_REG_STATUS, GDB_SIZEOF_REG, offsetof(struct pt_regs, status)},
+ {DBG_REG_BADADDR, GDB_SIZEOF_REG, offsetof(struct pt_regs, badaddr)},
+ {DBG_REG_CAUSE, GDB_SIZEOF_REG, offsetof(struct pt_regs, cause)},
+};
+
+char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
+{
+ if (regno >= DBG_MAX_REG_NUM || regno < 0)
+ return NULL;
+
+ if (dbg_reg_def[regno].offset != -1)
+ memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
+ dbg_reg_def[regno].size);
+ else
+ memset(mem, 0, dbg_reg_def[regno].size);
+ return dbg_reg_def[regno].name;
+}
+
+int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
+{
+ if (regno >= DBG_MAX_REG_NUM || regno < 0)
+ return -EINVAL;
+
+ if (dbg_reg_def[regno].offset != -1)
+ memcpy((void *)regs + dbg_reg_def[regno].offset, mem,
+ dbg_reg_def[regno].size);
+ return 0;
+}
+
+void
+sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
+{
+ /* Initialize to zero */
+ memset((char *)gdb_regs, 0, NUMREGBYTES);
+
+ gdb_regs[DBG_REG_SP_OFF] = task->thread.sp;
+ gdb_regs[DBG_REG_FP_OFF] = task->thread.s[0];
+ gdb_regs[DBG_REG_S1_OFF] = task->thread.s[1];
+ gdb_regs[DBG_REG_S2_OFF] = task->thread.s[2];
+ gdb_regs[DBG_REG_S3_OFF] = task->thread.s[3];
+ gdb_regs[DBG_REG_S4_OFF] = task->thread.s[4];
+ gdb_regs[DBG_REG_S5_OFF] = task->thread.s[5];
+ gdb_regs[DBG_REG_S6_OFF] = task->thread.s[6];
+ gdb_regs[DBG_REG_S7_OFF] = task->thread.s[7];
+ gdb_regs[DBG_REG_S8_OFF] = task->thread.s[8];
+ gdb_regs[DBG_REG_S9_OFF] = task->thread.s[10];
+ gdb_regs[DBG_REG_S10_OFF] = task->thread.s[11];
+ gdb_regs[DBG_REG_EPC_OFF] = task->thread.ra;
+}
+
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
+{
+ regs->epc = pc;
+}
+
+void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer,
+ char *remcom_out_buffer)
+{
+ if (!strncmp(remcom_in_buffer, gdb_xfer_read_target,
+ sizeof(gdb_xfer_read_target)))
+ strcpy(remcom_out_buffer, riscv_gdb_stub_target_desc);
+ else if (!strncmp(remcom_in_buffer, gdb_xfer_read_cpuxml,
+ sizeof(gdb_xfer_read_cpuxml)))
+ strcpy(remcom_out_buffer, riscv_gdb_stub_cpuxml);
+}
+
+static inline void kgdb_arch_update_addr(struct pt_regs *regs,
+ char *remcom_in_buffer)
+{
+ unsigned long addr;
+ char *ptr;
+
+ ptr = &remcom_in_buffer[1];
+ if (kgdb_hex2long(&ptr, &addr))
+ regs->epc = addr;
+}
+
+int kgdb_arch_handle_exception(int vector, int signo, int err_code,
+ char *remcom_in_buffer, char *remcom_out_buffer,
+ struct pt_regs *regs)
+{
+ int err = 0;
+
+ undo_single_step(regs);
+
+ switch (remcom_in_buffer[0]) {
+ case 'c':
+ case 'D':
+ case 'k':
+ if (remcom_in_buffer[0] == 'c')
+ kgdb_arch_update_addr(regs, remcom_in_buffer);
+ break;
+ case 's':
+ kgdb_arch_update_addr(regs, remcom_in_buffer);
+ err = do_single_step(regs);
+ break;
+ default:
+ err = -1;
+ }
+ return err;
+}
+
+static int kgdb_riscv_kgdbbreak(unsigned long addr)
+{
+ if (stepped_address == addr)
+ return KGDB_SW_SINGLE_STEP;
+ if (atomic_read(&kgdb_setting_breakpoint))
+ if (addr == (unsigned long)&kgdb_compiled_break)
+ return KGDB_COMPILED_BREAK;
+
+ return kgdb_has_hit_break(addr);
+}
+
+static int kgdb_riscv_notify(struct notifier_block *self, unsigned long cmd,
+ void *ptr)
+{
+ struct die_args *args = (struct die_args *)ptr;
+ struct pt_regs *regs = args->regs;
+ unsigned long flags;
+ int type;
+
+ if (user_mode(regs))
+ return NOTIFY_DONE;
+
+ type = kgdb_riscv_kgdbbreak(regs->epc);
+ if (type == NOT_KGDB_BREAK && cmd == DIE_TRAP)
+ return NOTIFY_DONE;
+
+ local_irq_save(flags);
+
+ if (kgdb_handle_exception(type == KGDB_SW_SINGLE_STEP ? 0 : 1,
+ args->signr, cmd, regs))
+ return NOTIFY_DONE;
+
+ if (type == KGDB_COMPILED_BREAK)
+ regs->epc += 4;
+
+ local_irq_restore(flags);
+
+ return NOTIFY_STOP;
+}
+
+static struct notifier_block kgdb_notifier = {
+ .notifier_call = kgdb_riscv_notify,
+};
+
+int kgdb_arch_init(void)
+{
+ register_die_notifier(&kgdb_notifier);
+
+ return 0;
+}
+
+void kgdb_arch_exit(void)
+{
+ unregister_die_notifier(&kgdb_notifier);
+}
+
+/*
+ * Global data
+ */
+#ifdef CONFIG_RISCV_ISA_C
+const struct kgdb_arch arch_kgdb_ops = {
+ .gdb_bpt_instr = {0x02, 0x90}, /* c.ebreak */
+};
+#else
+const struct kgdb_arch arch_kgdb_ops = {
+ .gdb_bpt_instr = {0x73, 0x00, 0x10, 0x00}, /* ebreak */
+};
+#endif
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 6bf5b16..c3310a6 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -10,9 +10,22 @@
#include <linux/moduleloader.h>
#include <linux/vmalloc.h>
#include <linux/sizes.h>
-#include <asm/pgtable.h>
+#include <linux/pgtable.h>
#include <asm/sections.h>
+/*
+ * The auipc+jalr instruction pair can reach any PC-relative offset
+ * in the range [-2^31 - 2^11, 2^31 - 2^11)
+ */
+static bool riscv_insn_valid_32bit_offset(ptrdiff_t val)
+{
+#ifdef CONFIG_32BIT
+ return true;
+#else
+ return (-(1L << 31) - (1L << 11)) <= val && val < ((1L << 31) - (1L << 11));
+#endif
+}
+
static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v)
{
if (v != (u32)v) {
@@ -95,7 +108,7 @@
ptrdiff_t offset = (void *)v - (void *)location;
s32 hi20;
- if (offset != (s32)offset) {
+ if (!riscv_insn_valid_32bit_offset(offset)) {
pr_err(
"%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
me->name, (long long)v, location);
@@ -197,10 +210,9 @@
Elf_Addr v)
{
ptrdiff_t offset = (void *)v - (void *)location;
- s32 fill_v = offset;
u32 hi20, lo12;
- if (offset != fill_v) {
+ if (!riscv_insn_valid_32bit_offset(offset)) {
/* Only emit the plt entry if offset over 32-bit range */
if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) {
offset = module_emit_plt_entry(me, v);
@@ -224,10 +236,9 @@
Elf_Addr v)
{
ptrdiff_t offset = (void *)v - (void *)location;
- s32 fill_v = offset;
u32 hi20, lo12;
- if (offset != fill_v) {
+ if (!riscv_insn_valid_32bit_offset(offset)) {
pr_err(
"%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
me->name, (long long)v, location);
@@ -263,6 +274,13 @@
return 0;
}
+static int apply_r_riscv_add64_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ *(u64 *)location += (u64)v;
+ return 0;
+}
+
static int apply_r_riscv_sub32_rela(struct module *me, u32 *location,
Elf_Addr v)
{
@@ -270,6 +288,13 @@
return 0;
}
+static int apply_r_riscv_sub64_rela(struct module *me, u32 *location,
+ Elf_Addr v)
+{
+ *(u64 *)location -= (u64)v;
+ return 0;
+}
+
static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
Elf_Addr v) = {
[R_RISCV_32] = apply_r_riscv_32_rela,
@@ -290,7 +315,9 @@
[R_RISCV_RELAX] = apply_r_riscv_relax_rela,
[R_RISCV_ALIGN] = apply_r_riscv_align_rela,
[R_RISCV_ADD32] = apply_r_riscv_add32_rela,
+ [R_RISCV_ADD64] = apply_r_riscv_add64_rela,
[R_RISCV_SUB32] = apply_r_riscv_sub32_rela,
+ [R_RISCV_SUB64] = apply_r_riscv_sub64_rela,
};
int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
@@ -319,8 +346,8 @@
/* 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);
+ pr_warn("%s: Unknown symbol %s\n",
+ me->name, strtab + sym->st_name);
return -ENOENT;
}
diff --git a/arch/riscv/kernel/module.lds b/arch/riscv/kernel/module.lds
deleted file mode 100644
index 295ecfb..0000000
--- a/arch/riscv/kernel/module.lds
+++ /dev/null
@@ -1,8 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2017 Andes Technology Corporation */
-
-SECTIONS {
- .plt (NOLOAD) : { BYTE(0) }
- .got (NOLOAD) : { BYTE(0) }
- .got.plt (NOLOAD) : { BYTE(0) }
-}
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
new file mode 100644
index 0000000..3fe7a52
--- /dev/null
+++ b/arch/riscv/kernel/patch.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/memory.h>
+#include <linux/uaccess.h>
+#include <linux/stop_machine.h>
+#include <asm/kprobes.h>
+#include <asm/cacheflush.h>
+#include <asm/fixmap.h>
+#include <asm/patch.h>
+
+struct patch_insn {
+ void *addr;
+ u32 insn;
+ atomic_t cpu_count;
+};
+
+#ifdef CONFIG_MMU
+static void *patch_map(void *addr, int fixmap)
+{
+ uintptr_t uintaddr = (uintptr_t) addr;
+ struct page *page;
+
+ if (core_kernel_text(uintaddr))
+ page = phys_to_page(__pa_symbol(addr));
+ else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+ page = vmalloc_to_page(addr);
+ else
+ return addr;
+
+ BUG_ON(!page);
+
+ return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
+ (uintaddr & ~PAGE_MASK));
+}
+NOKPROBE_SYMBOL(patch_map);
+
+static void patch_unmap(int fixmap)
+{
+ clear_fixmap(fixmap);
+}
+NOKPROBE_SYMBOL(patch_unmap);
+
+static int patch_insn_write(void *addr, const void *insn, size_t len)
+{
+ void *waddr = addr;
+ bool across_pages = (((uintptr_t) addr & ~PAGE_MASK) + len) > PAGE_SIZE;
+ int ret;
+
+ /*
+ * Before reaching here, it was expected to lock the text_mutex
+ * already, so we don't need to give another lock here and could
+ * ensure that it was safe between each cores.
+ */
+ lockdep_assert_held(&text_mutex);
+
+ if (across_pages)
+ patch_map(addr + len, FIX_TEXT_POKE1);
+
+ waddr = patch_map(addr, FIX_TEXT_POKE0);
+
+ ret = copy_to_kernel_nofault(waddr, insn, len);
+
+ patch_unmap(FIX_TEXT_POKE0);
+
+ if (across_pages)
+ patch_unmap(FIX_TEXT_POKE1);
+
+ return ret;
+}
+NOKPROBE_SYMBOL(patch_insn_write);
+#else
+static int patch_insn_write(void *addr, const void *insn, size_t len)
+{
+ return copy_to_kernel_nofault(addr, insn, len);
+}
+NOKPROBE_SYMBOL(patch_insn_write);
+#endif /* CONFIG_MMU */
+
+int patch_text_nosync(void *addr, const void *insns, size_t len)
+{
+ u32 *tp = addr;
+ int ret;
+
+ ret = patch_insn_write(tp, insns, len);
+
+ if (!ret)
+ flush_icache_range((uintptr_t) tp, (uintptr_t) tp + len);
+
+ return ret;
+}
+NOKPROBE_SYMBOL(patch_text_nosync);
+
+static int patch_text_cb(void *data)
+{
+ struct patch_insn *patch = data;
+ int ret = 0;
+
+ if (atomic_inc_return(&patch->cpu_count) == 1) {
+ ret =
+ patch_text_nosync(patch->addr, &patch->insn,
+ GET_INSN_LENGTH(patch->insn));
+ atomic_inc(&patch->cpu_count);
+ } else {
+ while (atomic_read(&patch->cpu_count) <= num_online_cpus())
+ cpu_relax();
+ smp_mb();
+ }
+
+ return ret;
+}
+NOKPROBE_SYMBOL(patch_text_cb);
+
+int patch_text(void *addr, u32 insn)
+{
+ struct patch_insn patch = {
+ .addr = addr,
+ .insn = insn,
+ .cpu_count = ATOMIC_INIT(0),
+ };
+
+ return stop_machine_cpuslocked(patch_text_cb,
+ &patch, cpu_online_mask);
+}
+NOKPROBE_SYMBOL(patch_text);
diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c
index 8d2804f..ad3001c 100644
--- a/arch/riscv/kernel/perf_callchain.c
+++ b/arch/riscv/kernel/perf_callchain.c
@@ -60,14 +60,15 @@
void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
+ struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
unsigned long fp = 0;
/* RISC-V does not support perf in guest mode. */
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
+ if (guest_cbs && guest_cbs->is_in_guest())
return;
fp = regs->s0;
- perf_callchain_store(entry, regs->sepc);
+ perf_callchain_store(entry, regs->epc);
fp = user_backtrace(entry, fp, regs->ra);
while (fp && !(fp & 0x3) && entry->nr < entry->max_stack)
@@ -84,8 +85,10 @@
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
+ struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
+
/* RISC-V does not support perf in guest mode. */
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ if (guest_cbs && guest_cbs->is_in_guest()) {
pr_warn("RISC-V does not support perf in guest mode!");
return;
}
diff --git a/arch/riscv/kernel/perf_event.c b/arch/riscv/kernel/perf_event.c
index 91626d9..c835f03 100644
--- a/arch/riscv/kernel/perf_event.c
+++ b/arch/riscv/kernel/perf_event.c
@@ -147,7 +147,7 @@
return riscv_pmu->hw_events[config];
}
-int riscv_map_cache_decode(u64 config, unsigned int *type,
+static int riscv_map_cache_decode(u64 config, unsigned int *type,
unsigned int *op, unsigned int *result)
{
return -ENOENT;
@@ -342,7 +342,7 @@
static DEFINE_MUTEX(pmc_reserve_mutex);
-irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev)
+static irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev)
{
return IRQ_NONE;
}
@@ -361,7 +361,7 @@
return err;
}
-void release_pmc_hardware(void)
+static void release_pmc_hardware(void)
{
mutex_lock(&pmc_reserve_mutex);
if (riscv_pmu->irq >= 0)
@@ -464,7 +464,7 @@
{ /* sentinel value */ }
};
-int __init init_hw_perf_events(void)
+static int __init init_hw_perf_events(void)
{
struct device_node *node = of_find_node_by_type(NULL, "pmu");
const struct of_device_id *of_id;
diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c
index 04a38fb..fd304a2 100644
--- a/arch/riscv/kernel/perf_regs.c
+++ b/arch/riscv/kernel/perf_regs.c
@@ -36,8 +36,7 @@
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 330b347..dd5f985 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -22,21 +22,29 @@
#include <asm/switch_to.h>
#include <asm/thread_info.h>
+register unsigned long gp_in_global __asm__("gp");
+
+#ifdef CONFIG_STACKPROTECTOR
+#include <linux/stackprotector.h>
+unsigned long __stack_chk_guard __read_mostly;
+EXPORT_SYMBOL(__stack_chk_guard);
+#endif
+
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();
+ raw_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("epc: " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n",
+ regs->epc, 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",
@@ -58,25 +66,24 @@
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);
+ pr_cont("status: " REG_FMT " badaddr: " REG_FMT " cause: " REG_FMT "\n",
+ regs->status, regs->badaddr, regs->cause);
}
void start_thread(struct pt_regs *regs, unsigned long pc,
unsigned long sp)
{
- regs->sstatus = SR_SPIE;
+ regs->status = SR_PIE;
if (has_fpu) {
- regs->sstatus |= SR_FS_INITIAL;
+ regs->status |= SR_FS_INITIAL;
/*
* Restore the initial value to the FP register
* before starting the user program.
*/
fstate_restore(current, regs);
}
- regs->sepc = pc;
+ regs->epc = pc;
regs->sp = sp;
- set_fs(USER_DS);
}
void flush_thread(void)
@@ -99,18 +106,18 @@
return 0;
}
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
- unsigned long arg, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
+ struct task_struct *p, unsigned long tls)
{
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_SPP | SR_SPIE; /* Supervisor, irqs on */
+ childregs->gp = gp_in_global;
+ /* Supervisor/Machine, irqs on: */
+ childregs->status = SR_PP | SR_PIE;
p->thread.ra = (unsigned long)ret_from_kernel_thread;
p->thread.s[0] = usp; /* fn */
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 1252113..69678ab 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -10,6 +10,7 @@
#include <asm/ptrace.h>
#include <asm/syscall.h>
#include <asm/thread_info.h>
+#include <asm/switch_to.h>
#include <linux/audit.h>
#include <linux/ptrace.h>
#include <linux/elf.h>
@@ -30,13 +31,10 @@
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 membuf to)
{
- struct pt_regs *regs;
-
- regs = task_pt_regs(target);
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
+ return membuf_write(&to, task_pt_regs(target),
+ sizeof(struct user_regs_struct));
}
static int riscv_gpr_set(struct task_struct *target,
@@ -55,21 +53,16 @@
#ifdef CONFIG_FPU
static int riscv_fpr_get(struct task_struct *target,
const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
+ struct membuf to)
{
- int ret;
struct __riscv_d_ext_state *fstate = &target->thread.fstate;
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, fstate, 0,
- offsetof(struct __riscv_d_ext_state, fcsr));
- if (!ret) {
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, fstate, 0,
- offsetof(struct __riscv_d_ext_state, fcsr) +
- sizeof(fstate->fcsr));
- }
+ if (target == current)
+ fstate_save(current, task_pt_regs(current));
- return ret;
+ membuf_write(&to, fstate, offsetof(struct __riscv_d_ext_state, fcsr));
+ membuf_store(&to, fstate->fcsr);
+ return membuf_zero(&to, 4); // explicitly pad
}
static int riscv_fpr_set(struct task_struct *target,
@@ -98,8 +91,8 @@
.n = ELF_NGREG,
.size = sizeof(elf_greg_t),
.align = sizeof(elf_greg_t),
- .get = &riscv_gpr_get,
- .set = &riscv_gpr_set,
+ .regset_get = riscv_gpr_get,
+ .set = riscv_gpr_set,
},
#ifdef CONFIG_FPU
[REGSET_F] = {
@@ -107,8 +100,8 @@
.n = ELF_NFPREG,
.size = sizeof(elf_fpreg_t),
.align = sizeof(elf_fpreg_t),
- .get = &riscv_fpr_get,
- .set = &riscv_fpr_set,
+ .regset_get = riscv_fpr_get,
+ .set = riscv_fpr_set,
},
#endif
};
@@ -148,11 +141,19 @@
* Allows PTRACE_SYSCALL to work. These are called from entry.S in
* {handle,ret_from}_syscall.
*/
-__visible void do_syscall_trace_enter(struct pt_regs *regs)
+__visible int 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);
+ return -1;
+
+ /*
+ * Do the secure computing after ptrace; failures should be fast.
+ * If this fails we might have return value in a0 from seccomp
+ * (via SECCOMP_RET_ERRNO/TRACE).
+ */
+ if (secure_computing() == -1)
+ return -1;
#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
@@ -160,6 +161,7 @@
#endif
audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3);
+ return 0;
}
__visible void do_syscall_trace_exit(struct pt_regs *regs)
diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c
index aa56bb1..ee5878d 100644
--- a/arch/riscv/kernel/reset.c
+++ b/arch/riscv/kernel/reset.c
@@ -5,12 +5,11 @@
#include <linux/reboot.h>
#include <linux/pm.h>
-#include <asm/sbi.h>
static void default_power_off(void)
{
- sbi_shutdown();
- while (1);
+ while (1)
+ wait_for_interrupt();
}
void (*pm_power_off)(void) = default_power_off;
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
index 4800cf7..450492e 100644
--- a/arch/riscv/kernel/riscv_ksyms.c
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -9,8 +9,7 @@
/*
* Assembly functions that may be used (directly or indirectly) by modules
*/
-EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(__asm_copy_to_user);
-EXPORT_SYMBOL(__asm_copy_from_user);
EXPORT_SYMBOL(memset);
EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(__memset);
+EXPORT_SYMBOL(__memcpy);
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
new file mode 100644
index 0000000..226ccce
--- /dev/null
+++ b/arch/riscv/kernel/sbi.c
@@ -0,0 +1,605 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * SBI initialilization and all extension implementation.
+ *
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/init.h>
+#include <linux/pm.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+/* default SBI version is 0.1 */
+unsigned long sbi_spec_version = SBI_SPEC_VERSION_DEFAULT;
+EXPORT_SYMBOL(sbi_spec_version);
+
+static void (*__sbi_set_timer)(uint64_t stime);
+static int (*__sbi_send_ipi)(const unsigned long *hart_mask);
+static int (*__sbi_rfence)(int fid, const unsigned long *hart_mask,
+ unsigned long start, unsigned long size,
+ unsigned long arg4, unsigned long arg5);
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+ unsigned long arg1, unsigned long arg2,
+ unsigned long arg3, unsigned long arg4,
+ unsigned long arg5)
+{
+ struct sbiret ret;
+
+ 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 a3 asm ("a3") = (uintptr_t)(arg3);
+ register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
+ register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
+ register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
+ register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
+ asm volatile ("ecall"
+ : "+r" (a0), "+r" (a1)
+ : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
+ : "memory");
+ ret.error = a0;
+ ret.value = a1;
+
+ return ret;
+}
+EXPORT_SYMBOL(sbi_ecall);
+
+int sbi_err_map_linux_errno(int err)
+{
+ switch (err) {
+ case SBI_SUCCESS:
+ return 0;
+ case SBI_ERR_DENIED:
+ return -EPERM;
+ case SBI_ERR_INVALID_PARAM:
+ return -EINVAL;
+ case SBI_ERR_INVALID_ADDRESS:
+ return -EFAULT;
+ case SBI_ERR_NOT_SUPPORTED:
+ case SBI_ERR_FAILURE:
+ default:
+ return -ENOTSUPP;
+ };
+}
+EXPORT_SYMBOL(sbi_err_map_linux_errno);
+
+#ifdef CONFIG_RISCV_SBI_V01
+/**
+ * sbi_console_putchar() - Writes given character to the console device.
+ * @ch: The data to be written to the console.
+ *
+ * Return: None
+ */
+void sbi_console_putchar(int ch)
+{
+ sbi_ecall(SBI_EXT_0_1_CONSOLE_PUTCHAR, 0, ch, 0, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_console_putchar);
+
+/**
+ * sbi_console_getchar() - Reads a byte from console device.
+ *
+ * Returns the value read from console.
+ */
+int sbi_console_getchar(void)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_0_1_CONSOLE_GETCHAR, 0, 0, 0, 0, 0, 0, 0);
+
+ return ret.error;
+}
+EXPORT_SYMBOL(sbi_console_getchar);
+
+/**
+ * sbi_shutdown() - Remove all the harts from executing supervisor code.
+ *
+ * Return: None
+ */
+void sbi_shutdown(void)
+{
+ sbi_ecall(SBI_EXT_0_1_SHUTDOWN, 0, 0, 0, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_shutdown);
+
+/**
+ * sbi_clear_ipi() - Clear any pending IPIs for the calling hart.
+ *
+ * Return: None
+ */
+void sbi_clear_ipi(void)
+{
+ sbi_ecall(SBI_EXT_0_1_CLEAR_IPI, 0, 0, 0, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_clear_ipi);
+
+/**
+ * sbi_set_timer_v01() - Program the timer for next timer event.
+ * @stime_value: The value after which next timer event should fire.
+ *
+ * Return: None
+ */
+static void __sbi_set_timer_v01(uint64_t stime_value)
+{
+#if __riscv_xlen == 32
+ sbi_ecall(SBI_EXT_0_1_SET_TIMER, 0, stime_value,
+ stime_value >> 32, 0, 0, 0, 0);
+#else
+ sbi_ecall(SBI_EXT_0_1_SET_TIMER, 0, stime_value, 0, 0, 0, 0, 0);
+#endif
+}
+
+static int __sbi_send_ipi_v01(const unsigned long *hart_mask)
+{
+ sbi_ecall(SBI_EXT_0_1_SEND_IPI, 0, (unsigned long)hart_mask,
+ 0, 0, 0, 0, 0);
+ return 0;
+}
+
+static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask,
+ unsigned long start, unsigned long size,
+ unsigned long arg4, unsigned long arg5)
+{
+ int result = 0;
+
+ /* v0.2 function IDs are equivalent to v0.1 extension IDs */
+ switch (fid) {
+ case SBI_EXT_RFENCE_REMOTE_FENCE_I:
+ sbi_ecall(SBI_EXT_0_1_REMOTE_FENCE_I, 0,
+ (unsigned long)hart_mask, 0, 0, 0, 0, 0);
+ break;
+ case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
+ sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA, 0,
+ (unsigned long)hart_mask, start, size,
+ 0, 0, 0);
+ break;
+ case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
+ sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID, 0,
+ (unsigned long)hart_mask, start, size,
+ arg4, 0, 0);
+ break;
+ default:
+ pr_err("SBI call [%d]not supported in SBI v0.1\n", fid);
+ result = -EINVAL;
+ }
+
+ return result;
+}
+
+static void sbi_set_power_off(void)
+{
+ pm_power_off = sbi_shutdown;
+}
+#else
+static void __sbi_set_timer_v01(uint64_t stime_value)
+{
+ pr_warn("Timer extension is not available in SBI v%lu.%lu\n",
+ sbi_major_version(), sbi_minor_version());
+}
+
+static int __sbi_send_ipi_v01(const unsigned long *hart_mask)
+{
+ pr_warn("IPI extension is not available in SBI v%lu.%lu\n",
+ sbi_major_version(), sbi_minor_version());
+
+ return 0;
+}
+
+static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask,
+ unsigned long start, unsigned long size,
+ unsigned long arg4, unsigned long arg5)
+{
+ pr_warn("remote fence extension is not available in SBI v%lu.%lu\n",
+ sbi_major_version(), sbi_minor_version());
+
+ return 0;
+}
+
+static void sbi_set_power_off(void) {}
+#endif /* CONFIG_RISCV_SBI_V01 */
+
+static void __sbi_set_timer_v02(uint64_t stime_value)
+{
+#if __riscv_xlen == 32
+ sbi_ecall(SBI_EXT_TIME, SBI_EXT_TIME_SET_TIMER, stime_value,
+ stime_value >> 32, 0, 0, 0, 0);
+#else
+ sbi_ecall(SBI_EXT_TIME, SBI_EXT_TIME_SET_TIMER, stime_value, 0,
+ 0, 0, 0, 0);
+#endif
+}
+
+static int __sbi_send_ipi_v02(const unsigned long *hart_mask)
+{
+ unsigned long hartid, hmask_val, hbase;
+ struct cpumask tmask;
+ struct sbiret ret = {0};
+ int result;
+
+ if (!hart_mask || !(*hart_mask)) {
+ riscv_cpuid_to_hartid_mask(cpu_online_mask, &tmask);
+ hart_mask = cpumask_bits(&tmask);
+ }
+
+ hmask_val = 0;
+ hbase = 0;
+ for_each_set_bit(hartid, hart_mask, NR_CPUS) {
+ if (hmask_val && ((hbase + BITS_PER_LONG) <= hartid)) {
+ ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
+ hmask_val, hbase, 0, 0, 0, 0);
+ if (ret.error)
+ goto ecall_failed;
+ hmask_val = 0;
+ hbase = 0;
+ }
+ if (!hmask_val)
+ hbase = hartid;
+ hmask_val |= 1UL << (hartid - hbase);
+ }
+
+ if (hmask_val) {
+ ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
+ hmask_val, hbase, 0, 0, 0, 0);
+ if (ret.error)
+ goto ecall_failed;
+ }
+
+ return 0;
+
+ecall_failed:
+ result = sbi_err_map_linux_errno(ret.error);
+ pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n",
+ __func__, hbase, hmask_val, result);
+ return result;
+}
+
+static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask_val,
+ unsigned long hbase, unsigned long start,
+ unsigned long size, unsigned long arg4,
+ unsigned long arg5)
+{
+ struct sbiret ret = {0};
+ int ext = SBI_EXT_RFENCE;
+ int result = 0;
+
+ switch (fid) {
+ case SBI_EXT_RFENCE_REMOTE_FENCE_I:
+ ret = sbi_ecall(ext, fid, hmask_val, hbase, 0, 0, 0, 0);
+ break;
+ case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
+ ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ size, 0, 0);
+ break;
+ case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
+ ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ size, arg4, 0);
+ break;
+
+ case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA:
+ ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ size, 0, 0);
+ break;
+ case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID:
+ ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ size, arg4, 0);
+ break;
+ case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA:
+ ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ size, 0, 0);
+ break;
+ case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID:
+ ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+ size, arg4, 0);
+ break;
+ default:
+ pr_err("unknown function ID [%lu] for SBI extension [%d]\n",
+ fid, ext);
+ result = -EINVAL;
+ }
+
+ if (ret.error) {
+ result = sbi_err_map_linux_errno(ret.error);
+ pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n",
+ __func__, hbase, hmask_val, result);
+ }
+
+ return result;
+}
+
+static int __sbi_rfence_v02(int fid, const unsigned long *hart_mask,
+ unsigned long start, unsigned long size,
+ unsigned long arg4, unsigned long arg5)
+{
+ unsigned long hmask_val, hartid, hbase;
+ struct cpumask tmask;
+ int result;
+
+ if (!hart_mask || !(*hart_mask)) {
+ riscv_cpuid_to_hartid_mask(cpu_online_mask, &tmask);
+ hart_mask = cpumask_bits(&tmask);
+ }
+
+ hmask_val = 0;
+ hbase = 0;
+ for_each_set_bit(hartid, hart_mask, NR_CPUS) {
+ if (hmask_val && ((hbase + BITS_PER_LONG) <= hartid)) {
+ result = __sbi_rfence_v02_call(fid, hmask_val, hbase,
+ start, size, arg4, arg5);
+ if (result)
+ return result;
+ hmask_val = 0;
+ hbase = 0;
+ }
+ if (!hmask_val)
+ hbase = hartid;
+ hmask_val |= 1UL << (hartid - hbase);
+ }
+
+ if (hmask_val) {
+ result = __sbi_rfence_v02_call(fid, hmask_val, hbase,
+ start, size, arg4, arg5);
+ if (result)
+ return result;
+ }
+
+ return 0;
+}
+
+/**
+ * sbi_set_timer() - Program the timer for next timer event.
+ * @stime_value: The value after which next timer event should fire.
+ *
+ * Return: None
+ */
+void sbi_set_timer(uint64_t stime_value)
+{
+ __sbi_set_timer(stime_value);
+}
+
+/**
+ * sbi_send_ipi() - Send an IPI to any hart.
+ * @hart_mask: A cpu mask containing all the target harts.
+ *
+ * Return: None
+ */
+void sbi_send_ipi(const unsigned long *hart_mask)
+{
+ __sbi_send_ipi(hart_mask);
+}
+EXPORT_SYMBOL(sbi_send_ipi);
+
+/**
+ * sbi_remote_fence_i() - Execute FENCE.I instruction on given remote harts.
+ * @hart_mask: A cpu mask containing all the target harts.
+ *
+ * Return: None
+ */
+void sbi_remote_fence_i(const unsigned long *hart_mask)
+{
+ __sbi_rfence(SBI_EXT_RFENCE_REMOTE_FENCE_I,
+ hart_mask, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_remote_fence_i);
+
+/**
+ * sbi_remote_sfence_vma() - Execute SFENCE.VMA instructions on given remote
+ * harts for the specified virtual address range.
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the virtual address
+ * @size: Total size of the virtual address range.
+ *
+ * Return: None
+ */
+void sbi_remote_sfence_vma(const unsigned long *hart_mask,
+ unsigned long start,
+ unsigned long size)
+{
+ __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
+ hart_mask, start, size, 0, 0);
+}
+EXPORT_SYMBOL(sbi_remote_sfence_vma);
+
+/**
+ * sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given
+ * remote harts for a virtual address range belonging to a specific ASID.
+ *
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the virtual address
+ * @size: Total size of the virtual address range.
+ * @asid: The value of address space identifier (ASID).
+ *
+ * Return: None
+ */
+void sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
+ unsigned long start,
+ unsigned long size,
+ unsigned long asid)
+{
+ __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
+ hart_mask, start, size, asid, 0);
+}
+EXPORT_SYMBOL(sbi_remote_sfence_vma_asid);
+
+/**
+ * sbi_remote_hfence_gvma() - Execute HFENCE.GVMA instructions on given remote
+ * harts for the specified guest physical address range.
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the guest physical address
+ * @size: Total size of the guest physical address range.
+ *
+ * Return: None
+ */
+int sbi_remote_hfence_gvma(const unsigned long *hart_mask,
+ unsigned long start,
+ unsigned long size)
+{
+ return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
+ hart_mask, start, size, 0, 0);
+}
+EXPORT_SYMBOL_GPL(sbi_remote_hfence_gvma);
+
+/**
+ * sbi_remote_hfence_gvma_vmid() - Execute HFENCE.GVMA instructions on given
+ * remote harts for a guest physical address range belonging to a specific VMID.
+ *
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the guest physical address
+ * @size: Total size of the guest physical address range.
+ * @vmid: The value of guest ID (VMID).
+ *
+ * Return: 0 if success, Error otherwise.
+ */
+int sbi_remote_hfence_gvma_vmid(const unsigned long *hart_mask,
+ unsigned long start,
+ unsigned long size,
+ unsigned long vmid)
+{
+ return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID,
+ hart_mask, start, size, vmid, 0);
+}
+EXPORT_SYMBOL(sbi_remote_hfence_gvma_vmid);
+
+/**
+ * sbi_remote_hfence_vvma() - Execute HFENCE.VVMA instructions on given remote
+ * harts for the current guest virtual address range.
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the current guest virtual address
+ * @size: Total size of the current guest virtual address range.
+ *
+ * Return: None
+ */
+int sbi_remote_hfence_vvma(const unsigned long *hart_mask,
+ unsigned long start,
+ unsigned long size)
+{
+ return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
+ hart_mask, start, size, 0, 0);
+}
+EXPORT_SYMBOL(sbi_remote_hfence_vvma);
+
+/**
+ * sbi_remote_hfence_vvma_asid() - Execute HFENCE.VVMA instructions on given
+ * remote harts for current guest virtual address range belonging to a specific
+ * ASID.
+ *
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the current guest virtual address
+ * @size: Total size of the current guest virtual address range.
+ * @asid: The value of address space identifier (ASID).
+ *
+ * Return: None
+ */
+int sbi_remote_hfence_vvma_asid(const unsigned long *hart_mask,
+ unsigned long start,
+ unsigned long size,
+ unsigned long asid)
+{
+ return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID,
+ hart_mask, start, size, asid, 0);
+}
+EXPORT_SYMBOL(sbi_remote_hfence_vvma_asid);
+
+/**
+ * sbi_probe_extension() - Check if an SBI extension ID is supported or not.
+ * @extid: The extension ID to be probed.
+ *
+ * Return: Extension specific nonzero value f yes, -ENOTSUPP otherwise.
+ */
+int sbi_probe_extension(int extid)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_PROBE_EXT, extid,
+ 0, 0, 0, 0, 0);
+ if (!ret.error)
+ if (ret.value)
+ return ret.value;
+
+ return -ENOTSUPP;
+}
+EXPORT_SYMBOL(sbi_probe_extension);
+
+static long __sbi_base_ecall(int fid)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_BASE, fid, 0, 0, 0, 0, 0, 0);
+ if (!ret.error)
+ return ret.value;
+ else
+ return sbi_err_map_linux_errno(ret.error);
+}
+
+static inline long sbi_get_spec_version(void)
+{
+ return __sbi_base_ecall(SBI_EXT_BASE_GET_SPEC_VERSION);
+}
+
+static inline long sbi_get_firmware_id(void)
+{
+ return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_ID);
+}
+
+static inline long sbi_get_firmware_version(void)
+{
+ return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION);
+}
+
+static void sbi_send_cpumask_ipi(const struct cpumask *target)
+{
+ struct cpumask hartid_mask;
+
+ riscv_cpuid_to_hartid_mask(target, &hartid_mask);
+
+ sbi_send_ipi(cpumask_bits(&hartid_mask));
+}
+
+static struct riscv_ipi_ops sbi_ipi_ops = {
+ .ipi_inject = sbi_send_cpumask_ipi
+};
+
+int __init sbi_init(void)
+{
+ int ret;
+
+ sbi_set_power_off();
+ ret = sbi_get_spec_version();
+ if (ret > 0)
+ sbi_spec_version = ret;
+
+ pr_info("SBI specification v%lu.%lu detected\n",
+ sbi_major_version(), sbi_minor_version());
+
+ if (!sbi_spec_is_0_1()) {
+ pr_info("SBI implementation ID=0x%lx Version=0x%lx\n",
+ sbi_get_firmware_id(), sbi_get_firmware_version());
+ if (sbi_probe_extension(SBI_EXT_TIME) > 0) {
+ __sbi_set_timer = __sbi_set_timer_v02;
+ pr_info("SBI v0.2 TIME extension detected\n");
+ } else {
+ __sbi_set_timer = __sbi_set_timer_v01;
+ }
+ if (sbi_probe_extension(SBI_EXT_IPI) > 0) {
+ __sbi_send_ipi = __sbi_send_ipi_v02;
+ pr_info("SBI v0.2 IPI extension detected\n");
+ } else {
+ __sbi_send_ipi = __sbi_send_ipi_v01;
+ }
+ if (sbi_probe_extension(SBI_EXT_RFENCE) > 0) {
+ __sbi_rfence = __sbi_rfence_v02;
+ pr_info("SBI v0.2 RFENCE extension detected\n");
+ } else {
+ __sbi_rfence = __sbi_rfence_v01;
+ }
+ } else {
+ __sbi_set_timer = __sbi_set_timer_v01;
+ __sbi_send_ipi = __sbi_send_ipi_v01;
+ __sbi_rfence = __sbi_rfence_v01;
+ }
+
+ riscv_set_ipi_ops(&sbi_ipi_ops);
+
+ return 0;
+}
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 845ae0e..117f321 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -16,18 +16,23 @@
#include <linux/of_platform.h>
#include <linux/sched/task.h>
#include <linux/swiotlb.h>
+#include <linux/smp.h>
+#include <linux/efi.h>
+#include <asm/cpu_ops.h>
+#include <asm/early_ioremap.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>
+#include <asm/kasan.h>
+#include <asm/efi.h>
#include "head.h"
-#ifdef CONFIG_DUMMY_CONSOLE
-struct screen_info screen_info = {
+#if defined(CONFIG_DUMMY_CONSOLE) || defined(CONFIG_EFI)
+struct screen_info screen_info __section(".data") = {
.orig_video_lines = 30,
.orig_video_cols = 80,
.orig_video_mode = 0,
@@ -37,12 +42,18 @@
};
#endif
-/* The lucky hart to first increment this variable will boot the other cores */
-atomic_t hart_lottery;
+/*
+ * The lucky hart to first increment this variable will boot the other cores.
+ * This is used before the kernel initializes the BSS so it can't be in the
+ * BSS.
+ */
+atomic_t hart_lottery __section(".sdata");
unsigned long boot_cpu_hartid;
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
-void __init parse_dtb(void)
+static void __init parse_dtb(void)
{
+ /* Early scan of device tree from init memory */
if (early_init_dt_scan(dtb_early_va))
return;
@@ -55,6 +66,7 @@
void __init setup_arch(char **cmdline_p)
{
+ parse_dtb();
init_mm.start_code = (unsigned long) _stext;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
@@ -62,23 +74,52 @@
*cmdline_p = boot_command_line;
+ early_ioremap_setup();
+ jump_label_init();
parse_early_param();
+ efi_init();
setup_bootmem();
paging_init();
- unflatten_device_tree();
+#if IS_ENABLED(CONFIG_BUILTIN_DTB)
+ unflatten_and_copy_device_tree();
+#else
+ if (early_init_dt_verify(__va(dtb_early_pa)))
+ unflatten_device_tree();
+ else
+ pr_err("No DTB found in kernel mappings\n");
+#endif
#ifdef CONFIG_SWIOTLB
swiotlb_init(1);
#endif
+#ifdef CONFIG_KASAN
+ kasan_init();
+#endif
+
+#if IS_ENABLED(CONFIG_RISCV_SBI)
+ sbi_init();
+#endif
+
#ifdef CONFIG_SMP
setup_smp();
#endif
-#ifdef CONFIG_DUMMY_CONSOLE
- conswitchp = &dummy_con;
-#endif
-
riscv_fill_hwcap();
}
+
+static int __init topology_init(void)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ struct cpu *cpu = &per_cpu(cpu_devices, i);
+
+ cpu->hotpluggable = cpu_has_hotplug(i);
+ register_cpu(cpu, i);
+ }
+
+ return 0;
+}
+subsys_initcall(topology_init);
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index d0f6f21..bc68418 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -17,11 +17,16 @@
#include <asm/switch_to.h>
#include <asm/csr.h>
+extern u32 __user_rt_sigreturn[2];
+
#define DEBUG_SIG 0
struct rt_sigframe {
struct siginfo info;
struct ucontext uc;
+#ifndef CONFIG_MMU
+ u32 sigreturn_code[2];
+#endif
};
#ifdef CONFIG_FPU
@@ -124,7 +129,7 @@
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);
+ frame, (void *)regs->epc, (void *)regs->sp);
}
force_sig(SIGSEGV);
return 0;
@@ -166,7 +171,6 @@
return (void __user *)sp;
}
-
static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
struct pt_regs *regs)
{
@@ -189,8 +193,19 @@
return -EFAULT;
/* Set up to return from userspace. */
+#ifdef CONFIG_MMU
regs->ra = (unsigned long)VDSO_SYMBOL(
current->mm->context.vdso, rt_sigreturn);
+#else
+ /*
+ * For the nommu case we don't have a VDSO. Instead we push two
+ * instructions to call the rt_sigreturn syscall onto the user stack.
+ */
+ if (copy_to_user(&frame->sigreturn_code, __user_rt_sigreturn,
+ sizeof(frame->sigreturn_code)))
+ return -EFAULT;
+ regs->ra = (unsigned long)&frame->sigreturn_code;
+#endif /* CONFIG_MMU */
/*
* Set up registers for signal handler.
@@ -199,7 +214,7 @@
* 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->epc = (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 */
@@ -208,7 +223,7 @@
#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);
+ (void *)regs->epc, (void *)regs->ra, frame);
#endif
return 0;
@@ -220,10 +235,9 @@
int ret;
/* Are we from a system call? */
- if (regs->scause == EXC_SYSCALL) {
+ if (regs->cause == EXC_SYSCALL) {
/* Avoid additional syscall restarting via ret_from_exception */
- regs->scause = -1UL;
-
+ regs->cause = -1UL;
/* If so, check system call restarting.. */
switch (regs->a0) {
case -ERESTART_RESTARTBLOCK:
@@ -236,10 +250,10 @@
regs->a0 = -EINTR;
break;
}
- /* fallthrough */
+ fallthrough;
case -ERESTARTNOINTR:
regs->a0 = regs->orig_a0;
- regs->sepc -= 0x4;
+ regs->epc -= 0x4;
break;
}
}
@@ -261,9 +275,9 @@
}
/* Did we come from a system call? */
- if (regs->scause == EXC_SYSCALL) {
+ if (regs->cause == EXC_SYSCALL) {
/* Avoid additional syscall restarting via ret_from_exception */
- regs->scause = -1UL;
+ regs->cause = -1UL;
/* Restart the system call - no handlers present */
switch (regs->a0) {
@@ -271,12 +285,12 @@
case -ERESTARTSYS:
case -ERESTARTNOINTR:
regs->a0 = regs->orig_a0;
- regs->sepc -= 0x4;
+ regs->epc -= 0x4;
break;
case -ERESTART_RESTARTBLOCK:
regs->a0 = regs->orig_a0;
regs->a7 = __NR_restart_syscall;
- regs->sepc -= 0x4;
+ regs->epc -= 0x4;
break;
}
}
@@ -299,8 +313,6 @@
if (thread_info_flags & _TIF_SIGPENDING)
do_signal(regs);
- if (thread_info_flags & _TIF_NOTIFY_RESUME) {
- clear_thread_flag(TIF_NOTIFY_RESUME);
+ if (thread_info_flags & _TIF_NOTIFY_RESUME)
tracehook_notify_resume(regs);
- }
}
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 098c04a..d445674 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -10,11 +10,13 @@
#include <linux/cpu.h>
#include <linux/interrupt.h>
+#include <linux/module.h>
#include <linux/profile.h>
#include <linux/smp.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/delay.h>
+#include <linux/irq_work.h>
#include <asm/sbi.h>
#include <asm/tlbflush.h>
@@ -24,6 +26,7 @@
IPI_RESCHEDULE,
IPI_CALL_FUNC,
IPI_CPU_STOP,
+ IPI_IRQ_WORK,
IPI_MAX
};
@@ -62,6 +65,7 @@
for_each_cpu(cpu, in)
cpumask_set_cpu(cpuid_to_hartid_map(cpu), out);
}
+EXPORT_SYMBOL_GPL(riscv_cpuid_to_hartid_mask);
bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
{
@@ -81,9 +85,25 @@
wait_for_interrupt();
}
+static struct riscv_ipi_ops *ipi_ops;
+
+void riscv_set_ipi_ops(struct riscv_ipi_ops *ops)
+{
+ ipi_ops = ops;
+}
+EXPORT_SYMBOL_GPL(riscv_set_ipi_ops);
+
+void riscv_clear_ipi(void)
+{
+ if (ipi_ops && ipi_ops->ipi_clear)
+ ipi_ops->ipi_clear();
+
+ csr_clear(CSR_IP, IE_SIE);
+}
+EXPORT_SYMBOL_GPL(riscv_clear_ipi);
+
static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op)
{
- struct cpumask hartid_mask;
int cpu;
smp_mb__before_atomic();
@@ -91,32 +111,40 @@
set_bit(op, &ipi_data[cpu].bits);
smp_mb__after_atomic();
- riscv_cpuid_to_hartid_mask(mask, &hartid_mask);
- sbi_send_ipi(cpumask_bits(&hartid_mask));
+ if (ipi_ops && ipi_ops->ipi_inject)
+ ipi_ops->ipi_inject(mask);
+ else
+ pr_warn("SMP: IPI inject method not available\n");
}
static void send_ipi_single(int cpu, enum ipi_message_type op)
{
- int hartid = cpuid_to_hartid_map(cpu);
-
smp_mb__before_atomic();
set_bit(op, &ipi_data[cpu].bits);
smp_mb__after_atomic();
- sbi_send_ipi(cpumask_bits(cpumask_of(hartid)));
+ if (ipi_ops && ipi_ops->ipi_inject)
+ ipi_ops->ipi_inject(cpumask_of(cpu));
+ else
+ pr_warn("SMP: IPI inject method not available\n");
}
-static inline void clear_ipi(void)
+#ifdef CONFIG_IRQ_WORK
+void arch_irq_work_raise(void)
{
- csr_clear(CSR_SIP, SIE_SSIE);
+ send_ipi_single(smp_processor_id(), IPI_IRQ_WORK);
}
+#endif
-void riscv_software_interrupt(void)
+void handle_IPI(struct pt_regs *regs)
{
+ struct pt_regs *old_regs = set_irq_regs(regs);
unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
unsigned long *stats = ipi_data[smp_processor_id()].stats;
- clear_ipi();
+ irq_enter();
+
+ riscv_clear_ipi();
while (true) {
unsigned long ops;
@@ -126,7 +154,7 @@
ops = xchg(pending_ipis, 0);
if (ops == 0)
- return;
+ goto done;
if (ops & (1 << IPI_RESCHEDULE)) {
stats[IPI_RESCHEDULE]++;
@@ -143,17 +171,27 @@
ipi_stop();
}
+ if (ops & (1 << IPI_IRQ_WORK)) {
+ stats[IPI_IRQ_WORK]++;
+ irq_work_run();
+ }
+
BUG_ON((ops >> IPI_MAX) != 0);
/* Order data access and bit testing. */
mb();
}
+
+done:
+ irq_exit();
+ set_irq_regs(old_regs);
}
static const char * const ipi_names[] = {
[IPI_RESCHEDULE] = "Rescheduling interrupts",
[IPI_CALL_FUNC] = "Function call interrupts",
[IPI_CPU_STOP] = "CPU stop interrupts",
+ [IPI_IRQ_WORK] = "IRQ work interrupts",
};
void show_ipi_stats(struct seq_file *p, int prec)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 261f408..0b04e0e 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -24,6 +24,7 @@
#include <linux/of.h>
#include <linux/sched/task_stack.h>
#include <linux/sched/mm.h>
+#include <asm/cpu_ops.h>
#include <asm/irq.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
@@ -33,8 +34,6 @@
#include "head.h"
-void *__cpu_up_stack_pointer[NR_CPUS];
-void *__cpu_up_task_pointer[NR_CPUS];
static DECLARE_COMPLETION(cpu_running);
void __init smp_prepare_boot_cpu(void)
@@ -45,6 +44,7 @@
void __init smp_prepare_cpus(unsigned int max_cpus)
{
int cpuid;
+ int ret;
/* This covers non-smp usecase mandated by "nosmp" option */
if (max_cpus == 0)
@@ -53,6 +53,11 @@
for_each_possible_cpu(cpuid) {
if (cpuid == smp_processor_id())
continue;
+ if (cpu_ops[cpuid]->cpu_prepare) {
+ ret = cpu_ops[cpuid]->cpu_prepare(cpuid);
+ if (ret)
+ continue;
+ }
set_cpu_present(cpuid, true);
}
}
@@ -64,6 +69,8 @@
bool found_boot_cpu = false;
int cpuid = 1;
+ cpu_set_ops(0);
+
for_each_of_cpu_node(dn) {
hart = riscv_of_processor_hartid(dn);
if (hart < 0)
@@ -91,36 +98,37 @@
cpuid, nr_cpu_ids);
for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
- if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID)
+ if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
+ cpu_set_ops(cpuid);
set_cpu_possible(cpuid, true);
+ }
}
}
+static int start_secondary_cpu(int cpu, struct task_struct *tidle)
+{
+ if (cpu_ops[cpu]->cpu_start)
+ return cpu_ops[cpu]->cpu_start(cpu, tidle);
+
+ return -EOPNOTSUPP;
+}
+
int __cpu_up(unsigned int cpu, struct task_struct *tidle)
{
int ret = 0;
- int hartid = cpuid_to_hartid_map(cpu);
tidle->thread_info.cpu = cpu;
- /*
- * On RISC-V systems, all harts boot on their own accord. Our _start
- * selects the first hart to boot the kernel and causes the remainder
- * of the harts to spin in a loop waiting for their stack pointer to be
- * setup by that main hart. Writing __cpu_up_stack_pointer signals to
- * the spinning harts that they can continue the boot process.
- */
- smp_mb();
- WRITE_ONCE(__cpu_up_stack_pointer[hartid],
- task_stack_page(tidle) + THREAD_SIZE);
- WRITE_ONCE(__cpu_up_task_pointer[hartid], tidle);
-
- lockdep_assert_held(&cpu_running);
- wait_for_completion_timeout(&cpu_running,
+ ret = start_secondary_cpu(cpu, tidle);
+ if (!ret) {
+ wait_for_completion_timeout(&cpu_running,
msecs_to_jiffies(1000));
- if (!cpu_online(cpu)) {
- pr_crit("CPU%u: failed to come online\n", cpu);
- ret = -EIO;
+ if (!cpu_online(cpu)) {
+ pr_crit("CPU%u: failed to come online\n", cpu);
+ ret = -EIO;
+ }
+ } else {
+ pr_crit("CPU%u: failed to start\n", cpu);
}
return ret;
@@ -133,18 +141,21 @@
/*
* C entry point for a secondary processor.
*/
-asmlinkage __visible void __init smp_callin(void)
+asmlinkage __visible void smp_callin(void)
{
struct mm_struct *mm = &init_mm;
+ unsigned int curr_cpuid = smp_processor_id();
+
+ riscv_clear_ipi();
/* All kernel threads share the same mm context. */
mmgrab(mm);
current->active_mm = mm;
- trap_init();
- notify_cpu_starting(smp_processor_id());
- update_siblings_masks(smp_processor_id());
- set_cpu_online(smp_processor_id(), 1);
+ notify_cpu_starting(curr_cpuid);
+ update_siblings_masks(curr_cpuid);
+ set_cpu_online(curr_cpuid, 1);
+
/*
* Remote TLB flushes are ignored while the CPU is offline, so emit
* a local TLB flush right now just in case.
@@ -155,7 +166,6 @@
* Disable preemption before enabling interrupts, so we don't try to
* schedule a CPU that hasn't actually started yet.
*/
- preempt_disable();
local_irq_enable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/riscv/kernel/soc.c b/arch/riscv/kernel/soc.c
new file mode 100644
index 0000000..c7b0a73
--- /dev/null
+++ b/arch/riscv/kernel/soc.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#include <linux/init.h>
+#include <linux/libfdt.h>
+#include <linux/pgtable.h>
+#include <asm/soc.h>
+
+/*
+ * This is called extremly early, before parse_dtb(), to allow initializing
+ * SoC hardware before memory or any device driver initialization.
+ */
+void __init soc_early_init(void)
+{
+ void (*early_fn)(const void *fdt);
+ const struct of_device_id *s;
+ const void *fdt = dtb_early_va;
+
+ for (s = (void *)&__soc_early_init_table_start;
+ (void *)s < (void *)&__soc_early_init_table_end; s++) {
+ if (!fdt_node_check_compatible(fdt, 0, s->compatible)) {
+ early_fn = s->data;
+ early_fn(fdt);
+ return;
+ }
+ }
+}
+
+static bool soc_builtin_dtb_match(unsigned long vendor_id,
+ unsigned long arch_id, unsigned long imp_id,
+ const struct soc_builtin_dtb *entry)
+{
+ return entry->vendor_id == vendor_id &&
+ entry->arch_id == arch_id &&
+ entry->imp_id == imp_id;
+}
+
+void * __init soc_lookup_builtin_dtb(void)
+{
+ unsigned long vendor_id, arch_id, imp_id;
+ const struct soc_builtin_dtb *s;
+
+ __asm__ ("csrr %0, mvendorid" : "=r"(vendor_id));
+ __asm__ ("csrr %0, marchid" : "=r"(arch_id));
+ __asm__ ("csrr %0, mimpid" : "=r"(imp_id));
+
+ for (s = (void *)&__soc_builtin_dtb_table_start;
+ (void *)s < (void *)&__soc_builtin_dtb_table_end; s++) {
+ if (soc_builtin_dtb_match(vendor_id, arch_id, imp_id, s))
+ return s->dtb_func();
+ }
+
+ return NULL;
+}
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 19e46f4..5953429 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -12,6 +12,8 @@
#include <linux/stacktrace.h>
#include <linux/ftrace.h>
+register unsigned long sp_in_global __asm__("sp");
+
#ifdef CONFIG_FRAME_POINTER
struct stackframe {
@@ -29,7 +31,7 @@
sp = user_stack_pointer(regs);
pc = instruction_pointer(regs);
} else if (task == NULL || task == current) {
- const register unsigned long current_sp __asm__ ("sp");
+ const register unsigned long current_sp = sp_in_global;
fp = (unsigned long)__builtin_frame_address(0);
sp = current_sp;
pc = (unsigned long)walk_stackframe;
@@ -73,8 +75,7 @@
sp = user_stack_pointer(regs);
pc = instruction_pointer(regs);
} else if (task == NULL || task == current) {
- const register unsigned long current_sp __asm__ ("sp");
- sp = current_sp;
+ sp = sp_in_global;
pc = (unsigned long)walk_stackframe;
} else {
/* task blocked in __switch_to */
@@ -98,17 +99,18 @@
static bool print_trace_address(unsigned long pc, void *arg)
{
- print_ip_sym(pc);
+ const char *loglvl = arg;
+
+ print_ip_sym(loglvl, pc);
return false;
}
-void show_stack(struct task_struct *task, unsigned long *sp)
+void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl)
{
pr_cont("Call Trace:\n");
- walk_stackframe(task, NULL, print_trace_address, NULL);
+ walk_stackframe(task, NULL, print_trace_address, (void *)loglvl);
}
-
static bool save_wchan(unsigned long pc, void *arg)
{
if (!in_sched_functions(pc)) {
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
index 8aa70b5..8a5cf99 100644
--- a/arch/riscv/kernel/time.c
+++ b/arch/riscv/kernel/time.c
@@ -29,3 +29,12 @@
of_clk_init(NULL);
timer_probe();
}
+
+void clocksource_arch_init(struct clocksource *cs)
+{
+#ifdef CONFIG_GENERIC_GETTIMEOFDAY
+ cs->vdso_clock_mode = VDSO_CLOCKMODE_ARCHTIMER;
+#else
+ cs->vdso_clock_mode = VDSO_CLOCKMODE_NONE;
+#endif
+}
diff --git a/arch/riscv/kernel/trace_irq.c b/arch/riscv/kernel/trace_irq.c
new file mode 100644
index 0000000..095ac97
--- /dev/null
+++ b/arch/riscv/kernel/trace_irq.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Changbin Du <changbin.du@gmail.com>
+ */
+
+#include <linux/irqflags.h>
+#include <linux/kprobes.h>
+#include "trace_irq.h"
+
+/*
+ * trace_hardirqs_on/off require the caller to setup frame pointer properly.
+ * Otherwise, CALLER_ADDR1 might trigger an pagging exception in kernel.
+ * Here we add one extra level so they can be safely called by low
+ * level entry code which $fp is used for other purpose.
+ */
+
+void __trace_hardirqs_on(void)
+{
+ trace_hardirqs_on();
+}
+NOKPROBE_SYMBOL(__trace_hardirqs_on);
+
+void __trace_hardirqs_off(void)
+{
+ trace_hardirqs_off();
+}
+NOKPROBE_SYMBOL(__trace_hardirqs_off);
diff --git a/arch/riscv/kernel/trace_irq.h b/arch/riscv/kernel/trace_irq.h
new file mode 100644
index 0000000..99fe673
--- /dev/null
+++ b/arch/riscv/kernel/trace_irq.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022 Changbin Du <changbin.du@gmail.com>
+ */
+#ifndef __TRACE_IRQ_H
+#define __TRACE_IRQ_H
+
+void __trace_hardirqs_on(void);
+void __trace_hardirqs_off(void);
+
+#endif /* __TRACE_IRQ_H */
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 473de3a..ad14f44 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -41,7 +41,7 @@
print_modules();
show_regs(regs);
- ret = notify_die(DIE_OOPS, str, regs, 0, regs->scause, SIGSEGV);
+ ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV);
bust_spinlocks(0);
add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
@@ -86,7 +86,7 @@
#define DO_ERROR_INFO(name, signo, code, str) \
asmlinkage __visible void name(struct pt_regs *regs) \
{ \
- do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \
+ do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \
}
DO_ERROR_INFO(do_trap_unknown,
@@ -97,12 +97,33 @@
SIGSEGV, SEGV_ACCERR, "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");
+#ifndef CONFIG_RISCV_M_MODE
+DO_ERROR_INFO(do_trap_load_misaligned,
+ SIGBUS, BUS_ADRALN, "Oops - load address misaligned");
DO_ERROR_INFO(do_trap_store_misaligned,
- SIGBUS, BUS_ADRALN, "store (or AMO) address misaligned");
+ SIGBUS, BUS_ADRALN, "Oops - store (or AMO) address misaligned");
+#else
+int handle_misaligned_load(struct pt_regs *regs);
+int handle_misaligned_store(struct pt_regs *regs);
+
+asmlinkage void do_trap_load_misaligned(struct pt_regs *regs)
+{
+ if (!handle_misaligned_load(regs))
+ return;
+ do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+ "Oops - load address misaligned");
+}
+
+asmlinkage void do_trap_store_misaligned(struct pt_regs *regs)
+{
+ if (!handle_misaligned_store(regs))
+ return;
+ do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+ "Oops - store (or AMO) address misaligned");
+}
+#endif
DO_ERROR_INFO(do_trap_store_fault,
SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
DO_ERROR_INFO(do_trap_ecall_u,
@@ -116,17 +137,23 @@
{
bug_insn_t insn;
- if (probe_kernel_address((bug_insn_t *)pc, insn))
+ if (get_kernel_nofault(insn, (bug_insn_t *)pc))
return 0;
- return (((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) ? 4UL : 2UL);
+
+ return GET_INSN_LENGTH(insn);
}
asmlinkage __visible void do_trap_break(struct pt_regs *regs)
{
if (user_mode(regs))
- force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->sepc);
- else if (report_bug(regs->sepc, regs) == BUG_TRAP_TYPE_WARN)
- regs->sepc += get_break_insn_length(regs->sepc);
+ force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->epc);
+#ifdef CONFIG_KGDB
+ else if (notify_die(DIE_TRAP, "EBREAK", regs, 0, regs->cause, SIGTRAP)
+ == NOTIFY_STOP)
+ return;
+#endif
+ else if (report_bug(regs->epc, regs) == BUG_TRAP_TYPE_WARN)
+ regs->epc += get_break_insn_length(regs->epc);
else
die(regs, "Kernel BUG");
}
@@ -138,7 +165,7 @@
if (pc < VMALLOC_START)
return 0;
- if (probe_kernel_address((bug_insn_t *)pc, insn))
+ if (get_kernel_nofault(insn, (bug_insn_t *)pc))
return 0;
if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32)
return (insn == __BUG_INSN_32);
@@ -147,15 +174,7 @@
}
#endif /* CONFIG_GENERIC_BUG */
-void __init trap_init(void)
+/* stvec & scratch is already set from head.S */
+void trap_init(void)
{
- /*
- * Set sup0 scratch register to 0, indicating to exception vector
- * that we are presently executing in the kernel
- */
- csr_write(CSR_SSCRATCH, 0);
- /* Set the exception vector address */
- csr_write(CSR_STVEC, &handle_exception);
- /* Enable all interrupts */
- csr_write(CSR_SIE, -1);
}
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
new file mode 100644
index 0000000..46c4daf
--- /dev/null
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -0,0 +1,370 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#include <linux/kernel.h>
+#include <linux/init.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>
+
+#define INSN_MATCH_LB 0x3
+#define INSN_MASK_LB 0x707f
+#define INSN_MATCH_LH 0x1003
+#define INSN_MASK_LH 0x707f
+#define INSN_MATCH_LW 0x2003
+#define INSN_MASK_LW 0x707f
+#define INSN_MATCH_LD 0x3003
+#define INSN_MASK_LD 0x707f
+#define INSN_MATCH_LBU 0x4003
+#define INSN_MASK_LBU 0x707f
+#define INSN_MATCH_LHU 0x5003
+#define INSN_MASK_LHU 0x707f
+#define INSN_MATCH_LWU 0x6003
+#define INSN_MASK_LWU 0x707f
+#define INSN_MATCH_SB 0x23
+#define INSN_MASK_SB 0x707f
+#define INSN_MATCH_SH 0x1023
+#define INSN_MASK_SH 0x707f
+#define INSN_MATCH_SW 0x2023
+#define INSN_MASK_SW 0x707f
+#define INSN_MATCH_SD 0x3023
+#define INSN_MASK_SD 0x707f
+
+#define INSN_MATCH_FLW 0x2007
+#define INSN_MASK_FLW 0x707f
+#define INSN_MATCH_FLD 0x3007
+#define INSN_MASK_FLD 0x707f
+#define INSN_MATCH_FLQ 0x4007
+#define INSN_MASK_FLQ 0x707f
+#define INSN_MATCH_FSW 0x2027
+#define INSN_MASK_FSW 0x707f
+#define INSN_MATCH_FSD 0x3027
+#define INSN_MASK_FSD 0x707f
+#define INSN_MATCH_FSQ 0x4027
+#define INSN_MASK_FSQ 0x707f
+
+#define INSN_MATCH_C_LD 0x6000
+#define INSN_MASK_C_LD 0xe003
+#define INSN_MATCH_C_SD 0xe000
+#define INSN_MASK_C_SD 0xe003
+#define INSN_MATCH_C_LW 0x4000
+#define INSN_MASK_C_LW 0xe003
+#define INSN_MATCH_C_SW 0xc000
+#define INSN_MASK_C_SW 0xe003
+#define INSN_MATCH_C_LDSP 0x6002
+#define INSN_MASK_C_LDSP 0xe003
+#define INSN_MATCH_C_SDSP 0xe002
+#define INSN_MASK_C_SDSP 0xe003
+#define INSN_MATCH_C_LWSP 0x4002
+#define INSN_MASK_C_LWSP 0xe003
+#define INSN_MATCH_C_SWSP 0xc002
+#define INSN_MASK_C_SWSP 0xe003
+
+#define INSN_MATCH_C_FLD 0x2000
+#define INSN_MASK_C_FLD 0xe003
+#define INSN_MATCH_C_FLW 0x6000
+#define INSN_MASK_C_FLW 0xe003
+#define INSN_MATCH_C_FSD 0xa000
+#define INSN_MASK_C_FSD 0xe003
+#define INSN_MATCH_C_FSW 0xe000
+#define INSN_MASK_C_FSW 0xe003
+#define INSN_MATCH_C_FLDSP 0x2002
+#define INSN_MASK_C_FLDSP 0xe003
+#define INSN_MATCH_C_FSDSP 0xa002
+#define INSN_MASK_C_FSDSP 0xe003
+#define INSN_MATCH_C_FLWSP 0x6002
+#define INSN_MASK_C_FLWSP 0xe003
+#define INSN_MATCH_C_FSWSP 0xe002
+#define INSN_MASK_C_FSWSP 0xe003
+
+#define INSN_LEN(insn) ((((insn) & 0x3) < 0x3) ? 2 : 4)
+
+#if defined(CONFIG_64BIT)
+#define LOG_REGBYTES 3
+#define XLEN 64
+#else
+#define LOG_REGBYTES 2
+#define XLEN 32
+#endif
+#define REGBYTES (1 << LOG_REGBYTES)
+#define XLEN_MINUS_16 ((XLEN) - 16)
+
+#define SH_RD 7
+#define SH_RS1 15
+#define SH_RS2 20
+#define SH_RS2C 2
+
+#define RV_X(x, s, n) (((x) >> (s)) & ((1 << (n)) - 1))
+#define RVC_LW_IMM(x) ((RV_X(x, 6, 1) << 2) | \
+ (RV_X(x, 10, 3) << 3) | \
+ (RV_X(x, 5, 1) << 6))
+#define RVC_LD_IMM(x) ((RV_X(x, 10, 3) << 3) | \
+ (RV_X(x, 5, 2) << 6))
+#define RVC_LWSP_IMM(x) ((RV_X(x, 4, 3) << 2) | \
+ (RV_X(x, 12, 1) << 5) | \
+ (RV_X(x, 2, 2) << 6))
+#define RVC_LDSP_IMM(x) ((RV_X(x, 5, 2) << 3) | \
+ (RV_X(x, 12, 1) << 5) | \
+ (RV_X(x, 2, 3) << 6))
+#define RVC_SWSP_IMM(x) ((RV_X(x, 9, 4) << 2) | \
+ (RV_X(x, 7, 2) << 6))
+#define RVC_SDSP_IMM(x) ((RV_X(x, 10, 3) << 3) | \
+ (RV_X(x, 7, 3) << 6))
+#define RVC_RS1S(insn) (8 + RV_X(insn, SH_RD, 3))
+#define RVC_RS2S(insn) (8 + RV_X(insn, SH_RS2C, 3))
+#define RVC_RS2(insn) RV_X(insn, SH_RS2C, 5)
+
+#define SHIFT_RIGHT(x, y) \
+ ((y) < 0 ? ((x) << -(y)) : ((x) >> (y)))
+
+#define REG_MASK \
+ ((1 << (5 + LOG_REGBYTES)) - (1 << LOG_REGBYTES))
+
+#define REG_OFFSET(insn, pos) \
+ (SHIFT_RIGHT((insn), (pos) - LOG_REGBYTES) & REG_MASK)
+
+#define REG_PTR(insn, pos, regs) \
+ (ulong *)((ulong)(regs) + REG_OFFSET(insn, pos))
+
+#define GET_RM(insn) (((insn) >> 12) & 7)
+
+#define GET_RS1(insn, regs) (*REG_PTR(insn, SH_RS1, regs))
+#define GET_RS2(insn, regs) (*REG_PTR(insn, SH_RS2, regs))
+#define GET_RS1S(insn, regs) (*REG_PTR(RVC_RS1S(insn), 0, regs))
+#define GET_RS2S(insn, regs) (*REG_PTR(RVC_RS2S(insn), 0, regs))
+#define GET_RS2C(insn, regs) (*REG_PTR(insn, SH_RS2C, regs))
+#define GET_SP(regs) (*REG_PTR(2, 0, regs))
+#define SET_RD(insn, regs, val) (*REG_PTR(insn, SH_RD, regs) = (val))
+#define IMM_I(insn) ((s32)(insn) >> 20)
+#define IMM_S(insn) (((s32)(insn) >> 25 << 5) | \
+ (s32)(((insn) >> 7) & 0x1f))
+#define MASK_FUNCT3 0x7000
+
+#define GET_PRECISION(insn) (((insn) >> 25) & 3)
+#define GET_RM(insn) (((insn) >> 12) & 7)
+#define PRECISION_S 0
+#define PRECISION_D 1
+
+#define STR(x) XSTR(x)
+#define XSTR(x) #x
+
+#define DECLARE_UNPRIVILEGED_LOAD_FUNCTION(type, insn) \
+static inline type load_##type(const type *addr) \
+{ \
+ type val; \
+ asm (#insn " %0, %1" \
+ : "=&r" (val) : "m" (*addr)); \
+ return val; \
+}
+
+#define DECLARE_UNPRIVILEGED_STORE_FUNCTION(type, insn) \
+static inline void store_##type(type *addr, type val) \
+{ \
+ asm volatile (#insn " %0, %1\n" \
+ : : "r" (val), "m" (*addr)); \
+}
+
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u8, lbu)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u16, lhu)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s8, lb)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s16, lh)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s32, lw)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u8, sb)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u16, sh)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u32, sw)
+#if defined(CONFIG_64BIT)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lwu)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u64, ld)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u64, sd)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, ld)
+#else
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lw)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, lw)
+
+static inline u64 load_u64(const u64 *addr)
+{
+ return load_u32((u32 *)addr)
+ + ((u64)load_u32((u32 *)addr + 1) << 32);
+}
+
+static inline void store_u64(u64 *addr, u64 val)
+{
+ store_u32((u32 *)addr, val);
+ store_u32((u32 *)addr + 1, val >> 32);
+}
+#endif
+
+static inline ulong get_insn(ulong mepc)
+{
+ register ulong __mepc asm ("a2") = mepc;
+ ulong val, rvc_mask = 3, tmp;
+
+ asm ("and %[tmp], %[addr], 2\n"
+ "bnez %[tmp], 1f\n"
+#if defined(CONFIG_64BIT)
+ STR(LWU) " %[insn], (%[addr])\n"
+#else
+ STR(LW) " %[insn], (%[addr])\n"
+#endif
+ "and %[tmp], %[insn], %[rvc_mask]\n"
+ "beq %[tmp], %[rvc_mask], 2f\n"
+ "sll %[insn], %[insn], %[xlen_minus_16]\n"
+ "srl %[insn], %[insn], %[xlen_minus_16]\n"
+ "j 2f\n"
+ "1:\n"
+ "lhu %[insn], (%[addr])\n"
+ "and %[tmp], %[insn], %[rvc_mask]\n"
+ "bne %[tmp], %[rvc_mask], 2f\n"
+ "lhu %[tmp], 2(%[addr])\n"
+ "sll %[tmp], %[tmp], 16\n"
+ "add %[insn], %[insn], %[tmp]\n"
+ "2:"
+ : [insn] "=&r" (val), [tmp] "=&r" (tmp)
+ : [addr] "r" (__mepc), [rvc_mask] "r" (rvc_mask),
+ [xlen_minus_16] "i" (XLEN_MINUS_16));
+
+ return val;
+}
+
+union reg_data {
+ u8 data_bytes[8];
+ ulong data_ulong;
+ u64 data_u64;
+};
+
+int handle_misaligned_load(struct pt_regs *regs)
+{
+ union reg_data val;
+ unsigned long epc = regs->epc;
+ unsigned long insn = get_insn(epc);
+ unsigned long addr = csr_read(mtval);
+ int i, fp = 0, shift = 0, len = 0;
+
+ regs->epc = 0;
+
+ if ((insn & INSN_MASK_LW) == INSN_MATCH_LW) {
+ len = 4;
+ shift = 8 * (sizeof(unsigned long) - len);
+#if defined(CONFIG_64BIT)
+ } else if ((insn & INSN_MASK_LD) == INSN_MATCH_LD) {
+ len = 8;
+ shift = 8 * (sizeof(unsigned long) - len);
+ } else if ((insn & INSN_MASK_LWU) == INSN_MATCH_LWU) {
+ len = 4;
+#endif
+ } else if ((insn & INSN_MASK_FLD) == INSN_MATCH_FLD) {
+ fp = 1;
+ len = 8;
+ } else if ((insn & INSN_MASK_FLW) == INSN_MATCH_FLW) {
+ fp = 1;
+ len = 4;
+ } else if ((insn & INSN_MASK_LH) == INSN_MATCH_LH) {
+ len = 2;
+ shift = 8 * (sizeof(unsigned long) - len);
+ } else if ((insn & INSN_MASK_LHU) == INSN_MATCH_LHU) {
+ len = 2;
+#if defined(CONFIG_64BIT)
+ } else if ((insn & INSN_MASK_C_LD) == INSN_MATCH_C_LD) {
+ len = 8;
+ shift = 8 * (sizeof(unsigned long) - len);
+ insn = RVC_RS2S(insn) << SH_RD;
+ } else if ((insn & INSN_MASK_C_LDSP) == INSN_MATCH_C_LDSP &&
+ ((insn >> SH_RD) & 0x1f)) {
+ len = 8;
+ shift = 8 * (sizeof(unsigned long) - len);
+#endif
+ } else if ((insn & INSN_MASK_C_LW) == INSN_MATCH_C_LW) {
+ len = 4;
+ shift = 8 * (sizeof(unsigned long) - len);
+ insn = RVC_RS2S(insn) << SH_RD;
+ } else if ((insn & INSN_MASK_C_LWSP) == INSN_MATCH_C_LWSP &&
+ ((insn >> SH_RD) & 0x1f)) {
+ len = 4;
+ shift = 8 * (sizeof(unsigned long) - len);
+ } else if ((insn & INSN_MASK_C_FLD) == INSN_MATCH_C_FLD) {
+ fp = 1;
+ len = 8;
+ insn = RVC_RS2S(insn) << SH_RD;
+ } else if ((insn & INSN_MASK_C_FLDSP) == INSN_MATCH_C_FLDSP) {
+ fp = 1;
+ len = 8;
+#if defined(CONFIG_32BIT)
+ } else if ((insn & INSN_MASK_C_FLW) == INSN_MATCH_C_FLW) {
+ fp = 1;
+ len = 4;
+ insn = RVC_RS2S(insn) << SH_RD;
+ } else if ((insn & INSN_MASK_C_FLWSP) == INSN_MATCH_C_FLWSP) {
+ fp = 1;
+ len = 4;
+#endif
+ } else {
+ regs->epc = epc;
+ return -1;
+ }
+
+ val.data_u64 = 0;
+ for (i = 0; i < len; i++)
+ val.data_bytes[i] = load_u8((void *)(addr + i));
+
+ if (fp)
+ return -1;
+ SET_RD(insn, regs, val.data_ulong << shift >> shift);
+
+ regs->epc = epc + INSN_LEN(insn);
+
+ return 0;
+}
+
+int handle_misaligned_store(struct pt_regs *regs)
+{
+ union reg_data val;
+ unsigned long epc = regs->epc;
+ unsigned long insn = get_insn(epc);
+ unsigned long addr = csr_read(mtval);
+ int i, len = 0;
+
+ regs->epc = 0;
+
+ val.data_ulong = GET_RS2(insn, regs);
+
+ if ((insn & INSN_MASK_SW) == INSN_MATCH_SW) {
+ len = 4;
+#if defined(CONFIG_64BIT)
+ } else if ((insn & INSN_MASK_SD) == INSN_MATCH_SD) {
+ len = 8;
+#endif
+ } else if ((insn & INSN_MASK_SH) == INSN_MATCH_SH) {
+ len = 2;
+#if defined(CONFIG_64BIT)
+ } else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) {
+ len = 8;
+ val.data_ulong = GET_RS2S(insn, regs);
+ } else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP &&
+ ((insn >> SH_RD) & 0x1f)) {
+ len = 8;
+ val.data_ulong = GET_RS2C(insn, regs);
+#endif
+ } else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) {
+ len = 4;
+ val.data_ulong = GET_RS2S(insn, regs);
+ } else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP &&
+ ((insn >> SH_RD) & 0x1f)) {
+ len = 4;
+ val.data_ulong = GET_RS2C(insn, regs);
+ } else {
+ regs->epc = epc;
+ return -1;
+ }
+
+ for (i = 0; i < len; i++)
+ store_u8((void *)(addr + i), val.data_bytes[i]);
+
+ regs->epc = epc + INSN_LEN(insn);
+
+ return 0;
+}
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 484d95a..73d4593 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -11,8 +11,12 @@
#include <linux/slab.h>
#include <linux/binfmts.h>
#include <linux/err.h>
-
+#include <asm/page.h>
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL
+#include <vdso/datapage.h>
+#else
#include <asm/vdso.h>
+#endif
extern char vdso_start[], vdso_end[];
@@ -26,7 +30,7 @@
struct vdso_data data;
u8 page[PAGE_SIZE];
} vdso_data_store __page_aligned_data;
-static struct vdso_data *vdso_data = &vdso_data_store.data;
+struct vdso_data *vdso_data = &vdso_data_store.data;
static int __init vdso_init(void)
{
@@ -61,7 +65,9 @@
vdso_len = (vdso_pages + 1) << PAGE_SHIFT;
- down_write(&mm->mmap_sem);
+ if (mmap_write_lock_killable(mm))
+ return -EINTR;
+
vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0);
if (IS_ERR_VALUE(vdso_base)) {
ret = vdso_base;
@@ -75,15 +81,24 @@
*/
mm->context.vdso = (void *)vdso_base;
- ret = install_special_mapping(mm, vdso_base, vdso_len,
+ ret =
+ install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
(VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
vdso_pagelist);
+ if (unlikely(ret)) {
+ mm->context.vdso = NULL;
+ goto end;
+ }
+
+ vdso_base += (vdso_pages << PAGE_SHIFT);
+ ret = install_special_mapping(mm, vdso_base, PAGE_SIZE,
+ (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]);
+
if (unlikely(ret))
mm->context.vdso = NULL;
-
end:
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
return ret;
}
@@ -91,5 +106,8 @@
{
if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso))
return "[vdso]";
+ if (vma->vm_mm && (vma->vm_start ==
+ (long)vma->vm_mm->context.vdso + PAGE_SIZE))
+ return "[vdso_data]";
return NULL;
}
diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore
index 97c2d69..3a19def 100644
--- a/arch/riscv/kernel/vdso/.gitignore
+++ b/arch/riscv/kernel/vdso/.gitignore
@@ -1,2 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
vdso.lds
*.tmp
+vdso-syms.S
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index a4ee3a0..24d936c 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -1,49 +1,56 @@
# SPDX-License-Identifier: GPL-2.0-only
# Copied from arch/tile/kernel/vdso/Makefile
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_RISCV_32|R_RISCV_64|R_RISCV_JUMP_SLOT
+include $(srctree)/lib/vdso/Makefile
# Symbols present in the vdso
vdso-syms = rt_sigreturn
ifdef CONFIG_64BIT
-vdso-syms += gettimeofday
-vdso-syms += clock_gettime
-vdso-syms += clock_getres
+vdso-syms += vgettimeofday
endif
vdso-syms += getcpu
vdso-syms += flush_icache
# Files to link into the vdso
-obj-vdso = $(patsubst %, %.o, $(vdso-syms))
+obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
+
+ccflags-y := -fno-stack-protector
+
+ifneq ($(c-gettimeofday-y),)
+ CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)
+endif
# Build rules
-targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-dummy.o
+targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-syms.S
obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
obj-y += vdso.o vdso-syms.o
CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
-# Disable gcov profiling for VDSO code
+# Disable -pg to prevent insert call site
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+
+# Disable profiling and instrumentation for VDSO code
GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
+KASAN_SANITIZE := n
# Force dependency
$(obj)/vdso.o: $(obj)/vdso.so
# link rule for the .so file, .lds has to be first
-SYSCFLAGS_vdso.so.dbg = $(c_flags)
-$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE
+$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
$(call if_changed,vdsold)
+LDFLAGS_vdso.so.dbg = -shared -s -soname=linux-vdso.so.1 \
+ --build-id=sha1 --hash-style=both --eh-frame-hdr
# We also create a special relocatable object that should mirror the symbol
# table and layout of the linked DSO. With ld --just-symbols we can then
# refer to these symbols in the kernel code rather than hand-coded addresses.
-
-SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
- -Wl,--build-id -Wl,--hash-style=both
-$(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE
- $(call if_changed,vdsold)
-
-LDFLAGS_vdso-syms.o := -r --just-symbols
-$(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE
- $(call if_changed,ld)
+$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE
+ $(call if_changed,so2s)
# strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
@@ -52,15 +59,17 @@
# actual build commands
# The DSO images are built using a special linker script
-# Add -lgcc so rv32 gets static muldi3 and lshrdi3 definitions.
# Make sure only to export the intended __vdso_xxx symbol offsets.
quiet_cmd_vdsold = VDSOLD $@
- cmd_vdsold = $(CC) $(KBUILD_CFLAGS) $(call cc-option, -no-pie) -nostdlib -nostartfiles $(SYSCFLAGS_$(@F)) \
- -Wl,-T,$(filter-out FORCE,$^) -o $@.tmp && \
- $(CROSS_COMPILE)objcopy \
- $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
+ cmd_vdsold = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \
+ $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
rm $@.tmp
+# Extracts symbol offsets from the VDSO, converting them into an assembly file
+# that contains the same symbols at the same offsets.
+quiet_cmd_so2s = SO2S $@
+ cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@
+
# install commands for the unstripped file
quiet_cmd_vdso_install = INSTALL $@
cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
diff --git a/arch/riscv/kernel/vdso/clock_getres.S b/arch/riscv/kernel/vdso/clock_getres.S
deleted file mode 100644
index 91378a5..0000000
--- a/arch/riscv/kernel/vdso/clock_getres.S
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2017 SiFive
- */
-
-#include <linux/linkage.h>
-#include <asm/unistd.h>
-
- .text
-/* int __vdso_clock_getres(clockid_t clock_id, struct timespec *res); */
-ENTRY(__vdso_clock_getres)
- .cfi_startproc
- /* For now, just do the syscall. */
- li a7, __NR_clock_getres
- ecall
- ret
- .cfi_endproc
-ENDPROC(__vdso_clock_getres)
diff --git a/arch/riscv/kernel/vdso/clock_gettime.S b/arch/riscv/kernel/vdso/clock_gettime.S
deleted file mode 100644
index 5371fd9..0000000
--- a/arch/riscv/kernel/vdso/clock_gettime.S
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2017 SiFive
- */
-
-#include <linux/linkage.h>
-#include <asm/unistd.h>
-
- .text
-/* int __vdso_clock_gettime(clockid_t clock_id, struct timespec *tp); */
-ENTRY(__vdso_clock_gettime)
- .cfi_startproc
- /* For now, just do the syscall. */
- li a7, __NR_clock_gettime
- ecall
- ret
- .cfi_endproc
-ENDPROC(__vdso_clock_gettime)
diff --git a/arch/riscv/kernel/vdso/gettimeofday.S b/arch/riscv/kernel/vdso/gettimeofday.S
deleted file mode 100644
index e6fb8af..0000000
--- a/arch/riscv/kernel/vdso/gettimeofday.S
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2017 SiFive
- */
-
-#include <linux/linkage.h>
-#include <asm/unistd.h>
-
- .text
-/* int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); */
-ENTRY(__vdso_gettimeofday)
- .cfi_startproc
- /* For now, just do the syscall. */
- li a7, __NR_gettimeofday
- ecall
- ret
- .cfi_endproc
-ENDPROC(__vdso_gettimeofday)
diff --git a/arch/riscv/kernel/vdso/note.S b/arch/riscv/kernel/vdso/note.S
new file mode 100644
index 0000000..2a956c9
--- /dev/null
+++ b/arch/riscv/kernel/vdso/note.S
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/elfnote.h>
+#include <linux/version.h>
+
+ELFNOTE_START(Linux, 0, "a")
+ .long LINUX_VERSION_CODE
+ELFNOTE_END
diff --git a/arch/riscv/kernel/vdso/so2s.sh b/arch/riscv/kernel/vdso/so2s.sh
new file mode 100755
index 0000000..e64cb6d
--- /dev/null
+++ b/arch/riscv/kernel/vdso/so2s.sh
@@ -0,0 +1,6 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+# Copyright 2020 Palmer Dabbelt <palmerdabbelt@google.com>
+
+sed 's!\([0-9a-f]*\) T \([a-z0-9_]*\)\(@@LINUX_4.15\)*!.global \2\n.set \2,0x\1!' \
+| grep '^\.'
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index f66a091..e6f558b 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -2,11 +2,13 @@
/*
* Copyright (C) 2012 Regents of the University of California
*/
+#include <asm/page.h>
OUTPUT_ARCH(riscv)
SECTIONS
{
+ PROVIDE(_vdso_data = . + PAGE_SIZE);
. = SIZEOF_HEADERS;
.hash : { *(.hash) } :text
diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c
new file mode 100644
index 0000000..cc0d806
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vgettimeofday.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copied from arch/arm64/kernel/vdso/vgettimeofday.c
+ *
+ * Copyright (C) 2018 ARM Ltd.
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/time.h>
+#include <linux/types.h>
+
+extern
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
+{
+ return __cvdso_clock_gettime(clock, ts);
+}
+
+extern
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
+{
+ return __cvdso_gettimeofday(tv, tz);
+}
+
+extern
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
+{
+ return __cvdso_clock_getres(clock_id, res);
+}
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 23cd1a9..3ffbd6c 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -9,21 +9,39 @@
#include <asm/page.h>
#include <asm/cache.h>
#include <asm/thread_info.h>
+#include <asm/set_memory.h>
+#include "image-vars.h"
+#include <linux/sizes.h>
OUTPUT_ARCH(riscv)
ENTRY(_start)
jiffies = jiffies_64;
+PECOFF_SECTION_ALIGNMENT = 0x1000;
+PECOFF_FILE_ALIGNMENT = 0x200;
+
SECTIONS
{
/* Beginning of code and text segment */
. = LOAD_OFFSET;
_start = .;
- __init_begin = .;
HEAD_TEXT_SECTION
+ . = ALIGN(PAGE_SIZE);
+
+ __init_begin = .;
INIT_TEXT_SECTION(PAGE_SIZE)
- INIT_DATA_SECTION(16)
+ . = ALIGN(8);
+ __soc_early_init_table : {
+ __soc_early_init_table_start = .;
+ KEEP(*(__soc_early_init_table))
+ __soc_early_init_table_end = .;
+ }
+ __soc_builtin_dtb_table : {
+ __soc_builtin_dtb_table_start = .;
+ KEEP(*(__soc_builtin_dtb_table))
+ __soc_builtin_dtb_table_end = .;
+ }
/* we have to discard exit text and such at runtime, not link time */
.exit.text :
{
@@ -36,6 +54,7 @@
PERCPU_SECTION(L1_CACHE_BYTES)
__init_end = .;
+ . = ALIGN(SECTION_ALIGN);
.text : {
_text = .;
_stext = .;
@@ -46,39 +65,59 @@
KPROBES_TEXT
ENTRY_TEXT
IRQENTRY_TEXT
+ SOFTIRQENTRY_TEXT
*(.fixup)
_etext = .;
}
+#ifdef CONFIG_EFI
+ . = ALIGN(PECOFF_SECTION_ALIGNMENT);
+ __pecoff_text_end = .;
+#endif
+
+ INIT_DATA_SECTION(16)
+
/* Start of data section */
_sdata = .;
- RO_DATA_SECTION(L1_CACHE_BYTES)
+ RO_DATA(SECTION_ALIGN)
.srodata : {
*(.srodata*)
}
- RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+ EXCEPTION_TABLE(0x10)
+
+ . = ALIGN(SECTION_ALIGN);
+ _data = .;
+
+ RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
.sdata : {
__global_pointer$ = . + 0x800;
*(.sdata*)
- /* End of data section */
- _edata = .;
- *(.sbss*)
}
- BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0)
+#ifdef CONFIG_EFI
+ .pecoff_edata_padding : { BYTE(0); . = ALIGN(PECOFF_FILE_ALIGNMENT); }
+ __pecoff_data_raw_size = ABSOLUTE(. - __pecoff_text_end);
+#endif
- EXCEPTION_TABLE(0x10)
- NOTES
+ /* End of data section */
+ _edata = .;
+
+ BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0)
.rel.dyn : {
*(.rel.dyn*)
}
+#ifdef CONFIG_EFI
+ . = ALIGN(PECOFF_SECTION_ALIGNMENT);
+ __pecoff_data_virt_size = ABSOLUTE(. - __pecoff_text_end);
+#endif
_end = .;
STABS_DEBUG
DWARF_DEBUG
+ ELF_DETAILS
DISCARDS
}